diff options
1092 files changed, 22370 insertions, 14973 deletions
diff --git a/.gitattributes b/.gitattributes index c9ba5bfc4036..2325c529e185 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2,3 +2,4 @@ *.[ch] diff=cpp *.dts diff=dts *.dts[io] diff=dts +*.rs diff=rust @@ -70,6 +70,8 @@ Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@unisoc.com> Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang7@gmail.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> +Ben Dooks <ben-linux@fluff.org> <ben.dooks@simtec.co.uk> +Ben Dooks <ben-linux@fluff.org> <ben.dooks@sifive.com> Ben Gardner <bgardner@wabtec.com> Ben M Cahill <ben.m.cahill@intel.com> Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net> @@ -181,6 +183,8 @@ Henrik Rydberg <rydberg@bitmath.org> Herbert Xu <herbert@gondor.apana.org.au> Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com> Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> +J. Bruce Fields <bfields@fieldses.org> <bfields@redhat.com> +J. Bruce Fields <bfields@fieldses.org> <bfields@citi.umich.edu> Jacob Shin <Jacob.Shin@amd.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com> @@ -233,6 +237,7 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Crispin <john@phrozen.org> <blogic@openwrt.org> +John Keeping <john@keeping.me.uk> <john@metanate.com> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com> diff --git a/Documentation/admin-guide/bcache.rst b/Documentation/admin-guide/bcache.rst index bb5032a99234..6fdb495ac466 100644 --- a/Documentation/admin-guide/bcache.rst +++ b/Documentation/admin-guide/bcache.rst @@ -508,9 +508,6 @@ cache_miss_collisions cache miss, but raced with a write and data was already present (usually 0 since the synchronization for cache misses was rewritten) -cache_readaheads - Count of times readahead occurred. - Sysfs - cache set ~~~~~~~~~~~~~~~~~ diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index e592a9364473..c63358c38a1d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2022,31 +2022,33 @@ that attribute: no-change Do not modify the I/O priority class. - none-to-rt - For requests that do not have an I/O priority class (NONE), - change the I/O priority class into RT. Do not modify - the I/O priority class of other requests. + promote-to-rt + For requests that have a non-RT I/O priority class, change it into RT. + Also change the priority level of these requests to 4. Do not modify + the I/O priority of requests that have priority class RT. restrict-to-be For requests that do not have an I/O priority class or that have I/O - priority class RT, change it into BE. Do not modify the I/O priority - class of requests that have priority class IDLE. + priority class RT, change it into BE. Also change the priority level + of these requests to 0. Do not modify the I/O priority class of + requests that have priority class IDLE. idle Change the I/O priority class of all requests into IDLE, the lowest I/O priority class. + none-to-rt + Deprecated. Just an alias for promote-to-rt. + The following numerical values are associated with the I/O priority policies: -+-------------+---+ -| no-change | 0 | -+-------------+---+ -| none-to-rt | 1 | -+-------------+---+ -| rt-to-be | 2 | -+-------------+---+ -| all-to-idle | 3 | -+-------------+---+ ++----------------+---+ +| no-change | 0 | ++----------------+---+ +| rt-to-be | 2 | ++----------------+---+ +| all-to-idle | 3 | ++----------------+---+ The numerical value that corresponds to each I/O priority class is as follows: @@ -2062,9 +2064,13 @@ The numerical value that corresponds to each I/O priority class is as follows: The algorithm to set the I/O priority class for a request is as follows: -- Translate the I/O priority class policy into a number. -- Change the request I/O priority class into the maximum of the I/O priority - class policy number and the numerical I/O priority class. +- If I/O priority class policy is promote-to-rt, change the request I/O + priority class to IOPRIO_CLASS_RT and change the request I/O priority + level to 4. +- If I/O priorityt class is not promote-to-rt, translate the I/O priority + class policy into a number, then change the request I/O priority class + into the maximum of the I/O priority class policy number and the numerical + I/O priority class. PID --- diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9e5bab29685f..d8fabfe37d5e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -818,20 +818,6 @@ Format: <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] - cpu0_hotplug [X86] Turn on CPU0 hotplug feature when - CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off. - Some features depend on CPU0. Known dependencies are: - 1. Resume from suspend/hibernate depends on CPU0. - Suspend/hibernate will fail if CPU0 is offline and you - need to online CPU0 before suspend/hibernate. - 2. PIC interrupts also depend on CPU0. CPU0 can't be - removed if a PIC interrupt is detected. - It's said poweroff/reboot may depend on CPU0 on some - machines although I haven't seen such issues so far - after CPU0 is offline on a few tested machines. - If the dependencies are under your control, you can - turn on cpu0_hotplug. - cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system @@ -852,6 +838,12 @@ on every CPU online, such as boot, and resume from suspend. Default: 10000 + cpuhp.parallel= + [SMP] Enable/disable parallel bringup of secondary CPUs + Format: <bool> + Default is enabled if CONFIG_HOTPLUG_PARALLEL=y. Otherwise + the parameter has no effect. + crash_kexec_post_notifiers Run kdump after running panic-notifiers and dumping kmsg. This only for the users who doubt kdump always @@ -5452,7 +5444,12 @@ port and the regular usb controller gets disabled. root= [KNL] Root filesystem - See name_to_dev_t comment in init/do_mounts.c. + Usually this a a block device specifier of some kind, + see the early_lookup_bdev comment in + block/early-lookup.c for details. + Alternatively this can be "ram" for the legacy initial + ramdisk, "nfs" and "cifs" for root on a network file + system, or "mtd" and "ubi" for mounting from raw flash. rootdelay= [KNL] Delay (in seconds) to pause before attempting to mount the root filesystem diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 9e311bc43e05..d6430ade349d 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -214,3 +214,7 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 | +----------------+-----------------+-----------------+-----------------------------+ + ++----------------+-----------------+-----------------+-----------------------------+ +| ASR | ASR8601 | #8601001 | N/A | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/core-api/cpu_hotplug.rst b/Documentation/core-api/cpu_hotplug.rst index f75778d37488..e6f5bc39cf5c 100644 --- a/Documentation/core-api/cpu_hotplug.rst +++ b/Documentation/core-api/cpu_hotplug.rst @@ -127,17 +127,8 @@ bring CPU4 back online:: $ echo 1 > /sys/devices/system/cpu/cpu4/online smpboot: Booting Node 0 Processor 4 APIC 0x1 -The CPU is usable again. This should work on all CPUs. CPU0 is often special -and excluded from CPU hotplug. On X86 the kernel option -*CONFIG_BOOTPARAM_HOTPLUG_CPU0* has to be enabled in order to be able to -shutdown CPU0. Alternatively the kernel command option *cpu0_hotplug* can be -used. Some known dependencies of CPU0: - -* Resume from hibernate/suspend. Hibernate/suspend will fail if CPU0 is offline. -* PIC interrupts. CPU0 can't be removed if a PIC interrupt is detected. - -Please let Fenghua Yu <fenghua.yu@intel.com> know if you find any dependencies -on CPU0. +The CPU is usable again. This should work on all CPUs, but CPU0 is often special +and excluded from CPU hotplug. The CPU hotplug coordination ============================ diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index 9fb0b1080d3b..d3c1f6d8c0e0 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -112,6 +112,12 @@ pages: This also leads to limitations: there are only 31-10==21 bits available for a counter that increments 10 bits at a time. +* Because of that limitation, special handling is applied to the zero pages + when using FOLL_PIN. We only pretend to pin a zero page - we don't alter its + refcount or pincount at all (it is permanent, so there's no need). The + unpinning functions also don't do anything to a zero page. This is + transparent to the caller. + * Callers must specifically request "dma-pinned tracking of pages". In other words, just calling get_user_pages() will not suffice; a new set of functions, pin_user_page() and related, must be used. diff --git a/Documentation/devicetree/bindings/ata/ahci-common.yaml b/Documentation/devicetree/bindings/ata/ahci-common.yaml index 7fdf40954a4c..38770c4c85fd 100644 --- a/Documentation/devicetree/bindings/ata/ahci-common.yaml +++ b/Documentation/devicetree/bindings/ata/ahci-common.yaml @@ -8,7 +8,7 @@ title: Common Properties for Serial ATA AHCI controllers maintainers: - Hans de Goede <hdegoede@redhat.com> - - Damien Le Moal <damien.lemoal@opensource.wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: This document defines device tree properties for a common AHCI SATA diff --git a/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml b/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml index 998e5cce652f..380cb6d80025 100644 --- a/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml +++ b/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Canaan Kendryte K210 Clock maintainers: - - Damien Le Moal <damien.lemoal@wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: | Canaan Kendryte K210 SoC clocks driver bindings. The clock diff --git a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml index 367d04ad1923..83381f3a1341 100644 --- a/Documentation/devicetree/bindings/firmware/qcom,scm.yaml +++ b/Documentation/devicetree/bindings/firmware/qcom,scm.yaml @@ -71,6 +71,8 @@ properties: minItems: 1 maxItems: 3 + dma-coherent: true + interconnects: maxItems: 1 diff --git a/Documentation/devicetree/bindings/i2c/opencores,i2c-ocores.yaml b/Documentation/devicetree/bindings/i2c/opencores,i2c-ocores.yaml index 85d9efb743ee..d9ef86729011 100644 --- a/Documentation/devicetree/bindings/i2c/opencores,i2c-ocores.yaml +++ b/Documentation/devicetree/bindings/i2c/opencores,i2c-ocores.yaml @@ -60,6 +60,7 @@ properties: default: 0 regstep: + $ref: /schemas/types.yaml#/definitions/uint32 description: | deprecated, use reg-shift above deprecated: true diff --git a/Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml b/Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml index 62f3ca66274f..32c821f97779 100644 --- a/Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml +++ b/Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml @@ -44,7 +44,7 @@ required: - clock-names - clocks -additionalProperties: true +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongson,eiointc.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongson,eiointc.yaml new file mode 100644 index 000000000000..393c128a41d8 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/loongson,eiointc.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interrupt-controller/loongson,eiointc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Loongson Extended I/O Interrupt Controller + +maintainers: + - Binbin Zhou <zhoubinbin@loongson.cn> + +description: | + This interrupt controller is found on the Loongson-3 family chips and + Loongson-2K series chips and is used to distribute interrupts directly to + individual cores without forwarding them through the HT's interrupt line. + +allOf: + - $ref: /schemas/interrupt-controller.yaml# + +properties: + compatible: + enum: + - loongson,ls2k0500-eiointc + - loongson,ls2k2000-eiointc + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + interrupt-controller: true + + '#interrupt-cells': + const: 1 + +required: + - compatible + - reg + - interrupts + - interrupt-controller + - '#interrupt-cells' + +unevaluatedProperties: false + +examples: + - | + eiointc: interrupt-controller@1fe11600 { + compatible = "loongson,ls2k0500-eiointc"; + reg = <0x1fe10000 0x10000>; + + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-parent = <&cpuintc>; + interrupts = <3>; + }; + +... diff --git a/Documentation/devicetree/bindings/memory-controllers/nuvoton,npcm-memory-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/nuvoton,npcm-memory-controller.yaml new file mode 100644 index 000000000000..ac1a5a17749d --- /dev/null +++ b/Documentation/devicetree/bindings/memory-controllers/nuvoton,npcm-memory-controller.yaml @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/memory-controllers/nuvoton,npcm-memory-controller.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Nuvoton NPCM Memory Controller + +maintainers: + - Marvin Lin <kflin@nuvoton.com> + - Stanley Chu <yschu@nuvoton.com> + +description: | + The Nuvoton BMC SoC supports DDR4 memory with or without ECC (error correction + check). + + The memory controller supports single bit error correction, double bit error + detection (in-line ECC in which a section (1/8th) of the memory device used to + store data is used for ECC storage). + + Note, the bootloader must configure ECC mode for the memory controller. + +properties: + compatible: + enum: + - nuvoton,npcm750-memory-controller + - nuvoton,npcm845-memory-controller + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + + mc: memory-controller@f0824000 { + compatible = "nuvoton,npcm750-memory-controller"; + reg = <0xf0824000 0x1000>; + interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>; + }; diff --git a/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml index 8459d3642205..3b3beab9db3f 100644 --- a/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml +++ b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Canaan Kendryte K210 System Controller maintainers: - - Damien Le Moal <damien.lemoal@wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: Canaan Inc. Kendryte K210 SoC system controller which provides a diff --git a/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml b/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml index 8cc2b9924680..043e118c605c 100644 --- a/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml +++ b/Documentation/devicetree/bindings/net/realtek-bluetooth.yaml @@ -11,7 +11,7 @@ maintainers: - Alistair Francis <alistair@alistair23.me> description: - RTL8723CS/RTL8723CS/RTL8821CS/RTL8822CS is a WiFi + BT chip. WiFi part + RTL8723BS/RTL8723CS/RTL8821CS/RTL8822CS is a WiFi + BT chip. WiFi part is connected over SDIO, while BT is connected over serial. It speaks H5 protocol with few extra commands to upload firmware and change module speed. @@ -27,7 +27,7 @@ properties: - items: - enum: - realtek,rtl8821cs-bt - - const: realtek,rtl8822cs-bt + - const: realtek,rtl8723bs-bt device-wake-gpios: maxItems: 1 diff --git a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml index 7f4f36a58e56..739a08f00467 100644 --- a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml +++ b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Canaan Kendryte K210 FPIOA maintainers: - - Damien Le Moal <damien.lemoal@wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: The Canaan Kendryte K210 SoC Fully Programmable IO Array (FPIOA) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml index c91d3e3a094b..80f960671857 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml @@ -144,8 +144,9 @@ $defs: enum: [0, 1, 2, 3, 4, 5, 6, 7] qcom,paired: - - description: - Indicates that the pin should be operating in paired mode. + type: boolean + description: + Indicates that the pin should be operating in paired mode. required: - pins diff --git a/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml index ee8a2dcf5dfa..0c0135964b91 100644 --- a/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml +++ b/Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Canaan Kendryte K210 Reset Controller maintainers: - - Damien Le Moal <damien.lemoal@wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: | Canaan Kendryte K210 reset controller driver which supports the SoC diff --git a/Documentation/devicetree/bindings/riscv/canaan.yaml b/Documentation/devicetree/bindings/riscv/canaan.yaml index f8f3f286bd55..41fd11f70a49 100644 --- a/Documentation/devicetree/bindings/riscv/canaan.yaml +++ b/Documentation/devicetree/bindings/riscv/canaan.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Canaan SoC-based boards maintainers: - - Damien Le Moal <damien.lemoal@wdc.com> + - Damien Le Moal <dlemoal@kernel.org> description: Canaan Kendryte K210 SoC-based boards diff --git a/Documentation/devicetree/bindings/timer/brcm,kona-timer.txt b/Documentation/devicetree/bindings/timer/brcm,kona-timer.txt deleted file mode 100644 index 39adf54b4388..000000000000 --- a/Documentation/devicetree/bindings/timer/brcm,kona-timer.txt +++ /dev/null @@ -1,25 +0,0 @@ -Broadcom Kona Family timer ------------------------------------------------------ -This timer is used in the following Broadcom SoCs: - BCM11130, BCM11140, BCM11351, BCM28145, BCM28155 - -Required properties: -- compatible : "brcm,kona-timer" -- DEPRECATED: compatible : "bcm,kona-timer" -- reg : Register range for the timer -- interrupts : interrupt for the timer -- clocks: phandle + clock specifier pair of the external clock -- clock-frequency: frequency that the clock operates - -Only one of clocks or clock-frequency should be specified. - -Refer to clocks/clock-bindings.txt for generic clock consumer properties. - -Example: - timer@35006000 { - compatible = "brcm,kona-timer"; - reg = <0x35006000 0x1000>; - interrupts = <0x0 7 0x4>; - clocks = <&hub_timer_clk>; - }; - diff --git a/Documentation/devicetree/bindings/timer/brcm,kona-timer.yaml b/Documentation/devicetree/bindings/timer/brcm,kona-timer.yaml new file mode 100644 index 000000000000..d6af8383d6fc --- /dev/null +++ b/Documentation/devicetree/bindings/timer/brcm,kona-timer.yaml @@ -0,0 +1,52 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/brcm,kona-timer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Broadcom Kona family timer + +maintainers: + - Florian Fainelli <f.fainelli@gmail.com> + +properties: + compatible: + const: brcm,kona-timer + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-frequency: true + +oneOf: + - required: + - clocks + - required: + - clock-frequency + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/clock/bcm281xx.h> + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + + timer@35006000 { + compatible = "brcm,kona-timer"; + reg = <0x35006000 0x1000>; + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&aon_ccu BCM281XX_AON_CCU_HUB_TIMER>; + }; +... diff --git a/Documentation/devicetree/bindings/timer/loongson,ls1x-pwmtimer.yaml b/Documentation/devicetree/bindings/timer/loongson,ls1x-pwmtimer.yaml new file mode 100644 index 000000000000..ad61ae55850b --- /dev/null +++ b/Documentation/devicetree/bindings/timer/loongson,ls1x-pwmtimer.yaml @@ -0,0 +1,48 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/loongson,ls1x-pwmtimer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Loongson-1 PWM timer + +maintainers: + - Keguang Zhang <keguang.zhang@gmail.com> + +description: + Loongson-1 PWM timer can be used for system clock source + and clock event timers. + +properties: + compatible: + const: loongson,ls1b-pwmtimer + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/clock/loongson,ls1x-clk.h> + #include <dt-bindings/interrupt-controller/irq.h> + clocksource: timer@1fe5c030 { + compatible = "loongson,ls1b-pwmtimer"; + reg = <0x1fe5c030 0x10>; + + clocks = <&clkc LS1X_CLKID_APB>; + interrupt-parent = <&intc0>; + interrupts = <20 IRQ_TYPE_LEVEL_HIGH>; + }; diff --git a/Documentation/devicetree/bindings/timer/ralink,rt2880-timer.yaml b/Documentation/devicetree/bindings/timer/ralink,rt2880-timer.yaml new file mode 100644 index 000000000000..daa7832babe3 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/ralink,rt2880-timer.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/ralink,rt2880-timer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Timer present in Ralink family SoCs + +maintainers: + - Sergio Paracuellos <sergio.paracuellos@gmail.com> + +properties: + compatible: + const: ralink,rt2880-timer + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - clocks + - interrupts + +additionalProperties: false + +examples: + - | + timer@100 { + compatible = "ralink,rt2880-timer"; + reg = <0x100 0x20>; + + clocks = <&sysc 3>; + + interrupt-parent = <&intc>; + interrupts = <1>; + }; +... diff --git a/Documentation/devicetree/usage-model.rst b/Documentation/devicetree/usage-model.rst index b6a287955ee5..0717426856b2 100644 --- a/Documentation/devicetree/usage-model.rst +++ b/Documentation/devicetree/usage-model.rst @@ -415,6 +415,6 @@ When using the DT, this creates problems for of_platform_populate() because it must decide whether to register each node as either a platform_device or an amba_device. This unfortunately complicates the device creation model a little bit, but the solution turns out not to -be too invasive. If a node is compatible with "arm,amba-primecell", then +be too invasive. If a node is compatible with "arm,primecell", then of_platform_populate() will register it as an amba_device instead of a platform_device. diff --git a/Documentation/driver-api/edac.rst b/Documentation/driver-api/edac.rst index b8c742aa0a71..f4f044b95c4f 100644 --- a/Documentation/driver-api/edac.rst +++ b/Documentation/driver-api/edac.rst @@ -106,6 +106,16 @@ will occupy those chip-select rows. This term is avoided because it is unclear when needing to distinguish between chip-select rows and socket sets. +* High Bandwidth Memory (HBM) + +HBM is a new memory type with low power consumption and ultra-wide +communication lanes. It uses vertically stacked memory chips (DRAM dies) +interconnected by microscopic wires called "through-silicon vias," or +TSVs. + +Several stacks of HBM chips connect to the CPU or GPU through an ultra-fast +interconnect called the "interposer". Therefore, HBM's characteristics +are nearly indistinguishable from on-chip integrated RAM. Memory Controllers ------------------ @@ -176,3 +186,113 @@ nodes:: the L1 and L2 directories would be "edac_device_block's" .. kernel-doc:: drivers/edac/edac_device.h + + +Heterogeneous system support +---------------------------- + +An AMD heterogeneous system is built by connecting the data fabrics of +both CPUs and GPUs via custom xGMI links. Thus, the data fabric on the +GPU nodes can be accessed the same way as the data fabric on CPU nodes. + +The MI200 accelerators are data center GPUs. They have 2 data fabrics, +and each GPU data fabric contains four Unified Memory Controllers (UMC). +Each UMC contains eight channels. Each UMC channel controls one 128-bit +HBM2e (2GB) channel (equivalent to 8 X 2GB ranks). This creates a total +of 4096-bits of DRAM data bus. + +While the UMC is interfacing a 16GB (8high X 2GB DRAM) HBM stack, each UMC +channel is interfacing 2GB of DRAM (represented as rank). + +Memory controllers on AMD GPU nodes can be represented in EDAC thusly: + + GPU DF / GPU Node -> EDAC MC + GPU UMC -> EDAC CSROW + GPU UMC channel -> EDAC CHANNEL + +For example: a heterogeneous system with 1 AMD CPU is connected to +4 MI200 (Aldebaran) GPUs using xGMI. + +Some more heterogeneous hardware details: + +- The CPU UMC (Unified Memory Controller) is mostly the same as the GPU UMC. + They have chip selects (csrows) and channels. However, the layouts are different + for performance, physical layout, or other reasons. +- CPU UMCs use 1 channel, In this case UMC = EDAC channel. This follows the + marketing speak. CPU has X memory channels, etc. +- CPU UMCs use up to 4 chip selects, So UMC chip select = EDAC CSROW. +- GPU UMCs use 1 chip select, So UMC = EDAC CSROW. +- GPU UMCs use 8 channels, So UMC channel = EDAC channel. + +The EDAC subsystem provides a mechanism to handle AMD heterogeneous +systems by calling system specific ops for both CPUs and GPUs. + +AMD GPU nodes are enumerated in sequential order based on the PCI +hierarchy, and the first GPU node is assumed to have a Node ID value +following those of the CPU nodes after latter are fully populated:: + + $ ls /sys/devices/system/edac/mc/ + mc0 - CPU MC node 0 + mc1 | + mc2 |- GPU card[0] => node 0(mc1), node 1(mc2) + mc3 | + mc4 |- GPU card[1] => node 0(mc3), node 1(mc4) + mc5 | + mc6 |- GPU card[2] => node 0(mc5), node 1(mc6) + mc7 | + mc8 |- GPU card[3] => node 0(mc7), node 1(mc8) + +For example, a heterogeneous system with one AMD CPU is connected to +four MI200 (Aldebaran) GPUs using xGMI. This topology can be represented +via the following sysfs entries:: + + /sys/devices/system/edac/mc/.. + + CPU # CPU node + ├── mc 0 + + GPU Nodes are enumerated sequentially after CPU nodes have been populated + GPU card 1 # Each MI200 GPU has 2 nodes/mcs + ├── mc 1 # GPU node 0 == mc1, Each MC node has 4 UMCs/CSROWs + │  ├── csrow 0 # UMC 0 + │  │  ├── channel 0 # Each UMC has 8 channels + │  │  ├── channel 1 # size of each channel is 2 GB, so each UMC has 16 GB + │  │  ├── channel 2 + │  │  ├── channel 3 + │  │  ├── channel 4 + │  │  ├── channel 5 + │  │  ├── channel 6 + │  │  ├── channel 7 + │  ├── csrow 1 # UMC 1 + │  │  ├── channel 0 + │  │  ├── .. + │  │  ├── channel 7 + │  ├── .. .. + │  ├── csrow 3 # UMC 3 + │  │  ├── channel 0 + │  │  ├── .. + │  │  ├── channel 7 + │  ├── rank 0 + │  ├── .. .. + │  ├── rank 31 # total 32 ranks/dimms from 4 UMCs + ├ + ├── mc 2 # GPU node 1 == mc2 + │  ├── .. # each GPU has total 64 GB + + GPU card 2 + ├── mc 3 + │  ├── .. + ├── mc 4 + │  ├── .. + + GPU card 3 + ├── mc 5 + │  ├── .. + ├── mc 6 + │  ├── .. + + GPU card 4 + ├── mc 7 + │  ├── .. + ├── mc 8 + │  ├── .. diff --git a/Documentation/filesystems/directory-locking.rst b/Documentation/filesystems/directory-locking.rst index 504ba940c36c..dccd61c7c5c3 100644 --- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,12 +22,11 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive. -4) rename() that is _not_ cross-directory. Locking rules: caller locks -the parent and finds source and target. In case of exchange (with -RENAME_EXCHANGE in flags argument) lock both. In any case, -if the target already exists, lock it. If the source is a non-directory, -lock it. If we need to lock both, lock them in inode pointer order. -Then call the method. All locks are exclusive. +4) rename() that is _not_ cross-directory. Locking rules: caller locks the +parent and finds source and target. We lock both (provided they exist). If we +need to lock two inodes of different type (dir vs non-dir), we lock directory +first. If we need to lock two inodes of the same type, lock them in inode +pointer order. Then call the method. All locks are exclusive. NB: we might get away with locking the source (and target in exchange case) shared. @@ -44,15 +43,17 @@ All locks are exclusive. rules: * lock the filesystem - * lock parents in "ancestors first" order. + * lock parents in "ancestors first" order. If one is not ancestor of + the other, lock them in inode pointer order. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * If it's an exchange, lock both the source and the target. - * If the target exists, lock it. If the source is a non-directory, - lock it. If we need to lock both, do so in inode pointer order. + * Lock both the source and the target provided they exist. If we + need to lock two inodes of different type (dir vs non-dir), we lock + the directory first. If we need to lock two inodes of the same type, + lock them in inode pointer order. * call the method. All ->i_rwsem are taken exclusive. Again, we might get away with locking @@ -66,8 +67,9 @@ If no directory is its own ancestor, the scheme above is deadlock-free. Proof: - First of all, at any moment we have a partial ordering of the - objects - A < B iff A is an ancestor of B. + First of all, at any moment we have a linear ordering of the + objects - A < B iff (A is an ancestor of B) or (B is not an ancestor + of A and ptr(A) < ptr(B)). That ordering can change. However, the following is true: diff --git a/Documentation/filesystems/fsverity.rst b/Documentation/filesystems/fsverity.rst index ede672dedf11..cb845e8e5435 100644 --- a/Documentation/filesystems/fsverity.rst +++ b/Documentation/filesystems/fsverity.rst @@ -38,20 +38,14 @@ fail at runtime. Use cases ========= -By itself, the base fs-verity feature only provides integrity -protection, i.e. detection of accidental (non-malicious) corruption. +By itself, fs-verity only provides integrity protection, i.e. +detection of accidental (non-malicious) corruption. However, because fs-verity makes retrieving the file hash extremely efficient, it's primarily meant to be used as a tool to support authentication (detection of malicious modifications) or auditing (logging file hashes before use). -Trusted userspace code (e.g. operating system code running on a -read-only partition that is itself authenticated by dm-verity) can -authenticate the contents of an fs-verity file by using the -`FS_IOC_MEASURE_VERITY`_ ioctl to retrieve its hash, then verifying a -digital signature of it. - A standard file hash could be used instead of fs-verity. However, this is inefficient if the file is large and only a small portion may be accessed. This is often the case for Android application package @@ -69,24 +63,31 @@ still be used on read-only filesystems. fs-verity is for files that must live on a read-write filesystem because they are independently updated and potentially user-installed, so dm-verity cannot be used. -The base fs-verity feature is a hashing mechanism only; actually -authenticating the files may be done by: - -* Userspace-only - -* Builtin signature verification + userspace policy - - fs-verity optionally supports a simple signature verification - mechanism where users can configure the kernel to require that - all fs-verity files be signed by a key loaded into a keyring; - see `Built-in signature verification`_. - -* Integrity Measurement Architecture (IMA) - - IMA supports including fs-verity file digests and signatures in the - IMA measurement list and verifying fs-verity based file signatures - stored as security.ima xattrs, based on policy. - +fs-verity does not mandate a particular scheme for authenticating its +file hashes. (Similarly, dm-verity does not mandate a particular +scheme for authenticating its block device root hashes.) Options for +authenticating fs-verity file hashes include: + +- Trusted userspace code. Often, the userspace code that accesses + files can be trusted to authenticate them. Consider e.g. an + application that wants to authenticate data files before using them, + or an application loader that is part of the operating system (which + is already authenticated in a different way, such as by being loaded + from a read-only partition that uses dm-verity) and that wants to + authenticate applications before loading them. In these cases, this + trusted userspace code can authenticate a file's contents by + retrieving its fs-verity digest using `FS_IOC_MEASURE_VERITY`_, then + verifying a signature of it using any userspace cryptographic + library that supports digital signatures. + +- Integrity Measurement Architecture (IMA). IMA supports fs-verity + file digests as an alternative to its traditional full file digests. + "IMA appraisal" enforces that files contain a valid, matching + signature in their "security.ima" extended attribute, as controlled + by the IMA policy. For more information, see the IMA documentation. + +- Trusted userspace code in combination with `Built-in signature + verification`_. This approach should be used only with great care. User API ======== @@ -111,8 +112,7 @@ follows:: }; This structure contains the parameters of the Merkle tree to build for -the file, and optionally contains a signature. It must be initialized -as follows: +the file. It must be initialized as follows: - ``version`` must be 1. - ``hash_algorithm`` must be the identifier for the hash algorithm to @@ -129,12 +129,14 @@ as follows: file or device. Currently the maximum salt size is 32 bytes. - ``salt_ptr`` is the pointer to the salt, or NULL if no salt is provided. -- ``sig_size`` is the size of the signature in bytes, or 0 if no - signature is provided. Currently the signature is (somewhat - arbitrarily) limited to 16128 bytes. See `Built-in signature - verification`_ for more information. -- ``sig_ptr`` is the pointer to the signature, or NULL if no - signature is provided. +- ``sig_size`` is the size of the builtin signature in bytes, or 0 if no + builtin signature is provided. Currently the builtin signature is + (somewhat arbitrarily) limited to 16128 bytes. +- ``sig_ptr`` is the pointer to the builtin signature, or NULL if no + builtin signature is provided. A builtin signature is only needed + if the `Built-in signature verification`_ feature is being used. It + is not needed for IMA appraisal, and it is not needed if the file + signature is being handled entirely in userspace. - All reserved fields must be zeroed. FS_IOC_ENABLE_VERITY causes the filesystem to build a Merkle tree for @@ -158,7 +160,7 @@ fatal signal), no changes are made to the file. FS_IOC_ENABLE_VERITY can fail with the following errors: - ``EACCES``: the process does not have write access to the file -- ``EBADMSG``: the signature is malformed +- ``EBADMSG``: the builtin signature is malformed - ``EBUSY``: this ioctl is already running on the file - ``EEXIST``: the file already has verity enabled - ``EFAULT``: the caller provided inaccessible memory @@ -168,10 +170,10 @@ FS_IOC_ENABLE_VERITY can fail with the following errors: reserved bits are set; or the file descriptor refers to neither a regular file nor a directory. - ``EISDIR``: the file descriptor refers to a directory -- ``EKEYREJECTED``: the signature doesn't match the file -- ``EMSGSIZE``: the salt or signature is too long -- ``ENOKEY``: the fs-verity keyring doesn't contain the certificate - needed to verify the signature +- ``EKEYREJECTED``: the builtin signature doesn't match the file +- ``EMSGSIZE``: the salt or builtin signature is too long +- ``ENOKEY``: the ".fs-verity" keyring doesn't contain the certificate + needed to verify the builtin signature - ``ENOPKG``: fs-verity recognizes the hash algorithm, but it's not available in the kernel's crypto API as currently configured (e.g. for SHA-512, missing CONFIG_CRYPTO_SHA512). @@ -180,8 +182,8 @@ FS_IOC_ENABLE_VERITY can fail with the following errors: support; or the filesystem superblock has not had the 'verity' feature enabled on it; or the filesystem does not support fs-verity on this file. (See `Filesystem support`_.) -- ``EPERM``: the file is append-only; or, a signature is required and - one was not provided. +- ``EPERM``: the file is append-only; or, a builtin signature is + required and one was not provided. - ``EROFS``: the filesystem is read-only - ``ETXTBSY``: someone has the file open for writing. This can be the caller's file descriptor, another open file descriptor, or the file @@ -270,9 +272,9 @@ This ioctl takes in a pointer to the following structure:: - ``FS_VERITY_METADATA_TYPE_DESCRIPTOR`` reads the fs-verity descriptor. See `fs-verity descriptor`_. -- ``FS_VERITY_METADATA_TYPE_SIGNATURE`` reads the signature which was - passed to FS_IOC_ENABLE_VERITY, if any. See `Built-in signature - verification`_. +- ``FS_VERITY_METADATA_TYPE_SIGNATURE`` reads the builtin signature + which was passed to FS_IOC_ENABLE_VERITY, if any. See `Built-in + signature verification`_. The semantics are similar to those of ``pread()``. ``offset`` specifies the offset in bytes into the metadata item to read from, and @@ -299,7 +301,7 @@ FS_IOC_READ_VERITY_METADATA can fail with the following errors: overflowed - ``ENODATA``: the file is not a verity file, or FS_VERITY_METADATA_TYPE_SIGNATURE was requested but the file doesn't - have a built-in signature + have a builtin signature - ``ENOTTY``: this type of filesystem does not implement fs-verity, or this ioctl is not yet implemented on it - ``EOPNOTSUPP``: the kernel was not configured with fs-verity @@ -347,8 +349,8 @@ non-verity one, with the following exceptions: with EIO (for read()) or SIGBUS (for mmap() reads). - If the sysctl "fs.verity.require_signatures" is set to 1 and the - file is not signed by a key in the fs-verity keyring, then opening - the file will fail. See `Built-in signature verification`_. + file is not signed by a key in the ".fs-verity" keyring, then + opening the file will fail. See `Built-in signature verification`_. Direct access to the Merkle tree is not supported. Therefore, if a verity file is copied, or is backed up and restored, then it will lose @@ -433,20 +435,25 @@ root hash as well as other fields such as the file size:: Built-in signature verification =============================== -With CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y, fs-verity supports putting -a portion of an authentication policy (see `Use cases`_) in the -kernel. Specifically, it adds support for: +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y adds supports for in-kernel +verification of fs-verity builtin signatures. + +**IMPORTANT**! Please take great care before using this feature. +It is not the only way to do signatures with fs-verity, and the +alternatives (such as userspace signature verification, and IMA +appraisal) can be much better. It's also easy to fall into a trap +of thinking this feature solves more problems than it actually does. + +Enabling this option adds the following: -1. At fs-verity module initialization time, a keyring ".fs-verity" is - created. The root user can add trusted X.509 certificates to this - keyring using the add_key() system call, then (when done) - optionally use keyctl_restrict_keyring() to prevent additional - certificates from being added. +1. At boot time, the kernel creates a keyring named ".fs-verity". The + root user can add trusted X.509 certificates to this keyring using + the add_key() system call. 2. `FS_IOC_ENABLE_VERITY`_ accepts a pointer to a PKCS#7 formatted detached signature in DER format of the file's fs-verity digest. - On success, this signature is persisted alongside the Merkle tree. - Then, any time the file is opened, the kernel will verify the + On success, the ioctl persists the signature alongside the Merkle + tree. Then, any time the file is opened, the kernel verifies the file's actual digest against this signature, using the certificates in the ".fs-verity" keyring. @@ -454,8 +461,8 @@ kernel. Specifically, it adds support for: When set to 1, the kernel requires that all verity files have a correctly signed digest as described in (2). -fs-verity file digests must be signed in the following format, which -is similar to the structure used by `FS_IOC_MEASURE_VERITY`_:: +The data that the signature as described in (2) must be a signature of +is the fs-verity file digest in the following format:: struct fsverity_formatted_digest { char magic[8]; /* must be "FSVerity" */ @@ -464,13 +471,66 @@ is similar to the structure used by `FS_IOC_MEASURE_VERITY`_:: __u8 digest[]; }; -fs-verity's built-in signature verification support is meant as a -relatively simple mechanism that can be used to provide some level of -authenticity protection for verity files, as an alternative to doing -the signature verification in userspace or using IMA-appraisal. -However, with this mechanism, userspace programs still need to check -that the verity bit is set, and there is no protection against verity -files being swapped around. +That's it. It should be emphasized again that fs-verity builtin +signatures are not the only way to do signatures with fs-verity. See +`Use cases`_ for an overview of ways in which fs-verity can be used. +fs-verity builtin signatures have some major limitations that should +be carefully considered before using them: + +- Builtin signature verification does *not* make the kernel enforce + that any files actually have fs-verity enabled. Thus, it is not a + complete authentication policy. Currently, if it is used, the only + way to complete the authentication policy is for trusted userspace + code to explicitly check whether files have fs-verity enabled with a + signature before they are accessed. (With + fs.verity.require_signatures=1, just checking whether fs-verity is + enabled suffices.) But, in this case the trusted userspace code + could just store the signature alongside the file and verify it + itself using a cryptographic library, instead of using this feature. + +- A file's builtin signature can only be set at the same time that + fs-verity is being enabled on the file. Changing or deleting the + builtin signature later requires re-creating the file. + +- Builtin signature verification uses the same set of public keys for + all fs-verity enabled files on the system. Different keys cannot be + trusted for different files; each key is all or nothing. + +- The sysctl fs.verity.require_signatures applies system-wide. + Setting it to 1 only works when all users of fs-verity on the system + agree that it should be set to 1. This limitation can prevent + fs-verity from being used in cases where it would be helpful. + +- Builtin signature verification can only use signature algorithms + that are supported by the kernel. For example, the kernel does not + yet support Ed25519, even though this is often the signature + algorithm that is recommended for new cryptographic designs. + +- fs-verity builtin signatures are in PKCS#7 format, and the public + keys are in X.509 format. These formats are commonly used, + including by some other kernel features (which is why the fs-verity + builtin signatures use them), and are very feature rich. + Unfortunately, history has shown that code that parses and handles + these formats (which are from the 1990s and are based on ASN.1) + often has vulnerabilities as a result of their complexity. This + complexity is not inherent to the cryptography itself. + + fs-verity users who do not need advanced features of X.509 and + PKCS#7 should strongly consider using simpler formats, such as plain + Ed25519 keys and signatures, and verifying signatures in userspace. + + fs-verity users who choose to use X.509 and PKCS#7 anyway should + still consider that verifying those signatures in userspace is more + flexible (for other reasons mentioned earlier in this document) and + eliminates the need to enable CONFIG_FS_VERITY_BUILTIN_SIGNATURES + and its associated increase in kernel attack surface. In some cases + it can even be necessary, since advanced X.509 and PKCS#7 features + do not always work as intended with the kernel. For example, the + kernel does not check X.509 certificate validity times. + + Note: IMA appraisal, which supports fs-verity, does not use PKCS#7 + for its signatures, so it partially avoids the issues discussed + here. IMA appraisal does use X.509. Filesystem support ================== diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index ef540865ad22..5cf6a5f8ca57 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -31,7 +31,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== GNU C 5.1 gcc --version Clang/LLVM (optional) 11.0.0 clang --version -Rust (optional) 1.62.0 rustc --version +Rust (optional) 1.68.2 rustc --version bindgen (optional) 0.56.0 bindgen --version GNU make 3.82 make --version bash 4.2 bash --version diff --git a/Documentation/riscv/patch-acceptance.rst b/Documentation/riscv/patch-acceptance.rst index 07d5a5623e2a..634aa222b410 100644 --- a/Documentation/riscv/patch-acceptance.rst +++ b/Documentation/riscv/patch-acceptance.rst @@ -16,6 +16,24 @@ tested code over experimental code. We wish to extend these same principles to the RISC-V-related code that will be accepted for inclusion in the kernel. +Patchwork +--------- + +RISC-V has a patchwork instance, where the status of patches can be checked: + + https://patchwork.kernel.org/project/linux-riscv/list/ + +If your patch does not appear in the default view, the RISC-V maintainers have +likely either requested changes, or expect it to be applied to another tree. + +Automation runs against this patchwork instance, building/testing patches as +they arrive. The automation applies patches against the current HEAD of the +RISC-V `for-next` and `fixes` branches, depending on whether the patch has been +detected as a fix. Failing those, it will use the RISC-V `master` branch. +The exact commit to which a series has been applied will be noted on patchwork. +Patches for which any of the checks fail are unlikely to be applied and in most +cases will need to be resubmitted. + Submit Checklist Addendum ------------------------- We'll only accept patches for new modules or extensions if the diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst index 13b7744b1e27..a8931512ed98 100644 --- a/Documentation/rust/quick-start.rst +++ b/Documentation/rust/quick-start.rst @@ -38,9 +38,9 @@ and run:: rustup override set $(scripts/min-tool-version.sh rustc) -Otherwise, fetch a standalone installer or install ``rustup`` from: +Otherwise, fetch a standalone installer from: - https://www.rust-lang.org + https://forge.rust-lang.org/infra/other-installation-methods.html#standalone Rust standard library source diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst index f79987e16cf4..e7b07313550a 100644 --- a/Documentation/trace/user_events.rst +++ b/Documentation/trace/user_events.rst @@ -14,10 +14,6 @@ Programs can view status of the events via /sys/kernel/tracing/user_events_status and can both register and write data out via /sys/kernel/tracing/user_events_data. -Programs can also use /sys/kernel/tracing/dynamic_events to register and -delete user based events via the u: prefix. The format of the command to -dynamic_events is the same as the ioctl with the u: prefix applied. - Typically programs will register a set of events that they wish to expose to tools that can read trace_events (such as ftrace and perf). The registration process tells the kernel which address and bit to reflect if any tool has @@ -144,6 +140,9 @@ its name. Delete will only succeed if there are no references left to the event (in both user and kernel space). User programs should use a separate file to request deletes than the one used for registration due to this. +**NOTE:** By default events will auto-delete when there are no references left +to the event. Flags in the future may change this logic. + Unregistering ------------- If after registering an event it is no longer wanted to be updated then it can diff --git a/Documentation/translations/zh_CN/devicetree/usage-model.rst b/Documentation/translations/zh_CN/devicetree/usage-model.rst index c6aee82c7e6e..19ba4ae0cd81 100644 --- a/Documentation/translations/zh_CN/devicetree/usage-model.rst +++ b/Documentation/translations/zh_CN/devicetree/usage-model.rst @@ -325,6 +325,6 @@ Primecell设备。然而,棘手的一点是,AMBA总线上的所有设备并é 当使用DT时,这给of_platform_populate()带æ¥äº†é—®é¢˜ï¼Œå› 为它必须决定是å¦å°† æ¯ä¸ªèŠ‚点注册为platform_device或amba_device。ä¸å¹¸çš„是,这使设备创建模型 -å˜å¾—有点å¤æ‚,但解决方案原æ¥å¹¶ä¸æ˜¯å¤ªå…·æœ‰ä¾µç•¥æ€§ã€‚如果一个节点与“arm,amba-primecell†+å˜å¾—有点å¤æ‚,但解决方案原æ¥å¹¶ä¸æ˜¯å¤ªå…·æœ‰ä¾µç•¥æ€§ã€‚如果一个节点与“arm,primecell†兼容,那么of_platform_populate()将把它注册为amba_device而ä¸æ˜¯ platform_device。 diff --git a/MAINTAINERS b/MAINTAINERS index f794002a192e..3ebcef64ba88 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5344,6 +5344,18 @@ F: include/linux/sched/cpufreq.h F: kernel/sched/cpufreq*.c F: tools/testing/selftests/cpufreq/ +CPU HOTPLUG +M: Thomas Gleixner <tglx@linutronix.de> +M: Peter Zijlstra <peterz@infradead.org> +L: linux-kernel@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp/core +F: kernel/cpu.c +F: kernel/smpboot.* +F: include/linux/cpu.h +F: include/linux/cpuhotplug.h +F: include/linux/smpboot.h + CPU IDLE TIME MANAGEMENT FRAMEWORK M: "Rafael J. Wysocki" <rafael@kernel.org> M: Daniel Lezcano <daniel.lezcano@linaro.org> @@ -7482,6 +7494,14 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/mpc85xx_edac.[ch] +EDAC-NPCM +M: Marvin Lin <kflin@nuvoton.com> +M: Stanley Chu <yschu@nuvoton.com> +L: linux-edac@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/memory-controllers/nuvoton,npcm-memory-controller.yaml +F: drivers/edac/npcm_edac.c + EDAC-PASEMI M: Egor Martovetsky <egor@pasemi.com> L: linux-edac@vger.kernel.org @@ -9972,8 +9992,9 @@ M: Miquel Raynal <miquel.raynal@bootlin.com> L: linux-wpan@vger.kernel.org S: Maintained W: https://linux-wpan.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git +Q: https://patchwork.kernel.org/project/linux-wpan/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wpan/wpan.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wpan/wpan-next.git F: Documentation/networking/ieee802154.rst F: drivers/net/ieee802154/ F: include/linux/ieee802154.h @@ -11274,6 +11295,10 @@ W: http://kernelnewbies.org/KernelJanitors KERNEL NFSD, SUNRPC, AND LOCKD SERVERS M: Chuck Lever <chuck.lever@oracle.com> M: Jeff Layton <jlayton@kernel.org> +R: Neil Brown <neilb@suse.de> +R: Olga Kornievskaia <kolga@netapp.com> +R: Dai Ngo <Dai.Ngo@oracle.com> +R: Tom Talpey <tom@talpey.com> L: linux-nfs@vger.kernel.org S: Supported W: http://nfs.sourceforge.net/ @@ -13269,10 +13294,11 @@ F: drivers/memory/mtk-smi.c F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER -M: Sean Wang <sean.wang@mediatek.com> +M: Arınç ÃœNAL <arinc.unal@arinc9.com> +M: Daniel Golle <daniel@makrotopia.org> M: Landen Chao <Landen.Chao@mediatek.com> M: DENG Qingfang <dqfext@gmail.com> -M: Daniel Golle <daniel@makrotopia.org> +M: Sean Wang <sean.wang@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530-mdio.c @@ -16384,7 +16410,7 @@ F: Documentation/devicetree/bindings/pci/intel,keembay-pcie* F: drivers/pci/controller/dwc/pcie-keembay.c PCIE DRIVER FOR INTEL LGM GW SOC -M: Rahul Tanwar <rtanwar@maxlinear.com> +M: Chuanhua Lei <lchuanhua@maxlinear.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml @@ -17827,7 +17853,7 @@ F: tools/testing/selftests/rtc/ Real-time Linux Analysis (RTLA) tools M: Daniel Bristot de Oliveira <bristot@kernel.org> M: Steven Rostedt <rostedt@goodmis.org> -L: linux-trace-devel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org S: Maintained F: Documentation/tools/rtla/ F: tools/tracing/rtla/ @@ -18397,7 +18423,7 @@ F: drivers/infiniband/ulp/rtrs/ RUNTIME VERIFICATION (RV) M: Daniel Bristot de Oliveira <bristot@kernel.org> M: Steven Rostedt <rostedt@goodmis.org> -L: linux-trace-devel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org S: Maintained F: Documentation/trace/rv/ F: include/linux/rv.h @@ -19140,6 +19166,9 @@ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS M: Karsten Graul <kgraul@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> M: Jan Karcher <jaka@linux.ibm.com> +R: D. Wythe <alibuda@linux.alibaba.com> +R: Tony Lu <tonylu@linux.alibaba.com> +R: Wen Gu <guwen@linux.alibaba.com> L: linux-s390@vger.kernel.org S: Supported F: net/smc/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 205fd23e0cad..e1faf3e3637b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -34,6 +34,29 @@ config ARCH_HAS_SUBPAGE_FAULTS config HOTPLUG_SMT bool +# Selected by HOTPLUG_CORE_SYNC_DEAD or HOTPLUG_CORE_SYNC_FULL +config HOTPLUG_CORE_SYNC + bool + +# Basic CPU dead synchronization selected by architecture +config HOTPLUG_CORE_SYNC_DEAD + bool + select HOTPLUG_CORE_SYNC + +# Full CPU synchronization with alive state selected by architecture +config HOTPLUG_CORE_SYNC_FULL + bool + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU + select HOTPLUG_CORE_SYNC + +config HOTPLUG_SPLIT_STARTUP + bool + select HOTPLUG_CORE_SYNC_FULL + +config HOTPLUG_PARALLEL + bool + select HOTPLUG_SPLIT_STARTUP + config GENERIC_ENTRY bool @@ -285,6 +308,9 @@ config ARCH_HAS_DMA_SET_UNCACHED config ARCH_HAS_DMA_CLEAR_UNCACHED bool +config ARCH_HAS_CPU_FINALIZE_INIT + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h deleted file mode 100644 index 78030d1c7e7e..000000000000 --- a/arch/alpha/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * include/asm-alpha/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any alpha bugs yet.. Nice chip - */ - -static void check_bugs(void) -{ -} diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 2a9a877a0508..d98701ee36c6 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1014,8 +1014,6 @@ SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv, return do_sys_settimeofday64(tv ? &kts : NULL, tz ? &ktz : NULL); } -asmlinkage long sys_ni_posix_timers(void); - SYSCALL_DEFINE2(osf_utimes, const char __user *, filename, struct timeval32 __user *, tvs) { diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 33bf3a627002..b650ff1cb022 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -658,7 +658,7 @@ setup_arch(char **cmdline_p) #endif /* Default root filesystem to sda2. */ - ROOT_DEV = Root_SDA2; + ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2); #ifdef CONFIG_EISA /* FIXME: only set this when we actually have EISA in this box? */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0fb4b218f665..1b158bbab29a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_32BIT_OFF_T select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE @@ -124,6 +125,7 @@ config ARM select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 select HAVE_VIRT_CPU_ACCOUNTING_GEN + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select IRQ_FORCED_THREADING select MODULES_USE_ELF_REL select NEED_DMA_MAP_STATE diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index f4db3e75d75f..f3cd04ff022d 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -222,6 +222,11 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) return false; } +static inline bool kvm_set_pmuserenr(u64 val) +{ + return false; +} + /* PMU Version in DFR Register */ #define ARMV8_PMU_DFR_VER_NI 0 #define ARMV8_PMU_DFR_VER_V3P4 0x5 diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h index 97a312ba0840..fe385551edec 100644 --- a/arch/arm/include/asm/bugs.h +++ b/arch/arm/include/asm/bugs.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * arch/arm/include/asm/bugs.h - * * Copyright (C) 1995-2003 Russell King */ #ifndef __ASM_BUGS_H @@ -10,10 +8,8 @@ extern void check_writebuffer_bugs(void); #ifdef CONFIG_MMU -extern void check_bugs(void); extern void check_other_bugs(void); #else -#define check_bugs() do { } while (0) #define check_other_bugs() do { } while (0) #endif diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index 7c1c90d9f582..8c05a7f374d8 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -64,7 +64,7 @@ extern void secondary_startup_arm(void); extern int __cpu_disable(void); -extern void __cpu_die(unsigned int cpu); +static inline void __cpu_die(unsigned int cpu) { } extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 14c8dbbb7d2d..087bce6ec8e9 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> +#include <linux/cpu.h> #include <asm/bugs.h> #include <asm/proc-fns.h> @@ -11,7 +12,7 @@ void check_other_bugs(void) #endif } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { check_writebuffer_bugs(); check_other_bugs(); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 87f8d0e5e314..6756203e45f3 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -288,15 +288,11 @@ int __cpu_disable(void) } /* - * called on the thread which is asking for a CPU to be shutdown - - * waits until shutdown has completed, or it is timed out. + * called on the thread which is asking for a CPU to be shutdown after the + * shutdown completed. */ -void __cpu_die(unsigned int cpu) +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { - if (!cpu_wait_death(cpu, 5)) { - pr_err("CPU%u: cpu didn't die\n", cpu); - return; - } pr_debug("CPU%u: shutdown\n", cpu); clear_tasks_mm_cpumask(cpu); @@ -336,11 +332,11 @@ void __noreturn arch_cpu_idle_dead(void) flush_cache_louis(); /* - * Tell __cpu_die() that this CPU is now safe to dispose of. Once - * this returns, power and/or clocks can be removed at any point - * from this CPU and its cache by platform_cpu_kill(). + * Tell cpuhp_bp_sync_dead() that this CPU is now safe to dispose + * of. Once this returns, power and/or clocks can be removed at + * any point from this CPU and its cache by platform_cpu_kill(). */ - (void)cpu_report_death(); + cpuhp_ap_report_dead(); /* * Ensure that the cache lines associated with that completion are diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 343e1e1cae10..44911bce5389 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -222,6 +222,7 @@ config ARM64 select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_GENERIC_VDSO + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select IRQ_DOMAIN select IRQ_FORCED_THREADING select KASAN_VMALLOC if KASAN diff --git a/arch/arm64/boot/dts/qcom/sc7180-idp.dts b/arch/arm64/boot/dts/qcom/sc7180-idp.dts index 9f052270e090..299ef5dc225a 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-idp.dts +++ b/arch/arm64/boot/dts/qcom/sc7180-idp.dts @@ -393,6 +393,11 @@ qcom,spare-regs = <&tcsr_regs_2 0xb3e4>; }; +&scm { + /* TF-A firmware maps memory cached so mark dma-coherent to match. */ + dma-coherent; +}; + &sdhc_1 { status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index ca6920de7ea8..1472e7f10831 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -892,6 +892,11 @@ hp_i2c: &i2c9 { qcom,spare-regs = <&tcsr_regs_2 0xb3e4>; }; +&scm { + /* TF-A firmware maps memory cached so mark dma-coherent to match. */ + dma-coherent; +}; + &sdhc_1 { status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index f479cab8ab45..a65be760d1a7 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -369,7 +369,7 @@ }; firmware { - scm { + scm: scm { compatible = "qcom,scm-sc7180", "qcom,scm"; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi index f562e4d2b655..2e1cd219fc18 100644 --- a/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280-chrome-common.dtsi @@ -79,6 +79,11 @@ firmware-name = "ath11k/WCN6750/hw1.0/wpss.mdt"; }; +&scm { + /* TF-A firmware maps memory cached so mark dma-coherent to match. */ + dma-coherent; +}; + &wifi { status = "okay"; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 2fd1d3c0eb34..36f0bb9b3cbb 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -656,7 +656,7 @@ }; firmware { - scm { + scm: scm { compatible = "qcom,scm-sc7280", "qcom,scm"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi index dd228a256a32..2ae4bb7d5e62 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi @@ -97,6 +97,7 @@ l2: l2-cache { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index f69a38f42d2d..0a27fa5271f5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -37,7 +37,8 @@ vin-supply = <&vcc_io>; }; - vcc_host_5v: vcc-host-5v-regulator { + /* Common enable line for all of the rails mentioned in the labels */ + vcc_host_5v: vcc_host1_5v: vcc_otg_5v: vcc-host-5v-regulator { compatible = "regulator-fixed"; gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; @@ -48,17 +49,6 @@ vin-supply = <&vcc_sys>; }; - vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator { - compatible = "regulator-fixed"; - gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>; - pinctrl-names = "default"; - pinctrl-0 = <&usb20_host_drv>; - regulator-name = "vcc_host1_5v"; - regulator-always-on; - regulator-boot-on; - vin-supply = <&vcc_sys>; - }; - vcc_sys: vcc-sys { compatible = "regulator-fixed"; regulator-name = "vcc_sys"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 6d7a7bf72ac7..e729e7a22b23 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -103,6 +103,7 @@ l2: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts index 263ce40770dd..cddf6cd2fecb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts @@ -28,6 +28,16 @@ regulator-max-microvolt = <5000000>; vin-supply = <&vcc12v_dcin>; }; + + vcc_sd_pwr: vcc-sd-pwr-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_sd_pwr"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc3v3_sys>; + }; }; /* phy for pcie */ @@ -130,13 +140,7 @@ }; &sdmmc0 { - vmmc-supply = <&sdmmc_pwr>; - status = "okay"; -}; - -&sdmmc_pwr { - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; + vmmc-supply = <&vcc_sd_pwr>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi index 102e448bc026..31aa2b8efe39 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi @@ -104,16 +104,6 @@ regulator-max-microvolt = <3300000>; vin-supply = <&vcc5v0_sys>; }; - - sdmmc_pwr: sdmmc-pwr-regulator { - compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&sdmmc_pwr_h>; - regulator-name = "sdmmc_pwr"; - status = "disabled"; - }; }; &cpu0 { @@ -155,6 +145,19 @@ status = "disabled"; }; +&gpio0 { + nextrst-hog { + gpio-hog; + /* + * GPIO_ACTIVE_LOW + output-low here means that the pin is set + * to high, because output-low decides the value pre-inversion. + */ + gpios = <RK_PA5 GPIO_ACTIVE_LOW>; + line-name = "nEXTRST"; + output-low; + }; +}; + &gpu { mali-supply = <&vdd_gpu>; status = "okay"; @@ -538,12 +541,6 @@ rockchip,pins = <2 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; }; }; - - sdmmc-pwr { - sdmmc_pwr_h: sdmmc-pwr-h { - rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; - }; - }; }; &pmu_io_domains { diff --git a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5c.dts b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5c.dts index f70ca9f0470a..c718b8dbb9c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5c.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5c.dts @@ -106,7 +106,7 @@ rockchip-key { reset_button_pin: reset-button-pin { - rockchip,pins = <4 RK_PA0 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <0 RK_PB7 RK_FUNC_GPIO &pcfg_pull_up>; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts index 2a1118f15c29..b6ad8328c7eb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-nanopi-r5s.dts @@ -134,4 +134,3 @@ }; }; }; - diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index ba67b58f05b7..f1be76a54ceb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -94,9 +94,10 @@ power-domains = <&power RK3568_PD_PIPE>; reg = <0x3 0xc0400000 0x0 0x00400000>, <0x0 0xfe270000 0x0 0x00010000>, - <0x3 0x7f000000 0x0 0x01000000>; - ranges = <0x01000000 0x0 0x3ef00000 0x3 0x7ef00000 0x0 0x00100000>, - <0x02000000 0x0 0x00000000 0x3 0x40000000 0x0 0x3ef00000>; + <0x0 0xf2000000 0x0 0x00100000>; + ranges = <0x01000000 0x0 0xf2100000 0x0 0xf2100000 0x0 0x00100000>, + <0x02000000 0x0 0xf2200000 0x0 0xf2200000 0x0 0x01e00000>, + <0x03000000 0x0 0x40000000 0x3 0x40000000 0x0 0x40000000>; reg-names = "dbi", "apb", "config"; resets = <&cru SRST_PCIE30X1_POWERUP>; reset-names = "pipe"; @@ -146,9 +147,10 @@ power-domains = <&power RK3568_PD_PIPE>; reg = <0x3 0xc0800000 0x0 0x00400000>, <0x0 0xfe280000 0x0 0x00010000>, - <0x3 0xbf000000 0x0 0x01000000>; - ranges = <0x01000000 0x0 0x3ef00000 0x3 0xbef00000 0x0 0x00100000>, - <0x02000000 0x0 0x00000000 0x3 0x80000000 0x0 0x3ef00000>; + <0x0 0xf0000000 0x0 0x00100000>; + ranges = <0x01000000 0x0 0xf0100000 0x0 0xf0100000 0x0 0x00100000>, + <0x02000000 0x0 0xf0200000 0x0 0xf0200000 0x0 0x01e00000>, + <0x03000000 0x0 0x40000000 0x3 0x80000000 0x0 0x40000000>; reg-names = "dbi", "apb", "config"; resets = <&cru SRST_PCIE30X2_POWERUP>; reset-names = "pipe"; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index f62e0fd881a9..61680c7ac489 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -952,7 +952,7 @@ compatible = "rockchip,rk3568-pcie"; reg = <0x3 0xc0000000 0x0 0x00400000>, <0x0 0xfe260000 0x0 0x00010000>, - <0x3 0x3f000000 0x0 0x01000000>; + <0x0 0xf4000000 0x0 0x00100000>; reg-names = "dbi", "apb", "config"; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>, @@ -982,8 +982,9 @@ phys = <&combphy2 PHY_TYPE_PCIE>; phy-names = "pcie-phy"; power-domains = <&power RK3568_PD_PIPE>; - ranges = <0x01000000 0x0 0x3ef00000 0x3 0x3ef00000 0x0 0x00100000 - 0x02000000 0x0 0x00000000 0x3 0x00000000 0x0 0x3ef00000>; + ranges = <0x01000000 0x0 0xf4100000 0x0 0xf4100000 0x0 0x00100000>, + <0x02000000 0x0 0xf4200000 0x0 0xf4200000 0x0 0x01e00000>, + <0x03000000 0x0 0x40000000 0x3 0x00000000 0x0 0x40000000>; resets = <&cru SRST_PCIE20_POWERUP>; reset-names = "pipe"; #address-cells = <3>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index 657c019d27fa..a3124bd2e092 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi @@ -229,6 +229,7 @@ cache-line-size = <64>; cache-sets = <512>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -238,6 +239,7 @@ cache-line-size = <64>; cache-sets = <512>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -247,6 +249,7 @@ cache-line-size = <64>; cache-sets = <512>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -256,6 +259,7 @@ cache-line-size = <64>; cache-sets = <512>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -265,6 +269,7 @@ cache-line-size = <64>; cache-sets = <1024>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -274,6 +279,7 @@ cache-line-size = <64>; cache-sets = <1024>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -283,6 +289,7 @@ cache-line-size = <64>; cache-sets = <1024>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -292,6 +299,7 @@ cache-line-size = <64>; cache-sets = <1024>; cache-level = <2>; + cache-unified; next-level-cache = <&l3_cache>; }; @@ -301,6 +309,7 @@ cache-line-size = <64>; cache-sets = <4096>; cache-level = <3>; + cache-unified; }; }; diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c index a406454578f0..f1b8a04ee9f2 100644 --- a/arch/arm64/hyperv/mshyperv.c +++ b/arch/arm64/hyperv/mshyperv.c @@ -67,7 +67,7 @@ static int __init hyperv_init(void) if (ret) return ret; - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/hyperv_init:online", + ret = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "arm64/hyperv_init:online", hv_common_cpu_init, hv_common_cpu_die); if (ret < 0) { hv_common_free(); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7e7e19ef6993..9787503ff43f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -699,6 +699,8 @@ struct kvm_vcpu_arch { #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) /* Software step state is Active-pending */ #define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) +/* PMUSERENR for the guest EL0 is on physical CPU */ +#define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(6)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ @@ -1065,9 +1067,14 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u32 clr); +bool kvm_set_pmuserenr(u64 val); #else static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} +static inline bool kvm_set_pmuserenr(u64 val) +{ + return false; +} #endif void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index f2d26235bfb4..9b31e6d0da17 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -99,7 +99,7 @@ static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask) extern int __cpu_disable(void); -extern void __cpu_die(unsigned int cpu); +static inline void __cpu_die(unsigned int cpu) { } extern void __noreturn cpu_die(void); extern void __noreturn cpu_die_early(void); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d00d4cbb31b1..edd63894d61e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -332,17 +332,13 @@ static int op_cpu_kill(unsigned int cpu) } /* - * called on the thread which is asking for a CPU to be shutdown - - * waits until shutdown has completed, or it is timed out. + * Called on the thread which is asking for a CPU to be shutdown after the + * shutdown completed. */ -void __cpu_die(unsigned int cpu) +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { int err; - if (!cpu_wait_death(cpu, 5)) { - pr_crit("CPU%u: cpu didn't die\n", cpu); - return; - } pr_debug("CPU%u: shutdown\n", cpu); /* @@ -369,8 +365,8 @@ void __noreturn cpu_die(void) local_daif_mask(); - /* Tell __cpu_die() that this CPU is now safe to dispose of */ - (void)cpu_report_death(); + /* Tell cpuhp_bp_sync_dead() that this CPU is now safe to dispose of */ + cpuhp_ap_report_dead(); /* * Actually shutdown the CPU. This must never fail. The specific hotplug diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 5c15c58f90cc..4fe217efa218 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -82,8 +82,14 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) * EL1 instead of being trapped to EL2. */ if (kvm_arm_support_pmu_v3()) { + struct kvm_cpu_context *hctxt; + write_sysreg(0, pmselr_el0); + + hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; + ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0); write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); + vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); } vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2); @@ -106,8 +112,13 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) write_sysreg(vcpu->arch.mdcr_el2_host, mdcr_el2); write_sysreg(0, hstr_el2); - if (kvm_arm_support_pmu_v3()) - write_sysreg(0, pmuserenr_el0); + if (kvm_arm_support_pmu_v3()) { + struct kvm_cpu_context *hctxt; + + hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; + write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); + vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU); + } if (cpus_have_final_cap(ARM64_SME)) { sysreg_clear_set_s(SYS_HFGRTR_EL2, 0, diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7a1aa511e7da..b37e7c96efea 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -92,14 +92,28 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) } NOKPROBE_SYMBOL(__deactivate_traps); +/* + * Disable IRQs in {activate,deactivate}_traps_vhe_{load,put}() to + * prevent a race condition between context switching of PMUSERENR_EL0 + * in __{activate,deactivate}_traps_common() and IPIs that attempts to + * update PMUSERENR_EL0. See also kvm_set_pmuserenr(). + */ void activate_traps_vhe_load(struct kvm_vcpu *vcpu) { + unsigned long flags; + + local_irq_save(flags); __activate_traps_common(vcpu); + local_irq_restore(flags); } void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu) { + unsigned long flags; + + local_irq_save(flags); __deactivate_traps_common(vcpu); + local_irq_restore(flags); } static const exit_handler_fn hyp_exit_handlers[] = { diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 491ca7eb2a4c..560650972478 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -700,7 +700,25 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void) mutex_lock(&arm_pmus_lock); - cpu = smp_processor_id(); + /* + * It is safe to use a stale cpu to iterate the list of PMUs so long as + * the same value is used for the entirety of the loop. Given this, and + * the fact that no percpu data is used for the lookup there is no need + * to disable preemption. + * + * It is still necessary to get a valid cpu, though, to probe for the + * default PMU instance as userspace is not required to specify a PMU + * type. In order to uphold the preexisting behavior KVM selects the + * PMU instance for the core where the first call to the + * KVM_ARM_VCPU_PMU_V3_CTRL attribute group occurs. A dependent use case + * would be a user with disdain of all things big.LITTLE that affines + * the VMM to a particular cluster of cores. + * + * In any case, userspace should just do the sane thing and use the UAPI + * to select a PMU type directly. But, be wary of the baggage being + * carried here. + */ + cpu = raw_smp_processor_id(); list_for_each_entry(entry, &arm_pmus, entry) { tmp = entry->arm_pmu; diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 7887133d15f0..121f1a14c829 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -209,3 +209,30 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest); } + +/* + * With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU + * where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched + * to the value for the guest on vcpu_load(). The value for the host EL0 + * will be restored on vcpu_put(), before returning to userspace. + * This isn't necessary for nVHE, as the register is context switched for + * every guest enter/exit. + * + * Return true if KVM takes care of the register. Otherwise return false. + */ +bool kvm_set_pmuserenr(u64 val) +{ + struct kvm_cpu_context *hctxt; + struct kvm_vcpu *vcpu; + + if (!kvm_arm_support_pmu_v3() || !has_vhe()) + return false; + + vcpu = kvm_get_running_vcpu(); + if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU)) + return false; + + hctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; + ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val; + return true; +} diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 6eafc2c45cfc..c8c3cb812783 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -446,6 +446,7 @@ int vgic_lazy_init(struct kvm *kvm) int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + enum vgic_type type; gpa_t dist_base; int ret = 0; @@ -460,10 +461,13 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (!irqchip_in_kernel(kvm)) goto out; - if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { ret = vgic_v2_map_resources(kvm); - else + type = VGIC_V2; + } else { ret = vgic_v3_map_resources(kvm); + type = VGIC_V3; + } if (ret) { __kvm_vgic_destroy(kvm); @@ -473,8 +477,7 @@ int kvm_vgic_map_resources(struct kvm *kvm) dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); - ret = vgic_register_dist_iodev(kvm, dist_base, - kvm_vgic_global_state.type); + ret = vgic_register_dist_iodev(kvm, dist_base, type); if (ret) { kvm_err("Unable to register VGIC dist MMIO regions\n"); kvm_vgic_destroy(kvm); diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 4df1f8c9d170..95f1e9bfd1c7 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -96,6 +96,7 @@ config CSKY select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES select OF diff --git a/arch/csky/include/asm/smp.h b/arch/csky/include/asm/smp.h index 668b79ce29ea..d3db334f3196 100644 --- a/arch/csky/include/asm/smp.h +++ b/arch/csky/include/asm/smp.h @@ -23,7 +23,7 @@ void __init set_send_ipi(void (*func)(const struct cpumask *mask), int irq); int __cpu_disable(void); -void __cpu_die(unsigned int cpu); +static inline void __cpu_die(unsigned int cpu) { } #endif /* CONFIG_SMP */ diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b12e2c3c387f..8e42352cbf12 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -291,12 +291,8 @@ int __cpu_disable(void) return 0; } -void __cpu_die(unsigned int cpu) +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { - if (!cpu_wait_death(cpu, 5)) { - pr_crit("CPU%u: shutdown failed\n", cpu); - return; - } pr_notice("CPU%u: shutdown\n", cpu); } @@ -304,7 +300,7 @@ void __noreturn arch_cpu_idle_dead(void) { idle_task_exit(); - cpu_report_death(); + cpuhp_ap_report_dead(); while (!secondary_stack) arch_cpu_idle(); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 21fa63ce5ffc..2cd93e6bf0fe 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -9,6 +9,7 @@ menu "Processor type and features" config IA64 bool select ARCH_BINFMT_ELF_EXTRA_PHDRS + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER diff --git a/arch/ia64/include/asm/bugs.h b/arch/ia64/include/asm/bugs.h deleted file mode 100644 index 0d6b9bded56c..000000000000 --- a/arch/ia64/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - * - * Based on <asm-alpha/bugs.h>. - * - * Modified 1998, 1999, 2003 - * David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co. - */ -#ifndef _ASM_IA64_BUGS_H -#define _ASM_IA64_BUGS_H - -#include <asm/processor.h> - -extern void check_bugs (void); - -#endif /* _ASM_IA64_BUGS_H */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index c05728044272..5a55ac82c13a 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -627,7 +627,7 @@ setup_arch (char **cmdline_p) * is physical disk 1 partition 1 and the Linux root disk is * physical disk 1 partition 2. */ - ROOT_DEV = Root_SDA2; /* default to second partition on first drive */ + ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2); if (is_uv_system()) uv_setup(cmdline_p); @@ -1067,8 +1067,7 @@ cpu_init (void) } } -void __init -check_bugs (void) +void __init arch_cpu_finalize_init(void) { ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles, (unsigned long) __end___mckinley_e9_bundles); diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index d38b066fc931..cbab4f9ca15c 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -10,6 +10,7 @@ config LOONGARCH select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL diff --git a/arch/loongarch/include/asm/bugs.h b/arch/loongarch/include/asm/bugs.h deleted file mode 100644 index 98396535163b..000000000000 --- a/arch/loongarch/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _ASM_BUGS_H -#define _ASM_BUGS_H - -#include <asm/cpu.h> -#include <asm/cpu-info.h> - -extern void check_bugs(void); - -#endif /* _ASM_BUGS_H */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index b3323ab5b78d..35e8a52fea11 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -1496,7 +1496,7 @@ __BUILD_CSR_OP(tlbidx) #define write_fcsr(dest, val) \ do { \ __asm__ __volatile__( \ - " movgr2fcsr %0, "__stringify(dest)" \n" \ + " movgr2fcsr "__stringify(dest)", %0 \n" \ : : "r" (val)); \ } while (0) diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 8b98d22a145b..de46a6b1e9f1 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -22,12 +22,14 @@ #define _PAGE_PFN_SHIFT 12 #define _PAGE_SWP_EXCLUSIVE_SHIFT 23 #define _PAGE_PFN_END_SHIFT 48 +#define _PAGE_PRESENT_INVALID_SHIFT 60 #define _PAGE_NO_READ_SHIFT 61 #define _PAGE_NO_EXEC_SHIFT 62 #define _PAGE_RPLV_SHIFT 63 /* Used by software */ #define _PAGE_PRESENT (_ULCAST_(1) << _PAGE_PRESENT_SHIFT) +#define _PAGE_PRESENT_INVALID (_ULCAST_(1) << _PAGE_PRESENT_INVALID_SHIFT) #define _PAGE_WRITE (_ULCAST_(1) << _PAGE_WRITE_SHIFT) #define _PAGE_ACCESSED (_ULCAST_(1) << _PAGE_ACCESSED_SHIFT) #define _PAGE_MODIFIED (_ULCAST_(1) << _PAGE_MODIFIED_SHIFT) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index d28fb9dbec59..9a9f9ff9b709 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -213,7 +213,7 @@ static inline int pmd_bad(pmd_t pmd) static inline int pmd_present(pmd_t pmd) { if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) - return !!(pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE)); + return !!(pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PRESENT_INVALID)); return pmd_val(pmd) != (unsigned long)invalid_pte_table; } @@ -558,6 +558,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) static inline pmd_t pmd_mkinvalid(pmd_t pmd) { + pmd_val(pmd) |= _PAGE_PRESENT_INVALID; pmd_val(pmd) &= ~(_PAGE_PRESENT | _PAGE_VALID | _PAGE_DIRTY | _PAGE_PROTNONE); return pmd; diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index 2406c95b34cc..021b59c248fa 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -396,6 +396,8 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) alignment_mask = 0x7; + else + alignment_mask = 0x3; offset = hw->address & alignment_mask; hw->address &= ~alignment_mask; diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index ff28f99b47d7..0491bf453cd4 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -271,7 +271,7 @@ static void loongarch_pmu_enable_event(struct hw_perf_event *evt, int idx) WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters); /* Make sure interrupt enabled. */ - cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) | + cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base) | (evt->config_base & M_PERFCTL_CONFIG_MASK) | CSR_PERFCTRL_IE; cpu = (event->cpu >= 0) ? event->cpu : smp_processor_id(); @@ -594,7 +594,7 @@ static struct pmu pmu = { static unsigned int loongarch_pmu_perf_event_encode(const struct loongarch_perf_event *pev) { - return (pev->event_id & 0xff); + return M_PERFCTL_EVENT(pev->event_id); } static const struct loongarch_perf_event *loongarch_pmu_map_general_event(int idx) @@ -849,7 +849,7 @@ static void resume_local_counters(void) static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config) { - raw_event.event_id = config & 0xff; + raw_event.event_id = M_PERFCTL_EVENT(config); return &raw_event; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 4444b13418f0..78a00359bde3 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -12,6 +12,7 @@ */ #include <linux/init.h> #include <linux/acpi.h> +#include <linux/cpu.h> #include <linux/dmi.h> #include <linux/efi.h> #include <linux/export.h> @@ -37,7 +38,6 @@ #include <asm/addrspace.h> #include <asm/alternative.h> #include <asm/bootinfo.h> -#include <asm/bugs.h> #include <asm/cache.h> #include <asm/cpu.h> #include <asm/dma.h> @@ -87,7 +87,7 @@ const char *get_system_type(void) return "generic-loongson-machine"; } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { alternative_instructions(); } diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c index bdff825d29ef..85fae3d2d71a 100644 --- a/arch/loongarch/kernel/unaligned.c +++ b/arch/loongarch/kernel/unaligned.c @@ -485,7 +485,7 @@ static int __init debugfs_unaligned(void) struct dentry *d; d = debugfs_create_dir("loongarch", NULL); - if (!d) + if (IS_ERR_OR_NULL(d)) return -ENOMEM; debugfs_create_u32("unaligned_instructions_user", diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 40198a1ebe27..dc792b321f1e 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -4,6 +4,7 @@ config M68K default y select ARCH_32BIT_OFF_T select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT if MMU select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h deleted file mode 100644 index 745530651e0b..000000000000 --- a/arch/m68k/include/asm/bugs.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-m68k/bugs.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#ifdef CONFIG_MMU -extern void check_bugs(void); /* in arch/m68k/kernel/setup.c */ -#else -static void check_bugs(void) -{ -} -#endif diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index fbff1cea62ca..6f1ae01f322c 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/cpu.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/delay.h> @@ -504,7 +505,7 @@ static int __init proc_hardware_init(void) module_init(proc_hardware_init); #endif -void check_bugs(void) +void __init arch_cpu_finalize_init(void) { #if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU) if (m68k_fputype == 0) { diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 675a8660cb85..ada18f3be229 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,6 +4,7 @@ config MIPS default y select ARCH_32BIT_OFF_T if !64BIT select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER if !CC_IS_CLANG || CLANG_VERSION >= 140000 select ARCH_HAS_DEBUG_VIRTUAL if !64BIT select ARCH_HAS_FORTIFY_SOURCE @@ -2286,6 +2287,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPS_PM if HOTPLUG_CPU select SMP + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU select SYS_SUPPORTS_SCHED_SMT if CPU_MIPSR6 diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 4212584e6efa..33c09688210f 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -345,6 +345,7 @@ void play_dead(void) int cpu = cpu_number_map(cvmx_get_core_num()); idle_task_exit(); + cpuhp_ap_report_dead(); octeon_processor_boot = 0xff; per_cpu(cpu_state, cpu) = CPU_DEAD; diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index 653f78f3a685..84be74afcb9a 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -1,17 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * This is included by init/main.c to check for architecture-dependent bugs. - * * Copyright (C) 2007 Maciej W. Rozycki - * - * Needs: - * void check_bugs(void); */ #ifndef _ASM_BUGS_H #define _ASM_BUGS_H #include <linux/bug.h> -#include <linux/delay.h> #include <linux/smp.h> #include <asm/cpu.h> @@ -24,17 +18,6 @@ extern void check_bugs64_early(void); extern void check_bugs32(void); extern void check_bugs64(void); -static inline void __init check_bugs(void) -{ - unsigned int cpu = smp_processor_id(); - - cpu_data[cpu].udelay_val = loops_per_jiffy; - check_bugs32(); - - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64(); -} - static inline int r4k_daddiu_bug(void) { if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) diff --git a/arch/mips/include/asm/mach-loongson32/loongson1.h b/arch/mips/include/asm/mach-loongson32/loongson1.h index eb3ddbec1752..d8f9dec0ecc3 100644 --- a/arch/mips/include/asm/mach-loongson32/loongson1.h +++ b/arch/mips/include/asm/mach-loongson32/loongson1.h @@ -47,7 +47,6 @@ #include <regs-clk.h> #include <regs-mux.h> -#include <regs-pwm.h> #include <regs-rtc.h> #include <regs-wdt.h> diff --git a/arch/mips/include/asm/mach-loongson32/regs-pwm.h b/arch/mips/include/asm/mach-loongson32/regs-pwm.h deleted file mode 100644 index ec870c82d492..000000000000 --- a/arch/mips/include/asm/mach-loongson32/regs-pwm.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (c) 2014 Zhang, Keguang <keguang.zhang@gmail.com> - * - * Loongson 1 PWM Register Definitions. - */ - -#ifndef __ASM_MACH_LOONGSON32_REGS_PWM_H -#define __ASM_MACH_LOONGSON32_REGS_PWM_H - -/* Loongson 1 PWM Timer Register Definitions */ -#define PWM_CNT 0x0 -#define PWM_HRC 0x4 -#define PWM_LRC 0x8 -#define PWM_CTRL 0xc - -/* PWM Control Register Bits */ -#define CNT_RST BIT(7) -#define INT_SR BIT(6) -#define INT_EN BIT(5) -#define PWM_SINGLE BIT(4) -#define PWM_OE BIT(3) -#define CNT_EN BIT(0) - -#endif /* __ASM_MACH_LOONGSON32_REGS_PWM_H */ diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 0145bbfb5efb..5719ff49eff1 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -33,6 +33,7 @@ struct plat_smp_ops { #ifdef CONFIG_HOTPLUG_CPU int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); + void (*cleanup_dead_cpu)(unsigned cpu); #endif #ifdef CONFIG_KEXEC void (*kexec_nonboot_cpu)(void); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index c0e65135481b..cb871eb784a7 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -11,6 +11,8 @@ * Copyright (C) 2000, 2001, 2002, 2007 Maciej W. Rozycki */ #include <linux/init.h> +#include <linux/cpu.h> +#include <linux/delay.h> #include <linux/ioport.h> #include <linux/export.h> #include <linux/screen_info.h> @@ -841,3 +843,14 @@ static int __init setnocoherentio(char *str) } early_param("nocoherentio", setnocoherentio); #endif + +void __init arch_cpu_finalize_init(void) +{ + unsigned int cpu = smp_processor_id(); + + cpu_data[cpu].udelay_val = loops_per_jiffy; + check_bugs32(); + + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64(); +} diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 15466d4cf4a0..c074ecce3fbf 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -392,6 +392,7 @@ static void bmips_cpu_die(unsigned int cpu) void __ref play_dead(void) { idle_task_exit(); + cpuhp_ap_report_dead(); /* flush data cache */ _dma_cache_wback_inv(0, ~0); diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 62f677b2306f..d7fdbec232da 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -503,8 +503,7 @@ void play_dead(void) } } - /* This CPU has chosen its way out */ - (void)cpu_report_death(); + cpuhp_ap_report_dead(); cps_shutdown_this_cpu(cpu_death); @@ -527,7 +526,9 @@ static void wait_for_sibling_halt(void *ptr_cpu) } while (!(halted & TCHALT_H)); } -static void cps_cpu_die(unsigned int cpu) +static void cps_cpu_die(unsigned int cpu) { } + +static void cps_cleanup_dead_cpu(unsigned cpu) { unsigned core = cpu_core(&cpu_data[cpu]); unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); @@ -535,12 +536,6 @@ static void cps_cpu_die(unsigned int cpu) unsigned stat; int err; - /* Wait for the cpu to choose its way out */ - if (!cpu_wait_death(cpu, 5)) { - pr_err("CPU%u: didn't offline\n", cpu); - return; - } - /* * Now wait for the CPU to actually offline. Without doing this that * offlining may race with one or more of: @@ -624,6 +619,7 @@ static const struct plat_smp_ops cps_smp_ops = { #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = cps_cpu_disable, .cpu_die = cps_cpu_die, + .cleanup_dead_cpu = cps_cleanup_dead_cpu, #endif #ifdef CONFIG_KEXEC .kexec_nonboot_cpu = cps_kexec_nonboot_cpu, diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 1d93b85271ba..90c71d800b59 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -690,6 +690,14 @@ void flush_tlb_one(unsigned long vaddr) EXPORT_SYMBOL(flush_tlb_page); EXPORT_SYMBOL(flush_tlb_one); +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ + if (mp_ops->cleanup_dead_cpu) + mp_ops->cleanup_dead_cpu(cpu); +} +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static void tick_broadcast_callee(void *info) diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig index 2ef9da0016df..a7c500959577 100644 --- a/arch/mips/loongson32/Kconfig +++ b/arch/mips/loongson32/Kconfig @@ -35,41 +35,4 @@ config LOONGSON1_LS1C select COMMON_CLK endchoice -menuconfig CEVT_CSRC_LS1X - bool "Use PWM Timer for clockevent/clocksource" - select MIPS_EXTERNAL_TIMER - depends on CPU_LOONGSON32 - help - This option changes the default clockevent/clocksource to PWM Timer, - and is required by Loongson1 CPUFreq support. - - If unsure, say N. - -choice - prompt "Select clockevent/clocksource" - depends on CEVT_CSRC_LS1X - default TIMER_USE_PWM0 - -config TIMER_USE_PWM0 - bool "Use PWM Timer 0" - help - Use PWM Timer 0 as the default clockevent/clocksourcer. - -config TIMER_USE_PWM1 - bool "Use PWM Timer 1" - help - Use PWM Timer 1 as the default clockevent/clocksourcer. - -config TIMER_USE_PWM2 - bool "Use PWM Timer 2" - help - Use PWM Timer 2 as the default clockevent/clocksourcer. - -config TIMER_USE_PWM3 - bool "Use PWM Timer 3" - help - Use PWM Timer 3 as the default clockevent/clocksourcer. - -endchoice - endif # MACH_LOONGSON32 diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c index 965c04aa56fd..74ad2b17918d 100644 --- a/arch/mips/loongson32/common/time.c +++ b/arch/mips/loongson32/common/time.c @@ -5,208 +5,8 @@ #include <linux/clk.h> #include <linux/of_clk.h> -#include <linux/interrupt.h> -#include <linux/sizes.h> #include <asm/time.h> -#include <loongson1.h> -#include <platform.h> - -#ifdef CONFIG_CEVT_CSRC_LS1X - -#if defined(CONFIG_TIMER_USE_PWM1) -#define LS1X_TIMER_BASE LS1X_PWM1_BASE -#define LS1X_TIMER_IRQ LS1X_PWM1_IRQ - -#elif defined(CONFIG_TIMER_USE_PWM2) -#define LS1X_TIMER_BASE LS1X_PWM2_BASE -#define LS1X_TIMER_IRQ LS1X_PWM2_IRQ - -#elif defined(CONFIG_TIMER_USE_PWM3) -#define LS1X_TIMER_BASE LS1X_PWM3_BASE -#define LS1X_TIMER_IRQ LS1X_PWM3_IRQ - -#else -#define LS1X_TIMER_BASE LS1X_PWM0_BASE -#define LS1X_TIMER_IRQ LS1X_PWM0_IRQ -#endif - -DEFINE_RAW_SPINLOCK(ls1x_timer_lock); - -static void __iomem *timer_reg_base; -static uint32_t ls1x_jiffies_per_tick; - -static inline void ls1x_pwmtimer_set_period(uint32_t period) -{ - __raw_writel(period, timer_reg_base + PWM_HRC); - __raw_writel(period, timer_reg_base + PWM_LRC); -} - -static inline void ls1x_pwmtimer_restart(void) -{ - __raw_writel(0x0, timer_reg_base + PWM_CNT); - __raw_writel(INT_EN | CNT_EN, timer_reg_base + PWM_CTRL); -} - -void __init ls1x_pwmtimer_init(void) -{ - timer_reg_base = ioremap(LS1X_TIMER_BASE, SZ_16); - if (!timer_reg_base) - panic("Failed to remap timer registers"); - - ls1x_jiffies_per_tick = DIV_ROUND_CLOSEST(mips_hpt_frequency, HZ); - - ls1x_pwmtimer_set_period(ls1x_jiffies_per_tick); - ls1x_pwmtimer_restart(); -} - -static u64 ls1x_clocksource_read(struct clocksource *cs) -{ - unsigned long flags; - int count; - u32 jifs; - static int old_count; - static u32 old_jifs; - - raw_spin_lock_irqsave(&ls1x_timer_lock, flags); - /* - * Although our caller may have the read side of xtime_lock, - * this is now a seqlock, and we are cheating in this routine - * by having side effects on state that we cannot undo if - * there is a collision on the seqlock and our caller has to - * retry. (Namely, old_jifs and old_count.) So we must treat - * jiffies as volatile despite the lock. We read jiffies - * before latching the timer count to guarantee that although - * the jiffies value might be older than the count (that is, - * the counter may underflow between the last point where - * jiffies was incremented and the point where we latch the - * count), it cannot be newer. - */ - jifs = jiffies; - /* read the count */ - count = __raw_readl(timer_reg_base + PWM_CNT); - - /* - * It's possible for count to appear to go the wrong way for this - * reason: - * - * The timer counter underflows, but we haven't handled the resulting - * interrupt and incremented jiffies yet. - * - * Previous attempts to handle these cases intelligently were buggy, so - * we just do the simple thing now. - */ - if (count < old_count && jifs == old_jifs) - count = old_count; - - old_count = count; - old_jifs = jifs; - - raw_spin_unlock_irqrestore(&ls1x_timer_lock, flags); - - return (u64) (jifs * ls1x_jiffies_per_tick) + count; -} - -static struct clocksource ls1x_clocksource = { - .name = "ls1x-pwmtimer", - .read = ls1x_clocksource_read, - .mask = CLOCKSOURCE_MASK(24), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - -static irqreturn_t ls1x_clockevent_isr(int irq, void *devid) -{ - struct clock_event_device *cd = devid; - - ls1x_pwmtimer_restart(); - cd->event_handler(cd); - - return IRQ_HANDLED; -} - -static int ls1x_clockevent_set_state_periodic(struct clock_event_device *cd) -{ - raw_spin_lock(&ls1x_timer_lock); - ls1x_pwmtimer_set_period(ls1x_jiffies_per_tick); - ls1x_pwmtimer_restart(); - __raw_writel(INT_EN | CNT_EN, timer_reg_base + PWM_CTRL); - raw_spin_unlock(&ls1x_timer_lock); - - return 0; -} - -static int ls1x_clockevent_tick_resume(struct clock_event_device *cd) -{ - raw_spin_lock(&ls1x_timer_lock); - __raw_writel(INT_EN | CNT_EN, timer_reg_base + PWM_CTRL); - raw_spin_unlock(&ls1x_timer_lock); - - return 0; -} - -static int ls1x_clockevent_set_state_shutdown(struct clock_event_device *cd) -{ - raw_spin_lock(&ls1x_timer_lock); - __raw_writel(__raw_readl(timer_reg_base + PWM_CTRL) & ~CNT_EN, - timer_reg_base + PWM_CTRL); - raw_spin_unlock(&ls1x_timer_lock); - - return 0; -} - -static int ls1x_clockevent_set_next(unsigned long evt, - struct clock_event_device *cd) -{ - raw_spin_lock(&ls1x_timer_lock); - ls1x_pwmtimer_set_period(evt); - ls1x_pwmtimer_restart(); - raw_spin_unlock(&ls1x_timer_lock); - - return 0; -} - -static struct clock_event_device ls1x_clockevent = { - .name = "ls1x-pwmtimer", - .features = CLOCK_EVT_FEAT_PERIODIC, - .rating = 300, - .irq = LS1X_TIMER_IRQ, - .set_next_event = ls1x_clockevent_set_next, - .set_state_shutdown = ls1x_clockevent_set_state_shutdown, - .set_state_periodic = ls1x_clockevent_set_state_periodic, - .set_state_oneshot = ls1x_clockevent_set_state_shutdown, - .tick_resume = ls1x_clockevent_tick_resume, -}; - -static void __init ls1x_time_init(void) -{ - struct clock_event_device *cd = &ls1x_clockevent; - int ret; - - if (!mips_hpt_frequency) - panic("Invalid timer clock rate"); - - ls1x_pwmtimer_init(); - - clockevent_set_clock(cd, mips_hpt_frequency); - cd->max_delta_ns = clockevent_delta2ns(0xffffff, cd); - cd->max_delta_ticks = 0xffffff; - cd->min_delta_ns = clockevent_delta2ns(0x000300, cd); - cd->min_delta_ticks = 0x000300; - cd->cpumask = cpumask_of(smp_processor_id()); - clockevents_register_device(cd); - - ls1x_clocksource.rating = 200 + mips_hpt_frequency / 10000000; - ret = clocksource_register_hz(&ls1x_clocksource, mips_hpt_frequency); - if (ret) - panic(KERN_ERR "Failed to register clocksource: %d\n", ret); - - if (request_irq(LS1X_TIMER_IRQ, ls1x_clockevent_isr, - IRQF_PERCPU | IRQF_TIMER, "ls1x-pwmtimer", - &ls1x_clockevent)) - pr_err("Failed to register ls1x-pwmtimer interrupt\n"); -} -#endif /* CONFIG_CEVT_CSRC_LS1X */ - void __init plat_time_init(void) { struct clk *clk = NULL; @@ -214,20 +14,10 @@ void __init plat_time_init(void) /* initialize LS1X clocks */ of_clk_init(NULL); -#ifdef CONFIG_CEVT_CSRC_LS1X - /* setup LS1X PWM timer */ - clk = clk_get(NULL, "ls1x-pwmtimer"); - if (IS_ERR(clk)) - panic("unable to get timer clock, err=%ld", PTR_ERR(clk)); - - mips_hpt_frequency = clk_get_rate(clk); - ls1x_time_init(); -#else /* setup mips r4k timer */ clk = clk_get(NULL, "cpu_clk"); if (IS_ERR(clk)) panic("unable to get cpu clock, err=%ld", PTR_ERR(clk)); mips_hpt_frequency = clk_get_rate(clk) / 2; -#endif /* CONFIG_CEVT_CSRC_LS1X */ } diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index b0e8bb9fa036..cdecd7af11a6 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -775,6 +775,7 @@ void play_dead(void) void (*play_dead_at_ckseg1)(int *); idle_task_exit(); + cpuhp_ap_report_dead(); prid_imp = read_c0_prid() & PRID_IMP_MASK; prid_rev = read_c0_prid() & PRID_REV_MASK; diff --git a/arch/nios2/boot/dts/10m50_devboard.dts b/arch/nios2/boot/dts/10m50_devboard.dts index 56339bef3247..0e7e5b0dd685 100644 --- a/arch/nios2/boot/dts/10m50_devboard.dts +++ b/arch/nios2/boot/dts/10m50_devboard.dts @@ -97,7 +97,7 @@ rx-fifo-depth = <8192>; tx-fifo-depth = <8192>; address-bits = <48>; - max-frame-size = <1518>; + max-frame-size = <1500>; local-mac-address = [00 00 00 00 00 00]; altr,has-supplementary-unicast; altr,enable-sup-addr = <1>; diff --git a/arch/nios2/boot/dts/3c120_devboard.dts b/arch/nios2/boot/dts/3c120_devboard.dts index d10fb81686c7..3ee316906379 100644 --- a/arch/nios2/boot/dts/3c120_devboard.dts +++ b/arch/nios2/boot/dts/3c120_devboard.dts @@ -106,7 +106,7 @@ interrupt-names = "rx_irq", "tx_irq"; rx-fifo-depth = <8192>; tx-fifo-depth = <8192>; - max-frame-size = <1518>; + max-frame-size = <1500>; local-mac-address = [ 00 00 00 00 00 00 ]; phy-mode = "rgmii-id"; phy-handle = <&phy0>; diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index ecd1657bb2ce..ce6bb8e74271 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -28,10 +28,10 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, extern pgd_t *pgd_alloc(struct mm_struct *mm); -#define __pte_free_tlb(tlb, pte, addr) \ - do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), (pte)); \ +#define __pte_free_tlb(tlb, pte, addr) \ + do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \ } while (0) #endif /* _ASM_NIOS2_PGALLOC_H */ diff --git a/arch/nios2/kernel/cpuinfo.c b/arch/nios2/kernel/cpuinfo.c index 203870c4b86d..338849c430a5 100644 --- a/arch/nios2/kernel/cpuinfo.c +++ b/arch/nios2/kernel/cpuinfo.c @@ -47,7 +47,7 @@ void __init setup_cpuinfo(void) str = of_get_property(cpu, "altr,implementation", &len); if (str) - strlcpy(cpuinfo.cpu_impl, str, sizeof(cpuinfo.cpu_impl)); + strscpy(cpuinfo.cpu_impl, str, sizeof(cpuinfo.cpu_impl)); else strcpy(cpuinfo.cpu_impl, "<unknown>"); diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index 40bc8fb75e0b..8582ed965844 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -121,7 +121,7 @@ asmlinkage void __init nios2_boot_init(unsigned r4, unsigned r5, unsigned r6, dtb_passed = r6; if (r7) - strlcpy(cmdline_passed, (char *)r7, COMMAND_LINE_SIZE); + strscpy(cmdline_passed, (char *)r7, COMMAND_LINE_SIZE); } #endif @@ -129,10 +129,10 @@ asmlinkage void __init nios2_boot_init(unsigned r4, unsigned r5, unsigned r6, #ifndef CONFIG_CMDLINE_FORCE if (cmdline_passed[0]) - strlcpy(boot_command_line, cmdline_passed, COMMAND_LINE_SIZE); + strscpy(boot_command_line, cmdline_passed, COMMAND_LINE_SIZE); #ifdef CONFIG_NIOS2_CMDLINE_IGNORE_DTB else - strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); #endif #endif diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 967bde65dd0e..c0b4b1c253d1 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -57,6 +57,7 @@ config PARISC select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_REGS_AND_STACK_ACCESS_API + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select GENERIC_SCHED_CLOCK select GENERIC_IRQ_MIGRATION if SMP select HAVE_UNSTABLE_SCHED_CLOCK if SMP diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 0f0d4a496fef..75677b526b2b 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -90,10 +90,6 @@ #include <asm/asmregs.h> #include <asm/psw.h> - sp = 30 - gp = 27 - ipsw = 22 - /* * We provide two versions of each macro to convert from physical * to virtual and vice versa. The "_r1" versions take one argument diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h deleted file mode 100644 index 0a7f9db6bd1c..000000000000 --- a/arch/parisc/include/asm/bugs.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/asm-parisc/bugs.h - * - * Copyright (C) 1999 Mike Shaver - */ - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -#include <asm/processor.h> - -static inline void check_bugs(void) -{ -// identify_cpu(&boot_cpu_data); -} diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index e715df5385d6..5656395c95ee 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -472,9 +472,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define pte_same(A,B) (pte_val(A) == pte_val(B)) -struct seq_file; -extern void arch_report_meminfo(struct seq_file *m); - #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 24411ab79c30..abdbf038d643 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -171,8 +171,8 @@ void __noreturn arch_cpu_idle_dead(void) local_irq_disable(); - /* Tell __cpu_die() that this CPU is now safe to dispose of. */ - (void)cpu_report_death(); + /* Tell the core that this CPU is now safe to dispose of. */ + cpuhp_ap_report_dead(); /* Ensure that the cache lines are written out. */ flush_cache_all_local(); diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index b7fc859fa87d..6b6eaa485946 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -500,11 +500,10 @@ int __cpu_disable(void) void __cpu_die(unsigned int cpu) { pdc_cpu_rendezvous_lock(); +} - if (!cpu_wait_death(cpu, 5)) { - pr_crit("CPU%u: cpu didn't die\n", cpu); - return; - } +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ pr_info("CPU%u: is shutting down\n", cpu); /* set task's state to interruptible sleep */ diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h deleted file mode 100644 index 01b8f6ca4dbb..000000000000 --- a/arch/powerpc/include/asm/bugs.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _ASM_POWERPC_BUGS_H -#define _ASM_POWERPC_BUGS_H - -/* - */ - -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* _ASM_POWERPC_BUGS_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 9972626ddaf6..6a88bfdaa69b 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -165,9 +165,6 @@ static inline bool is_ioremap_addr(const void *x) return addr >= IOREMAP_BASE && addr < IOREMAP_END; } - -struct seq_file; -void arch_report_meminfo(struct seq_file *m); #endif /* CONFIG_PPC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index ce804b7bf84e..0bd4866d9824 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -795,12 +795,20 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush) goto out; if (current->active_mm == mm) { + unsigned long flags; + WARN_ON_ONCE(current->mm != NULL); - /* Is a kernel thread and is using mm as the lazy tlb */ + /* + * It is a kernel thread and is using mm as the lazy tlb, so + * switch it to init_mm. This is not always called from IPI + * (e.g., flush_type_needed), so must disable irqs. + */ + local_irq_save(flags); mmgrab_lazy_tlb(&init_mm); current->active_mm = &init_mm; switch_mm_irqs_off(mm, &init_mm, current); mmdrop_lazy_tlb(mm); + local_irq_restore(flags); } /* diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 193cc9c39422..0c41f4b005bc 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -76,7 +76,8 @@ int pmac_newworld; static int current_root_goodness = -1; -#define DEFAULT_ROOT_DEVICE Root_SDA1 /* sda1 - slightly silly choice */ +/* sda1 - slightly silly choice */ +#define DEFAULT_ROOT_DEVICE MKDEV(SCSI_DISK0_MAJOR, 1) sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN; EXPORT_SYMBOL(sys_ctrler); diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 6f5e2727963c..78473d69cd2b 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -5,6 +5,11 @@ KCSAN_SANITIZE := n targets += trampoline_$(BITS).o purgatory.ro +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined $(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 5966ad97c30c..c69572fbe613 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -123,6 +123,7 @@ config RISCV select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS + select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select IRQ_DOMAIN select IRQ_FORCED_THREADING select KASAN_VMALLOC if KASAN diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index c4b77017ec58..0d555847cde6 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -70,7 +70,7 @@ asmlinkage void smp_callin(void); #if defined CONFIG_HOTPLUG_CPU int __cpu_disable(void); -void __cpu_die(unsigned int cpu); +static inline void __cpu_die(unsigned int cpu) { } #endif /* CONFIG_HOTPLUG_CPU */ #else diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index a941adc7cbf2..457a18efcb11 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/err.h> #include <linux/irq.h> +#include <linux/cpuhotplug.h> #include <linux/cpu.h> #include <linux/sched/hotplug.h> #include <asm/irq.h> @@ -49,17 +50,15 @@ int __cpu_disable(void) return ret; } +#ifdef CONFIG_HOTPLUG_CPU /* - * Called on the thread which is asking for a CPU to be shutdown. + * Called on the thread which is asking for a CPU to be shutdown, if the + * CPU reported dead to the hotplug core. */ -void __cpu_die(unsigned int cpu) +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { int ret = 0; - if (!cpu_wait_death(cpu, 5)) { - pr_err("CPU %u: didn't die\n", cpu); - return; - } pr_notice("CPU%u: off\n", cpu); /* Verify from the firmware if the cpu is really stopped*/ @@ -76,9 +75,10 @@ void __noreturn arch_cpu_idle_dead(void) { idle_task_exit(); - (void)cpu_report_death(); + cpuhp_ap_report_dead(); cpu_ops[smp_processor_id()]->cpu_stop(); /* It should never reach here */ BUG(); } +#endif diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index 5730797a6b40..bd2e27f82532 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -35,6 +35,11 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS CFLAGS_string.o := -D__DISABLE_EXPORTS CFLAGS_ctype.o := -D__DISABLE_EXPORTS +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index acb1f8b53105..c67f59db7a51 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -45,6 +45,13 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat static pte_t pte_z; +static inline void kasan_populate(unsigned long start, unsigned long end, enum populate_mode mode) +{ + start = PAGE_ALIGN_DOWN(__sha(start)); + end = PAGE_ALIGN(__sha(end)); + pgtable_populate(start, end, mode); +} + static void kasan_populate_shadow(void) { pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); @@ -95,17 +102,17 @@ static void kasan_populate_shadow(void) */ for_each_physmem_usable_range(i, &start, &end) - pgtable_populate(__sha(start), __sha(end), POPULATE_KASAN_MAP_SHADOW); + kasan_populate(start, end, POPULATE_KASAN_MAP_SHADOW); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { untracked_end = VMALLOC_START; /* shallowly populate kasan shadow for vmalloc and modules */ - pgtable_populate(__sha(VMALLOC_START), __sha(MODULES_END), POPULATE_KASAN_SHALLOW); + kasan_populate(VMALLOC_START, MODULES_END, POPULATE_KASAN_SHALLOW); } else { untracked_end = MODULES_VADDR; } /* populate kasan shadow for untracked memory */ - pgtable_populate(__sha(ident_map_size), __sha(untracked_end), POPULATE_KASAN_ZERO_SHADOW); - pgtable_populate(__sha(MODULES_END), __sha(_REGION1_SIZE), POPULATE_KASAN_ZERO_SHADOW); + kasan_populate(ident_map_size, untracked_end, POPULATE_KASAN_ZERO_SHADOW); + kasan_populate(MODULES_END, _REGION1_SIZE, POPULATE_KASAN_ZERO_SHADOW); } static bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr, diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index be3bf03bf361..aa95cf6dfabb 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -116,6 +116,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_TC_SKB_EXT=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 769c7eed8b6a..f041945f9148 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -107,6 +107,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_TC_SKB_EXT=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6822a11c2c8a..c55f3c3365af 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -42,9 +42,6 @@ static inline void update_page_count(int level, long count) atomic_long_add(count, &direct_pages_count[level]); } -struct seq_file; -void arch_report_meminfo(struct seq_file *m); - /* * The S390 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index 8e9c582592b3..9e41a74fce9a 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -3,6 +3,7 @@ #define _ASM_S390_MEM_DETECT_H #include <linux/types.h> +#include <asm/page.h> enum physmem_info_source { MEM_DETECT_NONE = 0, @@ -133,7 +134,7 @@ static inline const char *get_rr_type_name(enum reserved_range_type t) #define for_each_physmem_reserved_type_range(t, range, p_start, p_end) \ for (range = &physmem_info.reserved[t], *p_start = range->start, *p_end = range->end; \ - range && range->end; range = range->chain, \ + range && range->end; range = range->chain ? __va(range->chain) : NULL, \ *p_start = range ? range->start : 0, *p_end = range ? range->end : 0) static inline struct reserved_range *__physmem_reserved_next(enum reserved_range_type *t, @@ -145,7 +146,7 @@ static inline struct reserved_range *__physmem_reserved_next(enum reserved_range return range; } if (range->chain) - return range->chain; + return __va(range->chain); while (++*t < RR_MAX) { range = &physmem_info.reserved[*t]; if (range->end) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 8a617be28bb4..7af69948b290 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -568,9 +568,9 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt) int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) { Elf64_Phdr *phdr_notes, *phdr_loads; + size_t alloc_size; int mem_chunk_cnt; void *ptr, *hdr; - u32 alloc_size; u64 hdr_off; /* If we are not in kdump or zfcp/nvme dump mode return */ diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 5ba3bd8a7b12..ca5a418c58a8 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -4,6 +4,7 @@ * Author(s): Jan Glauber <jang@linux.vnet.ibm.com> */ #include <linux/hugetlb.h> +#include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <asm/cacheflush.h> diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 5b22c6e24528..b9dcb4ae6c59 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -667,7 +667,15 @@ static void __init memblock_region_swap(void *a, void *b, int size) #ifdef CONFIG_KASAN #define __sha(x) ((unsigned long)kasan_mem_to_shadow((void *)x)) + +static inline int set_memory_kasan(unsigned long start, unsigned long end) +{ + start = PAGE_ALIGN_DOWN(__sha(start)); + end = PAGE_ALIGN(__sha(end)); + return set_memory_rwnx(start, (end - start) >> PAGE_SHIFT); +} #endif + /* * map whole physical memory to virtual memory (identity mapping) * we reserve enough space in the vmalloc area for vmemmap to hotplug @@ -737,10 +745,8 @@ void __init vmem_map_init(void) } #ifdef CONFIG_KASAN - for_each_mem_range(i, &base, &end) { - set_memory_rwnx(__sha(base), - (__sha(end) - __sha(base)) >> PAGE_SHIFT); - } + for_each_mem_range(i, &base, &end) + set_memory_kasan(base, end); #endif set_memory_rox((unsigned long)_stext, (unsigned long)(_etext - _stext) >> PAGE_SHIFT); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 9652d367fc37..e339745f62a1 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -6,6 +6,7 @@ config SUPERH select ARCH_ENABLE_MEMORY_HOTREMOVE if SPARSEMEM && MMU select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_BINFMT_FLAT if !MMU + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h deleted file mode 100644 index fe52abb69cea..000000000000 --- a/arch/sh/include/asm/bugs.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_SH_BUGS_H -#define __ASM_SH_BUGS_H - -/* - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Needs: - * void check_bugs(void); - */ - -/* - * I don't know of any Super-H bugs yet. - */ - -#include <asm/processor.h> - -extern void select_idle_routine(void); - -static void __init check_bugs(void) -{ - extern unsigned long loops_per_jiffy; - char *p = &init_utsname()->machine[2]; /* "sh" */ - - select_idle_routine(); - - current_cpu_data.loops_per_jiffy = loops_per_jiffy; - - switch (current_cpu_data.family) { - case CPU_FAMILY_SH2: - *p++ = '2'; - break; - case CPU_FAMILY_SH2A: - *p++ = '2'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH3: - *p++ = '3'; - break; - case CPU_FAMILY_SH4: - *p++ = '4'; - break; - case CPU_FAMILY_SH4A: - *p++ = '4'; - *p++ = 'a'; - break; - case CPU_FAMILY_SH4AL_DSP: - *p++ = '4'; - *p++ = 'a'; - *p++ = 'l'; - *p++ = '-'; - *p++ = 'd'; - *p++ = 's'; - *p++ = 'p'; - break; - case CPU_FAMILY_UNKNOWN: - /* - * Specifically use CPU_FAMILY_UNKNOWN rather than - * default:, so we're able to have the compiler whine - * about unhandled enumerations. - */ - break; - } - - printk("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); - -#ifndef __LITTLE_ENDIAN__ - /* 'eb' means 'Endian Big' */ - *p++ = 'e'; - *p++ = 'b'; -#endif - *p = '\0'; -} -#endif /* __ASM_SH_BUGS_H */ diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h index 85a6c1c3c16e..73fba7c922f9 100644 --- a/arch/sh/include/asm/processor.h +++ b/arch/sh/include/asm/processor.h @@ -166,6 +166,8 @@ extern unsigned int instruction_size(unsigned int insn); #define instruction_size(insn) (2) #endif +void select_idle_routine(void); + #endif /* __ASSEMBLY__ */ #include <asm/processor_32.h> diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index d662503b0665..045d93f151fd 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -15,6 +15,7 @@ #include <linux/irqflags.h> #include <linux/smp.h> #include <linux/atomic.h> +#include <asm/processor.h> #include <asm/smp.h> #include <asm/bl_bit.h> diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index af977ec4ca5e..cf7c0f72f293 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -43,6 +43,7 @@ #include <asm/smp.h> #include <asm/mmu_context.h> #include <asm/mmzone.h> +#include <asm/processor.h> #include <asm/sparsemem.h> #include <asm/platform_early.h> @@ -354,3 +355,57 @@ int test_mode_pin(int pin) { return sh_mv.mv_mode_pins() & pin; } + +void __init arch_cpu_finalize_init(void) +{ + char *p = &init_utsname()->machine[2]; /* "sh" */ + + select_idle_routine(); + + current_cpu_data.loops_per_jiffy = loops_per_jiffy; + + switch (current_cpu_data.family) { + case CPU_FAMILY_SH2: + *p++ = '2'; + break; + case CPU_FAMILY_SH2A: + *p++ = '2'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH3: + *p++ = '3'; + break; + case CPU_FAMILY_SH4: + *p++ = '4'; + break; + case CPU_FAMILY_SH4A: + *p++ = '4'; + *p++ = 'a'; + break; + case CPU_FAMILY_SH4AL_DSP: + *p++ = '4'; + *p++ = 'a'; + *p++ = 'l'; + *p++ = '-'; + *p++ = 'd'; + *p++ = 's'; + *p++ = 'p'; + break; + case CPU_FAMILY_UNKNOWN: + /* + * Specifically use CPU_FAMILY_UNKNOWN rather than + * default:, so we're able to have the compiler whine + * about unhandled enumerations. + */ + break; + } + + pr_info("CPU: %s\n", get_cpu_subtype(¤t_cpu_data)); + +#ifndef __LITTLE_ENDIAN__ + /* 'eb' means 'Endian Big' */ + *p++ = 'e'; + *p++ = 'b'; +#endif + *p = '\0'; +} diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 8535e19062f6..36fd488ccbfa 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -52,6 +52,7 @@ config SPARC config SPARC32 def_bool !64BIT select ARCH_32BIT_OFF_T + select ARCH_HAS_CPU_FINALIZE_INIT if !SMP select ARCH_HAS_SYNC_DMA_FOR_CPU select CLZ_TAB select DMA_DIRECT_REMAP diff --git a/arch/sparc/include/asm/bugs.h b/arch/sparc/include/asm/bugs.h deleted file mode 100644 index 02fa369b9c21..000000000000 --- a/arch/sparc/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include/asm/bugs.h: Sparc probes for various bugs. - * - * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net) - */ - -#ifdef CONFIG_SPARC32 -#include <asm/cpudata.h> -#endif - -extern unsigned long loops_per_jiffy; - -static void __init check_bugs(void) -{ -#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) - cpu_data(0).udelay_val = loops_per_jiffy; -#endif -} diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index c8e0dd99f370..c9d1ba4f311b 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -412,3 +412,10 @@ static int __init topology_init(void) } subsys_initcall(topology_init); + +#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP) +void __init arch_cpu_finalize_init(void) +{ + cpu_data(0).udelay_val = loops_per_jiffy; +} +#endif diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 541a9b18e343..887cfb636c26 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -6,6 +6,7 @@ config UML bool default y select ARCH_EPHEMERAL_INODES + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index f4c1e6e97ad5..50206feac577 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -108,9 +108,9 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data) static DEFINE_MUTEX(ubd_lock); static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */ -static int ubd_open(struct block_device *bdev, fmode_t mode); -static void ubd_release(struct gendisk *disk, fmode_t mode); -static int ubd_ioctl(struct block_device *bdev, fmode_t mode, +static int ubd_open(struct gendisk *disk, blk_mode_t mode); +static void ubd_release(struct gendisk *disk); +static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo); @@ -1154,9 +1154,8 @@ static int __init ubd_driver_init(void){ device_initcall(ubd_driver_init); -static int ubd_open(struct block_device *bdev, fmode_t mode) +static int ubd_open(struct gendisk *disk, blk_mode_t mode) { - struct gendisk *disk = bdev->bd_disk; struct ubd *ubd_dev = disk->private_data; int err = 0; @@ -1171,19 +1170,12 @@ static int ubd_open(struct block_device *bdev, fmode_t mode) } ubd_dev->count++; set_disk_ro(disk, !ubd_dev->openflags.w); - - /* This should no more be needed. And it didn't work anyway to exclude - * read-write remounting of filesystems.*/ - /*if((mode & FMODE_WRITE) && !ubd_dev->openflags.w){ - if(--ubd_dev->count == 0) ubd_close_dev(ubd_dev); - err = -EROFS; - }*/ out: mutex_unlock(&ubd_mutex); return err; } -static void ubd_release(struct gendisk *disk, fmode_t mode) +static void ubd_release(struct gendisk *disk) { struct ubd *ubd_dev = disk->private_data; @@ -1397,7 +1389,7 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int ubd_ioctl(struct block_device *bdev, fmode_t mode, +static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct ubd *ubd_dev = bdev->bd_disk->private_data; diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h deleted file mode 100644 index 4473942a0839..000000000000 --- a/arch/um/include/asm/bugs.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_BUGS_H -#define __UM_BUGS_H - -void check_bugs(void); - -#endif diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 0a23a98d4ca0..918fed7ad4d8 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -3,6 +3,7 @@ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ +#include <linux/cpu.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/mm.h> @@ -430,7 +431,7 @@ void __init setup_arch(char **cmdline_p) } } -void __init check_bugs(void) +void __init arch_cpu_finalize_init(void) { arch_check_bugs(); os_check_bugs(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 53bab123a8ee..ee272423ec20 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -71,6 +71,7 @@ config X86 select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -274,7 +275,9 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select HAVE_GENERIC_VDSO + select HOTPLUG_PARALLEL if SMP && X86_64 select HOTPLUG_SMT if SMP + select HOTPLUG_SPLIT_STARTUP if SMP && X86_32 select IRQ_FORCED_THREADING select NEED_PER_CPU_EMBED_FIRST_CHUNK select NEED_PER_CPU_PAGE_FIRST_CHUNK @@ -2305,49 +2308,6 @@ config HOTPLUG_CPU def_bool y depends on SMP -config BOOTPARAM_HOTPLUG_CPU0 - bool "Set default setting of cpu0_hotpluggable" - depends on HOTPLUG_CPU - help - Set whether default state of cpu0_hotpluggable is on or off. - - Say Y here to enable CPU0 hotplug by default. If this switch - is turned on, there is no need to give cpu0_hotplug kernel - parameter and the CPU0 hotplug feature is enabled by default. - - Please note: there are two known CPU0 dependencies if you want - to enable the CPU0 hotplug feature either by this switch or by - cpu0_hotplug kernel parameter. - - First, resume from hibernate or suspend always starts from CPU0. - So hibernate and suspend are prevented if CPU0 is offline. - - Second dependency is PIC interrupts always go to CPU0. CPU0 can not - offline if any interrupt can not migrate out of CPU0. There may - be other CPU0 dependencies. - - Please make sure the dependencies are under your control before - you enable this feature. - - Say N if you don't want to enable CPU0 hotplug feature by default. - You still can enable the CPU0 hotplug feature at boot by kernel - parameter cpu0_hotplug. - -config DEBUG_HOTPLUG_CPU0 - def_bool n - prompt "Debug CPU0 hotplug" - depends on HOTPLUG_CPU - help - Enabling this option offlines CPU0 (if CPU0 can be offlined) as - soon as possible and boots up userspace with CPU0 offlined. User - can online CPU0 back after boot time. - - To debug CPU0 hotplug, you need to enable CPU0 offline/online - feature by either turning on CONFIG_BOOTPARAM_HOTPLUG_CPU0 during - compilation or giving cpu0_hotplug kernel parameter at boot. - - If unsure, say N. - config COMPAT_VDSO def_bool n prompt "Disable the 32-bit vDSO (needed for glibc 2.3.3)" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b39975977c03..fdc2e3abd615 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -305,6 +305,18 @@ ifeq ($(RETPOLINE_CFLAGS),) endif endif +ifdef CONFIG_UNWINDER_ORC +orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h +orc_hash_sh := $(srctree)/scripts/orc_hash.sh +targets += $(orc_hash_h) +quiet_cmd_orc_hash = GEN $@ + cmd_orc_hash = mkdir -p $(dir $@); \ + $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@ +$(orc_hash_h): $(srctree)/arch/x86/include/asm/orc_types.h $(orc_hash_sh) FORCE + $(call if_changed,orc_hash) +archprepare: $(orc_hash_h) +endif + archclean: $(Q)rm -rf $(objtree)/arch/i386 $(Q)rm -rf $(objtree)/arch/x86_64 diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index e146b599260f..27ce10c9ff61 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -871,5 +871,16 @@ void __init tdx_early_init(void) x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed; + /* + * TDX intercepts the RDMSR to read the X2APIC ID in the parallel + * bringup low level code. That raises #VE which cannot be handled + * there. + * + * Intel-TDX has a secure RDMSR hypercall, but that needs to be + * implemented seperately in the low level startup ASM code. + * Until that is in place, disable parallel bringup for TDX. + */ + x86_cpuinit.parallel_bringup = false; + pr_info("Guest detected\n"); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 89b9c1cebb61..27f3a7b34bd5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -349,6 +349,16 @@ static struct event_constraint intel_spr_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_gnr_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -6496,6 +6506,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + x86_pmu.extra_regs = intel_spr_extra_regs; fallthrough; case INTEL_FAM6_GRANITERAPIDS_X: case INTEL_FAM6_GRANITERAPIDS_D: @@ -6506,7 +6517,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_spr_event_constraints; x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; - x86_pmu.extra_regs = intel_spr_extra_regs; + if (!x86_pmu.extra_regs) + x86_pmu.extra_regs = intel_gnr_extra_regs; x86_pmu.limit_period = spr_limit_period; x86_pmu.pebs_ept = 1; x86_pmu.pebs_aliases = NULL; @@ -6650,6 +6662,7 @@ __init int intel_pmu_init(void) pmu->pebs_constraints = intel_grt_pebs_event_constraints; pmu->extra_regs = intel_grt_extra_regs; if (is_mtl(boot_cpu_data.x86_model)) { + x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs; x86_pmu.pebs_latency_data = mtl_latency_data_small; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a5f9474f08e1..6c04b52f139b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -416,7 +416,7 @@ void __init hyperv_init(void) goto free_vp_assist_page; } - cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", + cpuhp = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "x86/hyperv_init:online", hv_cpu_init, hv_cpu_die); if (cpuhp < 0) goto free_ghcb_page; diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 1ba5d3b99b16..85d38b9f3586 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -20,6 +20,8 @@ void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); + x86_platform.realmode_reserve = x86_init_noop; + x86_platform.realmode_init = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; x86_init.timers.timer_init = x86_init_noop; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 1e51650b79d7..4f1ce5fc4e19 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +generated-y += orc_hash.h generated-y += syscalls_32.h generated-y += syscalls_64.h generated-y += syscalls_x32.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3216da7074ba..98c32aa5963a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -55,6 +55,8 @@ extern int local_apic_timer_c2_ok; extern int disable_apic; extern unsigned int lapic_timer_period; +extern int cpuid_to_apicid[]; + extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { APIC_PIC, @@ -377,7 +379,6 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[]; * APIC functionality to boot other CPUs - only used on SMP: */ #ifdef CONFIG_SMP -extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); extern int lapic_can_unplug_cpu(void); #endif @@ -507,10 +508,8 @@ extern int default_check_phys_apicid_present(int phys_apicid); #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_SMP -bool apic_id_is_primary_thread(unsigned int id); void apic_smt_update(void); #else -static inline bool apic_id_is_primary_thread(unsigned int id) { return false; } static inline void apic_smt_update(void) { } #endif diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 68d213e83fcc..4b125e5b3187 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_APICDEF_H #define _ASM_X86_APICDEF_H +#include <linux/bits.h> + /* * Constants for various Intel APICs. (local APIC, IOAPIC, etc.) * @@ -138,9 +140,10 @@ #define APIC_EILVT_MASKED (1 << 16) #define APIC_BASE (fix_to_virt(FIX_APIC_BASE)) -#define APIC_BASE_MSR 0x800 -#define XAPIC_ENABLE (1UL << 11) -#define X2APIC_ENABLE (1UL << 10) +#define APIC_BASE_MSR 0x800 +#define APIC_X2APIC_ID_MSR 0x802 +#define XAPIC_ENABLE BIT(11) +#define X2APIC_ENABLE BIT(10) #ifdef CONFIG_X86_32 # define MAX_IO_APICS 64 @@ -162,6 +165,7 @@ #define APIC_CPUID(apicid) ((apicid) & XAPIC_DEST_CPUS_MASK) #define NUM_APIC_CLUSTERS ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT) +#ifndef __ASSEMBLY__ /* * the local APIC register structure, memory mapped. Not terribly well * tested, but we might eventually use this one in the future - the @@ -435,4 +439,5 @@ enum apic_delivery_modes { APIC_DELIVERY_MODE_EXTINT = 7, }; +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_APICDEF_H */ diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 92ae28389940..f25ca2d709d4 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -4,8 +4,6 @@ #include <asm/processor.h> -extern void check_bugs(void); - #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) int ppro_with_ram_bug(void); #else diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 78796b98a544..3a233ebff712 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -30,10 +30,7 @@ struct x86_cpu { #ifdef CONFIG_HOTPLUG_CPU extern int arch_register_cpu(int num); extern void arch_unregister_cpu(int); -extern void start_cpu0(void); -#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 -extern int _debug_hotplug_cpu(int cpu, int action); -#endif +extern void soft_restart_cpu(void); #endif extern void ap_init_aperfmperf(void); @@ -98,4 +95,6 @@ extern u64 x86_read_arch_cap_msr(void); int intel_find_matching_signature(void *mc, unsigned int csig, int cpf); int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); +extern struct cpumask cpus_stop_mask; + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index c5aed9e9226c..4acfd57de8f1 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -4,11 +4,6 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -extern cpumask_var_t cpu_callin_mask; -extern cpumask_var_t cpu_callout_mask; -extern cpumask_var_t cpu_initialized_mask; -extern cpumask_var_t cpu_sibling_setup_mask; - extern void setup_cpu_local_masks(void); /* diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 503a577814b2..b475d9a582b8 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void); /* Boot, hotplug and resume */ extern void fpu__init_cpu(void); -extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index b7126701574c..7f97a8a97e24 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -17,6 +17,12 @@ #include <asm/bootparam.h> +#ifdef CONFIG_X86_MEM_ENCRYPT +void __init mem_encrypt_init(void); +#else +static inline void mem_encrypt_init(void) { } +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; @@ -87,9 +93,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* Architecture __weak replacement functions */ -void __init mem_encrypt_init(void); - void add_encrypt_protection_map(void); /* diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h index c5573eaa5bb9..1c1b7550fa55 100644 --- a/arch/x86/include/asm/nops.h +++ b/arch/x86/include/asm/nops.h @@ -34,6 +34,8 @@ #define BYTES_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x3e,BYTES_NOP7 +#define ASM_NOP_MAX 8 + #else /* @@ -47,6 +49,9 @@ * 6: osp nopl 0x00(%eax,%eax,1) * 7: nopl 0x00000000(%eax) * 8: nopl 0x00000000(%eax,%eax,1) + * 9: cs nopl 0x00000000(%eax,%eax,1) + * 10: osp cs nopl 0x00000000(%eax,%eax,1) + * 11: osp osp cs nopl 0x00000000(%eax,%eax,1) */ #define BYTES_NOP1 0x90 #define BYTES_NOP2 0x66,BYTES_NOP1 @@ -56,6 +61,15 @@ #define BYTES_NOP6 0x66,BYTES_NOP5 #define BYTES_NOP7 0x0f,0x1f,0x80,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00 +#define BYTES_NOP9 0x2e,BYTES_NOP8 +#define BYTES_NOP10 0x66,BYTES_NOP9 +#define BYTES_NOP11 0x66,BYTES_NOP10 + +#define ASM_NOP9 _ASM_BYTES(BYTES_NOP9) +#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10) +#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11) + +#define ASM_NOP_MAX 11 #endif /* CONFIG_64BIT */ @@ -68,8 +82,6 @@ #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7) #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8) -#define ASM_NOP_MAX 8 - #ifndef __ASSEMBLY__ extern const unsigned char * const x86_nops[]; #endif diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index edb2b0cb8efe..55388c9f7601 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -84,12 +84,12 @@ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH \ - mov $0x80, %rax; \ - shl $56, %rax; \ + xor %eax, %eax; \ + bts $63, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ - mov $0xfc, %rax; \ + movb $0xfc, %al; \ shl $56, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS diff --git a/arch/x86/include/asm/orc_header.h b/arch/x86/include/asm/orc_header.h new file mode 100644 index 000000000000..07bacf3e160e --- /dev/null +++ b/arch/x86/include/asm/orc_header.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#ifndef _ORC_HEADER_H +#define _ORC_HEADER_H + +#include <linux/types.h> +#include <linux/compiler.h> +#include <asm/orc_hash.h> + +/* + * The header is currently a 20-byte hash of the ORC entry definition; see + * scripts/orc_hash.sh. + */ +#define ORC_HEADER \ + __used __section(".orc_header") __aligned(4) \ + static const u8 orc_header[] = { ORC_HASH } + +#endif /* _ORC_HEADER_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 15ae4d6ba476..5700bb337987 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -27,6 +27,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); +struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 447d4bee25c4..ba3e2554799a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -513,9 +513,6 @@ extern void native_pagetable_init(void); #define native_pagetable_init paging_init #endif -struct seq_file; -extern void arch_report_meminfo(struct seq_file *m); - enum pg_level { PG_LEVEL_NONE, PG_LEVEL_4K, diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a1e4fa58b357..d46300e94f85 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -551,7 +551,6 @@ extern void switch_gdt_and_percpu_base(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void cpu_init(void); -extern void cpu_init_secondary(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index f6a1737c77be..87e5482acd0d 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -52,6 +52,7 @@ struct trampoline_header { u64 efer; u32 cr4; u32 flags; + u32 lock; #endif }; @@ -64,6 +65,8 @@ extern unsigned long initial_stack; extern unsigned long initial_vc_handler; #endif +extern u32 *trampoline_lock; + extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 5b1ed650b124..84eab2724875 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -85,6 +85,4 @@ struct rt_sigframe_x32 { #endif /* CONFIG_X86_64 */ -void __init init_sigframe_size(void); - #endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4e91054c84be..600cf25dbfc6 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -38,7 +38,9 @@ struct smp_ops { void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); - int (*cpu_up)(unsigned cpu, struct task_struct *tidle); + void (*cleanup_dead_cpu)(unsigned cpu); + void (*poll_sync_state)(void); + int (*kick_ap_alive)(unsigned cpu, struct task_struct *tidle); int (*cpu_disable)(void); void (*cpu_die)(unsigned int cpu); void (*play_dead)(void); @@ -78,11 +80,6 @@ static inline void smp_cpus_done(unsigned int max_cpus) smp_ops.smp_cpus_done(max_cpus); } -static inline int __cpu_up(unsigned int cpu, struct task_struct *tidle) -{ - return smp_ops.cpu_up(cpu, tidle); -} - static inline int __cpu_disable(void) { return smp_ops.cpu_disable(); @@ -90,7 +87,8 @@ static inline int __cpu_disable(void) static inline void __cpu_die(unsigned int cpu) { - smp_ops.cpu_die(cpu); + if (smp_ops.cpu_die) + smp_ops.cpu_die(cpu); } static inline void __noreturn play_dead(void) @@ -121,22 +119,23 @@ void native_smp_prepare_cpus(unsigned int max_cpus); void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); -int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); +int native_kick_ap(unsigned int cpu, struct task_struct *tidle); int native_cpu_disable(void); -int common_cpu_die(unsigned int cpu); -void native_cpu_die(unsigned int cpu); void __noreturn hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); -void cond_wakeup_cpu0(void); + +void smp_kick_mwait_play_dead(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); +bool smp_park_other_cpus_in_init(void); + void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); @@ -201,7 +200,14 @@ extern void nmi_selftest(void); #endif extern unsigned int smpboot_control; +extern unsigned long apic_mmio_base; #endif /* !__ASSEMBLY__ */ +/* Control bits for startup_64 */ +#define STARTUP_READ_APICID 0x80000000 + +/* Top 8 bits are reserved for control */ +#define STARTUP_PARALLEL_MASK 0xFF000000 + #endif /* _ASM_X86_SMP_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 458c891a8273..caf41c4869a0 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -31,9 +31,9 @@ * CONFIG_NUMA. */ #include <linux/numa.h> +#include <linux/cpumask.h> #ifdef CONFIG_NUMA -#include <linux/cpumask.h> #include <asm/mpspec.h> #include <asm/percpu.h> @@ -139,23 +139,31 @@ static inline int topology_max_smt_threads(void) int topology_update_package_map(unsigned int apicid, unsigned int cpu); int topology_update_die_map(unsigned int dieid, unsigned int cpu); int topology_phys_to_logical_pkg(unsigned int pkg); -int topology_phys_to_logical_die(unsigned int die, unsigned int cpu); -bool topology_is_primary_thread(unsigned int cpu); bool topology_smt_supported(void); -#else + +extern struct cpumask __cpu_primary_thread_mask; +#define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask) + +/** + * topology_is_primary_thread - Check whether CPU is the primary SMT thread + * @cpu: CPU to check + */ +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + return cpumask_test_cpu(cpu, cpu_primary_thread_mask); +} +#else /* CONFIG_SMP */ #define topology_max_packages() (1) static inline int topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } static inline int topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } -static inline int topology_phys_to_logical_die(unsigned int die, - unsigned int cpu) { return 0; } static inline int topology_max_die_per_package(void) { return 1; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } static inline bool topology_smt_supported(void) { return false; } -#endif +#endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) { diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index fbdc3d951494..dc1b03be43eb 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -55,12 +55,10 @@ extern bool tsc_async_resets; #ifdef CONFIG_X86_TSC extern bool tsc_store_and_check_tsc_adjust(bool bootcpu); extern void tsc_verify_tsc_adjust(bool resume); -extern void check_tsc_sync_source(int cpu); extern void check_tsc_sync_target(void); #else static inline bool tsc_store_and_check_tsc_adjust(bool bootcpu) { return false; } static inline void tsc_verify_tsc_adjust(bool resume) { } -static inline void check_tsc_sync_source(int cpu) { } static inline void check_tsc_sync_target(void) { } #endif diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 88085f369ff6..0bf4d735ff00 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -177,11 +177,14 @@ struct x86_init_ops { * struct x86_cpuinit_ops - platform specific cpu hotplug setups * @setup_percpu_clockev: set up the per cpu clock event device * @early_percpu_clock_init: early init of the per cpu clock event device + * @fixup_cpu_id: fixup function for cpuinfo_x86::phys_proc_id + * @parallel_bringup: Parallel bringup control */ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); void (*early_percpu_clock_init)(void); void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); + bool parallel_bringup; }; struct timespec64; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 1328c221af30..6dfecb27b846 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include <asm/cacheflush.h> #include <asm/realmode.h> #include <asm/hypervisor.h> +#include <asm/smp.h> #include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" @@ -127,7 +128,13 @@ int x86_acpi_suspend_lowlevel(void) * value is in the actual %rsp register. */ current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack); - smpboot_control = smp_processor_id(); + /* + * Ensure the CPU knows which one it is when it comes back, if + * it isn't in parallel mode and expected to work that out for + * itself. + */ + if (!(smpboot_control & STARTUP_PARALLEL_MASK)) + smpboot_control = smp_processor_id(); #endif initial_code = (unsigned long)wakeup_long64; saved_magic = 0x123456789abcdef0L; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f615e0cb6d93..a7e1ec50ad29 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -37,11 +37,23 @@ EXPORT_SYMBOL_GPL(alternatives_patched); #define MAX_PATCH_LEN (255-1) -static int __initdata_or_module debug_alternative; +#define DA_ALL (~0) +#define DA_ALT 0x01 +#define DA_RET 0x02 +#define DA_RETPOLINE 0x04 +#define DA_ENDBR 0x08 +#define DA_SMP 0x10 + +static unsigned int __initdata_or_module debug_alternative; static int __init debug_alt(char *str) { - debug_alternative = 1; + if (str && *str == '=') + str++; + + if (!str || kstrtouint(str, 0, &debug_alternative)) + debug_alternative = DA_ALL; + return 1; } __setup("debug-alternative", debug_alt); @@ -55,15 +67,15 @@ static int __init setup_noreplace_smp(char *str) } __setup("noreplace-smp", setup_noreplace_smp); -#define DPRINTK(fmt, args...) \ +#define DPRINTK(type, fmt, args...) \ do { \ - if (debug_alternative) \ + if (debug_alternative & DA_##type) \ printk(KERN_DEBUG pr_fmt(fmt) "\n", ##args); \ } while (0) -#define DUMP_BYTES(buf, len, fmt, args...) \ +#define DUMP_BYTES(type, buf, len, fmt, args...) \ do { \ - if (unlikely(debug_alternative)) { \ + if (unlikely(debug_alternative & DA_##type)) { \ int j; \ \ if (!(len)) \ @@ -86,6 +98,11 @@ static const unsigned char x86nops[] = BYTES_NOP6, BYTES_NOP7, BYTES_NOP8, +#ifdef CONFIG_64BIT + BYTES_NOP9, + BYTES_NOP10, + BYTES_NOP11, +#endif }; const unsigned char * const x86_nops[ASM_NOP_MAX+1] = @@ -99,19 +116,44 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = x86nops + 1 + 2 + 3 + 4 + 5, x86nops + 1 + 2 + 3 + 4 + 5 + 6, x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +#ifdef CONFIG_64BIT + x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8, + x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9, + x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9 + 10, +#endif }; -/* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void __init_or_module add_nops(void *insns, unsigned int len) +/* + * Fill the buffer with a single effective instruction of size @len. + * + * In order not to issue an ORC stack depth tracking CFI entry (Call Frame Info) + * for every single-byte NOP, try to generate the maximally available NOP of + * size <= ASM_NOP_MAX such that only a single CFI entry is generated (vs one for + * each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and + * *jump* over instead of executing long and daft NOPs. + */ +static void __init_or_module add_nop(u8 *instr, unsigned int len) { - while (len > 0) { - unsigned int noplen = len; - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - memcpy(insns, x86_nops[noplen], noplen); - insns += noplen; - len -= noplen; + u8 *target = instr + len; + + if (!len) + return; + + if (len <= ASM_NOP_MAX) { + memcpy(instr, x86_nops[len], len); + return; } + + if (len < 128) { + __text_gen_insn(instr, JMP8_INSN_OPCODE, instr, target, JMP8_INSN_SIZE); + instr += JMP8_INSN_SIZE; + } else { + __text_gen_insn(instr, JMP32_INSN_OPCODE, instr, target, JMP32_INSN_SIZE); + instr += JMP32_INSN_SIZE; + } + + for (;instr < target; instr++) + *instr = INT3_INSN_OPCODE; } extern s32 __retpoline_sites[], __retpoline_sites_end[]; @@ -123,133 +165,223 @@ extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); /* - * Are we looking at a near JMP with a 1 or 4-byte displacement. + * Matches NOP and NOPL, not any of the other possible NOPs. */ -static inline bool is_jmp(const u8 opcode) +static bool insn_is_nop(struct insn *insn) { - return opcode == 0xeb || opcode == 0xe9; + /* Anything NOP, but no REP NOP */ + if (insn->opcode.bytes[0] == 0x90 && + (!insn->prefixes.nbytes || insn->prefixes.bytes[0] != 0xF3)) + return true; + + /* NOPL */ + if (insn->opcode.bytes[0] == 0x0F && insn->opcode.bytes[1] == 0x1F) + return true; + + /* TODO: more nops */ + + return false; } -static void __init_or_module -recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insn_buff) +/* + * Find the offset of the first non-NOP instruction starting at @offset + * but no further than @len. + */ +static int skip_nops(u8 *instr, int offset, int len) { - u8 *next_rip, *tgt_rip; - s32 n_dspl, o_dspl; - int repl_len; + struct insn insn; - if (a->replacementlen != 5) - return; + for (; offset < len; offset += insn.length) { + if (insn_decode_kernel(&insn, &instr[offset])) + break; - o_dspl = *(s32 *)(insn_buff + 1); + if (!insn_is_nop(&insn)) + break; + } - /* next_rip of the replacement JMP */ - next_rip = repl_insn + a->replacementlen; - /* target rip of the replacement JMP */ - tgt_rip = next_rip + o_dspl; - n_dspl = tgt_rip - orig_insn; + return offset; +} - DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); +/* + * Optimize a sequence of NOPs, possibly preceded by an unconditional jump + * to the end of the NOP sequence into a single NOP. + */ +static bool __init_or_module +__optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target) +{ + int i = *next - insn->length; - if (tgt_rip - orig_insn >= 0) { - if (n_dspl - 2 <= 127) - goto two_byte_jmp; - else - goto five_byte_jmp; - /* negative offset */ - } else { - if (((n_dspl - 2) & 0xff) == (n_dspl - 2)) - goto two_byte_jmp; - else - goto five_byte_jmp; + switch (insn->opcode.bytes[0]) { + case JMP8_INSN_OPCODE: + case JMP32_INSN_OPCODE: + *prev = i; + *target = *next + insn->immediate.value; + return false; } -two_byte_jmp: - n_dspl -= 2; + if (insn_is_nop(insn)) { + int nop = i; - insn_buff[0] = 0xeb; - insn_buff[1] = (s8)n_dspl; - add_nops(insn_buff + 2, 3); + *next = skip_nops(instr, *next, len); + if (*target && *next == *target) + nop = *prev; - repl_len = 2; - goto done; + add_nop(instr + nop, *next - nop); + DUMP_BYTES(ALT, instr, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, *next); + return true; + } + + *target = 0; + return false; +} -five_byte_jmp: - n_dspl -= 5; +/* + * "noinline" to cause control flow change and thus invalidate I$ and + * cause refetch after modification. + */ +static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) +{ + int prev, target = 0; - insn_buff[0] = 0xe9; - *(s32 *)&insn_buff[1] = n_dspl; + for (int next, i = 0; i < len; i = next) { + struct insn insn; - repl_len = 5; + if (insn_decode_kernel(&insn, &instr[i])) + return; -done: + next = i + insn.length; - DPRINTK("final displ: 0x%08x, JMP 0x%lx", - n_dspl, (unsigned long)orig_insn + n_dspl + repl_len); + __optimize_nops(instr, len, &insn, &next, &prev, &target); + } } /* - * optimize_nops_range() - Optimize a sequence of single byte NOPs (0x90) + * In this context, "source" is where the instructions are placed in the + * section .altinstr_replacement, for example during kernel build by the + * toolchain. + * "Destination" is where the instructions are being patched in by this + * machinery. * - * @instr: instruction byte stream - * @instrlen: length of the above - * @off: offset within @instr where the first NOP has been detected + * The source offset is: * - * Return: number of NOPs found (and replaced). + * src_imm = target - src_next_ip (1) + * + * and the target offset is: + * + * dst_imm = target - dst_next_ip (2) + * + * so rework (1) as an expression for target like: + * + * target = src_imm + src_next_ip (1a) + * + * and substitute in (2) to get: + * + * dst_imm = (src_imm + src_next_ip) - dst_next_ip (3) + * + * Now, since the instruction stream is 'identical' at src and dst (it + * is being copied after all) it can be stated that: + * + * src_next_ip = src + ip_offset + * dst_next_ip = dst + ip_offset (4) + * + * Substitute (4) in (3) and observe ip_offset being cancelled out to + * obtain: + * + * dst_imm = src_imm + (src + ip_offset) - (dst + ip_offset) + * = src_imm + src - dst + ip_offset - ip_offset + * = src_imm + src - dst (5) + * + * IOW, only the relative displacement of the code block matters. */ -static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off) -{ - unsigned long flags; - int i = off, nnops; - while (i < instrlen) { - if (instr[i] != 0x90) - break; +#define apply_reloc_n(n_, p_, d_) \ + do { \ + s32 v = *(s##n_ *)(p_); \ + v += (d_); \ + BUG_ON((v >> 31) != (v >> (n_-1))); \ + *(s##n_ *)(p_) = (s##n_)v; \ + } while (0) + - i++; +static __always_inline +void apply_reloc(int n, void *ptr, uintptr_t diff) +{ + switch (n) { + case 1: apply_reloc_n(8, ptr, diff); break; + case 2: apply_reloc_n(16, ptr, diff); break; + case 4: apply_reloc_n(32, ptr, diff); break; + default: BUG(); } +} - nnops = i - off; +static __always_inline +bool need_reloc(unsigned long offset, u8 *src, size_t src_len) +{ + u8 *target = src + offset; + /* + * If the target is inside the patched block, it's relative to the + * block itself and does not need relocation. + */ + return (target < src || target > src + src_len); +} - if (nnops <= 1) - return nnops; +static void __init_or_module noinline +apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) +{ + int prev, target = 0; - local_irq_save(flags); - add_nops(instr + off, nnops); - local_irq_restore(flags); + for (int next, i = 0; i < len; i = next) { + struct insn insn; - DUMP_BYTES(instr, instrlen, "%px: [%d:%d) optimized NOPs: ", instr, off, i); + if (WARN_ON_ONCE(insn_decode_kernel(&insn, &buf[i]))) + return; - return nnops; -} + next = i + insn.length; -/* - * "noinline" to cause control flow change and thus invalidate I$ and - * cause refetch after modification. - */ -static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) -{ - struct insn insn; - int i = 0; + if (__optimize_nops(buf, len, &insn, &next, &prev, &target)) + continue; - /* - * Jump over the non-NOP insns and optimize single-byte NOPs into bigger - * ones. - */ - for (;;) { - if (insn_decode_kernel(&insn, &instr[i])) - return; + switch (insn.opcode.bytes[0]) { + case 0x0f: + if (insn.opcode.bytes[1] < 0x80 || + insn.opcode.bytes[1] > 0x8f) + break; - /* - * See if this and any potentially following NOPs can be - * optimized. - */ - if (insn.length == 1 && insn.opcode.bytes[0] == 0x90) - i += optimize_nops_range(instr, len, i); - else - i += insn.length; + fallthrough; /* Jcc.d32 */ + case 0x70 ... 0x7f: /* Jcc.d8 */ + case JMP8_INSN_OPCODE: + case JMP32_INSN_OPCODE: + case CALL_INSN_OPCODE: + if (need_reloc(next + insn.immediate.value, src, src_len)) { + apply_reloc(insn.immediate.nbytes, + buf + i + insn_offset_immediate(&insn), + src - dest); + } - if (i >= len) - return; + /* + * Where possible, convert JMP.d32 into JMP.d8. + */ + if (insn.opcode.bytes[0] == JMP32_INSN_OPCODE) { + s32 imm = insn.immediate.value; + imm += src - dest; + imm += JMP32_INSN_SIZE - JMP8_INSN_SIZE; + if ((imm >> 31) == (imm >> 7)) { + buf[i+0] = JMP8_INSN_OPCODE; + buf[i+1] = (s8)imm; + + memset(&buf[i+2], INT3_INSN_OPCODE, insn.length - 2); + } + } + break; + } + + if (insn_rip_relative(&insn)) { + if (need_reloc(next + insn.displacement.value, src, src_len)) { + apply_reloc(insn.displacement.nbytes, + buf + i + insn_offset_displacement(&insn), + src - dest); + } + } } } @@ -270,7 +402,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insn_buff[MAX_PATCH_LEN]; - DPRINTK("alt table %px, -> %px", start, end); + DPRINTK(ALT, "alt table %px, -> %px", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -294,47 +426,31 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * - feature not present but ALT_FLAG_NOT is set to mean, * patch if feature is *NOT* present. */ - if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) - goto next; + if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { + optimize_nops(instr, a->instrlen); + continue; + } - DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", + DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", (a->flags & ALT_FLAG_NOT) ? "!" : "", a->cpuid >> 5, a->cpuid & 0x1f, instr, instr, a->instrlen, replacement, a->replacementlen); - DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); - memcpy(insn_buff, replacement, a->replacementlen); insn_buff_sz = a->replacementlen; - /* - * 0xe8 is a relative jump; fix the offset. - * - * Instruction length is checked before the opcode to avoid - * accessing uninitialized bytes for zero-length replacements. - */ - if (a->replacementlen == 5 && *insn_buff == 0xe8) { - *(s32 *)(insn_buff + 1) += replacement - instr; - DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx", - *(s32 *)(insn_buff + 1), - (unsigned long)instr + *(s32 *)(insn_buff + 1) + 5); - } - - if (a->replacementlen && is_jmp(replacement[0])) - recompute_jump(a, instr, replacement, insn_buff); - for (; insn_buff_sz < a->instrlen; insn_buff_sz++) insn_buff[insn_buff_sz] = 0x90; - DUMP_BYTES(insn_buff, insn_buff_sz, "%px: final_insn: ", instr); + apply_relocation(insn_buff, a->instrlen, instr, replacement, a->replacementlen); - text_poke_early(instr, insn_buff, insn_buff_sz); + DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement); + DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr); -next: - optimize_nops(instr, a->instrlen); + text_poke_early(instr, insn_buff, insn_buff_sz); } } @@ -555,15 +671,15 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) continue; } - DPRINTK("retpoline at: %pS (%px) len: %d to: %pS", + DPRINTK(RETPOLINE, "retpoline at: %pS (%px) len: %d to: %pS", addr, addr, insn.length, addr + insn.length + insn.immediate.value); len = patch_retpoline(addr, &insn, bytes); if (len == insn.length) { optimize_nops(bytes, len); - DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr); - DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr); + DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr); text_poke_early(addr, bytes, len); } } @@ -590,13 +706,12 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; + /* Patch the custom return thunks... */ if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - if (x86_return_thunk == __x86_return_thunk) - return -1; - i = JMP32_INSN_SIZE; __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); } else { + /* ... or patch them out if not needed. */ bytes[i++] = RET_INSN_OPCODE; } @@ -609,6 +724,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; + /* + * Do not patch out the default return thunks if those needed are the + * ones generated by the compiler. + */ + if (cpu_feature_enabled(X86_FEATURE_RETHUNK) && + (x86_return_thunk == __x86_return_thunk)) + return; + for (s = start; s < end; s++) { void *dest = NULL, *addr = (void *)s + *s; struct insn insn; @@ -630,14 +753,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) addr, dest, 5, addr)) continue; - DPRINTK("return thunk at: %pS (%px) len: %d to: %pS", + DPRINTK(RET, "return thunk at: %pS (%px) len: %d to: %pS", addr, addr, insn.length, addr + insn.length + insn.immediate.value); len = patch_return(addr, &insn, bytes); if (len == insn.length) { - DUMP_BYTES(((u8*)addr), len, "%px: orig: ", addr); - DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr); + DUMP_BYTES(RET, ((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr); text_poke_early(addr, bytes, len); } } @@ -655,7 +778,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #ifdef CONFIG_X86_KERNEL_IBT -static void poison_endbr(void *addr, bool warn) +static void __init_or_module poison_endbr(void *addr, bool warn) { u32 endbr, poison = gen_endbr_poison(); @@ -667,13 +790,13 @@ static void poison_endbr(void *addr, bool warn) return; } - DPRINTK("ENDBR at: %pS (%px)", addr, addr); + DPRINTK(ENDBR, "ENDBR at: %pS (%px)", addr, addr); /* * When we have IBT, the lack of ENDBR will trigger #CP */ - DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr); - DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr); + DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr); + DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr); text_poke_early(addr, &poison, 4); } @@ -1148,7 +1271,7 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, smp->locks_end = locks_end; smp->text = text; smp->text_end = text_end; - DPRINTK("locks %p -> %p, text %p -> %p, name %s\n", + DPRINTK(SMP, "locks %p -> %p, text %p -> %p, name %s\n", smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); @@ -1225,6 +1348,20 @@ int alternatives_text_reserved(void *start, void *end) #endif /* CONFIG_SMP */ #ifdef CONFIG_PARAVIRT + +/* Use this to add nops to a buffer, then text_poke the whole buffer. */ +static void __init_or_module add_nops(void *insns, unsigned int len) +{ + while (len > 0) { + unsigned int noplen = len; + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + memcpy(insns, x86_nops[noplen], noplen); + insns += noplen; + len -= noplen; + } +} + void __init_or_module apply_paravirt(struct paravirt_patch_site *start, struct paravirt_patch_site *end) { @@ -1332,6 +1469,35 @@ static noinline void __init int3_selftest(void) unregister_die_notifier(&int3_exception_nb); } +static __initdata int __alt_reloc_selftest_addr; + +__visible noinline void __init __alt_reloc_selftest(void *arg) +{ + WARN_ON(arg != &__alt_reloc_selftest_addr); +} + +static noinline void __init alt_reloc_selftest(void) +{ + /* + * Tests apply_relocation(). + * + * This has a relative immediate (CALL) in a place other than the first + * instruction and additionally on x86_64 we get a RIP-relative LEA: + * + * lea 0x0(%rip),%rdi # 5d0: R_X86_64_PC32 .init.data+0x5566c + * call +0 # 5d5: R_X86_64_PLT32 __alt_reloc_selftest-0x4 + * + * Getting this wrong will either crash and burn or tickle the WARN + * above. + */ + asm_inline volatile ( + ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS) + : /* output */ + : [mem] "m" (__alt_reloc_selftest_addr) + : _ASM_ARG1 + ); +} + void __init alternative_instructions(void) { int3_selftest(); @@ -1419,6 +1585,8 @@ void __init alternative_instructions(void) restart_nmi(); alternatives_patched = 1; + + alt_reloc_selftest(); } /** @@ -1954,6 +2122,16 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries atomic_set_release(&bp_desc.refs, 1); /* + * Function tracing can enable thousands of places that need to be + * updated. This can take quite some time, and with full kernel debugging + * enabled, this could cause the softlockup watchdog to trigger. + * This function gets called every 256 entries added to be patched. + * Call cond_resched() here to make sure that other tasks can get scheduled + * while processing all the functions being patched. + */ + cond_resched(); + + /* * Corresponding read barrier in int3 notifier for making sure the * nr_entries and handler are correctly ordered wrt. patching. */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 7e331e8f3692..035a3db5330b 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -15,28 +15,31 @@ #include <linux/pci_ids.h> #include <asm/amd_nb.h> -#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 -#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 -#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 -#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 -#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 -#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT 0x14d8 -#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 -#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 -#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec -#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 -#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c -#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 -#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4 0x1728 -#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 -#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 -#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d -#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e -#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 -#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 -#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc +#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 +#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 +#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 +#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT 0x14b5 +#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 +#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 +#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT 0x14d8 +#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 +#define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb + +#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec +#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c +#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4 0x1728 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 +#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d +#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e +#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 +#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc +#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); @@ -53,6 +56,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, {} }; @@ -81,6 +85,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, {} }; @@ -101,6 +106,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 770557110051..af49e24b46a4 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -101,6 +101,9 @@ static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP; */ static bool virt_ext_dest_id __ro_after_init; +/* For parallel bootup. */ +unsigned long apic_mmio_base __ro_after_init; + /* * Map cpu index to physical APIC ID */ @@ -2163,6 +2166,7 @@ void __init register_lapic_address(unsigned long address) if (!x2apic_mode) { set_fixmap_nocache(FIX_APIC_BASE, address); + apic_mmio_base = APIC_BASE; apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", APIC_BASE, address); } @@ -2376,7 +2380,7 @@ static int nr_logical_cpuids = 1; /* * Used to store mapping between logical CPU IDs and APIC IDs. */ -static int cpuid_to_apicid[] = { +int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; @@ -2386,20 +2390,31 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) } #ifdef CONFIG_SMP -/** - * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread - * @apicid: APIC ID to check +static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) +{ + /* Isolate the SMT bit(s) in the APICID and check for 0 */ + u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1; + + if (smp_num_siblings == 1 || !(apicid & mask)) + cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); +} + +/* + * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid + * during early boot. Initialize the primary thread mask before SMP + * bringup. */ -bool apic_id_is_primary_thread(unsigned int apicid) +static int __init smp_init_primary_thread_mask(void) { - u32 mask; + unsigned int cpu; - if (smp_num_siblings == 1) - return true; - /* Isolate the SMT bit(s) in the APICID and check for 0 */ - mask = (1U << (fls(smp_num_siblings) - 1)) - 1; - return !(apicid & mask); + for (cpu = 0; cpu < nr_logical_cpuids; cpu++) + cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]); + return 0; } +early_initcall(smp_init_primary_thread_mask); +#else +static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { } #endif /* @@ -2544,6 +2559,9 @@ int generic_processor_info(int apicid, int version) set_cpu_present(cpu, true); num_processors++; + if (system_state != SYSTEM_BOOTING) + cpu_mark_primary_thread(cpu, apicid); + return cpu; } diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 6bde05a86b4e..896bc41cb2ba 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -97,7 +97,10 @@ static void init_x2apic_ldr(void) static int x2apic_phys_probe(void) { - if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys())) + if (!x2apic_mode) + return 0; + + if (x2apic_phys || x2apic_fadt_phys()) return 1; return apic == &apic_x2apic_phys; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 22ab13966427..8bb937331acb 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -133,8 +133,8 @@ static bool skip_addr(void *dest) /* Accounts directly */ if (dest == ret_from_fork) return true; -#ifdef CONFIG_HOTPLUG_CPU - if (dest == start_cpu0) +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_AMD_MEM_ENCRYPT) + if (dest == soft_restart_cpu) return true; #endif #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 182af64387d0..9e2a91830f72 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,7 +9,6 @@ * - Andrew D. Balsa (code cleanup). */ #include <linux/init.h> -#include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nospec.h> @@ -27,8 +26,6 @@ #include <asm/msr.h> #include <asm/vmx.h> #include <asm/paravirt.h> -#include <asm/alternative.h> -#include <asm/set_memory.h> #include <asm/intel-family.h> #include <asm/e820/api.h> #include <asm/hypervisor.h> @@ -125,21 +122,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); -void __init check_bugs(void) +void __init cpu_select_mitigations(void) { - identify_boot_cpu(); - - /* - * identify_boot_cpu() initialized SMT support information, let the - * core code know. - */ - cpu_smt_check_topology(); - - if (!IS_ENABLED(CONFIG_SMP)) { - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); - } - /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD @@ -176,39 +160,6 @@ void __init check_bugs(void) md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); - - arch_smt_update(); - -#ifdef CONFIG_X86_32 - /* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); - - init_utsname()->machine[1] = - '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); - alternative_instructions(); - - fpu__init_check_bugs(); -#else /* CONFIG_X86_64 */ - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -#endif } /* diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 4063e8991211..8f86eacf69f7 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -39,6 +39,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Shared L2 cache maps */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); +static cpumask_var_t cpu_cacheinfo_mask; + /* Kernel controls MTRR and/or PAT MSRs. */ unsigned int memory_caching_control __ro_after_init; @@ -1172,8 +1174,10 @@ void cache_bp_restore(void) cache_cpu_init(); } -static int cache_ap_init(unsigned int cpu) +static int cache_ap_online(unsigned int cpu) { + cpumask_set_cpu(cpu, cpu_cacheinfo_mask); + if (!memory_caching_control || get_cache_aps_delayed_init()) return 0; @@ -1191,11 +1195,17 @@ static int cache_ap_init(unsigned int cpu) * lock to prevent MTRR entry changes */ stop_machine_from_inactive_cpu(cache_rendezvous_handler, NULL, - cpu_callout_mask); + cpu_cacheinfo_mask); return 0; } +static int cache_ap_offline(unsigned int cpu) +{ + cpumask_clear_cpu(cpu, cpu_cacheinfo_mask); + return 0; +} + /* * Delayed cache initialization for all AP's */ @@ -1210,9 +1220,12 @@ void cache_aps_init(void) static int __init cache_ap_register(void) { + zalloc_cpumask_var(&cpu_cacheinfo_mask, GFP_KERNEL); + cpumask_set_cpu(smp_processor_id(), cpu_cacheinfo_mask); + cpuhp_setup_state_nocalls(CPUHP_AP_CACHECTRL_STARTING, "x86/cachectrl:starting", - cache_ap_init, NULL); + cache_ap_online, cache_ap_offline); return 0; } -core_initcall(cache_ap_register); +early_initcall(cache_ap_register); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 80710a68ef7d..8075eb45a3a4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -18,12 +18,16 @@ #include <linux/init.h> #include <linux/kprobes.h> #include <linux/kgdb.h> +#include <linux/mem_encrypt.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/io.h> #include <linux/syscore_ops.h> #include <linux/pgtable.h> #include <linux/stackprotector.h> +#include <linux/utsname.h> +#include <asm/alternative.h> #include <asm/cmdline.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> @@ -59,7 +63,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> -#include <asm/sigframe.h> +#include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> @@ -67,14 +71,6 @@ u32 elf_hwcap2 __read_mostly; -/* all of these masks are initialized in setup_cpu_local_masks() */ -cpumask_var_t cpu_initialized_mask; -cpumask_var_t cpu_callout_mask; -cpumask_var_t cpu_callin_mask; - -/* representing cpus for which sibling maps can be computed */ -cpumask_var_t cpu_sibling_setup_mask; - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -169,15 +165,6 @@ clear_ppin: clear_cpu_cap(c, info->feature); } -/* correctly size the local cpu masks */ -void __init setup_cpu_local_masks(void) -{ - alloc_bootmem_cpumask_var(&cpu_initialized_mask); - alloc_bootmem_cpumask_var(&cpu_callin_mask); - alloc_bootmem_cpumask_var(&cpu_callout_mask); - alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); -} - static void default_init(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 @@ -1600,10 +1587,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) sld_setup(c); - fpu__init_system(c); - - init_sigframe_size(); - #ifdef CONFIG_X86_32 /* * Regardless of whether PCID is enumerated, the SDM says @@ -2123,19 +2106,6 @@ static void dbg_restore_debug_regs(void) #define dbg_restore_debug_regs() #endif /* ! CONFIG_KGDB */ -static void wait_for_master_cpu(int cpu) -{ -#ifdef CONFIG_SMP - /* - * wait for ACK from master CPU before continuing - * with AP initialization - */ - WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); - while (!cpumask_test_cpu(cpu, cpu_callout_mask)) - cpu_relax(); -#endif -} - static inline void setup_getcpu(int cpu) { unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); @@ -2158,11 +2128,7 @@ static inline void setup_getcpu(int cpu) } #ifdef CONFIG_X86_64 -static inline void ucode_cpu_init(int cpu) -{ - if (cpu) - load_ucode_ap(); -} +static inline void ucode_cpu_init(int cpu) { } static inline void tss_setup_ist(struct tss_struct *tss) { @@ -2239,8 +2205,6 @@ void cpu_init(void) struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - wait_for_master_cpu(cpu); - ucode_cpu_init(cpu); #ifdef CONFIG_NUMA @@ -2285,26 +2249,12 @@ void cpu_init(void) doublefault_init_cpu_tss(); - fpu__init_cpu(); - if (is_uv_system()) uv_cpu_init(); load_fixmap_gdt(cpu); } -#ifdef CONFIG_SMP -void cpu_init_secondary(void) -{ - /* - * Relies on the BP having set-up the IDT tables, which are loaded - * on this CPU in cpu_init_exception_handling(). - */ - cpu_init_exception_handling(); - cpu_init(); -} -#endif - #ifdef CONFIG_MICROCODE_LATE_LOADING /** * store_cpu_caps() - Store a snapshot of CPU capabilities @@ -2362,3 +2312,69 @@ void arch_smt_update(void) /* Check whether IPI broadcasting can be enabled */ apic_smt_update(); } + +void __init arch_cpu_finalize_init(void) +{ + identify_boot_cpu(); + + /* + * identify_boot_cpu() initialized SMT support information, let the + * core code know. + */ + cpu_smt_check_topology(); + + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + + cpu_select_mitigations(); + + arch_smt_update(); + + if (IS_ENABLED(CONFIG_X86_32)) { + /* + * Check whether this is a real i386 which is not longer + * supported and fixup the utsname. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + + init_utsname()->machine[1] = + '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); + } + + /* + * Must be before alternatives because it might set or clear + * feature bits. + */ + fpu__init_system(); + fpu__init_cpu(); + + alternative_instructions(); + + if (IS_ENABLED(CONFIG_X86_64)) { + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); + } else { + fpu__init_check_bugs(); + } + + /* + * This needs to be called before any devices perform DMA + * operations that might use the SWIOTLB bounce buffers. It will + * mark the bounce buffers as decrypted so that their usage will + * not cause "plain-text" data to be decrypted when accessed. It + * must be called after late_time_init() so that Hyper-V x86/x64 + * hypercalls work when the SWIOTLB bounce buffers are decrypted. + */ + mem_encrypt_init(); +} diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index f97b0fe13da8..1c44630d4789 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -79,6 +79,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +void cpu_select_mitigations(void); extern void x86_spec_ctrl_setup_ap(void); extern void update_srbds_msr(void); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0b971f974096..5e74610b39e7 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -715,11 +715,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) bool amd_mce_is_memory_error(struct mce *m) { + enum smca_bank_types bank_type; /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; + bank_type = smca_get_bank_type(m->extcpu, m->bank); if (mce_flags.smca) - return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0; + return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1050,7 +1052,7 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol if (bank_type >= N_SMCA_BANK_TYPES) return NULL; - if (b && bank_type == SMCA_UMC) { + if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; return NULL; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2eec60f50057..22dfcb2adcd7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1533,7 +1533,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - if (kill_current_task) + if (!mce_usable_address(&m)) queue_task_work(&m, msg, kill_me_now); else queue_task_work(&m, msg, kill_me_maybe); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 851eb13edc01..998a08f17e33 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -53,7 +53,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -static bool fpu__probe_without_cpuid(void) +static bool __init fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void) return fsw == 0 && (fcw & 0x103f) == 0x003f; } -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static void __init fpu__init_system_early_generic(void) { if (!boot_cpu_has(X86_FEATURE_CPUID) && !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { @@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void) * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ -void __init fpu__init_system(struct cpuinfo_x86 *c) +void __init fpu__init_system(void) { fpstate_reset(¤t->thread.fpu); - fpu__init_system_early_generic(c); + fpu__init_system_early_generic(); /* * The FPU has to be operational for some of the diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 67c8ed99144b..c9318993f959 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -138,20 +138,6 @@ SYM_CODE_START(startup_32) jmp .Ldefault_entry SYM_CODE_END(startup_32) -#ifdef CONFIG_HOTPLUG_CPU -/* - * Boot CPU0 entry point. It's called from play_dead(). Everything has been set - * up already except stack. We just set up stack here. Then call - * start_secondary(). - */ -SYM_FUNC_START(start_cpu0) - movl initial_stack, %ecx - movl %ecx, %esp - call *(initial_code) -1: jmp 1b -SYM_FUNC_END(start_cpu0) -#endif - /* * Non-boot CPU entry point; entered from trampoline.S * We can't lgdt here, because lgdt itself uses a data segment, but diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 113c13376e51..c5b9289837dc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,7 +24,9 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/apicdef.h> #include <asm/fixmap.h> +#include <asm/smp.h> /* * We are not able to switch in one step to the final KERNEL ADDRESS SPACE @@ -234,8 +236,67 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) ANNOTATE_NOENDBR // above #ifdef CONFIG_SMP + /* + * For parallel boot, the APIC ID is read from the APIC, and then + * used to look up the CPU number. For booting a single CPU, the + * CPU number is encoded in smpboot_control. + * + * Bit 31 STARTUP_READ_APICID (Read APICID from APIC) + * Bit 0-23 CPU# if STARTUP_xx flags are not set + */ movl smpboot_control(%rip), %ecx + testl $STARTUP_READ_APICID, %ecx + jnz .Lread_apicid + /* + * No control bit set, single CPU bringup. CPU number is provided + * in bit 0-23. This is also the boot CPU case (CPU number 0). + */ + andl $(~STARTUP_PARALLEL_MASK), %ecx + jmp .Lsetup_cpu +.Lread_apicid: + /* Check whether X2APIC mode is already enabled */ + mov $MSR_IA32_APICBASE, %ecx + rdmsr + testl $X2APIC_ENABLE, %eax + jnz .Lread_apicid_msr + + /* Read the APIC ID from the fix-mapped MMIO space. */ + movq apic_mmio_base(%rip), %rcx + addq $APIC_ID, %rcx + movl (%rcx), %eax + shr $24, %eax + jmp .Llookup_AP + +.Lread_apicid_msr: + mov $APIC_X2APIC_ID_MSR, %ecx + rdmsr + +.Llookup_AP: + /* EAX contains the APIC ID of the current CPU */ + xorq %rcx, %rcx + leaq cpuid_to_apicid(%rip), %rbx + +.Lfind_cpunr: + cmpl (%rbx,%rcx,4), %eax + jz .Lsetup_cpu + inc %ecx +#ifdef CONFIG_FORCE_NR_CPUS + cmpl $NR_CPUS, %ecx +#else + cmpl nr_cpu_ids(%rip), %ecx +#endif + jb .Lfind_cpunr + + /* APIC ID not found in the table. Drop the trampoline lock and bail. */ + movq trampoline_lock(%rip), %rax + movl $0, (%rax) + +1: cli + hlt + jmp 1b + +.Lsetup_cpu: /* Get the per cpu offset for the given CPU# which is in ECX */ movq __per_cpu_offset(,%rcx,8), %rdx #else @@ -252,6 +313,16 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) movq TASK_threadsp(%rax), %rsp /* + * Now that this CPU is running on its own stack, drop the realmode + * protection. For the boot CPU the pointer is NULL! + */ + movq trampoline_lock(%rip), %rax + testq %rax, %rax + jz .Lsetup_gdt + movl $0, (%rax) + +.Lsetup_gdt: + /* * We must switch to a new descriptor in kernel space for the GDT * because soon the kernel won't have access anymore to the userspace * addresses where we're currently running on. We have to do that here @@ -375,13 +446,13 @@ SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" #include "sev_verify_cbit.S" -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_AMD_MEM_ENCRYPT) /* - * Boot CPU0 entry point. It's called from play_dead(). Everything has been set - * up already except stack. We just set up stack here. Then call - * start_secondary() via .Ljump_to_C_code. + * Entry point for soft restart of a CPU. Invoked from xxx_play_dead() for + * restarting the boot CPU or for restarting SEV guest CPUs after CPU hot + * unplug. Everything is set up already except the stack. */ -SYM_CODE_START(start_cpu0) +SYM_CODE_START(soft_restart_cpu) ANNOTATE_NOENDBR UNWIND_HINT_END_OF_STACK @@ -390,7 +461,7 @@ SYM_CODE_START(start_cpu0) movq TASK_threadsp(%rcx), %rsp jmp .Ljump_to_C_code -SYM_CODE_END(start_cpu0) +SYM_CODE_END(soft_restart_cpu) #endif #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -433,6 +504,8 @@ SYM_DATA(initial_code, .quad x86_64_start_kernel) #ifdef CONFIG_AMD_MEM_ENCRYPT SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb) #endif + +SYM_DATA(trampoline_lock, .quad 0); __FINITDATA __INIT diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index dac41a0072ea..ff9b80a0e3e3 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -759,15 +759,26 @@ bool xen_set_default_idle(void) } #endif +struct cpumask cpus_stop_mask; + void __noreturn stop_this_cpu(void *dummy) { + struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info); + unsigned int cpu = smp_processor_id(); + local_irq_disable(); + /* - * Remove this CPU: + * Remove this CPU from the online mask and disable it + * unconditionally. This might be redundant in case that the reboot + * vector was handled late and stop_other_cpus() sent an NMI. + * + * According to SDM and APM NMIs can be accepted even after soft + * disabling the local APIC. */ - set_cpu_online(smp_processor_id(), false); + set_cpu_online(cpu, false); disable_local_APIC(); - mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + mcheck_cpu_clear(c); /* * Use wbinvd on processors that support SME. This provides support @@ -781,8 +792,17 @@ void __noreturn stop_this_cpu(void *dummy) * Test the CPUID bit directly because the machine might've cleared * X86_FEATURE_SME due to cmdline options. */ - if (cpuid_eax(0x8000001f) & BIT(0)) + if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) native_wbinvd(); + + /* + * This brings a cache line back and dirties it, but + * native_stop_other_cpus() will overwrite cpus_stop_mask after it + * observed that all CPUs reported stop. This write will invalidate + * the related cache line on this CPU. + */ + cpumask_clear_cpu(cpu, &cpus_stop_mask); + for (;;) { /* * Use native_halt() so that memory contents don't change diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index b031244d6d2d..d095a5d3c14a 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1328,7 +1328,7 @@ static void sev_es_play_dead(void) * If we get here, the VCPU was woken up again. Jump to CPU * startup code to get it back online. */ - start_cpu0(); + soft_restart_cpu(); } #else /* CONFIG_HOTPLUG_CPU */ #define sev_es_play_dead native_play_dead diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 004cb30b7419..cfeec3ee877e 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -182,7 +182,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; -void __init init_sigframe_size(void) +static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); @@ -194,7 +194,9 @@ void __init init_sigframe_size(void) max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); + return 0; } +early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 375b33ecafa2..7eb18ca7bd45 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -21,12 +21,14 @@ #include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/gfp.h> +#include <linux/kexec.h> #include <asm/mtrr.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/apic.h> +#include <asm/cpu.h> #include <asm/idtentry.h> #include <asm/nmi.h> #include <asm/mce.h> @@ -129,7 +131,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) } /* - * this function calls the 'stop' function on all other CPUs in the system. + * Disable virtualization, APIC etc. and park the CPU in a HLT loop */ DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { @@ -146,61 +148,96 @@ static int register_stop_handler(void) static void native_stop_other_cpus(int wait) { - unsigned long flags; - unsigned long timeout; + unsigned int cpu = smp_processor_id(); + unsigned long flags, timeout; if (reboot_force) return; - /* - * Use an own vector here because smp_call_function - * does lots of things not suitable in a panic situation. - */ + /* Only proceed if this is the first CPU to reach this code */ + if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1) + return; + + /* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */ + if (kexec_in_progress) + smp_kick_mwait_play_dead(); /* - * We start by using the REBOOT_VECTOR irq. - * The irq is treated as a sync point to allow critical - * regions of code on other cpus to release their spin locks - * and re-enable irqs. Jumping straight to an NMI might - * accidentally cause deadlocks with further shutdown/panic - * code. By syncing, we give the cpus up to one second to - * finish their work before we force them off with the NMI. + * 1) Send an IPI on the reboot vector to all other CPUs. + * + * The other CPUs should react on it after leaving critical + * sections and re-enabling interrupts. They might still hold + * locks, but there is nothing which can be done about that. + * + * 2) Wait for all other CPUs to report that they reached the + * HLT loop in stop_this_cpu() + * + * 3) If the system uses INIT/STARTUP for CPU bringup, then + * send all present CPUs an INIT vector, which brings them + * completely out of the way. + * + * 4) If #3 is not possible and #2 timed out send an NMI to the + * CPUs which did not yet report + * + * 5) Wait for all other CPUs to report that they reached the + * HLT loop in stop_this_cpu() + * + * #4 can obviously race against a CPU reaching the HLT loop late. + * That CPU will have reported already and the "have all CPUs + * reached HLT" condition will be true despite the fact that the + * other CPU is still handling the NMI. Again, there is no + * protection against that as "disabled" APICs still respond to + * NMIs. */ - if (num_online_cpus() > 1) { - /* did someone beat us here? */ - if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1) - return; - - /* sync above data before sending IRQ */ - wmb(); + cpumask_copy(&cpus_stop_mask, cpu_online_mask); + cpumask_clear_cpu(cpu, &cpus_stop_mask); + if (!cpumask_empty(&cpus_stop_mask)) { apic_send_IPI_allbutself(REBOOT_VECTOR); /* * Don't wait longer than a second for IPI completion. The * wait request is not checked here because that would - * prevent an NMI shutdown attempt in case that not all + * prevent an NMI/INIT shutdown in case that not all * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && timeout--) + while (!cpumask_empty(&cpus_stop_mask) && timeout--) udelay(1); } - /* if the REBOOT_VECTOR didn't work, try with the NMI */ - if (num_online_cpus() > 1) { + /* + * Park all other CPUs in INIT including "offline" CPUs, if + * possible. That's a safe place where they can't resume execution + * of HLT and then execute the HLT loop from overwritten text or + * page tables. + * + * The only downside is a broadcast MCE, but up to the point where + * the kexec() kernel brought all APs online again an MCE will just + * make HLT resume and handle the MCE. The machine crashes and burns + * due to overwritten text, page tables and data. So there is a + * choice between fire and frying pan. The result is pretty much + * the same. Chose frying pan until x86 provides a sane mechanism + * to park a CPU. + */ + if (smp_park_other_cpus_in_init()) + goto done; + + /* + * If park with INIT was not possible and the REBOOT_VECTOR didn't + * take all secondary CPUs offline, try with the NMI. + */ + if (!cpumask_empty(&cpus_stop_mask)) { /* * If NMI IPI is enabled, try to register the stop handler * and send the IPI. In any case try to wait for the other * CPUs to stop. */ if (!smp_no_nmi_ipi && !register_stop_handler()) { - /* Sync above data before sending IRQ */ - wmb(); - pr_emerg("Shutting down cpus with NMI\n"); - apic_send_IPI_allbutself(NMI_VECTOR); + for_each_cpu(cpu, &cpus_stop_mask) + apic->send_IPI(cpu, NMI_VECTOR); } /* * Don't wait longer than 10 ms if the caller didn't @@ -208,14 +245,21 @@ static void native_stop_other_cpus(int wait) * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; - while (num_online_cpus() > 1 && (wait || timeout--)) + while (!cpumask_empty(&cpus_stop_mask) && (wait || timeout--)) udelay(1); } +done: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); local_irq_restore(flags); + + /* + * Ensure that the cpus_stop_mask cache lines are invalidated on + * the other CPUs. See comment vs. SME in stop_this_cpu(). + */ + cpumask_clear(&cpus_stop_mask); } /* @@ -268,8 +312,7 @@ struct smp_ops smp_ops = { #endif .smp_send_reschedule = native_smp_send_reschedule, - .cpu_up = native_cpu_up, - .cpu_die = native_cpu_die, + .kick_ap_alive = native_kick_ap, .cpu_disable = native_cpu_disable, .play_dead = native_play_dead, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 352f0ce1ece4..8779a7ed3e87 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -53,10 +53,13 @@ #include <linux/tboot.h> #include <linux/gfp.h> #include <linux/cpuidle.h> +#include <linux/kexec.h> #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> #include <linux/stackprotector.h> +#include <linux/cpuhotplug.h> +#include <linux/mc146818rtc.h> #include <asm/acpi.h> #include <asm/cacheinfo.h> @@ -74,7 +77,7 @@ #include <asm/fpu/api.h> #include <asm/setup.h> #include <asm/uv/uv.h> -#include <linux/mc146818rtc.h> +#include <asm/microcode.h> #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> @@ -101,6 +104,26 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* CPUs which are the primary SMT threads */ +struct cpumask __cpu_primary_thread_mask __read_mostly; + +/* Representing CPUs for which sibling maps can be computed */ +static cpumask_var_t cpu_sibling_setup_mask; + +struct mwait_cpu_dead { + unsigned int control; + unsigned int status; +}; + +#define CPUDEAD_MWAIT_WAIT 0xDEADBEEF +#define CPUDEAD_MWAIT_KEXEC_HLT 0x4A17DEAD + +/* + * Cache line aligned data for mwait_play_dead(). Separate on purpose so + * that it's unlikely to be touched by other CPUs. + */ +static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); + /* Logical package management. We might want to allocate that dynamically */ unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); @@ -121,7 +144,6 @@ int arch_update_cpu_topology(void) return retval; } - static unsigned int smpboot_warm_reset_vector_count; static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) @@ -154,66 +176,63 @@ static inline void smpboot_restore_warm_reset_vector(void) } -/* - * Report back to the Boot Processor during boot time or to the caller processor - * during CPU online. - */ -static void smp_callin(void) +/* Run the next set of setup steps for the upcoming CPU */ +static void ap_starting(void) { - int cpuid; + int cpuid = smp_processor_id(); - /* - * If waken up by an INIT in an 82489DX configuration - * cpu_callout_mask guarantees we don't get here before - * an INIT_deassert IPI reaches our local APIC, so it is - * now safe to touch our local APIC. - */ - cpuid = smp_processor_id(); + /* Mop up eventual mwait_play_dead() wreckage */ + this_cpu_write(mwait_cpu_dead.status, 0); + this_cpu_write(mwait_cpu_dead.control, 0); /* - * the boot CPU has finished the init stage and is spinning - * on callin_map until we finish. We are free to set up this - * CPU, first the APIC. (this is probably redundant on most - * boards) + * If woken up by an INIT in an 82489DX configuration the alive + * synchronization guarantees that the CPU does not reach this + * point before an INIT_deassert IPI reaches the local APIC, so it + * is now safe to touch the local APIC. + * + * Set up this CPU, first the APIC, which is probably redundant on + * most boards. */ apic_ap_setup(); - /* - * Save our processor parameters. Note: this information - * is needed for clock calibration. - */ + /* Save the processor parameters. */ smp_store_cpu_info(cpuid); /* * The topology information must be up to date before - * calibrate_delay() and notify_cpu_starting(). + * notify_cpu_starting(). */ - set_cpu_sibling_map(raw_smp_processor_id()); + set_cpu_sibling_map(cpuid); ap_init_aperfmperf(); - /* - * Get our bogomips. - * Update loops_per_jiffy in cpu_data. Previous call to - * smp_store_cpu_info() stored a value that is close but not as - * accurate as the value just calculated. - */ - calibrate_delay(); - cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; pr_debug("Stack at about %p\n", &cpuid); wmb(); + /* + * This runs the AP through all the cpuhp states to its target + * state CPUHP_ONLINE. + */ notify_cpu_starting(cpuid); +} +static void ap_calibrate_delay(void) +{ /* - * Allow the master to continue. + * Calibrate the delay loop and update loops_per_jiffy in cpu_data. + * smp_store_cpu_info() stored a value that is close but not as + * accurate as the value just calculated. + * + * As this is invoked after the TSC synchronization check, + * calibrate_delay_is_known() will skip the calibration routine + * when TSC is synchronized across sockets. */ - cpumask_set_cpu(cpuid, cpu_callin_mask); + calibrate_delay(); + cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy; } -static int cpu0_logical_apicid; -static int enable_start_cpu0; /* * Activate a secondary processor. */ @@ -226,24 +245,63 @@ static void notrace start_secondary(void *unused) */ cr4_init(); -#ifdef CONFIG_X86_32 - /* switch away from the initial page table */ - load_cr3(swapper_pg_dir); - __flush_tlb_all(); -#endif - cpu_init_secondary(); + /* + * 32-bit specific. 64-bit reaches this code with the correct page + * table established. Yet another historical divergence. + */ + if (IS_ENABLED(CONFIG_X86_32)) { + /* switch away from the initial page table */ + load_cr3(swapper_pg_dir); + __flush_tlb_all(); + } + + cpu_init_exception_handling(); + + /* + * 32-bit systems load the microcode from the ASM startup code for + * historical reasons. + * + * On 64-bit systems load it before reaching the AP alive + * synchronization point below so it is not part of the full per + * CPU serialized bringup part when "parallel" bringup is enabled. + * + * That's even safe when hyperthreading is enabled in the CPU as + * the core code starts the primary threads first and leaves the + * secondary threads waiting for SIPI. Loading microcode on + * physical cores concurrently is a safe operation. + * + * This covers both the Intel specific issue that concurrent + * microcode loading on SMT siblings must be prohibited and the + * vendor independent issue`that microcode loading which changes + * CPUID, MSRs etc. must be strictly serialized to maintain + * software state correctness. + */ + if (IS_ENABLED(CONFIG_X86_64)) + load_ucode_ap(); + + /* + * Synchronization point with the hotplug core. Sets this CPUs + * synchronization state to ALIVE and spin-waits for the control CPU to + * release this CPU for further bringup. + */ + cpuhp_ap_sync_alive(); + + cpu_init(); + fpu__init_cpu(); rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); - smp_callin(); - enable_start_cpu0 = 0; + ap_starting(); + + /* Check TSC synchronization with the control CPU. */ + check_tsc_sync_target(); - /* otherwise gcc will move up smp_processor_id before the cpu_init */ - barrier(); /* - * Check TSC synchronization with the boot CPU: + * Calibrate the delay loop after the TSC synchronization check. + * This allows to skip the calibration when TSC is synchronized + * across sockets. */ - check_tsc_sync_target(); + ap_calibrate_delay(); speculative_store_bypass_ht_init(); @@ -257,7 +315,6 @@ static void notrace start_secondary(void *unused) set_cpu_online(smp_processor_id(), true); lapic_online(); unlock_vector_lock(); - cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); /* enable local interrupts */ @@ -270,15 +327,6 @@ static void notrace start_secondary(void *unused) } /** - * topology_is_primary_thread - Check whether CPU is the primary SMT thread - * @cpu: CPU to check - */ -bool topology_is_primary_thread(unsigned int cpu) -{ - return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu)); -} - -/** * topology_smt_supported - Check whether SMT is supported by the CPUs */ bool topology_smt_supported(void) @@ -288,6 +336,7 @@ bool topology_smt_supported(void) /** * topology_phys_to_logical_pkg - Map a physical package id to a logical + * @phys_pkg: The physical package id to map * * Returns logical package id or -1 if not found */ @@ -304,15 +353,17 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg) return -1; } EXPORT_SYMBOL(topology_phys_to_logical_pkg); + /** * topology_phys_to_logical_die - Map a physical die id to logical + * @die_id: The physical die id to map + * @cur_cpu: The CPU for which the mapping is done * * Returns logical die id or -1 if not found */ -int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) +static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) { - int cpu; - int proc_id = cpu_data(cur_cpu).phys_proc_id; + int cpu, proc_id = cpu_data(cur_cpu).phys_proc_id; for_each_possible_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -323,7 +374,6 @@ int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) } return -1; } -EXPORT_SYMBOL(topology_phys_to_logical_die); /** * topology_update_package_map - Update the physical to logical package map @@ -398,7 +448,7 @@ void smp_store_cpu_info(int id) c->cpu_index = id; /* * During boot time, CPU0 has this setup already. Save the info when - * bringing up AP or offlined CPU0. + * bringing up an AP. */ identify_secondary_cpu(c); c->initialized = true; @@ -706,9 +756,9 @@ static void impress_friends(void) * Allow the user to impress friends. */ pr_debug("Before bogomips\n"); - for_each_possible_cpu(cpu) - if (cpumask_test_cpu(cpu, cpu_callout_mask)) - bogosum += cpu_data(cpu).loops_per_jiffy; + for_each_online_cpu(cpu) + bogosum += cpu_data(cpu).loops_per_jiffy; + pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n", num_online_cpus(), bogosum/(500000/HZ), @@ -795,86 +845,42 @@ static void __init smp_quirk_init_udelay(void) } /* - * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal - * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this - * won't ... remember to clear down the APIC, etc later. + * Wake up AP by INIT, INIT, STARTUP sequence. */ -int -wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) +static void send_init_sequence(int phys_apicid) { - u32 dm = apic->dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; - unsigned long send_status, accept_status = 0; - int maxlvt; + int maxlvt = lapic_get_maxlvt(); - /* Target chip */ - /* Boot on the stack */ - /* Kick the second */ - apic_icr_write(APIC_DM_NMI | dm, apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - /* - * Give the other CPU some time to accept the IPI. - */ - udelay(200); + /* Be paranoid about clearing APIC errors. */ if (APIC_INTEGRATED(boot_cpu_apic_version)) { - maxlvt = lapic_get_maxlvt(); - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + /* Due to the Pentium erratum 3AP. */ + if (maxlvt > 3) apic_write(APIC_ESR, 0); - accept_status = (apic_read(APIC_ESR) & 0xEF); + apic_read(APIC_ESR); } - pr_debug("NMI sent\n"); - if (send_status) - pr_err("APIC never delivered???\n"); - if (accept_status) - pr_err("APIC delivery error (%lx)\n", accept_status); + /* Assert INIT on the target CPU */ + apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT, phys_apicid); + safe_apic_wait_icr_idle(); - return (send_status | accept_status); + udelay(init_udelay); + + /* Deassert INIT on the target CPU */ + apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid); + safe_apic_wait_icr_idle(); } -static int -wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) +/* + * Wake up AP by INIT, INIT, STARTUP sequence. + */ +static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) { unsigned long send_status = 0, accept_status = 0; - int maxlvt, num_starts, j; + int num_starts, j, maxlvt; + preempt_disable(); maxlvt = lapic_get_maxlvt(); - - /* - * Be paranoid about clearing APIC errors. - */ - if (APIC_INTEGRATED(boot_cpu_apic_version)) { - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - apic_read(APIC_ESR); - } - - pr_debug("Asserting INIT\n"); - - /* - * Turn INIT on target chip - */ - /* - * Send IPI - */ - apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT, - phys_apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - udelay(init_udelay); - - pr_debug("Deasserting INIT\n"); - - /* Target chip */ - /* Send IPI */ - apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); + send_init_sequence(phys_apicid); mb(); @@ -945,15 +951,16 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) if (accept_status) pr_err("APIC delivery error (%lx)\n", accept_status); + preempt_enable(); return (send_status | accept_status); } /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { + static int width, node_width, first = 1; static int current_node = NUMA_NO_NODE; int node = early_cpu_to_node(cpu); - static int width, node_width; if (!width) width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */ @@ -961,10 +968,10 @@ static void announce_cpu(int cpu, int apicid) if (!node_width) node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */ - if (cpu == 1) - printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state < SYSTEM_RUNNING) { + if (first) + pr_info("x86: Booting SMP configuration:\n"); + if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -975,77 +982,16 @@ static void announce_cpu(int cpu, int apicid) } /* Add padding for the BSP */ - if (cpu == 1) + if (first) pr_cont("%*s", width + 1, " "); + first = 0; pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu); - } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", node, cpu, apicid); } -static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) -{ - int cpu; - - cpu = smp_processor_id(); - if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0) - return NMI_HANDLED; - - return NMI_DONE; -} - -/* - * Wake up AP by INIT, INIT, STARTUP sequence. - * - * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS - * boot-strap code which is not a desired behavior for waking up BSP. To - * void the boot-strap code, wake up CPU0 by NMI instead. - * - * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined - * (i.e. physically hot removed and then hot added), NMI won't wake it up. - * We'll change this code in the future to wake up hard offlined CPU0 if - * real platform and request are available. - */ -static int -wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, - int *cpu0_nmi_registered) -{ - int id; - int boot_error; - - preempt_disable(); - - /* - * Wake up AP by INIT, INIT, STARTUP sequence. - */ - if (cpu) { - boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); - goto out; - } - - /* - * Wake up BSP by nmi. - * - * Register a NMI handler to help wake up CPU0. - */ - boot_error = register_nmi_handler(NMI_LOCAL, - wakeup_cpu0_nmi, 0, "wake_cpu0"); - - if (!boot_error) { - enable_start_cpu0 = 1; - *cpu0_nmi_registered = 1; - id = apic->dest_mode_logical ? cpu0_logical_apicid : apicid; - boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); - } - -out: - preempt_enable(); - - return boot_error; -} - int common_cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; @@ -1071,17 +1017,13 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. - * Returns zero if CPU booted OK, else error code from + * Returns zero if startup was successfully sent, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, - int *cpu0_nmi_registered) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) { - /* start_ip had better be page-aligned! */ unsigned long start_ip = real_mode_header->trampoline_start; - - unsigned long boot_error = 0; - unsigned long timeout; + int ret; #ifdef CONFIG_X86_64 /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ @@ -1094,7 +1036,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, if (IS_ENABLED(CONFIG_X86_32)) { early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_stack = idle->thread.sp; - } else { + } else if (!(smpboot_control & STARTUP_PARALLEL_MASK)) { smpboot_control = cpu; } @@ -1108,7 +1050,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, * This grunge runs the startup process for * the targeted processor. */ - if (x86_platform.legacy.warm_reset) { pr_debug("Setting warm reset code and vector.\n"); @@ -1123,13 +1064,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, } } - /* - * AP might wait on cpu_callout_mask in cpu_init() with - * cpu_initialized_mask set if previous attempt to online - * it timed-out. Clear cpu_initialized_mask so that after - * INIT/SIPI it could start with a clean state. - */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); smp_mb(); /* @@ -1137,66 +1071,25 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, * - Use a method from the APIC driver if one defined, with wakeup * straight to 64-bit mode preferred over wakeup to RM. * Otherwise, - * - Use an INIT boot APIC message for APs or NMI for BSP. + * - Use an INIT boot APIC message */ if (apic->wakeup_secondary_cpu_64) - boot_error = apic->wakeup_secondary_cpu_64(apicid, start_ip); + ret = apic->wakeup_secondary_cpu_64(apicid, start_ip); else if (apic->wakeup_secondary_cpu) - boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); + ret = apic->wakeup_secondary_cpu(apicid, start_ip); else - boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - cpu0_nmi_registered); - - if (!boot_error) { - /* - * Wait 10s total for first sign of life from AP - */ - boot_error = -1; - timeout = jiffies + 10*HZ; - while (time_before(jiffies, timeout)) { - if (cpumask_test_cpu(cpu, cpu_initialized_mask)) { - /* - * Tell AP to proceed with initialization - */ - cpumask_set_cpu(cpu, cpu_callout_mask); - boot_error = 0; - break; - } - schedule(); - } - } - - if (!boot_error) { - /* - * Wait till AP completes initial initialization - */ - while (!cpumask_test_cpu(cpu, cpu_callin_mask)) { - /* - * Allow other tasks to run while we wait for the - * AP to come online. This also gives a chance - * for the MTRR work(triggered by the AP coming online) - * to be completed in the stop machine context. - */ - schedule(); - } - } - - if (x86_platform.legacy.warm_reset) { - /* - * Cleanup possible dangling ends... - */ - smpboot_restore_warm_reset_vector(); - } + ret = wakeup_secondary_cpu_via_init(apicid, start_ip); - return boot_error; + /* If the wakeup mechanism failed, cleanup the warm reset vector */ + if (ret) + arch_cpuhp_cleanup_kick_cpu(cpu); + return ret; } -int native_cpu_up(unsigned int cpu, struct task_struct *tidle) +int native_kick_ap(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); - int cpu0_nmi_registered = 0; - unsigned long flags; - int err, ret = 0; + int err; lockdep_assert_irqs_enabled(); @@ -1210,24 +1103,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) } /* - * Already booted CPU? - */ - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - pr_debug("do_boot_cpu %d Already started\n", cpu); - return -ENOSYS; - } - - /* * Save current MTRR state in case it was changed since early boot * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync: */ mtrr_save_state(); - /* x86 CPUs take themselves offline, so delayed offline is OK. */ - err = cpu_check_up_prepare(cpu); - if (err && err != -EBUSY) - return err; - /* the FPU context is blank, nobody can own it */ per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; @@ -1235,41 +1115,44 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) if (err) return err; - err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); - if (err) { + err = do_boot_cpu(apicid, cpu, tidle); + if (err) pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - ret = -EIO; - goto unreg_nmi; - } - /* - * Check TSC synchronization with the AP (keep irqs disabled - * while doing so): - */ - local_irq_save(flags); - check_tsc_sync_source(cpu); - local_irq_restore(flags); + return err; +} - while (!cpu_online(cpu)) { - cpu_relax(); - touch_nmi_watchdog(); - } +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle) +{ + return smp_ops.kick_ap_alive(cpu, tidle); +} -unreg_nmi: - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); +void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) +{ + /* Cleanup possible dangling ends... */ + if (smp_ops.kick_ap_alive == native_kick_ap && x86_platform.legacy.warm_reset) + smpboot_restore_warm_reset_vector(); +} - return ret; +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ + if (smp_ops.cleanup_dead_cpu) + smp_ops.cleanup_dead_cpu(cpu); + + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); +} + +void arch_cpuhp_sync_state_poll(void) +{ + if (smp_ops.poll_sync_state) + smp_ops.poll_sync_state(); } /** - * arch_disable_smp_support() - disables SMP support for x86 at runtime + * arch_disable_smp_support() - Disables SMP support for x86 at boottime */ -void arch_disable_smp_support(void) +void __init arch_disable_smp_support(void) { disable_ioapic_support(); } @@ -1361,14 +1244,6 @@ static void __init smp_cpu_index_default(void) } } -static void __init smp_get_logical_apicid(void) -{ - if (x2apic_mode) - cpu0_logical_apicid = apic_read(APIC_LDR); - else - cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); -} - void __init smp_prepare_cpus_common(void) { unsigned int i; @@ -1379,7 +1254,6 @@ void __init smp_prepare_cpus_common(void) * Setup boot CPU information */ smp_store_boot_cpu_info(); /* Final full version of the data */ - cpumask_copy(cpu_callin_mask, cpumask_of(0)); mb(); for_each_possible_cpu(i) { @@ -1402,6 +1276,21 @@ void __init smp_prepare_cpus_common(void) set_cpu_sibling_map(0); } +#ifdef CONFIG_X86_64 +/* Establish whether parallel bringup can be supported. */ +bool __init arch_cpuhp_init_parallel_bringup(void) +{ + if (!x86_cpuinit.parallel_bringup) { + pr_info("Parallel CPU startup disabled by the platform\n"); + return false; + } + + smpboot_control = STARTUP_READ_APICID; + pr_debug("Parallel CPU startup enabled: 0x%08x\n", smpboot_control); + return true; +} +#endif + /* * Prepare for SMP bootup. * @max_cpus: configured maximum number of CPUs, It is a legacy parameter @@ -1431,8 +1320,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* Setup local timer */ x86_init.timers.setup_percpu_clockev(); - smp_get_logical_apicid(); - pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); @@ -1455,6 +1342,25 @@ void arch_thaw_secondary_cpus_end(void) cache_aps_init(); } +bool smp_park_other_cpus_in_init(void) +{ + unsigned int cpu, this_cpu = smp_processor_id(); + unsigned int apicid; + + if (apic->wakeup_secondary_cpu_64 || apic->wakeup_secondary_cpu) + return false; + + for_each_present_cpu(cpu) { + if (cpu == this_cpu) + continue; + apicid = apic->cpu_present_to_apicid(cpu); + if (apicid == BAD_APICID) + continue; + send_init_sequence(apicid); + } + return true; +} + /* * Early setup to make printk work. */ @@ -1466,9 +1372,6 @@ void __init native_smp_prepare_boot_cpu(void) if (!IS_ENABLED(CONFIG_SMP)) switch_gdt_and_percpu_base(me); - /* already set me in cpu_online_mask in boot_cpu_init() */ - cpumask_set_cpu(me, cpu_callout_mask); - cpu_set_state_online(me); native_pv_lock_init(); } @@ -1592,6 +1495,12 @@ __init void prefill_possible_map(void) set_cpu_possible(i, true); } +/* correctly size the local cpu masks */ +void __init setup_cpu_local_masks(void) +{ + alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); +} + #ifdef CONFIG_HOTPLUG_CPU /* Recompute SMT state for all CPUs on offline */ @@ -1650,10 +1559,6 @@ static void remove_siblinginfo(int cpu) static void remove_cpu_from_maps(int cpu) { set_cpu_online(cpu, false); - cpumask_clear_cpu(cpu, cpu_callout_mask); - cpumask_clear_cpu(cpu, cpu_callin_mask); - /* was set by cpu_init() */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); numa_remove_cpu(cpu); } @@ -1704,64 +1609,27 @@ int native_cpu_disable(void) return 0; } -int common_cpu_die(unsigned int cpu) -{ - int ret = 0; - - /* We don't do anything here: idle task is faking death itself. */ - - /* They ack this in play_dead() by setting CPU_DEAD */ - if (cpu_wait_death(cpu, 5)) { - if (system_state == SYSTEM_RUNNING) - pr_info("CPU %u is now offline\n", cpu); - } else { - pr_err("CPU %u didn't die...\n", cpu); - ret = -1; - } - - return ret; -} - -void native_cpu_die(unsigned int cpu) -{ - common_cpu_die(cpu); -} - void play_dead_common(void) { idle_task_exit(); - /* Ack it */ - (void)cpu_report_death(); - + cpuhp_ap_report_dead(); /* * With physical CPU hotplug, we should halt the cpu */ local_irq_disable(); } -/** - * cond_wakeup_cpu0 - Wake up CPU0 if needed. - * - * If NMI wants to wake up CPU0, start CPU0. - */ -void cond_wakeup_cpu0(void) -{ - if (smp_processor_id() == 0 && enable_start_cpu0) - start_cpu0(); -} -EXPORT_SYMBOL_GPL(cond_wakeup_cpu0); - /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. */ static inline void mwait_play_dead(void) { + struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); unsigned int eax, ebx, ecx, edx; unsigned int highest_cstate = 0; unsigned int highest_subcstate = 0; - void *mwait_ptr; int i; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || @@ -1796,12 +1664,9 @@ static inline void mwait_play_dead(void) (highest_subcstate - 1); } - /* - * This should be a memory location in a cache line which is - * unlikely to be touched by other processors. The actual - * content is immaterial as it is not actually modified in any way. - */ - mwait_ptr = ¤t_thread_info()->flags; + /* Set up state for the kexec() hack below */ + md->status = CPUDEAD_MWAIT_WAIT; + md->control = CPUDEAD_MWAIT_WAIT; wbinvd(); @@ -1814,13 +1679,58 @@ static inline void mwait_play_dead(void) * case where we return around the loop. */ mb(); - clflush(mwait_ptr); + clflush(md); mb(); - __monitor(mwait_ptr, 0, 0); + __monitor(md, 0, 0); mb(); __mwait(eax, 0); - cond_wakeup_cpu0(); + if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) { + /* + * Kexec is about to happen. Don't go back into mwait() as + * the kexec kernel might overwrite text and data including + * page tables and stack. So mwait() would resume when the + * monitor cache line is written to and then the CPU goes + * south due to overwritten text, page tables and stack. + * + * Note: This does _NOT_ protect against a stray MCE, NMI, + * SMI. They will resume execution at the instruction + * following the HLT instruction and run into the problem + * which this is trying to prevent. + */ + WRITE_ONCE(md->status, CPUDEAD_MWAIT_KEXEC_HLT); + while(1) + native_halt(); + } + } +} + +/* + * Kick all "offline" CPUs out of mwait on kexec(). See comment in + * mwait_play_dead(). + */ +void smp_kick_mwait_play_dead(void) +{ + u32 newstate = CPUDEAD_MWAIT_KEXEC_HLT; + struct mwait_cpu_dead *md; + unsigned int cpu, i; + + for_each_cpu_andnot(cpu, cpu_present_mask, cpu_online_mask) { + md = per_cpu_ptr(&mwait_cpu_dead, cpu); + + /* Does it sit in mwait_play_dead() ? */ + if (READ_ONCE(md->status) != CPUDEAD_MWAIT_WAIT) + continue; + + /* Wait up to 5ms */ + for (i = 0; READ_ONCE(md->status) != newstate && i < 1000; i++) { + /* Bring it out of mwait */ + WRITE_ONCE(md->control, newstate); + udelay(5); + } + + if (READ_ONCE(md->status) != newstate) + pr_err_once("CPU%u is stuck in mwait_play_dead()\n", cpu); } } @@ -1829,11 +1739,8 @@ void __noreturn hlt_play_dead(void) if (__this_cpu_read(cpu_info.x86) >= 4) wbinvd(); - while (1) { + while (1) native_halt(); - - cond_wakeup_cpu0(); - } } void native_play_dead(void) @@ -1852,12 +1759,6 @@ int native_cpu_disable(void) return -ENOSYS; } -void native_cpu_die(unsigned int cpu) -{ - /* We said "no" in __cpu_disable */ - BUG(); -} - void native_play_dead(void) { BUG(); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 1b83377274b8..ca004e2e4469 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -38,102 +38,12 @@ static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU - -#ifdef CONFIG_BOOTPARAM_HOTPLUG_CPU0 -static int cpu0_hotpluggable = 1; -#else -static int cpu0_hotpluggable; -static int __init enable_cpu0_hotplug(char *str) -{ - cpu0_hotpluggable = 1; - return 1; -} - -__setup("cpu0_hotplug", enable_cpu0_hotplug); -#endif - -#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 -/* - * This function offlines a CPU as early as possible and allows userspace to - * boot up without the CPU. The CPU can be onlined back by user after boot. - * - * This is only called for debugging CPU offline/online feature. - */ -int _debug_hotplug_cpu(int cpu, int action) +int arch_register_cpu(int cpu) { - int ret; - - if (!cpu_is_hotpluggable(cpu)) - return -EINVAL; + struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu); - switch (action) { - case 0: - ret = remove_cpu(cpu); - if (!ret) - pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu); - else - pr_debug("Can't offline CPU%d.\n", cpu); - break; - case 1: - ret = add_cpu(cpu); - if (ret) - pr_debug("Can't online CPU%d.\n", cpu); - - break; - default: - ret = -EINVAL; - } - - return ret; -} - -static int __init debug_hotplug_cpu(void) -{ - _debug_hotplug_cpu(0, 0); - return 0; -} - -late_initcall_sync(debug_hotplug_cpu); -#endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ - -int arch_register_cpu(int num) -{ - struct cpuinfo_x86 *c = &cpu_data(num); - - /* - * Currently CPU0 is only hotpluggable on Intel platforms. Other - * vendors can add hotplug support later. - * Xen PV guests don't support CPU0 hotplug at all. - */ - if (c->x86_vendor != X86_VENDOR_INTEL || - cpu_feature_enabled(X86_FEATURE_XENPV)) - cpu0_hotpluggable = 0; - - /* - * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate - * depends on BSP. PIC interrupts depend on BSP. - * - * If the BSP dependencies are under control, one can tell kernel to - * enable BSP hotplug. This basically adds a control file and - * one can attempt to offline BSP. - */ - if (num == 0 && cpu0_hotpluggable) { - unsigned int irq; - /* - * We won't take down the boot processor on i386 if some - * interrupts only are able to be serviced by the BSP in PIC. - */ - for_each_active_irq(irq) { - if (!IO_APIC_IRQ(irq) && irq_has_action(irq)) { - cpu0_hotpluggable = 0; - break; - } - } - } - if (num || cpu0_hotpluggable) - per_cpu(cpu_devices, num).cpu.hotpluggable = 1; - - return register_cpu(&per_cpu(cpu_devices, num).cpu, num); + xc->cpu.hotpluggable = cpu > 0; + return register_cpu(&xc->cpu, cpu); } EXPORT_SYMBOL(arch_register_cpu); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 344698852146..1412b771651e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1598,10 +1598,7 @@ void __init tsc_init(void) #ifdef CONFIG_SMP /* - * If we have a constant TSC and are using the TSC for the delay loop, - * we can skip clock calibration if another cpu in the same socket has already - * been calibrated. This assumes that CONSTANT_TSC applies to all - * cpus in the socket - this should be a safe assumption. + * Check whether existing calibration data can be reused. */ unsigned long calibrate_delay_is_known(void) { @@ -1609,6 +1606,21 @@ unsigned long calibrate_delay_is_known(void) int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); const struct cpumask *mask = topology_core_cpumask(cpu); + /* + * If TSC has constant frequency and TSC is synchronized across + * sockets then reuse CPU0 calibration. + */ + if (constant_tsc && !tsc_unstable) + return cpu_data(0).loops_per_jiffy; + + /* + * If TSC has constant frequency and TSC is not synchronized across + * sockets and this is not the first CPU in the socket, then reuse + * the calibration value of an already online CPU on that socket. + * + * This assumes that CONSTANT_TSC is consistent for all CPUs in a + * socket. + */ if (!constant_tsc || !mask) return 0; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 9452dc9664b5..bbc440c93e08 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -245,7 +245,6 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) */ static atomic_t start_count; static atomic_t stop_count; -static atomic_t skip_test; static atomic_t test_runs; /* @@ -344,21 +343,14 @@ static inline unsigned int loop_timeout(int cpu) } /* - * Source CPU calls into this - it waits for the freshly booted - * target CPU to arrive and then starts the measurement: + * The freshly booted CPU initiates this via an async SMP function call. */ -void check_tsc_sync_source(int cpu) +static void check_tsc_sync_source(void *__cpu) { + unsigned int cpu = (unsigned long)__cpu; int cpus = 2; /* - * No need to check if we already know that the TSC is not - * synchronized or if we have no TSC. - */ - if (unsynchronized_tsc()) - return; - - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR * 3 if the MSR is available, so the target can try to adjust @@ -368,16 +360,9 @@ void check_tsc_sync_source(int cpu) else atomic_set(&test_runs, 3); retry: - /* - * Wait for the target to start or to skip the test: - */ - while (atomic_read(&start_count) != cpus - 1) { - if (atomic_read(&skip_test) > 0) { - atomic_set(&skip_test, 0); - return; - } + /* Wait for the target to start. */ + while (atomic_read(&start_count) != cpus - 1) cpu_relax(); - } /* * Trigger the target to continue into the measurement too: @@ -397,14 +382,14 @@ retry: if (!nr_warps) { atomic_set(&test_runs, 0); - pr_debug("TSC synchronization [CPU#%d -> CPU#%d]: passed\n", + pr_debug("TSC synchronization [CPU#%d -> CPU#%u]: passed\n", smp_processor_id(), cpu); } else if (atomic_dec_and_test(&test_runs) || random_warps) { /* Force it to 0 if random warps brought us here */ atomic_set(&test_runs, 0); - pr_warn("TSC synchronization [CPU#%d -> CPU#%d]:\n", + pr_warn("TSC synchronization [CPU#%d -> CPU#%u]:\n", smp_processor_id(), cpu); pr_warn("Measured %Ld cycles TSC warp between CPUs, " "turning off TSC clock.\n", max_warp); @@ -457,11 +442,12 @@ void check_tsc_sync_target(void) * SoCs the TSC is frequency synchronized, but still the TSC ADJUST * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { - atomic_inc(&skip_test); + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) return; - } + /* Kick the control CPU into the TSC synchronization function */ + smp_call_function_single(cpumask_first(cpu_online_mask), check_tsc_sync_source, + (unsigned long *)(unsigned long)cpu, 0); retry: /* * Register this CPU's participation and wait for the diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 3ac50b7298d1..4d8e518365f4 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -7,6 +7,9 @@ #include <asm/unwind.h> #include <asm/orc_types.h> #include <asm/orc_lookup.h> +#include <asm/orc_header.h> + +ORC_HEADER; #define orc_warn(fmt, ...) \ printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index d82f4fa2f1bf..1da4baa34d1b 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -126,6 +126,7 @@ struct x86_init_ops x86_init __initdata = { struct x86_cpuinit_ops x86_cpuinit = { .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, + .parallel_bringup = true, }; static void default_nmi_init(void) { }; diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 02661861e5dd..0559b206fb11 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -38,10 +38,12 @@ SYM_FUNC_START(__memmove) cmp %rdi, %r8 jg 2f - /* FSRM implies ERMS => no length checks, do the copy directly */ +#define CHECK_LEN cmp $0x20, %rdx; jb 1f +#define MEMMOVE_BYTES movq %rdx, %rcx; rep movsb; RET .Lmemmove_begin_forward: - ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM - ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS + ALTERNATIVE_2 __stringify(CHECK_LEN), \ + __stringify(CHECK_LEN; MEMMOVE_BYTES), X86_FEATURE_ERMS, \ + __stringify(MEMMOVE_BYTES), X86_FEATURE_FSRM /* * movsq instruction have many startup latency @@ -207,11 +209,6 @@ SYM_FUNC_START(__memmove) movb %r11b, (%rdi) 13: RET - -.Lmemmove_erms: - movq %rdx, %rcx - rep movsb - RET SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 557f0fe25dff..37db264866b6 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -172,10 +172,10 @@ void __meminit init_trampoline_kaslr(void) set_p4d(p4d_tramp, __p4d(_KERNPG_TABLE | __pa(pud_page_tramp))); - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)); } else { - set_pgd(&trampoline_pgd_entry, - __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); + trampoline_pgd_entry = + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp)); } } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index e0b51c09109f..4855e5f92970 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -501,6 +501,21 @@ void __init sme_early_init(void) x86_platform.guest.enc_status_change_finish = amd_enc_status_change_finish; x86_platform.guest.enc_tlb_flush_required = amd_enc_tlb_flush_required; x86_platform.guest.enc_cache_flush_required = amd_enc_cache_flush_required; + + /* + * AMD-SEV-ES intercepts the RDMSR to read the X2APIC ID in the + * parallel bringup low level code. That raises #VC which cannot be + * handled there. + * It does not provide a RDMSR GHCB protocol so the early startup + * code cannot directly communicate with the secure firmware. The + * alternative solution to retrieve the APIC ID via CPUID(0xb), + * which is covered by the GHCB protocol, is not viable either + * because there is no enforcement of the CPUID(0xb) provided + * "initial" APIC ID to be the same as the real APIC ID. + * Disable parallel bootup. + */ + if (sev_status & MSR_AMD64_SEV_ES_ENABLED) + x86_cpuinit.parallel_bringup = false; } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 7159cf787613..d1515756e369 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/seq_file.h> +#include <linux/proc_fs.h> #include <linux/debugfs.h> #include <linux/pfn.h> #include <linux/percpu.h> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 1056bbf55b17..438adb695daa 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2570,7 +2570,7 @@ out_image: } if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, proglen, pass + 1, image); + bpf_jit_dump(prog->len, proglen, pass + 1, rw_image); if (image) { if (!prog->is_func || extra_pass) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 7a4d5e911415..63230ff8cf4f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -351,43 +351,6 @@ static int bsp_pm_callback(struct notifier_block *nb, unsigned long action, case PM_HIBERNATION_PREPARE: ret = bsp_check(); break; -#ifdef CONFIG_DEBUG_HOTPLUG_CPU0 - case PM_RESTORE_PREPARE: - /* - * When system resumes from hibernation, online CPU0 because - * 1. it's required for resume and - * 2. the CPU was online before hibernation - */ - if (!cpu_online(0)) - _debug_hotplug_cpu(0, 1); - break; - case PM_POST_RESTORE: - /* - * When a resume really happens, this code won't be called. - * - * This code is called only when user space hibernation software - * prepares for snapshot device during boot time. So we just - * call _debug_hotplug_cpu() to restore to CPU0's state prior to - * preparing the snapshot device. - * - * This works for normal boot case in our CPU0 hotplug debug - * mode, i.e. CPU0 is offline and user mode hibernation - * software initializes during boot time. - * - * If CPU0 is online and user application accesses snapshot - * device after boot time, this will offline CPU0 and user may - * see different CPU0 state before and after accessing - * the snapshot device. But hopefully this is not a case when - * user debugging CPU0 hotplug. Even if users hit this case, - * they can easily online CPU0 back. - * - * To simplify this debug code, we only consider normal boot - * case. Otherwise we need to remember CPU0's state and restore - * to that state and resolve racy conditions etc. - */ - _debug_hotplug_cpu(0, 0); - break; -#endif default: break; } diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 82fec66d46d2..42abd6af1198 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -14,6 +14,11 @@ $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE CFLAGS_sha256.o := -D__DISABLE_EXPORTS +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + # When linking purgatory.ro with -r unresolved symbols are not checked, # also link a purgatory.chk binary without -r to check for unresolved symbols. PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index af565816d2ba..788e5559549f 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -154,6 +154,9 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; + trampoline_lock = &trampoline_header->lock; + *trampoline_lock = 0; + trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); /* Map the real mode stub as virtual == physical */ diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index e38d61d6562e..c9f76fae902e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -37,6 +37,24 @@ .text .code16 +.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 + /* + * Make sure only one CPU fiddles with the realmode stack + */ +.Llock_rm\@: + .if \lock_pa + lock btsl $0, pa_tr_lock + .else + lock btsl $0, tr_lock + .endif + jnc 2f + pause + jmp .Llock_rm\@ +2: + # Setup stack + movl $rm_stack_end, %esp +.endm + .balign PAGE_SIZE SYM_CODE_START(trampoline_start) cli # We should be safe anyway @@ -49,8 +67,7 @@ SYM_CODE_START(trampoline_start) mov %ax, %es mov %ax, %ss - # Setup stack - movl $rm_stack_end, %esp + LOCK_AND_LOAD_REALMODE_ESP call verify_cpu # Verify the cpu supports long mode testl %eax, %eax # Check for return code @@ -93,8 +110,7 @@ SYM_CODE_START(sev_es_trampoline_start) mov %ax, %es mov %ax, %ss - # Setup stack - movl $rm_stack_end, %esp + LOCK_AND_LOAD_REALMODE_ESP jmp .Lswitch_to_protected SYM_CODE_END(sev_es_trampoline_start) @@ -177,7 +193,7 @@ SYM_CODE_START(pa_trampoline_compat) * In compatibility mode. Prep ESP and DX for startup_32, then disable * paging and complete the switch to legacy 32-bit mode. */ - movl $rm_stack_end, %esp + LOCK_AND_LOAD_REALMODE_ESP lock_pa=1 movw $__KERNEL_DS, %dx movl $(CR0_STATE & ~X86_CR0_PG), %eax @@ -241,6 +257,7 @@ SYM_DATA_START(trampoline_header) SYM_DATA(tr_efer, .space 8) SYM_DATA(tr_cr4, .space 4) SYM_DATA(tr_flags, .space 4) + SYM_DATA(tr_lock, .space 4) SYM_DATA_END(trampoline_header) #include "trampoline_common.S" diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index c1cd28e915a3..a6820ca940bf 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -161,13 +161,12 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) int rc = 0; /* - * This can happen if CPU was offlined earlier and - * offlining timed out in common_cpu_die(). + * If a CPU was offlined earlier and offlining timed out then the + * lock mechanism is still initialized. Uninit it unconditionally + * as it's safe to call even if already uninited. Interrupts and + * timer have already been handled in xen_cpu_dead_hvm(). */ - if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - } + xen_uninit_lock_cpu(cpu); if (cpu_acpi_id(cpu) != U32_MAX) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index b70afdff419c..ac95d1981cc0 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -55,18 +55,16 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) } #ifdef CONFIG_HOTPLUG_CPU -static void xen_hvm_cpu_die(unsigned int cpu) +static void xen_hvm_cleanup_dead_cpu(unsigned int cpu) { - if (common_cpu_die(cpu) == 0) { - if (xen_have_vector_callback) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); - } + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); } } #else -static void xen_hvm_cpu_die(unsigned int cpu) +static void xen_hvm_cleanup_dead_cpu(unsigned int cpu) { BUG(); } @@ -77,7 +75,7 @@ void __init xen_hvm_smp_init(void) smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_cpus_done = xen_smp_cpus_done; - smp_ops.cpu_die = xen_hvm_cpu_die; + smp_ops.cleanup_dead_cpu = xen_hvm_cleanup_dead_cpu; if (!xen_have_vector_callback) { #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index a9cf8c8fa074..a92e8002b5cf 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -62,6 +62,7 @@ static void cpu_bringup(void) int cpu; cr4_init(); + cpuhp_ap_sync_alive(); cpu_init(); touch_softlockup_watchdog(); @@ -83,7 +84,7 @@ static void cpu_bringup(void) set_cpu_online(cpu, true); - cpu_set_state_online(cpu); /* Implies full memory barrier. */ + smp_mb(); /* We can take interrupts now: we're officially "up". */ local_irq_enable(); @@ -254,15 +255,12 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) struct desc_struct *gdt; unsigned long gdt_mfn; - /* used to tell cpu_init() that it can proceed with initialization */ - cpumask_set_cpu(cpu, cpu_callout_mask); if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) return 0; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (ctxt == NULL) { cpumask_clear_cpu(cpu, xen_cpu_initialized_map); - cpumask_clear_cpu(cpu, cpu_callout_mask); return -ENOMEM; } @@ -316,7 +314,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) return 0; } -static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) +static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle) { int rc; @@ -326,14 +324,6 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) xen_setup_runstate_info(cpu); - /* - * PV VCPUs are always successfully taken down (see 'while' loop - * in xen_cpu_die()), so -EBUSY is an error. - */ - rc = cpu_check_up_prepare(cpu); - if (rc) - return rc; - /* make sure interrupts start blocked */ per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1; @@ -343,15 +333,20 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) xen_pmu_init(cpu); - rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL); - BUG_ON(rc); - - while (cpu_report_state(cpu) != CPU_ONLINE) - HYPERVISOR_sched_op(SCHEDOP_yield, NULL); + /* + * Why is this a BUG? If the hypercall fails then everything can be + * rolled back, no? + */ + BUG_ON(HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL)); return 0; } +static void xen_pv_poll_sync_state(void) +{ + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); +} + #ifdef CONFIG_HOTPLUG_CPU static int xen_pv_cpu_disable(void) { @@ -367,18 +362,18 @@ static int xen_pv_cpu_disable(void) static void xen_pv_cpu_die(unsigned int cpu) { - while (HYPERVISOR_vcpu_op(VCPUOP_is_up, - xen_vcpu_nr(cpu), NULL)) { + while (HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu), NULL)) { __set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(HZ/10); } +} - if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); - xen_pmu_finish(cpu); - } +static void xen_pv_cleanup_dead_cpu(unsigned int cpu) +{ + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + xen_pmu_finish(cpu); } static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ @@ -400,6 +395,11 @@ static void xen_pv_cpu_die(unsigned int cpu) BUG(); } +static void xen_pv_cleanup_dead_cpu(unsigned int cpu) +{ + BUG(); +} + static void __noreturn xen_pv_play_dead(void) { BUG(); @@ -438,8 +438,10 @@ static const struct smp_ops xen_smp_ops __initconst = { .smp_prepare_cpus = xen_pv_smp_prepare_cpus, .smp_cpus_done = xen_smp_cpus_done, - .cpu_up = xen_pv_cpu_up, + .kick_ap_alive = xen_pv_kick_ap, .cpu_die = xen_pv_cpu_die, + .cleanup_dead_cpu = xen_pv_cleanup_dead_cpu, + .poll_sync_state = xen_pv_poll_sync_state, .cpu_disable = xen_pv_cpu_disable, .play_dead = xen_pv_play_dead, diff --git a/arch/xtensa/include/asm/bugs.h b/arch/xtensa/include/asm/bugs.h deleted file mode 100644 index 69b29d198249..000000000000 --- a/arch/xtensa/include/asm/bugs.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * include/asm-xtensa/bugs.h - * - * This is included by init/main.c to check for architecture-dependent bugs. - * - * Xtensa processors don't have any bugs. :) - * - * This file is subject to the terms and conditions of the GNU General - * Public License. See the file "COPYING" in the main directory of - * this archive for more details. - */ - -#ifndef _XTENSA_BUGS_H -#define _XTENSA_BUGS_H - -static void check_bugs(void) { } - -#endif /* _XTENSA_BUGS_H */ diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index f50caaa1c249..178cf96ca10a 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -120,9 +120,9 @@ static void simdisk_submit_bio(struct bio *bio) bio_endio(bio); } -static int simdisk_open(struct block_device *bdev, fmode_t mode) +static int simdisk_open(struct gendisk *disk, blk_mode_t mode) { - struct simdisk *dev = bdev->bd_disk->private_data; + struct simdisk *dev = disk->private_data; spin_lock(&dev->lock); ++dev->users; @@ -130,7 +130,7 @@ static int simdisk_open(struct block_device *bdev, fmode_t mode) return 0; } -static void simdisk_release(struct gendisk *disk, fmode_t mode) +static void simdisk_release(struct gendisk *disk) { struct simdisk *dev = disk->private_data; spin_lock(&dev->lock); diff --git a/block/Makefile b/block/Makefile index b31b05390749..46ada9dc8bbf 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,7 +9,7 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ - disk-events.o blk-ia-ranges.o + disk-events.o blk-ia-ranges.o early-lookup.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o diff --git a/block/bdev.c b/block/bdev.c index 21c63bfef323..979e28a46b98 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -93,7 +93,7 @@ EXPORT_SYMBOL(invalidate_bdev); * Drop all buffers & page cache for given bdev range. This function bails * with error if bdev has other exclusive owner (such as filesystem). */ -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, +int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, loff_t lstart, loff_t lend) { /* @@ -101,14 +101,14 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, * while we discard the buffer cache to avoid discarding buffers * under live filesystem. */ - if (!(mode & FMODE_EXCL)) { - int err = bd_prepare_to_claim(bdev, truncate_bdev_range); + if (!(mode & BLK_OPEN_EXCL)) { + int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL); if (err) goto invalidate; } truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, truncate_bdev_range); return 0; @@ -308,7 +308,7 @@ EXPORT_SYMBOL(thaw_bdev); * pseudo-fs */ -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); +static __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock); static struct kmem_cache * bdev_cachep __read_mostly; static struct inode *bdev_alloc_inode(struct super_block *sb) @@ -415,6 +415,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev = I_BDEV(inode); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); + mutex_init(&bdev->bd_holder_lock); bdev->bd_partno = partno; bdev->bd_inode = inode; bdev->bd_queue = disk->queue; @@ -463,39 +464,48 @@ long nr_blockdev_pages(void) /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest - * @whole: whole block device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev + * @hops: holder ops * * Test whether @bdev can be claimed by @holder. * - * CONTEXT: - * spin_lock(&bdev_lock). - * * RETURNS: * %true if @bdev can be claimed, %false otherwise. */ -static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, - void *holder) +static bool bd_may_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { - if (bdev->bd_holder == holder) - return true; /* already a holder */ - else if (bdev->bd_holder != NULL) - return false; /* held by someone else */ - else if (whole == bdev) - return true; /* is a whole device which isn't held */ - - else if (whole->bd_holder == bd_may_claim) - return true; /* is a partition of a device that is being partitioned */ - else if (whole->bd_holder != NULL) - return false; /* is a partition of a held device */ - else - return true; /* is a partition of an un-held device */ + struct block_device *whole = bdev_whole(bdev); + + lockdep_assert_held(&bdev_lock); + + if (bdev->bd_holder) { + /* + * The same holder can always re-claim. + */ + if (bdev->bd_holder == holder) { + if (WARN_ON_ONCE(bdev->bd_holder_ops != hops)) + return false; + return true; + } + return false; + } + + /* + * If the whole devices holder is set to bd_may_claim, a partition on + * the device is claimed, but not the whole device. + */ + if (whole != bdev && + whole->bd_holder && whole->bd_holder != bd_may_claim) + return false; + return true; } /** * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @holder: holder trying to claim @bdev + * @hops: holder ops. * * Claim @bdev. This function fails if @bdev is already claimed by another * holder and waits if another claiming is in progress. return, the caller @@ -504,17 +514,18 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ -int bd_prepare_to_claim(struct block_device *bdev, void *holder) +int bd_prepare_to_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); if (WARN_ON_ONCE(!holder)) return -EINVAL; retry: - spin_lock(&bdev_lock); + mutex_lock(&bdev_lock); /* if someone else claimed, fail */ - if (!bd_may_claim(bdev, whole, holder)) { - spin_unlock(&bdev_lock); + if (!bd_may_claim(bdev, holder, hops)) { + mutex_unlock(&bdev_lock); return -EBUSY; } @@ -524,7 +535,7 @@ retry: DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); goto retry; @@ -532,7 +543,7 @@ retry: /* yay, all mine */ whole->bd_claiming = holder; - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); return 0; } EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ @@ -550,16 +561,18 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest * @holder: holder that has claimed @bdev + * @hops: block device holder operations * * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ -static void bd_finish_claiming(struct block_device *bdev, void *holder) +static void bd_finish_claiming(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); - spin_lock(&bdev_lock); - BUG_ON(!bd_may_claim(bdev, whole, holder)); + mutex_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, holder, hops)); /* * Note that for a whole device bd_holders will be incremented twice, * and bd_holder will be set to bd_may_claim before being set to holder @@ -567,9 +580,12 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) whole->bd_holders++; whole->bd_holder = bd_may_claim; bdev->bd_holders++; + mutex_lock(&bdev->bd_holder_lock); bdev->bd_holder = holder; + bdev->bd_holder_ops = hops; + mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); } /** @@ -583,12 +599,47 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) */ void bd_abort_claiming(struct block_device *bdev, void *holder) { - spin_lock(&bdev_lock); + mutex_lock(&bdev_lock); bd_clear_claiming(bdev_whole(bdev), holder); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); } EXPORT_SYMBOL(bd_abort_claiming); +static void bd_end_claim(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev_whole(bdev); + bool unblock = false; + + /* + * Release a claim on the device. The holder fields are protected with + * bdev_lock. open_mutex is used to synchronize disk_holder unlinking. + */ + mutex_lock(&bdev_lock); + WARN_ON_ONCE(bdev->bd_holder != holder); + WARN_ON_ONCE(--bdev->bd_holders < 0); + WARN_ON_ONCE(--whole->bd_holders < 0); + if (!bdev->bd_holders) { + mutex_lock(&bdev->bd_holder_lock); + bdev->bd_holder = NULL; + bdev->bd_holder_ops = NULL; + mutex_unlock(&bdev->bd_holder_lock); + if (bdev->bd_write_holder) + unblock = true; + } + if (!whole->bd_holders) + whole->bd_holder = NULL; + mutex_unlock(&bdev_lock); + + /* + * If this was the last claim, remove holder link and unblock evpoll if + * it was a write holder. + */ + if (unblock) { + disk_unblock_events(bdev->bd_disk); + bdev->bd_write_holder = false; + } +} + static void blkdev_flush_mapping(struct block_device *bdev) { WARN_ON_ONCE(bdev->bd_holders); @@ -597,13 +648,13 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } -static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) +static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; int ret; if (disk->fops->open) { - ret = disk->fops->open(bdev, mode); + ret = disk->fops->open(disk, mode); if (ret) { /* avoid ghost partitions on a removed medium */ if (ret == -ENOMEDIUM && @@ -621,22 +672,19 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) return 0; } -static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) +static void blkdev_put_whole(struct block_device *bdev) { if (atomic_dec_and_test(&bdev->bd_openers)) blkdev_flush_mapping(bdev); if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk, mode); + bdev->bd_disk->fops->release(bdev->bd_disk); } -static int blkdev_get_part(struct block_device *part, fmode_t mode) +static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; int ret; - if (atomic_read(&part->bd_openers)) - goto done; - ret = blkdev_get_whole(bdev_whole(part), mode); if (ret) return ret; @@ -645,26 +693,27 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) if (!bdev_nr_sectors(part)) goto out_blkdev_put; - disk->open_partitions++; - set_init_blocksize(part); -done: + if (!atomic_read(&part->bd_openers)) { + disk->open_partitions++; + set_init_blocksize(part); + } atomic_inc(&part->bd_openers); return 0; out_blkdev_put: - blkdev_put_whole(bdev_whole(part), mode); + blkdev_put_whole(bdev_whole(part)); return ret; } -static void blkdev_put_part(struct block_device *part, fmode_t mode) +static void blkdev_put_part(struct block_device *part) { struct block_device *whole = bdev_whole(part); - if (!atomic_dec_and_test(&part->bd_openers)) - return; - blkdev_flush_mapping(part); - whole->bd_disk->open_partitions--; - blkdev_put_whole(whole, mode); + if (atomic_dec_and_test(&part->bd_openers)) { + blkdev_flush_mapping(part); + whole->bd_disk->open_partitions--; + } + blkdev_put_whole(whole); } struct block_device *blkdev_get_no_open(dev_t dev) @@ -695,17 +744,17 @@ void blkdev_put_no_open(struct block_device *bdev) { put_device(&bdev->bd_device); } - + /** * blkdev_get_by_dev - open a block device by device number * @dev: device number of block device to open - * @mode: FMODE_* mask + * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier + * @hops: holder operations * - * Open the block device described by device number @dev. If @mode includes - * %FMODE_EXCL, the block device is opened with exclusive access. Specifying - * %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for - * the same @holder. + * Open the block device described by device number @dev. If @holder is not + * %NULL, the block device is opened with exclusive access. Exclusive opens may + * nest for the same @holder. * * Use this interface ONLY if you really do not have anything better - i.e. when * you are behind a truly sucky interface and all you are given is a device @@ -717,7 +766,8 @@ void blkdev_put_no_open(struct block_device *bdev) * RETURNS: * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) +struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops) { bool unblock_events = true; struct block_device *bdev; @@ -726,8 +776,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, MAJOR(dev), MINOR(dev), - ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | - ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); + ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | + ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) return ERR_PTR(ret); @@ -736,10 +786,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) return ERR_PTR(-ENXIO); disk = bdev->bd_disk; - if (mode & FMODE_EXCL) { - ret = bd_prepare_to_claim(bdev, holder); + if (holder) { + mode |= BLK_OPEN_EXCL; + ret = bd_prepare_to_claim(bdev, holder, hops); if (ret) goto put_blkdev; + } else { + if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) { + ret = -EIO; + goto put_blkdev; + } } disk_block_events(disk); @@ -756,8 +812,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) ret = blkdev_get_whole(bdev, mode); if (ret) goto put_module; - if (mode & FMODE_EXCL) { - bd_finish_claiming(bdev, holder); + if (holder) { + bd_finish_claiming(bdev, holder, hops); /* * Block event polling for write claims if requested. Any write @@ -766,7 +822,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) * writeable reference is too fragile given the way @mode is * used in blkdev_get/put(). */ - if ((mode & FMODE_WRITE) && !bdev->bd_write_holder && + if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder && (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) { bdev->bd_write_holder = true; unblock_events = false; @@ -780,7 +836,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) put_module: module_put(disk->fops->owner); abort_claiming: - if (mode & FMODE_EXCL) + if (holder) bd_abort_claiming(bdev, holder); mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); @@ -793,13 +849,13 @@ EXPORT_SYMBOL(blkdev_get_by_dev); /** * blkdev_get_by_path - open a block device by name * @path: path to the block device to open - * @mode: FMODE_* mask + * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier + * @hops: holder operations * - * Open the block device described by the device file at @path. If @mode - * includes %FMODE_EXCL, the block device is opened with exclusive access. - * Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may - * nest for the same @holder. + * Open the block device described by the device file at @path. If @holder is + * not %NULL, the block device is opened with exclusive access. Exclusive opens + * may nest for the same @holder. * * CONTEXT: * Might sleep. @@ -807,8 +863,8 @@ EXPORT_SYMBOL(blkdev_get_by_dev); * RETURNS: * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ -struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder) +struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops) { struct block_device *bdev; dev_t dev; @@ -818,9 +874,9 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, if (error) return ERR_PTR(error); - bdev = blkdev_get_by_dev(dev, mode, holder); - if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, mode); + bdev = blkdev_get_by_dev(dev, mode, holder, hops); + if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { + blkdev_put(bdev, holder); return ERR_PTR(-EACCES); } @@ -828,7 +884,7 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, } EXPORT_SYMBOL(blkdev_get_by_path); -void blkdev_put(struct block_device *bdev, fmode_t mode) +void blkdev_put(struct block_device *bdev, void *holder) { struct gendisk *disk = bdev->bd_disk; @@ -843,36 +899,8 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); - if (mode & FMODE_EXCL) { - struct block_device *whole = bdev_whole(bdev); - bool bdev_free; - - /* - * Release a claim on the device. The holder fields - * are protected with bdev_lock. open_mutex is to - * synchronize disk_holder unlinking. - */ - spin_lock(&bdev_lock); - - WARN_ON_ONCE(--bdev->bd_holders < 0); - WARN_ON_ONCE(--whole->bd_holders < 0); - - if ((bdev_free = !bdev->bd_holders)) - bdev->bd_holder = NULL; - if (!whole->bd_holders) - whole->bd_holder = NULL; - - spin_unlock(&bdev_lock); - - /* - * If this was the last claim, remove holder link and - * unblock evpoll if it was a write holder. - */ - if (bdev_free && bdev->bd_write_holder) { - disk_unblock_events(disk); - bdev->bd_write_holder = false; - } - } + if (holder) + bd_end_claim(bdev, holder); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -882,9 +910,9 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); if (bdev_is_partition(bdev)) - blkdev_put_part(bdev, mode); + blkdev_put_part(bdev); else - blkdev_put_whole(bdev, mode); + blkdev_put_whole(bdev); mutex_unlock(&disk->open_mutex); module_put(disk->fops->owner); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3164e3177965..09bbbcf9e049 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5403,6 +5403,10 @@ void bfq_put_queue(struct bfq_queue *bfqq) if (bfqq->bfqd->last_completed_rq_bfqq == bfqq) bfqq->bfqd->last_completed_rq_bfqq = NULL; + WARN_ON_ONCE(!list_empty(&bfqq->fifo)); + WARN_ON_ONCE(!RB_EMPTY_ROOT(&bfqq->sort_list)); + WARN_ON_ONCE(bfqq->dispatched); + kmem_cache_free(bfq_pool, bfqq); bfqg_and_blkg_put(bfqg); } @@ -7135,6 +7139,7 @@ static void bfq_exit_queue(struct elevator_queue *e) { struct bfq_data *bfqd = e->elevator_data; struct bfq_queue *bfqq, *n; + unsigned int actuator; hrtimer_cancel(&bfqd->idle_slice_timer); @@ -7143,6 +7148,10 @@ static void bfq_exit_queue(struct elevator_queue *e) bfq_deactivate_bfqq(bfqd, bfqq, false, false); spin_unlock_irq(&bfqd->lock); + for (actuator = 0; actuator < bfqd->num_actuators; actuator++) + WARN_ON_ONCE(bfqd->rq_in_driver[actuator]); + WARN_ON_ONCE(bfqd->tot_rq_in_driver); + hrtimer_cancel(&bfqd->idle_slice_timer); /* release oom-queue reference to root group */ diff --git a/block/bio.c b/block/bio.c index 043944fd46eb..8672179213b9 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1138,6 +1138,14 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off) +{ + WARN_ON_ONCE(len > UINT_MAX); + WARN_ON_ONCE(off > UINT_MAX); + __bio_add_page(bio, &folio->page, len, off); +} + /** * bio_add_folio - Attempt to add part of a folio to a bio. * @bio: BIO to add to. @@ -1169,7 +1177,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) bio_for_each_segment_all(bvec, bio, iter_all) { if (mark_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + bio_release_page(bio, bvec->bv_page); } } EXPORT_SYMBOL_GPL(__bio_release_pages); @@ -1191,7 +1199,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) bio->bi_io_vec = (struct bio_vec *)iter->bvec; bio->bi_iter.bi_bvec_done = iter->iov_offset; bio->bi_iter.bi_size = size; - bio_set_flag(bio, BIO_NO_PAGE_REF); bio_set_flag(bio, BIO_CLONED); } @@ -1206,7 +1213,7 @@ static int bio_iov_add_page(struct bio *bio, struct page *page, } if (same_page) - put_page(page); + bio_release_page(bio, page); return 0; } @@ -1220,7 +1227,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, queue_max_zone_append_sectors(q), &same_page) != len) return -EINVAL; if (same_page) - put_page(page); + bio_release_page(bio, page); return 0; } @@ -1231,10 +1238,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins pages from *iter and appends them to @bio's bvec array. The - * pages will have to be released using put_page() when done. - * For multi-segment *iter, this function only adds pages from the - * next non-empty segment of the iov iterator. + * Extracts pages from *iter and appends them to @bio's bvec array. The pages + * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag. + * For a multi-segment *iter, this function only adds pages from the next + * non-empty segment of the iov iterator. */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { @@ -1266,9 +1273,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ - size = iov_iter_get_pages(iter, pages, - UINT_MAX - bio->bi_iter.bi_size, - nr_pages, &offset, extraction_flags); + size = iov_iter_extract_pages(iter, &pages, + UINT_MAX - bio->bi_iter.bi_size, + nr_pages, extraction_flags, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; @@ -1301,7 +1308,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) iov_iter_revert(iter, left); out: while (i < nr_pages) - put_page(pages[i++]); + bio_release_page(bio, pages[i++]); return ret; } @@ -1336,6 +1343,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) return 0; } + if (iov_iter_extract_will_pin(iter)) + bio_set_flag(bio, BIO_PAGE_PINNED); do { ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); @@ -1489,8 +1498,8 @@ void bio_set_pages_dirty(struct bio *bio) * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from - * here on. It will run one put_page() against each page and will run one - * bio_put() against the BIO. + * here on. It will unpin each page and will run one bio_put() against the + * BIO. */ static void bio_dirty_fn(struct work_struct *work); diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c index 842e5e1c0f3c..3ec21333f393 100644 --- a/block/blk-cgroup-fc-appid.c +++ b/block/blk-cgroup-fc-appid.c @@ -34,7 +34,7 @@ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) * the vmid from the fabric. * Adding the overhead of a lock is not necessary. */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); + strscpy(blkcg->fc_app_id, app_id, app_id_len); css_put(css); out_cgrp_put: cgroup_put(cgrp); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 0ce64dd73cfe..aaf9903ad7b2 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -34,6 +34,8 @@ #include "blk-ioprio.h" #include "blk-throttle.h" +static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); + /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire @@ -56,6 +58,8 @@ static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; +static DEFINE_RAW_SPINLOCK(blkg_stat_lock); + #define BLKG_DESTROY_BATCH_SIZE 64 /* @@ -163,10 +167,20 @@ static void blkg_free(struct blkcg_gq *blkg) static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); + struct blkcg *blkcg = blkg->blkcg; + int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif + /* + * Flush all the non-empty percpu lockless lists before releasing + * us, given these stat belongs to us. + * + * blkg_stat_lock is for serializing blkg stat update + */ + for_each_possible_cpu(cpu) + __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); @@ -610,8 +624,13 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct blkg_iostat_set *bis = per_cpu_ptr(blkg->iostat_cpu, cpu); memset(bis, 0, sizeof(*bis)); + + /* Re-initialize the cleared blkg_iostat_set */ + u64_stats_init(&bis->sync); + bis->blkg = blkg; } memset(&blkg->iostat, 0, sizeof(blkg->iostat)); + u64_stats_init(&blkg->iostat.sync); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -748,6 +767,13 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) return -ENODEV; } + mutex_lock(&bdev->bd_queue->rq_qos_mutex); + if (!disk_live(bdev->bd_disk)) { + blkdev_put_no_open(bdev); + mutex_unlock(&bdev->bd_queue->rq_qos_mutex); + return -ENODEV; + } + ctx->body = input; ctx->bdev = bdev; return 0; @@ -892,6 +918,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep); */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) + __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); @@ -899,6 +926,7 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } if (ctx->bdev) { + mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; @@ -951,16 +979,12 @@ static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } -static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { - struct blkcg *blkcg = css_to_blkcg(css); struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; - - /* Root-level stats are sourced from system-wide IO stats */ - if (!cgroup_parent(css->cgroup)) - return; + unsigned long flags; rcu_read_lock(); @@ -969,6 +993,14 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) goto out; /* + * For covering concurrent parent blkg update from blkg_release(). + * + * When flushing from cgroup, cgroup_rstat_lock is always held, so + * this lock won't cause contention most of time. + */ + raw_spin_lock_irqsave(&blkg_stat_lock, flags); + + /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { @@ -991,13 +1023,19 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) if (parent && parent->parent) blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); - percpu_ref_put(&blkg->refcnt); } - + raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } +static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + /* Root-level stats are sourced from system-wide IO stats */ + if (cgroup_parent(css->cgroup)) + __blkcg_rstat_flush(css_to_blkcg(css), cpu); +} + /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no @@ -2075,7 +2113,6 @@ void blk_cgroup_bio_start(struct bio *bio) llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); - percpu_ref_get(&bis->blkg->refcnt); } u64_stats_update_end_irqrestore(&bis->sync, flags); diff --git a/block/blk-core.c b/block/blk-core.c index 1da77e7d6289..3fc68b944479 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -420,6 +420,7 @@ struct request_queue *blk_alloc_queue(int node_id) mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); + mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); diff --git a/block/blk-flush.c b/block/blk-flush.c index 04698ed9bcd4..dba392cf22be 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -188,7 +188,9 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); - blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD); + spin_lock(&q->requeue_lock); + list_add_tail(&rq->queuelist, &q->flush_list); + spin_unlock(&q->requeue_lock); blk_mq_kick_requeue_list(q); break; @@ -346,7 +348,10 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, smp_wmb(); req_ref_set(flush_rq, 1); - blk_mq_add_to_requeue_list(flush_rq, 0); + spin_lock(&q->requeue_lock); + list_add_tail(&flush_rq->queuelist, &q->flush_list); + spin_unlock(&q->requeue_lock); + blk_mq_kick_requeue_list(q); } @@ -376,22 +381,29 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, return RQ_END_IO_NONE; } -/** - * blk_insert_flush - insert a new PREFLUSH/FUA request - * @rq: request to insert - * - * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions. - * or __blk_mq_run_hw_queue() to dispatch request. - * @rq is being submitted. Analyze what needs to be done and put it on the - * right queue. +static void blk_rq_init_flush(struct request *rq) +{ + rq->flush.seq = 0; + INIT_LIST_HEAD(&rq->flush.list); + rq->rq_flags |= RQF_FLUSH_SEQ; + rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ + rq->end_io = mq_flush_data_end_io; +} + +/* + * Insert a PREFLUSH/FUA request into the flush state machine. + * Returns true if the request has been consumed by the flush state machine, + * or false if the caller should continue to process it. */ -void blk_insert_flush(struct request *rq) +bool blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; unsigned long fflags = q->queue_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); - struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + + /* FLUSH/FUA request must never be merged */ + WARN_ON_ONCE(rq->bio != rq->biotail); /* * @policy now records what operations need to be done. Adjust @@ -408,45 +420,45 @@ void blk_insert_flush(struct request *rq) */ rq->cmd_flags |= REQ_SYNC; - /* - * An empty flush handed down from a stacking driver may - * translate into nothing if the underlying device does not - * advertise a write-back cache. In this case, simply - * complete the request. - */ - if (!policy) { + switch (policy) { + case 0: + /* + * An empty flush handed down from a stacking driver may + * translate into nothing if the underlying device does not + * advertise a write-back cache. In this case, simply + * complete the request. + */ blk_mq_end_request(rq, 0); - return; - } - - BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */ - - /* - * If there's data but flush is not necessary, the request can be - * processed directly without going through flush machinery. Queue - * for normal execution. - */ - if ((policy & REQ_FSEQ_DATA) && - !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { - blk_mq_request_bypass_insert(rq, 0); - blk_mq_run_hw_queue(hctx, false); - return; + return true; + case REQ_FSEQ_DATA: + /* + * If there's data, but no flush is necessary, the request can + * be processed directly without going through flush machinery. + * Queue for normal execution. + */ + return false; + case REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH: + /* + * Initialize the flush fields and completion handler to trigger + * the post flush, and then just pass the command on. + */ + blk_rq_init_flush(rq); + rq->flush.seq |= REQ_FSEQ_POSTFLUSH; + spin_lock_irq(&fq->mq_flush_lock); + list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); + spin_unlock_irq(&fq->mq_flush_lock); + return false; + default: + /* + * Mark the request as part of a flush sequence and submit it + * for further processing to the flush state machine. + */ + blk_rq_init_flush(rq); + spin_lock_irq(&fq->mq_flush_lock); + blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); + spin_unlock_irq(&fq->mq_flush_lock); + return true; } - - /* - * @rq should go through flush machinery. Mark it part of flush - * sequence and submit for further processing. - */ - memset(&rq->flush, 0, sizeof(rq->flush)); - INIT_LIST_HEAD(&rq->flush.list); - rq->rq_flags |= RQF_FLUSH_SEQ; - rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ - - rq->end_io = mq_flush_data_end_io; - - spin_lock_irq(&fq->mq_flush_lock); - blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); - spin_unlock_irq(&fq->mq_flush_lock); } /** diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 63fc02042408..25dd4db11121 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -77,6 +77,10 @@ static void ioc_destroy_icq(struct io_cq *icq) struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); + lockdep_assert_held(&q->queue_lock); + + if (icq->flags & ICQ_DESTROYED) + return; radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); @@ -128,12 +132,7 @@ static void ioc_release_fn(struct work_struct *work) spin_lock(&q->queue_lock); spin_lock(&ioc->lock); - /* - * The icq may have been destroyed when the ioc lock - * was released. - */ - if (!(icq->flags & ICQ_DESTROYED)) - ioc_destroy_icq(icq); + ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); @@ -171,23 +170,20 @@ static bool ioc_delay_free(struct io_context *ioc) */ void ioc_clear_queue(struct request_queue *q) { - LIST_HEAD(icq_list); - spin_lock_irq(&q->queue_lock); - list_splice_init(&q->icq_list, &icq_list); - spin_unlock_irq(&q->queue_lock); - - rcu_read_lock(); - while (!list_empty(&icq_list)) { + while (!list_empty(&q->icq_list)) { struct io_cq *icq = - list_entry(icq_list.next, struct io_cq, q_node); - - spin_lock_irq(&icq->ioc->lock); - if (!(icq->flags & ICQ_DESTROYED)) - ioc_destroy_icq(icq); - spin_unlock_irq(&icq->ioc->lock); + list_first_entry(&q->icq_list, struct io_cq, q_node); + + /* + * Other context won't hold ioc lock to wait for queue_lock, see + * details in ioc_release_fn(). + */ + spin_lock(&icq->ioc->lock); + ioc_destroy_icq(icq); + spin_unlock(&icq->ioc->lock); } - rcu_read_unlock(); + spin_unlock_irq(&q->queue_lock); } #else /* CONFIG_BLK_ICQ */ static inline void ioc_exit_icqs(struct io_context *ioc) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 285ced3467ab..6084a9519883 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2455,6 +2455,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; + unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; @@ -2473,11 +2474,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, iocg->inuse == iocg->active) return cost; - spin_lock_irq(&ioc->lock); + spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); return cost; } @@ -2498,7 +2499,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index 055529b9b92b..4051fada01f1 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -23,25 +23,28 @@ /** * enum prio_policy - I/O priority class policy. * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. - * @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT. + * @POLICY_PROMOTE_TO_RT: modify no-IOPRIO_CLASS_RT to IOPRIO_CLASS_RT. * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into * IOPRIO_CLASS_BE. * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. + * @POLICY_NONE_TO_RT: an alias for POLICY_PROMOTE_TO_RT. * * See also <linux/ioprio.h>. */ enum prio_policy { POLICY_NO_CHANGE = 0, - POLICY_NONE_TO_RT = 1, + POLICY_PROMOTE_TO_RT = 1, POLICY_RESTRICT_TO_BE = 2, POLICY_ALL_TO_IDLE = 3, + POLICY_NONE_TO_RT = 4, }; static const char *policy_name[] = { [POLICY_NO_CHANGE] = "no-change", - [POLICY_NONE_TO_RT] = "none-to-rt", + [POLICY_PROMOTE_TO_RT] = "promote-to-rt", [POLICY_RESTRICT_TO_BE] = "restrict-to-be", [POLICY_ALL_TO_IDLE] = "idle", + [POLICY_NONE_TO_RT] = "none-to-rt", }; static struct blkcg_policy ioprio_policy; @@ -189,6 +192,20 @@ void blkcg_set_ioprio(struct bio *bio) if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE) return; + if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT || + blkcg->prio_policy == POLICY_NONE_TO_RT) { + /* + * For RT threads, the default priority level is 4 because + * task_nice is 0. By promoting non-RT io-priority to RT-class + * and default level 4, those requests that are already + * RT-class but need a higher io-priority can use ioprio_set() + * to achieve this. + */ + if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) != IOPRIO_CLASS_RT) + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 4); + return; + } + /* * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers * correspond to a lower priority. Hence, the max_t() below selects diff --git a/block/blk-map.c b/block/blk-map.c index 46eed2e627c3..44d74a30ddac 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -281,21 +281,21 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (blk_queue_pci_p2pdma(rq->q)) extraction_flags |= ITER_ALLOW_P2PDMA; + if (iov_iter_extract_will_pin(iter)) + bio_set_flag(bio, BIO_PAGE_PINNED); while (iov_iter_count(iter)) { - struct page **pages, *stack_pages[UIO_FASTIOV]; + struct page *stack_pages[UIO_FASTIOV]; + struct page **pages = stack_pages; ssize_t bytes; size_t offs; int npages; - if (nr_vecs <= ARRAY_SIZE(stack_pages)) { - pages = stack_pages; - bytes = iov_iter_get_pages(iter, pages, LONG_MAX, - nr_vecs, &offs, extraction_flags); - } else { - bytes = iov_iter_get_pages_alloc(iter, &pages, - LONG_MAX, &offs, extraction_flags); - } + if (nr_vecs > ARRAY_SIZE(stack_pages)) + pages = NULL; + + bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX, + nr_vecs, extraction_flags, &offs); if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; goto out_unmap; @@ -317,7 +317,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!bio_add_hw_page(rq->q, bio, page, n, offs, max_sectors, &same_page)) { if (same_page) - put_page(page); + bio_release_page(bio, page); break; } @@ -329,7 +329,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, * release the pages we didn't map into the bio, if any */ while (j < npages) - put_page(pages[j++]); + bio_release_page(bio, pages[j++]); if (pages != stack_pages) kvfree(pages); /* couldn't stuff something into bio? */ diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index d23a8554ec4a..c3b5930106b2 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -88,6 +88,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(IO_STAT), QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(ADD_RANDOM), + QUEUE_FLAG_NAME(SYNCHRONOUS), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(INIT_DONE), QUEUE_FLAG_NAME(STABLE_WRITES), @@ -103,6 +104,8 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(RQ_ALLOC_TIME), QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(NOWAIT), + QUEUE_FLAG_NAME(SQ_SCHED), + QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE), }; #undef QUEUE_FLAG_NAME @@ -241,14 +244,14 @@ static const char *const cmd_flag_name[] = { #define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name static const char *const rqf_name[] = { RQF_NAME(STARTED), - RQF_NAME(SOFTBARRIER), RQF_NAME(FLUSH_SEQ), RQF_NAME(MIXED_MERGE), RQF_NAME(MQ_INFLIGHT), RQF_NAME(DONTPREP), + RQF_NAME(SCHED_TAGS), + RQF_NAME(USE_SCHED), RQF_NAME(FAILED), RQF_NAME(QUIET), - RQF_NAME(ELVPRIV), RQF_NAME(IO_STAT), RQF_NAME(PM), RQF_NAME(HASHED), @@ -256,7 +259,6 @@ static const char *const rqf_name[] = { RQF_NAME(SPECIAL_PAYLOAD), RQF_NAME(ZONE_WRITE_LOCKED), RQF_NAME(TIMED_OUT), - RQF_NAME(ELV), RQF_NAME(RESV), }; #undef RQF_NAME @@ -399,7 +401,7 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m, seq_printf(m, "nr_tags=%u\n", tags->nr_tags); seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags); seq_printf(m, "active_queues=%d\n", - atomic_read(&tags->active_queues)); + READ_ONCE(tags->active_queues)); seq_puts(m, "\nbitmap_tags:\n"); sbitmap_queue_show(&tags->bitmap_tags, m); diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 7c3cbad17f30..1326526bb733 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -37,7 +37,7 @@ static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = q->elevator; if (e->type->ops.allow_merge) @@ -48,7 +48,7 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = rq->q->elevator; if (e->type->ops.completed_request) @@ -58,11 +58,11 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) static inline void blk_mq_sched_requeue_request(struct request *rq) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; - if ((rq->rq_flags & RQF_ELVPRIV) && e->type->ops.requeue_request) + if (e->type->ops.requeue_request) e->type->ops.requeue_request(rq); } } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index dfd81cab5788..cc57e2dd9a0b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + struct blk_mq_tags *tags = hctx->tags; /* * calling test_bit() prior to test_and_set_bit() is intentional, @@ -55,9 +56,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; } - users = atomic_inc_return(&hctx->tags->active_queues); - - blk_mq_update_wake_batch(hctx->tags, users); + spin_lock_irq(&tags->lock); + users = tags->active_queues + 1; + WRITE_ONCE(tags->active_queues, users); + blk_mq_update_wake_batch(tags, users); + spin_unlock_irq(&tags->lock); } /* @@ -90,9 +93,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) return; } - users = atomic_dec_return(&tags->active_queues); - + spin_lock_irq(&tags->lock); + users = tags->active_queues - 1; + WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); + spin_unlock_irq(&tags->lock); blk_mq_tag_wakeup_all(tags, false); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 850bfb844ed2..decb6ab2d508 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -45,6 +45,8 @@ static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); +static void blk_mq_request_bypass_insert(struct request *rq, + blk_insert_t flags); static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); @@ -354,12 +356,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, data->rq_flags |= RQF_IO_STAT; rq->rq_flags = data->rq_flags; - if (!(data->rq_flags & RQF_ELV)) { - rq->tag = tag; - rq->internal_tag = BLK_MQ_NO_TAG; - } else { + if (data->rq_flags & RQF_SCHED_TAGS) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; + } else { + rq->tag = tag; + rq->internal_tag = BLK_MQ_NO_TAG; } rq->timeout = 0; @@ -386,17 +388,14 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, WRITE_ONCE(rq->deadline, 0); req_ref_set(rq, 1); - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = data->q->elevator; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); - if (!op_is_flush(data->cmd_flags) && - e->type->ops.prepare_request) { + if (e->type->ops.prepare_request) e->type->ops.prepare_request(rq); - rq->rq_flags |= RQF_ELVPRIV; - } } return rq; @@ -449,26 +448,32 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) data->flags |= BLK_MQ_REQ_NOWAIT; if (q->elevator) { - struct elevator_queue *e = q->elevator; - - data->rq_flags |= RQF_ELV; + /* + * All requests use scheduler tags when an I/O scheduler is + * enabled for the queue. + */ + data->rq_flags |= RQF_SCHED_TAGS; /* * Flush/passthrough requests are special and go directly to the - * dispatch list. Don't include reserved tags in the - * limiting, as it isn't useful. + * dispatch list. */ - if (!op_is_flush(data->cmd_flags) && - !blk_op_is_passthrough(data->cmd_flags) && - e->type->ops.limit_depth && - !(data->flags & BLK_MQ_REQ_RESERVED)) - e->type->ops.limit_depth(data->cmd_flags, data); + if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH && + !blk_op_is_passthrough(data->cmd_flags)) { + struct elevator_mq_ops *ops = &q->elevator->type->ops; + + WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED); + + data->rq_flags |= RQF_USE_SCHED; + if (ops->limit_depth) + ops->limit_depth(data->cmd_flags, data); + } } retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); - if (!(data->rq_flags & RQF_ELV)) + if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_tag_busy(data->hctx); if (data->flags & BLK_MQ_REQ_RESERVED) @@ -648,10 +653,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); - if (!q->elevator) - blk_mq_tag_busy(data.hctx); + if (q->elevator) + data.rq_flags |= RQF_SCHED_TAGS; else - data.rq_flags |= RQF_ELV; + blk_mq_tag_busy(data.hctx); if (flags & BLK_MQ_REQ_RESERVED) data.rq_flags |= RQF_RESV; @@ -699,7 +704,7 @@ void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; - if ((rq->rq_flags & RQF_ELVPRIV) && + if ((rq->rq_flags & RQF_USE_SCHED) && q->elevator->type->ops.finish_request) q->elevator->type->ops.finish_request(rq); @@ -957,6 +962,8 @@ EXPORT_SYMBOL_GPL(blk_update_request); static inline void blk_account_io_done(struct request *req, u64 now) { + trace_block_io_done(req); + /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the @@ -976,6 +983,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) static inline void blk_account_io_start(struct request *req) { + trace_block_io_start(req); + if (blk_do_io_stat(req)) { /* * All non-passthrough requests are created from a bio with one @@ -1176,8 +1185,9 @@ bool blk_mq_complete_request_remote(struct request *rq) * or a polled request, always complete locally, * it's pointless to redirect the completion. */ - if (rq->mq_hctx->nr_ctx == 1 || - rq->cmd_flags & REQ_POLLED) + if ((rq->mq_hctx->nr_ctx == 1 && + rq->mq_ctx->cpu == raw_smp_processor_id()) || + rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { @@ -1270,7 +1280,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) if (!plug->multiple_queues && last && last->q != rq->q) plug->multiple_queues = true; - if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) + if (!plug->has_elevator && (rq->rq_flags & RQF_USE_SCHED)) plug->has_elevator = true; rq->rq_next = NULL; rq_list_add(&plug->mq_list, rq); @@ -1411,13 +1421,16 @@ static void __blk_mq_requeue_request(struct request *rq) void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { struct request_queue *q = rq->q; + unsigned long flags; __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); - blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD); + spin_lock_irqsave(&q->requeue_lock, flags); + list_add_tail(&rq->queuelist, &q->requeue_list); + spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); @@ -1429,13 +1442,16 @@ static void blk_mq_requeue_work(struct work_struct *work) struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); - struct request *rq, *next; + LIST_HEAD(flush_list); + struct request *rq; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); + list_splice_init(&q->flush_list, &flush_list); spin_unlock_irq(&q->requeue_lock); - list_for_each_entry_safe(rq, next, &rq_list, queuelist) { + while (!list_empty(&rq_list)) { + rq = list_entry(rq_list.next, struct request, queuelist); /* * If RQF_DONTPREP ist set, the request has been started by the * driver already and might have driver-specific data allocated @@ -1443,18 +1459,16 @@ static void blk_mq_requeue_work(struct work_struct *work) * block layer merges for the request. */ if (rq->rq_flags & RQF_DONTPREP) { - rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); blk_mq_request_bypass_insert(rq, 0); - } else if (rq->rq_flags & RQF_SOFTBARRIER) { - rq->rq_flags &= ~RQF_SOFTBARRIER; + } else { list_del_init(&rq->queuelist); blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); } } - while (!list_empty(&rq_list)) { - rq = list_entry(rq_list.next, struct request, queuelist); + while (!list_empty(&flush_list)) { + rq = list_entry(flush_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, 0); } @@ -1462,27 +1476,6 @@ static void blk_mq_requeue_work(struct work_struct *work) blk_mq_run_hw_queues(q, false); } -void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags) -{ - struct request_queue *q = rq->q; - unsigned long flags; - - /* - * We abuse this flag that is otherwise used by the I/O scheduler to - * request head insertion from the workqueue. - */ - BUG_ON(rq->rq_flags & RQF_SOFTBARRIER); - - spin_lock_irqsave(&q->requeue_lock, flags); - if (insert_flags & BLK_MQ_INSERT_AT_HEAD) { - rq->rq_flags |= RQF_SOFTBARRIER; - list_add(&rq->queuelist, &q->requeue_list); - } else { - list_add_tail(&rq->queuelist, &q->requeue_list); - } - spin_unlock_irqrestore(&q->requeue_lock, flags); -} - void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); @@ -2427,7 +2420,7 @@ static void blk_mq_run_work_fn(struct work_struct *work) * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ -void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) +static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; @@ -2492,7 +2485,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags) * dispatch it given we prioritize requests in hctx->dispatch. */ blk_mq_request_bypass_insert(rq, flags); - } else if (rq->rq_flags & RQF_FLUSH_SEQ) { + } else if (req_op(rq) == REQ_OP_FLUSH) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( @@ -2622,7 +2615,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, return; } - if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) { + if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, false); return; @@ -2711,6 +2704,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct request *requeue_list = NULL; struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; + bool is_passthrough = false; LIST_HEAD(list); do { @@ -2719,7 +2713,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; - } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { + is_passthrough = blk_rq_is_passthrough(rq); + } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || + is_passthrough != blk_rq_is_passthrough(rq)) { rq_list_add_tail(&requeue_lastp, rq); continue; } @@ -2731,7 +2727,13 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); - if (this_hctx->queue->elevator) { + /* passthrough requests should never be issued to the I/O scheduler */ + if (is_passthrough) { + spin_lock(&this_hctx->lock); + list_splice_tail_init(&list, &this_hctx->dispatch); + spin_unlock(&this_hctx->lock); + blk_mq_run_hw_queue(this_hctx, from_sched); + } else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); @@ -2970,10 +2972,8 @@ void blk_mq_submit_bio(struct bio *bio) return; } - if (op_is_flush(bio->bi_opf)) { - blk_insert_flush(rq); + if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq)) return; - } if (plug) { blk_add_rq_to_plug(plug, rq); @@ -2981,7 +2981,7 @@ void blk_mq_submit_bio(struct bio *bio) } hctx = rq->mq_hctx; - if ((rq->rq_flags & RQF_ELV) || + if ((rq->rq_flags & RQF_USE_SCHED) || (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, true); @@ -4232,6 +4232,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, blk_mq_update_poll_flag(q); INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); + INIT_LIST_HEAD(&q->flush_list); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); @@ -4608,9 +4609,6 @@ static bool blk_mq_elv_switch_none(struct list_head *head, { struct blk_mq_qe_pair *qe; - if (!q->elevator) - return true; - qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; @@ -4618,6 +4616,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, /* q->elevator needs protection from ->sysfs_lock */ mutex_lock(&q->sysfs_lock); + /* the check has to be done with holding sysfs_lock */ + if (!q->elevator) { + kfree(qe); + goto unlock; + } + INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; @@ -4625,6 +4629,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); +unlock: mutex_unlock(&q->sysfs_lock); return true; diff --git a/block/blk-mq.h b/block/blk-mq.h index e876584d3516..1743857e0b01 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -47,7 +47,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, unsigned int); -void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); @@ -64,10 +63,6 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); -/* - * Internal helpers for request insertion into sw queues - */ -void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags); /* * CPU -> queue mappings @@ -226,9 +221,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags) static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { - if (!(data->rq_flags & RQF_ELV)) - return data->hctx->tags; - return data->hctx->sched_tags; + if (data->rq_flags & RQF_SCHED_TAGS) + return data->hctx->sched_tags; + return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) @@ -417,8 +412,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, return true; } - users = atomic_read(&hctx->tags->active_queues); - + users = READ_ONCE(hctx->tags->active_queues); if (!users) return true; diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index d8cc820a365e..167be74df4ee 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -288,11 +288,13 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, void rq_qos_exit(struct request_queue *q) { + mutex_lock(&q->rq_qos_mutex); while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); } + mutex_unlock(&q->rq_qos_mutex); } int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, @@ -300,6 +302,8 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, { struct request_queue *q = disk->queue; + lockdep_assert_held(&q->rq_qos_mutex); + rqos->disk = disk; rqos->id = id; rqos->ops = ops; @@ -307,18 +311,13 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, /* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. - * - * Reuse ->queue_lock for protecting against other concurrent - * rq_qos adding/deleting */ blk_mq_freeze_queue(q); - spin_lock_irq(&q->queue_lock); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); @@ -330,7 +329,6 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, return 0; ebusy: - spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); return -EBUSY; } @@ -340,21 +338,15 @@ void rq_qos_del(struct rq_qos *rqos) struct request_queue *q = rqos->disk->queue; struct rq_qos **cur; - /* - * See comment in rq_qos_add() about freezing queue & using - * ->queue_lock. - */ - blk_mq_freeze_queue(q); + lockdep_assert_held(&q->rq_qos_mutex); - spin_lock_irq(&q->queue_lock); + blk_mq_freeze_queue(q); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } - spin_unlock_irq(&q->queue_lock); - blk_mq_unfreeze_queue(q); mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 9ec2a2f1eda3..7a87506ff8e1 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -944,7 +944,9 @@ int wbt_init(struct gendisk *disk) /* * Assign rwb and add the stats callback. */ + mutex_lock(&q->rq_qos_mutex); ret = rq_qos_add(&rwb->rqos, disk, RQ_QOS_WBT, &wbt_rqos_ops); + mutex_unlock(&q->rq_qos_mutex); if (ret) goto err_free; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index fce9082384d6..0f9f97cdddd9 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -57,16 +57,10 @@ EXPORT_SYMBOL_GPL(blk_zone_cond_str); */ bool blk_req_needs_zone_write_lock(struct request *rq) { - if (blk_rq_is_passthrough(rq)) - return false; - if (!rq->q->disk->seq_zones_wlock) return false; - if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq))) - return blk_rq_zone_is_seq(rq); - - return false; + return blk_rq_is_seq_zoned_write(rq); } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); @@ -329,8 +323,8 @@ static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, * BLKREPORTZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, + unsigned long arg) { void __user *argp = (void __user *)arg; struct zone_report_args args; @@ -362,8 +356,8 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, return 0; } -static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, - const struct blk_zone_range *zrange) +static int blkdev_truncate_zone_range(struct block_device *bdev, + blk_mode_t mode, const struct blk_zone_range *zrange) { loff_t start, end; @@ -382,7 +376,7 @@ static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -396,7 +390,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, if (!bdev_is_zoned(bdev)) return -ENOTTY; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) diff --git a/block/blk.h b/block/blk.h index 45547bcf1119..608c5dcc516b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -269,7 +269,7 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, */ #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) -void blk_insert_flush(struct request *rq); +bool blk_insert_flush(struct request *rq); int elevator_switch(struct request_queue *q, struct elevator_type *new_e); void elevator_disable(struct request_queue *q); @@ -394,10 +394,27 @@ static inline struct bio *blk_queue_bounce(struct bio *bio, #ifdef CONFIG_BLK_DEV_ZONED void disk_free_zone_bitmaps(struct gendisk *disk); void disk_clear_zone_settings(struct gendisk *disk); -#else +int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, + unsigned long arg); +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long arg); +#else /* CONFIG_BLK_DEV_ZONED */ static inline void disk_free_zone_bitmaps(struct gendisk *disk) {} static inline void disk_clear_zone_settings(struct gendisk *disk) {} -#endif +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + blk_mode_t mode, unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); +void bdev_add(struct block_device *bdev, dev_t dev); int blk_alloc_ext_minor(void); void blk_free_ext_minor(unsigned int minor); @@ -409,7 +426,7 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, int bdev_del_partition(struct gendisk *disk, int partno); int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); -void blk_drop_partitions(struct gendisk *disk); +void drop_partition(struct block_device *part); void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); @@ -420,9 +437,19 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); +/* + * Clean up a page appropriately, where the page may be pinned, may have a + * ref taken on it or neither. + */ +static inline void bio_release_page(struct bio *bio, struct page *page) +{ + if (bio_flagged(bio, BIO_PAGE_PINNED)) + unpin_user_page(page); +} + struct request_queue *blk_alloc_queue(int node_id); -int disk_scan_partitions(struct gendisk *disk, fmode_t mode); +int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode); int disk_alloc_events(struct gendisk *disk); void disk_add_events(struct gendisk *disk); @@ -437,6 +464,9 @@ extern struct device_attribute dev_attr_events_poll_msecs; extern struct attribute_group blk_trace_attr_group; +blk_mode_t file_to_blk_mode(struct file *file); +int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, + loff_t lstart, loff_t lend); long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 435c32373cd6..b3acdbdb6e7e 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -26,7 +26,7 @@ struct bsg_set { }; static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout) + bool open_for_write, unsigned int timeout) { struct bsg_job *job; struct request *rq; diff --git a/block/bsg.c b/block/bsg.c index 7eca43f33d7f..1a9396a3b7d7 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -39,7 +39,7 @@ static inline struct bsg_device *to_bsg_device(struct inode *inode) #define BSG_MAX_DEVS 32768 static DEFINE_IDA(bsg_minor_ida); -static struct class *bsg_class; +static const struct class bsg_class; static int bsg_major; static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr) @@ -54,7 +54,8 @@ static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr) return max_t(unsigned int, timeout, BLK_MIN_SG_TIMEOUT); } -static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) +static int bsg_sg_io(struct bsg_device *bd, bool open_for_write, + void __user *uarg) { struct sg_io_v4 hdr; int ret; @@ -63,7 +64,8 @@ static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) return -EFAULT; if (hdr.guard != 'Q') return -EINVAL; - ret = bd->sg_io_fn(bd->queue, &hdr, mode, bsg_timeout(bd, &hdr)); + ret = bd->sg_io_fn(bd->queue, &hdr, open_for_write, + bsg_timeout(bd, &hdr)); if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr))) return -EFAULT; return ret; @@ -146,7 +148,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case SG_EMULATED_HOST: return put_user(1, intp); case SG_IO: - return bsg_sg_io(bd, file->f_mode, uarg); + return bsg_sg_io(bd, file->f_mode & FMODE_WRITE, uarg); case SCSI_IOCTL_SEND_COMMAND: pr_warn_ratelimited("%s: calling unsupported SCSI_IOCTL_SEND_COMMAND\n", current->comm); @@ -206,7 +208,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, return ERR_PTR(ret); } bd->device.devt = MKDEV(bsg_major, ret); - bd->device.class = bsg_class; + bd->device.class = &bsg_class; bd->device.parent = parent; bd->device.release = bsg_device_release; dev_set_name(&bd->device, "%s", name); @@ -240,15 +242,19 @@ static char *bsg_devnode(const struct device *dev, umode_t *mode) return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev)); } +static const struct class bsg_class = { + .name = "bsg", + .devnode = bsg_devnode, +}; + static int __init bsg_init(void) { dev_t devid; int ret; - bsg_class = class_create("bsg"); - if (IS_ERR(bsg_class)) - return PTR_ERR(bsg_class); - bsg_class->devnode = bsg_devnode; + ret = class_register(&bsg_class); + if (ret) + return ret; ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg"); if (ret) @@ -260,7 +266,7 @@ static int __init bsg_init(void) return 0; destroy_bsg_class: - class_destroy(bsg_class); + class_unregister(&bsg_class); return ret; } diff --git a/block/disk-events.c b/block/disk-events.c index aee25a7e1ab7..0cfac464e6d1 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -263,31 +263,31 @@ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) } /** - * bdev_check_media_change - check if a removable media has been changed - * @bdev: block device to check + * disk_check_media_change - check if a removable media has been changed + * @disk: gendisk to check * * Check whether a removable media has been changed, and attempt to free all * dentries and inodes and invalidates all block device page cache entries in * that case. * - * Returns %true if the block device changed, or %false if not. + * Returns %true if the media has changed, or %false if not. */ -bool bdev_check_media_change(struct block_device *bdev) +bool disk_check_media_change(struct gendisk *disk) { unsigned int events; - events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | + events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; - if (__invalidate_device(bdev, true)) + if (__invalidate_device(disk->part0, true)) pr_warn("VFS: busy inodes on changed media %s\n", - bdev->bd_disk->disk_name); - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &disk->state); return true; } -EXPORT_SYMBOL(bdev_check_media_change); +EXPORT_SYMBOL(disk_check_media_change); /** * disk_force_media_change - force a media change event @@ -307,6 +307,7 @@ bool disk_force_media_change(struct gendisk *disk, unsigned int events) if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; + inc_diskseq(disk); if (__invalidate_device(disk->part0, true)) pr_warn("VFS: busy inodes on changed media %s\n", disk->disk_name); diff --git a/block/early-lookup.c b/block/early-lookup.c new file mode 100644 index 000000000000..3effbd0d35e9 --- /dev/null +++ b/block/early-lookup.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Code for looking up block devices in the early boot code before mounting the + * root file system. + */ +#include <linux/blkdev.h> +#include <linux/ctype.h> + +struct uuidcmp { + const char *uuid; + int len; +}; + +/** + * match_dev_by_uuid - callback for finding a partition using its uuid + * @dev: device passed in by the caller + * @data: opaque pointer to the desired struct uuidcmp to match + * + * Returns 1 if the device matches, and 0 otherwise. + */ +static int __init match_dev_by_uuid(struct device *dev, const void *data) +{ + struct block_device *bdev = dev_to_bdev(dev); + const struct uuidcmp *cmp = data; + + if (!bdev->bd_meta_info || + strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len)) + return 0; + return 1; +} + +/** + * devt_from_partuuid - looks up the dev_t of a partition by its UUID + * @uuid_str: char array containing ascii UUID + * @devt: dev_t result + * + * The function will return the first partition which contains a matching + * UUID value in its partition_meta_info struct. This does not search + * by filesystem UUIDs. + * + * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be + * extracted and used as an offset from the partition identified by the UUID. + * + * Returns 0 on success or a negative error code on failure. + */ +static int __init devt_from_partuuid(const char *uuid_str, dev_t *devt) +{ + struct uuidcmp cmp; + struct device *dev = NULL; + int offset = 0; + char *slash; + + cmp.uuid = uuid_str; + + slash = strchr(uuid_str, '/'); + /* Check for optional partition number offset attributes. */ + if (slash) { + char c = 0; + + /* Explicitly fail on poor PARTUUID syntax. */ + if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1) + goto out_invalid; + cmp.len = slash - uuid_str; + } else { + cmp.len = strlen(uuid_str); + } + + if (!cmp.len) + goto out_invalid; + + dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid); + if (!dev) + return -ENODEV; + + if (offset) { + /* + * Attempt to find the requested partition by adding an offset + * to the partition number found by UUID. + */ + *devt = part_devt(dev_to_disk(dev), + dev_to_bdev(dev)->bd_partno + offset); + } else { + *devt = dev->devt; + } + + put_device(dev); + return 0; + +out_invalid: + pr_err("VFS: PARTUUID= is invalid.\n" + "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n"); + return -EINVAL; +} + +/** + * match_dev_by_label - callback for finding a partition using its label + * @dev: device passed in by the caller + * @data: opaque pointer to the label to match + * + * Returns 1 if the device matches, and 0 otherwise. + */ +static int __init match_dev_by_label(struct device *dev, const void *data) +{ + struct block_device *bdev = dev_to_bdev(dev); + const char *label = data; + + if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname)) + return 0; + return 1; +} + +static int __init devt_from_partlabel(const char *label, dev_t *devt) +{ + struct device *dev; + + dev = class_find_device(&block_class, NULL, label, &match_dev_by_label); + if (!dev) + return -ENODEV; + *devt = dev->devt; + put_device(dev); + return 0; +} + +static dev_t __init blk_lookup_devt(const char *name, int partno) +{ + dev_t devt = MKDEV(0, 0); + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + + if (strcmp(dev_name(dev), name)) + continue; + + if (partno < disk->minors) { + /* We need to return the right devno, even + * if the partition doesn't exist yet. + */ + devt = MKDEV(MAJOR(dev->devt), + MINOR(dev->devt) + partno); + } else { + devt = part_devt(disk, partno); + if (devt) + break; + } + } + class_dev_iter_exit(&iter); + return devt; +} + +static int __init devt_from_devname(const char *name, dev_t *devt) +{ + int part; + char s[32]; + char *p; + + if (strlen(name) > 31) + return -EINVAL; + strcpy(s, name); + for (p = s; *p; p++) { + if (*p == '/') + *p = '!'; + } + + *devt = blk_lookup_devt(s, 0); + if (*devt) + return 0; + + /* + * Try non-existent, but valid partition, which may only exist after + * opening the device, like partitioned md devices. + */ + while (p > s && isdigit(p[-1])) + p--; + if (p == s || !*p || *p == '0') + return -ENODEV; + + /* try disk name without <part number> */ + part = simple_strtoul(p, NULL, 10); + *p = '\0'; + *devt = blk_lookup_devt(s, part); + if (*devt) + return 0; + + /* try disk name without p<part number> */ + if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p') + return -ENODEV; + p[-1] = '\0'; + *devt = blk_lookup_devt(s, part); + if (*devt) + return 0; + return -ENODEV; +} + +static int __init devt_from_devnum(const char *name, dev_t *devt) +{ + unsigned maj, min, offset; + char *p, dummy; + + if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || + sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { + *devt = MKDEV(maj, min); + if (maj != MAJOR(*devt) || min != MINOR(*devt)) + return -EINVAL; + } else { + *devt = new_decode_dev(simple_strtoul(name, &p, 16)); + if (*p) + return -EINVAL; + } + + return 0; +} + +/* + * Convert a name into device number. We accept the following variants: + * + * 1) <hex_major><hex_minor> device number in hexadecimal represents itself + * no leading 0x, for example b302. + * 3) /dev/<disk_name> represents the device number of disk + * 4) /dev/<disk_name><decimal> represents the device number + * of partition - device number of disk plus the partition number + * 5) /dev/<disk_name>p<decimal> - same as the above, that form is + * used when disk name of partitioned disk ends on a digit. + * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the + * unique id of a partition if the partition table provides it. + * The UUID may be either an EFI/GPT UUID, or refer to an MSDOS + * partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- + * filled hex representation of the 32-bit "NT disk signature", and PP + * is a zero-filled hex representation of the 1-based partition number. + * 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to + * a partition with a known unique id. + * 8) <major>:<minor> major and minor number of the device separated by + * a colon. + * 9) PARTLABEL=<name> with name being the GPT partition label. + * MSDOS partitions do not support labels! + * + * If name doesn't have fall into the categories above, we return (0,0). + * block_class is used to check if something is a disk name. If the disk + * name contains slashes, the device name has them replaced with + * bangs. + */ +int __init early_lookup_bdev(const char *name, dev_t *devt) +{ + if (strncmp(name, "PARTUUID=", 9) == 0) + return devt_from_partuuid(name + 9, devt); + if (strncmp(name, "PARTLABEL=", 10) == 0) + return devt_from_partlabel(name + 10, devt); + if (strncmp(name, "/dev/", 5) == 0) + return devt_from_devname(name + 5, devt); + return devt_from_devnum(name, devt); +} + +static char __init *bdevt_str(dev_t devt, char *buf) +{ + if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { + char tbuf[BDEVT_SIZE]; + snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); + snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); + } else + snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); + + return buf; +} + +/* + * print a full list of all partitions - intended for places where the root + * filesystem can't be mounted and thus to give the victim some idea of what + * went wrong + */ +void __init printk_all_partitions(void) +{ + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + struct block_device *part; + char devt_buf[BDEVT_SIZE]; + unsigned long idx; + + /* + * Don't show empty devices or things that have been + * suppressed + */ + if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN)) + continue; + + /* + * Note, unlike /proc/partitions, I am showing the numbers in + * hex - the same format as the root= option takes. + */ + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, part) { + if (!bdev_nr_sectors(part)) + continue; + printk("%s%s %10llu %pg %s", + bdev_is_partition(part) ? " " : "", + bdevt_str(part->bd_dev, devt_buf), + bdev_nr_sectors(part) >> 1, part, + part->bd_meta_info ? + part->bd_meta_info->uuid : ""); + if (bdev_is_partition(part)) + printk("\n"); + else if (dev->parent && dev->parent->driver) + printk(" driver: %s\n", + dev->parent->driver->name); + else + printk(" (driver?)\n"); + } + rcu_read_unlock(); + } + class_dev_iter_exit(&iter); +} diff --git a/block/elevator.c b/block/elevator.c index 24909069f872..8400e303fbcb 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -751,7 +751,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *buf, if (!elv_support_iosched(q)) return count; - strlcpy(elevator_name, buf, sizeof(elevator_name)); + strscpy(elevator_name, buf, sizeof(elevator_name)); ret = elevator_change(q, strstrip(elevator_name)); if (!ret) return count; diff --git a/block/fops.c b/block/fops.c index 58d0aebc7313..555b1b9ecd2c 100644 --- a/block/fops.c +++ b/block/fops.c @@ -54,7 +54,7 @@ static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos, static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; loff_t pos = iocb->ki_pos; bool should_dirty = false; @@ -170,7 +170,7 @@ static void blkdev_bio_end_io(struct bio *bio) static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct blk_plug plug; struct blkdev_dio *dio; struct bio *bio; @@ -310,7 +310,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); bool is_read = iov_iter_rw(iter) == READ; blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); struct blkdev_dio *dio; @@ -451,7 +451,7 @@ static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence) static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { - struct block_device *bdev = filp->private_data; + struct block_device *bdev = I_BDEV(filp->f_mapping->host); int error; error = file_write_and_wait_range(filp, start, end); @@ -470,6 +470,30 @@ static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, return error; } +blk_mode_t file_to_blk_mode(struct file *file) +{ + blk_mode_t mode = 0; + + if (file->f_mode & FMODE_READ) + mode |= BLK_OPEN_READ; + if (file->f_mode & FMODE_WRITE) + mode |= BLK_OPEN_WRITE; + if (file->private_data) + mode |= BLK_OPEN_EXCL; + if (file->f_flags & O_NDELAY) + mode |= BLK_OPEN_NDELAY; + + /* + * If all bits in O_ACCMODE set (aka O_RDWR | O_WRONLY), the floppy + * driver has historically allowed ioctls as if the file was opened for + * writing, but does not allow and actual reads or writes. + */ + if ((file->f_flags & O_ACCMODE) == (O_RDWR | O_WRONLY)) + mode |= BLK_OPEN_WRITE_IOCTL; + + return mode; +} + static int blkdev_open(struct inode *inode, struct file *filp) { struct block_device *bdev; @@ -481,30 +505,31 @@ static int blkdev_open(struct inode *inode, struct file *filp) * during an unstable branch. */ filp->f_flags |= O_LARGEFILE; - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; + filp->f_mode |= FMODE_BUF_RASYNC; - if (filp->f_flags & O_NDELAY) - filp->f_mode |= FMODE_NDELAY; + /* + * Use the file private data to store the holder for exclusive openes. + * file_to_blk_mode relies on it being present to set BLK_OPEN_EXCL. + */ if (filp->f_flags & O_EXCL) - filp->f_mode |= FMODE_EXCL; - if ((filp->f_flags & O_ACCMODE) == 3) - filp->f_mode |= FMODE_WRITE_IOCTL; + filp->private_data = filp; - bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); + bdev = blkdev_get_by_dev(inode->i_rdev, file_to_blk_mode(filp), + filp->private_data, NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); - filp->private_data = bdev; + if (bdev_nowait(bdev)) + filp->f_mode |= FMODE_NOWAIT; + filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); return 0; } -static int blkdev_close(struct inode *inode, struct file *filp) +static int blkdev_release(struct inode *inode, struct file *filp) { - struct block_device *bdev = filp->private_data; - - blkdev_put(bdev, filp->f_mode); + blkdev_put(I_BDEV(filp->f_mapping->host), filp->private_data); return 0; } @@ -517,10 +542,9 @@ static int blkdev_close(struct inode *inode, struct file *filp) */ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct inode *bd_inode = bdev->bd_inode; loff_t size = bdev_nr_bytes(bdev); - struct blk_plug plug; size_t shorted = 0; ssize_t ret; @@ -545,18 +569,16 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) iov_iter_truncate(from, size); } - blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); if (ret > 0) ret = generic_write_sync(iocb, ret); iov_iter_reexpand(from, iov_iter_count(from) + shorted); - blk_finish_plug(&plug); return ret; } static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); loff_t size = bdev_nr_bytes(bdev); loff_t pos = iocb->ki_pos; size_t shorted = 0; @@ -649,7 +671,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, filemap_invalidate_lock(inode->i_mapping); /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file->f_mode, start, end); + error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); if (error) goto fail; @@ -690,7 +712,7 @@ static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) const struct file_operations def_blk_fops = { .open = blkdev_open, - .release = blkdev_close, + .release = blkdev_release, .llseek = blkdev_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, @@ -701,7 +723,7 @@ const struct file_operations def_blk_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = blkdev_fallocate, }; diff --git a/block/genhd.c b/block/genhd.c index 1cb489b927d5..3d287b32d50d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -25,8 +25,9 @@ #include <linux/pm_runtime.h> #include <linux/badblocks.h> #include <linux/part_stat.h> -#include "blk-throttle.h" +#include <linux/blktrace_api.h> +#include "blk-throttle.h" #include "blk.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" @@ -253,7 +254,7 @@ int __register_blkdev(unsigned int major, const char *name, #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD p->probe = probe; #endif - strlcpy(p->name, name, sizeof(p->name)); + strscpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); @@ -318,18 +319,6 @@ void blk_free_ext_minor(unsigned int minor) ida_free(&ext_devt_ida, minor); } -static char *bdevt_str(dev_t devt, char *buf) -{ - if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { - char tbuf[BDEVT_SIZE]; - snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); - snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); - } else - snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); - - return buf; -} - void disk_uevent(struct gendisk *disk, enum kobject_action action) { struct block_device *part; @@ -351,7 +340,7 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action) } EXPORT_SYMBOL_GPL(disk_uevent); -int disk_scan_partitions(struct gendisk *disk, fmode_t mode) +int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) { struct block_device *bdev; int ret = 0; @@ -369,18 +358,20 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) * synchronize with other exclusive openers and other partition * scanners. */ - if (!(mode & FMODE_EXCL)) { - ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions); + if (!(mode & BLK_OPEN_EXCL)) { + ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions, + NULL); if (ret) return ret; } set_bit(GD_NEED_PART_SCAN, &disk->state); - bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL); + bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL, + NULL); if (IS_ERR(bdev)) ret = PTR_ERR(bdev); else - blkdev_put(bdev, mode & ~FMODE_EXCL); + blkdev_put(bdev, NULL); /* * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, @@ -388,7 +379,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) * creat partition for underlying disk. */ clear_bit(GD_NEED_PART_SCAN, &disk->state); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret; } @@ -516,7 +507,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) - disk_scan_partitions(disk, FMODE_READ); + disk_scan_partitions(disk, BLK_OPEN_READ); /* * Announce the disk and partitions after all partitions are @@ -563,6 +554,28 @@ out_exit_elevator: } EXPORT_SYMBOL(device_add_disk); +static void blk_report_disk_dead(struct gendisk *disk) +{ + struct block_device *bdev; + unsigned long idx; + + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, bdev) { + if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) + continue; + rcu_read_unlock(); + + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead) + bdev->bd_holder_ops->mark_dead(bdev); + mutex_unlock(&bdev->bd_holder_lock); + + put_device(&bdev->bd_device); + rcu_read_lock(); + } + rcu_read_unlock(); +} + /** * blk_mark_disk_dead - mark a disk as dead * @disk: disk to mark as dead @@ -572,13 +585,26 @@ EXPORT_SYMBOL(device_add_disk); */ void blk_mark_disk_dead(struct gendisk *disk) { - set_bit(GD_DEAD, &disk->state); - blk_queue_start_drain(disk->queue); + /* + * Fail any new I/O. + */ + if (test_and_set_bit(GD_DEAD, &disk->state)) + return; + + if (test_bit(GD_OWNS_QUEUE, &disk->state)) + blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue); /* * Stop buffered writers from dirtying pages that can't be written out. */ - set_capacity_and_notify(disk, 0); + set_capacity(disk, 0); + + /* + * Prevent new I/O from crossing bio_queue_enter(). + */ + blk_queue_start_drain(disk->queue); + + blk_report_disk_dead(disk); } EXPORT_SYMBOL_GPL(blk_mark_disk_dead); @@ -604,6 +630,8 @@ EXPORT_SYMBOL_GPL(blk_mark_disk_dead); void del_gendisk(struct gendisk *disk) { struct request_queue *q = disk->queue; + struct block_device *part; + unsigned long idx; might_sleep(); @@ -612,26 +640,27 @@ void del_gendisk(struct gendisk *disk) disk_del_events(disk); + /* + * Prevent new openers by unlinked the bdev inode, and write out + * dirty data before marking the disk dead and stopping all I/O. + */ mutex_lock(&disk->open_mutex); - remove_inode_hash(disk->part0->bd_inode); - blk_drop_partitions(disk); + xa_for_each(&disk->part_tbl, idx, part) { + remove_inode_hash(part->bd_inode); + fsync_bdev(part); + __invalidate_device(part, true); + } mutex_unlock(&disk->open_mutex); - fsync_bdev(disk->part0); - __invalidate_device(disk->part0, true); + blk_mark_disk_dead(disk); /* - * Fail any new I/O. + * Drop all partitions now that the disk is marked dead. */ - set_bit(GD_DEAD, &disk->state); - if (test_bit(GD_OWNS_QUEUE, &disk->state)) - blk_queue_flag_set(QUEUE_FLAG_DYING, q); - set_capacity(disk, 0); - - /* - * Prevent new I/O from crossing bio_queue_enter(). - */ - blk_queue_start_drain(q); + mutex_lock(&disk->open_mutex); + xa_for_each_start(&disk->part_tbl, idx, part, 1) + drop_partition(part); + mutex_unlock(&disk->open_mutex); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -755,57 +784,6 @@ void blk_request_module(dev_t devt) } #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */ -/* - * print a full list of all partitions - intended for places where the root - * filesystem can't be mounted and thus to give the victim some idea of what - * went wrong - */ -void __init printk_all_partitions(void) -{ - struct class_dev_iter iter; - struct device *dev; - - class_dev_iter_init(&iter, &block_class, NULL, &disk_type); - while ((dev = class_dev_iter_next(&iter))) { - struct gendisk *disk = dev_to_disk(dev); - struct block_device *part; - char devt_buf[BDEVT_SIZE]; - unsigned long idx; - - /* - * Don't show empty devices or things that have been - * suppressed - */ - if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN)) - continue; - - /* - * Note, unlike /proc/partitions, I am showing the numbers in - * hex - the same format as the root= option takes. - */ - rcu_read_lock(); - xa_for_each(&disk->part_tbl, idx, part) { - if (!bdev_nr_sectors(part)) - continue; - printk("%s%s %10llu %pg %s", - bdev_is_partition(part) ? " " : "", - bdevt_str(part->bd_dev, devt_buf), - bdev_nr_sectors(part) >> 1, part, - part->bd_meta_info ? - part->bd_meta_info->uuid : ""); - if (bdev_is_partition(part)) - printk("\n"); - else if (dev->parent && dev->parent->driver) - printk(" driver: %s\n", - dev->parent->driver->name); - else - printk(" (driver?)\n"); - } - rcu_read_unlock(); - } - class_dev_iter_exit(&iter); -} - #ifdef CONFIG_PROC_FS /* iterator */ static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) @@ -1171,6 +1149,8 @@ static void disk_release(struct device *dev) might_sleep(); WARN_ON_ONCE(disk_live(disk)); + blk_trace_remove(disk->queue); + /* * To undo the all initialization from blk_mq_init_allocated_queue in * case of a probe failure where add_disk is never called we have to @@ -1339,35 +1319,6 @@ dev_t part_devt(struct gendisk *disk, u8 partno) return devt; } -dev_t blk_lookup_devt(const char *name, int partno) -{ - dev_t devt = MKDEV(0, 0); - struct class_dev_iter iter; - struct device *dev; - - class_dev_iter_init(&iter, &block_class, NULL, &disk_type); - while ((dev = class_dev_iter_next(&iter))) { - struct gendisk *disk = dev_to_disk(dev); - - if (strcmp(dev_name(dev), name)) - continue; - - if (partno < disk->minors) { - /* We need to return the right devno, even - * if the partition doesn't exist yet. - */ - devt = MKDEV(MAJOR(dev->devt), - MINOR(dev->devt) + partno); - } else { - devt = part_devt(disk, partno); - if (devt) - break; - } - } - class_dev_iter_exit(&iter); - return devt; -} - struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass) { diff --git a/block/ioctl.c b/block/ioctl.c index 9c5f637ff153..3be11941fb2d 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -82,7 +82,7 @@ static int compat_blkpg_ioctl(struct block_device *bdev, } #endif -static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; @@ -90,7 +90,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, struct inode *inode = bdev->bd_inode; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_discard_sectors(bdev)) @@ -120,14 +120,14 @@ fail: return err; } -static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, void __user *argp) { uint64_t start, len; uint64_t range[2]; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_secure_erase_sectors(bdev)) return -EOPNOTSUPP; @@ -151,7 +151,7 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, } -static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; @@ -159,7 +159,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, struct inode *inode = bdev->bd_inode; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(range, (void __user *)arg, sizeof(range))) @@ -240,7 +240,7 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) * drivers that implement only commands that are completely compatible * between 32-bit and 64-bit user space */ -int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode, +int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; @@ -254,13 +254,28 @@ int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode, EXPORT_SYMBOL(blkdev_compat_ptr_ioctl); #endif -static int blkdev_pr_register(struct block_device *bdev, +static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode) +{ + /* no sense to make reservations for partitions */ + if (bdev_is_partition(bdev)) + return false; + + if (capable(CAP_SYS_ADMIN)) + return true; + /* + * Only allow unprivileged reservations if the file descriptor is open + * for writing. + */ + return mode & BLK_OPEN_WRITE; +} + +static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode, struct pr_registration __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_registration reg; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_register) return -EOPNOTSUPP; @@ -272,13 +287,13 @@ static int blkdev_pr_register(struct block_device *bdev, return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); } -static int blkdev_pr_reserve(struct block_device *bdev, +static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_reserve) return -EOPNOTSUPP; @@ -290,13 +305,13 @@ static int blkdev_pr_reserve(struct block_device *bdev, return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); } -static int blkdev_pr_release(struct block_device *bdev, +static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_release) return -EOPNOTSUPP; @@ -308,13 +323,13 @@ static int blkdev_pr_release(struct block_device *bdev, return ops->pr_release(bdev, rsv.key, rsv.type); } -static int blkdev_pr_preempt(struct block_device *bdev, +static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode, struct pr_preempt __user *arg, bool abort) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_preempt p; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_preempt) return -EOPNOTSUPP; @@ -326,13 +341,13 @@ static int blkdev_pr_preempt(struct block_device *bdev, return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); } -static int blkdev_pr_clear(struct block_device *bdev, +static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode, struct pr_clear __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_clear c; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_clear) return -EOPNOTSUPP; @@ -344,8 +359,8 @@ static int blkdev_pr_clear(struct block_device *bdev, return ops->pr_clear(bdev, c.key); } -static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) +static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd, + unsigned long arg) { if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -354,8 +369,8 @@ static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, return 0; } -static int blkdev_roset(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) +static int blkdev_roset(struct block_device *bdev, unsigned cmd, + unsigned long arg) { int ret, n; @@ -439,7 +454,7 @@ static int compat_hdio_getgeo(struct block_device *bdev, #endif /* set the logical block size */ -static int blkdev_bszset(struct block_device *bdev, fmode_t mode, +static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode, int __user *argp) { int ret, n; @@ -451,13 +466,13 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, if (get_user(n, argp)) return -EFAULT; - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) return set_blocksize(bdev, n); - if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev))) + if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode, &bdev, NULL))) return -EBUSY; ret = set_blocksize(bdev, n); - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, &bdev); return ret; } @@ -467,7 +482,7 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */ -static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, +static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg, void __user *argp) { @@ -475,9 +490,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case BLKFLSBUF: - return blkdev_flushbuf(bdev, mode, cmd, arg); + return blkdev_flushbuf(bdev, cmd, arg); case BLKROSET: - return blkdev_roset(bdev, mode, cmd, arg); + return blkdev_roset(bdev, cmd, arg); case BLKDISCARD: return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: @@ -487,7 +502,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKGETDISKSEQ: return put_u64(argp, bdev->bd_disk->diskseq); case BLKREPORTZONE: - return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); + return blkdev_report_zones_ioctl(bdev, cmd, arg); case BLKRESETZONE: case BLKOPENZONE: case BLKCLOSEZONE: @@ -534,17 +549,17 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: - return blkdev_pr_register(bdev, argp); + return blkdev_pr_register(bdev, mode, argp); case IOC_PR_RESERVE: - return blkdev_pr_reserve(bdev, argp); + return blkdev_pr_reserve(bdev, mode, argp); case IOC_PR_RELEASE: - return blkdev_pr_release(bdev, argp); + return blkdev_pr_release(bdev, mode, argp); case IOC_PR_PREEMPT: - return blkdev_pr_preempt(bdev, argp, false); + return blkdev_pr_preempt(bdev, mode, argp, false); case IOC_PR_PREEMPT_ABORT: - return blkdev_pr_preempt(bdev, argp, true); + return blkdev_pr_preempt(bdev, mode, argp, true); case IOC_PR_CLEAR: - return blkdev_pr_clear(bdev, argp); + return blkdev_pr_clear(bdev, mode, argp); default: return -ENOIOCTLCMD; } @@ -560,18 +575,9 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct block_device *bdev = I_BDEV(file->f_mapping->host); void __user *argp = (void __user *)arg; - fmode_t mode = file->f_mode; + blk_mode_t mode = file_to_blk_mode(file); int ret; - /* - * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have - * to updated it before every ioctl. - */ - if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY; - else - mode &= ~FMODE_NDELAY; - switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: @@ -630,16 +636,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) void __user *argp = compat_ptr(arg); struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; - fmode_t mode = file->f_mode; - - /* - * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have - * to updated it before every ioctl. - */ - if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY; - else - mode &= ~FMODE_NDELAY; + blk_mode_t mode = file_to_blk_mode(file); switch (cmd) { /* These need separate implementations for the data structure */ diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 5839a027e0f0..6aa5daf7ae32 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -74,8 +74,8 @@ struct dd_per_prio { struct list_head dispatch; struct rb_root sort_list[DD_DIR_COUNT]; struct list_head fifo_list[DD_DIR_COUNT]; - /* Next request in FIFO order. Read, write or both are NULL. */ - struct request *next_rq[DD_DIR_COUNT]; + /* Position of the most recently dispatched request. */ + sector_t latest_pos[DD_DIR_COUNT]; struct io_stats_per_prio stats; }; @@ -156,6 +156,40 @@ deadline_latter_request(struct request *rq) return NULL; } +/* + * Return the first request for which blk_rq_pos() >= @pos. For zoned devices, + * return the first request after the start of the zone containing @pos. + */ +static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir, sector_t pos) +{ + struct rb_node *node = per_prio->sort_list[data_dir].rb_node; + struct request *rq, *res = NULL; + + if (!node) + return NULL; + + rq = rb_entry_rq(node); + /* + * A zoned write may have been requeued with a starting position that + * is below that of the most recently dispatched request. Hence, for + * zoned writes, start searching from the start of a zone. + */ + if (blk_rq_is_seq_zoned_write(rq)) + pos -= round_down(pos, rq->q->limits.chunk_sectors); + + while (node) { + rq = rb_entry_rq(node); + if (blk_rq_pos(rq) >= pos) { + res = rq; + node = node->rb_left; + } else { + node = node->rb_right; + } + } + return res; +} + static void deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { @@ -167,11 +201,6 @@ deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) static inline void deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { - const enum dd_data_dir data_dir = rq_data_dir(rq); - - if (per_prio->next_rq[data_dir] == rq) - per_prio->next_rq[data_dir] = deadline_latter_request(rq); - elv_rb_del(deadline_rb_root(per_prio, rq), rq); } @@ -251,10 +280,6 @@ static void deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, struct request *rq) { - const enum dd_data_dir data_dir = rq_data_dir(rq); - - per_prio->next_rq[data_dir] = deadline_latter_request(rq); - /* * take it off the sort and fifo list */ @@ -272,21 +297,15 @@ static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) } /* - * deadline_check_fifo returns 0 if there are no expired requests on the fifo, - * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) + * deadline_check_fifo returns true if and only if there are expired requests + * in the FIFO list. Requires !list_empty(&dd->fifo_list[data_dir]). */ -static inline int deadline_check_fifo(struct dd_per_prio *per_prio, - enum dd_data_dir data_dir) +static inline bool deadline_check_fifo(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) { struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); - /* - * rq is expired! - */ - if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) - return 1; - - return 0; + return time_is_before_eq_jiffies((unsigned long)rq->fifo_time); } /* @@ -310,14 +329,11 @@ static struct request *deadline_skip_seq_writes(struct deadline_data *dd, struct request *rq) { sector_t pos = blk_rq_pos(rq); - sector_t skipped_sectors = 0; - while (rq) { - if (blk_rq_pos(rq) != pos + skipped_sectors) - break; - skipped_sectors += blk_rq_sectors(rq); + do { + pos += blk_rq_sectors(rq); rq = deadline_latter_request(rq); - } + } while (rq && blk_rq_pos(rq) == pos); return rq; } @@ -330,7 +346,7 @@ static struct request * deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, enum dd_data_dir data_dir) { - struct request *rq; + struct request *rq, *rb_rq, *next; unsigned long flags; if (list_empty(&per_prio->fifo_list[data_dir])) @@ -348,7 +364,12 @@ deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, * zones and these zones are unlocked. */ spin_lock_irqsave(&dd->zone_lock, flags); - list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) { + list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE], + queuelist) { + /* Check whether a prior request exists for the same zone. */ + rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq)); + if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq)) + rq = rb_rq; if (blk_req_can_dispatch_to_zone(rq) && (blk_queue_nonrot(rq->q) || !deadline_is_seq_write(dd, rq))) @@ -372,7 +393,8 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, struct request *rq; unsigned long flags; - rq = per_prio->next_rq[data_dir]; + rq = deadline_from_pos(per_prio, data_dir, + per_prio->latest_pos[data_dir]); if (!rq) return NULL; @@ -435,6 +457,7 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, if (started_after(dd, rq, latest_start)) return NULL; list_del_init(&rq->queuelist); + data_dir = rq_data_dir(rq); goto done; } @@ -442,9 +465,11 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, * batches are currently reads XOR writes */ rq = deadline_next_request(dd, per_prio, dd->last_dir); - if (rq && dd->batching < dd->fifo_batch) - /* we have a next request are still entitled to batch */ + if (rq && dd->batching < dd->fifo_batch) { + /* we have a next request and are still entitled to batch */ + data_dir = rq_data_dir(rq); goto dispatch_request; + } /* * at this point we are not running a batch. select the appropriate @@ -522,6 +547,7 @@ dispatch_request: done: ioprio_class = dd_rq_ioclass(rq); prio = ioprio_class_to_prio[ioprio_class]; + dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq); dd->per_prio[prio].stats.dispatched++; /* * If the request needs its target zone locked, do it. @@ -766,7 +792,7 @@ static bool dd_bio_merge(struct request_queue *q, struct bio *bio, * add rq to rbtree and fifo */ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, - blk_insert_t flags) + blk_insert_t flags, struct list_head *free) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; @@ -775,7 +801,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); struct dd_per_prio *per_prio; enum dd_prio prio; - LIST_HEAD(free); lockdep_assert_held(&dd->lock); @@ -792,10 +817,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, rq->elv.priv[0] = (void *)(uintptr_t)1; } - if (blk_mq_sched_try_insert_merge(q, rq, &free)) { - blk_mq_free_requests(&free); + if (blk_mq_sched_try_insert_merge(q, rq, free)) return; - } trace_block_rq_insert(rq); @@ -803,6 +826,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, list_add(&rq->queuelist, &per_prio->dispatch); rq->fifo_time = jiffies; } else { + struct list_head *insert_before; + deadline_add_rq_rb(per_prio, rq); if (rq_mergeable(rq)) { @@ -815,7 +840,20 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * set expire time and add to fifo list */ rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); + insert_before = &per_prio->fifo_list[data_dir]; +#ifdef CONFIG_BLK_DEV_ZONED + /* + * Insert zoned writes such that requests are sorted by + * position per zone. + */ + if (blk_rq_is_seq_zoned_write(rq)) { + struct request *rq2 = deadline_latter_request(rq); + + if (rq2 && blk_rq_zone_no(rq2) == blk_rq_zone_no(rq)) + insert_before = &rq2->queuelist; + } +#endif + list_add_tail(&rq->queuelist, insert_before); } } @@ -828,6 +866,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; + LIST_HEAD(free); spin_lock(&dd->lock); while (!list_empty(list)) { @@ -835,9 +874,11 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); - dd_insert_request(hctx, rq, flags); + dd_insert_request(hctx, rq, flags, &free); } spin_unlock(&dd->lock); + + blk_mq_free_requests(&free); } /* Callback from inside blk_mq_rq_ctx_init(). */ @@ -1035,8 +1076,10 @@ static int deadline_##name##_next_rq_show(void *data, \ struct request_queue *q = data; \ struct deadline_data *dd = q->elevator->elevator_data; \ struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ - struct request *rq = per_prio->next_rq[data_dir]; \ + struct request *rq; \ \ + rq = deadline_from_pos(per_prio, data_dir, \ + per_prio->latest_pos[data_dir]); \ if (rq) \ __blk_mq_debugfs_rq_show(m, rq); \ return 0; \ diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 5c8624e26a54..ed222b9c901b 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -11,10 +11,18 @@ #define pr_fmt(fmt) fmt #include <linux/types.h> +#include <linux/mm_types.h> +#include <linux/overflow.h> #include <linux/affs_hardblocks.h> #include "check.h" +/* magic offsets in partition DosEnvVec */ +#define NR_HD 3 +#define NR_SECT 5 +#define LO_CYL 9 +#define HI_CYL 10 + static __inline__ u32 checksum_block(__be32 *m, int size) { @@ -31,8 +39,12 @@ int amiga_partition(struct parsed_partitions *state) unsigned char *data; struct RigidDiskBlock *rdb; struct PartitionBlock *pb; - int start_sect, nr_sects, blk, part, res = 0; - int blksize = 1; /* Multiplier for disk block size */ + u64 start_sect, nr_sects; + sector_t blk, end_sect; + u32 cylblk; /* rdb_CylBlocks = nr_heads*sect_per_track */ + u32 nr_hd, nr_sect, lo_cyl, hi_cyl; + int part, res = 0; + unsigned int blksize = 1; /* Multiplier for disk block size */ int slot = 1; for (blk = 0; ; blk++, put_dev_sector(sect)) { @@ -40,7 +52,7 @@ int amiga_partition(struct parsed_partitions *state) goto rdb_done; data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read RDB block %d\n", + pr_err("Dev %s: unable to read RDB block %llu\n", state->disk->disk_name, blk); res = -1; goto rdb_done; @@ -57,12 +69,12 @@ int amiga_partition(struct parsed_partitions *state) *(__be32 *)(data+0xdc) = 0; if (checksum_block((__be32 *)data, be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) { - pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n", + pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n", blk); break; } - pr_err("Dev %s: RDB in block %d has bad checksum\n", + pr_err("Dev %s: RDB in block %llu has bad checksum\n", state->disk->disk_name, blk); } @@ -79,10 +91,15 @@ int amiga_partition(struct parsed_partitions *state) blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { - blk *= blksize; /* Read in terms partition table understands */ + /* Read in terms partition table understands */ + if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { + pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", + state->disk->disk_name, blk, part); + break; + } data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read partition block %d\n", + pr_err("Dev %s: unable to read partition block %llu\n", state->disk->disk_name, blk); res = -1; goto rdb_done; @@ -94,19 +111,70 @@ int amiga_partition(struct parsed_partitions *state) if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 ) continue; - /* Tell Kernel about it */ + /* RDB gives us more than enough rope to hang ourselves with, + * many times over (2^128 bytes if all fields max out). + * Some careful checks are in order, so check for potential + * overflows. + * We are multiplying four 32 bit numbers to one sector_t! + */ + + nr_hd = be32_to_cpu(pb->pb_Environment[NR_HD]); + nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]); + + /* CylBlocks is total number of blocks per cylinder */ + if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) { + pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n", + state->disk->disk_name, cylblk); + continue; + } + + /* check for consistency with RDB defined CylBlocks */ + if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) { + pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n", + state->disk->disk_name, cylblk, + be32_to_cpu(rdb->rdb_CylBlocks)); + } + + /* RDB allows for variable logical block size - + * normalize to 512 byte blocks and check result. + */ + + if (check_mul_overflow(cylblk, blksize, &cylblk)) { + pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n", + state->disk->disk_name, part); + continue; + } + + /* Calculate partition start and end. Limit of 32 bit on cylblk + * guarantees no overflow occurs if LBD support is enabled. + */ + + lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]); + start_sect = ((u64) lo_cyl * cylblk); + + hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]); + nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk); - nr_sects = (be32_to_cpu(pb->pb_Environment[10]) + 1 - - be32_to_cpu(pb->pb_Environment[9])) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; if (!nr_sects) continue; - start_sect = be32_to_cpu(pb->pb_Environment[9]) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; + + /* Warn user if partition end overflows u32 (AmigaDOS limit) */ + + if ((start_sect + nr_sects) > UINT_MAX) { + pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n", + state->disk->disk_name, part, + start_sect, start_sect + nr_sects); + } + + if (check_add_overflow(start_sect, nr_sects, &end_sect)) { + pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n", + state->disk->disk_name, part, + start_sect, end_sect); + continue; + } + + /* Tell Kernel about it */ + put_partition(state,slot++,start_sect,nr_sects); { /* Be even more informative to aid mounting */ diff --git a/block/partitions/core.c b/block/partitions/core.c index 49e0496ff23c..13a7341299a9 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -12,7 +12,7 @@ #include <linux/raid/detect.h> #include "check.h" -static int (*check_part[])(struct parsed_partitions *) = { +static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. @@ -228,7 +228,7 @@ static struct attribute *part_attrs[] = { NULL }; -static struct attribute_group part_attr_group = { +static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; @@ -256,31 +256,36 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -struct device_type part_type = { +const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; -static void delete_partition(struct block_device *part) +void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); - fsync_bdev(part); - __invalidate_device(part, true); - xa_erase(&part->bd_disk->part_tbl, part->bd_partno); kobject_put(part->bd_holder_dir); + device_del(&part->bd_device); + put_device(&part->bd_device); +} +static void delete_partition(struct block_device *part) +{ /* * Remove the block device from the inode hash, so that it cannot be * looked up any more even when openers still hold references. */ remove_inode_hash(part->bd_inode); - put_device(&part->bd_device); + fsync_bdev(part); + __invalidate_device(part, true); + + drop_partition(part); } static ssize_t whole_disk_show(struct device *dev, @@ -288,7 +293,7 @@ static ssize_t whole_disk_show(struct device *dev, { return 0; } -static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); +static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or @@ -436,10 +441,21 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { + sector_t capacity = get_capacity(disk), end; struct block_device *part; int ret; mutex_lock(&disk->open_mutex); + if (check_add_overflow(start, length, &end)) { + ret = -EINVAL; + goto out; + } + + if (start >= capacity || end > capacity) { + ret = -EINVAL; + goto out; + } + if (!disk_live(disk)) { ret = -ENXIO; goto out; @@ -519,17 +535,6 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) return true; } -void blk_drop_partitions(struct gendisk *disk) -{ - struct block_device *part; - unsigned long idx; - - lockdep_assert_held(&disk->open_mutex); - - xa_for_each_start(&disk->part_tbl, idx, part, 1) - delete_partition(part); -} - static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { @@ -646,6 +651,8 @@ out_free_state: int bdev_disk_changed(struct gendisk *disk, bool invalidate) { + struct block_device *part; + unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); @@ -658,8 +665,9 @@ rescan: return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); - blk_drop_partitions(disk); + xa_for_each_start(&disk->part_tbl, idx, part, 1) + delete_partition(part); clear_bit(GD_NEED_PART_SCAN, &disk->state); /* diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index e42c1f9ffff8..e9a1cb779b30 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -23,6 +23,7 @@ #include <linux/wait.h> #include <drm/drm_file.h> #include <drm/drm_gem.h> +#include <drm/drm_prime.h> #include <drm/drm_print.h> #include <uapi/drm/qaic_accel.h> @@ -616,8 +617,7 @@ static void qaic_free_object(struct drm_gem_object *obj) if (obj->import_attach) { /* DMABUF/PRIME Path */ - dma_buf_detach(obj->import_attach->dmabuf, obj->import_attach); - dma_buf_put(obj->import_attach->dmabuf); + drm_prime_gem_destroy(obj, NULL); } else { /* Private buffer allocation path */ qaic_free_sgt(bo->sgt); diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index 2d0828db28d8..b5ba550a0c04 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -97,6 +97,7 @@ static int qaic_open(struct drm_device *dev, struct drm_file *file) cleanup_usr: cleanup_srcu_struct(&usr->qddev_lock); + ida_free(&qaic_usrs, usr->handle); free_usr: kfree(usr); dev_unlock: @@ -224,6 +225,9 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id) struct qaic_user *usr; qddev = qdev->qddev; + qdev->qddev = NULL; + if (!qddev) + return; /* * Existing users get unresolvable errors till they close FDs. diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index ebf8fd373cf7..79bbfe00d241 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -101,8 +101,6 @@ acpi_status acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info, acpi_event_status *event_status); -acpi_status acpi_hw_disable_all_gpes(void); - acpi_status acpi_hw_enable_all_runtime_gpes(void); acpi_status acpi_hw_enable_all_wakeup_gpes(void); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 9718d07cc2a2..dc615ef6550a 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -597,10 +597,6 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) io_idle(cx->address); } else return -ENODEV; - -#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU) - cond_wakeup_cpu0(); -#endif } /* Never reached */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 72470b9f16c4..f32570f72b90 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -636,11 +636,19 @@ static int acpi_suspend_enter(suspend_state_t pm_state) } /* - * Disable and clear GPE status before interrupt is enabled. Some GPEs - * (like wakeup GPE) haven't handler, this can avoid such GPE misfire. - * acpi_leave_sleep_state will reenable specific GPEs later + * Disable all GPE and clear their status bits before interrupts are + * enabled. Some GPEs (like wakeup GPEs) have no handlers and this can + * prevent them from producing spurious interrups. + * + * acpi_leave_sleep_state() will reenable specific GPEs later. + * + * Because this code runs on one CPU with disabled interrupts (all of + * the other CPUs are offline at this time), it need not acquire any + * sleeping locks which may trigger an implicit preemption point even + * if there is no contention, so avoid doing that by using a low-level + * library routine here. */ - acpi_disable_all_gpes(); + acpi_hw_disable_all_gpes(); /* Allow EC transactions to happen. */ acpi_ec_unblock_transactions(); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8bf612bdd61a..b4f246f0cac7 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5348,7 +5348,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); - INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); + INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -5954,6 +5954,7 @@ static void ata_port_detach(struct ata_port *ap) WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); cancel_delayed_work_sync(&ap->hotplug_task); + cancel_delayed_work_sync(&ap->scsi_rescan_task); skip_eh: /* clean up zpodd on port removal */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index a6c901811802..6f8d14191593 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2984,7 +2984,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, ehc->i.flags |= ATA_EHI_SETMODE; /* schedule the scsi_rescan_device() here */ - schedule_work(&(ap->scsi_rescan_task)); + schedule_delayed_work(&ap->scsi_rescan_task, 0); } else if (dev->class == ATA_DEV_UNKNOWN && ehc->tries[dev->devno] && ata_class_enabled(ehc->classes[dev->devno])) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 8ce90284eb34..551077cea4e4 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4597,10 +4597,11 @@ int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, void ata_scsi_dev_rescan(struct work_struct *work) { struct ata_port *ap = - container_of(work, struct ata_port, scsi_rescan_task); + container_of(work, struct ata_port, scsi_rescan_task.work); struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool delay_rescan = false; mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); @@ -4614,6 +4615,21 @@ void ata_scsi_dev_rescan(struct work_struct *work) if (scsi_device_get(sdev)) continue; + /* + * If the rescan work was scheduled because of a resume + * event, the port is already fully resumed, but the + * SCSI device may not yet be fully resumed. In such + * case, executing scsi_rescan_device() may cause a + * deadlock with the PM code on device_lock(). Prevent + * this by giving up and retrying rescan after a short + * delay. + */ + delay_rescan = sdev->sdev_gendev.power.is_suspended; + if (delay_rescan) { + scsi_device_put(sdev); + break; + } + spin_unlock_irqrestore(ap->lock, flags); scsi_rescan_device(&(sdev->sdev_gendev)); scsi_device_put(sdev); @@ -4623,4 +4639,8 @@ void ata_scsi_dev_rescan(struct work_struct *work) spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_scan_mutex); + + if (delay_rescan) + schedule_delayed_work(&ap->scsi_rescan_task, + msecs_to_jiffies(5)); } diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 02425991c159..d44814b9562a 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -820,7 +820,7 @@ static const struct of_device_id ht16k33_of_match[] = { MODULE_DEVICE_TABLE(of, ht16k33_of_match); static struct i2c_driver ht16k33_driver = { - .probe_new = ht16k33_probe, + .probe = ht16k33_probe, .remove = ht16k33_remove, .driver = { .name = DRIVER_NAME, diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c index 135831a16514..6422be0dfe20 100644 --- a/drivers/auxdisplay/lcd2s.c +++ b/drivers/auxdisplay/lcd2s.c @@ -365,7 +365,7 @@ static struct i2c_driver lcd2s_i2c_driver = { .name = "lcd2s", .of_match_table = lcd2s_of_table, }, - .probe_new = lcd2s_i2c_probe, + .probe = lcd2s_i2c_probe, .remove = lcd2s_i2c_remove, .id_table = lcd2s_i2c_id, }; diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 9c09ca5c4ab6..878aa7646b37 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -751,14 +751,12 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv) * * Should somehow figure out how to use a semaphore, not an atomic variable... */ -int driver_probe_done(void) +bool __init driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); - if (local_probe_count) - return -EBUSY; - return 0; + return !local_probe_count; } /** diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index 029564695dbb..97c681fcf9f6 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -284,6 +284,9 @@ static bool regcache_reg_needs_sync(struct regmap *map, unsigned int reg, { int ret; + if (!regmap_writeable(map, reg)) + return false; + /* If we don't know the chip just got reset, then sync everything. */ if (!map->no_sync_defaults) return true; diff --git a/drivers/base/regmap/regmap-spi-avmm.c b/drivers/base/regmap/regmap-spi-avmm.c index 4c2b94b3e30b..6af692844c19 100644 --- a/drivers/base/regmap/regmap-spi-avmm.c +++ b/drivers/base/regmap/regmap-spi-avmm.c @@ -660,7 +660,7 @@ static const struct regmap_bus regmap_spi_avmm_bus = { .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .max_raw_read = SPI_AVMM_VAL_SIZE * MAX_READ_CNT, - .max_raw_write = SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, + .max_raw_write = SPI_AVMM_REG_SIZE + SPI_AVMM_VAL_SIZE * MAX_WRITE_CNT, .free_context = spi_avmm_bridge_ctx_free, }; diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 4c8b2ba579ee..e460c9799d9f 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1532,7 +1532,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct amiga_floppy_struct *p = bdev->bd_disk->private_data; @@ -1607,7 +1607,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -1654,10 +1654,10 @@ static void fd_probe(int dev) * /dev/PS0 etc), and disallows simultaneous access to the same * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - int drive = MINOR(bdev->bd_dev) & 3; - int system = (MINOR(bdev->bd_dev) & 4) >> 2; + int drive = disk->first_minor & 3; + int system = (disk->first_minor & 4) >> 2; int old_dev; unsigned long flags; @@ -1673,10 +1673,9 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) mutex_unlock(&amiflop_mutex); return -ENXIO; } - - if (mode & (FMODE_READ|FMODE_WRITE)) { - bdev_check_media_change(bdev); - if (mode & FMODE_WRITE) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + disk_check_media_change(disk); + if (mode & BLK_OPEN_WRITE) { int wrprot; get_fdc(drive); @@ -1691,7 +1690,6 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) } } } - local_irq_save(flags); fd_ref[drive]++; fd_device[drive] = system; @@ -1709,7 +1707,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct amiga_floppy_struct *p = disk->private_data; int drive = p - unit; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 128722cf6c3c..cf6883756155 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -204,9 +204,9 @@ aoedisk_rm_debugfs(struct aoedev *d) } static int -aoeblk_open(struct block_device *bdev, fmode_t mode) +aoeblk_open(struct gendisk *disk, blk_mode_t mode) { - struct aoedev *d = bdev->bd_disk->private_data; + struct aoedev *d = disk->private_data; ulong flags; if (!virt_addr_valid(d)) { @@ -232,7 +232,7 @@ aoeblk_open(struct block_device *bdev, fmode_t mode) } static void -aoeblk_release(struct gendisk *disk, fmode_t mode) +aoeblk_release(struct gendisk *disk) { struct aoedev *d = disk->private_data; ulong flags; @@ -285,7 +285,7 @@ aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo) } static int -aoeblk_ioctl(struct block_device *bdev, fmode_t mode, uint cmd, ulong arg) +aoeblk_ioctl(struct block_device *bdev, blk_mode_t mode, uint cmd, ulong arg) { struct aoedev *d; diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index 4c666f72203f..a42c4bcc85ba 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -49,7 +49,7 @@ static int emsgs_head_idx, emsgs_tail_idx; static struct completion emsgs_comp; static spinlock_t emsgs_lock; static int nblocked_emsgs_readers; -static struct class *aoe_class; + static struct aoe_chardev chardevs[] = { { MINOR_ERR, "err" }, { MINOR_DISCOVER, "discover" }, @@ -58,6 +58,16 @@ static struct aoe_chardev chardevs[] = { { MINOR_FLUSH, "flush" }, }; +static char *aoe_devnode(const struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev)); +} + +static const struct class aoe_class = { + .name = "aoe", + .devnode = aoe_devnode, +}; + static int discover(void) { @@ -273,11 +283,6 @@ static const struct file_operations aoe_fops = { .llseek = noop_llseek, }; -static char *aoe_devnode(const struct device *dev, umode_t *mode) -{ - return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev)); -} - int __init aoechr_init(void) { @@ -290,15 +295,14 @@ aoechr_init(void) } init_completion(&emsgs_comp); spin_lock_init(&emsgs_lock); - aoe_class = class_create("aoe"); - if (IS_ERR(aoe_class)) { + n = class_register(&aoe_class); + if (n) { unregister_chrdev(AOE_MAJOR, "aoechr"); - return PTR_ERR(aoe_class); + return n; } - aoe_class->devnode = aoe_devnode; for (i = 0; i < ARRAY_SIZE(chardevs); ++i) - device_create(aoe_class, NULL, + device_create(&aoe_class, NULL, MKDEV(AOE_MAJOR, chardevs[i].minor), NULL, chardevs[i].name); @@ -311,8 +315,8 @@ aoechr_exit(void) int i; for (i = 0; i < ARRAY_SIZE(chardevs); ++i) - device_destroy(aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor)); - class_destroy(aoe_class); + device_destroy(&aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor)); + class_unregister(&aoe_class); unregister_chrdev(AOE_MAJOR, "aoechr"); } diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 9deb4df6bdb8..cd738cab725f 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -442,13 +442,13 @@ static void fd_times_out(struct timer_list *unused); static void finish_fdc( void ); static void finish_fdc_done( int dummy ); static void setup_req_params( int drive ); -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int - cmd, unsigned long param); +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param); static void fd_probe( int drive ); static int fd_test_drive_present( int drive ); static void config_types( void ); -static int floppy_open(struct block_device *bdev, fmode_t mode); -static void floppy_release(struct gendisk *disk, fmode_t mode); +static int floppy_open(struct gendisk *disk, blk_mode_t mode); +static void floppy_release(struct gendisk *disk); /************************* End of Prototypes **************************/ @@ -1581,7 +1581,7 @@ out: return BLK_STS_OK; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct gendisk *disk = bdev->bd_disk; @@ -1760,15 +1760,15 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* invalidate the buffer track to force a reread */ BufferDrive = -1; set_bit(drive, &fake_change); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); return 0; default: return -EINVAL; } } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { int ret; @@ -1915,32 +1915,31 @@ static void __init config_types( void ) * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct atari_floppy_struct *p = bdev->bd_disk->private_data; - int type = MINOR(bdev->bd_dev) >> 2; + struct atari_floppy_struct *p = disk->private_data; + int type = disk->first_minor >> 2; DPRINT(("fd_open: type=%d\n",type)); if (p->ref && p->type != type) return -EBUSY; - if (p->ref == -1 || (p->ref && mode & FMODE_EXCL)) + if (p->ref == -1 || (p->ref && mode & BLK_OPEN_EXCL)) return -EBUSY; - - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) p->ref = -1; else p->ref++; p->type = type; - if (mode & FMODE_NDELAY) + if (mode & BLK_OPEN_NDELAY) return 0; - if (mode & (FMODE_READ|FMODE_WRITE)) { - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); - if (mode & FMODE_WRITE) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + if (disk_check_media_change(disk)) + floppy_revalidate(disk); + if (mode & BLK_OPEN_WRITE) { if (p->wpstat) { if (p->ref < 0) p->ref = 0; @@ -1953,18 +1952,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&ataflop_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&ataflop_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct atari_floppy_struct *p = disk->private_data; mutex_lock(&ataflop_mutex); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bcad9b926b0c..970bd6ff38c4 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -19,7 +19,7 @@ #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/pagemap.h> -#include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -28,7 +28,7 @@ #include <linux/uaccess.h> /* - * Each block ramdisk device has a radix_tree brd_pages of pages that stores + * Each block ramdisk device has a xarray brd_pages of pages that stores * the pages containing the block device's contents. A brd page's ->index is * its offset in PAGE_SIZE units. This is similar to, but in no way connected * with, the kernel's pagecache or buffer cache (which sit above our block @@ -40,11 +40,9 @@ struct brd_device { struct list_head brd_list; /* - * Backing store of pages and lock to protect it. This is the contents - * of the block device. + * Backing store of pages. This is the contents of the block device. */ - spinlock_t brd_lock; - struct radix_tree_root brd_pages; + struct xarray brd_pages; u64 brd_nr_pages; }; @@ -56,21 +54,8 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) pgoff_t idx; struct page *page; - /* - * The page lifetime is protected by the fact that we have opened the - * device node -- brd pages will never be deleted under us, so we - * don't need any further locking or refcounting. - * - * This is strictly true for the radix-tree nodes as well (ie. we - * don't actually need the rcu_read_lock()), however that is not a - * documented feature of the radix-tree API so it is better to be - * safe here (we don't have total exclusion from radix tree updates - * here, only deletes). - */ - rcu_read_lock(); idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */ - page = radix_tree_lookup(&brd->brd_pages, idx); - rcu_read_unlock(); + page = xa_load(&brd->brd_pages, idx); BUG_ON(page && page->index != idx); @@ -83,7 +68,7 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) { pgoff_t idx; - struct page *page; + struct page *page, *cur; int ret = 0; page = brd_lookup_page(brd, sector); @@ -94,71 +79,42 @@ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) if (!page) return -ENOMEM; - if (radix_tree_maybe_preload(gfp)) { - __free_page(page); - return -ENOMEM; - } + xa_lock(&brd->brd_pages); - spin_lock(&brd->brd_lock); idx = sector >> PAGE_SECTORS_SHIFT; page->index = idx; - if (radix_tree_insert(&brd->brd_pages, idx, page)) { + + cur = __xa_cmpxchg(&brd->brd_pages, idx, NULL, page, gfp); + + if (unlikely(cur)) { __free_page(page); - page = radix_tree_lookup(&brd->brd_pages, idx); - if (!page) - ret = -ENOMEM; - else if (page->index != idx) + ret = xa_err(cur); + if (!ret && (cur->index != idx)) ret = -EIO; } else { brd->brd_nr_pages++; } - spin_unlock(&brd->brd_lock); - radix_tree_preload_end(); + xa_unlock(&brd->brd_pages); + return ret; } /* - * Free all backing store pages and radix tree. This must only be called when + * Free all backing store pages and xarray. This must only be called when * there are no other users of the device. */ -#define FREE_BATCH 16 static void brd_free_pages(struct brd_device *brd) { - unsigned long pos = 0; - struct page *pages[FREE_BATCH]; - int nr_pages; - - do { - int i; - - nr_pages = radix_tree_gang_lookup(&brd->brd_pages, - (void **)pages, pos, FREE_BATCH); - - for (i = 0; i < nr_pages; i++) { - void *ret; - - BUG_ON(pages[i]->index < pos); - pos = pages[i]->index; - ret = radix_tree_delete(&brd->brd_pages, pos); - BUG_ON(!ret || ret != pages[i]); - __free_page(pages[i]); - } - - pos++; + struct page *page; + pgoff_t idx; - /* - * It takes 3.4 seconds to remove 80GiB ramdisk. - * So, we need cond_resched to avoid stalling the CPU. - */ + xa_for_each(&brd->brd_pages, idx, page) { + __free_page(page); cond_resched(); + } - /* - * This assumes radix_tree_gang_lookup always returns as - * many pages as possible. If the radix-tree code changes, - * so will this have to. - */ - } while (nr_pages == FREE_BATCH); + xa_destroy(&brd->brd_pages); } /* @@ -372,8 +328,7 @@ static int brd_alloc(int i) brd->brd_number = i; list_add_tail(&brd->brd_list, &brd_devices); - spin_lock_init(&brd->brd_lock); - INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC); + xa_init(&brd->brd_pages); snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 6ac8c54b44c7..85ca000a0564 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1043,9 +1043,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, GFP_NOIO, &drbd_md_io_bio_set); bio->bi_iter.bi_sector = on_disk_sector; - /* bio_add_page of a single page to an empty bio will always succeed, - * according to api. Do we want to assert that? */ - bio_add_page(bio, page, len, 0); + __bio_add_page(bio, page, len, 0); bio->bi_private = ctx; bio->bi_end_io = drbd_bm_endio; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 83987e7a5ef2..965f672557f2 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -37,7 +37,6 @@ #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/workqueue.h> -#define __KERNEL_SYSCALLS__ #include <linux/unistd.h> #include <linux/vmalloc.h> #include <linux/sched/signal.h> @@ -50,8 +49,8 @@ #include "drbd_debugfs.h" static DEFINE_MUTEX(drbd_main_mutex); -static int drbd_open(struct block_device *bdev, fmode_t mode); -static void drbd_release(struct gendisk *gd, fmode_t mode); +static int drbd_open(struct gendisk *disk, blk_mode_t mode); +static void drbd_release(struct gendisk *gd); static void md_sync_timer_fn(struct timer_list *t); static int w_bitmap_io(struct drbd_work *w, int unused); @@ -1883,9 +1882,9 @@ int drbd_send_all(struct drbd_connection *connection, struct socket *sock, void return 0; } -static int drbd_open(struct block_device *bdev, fmode_t mode) +static int drbd_open(struct gendisk *disk, blk_mode_t mode) { - struct drbd_device *device = bdev->bd_disk->private_data; + struct drbd_device *device = disk->private_data; unsigned long flags; int rv = 0; @@ -1895,7 +1894,7 @@ static int drbd_open(struct block_device *bdev, fmode_t mode) * and no race with updating open_cnt */ if (device->state.role != R_PRIMARY) { - if (mode & FMODE_WRITE) + if (mode & BLK_OPEN_WRITE) rv = -EROFS; else if (!drbd_allow_oos) rv = -EMEDIUMTYPE; @@ -1909,9 +1908,10 @@ static int drbd_open(struct block_device *bdev, fmode_t mode) return rv; } -static void drbd_release(struct gendisk *gd, fmode_t mode) +static void drbd_release(struct gendisk *gd) { struct drbd_device *device = gd->private_data; + mutex_lock(&drbd_main_mutex); device->open_cnt--; mutex_unlock(&drbd_main_mutex); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 1a5d3d72d91d..cddae6f4b00f 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1640,8 +1640,8 @@ static struct block_device *open_backing_dev(struct drbd_device *device, struct block_device *bdev; int err = 0; - bdev = blkdev_get_by_path(bdev_path, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, claim_ptr); + bdev = blkdev_get_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE, + claim_ptr, NULL); if (IS_ERR(bdev)) { drbd_err(device, "open(\"%s\") failed with %ld\n", bdev_path, PTR_ERR(bdev)); @@ -1653,7 +1653,7 @@ static struct block_device *open_backing_dev(struct drbd_device *device, err = bd_link_disk_holder(bdev, device->vdisk); if (err) { - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, claim_ptr); drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n", bdev_path, err); bdev = ERR_PTR(err); @@ -1695,13 +1695,13 @@ static int open_backing_devices(struct drbd_device *device, } static void close_backing_dev(struct drbd_device *device, struct block_device *bdev, - bool do_bd_unlink) + void *claim_ptr, bool do_bd_unlink) { if (!bdev) return; if (do_bd_unlink) bd_unlink_disk_holder(bdev, device->vdisk); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, claim_ptr); } void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev) @@ -1709,8 +1709,11 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev * if (ldev == NULL) return; - close_backing_dev(device, ldev->md_bdev, ldev->md_bdev != ldev->backing_bdev); - close_backing_dev(device, ldev->backing_bdev, true); + close_backing_dev(device, ldev->md_bdev, + ldev->md.meta_dev_idx < 0 ? + (void *)device : (void *)drbd_m_holder, + ldev->md_bdev != ldev->backing_bdev); + close_backing_dev(device, ldev->backing_bdev, device, true); kfree(ldev->disk_conf); kfree(ldev); @@ -2126,8 +2129,11 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) fail: conn_reconfig_done(connection); if (nbc) { - close_backing_dev(device, nbc->md_bdev, nbc->md_bdev != nbc->backing_bdev); - close_backing_dev(device, nbc->backing_bdev, true); + close_backing_dev(device, nbc->md_bdev, + nbc->disk_conf->meta_dev_idx < 0 ? + (void *)device : (void *)drbd_m_holder, + nbc->md_bdev != nbc->backing_bdev); + close_backing_dev(device, nbc->backing_bdev, device, true); kfree(nbc); } kfree(new_disk_conf); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 8c2bc47de473..0c9f54197768 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -27,7 +27,6 @@ #include <uapi/linux/sched/types.h> #include <linux/sched/signal.h> #include <linux/pkt_sched.h> -#define __KERNEL_SYSCALLS__ #include <linux/unistd.h> #include <linux/vmalloc.h> #include <linux/random.h> diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cec2c20f5e59..2db9b186b977 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -402,7 +402,7 @@ static struct floppy_drive_struct drive_state[N_DRIVE]; static struct floppy_write_errors write_errors[N_DRIVE]; static struct timer_list motor_off_timer[N_DRIVE]; static struct blk_mq_tag_set tag_sets[N_DRIVE]; -static struct block_device *opened_bdev[N_DRIVE]; +static struct gendisk *opened_disk[N_DRIVE]; static DEFINE_MUTEX(open_lock); static struct floppy_raw_cmd *raw_cmd, default_raw_cmd; @@ -3210,13 +3210,13 @@ static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, #endif -static int invalidate_drive(struct block_device *bdev) +static int invalidate_drive(struct gendisk *disk) { /* invalidate the buffer track to force a reread */ - set_bit((long)bdev->bd_disk->private_data, &fake_change); + set_bit((long)disk->private_data, &fake_change); process_fd_request(); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); return 0; } @@ -3251,10 +3251,11 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, floppy_type[type].size + 1; process_fd_request(); for (cnt = 0; cnt < N_DRIVE; cnt++) { - struct block_device *bdev = opened_bdev[cnt]; - if (!bdev || ITYPE(drive_state[cnt].fd_device) != type) + struct gendisk *disk = opened_disk[cnt]; + + if (!disk || ITYPE(drive_state[cnt].fd_device) != type) continue; - __invalidate_device(bdev, true); + __invalidate_device(disk->part0, true); } mutex_unlock(&open_lock); } else { @@ -3287,7 +3288,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, drive_state[current_drive].maxtrack || ((user_params[drive].sect ^ oldStretch) & (FD_SWAPSIDES | FD_SECTBASEMASK))) - invalidate_drive(bdev); + invalidate_drive(bdev->bd_disk); else process_fd_request(); } @@ -3393,8 +3394,8 @@ static bool valid_floppy_drive_params(const short autodetect[FD_AUTODETECT_SIZE] return true; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, - unsigned long param) +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param) { int drive = (long)bdev->bd_disk->private_data; int type = ITYPE(drive_state[drive].fd_device); @@ -3427,7 +3428,8 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int return ret; /* permission checks */ - if (((cmd & 0x40) && !(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) || + if (((cmd & 0x40) && + !(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL))) || ((cmd & 0x80) && !capable(CAP_SYS_ADMIN))) return -EPERM; @@ -3464,7 +3466,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int current_type[drive] = NULL; floppy_sizes[drive] = MAX_DISK_SIZE << 1; drive_state[drive].keep_data = 0; - return invalidate_drive(bdev); + return invalidate_drive(bdev->bd_disk); case FDSETPRM: case FDDEFPRM: return set_geometry(cmd, &inparam.g, drive, type, bdev); @@ -3503,7 +3505,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int case FDFLUSH: if (lock_fdc(drive)) return -EINTR; - return invalidate_drive(bdev); + return invalidate_drive(bdev->bd_disk); case FDSETEMSGTRESH: drive_params[drive].max_errors.reporting = (unsigned short)(param & 0x0f); return 0; @@ -3565,7 +3567,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -3653,8 +3655,8 @@ struct compat_floppy_write_errors { #define FDGETFDCSTAT32 _IOR(2, 0x15, struct compat_floppy_fdc_state) #define FDWERRORGET32 _IOR(2, 0x17, struct compat_floppy_write_errors) -static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned int cmd, - struct compat_floppy_struct __user *arg) +static int compat_set_geometry(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, struct compat_floppy_struct __user *arg) { struct floppy_struct v; int drive, type; @@ -3663,7 +3665,7 @@ static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned BUILD_BUG_ON(offsetof(struct floppy_struct, name) != offsetof(struct compat_floppy_struct, name)); - if (!(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) + if (!(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL))) return -EPERM; memset(&v, 0, sizeof(struct floppy_struct)); @@ -3860,8 +3862,8 @@ static int compat_werrorget(int drive, return 0; } -static int fd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, - unsigned long param) +static int fd_compat_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param) { int drive = (long)bdev->bd_disk->private_data; switch (cmd) { @@ -3962,7 +3964,7 @@ static void __init config_types(void) pr_cont("\n"); } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { int drive = (long)disk->private_data; @@ -3973,7 +3975,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) drive_state[drive].fd_ref = 0; } if (!drive_state[drive].fd_ref) - opened_bdev[drive] = NULL; + opened_disk[drive] = NULL; mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); } @@ -3983,9 +3985,9 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) * /dev/PS0 etc), and disallows simultaneous access to the same * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - int drive = (long)bdev->bd_disk->private_data; + int drive = (long)disk->private_data; int old_dev, new_dev; int try; int res = -EBUSY; @@ -3994,7 +3996,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) mutex_lock(&floppy_mutex); mutex_lock(&open_lock); old_dev = drive_state[drive].fd_device; - if (opened_bdev[drive] && opened_bdev[drive] != bdev) + if (opened_disk[drive] && opened_disk[drive] != disk) goto out2; if (!drive_state[drive].fd_ref && (drive_params[drive].flags & FD_BROKEN_DCL)) { @@ -4004,7 +4006,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) drive_state[drive].fd_ref++; - opened_bdev[drive] = bdev; + opened_disk[drive] = disk; res = -ENXIO; @@ -4038,7 +4040,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) } } - new_dev = MINOR(bdev->bd_dev); + new_dev = disk->first_minor; drive_state[drive].fd_device = new_dev; set_capacity(disks[drive][ITYPE(new_dev)], floppy_sizes[new_dev]); if (old_dev != -1 && old_dev != new_dev) { @@ -4048,21 +4050,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (fdc_state[FDC(drive)].rawcmd == 1) fdc_state[FDC(drive)].rawcmd = 2; - - if (!(mode & FMODE_NDELAY)) { - if (mode & (FMODE_READ|FMODE_WRITE)) { + if (!(mode & BLK_OPEN_NDELAY)) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { drive_state[drive].last_checked = 0; clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags)) goto out; if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags)) goto out; } res = -EROFS; - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && !test_bit(FD_DISK_WRITABLE_BIT, &drive_state[drive].flags)) goto out; } @@ -4073,7 +4074,7 @@ out: drive_state[drive].fd_ref--; if (!drive_state[drive].fd_ref) - opened_bdev[drive] = NULL; + opened_disk[drive] = NULL; out2: mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); @@ -4147,7 +4148,7 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) cbdata.drive = drive; bio_init(&bio, bdev, &bio_vec, 1, REQ_OP_READ); - bio_add_page(&bio, page, block_size(bdev), 0); + __bio_add_page(&bio, page, block_size(bdev), 0); bio.bi_iter.bi_sector = 0; bio.bi_flags |= (1 << BIO_QUIET); @@ -4203,7 +4204,8 @@ static int floppy_revalidate(struct gendisk *disk) drive_state[drive].generation++; if (drive_no_geom(drive)) { /* auto-sensing */ - res = __floppy_read_block_0(opened_bdev[drive], drive); + res = __floppy_read_block_0(opened_disk[drive]->part0, + drive); } else { if (cf) poll_drive(false, FD_RAW_NEED_DISK); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bc31bb7072a2..37511d2b2caf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -990,7 +990,7 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } -static int loop_configure(struct loop_device *lo, fmode_t mode, +static int loop_configure(struct loop_device *lo, blk_mode_t mode, struct block_device *bdev, const struct loop_config *config) { @@ -1014,8 +1014,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ - if (!(mode & FMODE_EXCL)) { - error = bd_prepare_to_claim(bdev, loop_configure); + if (!(mode & BLK_OPEN_EXCL)) { + error = bd_prepare_to_claim(bdev, loop_configure, NULL); if (error) goto out_putf; } @@ -1050,7 +1050,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (error) goto out_unlock; - if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || + if (!(file->f_mode & FMODE_WRITE) || !(mode & BLK_OPEN_WRITE) || !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; @@ -1116,7 +1116,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (partscan) loop_reread_partitions(lo); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); return 0; @@ -1124,7 +1124,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, out_unlock: loop_global_unlock(lo, is_loop); out_bdev: - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); @@ -1528,7 +1528,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, return err; } -static int lo_ioctl(struct block_device *bdev, fmode_t mode, +static int lo_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; @@ -1563,24 +1563,22 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status_old(lo, argp); - } break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status64(lo, argp); - } break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: case LOOP_SET_BLOCK_SIZE: - if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) + if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; default: @@ -1691,7 +1689,7 @@ loop_get_status_compat(struct loop_device *lo, return err; } -static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; @@ -1727,7 +1725,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif -static void lo_release(struct gendisk *disk, fmode_t mode) +static void lo_release(struct gendisk *disk) { struct loop_device *lo = disk->private_data; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 815d77ba6381..b200950e8fb5 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3041,7 +3041,7 @@ static int rssd_disk_name_format(char *prefix, * structure pointer. */ static int mtip_block_ioctl(struct block_device *dev, - fmode_t mode, + blk_mode_t mode, unsigned cmd, unsigned long arg) { @@ -3079,7 +3079,7 @@ static int mtip_block_ioctl(struct block_device *dev, * structure pointer. */ static int mtip_block_compat_ioctl(struct block_device *dev, - fmode_t mode, + blk_mode_t mode, unsigned cmd, unsigned long arg) { diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 65ecde3e2a5b..8576d696c7a2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1502,7 +1502,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, return -ENOTTY; } -static int nbd_ioctl(struct block_device *bdev, fmode_t mode, +static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nbd_device *nbd = bdev->bd_disk->private_data; @@ -1553,13 +1553,13 @@ static struct nbd_config *nbd_alloc_config(void) return config; } -static int nbd_open(struct block_device *bdev, fmode_t mode) +static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; int ret = 0; mutex_lock(&nbd_index_mutex); - nbd = bdev->bd_disk->private_data; + nbd = disk->private_data; if (!nbd) { ret = -ENXIO; goto out; @@ -1587,17 +1587,17 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + set_bit(GD_NEED_PART_SCAN, &disk->state); } else if (nbd_disconnected(nbd->config)) { if (max_part) - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + set_bit(GD_NEED_PART_SCAN, &disk->state); } out: mutex_unlock(&nbd_index_mutex); return ret; } -static void nbd_release(struct gendisk *disk, fmode_t mode) +static void nbd_release(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; @@ -1776,7 +1776,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) if (err == -ENOSPC) err = -EEXIST; } else { - err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL); + err = idr_alloc(&nbd_index_idr, nbd, 0, + (MINORMASK >> part_shift) + 1, GFP_KERNEL); if (err >= 0) index = err; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index d5d7884cedd4..a1428538bda5 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -46,47 +46,34 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/pktcdvd.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> +#include <linux/backing-dev.h> #include <linux/compat.h> -#include <linux/kthread.h> +#include <linux/debugfs.h> +#include <linux/device.h> #include <linux/errno.h> -#include <linux/spinlock.h> #include <linux/file.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/miscdevice.h> #include <linux/freezer.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/miscdevice.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/nospec.h> +#include <linux/pktcdvd.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/slab.h> -#include <linux/backing-dev.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/uaccess.h> + +#include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_ioctl.h> -#include <scsi/scsi.h> -#include <linux/debugfs.h> -#include <linux/device.h> -#include <linux/nospec.h> -#include <linux/uaccess.h> -#define DRIVER_NAME "pktcdvd" +#include <asm/unaligned.h> -#define pkt_err(pd, fmt, ...) \ - pr_err("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_notice(pd, fmt, ...) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_info(pd, fmt, ...) \ - pr_info("%s: " fmt, pd->name, ##__VA_ARGS__) - -#define pkt_dbg(level, pd, fmt, ...) \ -do { \ - if (level == 2 && PACKET_DEBUG >= 2) \ - pr_notice("%s: %s():" fmt, \ - pd->name, __func__, ##__VA_ARGS__); \ - else if (level == 1 && PACKET_DEBUG >= 1) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \ -} while (0) +#define DRIVER_NAME "pktcdvd" #define MAX_SPEED 0xffff @@ -107,7 +94,6 @@ static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ /* forward declaration */ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev); static int pkt_remove_dev(dev_t pkt_dev); -static int pkt_seq_show(struct seq_file *m, void *p); static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd) { @@ -253,15 +239,16 @@ static ssize_t congestion_off_store(struct device *dev, const char *buf, size_t len) { struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; + int val, ret; - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_off = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } + ret = kstrtoint(buf, 10, &val); + if (ret) + return ret; + + spin_lock(&pd->lock); + pd->write_congestion_off = val; + init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on); + spin_unlock(&pd->lock); return len; } static DEVICE_ATTR_RW(congestion_off); @@ -283,15 +270,16 @@ static ssize_t congestion_on_store(struct device *dev, const char *buf, size_t len) { struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; + int val, ret; - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_on = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } + ret = kstrtoint(buf, 10, &val); + if (ret) + return ret; + + spin_lock(&pd->lock); + pd->write_congestion_on = val; + init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on); + spin_unlock(&pd->lock); return len; } static DEVICE_ATTR_RW(congestion_on); @@ -319,7 +307,7 @@ static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) if (class_is_registered(&class_pktcdvd)) { pd->dev = device_create_with_groups(&class_pktcdvd, NULL, MKDEV(0, 0), pd, pkt_groups, - "%s", pd->name); + "%s", pd->disk->disk_name); if (IS_ERR(pd->dev)) pd->dev = NULL; } @@ -349,8 +337,8 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu struct pktcdvd_device *pd = pkt_devs[idx]; if (!pd) continue; - n += sprintf(data+n, "%s %u:%u %u:%u\n", - pd->name, + n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n", + pd->disk->disk_name, MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), MAJOR(pd->bdev->bd_dev), MINOR(pd->bdev->bd_dev)); @@ -428,34 +416,92 @@ static void pkt_sysfs_cleanup(void) *******************************************************************/ -static int pkt_debugfs_seq_show(struct seq_file *m, void *p) +static void pkt_count_states(struct pktcdvd_device *pd, int *states) { - return pkt_seq_show(m, p); + struct packet_data *pkt; + int i; + + for (i = 0; i < PACKET_NUM_STATES; i++) + states[i] = 0; + + spin_lock(&pd->cdrw.active_list_lock); + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + states[pkt->state]++; + } + spin_unlock(&pd->cdrw.active_list_lock); } -static int pkt_debugfs_fops_open(struct inode *inode, struct file *file) +static int pkt_seq_show(struct seq_file *m, void *p) { - return single_open(file, pkt_debugfs_seq_show, inode->i_private); -} + struct pktcdvd_device *pd = m->private; + char *msg; + int states[PACKET_NUM_STATES]; -static const struct file_operations debug_fops = { - .open = pkt_debugfs_fops_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; + seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name, pd->bdev); + + seq_printf(m, "\nSettings:\n"); + seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); + + if (pd->settings.write_type == 0) + msg = "Packet"; + else + msg = "Unknown"; + seq_printf(m, "\twrite type:\t\t%s\n", msg); + + seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); + seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); + + seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); + + if (pd->settings.block_mode == PACKET_BLOCK_MODE1) + msg = "Mode 1"; + else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) + msg = "Mode 2"; + else + msg = "Unknown"; + seq_printf(m, "\tblock mode:\t\t%s\n", msg); + + seq_printf(m, "\nStatistics:\n"); + seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); + seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); + seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); + seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); + seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); + + seq_printf(m, "\nMisc:\n"); + seq_printf(m, "\treference count:\t%d\n", pd->refcnt); + seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); + seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); + seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); + seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); + seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); + + seq_printf(m, "\nQueue state:\n"); + seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); + seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); + seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", pd->current_sector); + + pkt_count_states(pd, states); + seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); + + seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", + pd->write_congestion_off, + pd->write_congestion_on); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(pkt_seq); static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) { if (!pkt_debugfs_root) return; - pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root); + pd->dfs_d_root = debugfs_create_dir(pd->disk->disk_name, pkt_debugfs_root); if (!pd->dfs_d_root) return; - pd->dfs_f_info = debugfs_create_file("info", 0444, - pd->dfs_d_root, pd, &debug_fops); + pd->dfs_f_info = debugfs_create_file("info", 0444, pd->dfs_d_root, + pd, &pkt_seq_fops); } static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd) @@ -484,9 +530,11 @@ static void pkt_debugfs_cleanup(void) static void pkt_bio_finished(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); + BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0); if (atomic_dec_and_test(&pd->cdrw.pending_bios)) { - pkt_dbg(2, pd, "queue empty\n"); + dev_dbg(ddev, "queue empty\n"); atomic_set(&pd->iosched.attention, 1); wake_up(&pd->wqueue); } @@ -717,15 +765,16 @@ static const char *sense_key_string(__u8 index) static void pkt_dump_sense(struct pktcdvd_device *pd, struct packet_command *cgc) { + struct device *ddev = disk_to_dev(pd->disk); struct scsi_sense_hdr *sshdr = cgc->sshdr; if (sshdr) - pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", + dev_err(ddev, "%*ph - sense %02x.%02x.%02x (%s)\n", CDROM_PACKET_SIZE, cgc->cmd, sshdr->sense_key, sshdr->asc, sshdr->ascq, sense_key_string(sshdr->sense_key)); else - pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); + dev_err(ddev, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); } /* @@ -762,10 +811,8 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); cgc.sshdr = &sshdr; cgc.cmd[0] = GPCMD_SET_SPEED; - cgc.cmd[2] = (read_speed >> 8) & 0xff; - cgc.cmd[3] = read_speed & 0xff; - cgc.cmd[4] = (write_speed >> 8) & 0xff; - cgc.cmd[5] = write_speed & 0xff; + put_unaligned_be16(read_speed, &cgc.cmd[2]); + put_unaligned_be16(write_speed, &cgc.cmd[4]); ret = pkt_generic_packet(pd, &cgc); if (ret) @@ -809,6 +856,7 @@ static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) */ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); if (atomic_read(&pd->iosched.attention) == 0) return; @@ -836,7 +884,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) need_write_seek = 0; if (need_write_seek && reads_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "write, waiting\n"); + dev_dbg(ddev, "write, waiting\n"); break; } pkt_flush_cache(pd); @@ -845,7 +893,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) } else { if (!reads_queued && writes_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "read, waiting\n"); + dev_dbg(ddev, "read, waiting\n"); break; } pd->iosched.writing = 1; @@ -892,25 +940,27 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) */ static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) { - if ((pd->settings.size << 9) / CD_FRAMESIZE - <= queue_max_segments(q)) { + struct device *ddev = disk_to_dev(pd->disk); + + if ((pd->settings.size << 9) / CD_FRAMESIZE <= queue_max_segments(q)) { /* * The cdrom device can handle one segment/frame */ clear_bit(PACKET_MERGE_SEGS, &pd->flags); return 0; - } else if ((pd->settings.size << 9) / PAGE_SIZE - <= queue_max_segments(q)) { + } + + if ((pd->settings.size << 9) / PAGE_SIZE <= queue_max_segments(q)) { /* * We can handle this case at the expense of some extra memory * copies during write operations */ set_bit(PACKET_MERGE_SEGS, &pd->flags); return 0; - } else { - pkt_err(pd, "cdrom max_phys_segments too small\n"); - return -EIO; } + + dev_err(ddev, "cdrom max_phys_segments too small\n"); + return -EIO; } static void pkt_end_io_read(struct bio *bio) @@ -919,9 +969,8 @@ static void pkt_end_io_read(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", - bio, (unsigned long long)pkt->sector, - (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); + dev_dbg(disk_to_dev(pd->disk), "bio=%p sec0=%llx sec=%llx err=%d\n", + bio, pkt->sector, bio->bi_iter.bi_sector, bio->bi_status); if (bio->bi_status) atomic_inc(&pkt->io_errors); @@ -939,7 +988,7 @@ static void pkt_end_io_packet_write(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); + dev_dbg(disk_to_dev(pd->disk), "id=%d, err=%d\n", pkt->id, bio->bi_status); pd->stats.pkt_ended++; @@ -955,6 +1004,7 @@ static void pkt_end_io_packet_write(struct bio *bio) */ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int frames_read = 0; struct bio *bio; int f; @@ -983,8 +1033,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) spin_unlock(&pkt->lock); if (pkt->cache_valid) { - pkt_dbg(2, pd, "zone %llx cached\n", - (unsigned long long)pkt->sector); + dev_dbg(ddev, "zone %llx cached\n", pkt->sector); goto out_account; } @@ -1005,8 +1054,8 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) p = (f * CD_FRAMESIZE) / PAGE_SIZE; offset = (f * CD_FRAMESIZE) % PAGE_SIZE; - pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n", - f, pkt->pages[p], offset); + dev_dbg(ddev, "Adding frame %d, page:%p offs:%d\n", f, + pkt->pages[p], offset); if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset)) BUG(); @@ -1016,8 +1065,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) } out_account: - pkt_dbg(2, pd, "need %d frames for zone %llx\n", - frames_read, (unsigned long long)pkt->sector); + dev_dbg(ddev, "need %d frames for zone %llx\n", frames_read, pkt->sector); pd->stats.pkt_started++; pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9); } @@ -1051,17 +1099,17 @@ static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *p } } -static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state) +static inline void pkt_set_state(struct device *ddev, struct packet_data *pkt, + enum packet_data_state state) { -#if PACKET_DEBUG > 1 static const char *state_name[] = { "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED" }; enum packet_data_state old_state = pkt->state; - pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n", - pkt->id, (unsigned long long)pkt->sector, - state_name[old_state], state_name[state]); -#endif + + dev_dbg(ddev, "pkt %2d : s=%6llx %s -> %s\n", + pkt->id, pkt->sector, state_name[old_state], state_name[state]); + pkt->state = state; } @@ -1071,6 +1119,7 @@ static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state */ static int pkt_handle_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *p; struct bio *bio = NULL; sector_t zone = 0; /* Suppress gcc warning */ @@ -1080,7 +1129,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd) atomic_set(&pd->scan_queue, 0); if (list_empty(&pd->cdrw.pkt_free_list)) { - pkt_dbg(2, pd, "no pkt\n"); + dev_dbg(ddev, "no pkt\n"); return 0; } @@ -1117,7 +1166,7 @@ try_next_bio: } spin_unlock(&pd->lock); if (!bio) { - pkt_dbg(2, pd, "no bio\n"); + dev_dbg(ddev, "no bio\n"); return 0; } @@ -1133,12 +1182,13 @@ try_next_bio: * to this packet. */ spin_lock(&pd->lock); - pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone); + dev_dbg(ddev, "looking for zone %llx\n", zone); while ((node = pkt_rbtree_find(pd, zone)) != NULL) { + sector_t tmp = get_zone(node->bio->bi_iter.bi_sector, pd); + bio = node->bio; - pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long) - get_zone(bio->bi_iter.bi_sector, pd)); - if (get_zone(bio->bi_iter.bi_sector, pd) != zone) + dev_dbg(ddev, "found zone=%llx\n", tmp); + if (tmp != zone) break; pkt_rbtree_erase(pd, node); spin_lock(&pkt->lock); @@ -1157,7 +1207,7 @@ try_next_bio: spin_unlock(&pd->lock); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); - pkt_set_state(pkt, PACKET_WAITING_STATE); + pkt_set_state(ddev, pkt, PACKET_WAITING_STATE); atomic_set(&pkt->run_sm, 1); spin_lock(&pd->cdrw.active_list_lock); @@ -1209,6 +1259,7 @@ static void bio_list_copy_data(struct bio *dst, struct bio *src) */ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int f; bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, @@ -1225,7 +1276,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset)) BUG(); } - pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt); + dev_dbg(ddev, "vcnt=%d\n", pkt->w_bio->bi_vcnt); /* * Fill-in bvec with data from orig_bios. @@ -1233,11 +1284,10 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) spin_lock(&pkt->lock); bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); - pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_WRITE_WAIT_STATE); spin_unlock(&pkt->lock); - pkt_dbg(2, pd, "Writing %d frames for zone %llx\n", - pkt->write_size, (unsigned long long)pkt->sector); + dev_dbg(ddev, "Writing %d frames for zone %llx\n", pkt->write_size, pkt->sector); if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) pkt->cache_valid = 1; @@ -1265,7 +1315,9 @@ static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt) { - pkt_dbg(2, pd, "pkt %d\n", pkt->id); + struct device *ddev = disk_to_dev(pd->disk); + + dev_dbg(ddev, "pkt %d\n", pkt->id); for (;;) { switch (pkt->state) { @@ -1275,7 +1327,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data pkt->sleep_time = 0; pkt_gather_data(pd, pkt); - pkt_set_state(pkt, PACKET_READ_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_READ_WAIT_STATE); break; case PACKET_READ_WAIT_STATE: @@ -1283,7 +1335,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (atomic_read(&pkt->io_errors) > 0) { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } else { pkt_start_write(pd, pkt); } @@ -1294,15 +1346,15 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (!pkt->w_bio->bi_status) { - pkt_set_state(pkt, PACKET_FINISHED_STATE); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); } else { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } break; case PACKET_RECOVERY_STATE: - pkt_dbg(2, pd, "No recovery possible\n"); - pkt_set_state(pkt, PACKET_FINISHED_STATE); + dev_dbg(ddev, "No recovery possible\n"); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); break; case PACKET_FINISHED_STATE: @@ -1318,6 +1370,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data static void pkt_handle_packets(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *next; /* @@ -1338,28 +1391,13 @@ static void pkt_handle_packets(struct pktcdvd_device *pd) if (pkt->state == PACKET_FINISHED_STATE) { list_del(&pkt->list); pkt_put_packet_data(pd, pkt); - pkt_set_state(pkt, PACKET_IDLE_STATE); + pkt_set_state(ddev, pkt, PACKET_IDLE_STATE); atomic_set(&pd->scan_queue, 1); } } spin_unlock(&pd->cdrw.active_list_lock); } -static void pkt_count_states(struct pktcdvd_device *pd, int *states) -{ - struct packet_data *pkt; - int i; - - for (i = 0; i < PACKET_NUM_STATES; i++) - states[i] = 0; - - spin_lock(&pd->cdrw.active_list_lock); - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - states[pkt->state]++; - } - spin_unlock(&pd->cdrw.active_list_lock); -} - /* * kcdrwd is woken up when writes have been queued for one of our * registered devices @@ -1367,7 +1405,9 @@ static void pkt_count_states(struct pktcdvd_device *pd, int *states) static int kcdrwd(void *foobar) { struct pktcdvd_device *pd = foobar; + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt; + int states[PACKET_NUM_STATES]; long min_sleep_time, residue; set_user_nice(current, MIN_NICE); @@ -1398,13 +1438,9 @@ static int kcdrwd(void *foobar) goto work_to_do; /* Otherwise, go to sleep */ - if (PACKET_DEBUG > 1) { - int states[PACKET_NUM_STATES]; - pkt_count_states(pd, states); - pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], - states[3], states[4], states[5]); - } + pkt_count_states(pd, states); + dev_dbg(ddev, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); min_sleep_time = MAX_SCHEDULE_TIMEOUT; list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { @@ -1412,9 +1448,9 @@ static int kcdrwd(void *foobar) min_sleep_time = pkt->sleep_time; } - pkt_dbg(2, pd, "sleeping\n"); + dev_dbg(ddev, "sleeping\n"); residue = schedule_timeout(min_sleep_time); - pkt_dbg(2, pd, "wake up\n"); + dev_dbg(ddev, "wake up\n"); /* make swsusp happy with our thread */ try_to_freeze(); @@ -1462,7 +1498,7 @@ work_to_do: static void pkt_print_settings(struct pktcdvd_device *pd) { - pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n", + dev_info(disk_to_dev(pd->disk), "%s packets, %u blocks, Mode-%c disc\n", pd->settings.fp ? "Fixed" : "Variable", pd->settings.size >> 2, pd->settings.block_mode == 8 ? '1' : '2'); @@ -1474,8 +1510,7 @@ static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, cgc->cmd[0] = GPCMD_MODE_SENSE_10; cgc->cmd[2] = page_code | (page_control << 6); - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; + put_unaligned_be16(cgc->buflen, &cgc->cmd[7]); cgc->data_direction = CGC_DATA_READ; return pkt_generic_packet(pd, cgc); } @@ -1486,8 +1521,7 @@ static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc memset(cgc->buffer, 0, 2); cgc->cmd[0] = GPCMD_MODE_SELECT_10; cgc->cmd[1] = 0x10; /* PF */ - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; + put_unaligned_be16(cgc->buflen, &cgc->cmd[7]); cgc->data_direction = CGC_DATA_WRITE; return pkt_generic_packet(pd, cgc); } @@ -1528,8 +1562,7 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ); cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO; cgc.cmd[1] = type & 3; - cgc.cmd[4] = (track & 0xff00) >> 8; - cgc.cmd[5] = track & 0xff; + put_unaligned_be16(track, &cgc.cmd[4]); cgc.cmd[8] = 8; cgc.quiet = 1; @@ -1590,6 +1623,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, */ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; write_param_page *wp; @@ -1609,8 +1643,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) return ret; } - size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff)); - pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff); + size = 2 + get_unaligned_be16(&buffer[0]); + pd->mode_offset = get_unaligned_be16(&buffer[6]); if (size > sizeof(buffer)) size = sizeof(buffer); @@ -1656,7 +1690,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) /* * paranoia */ - pkt_err(pd, "write mode wrong %d\n", wp->data_block_type); + dev_err(ddev, "write mode wrong %d\n", wp->data_block_type); return 1; } wp->packet_size = cpu_to_be32(pd->settings.size >> 2); @@ -1677,6 +1711,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) */ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ @@ -1701,7 +1737,7 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) if (ti->rt == 1 && ti->blank == 0) return 1; - pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); + dev_err(ddev, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); return 0; } @@ -1710,6 +1746,8 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) */ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x0a: /* CD-RW */ case 0xffff: /* MMC3 not supported */ @@ -1719,8 +1757,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) case 0x12: /* DVD-RAM */ return 1; default: - pkt_dbg(2, pd, "Wrong disc profile (%x)\n", - pd->mmc3_profile); + dev_dbg(ddev, "Wrong disc profile (%x)\n", pd->mmc3_profile); return 0; } @@ -1729,22 +1766,22 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) * but i'm not sure, should we leave this to user apps? probably. */ if (di->disc_type == 0xff) { - pkt_notice(pd, "unknown disc - no track?\n"); + dev_notice(ddev, "unknown disc - no track?\n"); return 0; } if (di->disc_type != 0x20 && di->disc_type != 0) { - pkt_err(pd, "wrong disc type (%x)\n", di->disc_type); + dev_err(ddev, "wrong disc type (%x)\n", di->disc_type); return 0; } if (di->erasable == 0) { - pkt_notice(pd, "disc not erasable\n"); + dev_err(ddev, "disc not erasable\n"); return 0; } if (di->border_status == PACKET_SESSION_RESERVED) { - pkt_err(pd, "can't write to last track (reserved)\n"); + dev_err(ddev, "can't write to last track (reserved)\n"); return 0; } @@ -1753,6 +1790,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; unsigned char buf[12]; disc_information di; @@ -1763,14 +1801,14 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) cgc.cmd[0] = GPCMD_GET_CONFIGURATION; cgc.cmd[8] = 8; ret = pkt_generic_packet(pd, &cgc); - pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7]; + pd->mmc3_profile = ret ? 0xffff : get_unaligned_be16(&buf[6]); memset(&di, 0, sizeof(disc_information)); memset(&ti, 0, sizeof(track_information)); ret = pkt_get_disc_info(pd, &di); if (ret) { - pkt_err(pd, "failed get_disc\n"); + dev_err(ddev, "failed get_disc\n"); return ret; } @@ -1782,12 +1820,12 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */ ret = pkt_get_track_info(pd, track, 1, &ti); if (ret) { - pkt_err(pd, "failed get_track\n"); + dev_err(ddev, "failed get_track\n"); return ret; } if (!pkt_writable_track(pd, &ti)) { - pkt_err(pd, "can't write to this track\n"); + dev_err(ddev, "can't write to this track\n"); return -EROFS; } @@ -1797,11 +1835,11 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; if (pd->settings.size == 0) { - pkt_notice(pd, "detected zero packet size!\n"); + dev_notice(ddev, "detected zero packet size!\n"); return -ENXIO; } if (pd->settings.size > PACKET_MAX_SECTORS) { - pkt_err(pd, "packet size is too big\n"); + dev_err(ddev, "packet size is too big\n"); return -EROFS; } pd->settings.fp = ti.fp; @@ -1843,7 +1881,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) pd->settings.block_mode = PACKET_BLOCK_MODE2; break; default: - pkt_err(pd, "unknown data mode\n"); + dev_err(ddev, "unknown data mode\n"); return -EROFS; } return 0; @@ -1854,6 +1892,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -1880,13 +1919,13 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) */ buf[pd->mode_offset + 10] |= (set << 2); - cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff)); + cgc.buflen = cgc.cmd[8] = 2 + get_unaligned_be16(&buf[0]); ret = pkt_mode_select(pd, &cgc); if (ret) { - pkt_err(pd, "write caching control failed\n"); + dev_err(ddev, "write caching control failed\n"); pkt_dump_sense(pd, &cgc); } else if (!ret && set) - pkt_notice(pd, "enabled write caching\n"); + dev_notice(ddev, "enabled write caching\n"); return ret; } @@ -1935,12 +1974,12 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd, * Speed Performance Descriptor Block", use the information * in the first block. (contains the highest speed) */ - int num_spdb = (cap_buf[30] << 8) + cap_buf[31]; + int num_spdb = get_unaligned_be16(&cap_buf[30]); if (num_spdb > 0) offset = 34; } - *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1]; + *write_speed = get_unaligned_be16(&cap_buf[offset]); return 0; } @@ -1967,6 +2006,7 @@ static char us_clv_to_speed[16] = { static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, unsigned *speed) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -1984,7 +2024,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, pkt_dump_sense(pd, &cgc); return ret; } - size = ((unsigned int) buf[0]<<8) + buf[1] + 2; + size = 2 + get_unaligned_be16(&buf[0]); if (size > sizeof(buf)) size = sizeof(buf); @@ -2001,11 +2041,11 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, } if (!(buf[6] & 0x40)) { - pkt_notice(pd, "disc type is not CD-RW\n"); + dev_notice(ddev, "disc type is not CD-RW\n"); return 1; } if (!(buf[6] & 0x4)) { - pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n"); + dev_notice(ddev, "A1 values on media are not valid, maybe not CDRW?\n"); return 1; } @@ -2025,25 +2065,26 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, *speed = us_clv_to_speed[sp]; break; default: - pkt_notice(pd, "unknown disc sub-type %d\n", st); + dev_notice(ddev, "unknown disc sub-type %d\n", st); return 1; } if (*speed) { - pkt_info(pd, "maximum media speed: %d\n", *speed); + dev_info(ddev, "maximum media speed: %d\n", *speed); return 0; } else { - pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st); + dev_notice(ddev, "unknown speed %d for sub-type %d\n", sp, st); return 1; } } static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; int ret; - pkt_dbg(2, pd, "Performing OPC\n"); + dev_dbg(ddev, "Performing OPC\n"); init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); cgc.sshdr = &sshdr; @@ -2058,18 +2099,19 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) static int pkt_open_write(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); int ret; unsigned int write_speed, media_write_speed, read_speed; ret = pkt_probe_settings(pd); if (ret) { - pkt_dbg(2, pd, "failed probe\n"); + dev_dbg(ddev, "failed probe\n"); return ret; } ret = pkt_set_write_settings(pd); if (ret) { - pkt_dbg(1, pd, "failed saving write settings\n"); + dev_notice(ddev, "failed saving write settings\n"); return -EIO; } @@ -2082,30 +2124,29 @@ static int pkt_open_write(struct pktcdvd_device *pd) case 0x13: /* DVD-RW */ case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ - pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed); + dev_notice(ddev, "write speed %ukB/s\n", write_speed); break; default: ret = pkt_media_speed(pd, &media_write_speed); if (ret) media_write_speed = 16; write_speed = min(write_speed, media_write_speed * 177); - pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176); + dev_notice(ddev, "write speed %ux\n", write_speed / 176); break; } read_speed = write_speed; ret = pkt_set_speed(pd, write_speed, read_speed); if (ret) { - pkt_dbg(1, pd, "couldn't set write speed\n"); + dev_notice(ddev, "couldn't set write speed\n"); return -EIO; } pd->write_speed = write_speed; pd->read_speed = read_speed; ret = pkt_perform_opc(pd); - if (ret) { - pkt_dbg(1, pd, "Optimum Power Calibration failed\n"); - } + if (ret) + dev_notice(ddev, "Optimum Power Calibration failed\n"); return 0; } @@ -2113,8 +2154,9 @@ static int pkt_open_write(struct pktcdvd_device *pd) /* * called at open time. */ -static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) +static int pkt_open_dev(struct pktcdvd_device *pd, bool write) { + struct device *ddev = disk_to_dev(pd->disk); int ret; long lba; struct request_queue *q; @@ -2125,7 +2167,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) * to read/write from/to it. It is already opened in O_NONBLOCK mode * so open should not fail. */ - bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd); + bdev = blkdev_get_by_dev(pd->bdev->bd_dev, BLK_OPEN_READ, pd, NULL); if (IS_ERR(bdev)) { ret = PTR_ERR(bdev); goto out; @@ -2133,7 +2175,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) ret = pkt_get_last_written(pd, &lba); if (ret) { - pkt_err(pd, "pkt_get_last_written failed\n"); + dev_err(ddev, "pkt_get_last_written failed\n"); goto out_putdev; } @@ -2162,17 +2204,17 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) if (write) { if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { - pkt_err(pd, "not enough memory for buffers\n"); + dev_err(ddev, "not enough memory for buffers\n"); ret = -ENOMEM; goto out_putdev; } - pkt_info(pd, "%lukB available on disc\n", lba << 1); + dev_info(ddev, "%lukB available on disc\n", lba << 1); } return 0; out_putdev: - blkdev_put(bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(bdev, pd); out: return ret; } @@ -2183,13 +2225,15 @@ out: */ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) { + struct device *ddev = disk_to_dev(pd->disk); + if (flush && pkt_flush_cache(pd)) - pkt_dbg(1, pd, "not flushing cache\n"); + dev_notice(ddev, "not flushing cache\n"); pkt_lock_door(pd, 0); pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); - blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(pd->bdev, pd); pkt_shrink_pktlist(pd); } @@ -2203,14 +2247,14 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) return pkt_devs[dev_minor]; } -static int pkt_open(struct block_device *bdev, fmode_t mode) +static int pkt_open(struct gendisk *disk, blk_mode_t mode) { struct pktcdvd_device *pd = NULL; int ret; mutex_lock(&pktcdvd_mutex); mutex_lock(&ctl_mutex); - pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev)); + pd = pkt_find_dev_from_minor(disk->first_minor); if (!pd) { ret = -ENODEV; goto out; @@ -2219,22 +2263,21 @@ static int pkt_open(struct block_device *bdev, fmode_t mode) pd->refcnt++; if (pd->refcnt > 1) { - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && !test_bit(PACKET_WRITABLE, &pd->flags)) { ret = -EBUSY; goto out_dec; } } else { - ret = pkt_open_dev(pd, mode & FMODE_WRITE); + ret = pkt_open_dev(pd, mode & BLK_OPEN_WRITE); if (ret) goto out_dec; /* * needed here as well, since ext2 (among others) may change * the blocksize at mount time */ - set_blocksize(bdev, CD_FRAMESIZE); + set_blocksize(disk->part0, CD_FRAMESIZE); } - mutex_unlock(&ctl_mutex); mutex_unlock(&pktcdvd_mutex); return 0; @@ -2247,7 +2290,7 @@ out: return ret; } -static void pkt_close(struct gendisk *disk, fmode_t mode) +static void pkt_release(struct gendisk *disk) { struct pktcdvd_device *pd = disk->private_data; @@ -2385,15 +2428,15 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) static void pkt_submit_bio(struct bio *bio) { struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; + struct device *ddev = disk_to_dev(pd->disk); struct bio *split; bio = bio_split_to_limits(bio); if (!bio) return; - pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", - (unsigned long long)bio->bi_iter.bi_sector, - (unsigned long long)bio_end_sector(bio)); + dev_dbg(ddev, "start = %6llx stop = %6llx\n", + bio->bi_iter.bi_sector, bio_end_sector(bio)); /* * Clone READ bios so we can have our own bi_end_io callback. @@ -2404,13 +2447,12 @@ static void pkt_submit_bio(struct bio *bio) } if (!test_bit(PACKET_WRITABLE, &pd->flags)) { - pkt_notice(pd, "WRITE for ro device (%llu)\n", - (unsigned long long)bio->bi_iter.bi_sector); + dev_notice(ddev, "WRITE for ro device (%llu)\n", bio->bi_iter.bi_sector); goto end_io; } if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) { - pkt_err(pd, "wrong bio size\n"); + dev_err(ddev, "wrong bio size\n"); goto end_io; } @@ -2446,74 +2488,15 @@ static void pkt_init_queue(struct pktcdvd_device *pd) q->queuedata = pd; } -static int pkt_seq_show(struct seq_file *m, void *p) -{ - struct pktcdvd_device *pd = m->private; - char *msg; - int states[PACKET_NUM_STATES]; - - seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev); - - seq_printf(m, "\nSettings:\n"); - seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); - - if (pd->settings.write_type == 0) - msg = "Packet"; - else - msg = "Unknown"; - seq_printf(m, "\twrite type:\t\t%s\n", msg); - - seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); - seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); - - seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); - - if (pd->settings.block_mode == PACKET_BLOCK_MODE1) - msg = "Mode 1"; - else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) - msg = "Mode 2"; - else - msg = "Unknown"; - seq_printf(m, "\tblock mode:\t\t%s\n", msg); - - seq_printf(m, "\nStatistics:\n"); - seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); - seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); - seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); - seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); - seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); - - seq_printf(m, "\nMisc:\n"); - seq_printf(m, "\treference count:\t%d\n", pd->refcnt); - seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); - seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); - seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); - seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); - seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); - - seq_printf(m, "\nQueue state:\n"); - seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); - seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); - seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector); - - pkt_count_states(pd, states); - seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], states[3], states[4], states[5]); - - seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", - pd->write_congestion_off, - pd->write_congestion_on); - return 0; -} - static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) { + struct device *ddev = disk_to_dev(pd->disk); int i; struct block_device *bdev; struct scsi_device *sdev; if (pd->pkt_dev == dev) { - pkt_err(pd, "recursive setup not allowed\n"); + dev_err(ddev, "recursive setup not allowed\n"); return -EBUSY; } for (i = 0; i < MAX_WRITERS; i++) { @@ -2521,21 +2504,22 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) if (!pd2) continue; if (pd2->bdev->bd_dev == dev) { - pkt_err(pd, "%pg already setup\n", pd2->bdev); + dev_err(ddev, "%pg already setup\n", pd2->bdev); return -EBUSY; } if (pd2->pkt_dev == dev) { - pkt_err(pd, "can't chain pktcdvd devices\n"); + dev_err(ddev, "can't chain pktcdvd devices\n"); return -EBUSY; } } - bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY, NULL, + NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); sdev = scsi_device_from_queue(bdev->bd_disk->queue); if (!sdev) { - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(bdev, NULL); return -EINVAL; } put_device(&sdev->sdev_gendev); @@ -2549,30 +2533,31 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) pkt_init_queue(pd); atomic_set(&pd->cdrw.pending_bios, 0); - pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name); + pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name); if (IS_ERR(pd->cdrw.thread)) { - pkt_err(pd, "can't start kernel thread\n"); + dev_err(ddev, "can't start kernel thread\n"); goto out_mem; } - proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); - pkt_dbg(1, pd, "writer mapped to %pg\n", bdev); + proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd); + dev_notice(ddev, "writer mapped to %pg\n", bdev); return 0; out_mem: - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(bdev, NULL); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return -ENOMEM; } -static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) +static int pkt_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long arg) { struct pktcdvd_device *pd = bdev->bd_disk->private_data; + struct device *ddev = disk_to_dev(pd->disk); int ret; - pkt_dbg(2, pd, "cmd %x, dev %d:%d\n", - cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + dev_dbg(ddev, "cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); mutex_lock(&pktcdvd_mutex); switch (cmd) { @@ -2598,7 +2583,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); break; default: - pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); + dev_dbg(ddev, "Unknown ioctl (%x)\n", cmd); ret = -ENOTTY; } mutex_unlock(&pktcdvd_mutex); @@ -2631,7 +2616,7 @@ static const struct block_device_operations pktcdvd_ops = { .owner = THIS_MODULE, .submit_bio = pkt_submit_bio, .open = pkt_open, - .release = pkt_close, + .release = pkt_release, .ioctl = pkt_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, .check_events = pkt_check_events, @@ -2676,7 +2661,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) spin_lock_init(&pd->iosched.lock); bio_list_init(&pd->iosched.read_queue); bio_list_init(&pd->iosched.write_queue); - sprintf(pd->name, DRIVER_NAME"%d", idx); init_waitqueue_head(&pd->wqueue); pd->bio_queue = RB_ROOT; @@ -2693,7 +2677,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) disk->minors = 1; disk->fops = &pktcdvd_ops; disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; - strcpy(disk->disk_name, pd->name); + snprintf(disk->disk_name, sizeof(disk->disk_name), DRIVER_NAME"%d", idx); disk->private_data = pd; pd->pkt_dev = MKDEV(pktdev_major, idx); @@ -2735,6 +2719,7 @@ out_mutex: static int pkt_remove_dev(dev_t pkt_dev) { struct pktcdvd_device *pd; + struct device *ddev; int idx; int ret = 0; @@ -2755,6 +2740,9 @@ static int pkt_remove_dev(dev_t pkt_dev) ret = -EBUSY; goto out; } + + ddev = disk_to_dev(pd->disk); + if (!IS_ERR(pd->cdrw.thread)) kthread_stop(pd->cdrw.thread); @@ -2763,10 +2751,10 @@ static int pkt_remove_dev(dev_t pkt_dev) pkt_debugfs_dev_remove(pd); pkt_sysfs_dev_remove(pd); - blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(pd->bdev, NULL); - remove_proc_entry(pd->name, pkt_proc); - pkt_dbg(1, pd, "writer unmapped\n"); + remove_proc_entry(pd->disk->disk_name, pkt_proc); + dev_notice(ddev, "writer unmapped\n"); del_gendisk(pd->disk); put_disk(pd->disk); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 632751ddb287..bd0e075a5d89 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -660,9 +660,9 @@ static bool pending_result_dec(struct pending_result *pending, int *result) return true; } -static int rbd_open(struct block_device *bdev, fmode_t mode) +static int rbd_open(struct gendisk *disk, blk_mode_t mode) { - struct rbd_device *rbd_dev = bdev->bd_disk->private_data; + struct rbd_device *rbd_dev = disk->private_data; bool removing = false; spin_lock_irq(&rbd_dev->lock); @@ -679,7 +679,7 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) return 0; } -static void rbd_release(struct gendisk *disk, fmode_t mode) +static void rbd_release(struct gendisk *disk) { struct rbd_device *rbd_dev = disk->private_data; unsigned long open_count_before; diff --git a/drivers/block/rnbd/Makefile b/drivers/block/rnbd/Makefile index 40b31630822c..208e5f865497 100644 --- a/drivers/block/rnbd/Makefile +++ b/drivers/block/rnbd/Makefile @@ -3,13 +3,11 @@ ccflags-y := -I$(srctree)/drivers/infiniband/ulp/rtrs rnbd-client-y := rnbd-clt.o \ - rnbd-clt-sysfs.o \ - rnbd-common.o + rnbd-clt-sysfs.o CFLAGS_rnbd-srv-trace.o = -I$(src) -rnbd-server-y := rnbd-common.o \ - rnbd-srv.o \ +rnbd-server-y := rnbd-srv.o \ rnbd-srv-sysfs.o \ rnbd-srv-trace.o diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c index 8c6087949794..c36d8b1ceeed 100644 --- a/drivers/block/rnbd/rnbd-clt-sysfs.c +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -24,7 +24,9 @@ #include "rnbd-clt.h" static struct device *rnbd_dev; -static struct class *rnbd_dev_class; +static const struct class rnbd_dev_class = { + .name = "rnbd_client", +}; static struct kobject *rnbd_devs_kobj; enum { @@ -278,7 +280,7 @@ static ssize_t access_mode_show(struct kobject *kobj, dev = container_of(kobj, struct rnbd_clt_dev, kobj); - return sysfs_emit(page, "%s\n", rnbd_access_mode_str(dev->access_mode)); + return sysfs_emit(page, "%s\n", rnbd_access_modes[dev->access_mode].str); } static struct kobj_attribute rnbd_clt_access_mode = @@ -596,7 +598,7 @@ static ssize_t rnbd_clt_map_device_store(struct kobject *kobj, pr_info("Mapping device %s on session %s, (access_mode: %s, nr_poll_queues: %d)\n", pathname, sessname, - rnbd_access_mode_str(access_mode), + rnbd_access_modes[access_mode].str, nr_poll_queues); dev = rnbd_clt_map_device(sessname, paths, path_cnt, port_nr, pathname, @@ -646,11 +648,11 @@ int rnbd_clt_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create("rnbd-client"); - if (IS_ERR(rnbd_dev_class)) - return PTR_ERR(rnbd_dev_class); + err = class_register(&rnbd_dev_class); + if (err) + return err; - rnbd_dev = device_create_with_groups(rnbd_dev_class, NULL, + rnbd_dev = device_create_with_groups(&rnbd_dev_class, NULL, MKDEV(0, 0), NULL, default_attr_groups, "ctl"); if (IS_ERR(rnbd_dev)) { @@ -666,9 +668,9 @@ int rnbd_clt_create_sysfs_files(void) return 0; dev_destroy: - device_destroy(rnbd_dev_class, MKDEV(0, 0)); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); cls_destroy: - class_destroy(rnbd_dev_class); + class_unregister(&rnbd_dev_class); return err; } @@ -678,6 +680,6 @@ void rnbd_clt_destroy_sysfs_files(void) sysfs_remove_group(&rnbd_dev->kobj, &default_attr_group); kobject_del(rnbd_devs_kobj); kobject_put(rnbd_devs_kobj); - device_destroy(rnbd_dev_class, MKDEV(0, 0)); - class_destroy(rnbd_dev_class); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); + class_unregister(&rnbd_dev_class); } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 5eb8c7855970..b0550b68645d 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -921,11 +921,11 @@ rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first) return sess; } -static int rnbd_client_open(struct block_device *block_device, fmode_t mode) +static int rnbd_client_open(struct gendisk *disk, blk_mode_t mode) { - struct rnbd_clt_dev *dev = block_device->bd_disk->private_data; + struct rnbd_clt_dev *dev = disk->private_data; - if (get_disk_ro(dev->gd) && (mode & FMODE_WRITE)) + if (get_disk_ro(dev->gd) && (mode & BLK_OPEN_WRITE)) return -EPERM; if (dev->dev_state == DEV_STATE_UNMAPPED || @@ -935,7 +935,7 @@ static int rnbd_client_open(struct block_device *block_device, fmode_t mode) return 0; } -static void rnbd_client_release(struct gendisk *gen, fmode_t mode) +static void rnbd_client_release(struct gendisk *gen) { struct rnbd_clt_dev *dev = gen->private_data; diff --git a/drivers/block/rnbd/rnbd-common.c b/drivers/block/rnbd/rnbd-common.c deleted file mode 100644 index 596c3f732403..000000000000 --- a/drivers/block/rnbd/rnbd-common.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RDMA Network Block Driver - * - * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. - * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. - * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. - */ -#include "rnbd-proto.h" - -const char *rnbd_access_mode_str(enum rnbd_access_mode mode) -{ - switch (mode) { - case RNBD_ACCESS_RO: - return "ro"; - case RNBD_ACCESS_RW: - return "rw"; - case RNBD_ACCESS_MIGRATION: - return "migration"; - default: - return "unknown"; - } -} diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index da1d0542d7e2..e32f8f2c868a 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -61,6 +61,15 @@ enum rnbd_access_mode { RNBD_ACCESS_MIGRATION, }; +static const __maybe_unused struct { + enum rnbd_access_mode mode; + const char *str; +} rnbd_access_modes[] = { + [RNBD_ACCESS_RO] = {RNBD_ACCESS_RO, "ro"}, + [RNBD_ACCESS_RW] = {RNBD_ACCESS_RW, "rw"}, + [RNBD_ACCESS_MIGRATION] = {RNBD_ACCESS_MIGRATION, "migration"}, +}; + /** * struct rnbd_msg_sess_info - initial session info from client to server * @hdr: message header @@ -185,7 +194,6 @@ struct rnbd_msg_io { enum rnbd_io_flags { /* Operations */ - RNBD_OP_READ = 0, RNBD_OP_WRITE = 1, RNBD_OP_FLUSH = 2, @@ -193,15 +201,9 @@ enum rnbd_io_flags { RNBD_OP_SECURE_ERASE = 4, RNBD_OP_WRITE_SAME = 5, - RNBD_OP_LAST, - /* Flags */ - RNBD_F_SYNC = 1<<(RNBD_OP_BITS + 0), RNBD_F_FUA = 1<<(RNBD_OP_BITS + 1), - - RNBD_F_ALL = (RNBD_F_SYNC | RNBD_F_FUA) - }; static inline u32 rnbd_op(u32 flags) @@ -214,21 +216,6 @@ static inline u32 rnbd_flags(u32 flags) return flags & ~RNBD_OP_MASK; } -static inline bool rnbd_flags_supported(u32 flags) -{ - u32 op; - - op = rnbd_op(flags); - flags = rnbd_flags(flags); - - if (op >= RNBD_OP_LAST) - return false; - if (flags & ~RNBD_F_ALL) - return false; - - return true; -} - static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf) { blk_opf_t bio_opf; diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c index d5d9267e1fa5..cba6ba43c2c2 100644 --- a/drivers/block/rnbd/rnbd-srv-sysfs.c +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -9,7 +9,6 @@ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt -#include <uapi/linux/limits.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/stat.h> @@ -20,7 +19,9 @@ #include "rnbd-srv.h" static struct device *rnbd_dev; -static struct class *rnbd_dev_class; +static const struct class rnbd_dev_class = { + .name = "rnbd-server", +}; static struct kobject *rnbd_devs_kobj; static void rnbd_srv_dev_release(struct kobject *kobj) @@ -88,8 +89,7 @@ static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr, sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); - return sysfs_emit(page, "%d\n", - !(sess_dev->open_flags & FMODE_WRITE)); + return sysfs_emit(page, "%d\n", sess_dev->readonly); } static struct kobj_attribute rnbd_srv_dev_session_ro_attr = @@ -104,7 +104,7 @@ static ssize_t access_mode_show(struct kobject *kobj, sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); return sysfs_emit(page, "%s\n", - rnbd_access_mode_str(sess_dev->access_mode)); + rnbd_access_modes[sess_dev->access_mode].str); } static struct kobj_attribute rnbd_srv_dev_session_access_mode_attr = @@ -215,12 +215,12 @@ int rnbd_srv_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create("rnbd-server"); - if (IS_ERR(rnbd_dev_class)) - return PTR_ERR(rnbd_dev_class); + err = class_register(&rnbd_dev_class); + if (err) + return err; - rnbd_dev = device_create(rnbd_dev_class, NULL, - MKDEV(0, 0), NULL, "ctl"); + rnbd_dev = device_create(&rnbd_dev_class, NULL, + MKDEV(0, 0), NULL, "ctl"); if (IS_ERR(rnbd_dev)) { err = PTR_ERR(rnbd_dev); goto cls_destroy; @@ -234,9 +234,9 @@ int rnbd_srv_create_sysfs_files(void) return 0; dev_destroy: - device_destroy(rnbd_dev_class, MKDEV(0, 0)); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); cls_destroy: - class_destroy(rnbd_dev_class); + class_unregister(&rnbd_dev_class); return err; } @@ -245,6 +245,6 @@ void rnbd_srv_destroy_sysfs_files(void) { kobject_del(rnbd_devs_kobj); kobject_put(rnbd_devs_kobj); - device_destroy(rnbd_dev_class, MKDEV(0, 0)); - class_destroy(rnbd_dev_class); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); + class_unregister(&rnbd_dev_class); } diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 2cfed2e58d64..c186df0ec641 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -96,7 +96,7 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) ret = kref_get_unless_zero(&sess_dev->kref); rcu_read_unlock(); - if (!sess_dev || !ret) + if (!ret) return ERR_PTR(-ENXIO); return sess_dev; @@ -180,7 +180,7 @@ static void destroy_device(struct kref *kref) WARN_ONCE(!list_empty(&dev->sess_dev_list), "Device %s is being destroyed but still in use!\n", - dev->id); + dev->name); spin_lock(&dev_lock); list_del(&dev->list); @@ -219,10 +219,10 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) rnbd_put_sess_dev(sess_dev); wait_for_completion(&dc); /* wait for inflights to drop to zero */ - blkdev_put(sess_dev->bdev, sess_dev->open_flags); + blkdev_put(sess_dev->bdev, NULL); mutex_lock(&sess_dev->dev->lock); list_del(&sess_dev->dev_list); - if (sess_dev->open_flags & FMODE_WRITE) + if (!sess_dev->readonly) sess_dev->dev->open_write_cnt--; mutex_unlock(&sess_dev->dev->lock); @@ -356,7 +356,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen); -static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, +static void process_msg_sess_info(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen); @@ -384,8 +384,7 @@ static int rnbd_srv_rdma_ev(void *priv, struct rtrs_srv_op *id, ret = process_msg_open(srv_sess, usr, usrlen, data, datalen); break; case RNBD_MSG_SESS_INFO: - ret = process_msg_sess_info(srv_sess, usr, usrlen, data, - datalen); + process_msg_sess_info(srv_sess, usr, usrlen, data, datalen); break; default: pr_warn("Received unexpected message type %d from session %s\n", @@ -431,7 +430,7 @@ static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(struct block_device *bdev) if (!dev) return ERR_PTR(-ENOMEM); - snprintf(dev->id, sizeof(dev->id), "%pg", bdev); + snprintf(dev->name, sizeof(dev->name), "%pg", bdev); kref_init(&dev->kref); INIT_LIST_HEAD(&dev->sess_dev_list); mutex_init(&dev->lock); @@ -446,7 +445,7 @@ rnbd_srv_find_or_add_srv_dev(struct rnbd_srv_dev *new_dev) spin_lock(&dev_lock); list_for_each_entry(dev, &dev_list, list) { - if (!strncmp(dev->id, new_dev->id, sizeof(dev->id))) { + if (!strncmp(dev->name, new_dev->name, sizeof(dev->name))) { if (!kref_get_unless_zero(&dev->kref)) /* * We lost the race, device is almost dead. @@ -467,39 +466,38 @@ static int rnbd_srv_check_update_open_perm(struct rnbd_srv_dev *srv_dev, struct rnbd_srv_session *srv_sess, enum rnbd_access_mode access_mode) { - int ret = -EPERM; + int ret = 0; mutex_lock(&srv_dev->lock); switch (access_mode) { case RNBD_ACCESS_RO: - ret = 0; break; case RNBD_ACCESS_RW: if (srv_dev->open_write_cnt == 0) { srv_dev->open_write_cnt++; - ret = 0; } else { pr_err("Mapping device '%s' for session %s with RW permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", - srv_dev->id, srv_sess->sessname, + srv_dev->name, srv_sess->sessname, srv_dev->open_write_cnt, - rnbd_access_mode_str(access_mode)); + rnbd_access_modes[access_mode].str); + ret = -EPERM; } break; case RNBD_ACCESS_MIGRATION: if (srv_dev->open_write_cnt < 2) { srv_dev->open_write_cnt++; - ret = 0; } else { pr_err("Mapping device '%s' for session %s with migration permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", - srv_dev->id, srv_sess->sessname, + srv_dev->name, srv_sess->sessname, srv_dev->open_write_cnt, - rnbd_access_mode_str(access_mode)); + rnbd_access_modes[access_mode].str); + ret = -EPERM; } break; default: pr_err("Received mapping request for device '%s' on session %s with invalid access mode: %d\n", - srv_dev->id, srv_sess->sessname, access_mode); + srv_dev->name, srv_sess->sessname, access_mode); ret = -EINVAL; } @@ -561,7 +559,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, static struct rnbd_srv_sess_dev * rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, const struct rnbd_msg_open *open_msg, - struct block_device *bdev, fmode_t open_flags, + struct block_device *bdev, bool readonly, struct rnbd_srv_dev *srv_dev) { struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess); @@ -576,7 +574,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, sdev->bdev = bdev; sdev->sess = srv_sess; sdev->dev = srv_dev; - sdev->open_flags = open_flags; + sdev->readonly = readonly; sdev->access_mode = open_msg->access_mode; return sdev; @@ -631,7 +629,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, return full_path; } -static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, +static void process_msg_sess_info(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen) { @@ -644,8 +642,6 @@ static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, rsp->hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO_RSP); rsp->ver = srv_sess->ver; - - return 0; } /** @@ -681,15 +677,14 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, struct rnbd_srv_sess_dev *srv_sess_dev; const struct rnbd_msg_open *open_msg = msg; struct block_device *bdev; - fmode_t open_flags; + blk_mode_t open_flags = BLK_OPEN_READ; char *full_path; struct rnbd_msg_open_rsp *rsp = data; trace_process_msg_open(srv_sess, open_msg); - open_flags = FMODE_READ; if (open_msg->access_mode != RNBD_ACCESS_RO) - open_flags |= FMODE_WRITE; + open_flags |= BLK_OPEN_WRITE; mutex_lock(&srv_sess->lock); @@ -719,7 +714,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto reject; } - bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE); + bdev = blkdev_get_by_path(full_path, open_flags, NULL, NULL); if (IS_ERR(bdev)) { ret = PTR_ERR(bdev); pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n", @@ -736,9 +731,9 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto blkdev_put; } - srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, - bdev, open_flags, - srv_dev); + srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, bdev, + open_msg->access_mode == RNBD_ACCESS_RO, + srv_dev); if (IS_ERR(srv_sess_dev)) { pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n", full_path, srv_sess->sessname, PTR_ERR(srv_sess_dev)); @@ -774,7 +769,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, list_add(&srv_sess_dev->dev_list, &srv_dev->sess_dev_list); mutex_unlock(&srv_dev->lock); - rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->id); + rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->name); kfree(full_path); @@ -795,7 +790,7 @@ srv_dev_put: } rnbd_put_srv_dev(srv_dev); blkdev_put: - blkdev_put(bdev, open_flags); + blkdev_put(bdev, NULL); free_path: kfree(full_path); reject: @@ -808,7 +803,7 @@ static struct rtrs_srv_ctx *rtrs_ctx; static struct rtrs_srv_ops rtrs_ops; static int __init rnbd_srv_init_module(void) { - int err; + int err = 0; BUILD_BUG_ON(sizeof(struct rnbd_msg_hdr) != 4); BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info) != 36); @@ -822,19 +817,17 @@ static int __init rnbd_srv_init_module(void) }; rtrs_ctx = rtrs_srv_open(&rtrs_ops, port_nr); if (IS_ERR(rtrs_ctx)) { - err = PTR_ERR(rtrs_ctx); pr_err("rtrs_srv_open(), err: %d\n", err); - return err; + return PTR_ERR(rtrs_ctx); } err = rnbd_srv_create_sysfs_files(); if (err) { pr_err("rnbd_srv_create_sysfs_files(), err: %d\n", err); rtrs_srv_close(rtrs_ctx); - return err; } - return 0; + return err; } static void __exit rnbd_srv_cleanup_module(void) diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index f5962fd31d62..1027656dedb0 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -35,7 +35,7 @@ struct rnbd_srv_dev { struct kobject dev_kobj; struct kobject *dev_sessions_kobj; struct kref kref; - char id[NAME_MAX]; + char name[NAME_MAX]; /* List of rnbd_srv_sess_dev structs */ struct list_head sess_dev_list; struct mutex lock; @@ -52,7 +52,7 @@ struct rnbd_srv_sess_dev { struct kobject kobj; u32 device_id; bool keep_id; - fmode_t open_flags; + bool readonly; struct kref kref; struct completion *destroy_comp; char pathname[NAME_MAX]; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 9fa821fa76b0..7bf4b48e2282 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -139,7 +139,7 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD. * Needed to be able to install inside an ldom from an iso image. */ -static int vdc_ioctl(struct block_device *bdev, fmode_t mode, +static int vdc_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned command, unsigned long argument) { struct vdc_port *port = bdev->bd_disk->private_data; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 42b4b6828690..f85b6af414b4 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -608,20 +608,18 @@ static void setup_medium(struct floppy_state *fs) } } -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct floppy_state *fs = bdev->bd_disk->private_data; + struct floppy_state *fs = disk->private_data; struct swim __iomem *base = fs->swd->base; int err; - if (fs->ref_count == -1 || (fs->ref_count && mode & FMODE_EXCL)) + if (fs->ref_count == -1 || (fs->ref_count && mode & BLK_OPEN_EXCL)) return -EBUSY; - - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) fs->ref_count = -1; else fs->ref_count++; - swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2); udelay(10); swim_drive(base, fs->location); @@ -636,13 +634,13 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) set_capacity(fs->disk, fs->total_secs); - if (mode & FMODE_NDELAY) + if (mode & BLK_OPEN_NDELAY) return 0; - if (mode & (FMODE_READ|FMODE_WRITE)) { - if (bdev_check_media_change(bdev) && fs->disk_in) + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + if (disk_check_media_change(disk) && fs->disk_in) fs->ejected = 0; - if ((mode & FMODE_WRITE) && fs->write_protected) { + if ((mode & BLK_OPEN_WRITE) && fs->write_protected) { err = -EROFS; goto out; } @@ -659,18 +657,18 @@ out: return err; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&swim_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&swim_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct floppy_state *fs = disk->private_data; struct swim __iomem *base = fs->swd->base; @@ -686,7 +684,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) mutex_unlock(&swim_mutex); } -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct floppy_state *fs = bdev->bd_disk->private_data; diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index da811a7da03f..dc43a63b3469 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -246,10 +246,9 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state, int interruptible); static void release_drive(struct floppy_state *fs); static int fd_eject(struct floppy_state *fs); -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param); -static int floppy_open(struct block_device *bdev, fmode_t mode); -static void floppy_release(struct gendisk *disk, fmode_t mode); +static int floppy_open(struct gendisk *disk, blk_mode_t mode); static unsigned int floppy_check_events(struct gendisk *disk, unsigned int clearing); static int floppy_revalidate(struct gendisk *disk); @@ -883,7 +882,7 @@ static int fd_eject(struct floppy_state *fs) static struct floppy_struct floppy_type = { 2880,18,2,80,0,0x1B,0x00,0xCF,0x6C,NULL }; /* 7 1.44MB 3.5" */ -static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct floppy_state *fs = bdev->bd_disk->private_data; @@ -911,7 +910,7 @@ static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode, return -ENOTTY; } -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -923,9 +922,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, return ret; } -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct floppy_state *fs = bdev->bd_disk->private_data; + struct floppy_state *fs = disk->private_data; struct swim3 __iomem *sw = fs->swim3; int n, err = 0; @@ -958,18 +957,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) swim3_action(fs, SETMFM); swim3_select(fs, RELAX); - } else if (fs->ref_count == -1 || mode & FMODE_EXCL) + } else if (fs->ref_count == -1 || mode & BLK_OPEN_EXCL) return -EBUSY; - if (err == 0 && (mode & FMODE_NDELAY) == 0 - && (mode & (FMODE_READ|FMODE_WRITE))) { - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (err == 0 && !(mode & BLK_OPEN_NDELAY) && + (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE))) { + if (disk_check_media_change(disk)) + floppy_revalidate(disk); if (fs->ejected) err = -ENXIO; } - if (err == 0 && (mode & FMODE_WRITE)) { + if (err == 0 && (mode & BLK_OPEN_WRITE)) { if (fs->write_prot < 0) fs->write_prot = swim3_readbit(fs, WRITE_PROT); if (fs->write_prot) @@ -985,7 +984,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return err; } - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) fs->ref_count = -1; else ++fs->ref_count; @@ -993,18 +992,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&swim3_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&swim3_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct floppy_state *fs = disk->private_data; struct swim3 __iomem *sw = fs->swim3; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 33d3298a0da1..1c823750c95a 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -43,6 +43,7 @@ #include <asm/page.h> #include <linux/task_work.h> #include <linux/namei.h> +#include <linux/kref.h> #include <uapi/linux/ublk_cmd.h> #define UBLK_MINORS (1U << MINORBITS) @@ -54,7 +55,8 @@ | UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ | UBLK_F_UNPRIVILEGED_DEV \ - | UBLK_F_CMD_IOCTL_ENCODE) + | UBLK_F_CMD_IOCTL_ENCODE \ + | UBLK_F_USER_COPY) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ @@ -62,7 +64,8 @@ struct ublk_rq_data { struct llist_node node; - struct callback_head work; + + struct kref ref; }; struct ublk_uring_cmd_pdu { @@ -182,8 +185,13 @@ struct ublk_params_header { __u32 types; }; +static inline void __ublk_complete_rq(struct request *req); +static void ublk_complete_rq(struct kref *ref); + static dev_t ublk_chr_devt; -static struct class *ublk_chr_class; +static const struct class ublk_chr_class = { + .name = "ublk-char", +}; static DEFINE_IDR(ublk_index_idr); static DEFINE_SPINLOCK(ublk_idr_lock); @@ -202,6 +210,23 @@ static unsigned int ublks_added; /* protected by ublk_ctl_mutex */ static struct miscdevice ublk_misc; +static inline unsigned ublk_pos_to_hwq(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) & + UBLK_QID_BITS_MASK; +} + +static inline unsigned ublk_pos_to_buf_off(loff_t pos) +{ + return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK; +} + +static inline unsigned ublk_pos_to_tag(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) & + UBLK_TAG_BITS_MASK; +} + static void ublk_dev_param_basic_apply(struct ublk_device *ub) { struct request_queue *q = ub->ub_disk->queue; @@ -290,12 +315,52 @@ static int ublk_apply_params(struct ublk_device *ub) return 0; } -static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) +static inline bool ublk_support_user_copy(const struct ublk_queue *ubq) { - if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) && - !(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK)) - return true; - return false; + return ubq->flags & UBLK_F_USER_COPY; +} + +static inline bool ublk_need_req_ref(const struct ublk_queue *ubq) +{ + /* + * read()/write() is involved in user copy, so request reference + * has to be grabbed + */ + return ublk_support_user_copy(ubq); +} + +static inline void ublk_init_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + kref_init(&data->ref); + } +} + +static inline bool ublk_get_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + return kref_get_unless_zero(&data->ref); + } + + return true; +} + +static inline void ublk_put_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + kref_put(&data->ref, ublk_complete_rq); + } else { + __ublk_complete_rq(req); + } } static inline bool ublk_need_get_data(const struct ublk_queue *ubq) @@ -384,9 +449,9 @@ static void ublk_store_owner_uid_gid(unsigned int *owner_uid, *owner_gid = from_kgid(&init_user_ns, gid); } -static int ublk_open(struct block_device *bdev, fmode_t mode) +static int ublk_open(struct gendisk *disk, blk_mode_t mode) { - struct ublk_device *ub = bdev->bd_disk->private_data; + struct ublk_device *ub = disk->private_data; if (capable(CAP_SYS_ADMIN)) return 0; @@ -421,49 +486,39 @@ static const struct block_device_operations ub_fops = { #define UBLK_MAX_PIN_PAGES 32 -struct ublk_map_data { - const struct request *rq; - unsigned long ubuf; - unsigned int len; -}; - struct ublk_io_iter { struct page *pages[UBLK_MAX_PIN_PAGES]; - unsigned pg_off; /* offset in the 1st page in pages */ - int nr_pages; /* how many page pointers in pages */ struct bio *bio; struct bvec_iter iter; }; -static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data, - unsigned max_bytes, bool to_vm) +/* return how many pages are copied */ +static void ublk_copy_io_pages(struct ublk_io_iter *data, + size_t total, size_t pg_off, int dir) { - const unsigned total = min_t(unsigned, max_bytes, - PAGE_SIZE - data->pg_off + - ((data->nr_pages - 1) << PAGE_SHIFT)); unsigned done = 0; unsigned pg_idx = 0; while (done < total) { struct bio_vec bv = bio_iter_iovec(data->bio, data->iter); - const unsigned int bytes = min3(bv.bv_len, total - done, - (unsigned)(PAGE_SIZE - data->pg_off)); + unsigned int bytes = min3(bv.bv_len, (unsigned)total - done, + (unsigned)(PAGE_SIZE - pg_off)); void *bv_buf = bvec_kmap_local(&bv); void *pg_buf = kmap_local_page(data->pages[pg_idx]); - if (to_vm) - memcpy(pg_buf + data->pg_off, bv_buf, bytes); + if (dir == ITER_DEST) + memcpy(pg_buf + pg_off, bv_buf, bytes); else - memcpy(bv_buf, pg_buf + data->pg_off, bytes); + memcpy(bv_buf, pg_buf + pg_off, bytes); kunmap_local(pg_buf); kunmap_local(bv_buf); /* advance page array */ - data->pg_off += bytes; - if (data->pg_off == PAGE_SIZE) { + pg_off += bytes; + if (pg_off == PAGE_SIZE) { pg_idx += 1; - data->pg_off = 0; + pg_off = 0; } done += bytes; @@ -477,41 +532,58 @@ static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data, data->iter = data->bio->bi_iter; } } +} - return done; +static bool ublk_advance_io_iter(const struct request *req, + struct ublk_io_iter *iter, unsigned int offset) +{ + struct bio *bio = req->bio; + + for_each_bio(bio) { + if (bio->bi_iter.bi_size > offset) { + iter->bio = bio; + iter->iter = bio->bi_iter; + bio_advance_iter(iter->bio, &iter->iter, offset); + return true; + } + offset -= bio->bi_iter.bi_size; + } + return false; } -static int ublk_copy_user_pages(struct ublk_map_data *data, bool to_vm) +/* + * Copy data between request pages and io_iter, and 'offset' + * is the start point of linear offset of request. + */ +static size_t ublk_copy_user_pages(const struct request *req, + unsigned offset, struct iov_iter *uiter, int dir) { - const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0; - const unsigned long start_vm = data->ubuf; - unsigned int done = 0; - struct ublk_io_iter iter = { - .pg_off = start_vm & (PAGE_SIZE - 1), - .bio = data->rq->bio, - .iter = data->rq->bio->bi_iter, - }; - const unsigned int nr_pages = round_up(data->len + - (start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT; - - while (done < nr_pages) { - const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES, - nr_pages - done); - unsigned i, len; - - iter.nr_pages = get_user_pages_fast(start_vm + - (done << PAGE_SHIFT), to_pin, gup_flags, - iter.pages); - if (iter.nr_pages <= 0) - return done == 0 ? iter.nr_pages : done; - len = ublk_copy_io_pages(&iter, data->len, to_vm); - for (i = 0; i < iter.nr_pages; i++) { - if (to_vm) + struct ublk_io_iter iter; + size_t done = 0; + + if (!ublk_advance_io_iter(req, &iter, offset)) + return 0; + + while (iov_iter_count(uiter) && iter.bio) { + unsigned nr_pages; + ssize_t len; + size_t off; + int i; + + len = iov_iter_get_pages2(uiter, iter.pages, + iov_iter_count(uiter), + UBLK_MAX_PIN_PAGES, &off); + if (len <= 0) + return done; + + ublk_copy_io_pages(&iter, len, off, dir); + nr_pages = DIV_ROUND_UP(len + off, PAGE_SIZE); + for (i = 0; i < nr_pages; i++) { + if (dir == ITER_DEST) set_page_dirty(iter.pages[i]); put_page(iter.pages[i]); } - data->len -= len; - done += iter.nr_pages; + done += len; } return done; @@ -532,21 +604,23 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + /* * no zero copy, we delay copy WRITE request data into ublksrv * context and the big benefit is that pinning pages in current * context is pretty fast, see ublk_pin_user_pages */ if (ublk_need_map_req(req)) { - struct ublk_map_data data = { - .rq = req, - .ubuf = io->addr, - .len = rq_bytes, - }; + struct iov_iter iter; + struct iovec iov; + const int dir = ITER_DEST; - ublk_copy_user_pages(&data, true); + import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes, + &iov, &iter); - return rq_bytes - data.len; + return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; } @@ -557,18 +631,19 @@ static int ublk_unmap_io(const struct ublk_queue *ubq, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + if (ublk_need_unmap_req(req)) { - struct ublk_map_data data = { - .rq = req, - .ubuf = io->addr, - .len = io->res, - }; + struct iov_iter iter; + struct iovec iov; + const int dir = ITER_SOURCE; WARN_ON_ONCE(io->res > rq_bytes); - ublk_copy_user_pages(&data, false); - - return io->res - data.len; + import_single_range(dir, u64_to_user_ptr(io->addr), io->res, + &iov, &iter); + return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; } @@ -648,13 +723,19 @@ static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq) } /* todo: handle partial completion */ -static void ublk_complete_rq(struct request *req) +static inline void __ublk_complete_rq(struct request *req) { struct ublk_queue *ubq = req->mq_hctx->driver_data; struct ublk_io *io = &ubq->ios[req->tag]; unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; + /* called from ublk_abort_queue() code path */ + if (io->flags & UBLK_IO_FLAG_ABORTED) { + res = BLK_STS_IOERR; + goto exit; + } + /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) io->res = -EIO; @@ -694,6 +775,15 @@ exit: blk_mq_end_request(req, res); } +static void ublk_complete_rq(struct kref *ref) +{ + struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data, + ref); + struct request *req = blk_mq_rq_from_pdu(data); + + __ublk_complete_rq(req); +} + /* * Since __ublk_rq_task_work always fails requests immediately during * exiting, __ublk_fail_req() is only called from abort context during @@ -712,7 +802,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, if (ublk_queue_can_use_recovery_reissue(ubq)) blk_mq_requeue_request(req, false); else - blk_mq_end_request(req, BLK_STS_IOERR); + ublk_put_req_ref(ubq, req); } } @@ -821,6 +911,7 @@ static inline void __ublk_rq_task_work(struct request *req, mapped_bytes >> 9; } + ublk_init_req_ref(ubq, req); ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags); } @@ -852,17 +943,6 @@ static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags) ublk_forward_io_cmds(ubq, issue_flags); } -static void ublk_rq_task_work_fn(struct callback_head *work) -{ - struct ublk_rq_data *data = container_of(work, - struct ublk_rq_data, work); - struct request *req = blk_mq_rq_from_pdu(data); - struct ublk_queue *ubq = req->mq_hctx->driver_data; - unsigned issue_flags = IO_URING_F_UNLOCKED; - - ublk_forward_io_cmds(ubq, issue_flags); -} - static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) { struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); @@ -886,10 +966,6 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) */ if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { ublk_abort_io_cmds(ubq); - } else if (ublk_can_use_task_work(ubq)) { - if (task_work_add(ubq->ubq_daemon, &data->work, - TWA_SIGNAL_NO_IPI)) - ublk_abort_io_cmds(ubq); } else { struct io_uring_cmd *cmd = io->cmd; struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); @@ -961,19 +1037,9 @@ static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, return 0; } -static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - - init_task_work(&data->work, ublk_rq_task_work_fn); - return 0; -} - static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, .init_hctx = ublk_init_hctx, - .init_request = ublk_init_rq, .timeout = ublk_timeout, }; @@ -1050,7 +1116,7 @@ static void ublk_commit_completion(struct ublk_device *ub, req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag); if (req && likely(!blk_should_fake_timeout(req->q))) - ublk_complete_rq(req); + ublk_put_req_ref(ubq, req); } /* @@ -1295,6 +1361,14 @@ static inline int ublk_check_cmd_op(u32 cmd_op) return 0; } +static inline void ublk_fill_io_cmd(struct ublk_io *io, + struct io_uring_cmd *cmd, unsigned long buf_addr) +{ + io->cmd = cmd; + io->flags |= UBLK_IO_FLAG_ACTIVE; + io->addr = buf_addr; +} + static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags, const struct ublksrv_io_cmd *ub_cmd) @@ -1340,6 +1414,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, ^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA)) goto out; + if (ublk_support_user_copy(ubq) && ub_cmd->addr) { + ret = -EINVAL; + goto out; + } + ret = ublk_check_cmd_op(cmd_op); if (ret) goto out; @@ -1358,36 +1437,41 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, */ if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) goto out; - /* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */ - if (!ub_cmd->addr && !ublk_need_get_data(ubq)) - goto out; - io->cmd = cmd; - io->flags |= UBLK_IO_FLAG_ACTIVE; - io->addr = ub_cmd->addr; + if (!ublk_support_user_copy(ubq)) { + /* + * FETCH_RQ has to provide IO buffer if NEED GET + * DATA is not enabled + */ + if (!ub_cmd->addr && !ublk_need_get_data(ubq)) + goto out; + } + + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); - /* - * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is - * not enabled or it is Read IO. - */ - if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) - goto out; + if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; - io->addr = ub_cmd->addr; - io->flags |= UBLK_IO_FLAG_ACTIVE; - io->cmd = cmd; + + if (!ublk_support_user_copy(ubq)) { + /* + * COMMIT_AND_FETCH_REQ has to provide IO buffer if + * NEED GET DATA is not enabled or it is Read IO. + */ + if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || + req_op(req) == REQ_OP_READ)) + goto out; + } + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_commit_completion(ub, ub_cmd); break; case UBLK_IO_NEED_GET_DATA: if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; - io->addr = ub_cmd->addr; - io->cmd = cmd; - io->flags |= UBLK_IO_FLAG_ACTIVE; + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag); break; default: @@ -1402,6 +1486,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, return -EIOCBQUEUED; } +static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, + struct ublk_queue *ubq, int tag, size_t offset) +{ + struct request *req; + + if (!ublk_need_req_ref(ubq)) + return NULL; + + req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag); + if (!req) + return NULL; + + if (!ublk_get_req_ref(ubq, req)) + return NULL; + + if (unlikely(!blk_mq_request_started(req) || req->tag != tag)) + goto fail_put; + + if (!ublk_rq_has_data(req)) + goto fail_put; + + if (offset > blk_rq_bytes(req)) + goto fail_put; + + return req; +fail_put: + ublk_put_req_ref(ubq, req); + return NULL; +} + static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { /* @@ -1419,11 +1533,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); } +static inline bool ublk_check_ubuf_dir(const struct request *req, + int ubuf_dir) +{ + /* copy ubuf to request pages */ + if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE) + return true; + + /* copy request pages to ubuf */ + if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST) + return true; + + return false; +} + +static struct request *ublk_check_and_get_req(struct kiocb *iocb, + struct iov_iter *iter, size_t *off, int dir) +{ + struct ublk_device *ub = iocb->ki_filp->private_data; + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + u16 tag, q_id; + + if (!ub) + return ERR_PTR(-EACCES); + + if (!user_backed_iter(iter)) + return ERR_PTR(-EACCES); + + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + return ERR_PTR(-EACCES); + + tag = ublk_pos_to_tag(iocb->ki_pos); + q_id = ublk_pos_to_hwq(iocb->ki_pos); + buf_off = ublk_pos_to_buf_off(iocb->ki_pos); + + if (q_id >= ub->dev_info.nr_hw_queues) + return ERR_PTR(-EINVAL); + + ubq = ublk_get_queue(ub, q_id); + if (!ubq) + return ERR_PTR(-EINVAL); + + if (tag >= ubq->q_depth) + return ERR_PTR(-EINVAL); + + req = __ublk_check_and_get_req(ub, ubq, tag, buf_off); + if (!req) + return ERR_PTR(-EINVAL); + + if (!req->mq_hctx || !req->mq_hctx->driver_data) + goto fail; + + if (!ublk_check_ubuf_dir(req, dir)) + goto fail; + + *off = buf_off; + return req; +fail: + ublk_put_req_ref(ubq, req); + return ERR_PTR(-EACCES); +} + +static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + +static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, .llseek = no_llseek, + .read_iter = ublk_ch_read_iter, + .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, .mmap = ublk_ch_mmap, }; @@ -1547,7 +1762,7 @@ static int ublk_add_chdev(struct ublk_device *ub) dev->parent = ublk_misc.this_device; dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor); - dev->class = ublk_chr_class; + dev->class = &ublk_chr_class; dev->release = ublk_cdev_rel; device_initialize(dev); @@ -1818,10 +2033,12 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) */ ub->dev_info.flags &= UBLK_F_ALL; - if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK)) - ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK; + ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE | + UBLK_F_URING_CMD_COMP_IN_TASK; - ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE; + /* GET_DATA isn't needed any more with USER_COPY */ + if (ub->dev_info.flags & UBLK_F_USER_COPY) + ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; @@ -2133,6 +2350,21 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, return ret; } +static int ublk_ctrl_get_features(struct io_uring_cmd *cmd) +{ + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); + void __user *argp = (void __user *)(unsigned long)header->addr; + u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY; + + if (header->len != UBLK_FEATURES_LEN || !header->addr) + return -EINVAL; + + if (copy_to_user(argp, &features, UBLK_FEATURES_LEN)) + return -EFAULT; + + return 0; +} + /* * All control commands are sent via /dev/ublk-control, so we have to check * the destination device's permission @@ -2213,6 +2445,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, case UBLK_CMD_GET_DEV_INFO2: case UBLK_CMD_GET_QUEUE_AFFINITY: case UBLK_CMD_GET_PARAMS: + case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)): mask = MAY_READ; break; case UBLK_CMD_START_DEV: @@ -2262,6 +2495,11 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (ret) goto out; + if (cmd_op == UBLK_U_CMD_GET_FEATURES) { + ret = ublk_ctrl_get_features(cmd); + goto out; + } + if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) { ret = -ENODEV; ub = ublk_get_device_from_id(header->dev_id); @@ -2337,6 +2575,9 @@ static int __init ublk_init(void) { int ret; + BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET + + UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET); + init_waitqueue_head(&ublk_idr_wq); ret = misc_register(&ublk_misc); @@ -2347,11 +2588,10 @@ static int __init ublk_init(void) if (ret) goto unregister_mis; - ublk_chr_class = class_create("ublk-char"); - if (IS_ERR(ublk_chr_class)) { - ret = PTR_ERR(ublk_chr_class); + ret = class_register(&ublk_chr_class); + if (ret) goto free_chrdev_region; - } + return 0; free_chrdev_region: @@ -2369,7 +2609,7 @@ static void __exit ublk_exit(void) idr_for_each_entry(&ublk_index_idr, ub, id) ublk_remove(ub); - class_destroy(ublk_chr_class); + class_unregister(&ublk_chr_class); misc_deregister(&ublk_misc); idr_destroy(&ublk_index_idr); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2b918e28acaa..b47358da92a2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -348,63 +348,33 @@ static inline void virtblk_request_done(struct request *req) blk_mq_end_request(req, status); } -static void virtblk_complete_batch(struct io_comp_batch *iob) -{ - struct request *req; - - rq_list_for_each(&iob->req_list, req) { - virtblk_unmap_data(req, blk_mq_rq_to_pdu(req)); - virtblk_cleanup_cmd(req); - } - blk_mq_end_request_batch(iob); -} - -static int virtblk_handle_req(struct virtio_blk_vq *vq, - struct io_comp_batch *iob) -{ - struct virtblk_req *vbr; - int req_done = 0; - unsigned int len; - - while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) { - struct request *req = blk_mq_rq_from_pdu(vbr); - - if (likely(!blk_should_fake_timeout(req->q)) && - !blk_mq_complete_request_remote(req) && - !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), - virtblk_complete_batch)) - virtblk_request_done(req); - req_done++; - } - - return req_done; -} - static void virtblk_done(struct virtqueue *vq) { struct virtio_blk *vblk = vq->vdev->priv; - struct virtio_blk_vq *vblk_vq = &vblk->vqs[vq->index]; - int req_done = 0; + bool req_done = false; + int qid = vq->index; + struct virtblk_req *vbr; unsigned long flags; - DEFINE_IO_COMP_BATCH(iob); + unsigned int len; - spin_lock_irqsave(&vblk_vq->lock, flags); + spin_lock_irqsave(&vblk->vqs[qid].lock, flags); do { virtqueue_disable_cb(vq); - req_done += virtblk_handle_req(vblk_vq, &iob); + while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) { + struct request *req = blk_mq_rq_from_pdu(vbr); + if (likely(!blk_should_fake_timeout(req->q))) + blk_mq_complete_request(req); + req_done = true; + } if (unlikely(virtqueue_is_broken(vq))) break; } while (!virtqueue_enable_cb(vq)); - if (req_done) { - if (!rq_list_empty(iob.req_list)) - iob.complete(&iob); - - /* In case queue is stopped waiting for more buffers. */ + /* In case queue is stopped waiting for more buffers. */ + if (req_done) blk_mq_start_stopped_hw_queues(vblk->disk->queue, true); - } - spin_unlock_irqrestore(&vblk_vq->lock, flags); + spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags); } static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx) @@ -1283,15 +1253,37 @@ static void virtblk_map_queues(struct blk_mq_tag_set *set) } } +static void virtblk_complete_batch(struct io_comp_batch *iob) +{ + struct request *req; + + rq_list_for_each(&iob->req_list, req) { + virtblk_unmap_data(req, blk_mq_rq_to_pdu(req)); + virtblk_cleanup_cmd(req); + } + blk_mq_end_request_batch(iob); +} + static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct virtio_blk *vblk = hctx->queue->queuedata; struct virtio_blk_vq *vq = get_virtio_blk_vq(hctx); + struct virtblk_req *vbr; unsigned long flags; + unsigned int len; int found = 0; spin_lock_irqsave(&vq->lock, flags); - found = virtblk_handle_req(vq, iob); + + while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) { + struct request *req = blk_mq_rq_from_pdu(vbr); + + found++; + if (!blk_mq_complete_request_remote(req) && + !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr), + virtblk_complete_batch)) + virtblk_request_done(req); + } if (found) blk_mq_start_stopped_hw_queues(vblk->disk->queue, true); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 4807af1d5805..bb66178c432b 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -473,7 +473,7 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev) static void xen_vbd_free(struct xen_vbd *vbd) { if (vbd->bdev) - blkdev_put(vbd->bdev, vbd->readonly ? FMODE_READ : FMODE_WRITE); + blkdev_put(vbd->bdev, NULL); vbd->bdev = NULL; } @@ -492,7 +492,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, vbd->pdevice = MKDEV(major, minor); bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ? - FMODE_READ : FMODE_WRITE, NULL); + BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(bdev)) { pr_warn("xen_vbd_create: device %08x could not be opened\n", diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index c1890c8a9f6e..434fab306777 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -509,7 +509,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) return 0; } -static int blkif_ioctl(struct block_device *bdev, fmode_t mode, +static int blkif_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned command, unsigned long argument) { struct blkfront_info *info = bdev->bd_disk->private_data; diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index c1e85f356e4d..11493167b0a8 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -140,16 +140,14 @@ static void get_chipram(void) return; } -static int z2_open(struct block_device *bdev, fmode_t mode) +static int z2_open(struct gendisk *disk, blk_mode_t mode) { - int device; + int device = disk->first_minor; int max_z2_map = (Z2RAM_SIZE / Z2RAM_CHUNKSIZE) * sizeof(z2ram_map[0]); int max_chip_map = (amiga_chip_size / Z2RAM_CHUNKSIZE) * sizeof(z2ram_map[0]); int rc = -ENOMEM; - device = MINOR(bdev->bd_dev); - mutex_lock(&z2ram_mutex); if (current_device != -1 && current_device != device) { rc = -EBUSY; @@ -290,7 +288,7 @@ err_out: return rc; } -static void z2_release(struct gendisk *disk, fmode_t mode) +static void z2_release(struct gendisk *disk) { mutex_lock(&z2ram_mutex); if (current_device == -1) { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f6d90f1ba5cf..1867f378b319 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -420,7 +420,7 @@ static void reset_bdev(struct zram *zram) return; bdev = zram->bdev; - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, zram); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; @@ -507,8 +507,8 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - bdev = blkdev_get_by_dev(inode->i_rdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); + bdev = blkdev_get_by_dev(inode->i_rdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + zram, NULL); if (IS_ERR(bdev)) { err = PTR_ERR(bdev); bdev = NULL; @@ -539,7 +539,7 @@ out: kvfree(bitmap); if (bdev) - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, zram); if (backing_dev) filp_close(backing_dev, NULL); @@ -700,7 +700,7 @@ static ssize_t writeback_store(struct device *dev, bio_init(&bio, zram->bdev, &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); - bio_add_page(&bio, page, PAGE_SIZE, 0); + __bio_add_page(&bio, page, PAGE_SIZE, 0); /* * XXX: A single page IO would be inefficient for write @@ -2097,19 +2097,16 @@ static ssize_t reset_store(struct device *dev, return len; } -static int zram_open(struct block_device *bdev, fmode_t mode) +static int zram_open(struct gendisk *disk, blk_mode_t mode) { - int ret = 0; - struct zram *zram; + struct zram *zram = disk->private_data; - WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex)); + WARN_ON(!mutex_is_locked(&disk->open_mutex)); - zram = bdev->bd_disk->private_data; /* zram was claimed to reset so open request fails */ if (zram->claim) - ret = -EBUSY; - - return ret; + return -EBUSY; + return 0; } static const struct block_device_operations zram_devops = { diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 416f723a2dbb..cc2839805983 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -264,6 +264,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/nospec.h> #include <linux/slab.h> #include <linux/cdrom.h> #include <linux/sysctl.h> @@ -978,15 +979,6 @@ static void cdrom_dvd_rw_close_write(struct cdrom_device_info *cdi) cdi->media_written = 0; } -static int cdrom_close_write(struct cdrom_device_info *cdi) -{ -#if 0 - return cdrom_flush_cache(cdi); -#else - return 0; -#endif -} - /* badly broken, I know. Is due for a fixup anytime. */ static void cdrom_count_tracks(struct cdrom_device_info *cdi, tracktype *tracks) { @@ -1155,8 +1147,7 @@ clean_up_and_return: * is in their own interest: device control becomes a lot easier * this way. */ -int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode) +int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode) { int ret; @@ -1165,7 +1156,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, /* if this was a O_NONBLOCK open and we should honor the flags, * do a quick open without drive/disc integrity checks. */ cdi->use_count++; - if ((mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) { + if ((mode & BLK_OPEN_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) { ret = cdi->ops->open(cdi, 1); } else { ret = open_for_data(cdi); @@ -1173,7 +1164,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, goto err; if (CDROM_CAN(CDC_GENERIC_PACKET)) cdrom_mmc3_profile(cdi); - if (mode & FMODE_WRITE) { + if (mode & BLK_OPEN_WRITE) { ret = -EROFS; if (cdrom_open_write(cdi)) goto err_release; @@ -1182,6 +1173,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, ret = 0; cdi->media_written = 0; } + cdi->opened_for_data = true; } if (ret) @@ -1259,10 +1251,9 @@ static int check_for_audio_disc(struct cdrom_device_info *cdi, return 0; } -void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) +void cdrom_release(struct cdrom_device_info *cdi) { const struct cdrom_device_ops *cdo = cdi->ops; - int opened_for_data; cd_dbg(CD_CLOSE, "entering cdrom_release\n"); @@ -1280,20 +1271,12 @@ void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) } } - opened_for_data = !(cdi->options & CDO_USE_FFLAGS) || - !(mode & FMODE_NDELAY); - - /* - * flush cache on last write release - */ - if (CDROM_CAN(CDC_RAM) && !cdi->use_count && cdi->for_data) - cdrom_close_write(cdi); - cdo->release(cdi); - if (cdi->use_count == 0) { /* last process that closes dev*/ - if (opened_for_data && - cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY)) + + if (cdi->use_count == 0 && cdi->opened_for_data) { + if (cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY)) cdo->tray_move(cdi, 1); + cdi->opened_for_data = false; } } EXPORT_SYMBOL(cdrom_release); @@ -2329,6 +2312,9 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, if (arg >= cdi->capacity) return -EINVAL; + /* Prevent arg from speculatively bypassing the length check */ + barrier_nospec(); + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; @@ -3337,7 +3323,7 @@ static int mmc_ioctl(struct cdrom_device_info *cdi, unsigned int cmd, * ATAPI / SCSI specific code now mainly resides in mmc_ioctl(). */ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode, unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; int ret; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index ceded5772aac..3a46e27479ff 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -474,19 +474,19 @@ static const struct cdrom_device_ops gdrom_ops = { CDC_RESET | CDC_DRIVE_STATUS | CDC_CD_R, }; -static int gdrom_bdops_open(struct block_device *bdev, fmode_t mode) +static int gdrom_bdops_open(struct gendisk *disk, blk_mode_t mode) { int ret; - bdev_check_media_change(bdev); + disk_check_media_change(disk); mutex_lock(&gdrom_mutex); - ret = cdrom_open(gd.cd_info, bdev, mode); + ret = cdrom_open(gd.cd_info); mutex_unlock(&gdrom_mutex); return ret; } -static void gdrom_bdops_release(struct gendisk *disk, fmode_t mode) +static void gdrom_bdops_release(struct gendisk *disk) { mutex_lock(&gdrom_mutex); cdrom_release(gd.cd_info, mode); @@ -499,13 +499,13 @@ static unsigned int gdrom_bdops_check_events(struct gendisk *disk, return cdrom_check_events(gd.cd_info, clearing); } -static int gdrom_bdops_ioctl(struct block_device *bdev, fmode_t mode, +static int gdrom_bdops_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg) { int ret; mutex_lock(&gdrom_mutex); - ret = cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg); + ret = cdrom_ioctl(gd.cd_info, bdev, cmd, arg); mutex_unlock(&gdrom_mutex); return ret; diff --git a/drivers/char/random.c b/drivers/char/random.c index 253f2ddb8913..3cb37760dfec 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1546,7 +1546,7 @@ const struct file_operations random_fops = { .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; @@ -1557,7 +1557,7 @@ const struct file_operations urandom_fops = { .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index edfa94641bbf..66759fe28fad 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -119,7 +119,10 @@ static int clk_composite_determine_rate(struct clk_hw *hw, if (ret) continue; - rate_diff = abs(req->rate - tmp_req.rate); + if (req->rate >= tmp_req.rate) + rate_diff = req->rate - tmp_req.rate; + else + rate_diff = tmp_req.rate - req->rate; if (!rate_diff || !req->best_parent_hw || best_rate_diff > rate_diff) { diff --git a/drivers/clk/clk-loongson2.c b/drivers/clk/clk-loongson2.c index 70ae1dd2e474..bacdcbb287ac 100644 --- a/drivers/clk/clk-loongson2.c +++ b/drivers/clk/clk-loongson2.c @@ -40,7 +40,7 @@ static struct clk_hw *loongson2_clk_register(struct device *dev, { int ret; struct clk_hw *hw; - struct clk_init_data init; + struct clk_init_data init = { }; hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); if (!hw) diff --git a/drivers/clk/imx/clk-imx1.c b/drivers/clk/imx/clk-imx1.c index 22fc7491ba00..f6ea7e5052d5 100644 --- a/drivers/clk/imx/clk-imx1.c +++ b/drivers/clk/imx/clk-imx1.c @@ -10,7 +10,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <dt-bindings/clock/imx1-clock.h> -#include <soc/imx/timer.h> #include <asm/irq.h> #include "clk.h" diff --git a/drivers/clk/imx/clk-imx27.c b/drivers/clk/imx/clk-imx27.c index 5d177125728d..99618ded0939 100644 --- a/drivers/clk/imx/clk-imx27.c +++ b/drivers/clk/imx/clk-imx27.c @@ -8,7 +8,6 @@ #include <linux/of_address.h> #include <dt-bindings/clock/imx27-clock.h> #include <soc/imx/revision.h> -#include <soc/imx/timer.h> #include <asm/irq.h> #include "clk.h" diff --git a/drivers/clk/imx/clk-imx31.c b/drivers/clk/imx/clk-imx31.c index c44e18c6f63f..4c8d9ff0b2ad 100644 --- a/drivers/clk/imx/clk-imx31.c +++ b/drivers/clk/imx/clk-imx31.c @@ -11,7 +11,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <soc/imx/revision.h> -#include <soc/imx/timer.h> #include <asm/irq.h> #include "clk.h" diff --git a/drivers/clk/imx/clk-imx35.c b/drivers/clk/imx/clk-imx35.c index 7dcbaea3fea3..3b6fdb4e0be7 100644 --- a/drivers/clk/imx/clk-imx35.c +++ b/drivers/clk/imx/clk-imx35.c @@ -10,7 +10,6 @@ #include <linux/of.h> #include <linux/err.h> #include <soc/imx/revision.h> -#include <soc/imx/timer.h> #include <asm/irq.h> #include "clk.h" diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index 6b4e193f648d..c87a6c4a7967 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -23,6 +23,7 @@ static DEFINE_SPINLOCK(mt8365_clk_lock); static const struct mtk_fixed_clk top_fixed_clks[] = { + FIXED_CLK(CLK_TOP_CLK_NULL, "clk_null", NULL, 0), FIXED_CLK(CLK_TOP_I2S0_BCK, "i2s0_bck", NULL, 26000000), FIXED_CLK(CLK_TOP_DSI0_LNTC_DSICK, "dsi0_lntc_dsick", "clk26m", 75000000), @@ -559,6 +560,14 @@ static const struct mtk_clk_divider top_adj_divs[] = { 0x324, 16, 8, CLK_DIVIDER_ROUND_CLOSEST), DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV3, "apll12_ck_div3", "apll_i2s3_sel", 0x324, 24, 8, CLK_DIVIDER_ROUND_CLOSEST), + DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV4, "apll12_ck_div4", "apll_tdmout_sel", + 0x328, 0, 8, CLK_DIVIDER_ROUND_CLOSEST), + DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV4B, "apll12_ck_div4b", "apll_tdmout_sel", + 0x328, 8, 8, CLK_DIVIDER_ROUND_CLOSEST), + DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV5, "apll12_ck_div5", "apll_tdmin_sel", + 0x328, 16, 8, CLK_DIVIDER_ROUND_CLOSEST), + DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV5B, "apll12_ck_div5b", "apll_tdmin_sel", + 0x328, 24, 8, CLK_DIVIDER_ROUND_CLOSEST), DIV_ADJ_F(CLK_TOP_APLL12_CK_DIV6, "apll12_ck_div6", "apll_spdif_sel", 0x32c, 0, 8, CLK_DIVIDER_ROUND_CLOSEST), }; @@ -583,15 +592,15 @@ static const struct mtk_gate_regs top2_cg_regs = { #define GATE_TOP0(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top0_cg_regs, \ - _shift, &mtk_clk_gate_ops_no_setclr_inv) + _shift, &mtk_clk_gate_ops_no_setclr) #define GATE_TOP1(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top1_cg_regs, \ - _shift, &mtk_clk_gate_ops_no_setclr) + _shift, &mtk_clk_gate_ops_no_setclr_inv) #define GATE_TOP2(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top2_cg_regs, \ - _shift, &mtk_clk_gate_ops_no_setclr) + _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate top_clk_gates[] = { GATE_TOP0(CLK_TOP_CONN_32K, "conn_32k", "clk32k", 10), @@ -696,6 +705,7 @@ static const struct mtk_gate ifr_clks[] = { GATE_IFR3(CLK_IFR_GCPU, "ifr_gcpu", "axi_sel", 8), GATE_IFR3(CLK_IFR_TRNG, "ifr_trng", "axi_sel", 9), GATE_IFR3(CLK_IFR_AUXADC, "ifr_auxadc", "clk26m", 10), + GATE_IFR3(CLK_IFR_CPUM, "ifr_cpum", "clk26m", 11), GATE_IFR3(CLK_IFR_AUXADC_MD, "ifr_auxadc_md", "clk26m", 14), GATE_IFR3(CLK_IFR_AP_DMA, "ifr_ap_dma", "axi_sel", 18), GATE_IFR3(CLK_IFR_DEBUGSYS, "ifr_debugsys", "axi_sel", 24), @@ -717,6 +727,8 @@ static const struct mtk_gate ifr_clks[] = { GATE_IFR5(CLK_IFR_PWRAP_TMR, "ifr_pwrap_tmr", "clk26m", 12), GATE_IFR5(CLK_IFR_PWRAP_SPI, "ifr_pwrap_spi", "clk26m", 13), GATE_IFR5(CLK_IFR_PWRAP_SYS, "ifr_pwrap_sys", "clk26m", 14), + GATE_MTK_FLAGS(CLK_IFR_MCU_PM_BK, "ifr_mcu_pm_bk", NULL, &ifr5_cg_regs, + 17, &mtk_clk_gate_ops_setclr, CLK_IGNORE_UNUSED), GATE_IFR5(CLK_IFR_IRRX_26M, "ifr_irrx_26m", "clk26m", 22), GATE_IFR5(CLK_IFR_IRRX_32K, "ifr_irrx_32k", "clk32k", 23), GATE_IFR5(CLK_IFR_I2C0_AXI, "ifr_i2c0_axi", "i2c_sel", 24), diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c index 42958a542662..621e298f101a 100644 --- a/drivers/clk/pxa/clk-pxa3xx.c +++ b/drivers/clk/pxa/clk-pxa3xx.c @@ -164,7 +164,7 @@ void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask) accr &= ~disable; accr |= enable; - writel(accr, ACCR); + writel(accr, clk_regs + ACCR); if (xclkcfg) __asm__("mcr p14, 0, %0, c6, c0, 0\n" : : "r"(xclkcfg)); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 526382dc7482..c4d671a5a13d 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -612,6 +612,15 @@ config TIMER_IMX_SYS_CTR Enable this option to use i.MX system counter timer as a clockevent. +config CLKSRC_LOONGSON1_PWM + bool "Clocksource using Loongson1 PWM" + depends on MACH_LOONGSON32 || COMPILE_TEST + select MIPS_EXTERNAL_TIMER + select TIMER_OF + help + Enable this option to use Loongson1 PWM timer as clocksource + instead of the performance counter. + config CLKSRC_ST_LPC bool "Low power clocksource found in the LPC" if COMPILE_TEST select TIMER_OF if OF diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index f12d3987a960..5d93c9e3fc55 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -89,3 +89,4 @@ obj-$(CONFIG_MICROCHIP_PIT64B) += timer-microchip-pit64b.o obj-$(CONFIG_MSC313E_TIMER) += timer-msc313e.o obj-$(CONFIG_GOLDFISH_TIMER) += timer-goldfish.o obj-$(CONFIG_GXP_TIMER) += timer-gxp.o +obj-$(CONFIG_CLKSRC_LOONGSON1_PWM) += timer-loongson1-pwm.o diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index bcd9042a0c9f..9fc008c16636 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -475,15 +475,9 @@ static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg) return read_hv_clock_msr(); } -static u64 notrace read_hv_sched_clock_msr(void) -{ - return (read_hv_clock_msr() - hv_sched_clock_offset) * - (NSEC_PER_SEC / HV_CLOCK_HZ); -} - static struct clocksource hyperv_cs_msr = { .name = "hyperv_clocksource_msr", - .rating = 500, + .rating = 495, .read = read_hv_clock_msr_cs, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, @@ -513,7 +507,7 @@ static __always_inline void hv_setup_sched_clock(void *sched_clock) static __always_inline void hv_setup_sched_clock(void *sched_clock) {} #endif /* CONFIG_GENERIC_SCHED_CLOCK */ -static bool __init hv_init_tsc_clocksource(void) +static void __init hv_init_tsc_clocksource(void) { union hv_reference_tsc_msr tsc_msr; @@ -524,17 +518,14 @@ static bool __init hv_init_tsc_clocksource(void) * Hyper-V Reference TSC rating, causing the generic TSC to be used. * TSC_INVARIANT is not offered on ARM64, so the Hyper-V Reference * TSC will be preferred over the virtualized ARM64 arch counter. - * While the Hyper-V MSR clocksource won't be used since the - * Reference TSC clocksource is present, change its rating as - * well for consistency. */ if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) { hyperv_cs_tsc.rating = 250; - hyperv_cs_msr.rating = 250; + hyperv_cs_msr.rating = 245; } if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) - return false; + return; hv_read_reference_counter = read_hv_clock_tsc; @@ -565,33 +556,34 @@ static bool __init hv_init_tsc_clocksource(void) clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); - hv_sched_clock_offset = hv_read_reference_counter(); - hv_setup_sched_clock(read_hv_sched_clock_tsc); - - return true; + /* + * If TSC is invariant, then let it stay as the sched clock since it + * will be faster than reading the TSC page. But if not invariant, use + * the TSC page so that live migrations across hosts with different + * frequencies is handled correctly. + */ + if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT)) { + hv_sched_clock_offset = hv_read_reference_counter(); + hv_setup_sched_clock(read_hv_sched_clock_tsc); + } } void __init hv_init_clocksource(void) { /* - * Try to set up the TSC page clocksource. If it succeeds, we're - * done. Otherwise, set up the MSR clocksource. At least one of - * these will always be available except on very old versions of - * Hyper-V on x86. In that case we won't have a Hyper-V + * Try to set up the TSC page clocksource, then the MSR clocksource. + * At least one of these will always be available except on very old + * versions of Hyper-V on x86. In that case we won't have a Hyper-V * clocksource, but Linux will still run with a clocksource based * on the emulated PIT or LAPIC timer. + * + * Never use the MSR clocksource as sched clock. It's too slow. + * Better to use the native sched clock as the fallback. */ - if (hv_init_tsc_clocksource()) - return; - - if (!(ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)) - return; - - hv_read_reference_counter = read_hv_clock_msr; - clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); + hv_init_tsc_clocksource(); - hv_sched_clock_offset = hv_read_reference_counter(); - hv_setup_sched_clock(read_hv_sched_clock_msr); + if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE) + clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); } void __init hv_remap_tsc_clocksource(void) diff --git a/drivers/clocksource/ingenic-timer.c b/drivers/clocksource/ingenic-timer.c index 089ce64b1c3f..154ee5f7954a 100644 --- a/drivers/clocksource/ingenic-timer.c +++ b/drivers/clocksource/ingenic-timer.c @@ -369,7 +369,7 @@ static int __init ingenic_tcu_probe(struct platform_device *pdev) return 0; } -static int __maybe_unused ingenic_tcu_suspend(struct device *dev) +static int ingenic_tcu_suspend(struct device *dev) { struct ingenic_tcu *tcu = dev_get_drvdata(dev); unsigned int cpu; @@ -382,7 +382,7 @@ static int __maybe_unused ingenic_tcu_suspend(struct device *dev) return 0; } -static int __maybe_unused ingenic_tcu_resume(struct device *dev) +static int ingenic_tcu_resume(struct device *dev) { struct ingenic_tcu *tcu = dev_get_drvdata(dev); unsigned int cpu; @@ -406,7 +406,7 @@ err_timer_clk_disable: return ret; } -static const struct dev_pm_ops __maybe_unused ingenic_tcu_pm_ops = { +static const struct dev_pm_ops ingenic_tcu_pm_ops = { /* _noirq: We want the TCU clocks to be gated last / ungated first */ .suspend_noirq = ingenic_tcu_suspend, .resume_noirq = ingenic_tcu_resume, @@ -415,9 +415,7 @@ static const struct dev_pm_ops __maybe_unused ingenic_tcu_pm_ops = { static struct platform_driver ingenic_tcu_driver = { .driver = { .name = "ingenic-tcu-timer", -#ifdef CONFIG_PM_SLEEP - .pm = &ingenic_tcu_pm_ops, -#endif + .pm = pm_sleep_ptr(&ingenic_tcu_pm_ops), .of_match_table = ingenic_tcu_of_match, }, }; diff --git a/drivers/clocksource/timer-cadence-ttc.c b/drivers/clocksource/timer-cadence-ttc.c index 4efd0cf3b602..0d52e28fea4d 100644 --- a/drivers/clocksource/timer-cadence-ttc.c +++ b/drivers/clocksource/timer-cadence-ttc.c @@ -486,10 +486,10 @@ static int __init ttc_timer_probe(struct platform_device *pdev) * and use it. Note that the event timer uses the interrupt and it's the * 2nd TTC hence the irq_of_parse_and_map(,1) */ - timer_baseaddr = of_iomap(timer, 0); - if (!timer_baseaddr) { + timer_baseaddr = devm_of_iomap(&pdev->dev, timer, 0, NULL); + if (IS_ERR(timer_baseaddr)) { pr_err("ERROR: invalid timer base address\n"); - return -ENXIO; + return PTR_ERR(timer_baseaddr); } irq = irq_of_parse_and_map(timer, 1); @@ -513,20 +513,27 @@ static int __init ttc_timer_probe(struct platform_device *pdev) clk_ce = of_clk_get(timer, clksel); if (IS_ERR(clk_ce)) { pr_err("ERROR: timer input clock not found\n"); - return PTR_ERR(clk_ce); + ret = PTR_ERR(clk_ce); + goto put_clk_cs; } ret = ttc_setup_clocksource(clk_cs, timer_baseaddr, timer_width); if (ret) - return ret; + goto put_clk_ce; ret = ttc_setup_clockevent(clk_ce, timer_baseaddr + 4, irq); if (ret) - return ret; + goto put_clk_ce; pr_info("%pOFn #0 at %p, irq=%d\n", timer, timer_baseaddr, irq); return 0; + +put_clk_ce: + clk_put(clk_ce); +put_clk_cs: + clk_put(clk_cs); + return ret; } static const struct of_device_id ttc_timer_of_match[] = { diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index ca3e4cbc80c6..28ab4f1a7c71 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -16,7 +16,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <soc/imx/timer.h> /* * There are 4 versions of the timer hardware on Freescale MXC hardware. @@ -25,6 +24,12 @@ * - MX25, MX31, MX35, MX37, MX51, MX6Q(rev1.0) * - MX6DL, MX6SX, MX6Q(rev1.1+) */ +enum imx_gpt_type { + GPT_TYPE_IMX1, /* i.MX1 */ + GPT_TYPE_IMX21, /* i.MX21/27 */ + GPT_TYPE_IMX31, /* i.MX31/35/25/37/51/6Q */ + GPT_TYPE_IMX6DL, /* i.MX6DL/SX/SL */ +}; /* defines common for all i.MX */ #define MXC_TCTL 0x00 @@ -93,13 +98,11 @@ static void imx1_gpt_irq_disable(struct imx_timer *imxtm) tmp = readl_relaxed(imxtm->base + MXC_TCTL); writel_relaxed(tmp & ~MX1_2_TCTL_IRQEN, imxtm->base + MXC_TCTL); } -#define imx21_gpt_irq_disable imx1_gpt_irq_disable static void imx31_gpt_irq_disable(struct imx_timer *imxtm) { writel_relaxed(0, imxtm->base + V2_IR); } -#define imx6dl_gpt_irq_disable imx31_gpt_irq_disable static void imx1_gpt_irq_enable(struct imx_timer *imxtm) { @@ -108,13 +111,11 @@ static void imx1_gpt_irq_enable(struct imx_timer *imxtm) tmp = readl_relaxed(imxtm->base + MXC_TCTL); writel_relaxed(tmp | MX1_2_TCTL_IRQEN, imxtm->base + MXC_TCTL); } -#define imx21_gpt_irq_enable imx1_gpt_irq_enable static void imx31_gpt_irq_enable(struct imx_timer *imxtm) { writel_relaxed(1<<0, imxtm->base + V2_IR); } -#define imx6dl_gpt_irq_enable imx31_gpt_irq_enable static void imx1_gpt_irq_acknowledge(struct imx_timer *imxtm) { @@ -131,7 +132,6 @@ static void imx31_gpt_irq_acknowledge(struct imx_timer *imxtm) { writel_relaxed(V2_TSTAT_OF1, imxtm->base + V2_TSTAT); } -#define imx6dl_gpt_irq_acknowledge imx31_gpt_irq_acknowledge static void __iomem *sched_clock_reg; @@ -296,7 +296,6 @@ static void imx1_gpt_setup_tctl(struct imx_timer *imxtm) tctl_val = MX1_2_TCTL_FRR | MX1_2_TCTL_CLK_PCLK1 | MXC_TCTL_TEN; writel_relaxed(tctl_val, imxtm->base + MXC_TCTL); } -#define imx21_gpt_setup_tctl imx1_gpt_setup_tctl static void imx31_gpt_setup_tctl(struct imx_timer *imxtm) { @@ -343,10 +342,10 @@ static const struct imx_gpt_data imx21_gpt_data = { .reg_tstat = MX1_2_TSTAT, .reg_tcn = MX1_2_TCN, .reg_tcmp = MX1_2_TCMP, - .gpt_irq_enable = imx21_gpt_irq_enable, - .gpt_irq_disable = imx21_gpt_irq_disable, + .gpt_irq_enable = imx1_gpt_irq_enable, + .gpt_irq_disable = imx1_gpt_irq_disable, .gpt_irq_acknowledge = imx21_gpt_irq_acknowledge, - .gpt_setup_tctl = imx21_gpt_setup_tctl, + .gpt_setup_tctl = imx1_gpt_setup_tctl, .set_next_event = mx1_2_set_next_event, }; @@ -365,9 +364,9 @@ static const struct imx_gpt_data imx6dl_gpt_data = { .reg_tstat = V2_TSTAT, .reg_tcn = V2_TCN, .reg_tcmp = V2_TCMP, - .gpt_irq_enable = imx6dl_gpt_irq_enable, - .gpt_irq_disable = imx6dl_gpt_irq_disable, - .gpt_irq_acknowledge = imx6dl_gpt_irq_acknowledge, + .gpt_irq_enable = imx31_gpt_irq_enable, + .gpt_irq_disable = imx31_gpt_irq_disable, + .gpt_irq_acknowledge = imx31_gpt_irq_acknowledge, .gpt_setup_tctl = imx6dl_gpt_setup_tctl, .set_next_event = v2_set_next_event, }; diff --git a/drivers/clocksource/timer-loongson1-pwm.c b/drivers/clocksource/timer-loongson1-pwm.c new file mode 100644 index 000000000000..6335fee03017 --- /dev/null +++ b/drivers/clocksource/timer-loongson1-pwm.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Clocksource driver for Loongson-1 SoC + * + * Copyright (c) 2023 Keguang Zhang <keguang.zhang@gmail.com> + */ + +#include <linux/clockchips.h> +#include <linux/interrupt.h> +#include <linux/sizes.h> +#include "timer-of.h" + +/* Loongson-1 PWM Timer Register Definitions */ +#define PWM_CNTR 0x0 +#define PWM_HRC 0x4 +#define PWM_LRC 0x8 +#define PWM_CTRL 0xc + +/* PWM Control Register Bits */ +#define INT_LRC_EN BIT(11) +#define INT_HRC_EN BIT(10) +#define CNTR_RST BIT(7) +#define INT_SR BIT(6) +#define INT_EN BIT(5) +#define PWM_SINGLE BIT(4) +#define PWM_OE BIT(3) +#define CNT_EN BIT(0) + +#define CNTR_WIDTH 24 + +DEFINE_RAW_SPINLOCK(ls1x_timer_lock); + +struct ls1x_clocksource { + void __iomem *reg_base; + unsigned long ticks_per_jiffy; + struct clocksource clksrc; +}; + +static inline struct ls1x_clocksource *to_ls1x_clksrc(struct clocksource *c) +{ + return container_of(c, struct ls1x_clocksource, clksrc); +} + +static inline void ls1x_pwmtimer_set_period(unsigned int period, + struct timer_of *to) +{ + writel(period, timer_of_base(to) + PWM_LRC); + writel(period, timer_of_base(to) + PWM_HRC); +} + +static inline void ls1x_pwmtimer_clear(struct timer_of *to) +{ + writel(0, timer_of_base(to) + PWM_CNTR); +} + +static inline void ls1x_pwmtimer_start(struct timer_of *to) +{ + writel((INT_EN | PWM_OE | CNT_EN), timer_of_base(to) + PWM_CTRL); +} + +static inline void ls1x_pwmtimer_stop(struct timer_of *to) +{ + writel(0, timer_of_base(to) + PWM_CTRL); +} + +static inline void ls1x_pwmtimer_irq_ack(struct timer_of *to) +{ + int val; + + val = readl(timer_of_base(to) + PWM_CTRL); + val |= INT_SR; + writel(val, timer_of_base(to) + PWM_CTRL); +} + +static irqreturn_t ls1x_clockevent_isr(int irq, void *dev_id) +{ + struct clock_event_device *clkevt = dev_id; + struct timer_of *to = to_timer_of(clkevt); + + ls1x_pwmtimer_irq_ack(to); + ls1x_pwmtimer_clear(to); + ls1x_pwmtimer_start(to); + + clkevt->event_handler(clkevt); + + return IRQ_HANDLED; +} + +static int ls1x_clockevent_set_state_periodic(struct clock_event_device *clkevt) +{ + struct timer_of *to = to_timer_of(clkevt); + + raw_spin_lock(&ls1x_timer_lock); + ls1x_pwmtimer_set_period(timer_of_period(to), to); + ls1x_pwmtimer_clear(to); + ls1x_pwmtimer_start(to); + raw_spin_unlock(&ls1x_timer_lock); + + return 0; +} + +static int ls1x_clockevent_tick_resume(struct clock_event_device *clkevt) +{ + raw_spin_lock(&ls1x_timer_lock); + ls1x_pwmtimer_start(to_timer_of(clkevt)); + raw_spin_unlock(&ls1x_timer_lock); + + return 0; +} + +static int ls1x_clockevent_set_state_shutdown(struct clock_event_device *clkevt) +{ + raw_spin_lock(&ls1x_timer_lock); + ls1x_pwmtimer_stop(to_timer_of(clkevt)); + raw_spin_unlock(&ls1x_timer_lock); + + return 0; +} + +static int ls1x_clockevent_set_next(unsigned long evt, + struct clock_event_device *clkevt) +{ + struct timer_of *to = to_timer_of(clkevt); + + raw_spin_lock(&ls1x_timer_lock); + ls1x_pwmtimer_set_period(evt, to); + ls1x_pwmtimer_clear(to); + ls1x_pwmtimer_start(to); + raw_spin_unlock(&ls1x_timer_lock); + + return 0; +} + +static struct timer_of ls1x_to = { + .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK, + .clkevt = { + .name = "ls1x-pwmtimer", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + .rating = 300, + .set_next_event = ls1x_clockevent_set_next, + .set_state_periodic = ls1x_clockevent_set_state_periodic, + .set_state_oneshot = ls1x_clockevent_set_state_shutdown, + .set_state_shutdown = ls1x_clockevent_set_state_shutdown, + .tick_resume = ls1x_clockevent_tick_resume, + }, + .of_irq = { + .handler = ls1x_clockevent_isr, + .flags = IRQF_TIMER, + }, +}; + +/* + * Since the PWM timer overflows every two ticks, its not very useful + * to just read by itself. So use jiffies to emulate a free + * running counter: + */ +static u64 ls1x_clocksource_read(struct clocksource *cs) +{ + struct ls1x_clocksource *ls1x_cs = to_ls1x_clksrc(cs); + unsigned long flags; + int count; + u32 jifs; + static int old_count; + static u32 old_jifs; + + raw_spin_lock_irqsave(&ls1x_timer_lock, flags); + /* + * Although our caller may have the read side of xtime_lock, + * this is now a seqlock, and we are cheating in this routine + * by having side effects on state that we cannot undo if + * there is a collision on the seqlock and our caller has to + * retry. (Namely, old_jifs and old_count.) So we must treat + * jiffies as volatile despite the lock. We read jiffies + * before latching the timer count to guarantee that although + * the jiffies value might be older than the count (that is, + * the counter may underflow between the last point where + * jiffies was incremented and the point where we latch the + * count), it cannot be newer. + */ + jifs = jiffies; + /* read the count */ + count = readl(ls1x_cs->reg_base + PWM_CNTR); + + /* + * It's possible for count to appear to go the wrong way for this + * reason: + * + * The timer counter underflows, but we haven't handled the resulting + * interrupt and incremented jiffies yet. + * + * Previous attempts to handle these cases intelligently were buggy, so + * we just do the simple thing now. + */ + if (count < old_count && jifs == old_jifs) + count = old_count; + + old_count = count; + old_jifs = jifs; + + raw_spin_unlock_irqrestore(&ls1x_timer_lock, flags); + + return (u64)(jifs * ls1x_cs->ticks_per_jiffy) + count; +} + +static struct ls1x_clocksource ls1x_clocksource = { + .clksrc = { + .name = "ls1x-pwmtimer", + .rating = 300, + .read = ls1x_clocksource_read, + .mask = CLOCKSOURCE_MASK(CNTR_WIDTH), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + }, +}; + +static int __init ls1x_pwm_clocksource_init(struct device_node *np) +{ + struct timer_of *to = &ls1x_to; + int ret; + + ret = timer_of_init(np, to); + if (ret) + return ret; + + clockevents_config_and_register(&to->clkevt, timer_of_rate(to), + 0x1, GENMASK(CNTR_WIDTH - 1, 0)); + + ls1x_clocksource.reg_base = timer_of_base(to); + ls1x_clocksource.ticks_per_jiffy = timer_of_period(to); + + return clocksource_register_hz(&ls1x_clocksource.clksrc, + timer_of_rate(to)); +} + +TIMER_OF_DECLARE(ls1x_pwm_clocksource, "loongson,ls1b-pwmtimer", + ls1x_pwm_clocksource_init); diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 01f2e86f3f7c..12cf6bb2e3ce 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -12,7 +12,6 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/udmabuf.h> -#include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/iosys-map.h> @@ -207,9 +206,7 @@ static long udmabuf_create(struct miscdevice *device, struct udmabuf *ubuf; struct dma_buf *buf; pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit; - struct page *page, *hpage = NULL; - pgoff_t subpgoff, maxsubpgs; - struct hstate *hpstate; + struct page *page; int seals, ret = -EINVAL; u32 i, flags; @@ -245,7 +242,7 @@ static long udmabuf_create(struct miscdevice *device, if (!memfd) goto err; mapping = memfd->f_mapping; - if (!shmem_mapping(mapping) && !is_file_hugepages(memfd)) + if (!shmem_mapping(mapping)) goto err; seals = memfd_fcntl(memfd, F_GET_SEALS, 0); if (seals == -EINVAL) @@ -256,48 +253,16 @@ static long udmabuf_create(struct miscdevice *device, goto err; pgoff = list[i].offset >> PAGE_SHIFT; pgcnt = list[i].size >> PAGE_SHIFT; - if (is_file_hugepages(memfd)) { - hpstate = hstate_file(memfd); - pgoff = list[i].offset >> huge_page_shift(hpstate); - subpgoff = (list[i].offset & - ~huge_page_mask(hpstate)) >> PAGE_SHIFT; - maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT; - } for (pgidx = 0; pgidx < pgcnt; pgidx++) { - if (is_file_hugepages(memfd)) { - if (!hpage) { - hpage = find_get_page_flags(mapping, pgoff, - FGP_ACCESSED); - if (!hpage) { - ret = -EINVAL; - goto err; - } - } - page = hpage + subpgoff; - get_page(page); - subpgoff++; - if (subpgoff == maxsubpgs) { - put_page(hpage); - hpage = NULL; - subpgoff = 0; - pgoff++; - } - } else { - page = shmem_read_mapping_page(mapping, - pgoff + pgidx); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto err; - } + page = shmem_read_mapping_page(mapping, pgoff + pgidx); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto err; } ubuf->pages[pgbuf++] = page; } fput(memfd); memfd = NULL; - if (hpage) { - put_page(hpage); - hpage = NULL; - } } exp_info.ops = &udmabuf_ops; diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 68f576700911..110e99b86a66 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -550,4 +550,15 @@ config EDAC_ZYNQMP Xilinx ZynqMP OCM (On Chip Memory) controller. It can also be built as a module. In that case it will be called zynqmp_edac. +config EDAC_NPCM + tristate "Nuvoton NPCM DDR Memory Controller" + depends on (ARCH_NPCM || COMPILE_TEST) + help + Support for error detection and correction on the Nuvoton NPCM DDR + memory controller. + + The memory controller supports single bit error correction, double bit + error detection (in-line ECC in which a section 1/8th of the memory + device used to store data is used for ECC storage). + endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 9b025c5b3061..61945d3113cc 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -84,4 +84,5 @@ obj-$(CONFIG_EDAC_QCOM) += qcom_edac.o obj-$(CONFIG_EDAC_ASPEED) += aspeed_edac.o obj-$(CONFIG_EDAC_BLUEFIELD) += bluefield_edac.o obj-$(CONFIG_EDAC_DMC520) += dmc520_edac.o +obj-$(CONFIG_EDAC_NPCM) += npcm_edac.o obj-$(CONFIG_EDAC_ZYNQMP) += zynqmp_edac.o diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 5c4292e65b96..597dae7692b1 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -975,6 +975,74 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr) return csrow; } +/* + * See AMD PPR DF::LclNodeTypeMap + * + * This register gives information for nodes of the same type within a system. + * + * Reading this register from a GPU node will tell how many GPU nodes are in the + * system and what the lowest AMD Node ID value is for the GPU nodes. Use this + * info to fixup the Linux logical "Node ID" value set in the AMD NB code and EDAC. + */ +static struct local_node_map { + u16 node_count; + u16 base_node_id; +} gpu_node_map; + +#define PCI_DEVICE_ID_AMD_MI200_DF_F1 0x14d1 +#define REG_LOCAL_NODE_TYPE_MAP 0x144 + +/* Local Node Type Map (LNTM) fields */ +#define LNTM_NODE_COUNT GENMASK(27, 16) +#define LNTM_BASE_NODE_ID GENMASK(11, 0) + +static int gpu_get_node_map(void) +{ + struct pci_dev *pdev; + int ret; + u32 tmp; + + /* + * Node ID 0 is reserved for CPUs. + * Therefore, a non-zero Node ID means we've already cached the values. + */ + if (gpu_node_map.base_node_id) + return 0; + + pdev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F1, NULL); + if (!pdev) { + ret = -ENODEV; + goto out; + } + + ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp); + if (ret) + goto out; + + gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp); + gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp); + +out: + pci_dev_put(pdev); + return ret; +} + +static int fixup_node_id(int node_id, struct mce *m) +{ + /* MCA_IPID[InstanceIdHi] give the AMD Node ID for the bank. */ + u8 nid = (m->ipid >> 44) & 0xF; + + if (smca_get_bank_type(m->extcpu, m->bank) != SMCA_UMC_V2) + return node_id; + + /* Nodes below the GPU base node are CPU nodes and don't need a fixup. */ + if (nid < gpu_node_map.base_node_id) + return node_id; + + /* Convert the hardware-provided AMD Node ID to a Linux logical one. */ + return nid - gpu_node_map.base_node_id + 1; +} + /* Protect the PCI config register pairs used for DF indirect access. */ static DEFINE_MUTEX(df_indirect_mutex); @@ -1426,12 +1494,47 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt) return cs_mode; } +static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode, + int csrow_nr, int dimm) +{ + u32 msb, weight, num_zero_bits; + u32 addr_mask_deinterleaved; + int size = 0; + + /* + * The number of zero bits in the mask is equal to the number of bits + * in a full mask minus the number of bits in the current mask. + * + * The MSB is the number of bits in the full mask because BIT[0] is + * always 0. + * + * In the special 3 Rank interleaving case, a single bit is flipped + * without swapping with the most significant bit. This can be handled + * by keeping the MSB where it is and ignoring the single zero bit. + */ + msb = fls(addr_mask_orig) - 1; + weight = hweight_long(addr_mask_orig); + num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE); + + /* Take the number of zero bits off from the top of the mask. */ + addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1); + + edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm); + edac_dbg(1, " Original AddrMask: 0x%x\n", addr_mask_orig); + edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved); + + /* Register [31:1] = Address [39:9]. Size is in kBs here. */ + size = (addr_mask_deinterleaved >> 2) + 1; + + /* Return size in MBs. */ + return size >> 10; +} + static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, unsigned int cs_mode, int csrow_nr) { - u32 addr_mask_orig, addr_mask_deinterleaved; - u32 msb, weight, num_zero_bits; int cs_mask_nr = csrow_nr; + u32 addr_mask_orig; int dimm, size = 0; /* No Chip Selects are enabled. */ @@ -1475,33 +1578,7 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, else addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr]; - /* - * The number of zero bits in the mask is equal to the number of bits - * in a full mask minus the number of bits in the current mask. - * - * The MSB is the number of bits in the full mask because BIT[0] is - * always 0. - * - * In the special 3 Rank interleaving case, a single bit is flipped - * without swapping with the most significant bit. This can be handled - * by keeping the MSB where it is and ignoring the single zero bit. - */ - msb = fls(addr_mask_orig) - 1; - weight = hweight_long(addr_mask_orig); - num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE); - - /* Take the number of zero bits off from the top of the mask. */ - addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1); - - edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm); - edac_dbg(1, " Original AddrMask: 0x%x\n", addr_mask_orig); - edac_dbg(1, " Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved); - - /* Register [31:1] = Address [39:9]. Size is in kBs here. */ - size = (addr_mask_deinterleaved >> 2) + 1; - - /* Return size in MBs. */ - return size >> 10; + return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm); } static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) @@ -2992,6 +3069,8 @@ static void decode_umc_error(int node_id, struct mce *m) struct err_info err; u64 sys_addr; + node_id = fixup_node_id(node_id, m); + mci = edac_mc_find(node_id); if (!mci) return; @@ -3675,6 +3754,227 @@ static int umc_hw_info_get(struct amd64_pvt *pvt) return 0; } +/* + * The CPUs have one channel per UMC, so UMC number is equivalent to a + * channel number. The GPUs have 8 channels per UMC, so the UMC number no + * longer works as a channel number. + * + * The channel number within a GPU UMC is given in MCA_IPID[15:12]. + * However, the IDs are split such that two UMC values go to one UMC, and + * the channel numbers are split in two groups of four. + * + * Refer to comment on gpu_get_umc_base(). + * + * For example, + * UMC0 CH[3:0] = 0x0005[3:0]000 + * UMC0 CH[7:4] = 0x0015[3:0]000 + * UMC1 CH[3:0] = 0x0025[3:0]000 + * UMC1 CH[7:4] = 0x0035[3:0]000 + */ +static void gpu_get_err_info(struct mce *m, struct err_info *err) +{ + u8 ch = (m->ipid & GENMASK(31, 0)) >> 20; + u8 phy = ((m->ipid >> 12) & 0xf); + + err->channel = ch % 2 ? phy + 4 : phy; + err->csrow = phy; +} + +static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, + unsigned int cs_mode, int csrow_nr) +{ + u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr]; + + return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1); +} + +static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl) +{ + int size, cs_mode, cs = 0; + + edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl); + + cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY; + + for_each_chip_select(cs, ctrl, pvt) { + size = gpu_addr_mask_to_cs_size(pvt, ctrl, cs_mode, cs); + amd64_info(EDAC_MC ": %d: %5dMB\n", cs, size); + } +} + +static void gpu_dump_misc_regs(struct amd64_pvt *pvt) +{ + struct amd64_umc *umc; + u32 i; + + for_each_umc(i) { + umc = &pvt->umc[i]; + + edac_dbg(1, "UMC%d UMC cfg: 0x%x\n", i, umc->umc_cfg); + edac_dbg(1, "UMC%d SDP ctrl: 0x%x\n", i, umc->sdp_ctrl); + edac_dbg(1, "UMC%d ECC ctrl: 0x%x\n", i, umc->ecc_ctrl); + edac_dbg(1, "UMC%d All HBMs support ECC: yes\n", i); + + gpu_debug_display_dimm_sizes(pvt, i); + } +} + +static u32 gpu_get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr) +{ + u32 nr_pages; + int cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY; + + nr_pages = gpu_addr_mask_to_cs_size(pvt, dct, cs_mode, csrow_nr); + nr_pages <<= 20 - PAGE_SHIFT; + + edac_dbg(0, "csrow: %d, channel: %d\n", csrow_nr, dct); + edac_dbg(0, "nr_pages/channel: %u\n", nr_pages); + + return nr_pages; +} + +static void gpu_init_csrows(struct mem_ctl_info *mci) +{ + struct amd64_pvt *pvt = mci->pvt_info; + struct dimm_info *dimm; + u8 umc, cs; + + for_each_umc(umc) { + for_each_chip_select(cs, umc, pvt) { + if (!csrow_enabled(cs, umc, pvt)) + continue; + + dimm = mci->csrows[umc]->channels[cs]->dimm; + + edac_dbg(1, "MC node: %d, csrow: %d\n", + pvt->mc_node_id, cs); + + dimm->nr_pages = gpu_get_csrow_nr_pages(pvt, umc, cs); + dimm->edac_mode = EDAC_SECDED; + dimm->mtype = MEM_HBM2; + dimm->dtype = DEV_X16; + dimm->grain = 64; + } + } +} + +static void gpu_setup_mci_misc_attrs(struct mem_ctl_info *mci) +{ + struct amd64_pvt *pvt = mci->pvt_info; + + mci->mtype_cap = MEM_FLAG_HBM2; + mci->edac_ctl_cap = EDAC_FLAG_SECDED; + + mci->edac_cap = EDAC_FLAG_EC; + mci->mod_name = EDAC_MOD_STR; + mci->ctl_name = pvt->ctl_name; + mci->dev_name = pci_name(pvt->F3); + mci->ctl_page_to_phys = NULL; + + gpu_init_csrows(mci); +} + +/* ECC is enabled by default on GPU nodes */ +static bool gpu_ecc_enabled(struct amd64_pvt *pvt) +{ + return true; +} + +static inline u32 gpu_get_umc_base(u8 umc, u8 channel) +{ + /* + * On CPUs, there is one channel per UMC, so UMC numbering equals + * channel numbering. On GPUs, there are eight channels per UMC, + * so the channel numbering is different from UMC numbering. + * + * On CPU nodes channels are selected in 6th nibble + * UMC chY[3:0]= [(chY*2 + 1) : (chY*2)]50000; + * + * On GPU nodes channels are selected in 3rd nibble + * HBM chX[3:0]= [Y ]5X[3:0]000; + * HBM chX[7:4]= [Y+1]5X[3:0]000 + */ + umc *= 2; + + if (channel >= 4) + umc++; + + return 0x50000 + (umc << 20) + ((channel % 4) << 12); +} + +static void gpu_read_mc_regs(struct amd64_pvt *pvt) +{ + u8 nid = pvt->mc_node_id; + struct amd64_umc *umc; + u32 i, umc_base; + + /* Read registers from each UMC */ + for_each_umc(i) { + umc_base = gpu_get_umc_base(i, 0); + umc = &pvt->umc[i]; + + amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg); + amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl); + amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl); + } +} + +static void gpu_read_base_mask(struct amd64_pvt *pvt) +{ + u32 base_reg, mask_reg; + u32 *base, *mask; + int umc, cs; + + for_each_umc(umc) { + for_each_chip_select(cs, umc, pvt) { + base_reg = gpu_get_umc_base(umc, cs) + UMCCH_BASE_ADDR; + base = &pvt->csels[umc].csbases[cs]; + + if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) { + edac_dbg(0, " DCSB%d[%d]=0x%08x reg: 0x%x\n", + umc, cs, *base, base_reg); + } + + mask_reg = gpu_get_umc_base(umc, cs) + UMCCH_ADDR_MASK; + mask = &pvt->csels[umc].csmasks[cs]; + + if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) { + edac_dbg(0, " DCSM%d[%d]=0x%08x reg: 0x%x\n", + umc, cs, *mask, mask_reg); + } + } + } +} + +static void gpu_prep_chip_selects(struct amd64_pvt *pvt) +{ + int umc; + + for_each_umc(umc) { + pvt->csels[umc].b_cnt = 8; + pvt->csels[umc].m_cnt = 8; + } +} + +static int gpu_hw_info_get(struct amd64_pvt *pvt) +{ + int ret; + + ret = gpu_get_node_map(); + if (ret) + return ret; + + pvt->umc = kcalloc(pvt->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL); + if (!pvt->umc) + return -ENOMEM; + + gpu_prep_chip_selects(pvt); + gpu_read_base_mask(pvt); + gpu_read_mc_regs(pvt); + + return 0; +} + static void hw_info_put(struct amd64_pvt *pvt) { pci_dev_put(pvt->F1); @@ -3690,6 +3990,14 @@ static struct low_ops umc_ops = { .get_err_info = umc_get_err_info, }; +static struct low_ops gpu_ops = { + .hw_info_get = gpu_hw_info_get, + .ecc_enabled = gpu_ecc_enabled, + .setup_mci_misc_attrs = gpu_setup_mci_misc_attrs, + .dump_misc_regs = gpu_dump_misc_regs, + .get_err_info = gpu_get_err_info, +}; + /* Use Family 16h versions for defaults and adjust as needed below. */ static struct low_ops dct_ops = { .map_sysaddr_to_csrow = f1x_map_sysaddr_to_csrow, @@ -3813,9 +4121,27 @@ static int per_family_init(struct amd64_pvt *pvt) case 0x20 ... 0x2f: pvt->ctl_name = "F19h_M20h"; break; + case 0x30 ... 0x3f: + if (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) { + pvt->ctl_name = "MI200"; + pvt->max_mcs = 4; + pvt->ops = &gpu_ops; + } else { + pvt->ctl_name = "F19h_M30h"; + pvt->max_mcs = 8; + } + break; case 0x50 ... 0x5f: pvt->ctl_name = "F19h_M50h"; break; + case 0x60 ... 0x6f: + pvt->ctl_name = "F19h_M60h"; + pvt->flags.zn_regs_v2 = 1; + break; + case 0x70 ... 0x7f: + pvt->ctl_name = "F19h_M70h"; + pvt->flags.zn_regs_v2 = 1; + break; case 0xa0 ... 0xaf: pvt->ctl_name = "F19h_MA0h"; pvt->max_mcs = 12; @@ -3846,11 +4172,17 @@ static int init_one_instance(struct amd64_pvt *pvt) struct edac_mc_layer layers[2]; int ret = -ENOMEM; + /* + * For Heterogeneous family EDAC CHIP_SELECT and CHANNEL layers should + * be swapped to fit into the layers. + */ layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; - layers[0].size = pvt->csels[0].b_cnt; + layers[0].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ? + pvt->max_mcs : pvt->csels[0].b_cnt; layers[0].is_virt_csrow = true; layers[1].type = EDAC_MC_LAYER_CHANNEL; - layers[1].size = pvt->max_mcs; + layers[1].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ? + pvt->csels[0].b_cnt : pvt->max_mcs; layers[1].is_virt_csrow = false; mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0); @@ -4074,8 +4406,6 @@ static int __init amd64_edac_init(void) amd64_err("%s on 32-bit is unsupported. USE AT YOUR OWN RISK!\n", EDAC_MOD_STR); #endif - printk(KERN_INFO "AMD64 EDAC driver v%s\n", EDAC_AMD64_VERSION); - return 0; err_pci: @@ -4121,7 +4451,7 @@ module_exit(amd64_edac_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("SoftwareBitMaker: Doug Thompson, Dave Peterson, Thayne Harbaugh; AMD"); -MODULE_DESCRIPTION("MC support for AMD64 memory controllers - " EDAC_AMD64_VERSION); +MODULE_DESCRIPTION("MC support for AMD64 memory controllers"); module_param(edac_op_state, int, 0444); MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index e84fe0d4120a..5a4e4a59682b 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/mmzone.h> #include <linux/edac.h> +#include <linux/bitfield.h> #include <asm/cpu_device_id.h> #include <asm/msr.h> #include "edac_module.h" @@ -85,7 +86,6 @@ * sections 3.5.4 and 3.5.5 for more information. */ -#define EDAC_AMD64_VERSION "3.5.0" #define EDAC_MOD_STR "amd64_edac" /* Extended Model from CPUID, for CPU Revision numbers */ diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index cc5c63feb26a..9215c06783df 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -1186,7 +1186,8 @@ static void decode_smca_error(struct mce *m) if (xec < smca_mce_descs[bank_type].num_descs) pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]); - if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc) + if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && + xec == 0 && decode_dram_ecc) decode_dram_ecc(topology_die_id(m->extcpu), m); } diff --git a/drivers/edac/npcm_edac.c b/drivers/edac/npcm_edac.c new file mode 100644 index 000000000000..12b95be3e989 --- /dev/null +++ b/drivers/edac/npcm_edac.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (c) 2022 Nuvoton Technology Corporation + +#include <linux/debugfs.h> +#include <linux/iopoll.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include "edac_module.h" + +#define EDAC_MOD_NAME "npcm-edac" +#define EDAC_MSG_SIZE 256 + +/* chip serials */ +#define NPCM7XX_CHIP BIT(0) +#define NPCM8XX_CHIP BIT(1) + +/* syndrome values */ +#define UE_SYNDROME 0x03 + +/* error injection */ +#define ERROR_TYPE_CORRECTABLE 0 +#define ERROR_TYPE_UNCORRECTABLE 1 +#define ERROR_LOCATION_DATA 0 +#define ERROR_LOCATION_CHECKCODE 1 +#define ERROR_BIT_DATA_MAX 63 +#define ERROR_BIT_CHECKCODE_MAX 7 + +static char data_synd[] = { + 0xf4, 0xf1, 0xec, 0xea, 0xe9, 0xe6, 0xe5, 0xe3, + 0xdc, 0xda, 0xd9, 0xd6, 0xd5, 0xd3, 0xce, 0xcb, + 0xb5, 0xb0, 0xad, 0xab, 0xa8, 0xa7, 0xa4, 0xa2, + 0x9d, 0x9b, 0x98, 0x97, 0x94, 0x92, 0x8f, 0x8a, + 0x75, 0x70, 0x6d, 0x6b, 0x68, 0x67, 0x64, 0x62, + 0x5e, 0x5b, 0x58, 0x57, 0x54, 0x52, 0x4f, 0x4a, + 0x34, 0x31, 0x2c, 0x2a, 0x29, 0x26, 0x25, 0x23, + 0x1c, 0x1a, 0x19, 0x16, 0x15, 0x13, 0x0e, 0x0b +}; + +static struct regmap *npcm_regmap; + +struct npcm_platform_data { + /* chip serials */ + int chip; + + /* memory controller registers */ + u32 ctl_ecc_en; + u32 ctl_int_status; + u32 ctl_int_ack; + u32 ctl_int_mask_master; + u32 ctl_int_mask_ecc; + u32 ctl_ce_addr_l; + u32 ctl_ce_addr_h; + u32 ctl_ce_data_l; + u32 ctl_ce_data_h; + u32 ctl_ce_synd; + u32 ctl_ue_addr_l; + u32 ctl_ue_addr_h; + u32 ctl_ue_data_l; + u32 ctl_ue_data_h; + u32 ctl_ue_synd; + u32 ctl_source_id; + u32 ctl_controller_busy; + u32 ctl_xor_check_bits; + + /* masks and shifts */ + u32 ecc_en_mask; + u32 int_status_ce_mask; + u32 int_status_ue_mask; + u32 int_ack_ce_mask; + u32 int_ack_ue_mask; + u32 int_mask_master_non_ecc_mask; + u32 int_mask_master_global_mask; + u32 int_mask_ecc_non_event_mask; + u32 ce_addr_h_mask; + u32 ce_synd_mask; + u32 ce_synd_shift; + u32 ue_addr_h_mask; + u32 ue_synd_mask; + u32 ue_synd_shift; + u32 source_id_ce_mask; + u32 source_id_ce_shift; + u32 source_id_ue_mask; + u32 source_id_ue_shift; + u32 controller_busy_mask; + u32 xor_check_bits_mask; + u32 xor_check_bits_shift; + u32 writeback_en_mask; + u32 fwc_mask; +}; + +struct priv_data { + void __iomem *reg; + char message[EDAC_MSG_SIZE]; + const struct npcm_platform_data *pdata; + + /* error injection */ + struct dentry *debugfs; + u8 error_type; + u8 location; + u8 bit; +}; + +static void handle_ce(struct mem_ctl_info *mci) +{ + struct priv_data *priv = mci->pvt_info; + const struct npcm_platform_data *pdata; + u32 val_h = 0, val_l, id, synd; + u64 addr = 0, data = 0; + + pdata = priv->pdata; + regmap_read(npcm_regmap, pdata->ctl_ce_addr_l, &val_l); + if (pdata->chip == NPCM8XX_CHIP) { + regmap_read(npcm_regmap, pdata->ctl_ce_addr_h, &val_h); + val_h &= pdata->ce_addr_h_mask; + } + addr = ((addr | val_h) << 32) | val_l; + + regmap_read(npcm_regmap, pdata->ctl_ce_data_l, &val_l); + if (pdata->chip == NPCM8XX_CHIP) + regmap_read(npcm_regmap, pdata->ctl_ce_data_h, &val_h); + data = ((data | val_h) << 32) | val_l; + + regmap_read(npcm_regmap, pdata->ctl_source_id, &id); + id = (id & pdata->source_id_ce_mask) >> pdata->source_id_ce_shift; + + regmap_read(npcm_regmap, pdata->ctl_ce_synd, &synd); + synd = (synd & pdata->ce_synd_mask) >> pdata->ce_synd_shift; + + snprintf(priv->message, EDAC_MSG_SIZE, + "addr = 0x%llx, data = 0x%llx, id = 0x%x", addr, data, id); + + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, addr >> PAGE_SHIFT, + addr & ~PAGE_MASK, synd, 0, 0, -1, priv->message, ""); +} + +static void handle_ue(struct mem_ctl_info *mci) +{ + struct priv_data *priv = mci->pvt_info; + const struct npcm_platform_data *pdata; + u32 val_h = 0, val_l, id, synd; + u64 addr = 0, data = 0; + + pdata = priv->pdata; + regmap_read(npcm_regmap, pdata->ctl_ue_addr_l, &val_l); + if (pdata->chip == NPCM8XX_CHIP) { + regmap_read(npcm_regmap, pdata->ctl_ue_addr_h, &val_h); + val_h &= pdata->ue_addr_h_mask; + } + addr = ((addr | val_h) << 32) | val_l; + + regmap_read(npcm_regmap, pdata->ctl_ue_data_l, &val_l); + if (pdata->chip == NPCM8XX_CHIP) + regmap_read(npcm_regmap, pdata->ctl_ue_data_h, &val_h); + data = ((data | val_h) << 32) | val_l; + + regmap_read(npcm_regmap, pdata->ctl_source_id, &id); + id = (id & pdata->source_id_ue_mask) >> pdata->source_id_ue_shift; + + regmap_read(npcm_regmap, pdata->ctl_ue_synd, &synd); + synd = (synd & pdata->ue_synd_mask) >> pdata->ue_synd_shift; + + snprintf(priv->message, EDAC_MSG_SIZE, + "addr = 0x%llx, data = 0x%llx, id = 0x%x", addr, data, id); + + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, addr >> PAGE_SHIFT, + addr & ~PAGE_MASK, synd, 0, 0, -1, priv->message, ""); +} + +static irqreturn_t edac_ecc_isr(int irq, void *dev_id) +{ + const struct npcm_platform_data *pdata; + struct mem_ctl_info *mci = dev_id; + u32 status; + + pdata = ((struct priv_data *)mci->pvt_info)->pdata; + regmap_read(npcm_regmap, pdata->ctl_int_status, &status); + if (status & pdata->int_status_ce_mask) { + handle_ce(mci); + + /* acknowledge the CE interrupt */ + regmap_write(npcm_regmap, pdata->ctl_int_ack, + pdata->int_ack_ce_mask); + return IRQ_HANDLED; + } else if (status & pdata->int_status_ue_mask) { + handle_ue(mci); + + /* acknowledge the UE interrupt */ + regmap_write(npcm_regmap, pdata->ctl_int_ack, + pdata->int_ack_ue_mask); + return IRQ_HANDLED; + } + + WARN_ON_ONCE(1); + return IRQ_NONE; +} + +static ssize_t force_ecc_error(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct device *dev = file->private_data; + struct mem_ctl_info *mci = to_mci(dev); + struct priv_data *priv = mci->pvt_info; + const struct npcm_platform_data *pdata; + u32 val, syndrome; + int ret; + + pdata = priv->pdata; + edac_printk(KERN_INFO, EDAC_MOD_NAME, + "force an ECC error, type = %d, location = %d, bit = %d\n", + priv->error_type, priv->location, priv->bit); + + /* ensure no pending writes */ + ret = regmap_read_poll_timeout(npcm_regmap, pdata->ctl_controller_busy, + val, !(val & pdata->controller_busy_mask), + 1000, 10000); + if (ret) { + edac_printk(KERN_INFO, EDAC_MOD_NAME, + "wait pending writes timeout\n"); + return count; + } + + regmap_read(npcm_regmap, pdata->ctl_xor_check_bits, &val); + val &= ~pdata->xor_check_bits_mask; + + /* write syndrome to XOR_CHECK_BITS */ + if (priv->error_type == ERROR_TYPE_CORRECTABLE) { + if (priv->location == ERROR_LOCATION_DATA && + priv->bit > ERROR_BIT_DATA_MAX) { + edac_printk(KERN_INFO, EDAC_MOD_NAME, + "data bit should not exceed %d (%d)\n", + ERROR_BIT_DATA_MAX, priv->bit); + return count; + } + + if (priv->location == ERROR_LOCATION_CHECKCODE && + priv->bit > ERROR_BIT_CHECKCODE_MAX) { + edac_printk(KERN_INFO, EDAC_MOD_NAME, + "checkcode bit should not exceed %d (%d)\n", + ERROR_BIT_CHECKCODE_MAX, priv->bit); + return count; + } + + syndrome = priv->location ? 1 << priv->bit + : data_synd[priv->bit]; + + regmap_write(npcm_regmap, pdata->ctl_xor_check_bits, + val | (syndrome << pdata->xor_check_bits_shift) | + pdata->writeback_en_mask); + } else if (priv->error_type == ERROR_TYPE_UNCORRECTABLE) { + regmap_write(npcm_regmap, pdata->ctl_xor_check_bits, + val | (UE_SYNDROME << pdata->xor_check_bits_shift)); + } + + /* force write check */ + regmap_update_bits(npcm_regmap, pdata->ctl_xor_check_bits, + pdata->fwc_mask, pdata->fwc_mask); + + return count; +} + +static const struct file_operations force_ecc_error_fops = { + .open = simple_open, + .write = force_ecc_error, + .llseek = generic_file_llseek, +}; + +/* + * Setup debugfs for error injection. + * + * Nodes: + * error_type - 0: CE, 1: UE + * location - 0: data, 1: checkcode + * bit - 0 ~ 63 for data and 0 ~ 7 for checkcode + * force_ecc_error - trigger + * + * Examples: + * 1. Inject a correctable error (CE) at checkcode bit 7. + * ~# echo 0 > /sys/kernel/debug/edac/npcm-edac/error_type + * ~# echo 1 > /sys/kernel/debug/edac/npcm-edac/location + * ~# echo 7 > /sys/kernel/debug/edac/npcm-edac/bit + * ~# echo 1 > /sys/kernel/debug/edac/npcm-edac/force_ecc_error + * + * 2. Inject an uncorrectable error (UE). + * ~# echo 1 > /sys/kernel/debug/edac/npcm-edac/error_type + * ~# echo 1 > /sys/kernel/debug/edac/npcm-edac/force_ecc_error + */ +static void setup_debugfs(struct mem_ctl_info *mci) +{ + struct priv_data *priv = mci->pvt_info; + + priv->debugfs = edac_debugfs_create_dir(mci->mod_name); + if (!priv->debugfs) + return; + + edac_debugfs_create_x8("error_type", 0644, priv->debugfs, &priv->error_type); + edac_debugfs_create_x8("location", 0644, priv->debugfs, &priv->location); + edac_debugfs_create_x8("bit", 0644, priv->debugfs, &priv->bit); + edac_debugfs_create_file("force_ecc_error", 0200, priv->debugfs, + &mci->dev, &force_ecc_error_fops); +} + +static int setup_irq(struct mem_ctl_info *mci, struct platform_device *pdev) +{ + const struct npcm_platform_data *pdata; + int ret, irq; + + pdata = ((struct priv_data *)mci->pvt_info)->pdata; + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + edac_printk(KERN_ERR, EDAC_MOD_NAME, "IRQ not defined in DTS\n"); + return irq; + } + + ret = devm_request_irq(&pdev->dev, irq, edac_ecc_isr, 0, + dev_name(&pdev->dev), mci); + if (ret < 0) { + edac_printk(KERN_ERR, EDAC_MOD_NAME, "failed to request IRQ\n"); + return ret; + } + + /* enable the functional group of ECC and mask the others */ + regmap_write(npcm_regmap, pdata->ctl_int_mask_master, + pdata->int_mask_master_non_ecc_mask); + + if (pdata->chip == NPCM8XX_CHIP) + regmap_write(npcm_regmap, pdata->ctl_int_mask_ecc, + pdata->int_mask_ecc_non_event_mask); + + return 0; +} + +static const struct regmap_config npcm_regmap_cfg = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, +}; + +static int edac_probe(struct platform_device *pdev) +{ + const struct npcm_platform_data *pdata; + struct device *dev = &pdev->dev; + struct edac_mc_layer layers[1]; + struct mem_ctl_info *mci; + struct priv_data *priv; + void __iomem *reg; + u32 val; + int rc; + + reg = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(reg)) + return PTR_ERR(reg); + + npcm_regmap = devm_regmap_init_mmio(dev, reg, &npcm_regmap_cfg); + if (IS_ERR(npcm_regmap)) + return PTR_ERR(npcm_regmap); + + pdata = of_device_get_match_data(dev); + if (!pdata) + return -EINVAL; + + /* bail out if ECC is not enabled */ + regmap_read(npcm_regmap, pdata->ctl_ecc_en, &val); + if (!(val & pdata->ecc_en_mask)) { + edac_printk(KERN_ERR, EDAC_MOD_NAME, "ECC is not enabled\n"); + return -EPERM; + } + + edac_op_state = EDAC_OPSTATE_INT; + + layers[0].type = EDAC_MC_LAYER_ALL_MEM; + layers[0].size = 1; + + mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, + sizeof(struct priv_data)); + if (!mci) + return -ENOMEM; + + mci->pdev = &pdev->dev; + priv = mci->pvt_info; + priv->reg = reg; + priv->pdata = pdata; + platform_set_drvdata(pdev, mci); + + mci->mtype_cap = MEM_FLAG_DDR4; + mci->edac_ctl_cap = EDAC_FLAG_SECDED; + mci->scrub_cap = SCRUB_FLAG_HW_SRC; + mci->scrub_mode = SCRUB_HW_SRC; + mci->edac_cap = EDAC_FLAG_SECDED; + mci->ctl_name = "npcm_ddr_controller"; + mci->dev_name = dev_name(&pdev->dev); + mci->mod_name = EDAC_MOD_NAME; + mci->ctl_page_to_phys = NULL; + + rc = setup_irq(mci, pdev); + if (rc) + goto free_edac_mc; + + rc = edac_mc_add_mc(mci); + if (rc) + goto free_edac_mc; + + if (IS_ENABLED(CONFIG_EDAC_DEBUG) && pdata->chip == NPCM8XX_CHIP) + setup_debugfs(mci); + + return rc; + +free_edac_mc: + edac_mc_free(mci); + return rc; +} + +static int edac_remove(struct platform_device *pdev) +{ + struct mem_ctl_info *mci = platform_get_drvdata(pdev); + struct priv_data *priv = mci->pvt_info; + const struct npcm_platform_data *pdata; + + pdata = priv->pdata; + if (IS_ENABLED(CONFIG_EDAC_DEBUG) && pdata->chip == NPCM8XX_CHIP) + edac_debugfs_remove_recursive(priv->debugfs); + + edac_mc_del_mc(&pdev->dev); + edac_mc_free(mci); + + regmap_write(npcm_regmap, pdata->ctl_int_mask_master, + pdata->int_mask_master_global_mask); + regmap_update_bits(npcm_regmap, pdata->ctl_ecc_en, pdata->ecc_en_mask, 0); + + return 0; +} + +static const struct npcm_platform_data npcm750_edac = { + .chip = NPCM7XX_CHIP, + + /* memory controller registers */ + .ctl_ecc_en = 0x174, + .ctl_int_status = 0x1d0, + .ctl_int_ack = 0x1d4, + .ctl_int_mask_master = 0x1d8, + .ctl_ce_addr_l = 0x188, + .ctl_ce_data_l = 0x190, + .ctl_ce_synd = 0x18c, + .ctl_ue_addr_l = 0x17c, + .ctl_ue_data_l = 0x184, + .ctl_ue_synd = 0x180, + .ctl_source_id = 0x194, + + /* masks and shifts */ + .ecc_en_mask = BIT(24), + .int_status_ce_mask = GENMASK(4, 3), + .int_status_ue_mask = GENMASK(6, 5), + .int_ack_ce_mask = GENMASK(4, 3), + .int_ack_ue_mask = GENMASK(6, 5), + .int_mask_master_non_ecc_mask = GENMASK(30, 7) | GENMASK(2, 0), + .int_mask_master_global_mask = BIT(31), + .ce_synd_mask = GENMASK(6, 0), + .ce_synd_shift = 0, + .ue_synd_mask = GENMASK(6, 0), + .ue_synd_shift = 0, + .source_id_ce_mask = GENMASK(29, 16), + .source_id_ce_shift = 16, + .source_id_ue_mask = GENMASK(13, 0), + .source_id_ue_shift = 0, +}; + +static const struct npcm_platform_data npcm845_edac = { + .chip = NPCM8XX_CHIP, + + /* memory controller registers */ + .ctl_ecc_en = 0x16c, + .ctl_int_status = 0x228, + .ctl_int_ack = 0x244, + .ctl_int_mask_master = 0x220, + .ctl_int_mask_ecc = 0x260, + .ctl_ce_addr_l = 0x18c, + .ctl_ce_addr_h = 0x190, + .ctl_ce_data_l = 0x194, + .ctl_ce_data_h = 0x198, + .ctl_ce_synd = 0x190, + .ctl_ue_addr_l = 0x17c, + .ctl_ue_addr_h = 0x180, + .ctl_ue_data_l = 0x184, + .ctl_ue_data_h = 0x188, + .ctl_ue_synd = 0x180, + .ctl_source_id = 0x19c, + .ctl_controller_busy = 0x20c, + .ctl_xor_check_bits = 0x174, + + /* masks and shifts */ + .ecc_en_mask = GENMASK(17, 16), + .int_status_ce_mask = GENMASK(1, 0), + .int_status_ue_mask = GENMASK(3, 2), + .int_ack_ce_mask = GENMASK(1, 0), + .int_ack_ue_mask = GENMASK(3, 2), + .int_mask_master_non_ecc_mask = GENMASK(30, 3) | GENMASK(1, 0), + .int_mask_master_global_mask = BIT(31), + .int_mask_ecc_non_event_mask = GENMASK(8, 4), + .ce_addr_h_mask = GENMASK(1, 0), + .ce_synd_mask = GENMASK(15, 8), + .ce_synd_shift = 8, + .ue_addr_h_mask = GENMASK(1, 0), + .ue_synd_mask = GENMASK(15, 8), + .ue_synd_shift = 8, + .source_id_ce_mask = GENMASK(29, 16), + .source_id_ce_shift = 16, + .source_id_ue_mask = GENMASK(13, 0), + .source_id_ue_shift = 0, + .controller_busy_mask = BIT(0), + .xor_check_bits_mask = GENMASK(23, 16), + .xor_check_bits_shift = 16, + .writeback_en_mask = BIT(24), + .fwc_mask = BIT(8), +}; + +static const struct of_device_id npcm_edac_of_match[] = { + { + .compatible = "nuvoton,npcm750-memory-controller", + .data = &npcm750_edac + }, + { + .compatible = "nuvoton,npcm845-memory-controller", + .data = &npcm845_edac + }, + {}, +}; + +MODULE_DEVICE_TABLE(of, npcm_edac_of_match); + +static struct platform_driver npcm_edac_driver = { + .driver = { + .name = "npcm-edac", + .of_match_table = npcm_edac_of_match, + }, + .probe = edac_probe, + .remove = edac_remove, +}; + +module_platform_driver(npcm_edac_driver); + +MODULE_AUTHOR("Medad CChien <medadyoung@gmail.com>"); +MODULE_AUTHOR("Marvin Lin <kflin@nuvoton.com>"); +MODULE_DESCRIPTION("Nuvoton NPCM EDAC Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 0bcd9f02c84a..b9c5772da959 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -481,7 +481,7 @@ static int thunderx_create_debugfs_nodes(struct dentry *parent, ent = edac_debugfs_create_file(attrs[i]->name, attrs[i]->mode, parent, data, &attrs[i]->fops); - if (!ent) + if (IS_ERR(ent)) break; } diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index e4ccfb6a8fa5..ec056f6f40ce 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -2124,6 +2124,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware file, blocks, le32_to_cpu(blk->len), type, le32_to_cpu(blk->id)); + region_name = cs_dsp_mem_region_name(type); mem = cs_dsp_find_region(dsp, type); if (!mem) { cs_dsp_err(dsp, "No base for region %x\n", type); @@ -2147,8 +2148,8 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware reg = dsp->ops->region_to_reg(mem, reg); reg += offset; } else { - cs_dsp_err(dsp, "No %x for algorithm %x\n", - type, le32_to_cpu(blk->id)); + cs_dsp_err(dsp, "No %s for algorithm %x\n", + region_name, le32_to_cpu(blk->id)); } break; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index abeff7dc0b58..34b9e7876538 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -361,24 +361,6 @@ static void __init efi_debugfs_init(void) static inline void efi_debugfs_init(void) {} #endif -static void refresh_nv_rng_seed(struct work_struct *work) -{ - u8 seed[EFI_RANDOM_SEED_SIZE]; - - get_random_bytes(seed, sizeof(seed)); - efi.set_variable(L"RandomSeed", &LINUX_EFI_RANDOM_SEED_TABLE_GUID, - EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, sizeof(seed), seed); - memzero_explicit(seed, sizeof(seed)); -} -static int refresh_nv_rng_seed_notification(struct notifier_block *nb, unsigned long action, void *data) -{ - static DECLARE_WORK(work, refresh_nv_rng_seed); - schedule_work(&work); - return NOTIFY_DONE; -} -static struct notifier_block refresh_nv_rng_seed_nb = { .notifier_call = refresh_nv_rng_seed_notification }; - /* * We register the efi subsystem with the firmware subsystem and the * efivars subsystem with the efi subsystem, if the system was booted with @@ -451,9 +433,6 @@ static int __init efisubsys_init(void) platform_device_register_simple("efi_secret", 0, NULL, 0); #endif - if (efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE)) - execute_with_initialized_rng(&refresh_nv_rng_seed_nb); - return 0; err_remove_group: diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index 98939cd4a71e..745e5f67254e 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -221,8 +221,12 @@ static int sifive_gpio_probe(struct platform_device *pdev) return -ENODEV; } - for (i = 0; i < ngpio; i++) - chip->irq_number[i] = platform_get_irq(pdev, i); + for (i = 0; i < ngpio; i++) { + ret = platform_get_irq(pdev, i); + if (ret < 0) + return ret; + chip->irq_number[i] = ret; + } ret = bgpio_init(&chip->gc, dev, 4, chip->base + SIFIVE_GPIO_INPUT_VAL, diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index a7220e04a93e..5be8ad61523e 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1745,7 +1745,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gc) } /* Remove all IRQ mappings and delete the domain */ - if (gc->irq.domain) { + if (!gc->irq.domain_is_allocated_externally && gc->irq.domain) { unsigned int irq; for (offset = 0; offset < gc->ngpio; offset++) { @@ -1791,6 +1791,15 @@ int gpiochip_irqchip_add_domain(struct gpio_chip *gc, gc->to_irq = gpiochip_to_irq; gc->irq.domain = domain; + gc->irq.domain_is_allocated_externally = true; + + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before adding irqdomain. + */ + barrier(); + + gc->irq.initialized = true; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b1ca1ab6d6ad..393b6fb7a71d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1615,6 +1615,7 @@ static const u16 amdgpu_unsupported_pciidlist[] = { 0x5874, 0x5940, 0x5941, + 0x5b70, 0x5b72, 0x5b73, 0x5b74, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 3b225be89cb7..a70103ac0026 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -140,7 +140,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) places[c].lpfn = visible_pfn; - else if (adev->gmc.real_vram_size != adev->gmc.visible_vram_size) + else places[c].flags |= TTM_PL_FLAG_TOPDOWN; if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 9d7e6e0e73ed..a150b7a4b4aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -3548,6 +3548,9 @@ static ssize_t amdgpu_psp_vbflash_read(struct file *filp, struct kobject *kobj, void *fw_pri_cpu_addr; int ret; + if (adev->psp.vbflash_image_size == 0) + return -EINVAL; + dev_info(adev->dev, "VBIOS flash to PSP started"); ret = amdgpu_bo_create_kernel(adev, adev->psp.vbflash_image_size, @@ -3599,13 +3602,13 @@ static ssize_t amdgpu_psp_vbflash_status(struct device *dev, } static const struct bin_attribute psp_vbflash_bin_attr = { - .attr = {.name = "psp_vbflash", .mode = 0664}, + .attr = {.name = "psp_vbflash", .mode = 0660}, .size = 0, .write = amdgpu_psp_vbflash_write, .read = amdgpu_psp_vbflash_read, }; -static DEVICE_ATTR(psp_vbflash_status, 0444, amdgpu_psp_vbflash_status, NULL); +static DEVICE_ATTR(psp_vbflash_status, 0440, amdgpu_psp_vbflash_status, NULL); int amdgpu_psp_sysfs_init(struct amdgpu_device *adev) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index dc474b809604..49de3a3eebc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -581,3 +581,21 @@ void amdgpu_ring_ib_end(struct amdgpu_ring *ring) if (ring->is_sw_ring) amdgpu_sw_ring_ib_end(ring); } + +void amdgpu_ring_ib_on_emit_cntl(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CONTROL); +} + +void amdgpu_ring_ib_on_emit_ce(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CE); +} + +void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE); +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index d8749444b689..2474cb71e476 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -227,6 +227,9 @@ struct amdgpu_ring_funcs { int (*preempt_ib)(struct amdgpu_ring *ring); void (*emit_mem_sync)(struct amdgpu_ring *ring); void (*emit_wave_limit)(struct amdgpu_ring *ring, bool enable); + void (*patch_cntl)(struct amdgpu_ring *ring, unsigned offset); + void (*patch_ce)(struct amdgpu_ring *ring, unsigned offset); + void (*patch_de)(struct amdgpu_ring *ring, unsigned offset); }; struct amdgpu_ring { @@ -318,10 +321,16 @@ struct amdgpu_ring { #define amdgpu_ring_init_cond_exec(r) (r)->funcs->init_cond_exec((r)) #define amdgpu_ring_patch_cond_exec(r,o) (r)->funcs->patch_cond_exec((r),(o)) #define amdgpu_ring_preempt_ib(r) (r)->funcs->preempt_ib(r) +#define amdgpu_ring_patch_cntl(r, o) ((r)->funcs->patch_cntl((r), (o))) +#define amdgpu_ring_patch_ce(r, o) ((r)->funcs->patch_ce((r), (o))) +#define amdgpu_ring_patch_de(r, o) ((r)->funcs->patch_de((r), (o))) int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw); void amdgpu_ring_ib_begin(struct amdgpu_ring *ring); void amdgpu_ring_ib_end(struct amdgpu_ring *ring); +void amdgpu_ring_ib_on_emit_cntl(struct amdgpu_ring *ring); +void amdgpu_ring_ib_on_emit_ce(struct amdgpu_ring *ring); +void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring); void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count); void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c index 62079f0e3ee8..73516abef662 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c @@ -105,6 +105,16 @@ static void amdgpu_mux_resubmit_chunks(struct amdgpu_ring_mux *mux) amdgpu_fence_update_start_timestamp(e->ring, chunk->sync_seq, ktime_get()); + if (chunk->sync_seq == + le32_to_cpu(*(e->ring->fence_drv.cpu_addr + 2))) { + if (chunk->cntl_offset <= e->ring->buf_mask) + amdgpu_ring_patch_cntl(e->ring, + chunk->cntl_offset); + if (chunk->ce_offset <= e->ring->buf_mask) + amdgpu_ring_patch_ce(e->ring, chunk->ce_offset); + if (chunk->de_offset <= e->ring->buf_mask) + amdgpu_ring_patch_de(e->ring, chunk->de_offset); + } amdgpu_ring_mux_copy_pkt_from_sw_ring(mux, e->ring, chunk->start, chunk->end); @@ -407,6 +417,17 @@ void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring) amdgpu_ring_mux_end_ib(mux, ring); } +void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mux_offset_type type) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ring_mux *mux = &adev->gfx.muxer; + unsigned offset; + + offset = ring->wptr & ring->buf_mask; + + amdgpu_ring_mux_ib_mark_offset(mux, ring, offset, type); +} + void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) { struct amdgpu_mux_entry *e; @@ -429,6 +450,10 @@ void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *r } chunk->start = ring->wptr; + /* the initialized value used to check if they are set by the ib submission*/ + chunk->cntl_offset = ring->buf_mask + 1; + chunk->de_offset = ring->buf_mask + 1; + chunk->ce_offset = ring->buf_mask + 1; list_add_tail(&chunk->entry, &e->list); } @@ -454,6 +479,41 @@ static void scan_and_remove_signaled_chunk(struct amdgpu_ring_mux *mux, struct a } } +void amdgpu_ring_mux_ib_mark_offset(struct amdgpu_ring_mux *mux, + struct amdgpu_ring *ring, u64 offset, + enum amdgpu_ring_mux_offset_type type) +{ + struct amdgpu_mux_entry *e; + struct amdgpu_mux_chunk *chunk; + + e = amdgpu_ring_mux_sw_entry(mux, ring); + if (!e) { + DRM_ERROR("cannot find entry!\n"); + return; + } + + chunk = list_last_entry(&e->list, struct amdgpu_mux_chunk, entry); + if (!chunk) { + DRM_ERROR("cannot find chunk!\n"); + return; + } + + switch (type) { + case AMDGPU_MUX_OFFSET_TYPE_CONTROL: + chunk->cntl_offset = offset; + break; + case AMDGPU_MUX_OFFSET_TYPE_DE: + chunk->de_offset = offset; + break; + case AMDGPU_MUX_OFFSET_TYPE_CE: + chunk->ce_offset = offset; + break; + default: + DRM_ERROR("invalid type (%d)\n", type); + break; + } +} + void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring) { struct amdgpu_mux_entry *e; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h index 4be45fc14954..b22d4fb2a847 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.h @@ -50,6 +50,12 @@ struct amdgpu_mux_entry { struct list_head list; }; +enum amdgpu_ring_mux_offset_type { + AMDGPU_MUX_OFFSET_TYPE_CONTROL, + AMDGPU_MUX_OFFSET_TYPE_DE, + AMDGPU_MUX_OFFSET_TYPE_CE, +}; + struct amdgpu_ring_mux { struct amdgpu_ring *real_ring; @@ -72,12 +78,18 @@ struct amdgpu_ring_mux { * @sync_seq: the fence seqno related with the saved IB. * @start:- start location on the software ring. * @end:- end location on the software ring. + * @control_offset:- the PRE_RESUME bit position used for resubmission. + * @de_offset:- the anchor in write_data for de meta of resubmission. + * @ce_offset:- the anchor in write_data for ce meta of resubmission. */ struct amdgpu_mux_chunk { struct list_head entry; uint32_t sync_seq; u64 start; u64 end; + u64 cntl_offset; + u64 de_offset; + u64 ce_offset; }; int amdgpu_ring_mux_init(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, @@ -89,6 +101,8 @@ u64 amdgpu_ring_mux_get_wptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ri u64 amdgpu_ring_mux_get_rptr(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); void amdgpu_ring_mux_start_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); void amdgpu_ring_mux_end_ib(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring); +void amdgpu_ring_mux_ib_mark_offset(struct amdgpu_ring_mux *mux, struct amdgpu_ring *ring, + u64 offset, enum amdgpu_ring_mux_offset_type type); bool amdgpu_mcbp_handle_trailing_fence_irq(struct amdgpu_ring_mux *mux); u64 amdgpu_sw_ring_get_rptr_gfx(struct amdgpu_ring *ring); @@ -97,6 +111,7 @@ void amdgpu_sw_ring_set_wptr_gfx(struct amdgpu_ring *ring); void amdgpu_sw_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count); void amdgpu_sw_ring_ib_begin(struct amdgpu_ring *ring); void amdgpu_sw_ring_ib_end(struct amdgpu_ring *ring); +void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mux_offset_type type); const char *amdgpu_sw_ring_name(int idx); unsigned int amdgpu_sw_ring_priority(int idx); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index e7f2b7bf0ff5..a674c8a58dc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -755,7 +755,7 @@ static void gfx_v9_0_set_rlc_funcs(struct amdgpu_device *adev); static int gfx_v9_0_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info); static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev); -static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume); +static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume, bool usegds); static u64 gfx_v9_0_ring_get_rptr_compute(struct amdgpu_ring *ring); static void gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev, void *ras_error_status); @@ -5127,7 +5127,8 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, gfx_v9_0_ring_emit_de_meta(ring, (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? - true : false); + true : false, + job->gds_size > 0 && job->gds_base != 0); } amdgpu_ring_write(ring, header); @@ -5138,9 +5139,83 @@ static void gfx_v9_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, #endif lower_32_bits(ib->gpu_addr)); amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr)); + amdgpu_ring_ib_on_emit_cntl(ring); amdgpu_ring_write(ring, control); } +static void gfx_v9_0_ring_patch_cntl(struct amdgpu_ring *ring, + unsigned offset) +{ + u32 control = ring->ring[offset]; + + control |= INDIRECT_BUFFER_PRE_RESUME(1); + ring->ring[offset] = control; +} + +static void gfx_v9_0_ring_patch_ce_meta(struct amdgpu_ring *ring, + unsigned offset) +{ + struct amdgpu_device *adev = ring->adev; + void *ce_payload_cpu_addr; + uint64_t payload_offset, payload_size; + + payload_size = sizeof(struct v9_ce_ib_state); + + if (ring->is_mes_queue) { + payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data, + gfx[0].gfx_meta_data) + + offsetof(struct v9_gfx_meta_data, ce_payload); + ce_payload_cpu_addr = + amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset); + } else { + payload_offset = offsetof(struct v9_gfx_meta_data, ce_payload); + ce_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset; + } + + if (offset + (payload_size >> 2) <= ring->buf_mask + 1) { + memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr, payload_size); + } else { + memcpy((void *)&ring->ring[offset], ce_payload_cpu_addr, + (ring->buf_mask + 1 - offset) << 2); + payload_size -= (ring->buf_mask + 1 - offset) << 2; + memcpy((void *)&ring->ring[0], + ce_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2), + payload_size); + } +} + +static void gfx_v9_0_ring_patch_de_meta(struct amdgpu_ring *ring, + unsigned offset) +{ + struct amdgpu_device *adev = ring->adev; + void *de_payload_cpu_addr; + uint64_t payload_offset, payload_size; + + payload_size = sizeof(struct v9_de_ib_state); + + if (ring->is_mes_queue) { + payload_offset = offsetof(struct amdgpu_mes_ctx_meta_data, + gfx[0].gfx_meta_data) + + offsetof(struct v9_gfx_meta_data, de_payload); + de_payload_cpu_addr = + amdgpu_mes_ctx_get_offs_cpu_addr(ring, payload_offset); + } else { + payload_offset = offsetof(struct v9_gfx_meta_data, de_payload); + de_payload_cpu_addr = adev->virt.csa_cpu_addr + payload_offset; + } + + if (offset + (payload_size >> 2) <= ring->buf_mask + 1) { + memcpy((void *)&ring->ring[offset], de_payload_cpu_addr, payload_size); + } else { + memcpy((void *)&ring->ring[offset], de_payload_cpu_addr, + (ring->buf_mask + 1 - offset) << 2); + payload_size -= (ring->buf_mask + 1 - offset) << 2; + memcpy((void *)&ring->ring[0], + de_payload_cpu_addr + ((ring->buf_mask + 1 - offset) << 2), + payload_size); + } +} + static void gfx_v9_0_ring_emit_ib_compute(struct amdgpu_ring *ring, struct amdgpu_job *job, struct amdgpu_ib *ib, @@ -5336,6 +5411,8 @@ static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume) amdgpu_ring_write(ring, lower_32_bits(ce_payload_gpu_addr)); amdgpu_ring_write(ring, upper_32_bits(ce_payload_gpu_addr)); + amdgpu_ring_ib_on_emit_ce(ring); + if (resume) amdgpu_ring_write_multiple(ring, ce_payload_cpu_addr, sizeof(ce_payload) >> 2); @@ -5369,10 +5446,6 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring) amdgpu_ring_alloc(ring, 13); gfx_v9_0_ring_emit_fence(ring, ring->trail_fence_gpu_addr, ring->trail_seq, AMDGPU_FENCE_FLAG_EXEC | AMDGPU_FENCE_FLAG_INT); - /*reset the CP_VMID_PREEMPT after trailing fence*/ - amdgpu_ring_emit_wreg(ring, - SOC15_REG_OFFSET(GC, 0, mmCP_VMID_PREEMPT), - 0x0); /* assert IB preemption, emit the trailing fence */ kiq->pmf->kiq_unmap_queues(kiq_ring, ring, PREEMPT_QUEUES_NO_UNMAP, @@ -5395,6 +5468,10 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring) DRM_WARN("ring %d timeout to preempt ib\n", ring->idx); } + /*reset the CP_VMID_PREEMPT after trailing fence*/ + amdgpu_ring_emit_wreg(ring, + SOC15_REG_OFFSET(GC, 0, mmCP_VMID_PREEMPT), + 0x0); amdgpu_ring_commit(ring); /* deassert preemption condition */ @@ -5402,7 +5479,7 @@ static int gfx_v9_0_ring_preempt_ib(struct amdgpu_ring *ring) return r; } -static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume) +static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume, bool usegds) { struct amdgpu_device *adev = ring->adev; struct v9_de_ib_state de_payload = {0}; @@ -5433,8 +5510,10 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume) PAGE_SIZE); } - de_payload.gds_backup_addrlo = lower_32_bits(gds_addr); - de_payload.gds_backup_addrhi = upper_32_bits(gds_addr); + if (usegds) { + de_payload.gds_backup_addrlo = lower_32_bits(gds_addr); + de_payload.gds_backup_addrhi = upper_32_bits(gds_addr); + } cnt = (sizeof(de_payload) >> 2) + 4 - 2; amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt)); @@ -5445,6 +5524,7 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume) amdgpu_ring_write(ring, lower_32_bits(de_payload_gpu_addr)); amdgpu_ring_write(ring, upper_32_bits(de_payload_gpu_addr)); + amdgpu_ring_ib_on_emit_de(ring); if (resume) amdgpu_ring_write_multiple(ring, de_payload_cpu_addr, sizeof(de_payload) >> 2); @@ -6855,6 +6935,9 @@ static const struct amdgpu_ring_funcs gfx_v9_0_sw_ring_funcs_gfx = { .emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait, .soft_recovery = gfx_v9_0_ring_soft_recovery, .emit_mem_sync = gfx_v9_0_emit_mem_sync, + .patch_cntl = gfx_v9_0_ring_patch_cntl, + .patch_de = gfx_v9_0_ring_patch_de_meta, + .patch_ce = gfx_v9_0_ring_patch_ce_meta, }; static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index e5fd1e00914d..da126ff8bcbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -129,7 +129,11 @@ static int vcn_v4_0_sw_init(void *handle) if (adev->vcn.harvest_config & (1 << i)) continue; - atomic_set(&adev->vcn.inst[i].sched_score, 0); + /* Init instance 0 sched_score to 1, so it's scheduled after other instances */ + if (i == 0) + atomic_set(&adev->vcn.inst[i].sched_score, 1); + else + atomic_set(&adev->vcn.inst[i].sched_score, 0); /* VCN UNIFIED TRAP */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i], diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d5cec03eaa8d..7acd73e5004f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7196,7 +7196,13 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 1920, 1080); } else { amdgpu_dm_connector_ddc_get_modes(connector, edid); - amdgpu_dm_connector_add_common_modes(encoder, connector); + /* most eDP supports only timings from its edid, + * usually only detailed timings are available + * from eDP edid. timings which are not from edid + * may damage eDP + */ + if (connector->connector_type != DRM_MODE_CONNECTOR_eDP) + amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, edid); } amdgpu_dm_fbc_init(connector); @@ -8198,6 +8204,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, if (acrtc_state->abm_level != dm_old_crtc_state->abm_level) bundle->stream_update.abm_level = &acrtc_state->abm_level; + mutex_lock(&dm->dc_lock); + if ((acrtc_state->update_type > UPDATE_TYPE_FAST) && + acrtc_state->stream->link->psr_settings.psr_allow_active) + amdgpu_dm_psr_disable(acrtc_state->stream); + mutex_unlock(&dm->dc_lock); + /* * If FreeSync state on the stream has changed then we need to * re-adjust the min/max bounds now that DC doesn't handle this @@ -8211,10 +8223,6 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } mutex_lock(&dm->dc_lock); - if ((acrtc_state->update_type > UPDATE_TYPE_FAST) && - acrtc_state->stream->link->psr_settings.psr_allow_active) - amdgpu_dm_psr_disable(acrtc_state->stream); - update_planes_and_stream_adapter(dm->dc, acrtc_state->update_type, planes_count, diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index a131e30fd7d6..d471d58aba92 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -980,6 +980,11 @@ static bool detect_link_and_local_sink(struct dc_link *link, (link->dpcd_caps.dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER)) converter_disable_audio = true; + + /* limited link rate to HBR3 for DPIA until we implement USB4 V2 */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + link->reported_link_cap.link_rate > LINK_RATE_HIGH3) + link->reported_link_cap.link_rate = LINK_RATE_HIGH3; break; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 09405ef1e3c8..08577d1b84ec 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1696,10 +1696,39 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ - workload_type = smu_cmn_to_asic_specific_index(smu, + if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE && + (((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xC8)) || + ((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xCC)))) { + ret = smu_cmn_update_table(smu, + SMU_TABLE_ACTIVITY_MONITOR_COEFF, + WORKLOAD_PPLIB_COMPUTE_BIT, + (void *)(&activity_monitor_external), + false); + if (ret) { + dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__); + return ret; + } + + ret = smu_cmn_update_table(smu, + SMU_TABLE_ACTIVITY_MONITOR_COEFF, + WORKLOAD_PPLIB_CUSTOM_BIT, + (void *)(&activity_monitor_external), + true); + if (ret) { + dev_err(smu->adev->dev, "[%s] Failed to set activity monitor!", __func__); + return ret; + } + + workload_type = smu_cmn_to_asic_specific_index(smu, + CMN2ASIC_MAPPING_WORKLOAD, + PP_SMC_POWER_PROFILE_CUSTOM); + } else { + /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ + workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, smu->power_profile_mode); + } + if (workload_type < 0) return -EINVAL; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 7a748785c545..4676cf2900df 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -298,6 +298,10 @@ static void ti_sn_bridge_set_refclk_freq(struct ti_sn65dsi86 *pdata) if (refclk_lut[i] == refclk_rate) break; + /* avoid buffer overflow and "1" is the default rate in the datasheet. */ + if (i >= refclk_lut_size) + i = 1; + regmap_update_bits(pdata->regmap, SN_DPPLL_SRC_REG, REFCLK_FREQ_MASK, REFCLK_FREQ(i)); diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 38dab76ae69e..e2e21ce79510 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3404,7 +3404,7 @@ int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, /* Skip failed payloads */ if (payload->vc_start_slot == -1) { - drm_dbg_kms(state->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", + drm_dbg_kms(mgr->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", payload->port->connector->name); return -EIO; } diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 8cf096f841a9..a2ae8c21e4dc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -220,6 +220,9 @@ static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out int optimus_funcs; struct pci_dev *parent_pdev; + if (pdev->vendor != PCI_VENDOR_ID_NVIDIA) + return; + *has_pr3 = false; parent_pdev = pci_upstream_bridge(pdev); if (parent_pdev) { diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 086b66b60d91..f75c6f09dd2a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -730,7 +730,8 @@ out: #endif nouveau_connector_set_edid(nv_connector, edid); - nouveau_connector_set_encoder(connector, nv_encoder); + if (nv_encoder) + nouveau_connector_set_encoder(connector, nv_encoder); return status; } @@ -966,7 +967,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) /* Determine display colour depth for everything except LVDS now, * DP requires this before mode_valid() is called. */ - if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS) + if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) nouveau_connector_detect_depth(connector); /* Find the native mode if this is a digital panel, if we didn't @@ -987,7 +988,7 @@ nouveau_connector_get_modes(struct drm_connector *connector) * "native" mode as some VBIOS tables require us to use the * pixel clock as part of the lookup... */ - if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS) + if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS && nv_connector->native_mode) nouveau_connector_detect_depth(connector); if (nv_encoder->dcb->type == DCB_OUTPUT_TV) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index cc7c5b4a05fd..7aac9384600e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -137,10 +137,16 @@ nouveau_name(struct drm_device *dev) static inline bool nouveau_cli_work_ready(struct dma_fence *fence) { - if (!dma_fence_is_signaled(fence)) - return false; - dma_fence_put(fence); - return true; + bool ret = true; + + spin_lock_irq(fence->lock); + if (!dma_fence_is_signaled_locked(fence)) + ret = false; + spin_unlock_irq(fence->lock); + + if (ret == true) + dma_fence_put(fence); + return ret; } static void diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c index fe76e29910ef..8f6c3aef0962 100644 --- a/drivers/gpu/drm/radeon/radeon_fbdev.c +++ b/drivers/gpu/drm/radeon/radeon_fbdev.c @@ -307,6 +307,7 @@ static void radeon_fbdev_client_unregister(struct drm_client_dev *client) if (fb_helper->info) { vga_switcheroo_client_fb_set(rdev->pdev, NULL); + drm_helper_force_disable_all(dev); drm_fb_helper_unregister_info(fb_helper); } else { drm_client_release(&fb_helper->client); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 007f26d5f1a4..2f4d09ce027a 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -829,11 +829,22 @@ static void vmbus_wait_for_unload(void) if (completion_done(&vmbus_connection.unload_event)) goto completed; - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); + /* + * In a CoCo VM the synic_message_page is not allocated + * in hv_synic_alloc(). Instead it is set/cleared in + * hv_synic_enable_regs() and hv_synic_disable_regs() + * such that it is set only when the CPU is online. If + * not all present CPUs are online, the message page + * might be NULL, so skip such CPUs. + */ page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; @@ -867,11 +878,14 @@ completed: * maybe-pending messages on all CPUs to be able to receive new * messages after we reconnect. */ - for_each_online_cpu(cpu) { + for_each_present_cpu(cpu) { struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); page_addr = hv_cpu->synic_message_page; + if (!page_addr) + continue; + msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT; msg->header.message_type = HVMSG_NONE; } diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 64f9ceca887b..542a1d53b303 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -364,13 +364,20 @@ int hv_common_cpu_init(unsigned int cpu) flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL; inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - *inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags); - if (!(*inputarg)) - return -ENOMEM; - if (hv_root_partition) { - outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); - *outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE; + /* + * hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory is already + * allocated if this CPU was previously online and then taken offline + */ + if (!*inputarg) { + *inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags); + if (!(*inputarg)) + return -ENOMEM; + + if (hv_root_partition) { + outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); + *outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE; + } } msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); @@ -385,24 +392,17 @@ int hv_common_cpu_init(unsigned int cpu) int hv_common_cpu_die(unsigned int cpu) { - unsigned long flags; - void **inputarg, **outputarg; - void *mem; - - local_irq_save(flags); - - inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - mem = *inputarg; - *inputarg = NULL; - - if (hv_root_partition) { - outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg); - *outputarg = NULL; - } - - local_irq_restore(flags); - - kfree(mem); + /* + * The hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory + * is not freed when the CPU goes offline as the hyperv_pcpu_input_arg + * may be used by the Hyper-V vPCI driver in reassigning interrupts + * as part of the offlining process. The interrupt reassignment + * happens *after* the CPUHP_AP_HYPERV_ONLINE state has run and + * called this function. + * + * If a previously offlined CPU is brought back online again, the + * originally allocated memory is reused in hv_common_cpu_init(). + */ return 0; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 1c65a6dfb9fa..67f95a29aeca 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1372,7 +1372,7 @@ static int vmbus_bus_init(void) ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "hyperv/vmbus:online", hv_synic_init, hv_synic_cleanup); if (ret < 0) - goto err_cpuhp; + goto err_alloc; hyperv_cpuhp_online = ret; ret = vmbus_connect(); @@ -1392,9 +1392,8 @@ static int vmbus_bus_init(void) err_connect: cpuhp_remove_state(hyperv_cpuhp_online); -err_cpuhp: - hv_synic_free(); err_alloc: + hv_synic_free(); if (vmbus_irq == -1) { hv_remove_vmbus_handler(); } else { diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 1af0a637d7f1..4d24ceb57ee7 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -201,8 +201,8 @@ static void lpi2c_imx_stop(struct lpi2c_imx_struct *lpi2c_imx) /* CLKLO = I2C_CLK_RATIO * CLKHI, SETHOLD = CLKHI, DATAVD = CLKHI/2 */ static int lpi2c_imx_config(struct lpi2c_imx_struct *lpi2c_imx) { - u8 prescale, filt, sethold, clkhi, clklo, datavd; - unsigned int clk_rate, clk_cycle; + u8 prescale, filt, sethold, datavd; + unsigned int clk_rate, clk_cycle, clkhi, clklo; enum lpi2c_imx_pincfg pincfg; unsigned int temp; diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c index 2e153f2f71b6..78682388e02e 100644 --- a/drivers/i2c/busses/i2c-qup.c +++ b/drivers/i2c/busses/i2c-qup.c @@ -1752,16 +1752,21 @@ nodma: if (!clk_freq || clk_freq > I2C_MAX_FAST_MODE_PLUS_FREQ) { dev_err(qup->dev, "clock frequency not supported %d\n", clk_freq); - return -EINVAL; + ret = -EINVAL; + goto fail_dma; } qup->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(qup->base)) - return PTR_ERR(qup->base); + if (IS_ERR(qup->base)) { + ret = PTR_ERR(qup->base); + goto fail_dma; + } qup->irq = platform_get_irq(pdev, 0); - if (qup->irq < 0) - return qup->irq; + if (qup->irq < 0) { + ret = qup->irq; + goto fail_dma; + } if (has_acpi_companion(qup->dev)) { ret = device_property_read_u32(qup->dev, @@ -1775,13 +1780,15 @@ nodma: qup->clk = devm_clk_get(qup->dev, "core"); if (IS_ERR(qup->clk)) { dev_err(qup->dev, "Could not get core clock\n"); - return PTR_ERR(qup->clk); + ret = PTR_ERR(qup->clk); + goto fail_dma; } qup->pclk = devm_clk_get(qup->dev, "iface"); if (IS_ERR(qup->pclk)) { dev_err(qup->dev, "Could not get iface clock\n"); - return PTR_ERR(qup->pclk); + ret = PTR_ERR(qup->pclk); + goto fail_dma; } qup_i2c_enable_clocks(qup); src_clk_freq = clk_get_rate(qup->clk); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 93a1c48d0c32..6b3f4384e46a 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3295,7 +3295,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; - route->path_rec->rate = iboe_get_rate(ndev); + route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate @@ -4964,7 +4964,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (!ndev) return -ENODEV; - ib.rec.rate = iboe_get_rate(ndev); + ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4796f6a8828c..e836c9c477f6 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1850,8 +1850,13 @@ static int modify_qp(struct uverbs_attr_bundle *attrs, attr->path_mtu = cmd->base.path_mtu; if (cmd->base.attr_mask & IB_QP_PATH_MIG_STATE) attr->path_mig_state = cmd->base.path_mig_state; - if (cmd->base.attr_mask & IB_QP_QKEY) + if (cmd->base.attr_mask & IB_QP_QKEY) { + if (cmd->base.qkey & IB_QP_SET_QKEY && !capable(CAP_NET_RAW)) { + ret = -EPERM; + goto release_qp; + } attr->qkey = cmd->base.qkey; + } if (cmd->base.attr_mask & IB_QP_RQ_PSN) attr->rq_psn = cmd->base.rq_psn; if (cmd->base.attr_mask & IB_QP_SQ_PSN) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index fbace69672ca..7c9c79c13941 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -222,8 +222,12 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { - spin_unlock_irq(&ev_queue->lock); + if (ev_queue->is_closed) { + spin_unlock_irq(&ev_queue->lock); + return -EIO; + } + spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; @@ -233,12 +237,6 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); - - /* If device was disassociated and no event exists set an error */ - if (list_empty(&ev_queue->event_list) && ev_queue->is_closed) { - spin_unlock_irq(&ev_queue->lock); - return -EIO; - } } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 5a2baf49ecaa..2c95e6f3d47a 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -135,8 +135,6 @@ struct bnxt_re_dev { struct delayed_work worker; u8 cur_prio_map; - u16 active_speed; - u8 active_width; /* FP Notification Queue (CQ & SRQ) */ struct tasklet_struct nq_task; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index b1c36412025f..952811c40c54 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -199,6 +199,7 @@ int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num, { struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev); struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr; + int rc; memset(port_attr, 0, sizeof(*port_attr)); @@ -228,10 +229,10 @@ int bnxt_re_query_port(struct ib_device *ibdev, u32 port_num, port_attr->sm_sl = 0; port_attr->subnet_timeout = 0; port_attr->init_type_reply = 0; - port_attr->active_speed = rdev->active_speed; - port_attr->active_width = rdev->active_width; + rc = ib_get_eth_speed(&rdev->ibdev, port_num, &port_attr->active_speed, + &port_attr->active_width); - return 0; + return rc; } int bnxt_re_get_port_immutable(struct ib_device *ibdev, u32 port_num, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index e34eccd178d0..3073398a2183 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1077,8 +1077,6 @@ static int bnxt_re_ib_init(struct bnxt_re_dev *rdev) return rc; } dev_info(rdev_to_dev(rdev), "Device registered with IB successfully"); - ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, - &rdev->active_width); set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags); event = netif_running(rdev->netdev) && netif_carrier_ok(rdev->netdev) ? diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c index 1c06920505d2..93257fa5aae8 100644 --- a/drivers/infiniband/hw/mlx5/counters.c +++ b/drivers/infiniband/hw/mlx5/counters.c @@ -209,7 +209,8 @@ static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev, !vport_qcounters_supported(dev)) || !port_num) return &dev->port[0].cnts; - return &dev->port[port_num - 1].cnts; + return is_mdev_switchdev_mode(dev->mdev) ? + &dev->port[1].cnts : &dev->port[port_num - 1].cnts; } /** @@ -262,7 +263,7 @@ static struct rdma_hw_stats * mlx5_ib_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - const struct mlx5_ib_counters *cnts = &dev->port[port_num - 1].cnts; + const struct mlx5_ib_counters *cnts = get_counters(dev, port_num); return do_alloc_stats(cnts); } @@ -329,6 +330,7 @@ static int mlx5_ib_query_q_counters_vport(struct mlx5_ib_dev *dev, { u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; + struct mlx5_core_dev *mdev; __be32 val; int ret, i; @@ -336,12 +338,16 @@ static int mlx5_ib_query_q_counters_vport(struct mlx5_ib_dev *dev, dev->port[port_num].rep->vport == MLX5_VPORT_UPLINK) return 0; + mdev = mlx5_eswitch_get_core_dev(dev->port[port_num].rep->esw); + if (!mdev) + return -EOPNOTSUPP; + MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); MLX5_SET(query_q_counter_in, in, other_vport, 1); MLX5_SET(query_q_counter_in, in, vport_number, dev->port[port_num].rep->vport); MLX5_SET(query_q_counter_in, in, aggregate, 1); - ret = mlx5_cmd_exec_inout(dev->mdev, query_q_counter, in, out); + ret = mlx5_cmd_exec_inout(mdev, query_q_counter, in, out); if (ret) return ret; @@ -575,43 +581,53 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev, bool is_vport = is_mdev_switchdev_mode(dev->mdev) && port_num != MLX5_VPORT_PF; const struct mlx5_ib_counter *names; - int j = 0, i; + int j = 0, i, size; names = is_vport ? vport_basic_q_cnts : basic_q_cnts; - for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) { + size = is_vport ? ARRAY_SIZE(vport_basic_q_cnts) : + ARRAY_SIZE(basic_q_cnts); + for (i = 0; i < size; i++, j++) { descs[j].name = names[i].name; - offsets[j] = basic_q_cnts[i].offset; + offsets[j] = names[i].offset; } names = is_vport ? vport_out_of_seq_q_cnts : out_of_seq_q_cnts; + size = is_vport ? ARRAY_SIZE(vport_out_of_seq_q_cnts) : + ARRAY_SIZE(out_of_seq_q_cnts); if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) { - for (i = 0; i < ARRAY_SIZE(out_of_seq_q_cnts); i++, j++) { + for (i = 0; i < size; i++, j++) { descs[j].name = names[i].name; - offsets[j] = out_of_seq_q_cnts[i].offset; + offsets[j] = names[i].offset; } } names = is_vport ? vport_retrans_q_cnts : retrans_q_cnts; + size = is_vport ? ARRAY_SIZE(vport_retrans_q_cnts) : + ARRAY_SIZE(retrans_q_cnts); if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) { - for (i = 0; i < ARRAY_SIZE(retrans_q_cnts); i++, j++) { + for (i = 0; i < size; i++, j++) { descs[j].name = names[i].name; - offsets[j] = retrans_q_cnts[i].offset; + offsets[j] = names[i].offset; } } names = is_vport ? vport_extended_err_cnts : extended_err_cnts; + size = is_vport ? ARRAY_SIZE(vport_extended_err_cnts) : + ARRAY_SIZE(extended_err_cnts); if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) { - for (i = 0; i < ARRAY_SIZE(extended_err_cnts); i++, j++) { + for (i = 0; i < size; i++, j++) { descs[j].name = names[i].name; - offsets[j] = extended_err_cnts[i].offset; + offsets[j] = names[i].offset; } } names = is_vport ? vport_roce_accl_cnts : roce_accl_cnts; + size = is_vport ? ARRAY_SIZE(vport_roce_accl_cnts) : + ARRAY_SIZE(roce_accl_cnts); if (MLX5_CAP_GEN(dev->mdev, roce_accl)) { - for (i = 0; i < ARRAY_SIZE(roce_accl_cnts); i++, j++) { + for (i = 0; i < size; i++, j++) { descs[j].name = names[i].name; - offsets[j] = roce_accl_cnts[i].offset; + offsets[j] = names[i].offset; } } @@ -661,25 +677,37 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev, static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev, struct mlx5_ib_counters *cnts, u32 port_num) { - u32 num_counters, num_op_counters = 0; + bool is_vport = is_mdev_switchdev_mode(dev->mdev) && + port_num != MLX5_VPORT_PF; + u32 num_counters, num_op_counters = 0, size; - num_counters = ARRAY_SIZE(basic_q_cnts); + size = is_vport ? ARRAY_SIZE(vport_basic_q_cnts) : + ARRAY_SIZE(basic_q_cnts); + num_counters = size; + size = is_vport ? ARRAY_SIZE(vport_out_of_seq_q_cnts) : + ARRAY_SIZE(out_of_seq_q_cnts); if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) - num_counters += ARRAY_SIZE(out_of_seq_q_cnts); + num_counters += size; + size = is_vport ? ARRAY_SIZE(vport_retrans_q_cnts) : + ARRAY_SIZE(retrans_q_cnts); if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) - num_counters += ARRAY_SIZE(retrans_q_cnts); + num_counters += size; + size = is_vport ? ARRAY_SIZE(vport_extended_err_cnts) : + ARRAY_SIZE(extended_err_cnts); if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) - num_counters += ARRAY_SIZE(extended_err_cnts); + num_counters += size; + size = is_vport ? ARRAY_SIZE(vport_roce_accl_cnts) : + ARRAY_SIZE(roce_accl_cnts); if (MLX5_CAP_GEN(dev->mdev, roce_accl)) - num_counters += ARRAY_SIZE(roce_accl_cnts); + num_counters += size; cnts->num_q_counters = num_counters; - if (is_mdev_switchdev_mode(dev->mdev) && port_num != MLX5_VPORT_PF) + if (is_vport) goto skip_non_qcounters; if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { @@ -725,11 +753,11 @@ err: static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev) { u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {}; - int num_cnt_ports; + int num_cnt_ports = dev->num_ports; int i, j; - num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) || - vport_qcounters_supported(dev)) ? dev->num_ports : 1; + if (is_mdev_switchdev_mode(dev->mdev)) + num_cnt_ports = min(2, num_cnt_ports); MLX5_SET(dealloc_q_counter_in, in, opcode, MLX5_CMD_OP_DEALLOC_Q_COUNTER); @@ -761,15 +789,22 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev) { u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {}; - int num_cnt_ports; + int num_cnt_ports = dev->num_ports; int err = 0; int i; bool is_shared; MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER); is_shared = MLX5_CAP_GEN(dev->mdev, log_max_uctx) != 0; - num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) || - vport_qcounters_supported(dev)) ? dev->num_ports : 1; + + /* + * In switchdev we need to allocate two ports, one that is used for + * the device Q_counters and it is essentially the real Q_counters of + * this device, while the other is used as a helper for PF to be able to + * query all other vports. + */ + if (is_mdev_switchdev_mode(dev->mdev)) + num_cnt_ports = min(2, num_cnt_ports); for (i = 0; i < num_cnt_ports; i++) { err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts, i); diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 3008632a6c20..1e419e080b53 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -695,8 +695,6 @@ static struct mlx5_ib_flow_prio *_get_prio(struct mlx5_ib_dev *dev, struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_flow_table *ft; - if (mlx5_ib_shared_ft_allowed(&dev->ib_dev)) - ft_attr.uid = MLX5_SHARED_RESOURCE_UID; ft_attr.prio = priority; ft_attr.max_fte = num_entries; ft_attr.flags = flags; @@ -2025,6 +2023,237 @@ static int flow_matcher_cleanup(struct ib_uobject *uobject, return 0; } +static int steering_anchor_create_ft(struct mlx5_ib_dev *dev, + struct mlx5_ib_flow_prio *ft_prio, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *ft; + + if (ft_prio->anchor.ft) + return 0; + + ns = mlx5_get_flow_namespace(dev->mdev, ns_type); + if (!ns) + return -EOPNOTSUPP; + + ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED; + ft_attr.uid = MLX5_SHARED_RESOURCE_UID; + ft_attr.prio = 0; + ft_attr.max_fte = 2; + ft_attr.level = 1; + + ft = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(ft)) + return PTR_ERR(ft); + + ft_prio->anchor.ft = ft; + + return 0; +} + +static void steering_anchor_destroy_ft(struct mlx5_ib_flow_prio *ft_prio) +{ + if (ft_prio->anchor.ft) { + mlx5_destroy_flow_table(ft_prio->anchor.ft); + ft_prio->anchor.ft = NULL; + } +} + +static int +steering_anchor_create_fg_drop(struct mlx5_ib_flow_prio *ft_prio) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + void *flow_group_in; + int err = 0; + + if (ft_prio->anchor.fg_drop) + return 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); + + fg = mlx5_create_flow_group(ft_prio->anchor.ft, flow_group_in); + if (IS_ERR(fg)) { + err = PTR_ERR(fg); + goto out; + } + + ft_prio->anchor.fg_drop = fg; + +out: + kvfree(flow_group_in); + + return err; +} + +static void +steering_anchor_destroy_fg_drop(struct mlx5_ib_flow_prio *ft_prio) +{ + if (ft_prio->anchor.fg_drop) { + mlx5_destroy_flow_group(ft_prio->anchor.fg_drop); + ft_prio->anchor.fg_drop = NULL; + } +} + +static int +steering_anchor_create_fg_goto_table(struct mlx5_ib_flow_prio *ft_prio) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + void *flow_group_in; + int err = 0; + + if (ft_prio->anchor.fg_goto_table) + return 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + fg = mlx5_create_flow_group(ft_prio->anchor.ft, flow_group_in); + if (IS_ERR(fg)) { + err = PTR_ERR(fg); + goto out; + } + ft_prio->anchor.fg_goto_table = fg; + +out: + kvfree(flow_group_in); + + return err; +} + +static void +steering_anchor_destroy_fg_goto_table(struct mlx5_ib_flow_prio *ft_prio) +{ + if (ft_prio->anchor.fg_goto_table) { + mlx5_destroy_flow_group(ft_prio->anchor.fg_goto_table); + ft_prio->anchor.fg_goto_table = NULL; + } +} + +static int +steering_anchor_create_rule_drop(struct mlx5_ib_flow_prio *ft_prio) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *handle; + + if (ft_prio->anchor.rule_drop) + return 0; + + flow_act.fg = ft_prio->anchor.fg_drop; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; + + handle = mlx5_add_flow_rules(ft_prio->anchor.ft, NULL, &flow_act, + NULL, 0); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + ft_prio->anchor.rule_drop = handle; + + return 0; +} + +static void steering_anchor_destroy_rule_drop(struct mlx5_ib_flow_prio *ft_prio) +{ + if (ft_prio->anchor.rule_drop) { + mlx5_del_flow_rules(ft_prio->anchor.rule_drop); + ft_prio->anchor.rule_drop = NULL; + } +} + +static int +steering_anchor_create_rule_goto_table(struct mlx5_ib_flow_prio *ft_prio) +{ + struct mlx5_flow_destination dest = {}; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *handle; + + if (ft_prio->anchor.rule_goto_table) + return 0; + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; + flow_act.fg = ft_prio->anchor.fg_goto_table; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = ft_prio->flow_table; + + handle = mlx5_add_flow_rules(ft_prio->anchor.ft, NULL, &flow_act, + &dest, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + ft_prio->anchor.rule_goto_table = handle; + + return 0; +} + +static void +steering_anchor_destroy_rule_goto_table(struct mlx5_ib_flow_prio *ft_prio) +{ + if (ft_prio->anchor.rule_goto_table) { + mlx5_del_flow_rules(ft_prio->anchor.rule_goto_table); + ft_prio->anchor.rule_goto_table = NULL; + } +} + +static int steering_anchor_create_res(struct mlx5_ib_dev *dev, + struct mlx5_ib_flow_prio *ft_prio, + enum mlx5_flow_namespace_type ns_type) +{ + int err; + + err = steering_anchor_create_ft(dev, ft_prio, ns_type); + if (err) + return err; + + err = steering_anchor_create_fg_drop(ft_prio); + if (err) + goto destroy_ft; + + err = steering_anchor_create_fg_goto_table(ft_prio); + if (err) + goto destroy_fg_drop; + + err = steering_anchor_create_rule_drop(ft_prio); + if (err) + goto destroy_fg_goto_table; + + err = steering_anchor_create_rule_goto_table(ft_prio); + if (err) + goto destroy_rule_drop; + + return 0; + +destroy_rule_drop: + steering_anchor_destroy_rule_drop(ft_prio); +destroy_fg_goto_table: + steering_anchor_destroy_fg_goto_table(ft_prio); +destroy_fg_drop: + steering_anchor_destroy_fg_drop(ft_prio); +destroy_ft: + steering_anchor_destroy_ft(ft_prio); + + return err; +} + +static void mlx5_steering_anchor_destroy_res(struct mlx5_ib_flow_prio *ft_prio) +{ + steering_anchor_destroy_rule_goto_table(ft_prio); + steering_anchor_destroy_rule_drop(ft_prio); + steering_anchor_destroy_fg_goto_table(ft_prio); + steering_anchor_destroy_fg_drop(ft_prio); + steering_anchor_destroy_ft(ft_prio); +} + static int steering_anchor_cleanup(struct ib_uobject *uobject, enum rdma_remove_reason why, struct uverbs_attr_bundle *attrs) @@ -2035,6 +2264,9 @@ static int steering_anchor_cleanup(struct ib_uobject *uobject, return -EBUSY; mutex_lock(&obj->dev->flow_db->lock); + if (!--obj->ft_prio->anchor.rule_goto_table_ref) + steering_anchor_destroy_rule_goto_table(obj->ft_prio); + put_flow_table(obj->dev, obj->ft_prio, true); mutex_unlock(&obj->dev->flow_db->lock); @@ -2042,6 +2274,24 @@ static int steering_anchor_cleanup(struct ib_uobject *uobject, return 0; } +static void fs_cleanup_anchor(struct mlx5_ib_flow_prio *prio, + int count) +{ + while (count--) + mlx5_steering_anchor_destroy_res(&prio[count]); +} + +void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev) +{ + fs_cleanup_anchor(dev->flow_db->prios, MLX5_IB_NUM_FLOW_FT); + fs_cleanup_anchor(dev->flow_db->egress_prios, MLX5_IB_NUM_FLOW_FT); + fs_cleanup_anchor(dev->flow_db->sniffer, MLX5_IB_NUM_SNIFFER_FTS); + fs_cleanup_anchor(dev->flow_db->egress, MLX5_IB_NUM_EGRESS_FTS); + fs_cleanup_anchor(dev->flow_db->fdb, MLX5_IB_NUM_FDB_FTS); + fs_cleanup_anchor(dev->flow_db->rdma_rx, MLX5_IB_NUM_FLOW_FT); + fs_cleanup_anchor(dev->flow_db->rdma_tx, MLX5_IB_NUM_FLOW_FT); +} + static int mlx5_ib_matcher_ns(struct uverbs_attr_bundle *attrs, struct mlx5_ib_flow_matcher *obj) { @@ -2182,21 +2432,31 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)( return -ENOMEM; mutex_lock(&dev->flow_db->lock); + ft_prio = _get_flow_table(dev, priority, ns_type, 0); if (IS_ERR(ft_prio)) { - mutex_unlock(&dev->flow_db->lock); err = PTR_ERR(ft_prio); goto free_obj; } ft_prio->refcount++; - ft_id = mlx5_flow_table_id(ft_prio->flow_table); - mutex_unlock(&dev->flow_db->lock); + + if (!ft_prio->anchor.rule_goto_table_ref) { + err = steering_anchor_create_res(dev, ft_prio, ns_type); + if (err) + goto put_flow_table; + } + + ft_prio->anchor.rule_goto_table_ref++; + + ft_id = mlx5_flow_table_id(ft_prio->anchor.ft); err = uverbs_copy_to(attrs, MLX5_IB_ATTR_STEERING_ANCHOR_FT_ID, &ft_id, sizeof(ft_id)); if (err) - goto put_flow_table; + goto destroy_res; + + mutex_unlock(&dev->flow_db->lock); uobj->object = obj; obj->dev = dev; @@ -2205,8 +2465,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)( return 0; +destroy_res: + --ft_prio->anchor.rule_goto_table_ref; + mlx5_steering_anchor_destroy_res(ft_prio); put_flow_table: - mutex_lock(&dev->flow_db->lock); put_flow_table(dev, ft_prio, true); mutex_unlock(&dev->flow_db->lock); free_obj: diff --git a/drivers/infiniband/hw/mlx5/fs.h b/drivers/infiniband/hw/mlx5/fs.h index ad320adaf321..b9734904f5f0 100644 --- a/drivers/infiniband/hw/mlx5/fs.h +++ b/drivers/infiniband/hw/mlx5/fs.h @@ -10,6 +10,7 @@ #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) int mlx5_ib_fs_init(struct mlx5_ib_dev *dev); +void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev); #else static inline int mlx5_ib_fs_init(struct mlx5_ib_dev *dev) { @@ -21,9 +22,24 @@ static inline int mlx5_ib_fs_init(struct mlx5_ib_dev *dev) mutex_init(&dev->flow_db->lock); return 0; } + +inline void mlx5_ib_fs_cleanup_anchor(struct mlx5_ib_dev *dev) {} #endif + static inline void mlx5_ib_fs_cleanup(struct mlx5_ib_dev *dev) { + /* When a steering anchor is created, a special flow table is also + * created for the user to reference. Since the user can reference it, + * the kernel cannot trust that when the user destroys the steering + * anchor, they no longer reference the flow table. + * + * To address this issue, when a user destroys a steering anchor, only + * the flow steering rule in the table is destroyed, but the table + * itself is kept to deal with the above scenario. The remaining + * resources are only removed when the RDMA device is destroyed, which + * is a safe assumption that all references are gone. + */ + mlx5_ib_fs_cleanup_anchor(dev); kfree(dev->flow_db); } #endif /* _MLX5_IB_FS_H */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5d45de223c43..f0b394ed7452 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4275,6 +4275,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), + STAGE_CREATE(MLX5_IB_STAGE_DELAY_DROP, + mlx5_ib_stage_delay_drop_init, + mlx5_ib_stage_delay_drop_cleanup), STAGE_CREATE(MLX5_IB_STAGE_RESTRACK, mlx5_ib_restrack_init, NULL), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index efa4dc6e7dee..2dfa6f49a6f4 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -237,8 +237,19 @@ enum { #define MLX5_IB_NUM_SNIFFER_FTS 2 #define MLX5_IB_NUM_EGRESS_FTS 1 #define MLX5_IB_NUM_FDB_FTS MLX5_BY_PASS_NUM_REGULAR_PRIOS + +struct mlx5_ib_anchor { + struct mlx5_flow_table *ft; + struct mlx5_flow_group *fg_goto_table; + struct mlx5_flow_group *fg_drop; + struct mlx5_flow_handle *rule_goto_table; + struct mlx5_flow_handle *rule_drop; + unsigned int rule_goto_table_ref; +}; + struct mlx5_ib_flow_prio { struct mlx5_flow_table *flow_table; + struct mlx5_ib_anchor anchor; unsigned int refcount; }; @@ -1587,6 +1598,9 @@ static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev) MLX5_CAP_PORT_SELECTION(dev->mdev, port_select_flow_table_bypass)) return 0; + if (mlx5_lag_is_lacp_owner(dev->mdev) && !dev->lag_active) + return 0; + return dev->lag_active || (MLX5_CAP_GEN(dev->mdev, num_lag_ports) > 1 && MLX5_CAP_GEN(dev->mdev, lag_tx_port_affinity)); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 70ca8ffa9256..78b96bfb4e6a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1237,6 +1237,9 @@ static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev, MLX5_SET(create_tis_in, in, uid, to_mpd(pd)->uid); MLX5_SET(tisc, tisc, transport_domain, tdn); + if (!mlx5_ib_lag_should_assign_affinity(dev) && + mlx5_lag_is_lacp_owner(dev->mdev)) + MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1); if (qp->flags & IB_QP_CREATE_SOURCE_QPN) MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn); diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index 20ff0c0c4605..6ca2a05b6a2a 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -113,8 +113,6 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) queue_advance_producer(cq->queue, QUEUE_TYPE_TO_CLIENT); - spin_unlock_irqrestore(&cq->cq_lock, flags); - if ((cq->notify == IB_CQ_NEXT_COMP) || (cq->notify == IB_CQ_SOLICITED && solicited)) { cq->notify = 0; @@ -122,6 +120,8 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); } + spin_unlock_irqrestore(&cq->cq_lock, flags); + return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index a38fab19bed1..cd59666158b1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -159,6 +159,9 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) pkt->mask = RXE_GRH_MASK; pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); + /* remove udp header */ + skb_pull(skb, sizeof(struct udphdr)); + rxe_rcv(skb); return 0; @@ -401,6 +404,9 @@ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) return -EIO; } + /* remove udp header */ + skb_pull(skb, sizeof(struct udphdr)); + rxe_rcv(skb); return 0; diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 61a2eb77d999..a0f206431cf8 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -176,6 +176,9 @@ static void rxe_qp_init_misc(struct rxe_dev *rxe, struct rxe_qp *qp, spin_lock_init(&qp->rq.producer_lock); spin_lock_init(&qp->rq.consumer_lock); + skb_queue_head_init(&qp->req_pkts); + skb_queue_head_init(&qp->resp_pkts); + atomic_set(&qp->ssn, 0); atomic_set(&qp->skb_out, 0); } @@ -234,8 +237,6 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, qp->req.opcode = -1; qp->comp.opcode = -1; - skb_queue_head_init(&qp->req_pkts); - rxe_init_task(&qp->req.task, qp, rxe_requester); rxe_init_task(&qp->comp.task, qp, rxe_completer); @@ -279,8 +280,6 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, } } - skb_queue_head_init(&qp->resp_pkts); - rxe_init_task(&qp->resp.task, qp, rxe_responder); qp->resp.opcode = OPCODE_NONE; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 1da044f6b7d4..ee68306555b9 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -489,8 +489,9 @@ static enum resp_states check_rkey(struct rxe_qp *qp, if (mw->access & IB_ZERO_BASED) qp->resp.offset = mw->addr; - rxe_put(mw); rxe_get(mr); + rxe_put(mw); + mw = NULL; } else { mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE); if (!mr) { diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index f290cd49698e..92e1e7587af8 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -657,9 +657,13 @@ static int isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + struct isert_np *isert_np = cma_id->context; ib_drain_qp(isert_conn->qp); + + mutex_lock(&isert_np->mutex); list_del_init(&isert_conn->node); + mutex_unlock(&isert_np->mutex); isert_conn->cm_id = NULL; isert_put_conn(isert_conn); @@ -2431,6 +2435,7 @@ isert_free_np(struct iscsi_np *np) { struct isert_np *isert_np = np->np_context; struct isert_conn *isert_conn, *n; + LIST_HEAD(drop_conn_list); if (isert_np->cm_id) rdma_destroy_id(isert_np->cm_id); @@ -2450,7 +2455,7 @@ isert_free_np(struct iscsi_np *np) node) { isert_info("cleaning isert_conn %p state (%d)\n", isert_conn, isert_conn->state); - isert_connect_release(isert_conn); + list_move_tail(&isert_conn->node, &drop_conn_list); } } @@ -2461,11 +2466,16 @@ isert_free_np(struct iscsi_np *np) node) { isert_info("cleaning isert_conn %p state (%d)\n", isert_conn, isert_conn->state); - isert_connect_release(isert_conn); + list_move_tail(&isert_conn->node, &drop_conn_list); } } mutex_unlock(&isert_np->mutex); + list_for_each_entry_safe(isert_conn, n, &drop_conn_list, node) { + list_del_init(&isert_conn->node); + isert_connect_release(isert_conn); + } + np->np_context = NULL; kfree(isert_np); } @@ -2560,8 +2570,6 @@ static void isert_wait_conn(struct iscsit_conn *conn) isert_put_unsol_pending_cmds(conn); isert_wait4cmds(conn); isert_wait4logout(isert_conn); - - queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsit_conn *conn) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index edb2e3a25880..cfb50bfe53c3 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2040,6 +2040,7 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id, return 0; } +/* The caller should do the cleanup in case of error */ static int create_cm(struct rtrs_clt_con *con) { struct rtrs_path *s = con->c.path; @@ -2062,14 +2063,14 @@ static int create_cm(struct rtrs_clt_con *con) err = rdma_set_reuseaddr(cm_id, 1); if (err != 0) { rtrs_err(s, "Set address reuse failed, err: %d\n", err); - goto destroy_cm; + return err; } err = rdma_resolve_addr(cm_id, (struct sockaddr *)&clt_path->s.src_addr, (struct sockaddr *)&clt_path->s.dst_addr, RTRS_CONNECT_TIMEOUT_MS); if (err) { rtrs_err(s, "Failed to resolve address, err: %d\n", err); - goto destroy_cm; + return err; } /* * Combine connection status and session events. This is needed @@ -2084,29 +2085,15 @@ static int create_cm(struct rtrs_clt_con *con) if (err == 0) err = -ETIMEDOUT; /* Timedout or interrupted */ - goto errr; - } - if (con->cm_err < 0) { - err = con->cm_err; - goto errr; + return err; } - if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTING) { + if (con->cm_err < 0) + return con->cm_err; + if (READ_ONCE(clt_path->state) != RTRS_CLT_CONNECTING) /* Device removal */ - err = -ECONNABORTED; - goto errr; - } + return -ECONNABORTED; return 0; - -errr: - stop_cm(con); - mutex_lock(&con->con_mutex); - destroy_con_cq_qp(con); - mutex_unlock(&con->con_mutex); -destroy_cm: - destroy_cm(con); - - return err; } static void rtrs_clt_path_up(struct rtrs_clt_path *clt_path) @@ -2334,7 +2321,7 @@ static void rtrs_clt_close_work(struct work_struct *work) static int init_conns(struct rtrs_clt_path *clt_path) { unsigned int cid; - int err; + int err, i; /* * On every new session connections increase reconnect counter @@ -2350,10 +2337,8 @@ static int init_conns(struct rtrs_clt_path *clt_path) goto destroy; err = create_cm(to_clt_con(clt_path->s.con[cid])); - if (err) { - destroy_con(to_clt_con(clt_path->s.con[cid])); + if (err) goto destroy; - } } err = alloc_path_reqs(clt_path); if (err) @@ -2364,15 +2349,21 @@ static int init_conns(struct rtrs_clt_path *clt_path) return 0; destroy: - while (cid--) { - struct rtrs_clt_con *con = to_clt_con(clt_path->s.con[cid]); + /* Make sure we do the cleanup in the order they are created */ + for (i = 0; i <= cid; i++) { + struct rtrs_clt_con *con; - stop_cm(con); + if (!clt_path->s.con[i]) + break; - mutex_lock(&con->con_mutex); - destroy_con_cq_qp(con); - mutex_unlock(&con->con_mutex); - destroy_cm(con); + con = to_clt_con(clt_path->s.con[i]); + if (con->c.cm_id) { + stop_cm(con); + mutex_lock(&con->con_mutex); + destroy_con_cq_qp(con); + mutex_unlock(&con->con_mutex); + destroy_cm(con); + } destroy_con(con); } /* diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c index 4bf9d868cc52..3696f367ff51 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs.c @@ -37,8 +37,10 @@ struct rtrs_iu *rtrs_iu_alloc(u32 iu_num, size_t size, gfp_t gfp_mask, goto err; iu->dma_addr = ib_dma_map_single(dma_dev, iu->buf, size, dir); - if (ib_dma_mapping_error(dma_dev, iu->dma_addr)) + if (ib_dma_mapping_error(dma_dev, iu->dma_addr)) { + kfree(iu->buf); goto err; + } iu->cqe.done = done; iu->size = size; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index dc1ec6849775..e8a2e5984acb 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2078,10 +2078,6 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) int mode = DEFAULT_PGTABLE_LEVEL; int ret; - domain = kzalloc(sizeof(*domain), GFP_KERNEL); - if (!domain) - return NULL; - /* * Force IOMMU v1 page table when iommu=pt and * when allocating domain for pass-through devices. @@ -2097,6 +2093,10 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) return NULL; } + domain = kzalloc(sizeof(*domain), GFP_KERNEL); + if (!domain) + return NULL; + switch (pgtable) { case AMD_IOMMU_V1: ret = protection_domain_init_v1(domain, mode); diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c index 77ebe7e47e0e..e731e0784f7e 100644 --- a/drivers/irqchip/irq-clps711x.c +++ b/drivers/irqchip/irq-clps711x.c @@ -212,12 +212,6 @@ out_kfree: return err; } -void __init clps711x_intc_init(phys_addr_t base, resource_size_t size) -{ - BUG_ON(_clps711x_intc_init(NULL, base, size)); -} - -#ifdef CONFIG_IRQCHIP static int __init clps711x_intc_init_dt(struct device_node *np, struct device_node *parent) { @@ -231,4 +225,3 @@ static int __init clps711x_intc_init_dt(struct device_node *np, return _clps711x_intc_init(np, res.start, resource_size(&res)); } IRQCHIP_DECLARE(clps711x, "cirrus,ep7209-intc", clps711x_intc_init_dt); -#endif diff --git a/drivers/irqchip/irq-ftintc010.c b/drivers/irqchip/irq-ftintc010.c index 46a3aa60e50e..359efc1d1be7 100644 --- a/drivers/irqchip/irq-ftintc010.c +++ b/drivers/irqchip/irq-ftintc010.c @@ -125,7 +125,7 @@ static struct irq_chip ft010_irq_chip = { /* Local static for the IRQ entry call */ static struct ft010_irq_data firq; -asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs) +static asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs) { struct ft010_irq_data *f = &firq; int irq; @@ -162,7 +162,7 @@ static const struct irq_domain_ops ft010_irqdomain_ops = { .xlate = irq_domain_xlate_onetwocell, }; -int __init ft010_of_init_irq(struct device_node *node, +static int __init ft010_of_init_irq(struct device_node *node, struct device_node *parent) { struct ft010_irq_data *f = &firq; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0ec2b1e1df75..1994541eaef8 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3585,6 +3585,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, irqd = irq_get_irq_data(virq + i); irqd_set_single_target(irqd); irqd_set_affinity_on_activate(irqd); + irqd_set_resend_when_in_progress(irqd); pr_debug("ID:%d pID:%d vID:%d\n", (int)(hwirq + i - its_dev->event_map.lpi_base), (int)(hwirq + i), virq + i); @@ -4523,6 +4524,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq irq_domain_set_hwirq_and_chip(domain, virq + i, i, irqchip, vm->vpes[i]); set_bit(i, bitmap); + irqd_set_resend_when_in_progress(irq_get_irq_data(virq + i)); } if (err) { diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index a605aa79435a..0c6c1af9a5b7 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -40,6 +40,7 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) #define FLAGS_WORKAROUND_MTK_GICR_SAVE (1ULL << 2) +#define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 3) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -656,10 +657,16 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) return 0; } -static u64 gic_mpidr_to_affinity(unsigned long mpidr) +static u64 gic_cpu_to_affinity(int cpu) { + u64 mpidr = cpu_logical_map(cpu); u64 aff; + /* ASR8601 needs to have its affinities shifted down... */ + if (unlikely(gic_data.flags & FLAGS_WORKAROUND_ASR_ERRATUM_8601001)) + mpidr = (MPIDR_AFFINITY_LEVEL(mpidr, 1) | + (MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8)); + aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | @@ -914,7 +921,7 @@ static void __init gic_dist_init(void) * Set all global interrupts to the boot CPU only. ARE must be * enabled. */ - affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id())); + affinity = gic_cpu_to_affinity(smp_processor_id()); for (i = 32; i < GIC_LINE_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTER + i * 8); @@ -963,7 +970,7 @@ static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *)) static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) { - unsigned long mpidr = cpu_logical_map(smp_processor_id()); + unsigned long mpidr; u64 typer; u32 aff; @@ -971,6 +978,8 @@ static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) * Convert affinity to a 32bit value that can be matched to * GICR_TYPER bits [63:32]. */ + mpidr = gic_cpu_to_affinity(smp_processor_id()); + aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | @@ -1084,7 +1093,7 @@ static inline bool gic_dist_security_disabled(void) static void gic_cpu_sys_reg_init(void) { int i, cpu = smp_processor_id(); - u64 mpidr = cpu_logical_map(cpu); + u64 mpidr = gic_cpu_to_affinity(cpu); u64 need_rss = MPIDR_RS(mpidr); bool group0; u32 pribits; @@ -1183,11 +1192,11 @@ static void gic_cpu_sys_reg_init(void) for_each_online_cpu(i) { bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu); - need_rss |= MPIDR_RS(cpu_logical_map(i)); + need_rss |= MPIDR_RS(gic_cpu_to_affinity(i)); if (need_rss && (!have_rss)) pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n", cpu, (unsigned long)mpidr, - i, (unsigned long)cpu_logical_map(i)); + i, (unsigned long)gic_cpu_to_affinity(i)); } /** @@ -1263,9 +1272,11 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, unsigned long cluster_id) { int next_cpu, cpu = *base_cpu; - unsigned long mpidr = cpu_logical_map(cpu); + unsigned long mpidr; u16 tlist = 0; + mpidr = gic_cpu_to_affinity(cpu); + while (cpu < nr_cpu_ids) { tlist |= 1 << (mpidr & 0xf); @@ -1274,7 +1285,7 @@ static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, goto out; cpu = next_cpu; - mpidr = cpu_logical_map(cpu); + mpidr = gic_cpu_to_affinity(cpu); if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) { cpu--; @@ -1319,7 +1330,7 @@ static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) dsb(ishst); for_each_cpu(cpu, mask) { - u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(cpu_logical_map(cpu)); + u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(gic_cpu_to_affinity(cpu)); u16 tlist; tlist = gic_compute_target_list(&cpu, mask, cluster_id); @@ -1377,7 +1388,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, offset = convert_offset_index(d, GICD_IROUTER, &index); reg = gic_dist_base(d) + offset + (index * 8); - val = gic_mpidr_to_affinity(cpu_logical_map(cpu)); + val = gic_cpu_to_affinity(cpu); gic_write_irouter(val, reg); @@ -1796,6 +1807,15 @@ static bool gic_enable_quirk_nvidia_t241(void *data) return true; } +static bool gic_enable_quirk_asr8601(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_ASR_ERRATUM_8601001; + + return true; +} + static const struct gic_quirk gic_quirks[] = { { .desc = "GICv3: Qualcomm MSM8996 broken firmware", @@ -1803,6 +1823,11 @@ static const struct gic_quirk gic_quirks[] = { .init = gic_enable_quirk_msm8996, }, { + .desc = "GICv3: ASR erratum 8601001", + .compatible = "asr,asr8601-gic-v3", + .init = gic_enable_quirk_asr8601, + }, + { .desc = "GICv3: Mediatek Chromebook GICR save problem", .property = "mediatek,broken-save-restore-fw", .init = gic_enable_quirk_mtk_gicr, diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c index 5f47d8ee4ae3..b9dcc8e78c75 100644 --- a/drivers/irqchip/irq-jcore-aic.c +++ b/drivers/irqchip/irq-jcore-aic.c @@ -68,6 +68,7 @@ static int __init aic_irq_of_init(struct device_node *node, unsigned min_irq = JCORE_AIC2_MIN_HWIRQ; unsigned dom_sz = JCORE_AIC_MAX_HWIRQ+1; struct irq_domain *domain; + int ret; pr_info("Initializing J-Core AIC\n"); @@ -100,6 +101,12 @@ static int __init aic_irq_of_init(struct device_node *node, jcore_aic.irq_unmask = noop; jcore_aic.name = "AIC"; + ret = irq_alloc_descs(-1, min_irq, dom_sz - min_irq, + of_node_to_nid(node)); + + if (ret < 0) + return ret; + domain = irq_domain_add_legacy(node, dom_sz - min_irq, min_irq, min_irq, &jcore_aic_irqdomain_ops, &jcore_aic); diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 71ef19f77a5a..92d8aa28bdf5 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -36,6 +36,7 @@ static int nr_pics; struct eiointc_priv { u32 node; + u32 vec_count; nodemask_t node_map; cpumask_t cpuspan_map; struct fwnode_handle *domain_handle; @@ -153,18 +154,18 @@ static int eiointc_router_init(unsigned int cpu) if ((cpu_logical_map(cpu) % CORES_PER_EIO_NODE) == 0) { eiointc_enable(); - for (i = 0; i < VEC_COUNT / 32; i++) { + for (i = 0; i < eiointc_priv[0]->vec_count / 32; i++) { data = (((1 << (i * 2 + 1)) << 16) | (1 << (i * 2))); iocsr_write32(data, EIOINTC_REG_NODEMAP + i * 4); } - for (i = 0; i < VEC_COUNT / 32 / 4; i++) { + for (i = 0; i < eiointc_priv[0]->vec_count / 32 / 4; i++) { bit = BIT(1 + index); /* Route to IP[1 + index] */ data = bit | (bit << 8) | (bit << 16) | (bit << 24); iocsr_write32(data, EIOINTC_REG_IPMAP + i * 4); } - for (i = 0; i < VEC_COUNT / 4; i++) { + for (i = 0; i < eiointc_priv[0]->vec_count / 4; i++) { /* Route to Node-0 Core-0 */ if (index == 0) bit = BIT(cpu_logical_map(0)); @@ -175,7 +176,7 @@ static int eiointc_router_init(unsigned int cpu) iocsr_write32(data, EIOINTC_REG_ROUTE + i * 4); } - for (i = 0; i < VEC_COUNT / 32; i++) { + for (i = 0; i < eiointc_priv[0]->vec_count / 32; i++) { data = 0xffffffff; iocsr_write32(data, EIOINTC_REG_ENABLE + i * 4); iocsr_write32(data, EIOINTC_REG_BOUNCE + i * 4); @@ -195,7 +196,7 @@ static void eiointc_irq_dispatch(struct irq_desc *desc) chained_irq_enter(chip, desc); - for (i = 0; i < VEC_REG_COUNT; i++) { + for (i = 0; i < eiointc_priv[0]->vec_count / VEC_COUNT_PER_REG; i++) { pending = iocsr_read64(EIOINTC_REG_ISR + (i << 3)); iocsr_write64(pending, EIOINTC_REG_ISR + (i << 3)); while (pending) { @@ -310,11 +311,11 @@ static void eiointc_resume(void) eiointc_router_init(0); for (i = 0; i < nr_pics; i++) { - for (j = 0; j < VEC_COUNT; j++) { + for (j = 0; j < eiointc_priv[0]->vec_count; j++) { desc = irq_resolve_mapping(eiointc_priv[i]->eiointc_domain, j); if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) { raw_spin_lock(&desc->lock); - irq_data = &desc->irq_data; + irq_data = irq_domain_get_irq_data(eiointc_priv[i]->eiointc_domain, irq_desc_get_irq(desc)); eiointc_set_irq_affinity(irq_data, irq_data->common->affinity, 0); raw_spin_unlock(&desc->lock); } @@ -375,11 +376,47 @@ static int __init acpi_cascade_irqdomain_init(void) return 0; } +static int __init eiointc_init(struct eiointc_priv *priv, int parent_irq, + u64 node_map) +{ + int i; + + node_map = node_map ? node_map : -1ULL; + for_each_possible_cpu(i) { + if (node_map & (1ULL << (cpu_to_eio_node(i)))) { + node_set(cpu_to_eio_node(i), priv->node_map); + cpumask_or(&priv->cpuspan_map, &priv->cpuspan_map, + cpumask_of(i)); + } + } + + priv->eiointc_domain = irq_domain_create_linear(priv->domain_handle, + priv->vec_count, + &eiointc_domain_ops, + priv); + if (!priv->eiointc_domain) { + pr_err("loongson-extioi: cannot add IRQ domain\n"); + return -ENOMEM; + } + + eiointc_priv[nr_pics++] = priv; + eiointc_router_init(0); + irq_set_chained_handler_and_data(parent_irq, eiointc_irq_dispatch, priv); + + if (nr_pics == 1) { + register_syscore_ops(&eiointc_syscore_ops); + cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, + "irqchip/loongarch/intc:starting", + eiointc_router_init, NULL); + } + + return 0; +} + int __init eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc) { - int i, ret, parent_irq; - unsigned long node_map; + int parent_irq, ret; struct eiointc_priv *priv; int node; @@ -394,37 +431,14 @@ int __init eiointc_acpi_init(struct irq_domain *parent, goto out_free_priv; } + priv->vec_count = VEC_COUNT; priv->node = acpi_eiointc->node; - node_map = acpi_eiointc->node_map ? : -1ULL; - - for_each_possible_cpu(i) { - if (node_map & (1ULL << cpu_to_eio_node(i))) { - node_set(cpu_to_eio_node(i), priv->node_map); - cpumask_or(&priv->cpuspan_map, &priv->cpuspan_map, cpumask_of(i)); - } - } - - /* Setup IRQ domain */ - priv->eiointc_domain = irq_domain_create_linear(priv->domain_handle, VEC_COUNT, - &eiointc_domain_ops, priv); - if (!priv->eiointc_domain) { - pr_err("loongson-eiointc: cannot add IRQ domain\n"); - goto out_free_handle; - } - - eiointc_priv[nr_pics++] = priv; - - eiointc_router_init(0); parent_irq = irq_create_mapping(parent, acpi_eiointc->cascade); - irq_set_chained_handler_and_data(parent_irq, eiointc_irq_dispatch, priv); - if (nr_pics == 1) { - register_syscore_ops(&eiointc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, - "irqchip/loongarch/intc:starting", - eiointc_router_init, NULL); - } + ret = eiointc_init(priv, parent_irq, acpi_eiointc->node_map); + if (ret < 0) + goto out_free_handle; if (cpu_has_flatmode) node = cpu_to_node(acpi_eiointc->node * CORES_PER_EIO_NODE); @@ -432,7 +446,10 @@ int __init eiointc_acpi_init(struct irq_domain *parent, node = acpi_eiointc->node; acpi_set_vec_parent(node, priv->eiointc_domain, pch_group); acpi_set_vec_parent(node, priv->eiointc_domain, msi_group); + ret = acpi_cascade_irqdomain_init(); + if (ret < 0) + goto out_free_handle; return ret; @@ -444,3 +461,49 @@ out_free_priv: return -ENOMEM; } + +static int __init eiointc_of_init(struct device_node *of_node, + struct device_node *parent) +{ + int parent_irq, ret; + struct eiointc_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + parent_irq = irq_of_parse_and_map(of_node, 0); + if (parent_irq <= 0) { + ret = -ENODEV; + goto out_free_priv; + } + + ret = irq_set_handler_data(parent_irq, priv); + if (ret < 0) + goto out_free_priv; + + /* + * In particular, the number of devices supported by the LS2K0500 + * extended I/O interrupt vector is 128. + */ + if (of_device_is_compatible(of_node, "loongson,ls2k0500-eiointc")) + priv->vec_count = 128; + else + priv->vec_count = VEC_COUNT; + + priv->node = 0; + priv->domain_handle = of_node_to_fwnode(of_node); + + ret = eiointc_init(priv, parent_irq, 0); + if (ret < 0) + goto out_free_priv; + + return 0; + +out_free_priv: + kfree(priv); + return ret; +} + +IRQCHIP_DECLARE(loongson_ls2k0500_eiointc, "loongson,ls2k0500-eiointc", eiointc_of_init); +IRQCHIP_DECLARE(loongson_ls2k2000_eiointc, "loongson,ls2k2000-eiointc", eiointc_of_init); diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 8d00a9ad5b00..e4b33aed1c97 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -32,6 +32,10 @@ #define LIOINTC_REG_INTC_EN_STATUS (LIOINTC_INTC_CHIP_START + 0x04) #define LIOINTC_REG_INTC_ENABLE (LIOINTC_INTC_CHIP_START + 0x08) #define LIOINTC_REG_INTC_DISABLE (LIOINTC_INTC_CHIP_START + 0x0c) +/* + * LIOINTC_REG_INTC_POL register is only valid for Loongson-2K series, and + * Loongson-3 series behave as noops. + */ #define LIOINTC_REG_INTC_POL (LIOINTC_INTC_CHIP_START + 0x10) #define LIOINTC_REG_INTC_EDGE (LIOINTC_INTC_CHIP_START + 0x14) @@ -116,19 +120,19 @@ static int liointc_set_type(struct irq_data *data, unsigned int type) switch (type) { case IRQ_TYPE_LEVEL_HIGH: liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, false); - liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true); + liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false); break; case IRQ_TYPE_LEVEL_LOW: liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, false); - liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false); + liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true); break; case IRQ_TYPE_EDGE_RISING: liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, true); - liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true); + liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false); break; case IRQ_TYPE_EDGE_FALLING: liointc_set_bit(gc, LIOINTC_REG_INTC_EDGE, mask, true); - liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, false); + liointc_set_bit(gc, LIOINTC_REG_INTC_POL, mask, true); break; default: irq_gc_unlock_irqrestore(gc, flags); @@ -291,6 +295,7 @@ static int liointc_init(phys_addr_t addr, unsigned long size, int revision, ct->chip.irq_mask = irq_gc_mask_disable_reg; ct->chip.irq_mask_ack = irq_gc_mask_disable_reg; ct->chip.irq_set_type = liointc_set_type; + ct->chip.flags = IRQCHIP_SKIP_SET_WAKE; gc->mask_cache = 0; priv->gc = gc; diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index e5fe4d50be05..93a71f66efeb 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -164,7 +164,7 @@ static int pch_pic_domain_translate(struct irq_domain *d, if (fwspec->param_count < 2) return -EINVAL; - *hwirq = fwspec->param[0] + priv->ht_vec_base; + *hwirq = fwspec->param[0]; *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; } else { if (fwspec->param_count < 1) @@ -196,7 +196,7 @@ static int pch_pic_alloc(struct irq_domain *domain, unsigned int virq, parent_fwspec.fwnode = domain->parent->fwnode; parent_fwspec.param_count = 1; - parent_fwspec.param[0] = hwirq; + parent_fwspec.param[0] = hwirq + priv->ht_vec_base; err = irq_domain_alloc_irqs_parent(domain, virq, 1, &parent_fwspec); if (err) @@ -401,14 +401,12 @@ static int __init acpi_cascade_irqdomain_init(void) int __init pch_pic_acpi_init(struct irq_domain *parent, struct acpi_madt_bio_pic *acpi_pchpic) { - int ret, vec_base; + int ret; struct fwnode_handle *domain_handle; if (find_pch_pic(acpi_pchpic->gsi_base) >= 0) return 0; - vec_base = acpi_pchpic->gsi_base - GSI_MIN_PCH_IRQ; - domain_handle = irq_domain_alloc_fwnode(&acpi_pchpic->address); if (!domain_handle) { pr_err("Unable to allocate domain handle\n"); @@ -416,7 +414,7 @@ int __init pch_pic_acpi_init(struct irq_domain *parent, } ret = pch_pic_init(acpi_pchpic->address, acpi_pchpic->size, - vec_base, parent, domain_handle, acpi_pchpic->gsi_base); + 0, parent, domain_handle, acpi_pchpic->gsi_base); if (ret < 0) { irq_domain_free_fwnode(domain_handle); diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 83455ca72439..25cf4f80e767 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -244,132 +244,6 @@ static void __exception_irq_entry mmp2_handle_irq(struct pt_regs *regs) generic_handle_domain_irq(icu_data[0].domain, hwirq); } -/* MMP (ARMv5) */ -void __init icu_init_irq(void) -{ - int irq; - - max_icu_nr = 1; - mmp_icu_base = ioremap(0xd4282000, 0x1000); - icu_data[0].conf_enable = mmp_conf.conf_enable; - icu_data[0].conf_disable = mmp_conf.conf_disable; - icu_data[0].conf_mask = mmp_conf.conf_mask; - icu_data[0].nr_irqs = 64; - icu_data[0].virq_base = 0; - icu_data[0].domain = irq_domain_add_legacy(NULL, 64, 0, 0, - &irq_domain_simple_ops, - &icu_data[0]); - for (irq = 0; irq < 64; irq++) { - icu_mask_irq(irq_get_irq_data(irq)); - irq_set_chip_and_handler(irq, &icu_irq_chip, handle_level_irq); - } - irq_set_default_host(icu_data[0].domain); - set_handle_irq(mmp_handle_irq); -} - -/* MMP2 (ARMv7) */ -void __init mmp2_init_icu(void) -{ - int irq, end; - - max_icu_nr = 8; - mmp_icu_base = ioremap(0xd4282000, 0x1000); - icu_data[0].conf_enable = mmp2_conf.conf_enable; - icu_data[0].conf_disable = mmp2_conf.conf_disable; - icu_data[0].conf_mask = mmp2_conf.conf_mask; - icu_data[0].nr_irqs = 64; - icu_data[0].virq_base = 0; - icu_data[0].domain = irq_domain_add_legacy(NULL, 64, 0, 0, - &irq_domain_simple_ops, - &icu_data[0]); - icu_data[1].reg_status = mmp_icu_base + 0x150; - icu_data[1].reg_mask = mmp_icu_base + 0x168; - icu_data[1].clr_mfp_irq_base = icu_data[0].virq_base + - icu_data[0].nr_irqs; - icu_data[1].clr_mfp_hwirq = 1; /* offset to IRQ_MMP2_PMIC_BASE */ - icu_data[1].nr_irqs = 2; - icu_data[1].cascade_irq = 4; - icu_data[1].virq_base = icu_data[0].virq_base + icu_data[0].nr_irqs; - icu_data[1].domain = irq_domain_add_legacy(NULL, icu_data[1].nr_irqs, - icu_data[1].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[1]); - icu_data[2].reg_status = mmp_icu_base + 0x154; - icu_data[2].reg_mask = mmp_icu_base + 0x16c; - icu_data[2].nr_irqs = 2; - icu_data[2].cascade_irq = 5; - icu_data[2].virq_base = icu_data[1].virq_base + icu_data[1].nr_irqs; - icu_data[2].domain = irq_domain_add_legacy(NULL, icu_data[2].nr_irqs, - icu_data[2].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[2]); - icu_data[3].reg_status = mmp_icu_base + 0x180; - icu_data[3].reg_mask = mmp_icu_base + 0x17c; - icu_data[3].nr_irqs = 3; - icu_data[3].cascade_irq = 9; - icu_data[3].virq_base = icu_data[2].virq_base + icu_data[2].nr_irqs; - icu_data[3].domain = irq_domain_add_legacy(NULL, icu_data[3].nr_irqs, - icu_data[3].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[3]); - icu_data[4].reg_status = mmp_icu_base + 0x158; - icu_data[4].reg_mask = mmp_icu_base + 0x170; - icu_data[4].nr_irqs = 5; - icu_data[4].cascade_irq = 17; - icu_data[4].virq_base = icu_data[3].virq_base + icu_data[3].nr_irqs; - icu_data[4].domain = irq_domain_add_legacy(NULL, icu_data[4].nr_irqs, - icu_data[4].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[4]); - icu_data[5].reg_status = mmp_icu_base + 0x15c; - icu_data[5].reg_mask = mmp_icu_base + 0x174; - icu_data[5].nr_irqs = 15; - icu_data[5].cascade_irq = 35; - icu_data[5].virq_base = icu_data[4].virq_base + icu_data[4].nr_irqs; - icu_data[5].domain = irq_domain_add_legacy(NULL, icu_data[5].nr_irqs, - icu_data[5].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[5]); - icu_data[6].reg_status = mmp_icu_base + 0x160; - icu_data[6].reg_mask = mmp_icu_base + 0x178; - icu_data[6].nr_irqs = 2; - icu_data[6].cascade_irq = 51; - icu_data[6].virq_base = icu_data[5].virq_base + icu_data[5].nr_irqs; - icu_data[6].domain = irq_domain_add_legacy(NULL, icu_data[6].nr_irqs, - icu_data[6].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[6]); - icu_data[7].reg_status = mmp_icu_base + 0x188; - icu_data[7].reg_mask = mmp_icu_base + 0x184; - icu_data[7].nr_irqs = 2; - icu_data[7].cascade_irq = 55; - icu_data[7].virq_base = icu_data[6].virq_base + icu_data[6].nr_irqs; - icu_data[7].domain = irq_domain_add_legacy(NULL, icu_data[7].nr_irqs, - icu_data[7].virq_base, 0, - &irq_domain_simple_ops, - &icu_data[7]); - end = icu_data[7].virq_base + icu_data[7].nr_irqs; - for (irq = 0; irq < end; irq++) { - icu_mask_irq(irq_get_irq_data(irq)); - if (irq == icu_data[1].cascade_irq || - irq == icu_data[2].cascade_irq || - irq == icu_data[3].cascade_irq || - irq == icu_data[4].cascade_irq || - irq == icu_data[5].cascade_irq || - irq == icu_data[6].cascade_irq || - irq == icu_data[7].cascade_irq) { - irq_set_chip(irq, &icu_irq_chip); - irq_set_chained_handler(irq, icu_mux_irq_demux); - } else { - irq_set_chip_and_handler(irq, &icu_irq_chip, - handle_level_irq); - } - } - irq_set_default_host(icu_data[0].domain); - set_handle_irq(mmp2_handle_irq); -} - -#ifdef CONFIG_OF static int __init mmp_init_bases(struct device_node *node) { int ret, nr_irqs, irq, i = 0; @@ -548,4 +422,3 @@ err: return -EINVAL; } IRQCHIP_DECLARE(mmp2_mux_intc, "mrvl,mmp2-mux-intc", mmp2_mux_of_init); -#endif diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 6a3f7498ea8e..b5fa76ce5046 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -173,6 +173,16 @@ static struct irq_chip stm32_exti_h_chip_direct; #define EXTI_INVALID_IRQ U8_MAX #define STM32MP1_DESC_IRQ_SIZE (ARRAY_SIZE(stm32mp1_exti_banks) * IRQS_PER_BANK) +/* + * Use some intentionally tricky logic here to initialize the whole array to + * EXTI_INVALID_IRQ, but then override certain fields, requiring us to indicate + * that we "know" that there are overrides in this structure, and we'll need to + * disable that warning from W=1 builds. + */ +__diag_push(); +__diag_ignore_all("-Woverride-init", + "logic to initialize all and then override some is OK"); + static const u8 stm32mp1_desc_irq[] = { /* default value */ [0 ... (STM32MP1_DESC_IRQ_SIZE - 1)] = EXTI_INVALID_IRQ, @@ -208,6 +218,7 @@ static const u8 stm32mp1_desc_irq[] = { [31] = 53, [32] = 82, [33] = 83, + [46] = 151, [47] = 93, [48] = 138, [50] = 139, @@ -266,6 +277,8 @@ static const u8 stm32mp13_desc_irq[] = { [70] = 98, }; +__diag_pop(); + static const struct stm32_exti_drv_data stm32mp1_drv_data = { .exti_banks = stm32mp1_exti_banks, .bank_nr = ARRAY_SIZE(stm32mp1_exti_banks), diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index aebb7ef10e63..5a79bb3c272f 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -275,7 +275,7 @@ struct bcache_device { int (*cache_miss)(struct btree *b, struct search *s, struct bio *bio, unsigned int sectors); - int (*ioctl)(struct bcache_device *d, fmode_t mode, + int (*ioctl)(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg); }; @@ -1004,11 +1004,11 @@ extern struct workqueue_struct *bch_flush_wq; extern struct mutex bch_register_lock; extern struct list_head bch_cache_sets; -extern struct kobj_type bch_cached_dev_ktype; -extern struct kobj_type bch_flash_dev_ktype; -extern struct kobj_type bch_cache_set_ktype; -extern struct kobj_type bch_cache_set_internal_ktype; -extern struct kobj_type bch_cache_ktype; +extern const struct kobj_type bch_cached_dev_ktype; +extern const struct kobj_type bch_flash_dev_ktype; +extern const struct kobj_type bch_cache_set_ktype; +extern const struct kobj_type bch_cache_set_internal_ktype; +extern const struct kobj_type bch_cache_ktype; void bch_cached_dev_release(struct kobject *kobj); void bch_flash_dev_release(struct kobject *kobj); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 147c493a989a..68b9d7ca864e 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -885,7 +885,7 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, * cannibalize_bucket() will take. This means every time we unlock the root of * the btree, we need to release this lock if we have it held. */ -static void bch_cannibalize_unlock(struct cache_set *c) +void bch_cannibalize_unlock(struct cache_set *c) { spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { @@ -1090,10 +1090,12 @@ struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op, struct btree *parent) { BKEY_PADDED(key) k; - struct btree *b = ERR_PTR(-EAGAIN); + struct btree *b; mutex_lock(&c->bucket_lock); retry: + /* return ERR_PTR(-EAGAIN) when it fails */ + b = ERR_PTR(-EAGAIN); if (__bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, wait)) goto err; @@ -1138,7 +1140,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b, { struct btree *n = bch_btree_node_alloc(b->c, op, b->level, b->parent); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { mutex_lock(&n->write_lock); bch_btree_sort_into(&b->keys, &n->keys, &b->c->sort); bkey_copy_key(&n->key, &b->key); @@ -1340,7 +1342,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, memset(new_nodes, 0, sizeof(new_nodes)); closure_init_stack(&cl); - while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b)) + while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b)) keys += r[nodes++].keys; blocks = btree_default_blocks(b->c) * 2 / 3; @@ -1352,7 +1354,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, for (i = 0; i < nodes; i++) { new_nodes[i] = btree_node_alloc_replacement(r[i].b, NULL); - if (IS_ERR_OR_NULL(new_nodes[i])) + if (IS_ERR(new_nodes[i])) goto out_nocoalesce; } @@ -1487,7 +1489,7 @@ out_nocoalesce: bch_keylist_free(&keylist); for (i = 0; i < nodes; i++) - if (!IS_ERR_OR_NULL(new_nodes[i])) { + if (!IS_ERR(new_nodes[i])) { btree_node_free(new_nodes[i]); rw_unlock(true, new_nodes[i]); } @@ -1669,7 +1671,7 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op, if (should_rewrite) { n = btree_node_alloc_replacement(b, NULL); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { bch_btree_node_write_sync(n); bch_btree_set_root(n); @@ -1968,6 +1970,15 @@ static int bch_btree_check_thread(void *arg) c->gc_stats.nodes++; bch_btree_op_init(&op, 0); ret = bcache_btree(check_recurse, p, c->root, &op); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op)->wait); if (ret) goto out; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 1b5fdbc0d83e..a2920bbfcad5 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -282,6 +282,7 @@ void bch_initial_gc_finish(struct cache_set *c); void bch_moving_gc(struct cache_set *c); int bch_btree_check(struct cache_set *c); void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k); +void bch_cannibalize_unlock(struct cache_set *c); static inline void wake_up_gc(struct cache_set *c) { diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 67a2e29e0b40..a9b1f3896249 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1228,7 +1228,7 @@ void cached_dev_submit_bio(struct bio *bio) detached_dev_do_request(d, bio, orig_bdev, start_time); } -static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, +static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct cached_dev *dc = container_of(d, struct cached_dev, disk); @@ -1318,7 +1318,7 @@ void flash_dev_submit_bio(struct bio *bio) continue_at(cl, search_free, NULL); } -static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, +static int flash_dev_ioctl(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index bd3afc856d53..21b445f8af15 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -18,7 +18,6 @@ struct cache_stats { unsigned long cache_misses; unsigned long cache_bypass_hits; unsigned long cache_bypass_misses; - unsigned long cache_readaheads; unsigned long cache_miss_collisions; unsigned long sectors_bypassed; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 7e9d19fd21dd..e2a803683105 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -732,9 +732,9 @@ out: /* Bcache device */ -static int open_dev(struct block_device *b, fmode_t mode) +static int open_dev(struct gendisk *disk, blk_mode_t mode) { - struct bcache_device *d = b->bd_disk->private_data; + struct bcache_device *d = disk->private_data; if (test_bit(BCACHE_DEV_CLOSING, &d->flags)) return -ENXIO; @@ -743,14 +743,14 @@ static int open_dev(struct block_device *b, fmode_t mode) return 0; } -static void release_dev(struct gendisk *b, fmode_t mode) +static void release_dev(struct gendisk *b) { struct bcache_device *d = b->private_data; closure_put(&d->cl); } -static int ioctl_dev(struct block_device *b, fmode_t mode, +static int ioctl_dev(struct block_device *b, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct bcache_device *d = b->bd_disk->private_data; @@ -1369,7 +1369,7 @@ static void cached_dev_free(struct closure *cl) put_page(virt_to_page(dc->sb_disk)); if (!IS_ERR_OR_NULL(dc->bdev)) - blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(dc->bdev, bcache_kobj); wake_up(&unregister_wait); @@ -1723,7 +1723,7 @@ static void cache_set_flush(struct closure *cl) if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread); - if (!IS_ERR_OR_NULL(c->root)) + if (!IS_ERR(c->root)) list_add(&c->root->list, &c->btree_cache); /* @@ -2087,7 +2087,7 @@ static int run_cache_set(struct cache_set *c) err = "cannot allocate new btree root"; c->root = __bch_btree_node_alloc(c, NULL, 0, true, NULL); - if (IS_ERR_OR_NULL(c->root)) + if (IS_ERR(c->root)) goto err; mutex_lock(&c->root->write_lock); @@ -2218,7 +2218,7 @@ void bch_cache_release(struct kobject *kobj) put_page(virt_to_page(ca->sb_disk)); if (!IS_ERR_OR_NULL(ca->bdev)) - blkdev_put(ca->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(ca->bdev, bcache_kobj); kfree(ca); module_put(THIS_MODULE); @@ -2359,7 +2359,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, * call blkdev_put() to bdev in bch_cache_release(). So we * explicitly call blkdev_put() here. */ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, bcache_kobj); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; else if (ret == -EPERM) @@ -2461,7 +2461,7 @@ static void register_bdev_worker(struct work_struct *work) if (!dc) { fail = true; put_page(virt_to_page(args->sb_disk)); - blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(args->bdev, bcache_kobj); goto out; } @@ -2491,7 +2491,7 @@ static void register_cache_worker(struct work_struct *work) if (!ca) { fail = true; put_page(virt_to_page(args->sb_disk)); - blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(args->bdev, bcache_kobj); goto out; } @@ -2558,9 +2558,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, ret = -EINVAL; err = "failed to open device"; - bdev = blkdev_get_by_path(strim(path), - FMODE_READ|FMODE_WRITE|FMODE_EXCL, - sb); + bdev = blkdev_get_by_path(strim(path), BLK_OPEN_READ | BLK_OPEN_WRITE, + bcache_kobj, NULL); if (IS_ERR(bdev)) { if (bdev == ERR_PTR(-EBUSY)) { dev_t dev; @@ -2648,7 +2647,7 @@ async_done: out_put_sb_page: put_page(virt_to_page(sb_disk)); out_blkdev_put: - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, register_bcache); out_free_sb: kfree(sb); out_free_path: diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index c6f677059214..0e2c1880f60b 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1111,26 +1111,25 @@ SHOW(__bch_cache) vfree(p); - ret = scnprintf(buf, PAGE_SIZE, - "Unused: %zu%%\n" - "Clean: %zu%%\n" - "Dirty: %zu%%\n" - "Metadata: %zu%%\n" - "Average: %llu\n" - "Sectors per Q: %zu\n" - "Quantiles: [", - unused * 100 / (size_t) ca->sb.nbuckets, - available * 100 / (size_t) ca->sb.nbuckets, - dirty * 100 / (size_t) ca->sb.nbuckets, - meta * 100 / (size_t) ca->sb.nbuckets, sum, - n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1)); + ret = sysfs_emit(buf, + "Unused: %zu%%\n" + "Clean: %zu%%\n" + "Dirty: %zu%%\n" + "Metadata: %zu%%\n" + "Average: %llu\n" + "Sectors per Q: %zu\n" + "Quantiles: [", + unused * 100 / (size_t) ca->sb.nbuckets, + available * 100 / (size_t) ca->sb.nbuckets, + dirty * 100 / (size_t) ca->sb.nbuckets, + meta * 100 / (size_t) ca->sb.nbuckets, sum, + n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1)); for (i = 0; i < ARRAY_SIZE(q); i++) - ret += scnprintf(buf + ret, PAGE_SIZE - ret, - "%u ", q[i]); + ret += sysfs_emit_at(buf, ret, "%u ", q[i]); ret--; - ret += scnprintf(buf + ret, PAGE_SIZE - ret, "]\n"); + ret += sysfs_emit_at(buf, ret, "]\n"); return ret; } diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index a2ff6447b699..65b8bd975ab1 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -3,7 +3,7 @@ #define _BCACHE_SYSFS_H_ #define KTYPE(type) \ -struct kobj_type type ## _ktype = { \ +const struct kobj_type type ## _ktype = { \ .release = type ## _release, \ .sysfs_ops = &((const struct sysfs_ops) { \ .show = type ## _show, \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d4a5fc0650bb..24c049067f61 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -890,6 +890,16 @@ static int bch_root_node_dirty_init(struct cache_set *c, if (ret < 0) pr_warn("sectors dirty init failed, ret=%d!\n", ret); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op.op)->wait); + return ret; } diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 9e0c69958587..acffed750e3e 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs cmd root_lock). - * - must take shrinker_mutex without holding cmd->root_lock + * - must take shrinker_rwsem without holding cmd->root_lock */ new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 872896218550..911f73f7ebba 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2051,8 +2051,8 @@ static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->metadata_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->metadata_dev); if (r) { *error = "Error opening metadata device"; return r; @@ -2074,8 +2074,8 @@ static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->cache_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->cache_dev); if (r) { *error = "Error opening cache device"; return r; @@ -2093,8 +2093,8 @@ static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->origin_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->origin_dev); if (r) { *error = "Error opening origin device"; return r; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index f467cdb5a022..94b2fc33f64b 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1683,8 +1683,8 @@ static int parse_metadata_dev(struct clone *clone, struct dm_arg_set *as, char * int r; sector_t metadata_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &clone->metadata_dev); + r = dm_get_device(clone->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->metadata_dev); if (r) { *error = "Error opening metadata device"; return r; @@ -1703,8 +1703,8 @@ static int parse_dest_dev(struct clone *clone, struct dm_arg_set *as, char **err int r; sector_t dest_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &clone->dest_dev); + r = dm_get_device(clone->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->dest_dev); if (r) { *error = "Error opening destination device"; return r; @@ -1725,7 +1725,7 @@ static int parse_source_dev(struct clone *clone, struct dm_arg_set *as, char **e int r; sector_t source_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ, + r = dm_get_device(clone->ti, dm_shift_arg(as), BLK_OPEN_READ, &clone->source_dev); if (r) { *error = "Error opening source device"; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index aecab0c0720f..ce913ad91a52 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -207,11 +207,10 @@ struct dm_table { unsigned integrity_added:1; /* - * Indicates the rw permissions for the new logical - * device. This should be a combination of FMODE_READ - * and FMODE_WRITE. + * Indicates the rw permissions for the new logical device. This + * should be a combination of BLK_OPEN_READ and BLK_OPEN_WRITE. */ - fmode_t mode; + blk_mode_t mode; /* a list of devices used by this table */ struct list_head devices; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 8b47b913ee83..09e37ebf7cc8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1693,8 +1693,7 @@ retry: len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size; - bio_add_page(clone, page, len, 0); - + __bio_add_page(clone, page, len, 0); remaining_size -= len; } diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 0d70914217ee..6acfa5bf97a4 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1482,14 +1482,16 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) era->ti = ti; - r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &era->metadata_dev); + r = dm_get_device(ti, argv[0], BLK_OPEN_READ | BLK_OPEN_WRITE, + &era->metadata_dev); if (r) { ti->error = "Error opening metadata device"; era_destroy(era); return -EINVAL; } - r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &era->origin_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, + &era->origin_dev); if (r) { ti->error = "Error opening data device"; era_destroy(era); diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index d369457dbed0..2a71bcdba92d 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -293,8 +293,10 @@ static int __init dm_init_init(void) for (i = 0; i < ARRAY_SIZE(waitfor); i++) { if (waitfor[i]) { + dev_t dev; + DMINFO("waiting for device %s ...", waitfor[i]); - while (!dm_get_dev_t(waitfor[i])) + while (early_lookup_bdev(waitfor[i], &dev)) fsleep(5000); } } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index cc77cf3d4109..6d301019e5e3 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -861,7 +861,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param) table = dm_get_inactive_table(md, &srcu_idx); if (table) { - if (!(dm_table_get_mode(table) & FMODE_WRITE)) + if (!(dm_table_get_mode(table) & BLK_OPEN_WRITE)) param->flags |= DM_READONLY_FLAG; param->target_count = table->num_targets; } @@ -1168,13 +1168,10 @@ static int do_resume(struct dm_ioctl *param) /* Do we need to load a new map ? */ if (new_map) { sector_t old_size, new_size; - int srcu_idx; /* Suspend if it isn't already suspended */ - old_map = dm_get_live_table(md, &srcu_idx); - if ((param->flags & DM_SKIP_LOCKFS_FLAG) || !old_map) + if (param->flags & DM_SKIP_LOCKFS_FLAG) suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; - dm_put_live_table(md, srcu_idx); if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; if (!dm_suspended_md(md)) @@ -1192,7 +1189,7 @@ static int do_resume(struct dm_ioctl *param) if (old_size && new_size && old_size != new_size) need_resize_uevent = true; - if (dm_table_get_mode(new_map) & FMODE_WRITE) + if (dm_table_get_mode(new_map) & BLK_OPEN_WRITE) set_disk_ro(dm_disk(md), 0); else set_disk_ro(dm_disk(md), 1); @@ -1381,12 +1378,12 @@ static int dev_arm_poll(struct file *filp, struct dm_ioctl *param, size_t param_ return 0; } -static inline fmode_t get_mode(struct dm_ioctl *param) +static inline blk_mode_t get_mode(struct dm_ioctl *param) { - fmode_t mode = FMODE_READ | FMODE_WRITE; + blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; if (param->flags & DM_READONLY_FLAG) - mode = FMODE_READ; + mode = BLK_OPEN_READ; return mode; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c8821fcb8299..8846bf510a35 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3750,11 +3750,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, * canceling read-auto mode */ mddev->ro = 0; - if (!mddev->suspended && mddev->sync_thread) + if (!mddev->suspended) md_wakeup_thread(mddev->sync_thread); } set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (!mddev->suspended && mddev->thread) + if (!mddev->suspended) md_wakeup_thread(mddev->thread); return 0; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 9c49f53760d0..bf7a574499a3 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1241,9 +1241,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) int i; int r = -EINVAL; char *origin_path, *cow_path; - dev_t origin_dev, cow_dev; unsigned int args_used, num_flush_bios = 1; - fmode_t origin_mode = FMODE_READ; + blk_mode_t origin_mode = BLK_OPEN_READ; if (argc < 4) { ti->error = "requires 4 or more arguments"; @@ -1253,7 +1252,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (dm_target_is_snapshot_merge(ti)) { num_flush_bios = 2; - origin_mode = FMODE_WRITE; + origin_mode = BLK_OPEN_WRITE; } s = kzalloc(sizeof(*s), GFP_KERNEL); @@ -1279,24 +1278,21 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Cannot get origin device"; goto bad_origin; } - origin_dev = s->origin->bdev->bd_dev; cow_path = argv[0]; argv++; argc--; - cow_dev = dm_get_dev_t(cow_path); - if (cow_dev && cow_dev == origin_dev) { - ti->error = "COW device cannot be the same as origin device"; - r = -EINVAL; - goto bad_cow; - } - r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow); if (r) { ti->error = "Cannot get COW device"; goto bad_cow; } + if (s->cow->bdev && s->cow->bdev == s->origin->bdev) { + ti->error = "COW device cannot be the same as origin device"; + r = -EINVAL; + goto bad_store; + } r = dm_exception_store_create(ti, argc, argv, s, &args_used, &s->store); if (r) { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 1398f1d6e83e..7d208b2b1a19 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -126,7 +126,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num) return 0; } -int dm_table_create(struct dm_table **result, fmode_t mode, +int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md) { struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); @@ -304,7 +304,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * device and not to touch the existing bdev field in case * it is accessed concurrently. */ -static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, +static int upgrade_mode(struct dm_dev_internal *dd, blk_mode_t new_mode, struct mapped_device *md) { int r; @@ -324,23 +324,13 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, } /* - * Convert the path to a device - */ -dev_t dm_get_dev_t(const char *path) -{ - dev_t dev; - - if (lookup_bdev(path, &dev)) - dev = name_to_dev_t(path); - return dev; -} -EXPORT_SYMBOL_GPL(dm_get_dev_t); - -/* * Add a device to the list, or just increment the usage count if * it's already present. + * + * Note: the __ref annotation is because this function can call the __init + * marked early_lookup_bdev when called during early boot code from dm-init.c. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, +int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, struct dm_dev **result) { int r; @@ -358,9 +348,13 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, if (MAJOR(dev) != major || MINOR(dev) != minor) return -EOVERFLOW; } else { - dev = dm_get_dev_t(path); - if (!dev) - return -ENODEV; + r = lookup_bdev(path, &dev); +#ifndef MODULE + if (r && system_state < SYSTEM_RUNNING) + r = early_lookup_bdev(path, &dev); +#endif + if (r) + return r; } if (dev == disk_devt(t->md->disk)) return -EINVAL; @@ -668,7 +662,8 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->singleton = true; } - if (dm_target_always_writeable(ti->type) && !(t->mode & FMODE_WRITE)) { + if (dm_target_always_writeable(ti->type) && + !(t->mode & BLK_OPEN_WRITE)) { ti->error = "target type may not be included in a read-only table"; goto bad; } @@ -2039,7 +2034,7 @@ struct list_head *dm_table_get_devices(struct dm_table *t) return &t->devices; } -fmode_t dm_table_get_mode(struct dm_table *t) +blk_mode_t dm_table_get_mode(struct dm_table *t) { return t->mode; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 9f5cb52c5763..9dd0409848ab 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1756,13 +1756,15 @@ int dm_thin_remove_range(struct dm_thin_device *td, int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *result) { - int r; + int r = -EINVAL; uint32_t ref_count; down_read(&pmd->root_lock); - r = dm_sm_get_count(pmd->data_sm, b, &ref_count); - if (!r) - *result = (ref_count > 1); + if (!pmd->fail_io) { + r = dm_sm_get_count(pmd->data_sm, b, &ref_count); + if (!r) + *result = (ref_count > 1); + } up_read(&pmd->root_lock); return r; @@ -1770,10 +1772,11 @@ int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *re int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e) { - int r = 0; + int r = -EINVAL; pmd_write_lock(pmd); - r = dm_sm_inc_blocks(pmd->data_sm, b, e); + if (!pmd->fail_io) + r = dm_sm_inc_blocks(pmd->data_sm, b, e); pmd_write_unlock(pmd); return r; @@ -1781,10 +1784,11 @@ int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_ int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e) { - int r = 0; + int r = -EINVAL; pmd_write_lock(pmd); - r = dm_sm_dec_blocks(pmd->data_sm, b, e); + if (!pmd->fail_io) + r = dm_sm_dec_blocks(pmd->data_sm, b, e); pmd_write_unlock(pmd); return r; @@ -1887,7 +1891,7 @@ int dm_pool_abort_metadata(struct dm_pool_metadata *pmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs pmd root_lock). - * - must take shrinker_mutex without holding pmd->root_lock + * - must take shrinker_rwsem without holding pmd->root_lock */ new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, THIN_MAX_CONCURRENT_LOCKS); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 2b13c949bd72..f1d0dcb9db22 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -401,8 +401,7 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da sector_t s = block_to_sectors(tc->pool, data_b); sector_t len = block_to_sectors(tc->pool, data_e - data_b); - return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOWAIT, - &op->bio); + return __blkdev_issue_discard(tc->pool_dev->bdev, s, len, GFP_NOIO, &op->bio); } static void end_discard(struct discard_op *op, int r) @@ -3301,7 +3300,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) unsigned long block_size; dm_block_t low_water_blocks; struct dm_dev *metadata_dev; - fmode_t metadata_mode; + blk_mode_t metadata_mode; /* * FIXME Remove validation from scope of lock. @@ -3334,7 +3333,8 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto out_unlock; - metadata_mode = FMODE_READ | ((pf.mode == PM_READ_ONLY) ? 0 : FMODE_WRITE); + metadata_mode = BLK_OPEN_READ | + ((pf.mode == PM_READ_ONLY) ? 0 : BLK_OPEN_WRITE); r = dm_get_device(ti, argv[0], metadata_mode, &metadata_dev); if (r) { ti->error = "Error opening metadata block device"; @@ -3342,7 +3342,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) } warn_if_metadata_device_too_big(metadata_dev->bdev); - r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, &data_dev); if (r) { ti->error = "Error getting data device"; goto out_metadata; @@ -4223,7 +4223,7 @@ static int thin_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_origin_dev; } - r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev); + r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &origin_dev); if (r) { ti->error = "Error opening origin device"; goto bad_origin_dev; diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index a9ee2faa75a2..3ef9f018da60 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -607,7 +607,7 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, (*argc)--; if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { - r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev); if (r) { ti->error = "FEC device lookup failed"; return r; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index e35c16e06d06..26adcfea0302 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1196,7 +1196,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto bad; - if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { + if ((dm_table_get_mode(ti->table) & ~BLK_OPEN_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; goto bad; @@ -1225,13 +1225,13 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) } v->version = num; - r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ, &v->data_dev); if (r) { ti->error = "Data device lookup failed"; goto bad; } - r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev); + r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &v->hash_dev); if (r) { ti->error = "Hash device lookup failed"; goto bad; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 8f0896a6990b..9d3cca8e3dc9 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -577,7 +577,7 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, bio->bi_iter.bi_sector = dmz_blk2sect(block); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); return mblk; @@ -728,7 +728,7 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, bio->bi_iter.bi_sector = dmz_blk2sect(block); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); return 0; @@ -752,7 +752,7 @@ static int dmz_rdwr_block(struct dmz_dev *dev, enum req_op op, bio = bio_alloc(dev->bdev, 1, op | REQ_SYNC | REQ_META | REQ_PRIO, GFP_NOIO); bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); ret = submit_bio_wait(bio); bio_put(bio); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3b694ba3a106..ae0a88defb41 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -310,13 +310,13 @@ int dm_deleting_md(struct mapped_device *md) return test_bit(DMF_DELETING, &md->flags); } -static int dm_blk_open(struct block_device *bdev, fmode_t mode) +static int dm_blk_open(struct gendisk *disk, blk_mode_t mode) { struct mapped_device *md; spin_lock(&_minor_lock); - md = bdev->bd_disk->private_data; + md = disk->private_data; if (!md) goto out; @@ -334,7 +334,7 @@ out: return md ? 0 : -ENXIO; } -static void dm_blk_close(struct gendisk *disk, fmode_t mode) +static void dm_blk_close(struct gendisk *disk) { struct mapped_device *md; @@ -448,7 +448,7 @@ static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx) dm_put_live_table(md, srcu_idx); } -static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, +static int dm_blk_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct mapped_device *md = bdev->bd_disk->private_data; @@ -734,7 +734,7 @@ static char *_dm_claim_ptr = "I belong to device-mapper"; * Open a table device so we can use it as a map destination. */ static struct table_device *open_table_device(struct mapped_device *md, - dev_t dev, fmode_t mode) + dev_t dev, blk_mode_t mode) { struct table_device *td; struct block_device *bdev; @@ -746,7 +746,7 @@ static struct table_device *open_table_device(struct mapped_device *md, return ERR_PTR(-ENOMEM); refcount_set(&td->count, 1); - bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr); + bdev = blkdev_get_by_dev(dev, mode, _dm_claim_ptr, NULL); if (IS_ERR(bdev)) { r = PTR_ERR(bdev); goto out_free_td; @@ -771,7 +771,7 @@ static struct table_device *open_table_device(struct mapped_device *md, return td; out_blkdev_put: - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, _dm_claim_ptr); out_free_td: kfree(td); return ERR_PTR(r); @@ -784,14 +784,14 @@ static void close_table_device(struct table_device *td, struct mapped_device *md { if (md->disk->slave_dir) bd_unlink_disk_holder(td->dm_dev.bdev, md->disk); - blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL); + blkdev_put(td->dm_dev.bdev, _dm_claim_ptr); put_dax(td->dm_dev.dax_dev); list_del(&td->list); kfree(td); } static struct table_device *find_table_device(struct list_head *l, dev_t dev, - fmode_t mode) + blk_mode_t mode) { struct table_device *td; @@ -802,7 +802,7 @@ static struct table_device *find_table_device(struct list_head *l, dev_t dev, return NULL; } -int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode, +int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode, struct dm_dev **result) { struct table_device *td; @@ -1172,7 +1172,8 @@ static inline sector_t max_io_len_target_boundary(struct dm_target *ti, } static sector_t __max_io_len(struct dm_target *ti, sector_t sector, - unsigned int max_granularity) + unsigned int max_granularity, + unsigned int max_sectors) { sector_t target_offset = dm_target_offset(ti, sector); sector_t len = max_io_len_target_boundary(ti, target_offset); @@ -1186,13 +1187,13 @@ static sector_t __max_io_len(struct dm_target *ti, sector_t sector, if (!max_granularity) return len; return min_t(sector_t, len, - min(queue_max_sectors(ti->table->md->queue), + min(max_sectors ? : queue_max_sectors(ti->table->md->queue), blk_chunk_sectors_left(target_offset, max_granularity))); } static inline sector_t max_io_len(struct dm_target *ti, sector_t sector) { - return __max_io_len(ti, sector, ti->max_io_len); + return __max_io_len(ti, sector, ti->max_io_len, 0); } int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) @@ -1581,12 +1582,13 @@ static void __send_empty_flush(struct clone_info *ci) static void __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti, unsigned int num_bios, - unsigned int max_granularity) + unsigned int max_granularity, + unsigned int max_sectors) { unsigned int len, bios; len = min_t(sector_t, ci->sector_count, - __max_io_len(ti, ci->sector, max_granularity)); + __max_io_len(ti, ci->sector, max_granularity, max_sectors)); atomic_add(num_bios, &ci->io->io_count); bios = __send_duplicate_bios(ci, ti, num_bios, &len); @@ -1623,23 +1625,27 @@ static blk_status_t __process_abnormal_io(struct clone_info *ci, { unsigned int num_bios = 0; unsigned int max_granularity = 0; + unsigned int max_sectors = 0; struct queue_limits *limits = dm_get_queue_limits(ti->table->md); switch (bio_op(ci->bio)) { case REQ_OP_DISCARD: num_bios = ti->num_discard_bios; + max_sectors = limits->max_discard_sectors; if (ti->max_discard_granularity) - max_granularity = limits->max_discard_sectors; + max_granularity = max_sectors; break; case REQ_OP_SECURE_ERASE: num_bios = ti->num_secure_erase_bios; + max_sectors = limits->max_secure_erase_sectors; if (ti->max_secure_erase_granularity) - max_granularity = limits->max_secure_erase_sectors; + max_granularity = max_sectors; break; case REQ_OP_WRITE_ZEROES: num_bios = ti->num_write_zeroes_bios; + max_sectors = limits->max_write_zeroes_sectors; if (ti->max_write_zeroes_granularity) - max_granularity = limits->max_write_zeroes_sectors; + max_granularity = max_sectors; break; default: break; @@ -1654,7 +1660,8 @@ static blk_status_t __process_abnormal_io(struct clone_info *ci, if (unlikely(!num_bios)) return BLK_STS_NOTSUPP; - __send_changing_extent_only(ci, ti, num_bios, max_granularity); + __send_changing_extent_only(ci, ti, num_bios, + max_granularity, max_sectors); return BLK_STS_OK; } @@ -2808,6 +2815,10 @@ retry: } map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); + if (!map) { + /* avoid deadlock with fs/namespace.c:do_mount() */ + suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; + } r = __dm_suspend(md, map, suspend_flags, TASK_INTERRUPTIBLE, DMF_SUSPENDED); if (r) diff --git a/drivers/md/dm.h b/drivers/md/dm.h index a856e0aee73b..63d9010d8e61 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -203,7 +203,7 @@ int dm_open_count(struct mapped_device *md); int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred); int dm_cancel_deferred_remove(struct mapped_device *md); int dm_request_based(struct mapped_device *md); -int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode, +int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode, struct dm_dev **result); void dm_put_table_device(struct mapped_device *md, struct dm_dev *d); diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 91836e6de326..6eaa0eab40f9 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -147,7 +147,8 @@ static void __init md_setup_drive(struct md_setup_args *args) if (p) *p++ = 0; - dev = name_to_dev_t(devname); + if (early_lookup_bdev(devname, &dev)) + dev = 0; if (strncmp(devname, "/dev/", 5) == 0) devname += 5; snprintf(comp_name, 63, "/dev/%s", devname); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bc8d7565171d..1ff712889a3b 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -54,14 +54,7 @@ __acquires(bitmap->lock) { unsigned char *mappage; - if (page >= bitmap->pages) { - /* This can happen if bitmap_start_sync goes beyond - * End-of-device while looking for a whole page. - * It is harmless. - */ - return -EINVAL; - } - + WARN_ON_ONCE(page >= bitmap->pages); if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */ return 0; @@ -1023,7 +1016,6 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) return set; } - /* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */ @@ -1033,8 +1025,7 @@ void md_bitmap_unplug(struct bitmap *bitmap) int dirty, need_write; int writing = 0; - if (!bitmap || !bitmap->storage.filemap || - test_bit(BITMAP_STALE, &bitmap->flags)) + if (!md_bitmap_enabled(bitmap)) return; /* look at each page to see if there are any set bits that need to be @@ -1063,6 +1054,35 @@ void md_bitmap_unplug(struct bitmap *bitmap) } EXPORT_SYMBOL(md_bitmap_unplug); +struct bitmap_unplug_work { + struct work_struct work; + struct bitmap *bitmap; + struct completion *done; +}; + +static void md_bitmap_unplug_fn(struct work_struct *work) +{ + struct bitmap_unplug_work *unplug_work = + container_of(work, struct bitmap_unplug_work, work); + + md_bitmap_unplug(unplug_work->bitmap); + complete(unplug_work->done); +} + +void md_bitmap_unplug_async(struct bitmap *bitmap) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct bitmap_unplug_work unplug_work; + + INIT_WORK_ONSTACK(&unplug_work.work, md_bitmap_unplug_fn); + unplug_work.bitmap = bitmap; + unplug_work.done = &done; + + queue_work(md_bitmap_wq, &unplug_work.work); + wait_for_completion(&done); +} +EXPORT_SYMBOL(md_bitmap_unplug_async); + static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed); /* * bitmap_init_from_disk -- called at bitmap_create time to initialize * the in-memory bitmap from the on-disk bitmap -- also, sets up the @@ -1241,11 +1261,28 @@ static bitmap_counter_t *md_bitmap_get_counter(struct bitmap_counts *bitmap, sector_t offset, sector_t *blocks, int create); +static void mddev_set_timeout(struct mddev *mddev, unsigned long timeout, + bool force) +{ + struct md_thread *thread; + + rcu_read_lock(); + thread = rcu_dereference(mddev->thread); + + if (!thread) + goto out; + + if (force || thread->timeout < MAX_SCHEDULE_TIMEOUT) + thread->timeout = timeout; + +out: + rcu_read_unlock(); +} + /* * bitmap daemon -- periodically wakes up to clean bits and flush pages * out to disk */ - void md_bitmap_daemon_work(struct mddev *mddev) { struct bitmap *bitmap; @@ -1269,7 +1306,7 @@ void md_bitmap_daemon_work(struct mddev *mddev) bitmap->daemon_lastrun = jiffies; if (bitmap->allclean) { - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true); goto done; } bitmap->allclean = 1; @@ -1366,8 +1403,7 @@ void md_bitmap_daemon_work(struct mddev *mddev) done: if (bitmap->allclean == 0) - mddev->thread->timeout = - mddev->bitmap_info.daemon_sleep; + mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true); mutex_unlock(&mddev->bitmap_info.mutex); } @@ -1387,6 +1423,14 @@ __acquires(bitmap->lock) sector_t csize; int err; + if (page >= bitmap->pages) { + /* + * This can happen if bitmap_start_sync goes beyond + * End-of-device while looking for a whole page or + * user set a huge number to sysfs bitmap_set_bits. + */ + return NULL; + } err = md_bitmap_checkpage(bitmap, page, create, 0); if (bitmap->bp[page].hijacked || @@ -1820,8 +1864,7 @@ void md_bitmap_destroy(struct mddev *mddev) mddev->bitmap = NULL; /* disconnect from the md device */ spin_unlock(&mddev->lock); mutex_unlock(&mddev->bitmap_info.mutex); - if (mddev->thread) - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true); md_bitmap_free(bitmap); } @@ -1964,7 +2007,7 @@ int md_bitmap_load(struct mddev *mddev) /* Kick recovery in case any bits were set */ set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); - mddev->thread->timeout = mddev->bitmap_info.daemon_sleep; + mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true); md_wakeup_thread(mddev->thread); md_bitmap_update_sb(bitmap); @@ -2469,17 +2512,11 @@ timeout_store(struct mddev *mddev, const char *buf, size_t len) timeout = MAX_SCHEDULE_TIMEOUT-1; if (timeout < 1) timeout = 1; + mddev->bitmap_info.daemon_sleep = timeout; - if (mddev->thread) { - /* if thread->timeout is MAX_SCHEDULE_TIMEOUT, then - * the bitmap is all clean and we don't need to - * adjust the timeout right now - */ - if (mddev->thread->timeout < MAX_SCHEDULE_TIMEOUT) { - mddev->thread->timeout = timeout; - md_wakeup_thread(mddev->thread); - } - } + mddev_set_timeout(mddev, timeout, false); + md_wakeup_thread(mddev->thread); + return len; } diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index cfd7395de8fd..8a3788c9bfef 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -264,6 +264,7 @@ void md_bitmap_sync_with_cluster(struct mddev *mddev, sector_t new_lo, sector_t new_hi); void md_bitmap_unplug(struct bitmap *bitmap); +void md_bitmap_unplug_async(struct bitmap *bitmap); void md_bitmap_daemon_work(struct mddev *mddev); int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, @@ -273,6 +274,13 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot, sector_t *lo, sector_t *hi, bool clear_bits); void md_bitmap_free(struct bitmap *bitmap); void md_bitmap_wait_behind_writes(struct mddev *mddev); + +static inline bool md_bitmap_enabled(struct bitmap *bitmap) +{ + return bitmap && bitmap->storage.filemap && + !test_bit(BITMAP_STALE, &bitmap->flags); +} + #endif #endif diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 10e0c5381d01..3d9fd74233df 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -75,14 +75,14 @@ struct md_cluster_info { sector_t suspend_hi; int suspend_from; /* the slot which broadcast suspend_lo/hi */ - struct md_thread *recovery_thread; + struct md_thread __rcu *recovery_thread; unsigned long recovery_map; /* communication loc resources */ struct dlm_lock_resource *ack_lockres; struct dlm_lock_resource *message_lockres; struct dlm_lock_resource *token_lockres; struct dlm_lock_resource *no_new_dev_lockres; - struct md_thread *recv_thread; + struct md_thread __rcu *recv_thread; struct completion newdisk_completion; wait_queue_head_t wait; unsigned long state; @@ -362,8 +362,8 @@ static void __recover_slot(struct mddev *mddev, int slot) set_bit(slot, &cinfo->recovery_map); if (!cinfo->recovery_thread) { - cinfo->recovery_thread = md_register_thread(recover_bitmaps, - mddev, "recover"); + rcu_assign_pointer(cinfo->recovery_thread, + md_register_thread(recover_bitmaps, mddev, "recover")); if (!cinfo->recovery_thread) { pr_warn("md-cluster: Could not create recovery thread\n"); return; @@ -526,11 +526,15 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg) { int got_lock = 0; + struct md_thread *thread; struct md_cluster_info *cinfo = mddev->cluster_info; mddev->good_device_nr = le32_to_cpu(msg->raid_slot); dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); - wait_event(mddev->thread->wqueue, + + /* daemaon thread must exist */ + thread = rcu_dereference_protected(mddev->thread, true); + wait_event(thread->wqueue, (got_lock = mddev_trylock(mddev)) || test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state)); md_reload_sb(mddev, mddev->good_device_nr); @@ -889,7 +893,8 @@ static int join(struct mddev *mddev, int nodes) } /* Initiate the communication resources */ ret = -ENOMEM; - cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv"); + rcu_assign_pointer(cinfo->recv_thread, + md_register_thread(recv_daemon, mddev, "cluster_recv")); if (!cinfo->recv_thread) { pr_err("md-cluster: cannot allocate memory for recv_thread!\n"); goto err; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 66edf5e72bd6..92c45be203d7 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -400,8 +400,8 @@ static int multipath_run (struct mddev *mddev) if (ret) goto out_free_conf; - mddev->thread = md_register_thread(multipathd, mddev, - "multipath"); + rcu_assign_pointer(mddev->thread, + md_register_thread(multipathd, mddev, "multipath")); if (!mddev->thread) goto out_free_conf; diff --git a/drivers/md/md.c b/drivers/md/md.c index 8e344b4b3444..cf3733c90c47 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -70,11 +70,7 @@ #include "md-bitmap.h" #include "md-cluster.h" -/* pers_list is a list of registered personalities protected - * by pers_lock. - * pers_lock does extra service to protect accesses to - * mddev->thread when the mutex cannot be held. - */ +/* pers_list is a list of registered personalities protected by pers_lock. */ static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); @@ -87,23 +83,13 @@ static struct module *md_cluster_mod; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; static struct workqueue_struct *md_misc_wq; -static struct workqueue_struct *md_rdev_misc_wq; +struct workqueue_struct *md_bitmap_wq; static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); static void mddev_detach(struct mddev *mddev); - -enum md_ro_state { - MD_RDWR, - MD_RDONLY, - MD_AUTO_READ, - MD_MAX_STATE -}; - -static bool md_is_rdwr(struct mddev *mddev) -{ - return (mddev->ro == MD_RDWR); -} +static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); +static void md_wakeup_thread_directly(struct md_thread __rcu *thread); /* * Default number of read corrections we'll attempt on an rdev @@ -360,10 +346,6 @@ EXPORT_SYMBOL_GPL(md_new_event); static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); -static bool is_md_suspended(struct mddev *mddev) -{ - return percpu_ref_is_dying(&mddev->active_io); -} /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. @@ -457,13 +439,19 @@ static void md_submit_bio(struct bio *bio) */ void mddev_suspend(struct mddev *mddev) { - WARN_ON_ONCE(mddev->thread && current == mddev->thread->tsk); - lockdep_assert_held(&mddev->reconfig_mutex); + struct md_thread *thread = rcu_dereference_protected(mddev->thread, + lockdep_is_held(&mddev->reconfig_mutex)); + + WARN_ON_ONCE(thread && current == thread->tsk); if (mddev->suspended++) return; wake_up(&mddev->sb_wait); set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags); percpu_ref_kill(&mddev->active_io); + + if (mddev->pers->prepare_suspend) + mddev->pers->prepare_suspend(mddev); + wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); mddev->pers->quiesce(mddev, 1); clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags); @@ -655,9 +643,11 @@ void mddev_init(struct mddev *mddev) { mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); + mutex_init(&mddev->delete_mutex); mutex_init(&mddev->bitmap_info.mutex); INIT_LIST_HEAD(&mddev->disks); INIT_LIST_HEAD(&mddev->all_mddevs); + INIT_LIST_HEAD(&mddev->deleting); timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0); atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); @@ -759,6 +749,24 @@ static void mddev_free(struct mddev *mddev) static const struct attribute_group md_redundancy_group; +static void md_free_rdev(struct mddev *mddev) +{ + struct md_rdev *rdev; + struct md_rdev *tmp; + + mutex_lock(&mddev->delete_mutex); + if (list_empty(&mddev->deleting)) + goto out; + + list_for_each_entry_safe(rdev, tmp, &mddev->deleting, same_set) { + list_del_init(&rdev->same_set); + kobject_del(&rdev->kobj); + export_rdev(rdev, mddev); + } +out: + mutex_unlock(&mddev->delete_mutex); +} + void mddev_unlock(struct mddev *mddev) { if (mddev->to_remove) { @@ -800,13 +808,10 @@ void mddev_unlock(struct mddev *mddev) } else mutex_unlock(&mddev->reconfig_mutex); - /* As we've dropped the mutex we need a spinlock to - * make sure the thread doesn't disappear - */ - spin_lock(&pers_lock); + md_free_rdev(mddev); + md_wakeup_thread(mddev->thread); wake_up(&mddev->sb_wait); - spin_unlock(&pers_lock); } EXPORT_SYMBOL_GPL(mddev_unlock); @@ -938,7 +943,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector; - bio_add_page(bio, page, size, 0); + __bio_add_page(bio, page, size, 0); bio->bi_private = rdev; bio->bi_end_io = super_written; @@ -979,7 +984,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, bio.bi_iter.bi_sector = sector + rdev->new_data_offset; else bio.bi_iter.bi_sector = sector + rdev->data_offset; - bio_add_page(&bio, page, size, 0); + __bio_add_page(&bio, page, size, 0); submit_bio_wait(&bio); @@ -2440,16 +2445,12 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) return err; } -static void rdev_delayed_delete(struct work_struct *ws) -{ - struct md_rdev *rdev = container_of(ws, struct md_rdev, del_work); - kobject_del(&rdev->kobj); - kobject_put(&rdev->kobj); -} - void md_autodetect_dev(dev_t dev); -static void export_rdev(struct md_rdev *rdev) +/* just for claiming the bdev */ +static struct md_rdev claim_rdev; + +static void export_rdev(struct md_rdev *rdev, struct mddev *mddev) { pr_debug("md: export_rdev(%pg)\n", rdev->bdev); md_rdev_clear(rdev); @@ -2457,13 +2458,15 @@ static void export_rdev(struct md_rdev *rdev) if (test_bit(AutoDetected, &rdev->flags)) md_autodetect_dev(rdev->bdev->bd_dev); #endif - blkdev_put(rdev->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(rdev->bdev, mddev->major_version == -2 ? &claim_rdev : rdev); rdev->bdev = NULL; kobject_put(&rdev->kobj); } static void md_kick_rdev_from_array(struct md_rdev *rdev) { + struct mddev *mddev = rdev->mddev; + bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk); list_del_rcu(&rdev->same_set); pr_debug("md: unbind<%pg>\n", rdev->bdev); @@ -2477,15 +2480,17 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev) rdev->sysfs_unack_badblocks = NULL; rdev->sysfs_badblocks = NULL; rdev->badblocks.count = 0; - /* We need to delay this, otherwise we can deadlock when - * writing to 'remove' to "dev/state". We also need - * to delay it due to rcu usage. - */ + synchronize_rcu(); - INIT_WORK(&rdev->del_work, rdev_delayed_delete); - kobject_get(&rdev->kobj); - queue_work(md_rdev_misc_wq, &rdev->del_work); - export_rdev(rdev); + + /* + * kobject_del() will wait for all in progress writers to be done, where + * reconfig_mutex is held, hence it can't be called under + * reconfig_mutex and it's delayed to mddev_unlock(). + */ + mutex_lock(&mddev->delete_mutex); + list_add(&rdev->same_set, &mddev->deleting); + mutex_unlock(&mddev->delete_mutex); } static void export_array(struct mddev *mddev) @@ -3553,6 +3558,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); + struct kernfs_node *kn = NULL; ssize_t rv; struct mddev *mddev = rdev->mddev; @@ -3560,6 +3566,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, return -EIO; if (!capable(CAP_SYS_ADMIN)) return -EACCES; + + if (entry->store == state_store && cmd_match(page, "remove")) + kn = sysfs_break_active_protection(kobj, attr); + rv = mddev ? mddev_lock(mddev) : -ENODEV; if (!rv) { if (rdev->mddev == NULL) @@ -3568,6 +3578,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, rv = entry->store(rdev, page, length); mddev_unlock(mddev); } + + if (kn) + sysfs_unbreak_active_protection(kn); + return rv; } @@ -3612,6 +3626,7 @@ int md_rdev_init(struct md_rdev *rdev) return badblocks_init(&rdev->badblocks, 0); } EXPORT_SYMBOL_GPL(md_rdev_init); + /* * Import a device. If 'super_format' >= 0, then sanity check the superblock * @@ -3624,7 +3639,6 @@ EXPORT_SYMBOL_GPL(md_rdev_init); */ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor) { - static struct md_rdev claim_rdev; /* just for claiming the bdev */ struct md_rdev *rdev; sector_t size; int err; @@ -3640,9 +3654,8 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe if (err) goto out_clear_rdev; - rdev->bdev = blkdev_get_by_dev(newdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, - super_format == -2 ? &claim_rdev : rdev); + rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + super_format == -2 ? &claim_rdev : rdev, NULL); if (IS_ERR(rdev->bdev)) { pr_warn("md: could not open device unknown-block(%u,%u).\n", MAJOR(newdev), MINOR(newdev)); @@ -3679,7 +3692,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe return rdev; out_blkdev_put: - blkdev_put(rdev->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(rdev->bdev, super_format == -2 ? &claim_rdev : rdev); out_clear_rdev: md_rdev_clear(rdev); out_free_rdev: @@ -3794,8 +3807,9 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale) static ssize_t safe_delay_show(struct mddev *mddev, char *page) { - int msec = (mddev->safemode_delay*1000)/HZ; - return sprintf(page, "%d.%03d\n", msec/1000, msec%1000); + unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ; + + return sprintf(page, "%u.%03u\n", msec/1000, msec%1000); } static ssize_t safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) @@ -3807,7 +3821,7 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) return -EINVAL; } - if (strict_strtoul_scaled(cbuf, &msec, 3) < 0) + if (strict_strtoul_scaled(cbuf, &msec, 3) < 0 || msec > UINT_MAX / HZ) return -EINVAL; if (msec == 0) mddev->safemode_delay = 0; @@ -4477,6 +4491,8 @@ max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len rv = kstrtouint(buf, 10, &n); if (rv < 0) return rv; + if (n > INT_MAX) + return -EINVAL; atomic_set(&mddev->max_corr_read_errors, n); return len; } @@ -4491,20 +4507,6 @@ null_show(struct mddev *mddev, char *page) return -EINVAL; } -/* need to ensure rdev_delayed_delete() has completed */ -static void flush_rdev_wq(struct mddev *mddev) -{ - struct md_rdev *rdev; - - rcu_read_lock(); - rdev_for_each_rcu(rdev, mddev) - if (work_pending(&rdev->del_work)) { - flush_workqueue(md_rdev_misc_wq); - break; - } - rcu_read_unlock(); -} - static ssize_t new_dev_store(struct mddev *mddev, const char *buf, size_t len) { @@ -4532,7 +4534,6 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) minor != MINOR(dev)) return -EOVERFLOW; - flush_rdev_wq(mddev); err = mddev_lock(mddev); if (err) return err; @@ -4560,7 +4561,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) err = bind_rdev_to_array(rdev, mddev); out: if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); mddev_unlock(mddev); if (!err) md_new_event(); @@ -4804,11 +4805,21 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { err = -EBUSY; - else { + } else if (mddev->reshape_position == MaxSector || + mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev)) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); + } else { + /* + * If reshape is still in progress, and + * md_check_recovery() can continue to reshape, + * don't restart reshape because data can be + * corrupted for raid456. + */ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } mddev_unlock(mddev); } @@ -5592,7 +5603,6 @@ struct mddev *md_alloc(dev_t dev, char *name) * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); - flush_workqueue(md_rdev_misc_wq); mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); @@ -6269,10 +6279,12 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) set_bit(MD_RECOVERY_INTR, &mddev->recovery); - if (mddev->sync_thread) - /* Thread might be blocked waiting for metadata update - * which will now never happen */ - wake_up_process(mddev->sync_thread->tsk); + + /* + * Thread might be blocked waiting for metadata update which will now + * never happen + */ + md_wakeup_thread_directly(mddev->sync_thread); if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) return -EBUSY; @@ -6333,10 +6345,12 @@ static int do_md_stop(struct mddev *mddev, int mode, } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) set_bit(MD_RECOVERY_INTR, &mddev->recovery); - if (mddev->sync_thread) - /* Thread might be blocked waiting for metadata update - * which will now never happen */ - wake_up_process(mddev->sync_thread->tsk); + + /* + * Thread might be blocked waiting for metadata update which will now + * never happen + */ + md_wakeup_thread_directly(mddev->sync_thread); mddev_unlock(mddev); wait_event(resync_wait, (mddev->sync_thread == NULL && @@ -6498,7 +6512,7 @@ static void autorun_devices(int part) rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); if (bind_rdev_to_array(rdev, mddev)) - export_rdev(rdev); + export_rdev(rdev, mddev); } autorun_array(mddev); mddev_unlock(mddev); @@ -6508,7 +6522,7 @@ static void autorun_devices(int part) */ rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); - export_rdev(rdev); + export_rdev(rdev, mddev); } mddev_put(mddev); } @@ -6696,13 +6710,13 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) pr_warn("md: %pg has different UUID to %pg\n", rdev->bdev, rdev0->bdev); - export_rdev(rdev); + export_rdev(rdev, mddev); return -EINVAL; } } err = bind_rdev_to_array(rdev, mddev); if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } @@ -6733,7 +6747,6 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) if (info->state & (1<<MD_DISK_SYNC) && info->raid_disk < mddev->raid_disks) { rdev->raid_disk = info->raid_disk; - set_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); } else rdev->raid_disk = -1; @@ -6746,7 +6759,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) /* This was a hot-add request, but events doesn't * match, so reject it. */ - export_rdev(rdev); + export_rdev(rdev, mddev); return -EINVAL; } @@ -6772,7 +6785,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) } } if (has_journal || mddev->bitmap) { - export_rdev(rdev); + export_rdev(rdev, mddev); return -EBUSY; } set_bit(Journal, &rdev->flags); @@ -6787,7 +6800,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) /* --add initiated by this node */ err = md_cluster_ops->add_new_disk(mddev, rdev); if (err) { - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } } @@ -6797,7 +6810,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) err = bind_rdev_to_array(rdev, mddev); if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); if (mddev_is_clustered(mddev)) { if (info->state & (1 << MD_DISK_CANDIDATE)) { @@ -6860,7 +6873,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) err = bind_rdev_to_array(rdev, mddev); if (err) { - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } } @@ -6985,7 +6998,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) return 0; abort_export: - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } @@ -7486,7 +7499,7 @@ static int __md_set_array_info(struct mddev *mddev, void __user *argp) return err; } -static int md_ioctl(struct block_device *bdev, fmode_t mode, +static int md_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { int err = 0; @@ -7555,9 +7568,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, } - if (cmd == ADD_NEW_DISK || cmd == HOT_ADD_DISK) - flush_rdev_wq(mddev); - if (cmd == HOT_REMOVE_DISK) /* need to ensure recovery thread has run */ wait_event_interruptible_timeout(mddev->sb_wait, @@ -7718,7 +7728,7 @@ out: return err; } #ifdef CONFIG_COMPAT -static int md_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int md_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { switch (cmd) { @@ -7767,13 +7777,13 @@ out_unlock: return err; } -static int md_open(struct block_device *bdev, fmode_t mode) +static int md_open(struct gendisk *disk, blk_mode_t mode) { struct mddev *mddev; int err; spin_lock(&all_mddevs_lock); - mddev = mddev_get(bdev->bd_disk->private_data); + mddev = mddev_get(disk->private_data); spin_unlock(&all_mddevs_lock); if (!mddev) return -ENODEV; @@ -7789,7 +7799,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); - bdev_check_media_change(bdev); + disk_check_media_change(disk); return 0; out_unlock: @@ -7799,7 +7809,7 @@ out: return err; } -static void md_release(struct gendisk *disk, fmode_t mode) +static void md_release(struct gendisk *disk) { struct mddev *mddev = disk->private_data; @@ -7886,13 +7896,29 @@ static int md_thread(void *arg) return 0; } -void md_wakeup_thread(struct md_thread *thread) +static void md_wakeup_thread_directly(struct md_thread __rcu *thread) { - if (thread) { - pr_debug("md: waking up MD thread %s.\n", thread->tsk->comm); - set_bit(THREAD_WAKEUP, &thread->flags); - wake_up(&thread->wqueue); + struct md_thread *t; + + rcu_read_lock(); + t = rcu_dereference(thread); + if (t) + wake_up_process(t->tsk); + rcu_read_unlock(); +} + +void md_wakeup_thread(struct md_thread __rcu *thread) +{ + struct md_thread *t; + + rcu_read_lock(); + t = rcu_dereference(thread); + if (t) { + pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); + set_bit(THREAD_WAKEUP, &t->flags); + wake_up(&t->wqueue); } + rcu_read_unlock(); } EXPORT_SYMBOL(md_wakeup_thread); @@ -7922,22 +7948,15 @@ struct md_thread *md_register_thread(void (*run) (struct md_thread *), } EXPORT_SYMBOL(md_register_thread); -void md_unregister_thread(struct md_thread **threadp) +void md_unregister_thread(struct md_thread __rcu **threadp) { - struct md_thread *thread; + struct md_thread *thread = rcu_dereference_protected(*threadp, true); - /* - * Locking ensures that mddev_unlock does not wake_up a - * non-existent thread - */ - spin_lock(&pers_lock); - thread = *threadp; - if (!thread) { - spin_unlock(&pers_lock); + if (!thread) return; - } - *threadp = NULL; - spin_unlock(&pers_lock); + + rcu_assign_pointer(*threadp, NULL); + synchronize_rcu(); pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk)); kthread_stop(thread->tsk); @@ -9100,6 +9119,7 @@ void md_do_sync(struct md_thread *thread) spin_unlock(&mddev->lock); wake_up(&resync_wait); + wake_up(&mddev->sb_wait); md_wakeup_thread(mddev->thread); return; } @@ -9202,9 +9222,8 @@ static void md_start_sync(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); - mddev->sync_thread = md_register_thread(md_do_sync, - mddev, - "resync"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "resync")); if (!mddev->sync_thread) { pr_warn("%s: could not start resync thread...\n", mdname(mddev)); @@ -9619,9 +9638,10 @@ static int __init md_init(void) if (!md_misc_wq) goto err_misc_wq; - md_rdev_misc_wq = alloc_workqueue("md_rdev_misc", 0, 0); - if (!md_rdev_misc_wq) - goto err_rdev_misc_wq; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, + 0); + if (!md_bitmap_wq) + goto err_bitmap_wq; ret = __register_blkdev(MD_MAJOR, "md", md_probe); if (ret < 0) @@ -9641,8 +9661,8 @@ static int __init md_init(void) err_mdp: unregister_blkdev(MD_MAJOR, "md"); err_md: - destroy_workqueue(md_rdev_misc_wq); -err_rdev_misc_wq: + destroy_workqueue(md_bitmap_wq); +err_bitmap_wq: destroy_workqueue(md_misc_wq); err_misc_wq: destroy_workqueue(md_wq); @@ -9938,8 +9958,8 @@ static __exit void md_exit(void) } spin_unlock(&all_mddevs_lock); - destroy_workqueue(md_rdev_misc_wq); destroy_workqueue(md_misc_wq); + destroy_workqueue(md_bitmap_wq); destroy_workqueue(md_wq); } diff --git a/drivers/md/md.h b/drivers/md/md.h index fd8f260ed5f8..bfd2306bc750 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -122,8 +122,6 @@ struct md_rdev { struct serial_in_rdev *serial; /* used for raid1 io serialization */ - struct work_struct del_work; /* used for delayed sysfs removal */ - struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ @@ -367,8 +365,8 @@ struct mddev { int new_chunk_sectors; int reshape_backwards; - struct md_thread *thread; /* management thread */ - struct md_thread *sync_thread; /* doing resync or reconstruct */ + struct md_thread __rcu *thread; /* management thread */ + struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ /* 'last_sync_action' is initialized to "none". It is set when a * sync operation (i.e "data-check", "requested-resync", "resync", @@ -531,6 +529,14 @@ struct mddev { unsigned int good_device_nr; /* good device num within cluster raid */ unsigned int noio_flag; /* for memalloc scope API */ + /* + * Temporarily store rdev that will be finally removed when + * reconfig_mutex is unlocked. + */ + struct list_head deleting; + /* Protect the deleting list */ + struct mutex delete_mutex; + bool has_superblocks:1; bool fail_last_dev:1; bool serialize_policy:1; @@ -555,6 +561,23 @@ enum recovery_flags { MD_RESYNCING_REMOTE, /* remote node is running resync thread */ }; +enum md_ro_state { + MD_RDWR, + MD_RDONLY, + MD_AUTO_READ, + MD_MAX_STATE +}; + +static inline bool md_is_rdwr(struct mddev *mddev) +{ + return (mddev->ro == MD_RDWR); +} + +static inline bool is_md_suspended(struct mddev *mddev) +{ + return percpu_ref_is_dying(&mddev->active_io); +} + static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); @@ -614,6 +637,7 @@ struct md_personality int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); + void (*prepare_suspend) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour @@ -734,8 +758,8 @@ extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, const char *name); -extern void md_unregister_thread(struct md_thread **threadp); -extern void md_wakeup_thread(struct md_thread *thread); +extern void md_unregister_thread(struct md_thread __rcu **threadp); +extern void md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern int mddev_init_writes_pending(struct mddev *mddev); @@ -828,6 +852,7 @@ struct mdu_array_info_s; struct mdu_disk_info_s; extern int mdp_major; +extern struct workqueue_struct *md_bitmap_wq; void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index e61f6cad4e08..169ebe296f2d 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -21,6 +21,7 @@ #define IO_MADE_GOOD ((struct bio *)2) #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) +#define MAX_PLUG_BIO 32 /* for managing resync I/O pages */ struct resync_pages { @@ -31,6 +32,7 @@ struct resync_pages { struct raid1_plug_cb { struct blk_plug_cb cb; struct bio_list pending; + unsigned int count; }; static void rbio_pool_free(void *rbio, void *data) @@ -101,11 +103,73 @@ static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp, struct page *page = resync_fetch_page(rp, idx); int len = min_t(int, size, PAGE_SIZE); - /* - * won't fail because the vec table is big - * enough to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return; + } + size -= len; } while (idx++ < RESYNC_PAGES && size > 0); } + + +static inline void raid1_submit_write(struct bio *bio) +{ + struct md_rdev *rdev = (struct md_rdev *)bio->bi_bdev; + + bio->bi_next = NULL; + bio_set_dev(bio, rdev->bdev); + if (test_bit(Faulty, &rdev->flags)) + bio_io_error(bio); + else if (unlikely(bio_op(bio) == REQ_OP_DISCARD && + !bdev_max_discard_sectors(bio->bi_bdev))) + /* Just ignore it */ + bio_endio(bio); + else + submit_bio_noacct(bio); +} + +static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio, + blk_plug_cb_fn unplug, int copies) +{ + struct raid1_plug_cb *plug = NULL; + struct blk_plug_cb *cb; + + /* + * If bitmap is not enabled, it's safe to submit the io directly, and + * this can get optimal performance. + */ + if (!md_bitmap_enabled(mddev->bitmap)) { + raid1_submit_write(bio); + return true; + } + + cb = blk_check_plugged(unplug, mddev, sizeof(*plug)); + if (!cb) + return false; + + plug = container_of(cb, struct raid1_plug_cb, cb); + bio_list_add(&plug->pending, bio); + if (++plug->count / MAX_PLUG_BIO >= copies) { + list_del(&cb->list); + cb->callback(cb, false); + } + + + return true; +} + +/* + * current->bio_list will be set under submit_bio() context, in this case bitmap + * io will be added to the list and wait for current io submission to finish, + * while current io submission must wait for bitmap io to be done. In order to + * avoid such deadlock, submit bitmap io asynchronously. + */ +static inline void raid1_prepare_flush_writes(struct bitmap *bitmap) +{ + if (current->bio_list) + md_bitmap_unplug_async(bitmap); + else + md_bitmap_unplug(bitmap); +} diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 68a9e2d9985b..dd25832eb045 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -794,22 +794,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect static void flush_bio_list(struct r1conf *conf, struct bio *bio) { /* flush any pending bitmap writes to disk before proceeding w/ I/O */ - md_bitmap_unplug(conf->mddev->bitmap); + raid1_prepare_flush_writes(conf->mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void *)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; cond_resched(); } @@ -1147,7 +1138,10 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, if (unlikely(!page)) goto free_pages; - bio_add_page(behind_bio, page, len, 0); + if (!bio_add_page(behind_bio, page, len, 0)) { + put_page(page); + goto free_pages; + } size -= len; i++; @@ -1175,7 +1169,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) struct r1conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); spin_unlock_irq(&conf->device_lock); @@ -1343,8 +1337,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, struct bitmap *bitmap = mddev->bitmap; unsigned long flags; struct md_rdev *blocked_rdev; - struct blk_plug_cb *cb; - struct raid1_plug_cb *plug = NULL; int first_clone; int max_sectors; bool write_behind = false; @@ -1573,15 +1565,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; - - cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); - else - plug = NULL; - if (plug) { - bio_list_add(&plug->pending, mbio); - } else { + if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); spin_unlock_irqrestore(&conf->device_lock, flags); @@ -2914,7 +2898,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, * won't fail because the vec table is big * enough to hold all these pages */ - bio_add_page(bio, page, len, 0); + __bio_add_page(bio, page, len, 0); } } nr_sectors += len>>9; @@ -3084,7 +3068,8 @@ static struct r1conf *setup_conf(struct mddev *mddev) } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, "raid1"); + rcu_assign_pointer(conf->thread, + md_register_thread(raid1d, mddev, "raid1")); if (!conf->thread) goto abort; @@ -3177,8 +3162,8 @@ static int raid1_run(struct mddev *mddev) /* * Ok, everything is just fine now */ - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); mddev->private = conf; set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index ebb6788820e7..468f189da7a0 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -130,7 +130,7 @@ struct r1conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; /* Keep track of cluster resync window to send to other * nodes. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4fcfcb350d2b..d0de8c9fb3cf 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -779,8 +779,16 @@ static struct md_rdev *read_balance(struct r10conf *conf, disk = r10_bio->devs[slot].devnum; rdev = rcu_dereference(conf->mirrors[disk].replacement); if (rdev == NULL || test_bit(Faulty, &rdev->flags) || - r10_bio->devs[slot].addr + sectors > rdev->recovery_offset) + r10_bio->devs[slot].addr + sectors > + rdev->recovery_offset) { + /* + * Read replacement first to prevent reading both rdev + * and replacement as NULL during replacement replace + * rdev. + */ + smp_mb(); rdev = rcu_dereference(conf->mirrors[disk].rdev); + } if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; @@ -902,25 +910,15 @@ static void flush_pending_writes(struct r10conf *conf) __set_current_state(TASK_RUNNING); blk_start_plug(&plug); - /* flush any pending bitmap writes to disk - * before proceeding w/ I/O */ - md_bitmap_unplug(conf->mddev->bitmap); + raid1_prepare_flush_writes(conf->mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } blk_finish_plug(&plug); } else @@ -982,6 +980,7 @@ static void lower_barrier(struct r10conf *conf) static bool stop_waiting_barrier(struct r10conf *conf) { struct bio_list *bio_list = current->bio_list; + struct md_thread *thread; /* barrier is dropped */ if (!conf->barrier) @@ -997,12 +996,14 @@ static bool stop_waiting_barrier(struct r10conf *conf) (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1]))) return true; + /* daemon thread must exist while handling io */ + thread = rcu_dereference_protected(conf->mddev->thread, true); /* * move on if io is issued from raid10d(), nr_pending is not released * from original io(see handle_read_error()). All raise barrier is * blocked until this io is done. */ - if (conf->mddev->thread->tsk == current) { + if (thread->tsk == current) { WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0); return true; } @@ -1113,7 +1114,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) struct r10conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); spin_unlock_irq(&conf->device_lock); @@ -1125,23 +1126,15 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) /* we aren't scheduling, so we can do the write-out directly. */ bio = bio_list_get(&plug->pending); - md_bitmap_unplug(mddev->bitmap); + raid1_prepare_flush_writes(mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } kfree(plug); } @@ -1282,8 +1275,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; const blk_opf_t do_fua = bio->bi_opf & REQ_FUA; unsigned long flags; - struct blk_plug_cb *cb; - struct raid1_plug_cb *plug = NULL; struct r10conf *conf = mddev->private; struct md_rdev *rdev; int devnum = r10_bio->devs[n_copy].devnum; @@ -1323,14 +1314,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, atomic_inc(&r10_bio->remaining); - cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); - else - plug = NULL; - if (plug) { - bio_list_add(&plug->pending, mbio); - } else { + if (!raid1_add_bio_to_plug(mddev, mbio, raid10_unplug, conf->copies)) { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); spin_unlock_irqrestore(&conf->device_lock, flags); @@ -1479,9 +1463,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[d].replacement); + struct md_rdev *rdev, *rrdev; + + rrdev = rcu_dereference(conf->mirrors[d].replacement); + /* + * Read replacement first to prevent reading both rdev and + * replacement as NULL during replacement replace rdev. + */ + smp_mb(); + rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev == rrdev) rrdev = NULL; if (rdev && (test_bit(Faulty, &rdev->flags))) @@ -2148,9 +2138,10 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r10conf *conf = mddev->private; int err = -EEXIST; - int mirror; + int mirror, repl_slot = -1; int first = 0; int last = conf->geo.raid_disks - 1; + struct raid10_info *p; if (mddev->recovery_cp < MaxSector) /* only hot-add to in-sync arrays, as recovery is @@ -2173,23 +2164,14 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) else mirror = first; for ( ; mirror <= last ; mirror++) { - struct raid10_info *p = &conf->mirrors[mirror]; + p = &conf->mirrors[mirror]; if (p->recovery_disabled == mddev->recovery_disabled) continue; if (p->rdev) { - if (!test_bit(WantReplacement, &p->rdev->flags) || - p->replacement != NULL) - continue; - clear_bit(In_sync, &rdev->flags); - set_bit(Replacement, &rdev->flags); - rdev->raid_disk = mirror; - err = 0; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - conf->fullsync = 1; - rcu_assign_pointer(p->replacement, rdev); - break; + if (test_bit(WantReplacement, &p->rdev->flags) && + p->replacement == NULL && repl_slot < 0) + repl_slot = mirror; + continue; } if (mddev->gendisk) @@ -2206,6 +2188,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } + if (err && repl_slot >= 0) { + p = &conf->mirrors[repl_slot]; + clear_bit(In_sync, &rdev->flags); + set_bit(Replacement, &rdev->flags); + rdev->raid_disk = repl_slot; + err = 0; + if (mddev->gendisk) + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + conf->fullsync = 1; + rcu_assign_pointer(p->replacement, rdev); + } + print_conf(conf); return err; } @@ -3303,6 +3298,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int chunks_skipped = 0; sector_t chunk_mask = conf->geo.chunk_mask; int page_idx = 0; + int error_disk = -1; /* * Allow skipping a full rebuild for incremental assembly @@ -3386,8 +3382,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return reshape_request(mddev, sector_nr, skipped); if (chunks_skipped >= conf->geo.raid_disks) { - /* if there has been nothing to do on any drive, - * then there is nothing to do at all.. + pr_err("md/raid10:%s: %s fails\n", mdname(mddev), + test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ? "resync" : "recovery"); + if (error_disk >= 0 && + !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { + /* + * recovery fails, set mirrors.recovery_disabled, + * device shouldn't be added to there. + */ + conf->mirrors[error_disk].recovery_disabled = + mddev->recovery_disabled; + return 0; + } + /* + * if there has been nothing to do on any drive, + * then there is nothing to do at all. */ *skipped = 1; return (max_sector - sector_nr) + sectors_skipped; @@ -3437,8 +3446,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, sector_t sect; int must_sync; int any_working; - int need_recover = 0; - int need_replace = 0; struct raid10_info *mirror = &conf->mirrors[i]; struct md_rdev *mrdev, *mreplace; @@ -3446,15 +3453,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mrdev = rcu_dereference(mirror->rdev); mreplace = rcu_dereference(mirror->replacement); - if (mrdev != NULL && - !test_bit(Faulty, &mrdev->flags) && - !test_bit(In_sync, &mrdev->flags)) - need_recover = 1; - if (mreplace != NULL && - !test_bit(Faulty, &mreplace->flags)) - need_replace = 1; + if (mrdev && (test_bit(Faulty, &mrdev->flags) || + test_bit(In_sync, &mrdev->flags))) + mrdev = NULL; + if (mreplace && test_bit(Faulty, &mreplace->flags)) + mreplace = NULL; - if (!need_recover && !need_replace) { + if (!mrdev && !mreplace) { rcu_read_unlock(); continue; } @@ -3470,8 +3475,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, rcu_read_unlock(); continue; } - if (mreplace && test_bit(Faulty, &mreplace->flags)) - mreplace = NULL; /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3490,7 +3493,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, rcu_read_unlock(); continue; } - atomic_inc(&mrdev->nr_pending); + if (mrdev) + atomic_inc(&mrdev->nr_pending); if (mreplace) atomic_inc(&mreplace->nr_pending); rcu_read_unlock(); @@ -3577,7 +3581,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[1].devnum = i; r10_bio->devs[1].addr = to_addr; - if (need_recover) { + if (mrdev) { bio = r10_bio->devs[1].bio; bio->bi_next = biolist; biolist = bio; @@ -3594,11 +3598,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - /* Note: if need_replace, then bio + /* Note: if replace is not NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. */ - if (!need_replace) + if (!mreplace) break; bio->bi_next = biolist; biolist = bio; @@ -3622,7 +3626,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (k = 0; k < conf->copies; k++) if (r10_bio->devs[k].devnum == i) break; - if (!test_bit(In_sync, + if (mrdev && !test_bit(In_sync, &mrdev->flags) && !rdev_set_badblocks( mrdev, @@ -3643,17 +3647,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mdname(mddev)); mirror->recovery_disabled = mddev->recovery_disabled; + } else { + error_disk = i; } put_buf(r10_bio); if (rb2) atomic_dec(&rb2->remaining); r10_bio = rb2; - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); break; } - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); if (r10_bio->devs[0].bio->bi_opf & MD_FAILFAST) { @@ -3819,11 +3827,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (bio= biolist ; bio ; bio=bio->bi_next) { struct resync_pages *rp = get_resync_pages(bio); page = resync_fetch_page(rp, page_idx); - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + goto giveup; + } } nr_sectors += len>>9; sector_nr += len>>9; @@ -4107,7 +4115,8 @@ static struct r10conf *setup_conf(struct mddev *mddev) atomic_set(&conf->nr_pending, 0); err = -ENOMEM; - conf->thread = md_register_thread(raid10d, mddev, "raid10"); + rcu_assign_pointer(conf->thread, + md_register_thread(raid10d, mddev, "raid10")); if (!conf->thread) goto out; @@ -4152,8 +4161,8 @@ static int raid10_run(struct mddev *mddev) if (!conf) goto out; - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); if (mddev_is_clustered(conf->mddev)) { int fc, fo; @@ -4296,8 +4305,8 @@ static int raid10_run(struct mddev *mddev) clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) goto out_free_conf; } @@ -4698,8 +4707,8 @@ out: set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) { ret = -EAGAIN; goto abort; @@ -4997,11 +5006,11 @@ read_more: if (len > PAGE_SIZE) len = PAGE_SIZE; for (bio = blist; bio ; bio = bio->bi_next) { - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return sectors_done; + } } sector_nr += len >> 9; nr_sectors += len >> 9; diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 8c072ce0bc54..63e48b11b552 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -100,7 +100,7 @@ struct r10conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; /* * Keep track of cluster resync window to send to other nodes. diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 46182b955aef..47ba7d9e81e1 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -120,7 +120,7 @@ struct r5l_log { struct bio_set bs; mempool_t meta_pool; - struct md_thread *reclaim_thread; + struct md_thread __rcu *reclaim_thread; unsigned long reclaim_target; /* number of space that need to be * reclaimed. if it's 0, reclaim spaces * used by io_units which are in @@ -792,7 +792,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log) io->current_bio = r5l_bio_alloc(log); io->current_bio->bi_end_io = r5l_log_endio; io->current_bio->bi_private = io; - bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0); + __bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0); r5_reserve_log_entry(log, io); @@ -1576,17 +1576,18 @@ void r5l_wake_reclaim(struct r5l_log *log, sector_t space) void r5l_quiesce(struct r5l_log *log, int quiesce) { - struct mddev *mddev; + struct mddev *mddev = log->rdev->mddev; + struct md_thread *thread = rcu_dereference_protected( + log->reclaim_thread, lockdep_is_held(&mddev->reconfig_mutex)); if (quiesce) { /* make sure r5l_write_super_and_discard_space exits */ - mddev = log->rdev->mddev; wake_up(&mddev->sb_wait); - kthread_park(log->reclaim_thread->tsk); + kthread_park(thread->tsk); r5l_wake_reclaim(log, MaxSector); r5l_do_reclaim(log); } else - kthread_unpark(log->reclaim_thread->tsk); + kthread_unpark(thread->tsk); } bool r5l_log_disk_error(struct r5conf *conf) @@ -3063,6 +3064,7 @@ void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev) int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) { struct r5l_log *log; + struct md_thread *thread; int ret; pr_debug("md/raid:%s: using device %pg as journal\n", @@ -3121,11 +3123,13 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->tree_lock); INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT | __GFP_NOWARN); - log->reclaim_thread = md_register_thread(r5l_reclaim_thread, - log->rdev->mddev, "reclaim"); - if (!log->reclaim_thread) + thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev, + "reclaim"); + if (!thread) goto reclaim_thread; - log->reclaim_thread->timeout = R5C_RECLAIM_WAKEUP_INTERVAL; + + thread->timeout = R5C_RECLAIM_WAKEUP_INTERVAL; + rcu_assign_pointer(log->reclaim_thread, thread); init_waitqueue_head(&log->iounit_wait); diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index e495939bb3e0..eaea57aee602 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -465,7 +465,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) bio->bi_end_io = ppl_log_endio; bio->bi_iter.bi_sector = log->next_io_sector; - bio_add_page(bio, io->header_page, PAGE_SIZE, 0); + __bio_add_page(bio, io->header_page, PAGE_SIZE, 0); pr_debug("%s: log->current_io_sector: %llu\n", __func__, (unsigned long long)log->next_io_sector); @@ -496,7 +496,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) prev->bi_opf, GFP_NOIO, &ppl_conf->bs); bio->bi_iter.bi_sector = bio_end_sector(prev); - bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); + __bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); bio_chain(bio, prev); ppl_submit_iounit_bio(io, prev); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9ea285fbc4a6..6615abf54d3f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5966,6 +5966,19 @@ out: return ret; } +static bool reshape_inprogress(struct mddev *mddev) +{ + return test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && + !test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + !test_bit(MD_RECOVERY_INTR, &mddev->recovery); +} + +static bool reshape_disabled(struct mddev *mddev) +{ + return is_md_suspended(mddev) || !md_is_rdwr(mddev); +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -5997,7 +6010,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, if (ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { spin_unlock_irq(&conf->device_lock); - return STRIPE_SCHEDULE_AND_RETRY; + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } } spin_unlock_irq(&conf->device_lock); @@ -6076,6 +6090,15 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, out_release: raid5_release_stripe(sh); +out: + if (ret == STRIPE_SCHEDULE_AND_RETRY && !reshape_inprogress(mddev) && + reshape_disabled(mddev)) { + bi->bi_status = BLK_STS_IOERR; + ret = STRIPE_FAIL; + pr_err("md/raid456:%s: io failed across reshape position while reshape can't make progress.\n", + mdname(mddev)); + } + return ret; } @@ -7708,7 +7731,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) } sprintf(pers_name, "raid%d", mddev->new_level); - conf->thread = md_register_thread(raid5d, mddev, pers_name); + rcu_assign_pointer(conf->thread, + md_register_thread(raid5d, mddev, pers_name)); if (!conf->thread) { pr_warn("md/raid:%s: couldn't allocate thread.\n", mdname(mddev)); @@ -7931,8 +7955,8 @@ static int raid5_run(struct mddev *mddev) } conf->min_offset_diff = min_offset_diff; - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); mddev->private = conf; for (i = 0; i < conf->raid_disks && conf->previous_raid_disks; @@ -8029,8 +8053,8 @@ static int raid5_run(struct mddev *mddev) clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) goto abort; } @@ -8377,6 +8401,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) p = conf->disks + disk; tmp = rdev_mdlock_deref(mddev, p->rdev); if (test_bit(WantReplacement, &tmp->flags) && + mddev->reshape_position == MaxSector && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); @@ -8500,6 +8525,7 @@ static int raid5_start_reshape(struct mddev *mddev) struct r5conf *conf = mddev->private; struct md_rdev *rdev; int spares = 0; + int i; unsigned long flags; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) @@ -8511,6 +8537,13 @@ static int raid5_start_reshape(struct mddev *mddev) if (has_failed(conf)) return -EINVAL; + /* raid5 can't handle concurrent reshape and recovery */ + if (mddev->recovery_cp < MaxSector) + return -EBUSY; + for (i = 0; i < conf->raid_disks; i++) + if (rdev_mdlock_deref(mddev, conf->disks[i].replacement)) + return -EBUSY; + rdev_for_each(rdev, mddev) { if (!test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) @@ -8607,8 +8640,8 @@ static int raid5_start_reshape(struct mddev *mddev) clear_bit(MD_RECOVERY_DONE, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) { mddev->recovery = 0; spin_lock_irq(&conf->device_lock); @@ -9043,6 +9076,22 @@ static int raid5_start(struct mddev *mddev) return r5l_start(conf->log); } +static void raid5_prepare_suspend(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + wait_event(mddev->sb_wait, !reshape_inprogress(mddev) || + percpu_ref_is_zero(&mddev->active_io)); + if (percpu_ref_is_zero(&mddev->active_io)) + return; + + /* + * Reshape is not in progress, and array is suspended, io that is + * waiting for reshpape can never be done. + */ + wake_up(&conf->wait_for_overlap); +} + static struct md_personality raid6_personality = { .name = "raid6", @@ -9063,6 +9112,7 @@ static struct md_personality raid6_personality = .check_reshape = raid6_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, @@ -9087,6 +9137,7 @@ static struct md_personality raid5_personality = .check_reshape = raid5_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, @@ -9112,6 +9163,7 @@ static struct md_personality raid4_personality = .check_reshape = raid5_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index e873938a6125..f19707189a7b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -679,7 +679,7 @@ struct r5conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; struct r5worker_group *worker_groups; int group_cnt; diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index bc6950a5740f..9293b058ab99 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -817,26 +817,15 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); - mutex_lock(&fe->remove_mutex); - if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) { - mutex_unlock(&fe->remove_mutex); + if (!fepriv->thread) return; - } kthread_stop(fepriv->thread); - mutex_unlock(&fe->remove_mutex); - - if (fepriv->dvbdev->users < -1) { - wait_event(fepriv->dvbdev->wait_queue, - fepriv->dvbdev->users == -1); - } - sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2780,13 +2769,9 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; - mutex_lock(&fe->remove_mutex); - dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) { - ret = -ENODEV; - goto err_remove_mutex; - } + if (fe->exit == DVB_FE_DEVICE_REMOVED) + return -ENODEV; if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2794,8 +2779,7 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - ret = -EBUSY; - goto err_remove_mutex; + return -EBUSY; } adapter->mfe_dvbdev = dvbdev; } @@ -2818,10 +2802,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) { - ret = -EINTR; - goto err_remove_mutex; - } + if (signal_pending(current)) + return -EINTR; } } @@ -2833,8 +2815,7 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - ret = -EBUSY; - goto err_remove_mutex; + return -EBUSY; } adapter->mfe_dvbdev = dvbdev; } @@ -2893,8 +2874,6 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); - - mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2916,9 +2895,6 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); - -err_remove_mutex: - mutex_unlock(&fe->remove_mutex); return ret; } @@ -2929,8 +2905,6 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; - mutex_lock(&fe->remove_mutex); - dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2952,18 +2926,10 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif + if (fe->exit != DVB_FE_NO_EXIT) + wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); - - if (fe->exit != DVB_FE_NO_EXIT) { - mutex_unlock(&fe->remove_mutex); - wake_up(&dvbdev->wait_queue); - } else { - mutex_unlock(&fe->remove_mutex); - } - - } else { - mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3064,7 +3030,6 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); - mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index d920c4178389..6d01025f1fcf 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -358,15 +358,15 @@ static const struct attribute_group *mmc_disk_attr_groups[] = { NULL, }; -static int mmc_blk_open(struct block_device *bdev, fmode_t mode) +static int mmc_blk_open(struct gendisk *disk, blk_mode_t mode) { - struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk); + struct mmc_blk_data *md = mmc_blk_get(disk); int ret = -ENXIO; mutex_lock(&block_mutex); if (md) { ret = 0; - if ((mode & FMODE_WRITE) && md->read_only) { + if ((mode & BLK_OPEN_WRITE) && md->read_only) { mmc_blk_put(md); ret = -EROFS; } @@ -376,7 +376,7 @@ static int mmc_blk_open(struct block_device *bdev, fmode_t mode) return ret; } -static void mmc_blk_release(struct gendisk *disk, fmode_t mode) +static void mmc_blk_release(struct gendisk *disk) { struct mmc_blk_data *md = disk->private_data; @@ -757,7 +757,7 @@ static int mmc_blk_check_blkdev(struct block_device *bdev) return 0; } -static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode, +static int mmc_blk_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct mmc_blk_data *md; @@ -794,7 +794,7 @@ static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode, } #ifdef CONFIG_COMPAT -static int mmc_blk_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int mmc_blk_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { return mmc_blk_ioctl(bdev, mode, cmd, (unsigned long) compat_ptr(arg)); diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 8648f7e63ca1..eea208856ce0 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1403,8 +1403,8 @@ static int bcm2835_probe(struct platform_device *pdev) host->max_clk = clk_get_rate(clk); host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { - ret = -EINVAL; + if (host->irq < 0) { + ret = host->irq; goto err; } diff --git a/drivers/mmc/host/litex_mmc.c b/drivers/mmc/host/litex_mmc.c index 39c6707fdfdb..9af6b0902efe 100644 --- a/drivers/mmc/host/litex_mmc.c +++ b/drivers/mmc/host/litex_mmc.c @@ -649,6 +649,7 @@ static struct platform_driver litex_mmc_driver = { .driver = { .name = "litex-mmc", .of_match_table = litex_match, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; module_platform_driver(litex_mmc_driver); diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index b8514d9d5e73..ee9a25b900ae 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -991,11 +991,8 @@ static irqreturn_t meson_mmc_irq(int irq, void *dev_id) if (data && !cmd->error) data->bytes_xfered = data->blksz * data->blocks; - if (meson_mmc_bounce_buf_read(data) || - meson_mmc_get_next_command(cmd)) - ret = IRQ_WAKE_THREAD; - else - ret = IRQ_HANDLED; + + return IRQ_WAKE_THREAD; } out: @@ -1007,9 +1004,6 @@ out: writel(start, host->regs + SD_EMMC_START); } - if (ret == IRQ_HANDLED) - meson_mmc_request_done(host->mmc, cmd->mrq); - return ret; } @@ -1192,8 +1186,8 @@ static int meson_mmc_probe(struct platform_device *pdev) return PTR_ERR(host->regs); host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) - return -EINVAL; + if (host->irq < 0) + return host->irq; cd_irq = platform_get_irq_optional(pdev, 1); mmc_gpio_set_cd_irq(mmc, cd_irq); diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index f2b2e8b0574e..696cbef3ff7d 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1735,7 +1735,8 @@ static void mmci_set_max_busy_timeout(struct mmc_host *mmc) return; if (host->variant->busy_timeout && mmc->actual_clock) - max_busy_timeout = ~0UL / (mmc->actual_clock / MSEC_PER_SEC); + max_busy_timeout = U32_MAX / DIV_ROUND_UP(mmc->actual_clock, + MSEC_PER_SEC); mmc->max_busy_timeout = max_busy_timeout; } diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index edade0e54a0c..9785ec91654f 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2680,7 +2680,7 @@ static int msdc_drv_probe(struct platform_device *pdev) host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - ret = -EINVAL; + ret = host->irq; goto host_free; } diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c index 629efbe639c4..b4f6a0a2fcb5 100644 --- a/drivers/mmc/host/mvsdio.c +++ b/drivers/mmc/host/mvsdio.c @@ -704,7 +704,7 @@ static int mvsd_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq; mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev); if (!mmc) { diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index ce78edfb402b..86454f1182bb 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -1343,7 +1343,7 @@ static int mmc_omap_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) - return -ENXIO; + return irq; host->virt_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(host->virt_base)) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 517dde777413..1e0f2d7774bd 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1791,9 +1791,11 @@ static int omap_hsmmc_probe(struct platform_device *pdev) } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - irq = platform_get_irq(pdev, 0); - if (res == NULL || irq < 0) + if (!res) return -ENXIO; + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) diff --git a/drivers/mmc/host/owl-mmc.c b/drivers/mmc/host/owl-mmc.c index 6f9d31a886ba..1bf22b08b373 100644 --- a/drivers/mmc/host/owl-mmc.c +++ b/drivers/mmc/host/owl-mmc.c @@ -637,7 +637,7 @@ static int owl_mmc_probe(struct platform_device *pdev) owl_host->irq = platform_get_irq(pdev, 0); if (owl_host->irq < 0) { - ret = -EINVAL; + ret = owl_host->irq; goto err_release_channel; } diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 8f0e639236b1..edf2e6c14dc6 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -829,7 +829,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev) host->ops = &sdhci_acpi_ops_dflt; host->irq = platform_get_irq(pdev, 0); if (host->irq < 0) { - err = -EINVAL; + err = host->irq; goto err_free; } diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 8ac81d57a3df..1877d583fe8c 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2479,6 +2479,9 @@ static inline void sdhci_msm_get_of_property(struct platform_device *pdev, msm_host->ddr_config = DDR_CONFIG_POR_VAL; of_property_read_u32(node, "qcom,dll-config", &msm_host->dll_config); + + if (of_device_is_compatible(node, "qcom,msm8916-sdhci")) + host->quirks2 |= SDHCI_QUIRK2_BROKEN_64_BIT_DMA; } static int sdhci_msm_gcc_reset(struct device *dev, struct sdhci_host *host) diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c index d463e2fd5b1a..c79035727b20 100644 --- a/drivers/mmc/host/sdhci-spear.c +++ b/drivers/mmc/host/sdhci-spear.c @@ -65,8 +65,8 @@ static int sdhci_probe(struct platform_device *pdev) host->hw_name = "sdhci"; host->ops = &sdhci_pltfm_ops; host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { - ret = -EINVAL; + if (host->irq < 0) { + ret = host->irq; goto err_host; } host->quirks = SDHCI_QUIRK_BROKEN_ADMA; diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 0fd4c9d644dd..5cf53348372a 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -1400,7 +1400,7 @@ static int sh_mmcif_probe(struct platform_device *pdev) irq[0] = platform_get_irq(pdev, 0); irq[1] = platform_get_irq_optional(pdev, 1); if (irq[0] < 0) - return -ENXIO; + return irq[0]; reg = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(reg)) diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 3db9f32d6a7b..69dcb8805e05 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1350,8 +1350,8 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host, return ret; host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { - ret = -EINVAL; + if (host->irq < 0) { + ret = host->irq; goto error_disable_mmc; } diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c index 2f59917b105e..2e17903658fc 100644 --- a/drivers/mmc/host/usdhi6rol0.c +++ b/drivers/mmc/host/usdhi6rol0.c @@ -1757,8 +1757,10 @@ static int usdhi6_probe(struct platform_device *pdev) irq_cd = platform_get_irq_byname(pdev, "card detect"); irq_sd = platform_get_irq_byname(pdev, "data"); irq_sdio = platform_get_irq_byname(pdev, "SDIO"); - if (irq_sd < 0 || irq_sdio < 0) - return -ENODEV; + if (irq_sd < 0) + return irq_sd; + if (irq_sdio < 0) + return irq_sdio; mmc = mmc_alloc_host(sizeof(struct usdhi6_host), dev); if (!mmc) diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 4cd37ec45762..be106dc20ff3 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -209,40 +209,34 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) if (dev->blkdev) { invalidate_mapping_pages(dev->blkdev->bd_inode->i_mapping, 0, -1); - blkdev_put(dev->blkdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(dev->blkdev, NULL); } kfree(dev); } - -static struct block2mtd_dev *add_device(char *devname, int erase_size, - char *label, int timeout) +/* + * This function is marked __ref because it calls the __init marked + * early_lookup_bdev when called from the early boot code. + */ +static struct block_device __ref *mdtblock_early_get_bdev(const char *devname, + blk_mode_t mode, int timeout, struct block2mtd_dev *dev) { + struct block_device *bdev = ERR_PTR(-ENODEV); #ifndef MODULE int i; -#endif - const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL; - struct block_device *bdev; - struct block2mtd_dev *dev; - char *name; - if (!devname) - return NULL; - - dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL); - if (!dev) - return NULL; - - /* Get a handle on the device */ - bdev = blkdev_get_by_path(devname, mode, dev); + /* + * We can't use early_lookup_bdev from a running system. + */ + if (system_state >= SYSTEM_RUNNING) + return bdev; -#ifndef MODULE /* * We might not have the root device mounted at this point. * Try to resolve the device name by other means. */ - for (i = 0; IS_ERR(bdev) && i <= timeout; i++) { + for (i = 0; i <= timeout; i++) { dev_t devt; if (i) @@ -254,13 +248,35 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, msleep(1000); wait_for_device_probe(); - devt = name_to_dev_t(devname); - if (!devt) - continue; - bdev = blkdev_get_by_dev(devt, mode, dev); + if (!early_lookup_bdev(devname, &devt)) { + bdev = blkdev_get_by_dev(devt, mode, dev, NULL); + if (!IS_ERR(bdev)) + break; + } } #endif + return bdev; +} +static struct block2mtd_dev *add_device(char *devname, int erase_size, + char *label, int timeout) +{ + const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; + struct block_device *bdev; + struct block2mtd_dev *dev; + char *name; + + if (!devname) + return NULL; + + dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL); + if (!dev) + return NULL; + + /* Get a handle on the device */ + bdev = blkdev_get_by_path(devname, mode, dev, NULL); + if (IS_ERR(bdev)) + bdev = mdtblock_early_get_bdev(devname, mode, timeout, dev); if (IS_ERR(bdev)) { pr_err("error: cannot open device %s\n", devname); goto err_free_block2mtd; diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 60b222799871..ff18636e0889 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -182,9 +182,9 @@ static blk_status_t mtd_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static int blktrans_open(struct block_device *bdev, fmode_t mode) +static int blktrans_open(struct gendisk *disk, blk_mode_t mode) { - struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data; + struct mtd_blktrans_dev *dev = disk->private_data; int ret = 0; kref_get(&dev->ref); @@ -208,7 +208,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) ret = __get_mtd_device(dev->mtd); if (ret) goto error_release; - dev->file_mode = mode; + dev->writable = mode & BLK_OPEN_WRITE; unlock: dev->open++; @@ -225,7 +225,7 @@ error_put: return ret; } -static void blktrans_release(struct gendisk *disk, fmode_t mode) +static void blktrans_release(struct gendisk *disk) { struct mtd_blktrans_dev *dev = disk->private_data; diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index a0a1194dc1d9..fa476fb4dffb 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -294,7 +294,7 @@ static void mtdblock_release(struct mtd_blktrans_dev *mbd) * It was the last usage. Free the cache, but only sync if * opened for writing. */ - if (mbd->file_mode & FMODE_WRITE) + if (mbd->writable) mtd_sync(mbd->mtd); vfree(mtdblk->cache_data); } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 3711d7f74600..437c5b83ffe5 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -227,9 +227,9 @@ static blk_status_t ubiblock_read(struct request *req) return BLK_STS_OK; } -static int ubiblock_open(struct block_device *bdev, fmode_t mode) +static int ubiblock_open(struct gendisk *disk, blk_mode_t mode) { - struct ubiblock *dev = bdev->bd_disk->private_data; + struct ubiblock *dev = disk->private_data; int ret; mutex_lock(&dev->dev_mutex); @@ -246,11 +246,10 @@ static int ubiblock_open(struct block_device *bdev, fmode_t mode) * It's just a paranoid check, as write requests will get rejected * in any case. */ - if (mode & FMODE_WRITE) { + if (mode & BLK_OPEN_WRITE) { ret = -EROFS; goto out_unlock; } - dev->desc = ubi_open_volume(dev->ubi_num, dev->vol_id, UBI_READONLY); if (IS_ERR(dev->desc)) { dev_err(disk_to_dev(dev->gd), "failed to open ubi volume %d_%d", @@ -270,7 +269,7 @@ out_unlock: return ret; } -static void ubiblock_release(struct gendisk *gd, fmode_t mode) +static void ubiblock_release(struct gendisk *gd) { struct ubiblock *dev = gd->private_data; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 9bc54e1348cb..7e773c4ba046 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -399,6 +399,20 @@ static void mt7530_pll_setup(struct mt7530_priv *priv) core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); } +/* If port 6 is available as a CPU port, always prefer that as the default, + * otherwise don't care. + */ +static struct dsa_port * +mt753x_preferred_default_local_cpu_port(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp = dsa_to_port(ds, 6); + + if (dsa_port_is_cpu(cpu_dp)) + return cpu_dp; + + return NULL; +} + /* Setup port 6 interface mode and TRGMII TX circuit */ static int mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) @@ -985,6 +999,18 @@ unlock_exit: mutex_unlock(&priv->reg_mutex); } +static void +mt753x_trap_frames(struct mt7530_priv *priv) +{ + /* Trap BPDUs to the CPU port(s) */ + mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, + MT753X_BPDU_CPU_ONLY); + + /* Trap LLDP frames with :0E MAC DA to the CPU port(s) */ + mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK, + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); +} + static int mt753x_cpu_port_enable(struct dsa_switch *ds, int port) { @@ -1007,9 +1033,16 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) UNU_FFP(BIT(port))); /* Set CPU port number */ - if (priv->id == ID_MT7621) + if (priv->id == ID_MT7530 || priv->id == ID_MT7621) mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port)); + /* Add the CPU port to the CPU port bitmap for MT7531 and the switch on + * the MT7988 SoC. Trapped frames will be forwarded to the CPU port that + * is affine to the inbound user port. + */ + if (priv->id == ID_MT7531 || priv->id == ID_MT7988) + mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port))); + /* CPU port gets connected to all user ports of * the switch. */ @@ -2255,6 +2288,8 @@ mt7530_setup(struct dsa_switch *ds) priv->p6_interface = PHY_INTERFACE_MODE_NA; + mt753x_trap_frames(priv); + /* Enable and reset MIB counters */ mt7530_mib_reset(ds); @@ -2352,17 +2387,9 @@ static int mt7531_setup_common(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; - struct dsa_port *cpu_dp; int ret, i; - /* BPDU to CPU port */ - dsa_switch_for_each_cpu_port(cpu_dp, ds) { - mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, - BIT(cpu_dp->index)); - break; - } - mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, - MT753X_BPDU_CPU_ONLY); + mt753x_trap_frames(priv); /* Enable and reset MIB counters */ mt7530_mib_reset(ds); @@ -3085,6 +3112,7 @@ static int mt7988_setup(struct dsa_switch *ds) const struct dsa_switch_ops mt7530_switch_ops = { .get_tag_protocol = mtk_get_tag_protocol, .setup = mt753x_setup, + .preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port, .get_strings = mt7530_get_strings, .get_ethtool_stats = mt7530_get_ethtool_stats, .get_sset_count = mt7530_get_sset_count, diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 5084f48a8869..08045b035e6a 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -54,6 +54,7 @@ enum mt753x_id { #define MT7531_MIRROR_PORT_GET(x) (((x) >> 16) & MIRROR_MASK) #define MT7531_MIRROR_PORT_SET(x) (((x) & MIRROR_MASK) << 16) #define MT7531_CPU_PMAP_MASK GENMASK(7, 0) +#define MT7531_CPU_PMAP(x) FIELD_PREP(MT7531_CPU_PMAP_MASK, x) #define MT753X_MIRROR_REG(id) ((((id) == ID_MT7531) || ((id) == ID_MT7988)) ? \ MT7531_CFC : MT7530_MFC) @@ -66,6 +67,11 @@ enum mt753x_id { #define MT753X_BPC 0x24 #define MT753X_BPDU_PORT_FW_MASK GENMASK(2, 0) +/* Register for :03 and :0E MAC DA frame control */ +#define MT753X_RGAC2 0x2c +#define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) +#define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) + enum mt753x_bpdu_port_fw { MT753X_BPDU_FOLLOW_MFC, MT753X_BPDU_CPU_EXCLUDE = 4, diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index cfb3faeaa5bf..d172a3e9736c 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1263,7 +1263,7 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) /* Consider the standard Ethernet overhead of 8 octets preamble+SFD, * 4 octets FCS, 12 octets IFG. */ - needed_bit_time_ps = (maxlen + 24) * picos_per_byte; + needed_bit_time_ps = (u64)(maxlen + 24) * picos_per_byte; dev_dbg(ocelot->dev, "port %d: max frame size %d needs %llu ps at speed %d\n", diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 637d162bbcfa..1e7a6f1d4223 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14294,11 +14294,16 @@ static void bnx2x_io_resume(struct pci_dev *pdev) bp->fw_seq = SHMEM_RD(bp, func_mb[BP_FW_MB_IDX(bp)].drv_mb_header) & DRV_MSG_SEQ_NUMBER_MASK; - if (netif_running(dev)) - bnx2x_nic_load(bp, LOAD_NORMAL); + if (netif_running(dev)) { + if (bnx2x_nic_load(bp, LOAD_NORMAL)) { + netdev_err(bp->dev, "Error during driver initialization, try unloading/reloading the driver\n"); + goto done; + } + } netif_device_attach(dev); +done: rtnl_unlock(); } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7e408bcc88de..0defd519ba62 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1135,8 +1135,8 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter, eth_hdr_len = ntohs(skb->protocol) == ETH_P_8021Q ? VLAN_ETH_HLEN : ETH_HLEN; if (skb->len <= 60 && - (lancer_chip(adapter) || skb_vlan_tag_present(skb)) && - is_ipv4_pkt(skb)) { + (lancer_chip(adapter) || BE3_chip(adapter) || + skb_vlan_tag_present(skb)) && is_ipv4_pkt(skb)) { ip = (struct iphdr *)ip_hdr(skb); pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len)); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index b1871e6c4006..00e50bd30189 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -54,6 +54,9 @@ static int phy_mode(enum dpmac_eth_if eth_if, phy_interface_t *if_mode) case DPMAC_ETH_IF_XFI: *if_mode = PHY_INTERFACE_MODE_10GBASER; break; + case DPMAC_ETH_IF_CAUI: + *if_mode = PHY_INTERFACE_MODE_25GBASER; + break; default: return -EINVAL; } @@ -79,6 +82,8 @@ static enum dpmac_eth_if dpmac_eth_if_mode(phy_interface_t if_mode) return DPMAC_ETH_IF_XFI; case PHY_INTERFACE_MODE_1000BASEX: return DPMAC_ETH_IF_1000BASEX; + case PHY_INTERFACE_MODE_25GBASER: + return DPMAC_ETH_IF_CAUI; default: return DPMAC_ETH_IF_MII; } @@ -418,7 +423,7 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) mac->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD | MAC_2500FD | MAC_5000FD | - MAC_10000FD; + MAC_10000FD | MAC_25000FD; dpaa2_mac_set_supported_interfaces(mac); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 83c27bbbc6ed..126007ab70f6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -181,8 +181,8 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) int bw_sum = 0; u8 bw; - prio_top = netdev_get_prio_tc_map(ndev, tc_nums - 1); - prio_next = netdev_get_prio_tc_map(ndev, tc_nums - 2); + prio_top = tc_nums - 1; + prio_next = tc_nums - 2; /* Support highest prio and second prio tc in cbs mode */ if (tc != prio_top && tc != prio_next) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 9abaff1f2aff..39d0fe76a38f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -525,7 +525,7 @@ void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_irq_enable_queues(struct iavf_adapter *adapter); void iavf_free_all_tx_resources(struct iavf_adapter *adapter); void iavf_free_all_rx_resources(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 2de4baff4c20..4a66873882d1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -359,21 +359,18 @@ static void iavf_irq_disable(struct iavf_adapter *adapter) } /** - * iavf_irq_enable_queues - Enable interrupt for specified queues + * iavf_irq_enable_queues - Enable interrupt for all queues * @adapter: board private structure - * @mask: bitmap of queues to enable **/ -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) +void iavf_irq_enable_queues(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; int i; for (i = 1; i < adapter->num_msix_vectors; i++) { - if (mask & BIT(i - 1)) { - wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), - IAVF_VFINT_DYN_CTLN1_INTENA_MASK | - IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); - } + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); } } @@ -387,7 +384,7 @@ void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) struct iavf_hw *hw = &adapter->hw; iavf_misc_irq_enable(adapter); - iavf_irq_enable_queues(adapter, ~0); + iavf_irq_enable_queues(adapter); if (flush) iavf_flush(hw); diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h index bf793332fc9d..a19e88898a0b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_register.h +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -40,7 +40,7 @@ #define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 #define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) -#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...63 */ /* Reset: VFR */ #define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 #define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index bd0ed155e11b..75c9de675f20 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -96,12 +96,7 @@ static void ice_gnss_read(struct kthread_work *work) int err = 0; pf = gnss->back; - if (!pf) { - err = -EFAULT; - goto exit; - } - - if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + if (!pf || !test_bit(ICE_FLAG_GNSS, pf->flags)) return; hw = &pf->hw; @@ -159,7 +154,6 @@ free_buf: free_page((unsigned long)buf); requeue: kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, delay); -exit: if (err) dev_dbg(ice_pf_to_dev(pf), "GNSS failed to read err=%d\n", err); } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a1f7c8edc22f..42c318ceff61 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4802,9 +4802,13 @@ err_init_pf: static void ice_deinit_dev(struct ice_pf *pf) { ice_free_irq_msix_misc(pf); - ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); + + /* Service task is already stopped, so call reset directly. */ + ice_reset(&pf->hw, ICE_RESET_PFR); + pci_wait_for_pending_transaction(pf->pdev); + ice_clear_interrupt_scheme(pf); } static void ice_init_features(struct ice_pf *pf) @@ -5094,10 +5098,6 @@ int ice_load(struct ice_pf *pf) struct ice_vsi *vsi; int err; - err = ice_reset(&pf->hw, ICE_RESET_PFR); - if (err) - return err; - err = ice_init_dev(pf); if (err) return err; @@ -5354,12 +5354,6 @@ static void ice_remove(struct pci_dev *pdev) ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - /* Issue a PFR as part of the prescribed driver unload flow. Do not - * do it via ice_schedule_reset() since there is no need to rebuild - * and the service task is already stopped. - */ - ice_reset(&pf->hw, ICE_RESET_PFR); - pci_wait_for_pending_transaction(pdev); pci_disable_device(pdev); } @@ -7056,6 +7050,10 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); + if (ice_is_xdp_ena_vsi(vsi)) + ice_for_each_xdp_txq(vsi, i) + ice_clean_tx_ring(vsi->xdp_rings[i]); + ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 7d60da1b7bf4..319ed601eaa1 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -822,6 +822,8 @@ static int igb_set_eeprom(struct net_device *netdev, */ ret_val = hw->nvm.ops.read(hw, last_word, 1, &eeprom_buff[last_word - first_word]); + if (ret_val) + goto out; } /* Device's eeprom is always little-endian, word addressable */ @@ -841,6 +843,7 @@ static int igb_set_eeprom(struct net_device *netdev, hw->nvm.ops.update(hw); igb_set_fw_version(adapter); +out: kfree(eeprom_buff); return ret_val; } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 58872a4c2540..bb3db387d49c 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6947,6 +6947,7 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) struct e1000_hw *hw = &adapter->hw; struct ptp_clock_event event; struct timespec64 ts; + unsigned long flags; if (pin < 0 || pin >= IGB_N_SDP) return; @@ -6954,9 +6955,12 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) if (hw->mac.type == e1000_82580 || hw->mac.type == e1000_i354 || hw->mac.type == e1000_i350) { - s64 ns = rd32(auxstmpl); + u64 ns = rd32(auxstmpl); - ns += ((s64)(rd32(auxstmph) & 0xFF)) << 32; + ns += ((u64)(rd32(auxstmph) & 0xFF)) << 32; + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, ns); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); ts = ns_to_timespec64(ns); } else { ts.tv_nsec = rd32(auxstmpl); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 1c4676882082..fa764190f270 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -254,6 +254,13 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + /* Zero out the buffer ring */ + memset(tx_ring->tx_buffer_info, 0, + sizeof(*tx_ring->tx_buffer_info) * tx_ring->count); + + /* Zero out the descriptor ring */ + memset(tx_ring->desc, 0, tx_ring->size); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -267,7 +274,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) */ void igc_free_tx_resources(struct igc_ring *tx_ring) { - igc_clean_tx_ring(tx_ring); + igc_disable_tx_ring(tx_ring); vfree(tx_ring->tx_buffer_info); tx_ring->tx_buffer_info = NULL; @@ -6723,6 +6730,9 @@ static void igc_remove(struct pci_dev *pdev) igc_ptp_stop(adapter); + pci_disable_ptm(pdev); + pci_clear_master(pdev); + set_bit(__IGC_DOWN, &adapter->state); del_timer_sync(&adapter->watchdog_timer); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index e1853da280f9..43eb6e871351 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -981,6 +981,9 @@ int octep_device_setup(struct octep_device *oct) oct->mmio[i].hw_addr = ioremap(pci_resource_start(oct->pdev, i * 2), pci_resource_len(oct->pdev, i * 2)); + if (!oct->mmio[i].hw_addr) + goto unmap_prev; + oct->mmio[i].mapped = 1; } @@ -1015,7 +1018,9 @@ int octep_device_setup(struct octep_device *oct) return 0; unsupported_dev: - for (i = 0; i < OCTEP_MMIO_REGIONS; i++) + i = OCTEP_MMIO_REGIONS; +unmap_prev: + while (i--) iounmap(oct->mmio[i].hw_addr); kfree(oct->conf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 4ad707e758b9..f01d057ad025 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1878,7 +1878,8 @@ static int nix_check_txschq_alloc_req(struct rvu *rvu, int lvl, u16 pcifunc, free_cnt = rvu_rsrc_free_count(&txsch->schq); } - if (free_cnt < req_schq || req_schq > MAX_TXSCHQ_PER_FUNC) + if (free_cnt < req_schq || req->schq[lvl] > MAX_TXSCHQ_PER_FUNC || + req->schq_contig[lvl] > MAX_TXSCHQ_PER_FUNC) return NIX_AF_ERR_TLX_ALLOC_FAIL; /* If contiguous queues are needed, check for availability */ @@ -4080,10 +4081,6 @@ int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, static u64 rvu_get_lbk_link_credits(struct rvu *rvu, u16 lbk_max_frs) { - /* CN10k supports 72KB FIFO size and max packet size of 64k */ - if (rvu->hw->lbk_bufsize == 0x12000) - return (rvu->hw->lbk_bufsize - lbk_max_frs) / 16; - return 1600; /* 16 * max LBK datarate = 16 * 100Gbps */ } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 51209119f0f2..9f11c1e40737 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1164,10 +1164,8 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i { struct npc_exact_table *table; u16 *cnt, old_cnt; - bool promisc; table = rvu->hw->table; - promisc = table->promisc_mode[drop_mcam_idx]; cnt = &table->cnt_cmd_rules[drop_mcam_idx]; old_cnt = *cnt; @@ -1179,16 +1177,13 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i *enable_or_disable_cam = false; - if (promisc) - goto done; - - /* If all rules are deleted and not already in promisc mode; disable cam */ + /* If all rules are deleted, disable cam */ if (!*cnt && val < 0) { *enable_or_disable_cam = true; goto done; } - /* If rule got added and not already in promisc mode; enable cam */ + /* If rule got added, enable cam */ if (!old_cnt && val > 0) { *enable_or_disable_cam = true; goto done; @@ -1443,7 +1438,6 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc) u32 drop_mcam_idx; bool *promisc; bool rc; - u32 cnt; table = rvu->hw->table; @@ -1466,17 +1460,8 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc) return LMAC_AF_ERR_INVALID_PARAM; } *promisc = false; - cnt = __rvu_npc_exact_cmd_rules_cnt_update(rvu, drop_mcam_idx, 0, NULL); mutex_unlock(&table->lock); - /* If no dmac filter entries configured, disable drop rule */ - if (!cnt) - rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, false); - else - rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, !*promisc); - - dev_dbg(rvu->dev, "%s: disabled promisc mode (cgx=%d lmac=%d, cnt=%d)\n", - __func__, cgx_id, lmac_id, cnt); return 0; } @@ -1494,7 +1479,6 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc) u32 drop_mcam_idx; bool *promisc; bool rc; - u32 cnt; table = rvu->hw->table; @@ -1517,17 +1501,8 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc) return LMAC_AF_ERR_INVALID_PARAM; } *promisc = true; - cnt = __rvu_npc_exact_cmd_rules_cnt_update(rvu, drop_mcam_idx, 0, NULL); mutex_unlock(&table->lock); - /* If no dmac filter entries configured, disable drop rule */ - if (!cnt) - rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, false); - else - rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX, !*promisc); - - dev_dbg(rvu->dev, "%s: Enabled promisc mode (cgx=%d lmac=%d cnt=%d)\n", - __func__, cgx_id, lmac_id, cnt); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 9c94807097cb..5ce28ff7685f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -732,7 +732,8 @@ static void mlx5e_rx_compute_wqe_bulk_params(struct mlx5e_params *params, static int mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - struct mlx5e_rq_frags_info *info) + struct mlx5e_rq_frags_info *info, + u32 *xdp_frag_size) { u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu); int frag_size_max = DEFAULT_FRAG_SIZE; @@ -845,6 +846,8 @@ out: info->log_num_frags = order_base_2(info->num_frags); + *xdp_frag_size = info->num_frags > 1 && params->xdp_prog ? PAGE_SIZE : 0; + return 0; } @@ -989,7 +992,8 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } default: /* MLX5_WQ_TYPE_CYCLIC */ MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames); - err = mlx5e_build_rq_frags_info(mdev, params, xsk, ¶m->frags_info); + err = mlx5e_build_rq_frags_info(mdev, params, xsk, ¶m->frags_info, + ¶m->xdp_frag_size); if (err) return err; ndsegs = param->frags_info.num_frags; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index a5d20f6d6d9c..6800949dafbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -24,6 +24,7 @@ struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; struct mlx5_wq_param wq; struct mlx5e_rq_frags_info frags_info; + u32 xdp_frag_size; }; struct mlx5e_sq_param { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index ead38ef69483..a254e728ac95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2021,6 +2021,8 @@ void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr) { + if (!attr->ct_attr.ft) /* no ct action, return */ + return; if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */ return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index ed279f450976..36826b582484 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -86,7 +86,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c, if (err) return err; - return xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix, 0); + return xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix, c->napi.napi_id); } static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 55b38544422f..891d39b4bfd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -61,16 +61,19 @@ static void mlx5e_ipsec_handle_tx_limit(struct work_struct *_work) struct mlx5e_ipsec_sa_entry *sa_entry = dwork->sa_entry; struct xfrm_state *x = sa_entry->x; - spin_lock(&x->lock); + if (sa_entry->attrs.drop) + return; + + spin_lock_bh(&x->lock); xfrm_state_check_expire(x); if (x->km.state == XFRM_STATE_EXPIRED) { sa_entry->attrs.drop = true; - mlx5e_accel_ipsec_fs_modify(sa_entry); - } - spin_unlock(&x->lock); + spin_unlock_bh(&x->lock); - if (sa_entry->attrs.drop) + mlx5e_accel_ipsec_fs_modify(sa_entry); return; + } + spin_unlock_bh(&x->lock); queue_delayed_work(sa_entry->ipsec->wq, &dwork->dwork, MLX5_IPSEC_RESCHED); @@ -1040,11 +1043,17 @@ err_fs: return err; } -static void mlx5e_xfrm_free_policy(struct xfrm_policy *x) +static void mlx5e_xfrm_del_policy(struct xfrm_policy *x) { struct mlx5e_ipsec_pol_entry *pol_entry = to_ipsec_pol_entry(x); mlx5e_accel_ipsec_fs_del_pol(pol_entry); +} + +static void mlx5e_xfrm_free_policy(struct xfrm_policy *x) +{ + struct mlx5e_ipsec_pol_entry *pol_entry = to_ipsec_pol_entry(x); + kfree(pol_entry); } @@ -1065,6 +1074,7 @@ static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, + .xdo_dev_policy_delete = mlx5e_xfrm_del_policy, .xdo_dev_policy_free = mlx5e_xfrm_free_policy, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index df90e19066bc..a3554bde3e07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -305,7 +305,17 @@ static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry, } mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &attrs); + + /* It is safe to execute the modify below unlocked since the only flows + * that could affect this HW object, are create, destroy and this work. + * + * Creation flow can't co-exist with this modify work, the destruction + * flow would cancel this work, and this work is a single entity that + * can't conflict with it self. + */ + spin_unlock_bh(&sa_entry->x->lock); mlx5_accel_esp_modify_xfrm(sa_entry, &attrs); + spin_lock_bh(&sa_entry->x->lock); data.data_offset_condition_operand = MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET; @@ -431,7 +441,7 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) aso = sa_entry->ipsec->aso; attrs = &sa_entry->attrs; - spin_lock(&sa_entry->x->lock); + spin_lock_bh(&sa_entry->x->lock); ret = mlx5e_ipsec_aso_query(sa_entry, NULL); if (ret) goto unlock; @@ -447,7 +457,7 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) mlx5e_ipsec_handle_limits(sa_entry); unlock: - spin_unlock(&sa_entry->x->lock); + spin_unlock_bh(&sa_entry->x->lock); kfree(work); } @@ -596,7 +606,8 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, do { ret = mlx5_aso_poll_cq(aso->aso, false); if (ret) - usleep_range(2, 10); + /* We are in atomic context */ + udelay(10); } while (ret && time_is_after_jiffies(expires)); spin_unlock_bh(&aso->lock); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index a7c526ee5024..a5bdf78955d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -641,7 +641,7 @@ static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq) } static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params, - struct mlx5e_rq *rq) + u32 xdp_frag_size, struct mlx5e_rq *rq) { struct mlx5_core_dev *mdev = c->mdev; int err; @@ -665,7 +665,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param if (err) return err; - return xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix, c->napi.napi_id); + return __xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix, c->napi.napi_id, + xdp_frag_size); } static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, @@ -2240,7 +2241,7 @@ static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param { int err; - err = mlx5e_init_rxq_rq(c, params, &c->rq); + err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8a5a8703f0a3..b9b1da751a3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1439,6 +1439,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, mlx5e_hairpin_flow_del(priv, flow); free_flow_post_acts(flow); + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); kvfree(attr->parse_attr); kfree(flow->attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 144e59480686..ec83e6483d1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -511,10 +511,11 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, struct mlx5_flow_rule *dst; void *in_flow_context, *vlan; void *in_match_value; + int reformat_id = 0; unsigned int inlen; int dst_cnt_size; + u32 *in, action; void *in_dests; - u32 *in; int err; if (mlx5_set_extended_dest(dev, fte, &extended_dest)) @@ -553,22 +554,42 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(flow_context, in_flow_context, extended_destination, extended_dest); - if (extended_dest) { - u32 action; - action = fte->action.action & - ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - MLX5_SET(flow_context, in_flow_context, action, action); - } else { - MLX5_SET(flow_context, in_flow_context, action, - fte->action.action); - if (fte->action.pkt_reformat) - MLX5_SET(flow_context, in_flow_context, packet_reformat_id, - fte->action.pkt_reformat->id); + action = fte->action.action; + if (extended_dest) + action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + + MLX5_SET(flow_context, in_flow_context, action, action); + + if (!extended_dest && fte->action.pkt_reformat) { + struct mlx5_pkt_reformat *pkt_reformat = fte->action.pkt_reformat; + + if (pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_SW) { + reformat_id = mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat); + if (reformat_id < 0) { + mlx5_core_err(dev, + "Unsupported SW-owned pkt_reformat type (%d) in FW-owned table\n", + pkt_reformat->reformat_type); + err = reformat_id; + goto err_out; + } + } else { + reformat_id = fte->action.pkt_reformat->id; + } } - if (fte->action.modify_hdr) + + MLX5_SET(flow_context, in_flow_context, packet_reformat_id, (u32)reformat_id); + + if (fte->action.modify_hdr) { + if (fte->action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) { + mlx5_core_err(dev, "Can't use SW-owned modify_hdr in FW-owned table\n"); + err = -EOPNOTSUPP; + goto err_out; + } + MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->action.modify_hdr->id); + } MLX5_SET(flow_context, in_flow_context, encrypt_decrypt_type, fte->action.crypto.type); @@ -885,6 +906,8 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); + pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_FW; + kfree(in); return err; } @@ -969,6 +992,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); + modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_FW; kfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index f137a0611b77..b043190e50a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -54,8 +54,14 @@ struct mlx5_flow_definer { u32 id; }; +enum mlx5_flow_resource_owner { + MLX5_FLOW_RESOURCE_OWNER_FW, + MLX5_FLOW_RESOURCE_OWNER_SW, +}; + struct mlx5_modify_hdr { enum mlx5_flow_namespace_type ns_type; + enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action action; u32 id; @@ -65,6 +71,7 @@ struct mlx5_modify_hdr { struct mlx5_pkt_reformat { enum mlx5_flow_namespace_type ns_type; int reformat_type; /* from mlx5_ifc */ + enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action action; u32 id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 1d879374acaa..229520405d4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -276,18 +276,6 @@ static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) return pci_num_vf(dev->pdev) ? true : false; } -static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) -{ - /* LACP owner conditions: - * 1) Function is physical. - * 2) LAG is supported by FW. - * 3) LAG is managed by driver (currently the only option). - */ - return MLX5_CAP_GEN(dev, vport_group_manager) && - (MLX5_CAP_GEN(dev, num_lag_ports) > 1) && - MLX5_CAP_GEN(dev, lag_master); -} - int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev); static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 843da89a9035..98412bd5a696 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -126,14 +126,22 @@ out: return ret; } -static void irq_release(struct mlx5_irq *irq) +/* mlx5_system_free_irq - Free an IRQ + * @irq: IRQ to free + * + * Free the IRQ and other resources such as rmap from the system. + * BUT doesn't free or remove reference from mlx5. + * This function is very important for the shutdown flow, where we need to + * cleanup system resoruces but keep mlx5 objects alive, + * see mlx5_irq_table_free_irqs(). + */ +static void mlx5_system_free_irq(struct mlx5_irq *irq) { struct mlx5_irq_pool *pool = irq->pool; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif - xa_erase(&pool->irqs, irq->pool_index); /* free_irq requires that affinity_hint and rmap will be cleared before * calling it. To satisfy this requirement, we call * irq_cpu_rmap_remove() to remove the notifier @@ -145,10 +153,18 @@ static void irq_release(struct mlx5_irq *irq) irq_cpu_rmap_remove(rmap, irq->map.virq); #endif - free_cpumask_var(irq->mask); free_irq(irq->map.virq, &irq->nh); if (irq->map.index && pci_msix_can_alloc_dyn(pool->dev->pdev)) pci_msix_free_irq(pool->dev->pdev, irq->map); +} + +static void irq_release(struct mlx5_irq *irq) +{ + struct mlx5_irq_pool *pool = irq->pool; + + xa_erase(&pool->irqs, irq->pool_index); + mlx5_system_free_irq(irq); + free_cpumask_var(irq->mask); kfree(irq); } @@ -565,15 +581,21 @@ void mlx5_irqs_release_vectors(struct mlx5_irq **irqs, int nirqs) int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, struct mlx5_irq **irqs, struct cpu_rmap **rmap) { + struct mlx5_irq_table *table = mlx5_irq_table_get(dev); + struct mlx5_irq_pool *pool = table->pcif_pool; struct irq_affinity_desc af_desc; struct mlx5_irq *irq; + int offset = 1; int i; + if (!pool->xa_num_irqs.max) + offset = 0; + af_desc.is_managed = false; for (i = 0; i < nirqs; i++) { cpumask_clear(&af_desc.mask); cpumask_set_cpu(cpus[i], &af_desc.mask); - irq = mlx5_irq_request(dev, i + 1, &af_desc, rmap); + irq = mlx5_irq_request(dev, i + offset, &af_desc, rmap); if (IS_ERR(irq)) break; irqs[i] = irq; @@ -699,7 +721,8 @@ static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) unsigned long index; xa_for_each(&pool->irqs, index, irq) - free_irq(irq->map.virq, &irq->nh); + mlx5_system_free_irq(irq); + } static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 0eb9a8d7f282..0f783e7906cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -1421,9 +1421,13 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, } case DR_ACTION_TYP_TNL_L3_TO_L2: { - u8 hw_actions[DR_ACTION_CACHE_LINE_SIZE] = {}; + u8 *hw_actions; int ret; + hw_actions = kzalloc(DR_ACTION_CACHE_LINE_SIZE, GFP_KERNEL); + if (!hw_actions) + return -ENOMEM; + ret = mlx5dr_ste_set_action_decap_l3_list(dmn->ste_ctx, data, data_sz, hw_actions, @@ -1431,6 +1435,7 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, &action->rewrite->num_of_actions); if (ret) { mlx5dr_dbg(dmn, "Failed creating decap l3 action list\n"); + kfree(hw_actions); return ret; } @@ -1440,6 +1445,7 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, ret = mlx5dr_ste_alloc_modify_hdr(action); if (ret) { mlx5dr_dbg(dmn, "Failed preparing reformat data\n"); + kfree(hw_actions); return ret; } return 0; @@ -2129,6 +2135,11 @@ mlx5dr_action_create_aso(struct mlx5dr_domain *dmn, u32 obj_id, return action; } +u32 mlx5dr_action_get_pkt_reformat_id(struct mlx5dr_action *action) +{ + return action->reformat->id; +} + int mlx5dr_action_destroy(struct mlx5dr_action *action) { if (WARN_ON_ONCE(refcount_read(&action->refcount) > 1)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 984653756779..cc215beb7436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -331,8 +331,16 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { - bool is_decap = fte->action.pkt_reformat->reformat_type == - MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; + bool is_decap; + + if (fte->action.pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) { + err = -EINVAL; + mlx5dr_err(domain, "FW-owned reformat can't be used in SW rule\n"); + goto free_actions; + } + + is_decap = fte->action.pkt_reformat->reformat_type == + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; if (is_decap) actions[num_actions++] = @@ -661,6 +669,7 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns return -EINVAL; } + pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_SW; pkt_reformat->action.dr_action = action; return 0; @@ -691,6 +700,7 @@ static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns, return -EINVAL; } + modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW; modify_hdr->action.dr_action = action; return 0; @@ -816,6 +826,19 @@ static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns, return steering_caps; } +int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat) +{ + switch (pkt_reformat->reformat_type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + case MLX5_REFORMAT_TYPE_INSERT_HDR: + return mlx5dr_action_get_pkt_reformat_id(pkt_reformat->action.dr_action); + } + return -EOPNOTSUPP; +} + bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) { return mlx5dr_is_supported(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h index d168622063d5..99a3b2eff6b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h @@ -38,6 +38,8 @@ struct mlx5_fs_dr_table { bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev); +int mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat); + const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void); #else @@ -47,6 +49,11 @@ static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) return NULL; } +static inline u32 mlx5_fs_dr_action_get_pkt_reformat_id(struct mlx5_pkt_reformat *pkt_reformat) +{ + return 0; +} + static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) { return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 9afd268a2573..d1c04f43d86d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -150,6 +150,8 @@ mlx5dr_action_create_dest_match_range(struct mlx5dr_domain *dmn, int mlx5dr_action_destroy(struct mlx5dr_action *action); +u32 mlx5dr_action_get_pkt_reformat_id(struct mlx5dr_action *action); + int mlx5dr_definer_get(struct mlx5dr_domain *dmn, u16 format_id, u8 *dw_selectors, u8 *byte_selectors, u8 *match_mask, u32 *definer_id); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index c865a4be05ee..4a1b94e5a8ea 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -582,8 +582,7 @@ qcaspi_spi_thread(void *data) while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); if ((qca->intr_req == qca->intr_svc) && - (qca->txr.skb[qca->txr.head] == NULL) && - (qca->sync == QCASPI_SYNC_READY)) + !qca->txr.skb[qca->txr.head]) schedule(); set_current_state(TASK_RUNNING); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index aace87139cea..fa6d6202b129 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -347,17 +347,6 @@ out: return -ENOMEM; } -static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) -{ - struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - - gq->ring_size = TS_RING_SIZE; - gq->ts_ring = dma_alloc_coherent(&priv->pdev->dev, - sizeof(struct rswitch_ts_desc) * - (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); - return !gq->ts_ring ? -ENOMEM : 0; -} - static void rswitch_desc_set_dptr(struct rswitch_desc *desc, dma_addr_t addr) { desc->dptrl = cpu_to_le32(lower_32_bits(addr)); @@ -533,6 +522,28 @@ static void rswitch_gwca_linkfix_free(struct rswitch_private *priv) gwca->linkfix_table = NULL; } +static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) +{ + struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; + struct rswitch_ts_desc *desc; + + gq->ring_size = TS_RING_SIZE; + gq->ts_ring = dma_alloc_coherent(&priv->pdev->dev, + sizeof(struct rswitch_ts_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + + if (!gq->ts_ring) + return -ENOMEM; + + rswitch_gwca_ts_queue_fill(priv, 0, TS_RING_SIZE); + desc = &gq->ts_ring[gq->ring_size]; + desc->desc.die_dt = DT_LINKFIX; + rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); + INIT_LIST_HEAD(&priv->gwca.ts_info_list); + + return 0; +} + static struct rswitch_gwca_queue *rswitch_gwca_get(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq; @@ -1780,9 +1791,6 @@ static int rswitch_init(struct rswitch_private *priv) if (err < 0) goto err_ts_queue_alloc; - rswitch_gwca_ts_queue_fill(priv, 0, TS_RING_SIZE); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { err = rswitch_device_alloc(priv, i); if (err < 0) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index d30459dbfe8f..b63e47af6365 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -2950,7 +2950,7 @@ static u32 efx_ef10_extract_event_ts(efx_qword_t *event) return tstamp; } -static void +static int efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) { struct efx_nic *efx = channel->efx; @@ -2958,13 +2958,14 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) unsigned int tx_ev_desc_ptr; unsigned int tx_ev_q_label; unsigned int tx_ev_type; + int work_done; u64 ts_part; if (unlikely(READ_ONCE(efx->reset_pending))) - return; + return 0; if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT))) - return; + return 0; /* Get the transmit queue */ tx_ev_q_label = EFX_QWORD_FIELD(*event, ESF_DZ_TX_QLABEL); @@ -2973,8 +2974,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) if (!tx_queue->timestamping) { /* Transmit completion */ tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, ESF_DZ_TX_DESCR_INDX); - efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask); - return; + return efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask); } /* Transmit timestamps are only available for 8XXX series. They result @@ -3000,6 +3000,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) * fields in the event. */ tx_ev_type = EFX_QWORD_FIELD(*event, ESF_EZ_TX_SOFT1); + work_done = 0; switch (tx_ev_type) { case TX_TIMESTAMP_EVENT_TX_EV_COMPLETION: @@ -3016,6 +3017,7 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) tx_queue->completed_timestamp_major = ts_part; efx_xmit_done_single(tx_queue); + work_done = 1; break; default: @@ -3026,6 +3028,8 @@ efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) EFX_QWORD_VAL(*event)); break; } + + return work_done; } static void @@ -3081,13 +3085,16 @@ static void efx_ef10_handle_driver_generated_event(struct efx_channel *channel, } } +#define EFX_NAPI_MAX_TX 512 + static int efx_ef10_ev_process(struct efx_channel *channel, int quota) { struct efx_nic *efx = channel->efx; efx_qword_t event, *p_event; unsigned int read_ptr; - int ev_code; + int spent_tx = 0; int spent = 0; + int ev_code; if (quota <= 0) return spent; @@ -3126,7 +3133,11 @@ static int efx_ef10_ev_process(struct efx_channel *channel, int quota) } break; case ESE_DZ_EV_CODE_TX_EV: - efx_ef10_handle_tx_event(channel, &event); + spent_tx += efx_ef10_handle_tx_event(channel, &event); + if (spent_tx >= EFX_NAPI_MAX_TX) { + spent = quota; + goto out; + } break; case ESE_DZ_EV_CODE_DRIVER_EV: efx_ef10_handle_driver_event(channel, &event); diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 4dc643b0d2db..7adde9639c8a 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -253,6 +253,8 @@ static void ef100_ev_read_ack(struct efx_channel *channel) efx_reg(channel->efx, ER_GZ_EVQ_INT_PRIME)); } +#define EFX_NAPI_MAX_TX 512 + static int ef100_ev_process(struct efx_channel *channel, int quota) { struct efx_nic *efx = channel->efx; @@ -260,6 +262,7 @@ static int ef100_ev_process(struct efx_channel *channel, int quota) bool evq_phase, old_evq_phase; unsigned int read_ptr; efx_qword_t *p_event; + int spent_tx = 0; int spent = 0; bool ev_phase; int ev_type; @@ -295,7 +298,9 @@ static int ef100_ev_process(struct efx_channel *channel, int quota) efx_mcdi_process_event(channel, p_event); break; case ESE_GZ_EF100_EV_TX_COMPLETION: - ef100_ev_tx(channel, p_event); + spent_tx += ef100_ev_tx(channel, p_event); + if (spent_tx >= EFX_NAPI_MAX_TX) + spent = quota; break; case ESE_GZ_EF100_EV_DRIVER: netif_info(efx, drv, efx->net_dev, diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index 29ffaf35559d..849e5555bd12 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -346,7 +346,7 @@ void ef100_tx_write(struct efx_tx_queue *tx_queue) ef100_tx_push_buffers(tx_queue); } -void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) +int ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) { unsigned int tx_done = EFX_QWORD_FIELD(*p_event, ESF_GZ_EV_TXCMPL_NUM_DESC); @@ -357,7 +357,7 @@ void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event) unsigned int tx_index = (tx_queue->read_count + tx_done - 1) & tx_queue->ptr_mask; - efx_xmit_done(tx_queue, tx_index); + return efx_xmit_done(tx_queue, tx_index); } /* Add a socket buffer to a TX queue diff --git a/drivers/net/ethernet/sfc/ef100_tx.h b/drivers/net/ethernet/sfc/ef100_tx.h index e9e11540fcde..d9a0819c5a72 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.h +++ b/drivers/net/ethernet/sfc/ef100_tx.h @@ -20,7 +20,7 @@ void ef100_tx_init(struct efx_tx_queue *tx_queue); void ef100_tx_write(struct efx_tx_queue *tx_queue); unsigned int ef100_tx_max_skb_descs(struct efx_nic *efx); -void ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event); +int ef100_ev_tx(struct efx_channel *channel, const efx_qword_t *p_event); netdev_tx_t ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); int __ef100_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb, diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index fcea3ea809d7..41b33a75333c 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -301,6 +301,7 @@ int efx_probe_interrupts(struct efx_nic *efx) efx->tx_channel_offset = 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; rc = pci_enable_msi(efx->pci_dev); if (rc == 0) { efx_get_channel(efx, 0)->irq = efx->pci_dev->irq; @@ -322,6 +323,7 @@ int efx_probe_interrupts(struct efx_nic *efx) efx->tx_channel_offset = efx_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; efx->legacy_irq = efx->pci_dev->irq; } diff --git a/drivers/net/ethernet/sfc/siena/efx_channels.c b/drivers/net/ethernet/sfc/siena/efx_channels.c index 06ed74994e36..1776f7f8a7a9 100644 --- a/drivers/net/ethernet/sfc/siena/efx_channels.c +++ b/drivers/net/ethernet/sfc/siena/efx_channels.c @@ -302,6 +302,7 @@ int efx_siena_probe_interrupts(struct efx_nic *efx) efx->tx_channel_offset = 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; rc = pci_enable_msi(efx->pci_dev); if (rc == 0) { efx_get_channel(efx, 0)->irq = efx->pci_dev->irq; @@ -323,6 +324,7 @@ int efx_siena_probe_interrupts(struct efx_nic *efx) efx->tx_channel_offset = efx_siena_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; efx->legacy_irq = efx->pci_dev->irq; } diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index 67e789b96c43..755aa92bf823 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -249,7 +249,7 @@ void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue) } } -void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) +int efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) { unsigned int fill_level, pkts_compl = 0, bytes_compl = 0; unsigned int efv_pkts_compl = 0; @@ -279,6 +279,8 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index) } efx_xmit_done_check_empty(tx_queue); + + return pkts_compl + efv_pkts_compl; } /* Remove buffers put into a tx_queue for the current packet. diff --git a/drivers/net/ethernet/sfc/tx_common.h b/drivers/net/ethernet/sfc/tx_common.h index d87aecbc7bf1..1e9f42938aac 100644 --- a/drivers/net/ethernet/sfc/tx_common.h +++ b/drivers/net/ethernet/sfc/tx_common.h @@ -28,7 +28,7 @@ static inline bool efx_tx_buffer_in_use(struct efx_tx_buffer *buffer) } void efx_xmit_done_check_empty(struct efx_tx_queue *tx_queue); -void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); +int efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); void efx_enqueue_unwind(struct efx_tx_queue *tx_queue, unsigned int insert_count); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 52cab9de05f2..87510951f4e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3873,7 +3873,6 @@ irq_error: stmmac_hw_teardown(dev); init_error: - free_dma_desc_resources(priv, &priv->dma_conf); phylink_disconnect_phy(priv->phylink); init_phy_error: pm_runtime_put(priv->device); @@ -3891,6 +3890,9 @@ static int stmmac_open(struct net_device *dev) return PTR_ERR(dma_conf); ret = __stmmac_open(dev, dma_conf); + if (ret) + free_dma_desc_resources(priv, dma_conf); + kfree(dma_conf); return ret; } @@ -5633,12 +5635,15 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu) stmmac_release(dev); ret = __stmmac_open(dev, dma_conf); - kfree(dma_conf); if (ret) { + free_dma_desc_resources(priv, dma_conf); + kfree(dma_conf); netdev_err(priv->dev, "failed reopening the interface after MTU change\n"); return ret; } + kfree(dma_conf); + stmmac_set_rx_mode(dev); } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 11cbcd9e2c72..bebcfd5e6b57 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2068,7 +2068,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* Initialize the Serdes PHY for the port */ ret = am65_cpsw_init_serdes_phy(dev, port_np, port); if (ret) - return ret; + goto of_node_put; port->slave.mac_only = of_property_read_bool(port_np, "ti,mac-only"); diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index f9972b8140f9..a03490ba2e5b 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1348,3 +1348,5 @@ module_spi_driver(adf7242_driver); MODULE_AUTHOR("Michael Hennerich <michael.hennerich@analog.com>"); MODULE_DESCRIPTION("ADF7242 IEEE802.15.4 Transceiver Driver"); MODULE_LICENSE("GPL"); + +MODULE_FIRMWARE(FIRMWARE); diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 8445c2189d11..31cba9aa7636 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -685,7 +685,7 @@ static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info) static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) { struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1]; - struct hwsim_edge_info *einfo; + struct hwsim_edge_info *einfo, *einfo_old; struct hwsim_phy *phy_v0; struct hwsim_edge *e; u32 v0, v1; @@ -723,8 +723,10 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) list_for_each_entry_rcu(e, &phy_v0->edges, list) { if (e->endpoint->idx == v1) { einfo->lqi = lqi; - rcu_assign_pointer(e->info, einfo); + einfo_old = rcu_replace_pointer(e->info, einfo, + lockdep_is_held(&hwsim_phys_lock)); rcu_read_unlock(); + kfree_rcu(einfo_old, rcu); mutex_unlock(&hwsim_phys_lock); return 0; } diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c index 71712ea25403..d5b05e803219 100644 --- a/drivers/net/ipvlan/ipvlan_l3s.c +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -102,6 +102,10 @@ static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, skb->dev = addr->master->dev; skb->skb_iif = skb->dev->ifindex; +#if IS_ENABLED(CONFIG_IPV6) + if (addr->atype == IPVL_IPV6) + IP6CB(skb)->iif = skb->dev->ifindex; +#endif len = skb->len + ETH_HLEN; ipvlan_count_rx(addr->master, len, true, false); out: diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 3427993f94f7..984dfa5d6c11 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3997,17 +3997,15 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) return -ENOMEM; secy->tx_sc.stats = netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats); - if (!secy->tx_sc.stats) { - free_percpu(macsec->stats); + if (!secy->tx_sc.stats) return -ENOMEM; - } secy->tx_sc.md_dst = metadata_dst_alloc(0, METADATA_MACSEC, GFP_KERNEL); - if (!secy->tx_sc.md_dst) { - free_percpu(secy->tx_sc.stats); - free_percpu(macsec->stats); + if (!secy->tx_sc.md_dst) + /* macsec and secy percpu stats will be freed when unregistering + * net_device in macsec_free_netdev() + */ return -ENOMEM; - } if (sci == MACSEC_UNDEF_SCI) sci = dev_to_sci(dev, MACSEC_PORT_ES); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 76f5a2402fb0..e397e7d642d9 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -936,7 +936,7 @@ static int dp83867_phy_reset(struct phy_device *phydev) { int err; - err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET); if (err < 0) return err; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 389f33a12534..8b3618d3da4a 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -1287,7 +1287,7 @@ EXPORT_SYMBOL_GPL(mdiobus_modify_changed); * @mask: bit mask of bits to clear * @set: bit mask of bits to set */ -int mdiobus_c45_modify_changed(struct mii_bus *bus, int devad, int addr, +int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad, u32 regnum, u16 mask, u16 set) { int err; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 17d0d0555a79..53598210be6c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3021,6 +3021,15 @@ static int phy_led_blink_set(struct led_classdev *led_cdev, return err; } +static void phy_leds_unregister(struct phy_device *phydev) +{ + struct phy_led *phyled; + + list_for_each_entry(phyled, &phydev->leds, list) { + led_classdev_unregister(&phyled->led_cdev); + } +} + static int of_phy_led(struct phy_device *phydev, struct device_node *led) { @@ -3054,7 +3063,7 @@ static int of_phy_led(struct phy_device *phydev, init_data.fwnode = of_fwnode_handle(led); init_data.devname_mandatory = true; - err = devm_led_classdev_register_ext(dev, cdev, &init_data); + err = led_classdev_register_ext(dev, cdev, &init_data); if (err) return err; @@ -3083,6 +3092,7 @@ static int of_phy_leds(struct phy_device *phydev) err = of_phy_led(phydev, led); if (err) { of_node_put(led); + phy_leds_unregister(phydev); return err; } } @@ -3305,6 +3315,9 @@ static int phy_remove(struct device *dev) cancel_delayed_work_sync(&phydev->state_queue); + if (IS_ENABLED(CONFIG_PHYLIB_LEDS)) + phy_leds_unregister(phydev); + phydev->state = PHY_DOWN; sfp_bus_del_upstream(phydev->sfp_bus); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index b4831110003c..5efdeb59f4b2 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -188,6 +188,7 @@ static int phylink_interface_max_speed(phy_interface_t interface) case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_QUSGMII: case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_GMII: return SPEED_1000; @@ -204,7 +205,6 @@ static int phylink_interface_max_speed(phy_interface_t interface) case PHY_INTERFACE_MODE_10GBASER: case PHY_INTERFACE_MODE_10GKR: case PHY_INTERFACE_MODE_USXGMII: - case PHY_INTERFACE_MODE_QUSGMII: return SPEED_10000; case PHY_INTERFACE_MODE_25GBASER: @@ -3299,6 +3299,41 @@ void phylink_decode_usxgmii_word(struct phylink_link_state *state, EXPORT_SYMBOL_GPL(phylink_decode_usxgmii_word); /** + * phylink_decode_usgmii_word() - decode the USGMII word from a MAC PCS + * @state: a pointer to a struct phylink_link_state. + * @lpa: a 16 bit value which stores the USGMII auto-negotiation word + * + * Helper for MAC PCS supporting the USGMII protocol and the auto-negotiation + * code word. Decode the USGMII code word and populate the corresponding fields + * (speed, duplex) into the phylink_link_state structure. The structure for this + * word is the same as the USXGMII word, except it only supports speeds up to + * 1Gbps. + */ +static void phylink_decode_usgmii_word(struct phylink_link_state *state, + uint16_t lpa) +{ + switch (lpa & MDIO_USXGMII_SPD_MASK) { + case MDIO_USXGMII_10: + state->speed = SPEED_10; + break; + case MDIO_USXGMII_100: + state->speed = SPEED_100; + break; + case MDIO_USXGMII_1000: + state->speed = SPEED_1000; + break; + default: + state->link = false; + return; + } + + if (lpa & MDIO_USXGMII_FULL_DUPLEX) + state->duplex = DUPLEX_FULL; + else + state->duplex = DUPLEX_HALF; +} + +/** * phylink_mii_c22_pcs_decode_state() - Decode MAC PCS state from MII registers * @state: a pointer to a &struct phylink_link_state. * @bmsr: The value of the %MII_BMSR register @@ -3335,9 +3370,11 @@ void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: - case PHY_INTERFACE_MODE_QUSGMII: phylink_decode_sgmii_word(state, lpa); break; + case PHY_INTERFACE_MODE_QUSGMII: + phylink_decode_usgmii_word(state, lpa); + break; default: state->link = false; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index f1865d047971..2e7c7b0cdc54 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1220,7 +1220,9 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x05c6, 0x9080, 8)}, {QMI_FIXED_INTF(0x05c6, 0x9083, 3)}, {QMI_FIXED_INTF(0x05c6, 0x9084, 4)}, + {QMI_QUIRK_SET_DTR(0x05c6, 0x9091, 2)}, /* Compal RXM-G1 */ {QMI_FIXED_INTF(0x05c6, 0x90b2, 3)}, /* ublox R410M */ + {QMI_QUIRK_SET_DTR(0x05c6, 0x90db, 2)}, /* Compal RXM-G1 */ {QMI_FIXED_INTF(0x05c6, 0x920d, 0)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 5)}, {QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)}, /* YUGA CLM920-NC5 */ diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index d62a904d2e42..56326f38fe8a 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -384,6 +384,9 @@ static int lapbeth_new_device(struct net_device *dev) ASSERT_RTNL(); + if (dev->type != ARPHRD_ETHER) + return -EINVAL; + ndev = alloc_netdev(sizeof(*lapbeth), "lapb%d", NET_NAME_UNKNOWN, lapbeth_setup); if (!ndev) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 23266d0c9ce4..9a20468345e4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2692,7 +2692,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, lq_sta = mvm_sta; - spin_lock(&lq_sta->pers.lock); + spin_lock_bh(&lq_sta->pers.lock); iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags, info->band, &info->control.rates[0]); info->control.rates[0].count = 1; @@ -2707,7 +2707,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band, &txrc->reported_rate); } - spin_unlock(&lq_sta->pers.lock); + spin_unlock_bh(&lq_sta->pers.lock); } static void *rs_drv_alloc_sta(void *mvm_rate, struct ieee80211_sta *sta, @@ -3264,11 +3264,11 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, /* If it's locked we are in middle of init flow * just wait for next tx status to update the lq_sta data */ - if (!spin_trylock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock)) + if (!spin_trylock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock)) return; __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); - spin_unlock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); + spin_unlock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); } #ifdef CONFIG_MAC80211_DEBUGFS @@ -4117,9 +4117,9 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, } else { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - spin_lock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); + spin_lock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); rs_drv_rate_init(mvm, sta, band); - spin_unlock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); + spin_unlock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock); } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index dba112394838..79115eb1c285 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -548,6 +548,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x54F0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x7A70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), + IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), + IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name), IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma_a0_gf4_a0, iwl_ax411_killer_1690s_name), diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index d6b166fc5c0e..bff46f7ca59f 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -626,14 +626,12 @@ static void mux_dl_adb_decode(struct iosm_mux *ipc_mux, if (adth->signature != cpu_to_le32(IOSM_AGGR_MUX_SIG_ADTH)) goto adb_decode_err; - if (le16_to_cpu(adth->table_length) < (sizeof(struct mux_adth) - - sizeof(struct mux_adth_dg))) + if (le16_to_cpu(adth->table_length) < sizeof(struct mux_adth)) goto adb_decode_err; /* Calculate the number of datagrams. */ nr_of_dg = (le16_to_cpu(adth->table_length) - - sizeof(struct mux_adth) + - sizeof(struct mux_adth_dg)) / + sizeof(struct mux_adth)) / sizeof(struct mux_adth_dg); /* Is the datagram table empty ? */ @@ -649,7 +647,7 @@ static void mux_dl_adb_decode(struct iosm_mux *ipc_mux, } /* New aggregated datagram table. */ - dg = &adth->dg; + dg = adth->dg; if (mux_dl_process_dg(ipc_mux, adbh, dg, skb, if_id, nr_of_dg) < 0) goto adb_decode_err; @@ -849,7 +847,7 @@ static void ipc_mux_ul_encode_adth(struct iosm_mux *ipc_mux, adth->if_id = i; adth->table_length = cpu_to_le16(adth_dg_size); adth_dg_size -= offsetof(struct mux_adth, dg); - memcpy(&adth->dg, ul_adb->dg[i], adth_dg_size); + memcpy(adth->dg, ul_adb->dg[i], adth_dg_size); ul_adb->if_cnt++; } @@ -1426,14 +1424,13 @@ static int ipc_mux_get_payload_from_adb(struct iosm_mux *ipc_mux, if (adth->signature == cpu_to_le32(IOSM_AGGR_MUX_SIG_ADTH)) { nr_of_dg = (le16_to_cpu(adth->table_length) - - sizeof(struct mux_adth) + - sizeof(struct mux_adth_dg)) / + sizeof(struct mux_adth)) / sizeof(struct mux_adth_dg); if (nr_of_dg <= 0) return payload_size; - dg = &adth->dg; + dg = adth->dg; for (i = 0; i < nr_of_dg; i++, dg++) { if (le32_to_cpu(dg->datagram_index) < diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h index 5d4e3b89542c..f8df88f816c4 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h @@ -161,7 +161,7 @@ struct mux_adth { u8 opt_ipv4v6; __le32 next_table_index; __le32 reserved2; - struct mux_adth_dg dg; + struct mux_adth_dg dg[]; }; /** diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index f12f903a9dd1..da3e2dce8e70 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -762,3 +762,6 @@ EXPORT_SYMBOL(fdp_nci_remove); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("NFC NCI driver for Intel Fields Peak NFC controller"); MODULE_AUTHOR("Robert Dolca <robert.dolca@intel.com>"); + +MODULE_FIRMWARE(FDP_OTP_PATCH_NAME); +MODULE_FIRMWARE(FDP_RAM_PATCH_NAME); diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index e27202d22c7d..d3fc5063e4be 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_FC) += nvme-fc.o obj-$(CONFIG_NVME_TCP) += nvme-tcp.o obj-$(CONFIG_NVME_APPLE) += nvme-apple.o -nvme-core-y += core.o ioctl.o +nvme-core-y += core.o ioctl.o sysfs.o nvme-core-$(CONFIG_NVME_VERBOSE_ERRORS) += constants.o nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index ea16a0aba679..daf5d144a8ea 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -30,18 +30,18 @@ struct nvme_dhchap_queue_context { u32 s2; u16 transaction; u8 status; + u8 dhgroup_id; u8 hash_id; size_t hash_len; - u8 dhgroup_id; u8 c1[64]; u8 c2[64]; u8 response[64]; u8 *host_response; u8 *ctrl_key; - int ctrl_key_len; u8 *host_key; - int host_key_len; u8 *sess_key; + int ctrl_key_len; + int host_key_len; int sess_key_len; }; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3ec38e2b9173..fdfcf2781c85 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -237,7 +237,7 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_delete_ctrl); -static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) +void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) { /* * Keep a reference until nvme_do_delete_ctrl() complete, @@ -1635,12 +1635,12 @@ static void nvme_ns_release(struct nvme_ns *ns) nvme_put_ns(ns); } -static int nvme_open(struct block_device *bdev, fmode_t mode) +static int nvme_open(struct gendisk *disk, blk_mode_t mode) { - return nvme_ns_open(bdev->bd_disk->private_data); + return nvme_ns_open(disk->private_data); } -static void nvme_release(struct gendisk *disk, fmode_t mode) +static void nvme_release(struct gendisk *disk) { nvme_ns_release(disk->private_data); } @@ -1879,7 +1879,7 @@ static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze)); - unsigned short bs = 1 << ns->lba_shift; + u32 bs = 1U << ns->lba_shift; u32 atomic_bs, phys_bs, io_opt = 0; /* @@ -2300,7 +2300,7 @@ static int nvme_report_zones(struct gendisk *disk, sector_t sector, #define nvme_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ -static const struct block_device_operations nvme_bdev_ops = { +const struct block_device_operations nvme_bdev_ops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, @@ -2835,75 +2835,6 @@ static struct nvme_subsystem *__nvme_find_get_subsystem(const char *subsysnqn) return NULL; } -#define SUBSYS_ATTR_RO(_name, _mode, _show) \ - struct device_attribute subsys_attr_##_name = \ - __ATTR(_name, _mode, _show, NULL) - -static ssize_t nvme_subsys_show_nqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_subsystem *subsys = - container_of(dev, struct nvme_subsystem, dev); - - return sysfs_emit(buf, "%s\n", subsys->subnqn); -} -static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); - -static ssize_t nvme_subsys_show_type(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_subsystem *subsys = - container_of(dev, struct nvme_subsystem, dev); - - switch (subsys->subtype) { - case NVME_NQN_DISC: - return sysfs_emit(buf, "discovery\n"); - case NVME_NQN_NVME: - return sysfs_emit(buf, "nvm\n"); - default: - return sysfs_emit(buf, "reserved\n"); - } -} -static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type); - -#define nvme_subsys_show_str_function(field) \ -static ssize_t subsys_##field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_subsystem *subsys = \ - container_of(dev, struct nvme_subsystem, dev); \ - return sysfs_emit(buf, "%.*s\n", \ - (int)sizeof(subsys->field), subsys->field); \ -} \ -static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show); - -nvme_subsys_show_str_function(model); -nvme_subsys_show_str_function(serial); -nvme_subsys_show_str_function(firmware_rev); - -static struct attribute *nvme_subsys_attrs[] = { - &subsys_attr_model.attr, - &subsys_attr_serial.attr, - &subsys_attr_firmware_rev.attr, - &subsys_attr_subsysnqn.attr, - &subsys_attr_subsystype.attr, -#ifdef CONFIG_NVME_MULTIPATH - &subsys_attr_iopolicy.attr, -#endif - NULL, -}; - -static const struct attribute_group nvme_subsys_attrs_group = { - .attrs = nvme_subsys_attrs, -}; - -static const struct attribute_group *nvme_subsys_attrs_groups[] = { - &nvme_subsys_attrs_group, - NULL, -}; - static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl) { return ctrl->opts && ctrl->opts->discovery_nqn; @@ -3108,7 +3039,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = 0; if (ctrl->subsys->subtype != NVME_NQN_NVME || - nvme_ctrl_limited_cns(ctrl)) + nvme_ctrl_limited_cns(ctrl) || + test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags)) return 0; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -3130,6 +3062,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); free_data: + if (ret > 0) + set_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags); kfree(id); return ret; } @@ -3437,586 +3371,6 @@ static const struct file_operations nvme_dev_fops = { .uring_cmd = nvme_dev_uring_cmd, }; -static ssize_t nvme_sysfs_reset(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - int ret; - - ret = nvme_reset_ctrl_sync(ctrl); - if (ret < 0) - return ret; - return count; -} -static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); - -static ssize_t nvme_sysfs_rescan(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - nvme_queue_scan(ctrl); - return count; -} -static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); - -static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (disk->fops == &nvme_bdev_ops) - return nvme_get_ns_from_dev(dev)->head; - else - return disk->private_data; -} - -static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct nvme_ns_head *head = dev_to_ns_head(dev); - struct nvme_ns_ids *ids = &head->ids; - struct nvme_subsystem *subsys = head->subsys; - int serial_len = sizeof(subsys->serial); - int model_len = sizeof(subsys->model); - - if (!uuid_is_null(&ids->uuid)) - return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid); - - if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return sysfs_emit(buf, "eui.%16phN\n", ids->nguid); - - if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - return sysfs_emit(buf, "eui.%8phN\n", ids->eui64); - - while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' || - subsys->serial[serial_len - 1] == '\0')) - serial_len--; - while (model_len > 0 && (subsys->model[model_len - 1] == ' ' || - subsys->model[model_len - 1] == '\0')) - model_len--; - - return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id, - serial_len, subsys->serial, model_len, subsys->model, - head->ns_id); -} -static DEVICE_ATTR_RO(wwid); - -static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid); -} -static DEVICE_ATTR_RO(nguid); - -static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; - - /* For backward compatibility expose the NGUID to userspace if - * we have no UUID set - */ - if (uuid_is_null(&ids->uuid)) { - dev_warn_ratelimited(dev, - "No UUID available providing old NGUID\n"); - return sysfs_emit(buf, "%pU\n", ids->nguid); - } - return sysfs_emit(buf, "%pU\n", &ids->uuid); -} -static DEVICE_ATTR_RO(uuid); - -static ssize_t eui_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64); -} -static DEVICE_ATTR_RO(eui); - -static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); -} -static DEVICE_ATTR_RO(nsid); - -static struct attribute *nvme_ns_id_attrs[] = { - &dev_attr_wwid.attr, - &dev_attr_uuid.attr, - &dev_attr_nguid.attr, - &dev_attr_eui.attr, - &dev_attr_nsid.attr, -#ifdef CONFIG_NVME_MULTIPATH - &dev_attr_ana_grpid.attr, - &dev_attr_ana_state.attr, -#endif - NULL, -}; - -static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; - - if (a == &dev_attr_uuid.attr) { - if (uuid_is_null(&ids->uuid) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return 0; - } - if (a == &dev_attr_nguid.attr) { - if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return 0; - } - if (a == &dev_attr_eui.attr) { - if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - return 0; - } -#ifdef CONFIG_NVME_MULTIPATH - if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { - if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ - return 0; - if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) - return 0; - } -#endif - return a->mode; -} - -static const struct attribute_group nvme_ns_id_attr_group = { - .attrs = nvme_ns_id_attrs, - .is_visible = nvme_ns_id_attrs_are_visible, -}; - -const struct attribute_group *nvme_ns_id_attr_groups[] = { - &nvme_ns_id_attr_group, - NULL, -}; - -#define nvme_show_str_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sysfs_emit(buf, "%.*s\n", \ - (int)sizeof(ctrl->subsys->field), ctrl->subsys->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -nvme_show_str_function(model); -nvme_show_str_function(serial); -nvme_show_str_function(firmware_rev); - -#define nvme_show_int_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sysfs_emit(buf, "%d\n", ctrl->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -nvme_show_int_function(cntlid); -nvme_show_int_function(numa_node); -nvme_show_int_function(queue_count); -nvme_show_int_function(sqsize); -nvme_show_int_function(kato); - -static ssize_t nvme_sysfs_delete(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) - return -EBUSY; - - if (device_remove_file_self(dev, attr)) - nvme_delete_ctrl_sync(ctrl); - return count; -} -static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); - -static ssize_t nvme_sysfs_show_transport(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->ops->name); -} -static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); - -static ssize_t nvme_sysfs_show_state(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - static const char *const state_name[] = { - [NVME_CTRL_NEW] = "new", - [NVME_CTRL_LIVE] = "live", - [NVME_CTRL_RESETTING] = "resetting", - [NVME_CTRL_CONNECTING] = "connecting", - [NVME_CTRL_DELETING] = "deleting", - [NVME_CTRL_DELETING_NOIO]= "deleting (no IO)", - [NVME_CTRL_DEAD] = "dead", - }; - - if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && - state_name[ctrl->state]) - return sysfs_emit(buf, "%s\n", state_name[ctrl->state]); - - return sysfs_emit(buf, "unknown state\n"); -} - -static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL); - -static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn); -} -static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); - -static ssize_t nvme_sysfs_show_hostnqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn); -} -static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL); - -static ssize_t nvme_sysfs_show_hostid(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id); -} -static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL); - -static ssize_t nvme_sysfs_show_address(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE); -} -static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); - -static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (ctrl->opts->max_reconnects == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", - opts->max_reconnects * opts->reconnect_delay); -} - -static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - int ctrl_loss_tmo, err; - - err = kstrtoint(buf, 10, &ctrl_loss_tmo); - if (err) - return -EINVAL; - - if (ctrl_loss_tmo < 0) - opts->max_reconnects = -1; - else - opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, - opts->reconnect_delay); - return count; -} -static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR, - nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store); - -static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->opts->reconnect_delay == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay); -} - -static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - unsigned int v; - int err; - - err = kstrtou32(buf, 10, &v); - if (err) - return err; - - ctrl->opts->reconnect_delay = v; - return count; -} -static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, - nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store); - -static ssize_t nvme_ctrl_fast_io_fail_tmo_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->opts->fast_io_fail_tmo == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", ctrl->opts->fast_io_fail_tmo); -} - -static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - int fast_io_fail_tmo, err; - - err = kstrtoint(buf, 10, &fast_io_fail_tmo); - if (err) - return -EINVAL; - - if (fast_io_fail_tmo < 0) - opts->fast_io_fail_tmo = -1; - else - opts->fast_io_fail_tmo = fast_io_fail_tmo; - return count; -} -static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR, - nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store); - -static ssize_t cntrltype_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - static const char * const type[] = { - [NVME_CTRL_IO] = "io\n", - [NVME_CTRL_DISC] = "discovery\n", - [NVME_CTRL_ADMIN] = "admin\n", - }; - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->cntrltype > NVME_CTRL_ADMIN || !type[ctrl->cntrltype]) - return sysfs_emit(buf, "reserved\n"); - - return sysfs_emit(buf, type[ctrl->cntrltype]); -} -static DEVICE_ATTR_RO(cntrltype); - -static ssize_t dctype_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - static const char * const type[] = { - [NVME_DCTYPE_NOT_REPORTED] = "none\n", - [NVME_DCTYPE_DDC] = "ddc\n", - [NVME_DCTYPE_CDC] = "cdc\n", - }; - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->dctype > NVME_DCTYPE_CDC || !type[ctrl->dctype]) - return sysfs_emit(buf, "reserved\n"); - - return sysfs_emit(buf, type[ctrl->dctype]); -} -static DEVICE_ATTR_RO(dctype); - -#ifdef CONFIG_NVME_AUTH -static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (!opts->dhchap_secret) - return sysfs_emit(buf, "none\n"); - return sysfs_emit(buf, "%s\n", opts->dhchap_secret); -} - -static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - char *dhchap_secret; - - if (!ctrl->opts->dhchap_secret) - return -EINVAL; - if (count < 7) - return -EINVAL; - if (memcmp(buf, "DHHC-1:", 7)) - return -EINVAL; - - dhchap_secret = kzalloc(count + 1, GFP_KERNEL); - if (!dhchap_secret) - return -ENOMEM; - memcpy(dhchap_secret, buf, count); - nvme_auth_stop(ctrl); - if (strcmp(dhchap_secret, opts->dhchap_secret)) { - struct nvme_dhchap_key *key, *host_key; - int ret; - - ret = nvme_auth_generate_key(dhchap_secret, &key); - if (ret) - return ret; - kfree(opts->dhchap_secret); - opts->dhchap_secret = dhchap_secret; - host_key = ctrl->host_key; - mutex_lock(&ctrl->dhchap_auth_mutex); - ctrl->host_key = key; - mutex_unlock(&ctrl->dhchap_auth_mutex); - nvme_auth_free_key(host_key); - } - /* Start re-authentication */ - dev_info(ctrl->device, "re-authenticating controller\n"); - queue_work(nvme_wq, &ctrl->dhchap_auth_work); - - return count; -} -static DEVICE_ATTR(dhchap_secret, S_IRUGO | S_IWUSR, - nvme_ctrl_dhchap_secret_show, nvme_ctrl_dhchap_secret_store); - -static ssize_t nvme_ctrl_dhchap_ctrl_secret_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (!opts->dhchap_ctrl_secret) - return sysfs_emit(buf, "none\n"); - return sysfs_emit(buf, "%s\n", opts->dhchap_ctrl_secret); -} - -static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - char *dhchap_secret; - - if (!ctrl->opts->dhchap_ctrl_secret) - return -EINVAL; - if (count < 7) - return -EINVAL; - if (memcmp(buf, "DHHC-1:", 7)) - return -EINVAL; - - dhchap_secret = kzalloc(count + 1, GFP_KERNEL); - if (!dhchap_secret) - return -ENOMEM; - memcpy(dhchap_secret, buf, count); - nvme_auth_stop(ctrl); - if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) { - struct nvme_dhchap_key *key, *ctrl_key; - int ret; - - ret = nvme_auth_generate_key(dhchap_secret, &key); - if (ret) - return ret; - kfree(opts->dhchap_ctrl_secret); - opts->dhchap_ctrl_secret = dhchap_secret; - ctrl_key = ctrl->ctrl_key; - mutex_lock(&ctrl->dhchap_auth_mutex); - ctrl->ctrl_key = key; - mutex_unlock(&ctrl->dhchap_auth_mutex); - nvme_auth_free_key(ctrl_key); - } - /* Start re-authentication */ - dev_info(ctrl->device, "re-authenticating controller\n"); - queue_work(nvme_wq, &ctrl->dhchap_auth_work); - - return count; -} -static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR, - nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store); -#endif - -static struct attribute *nvme_dev_attrs[] = { - &dev_attr_reset_controller.attr, - &dev_attr_rescan_controller.attr, - &dev_attr_model.attr, - &dev_attr_serial.attr, - &dev_attr_firmware_rev.attr, - &dev_attr_cntlid.attr, - &dev_attr_delete_controller.attr, - &dev_attr_transport.attr, - &dev_attr_subsysnqn.attr, - &dev_attr_address.attr, - &dev_attr_state.attr, - &dev_attr_numa_node.attr, - &dev_attr_queue_count.attr, - &dev_attr_sqsize.attr, - &dev_attr_hostnqn.attr, - &dev_attr_hostid.attr, - &dev_attr_ctrl_loss_tmo.attr, - &dev_attr_reconnect_delay.attr, - &dev_attr_fast_io_fail_tmo.attr, - &dev_attr_kato.attr, - &dev_attr_cntrltype.attr, - &dev_attr_dctype.attr, -#ifdef CONFIG_NVME_AUTH - &dev_attr_dhchap_secret.attr, - &dev_attr_dhchap_ctrl_secret.attr, -#endif - NULL -}; - -static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) - return 0; - if (a == &dev_attr_address.attr && !ctrl->ops->get_address) - return 0; - if (a == &dev_attr_hostnqn.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_hostid.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) - return 0; -#ifdef CONFIG_NVME_AUTH - if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) - return 0; -#endif - - return a->mode; -} - -const struct attribute_group nvme_dev_attrs_group = { - .attrs = nvme_dev_attrs, - .is_visible = nvme_dev_attrs_are_visible, -}; -EXPORT_SYMBOL_GPL(nvme_dev_attrs_group); - -static const struct attribute_group *nvme_dev_attr_groups[] = { - &nvme_dev_attrs_group, - NULL, -}; - static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, unsigned nsid) { @@ -4256,7 +3610,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) goto out_put_ns_head; } - if (!multipath && !list_empty(&head->list)) { + if (!multipath) { dev_warn(ctrl->device, "Found shared namespace %d, but multipathing not supported.\n", info->nsid); @@ -4357,7 +3711,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) * instance as shared namespaces will show up as multiple block * devices. */ - if (ns->head->disk) { + if (nvme_ns_head_multipath(ns->head)) { sprintf(disk->disk_name, "nvme%dc%dn%d", ctrl->subsys->instance, ctrl->instance, ns->head->instance); disk->flags |= GENHD_FL_HIDDEN; @@ -5243,6 +4597,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_cdev: + nvme_fault_inject_fini(&ctrl->fault_inject); + dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); out_free_name: nvme_put_ctrl(ctrl); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 0069ebff85df..8175d49f2909 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -21,35 +21,60 @@ static DEFINE_MUTEX(nvmf_hosts_mutex); static struct nvmf_host *nvmf_default_host; -static struct nvmf_host *__nvmf_host_find(const char *hostnqn) +static struct nvmf_host *nvmf_host_alloc(const char *hostnqn, uuid_t *id) { struct nvmf_host *host; - list_for_each_entry(host, &nvmf_hosts, list) { - if (!strcmp(host->nqn, hostnqn)) - return host; - } + host = kmalloc(sizeof(*host), GFP_KERNEL); + if (!host) + return NULL; - return NULL; + kref_init(&host->ref); + uuid_copy(&host->id, id); + strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE); + + return host; } -static struct nvmf_host *nvmf_host_add(const char *hostnqn) +static struct nvmf_host *nvmf_host_add(const char *hostnqn, uuid_t *id) { struct nvmf_host *host; mutex_lock(&nvmf_hosts_mutex); - host = __nvmf_host_find(hostnqn); - if (host) { - kref_get(&host->ref); - goto out_unlock; + + /* + * We have defined a host as how it is perceived by the target. + * Therefore, we don't allow different Host NQNs with the same Host ID. + * Similarly, we do not allow the usage of the same Host NQN with + * different Host IDs. This'll maintain unambiguous host identification. + */ + list_for_each_entry(host, &nvmf_hosts, list) { + bool same_hostnqn = !strcmp(host->nqn, hostnqn); + bool same_hostid = uuid_equal(&host->id, id); + + if (same_hostnqn && same_hostid) { + kref_get(&host->ref); + goto out_unlock; + } + if (same_hostnqn) { + pr_err("found same hostnqn %s but different hostid %pUb\n", + hostnqn, id); + host = ERR_PTR(-EINVAL); + goto out_unlock; + } + if (same_hostid) { + pr_err("found same hostid %pUb but different hostnqn %s\n", + id, hostnqn); + host = ERR_PTR(-EINVAL); + goto out_unlock; + } } - host = kmalloc(sizeof(*host), GFP_KERNEL); - if (!host) + host = nvmf_host_alloc(hostnqn, id); + if (!host) { + host = ERR_PTR(-ENOMEM); goto out_unlock; - - kref_init(&host->ref); - strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE); + } list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -60,16 +85,17 @@ out_unlock: static struct nvmf_host *nvmf_host_default(void) { struct nvmf_host *host; + char nqn[NVMF_NQN_SIZE]; + uuid_t id; - host = kmalloc(sizeof(*host), GFP_KERNEL); + uuid_gen(&id); + snprintf(nqn, NVMF_NQN_SIZE, + "nqn.2014-08.org.nvmexpress:uuid:%pUb", &id); + + host = nvmf_host_alloc(nqn, &id); if (!host) return NULL; - kref_init(&host->ref); - uuid_gen(&host->id); - snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id); - mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); mutex_unlock(&nvmf_hosts_mutex); @@ -349,6 +375,45 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, } } +static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl, + u16 cntlid) +{ + struct nvmf_connect_data *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return NULL; + + uuid_copy(&data->hostid, &ctrl->opts->host->id); + data->cntlid = cpu_to_le16(cntlid); + strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); + strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); + + return data; +} + +static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid, + struct nvme_command *cmd) +{ + cmd->connect.opcode = nvme_fabrics_command; + cmd->connect.fctype = nvme_fabrics_type_connect; + cmd->connect.qid = cpu_to_le16(qid); + + if (qid) { + cmd->connect.sqsize = cpu_to_le16(ctrl->sqsize); + } else { + cmd->connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); + + /* + * set keep-alive timeout in seconds granularity (ms * 1000) + */ + cmd->connect.kato = cpu_to_le32(ctrl->kato * 1000); + } + + if (ctrl->opts->disable_sqflow) + cmd->connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; +} + /** * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect" * API function. @@ -377,28 +442,12 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) int ret; u32 result; - cmd.connect.opcode = nvme_fabrics_command; - cmd.connect.fctype = nvme_fabrics_type_connect; - cmd.connect.qid = 0; - cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); - - /* - * Set keep-alive timeout in seconds granularity (ms * 1000) - */ - cmd.connect.kato = cpu_to_le32(ctrl->kato * 1000); - - if (ctrl->opts->disable_sqflow) - cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; + nvmf_connect_cmd_prep(ctrl, 0, &cmd); - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = nvmf_connect_data_prep(ctrl, 0xffff); if (!data) return -ENOMEM; - uuid_copy(&data->hostid, &ctrl->opts->host->id); - data->cntlid = cpu_to_le16(0xffff); - strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); - strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); - ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, data, sizeof(*data), NVME_QID_ANY, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); @@ -468,23 +517,12 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) int ret; u32 result; - cmd.connect.opcode = nvme_fabrics_command; - cmd.connect.fctype = nvme_fabrics_type_connect; - cmd.connect.qid = cpu_to_le16(qid); - cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); + nvmf_connect_cmd_prep(ctrl, qid, &cmd); - if (ctrl->opts->disable_sqflow) - cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; - - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = nvmf_connect_data_prep(ctrl, ctrl->cntlid); if (!data) return -ENOMEM; - uuid_copy(&data->hostid, &ctrl->opts->host->id); - data->cntlid = cpu_to_le16(ctrl->cntlid); - strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); - strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); - ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res, data, sizeof(*data), qid, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); @@ -621,6 +659,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, size_t nqnlen = 0; int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO; uuid_t hostid; + char hostnqn[NVMF_NQN_SIZE]; /* Set defaults */ opts->queue_size = NVMF_DEF_QUEUE_SIZE; @@ -637,7 +676,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, if (!options) return -ENOMEM; - uuid_gen(&hostid); + /* use default host if not given by user space */ + uuid_copy(&hostid, &nvmf_default_host->id); + strscpy(hostnqn, nvmf_default_host->nqn, NVMF_NQN_SIZE); while ((p = strsep(&o, ",\n")) != NULL) { if (!*p) @@ -783,12 +824,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, ret = -EINVAL; goto out; } - opts->host = nvmf_host_add(p); + strscpy(hostnqn, p, NVMF_NQN_SIZE); kfree(p); - if (!opts->host) { - ret = -ENOMEM; - goto out; - } break; case NVMF_OPT_RECONNECT_DELAY: if (match_int(args, &token)) { @@ -945,18 +982,94 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->fast_io_fail_tmo, ctrl_loss_tmo); } - if (!opts->host) { - kref_get(&nvmf_default_host->ref); - opts->host = nvmf_default_host; + opts->host = nvmf_host_add(hostnqn, &hostid); + if (IS_ERR(opts->host)) { + ret = PTR_ERR(opts->host); + opts->host = NULL; + goto out; } - uuid_copy(&opts->host->id, &hostid); - out: kfree(options); return ret; } +void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, + u32 io_queues[HCTX_MAX_TYPES]) +{ + if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { + /* + * separate read/write queues + * hand out dedicated default queues only after we have + * sufficient read queues. + */ + io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; + nr_io_queues -= io_queues[HCTX_TYPE_READ]; + io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_write_queues, nr_io_queues); + nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* + * shared read/write queues + * either no write queues were requested, or we don't have + * sufficient queue count to have dedicated default queues. + */ + io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_io_queues, nr_io_queues); + nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT]; + } + + if (opts->nr_poll_queues && nr_io_queues) { + /* map dedicated poll queues only if we have queues left */ + io_queues[HCTX_TYPE_POLL] = + min(opts->nr_poll_queues, nr_io_queues); + } +} +EXPORT_SYMBOL_GPL(nvmf_set_io_queues); + +void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl, + u32 io_queues[HCTX_MAX_TYPES]) +{ + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (opts->nr_write_queues && io_queues[HCTX_TYPE_READ]) { + /* separate read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + io_queues[HCTX_TYPE_READ]; + set->map[HCTX_TYPE_READ].queue_offset = + io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* shared read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_READ].queue_offset = 0; + } + + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); + if (opts->nr_poll_queues && io_queues[HCTX_TYPE_POLL]) { + /* map dedicated poll queues only if we have queues left */ + set->map[HCTX_TYPE_POLL].nr_queues = io_queues[HCTX_TYPE_POLL]; + set->map[HCTX_TYPE_POLL].queue_offset = + io_queues[HCTX_TYPE_DEFAULT] + + io_queues[HCTX_TYPE_READ]; + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); + } + + dev_info(ctrl->device, + "mapped %d/%d/%d default/read/poll queues.\n", + io_queues[HCTX_TYPE_DEFAULT], + io_queues[HCTX_TYPE_READ], + io_queues[HCTX_TYPE_POLL]); +} +EXPORT_SYMBOL_GPL(nvmf_map_queues); + static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts, unsigned int required_opts) { diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index dcac3df8a5f7..82e7a27ffbde 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -77,6 +77,9 @@ enum { * with the parsing opts enum. * @mask: Used by the fabrics library to parse through sysfs options * on adding a NVMe controller. + * @max_reconnects: maximum number of allowed reconnect attempts before removing + * the controller, (-1) means reconnect forever, zero means remove + * immediately; * @transport: Holds the fabric transport "technology name" (for a lack of * better description) that will be used by an NVMe controller * being added. @@ -96,9 +99,6 @@ enum { * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN. * @kato: Keep-alive timeout. * @host: Virtual NVMe host, contains the NQN and Host ID. - * @max_reconnects: maximum number of allowed reconnect attempts before removing - * the controller, (-1) means reconnect forever, zero means remove - * immediately; * @dhchap_secret: DH-HMAC-CHAP secret * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional * authentication @@ -112,6 +112,7 @@ enum { */ struct nvmf_ctrl_options { unsigned mask; + int max_reconnects; char *transport; char *subsysnqn; char *traddr; @@ -125,7 +126,6 @@ struct nvmf_ctrl_options { bool duplicate_connect; unsigned int kato; struct nvmf_host *host; - int max_reconnects; char *dhchap_secret; char *dhchap_ctrl_secret; bool disable_sqflow; @@ -181,7 +181,7 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, ctrl->state == NVME_CTRL_DEAD || strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) || strcmp(opts->host->nqn, ctrl->opts->host->nqn) || - memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t))) + !uuid_equal(&opts->host->id, &ctrl->opts->host->id)) return false; return true; @@ -203,6 +203,13 @@ static inline void nvmf_complete_timed_out_request(struct request *rq) } } +static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts) +{ + return min(opts->nr_io_queues, num_online_cpus()) + + min(opts->nr_write_queues, num_online_cpus()) + + min(opts->nr_poll_queues, num_online_cpus()); +} + int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); @@ -215,5 +222,9 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts); +void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, + u32 io_queues[HCTX_MAX_TYPES]); +void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl, + u32 io_queues[HCTX_MAX_TYPES]); #endif /* _NVME_FABRICS_H */ diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index f15e7330b75a..2130ad65b58c 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -14,7 +14,7 @@ enum { }; static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, - unsigned int flags, fmode_t mode) + unsigned int flags, bool open_for_write) { u32 effects; @@ -80,7 +80,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, * writing. */ if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) - return mode & FMODE_WRITE; + return open_for_write; return true; } @@ -337,7 +337,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_passthru_cmd __user *ucmd, unsigned int flags, - fmode_t mode) + bool open_for_write) { struct nvme_passthru_cmd cmd; struct nvme_command c; @@ -365,7 +365,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, 0, mode)) + if (!nvme_cmd_allowed(ns, &c, 0, open_for_write)) return -EACCES; if (cmd.timeout_ms) @@ -385,7 +385,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags, - fmode_t mode) + bool open_for_write) { struct nvme_passthru_cmd64 cmd; struct nvme_command c; @@ -412,7 +412,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, flags, mode)) + if (!nvme_cmd_allowed(ns, &c, flags, open_for_write)) return -EACCES; if (cmd.timeout_ms) @@ -521,7 +521,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, if (cookie != NULL && blk_rq_is_poll(req)) nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED); else - io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); return RQ_END_IO_FREE; } @@ -543,7 +543,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, if (cookie != NULL && blk_rq_is_poll(req)) nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED); else - io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb); + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb); return RQ_END_IO_NONE; } @@ -583,7 +583,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14)); c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15)); - if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode)) + if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode & FMODE_WRITE)) return -EACCES; d.metadata = READ_ONCE(cmd->metadata); @@ -649,13 +649,13 @@ static bool is_ctrl_ioctl(unsigned int cmd) } static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd, - void __user *argp, fmode_t mode) + void __user *argp, bool open_for_write) { switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, 0, mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, 0, mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write); default: return sed_ioctl(ctrl->opal_dev, cmd, argp); } @@ -680,14 +680,14 @@ struct nvme_user_io32 { #endif /* COMPAT_FOR_U64_ALIGNMENT */ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, - void __user *argp, unsigned int flags, fmode_t mode) + void __user *argp, unsigned int flags, bool open_for_write) { switch (cmd) { case NVME_IOCTL_ID: force_successful_syscall_return(); return ns->head->ns_id; case NVME_IOCTL_IO_CMD: - return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode); + return nvme_user_cmd(ns->ctrl, ns, argp, flags, open_for_write); /* * struct nvme_user_io can have different padding on some 32-bit ABIs. * Just accept the compat version as all fields that are used are the @@ -702,16 +702,18 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, flags |= NVME_IOCTL_VEC; fallthrough; case NVME_IOCTL_IO64_CMD: - return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode); + return nvme_user_cmd64(ns->ctrl, ns, argp, flags, + open_for_write); default: return -ENOTTY; } } -int nvme_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = bdev->bd_disk->private_data; + bool open_for_write = mode & BLK_OPEN_WRITE; void __user *argp = (void __user *)arg; unsigned int flags = 0; @@ -719,19 +721,20 @@ int nvme_ioctl(struct block_device *bdev, fmode_t mode, flags |= NVME_IOCTL_PARTITION; if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode); - return nvme_ns_ioctl(ns, cmd, argp, flags, mode); + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); + return nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write); } long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev); + bool open_for_write = file->f_mode & FMODE_WRITE; void __user *argp = (void __user *)arg; if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode); - return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); + return nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write); } static int nvme_uring_cmd_checks(unsigned int issue_flags) @@ -800,7 +803,7 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd, #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp, struct nvme_ns_head *head, int srcu_idx, - fmode_t mode) + bool open_for_write) __releases(&head->srcu) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -808,16 +811,17 @@ static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, nvme_get_ctrl(ns->ctrl); srcu_read_unlock(&head->srcu, srcu_idx); - ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode); + ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); nvme_put_ctrl(ctrl); return ret; } -int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns_head *head = bdev->bd_disk->private_data; + bool open_for_write = mode & BLK_OPEN_WRITE; void __user *argp = (void __user *)arg; struct nvme_ns *ns; int srcu_idx, ret = -EWOULDBLOCK; @@ -838,9 +842,9 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, */ if (is_ctrl_ioctl(cmd)) return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, - mode); + open_for_write); - ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode); + ret = nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -849,6 +853,7 @@ out_unlock: long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + bool open_for_write = file->f_mode & FMODE_WRITE; struct cdev *cdev = file_inode(file)->i_cdev; struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev); @@ -863,9 +868,9 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, if (is_ctrl_ioctl(cmd)) return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, - file->f_mode); + open_for_write); - ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); + ret = nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -940,7 +945,7 @@ int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) } static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp, - fmode_t mode) + bool open_for_write) { struct nvme_ns *ns; int ret; @@ -964,7 +969,7 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp, kref_get(&ns->kref); up_read(&ctrl->namespaces_rwsem); - ret = nvme_user_cmd(ctrl, ns, argp, 0, mode); + ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write); nvme_put_ns(ns); return ret; @@ -976,16 +981,17 @@ out_unlock: long nvme_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + bool open_for_write = file->f_mode & FMODE_WRITE; struct nvme_ctrl *ctrl = file->private_data; void __user *argp = (void __user *)arg; switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_IO_CMD: - return nvme_dev_user_cmd(ctrl, argp, file->f_mode); + return nvme_dev_user_cmd(ctrl, argp, open_for_write); case NVME_IOCTL_RESET: if (!capable(CAP_SYS_ADMIN)) return -EACCES; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2bc159a318ff..98001eebd275 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -402,14 +402,14 @@ static void nvme_ns_head_submit_bio(struct bio *bio) srcu_read_unlock(&head->srcu, srcu_idx); } -static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode) +static int nvme_ns_head_open(struct gendisk *disk, blk_mode_t mode) { - if (!nvme_tryget_ns_head(bdev->bd_disk->private_data)) + if (!nvme_tryget_ns_head(disk->private_data)) return -ENXIO; return 0; } -static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode) +static void nvme_ns_head_release(struct gendisk *disk) { nvme_put_ns_head(disk->private_data); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 8657811f8b88..9a98c14c552a 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -247,12 +247,13 @@ enum nvme_ctrl_flags { NVME_CTRL_ADMIN_Q_STOPPED = 1, NVME_CTRL_STARTED_ONCE = 2, NVME_CTRL_STOPPED = 3, + NVME_CTRL_SKIP_ID_CNS_CS = 4, }; struct nvme_ctrl { bool comp_seen; - enum nvme_ctrl_state state; bool identified; + enum nvme_ctrl_state state; spinlock_t lock; struct mutex scan_lock; const struct nvme_ctrl_ops *ops; @@ -284,8 +285,8 @@ struct nvme_ctrl { char name[12]; u16 cntlid; - u32 ctrl_config; u16 mtfa; + u32 ctrl_config; u32 queue_count; u64 cap; @@ -359,10 +360,10 @@ struct nvme_ctrl { bool apst_enabled; /* PCIe only: */ + u16 hmmaxd; u32 hmpre; u32 hmmin; u32 hmminds; - u16 hmmaxd; /* Fabrics only */ u32 ioccsz; @@ -842,10 +843,10 @@ void nvme_put_ns_head(struct nvme_ns_head *head); int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, const struct file_operations *fops, struct module *owner); void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device); -int nvme_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -866,7 +867,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct pr_ops nvme_pr_ops; extern const struct block_device_operations nvme_ns_head_ops; extern const struct attribute_group nvme_dev_attrs_group; +extern const struct attribute_group *nvme_subsys_attrs_groups[]; +extern const struct attribute_group *nvme_dev_attr_groups[]; +extern const struct block_device_operations nvme_bdev_ops; +void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); #ifdef CONFIG_NVME_MULTIPATH static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 492f319ebdf3..48c60f7fda0b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -420,10 +420,9 @@ static int nvme_pci_init_request(struct blk_mq_tag_set *set, struct request *req, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_dev *dev = to_nvme_dev(set->driver_data); struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - nvme_req(req)->ctrl = &dev->ctrl; + nvme_req(req)->ctrl = set->driver_data; nvme_req(req)->cmd = &iod->cmd; return 0; } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 0eb79696fb73..d433b2ec07a6 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -501,7 +501,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) } ibdev = queue->device->dev; - /* +1 for ib_stop_cq */ + /* +1 for ib_drain_qp */ queue->cq_size = cq_factor * queue->queue_size + 1; ret = nvme_rdma_create_cq(ibdev, queue); @@ -713,18 +713,10 @@ out_stop_queues: static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - struct ib_device *ibdev = ctrl->device->dev; - unsigned int nr_io_queues, nr_default_queues; - unsigned int nr_read_queues, nr_poll_queues; + unsigned int nr_io_queues; int i, ret; - nr_read_queues = min_t(unsigned int, ibdev->num_comp_vectors, - min(opts->nr_io_queues, num_online_cpus())); - nr_default_queues = min_t(unsigned int, ibdev->num_comp_vectors, - min(opts->nr_write_queues, num_online_cpus())); - nr_poll_queues = min(opts->nr_poll_queues, num_online_cpus()); - nr_io_queues = nr_read_queues + nr_default_queues + nr_poll_queues; - + nr_io_queues = nvmf_nr_io_queues(opts); ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) return ret; @@ -739,34 +731,7 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues); - if (opts->nr_write_queues && nr_read_queues < nr_io_queues) { - /* - * separate read/write queues - * hand out dedicated default queues only after we have - * sufficient read queues. - */ - ctrl->io_queues[HCTX_TYPE_READ] = nr_read_queues; - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(nr_default_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* - * shared read/write queues - * either no write queues were requested, or we don't have - * sufficient queue count to have dedicated default queues. - */ - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(nr_read_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } - - if (opts->nr_poll_queues && nr_io_queues) { - /* map dedicated poll queues only if we have queues left */ - ctrl->io_queues[HCTX_TYPE_POLL] = - min(nr_poll_queues, nr_io_queues); - } - + nvmf_set_io_queues(opts, nr_io_queues, ctrl->io_queues); for (i = 1; i < ctrl->ctrl.queue_count; i++) { ret = nvme_rdma_alloc_queue(ctrl, i, ctrl->ctrl.sqsize + 1); @@ -2138,44 +2103,8 @@ static void nvme_rdma_complete_rq(struct request *rq) static void nvme_rdma_map_queues(struct blk_mq_tag_set *set) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(set->driver_data); - struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { - /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_READ]; - set->map[HCTX_TYPE_READ].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* shared read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_READ].queue_offset = 0; - } - blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); - blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); - - if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { - /* map dedicated poll queues only if we have queues left */ - set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->io_queues[HCTX_TYPE_POLL]; - set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT] + - ctrl->io_queues[HCTX_TYPE_READ]; - blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); - } - - dev_info(ctrl->ctrl.device, - "mapped %d/%d/%d default/read/poll queues.\n", - ctrl->io_queues[HCTX_TYPE_DEFAULT], - ctrl->io_queues[HCTX_TYPE_READ], - ctrl->io_queues[HCTX_TYPE_POLL]); + nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues); } static const struct blk_mq_ops nvme_rdma_mq_ops = { diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c new file mode 100644 index 000000000000..45e91811f905 --- /dev/null +++ b/drivers/nvme/host/sysfs.c @@ -0,0 +1,668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sysfs interface for the NVMe core driver. + * + * Copyright (c) 2011-2014, Intel Corporation. + */ + +#include <linux/nvme-auth.h> + +#include "nvme.h" +#include "fabrics.h" + +static ssize_t nvme_sysfs_reset(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + int ret; + + ret = nvme_reset_ctrl_sync(ctrl); + if (ret < 0) + return ret; + return count; +} +static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); + +static ssize_t nvme_sysfs_rescan(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + nvme_queue_scan(ctrl); + return count; +} +static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); + +static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (disk->fops == &nvme_bdev_ops) + return nvme_get_ns_from_dev(dev)->head; + else + return disk->private_data; +} + +static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns_head *head = dev_to_ns_head(dev); + struct nvme_ns_ids *ids = &head->ids; + struct nvme_subsystem *subsys = head->subsys; + int serial_len = sizeof(subsys->serial); + int model_len = sizeof(subsys->model); + + if (!uuid_is_null(&ids->uuid)) + return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid); + + if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return sysfs_emit(buf, "eui.%16phN\n", ids->nguid); + + if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + return sysfs_emit(buf, "eui.%8phN\n", ids->eui64); + + while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' || + subsys->serial[serial_len - 1] == '\0')) + serial_len--; + while (model_len > 0 && (subsys->model[model_len - 1] == ' ' || + subsys->model[model_len - 1] == '\0')) + model_len--; + + return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id, + serial_len, subsys->serial, model_len, subsys->model, + head->ns_id); +} +static DEVICE_ATTR_RO(wwid); + +static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid); +} +static DEVICE_ATTR_RO(nguid); + +static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; + + /* For backward compatibility expose the NGUID to userspace if + * we have no UUID set + */ + if (uuid_is_null(&ids->uuid)) { + dev_warn_ratelimited(dev, + "No UUID available providing old NGUID\n"); + return sysfs_emit(buf, "%pU\n", ids->nguid); + } + return sysfs_emit(buf, "%pU\n", &ids->uuid); +} +static DEVICE_ATTR_RO(uuid); + +static ssize_t eui_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64); +} +static DEVICE_ATTR_RO(eui); + +static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); +} +static DEVICE_ATTR_RO(nsid); + +static struct attribute *nvme_ns_id_attrs[] = { + &dev_attr_wwid.attr, + &dev_attr_uuid.attr, + &dev_attr_nguid.attr, + &dev_attr_eui.attr, + &dev_attr_nsid.attr, +#ifdef CONFIG_NVME_MULTIPATH + &dev_attr_ana_grpid.attr, + &dev_attr_ana_state.attr, +#endif + NULL, +}; + +static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; + + if (a == &dev_attr_uuid.attr) { + if (uuid_is_null(&ids->uuid) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return 0; + } + if (a == &dev_attr_nguid.attr) { + if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return 0; + } + if (a == &dev_attr_eui.attr) { + if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + return 0; + } +#ifdef CONFIG_NVME_MULTIPATH + if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { + if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ + return 0; + if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) + return 0; + } +#endif + return a->mode; +} + +static const struct attribute_group nvme_ns_id_attr_group = { + .attrs = nvme_ns_id_attrs, + .is_visible = nvme_ns_id_attrs_are_visible, +}; + +const struct attribute_group *nvme_ns_id_attr_groups[] = { + &nvme_ns_id_attr_group, + NULL, +}; + +#define nvme_show_str_function(field) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ + return sysfs_emit(buf, "%.*s\n", \ + (int)sizeof(ctrl->subsys->field), ctrl->subsys->field); \ +} \ +static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); + +nvme_show_str_function(model); +nvme_show_str_function(serial); +nvme_show_str_function(firmware_rev); + +#define nvme_show_int_function(field) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ + return sysfs_emit(buf, "%d\n", ctrl->field); \ +} \ +static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); + +nvme_show_int_function(cntlid); +nvme_show_int_function(numa_node); +nvme_show_int_function(queue_count); +nvme_show_int_function(sqsize); +nvme_show_int_function(kato); + +static ssize_t nvme_sysfs_delete(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + + if (device_remove_file_self(dev, attr)) + nvme_delete_ctrl_sync(ctrl); + return count; +} +static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); + +static ssize_t nvme_sysfs_show_transport(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->ops->name); +} +static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); + +static ssize_t nvme_sysfs_show_state(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + static const char *const state_name[] = { + [NVME_CTRL_NEW] = "new", + [NVME_CTRL_LIVE] = "live", + [NVME_CTRL_RESETTING] = "resetting", + [NVME_CTRL_CONNECTING] = "connecting", + [NVME_CTRL_DELETING] = "deleting", + [NVME_CTRL_DELETING_NOIO]= "deleting (no IO)", + [NVME_CTRL_DEAD] = "dead", + }; + + if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && + state_name[ctrl->state]) + return sysfs_emit(buf, "%s\n", state_name[ctrl->state]); + + return sysfs_emit(buf, "unknown state\n"); +} + +static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL); + +static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn); +} +static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); + +static ssize_t nvme_sysfs_show_hostnqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn); +} +static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL); + +static ssize_t nvme_sysfs_show_hostid(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id); +} +static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL); + +static ssize_t nvme_sysfs_show_address(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE); +} +static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); + +static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (ctrl->opts->max_reconnects == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", + opts->max_reconnects * opts->reconnect_delay); +} + +static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + int ctrl_loss_tmo, err; + + err = kstrtoint(buf, 10, &ctrl_loss_tmo); + if (err) + return -EINVAL; + + if (ctrl_loss_tmo < 0) + opts->max_reconnects = -1; + else + opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, + opts->reconnect_delay); + return count; +} +static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR, + nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store); + +static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->opts->reconnect_delay == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay); +} + +static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + unsigned int v; + int err; + + err = kstrtou32(buf, 10, &v); + if (err) + return err; + + ctrl->opts->reconnect_delay = v; + return count; +} +static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, + nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store); + +static ssize_t nvme_ctrl_fast_io_fail_tmo_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->opts->fast_io_fail_tmo == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", ctrl->opts->fast_io_fail_tmo); +} + +static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + int fast_io_fail_tmo, err; + + err = kstrtoint(buf, 10, &fast_io_fail_tmo); + if (err) + return -EINVAL; + + if (fast_io_fail_tmo < 0) + opts->fast_io_fail_tmo = -1; + else + opts->fast_io_fail_tmo = fast_io_fail_tmo; + return count; +} +static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR, + nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store); + +static ssize_t cntrltype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + static const char * const type[] = { + [NVME_CTRL_IO] = "io\n", + [NVME_CTRL_DISC] = "discovery\n", + [NVME_CTRL_ADMIN] = "admin\n", + }; + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->cntrltype > NVME_CTRL_ADMIN || !type[ctrl->cntrltype]) + return sysfs_emit(buf, "reserved\n"); + + return sysfs_emit(buf, type[ctrl->cntrltype]); +} +static DEVICE_ATTR_RO(cntrltype); + +static ssize_t dctype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + static const char * const type[] = { + [NVME_DCTYPE_NOT_REPORTED] = "none\n", + [NVME_DCTYPE_DDC] = "ddc\n", + [NVME_DCTYPE_CDC] = "cdc\n", + }; + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->dctype > NVME_DCTYPE_CDC || !type[ctrl->dctype]) + return sysfs_emit(buf, "reserved\n"); + + return sysfs_emit(buf, type[ctrl->dctype]); +} +static DEVICE_ATTR_RO(dctype); + +#ifdef CONFIG_NVME_AUTH +static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_secret); +} + +static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_secret)) { + struct nvme_dhchap_key *key, *host_key; + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &key); + if (ret) { + kfree(dhchap_secret); + return ret; + } + kfree(opts->dhchap_secret); + opts->dhchap_secret = dhchap_secret; + host_key = ctrl->host_key; + mutex_lock(&ctrl->dhchap_auth_mutex); + ctrl->host_key = key; + mutex_unlock(&ctrl->dhchap_auth_mutex); + nvme_auth_free_key(host_key); + } else + kfree(dhchap_secret); + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} + +static DEVICE_ATTR(dhchap_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_secret_show, nvme_ctrl_dhchap_secret_store); + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_ctrl_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_ctrl_secret); +} + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_ctrl_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) { + struct nvme_dhchap_key *key, *ctrl_key; + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &key); + if (ret) { + kfree(dhchap_secret); + return ret; + } + kfree(opts->dhchap_ctrl_secret); + opts->dhchap_ctrl_secret = dhchap_secret; + ctrl_key = ctrl->ctrl_key; + mutex_lock(&ctrl->dhchap_auth_mutex); + ctrl->ctrl_key = key; + mutex_unlock(&ctrl->dhchap_auth_mutex); + nvme_auth_free_key(ctrl_key); + } else + kfree(dhchap_secret); + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} + +static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store); +#endif + +static struct attribute *nvme_dev_attrs[] = { + &dev_attr_reset_controller.attr, + &dev_attr_rescan_controller.attr, + &dev_attr_model.attr, + &dev_attr_serial.attr, + &dev_attr_firmware_rev.attr, + &dev_attr_cntlid.attr, + &dev_attr_delete_controller.attr, + &dev_attr_transport.attr, + &dev_attr_subsysnqn.attr, + &dev_attr_address.attr, + &dev_attr_state.attr, + &dev_attr_numa_node.attr, + &dev_attr_queue_count.attr, + &dev_attr_sqsize.attr, + &dev_attr_hostnqn.attr, + &dev_attr_hostid.attr, + &dev_attr_ctrl_loss_tmo.attr, + &dev_attr_reconnect_delay.attr, + &dev_attr_fast_io_fail_tmo.attr, + &dev_attr_kato.attr, + &dev_attr_cntrltype.attr, + &dev_attr_dctype.attr, +#ifdef CONFIG_NVME_AUTH + &dev_attr_dhchap_secret.attr, + &dev_attr_dhchap_ctrl_secret.attr, +#endif + NULL +}; + +static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) + return 0; + if (a == &dev_attr_address.attr && !ctrl->ops->get_address) + return 0; + if (a == &dev_attr_hostnqn.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_hostid.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) + return 0; +#ifdef CONFIG_NVME_AUTH + if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) + return 0; +#endif + + return a->mode; +} + +const struct attribute_group nvme_dev_attrs_group = { + .attrs = nvme_dev_attrs, + .is_visible = nvme_dev_attrs_are_visible, +}; +EXPORT_SYMBOL_GPL(nvme_dev_attrs_group); + +const struct attribute_group *nvme_dev_attr_groups[] = { + &nvme_dev_attrs_group, + NULL, +}; + +#define SUBSYS_ATTR_RO(_name, _mode, _show) \ + struct device_attribute subsys_attr_##_name = \ + __ATTR(_name, _mode, _show, NULL) + +static ssize_t nvme_subsys_show_nqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + return sysfs_emit(buf, "%s\n", subsys->subnqn); +} +static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); + +static ssize_t nvme_subsys_show_type(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + switch (subsys->subtype) { + case NVME_NQN_DISC: + return sysfs_emit(buf, "discovery\n"); + case NVME_NQN_NVME: + return sysfs_emit(buf, "nvm\n"); + default: + return sysfs_emit(buf, "reserved\n"); + } +} +static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type); + +#define nvme_subsys_show_str_function(field) \ +static ssize_t subsys_##field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_subsystem *subsys = \ + container_of(dev, struct nvme_subsystem, dev); \ + return sysfs_emit(buf, "%.*s\n", \ + (int)sizeof(subsys->field), subsys->field); \ +} \ +static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show); + +nvme_subsys_show_str_function(model); +nvme_subsys_show_str_function(serial); +nvme_subsys_show_str_function(firmware_rev); + +static struct attribute *nvme_subsys_attrs[] = { + &subsys_attr_model.attr, + &subsys_attr_serial.attr, + &subsys_attr_firmware_rev.attr, + &subsys_attr_subsysnqn.attr, + &subsys_attr_subsystype.attr, +#ifdef CONFIG_NVME_MULTIPATH + &subsys_attr_iopolicy.attr, +#endif + NULL, +}; + +static const struct attribute_group nvme_subsys_attrs_group = { + .attrs = nvme_subsys_attrs, +}; + +const struct attribute_group *nvme_subsys_attrs_groups[] = { + &nvme_subsys_attrs_group, + NULL, +}; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index bf0230442d57..260b3554d821 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1802,58 +1802,12 @@ out_free_queues: return ret; } -static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) -{ - unsigned int nr_io_queues; - - nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus()); - nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus()); - nr_io_queues += min(ctrl->opts->nr_poll_queues, num_online_cpus()); - - return nr_io_queues; -} - -static void nvme_tcp_set_io_queues(struct nvme_ctrl *nctrl, - unsigned int nr_io_queues) -{ - struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); - struct nvmf_ctrl_options *opts = nctrl->opts; - - if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { - /* - * separate read/write queues - * hand out dedicated default queues only after we have - * sufficient read queues. - */ - ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(opts->nr_write_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* - * shared read/write queues - * either no write queues were requested, or we don't have - * sufficient queue count to have dedicated default queues. - */ - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(opts->nr_io_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } - - if (opts->nr_poll_queues && nr_io_queues) { - /* map dedicated poll queues only if we have queues left */ - ctrl->io_queues[HCTX_TYPE_POLL] = - min(opts->nr_poll_queues, nr_io_queues); - } -} - static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) { unsigned int nr_io_queues; int ret; - nr_io_queues = nvme_tcp_nr_io_queues(ctrl); + nr_io_queues = nvmf_nr_io_queues(ctrl->opts); ret = nvme_set_queue_count(ctrl, &nr_io_queues); if (ret) return ret; @@ -1868,8 +1822,8 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) dev_info(ctrl->device, "creating %d I/O queues.\n", nr_io_queues); - nvme_tcp_set_io_queues(ctrl, nr_io_queues); - + nvmf_set_io_queues(ctrl->opts, nr_io_queues, + to_tcp_ctrl(ctrl)->io_queues); return __nvme_tcp_alloc_io_queues(ctrl); } @@ -2449,44 +2403,8 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, static void nvme_tcp_map_queues(struct blk_mq_tag_set *set) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data); - struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - - if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { - /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_READ]; - set->map[HCTX_TYPE_READ].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* shared read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_READ].queue_offset = 0; - } - blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); - blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); - - if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { - /* map dedicated poll queues only if we have queues left */ - set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->io_queues[HCTX_TYPE_POLL]; - set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT] + - ctrl->io_queues[HCTX_TYPE_READ]; - blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); - } - - dev_info(ctrl->ctrl.device, - "mapped %d/%d/%d default/read/poll queues.\n", - ctrl->io_queues[HCTX_TYPE_DEFAULT], - ctrl->io_queues[HCTX_TYPE_READ], - ctrl->io_queues[HCTX_TYPE_POLL]); + + nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues); } static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index 7970a7640e58..586458f765f1 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -295,13 +295,11 @@ void nvmet_execute_auth_send(struct nvmet_req *req) status = 0; } goto done_kfree; - break; case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2: req->sq->authenticated = true; pr_debug("%s: ctrl %d qid %d ctrl authenticated\n", __func__, ctrl->cntlid, req->sq->qid); goto done_kfree; - break; case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2: status = nvmet_auth_failure2(d); if (status) { @@ -312,7 +310,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req) status = 0; } goto done_kfree; - break; default: req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; @@ -320,7 +317,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req) NVME_AUTH_DHCHAP_MESSAGE_FAILURE2; req->sq->authenticated = false; goto done_kfree; - break; } done_failure1: req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; @@ -483,15 +479,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = NVME_SC_INTERNAL; break; } - if (status) { - req->sq->dhchap_status = status; - nvmet_auth_failure1(req, d, al); - pr_warn("ctrl %d qid %d: challenge status (%x)\n", - ctrl->cntlid, req->sq->qid, - req->sq->dhchap_status); - status = 0; - break; - } req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_REPLY; break; case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1: diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index e940a7d37a9d..c65a73433c05 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -645,8 +645,6 @@ fcloop_fcp_recv_work(struct work_struct *work) } if (ret) fcloop_call_host_done(fcpreq, tfcp_req, ret); - - return; } static void @@ -1168,7 +1166,8 @@ __wait_localport_unreg(struct fcloop_lport *lport) ret = nvme_fc_unregister_localport(lport->localport); - wait_for_completion(&lport->unreg_done); + if (!ret) + wait_for_completion(&lport->unreg_done); kfree(lport); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index c2d6cea0236b..2733e0158585 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -51,7 +51,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) void nvmet_bdev_ns_disable(struct nvmet_ns *ns) { if (ns->bdev) { - blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ); + blkdev_put(ns->bdev, NULL); ns->bdev = NULL; } } @@ -85,7 +85,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) return -ENOTBLK; ns->bdev = blkdev_get_by_path(ns->device_path, - FMODE_READ | FMODE_WRITE, NULL); + BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(ns->bdev)) { ret = PTR_ERR(ns->bdev); if (ret != -ENOTBLK) { diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index dc60a22646f7..6cf723bc664e 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -109,8 +109,8 @@ struct nvmet_sq { u32 sqhd; bool sqhd_disabled; #ifdef CONFIG_NVME_TARGET_AUTH - struct delayed_work auth_expired_work; bool authenticated; + struct delayed_work auth_expired_work; u16 dhchap_tid; u16 dhchap_status; int dhchap_step; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 2e01960f1aeb..7feb643f1370 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -811,6 +811,7 @@ static int init_overlay_changeset(struct overlay_changeset *ovcs) if (!fragment->target) { pr_err("symbols in overlay, but not in live tree\n"); ret = -EINVAL; + of_node_put(node); goto err_out; } diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index bc32662c6bb7..2d93d0c4f10d 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -489,7 +489,10 @@ struct hv_pcibus_device { struct fwnode_handle *fwnode; /* Protocol version negotiated with the host */ enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; enum hv_pcibus_state state; + struct hv_device *hdev; resource_size_t low_mmio_space; resource_size_t high_mmio_space; @@ -545,19 +548,10 @@ struct hv_dr_state { struct hv_pcidev_description func[]; }; -enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum -}; - struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; struct hv_pcidev_description desc; bool reported_missing; @@ -635,6 +629,11 @@ static void hv_arch_irq_unmask(struct irq_data *data) pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } local_irq_save(flags); @@ -2004,12 +2003,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) hv_pci_onchannelcallback(hbus); spin_unlock_irqrestore(&channel->sched_lock, flags); - if (hpdev->state == hv_pcichild_ejecting) { - dev_err_once(&hbus->hdev->device, - "the device is being ejected\n"); - goto enable_tasklet; - } - udelay(100); } @@ -2615,6 +2608,8 @@ static void pci_devices_present_work(struct work_struct *work) if (!dr) return; + mutex_lock(&hbus->state_lock); + /* First, mark all existing children as reported missing. */ spin_lock_irqsave(&hbus->device_list_lock, flags); list_for_each_entry(hpdev, &hbus->children, list_entry) { @@ -2696,6 +2691,8 @@ static void pci_devices_present_work(struct work_struct *work) break; } + mutex_unlock(&hbus->state_lock); + kfree(dr); } @@ -2844,7 +2841,7 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus; - WARN_ON(hpdev->state != hv_pcichild_ejecting); + mutex_lock(&hbus->state_lock); /* * Ejection can come before or after the PCI bus has been set up, so @@ -2882,6 +2879,8 @@ static void hv_eject_device_work(struct work_struct *work) put_pcichild(hpdev); put_pcichild(hpdev); /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); } /** @@ -2902,7 +2901,6 @@ static void hv_pci_eject_device(struct hv_pci_dev *hpdev) return; } - hpdev->state = hv_pcichild_ejecting; get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); queue_work(hbus->wq, &hpdev->wrk); @@ -3331,8 +3329,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -3359,6 +3359,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -3401,6 +3433,24 @@ static int hv_pci_query_relations(struct hv_device *hdev) if (!ret) ret = wait_for_response(hdev, &comp); + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + return ret; } @@ -3586,7 +3636,6 @@ static int hv_pci_probe(struct hv_device *hdev, struct hv_pcibus_device *hbus; u16 dom_req, dom; char *name; - bool enter_d0_retry = true; int ret; bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); @@ -3598,6 +3647,7 @@ static int hv_pci_probe(struct hv_device *hdev, return -ENOMEM; hbus->bridge = bridge; + mutex_init(&hbus->state_lock); hbus->state = hv_pcibus_init; hbus->wslot_res_allocated = -1; @@ -3703,49 +3753,15 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_fwnode; -retry: ret = hv_pci_query_relations(hdev); if (ret) goto free_irq_domain; - ret = hv_pci_enter_d0(hdev); - /* - * In certain case (Kdump) the pci device of interest was - * not cleanly shut down and resource is still held on host - * side, the host could return invalid device status. - * We need to explicitly request host to release the resource - * and try to enter D0 again. - * Since the hv_pci_bus_exit() call releases structures - * of all its child devices, we need to start the retry from - * hv_pci_query_relations() call, requesting host to send - * the synchronous child device relations message before this - * information is needed in hv_send_resources_allocated() - * call later. - */ - if (ret == -EPROTO && enter_d0_retry) { - enter_d0_retry = false; - - dev_err(&hdev->device, "Retrying D0 Entry\n"); - - /* - * Hv_pci_bus_exit() calls hv_send_resources_released() - * to free up resources of its child devices. - * In the kdump kernel we need to set the - * wslot_res_allocated to 255 so it scans all child - * devices to release resources allocated in the - * normal kernel before panic happened. - */ - hbus->wslot_res_allocated = 255; - ret = hv_pci_bus_exit(hdev, true); - - if (ret == 0) - goto retry; + mutex_lock(&hbus->state_lock); - dev_err(&hdev->device, - "Retrying D0 failed with ret %d\n", ret); - } + ret = hv_pci_enter_d0(hdev); if (ret) - goto free_irq_domain; + goto release_state_lock; ret = hv_pci_allocate_bridge_windows(hbus); if (ret) @@ -3763,12 +3779,15 @@ retry: if (ret) goto free_windows; + mutex_unlock(&hbus->state_lock); return 0; free_windows: hv_pci_free_bridge_windows(hbus); exit_d0: (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: @@ -4018,20 +4037,26 @@ static int hv_pci_resume(struct hv_device *hdev) if (ret) goto out; + mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto out; + goto release_state_lock; ret = hv_send_resources_allocated(hdev); if (ret) - goto out; + goto release_state_lock; prepopulate_bars(hbus); hv_pci_restore_msi_state(hbus); hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); out: vmbus_close(hdev->channel); return ret; diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index c98e4039386d..93b7edb5f1e7 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -677,9 +677,25 @@ static inline u32 armv8pmu_getreset_flags(void) return value; } +static void update_pmuserenr(u64 val) +{ + lockdep_assert_irqs_disabled(); + + /* + * The current PMUSERENR_EL0 value might be the value for the guest. + * If that's the case, have KVM keep tracking of the register value + * for the host EL0 so that KVM can restore it before returning to + * the host EL0. Otherwise, update the register now. + */ + if (kvm_set_pmuserenr(val)) + return; + + write_pmuserenr(val); +} + static void armv8pmu_disable_user_access(void) { - write_pmuserenr(0); + update_pmuserenr(0); } static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) @@ -695,8 +711,7 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) armv8pmu_write_evcntr(i, 0); } - write_pmuserenr(0); - write_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR); + update_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR); } static void armv8pmu_enable_event(struct perf_event *event) diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index ee5f124f78b6..7780705917b7 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -297,6 +297,8 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev) /* Enable Static Slider */ if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { amd_pmf_init_sps(dev); + dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; + power_supply_reg_notifier(&dev->pwr_src_notifier); dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n"); } @@ -315,8 +317,10 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev) static void amd_pmf_deinit_features(struct amd_pmf_dev *dev) { - if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) + if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { + power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_sps(dev); + } if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) { amd_pmf_deinit_auto_mode(dev); @@ -399,9 +403,6 @@ static int amd_pmf_probe(struct platform_device *pdev) apmf_install_handler(dev); amd_pmf_dbgfs_register(dev); - dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; - power_supply_reg_notifier(&dev->pwr_src_notifier); - dev_info(dev->dev, "registered PMF device successfully\n"); return 0; @@ -411,7 +412,6 @@ static void amd_pmf_remove(struct platform_device *pdev) { struct amd_pmf_dev *dev = platform_get_drvdata(pdev); - power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_features(dev); apmf_acpi_deinit(dev); amd_pmf_dbgfs_unregister(dev); diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c index f0a6391b1146..ffb973c328e3 100644 --- a/drivers/ras/debugfs.c +++ b/drivers/ras/debugfs.c @@ -46,7 +46,7 @@ int __init ras_add_daemon_trace(void) fentry = debugfs_create_file("daemon_active", S_IRUSR, ras_debugfs_dir, NULL, &trace_fops); - if (!fentry) + if (IS_ERR(fentry)) return -ENODEV; return 0; diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index b0a58c62b1e2..f3b280af0773 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -1057,21 +1057,21 @@ static const struct rpmh_vreg_init_data pm8450_vreg_data[] = { }; static const struct rpmh_vreg_init_data pm8550_vreg_data[] = { - RPMH_VREG("ldo1", "ldo%s1", &pmic5_pldo, "vdd-l1-l4-l10"), + RPMH_VREG("ldo1", "ldo%s1", &pmic5_nldo515, "vdd-l1-l4-l10"), RPMH_VREG("ldo2", "ldo%s2", &pmic5_pldo, "vdd-l2-l13-l14"), - RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo, "vdd-l3"), - RPMH_VREG("ldo4", "ldo%s4", &pmic5_nldo, "vdd-l1-l4-l10"), + RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo515, "vdd-l3"), + RPMH_VREG("ldo4", "ldo%s4", &pmic5_nldo515, "vdd-l1-l4-l10"), RPMH_VREG("ldo5", "ldo%s5", &pmic5_pldo, "vdd-l5-l16"), - RPMH_VREG("ldo6", "ldo%s6", &pmic5_pldo_lv, "vdd-l6-l7"), - RPMH_VREG("ldo7", "ldo%s7", &pmic5_pldo_lv, "vdd-l6-l7"), - RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"), + RPMH_VREG("ldo6", "ldo%s6", &pmic5_pldo, "vdd-l6-l7"), + RPMH_VREG("ldo7", "ldo%s7", &pmic5_pldo, "vdd-l6-l7"), + RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo, "vdd-l8-l9"), RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"), - RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"), - RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"), + RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo515, "vdd-l1-l4-l10"), + RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo515, "vdd-l11"), RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"), RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"), RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"), - RPMH_VREG("ldo15", "ldo%s15", &pmic5_pldo, "vdd-l15"), + RPMH_VREG("ldo15", "ldo%s15", &pmic5_nldo515, "vdd-l15"), RPMH_VREG("ldo16", "ldo%s16", &pmic5_pldo, "vdd-l5-l16"), RPMH_VREG("ldo17", "ldo%s17", &pmic5_pldo, "vdd-l17"), RPMH_VREG("bob1", "bob%s1", &pmic5_bob, "vdd-bob1"), @@ -1086,9 +1086,9 @@ static const struct rpmh_vreg_init_data pm8550vs_vreg_data[] = { RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps525_lv, "vdd-s4"), RPMH_VREG("smps5", "smp%s5", &pmic5_ftsmps525_lv, "vdd-s5"), RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525_mv, "vdd-s6"), - RPMH_VREG("ldo1", "ldo%s1", &pmic5_nldo, "vdd-l1"), - RPMH_VREG("ldo2", "ldo%s2", &pmic5_nldo, "vdd-l2"), - RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo, "vdd-l3"), + RPMH_VREG("ldo1", "ldo%s1", &pmic5_nldo515, "vdd-l1"), + RPMH_VREG("ldo2", "ldo%s2", &pmic5_nldo515, "vdd-l2"), + RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo515, "vdd-l3"), {} }; @@ -1101,9 +1101,9 @@ static const struct rpmh_vreg_init_data pm8550ve_vreg_data[] = { RPMH_VREG("smps6", "smp%s6", &pmic5_ftsmps525_lv, "vdd-s6"), RPMH_VREG("smps7", "smp%s7", &pmic5_ftsmps525_lv, "vdd-s7"), RPMH_VREG("smps8", "smp%s8", &pmic5_ftsmps525_lv, "vdd-s8"), - RPMH_VREG("ldo1", "ldo%s1", &pmic5_nldo, "vdd-l1"), - RPMH_VREG("ldo2", "ldo%s2", &pmic5_nldo, "vdd-l2"), - RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo, "vdd-l3"), + RPMH_VREG("ldo1", "ldo%s1", &pmic5_nldo515, "vdd-l1"), + RPMH_VREG("ldo2", "ldo%s2", &pmic5_nldo515, "vdd-l2"), + RPMH_VREG("ldo3", "ldo%s3", &pmic5_nldo515, "vdd-l3"), {} }; diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 9fbfce735d56..45788955c4e6 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3234,12 +3234,12 @@ struct blk_mq_ops dasd_mq_ops = { .exit_hctx = dasd_exit_hctx, }; -static int dasd_open(struct block_device *bdev, fmode_t mode) +static int dasd_open(struct gendisk *disk, blk_mode_t mode) { struct dasd_device *base; int rc; - base = dasd_device_from_gendisk(bdev->bd_disk); + base = dasd_device_from_gendisk(disk); if (!base) return -ENODEV; @@ -3268,14 +3268,12 @@ static int dasd_open(struct block_device *bdev, fmode_t mode) rc = -ENODEV; goto out; } - - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && (test_bit(DASD_FLAG_DEVICE_RO, &base->flags) || (base->features & DASD_FEATURE_READONLY))) { rc = -EROFS; goto out; } - dasd_put_device(base); return 0; @@ -3287,7 +3285,7 @@ unlock: return rc; } -static void dasd_release(struct gendisk *disk, fmode_t mode) +static void dasd_release(struct gendisk *disk) { struct dasd_device *base = dasd_device_from_gendisk(disk); if (base) { diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 998a961e1704..fe5108a1b332 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -130,7 +130,8 @@ int dasd_scan_partitions(struct dasd_block *block) struct block_device *bdev; int rc; - bdev = blkdev_get_by_dev(disk_devt(block->gdp), FMODE_READ, NULL); + bdev = blkdev_get_by_dev(disk_devt(block->gdp), BLK_OPEN_READ, NULL, + NULL); if (IS_ERR(bdev)) { DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, blkdev_get returned %ld", @@ -179,7 +180,7 @@ void dasd_destroy_partitions(struct dasd_block *block) mutex_unlock(&bdev->bd_disk->open_mutex); /* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */ - blkdev_put(bdev, FMODE_READ); + blkdev_put(bdev, NULL); } int dasd_gendisk_init(void) diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 33f812f0e515..0aa56351da72 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -965,7 +965,8 @@ int dasd_scan_partitions(struct dasd_block *); void dasd_destroy_partitions(struct dasd_block *); /* externals in dasd_ioctl.c */ -int dasd_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); +int dasd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, + unsigned long arg); int dasd_set_read_only(struct block_device *bdev, bool ro); /* externals in dasd_proc.c */ diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 8fca725b3dae..513a7e6eee63 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -612,7 +612,7 @@ static int dasd_ioctl_readall_cmb(struct dasd_block *block, unsigned int cmd, return ret; } -int dasd_ioctl(struct block_device *bdev, fmode_t mode, +int dasd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct dasd_block *block; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index c09f2e053bf8..200f88f0e451 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -28,8 +28,8 @@ #define DCSSBLK_PARM_LEN 400 #define DCSS_BUS_ID_SIZE 20 -static int dcssblk_open(struct block_device *bdev, fmode_t mode); -static void dcssblk_release(struct gendisk *disk, fmode_t mode); +static int dcssblk_open(struct gendisk *disk, blk_mode_t mode); +static void dcssblk_release(struct gendisk *disk); static void dcssblk_submit_bio(struct bio *bio); static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, @@ -809,12 +809,11 @@ out_buf: } static int -dcssblk_open(struct block_device *bdev, fmode_t mode) +dcssblk_open(struct gendisk *disk, blk_mode_t mode) { - struct dcssblk_dev_info *dev_info; + struct dcssblk_dev_info *dev_info = disk->private_data; int rc; - dev_info = bdev->bd_disk->private_data; if (NULL == dev_info) { rc = -ENODEV; goto out; @@ -826,7 +825,7 @@ out: } static void -dcssblk_release(struct gendisk *disk, fmode_t mode) +dcssblk_release(struct gendisk *disk) { struct dcssblk_dev_info *dev_info = disk->private_data; struct segment_info *entry; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 8acb9eba691b..c2096e4bba31 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -771,14 +771,6 @@ static int __init ism_init(void) static void __exit ism_exit(void) { - struct ism_dev *ism; - - mutex_lock(&ism_dev_list.mutex); - list_for_each_entry(ism, &ism_dev_list.list, list) { - ism_dev_exit(ism); - } - mutex_unlock(&ism_dev_list.mutex); - pci_unregister_driver(&ism_driver); debug_unregister(ism_debug_info); } diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 5e115e8b2ba4..7c6efde75da6 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1678,6 +1678,7 @@ struct aac_dev u32 handle_pci_error; bool init_reset; u8 soft_reset_support; + u8 use_map_queue; }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index deb32c9f4b3e..3f062e4013ab 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -223,8 +223,12 @@ int aac_fib_setup(struct aac_dev * dev) struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd) { struct fib *fibptr; + u32 blk_tag; + int i; - fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag]; + blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); + i = blk_mq_unique_tag_to_tag(blk_tag); + fibptr = &dev->fibs[i]; /* * Null out fields that depend on being zero at the start of * each I/O diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 68f4dbcfff49..c4a36c0be527 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -19,6 +19,7 @@ #include <linux/compat.h> #include <linux/blkdev.h> +#include <linux/blk-mq-pci.h> #include <linux/completion.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -504,6 +505,15 @@ common_config: return 0; } +static void aac_map_queues(struct Scsi_Host *shost) +{ + struct aac_dev *aac = (struct aac_dev *)shost->hostdata; + + blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + aac->pdev, 0); + aac->use_map_queue = true; +} + /** * aac_change_queue_depth - alter queue depths * @sdev: SCSI device we are considering @@ -1488,6 +1498,7 @@ static const struct scsi_host_template aac_driver_template = { .bios_param = aac_biosparm, .shost_groups = aac_host_groups, .slave_configure = aac_slave_configure, + .map_queues = aac_map_queues, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, @@ -1775,6 +1786,8 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = AAC_MAX_LUN; pci_set_drvdata(pdev, shost); + shost->nr_hw_queues = aac->max_msix; + shost->host_tagset = 1; error = scsi_add_host(shost, &pdev->dev); if (error) @@ -1906,6 +1919,7 @@ static void aac_remove_one(struct pci_dev *pdev) struct aac_dev *aac = (struct aac_dev *)shost->hostdata; aac_cancel_rescan_worker(aac); + aac->use_map_queue = false; scsi_remove_host(shost); __aac_shutdown(aac); diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 11ef58204e96..61949f374188 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -493,6 +493,10 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 vector_no; + struct scsi_cmnd *scmd; + u32 blk_tag; + struct Scsi_Host *shost = dev->scsi_host_ptr; + struct blk_mq_queue_map *qmap; atomic_inc(&q->numpending); @@ -505,8 +509,25 @@ static int aac_src_deliver_message(struct fib *fib) if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) && dev->sa_firmware) vector_no = aac_get_vector(dev); - else - vector_no = fib->vector_no; + else { + if (!fib->vector_no || !fib->callback_data) { + if (shost && dev->use_map_queue) { + qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; + vector_no = qmap->mq_map[raw_smp_processor_id()]; + } + /* + * We hardcode the vector_no for + * reserved commands as a valid shost is + * absent during the init + */ + else + vector_no = 0; + } else { + scmd = (struct scsi_cmnd *)fib->callback_data; + blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); + vector_no = blk_mq_unique_tag_to_hwq(blk_tag); + } + } if (native_hba) { if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) { diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index ac648bb8f7e7..cb0a399be1cc 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -877,7 +877,8 @@ static long ch_ioctl(struct file *file, } default: - return scsi_ioctl(ch->device, file->f_mode, cmd, argp); + return scsi_ioctl(ch->device, file->f_mode & FMODE_WRITE, cmd, + argp); } } diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 9a322a3a2150..595dca92e8db 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -889,7 +889,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, struct lpfc_iocbq *piocbq) { uint32_t evt_req_id = 0; - uint32_t cmd; + u16 cmd; struct lpfc_dmabuf *dmabuf = NULL; struct lpfc_bsg_event *evt; struct event_data *evt_dat = NULL; @@ -915,7 +915,7 @@ lpfc_bsg_ct_unsol_event(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, ct_req = (struct lpfc_sli_ct_request *)bdeBuf1->virt; evt_req_id = ct_req->FsType; - cmd = ct_req->CommandResponse.bits.CmdRsp; + cmd = be16_to_cpu(ct_req->CommandResponse.bits.CmdRsp); spin_lock_irqsave(&phba->ct_ev_lock, flags); list_for_each_entry(evt, &phba->ct_ev_waiters, node) { @@ -3186,8 +3186,8 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) ctreq->RevisionId.bits.InId = 0; ctreq->FsType = SLI_CT_ELX_LOOPBACK; ctreq->FsSubType = 0; - ctreq->CommandResponse.bits.CmdRsp = ELX_LOOPBACK_DATA; - ctreq->CommandResponse.bits.Size = size; + ctreq->CommandResponse.bits.CmdRsp = cpu_to_be16(ELX_LOOPBACK_DATA); + ctreq->CommandResponse.bits.Size = cpu_to_be16(size); segment_offset = ELX_LOOPBACK_HEADER_SZ; } else segment_offset = 0; diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 96ee35256a16..a9a9ec086a7e 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -10,7 +10,7 @@ #define uptr64(val) ((void __user *)(uintptr_t)(val)) static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout) + bool open_for_write, unsigned int timeout) { struct scsi_cmnd *scmd; struct request *rq; @@ -42,7 +42,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, if (copy_from_user(scmd->cmnd, uptr64(hdr->request), scmd->cmd_len)) goto out_put_request; ret = -EPERM; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) goto out_put_request; ret = 0; diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index e3b31d32b6a9..6f6c5973c3ea 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -248,7 +248,7 @@ static int scsi_send_start_stop(struct scsi_device *sdev, int data) * Only a subset of commands are allowed for unprivileged users. Commands used * to format the media, update the firmware, etc. are not permitted. */ -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) +bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write) { /* root can do any command. */ if (capable(CAP_SYS_RAWIO)) @@ -338,7 +338,7 @@ bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) case GPCMD_SET_READ_AHEAD: /* ZBC */ case ZBC_OUT: - return (mode & FMODE_WRITE); + return open_for_write; default: return false; } @@ -346,7 +346,7 @@ bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) EXPORT_SYMBOL(scsi_cmd_allowed); static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, - struct sg_io_hdr *hdr, fmode_t mode) + struct sg_io_hdr *hdr, bool open_for_write) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); @@ -354,7 +354,7 @@ static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, return -EMSGSIZE; if (copy_from_user(scmd->cmnd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) return -EPERM; scmd->cmd_len = hdr->cmd_len; @@ -407,7 +407,8 @@ static int scsi_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, return ret; } -static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode) +static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, + bool open_for_write) { unsigned long start_time; ssize_t ret = 0; @@ -448,7 +449,7 @@ static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode) goto out_put_request; } - ret = scsi_fill_sghdr_rq(sdev, rq, hdr, mode); + ret = scsi_fill_sghdr_rq(sdev, rq, hdr, open_for_write); if (ret < 0) goto out_put_request; @@ -477,8 +478,7 @@ out_put_request: /** * sg_scsi_ioctl -- handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl * @q: request queue to send scsi commands down - * @mode: mode used to open the file through which the ioctl has been - * submitted + * @open_for_write: is the file / block device opened for writing? * @sic: userspace structure describing the command to perform * * Send down the scsi command described by @sic to the device below @@ -501,7 +501,7 @@ out_put_request: * Positive numbers returned are the compacted SCSI error codes (4 * bytes in one int) where the lowest byte is the SCSI status. */ -static int sg_scsi_ioctl(struct request_queue *q, fmode_t mode, +static int sg_scsi_ioctl(struct request_queue *q, bool open_for_write, struct scsi_ioctl_command __user *sic) { struct request *rq; @@ -554,7 +554,7 @@ static int sg_scsi_ioctl(struct request_queue *q, fmode_t mode, goto error; err = -EPERM; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) goto error; /* default. possible overridden later */ @@ -776,7 +776,7 @@ static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc, return 0; } -static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, +static int scsi_cdrom_send_packet(struct scsi_device *sdev, bool open_for_write, void __user *arg) { struct cdrom_generic_command cgc; @@ -817,7 +817,7 @@ static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, hdr.cmdp = ((struct cdrom_generic_command __user *) arg)->cmd; hdr.cmd_len = sizeof(cgc.cmd); - err = sg_io(sdev, &hdr, mode); + err = sg_io(sdev, &hdr, open_for_write); if (err == -EFAULT) return -EFAULT; @@ -832,7 +832,7 @@ static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, return err; } -static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, +static int scsi_ioctl_sg_io(struct scsi_device *sdev, bool open_for_write, void __user *argp) { struct sg_io_hdr hdr; @@ -841,7 +841,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, error = get_sg_io_hdr(&hdr, argp); if (error) return error; - error = sg_io(sdev, &hdr, mode); + error = sg_io(sdev, &hdr, open_for_write); if (error == -EFAULT) return error; if (put_sg_io_hdr(&hdr, argp)) @@ -852,7 +852,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, /** * scsi_ioctl - Dispatch ioctl to scsi device * @sdev: scsi device receiving ioctl - * @mode: mode the block/char device is opened with + * @open_for_write: is the file / block device opened for writing? * @cmd: which ioctl is it * @arg: data associated with ioctl * @@ -860,7 +860,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, * does not take a major/minor number as the dev field. Rather, it takes * a pointer to a &struct scsi_device. */ -int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, +int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg) { struct request_queue *q = sdev->request_queue; @@ -896,11 +896,11 @@ int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, case SG_EMULATED_HOST: return sg_emulated_host(q, arg); case SG_IO: - return scsi_ioctl_sg_io(sdev, mode, arg); + return scsi_ioctl_sg_io(sdev, open_for_write, arg); case SCSI_IOCTL_SEND_COMMAND: - return sg_scsi_ioctl(q, mode, arg); + return sg_scsi_ioctl(q, open_for_write, arg); case CDROM_SEND_PACKET: - return scsi_cdrom_send_packet(sdev, mode, arg); + return scsi_cdrom_send_packet(sdev, open_for_write, arg); case CDROMCLOSETRAY: return scsi_send_start_stop(sdev, 3); case CDROMEJECT: diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1624d528aa1f..ab216976dbdc 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1280,11 +1280,10 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) mempool_free(rq->special_vec.bv_page, sd_page_pool); } -static bool sd_need_revalidate(struct block_device *bdev, - struct scsi_disk *sdkp) +static bool sd_need_revalidate(struct gendisk *disk, struct scsi_disk *sdkp) { if (sdkp->device->removable || sdkp->write_prot) { - if (bdev_check_media_change(bdev)) + if (disk_check_media_change(disk)) return true; } @@ -1293,13 +1292,13 @@ static bool sd_need_revalidate(struct block_device *bdev, * nothing to do with partitions, BLKRRPART is used to force a full * revalidate after things like a format for historical reasons. */ - return test_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + return test_bit(GD_NEED_PART_SCAN, &disk->state); } /** * sd_open - open a scsi disk device - * @bdev: Block device of the scsi disk to open - * @mode: FMODE_* mask + * @disk: disk to open + * @mode: open mode * * Returns 0 if successful. Returns a negated errno value in case * of error. @@ -1309,11 +1308,11 @@ static bool sd_need_revalidate(struct block_device *bdev, * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * - * Locking: called with bdev->bd_disk->open_mutex held. + * Locking: called with disk->open_mutex held. **/ -static int sd_open(struct block_device *bdev, fmode_t mode) +static int sd_open(struct gendisk *disk, blk_mode_t mode) { - struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; int retval; @@ -1330,14 +1329,15 @@ static int sd_open(struct block_device *bdev, fmode_t mode) if (!scsi_block_when_processing_errors(sdev)) goto error_out; - if (sd_need_revalidate(bdev, sdkp)) - sd_revalidate_disk(bdev->bd_disk); + if (sd_need_revalidate(disk, sdkp)) + sd_revalidate_disk(disk); /* * If the drive is empty, just let the open fail. */ retval = -ENOMEDIUM; - if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY)) + if (sdev->removable && !sdkp->media_present && + !(mode & BLK_OPEN_NDELAY)) goto error_out; /* @@ -1345,7 +1345,7 @@ static int sd_open(struct block_device *bdev, fmode_t mode) * if the user expects to be able to write to the thing. */ retval = -EROFS; - if (sdkp->write_prot && (mode & FMODE_WRITE)) + if (sdkp->write_prot && (mode & BLK_OPEN_WRITE)) goto error_out; /* @@ -1374,16 +1374,15 @@ error_out: * sd_release - invoked when the (last) close(2) is called on this * scsi disk. * @disk: disk to release - * @mode: FMODE_* mask * * Returns 0. * * Note: may block (uninterruptible) if error recovery is underway * on this disk. * - * Locking: called with bdev->bd_disk->open_mutex held. + * Locking: called with disk->open_mutex held. **/ -static void sd_release(struct gendisk *disk, fmode_t mode) +static void sd_release(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; @@ -1426,7 +1425,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) /** * sd_ioctl - process an ioctl * @bdev: target block device - * @mode: FMODE_* mask + * @mode: open mode * @cmd: ioctl command number * @arg: this is third argument given to ioctl(2) system call. * Often contains a pointer. @@ -1437,7 +1436,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) * Note: most ioctls are forward onto the block subsystem or further * down in the scsi subsystem. **/ -static int sd_ioctl(struct block_device *bdev, fmode_t mode, +static int sd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; @@ -1459,13 +1458,13 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, * access to the device is prohibited. */ error = scsi_ioctl_block_when_processing_errors(sdp, cmd, - (mode & FMODE_NDELAY) != 0); + (mode & BLK_OPEN_NDELAY)); if (error) return error; if (is_sed_ioctl(cmd)) return sed_ioctl(sdkp->opal_dev, cmd, p); - return scsi_ioctl(sdp, mode, cmd, p); + return scsi_ioctl(sdp, mode & BLK_OPEN_WRITE, cmd, p); } static void set_media_not_present(struct scsi_disk *sdkp) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 037f8c98a6d3..dcb73787c29d 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -237,7 +237,7 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd) if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; - if (!scsi_cmd_allowed(cmd, filp->f_mode)) + if (!scsi_cmd_allowed(cmd, filp->f_mode & FMODE_WRITE)) return -EPERM; return 0; } @@ -1103,7 +1103,8 @@ sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp, case SCSI_IOCTL_SEND_COMMAND: if (atomic_read(&sdp->detaching)) return -ENODEV; - return scsi_ioctl(sdp->device, filp->f_mode, cmd_in, p); + return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, + cmd_in, p); case SG_SET_DEBUG: result = get_user(val, ip); if (result) @@ -1159,7 +1160,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p); if (ret != -ENOIOCTLCMD) return ret; - return scsi_ioctl(sdp->device, filp->f_mode, cmd_in, p); + return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); } static __poll_t @@ -1496,6 +1497,10 @@ sg_add_device(struct device *cl_dev) int error; unsigned long iflags; + error = blk_get_queue(scsidp->request_queue); + if (error) + return error; + error = -ENOMEM; cdev = cdev_alloc(); if (!cdev) { @@ -1553,6 +1558,7 @@ cdev_add_err: out: if (cdev) cdev_del(cdev); + blk_put_queue(scsidp->request_queue); return error; } @@ -1560,6 +1566,7 @@ static void sg_device_destroy(struct kref *kref) { struct sg_device *sdp = container_of(kref, struct sg_device, d_ref); + struct request_queue *q = sdp->device->request_queue; unsigned long flags; /* CAUTION! Note that the device can still be found via idr_find() @@ -1567,6 +1574,9 @@ sg_device_destroy(struct kref *kref) * any other cleanup. */ + blk_trace_remove(q); + blk_put_queue(q); + write_lock_irqsave(&sg_index_lock, flags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, flags); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 12869e6d4ebd..ce886c8c9dbe 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -484,9 +484,9 @@ static void sr_revalidate_disk(struct scsi_cd *cd) get_sectorsize(cd); } -static int sr_block_open(struct block_device *bdev, fmode_t mode) +static int sr_block_open(struct gendisk *disk, blk_mode_t mode) { - struct scsi_cd *cd = scsi_cd(bdev->bd_disk); + struct scsi_cd *cd = scsi_cd(disk); struct scsi_device *sdev = cd->device; int ret; @@ -494,11 +494,11 @@ static int sr_block_open(struct block_device *bdev, fmode_t mode) return -ENXIO; scsi_autopm_get_device(sdev); - if (bdev_check_media_change(bdev)) + if (disk_check_media_change(disk)) sr_revalidate_disk(cd); mutex_lock(&cd->lock); - ret = cdrom_open(&cd->cdi, bdev, mode); + ret = cdrom_open(&cd->cdi, mode); mutex_unlock(&cd->lock); scsi_autopm_put_device(sdev); @@ -507,19 +507,19 @@ static int sr_block_open(struct block_device *bdev, fmode_t mode) return ret; } -static void sr_block_release(struct gendisk *disk, fmode_t mode) +static void sr_block_release(struct gendisk *disk) { struct scsi_cd *cd = scsi_cd(disk); mutex_lock(&cd->lock); - cdrom_release(&cd->cdi, mode); + cdrom_release(&cd->cdi); mutex_unlock(&cd->lock); scsi_device_put(cd->device); } -static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, - unsigned long arg) +static int sr_block_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg) { struct scsi_cd *cd = scsi_cd(bdev->bd_disk); struct scsi_device *sdev = cd->device; @@ -532,18 +532,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, mutex_lock(&cd->lock); ret = scsi_ioctl_block_when_processing_errors(sdev, cmd, - (mode & FMODE_NDELAY) != 0); + (mode & BLK_OPEN_NDELAY)); if (ret) goto out; scsi_autopm_get_device(sdev); if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { - ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); + ret = cdrom_ioctl(&cd->cdi, bdev, cmd, arg); if (ret != -ENOSYS) goto put; } - ret = scsi_ioctl(sdev, mode, cmd, argp); + ret = scsi_ioctl(sdev, mode & BLK_OPEN_WRITE, cmd, argp); put: scsi_autopm_put_device(sdev); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index b90a440e135d..14d7981ddcdd 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -3832,7 +3832,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) break; } - retval = scsi_ioctl(STp->device, file->f_mode, cmd_in, p); + retval = scsi_ioctl(STp->device, file->f_mode & FMODE_WRITE, cmd_in, p); if (!retval && cmd_in == SCSI_IOCTL_STOP_UNIT) { /* unload */ STp->rew_at_close = 0; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index e6bc622954cf..659196a2f63a 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1567,6 +1567,8 @@ static int storvsc_device_configure(struct scsi_device *sdevice) { blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ)); + /* storvsc devices don't support MAINTENANCE_IN SCSI cmd */ + sdevice->no_report_opcodes = 1; sdevice->no_write_same = 1; /* diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 6ddb2dfc0f00..32449bef4415 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -1756,8 +1756,11 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->slow_sram = true; if (of_device_is_compatible(pdev->dev.of_node, - "xlnx,versal-ospi-1.0")) - dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + "xlnx,versal-ospi-1.0")) { + ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) + goto probe_reset_failed; + } } ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0, diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index 5f2aee69c1c1..15f5e9cb54ad 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -274,7 +274,7 @@ static void dw_spi_elba_set_cs(struct spi_device *spi, bool enable) */ spi_set_chipselect(spi, 0, 0); dw_spi_set_cs(spi, enable); - spi_get_chipselect(spi, cs); + spi_set_chipselect(spi, 0, cs); } static int dw_spi_elba_init(struct platform_device *pdev, diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 4339485d202c..674cfe05f411 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1002,7 +1002,9 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, static int dspi_setup(struct spi_device *spi) { struct fsl_dspi *dspi = spi_controller_get_devdata(spi->controller); + u32 period_ns = DIV_ROUND_UP(NSEC_PER_SEC, spi->max_speed_hz); unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0; + u32 quarter_period_ns = DIV_ROUND_UP(period_ns, 4); u32 cs_sck_delay = 0, sck_cs_delay = 0; struct fsl_dspi_platform_data *pdata; unsigned char pasc = 0, asc = 0; @@ -1031,6 +1033,19 @@ static int dspi_setup(struct spi_device *spi) sck_cs_delay = pdata->sck_cs_delay; } + /* Since tCSC and tASC apply to continuous transfers too, avoid SCK + * glitches of half a cycle by never allowing tCSC + tASC to go below + * half a SCK period. + */ + if (cs_sck_delay < quarter_period_ns) + cs_sck_delay = quarter_period_ns; + if (sck_cs_delay < quarter_period_ns) + sck_cs_delay = quarter_period_ns; + + dev_dbg(&spi->dev, + "DSPI controller timing params: CS-to-SCK delay %u ns, SCK-to-CS delay %u ns\n", + cs_sck_delay, sck_cs_delay); + clkrate = clk_get_rate(dspi->clk); hz_to_spi_baud(&pbr, &br, spi->max_speed_hz, clkrate); diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index a98b781b103a..b293428760bc 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -646,6 +646,8 @@ static int spi_geni_init(struct spi_geni_master *mas) geni_se_select_mode(se, GENI_GPI_DMA); dev_dbg(mas->dev, "Using GPI DMA mode for SPI\n"); break; + } else if (ret == -EPROBE_DEFER) { + goto out_pm; } /* * in case of failure to get gpi dma channel, we can still do the diff --git a/drivers/staging/octeon/TODO b/drivers/staging/octeon/TODO index 67a0a1f6b922..044e48e3d65f 100644 --- a/drivers/staging/octeon/TODO +++ b/drivers/staging/octeon/TODO @@ -6,4 +6,3 @@ TODO: - make driver self-contained instead of being split between staging and arch/mips/cavium-octeon. -Contact: Aaro Koskinen <aaro.koskinen@iki.fi> diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index cc838ffd1294..3c462d69daca 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -90,7 +90,7 @@ static int iblock_configure_device(struct se_device *dev) struct request_queue *q; struct block_device *bd = NULL; struct blk_integrity *bi; - fmode_t mode; + blk_mode_t mode = BLK_OPEN_READ; unsigned int max_write_zeroes_sectors; int ret; @@ -108,13 +108,12 @@ static int iblock_configure_device(struct se_device *dev) pr_debug( "IBLOCK: Claiming struct block_device: %s\n", ib_dev->ibd_udev_path); - mode = FMODE_READ|FMODE_EXCL; if (!ib_dev->ibd_readonly) - mode |= FMODE_WRITE; + mode |= BLK_OPEN_WRITE; else dev->dev_flags |= DF_READ_ONLY; - bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev); + bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev, NULL); if (IS_ERR(bd)) { ret = PTR_ERR(bd); goto out_free_bioset; @@ -175,7 +174,7 @@ static int iblock_configure_device(struct se_device *dev) return 0; out_blkdev_put: - blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(ib_dev->ibd_bd, ib_dev); out_free_bioset: bioset_exit(&ib_dev->ibd_bio_set); out: @@ -201,7 +200,7 @@ static void iblock_destroy_device(struct se_device *dev) struct iblock_dev *ib_dev = IBLOCK_DEV(dev); if (ib_dev->ibd_bd != NULL) - blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(ib_dev->ibd_bd, ib_dev); bioset_exit(&ib_dev->ibd_bio_set); } diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index e7425549e39c..0d4f09693ef4 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -366,8 +366,8 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) * Claim exclusive struct block_device access to struct scsi_device * for TYPE_DISK and TYPE_ZBC using supplied udev_path */ - bd = blkdev_get_by_path(dev->udev_path, - FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv); + bd = blkdev_get_by_path(dev->udev_path, BLK_OPEN_WRITE | BLK_OPEN_READ, + pdv, NULL); if (IS_ERR(bd)) { pr_err("pSCSI: blkdev_get_by_path() failed\n"); scsi_device_put(sd); @@ -377,7 +377,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) ret = pscsi_add_device_to_list(dev, sd); if (ret) { - blkdev_put(pdv->pdv_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(pdv->pdv_bd, pdv); scsi_device_put(sd); return ret; } @@ -565,8 +565,7 @@ static void pscsi_destroy_device(struct se_device *dev) */ if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) && pdv->pdv_bd) { - blkdev_put(pdv->pdv_bd, - FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(pdv->pdv_bd, pdv); pdv->pdv_bd = NULL; } /* diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 86adff2a86ed..687adc9e086c 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -504,6 +504,8 @@ target_setup_session(struct se_portal_group *tpg, free_sess: transport_free_session(sess); + return ERR_PTR(rc); + free_cnt: target_free_cmd_counter(cmd_cnt); return ERR_PTR(rc); diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.c b/drivers/thermal/intel/intel_soc_dts_iosf.c index f99dc7e4ae89..db97499f4f0a 100644 --- a/drivers/thermal/intel/intel_soc_dts_iosf.c +++ b/drivers/thermal/intel/intel_soc_dts_iosf.c @@ -398,7 +398,7 @@ struct intel_soc_dts_sensors *intel_soc_dts_iosf_init( spin_lock_init(&sensors->intr_notify_lock); mutex_init(&sensors->dts_update_lock); sensors->intr_type = intr_type; - sensors->tj_max = tj_max; + sensors->tj_max = tj_max * 1000; if (intr_type == INTEL_SOC_DTS_INTERRUPT_NONE) notification = false; else diff --git a/drivers/thunderbolt/dma_test.c b/drivers/thunderbolt/dma_test.c index 3bedecb236e0..14bb6dec6c4b 100644 --- a/drivers/thunderbolt/dma_test.c +++ b/drivers/thunderbolt/dma_test.c @@ -192,9 +192,9 @@ static int dma_test_start_rings(struct dma_test *dt) } ret = tb_xdomain_enable_paths(dt->xd, dt->tx_hopid, - dt->tx_ring ? dt->tx_ring->hop : 0, + dt->tx_ring ? dt->tx_ring->hop : -1, dt->rx_hopid, - dt->rx_ring ? dt->rx_ring->hop : 0); + dt->rx_ring ? dt->rx_ring->hop : -1); if (ret) { dma_test_free_rings(dt); return ret; @@ -218,9 +218,9 @@ static void dma_test_stop_rings(struct dma_test *dt) tb_ring_stop(dt->tx_ring); ret = tb_xdomain_disable_paths(dt->xd, dt->tx_hopid, - dt->tx_ring ? dt->tx_ring->hop : 0, + dt->tx_ring ? dt->tx_ring->hop : -1, dt->rx_hopid, - dt->rx_ring ? dt->rx_ring->hop : 0); + dt->rx_ring ? dt->rx_ring->hop : -1); if (ret) dev_warn(&dt->svc->dev, "failed to disable DMA paths\n"); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index c0aee5dc5237..e58beac44295 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -56,9 +56,14 @@ static int ring_interrupt_index(const struct tb_ring *ring) static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) { - if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) - return; - iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) { + u32 val; + + val = ioread32(nhi->iobase + REG_RING_INTERRUPT_BASE + ring); + iowrite32(val & ~mask, nhi->iobase + REG_RING_INTERRUPT_BASE + ring); + } else { + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); + } } static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 7bfbc9ca9ba4..c1af712ca728 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -737,6 +737,7 @@ static void tb_scan_port(struct tb_port *port) { struct tb_cm *tcm = tb_priv(port->sw->tb); struct tb_port *upstream_port; + bool discovery = false; struct tb_switch *sw; int ret; @@ -804,8 +805,10 @@ static void tb_scan_port(struct tb_port *port) * tunnels and know which switches were authorized already by * the boot firmware. */ - if (!tcm->hotplug_active) + if (!tcm->hotplug_active) { dev_set_uevent_suppress(&sw->dev, true); + discovery = true; + } /* * At the moment Thunderbolt 2 and beyond (devices with LC) we @@ -835,10 +838,14 @@ static void tb_scan_port(struct tb_port *port) * CL0s and CL1 are enabled and supported together. * Silently ignore CLx enabling in case CLx is not supported. */ - ret = tb_switch_enable_clx(sw, TB_CL1); - if (ret && ret != -EOPNOTSUPP) - tb_sw_warn(sw, "failed to enable %s on upstream port\n", - tb_switch_clx_name(TB_CL1)); + if (discovery) { + tb_sw_dbg(sw, "discovery, not touching CL states\n"); + } else { + ret = tb_switch_enable_clx(sw, TB_CL1); + if (ret && ret != -EOPNOTSUPP) + tb_sw_warn(sw, "failed to enable %s on upstream port\n", + tb_switch_clx_name(TB_CL1)); + } if (tb_switch_is_clx_enabled(sw, TB_CL1)) /* diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 9099ae73e78f..4f222673d651 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -526,7 +526,7 @@ static int tb_dp_xchg_caps(struct tb_tunnel *tunnel) * Perform connection manager handshake between IN and OUT ports * before capabilities exchange can take place. */ - ret = tb_dp_cm_handshake(in, out, 1500); + ret = tb_dp_cm_handshake(in, out, 3000); if (ret) return ret; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 7486a2b8556c..7fd30fcc10c6 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -310,7 +310,7 @@ static const struct lpuart_soc_data ls1021a_data = { static const struct lpuart_soc_data ls1028a_data = { .devtype = LS1028A_LPUART, .iotype = UPIO_MEM32, - .rx_watermark = 1, + .rx_watermark = 0, }; static struct lpuart_soc_data imx7ulp_data = { diff --git a/drivers/tty/serial/lantiq.c b/drivers/tty/serial/lantiq.c index a58e9277dfad..f1387f1024db 100644 --- a/drivers/tty/serial/lantiq.c +++ b/drivers/tty/serial/lantiq.c @@ -250,6 +250,7 @@ lqasc_err_int(int irq, void *_port) struct ltq_uart_port *ltq_port = to_ltq_uart_port(port); spin_lock_irqsave(<q_port->lock, flags); + __raw_writel(ASC_IRNCR_EIR, port->membase + LTQ_ASC_IRNCR); /* clear any pending interrupts */ asc_update_bits(0, ASCWHBSTATE_CLRPE | ASCWHBSTATE_CLRFE | ASCWHBSTATE_CLRROE, port->membase + LTQ_ASC_WHBSTATE); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index c84be40fb8df..4737a8f92c2e 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -466,7 +466,7 @@ static const struct file_operations tty_fops = { .llseek = no_llseek, .read_iter = tty_read, .write_iter = tty_write, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, @@ -481,7 +481,7 @@ static const struct file_operations console_fops = { .llseek = no_llseek, .read_iter = tty_read, .write_iter = redirected_tty_write, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 7b2ce013cc5b..d68958e151a7 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1929,6 +1929,11 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); + /* + * HACK: Clear the driver data, which is currently accessed by parent + * glue drivers, before allowing the parent to suspend. + */ + platform_set_drvdata(pdev, NULL); pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 959fc925ca7c..79b22abf9727 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -308,7 +308,16 @@ static void dwc3_qcom_interconnect_exit(struct dwc3_qcom *qcom) /* Only usable in contexts where the role can not change. */ static bool dwc3_qcom_is_host(struct dwc3_qcom *qcom) { - struct dwc3 *dwc = platform_get_drvdata(qcom->dwc3); + struct dwc3 *dwc; + + /* + * FIXME: Fix this layering violation. + */ + dwc = platform_get_drvdata(qcom->dwc3); + + /* Core driver may not have probed yet. */ + if (!dwc) + return false; return dwc->xhci; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index d831f5acf7b5..b78599dd705c 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -198,6 +198,7 @@ static void dwc3_gadget_del_and_unmap_request(struct dwc3_ep *dep, list_del(&req->list); req->remaining = 0; req->needs_extra_trb = false; + req->num_trbs = 0; if (req->request.status == -EINPROGRESS) req->request.status = status; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 52e6d2e84e35..83fd1de14784 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,6 +37,14 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. + * @allow_connect: Indicates whether UDC is allowed to be pulled up. + * Set/cleared by gadget_(un)bind_driver() after gadget driver is bound or + * unbound. + * @connect_lock: protects udc->started, gadget->connect, + * gadget->allow_connect and gadget->deactivate. The routines + * usb_gadget_connect_locked(), usb_gadget_disconnect_locked(), + * usb_udc_connect_control_locked(), usb_gadget_udc_start_locked() and + * usb_gadget_udc_stop_locked() are called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -48,6 +56,9 @@ struct usb_udc { struct list_head list; bool vbus; bool started; + bool allow_connect; + struct work_struct vbus_work; + struct mutex connect_lock; }; static struct class *udc_class; @@ -687,17 +698,8 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected - * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_connect(struct usb_gadget *gadget) +static int usb_gadget_connect_locked(struct usb_gadget *gadget) + __must_hold(&gadget->udc->connect_lock) { int ret = 0; @@ -706,10 +708,12 @@ int usb_gadget_connect(struct usb_gadget *gadget) goto out; } - if (gadget->deactivated) { + if (gadget->deactivated || !gadget->udc->allow_connect || !gadget->udc->started) { /* - * If gadget is deactivated we only save new state. - * Gadget will be connected automatically after activation. + * If the gadget isn't usable (because it is deactivated, + * unbound, or not yet started), we only save the new state. + * The gadget will be connected automatically when it is + * activated/bound/started. */ gadget->connected = true; goto out; @@ -724,22 +728,31 @@ out: return ret; } -EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). * * Returns zero on success, else negative errno. */ -int usb_gadget_disconnect(struct usb_gadget *gadget) +int usb_gadget_connect(struct usb_gadget *gadget) +{ + int ret; + + mutex_lock(&gadget->udc->connect_lock); + ret = usb_gadget_connect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_connect); + +static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) + __must_hold(&gadget->udc->connect_lock) { int ret = 0; @@ -751,7 +764,7 @@ int usb_gadget_disconnect(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated) { + if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. @@ -774,6 +787,30 @@ out: return ret; } + +/** + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected + * + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_disconnect(struct usb_gadget *gadget) +{ + int ret; + + mutex_lock(&gadget->udc->connect_lock); + ret = usb_gadget_disconnect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); + + return ret; +} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -791,13 +828,14 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) { int ret = 0; + mutex_lock(&gadget->udc->connect_lock); if (gadget->deactivated) - goto out; + goto unlock; if (gadget->connected) { - ret = usb_gadget_disconnect(gadget); + ret = usb_gadget_disconnect_locked(gadget); if (ret) - goto out; + goto unlock; /* * If gadget was being connected before deactivation, we want @@ -807,7 +845,8 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -out: +unlock: + mutex_unlock(&gadget->udc->connect_lock); trace_usb_gadget_deactivate(gadget, ret); return ret; @@ -827,8 +866,9 @@ int usb_gadget_activate(struct usb_gadget *gadget) { int ret = 0; + mutex_lock(&gadget->udc->connect_lock); if (!gadget->deactivated) - goto out; + goto unlock; gadget->deactivated = false; @@ -837,9 +877,11 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect(gadget); + ret = usb_gadget_connect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); -out: +unlock: + mutex_unlock(&gadget->udc->connect_lock); trace_usb_gadget_activate(gadget, ret); return ret; @@ -1078,12 +1120,22 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -static void usb_udc_connect_control(struct usb_udc *udc) +/* Acquire connect_lock before calling this function. */ +static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) { if (udc->vbus) - usb_gadget_connect(udc->gadget); + usb_gadget_connect_locked(udc->gadget); else - usb_gadget_disconnect(udc->gadget); + usb_gadget_disconnect_locked(udc->gadget); +} + +static void vbus_event_work(struct work_struct *work) +{ + struct usb_udc *udc = container_of(work, struct usb_udc, vbus_work); + + mutex_lock(&udc->connect_lock); + usb_udc_connect_control_locked(udc); + mutex_unlock(&udc->connect_lock); } /** @@ -1094,6 +1146,14 @@ static void usb_udc_connect_control(struct usb_udc *udc) * * The udc driver calls it when it wants to connect or disconnect gadget * according to vbus status. + * + * This function can be invoked from interrupt context by irq handlers of + * the gadget drivers, however, usb_udc_connect_control() has to run in + * non-atomic context due to the following: + * a. Some of the gadget driver implementations expect the ->pullup + * callback to be invoked in non-atomic context. + * b. usb_gadget_disconnect() acquires udc_lock which is a mutex. + * Hence offload invocation of usb_udc_connect_control() to workqueue. */ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { @@ -1101,7 +1161,7 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) if (udc) { udc->vbus = status; - usb_udc_connect_control(udc); + schedule_work(&udc->vbus_work); } } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1124,7 +1184,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start - tells usb device controller to start up + * usb_gadget_udc_start_locked - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1135,8 +1195,11 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. + * + * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start(struct usb_udc *udc) +static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) + __must_hold(&udc->connect_lock) { int ret; @@ -1153,7 +1216,7 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc) } /** - * usb_gadget_udc_stop - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1162,8 +1225,11 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. + * + * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop(struct usb_udc *udc) +static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) + __must_hold(&udc->connect_lock) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1322,12 +1388,14 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; + mutex_init(&udc->connect_lock); udc->started = false; mutex_lock(&udc_lock); list_add_tail(&udc->list, &udc_list); mutex_unlock(&udc_lock); + INIT_WORK(&udc->vbus_work, vbus_event_work); ret = device_add(&udc->dev); if (ret) @@ -1459,6 +1527,7 @@ void usb_del_gadget(struct usb_gadget *gadget) flush_work(&gadget->work); device_del(&gadget->dev); ida_free(&gadget_id_numbers, gadget->id_number); + cancel_work_sync(&udc->vbus_work); device_unregister(&udc->dev); } EXPORT_SYMBOL_GPL(usb_del_gadget); @@ -1523,11 +1592,16 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - ret = usb_gadget_udc_start(udc); - if (ret) + mutex_lock(&udc->connect_lock); + ret = usb_gadget_udc_start_locked(udc); + if (ret) { + mutex_unlock(&udc->connect_lock); goto err_start; + } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control(udc); + udc->allow_connect = true; + usb_udc_connect_control_locked(udc); + mutex_unlock(&udc->connect_lock); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1558,12 +1632,16 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - usb_gadget_disconnect(gadget); + udc->allow_connect = false; + cancel_work_sync(&udc->vbus_work); + mutex_lock(&udc->connect_lock); + usb_gadget_disconnect_locked(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop(udc); + usb_gadget_udc_stop_locked(udc); + mutex_unlock(&udc->connect_lock); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1649,11 +1727,15 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - usb_gadget_udc_start(udc); - usb_gadget_connect(udc->gadget); + mutex_lock(&udc->connect_lock); + usb_gadget_udc_start_locked(udc); + usb_gadget_connect_locked(udc->gadget); + mutex_unlock(&udc->connect_lock); } else if (sysfs_streq(buf, "disconnect")) { - usb_gadget_disconnect(udc->gadget); - usb_gadget_udc_stop(udc); + mutex_lock(&udc->connect_lock); + usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_udc_stop_locked(udc); + mutex_unlock(&udc->connect_lock); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index aac8bc185afa..eb008e873361 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2877,9 +2877,9 @@ static int renesas_usb3_probe(struct platform_device *pdev) struct rzv2m_usb3drd *ddata = dev_get_drvdata(pdev->dev.parent); usb3->drd_reg = ddata->reg; - ret = devm_request_irq(ddata->dev, ddata->drd_irq, + ret = devm_request_irq(&pdev->dev, ddata->drd_irq, renesas_usb3_otg_irq, 0, - dev_name(ddata->dev), usb3); + dev_name(&pdev->dev), usb3); if (ret < 0) return ret; } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 644a55447fd7..fd42e3a0bd18 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -248,6 +248,8 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_VENDOR_ID 0x2c7c /* These Quectel products use Quectel's vendor ID */ #define QUECTEL_PRODUCT_EC21 0x0121 +#define QUECTEL_PRODUCT_EM061K_LTA 0x0123 +#define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 @@ -266,6 +268,8 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200U 0x0901 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 +#define QUECTEL_PRODUCT_EM061K_LWW 0x6008 +#define QUECTEL_PRODUCT_EM061K_LCN 0x6009 #define QUECTEL_PRODUCT_EC200T 0x6026 #define QUECTEL_PRODUCT_RM500K 0x7001 @@ -1189,6 +1193,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LMS, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LTA, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LWW, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) }, diff --git a/drivers/usb/typec/pd.c b/drivers/usb/typec/pd.c index 0bcde1ff4d39..8cc66e4467c4 100644 --- a/drivers/usb/typec/pd.c +++ b/drivers/usb/typec/pd.c @@ -95,7 +95,7 @@ peak_current_show(struct device *dev, struct device_attribute *attr, char *buf) static ssize_t fast_role_swap_current_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sysfs_emit(buf, "%u\n", to_pdo(dev)->pdo >> PDO_FIXED_FRS_CURR_SHIFT) & 3; + return sysfs_emit(buf, "%u\n", (to_pdo(dev)->pdo >> PDO_FIXED_FRS_CURR_SHIFT) & 3); } static DEVICE_ATTR_RO(fast_role_swap_current); diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 2b472ec01dc4..b664ecbb798b 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -132,10 +132,8 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) if (ret) return ret; - if (cci & UCSI_CCI_BUSY) { - ucsi->ops->async_write(ucsi, UCSI_CANCEL, NULL, 0); - return -EBUSY; - } + if (cmd != UCSI_CANCEL && cci & UCSI_CCI_BUSY) + return ucsi_exec_command(ucsi, UCSI_CANCEL); if (!(cci & UCSI_CCI_COMMAND_COMPLETE)) return -EIO; @@ -149,6 +147,11 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) return ucsi_read_error(ucsi); } + if (cmd == UCSI_CANCEL && cci & UCSI_CCI_CANCEL_COMPLETE) { + ret = ucsi_acknowledge_command(ucsi); + return ret ? ret : -EBUSY; + } + return UCSI_CCI_LENGTH(cci); } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 6c31b8c8112d..2996fb00387f 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -374,6 +374,28 @@ v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +/* + * v9fs_file_splice_read - splice-read from a file + * @in: The 9p file to read from + * @ppos: Where to find/update the file position + * @pipe: The pipe to splice into + * @len: The maximum amount of data to splice + * @flags: SPLICE_F_* flags + */ +static ssize_t v9fs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct p9_fid *fid = in->private_data; + + p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n", + fid->fid, len, *ppos); + + if (fid->mode & P9L_DIRECT) + return copy_splice_read(in, ppos, pipe, len, flags); + return filemap_splice_read(in, ppos, pipe, len, flags); +} + /** * v9fs_file_write_iter - write to a file * @iocb: The operation parameters @@ -569,7 +591,7 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, - .splice_read = generic_file_splice_read, + .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -583,7 +605,7 @@ const struct file_operations v9fs_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/Makefile b/fs/Makefile index 5bfdbf0d7037..e513aaee0603 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -17,14 +17,8 @@ obj-y := open.o read_write.o file_table.o super.o \ fs_types.o fs_context.o fs_parser.o fsopen.o init.o \ kernel_read_file.o mnt_idmapping.o remap_range.o -ifeq ($(CONFIG_BLOCK),y) -obj-y += buffer.o mpage.o -else -obj-y += no-block.o -endif - -obj-$(CONFIG_PROC_FS) += proc_namespace.o - +obj-$(CONFIG_BLOCK) += buffer.o mpage.o +obj-$(CONFIG_PROC_FS) += proc_namespace.o obj-$(CONFIG_LEGACY_DIRECT_IO) += direct-io.o obj-y += notify/ obj-$(CONFIG_EPOLL) += eventpoll.o diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 754afb14a6ff..ee80718aaeec 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -28,7 +28,7 @@ const struct file_operations adfs_file_operations = { .mmap = generic_file_mmap, .fsync = generic_file_fsync, .write_iter = generic_file_write_iter, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; const struct inode_operations adfs_file_inode_operations = { diff --git a/fs/affs/file.c b/fs/affs/file.c index 8daeed31e1af..e43f2f007ac1 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -1001,7 +1001,7 @@ const struct file_operations affs_file_operations = { .open = affs_file_open, .release = affs_file_release, .fsync = affs_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; const struct inode_operations affs_file_inode_operations = { diff --git a/fs/afs/file.c b/fs/afs/file.c index 719b31374879..d37dd201752b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -25,6 +25,9 @@ static void afs_invalidate_folio(struct folio *folio, size_t offset, static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); +static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); static void afs_vm_open(struct vm_area_struct *area); static void afs_vm_close(struct vm_area_struct *area); static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); @@ -36,7 +39,7 @@ const struct file_operations afs_file_operations = { .read_iter = afs_file_read_iter, .write_iter = afs_file_write, .mmap = afs_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = afs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = afs_fsync, .lock = afs_lock, @@ -587,3 +590,18 @@ static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) return generic_file_read_iter(iocb, iter); } + +static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct afs_vnode *vnode = AFS_FS_I(file_inode(in)); + struct afs_file *af = in->private_data; + int ret; + + ret = afs_validate(vnode, af->key); + if (ret < 0) + return ret; + + return filemap_splice_read(in, ppos, pipe, len, flags); +} diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index d1c7068b4346..58452b86e672 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -115,8 +115,8 @@ responded: } } - if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && - rtt_us < server->probe.rtt) { + rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us); + if (rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; diff --git a/fs/afs/write.c b/fs/afs/write.c index c822d6006033..8750b99c3f56 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -731,6 +731,7 @@ static int afs_writepages_region(struct address_space *mapping, * (changing page->mapping to NULL), or even swizzled * back from swapper_space to tmpfs file mapping */ +try_again: if (wbc->sync_mode != WB_SYNC_NONE) { ret = folio_lock_killable(folio); if (ret < 0) { @@ -757,12 +758,14 @@ static int afs_writepages_region(struct address_space *mapping, #ifdef CONFIG_AFS_FSCACHE folio_wait_fscache(folio); #endif - } else { - start += folio_size(folio); + goto try_again; } + + start += folio_size(folio); if (wbc->sync_mode == WB_SYNC_NONE) { if (skips >= 5 || need_resched()) { *_next = start; + folio_batch_release(&fbatch); _leave(" = 0 [%llx]", *_next); return 0; } @@ -530,7 +530,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) for (i = 0; i < nr_pages; i++) { struct page *page; page = find_or_create_page(file->f_mapping, - i, GFP_HIGHUSER | __GFP_ZERO); + i, GFP_USER | __GFP_ZERO); if (!page) break; pr_debug("pid(%d) page[%d]->count=%d\n", @@ -571,7 +571,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); ring->nr = nr_events; /* user copy */ ring->id = ~0U; ring->head = ring->tail = 0; @@ -579,7 +579,6 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) ring->compat_features = AIO_RING_COMPAT_FEATURES; ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); - kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); return 0; @@ -682,9 +681,8 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) * we are protected from page migration * changes ring_pages by ->ring_lock. */ - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); ring->id = ctx->id; - kunmap_atomic(ring); return 0; } @@ -1025,9 +1023,8 @@ static void user_refill_reqs_available(struct kioctx *ctx) * against ctx->completed_events below will make sure we do the * safe/right thing. */ - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); head = ring->head; - kunmap_atomic(ring); refill_reqs_available(ctx, head, ctx->tail); } @@ -1133,12 +1130,11 @@ static void aio_complete(struct aio_kiocb *iocb) if (++tail >= ctx->nr_events) tail = 0; - ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); + ev_page = page_address(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; *event = iocb->ki_res; - kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, @@ -1152,10 +1148,9 @@ static void aio_complete(struct aio_kiocb *iocb) ctx->tail = tail; - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); head = ring->head; ring->tail = tail; - kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); ctx->completed_events++; @@ -1215,10 +1210,9 @@ static long aio_read_events_ring(struct kioctx *ctx, mutex_lock(&ctx->ring_lock); /* Access to ->ring_pages here is protected by ctx->ring_lock. */ - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); head = ring->head; tail = ring->tail; - kunmap_atomic(ring); /* * Ensure that once we've read the current tail pointer, that @@ -1250,10 +1244,9 @@ static long aio_read_events_ring(struct kioctx *ctx, avail = min(avail, nr - ret); avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos); - ev = kmap(page); + ev = page_address(page); copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); - kunmap(page); if (unlikely(copy_ret)) { ret = -EFAULT; @@ -1265,9 +1258,8 @@ static long aio_read_events_ring(struct kioctx *ctx, head %= ctx->nr_events; } - ring = kmap_atomic(ctx->ring_pages[0]); + ring = page_address(ctx->ring_pages[0]); ring->head = head; - kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); pr_debug("%li h%u t%u\n", ret, head, tail); diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 6baf90b08e0e..93046c9dc461 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -600,7 +600,7 @@ static int autofs_dir_symlink(struct mnt_idmap *idmap, p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; - dir->i_mtime = current_time(dir); + dir->i_mtime = dir->i_ctime = current_time(dir); return 0; } @@ -633,7 +633,7 @@ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) d_inode(dentry)->i_size = 0; clear_nlink(d_inode(dentry)); - dir->i_mtime = current_time(dir); + dir->i_mtime = dir->i_ctime = current_time(dir); spin_lock(&sbi->lookup_lock); __autofs_add_expiring(dentry); @@ -749,7 +749,7 @@ static int autofs_dir_mkdir(struct mnt_idmap *idmap, p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; inc_nlink(dir); - dir->i_mtime = current_time(dir); + dir->i_mtime = dir->i_ctime = current_time(dir); return 0; } diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 57ae5ee6deec..adc2230079c6 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -27,7 +27,7 @@ const struct file_operations bfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; static int bfs_move_block(unsigned long from, unsigned long to, diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index aac240430efe..ce083e99ef68 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -71,6 +71,16 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq) return atomic_read(&wq->pending) > wq->thresh * 2; } +static void btrfs_init_workqueue(struct btrfs_workqueue *wq, + struct btrfs_fs_info *fs_info) +{ + wq->fs_info = fs_info; + atomic_set(&wq->pending, 0); + INIT_LIST_HEAD(&wq->ordered_list); + spin_lock_init(&wq->list_lock); + spin_lock_init(&wq->thres_lock); +} + struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name, unsigned int flags, int limit_active, int thresh) @@ -80,9 +90,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, if (!ret) return NULL; - ret->fs_info = fs_info; + btrfs_init_workqueue(ret, fs_info); + ret->limit_active = limit_active; - atomic_set(&ret->pending, 0); if (thresh == 0) thresh = DFT_THRESHOLD; /* For low threshold, disabling threshold is a better choice */ @@ -106,9 +116,33 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, return NULL; } - INIT_LIST_HEAD(&ret->ordered_list); - spin_lock_init(&ret->list_lock); - spin_lock_init(&ret->thres_lock); + trace_btrfs_workqueue_alloc(ret, name); + return ret; +} + +struct btrfs_workqueue *btrfs_alloc_ordered_workqueue( + struct btrfs_fs_info *fs_info, const char *name, + unsigned int flags) +{ + struct btrfs_workqueue *ret; + + ret = kzalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) + return NULL; + + btrfs_init_workqueue(ret, fs_info); + + /* Ordered workqueues don't allow @max_active adjustments. */ + ret->limit_active = 1; + ret->current_active = 1; + ret->thresh = NO_THRESHOLD; + + ret->normal_wq = alloc_ordered_workqueue("btrfs-%s", flags, name); + if (!ret->normal_wq) { + kfree(ret); + return NULL; + } + trace_btrfs_workqueue_alloc(ret, name); return ret; } diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 6e2596ddae10..30f66c5e2e6e 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -31,6 +31,9 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, unsigned int flags, int limit_active, int thresh); +struct btrfs_workqueue *btrfs_alloc_ordered_workqueue( + struct btrfs_fs_info *fs_info, const char *name, + unsigned int flags); void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func, btrfs_func_t ordered_func, btrfs_func_t ordered_free); void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index b3ad0f51e616..12b12443efaa 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -27,6 +27,17 @@ struct btrfs_failed_bio { atomic_t repair_count; }; +/* Is this a data path I/O that needs storage layer checksum and repair? */ +static inline bool is_data_bbio(struct btrfs_bio *bbio) +{ + return bbio->inode && is_data_inode(&bbio->inode->vfs_inode); +} + +static bool bbio_has_ordered_extent(struct btrfs_bio *bbio) +{ + return is_data_bbio(bbio) && btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE; +} + /* * Initialize a btrfs_bio structure. This skips the embedded bio itself as it * is already initialized by the block layer. @@ -61,20 +72,6 @@ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, return bbio; } -static blk_status_t btrfs_bio_extract_ordered_extent(struct btrfs_bio *bbio) -{ - struct btrfs_ordered_extent *ordered; - int ret; - - ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset); - if (WARN_ON_ONCE(!ordered)) - return BLK_STS_IOERR; - ret = btrfs_extract_ordered_extent(bbio, ordered); - btrfs_put_ordered_extent(ordered); - - return errno_to_blk_status(ret); -} - static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, struct btrfs_bio *orig_bbio, u64 map_length, bool use_append) @@ -95,13 +92,41 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; bbio->file_offset = orig_bbio->file_offset; - if (!(orig_bbio->bio.bi_opf & REQ_BTRFS_ONE_ORDERED)) - orig_bbio->file_offset += map_length; - + orig_bbio->file_offset += map_length; + if (bbio_has_ordered_extent(bbio)) { + refcount_inc(&orig_bbio->ordered->refs); + bbio->ordered = orig_bbio->ordered; + } atomic_inc(&orig_bbio->pending_ios); return bbio; } +/* Free a bio that was never submitted to the underlying device. */ +static void btrfs_cleanup_bio(struct btrfs_bio *bbio) +{ + if (bbio_has_ordered_extent(bbio)) + btrfs_put_ordered_extent(bbio->ordered); + bio_put(&bbio->bio); +} + +static void __btrfs_bio_end_io(struct btrfs_bio *bbio) +{ + if (bbio_has_ordered_extent(bbio)) { + struct btrfs_ordered_extent *ordered = bbio->ordered; + + bbio->end_io(bbio); + btrfs_put_ordered_extent(ordered); + } else { + bbio->end_io(bbio); + } +} + +void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) +{ + bbio->bio.bi_status = status; + __btrfs_bio_end_io(bbio); +} + static void btrfs_orig_write_end_io(struct bio *bio); static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio, @@ -130,12 +155,12 @@ static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio) if (bbio->bio.bi_status) btrfs_bbio_propagate_error(bbio, orig_bbio); - bio_put(&bbio->bio); + btrfs_cleanup_bio(bbio); bbio = orig_bbio; } if (atomic_dec_and_test(&bbio->pending_ios)) - bbio->end_io(bbio); + __btrfs_bio_end_io(bbio); } static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror) @@ -327,7 +352,7 @@ static void btrfs_end_bio_work(struct work_struct *work) struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, end_io_work); /* Metadata reads are checked and repaired by the submitter. */ - if (bbio->inode && !(bbio->bio.bi_opf & REQ_META)) + if (is_data_bbio(bbio)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else btrfs_orig_bbio_end_io(bbio); @@ -348,7 +373,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND) + if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_orig_bbio_end_io(bbio); } @@ -361,8 +386,7 @@ static void btrfs_raid56_end_io(struct bio *bio) btrfs_bio_counter_dec(bioc->fs_info); bbio->mirror_num = bioc->mirror_num; - if (bio_op(bio) == REQ_OP_READ && bbio->inode && - !(bbio->bio.bi_opf & REQ_META)) + if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) btrfs_check_read_bio(bbio, NULL); else btrfs_orig_bbio_end_io(bbio); @@ -472,13 +496,12 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr) static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc, struct btrfs_io_stripe *smap, int mirror_num) { - /* Do not leak our private flag into the block layer. */ - bio->bi_opf &= ~REQ_BTRFS_ONE_ORDERED; - if (!bioc) { /* Single mirror read/write fast path. */ btrfs_bio(bio)->mirror_num = mirror_num; bio->bi_iter.bi_sector = smap->physical >> SECTOR_SHIFT; + if (bio_op(bio) != REQ_OP_READ) + btrfs_bio(bio)->orig_physical = smap->physical; bio->bi_private = smap->dev; bio->bi_end_io = btrfs_simple_end_io; btrfs_submit_dev_bio(smap->dev, bio); @@ -574,27 +597,20 @@ static void run_one_async_free(struct btrfs_work *work) static bool should_async_write(struct btrfs_bio *bbio) { - /* - * If the I/O is not issued by fsync and friends, (->sync_writers != 0), - * then try to defer the submission to a workqueue to parallelize the - * checksum calculation. - */ - if (atomic_read(&bbio->inode->sync_writers)) + /* Submit synchronously if the checksum implementation is fast. */ + if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &bbio->fs_info->flags)) return false; /* - * Submit metadata writes synchronously if the checksum implementation - * is fast, or we are on a zoned device that wants I/O to be submitted - * in order. + * Try to defer the submission to a workqueue to parallelize the + * checksum calculation unless the I/O is issued synchronously. */ - if (bbio->bio.bi_opf & REQ_META) { - struct btrfs_fs_info *fs_info = bbio->fs_info; + if (op_is_sync(bbio->bio.bi_opf)) + return false; - if (btrfs_is_zoned(fs_info)) - return false; - if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) - return false; - } + /* Zoned devices require I/O to be submitted in order. */ + if ((bbio->bio.bi_opf & REQ_META) && btrfs_is_zoned(bbio->fs_info)) + return false; return true; } @@ -622,10 +638,7 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, run_one_async_free); - if (op_is_sync(bbio->bio.bi_opf)) - btrfs_queue_work(fs_info->hipri_workers, &async->work); - else - btrfs_queue_work(fs_info->workers, &async->work); + btrfs_queue_work(fs_info->workers, &async->work); return true; } @@ -635,7 +648,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) struct btrfs_fs_info *fs_info = bbio->fs_info; struct btrfs_bio *orig_bbio = bbio; struct bio *bio = &bbio->bio; - u64 logical = bio->bi_iter.bi_sector << 9; + u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; u64 length = bio->bi_iter.bi_size; u64 map_length = length; bool use_append = btrfs_use_zone_append(bbio); @@ -645,8 +658,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) int error; btrfs_bio_counter_inc_blocked(fs_info); - error = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, - &bioc, &smap, &mirror_num, 1); + error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, + &bioc, &smap, &mirror_num, 1); if (error) { ret = errno_to_blk_status(error); goto fail; @@ -665,7 +678,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) * Save the iter for the end_io handler and preload the checksums for * data reads. */ - if (bio_op(bio) == REQ_OP_READ && inode && !(bio->bi_opf & REQ_META)) { + if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) { bbio->saved_iter = bio->bi_iter; ret = btrfs_lookup_bio_sums(bbio); if (ret) @@ -676,9 +689,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) if (use_append) { bio->bi_opf &= ~REQ_OP_WRITE; bio->bi_opf |= REQ_OP_ZONE_APPEND; - ret = btrfs_bio_extract_ordered_extent(bbio); - if (ret) - goto fail_put_bio; } /* @@ -695,6 +705,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) ret = btrfs_bio_csum(bbio); if (ret) goto fail_put_bio; + } else if (use_append) { + ret = btrfs_alloc_dummy_sum(bbio); + if (ret) + goto fail_put_bio; } } @@ -704,7 +718,7 @@ done: fail_put_bio: if (map_length < length) - bio_put(bio); + btrfs_cleanup_bio(bbio); fail: btrfs_bio_counter_dec(fs_info); btrfs_bio_end_io(orig_bbio, ret); diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h index a8eca3a65673..ca79decee060 100644 --- a/fs/btrfs/bio.h +++ b/fs/btrfs/bio.h @@ -39,8 +39,8 @@ struct btrfs_bio { union { /* - * Data checksumming and original I/O information for internal - * use in the btrfs_submit_bio machinery. + * For data reads: checksumming and original I/O information. + * (for internal use in the btrfs_submit_bio machinery only) */ struct { u8 *csum; @@ -48,7 +48,20 @@ struct btrfs_bio { struct bvec_iter saved_iter; }; - /* For metadata parentness verification. */ + /* + * For data writes: + * - ordered extent covering the bio + * - pointer to the checksums for this bio + * - original physical address from the allocator + * (for zone append only) + */ + struct { + struct btrfs_ordered_extent *ordered; + struct btrfs_ordered_sum *sums; + u64 orig_physical; + }; + + /* For metadata reads: parentness verification. */ struct btrfs_tree_parent_check parent_check; }; @@ -84,15 +97,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, struct btrfs_fs_info *fs_info, btrfs_bio_end_io_t end_io, void *private); - -static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) -{ - bbio->bio.bi_status = status; - bbio->end_io(bbio); -} - -/* Bio only refers to one ordered extent. */ -#define REQ_BTRFS_ONE_ORDERED REQ_DRV +void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status); /* Submit using blkcg_punt_bio_submit. */ #define REQ_BTRFS_CGROUP_PUNT REQ_FS_PRIVATE diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 590b03560265..48ae509f2ac2 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -95,14 +95,21 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags) } allowed &= flags; - if (allowed & BTRFS_BLOCK_GROUP_RAID6) + /* Select the highest-redundancy RAID level. */ + if (allowed & BTRFS_BLOCK_GROUP_RAID1C4) + allowed = BTRFS_BLOCK_GROUP_RAID1C4; + else if (allowed & BTRFS_BLOCK_GROUP_RAID6) allowed = BTRFS_BLOCK_GROUP_RAID6; + else if (allowed & BTRFS_BLOCK_GROUP_RAID1C3) + allowed = BTRFS_BLOCK_GROUP_RAID1C3; else if (allowed & BTRFS_BLOCK_GROUP_RAID5) allowed = BTRFS_BLOCK_GROUP_RAID5; else if (allowed & BTRFS_BLOCK_GROUP_RAID10) allowed = BTRFS_BLOCK_GROUP_RAID10; else if (allowed & BTRFS_BLOCK_GROUP_RAID1) allowed = BTRFS_BLOCK_GROUP_RAID1; + else if (allowed & BTRFS_BLOCK_GROUP_DUP) + allowed = BTRFS_BLOCK_GROUP_DUP; else if (allowed & BTRFS_BLOCK_GROUP_RAID0) allowed = BTRFS_BLOCK_GROUP_RAID0; @@ -1633,11 +1640,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; + trace_btrfs_add_unused_block_group(bg); spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); - trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); + } else { + /* Pull out the block group from the reclaim_bgs list. */ + list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); } @@ -1791,8 +1801,15 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) } spin_unlock(&bg->lock); - /* Get out fast, in case we're unmounting the filesystem */ - if (btrfs_fs_closing(fs_info)) { + /* + * Get out fast, in case we're read-only or unmounting the + * filesystem. It is OK to drop block groups from the list even + * for the read-only case. As we did sb_start_write(), + * "mount -o remount,ro" won't happen and read-only filesystem + * means it is forced read-only due to a fatal error. So, it + * never gets back to read-write to let us reclaim again. + */ + if (btrfs_need_cleaner_sleep(fs_info)) { up_write(&space_info->groups_sem); goto next; } @@ -1823,11 +1840,27 @@ void btrfs_reclaim_bgs_work(struct work_struct *work) } next: + if (ret) + btrfs_mark_bg_to_reclaim(bg); btrfs_put_block_group(bg); + + mutex_unlock(&fs_info->reclaim_bgs_lock); + /* + * Reclaiming all the block groups in the list can take really + * long. Prioritize cleaning up unused block groups. + */ + btrfs_delete_unused_bgs(fs_info); + /* + * If we are interrupted by a balance, we can just bail out. The + * cleaner thread restart again if necessary. + */ + if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) + goto end; spin_lock(&fs_info->unused_bgs_lock); } spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); +end: btrfs_exclop_finish(fs_info); sb_end_write(fs_info->sb); } @@ -1973,7 +2006,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) - io_stripe_size = nr_data_stripes(map) << BTRFS_STRIPE_LEN_SHIFT; + io_stripe_size = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); buf = kcalloc(map->num_stripes, sizeof(u64), GFP_NOFS); if (!buf) { @@ -3521,9 +3554,9 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&space_info->lock); - set_extent_dirty(&trans->transaction->pinned_extents, - bytenr, bytenr + num_bytes - 1, - GFP_NOFS | __GFP_NOFAIL); + set_extent_bit(&trans->transaction->pinned_extents, + bytenr, bytenr + num_bytes - 1, + EXTENT_DIRTY, NULL); } spin_lock(&trans->transaction->dirty_bgs_lock); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index cc0e4b37db2d..f204addc3fe8 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -162,7 +162,14 @@ struct btrfs_block_group { */ struct list_head cluster_list; - /* For delayed block group creation or deletion of empty block groups */ + /* + * Used for several lists: + * + * 1) struct btrfs_fs_info::unused_bgs + * 2) struct btrfs_fs_info::reclaim_bgs + * 3) struct btrfs_transaction::deleted_bgs + * 4) struct btrfs_trans_handle::new_bgs + */ struct list_head bg_list; /* For read-only block groups */ diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index ac18c43fadad..6279d200cf83 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -541,3 +541,22 @@ try_reserve: return ERR_PTR(ret); } + +int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, + struct btrfs_block_rsv *rsv) +{ + u64 needed_bytes; + int ret; + + /* 1 for slack space, 1 for updating the inode */ + needed_bytes = btrfs_calc_insert_metadata_size(fs_info, 1) + + btrfs_calc_metadata_size(fs_info, 1); + + spin_lock(&rsv->lock); + if (rsv->reserved < needed_bytes) + ret = -ENOSPC; + else + ret = 0; + spin_unlock(&rsv->lock); + return ret; +} diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index 6dc781709aca..b0bd12b8652f 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -82,6 +82,8 @@ void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info); struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize); +int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, + struct btrfs_block_rsv *rsv); static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, u32 blocksize) diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index ec2ae4406c16..d47a927b3504 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -116,9 +116,6 @@ struct btrfs_inode { unsigned long runtime_flags; - /* Keep track of who's O_SYNC/fsyncing currently */ - atomic_t sync_writers; - /* full 64 bit generation number, struct vfs_inode doesn't have a big * enough field for this. */ @@ -335,7 +332,7 @@ static inline void btrfs_mod_outstanding_extents(struct btrfs_inode *inode, if (btrfs_is_free_space_inode(inode)) return; trace_btrfs_inode_mod_outstanding_extents(inode->root, btrfs_ino(inode), - mod); + mod, inode->outstanding_extents); } /* @@ -407,30 +404,12 @@ static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) return true; } -/* - * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two - * separate u32s. These two functions convert between the two representations. - */ -static inline u64 btrfs_inode_combine_flags(u32 flags, u32 ro_flags) -{ - return (flags | ((u64)ro_flags << 32)); -} - -static inline void btrfs_inode_split_flags(u64 inode_item_flags, - u32 *flags, u32 *ro_flags) -{ - *flags = (u32)inode_item_flags; - *ro_flags = (u32)(inode_item_flags >> 32); -} - /* Array of bytes with variable length, hexadecimal format 0x1234 */ #define CSUM_FMT "0x%*phN" #define CSUM_FMT_VALUE(size, bytes) size, bytes int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page, u32 pgoff, u8 *csum, const u8 * const csum_expected); -int btrfs_extract_ordered_extent(struct btrfs_bio *bbio, - struct btrfs_ordered_extent *ordered); bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev, u32 bio_offset, struct bio_vec *bv); noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 82e49d985019..3caf339c4bb3 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -1459,13 +1459,13 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, struct btrfs_fs_info *fs_info = state->fs_info; int ret; u64 length; - struct btrfs_io_context *multi = NULL; + struct btrfs_io_context *bioc = NULL; + struct btrfs_io_stripe smap, *map; struct btrfs_device *device; length = len; - ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, - bytenr, &length, &multi, mirror_num); - + ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, bytenr, &length, &bioc, + NULL, &mirror_num, 0); if (ret) { block_ctx_out->start = 0; block_ctx_out->dev_bytenr = 0; @@ -1478,21 +1478,26 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, return ret; } - device = multi->stripes[0].dev; + if (bioc) + map = &bioc->stripes[0]; + else + map = &smap; + + device = map->dev; if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state) || !device->bdev || !device->name) block_ctx_out->dev = NULL; else block_ctx_out->dev = btrfsic_dev_state_lookup( device->bdev->bd_dev); - block_ctx_out->dev_bytenr = multi->stripes[0].physical; + block_ctx_out->dev_bytenr = map->physical; block_ctx_out->start = bytenr; block_ctx_out->len = len; block_ctx_out->datav = NULL; block_ctx_out->pagev = NULL; block_ctx_out->mem_to_free = NULL; - kfree(multi); + kfree(bioc); if (NULL == block_ctx_out->dev) { ret = -ENXIO; pr_info("btrfsic: error, cannot lookup dev (#1)!\n"); @@ -1565,7 +1570,7 @@ static int btrfsic_read_block(struct btrfsic_state *state, bio = bio_alloc(block_ctx->dev->bdev, num_pages - i, REQ_OP_READ, GFP_NOFS); - bio->bi_iter.bi_sector = dev_bytenr >> 9; + bio->bi_iter.bi_sector = dev_bytenr >> SECTOR_SHIFT; for (j = i; j < num_pages; j++) { ret = bio_add_page(bio, block_ctx->pagev[j], diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 2d0493f0a184..8818ed5c390f 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -37,7 +37,7 @@ #include "file-item.h" #include "super.h" -struct bio_set btrfs_compressed_bioset; +static struct bio_set btrfs_compressed_bioset; static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" }; @@ -211,8 +211,6 @@ static noinline void end_compressed_writeback(const struct compressed_bio *cb) for (i = 0; i < ret; i++) { struct folio *folio = fbatch.folios[i]; - if (errno) - folio_set_error(folio); btrfs_page_clamp_clear_writeback(fs_info, &folio->page, cb->start, cb->len); } @@ -226,13 +224,8 @@ static void btrfs_finish_compressed_write_work(struct work_struct *work) struct compressed_bio *cb = container_of(work, struct compressed_bio, write_end_work); - /* - * Ok, we're the last bio for this extent, step one is to call back - * into the FS and do all the end_io operations. - */ - btrfs_writepage_endio_finish_ordered(cb->bbio.inode, NULL, - cb->start, cb->start + cb->len - 1, - cb->bbio.bio.bi_status == BLK_STS_OK); + btrfs_finish_ordered_extent(cb->bbio.ordered, NULL, cb->start, cb->len, + cb->bbio.bio.bi_status == BLK_STS_OK); if (cb->writeback) end_compressed_writeback(cb); @@ -281,32 +274,31 @@ static void btrfs_add_compressed_bio_pages(struct compressed_bio *cb) * This also checksums the file bytes and gets things ready for * the end io hooks. */ -void btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, - unsigned int len, u64 disk_start, - unsigned int compressed_len, - struct page **compressed_pages, - unsigned int nr_pages, - blk_opf_t write_flags, - bool writeback) +void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered, + struct page **compressed_pages, + unsigned int nr_pages, + blk_opf_t write_flags, + bool writeback) { + struct btrfs_inode *inode = BTRFS_I(ordered->inode); struct btrfs_fs_info *fs_info = inode->root->fs_info; struct compressed_bio *cb; - ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && - IS_ALIGNED(len, fs_info->sectorsize)); - - write_flags |= REQ_BTRFS_ONE_ORDERED; + ASSERT(IS_ALIGNED(ordered->file_offset, fs_info->sectorsize)); + ASSERT(IS_ALIGNED(ordered->num_bytes, fs_info->sectorsize)); - cb = alloc_compressed_bio(inode, start, REQ_OP_WRITE | write_flags, + cb = alloc_compressed_bio(inode, ordered->file_offset, + REQ_OP_WRITE | write_flags, end_compressed_bio_write); - cb->start = start; - cb->len = len; + cb->start = ordered->file_offset; + cb->len = ordered->num_bytes; cb->compressed_pages = compressed_pages; - cb->compressed_len = compressed_len; + cb->compressed_len = ordered->disk_num_bytes; cb->writeback = writeback; INIT_WORK(&cb->write_end_work, btrfs_finish_compressed_write_work); cb->nr_pages = nr_pages; - cb->bbio.bio.bi_iter.bi_sector = disk_start >> SECTOR_SHIFT; + cb->bbio.bio.bi_iter.bi_sector = ordered->disk_bytenr >> SECTOR_SHIFT; + cb->bbio.ordered = ordered; btrfs_add_compressed_bio_pages(cb); btrfs_submit_bio(&cb->bbio, 0); @@ -421,7 +413,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, */ if (!em || cur < em->start || (cur + fs_info->sectorsize > extent_map_end(em)) || - (em->block_start >> 9) != orig_bio->bi_iter.bi_sector) { + (em->block_start >> SECTOR_SHIFT) != orig_bio->bi_iter.bi_sector) { free_extent_map(em); unlock_extent(tree, cur, page_end, NULL); unlock_page(page); @@ -472,7 +464,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, * After the compressed pages are read, we copy the bytes into the * bio we were passed and then call the bio end_io calls */ -void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num) +void btrfs_submit_compressed_read(struct btrfs_bio *bbio) { struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; @@ -538,7 +530,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num) if (memstall) psi_memstall_leave(&pflags); - btrfs_submit_bio(&cb->bbio, mirror_num); + btrfs_submit_bio(&cb->bbio, 0); return; out_free_compressed_pages: diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 19ab2abeddc0..03bb9d143fa7 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -10,6 +10,7 @@ #include "bio.h" struct btrfs_inode; +struct btrfs_ordered_extent; /* * We want to make sure that amount of RAM required to uncompress an extent is @@ -86,14 +87,12 @@ int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, int btrfs_decompress_buf2page(const char *buf, u32 buf_len, struct compressed_bio *cb, u32 decompressed); -void btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, - unsigned int len, u64 disk_start, - unsigned int compressed_len, +void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered, struct page **compressed_pages, unsigned int nr_pages, blk_opf_t write_flags, bool writeback); -void btrfs_submit_compressed_read(struct btrfs_bio *bbio, int mirror_num); +void btrfs_submit_compressed_read(struct btrfs_bio *bbio); unsigned int btrfs_compress_str2level(unsigned int type, const char *str); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 2ff2961b1183..a4cb4b642987 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -37,8 +37,6 @@ static int push_node_left(struct btrfs_trans_handle *trans, static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); -static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, - int level, int slot); static const struct btrfs_csums { u16 size; @@ -150,13 +148,19 @@ static inline void copy_leaf_items(const struct extent_buffer *dst, nr_items * sizeof(struct btrfs_item)); } +/* This exists for btrfs-progs usages. */ +u16 btrfs_csum_type_size(u16 type) +{ + return btrfs_csums[type].size; +} + int btrfs_super_csum_size(const struct btrfs_super_block *s) { u16 t = btrfs_super_csum_type(s); /* * csum type is validated at mount time */ - return btrfs_csums[t].size; + return btrfs_csum_type_size(t); } const char *btrfs_super_csum_name(u16 csum_type) @@ -417,9 +421,13 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, &refs, &flags); if (ret) return ret; - if (refs == 0) { - ret = -EROFS; - btrfs_handle_fs_error(fs_info, ret, NULL); + if (unlikely(refs == 0)) { + btrfs_crit(fs_info, + "found 0 references for tree block at bytenr %llu level %d root %llu", + buf->start, btrfs_header_level(buf), + btrfs_root_id(root)); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); return ret; } } else { @@ -464,10 +472,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return ret; } if (new_flags != 0) { - int level = btrfs_header_level(buf); - - ret = btrfs_set_disk_extent_flags(trans, buf, - new_flags, level); + ret = btrfs_set_disk_extent_flags(trans, buf, new_flags); if (ret) return ret; } @@ -583,9 +588,14 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV) parent_start = buf->start; - atomic_inc(&cow->refs); ret = btrfs_tree_mod_log_insert_root(root->node, cow, true); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); + return ret; + } + atomic_inc(&cow->refs); rcu_assign_pointer(root->node, cow); btrfs_free_tree_block(trans, btrfs_root_id(root), buf, @@ -594,8 +604,14 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, add_root_to_dirty_list(root); } else { WARN_ON(trans->transid != btrfs_header_generation(parent)); - btrfs_tree_mod_log_insert_key(parent, parent_slot, - BTRFS_MOD_LOG_KEY_REPLACE); + ret = btrfs_tree_mod_log_insert_key(parent, parent_slot, + BTRFS_MOD_LOG_KEY_REPLACE); + if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); + return ret; + } btrfs_set_node_blockptr(parent, parent_slot, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, @@ -1028,8 +1044,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, child = btrfs_read_node_slot(mid, 0); if (IS_ERR(child)) { ret = PTR_ERR(child); - btrfs_handle_fs_error(fs_info, ret, NULL); - goto enospc; + goto out; } btrfs_tree_lock(child); @@ -1038,11 +1053,16 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (ret) { btrfs_tree_unlock(child); free_extent_buffer(child); - goto enospc; + goto out; } ret = btrfs_tree_mod_log_insert_root(root->node, child, true); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_tree_unlock(child); + free_extent_buffer(child); + btrfs_abort_transaction(trans, ret); + goto out; + } rcu_assign_pointer(root->node, child); add_root_to_dirty_list(root); @@ -1070,7 +1090,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (IS_ERR(left)) { ret = PTR_ERR(left); left = NULL; - goto enospc; + goto out; } __btrfs_tree_lock(left, BTRFS_NESTING_LEFT); @@ -1079,7 +1099,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NESTING_LEFT_COW); if (wret) { ret = wret; - goto enospc; + goto out; } } @@ -1088,7 +1108,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (IS_ERR(right)) { ret = PTR_ERR(right); right = NULL; - goto enospc; + goto out; } __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT); @@ -1097,7 +1117,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NESTING_RIGHT_COW); if (wret) { ret = wret; - goto enospc; + goto out; } } @@ -1119,7 +1139,12 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (btrfs_header_nritems(right) == 0) { btrfs_clear_buffer_dirty(trans, right); btrfs_tree_unlock(right); - del_ptr(root, path, level + 1, pslot + 1); + ret = btrfs_del_ptr(trans, root, path, level + 1, pslot + 1); + if (ret < 0) { + free_extent_buffer_stale(right); + right = NULL; + goto out; + } root_sub_used(root, right->len); btrfs_free_tree_block(trans, btrfs_root_id(root), right, 0, 1); @@ -1130,7 +1155,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_node_key(right, &right_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out; + } btrfs_set_node_key(parent, &right_key, pslot + 1); btrfs_mark_buffer_dirty(parent); } @@ -1145,15 +1173,19 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, * otherwise we would have pulled some pointers from the * right */ - if (!left) { - ret = -EROFS; - btrfs_handle_fs_error(fs_info, ret, NULL); - goto enospc; + if (unlikely(!left)) { + btrfs_crit(fs_info, +"missing left child when middle child only has 1 item, parent bytenr %llu level %d mid bytenr %llu root %llu", + parent->start, btrfs_header_level(parent), + mid->start, btrfs_root_id(root)); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + goto out; } wret = balance_node_right(trans, mid, left); if (wret < 0) { ret = wret; - goto enospc; + goto out; } if (wret == 1) { wret = push_node_left(trans, left, mid, 1); @@ -1165,7 +1197,12 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (btrfs_header_nritems(mid) == 0) { btrfs_clear_buffer_dirty(trans, mid); btrfs_tree_unlock(mid); - del_ptr(root, path, level + 1, pslot); + ret = btrfs_del_ptr(trans, root, path, level + 1, pslot); + if (ret < 0) { + free_extent_buffer_stale(mid); + mid = NULL; + goto out; + } root_sub_used(root, mid->len); btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); @@ -1176,7 +1213,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_node_key(mid, &mid_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out; + } btrfs_set_node_key(parent, &mid_key, pslot); btrfs_mark_buffer_dirty(parent); } @@ -1202,7 +1242,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (orig_ptr != btrfs_node_blockptr(path->nodes[level], path->slots[level])) BUG(); -enospc: +out: if (right) { btrfs_tree_unlock(right); free_extent_buffer(right); @@ -1278,7 +1318,12 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, btrfs_node_key(mid, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot, BTRFS_MOD_LOG_KEY_REPLACE); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_tree_unlock(left); + free_extent_buffer(left); + btrfs_abort_transaction(trans, ret); + return ret; + } btrfs_set_node_key(parent, &disk_key, pslot); btrfs_mark_buffer_dirty(parent); if (btrfs_header_nritems(left) > orig_slot) { @@ -1333,7 +1378,12 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, btrfs_node_key(right, &disk_key, 0); ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1, BTRFS_MOD_LOG_KEY_REPLACE); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_tree_unlock(right); + free_extent_buffer(right); + btrfs_abort_transaction(trans, ret); + return ret; + } btrfs_set_node_key(parent, &disk_key, pslot + 1); btrfs_mark_buffer_dirty(parent); @@ -2379,6 +2429,87 @@ done: } /* + * Search the tree again to find a leaf with smaller keys. + * Returns 0 if it found something. + * Returns 1 if there are no smaller keys. + * Returns < 0 on error. + * + * This may release the path, and so you may lose any locks held at the + * time you call it. + */ +static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) +{ + struct btrfs_key key; + struct btrfs_key orig_key; + struct btrfs_disk_key found_key; + int ret; + + btrfs_item_key_to_cpu(path->nodes[0], &key, 0); + orig_key = key; + + if (key.offset > 0) { + key.offset--; + } else if (key.type > 0) { + key.type--; + key.offset = (u64)-1; + } else if (key.objectid > 0) { + key.objectid--; + key.type = (u8)-1; + key.offset = (u64)-1; + } else { + return 1; + } + + btrfs_release_path(path); + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret <= 0) + return ret; + + /* + * Previous key not found. Even if we were at slot 0 of the leaf we had + * before releasing the path and calling btrfs_search_slot(), we now may + * be in a slot pointing to the same original key - this can happen if + * after we released the path, one of more items were moved from a + * sibling leaf into the front of the leaf we had due to an insertion + * (see push_leaf_right()). + * If we hit this case and our slot is > 0 and just decrement the slot + * so that the caller does not process the same key again, which may or + * may not break the caller, depending on its logic. + */ + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); + ret = comp_keys(&found_key, &orig_key); + if (ret == 0) { + if (path->slots[0] > 0) { + path->slots[0]--; + return 0; + } + /* + * At slot 0, same key as before, it means orig_key is + * the lowest, leftmost, key in the tree. We're done. + */ + return 1; + } + } + + btrfs_item_key(path->nodes[0], &found_key, 0); + ret = comp_keys(&found_key, &key); + /* + * We might have had an item with the previous key in the tree right + * before we released our path. And after we released our path, that + * item might have been pushed to the first slot (0) of the leaf we + * were holding due to a tree balance. Alternatively, an item with the + * previous key can exist as the only element of a leaf (big fat item). + * Therefore account for these 2 cases, so that our callers (like + * btrfs_previous_item) don't miss an existing item with a key matching + * the previous key we computed above. + */ + if (ret <= 0) + return 0; + return 1; +} + +/* * helper to use instead of search slot if no exact match is needed but * instead the next or previous item should be returned. * When find_higher is true, the next higher item is returned, the next lower @@ -2552,6 +2683,7 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, if (slot > 0) { btrfs_item_key(eb, &disk_key, slot - 1); if (unlikely(comp_keys(&disk_key, new_key) >= 0)) { + btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), @@ -2559,13 +2691,13 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); - btrfs_print_leaf(eb); BUG(); } } if (slot < btrfs_header_nritems(eb) - 1) { btrfs_item_key(eb, &disk_key, slot + 1); if (unlikely(comp_keys(&disk_key, new_key) <= 0)) { + btrfs_print_leaf(eb); btrfs_crit(fs_info, "slot %u key (%llu %u %llu) new key (%llu %u %llu)", slot, btrfs_disk_key_objectid(&disk_key), @@ -2573,7 +2705,6 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, btrfs_disk_key_offset(&disk_key), new_key->objectid, new_key->type, new_key->offset); - btrfs_print_leaf(eb); BUG(); } } @@ -2626,7 +2757,7 @@ static bool check_sibling_keys(struct extent_buffer *left, btrfs_item_key_to_cpu(right, &right_first, 0); } - if (btrfs_comp_cpu_keys(&left_last, &right_first) >= 0) { + if (unlikely(btrfs_comp_cpu_keys(&left_last, &right_first) >= 0)) { btrfs_crit(left->fs_info, "left extent buffer:"); btrfs_print_tree(left, false); btrfs_crit(left->fs_info, "right extent buffer:"); @@ -2703,8 +2834,8 @@ static int push_node_left(struct btrfs_trans_handle *trans, if (push_items < src_nritems) { /* - * Don't call btrfs_tree_mod_log_insert_move() here, key removal - * was already fully logged by btrfs_tree_mod_log_eb_copy() above. + * btrfs_tree_mod_log_eb_copy handles logging the move, so we + * don't need to do an explicit tree mod log operation for it. */ memmove_extent_buffer(src, btrfs_node_key_ptr_offset(src, 0), btrfs_node_key_ptr_offset(src, push_items), @@ -2765,8 +2896,11 @@ static int balance_node_right(struct btrfs_trans_handle *trans, btrfs_abort_transaction(trans, ret); return ret; } - ret = btrfs_tree_mod_log_insert_move(dst, push_items, 0, dst_nritems); - BUG_ON(ret < 0); + + /* + * btrfs_tree_mod_log_eb_copy handles logging the move, so we don't + * need to do an explicit tree mod log operation for it. + */ memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(dst, push_items), btrfs_node_key_ptr_offset(dst, 0), (dst_nritems) * @@ -2840,7 +2974,12 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, old = root->node; ret = btrfs_tree_mod_log_insert_root(root->node, c, false); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_free_tree_block(trans, btrfs_root_id(root), c, 0, 1); + btrfs_tree_unlock(c); + free_extent_buffer(c); + return ret; + } rcu_assign_pointer(root->node, c); /* the super has an extra ref to root->node */ @@ -2861,10 +3000,10 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, * slot and level indicate where you want the key to go, and * blocknr is the block the key points to. */ -static void insert_ptr(struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct btrfs_disk_key *key, u64 bytenr, - int slot, int level) +static int insert_ptr(struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct btrfs_disk_key *key, u64 bytenr, + int slot, int level) { struct extent_buffer *lower; int nritems; @@ -2880,7 +3019,10 @@ static void insert_ptr(struct btrfs_trans_handle *trans, if (level) { ret = btrfs_tree_mod_log_insert_move(lower, slot + 1, slot, nritems - slot); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + return ret; + } } memmove_extent_buffer(lower, btrfs_node_key_ptr_offset(lower, slot + 1), @@ -2890,7 +3032,10 @@ static void insert_ptr(struct btrfs_trans_handle *trans, if (level) { ret = btrfs_tree_mod_log_insert_key(lower, slot, BTRFS_MOD_LOG_KEY_ADD); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + return ret; + } } btrfs_set_node_key(lower, key, slot); btrfs_set_node_blockptr(lower, slot, bytenr); @@ -2898,6 +3043,8 @@ static void insert_ptr(struct btrfs_trans_handle *trans, btrfs_set_node_ptr_generation(lower, slot, trans->transid); btrfs_set_header_nritems(lower, nritems + 1); btrfs_mark_buffer_dirty(lower); + + return 0; } /* @@ -2962,6 +3109,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, ret = btrfs_tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid); if (ret) { + btrfs_tree_unlock(split); + free_extent_buffer(split); btrfs_abort_transaction(trans, ret); return ret; } @@ -2975,8 +3124,13 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(c); btrfs_mark_buffer_dirty(split); - insert_ptr(trans, path, &disk_key, split->start, - path->slots[level + 1] + 1, level + 1); + ret = insert_ptr(trans, path, &disk_key, split->start, + path->slots[level + 1] + 1, level + 1); + if (ret < 0) { + btrfs_tree_unlock(split); + free_extent_buffer(split); + return ret; + } if (path->slots[level] >= mid) { path->slots[level] -= mid; @@ -2996,7 +3150,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, * and nr indicate which items in the leaf to check. This totals up the * space used both by the item structs and the item data */ -static int leaf_space_used(struct extent_buffer *l, int start, int nr) +static int leaf_space_used(const struct extent_buffer *l, int start, int nr) { int data_len; int nritems = btrfs_header_nritems(l); @@ -3016,7 +3170,7 @@ static int leaf_space_used(struct extent_buffer *l, int start, int nr) * the start of the leaf data. IOW, how much room * the leaf has left for both items and data */ -noinline int btrfs_leaf_free_space(struct extent_buffer *leaf) +int btrfs_leaf_free_space(const struct extent_buffer *leaf) { struct btrfs_fs_info *fs_info = leaf->fs_info; int nritems = btrfs_header_nritems(leaf); @@ -3453,16 +3607,17 @@ out: * split the path's leaf in two, making sure there is at least data_size * available for the resulting leaf level of the path. */ -static noinline void copy_for_split(struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct extent_buffer *l, - struct extent_buffer *right, - int slot, int mid, int nritems) +static noinline int copy_for_split(struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct extent_buffer *l, + struct extent_buffer *right, + int slot, int mid, int nritems) { struct btrfs_fs_info *fs_info = trans->fs_info; int data_copy_size; int rt_data_off; int i; + int ret; struct btrfs_disk_key disk_key; struct btrfs_map_token token; @@ -3487,7 +3642,9 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); - insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); + ret = insert_ptr(trans, path, &disk_key, right->start, path->slots[1] + 1, 1); + if (ret < 0) + return ret; btrfs_mark_buffer_dirty(right); btrfs_mark_buffer_dirty(l); @@ -3505,6 +3662,8 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, } BUG_ON(path->slots[0] < 0); + + return 0; } /* @@ -3703,8 +3862,13 @@ again: if (split == 0) { if (mid <= slot) { btrfs_set_header_nritems(right, 0); - insert_ptr(trans, path, &disk_key, - right->start, path->slots[1] + 1, 1); + ret = insert_ptr(trans, path, &disk_key, + right->start, path->slots[1] + 1, 1); + if (ret < 0) { + btrfs_tree_unlock(right); + free_extent_buffer(right); + return ret; + } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3712,8 +3876,13 @@ again: path->slots[1] += 1; } else { btrfs_set_header_nritems(right, 0); - insert_ptr(trans, path, &disk_key, - right->start, path->slots[1], 1); + ret = insert_ptr(trans, path, &disk_key, + right->start, path->slots[1], 1); + if (ret < 0) { + btrfs_tree_unlock(right); + free_extent_buffer(right); + return ret; + } btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3729,7 +3898,12 @@ again: return ret; } - copy_for_split(trans, path, l, right, slot, mid, nritems); + ret = copy_for_split(trans, path, l, right, slot, mid, nritems); + if (ret < 0) { + btrfs_tree_unlock(right); + free_extent_buffer(right); + return ret; + } if (split == 2) { BUG_ON(num_doubles != 0); @@ -3826,7 +4000,12 @@ static noinline int split_item(struct btrfs_path *path, struct btrfs_disk_key disk_key; leaf = path->nodes[0]; - BUG_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item)); + /* + * Shouldn't happen because the caller must have previously called + * setup_leaf_for_split() to make room for the new item in the leaf. + */ + if (WARN_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item))) + return -ENOSPC; orig_slot = path->slots[0]; orig_offset = btrfs_item_offset(leaf, path->slots[0]); @@ -4273,9 +4452,11 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, * * the tree should have been previously balanced so the deletion does not * empty a node. + * + * This is exported for use inside btrfs-progs, don't un-export it. */ -static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, - int level, int slot) +int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, + struct btrfs_path *path, int level, int slot) { struct extent_buffer *parent = path->nodes[level]; u32 nritems; @@ -4286,7 +4467,10 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, if (level) { ret = btrfs_tree_mod_log_insert_move(parent, slot, slot + 1, nritems - slot - 1); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + return ret; + } } memmove_extent_buffer(parent, btrfs_node_key_ptr_offset(parent, slot), @@ -4296,7 +4480,10 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, } else if (level) { ret = btrfs_tree_mod_log_insert_key(parent, slot, BTRFS_MOD_LOG_KEY_REMOVE); - BUG_ON(ret < 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + return ret; + } } nritems--; @@ -4312,6 +4499,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, fixup_low_keys(path, &disk_key, level + 1); } btrfs_mark_buffer_dirty(parent); + return 0; } /* @@ -4324,13 +4512,17 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path, * The path must have already been setup for deleting the leaf, including * all the proper balancing. path->nodes[1] must be locked. */ -static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_path *path, - struct extent_buffer *leaf) +static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + struct extent_buffer *leaf) { + int ret; + WARN_ON(btrfs_header_generation(leaf) != trans->transid); - del_ptr(root, path, 1, path->slots[1]); + ret = btrfs_del_ptr(trans, root, path, 1, path->slots[1]); + if (ret < 0) + return ret; /* * btrfs_free_extent is expensive, we want to make sure we @@ -4343,6 +4535,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, atomic_inc(&leaf->refs); btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); + return 0; } /* * delete the item at the leaf level in path. If that empties @@ -4392,7 +4585,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_set_header_level(leaf, 0); } else { btrfs_clear_buffer_dirty(trans, leaf); - btrfs_del_leaf(trans, root, path, leaf); + ret = btrfs_del_leaf(trans, root, path, leaf); + if (ret < 0) + return ret; } } else { int used = leaf_space_used(leaf, 0, nritems); @@ -4416,7 +4611,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, /* push_leaf_left fixes the path. * make sure the path still points to our leaf - * for possible call to del_ptr below + * for possible call to btrfs_del_ptr below */ slot = path->slots[1]; atomic_inc(&leaf->refs); @@ -4453,7 +4648,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (btrfs_header_nritems(leaf) == 0) { path->slots[1] = slot; - btrfs_del_leaf(trans, root, path, leaf); + ret = btrfs_del_leaf(trans, root, path, leaf); + if (ret < 0) + return ret; free_extent_buffer(leaf); ret = 0; } else { @@ -4474,86 +4671,6 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, } /* - * search the tree again to find a leaf with lesser keys - * returns 0 if it found something or 1 if there are no lesser leaves. - * returns < 0 on io errors. - * - * This may release the path, and so you may lose any locks held at the - * time you call it. - */ -int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) -{ - struct btrfs_key key; - struct btrfs_key orig_key; - struct btrfs_disk_key found_key; - int ret; - - btrfs_item_key_to_cpu(path->nodes[0], &key, 0); - orig_key = key; - - if (key.offset > 0) { - key.offset--; - } else if (key.type > 0) { - key.type--; - key.offset = (u64)-1; - } else if (key.objectid > 0) { - key.objectid--; - key.type = (u8)-1; - key.offset = (u64)-1; - } else { - return 1; - } - - btrfs_release_path(path); - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret <= 0) - return ret; - - /* - * Previous key not found. Even if we were at slot 0 of the leaf we had - * before releasing the path and calling btrfs_search_slot(), we now may - * be in a slot pointing to the same original key - this can happen if - * after we released the path, one of more items were moved from a - * sibling leaf into the front of the leaf we had due to an insertion - * (see push_leaf_right()). - * If we hit this case and our slot is > 0 and just decrement the slot - * so that the caller does not process the same key again, which may or - * may not break the caller, depending on its logic. - */ - if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { - btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); - ret = comp_keys(&found_key, &orig_key); - if (ret == 0) { - if (path->slots[0] > 0) { - path->slots[0]--; - return 0; - } - /* - * At slot 0, same key as before, it means orig_key is - * the lowest, leftmost, key in the tree. We're done. - */ - return 1; - } - } - - btrfs_item_key(path->nodes[0], &found_key, 0); - ret = comp_keys(&found_key, &key); - /* - * We might have had an item with the previous key in the tree right - * before we released our path. And after we released our path, that - * item might have been pushed to the first slot (0) of the leaf we - * were holding due to a tree balance. Alternatively, an item with the - * previous key can exist as the only element of a leaf (big fat item). - * Therefore account for these 2 cases, so that our callers (like - * btrfs_previous_item) don't miss an existing item with a key matching - * the previous key we computed above. - */ - if (ret <= 0) - return 0; - return 1; -} - -/* * A helper function to walk down the tree starting at min_key, and looking * for nodes or leaves that are have a minimum transaction id. * This is used by the btree defrag code, and tree logging diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4c1986cd5bed..f2d2b313bde5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -541,6 +541,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct extent_buffer **cow_ret, u64 new_root_objectid); int btrfs_block_can_be_shared(struct btrfs_root *root, struct extent_buffer *buf); +int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, + struct btrfs_path *path, int level, int slot); void btrfs_extend_item(struct btrfs_path *path, u32 data_size); void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end); int btrfs_split_item(struct btrfs_trans_handle *trans, @@ -633,7 +635,6 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, return btrfs_insert_empty_items(trans, root, path, &batch); } -int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, u64 time_seq); @@ -686,7 +687,7 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) { return btrfs_next_old_item(root, p, 0); } -int btrfs_leaf_free_space(struct extent_buffer *leaf); +int btrfs_leaf_free_space(const struct extent_buffer *leaf); static inline int is_fstree(u64 rootid) { @@ -702,6 +703,7 @@ static inline bool btrfs_is_data_reloc_root(const struct btrfs_root *root) return root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID; } +u16 btrfs_csum_type_size(u16 type); int btrfs_super_csum_size(const struct btrfs_super_block *s); const char *btrfs_super_csum_name(u16 csum_type); const char *btrfs_super_csum_driver(u16 csum_type); diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index 8065341d831a..f2ff4cbe8656 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -1040,7 +1040,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode, clear_extent_bit(&inode->io_tree, start, start + len - 1, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, cached_state); - set_extent_defrag(&inode->io_tree, start, start + len - 1, cached_state); + set_extent_bit(&inode->io_tree, start, start + len - 1, + EXTENT_DELALLOC | EXTENT_DEFRAG, cached_state); /* Update the page status */ for (i = start_index - first_index; i <= last_index - first_index; i++) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 0b32432d7d56..6a13cf00218b 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -407,7 +407,6 @@ static inline void drop_delayed_ref(struct btrfs_delayed_ref_root *delayed_refs, RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) list_del(&ref->add_list); - ref->in_tree = 0; btrfs_put_delayed_ref(ref); atomic_dec(&delayed_refs->num_entries); } @@ -507,6 +506,7 @@ struct btrfs_delayed_ref_head *btrfs_select_ref_head( { struct btrfs_delayed_ref_head *head; + lockdep_assert_held(&delayed_refs->lock); again: head = find_ref_head(delayed_refs, delayed_refs->run_delayed_start, true); @@ -531,7 +531,7 @@ again: href_node); } - head->processing = 1; + head->processing = true; WARN_ON(delayed_refs->num_heads_ready == 0); delayed_refs->num_heads_ready--; delayed_refs->run_delayed_start = head->bytenr + @@ -549,31 +549,35 @@ void btrfs_delete_ref_head(struct btrfs_delayed_ref_root *delayed_refs, RB_CLEAR_NODE(&head->href_node); atomic_dec(&delayed_refs->num_entries); delayed_refs->num_heads--; - if (head->processing == 0) + if (!head->processing) delayed_refs->num_heads_ready--; } /* * Helper to insert the ref_node to the tail or merge with tail. * - * Return 0 for insert. - * Return >0 for merge. + * Return false if the ref was inserted. + * Return true if the ref was merged into an existing one (and therefore can be + * freed by the caller). */ -static int insert_delayed_ref(struct btrfs_delayed_ref_root *root, - struct btrfs_delayed_ref_head *href, - struct btrfs_delayed_ref_node *ref) +static bool insert_delayed_ref(struct btrfs_delayed_ref_root *root, + struct btrfs_delayed_ref_head *href, + struct btrfs_delayed_ref_node *ref) { struct btrfs_delayed_ref_node *exist; int mod; - int ret = 0; spin_lock(&href->lock); exist = tree_insert(&href->ref_tree, ref); - if (!exist) - goto inserted; + if (!exist) { + if (ref->action == BTRFS_ADD_DELAYED_REF) + list_add_tail(&ref->add_list, &href->ref_add_list); + atomic_inc(&root->num_entries); + spin_unlock(&href->lock); + return false; + } /* Now we are sure we can merge */ - ret = 1; if (exist->action == ref->action) { mod = ref->ref_mod; } else { @@ -600,13 +604,7 @@ static int insert_delayed_ref(struct btrfs_delayed_ref_root *root, if (exist->ref_mod == 0) drop_delayed_ref(root, href, exist); spin_unlock(&href->lock); - return ret; -inserted: - if (ref->action == BTRFS_ADD_DELAYED_REF) - list_add_tail(&ref->add_list, &href->ref_add_list); - atomic_inc(&root->num_entries); - spin_unlock(&href->lock); - return ret; + return true; } /* @@ -699,34 +697,38 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref, bool is_system) { int count_mod = 1; - int must_insert_reserved = 0; + bool must_insert_reserved = false; /* If reserved is provided, it must be a data extent. */ BUG_ON(!is_data && reserved); - /* - * The head node stores the sum of all the mods, so dropping a ref - * should drop the sum in the head node by one. - */ - if (action == BTRFS_UPDATE_DELAYED_HEAD) + switch (action) { + case BTRFS_UPDATE_DELAYED_HEAD: count_mod = 0; - else if (action == BTRFS_DROP_DELAYED_REF) + break; + case BTRFS_DROP_DELAYED_REF: + /* + * The head node stores the sum of all the mods, so dropping a ref + * should drop the sum in the head node by one. + */ count_mod = -1; - - /* - * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved - * accounting when the extent is finally added, or if a later - * modification deletes the delayed ref without ever inserting the - * extent into the extent allocation tree. ref->must_insert_reserved - * is the flag used to record that accounting mods are required. - * - * Once we record must_insert_reserved, switch the action to - * BTRFS_ADD_DELAYED_REF because other special casing is not required. - */ - if (action == BTRFS_ADD_DELAYED_EXTENT) - must_insert_reserved = 1; - else - must_insert_reserved = 0; + break; + case BTRFS_ADD_DELAYED_EXTENT: + /* + * BTRFS_ADD_DELAYED_EXTENT means that we need to update the + * reserved accounting when the extent is finally added, or if a + * later modification deletes the delayed ref without ever + * inserting the extent into the extent allocation tree. + * ref->must_insert_reserved is the flag used to record that + * accounting mods are required. + * + * Once we record must_insert_reserved, switch the action to + * BTRFS_ADD_DELAYED_REF because other special casing is not + * required. + */ + must_insert_reserved = true; + break; + } refcount_set(&head_ref->refs, 1); head_ref->bytenr = bytenr; @@ -738,7 +740,7 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref, head_ref->ref_tree = RB_ROOT_CACHED; INIT_LIST_HEAD(&head_ref->ref_add_list); RB_CLEAR_NODE(&head_ref->href_node); - head_ref->processing = 0; + head_ref->processing = false; head_ref->total_ref_mod = count_mod; spin_lock_init(&head_ref->lock); mutex_init(&head_ref->mutex); @@ -763,11 +765,11 @@ static noinline struct btrfs_delayed_ref_head * add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref, struct btrfs_qgroup_extent_record *qrecord, - int action, int *qrecord_inserted_ret) + int action, bool *qrecord_inserted_ret) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; - int qrecord_inserted = 0; + bool qrecord_inserted = false; delayed_refs = &trans->transaction->delayed_refs; @@ -777,7 +779,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, delayed_refs, qrecord)) kfree(qrecord); else - qrecord_inserted = 1; + qrecord_inserted = true; } trace_add_delayed_ref_head(trans->fs_info, head_ref, action); @@ -853,8 +855,6 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, ref->num_bytes = num_bytes; ref->ref_mod = 1; ref->action = action; - ref->is_head = 0; - ref->in_tree = 1; ref->seq = seq; ref->type = ref_type; RB_CLEAR_NODE(&ref->ref_node); @@ -875,11 +875,11 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - int qrecord_inserted; + bool qrecord_inserted; bool is_system; + bool merged; int action = generic_ref->action; int level = generic_ref->tree_ref.level; - int ret; u64 bytenr = generic_ref->bytenr; u64 num_bytes = generic_ref->len; u64 parent = generic_ref->parent; @@ -935,7 +935,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, head_ref = add_delayed_ref_head(trans, head_ref, record, action, &qrecord_inserted); - ret = insert_delayed_ref(delayed_refs, head_ref, &ref->node); + merged = insert_delayed_ref(delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); /* @@ -947,7 +947,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, trace_add_delayed_tree_ref(fs_info, &ref->node, ref, action == BTRFS_ADD_DELAYED_EXTENT ? BTRFS_ADD_DELAYED_REF : action); - if (ret > 0) + if (merged) kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref); if (qrecord_inserted) @@ -968,9 +968,9 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_qgroup_extent_record *record = NULL; - int qrecord_inserted; + bool qrecord_inserted; int action = generic_ref->action; - int ret; + bool merged; u64 bytenr = generic_ref->bytenr; u64 num_bytes = generic_ref->len; u64 parent = generic_ref->parent; @@ -1027,7 +1027,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, head_ref = add_delayed_ref_head(trans, head_ref, record, action, &qrecord_inserted); - ret = insert_delayed_ref(delayed_refs, head_ref, &ref->node); + merged = insert_delayed_ref(delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); /* @@ -1039,7 +1039,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref, action == BTRFS_ADD_DELAYED_EXTENT ? BTRFS_ADD_DELAYED_REF : action); - if (ret > 0) + if (merged) kmem_cache_free(btrfs_delayed_data_ref_cachep, ref); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index b54261fe509b..b8e14b0ba5f1 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -48,9 +48,6 @@ struct btrfs_delayed_ref_node { unsigned int action:8; unsigned int type:8; - /* is this node still in the rbtree? */ - unsigned int is_head:1; - unsigned int in_tree:1; }; struct btrfs_delayed_extent_op { @@ -70,20 +67,26 @@ struct btrfs_delayed_extent_op { struct btrfs_delayed_ref_head { u64 bytenr; u64 num_bytes; - refcount_t refs; + /* + * For insertion into struct btrfs_delayed_ref_root::href_root. + * Keep it in the same cache line as 'bytenr' for more efficient + * searches in the rbtree. + */ + struct rb_node href_node; /* * the mutex is held while running the refs, and it is also * held when checking the sum of reference modifications. */ struct mutex mutex; + refcount_t refs; + + /* Protects 'ref_tree' and 'ref_add_list'. */ spinlock_t lock; struct rb_root_cached ref_tree; /* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */ struct list_head ref_add_list; - struct rb_node href_node; - struct btrfs_delayed_extent_op *extent_op; /* @@ -113,10 +116,10 @@ struct btrfs_delayed_ref_head { * we need to update the in ram accounting to properly reflect * the free has happened. */ - unsigned int must_insert_reserved:1; - unsigned int is_data:1; - unsigned int is_system:1; - unsigned int processing:1; + bool must_insert_reserved; + bool is_data; + bool is_system; + bool processing; }; struct btrfs_delayed_tree_ref { @@ -337,7 +340,7 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) { WARN_ON(refcount_read(&ref->refs) == 0); if (refcount_dec_and_test(&ref->refs)) { - WARN_ON(ref->in_tree); + WARN_ON(!RB_EMPTY_NODE(&ref->ref_node)); switch (ref->type) { case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_BLOCK_REF_KEY: diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 78696d331639..5f10965fd72b 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -41,7 +41,7 @@ * All new writes will be written to both target and source devices, so even * if replace gets canceled, sources device still contains up-to-date data. * - * Location: handle_ops_on_dev_replace() from __btrfs_map_block() + * Location: handle_ops_on_dev_replace() from btrfs_map_block() * Start: btrfs_dev_replace_start() * End: btrfs_dev_replace_finishing() * Content: Latest data/metadata @@ -257,8 +257,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return -EINVAL; } - bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, - fs_info->bdev_holder); + bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); if (IS_ERR(bdev)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); return PTR_ERR(bdev); @@ -315,7 +315,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, device->bdev = bdev; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->mode = FMODE_EXCL; + device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; @@ -334,7 +334,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return 0; error: - blkdev_put(bdev, FMODE_EXCL); + blkdev_put(bdev, fs_info->bdev_holder); return ret; } @@ -795,8 +795,8 @@ static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev, while (!find_first_extent_bit(&srcdev->alloc_state, start, &found_start, &found_end, CHUNK_ALLOCATED, &cached_state)) { - ret = set_extent_bits(&tgtdev->alloc_state, found_start, - found_end, CHUNK_ALLOCATED); + ret = set_extent_bit(&tgtdev->alloc_state, found_start, + found_end, CHUNK_ALLOCATED, NULL); if (ret) break; start = found_end + 1; diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index a6d77fe41e1a..944a7340f6a4 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -73,6 +73,23 @@ static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl, return &discard_ctl->discard_list[block_group->discard_index]; } +/* + * Determine if async discard should be running. + * + * @discard_ctl: discard control + * + * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set. + */ +static bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl) +{ + struct btrfs_fs_info *fs_info = container_of(discard_ctl, + struct btrfs_fs_info, + discard_ctl); + + return (!(fs_info->sb->s_flags & SB_RDONLY) && + test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags)); +} + static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { @@ -545,23 +562,6 @@ static void btrfs_discard_workfn(struct work_struct *work) } /* - * Determine if async discard should be running. - * - * @discard_ctl: discard control - * - * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set. - */ -bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl) -{ - struct btrfs_fs_info *fs_info = container_of(discard_ctl, - struct btrfs_fs_info, - discard_ctl); - - return (!(fs_info->sb->s_flags & SB_RDONLY) && - test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags)); -} - -/* * Recalculate the base delay. * * @discard_ctl: discard control diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h index 57b9202f427f..dddb0f9101ba 100644 --- a/fs/btrfs/discard.h +++ b/fs/btrfs/discard.h @@ -24,7 +24,6 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group); void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, bool override); -bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl); /* Update operations */ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2b1b227505f3..7513388b0567 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -60,15 +60,6 @@ BTRFS_SUPER_FLAG_METADUMP |\ BTRFS_SUPER_FLAG_METADUMP_V2) -static void btrfs_destroy_ordered_extents(struct btrfs_root *root); -static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_fs_info *fs_info); -static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root); -static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info, - struct extent_io_tree *dirty_pages, - int mark); -static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, - struct extent_io_tree *pinned_extents); static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info); static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info); @@ -110,35 +101,27 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) * detect blocks that either didn't get written at all or got written * in the wrong place. */ -static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid, - int atomic) +int btrfs_buffer_uptodate(struct extent_buffer *eb, u64 parent_transid, int atomic) { - struct extent_state *cached_state = NULL; - int ret; + if (!extent_buffer_uptodate(eb)) + return 0; if (!parent_transid || btrfs_header_generation(eb) == parent_transid) - return 0; + return 1; if (atomic) return -EAGAIN; - lock_extent(io_tree, eb->start, eb->start + eb->len - 1, &cached_state); - if (extent_buffer_uptodate(eb) && - btrfs_header_generation(eb) == parent_transid) { - ret = 0; - goto out; - } - btrfs_err_rl(eb->fs_info, + if (!extent_buffer_uptodate(eb) || + btrfs_header_generation(eb) != parent_transid) { + btrfs_err_rl(eb->fs_info, "parent transid verify failed on logical %llu mirror %u wanted %llu found %llu", eb->start, eb->read_mirror, parent_transid, btrfs_header_generation(eb)); - ret = 1; - clear_extent_buffer_uptodate(eb); -out: - unlock_extent(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state); - return ret; + clear_extent_buffer_uptodate(eb); + return 0; + } + return 1; } static bool btrfs_supported_super_csum(u16 csum_type) @@ -180,69 +163,10 @@ int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, return 0; } -int btrfs_verify_level_key(struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) -{ - struct btrfs_fs_info *fs_info = eb->fs_info; - int found_level; - struct btrfs_key found_key; - int ret; - - found_level = btrfs_header_level(eb); - if (found_level != level) { - WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), - KERN_ERR "BTRFS: tree level check failed\n"); - btrfs_err(fs_info, -"tree level mismatch detected, bytenr=%llu level expected=%u has=%u", - eb->start, level, found_level); - return -EIO; - } - - if (!first_key) - return 0; - - /* - * For live tree block (new tree blocks in current transaction), - * we need proper lock context to avoid race, which is impossible here. - * So we only checks tree blocks which is read from disk, whose - * generation <= fs_info->last_trans_committed. - */ - if (btrfs_header_generation(eb) > fs_info->last_trans_committed) - return 0; - - /* We have @first_key, so this @eb must have at least one item */ - if (btrfs_header_nritems(eb) == 0) { - btrfs_err(fs_info, - "invalid tree nritems, bytenr=%llu nritems=0 expect >0", - eb->start); - WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); - return -EUCLEAN; - } - - if (found_level) - btrfs_node_key_to_cpu(eb, &found_key, 0); - else - btrfs_item_key_to_cpu(eb, &found_key, 0); - ret = btrfs_comp_cpu_keys(first_key, &found_key); - - if (ret) { - WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), - KERN_ERR "BTRFS: tree first key check failed\n"); - btrfs_err(fs_info, -"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", - eb->start, parent_transid, first_key->objectid, - first_key->type, first_key->offset, - found_key.objectid, found_key.type, - found_key.offset); - } - return ret; -} - static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num) { struct btrfs_fs_info *fs_info = eb->fs_info; - u64 start = eb->start; int i, num_pages = num_extent_pages(eb); int ret = 0; @@ -251,12 +175,14 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, for (i = 0; i < num_pages; i++) { struct page *p = eb->pages[i]; + u64 start = max_t(u64, eb->start, page_offset(p)); + u64 end = min_t(u64, eb->start + eb->len, page_offset(p) + PAGE_SIZE); + u32 len = end - start; - ret = btrfs_repair_io_failure(fs_info, 0, start, PAGE_SIZE, - start, p, start - page_offset(p), mirror_num); + ret = btrfs_repair_io_failure(fs_info, 0, start, len, + start, p, offset_in_page(start), mirror_num); if (ret) break; - start += PAGE_SIZE; } return ret; @@ -311,12 +237,34 @@ int btrfs_read_extent_buffer(struct extent_buffer *eb, return ret; } -static int csum_one_extent_buffer(struct extent_buffer *eb) +/* + * Checksum a dirty tree block before IO. + */ +blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio) { + struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info; + u64 found_start = btrfs_header_bytenr(eb); u8 result[BTRFS_CSUM_SIZE]; int ret; + /* Btree blocks are always contiguous on disk. */ + if (WARN_ON_ONCE(bbio->file_offset != eb->start)) + return BLK_STS_IOERR; + if (WARN_ON_ONCE(bbio->bio.bi_iter.bi_size != eb->len)) + return BLK_STS_IOERR; + + if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { + WARN_ON_ONCE(found_start != 0); + return BLK_STS_OK; + } + + if (WARN_ON_ONCE(found_start != eb->start)) + return BLK_STS_IOERR; + if (WARN_ON(!btrfs_page_test_uptodate(fs_info, eb->pages[0], eb->start, + eb->len))) + return BLK_STS_IOERR; + ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid, offsetof(struct btrfs_header, fsid), BTRFS_FSID_SIZE) == 0); @@ -325,7 +273,7 @@ static int csum_one_extent_buffer(struct extent_buffer *eb) if (btrfs_header_level(eb)) ret = btrfs_check_node(eb); else - ret = btrfs_check_leaf_full(eb); + ret = btrfs_check_leaf(eb); if (ret < 0) goto error; @@ -343,8 +291,7 @@ static int csum_one_extent_buffer(struct extent_buffer *eb) goto error; } write_extent_buffer(eb, result, 0, fs_info->csum_size); - - return 0; + return BLK_STS_OK; error: btrfs_print_tree(eb, 0); @@ -358,103 +305,10 @@ error: */ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) || btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); - return ret; -} - -/* Checksum all dirty extent buffers in one bio_vec */ -static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info, - struct bio_vec *bvec) -{ - struct page *page = bvec->bv_page; - u64 bvec_start = page_offset(page) + bvec->bv_offset; - u64 cur; - int ret = 0; - - for (cur = bvec_start; cur < bvec_start + bvec->bv_len; - cur += fs_info->nodesize) { - struct extent_buffer *eb; - bool uptodate; - - eb = find_extent_buffer(fs_info, cur); - uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur, - fs_info->nodesize); - - /* A dirty eb shouldn't disappear from buffer_radix */ - if (WARN_ON(!eb)) - return -EUCLEAN; - - if (WARN_ON(cur != btrfs_header_bytenr(eb))) { - free_extent_buffer(eb); - return -EUCLEAN; - } - if (WARN_ON(!uptodate)) { - free_extent_buffer(eb); - return -EUCLEAN; - } - - ret = csum_one_extent_buffer(eb); - free_extent_buffer(eb); - if (ret < 0) - return ret; - } - return ret; -} - -/* - * Checksum a dirty tree block before IO. This has extra checks to make sure - * we only fill in the checksum field in the first page of a multi-page block. - * For subpage extent buffers we need bvec to also read the offset in the page. - */ -static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec) -{ - struct page *page = bvec->bv_page; - u64 start = page_offset(page); - u64 found_start; - struct extent_buffer *eb; - - if (fs_info->nodesize < PAGE_SIZE) - return csum_dirty_subpage_buffers(fs_info, bvec); - - eb = (struct extent_buffer *)page->private; - if (page != eb->pages[0]) - return 0; - - found_start = btrfs_header_bytenr(eb); - - if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { - WARN_ON(found_start != 0); - return 0; - } - - /* - * Please do not consolidate these warnings into a single if. - * It is useful to know what went wrong. - */ - if (WARN_ON(found_start != start)) - return -EUCLEAN; - if (WARN_ON(!PageUptodate(page))) - return -EUCLEAN; - - return csum_one_extent_buffer(eb); -} - -blk_status_t btree_csum_one_bio(struct btrfs_bio *bbio) -{ - struct btrfs_fs_info *fs_info = bbio->inode->root->fs_info; - struct bvec_iter iter; - struct bio_vec bv; - int ret = 0; - - bio_for_each_segment(bv, &bbio->bio, iter) { - ret = csum_dirty_buffer(fs_info, &bv); - if (ret) - break; - } - return errno_to_blk_status(ret); } -static int check_tree_block_fsid(struct extent_buffer *eb) +static bool check_tree_block_fsid(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs; @@ -474,18 +328,18 @@ static int check_tree_block_fsid(struct extent_buffer *eb) metadata_uuid = fs_devices->fsid; if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) - return 0; + return false; list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE)) - return 0; + return false; - return 1; + return true; } /* Do basic extent buffer checks at read time */ -static int validate_extent_buffer(struct extent_buffer *eb, - struct btrfs_tree_parent_check *check) +int btrfs_validate_extent_buffer(struct extent_buffer *eb, + struct btrfs_tree_parent_check *check) { struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start; @@ -582,7 +436,7 @@ static int validate_extent_buffer(struct extent_buffer *eb, * that we don't try and read the other copies of this block, just * return -EIO. */ - if (found_level == 0 && btrfs_check_leaf_full(eb)) { + if (found_level == 0 && btrfs_check_leaf(eb)) { set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = -EIO; } @@ -590,9 +444,7 @@ static int validate_extent_buffer(struct extent_buffer *eb, if (found_level > 0 && btrfs_check_node(eb)) ret = -EIO; - if (!ret) - set_extent_buffer_uptodate(eb); - else + if (ret) btrfs_err(fs_info, "read time tree block corruption detected on logical %llu mirror %u", eb->start, eb->read_mirror); @@ -600,105 +452,6 @@ out: return ret; } -static int validate_subpage_buffer(struct page *page, u64 start, u64 end, - int mirror, struct btrfs_tree_parent_check *check) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); - struct extent_buffer *eb; - bool reads_done; - int ret = 0; - - ASSERT(check); - - /* - * We don't allow bio merge for subpage metadata read, so we should - * only get one eb for each endio hook. - */ - ASSERT(end == start + fs_info->nodesize - 1); - ASSERT(PagePrivate(page)); - - eb = find_extent_buffer(fs_info, start); - /* - * When we are reading one tree block, eb must have been inserted into - * the radix tree. If not, something is wrong. - */ - ASSERT(eb); - - reads_done = atomic_dec_and_test(&eb->io_pages); - /* Subpage read must finish in page read */ - ASSERT(reads_done); - - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { - ret = -EIO; - goto err; - } - ret = validate_extent_buffer(eb, check); - if (ret < 0) - goto err; - - set_extent_buffer_uptodate(eb); - - free_extent_buffer(eb); - return ret; -err: - /* - * end_bio_extent_readpage decrements io_pages in case of error, - * make sure it has something to decrement. - */ - atomic_inc(&eb->io_pages); - clear_extent_buffer_uptodate(eb); - free_extent_buffer(eb); - return ret; -} - -int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio, - struct page *page, u64 start, u64 end, - int mirror) -{ - struct extent_buffer *eb; - int ret = 0; - int reads_done; - - ASSERT(page->private); - - if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) - return validate_subpage_buffer(page, start, end, mirror, - &bbio->parent_check); - - eb = (struct extent_buffer *)page->private; - - /* - * The pending IO might have been the only thing that kept this buffer - * in memory. Make sure we have a ref for all this other checks - */ - atomic_inc(&eb->refs); - - reads_done = atomic_dec_and_test(&eb->io_pages); - if (!reads_done) - goto err; - - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { - ret = -EIO; - goto err; - } - ret = validate_extent_buffer(eb, &bbio->parent_check); -err: - if (ret) { - /* - * our io error hook is going to dec the io pages - * again, we have to make sure it has something - * to decrement - */ - atomic_inc(&eb->io_pages); - clear_extent_buffer_uptodate(eb); - } - free_extent_buffer(eb); - - return ret; -} - #ifdef CONFIG_MIGRATION static int btree_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) @@ -995,13 +748,18 @@ int btrfs_global_root_insert(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; struct rb_node *tmp; + int ret = 0; write_lock(&fs_info->global_root_lock); tmp = rb_find_add(&root->rb_node, &fs_info->global_root_tree, global_root_cmp); write_unlock(&fs_info->global_root_lock); - ASSERT(!tmp); - return tmp ? -EEXIST : 0; + if (tmp) { + ret = -EEXIST; + btrfs_warn(fs_info, "global root %llu %llu already exists", + root->root_key.objectid, root->root_key.offset); + } + return ret; } void btrfs_global_root_delete(struct btrfs_root *root) @@ -1390,8 +1148,7 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->fs_roots_radix_lock); root = radix_tree_lookup(&fs_info->fs_roots_radix, (unsigned long)root_id); - if (root) - root = btrfs_grab_root(root); + root = btrfs_grab_root(root); spin_unlock(&fs_info->fs_roots_radix_lock); return root; } @@ -1405,31 +1162,28 @@ static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, .offset = 0, }; - if (objectid == BTRFS_ROOT_TREE_OBJECTID) + switch (objectid) { + case BTRFS_ROOT_TREE_OBJECTID: return btrfs_grab_root(fs_info->tree_root); - if (objectid == BTRFS_EXTENT_TREE_OBJECTID) + case BTRFS_EXTENT_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); - if (objectid == BTRFS_CHUNK_TREE_OBJECTID) + case BTRFS_CHUNK_TREE_OBJECTID: return btrfs_grab_root(fs_info->chunk_root); - if (objectid == BTRFS_DEV_TREE_OBJECTID) + case BTRFS_DEV_TREE_OBJECTID: return btrfs_grab_root(fs_info->dev_root); - if (objectid == BTRFS_CSUM_TREE_OBJECTID) + case BTRFS_CSUM_TREE_OBJECTID: + return btrfs_grab_root(btrfs_global_root(fs_info, &key)); + case BTRFS_QUOTA_TREE_OBJECTID: + return btrfs_grab_root(fs_info->quota_root); + case BTRFS_UUID_TREE_OBJECTID: + return btrfs_grab_root(fs_info->uuid_root); + case BTRFS_BLOCK_GROUP_TREE_OBJECTID: + return btrfs_grab_root(fs_info->block_group_root); + case BTRFS_FREE_SPACE_TREE_OBJECTID: return btrfs_grab_root(btrfs_global_root(fs_info, &key)); - if (objectid == BTRFS_QUOTA_TREE_OBJECTID) - return btrfs_grab_root(fs_info->quota_root) ? - fs_info->quota_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_UUID_TREE_OBJECTID) - return btrfs_grab_root(fs_info->uuid_root) ? - fs_info->uuid_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_BLOCK_GROUP_TREE_OBJECTID) - return btrfs_grab_root(fs_info->block_group_root) ? - fs_info->block_group_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) { - struct btrfs_root *root = btrfs_global_root(fs_info, &key); - - return btrfs_grab_root(root) ? root : ERR_PTR(-ENOENT); - } - return NULL; + default: + return NULL; + } } int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, @@ -1985,7 +1739,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) { btrfs_destroy_workqueue(fs_info->fixup_workers); btrfs_destroy_workqueue(fs_info->delalloc_workers); - btrfs_destroy_workqueue(fs_info->hipri_workers); btrfs_destroy_workqueue(fs_info->workers); if (fs_info->endio_workers) destroy_workqueue(fs_info->endio_workers); @@ -2177,12 +1930,10 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) { u32 max_active = fs_info->thread_pool_size; unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE; fs_info->workers = btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16); - fs_info->hipri_workers = - btrfs_alloc_workqueue(fs_info, "worker-high", - flags | WQ_HIGHPRI, max_active, 16); fs_info->delalloc_workers = btrfs_alloc_workqueue(fs_info, "delalloc", @@ -2196,7 +1947,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0); fs_info->fixup_workers = - btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0); + btrfs_alloc_ordered_workqueue(fs_info, "fixup", ordered_flags); fs_info->endio_workers = alloc_workqueue("btrfs-endio", flags, max_active); @@ -2215,11 +1966,12 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info) btrfs_alloc_workqueue(fs_info, "delayed-meta", flags, max_active, 0); fs_info->qgroup_rescan_workers = - btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0); + btrfs_alloc_ordered_workqueue(fs_info, "qgroup-rescan", + ordered_flags); fs_info->discard_ctl.discard_workers = - alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1); + alloc_ordered_workqueue("btrfs_discard", WQ_FREEZABLE); - if (!(fs_info->workers && fs_info->hipri_workers && + if (!(fs_info->workers && fs_info->delalloc_workers && fs_info->flush_workers && fs_info->endio_workers && fs_info->endio_meta_workers && fs_info->compressed_write_workers && @@ -2259,6 +2011,9 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); break; + case BTRFS_CSUM_TYPE_XXHASH: + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; default: break; } @@ -2636,6 +2391,14 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } + if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, + BTRFS_FSID_SIZE) != 0) { + btrfs_err(fs_info, + "dev_item UUID does not match metadata fsid: %pU != %pU", + fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid); + ret = -EINVAL; + } + /* * Artificial requirement for block-group-tree to force newer features * (free-space-tree, no-holes) so the test matrix is smaller. @@ -2648,14 +2411,6 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info, ret = -EINVAL; } - if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid, - BTRFS_FSID_SIZE) != 0) { - btrfs_err(fs_info, - "dev_item UUID does not match metadata fsid: %pU != %pU", - fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid); - ret = -EINVAL; - } - /* * Hint to catch really bogus numbers, bitflips or so, more exact checks are * done later @@ -2841,6 +2596,7 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) /* We can't trust the free space cache either */ btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); + btrfs_warn(fs_info, "try to load backup roots slot %d", i); ret = read_backup_root(fs_info, i); backup_index = ret; if (ret < 0) @@ -4655,28 +4411,10 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_close_devices(fs_info->fs_devices); } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, - int atomic) -{ - int ret; - struct inode *btree_inode = buf->pages[0]->mapping->host; - - ret = extent_buffer_uptodate(buf); - if (!ret) - return ret; - - ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid, atomic); - if (ret == -EAGAIN) - return ret; - return !ret; -} - void btrfs_mark_buffer_dirty(struct extent_buffer *buf) { struct btrfs_fs_info *fs_info = buf->fs_info; u64 transid = btrfs_header_generation(buf); - int was_dirty; #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* @@ -4691,19 +4429,13 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (transid != fs_info->generation) WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n", buf->start, transid, fs_info->generation); - was_dirty = set_extent_buffer_dirty(buf); - if (!was_dirty) - percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, - buf->len, - fs_info->dirty_metadata_batch); + set_extent_buffer_dirty(buf); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY /* - * Since btrfs_mark_buffer_dirty() can be called with item pointer set - * but item data not updated. - * So here we should only check item pointers, not item data. + * btrfs_check_leaf() won't check item data if we don't have WRITTEN + * set, so this will only validate the basic structure of the items. */ - if (btrfs_header_level(buf) == 0 && - btrfs_check_leaf_relaxed(buf)) { + if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(buf)) { btrfs_print_leaf(buf); ASSERT(0); } @@ -4833,13 +4565,12 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } -static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, - struct btrfs_fs_info *fs_info) +static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, + struct btrfs_fs_info *fs_info) { struct rb_node *node; struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; - int ret = 0; delayed_refs = &trans->delayed_refs; @@ -4847,7 +4578,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, if (atomic_read(&delayed_refs->num_entries) == 0) { spin_unlock(&delayed_refs->lock); btrfs_debug(fs_info, "delayed_refs has NO entry"); - return ret; + return; } while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) { @@ -4864,7 +4595,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, while ((n = rb_first_cached(&head->ref_tree)) != NULL) { ref = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); - ref->in_tree = 0; rb_erase_cached(&ref->ref_node, &head->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) @@ -4909,8 +4639,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, btrfs_qgroup_destroy_extent_records(trans); spin_unlock(&delayed_refs->lock); - - return ret; } static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) @@ -5135,8 +4863,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); - btrfs_free_redirty_list(cur_trans); - cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 4d5772330110..b03767f4d7ed 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -31,8 +31,6 @@ struct btrfs_tree_parent_check; void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info); void btrfs_init_fs_info(struct btrfs_fs_info *fs_info); -int btrfs_verify_level_key(struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid); struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, struct btrfs_tree_parent_check *check); struct extent_buffer *btrfs_find_create_tree_block( @@ -84,9 +82,8 @@ void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info); void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info); void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); -int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio, - struct page *page, u64 start, u64 end, - int mirror); +int btrfs_validate_extent_buffer(struct extent_buffer *eb, + struct btrfs_tree_parent_check *check); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info); #endif diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c index 29a225836e28..a2315a4b8b75 100644 --- a/fs/btrfs/extent-io-tree.c +++ b/fs/btrfs/extent-io-tree.c @@ -533,6 +533,16 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree, } /* + * Detect if extent bits request NOWAIT semantics and set the gfp mask accordingly, + * unset the EXTENT_NOWAIT bit. + */ +static void set_gfp_mask_from_bits(u32 *bits, gfp_t *mask) +{ + *mask = (*bits & EXTENT_NOWAIT ? GFP_NOWAIT : GFP_NOFS); + *bits &= EXTENT_NOWAIT - 1; +} + +/* * Clear some bits on a range in the tree. This may require splitting or * inserting elements in the tree, so the gfp mask is used to indicate which * allocations or sleeping are allowed. @@ -546,7 +556,7 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree, */ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_state **cached_state, - gfp_t mask, struct extent_changeset *changeset) + struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *cached; @@ -556,7 +566,9 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int clear = 0; int wake; int delete = (bits & EXTENT_CLEAR_ALL_BITS); + gfp_t mask; + set_gfp_mask_from_bits(&bits, &mask); btrfs_debug_check_extent_io_range(tree, start, end); trace_btrfs_clear_extent_bit(tree, start, end - start + 1, bits); @@ -953,7 +965,8 @@ out: /* * Set some bits on a range in the tree. This may require allocations or - * sleeping, so the gfp mask is used to indicate what is allowed. + * sleeping. By default all allocations use GFP_NOFS, use EXTENT_NOWAIT for + * GFP_NOWAIT. * * If any of the exclusive bits are set, this will fail with -EEXIST if some * part of the range already has the desired bits set. The extent_state of the @@ -968,7 +981,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, u64 *failed_start, struct extent_state **failed_state, struct extent_state **cached_state, - struct extent_changeset *changeset, gfp_t mask) + struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *prealloc = NULL; @@ -978,7 +991,9 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u64 last_start; u64 last_end; u32 exclusive_bits = (bits & EXTENT_LOCKED); + gfp_t mask; + set_gfp_mask_from_bits(&bits, &mask); btrfs_debug_check_extent_io_range(tree, start, end); trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits); @@ -1188,10 +1203,10 @@ out: } int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - u32 bits, struct extent_state **cached_state, gfp_t mask) + u32 bits, struct extent_state **cached_state) { return __set_extent_bit(tree, start, end, bits, NULL, NULL, - cached_state, NULL, mask); + cached_state, NULL); } /* @@ -1687,8 +1702,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, */ ASSERT(!(bits & EXTENT_LOCKED)); - return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL, - changeset, GFP_NOFS); + return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL, changeset); } int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, @@ -1700,8 +1714,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, */ ASSERT(!(bits & EXTENT_LOCKED)); - return __clear_extent_bit(tree, start, end, bits, NULL, GFP_NOFS, - changeset); + return __clear_extent_bit(tree, start, end, bits, NULL, changeset); } int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, @@ -1711,7 +1724,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u64 failed_start; err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, - NULL, cached, NULL, GFP_NOFS); + NULL, cached, NULL); if (err == -EEXIST) { if (failed_start > start) clear_extent_bit(tree, start, failed_start - 1, @@ -1733,7 +1746,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u64 failed_start; err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, - &failed_state, cached_state, NULL, GFP_NOFS); + &failed_state, cached_state, NULL); while (err == -EEXIST) { if (failed_start != start) clear_extent_bit(tree, start, failed_start - 1, @@ -1743,7 +1756,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, &failed_state); err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, &failed_state, - cached_state, NULL, GFP_NOFS); + cached_state, NULL); } return err; } diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index 21766e49ec02..fbd3b275ab1c 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -43,6 +43,15 @@ enum { * want the extent states to go away. */ ENUM_BIT(EXTENT_CLEAR_ALL_BITS), + + /* + * This must be last. + * + * Bit not representing a state but a request for NOWAIT semantics, + * e.g. when allocating memory, and must be masked out from the other + * bits. + */ + ENUM_BIT(EXTENT_NOWAIT) }; #define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \ @@ -127,22 +136,20 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_changeset *changeset); int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - u32 bits, struct extent_state **cached, gfp_t mask, + u32 bits, struct extent_state **cached, struct extent_changeset *changeset); static inline int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_state **cached) { - return __clear_extent_bit(tree, start, end, bits, cached, - GFP_NOFS, NULL); + return __clear_extent_bit(tree, start, end, bits, cached, NULL); } static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached) { - return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached, - GFP_NOFS, NULL); + return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, cached, NULL); } static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, @@ -154,31 +161,13 @@ static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_changeset *changeset); int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - u32 bits, struct extent_state **cached_state, gfp_t mask); - -static inline int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, - u64 end, u32 bits) -{ - return set_extent_bit(tree, start, end, bits, NULL, GFP_NOWAIT); -} - -static inline int set_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, u32 bits) -{ - return set_extent_bit(tree, start, end, bits, NULL, GFP_NOFS); -} + u32 bits, struct extent_state **cached_state); static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state) { return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, - cached_state, GFP_NOFS, NULL); -} - -static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start, - u64 end, gfp_t mask) -{ - return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, mask); + cached_state, NULL); } static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start, @@ -193,29 +182,6 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, u32 clear_bits, struct extent_state **cached_state); -static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, - u64 end, u32 extra_bits, - struct extent_state **cached_state) -{ - return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | extra_bits, - cached_state, GFP_NOFS); -} - -static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state) -{ - return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_DEFRAG, - cached_state, GFP_NOFS); -} - -static inline int set_extent_new(struct extent_io_tree *tree, u64 start, - u64 end) -{ - return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, GFP_NOFS); -} - int find_first_extent_bit(struct extent_io_tree *tree, u64 start, u64 *start_ret, u64 *end_ret, u32 bits, struct extent_state **cached_state); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5cd289de4e92..911908ea5f6f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -73,8 +73,8 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info, u64 start, u64 num_bytes) { u64 end = start + num_bytes - 1; - set_extent_bits(&fs_info->excluded_extents, start, end, - EXTENT_UPTODATE); + set_extent_bit(&fs_info->excluded_extents, start, end, + EXTENT_UPTODATE, NULL); return 0; } @@ -402,7 +402,7 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, } } - btrfs_print_leaf((struct extent_buffer *)eb); + btrfs_print_leaf(eb); btrfs_err(eb->fs_info, "eb %llu iref 0x%lx invalid extent inline ref type %d", eb->start, (unsigned long)iref, type); @@ -1164,15 +1164,10 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans, * should not happen at all. */ if (owner < BTRFS_FIRST_FREE_OBJECTID) { + btrfs_print_leaf(path->nodes[0]); btrfs_crit(trans->fs_info, -"adding refs to an existing tree ref, bytenr %llu num_bytes %llu root_objectid %llu", - bytenr, num_bytes, root_objectid); - if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) { - WARN_ON(1); - btrfs_crit(trans->fs_info, - "path->slots[0]=%d path->nodes[0]:", path->slots[0]); - btrfs_print_leaf(path->nodes[0]); - } +"adding refs to an existing tree ref, bytenr %llu num_bytes %llu root_objectid %llu slot %u", + bytenr, num_bytes, root_objectid, path->slots[0]); return -EUCLEAN; } update_inline_extent_backref(path, iref, refs_to_add, extent_op); @@ -1208,11 +1203,11 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, { int j, ret = 0; u64 bytes_left, end; - u64 aligned_start = ALIGN(start, 1 << 9); + u64 aligned_start = ALIGN(start, 1 << SECTOR_SHIFT); if (WARN_ON(start != aligned_start)) { len -= aligned_start - start; - len = round_down(len, 1 << 9); + len = round_down(len, 1 << SECTOR_SHIFT); start = aligned_start; } @@ -1250,7 +1245,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, } if (size) { - ret = blkdev_issue_discard(bdev, start >> 9, size >> 9, + ret = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, + size >> SECTOR_SHIFT, GFP_NOFS); if (!ret) *discarded_bytes += size; @@ -1267,7 +1263,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, } if (bytes_left) { - ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9, + ret = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, + bytes_left >> SECTOR_SHIFT, GFP_NOFS); if (!ret) *discarded_bytes += bytes_left; @@ -1500,7 +1497,7 @@ out: static int run_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, - int insert_reserved) + bool insert_reserved) { int ret = 0; struct btrfs_delayed_data_ref *ref; @@ -1650,7 +1647,7 @@ out: static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, - int insert_reserved) + bool insert_reserved) { int ret = 0; struct btrfs_delayed_tree_ref *ref; @@ -1690,7 +1687,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, static int run_one_delayed_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *node, struct btrfs_delayed_extent_op *extent_op, - int insert_reserved) + bool insert_reserved) { int ret = 0; @@ -1748,7 +1745,7 @@ static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_ref struct btrfs_delayed_ref_head *head) { spin_lock(&delayed_refs->lock); - head->processing = 0; + head->processing = false; delayed_refs->num_heads_ready++; spin_unlock(&delayed_refs->lock); btrfs_delayed_ref_unlock(head); @@ -1900,7 +1897,7 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_extent_op *extent_op; struct btrfs_delayed_ref_node *ref; - int must_insert_reserved = 0; + bool must_insert_reserved; int ret; delayed_refs = &trans->transaction->delayed_refs; @@ -1916,7 +1913,6 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, return -EAGAIN; } - ref->in_tree = 0; rb_erase_cached(&ref->ref_node, &locked_ref->ref_tree); RB_CLEAR_NODE(&ref->ref_node); if (!list_empty(&ref->add_list)) @@ -1943,7 +1939,7 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans, * spin lock. */ must_insert_reserved = locked_ref->must_insert_reserved; - locked_ref->must_insert_reserved = 0; + locked_ref->must_insert_reserved = false; extent_op = locked_ref->extent_op; locked_ref->extent_op = NULL; @@ -2155,10 +2151,10 @@ out: } int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, - struct extent_buffer *eb, u64 flags, - int level) + struct extent_buffer *eb, u64 flags) { struct btrfs_delayed_extent_op *extent_op; + int level = btrfs_header_level(eb); int ret; extent_op = btrfs_alloc_delayed_extent_op(); @@ -2510,8 +2506,8 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - set_extent_dirty(&trans->transaction->pinned_extents, bytenr, - bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); + set_extent_bit(&trans->transaction->pinned_extents, bytenr, + bytenr + num_bytes - 1, EXTENT_DIRTY, NULL); return 0; } @@ -2838,6 +2834,13 @@ static int do_free_extent_accounting(struct btrfs_trans_handle *trans, return ret; } +#define abort_and_dump(trans, path, fmt, args...) \ +({ \ + btrfs_abort_transaction(trans, -EUCLEAN); \ + btrfs_print_leaf(path->nodes[0]); \ + btrfs_crit(trans->fs_info, fmt, ##args); \ +}) + /* * Drop one or more refs of @node. * @@ -2978,10 +2981,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (!found_extent) { if (iref) { - btrfs_crit(info, -"invalid iref, no EXTENT/METADATA_ITEM found but has inline extent ref"); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, +"invalid iref slot %u, no EXTENT/METADATA_ITEM found but has inline extent ref", + path->slots[0]); + ret = -EUCLEAN; + goto out; } /* Must be SHARED_* item, remove the backref first */ ret = remove_extent_backref(trans, extent_root, path, @@ -3029,11 +3033,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } if (ret) { - btrfs_err(info, - "umm, got %d back from search, was looking for %llu", - ret, bytenr); if (ret > 0) btrfs_print_leaf(path->nodes[0]); + btrfs_err(info, + "umm, got %d back from search, was looking for %llu, slot %d", + ret, bytenr, path->slots[0]); } if (ret < 0) { btrfs_abort_transaction(trans, ret); @@ -3042,12 +3046,10 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, extent_slot = path->slots[0]; } } else if (WARN_ON(ret == -ENOENT)) { - btrfs_print_leaf(path->nodes[0]); - btrfs_err(info, - "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu", - bytenr, parent, root_objectid, owner_objectid, - owner_offset); - btrfs_abort_transaction(trans, ret); + abort_and_dump(trans, path, +"unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu slot %d", + bytenr, parent, root_objectid, owner_objectid, + owner_offset, path->slots[0]); goto out; } else { btrfs_abort_transaction(trans, ret); @@ -3067,14 +3069,15 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID && key.type == BTRFS_EXTENT_ITEM_KEY) { struct btrfs_tree_block_info *bi; + if (item_size < sizeof(*ei) + sizeof(*bi)) { - btrfs_crit(info, -"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %zu", - key.objectid, key.type, key.offset, - owner_objectid, item_size, - sizeof(*ei) + sizeof(*bi)); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, +"invalid extent item size for key (%llu, %u, %llu) slot %u owner %llu, has %u expect >= %zu", + key.objectid, key.type, key.offset, + path->slots[0], owner_objectid, item_size, + sizeof(*ei) + sizeof(*bi)); + ret = -EUCLEAN; + goto out; } bi = (struct btrfs_tree_block_info *)(ei + 1); WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi)); @@ -3082,11 +3085,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, refs = btrfs_extent_refs(leaf, ei); if (refs < refs_to_drop) { - btrfs_crit(info, - "trying to drop %d refs but we only have %llu for bytenr %llu", - refs_to_drop, refs, bytenr); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, + "trying to drop %d refs but we only have %llu for bytenr %llu slot %u", + refs_to_drop, refs, bytenr, path->slots[0]); + ret = -EUCLEAN; + goto out; } refs -= refs_to_drop; @@ -3099,10 +3102,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, */ if (iref) { if (!found_extent) { - btrfs_crit(info, -"invalid iref, got inlined extent ref but no EXTENT/METADATA_ITEM found"); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, +"invalid iref, got inlined extent ref but no EXTENT/METADATA_ITEM found, slot %u", + path->slots[0]); + ret = -EUCLEAN; + goto out; } } else { btrfs_set_extent_refs(leaf, ei, refs); @@ -3121,21 +3125,21 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (found_extent) { if (is_data && refs_to_drop != extent_data_ref_count(path, iref)) { - btrfs_crit(info, - "invalid refs_to_drop, current refs %u refs_to_drop %u", - extent_data_ref_count(path, iref), - refs_to_drop); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, + "invalid refs_to_drop, current refs %u refs_to_drop %u slot %u", + extent_data_ref_count(path, iref), + refs_to_drop, path->slots[0]); + ret = -EUCLEAN; + goto out; } if (iref) { if (path->slots[0] != extent_slot) { - btrfs_crit(info, -"invalid iref, extent item key (%llu %u %llu) doesn't have wanted iref", - key.objectid, key.type, - key.offset); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, +"invalid iref, extent item key (%llu %u %llu) slot %u doesn't have wanted iref", + key.objectid, key.type, + key.offset, path->slots[0]); + ret = -EUCLEAN; + goto out; } } else { /* @@ -3145,10 +3149,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, * [ EXTENT/METADATA_ITEM ][ SHARED_* ITEM ] */ if (path->slots[0] != extent_slot + 1) { - btrfs_crit(info, - "invalid SHARED_* item, previous item is not EXTENT/METADATA_ITEM"); - btrfs_abort_transaction(trans, -EUCLEAN); - goto err_dump; + abort_and_dump(trans, path, + "invalid SHARED_* item slot %u, previous item is not EXTENT/METADATA_ITEM", + path->slots[0]); + ret = -EUCLEAN; + goto out; } path->slots[0] = extent_slot; num_to_del = 2; @@ -3170,19 +3175,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, out: btrfs_free_path(path); return ret; -err_dump: - /* - * Leaf dump can take up a lot of log buffer, so we only do full leaf - * dump for debug build. - */ - if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) { - btrfs_crit(info, "path->slots[0]=%d extent_slot=%d", - path->slots[0], extent_slot); - btrfs_print_leaf(path->nodes[0]); - } - - btrfs_free_path(path); - return -EUCLEAN; } /* @@ -3219,7 +3211,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, goto out; btrfs_delete_ref_head(delayed_refs, head); - head->processing = 0; + head->processing = false; spin_unlock(&head->lock); spin_unlock(&delayed_refs->lock); @@ -4804,7 +4796,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) lockdep_owner = BTRFS_FS_TREE_OBJECTID; - /* btrfs_clean_tree_block() accesses generation field. */ + /* btrfs_clear_buffer_dirty() accesses generation field. */ btrfs_set_header_generation(buf, trans->transid); /* @@ -4836,15 +4828,17 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, * EXTENT bit to differentiate dirty pages. */ if (buf->log_index == 0) - set_extent_dirty(&root->dirty_log_pages, buf->start, - buf->start + buf->len - 1, GFP_NOFS); + set_extent_bit(&root->dirty_log_pages, buf->start, + buf->start + buf->len - 1, + EXTENT_DIRTY, NULL); else - set_extent_new(&root->dirty_log_pages, buf->start, - buf->start + buf->len - 1); + set_extent_bit(&root->dirty_log_pages, buf->start, + buf->start + buf->len - 1, + EXTENT_NEW, NULL); } else { buf->log_index = -1; - set_extent_dirty(&trans->transaction->dirty_pages, buf->start, - buf->start + buf->len - 1, GFP_NOFS); + set_extent_bit(&trans->transaction->dirty_pages, buf->start, + buf->start + buf->len - 1, EXTENT_DIRTY, NULL); } /* this returns a buffer locked for blocking */ return buf; @@ -5102,8 +5096,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, BUG_ON(ret); /* -ENOMEM */ ret = btrfs_dec_ref(trans, root, eb, 0); BUG_ON(ret); /* -ENOMEM */ - ret = btrfs_set_disk_extent_flags(trans, eb, flag, - btrfs_header_level(eb)); + ret = btrfs_set_disk_extent_flags(trans, eb, flag); BUG_ON(ret); /* -ENOMEM */ wc->flags[level] |= flag; } @@ -5985,9 +5978,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) ret = btrfs_issue_discard(device->bdev, start, len, &bytes); if (!ret) - set_extent_bits(&device->alloc_state, start, - start + bytes - 1, - CHUNK_TRIMMED); + set_extent_bit(&device->alloc_state, start, + start + bytes - 1, CHUNK_TRIMMED, NULL); mutex_unlock(&fs_info->chunk_mutex); if (ret) diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h index 0c958fc1b3b8..429d5c570061 100644 --- a/fs/btrfs/extent-tree.h +++ b/fs/btrfs/extent-tree.h @@ -141,7 +141,7 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, int full_backref); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, - struct extent_buffer *eb, u64 flags, int level); + struct extent_buffer *eb, u64 flags); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref); int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a1adadd5d25d..a91d5ad27984 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -98,33 +98,16 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info) */ struct btrfs_bio_ctrl { struct btrfs_bio *bbio; - int mirror_num; enum btrfs_compression_type compress_type; u32 len_to_oe_boundary; blk_opf_t opf; btrfs_bio_end_io_t end_io_func; struct writeback_control *wbc; - - /* - * This is for metadata read, to provide the extra needed verification - * info. This has to be provided for submit_one_bio(), as - * submit_one_bio() can submit a bio if it ends at stripe boundary. If - * no such parent_check is provided, the metadata can hit false alert at - * endio time. - */ - struct btrfs_tree_parent_check *parent_check; - - /* - * Tell writepage not to lock the state bits for this range, it still - * does the unlocking. - */ - bool extent_locked; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_bio *bbio = bio_ctrl->bbio; - int mirror_num = bio_ctrl->mirror_num; if (!bbio) return; @@ -132,25 +115,11 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) /* Caller should ensure the bio has at least some range added */ ASSERT(bbio->bio.bi_iter.bi_size); - if (!is_data_inode(&bbio->inode->vfs_inode)) { - if (btrfs_op(&bbio->bio) != BTRFS_MAP_WRITE) { - /* - * For metadata read, we should have the parent_check, - * and copy it to bbio for metadata verification. - */ - ASSERT(bio_ctrl->parent_check); - memcpy(&bbio->parent_check, - bio_ctrl->parent_check, - sizeof(struct btrfs_tree_parent_check)); - } - bbio->bio.bi_opf |= REQ_META; - } - if (btrfs_op(&bbio->bio) == BTRFS_MAP_READ && bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) - btrfs_submit_compressed_read(bbio, mirror_num); + btrfs_submit_compressed_read(bbio); else - btrfs_submit_bio(bbio, mirror_num); + btrfs_submit_bio(bbio, 0); /* The bbio is owned by the end_io handler now */ bio_ctrl->bbio = NULL; @@ -248,8 +217,6 @@ static int process_one_page(struct btrfs_fs_info *fs_info, if (page_ops & PAGE_SET_ORDERED) btrfs_page_clamp_set_ordered(fs_info, page, start, len); - if (page_ops & PAGE_SET_ERROR) - btrfs_page_clamp_set_error(fs_info, page, start, len); if (page_ops & PAGE_START_WRITEBACK) { btrfs_page_clamp_clear_dirty(fs_info, page, start, len); btrfs_page_clamp_set_writeback(fs_info, page, start, len); @@ -295,9 +262,6 @@ static int __process_pages_contig(struct address_space *mapping, ASSERT(processed_end && *processed_end == start); } - if ((page_ops & PAGE_SET_ERROR) && start_index <= end_index) - mapping_set_error(mapping, -EIO); - folio_batch_init(&fbatch); while (index <= end_index) { int found_folios; @@ -506,6 +470,15 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, start, end, page_ops, NULL); } +static bool btrfs_verify_page(struct page *page, u64 start) +{ + if (!fsverity_active(page->mapping->host) || + PageUptodate(page) || + start >= i_size_read(page->mapping->host)) + return true; + return fsverity_verify_page(page); +} + static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) { struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); @@ -513,20 +486,10 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) ASSERT(page_offset(page) <= start && start + len <= page_offset(page) + PAGE_SIZE); - if (uptodate) { - if (fsverity_active(page->mapping->host) && - !PageError(page) && - !PageUptodate(page) && - start < i_size_read(page->mapping->host) && - !fsverity_verify_page(page)) { - btrfs_page_set_error(fs_info, page, start, len); - } else { - btrfs_page_set_uptodate(fs_info, page, start, len); - } - } else { + if (uptodate && btrfs_verify_page(page, start)) + btrfs_page_set_uptodate(fs_info, page, start, len); + else btrfs_page_clear_uptodate(fs_info, page, start, len); - btrfs_page_set_error(fs_info, page, start, len); - } if (!btrfs_is_subpage(fs_info, page)) unlock_page(page); @@ -554,7 +517,6 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) len = end + 1 - start; btrfs_page_clear_uptodate(fs_info, page, start, len); - btrfs_page_set_error(fs_info, page, start, len); ret = err < 0 ? err : -EIO; mapping_set_error(page->mapping, ret); } @@ -574,8 +536,6 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio) struct bio *bio = &bbio->bio; int error = blk_status_to_errno(bio->bi_status); struct bio_vec *bvec; - u64 start; - u64 end; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); @@ -584,6 +544,8 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio) struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const u32 sectorsize = fs_info->sectorsize; + u64 start = page_offset(page) + bvec->bv_offset; + u32 len = bvec->bv_len; /* Our read/write should always be sector aligned. */ if (!IS_ALIGNED(bvec->bv_offset, sectorsize)) @@ -595,12 +557,12 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio) "incomplete page write with offset %u and length %u", bvec->bv_offset, bvec->bv_len); - start = page_offset(page) + bvec->bv_offset; - end = start + bvec->bv_len - 1; - - end_extent_writepage(page, error, start, end); - - btrfs_page_clear_writeback(fs_info, page, start, bvec->bv_len); + btrfs_finish_ordered_extent(bbio->ordered, page, start, len, !error); + if (error) { + btrfs_page_clear_uptodate(fs_info, page, start, len); + mapping_set_error(page->mapping, error); + } + btrfs_page_clear_writeback(fs_info, page, start, len); } bio_put(bio); @@ -686,35 +648,6 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) } /* - * Find extent buffer for a givne bytenr. - * - * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking - * in endio context. - */ -static struct extent_buffer *find_extent_buffer_readpage( - struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) -{ - struct extent_buffer *eb; - - /* - * For regular sectorsize, we can use page->private to grab extent - * buffer - */ - if (fs_info->nodesize >= PAGE_SIZE) { - ASSERT(PagePrivate(page) && page->private); - return (struct extent_buffer *)page->private; - } - - /* For subpage case, we need to lookup buffer radix tree */ - rcu_read_lock(); - eb = radix_tree_lookup(&fs_info->buffer_radix, - bytenr >> fs_info->sectorsize_bits); - rcu_read_unlock(); - ASSERT(eb); - return eb; -} - -/* * after a readpage IO is done, we need to: * clear the uptodate bits on error * set the uptodate bits if things worked @@ -735,7 +668,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio) * larger than UINT_MAX, u32 here is enough. */ u32 bio_offset = 0; - int mirror; struct bvec_iter_all iter_all; ASSERT(!bio_flagged(bio, BIO_CLONED)); @@ -775,11 +707,6 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio) end = start + bvec->bv_len - 1; len = bvec->bv_len; - mirror = bbio->mirror_num; - if (uptodate && !is_data_inode(inode) && - btrfs_validate_metadata_buffer(bbio, page, start, end, mirror)) - uptodate = false; - if (likely(uptodate)) { loff_t i_size = i_size_read(inode); pgoff_t end_index = i_size >> PAGE_SHIFT; @@ -800,19 +727,12 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio) zero_user_segment(page, zero_start, offset_in_page(end) + 1); } - } else if (!is_data_inode(inode)) { - struct extent_buffer *eb; - - eb = find_extent_buffer_readpage(fs_info, page, start); - set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); - eb->read_mirror = mirror; - atomic_dec(&eb->io_pages); } /* Update page status and unlock. */ end_page_read(page, uptodate, start, len); endio_readpage_release_extent(&processed, BTRFS_I(inode), - start, end, PageUptodate(page)); + start, end, uptodate); ASSERT(bio_offset + len > bio_offset); bio_offset += len; @@ -906,13 +826,8 @@ static void alloc_new_bio(struct btrfs_inode *inode, bio_ctrl->bbio = bbio; bio_ctrl->len_to_oe_boundary = U32_MAX; - /* - * Limit the extent to the ordered boundary for Zone Append. - * Compressed bios aren't submitted directly, so it doesn't apply to - * them. - */ - if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE && - btrfs_use_zone_append(bbio)) { + /* Limit data write bios to the ordered boundary. */ + if (bio_ctrl->wbc) { struct btrfs_ordered_extent *ordered; ordered = btrfs_lookup_ordered_extent(inode, file_offset); @@ -920,11 +835,9 @@ static void alloc_new_bio(struct btrfs_inode *inode, bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX, ordered->file_offset + ordered->disk_num_bytes - file_offset); - btrfs_put_ordered_extent(ordered); + bbio->ordered = ordered; } - } - if (bio_ctrl->wbc) { /* * Pick the last added device to support cgroup writeback. For * multi-device file systems this means blk-cgroup policies have @@ -1125,7 +1038,6 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, ret = set_page_extent_mapped(page); if (ret < 0) { unlock_extent(tree, start, end, NULL); - btrfs_page_set_error(fs_info, page, start, PAGE_SIZE); unlock_page(page); return ret; } @@ -1329,11 +1241,9 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, } ret = btrfs_run_delalloc_range(inode, page, delalloc_start, delalloc_end, &page_started, &nr_written, wbc); - if (ret) { - btrfs_page_set_error(inode->root->fs_info, page, - page_offset(page), PAGE_SIZE); + if (ret) return ret; - } + /* * delalloc_end is already one less than the total length, so * we don't subtract one from PAGE_SIZE @@ -1438,7 +1348,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, struct extent_map *em; int ret = 0; int nr = 0; - bool compressed; ret = btrfs_writepage_cow_fixup(page); if (ret) { @@ -1448,12 +1357,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, return 1; } - /* - * we don't want to touch the inode after unlocking the page, - * so we update the mapping writeback index now - */ - bio_ctrl->wbc->nr_to_write--; - bio_ctrl->end_io_func = end_bio_extent_writepage; while (cur <= end) { u64 disk_bytenr; @@ -1486,7 +1389,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); if (IS_ERR(em)) { - btrfs_page_set_error(fs_info, page, cur, end - cur + 1); ret = PTR_ERR_OR_ZERO(em); goto out_error; } @@ -1497,10 +1399,14 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, ASSERT(cur < end); ASSERT(IS_ALIGNED(em->start, fs_info->sectorsize)); ASSERT(IS_ALIGNED(em->len, fs_info->sectorsize)); + block_start = em->block_start; - compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); disk_bytenr = em->block_start + extent_offset; + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + ASSERT(block_start != EXTENT_MAP_HOLE); + ASSERT(block_start != EXTENT_MAP_INLINE); + /* * Note that em_end from extent_map_end() and dirty_range_end from * find_next_dirty_byte() are all exclusive @@ -1509,22 +1415,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, free_extent_map(em); em = NULL; - /* - * compressed and inline extents are written through other - * paths in the FS - */ - if (compressed || block_start == EXTENT_MAP_HOLE || - block_start == EXTENT_MAP_INLINE) { - if (compressed) - nr++; - else - btrfs_writepage_endio_finish_ordered(inode, - page, cur, cur + iosize - 1, true); - btrfs_page_clear_dirty(fs_info, page, cur, iosize); - cur += iosize; - continue; - } - btrfs_set_range_writeback(inode, cur, cur + iosize - 1); if (!PageWriteback(page)) { btrfs_err(inode->root->fs_info, @@ -1572,7 +1462,6 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl { struct folio *folio = page_folio(page); struct inode *inode = page->mapping->host; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const u64 page_start = page_offset(page); const u64 page_end = page_start + PAGE_SIZE - 1; int ret; @@ -1585,9 +1474,6 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl WARN_ON(!PageLocked(page)); - btrfs_page_clear_error(btrfs_sb(inode->i_sb), page, - page_offset(page), PAGE_SIZE); - pg_offset = offset_in_page(i_size); if (page->index > end_index || (page->index == end_index && !pg_offset)) { @@ -1600,77 +1486,30 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl memzero_page(page, pg_offset, PAGE_SIZE - pg_offset); ret = set_page_extent_mapped(page); - if (ret < 0) { - SetPageError(page); + if (ret < 0) goto done; - } - if (!bio_ctrl->extent_locked) { - ret = writepage_delalloc(BTRFS_I(inode), page, bio_ctrl->wbc); - if (ret == 1) - return 0; - if (ret) - goto done; - } + ret = writepage_delalloc(BTRFS_I(inode), page, bio_ctrl->wbc); + if (ret == 1) + return 0; + if (ret) + goto done; ret = __extent_writepage_io(BTRFS_I(inode), page, bio_ctrl, i_size, &nr); if (ret == 1) return 0; + bio_ctrl->wbc->nr_to_write--; + done: if (nr == 0) { /* make sure the mapping tag for page dirty gets cleared */ set_page_writeback(page); end_page_writeback(page); } - /* - * Here we used to have a check for PageError() and then set @ret and - * call end_extent_writepage(). - * - * But in fact setting @ret here will cause different error paths - * between subpage and regular sectorsize. - * - * For regular page size, we never submit current page, but only add - * current page to current bio. - * The bio submission can only happen in next page. - * Thus if we hit the PageError() branch, @ret is already set to - * non-zero value and will not get updated for regular sectorsize. - * - * But for subpage case, it's possible we submit part of current page, - * thus can get PageError() set by submitted bio of the same page, - * while our @ret is still 0. - * - * So here we unify the behavior and don't set @ret. - * Error can still be properly passed to higher layer as page will - * be set error, here we just don't handle the IO failure. - * - * NOTE: This is just a hotfix for subpage. - * The root fix will be properly ending ordered extent when we hit - * an error during writeback. - * - * But that needs a bigger refactoring, as we not only need to grab the - * submitted OE, but also need to know exactly at which bytenr we hit - * the error. - * Currently the full page based __extent_writepage_io() is not - * capable of that. - */ - if (PageError(page)) + if (ret) end_extent_writepage(page, ret, page_start, page_end); - if (bio_ctrl->extent_locked) { - struct writeback_control *wbc = bio_ctrl->wbc; - - /* - * If bio_ctrl->extent_locked, it's from extent_write_locked_range(), - * the page can either be locked by lock_page() or - * process_one_page(). - * Let btrfs_page_unlock_writer() handle both cases. - */ - ASSERT(wbc); - btrfs_page_unlock_writer(fs_info, page, wbc->range_start, - wbc->range_end + 1 - wbc->range_start); - } else { - unlock_page(page); - } + unlock_page(page); ASSERT(ret <= 0); return ret; } @@ -1681,52 +1520,26 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb) TASK_UNINTERRUPTIBLE); } -static void end_extent_buffer_writeback(struct extent_buffer *eb) -{ - clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); - smp_mb__after_atomic(); - wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); -} - /* * Lock extent buffer status and pages for writeback. * - * May try to flush write bio if we can't get the lock. - * - * Return 0 if the extent buffer doesn't need to be submitted. - * (E.g. the extent buffer is not dirty) - * Return >0 is the extent buffer is submitted to bio. - * Return <0 if something went wrong, no page is locked. + * Return %false if the extent buffer doesn't need to be submitted (e.g. the + * extent buffer is not dirty) + * Return %true is the extent buffer is submitted to bio. */ -static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb, - struct btrfs_bio_ctrl *bio_ctrl) +static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eb, + struct writeback_control *wbc) { struct btrfs_fs_info *fs_info = eb->fs_info; - int i, num_pages; - int flush = 0; - int ret = 0; + bool ret = false; - if (!btrfs_try_tree_write_lock(eb)) { - submit_write_bio(bio_ctrl, 0); - flush = 1; - btrfs_tree_lock(eb); - } - - if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) { + btrfs_tree_lock(eb); + while (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) { btrfs_tree_unlock(eb); - if (bio_ctrl->wbc->sync_mode != WB_SYNC_ALL) - return 0; - if (!flush) { - submit_write_bio(bio_ctrl, 0); - flush = 1; - } - while (1) { - wait_on_extent_buffer_writeback(eb); - btrfs_tree_lock(eb); - if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) - break; - btrfs_tree_unlock(eb); - } + if (wbc->sync_mode != WB_SYNC_ALL) + return false; + wait_on_extent_buffer_writeback(eb); + btrfs_tree_lock(eb); } /* @@ -1742,45 +1555,19 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len, fs_info->dirty_metadata_batch); - ret = 1; + ret = true; } else { spin_unlock(&eb->refs_lock); } - btrfs_tree_unlock(eb); - - /* - * Either we don't need to submit any tree block, or we're submitting - * subpage eb. - * Subpage metadata doesn't use page locking at all, so we can skip - * the page locking. - */ - if (!ret || fs_info->nodesize < PAGE_SIZE) - return ret; - - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - struct page *p = eb->pages[i]; - - if (!trylock_page(p)) { - if (!flush) { - submit_write_bio(bio_ctrl, 0); - flush = 1; - } - lock_page(p); - } - } - return ret; } -static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) +static void set_btree_ioerr(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; - btrfs_page_set_error(fs_info, page, eb->start, eb->len); - if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) - return; + set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); /* * A read may stumble upon this buffer later, make sure that it gets an @@ -1794,7 +1581,7 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) * return a 0 because we are readonly if we don't modify the err seq for * the superblock. */ - mapping_set_error(page->mapping, -EIO); + mapping_set_error(eb->fs_info->btree_inode->i_mapping, -EIO); /* * If writeback for a btree extent that doesn't belong to a log tree @@ -1869,101 +1656,34 @@ static struct extent_buffer *find_extent_buffer_nolock( return NULL; } -/* - * The endio function for subpage extent buffer write. - * - * Unlike end_bio_extent_buffer_writepage(), we only call end_page_writeback() - * after all extent buffers in the page has finished their writeback. - */ -static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio) +static void extent_buffer_write_end_io(struct btrfs_bio *bbio) { - struct bio *bio = &bbio->bio; - struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct extent_buffer *eb = bbio->private; + struct btrfs_fs_info *fs_info = eb->fs_info; + bool uptodate = !bbio->bio.bi_status; struct bvec_iter_all iter_all; + struct bio_vec *bvec; + u32 bio_offset = 0; - fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb); - ASSERT(fs_info->nodesize < PAGE_SIZE); + if (!uptodate) + set_btree_ioerr(eb); - ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, iter_all) { + bio_for_each_segment_all(bvec, &bbio->bio, iter_all) { + u64 start = eb->start + bio_offset; struct page *page = bvec->bv_page; - u64 bvec_start = page_offset(page) + bvec->bv_offset; - u64 bvec_end = bvec_start + bvec->bv_len - 1; - u64 cur_bytenr = bvec_start; - - ASSERT(IS_ALIGNED(bvec->bv_len, fs_info->nodesize)); - - /* Iterate through all extent buffers in the range */ - while (cur_bytenr <= bvec_end) { - struct extent_buffer *eb; - int done; - - /* - * Here we can't use find_extent_buffer(), as it may - * try to lock eb->refs_lock, which is not safe in endio - * context. - */ - eb = find_extent_buffer_nolock(fs_info, cur_bytenr); - ASSERT(eb); - - cur_bytenr = eb->start + eb->len; - - ASSERT(test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)); - done = atomic_dec_and_test(&eb->io_pages); - ASSERT(done); - - if (bio->bi_status || - test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { - ClearPageUptodate(page); - set_btree_ioerr(page, eb); - } + u32 len = bvec->bv_len; - btrfs_subpage_clear_writeback(fs_info, page, eb->start, - eb->len); - end_extent_buffer_writeback(eb); - /* - * free_extent_buffer() will grab spinlock which is not - * safe in endio context. Thus here we manually dec - * the ref. - */ - atomic_dec(&eb->refs); - } + if (!uptodate) + btrfs_page_clear_uptodate(fs_info, page, start, len); + btrfs_page_clear_writeback(fs_info, page, start, len); + bio_offset += len; } - bio_put(bio); -} -static void end_bio_extent_buffer_writepage(struct btrfs_bio *bbio) -{ - struct bio *bio = &bbio->bio; - struct bio_vec *bvec; - struct extent_buffer *eb; - int done; - struct bvec_iter_all iter_all; - - ASSERT(!bio_flagged(bio, BIO_CLONED)); - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; - - eb = (struct extent_buffer *)page->private; - BUG_ON(!eb); - done = atomic_dec_and_test(&eb->io_pages); - - if (bio->bi_status || - test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { - ClearPageUptodate(page); - set_btree_ioerr(page, eb); - } - - end_page_writeback(page); - - if (!done) - continue; - - end_extent_buffer_writeback(eb); - } + clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); + smp_mb__after_atomic(); + wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK); - bio_put(bio); + bio_put(&bbio->bio); } static void prepare_eb_write(struct extent_buffer *eb) @@ -1973,7 +1693,6 @@ static void prepare_eb_write(struct extent_buffer *eb) unsigned long end; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); - atomic_set(&eb->io_pages, num_extent_pages(eb)); /* Set btree blocks beyond nritems with 0 to avoid stale content */ nritems = btrfs_header_nritems(eb); @@ -1995,63 +1714,49 @@ static void prepare_eb_write(struct extent_buffer *eb) } } -/* - * Unlike the work in write_one_eb(), we rely completely on extent locking. - * Page locking is only utilized at minimum to keep the VMM code happy. - */ -static void write_one_subpage_eb(struct extent_buffer *eb, - struct btrfs_bio_ctrl *bio_ctrl) -{ - struct btrfs_fs_info *fs_info = eb->fs_info; - struct page *page = eb->pages[0]; - bool no_dirty_ebs = false; - - prepare_eb_write(eb); - - /* clear_page_dirty_for_io() in subpage helper needs page locked */ - lock_page(page); - btrfs_subpage_set_writeback(fs_info, page, eb->start, eb->len); - - /* Check if this is the last dirty bit to update nr_written */ - no_dirty_ebs = btrfs_subpage_clear_and_test_dirty(fs_info, page, - eb->start, eb->len); - if (no_dirty_ebs) - clear_page_dirty_for_io(page); - - bio_ctrl->end_io_func = end_bio_subpage_eb_writepage; - - submit_extent_page(bio_ctrl, eb->start, page, eb->len, - eb->start - page_offset(page)); - unlock_page(page); - /* - * Submission finished without problem, if no range of the page is - * dirty anymore, we have submitted a page. Update nr_written in wbc. - */ - if (no_dirty_ebs) - bio_ctrl->wbc->nr_to_write--; -} - static noinline_for_stack void write_one_eb(struct extent_buffer *eb, - struct btrfs_bio_ctrl *bio_ctrl) + struct writeback_control *wbc) { - u64 disk_bytenr = eb->start; - int i, num_pages; + struct btrfs_fs_info *fs_info = eb->fs_info; + struct btrfs_bio *bbio; prepare_eb_write(eb); - bio_ctrl->end_io_func = end_bio_extent_buffer_writepage; - - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - struct page *p = eb->pages[i]; - - clear_page_dirty_for_io(p); - set_page_writeback(p); - submit_extent_page(bio_ctrl, disk_bytenr, p, PAGE_SIZE, 0); - disk_bytenr += PAGE_SIZE; - bio_ctrl->wbc->nr_to_write--; + bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, + REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc), + eb->fs_info, extent_buffer_write_end_io, eb); + bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; + bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev); + wbc_init_bio(wbc, &bbio->bio); + bbio->inode = BTRFS_I(eb->fs_info->btree_inode); + bbio->file_offset = eb->start; + if (fs_info->nodesize < PAGE_SIZE) { + struct page *p = eb->pages[0]; + + lock_page(p); + btrfs_subpage_set_writeback(fs_info, p, eb->start, eb->len); + if (btrfs_subpage_clear_and_test_dirty(fs_info, p, eb->start, + eb->len)) { + clear_page_dirty_for_io(p); + wbc->nr_to_write--; + } + __bio_add_page(&bbio->bio, p, eb->len, eb->start - page_offset(p)); + wbc_account_cgroup_owner(wbc, p, eb->len); unlock_page(p); + } else { + for (int i = 0; i < num_extent_pages(eb); i++) { + struct page *p = eb->pages[i]; + + lock_page(p); + clear_page_dirty_for_io(p); + set_page_writeback(p); + __bio_add_page(&bbio->bio, p, PAGE_SIZE, 0); + wbc_account_cgroup_owner(wbc, p, PAGE_SIZE); + wbc->nr_to_write--; + unlock_page(p); + } } + btrfs_submit_bio(bbio, 0); } /* @@ -2068,14 +1773,13 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, * Return >=0 for the number of submitted extent buffers. * Return <0 for fatal error. */ -static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl) +static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) { struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); int submitted = 0; u64 page_start = page_offset(page); int bit_start = 0; int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits; - int ret; /* Lock and write each dirty extent buffers in the range */ while (bit_start < fs_info->subpage_info->bitmap_nr_bits) { @@ -2121,25 +1825,13 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl) if (!eb) continue; - ret = lock_extent_buffer_for_io(eb, bio_ctrl); - if (ret == 0) { - free_extent_buffer(eb); - continue; + if (lock_extent_buffer_for_io(eb, wbc)) { + write_one_eb(eb, wbc); + submitted++; } - if (ret < 0) { - free_extent_buffer(eb); - goto cleanup; - } - write_one_subpage_eb(eb, bio_ctrl); free_extent_buffer(eb); - submitted++; } return submitted; - -cleanup: - /* We hit error, end bio for the submitted extent buffers */ - submit_write_bio(bio_ctrl, ret); - return ret; } /* @@ -2162,7 +1854,7 @@ cleanup: * previous call. * Return <0 for fatal error. */ -static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, +static int submit_eb_page(struct page *page, struct writeback_control *wbc, struct extent_buffer **eb_context) { struct address_space *mapping = page->mapping; @@ -2174,7 +1866,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, return 0; if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE) - return submit_eb_subpage(page, bio_ctrl); + return submit_eb_subpage(page, wbc); spin_lock(&mapping->private_lock); if (!PagePrivate(page)) { @@ -2207,8 +1899,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, * If for_sync, this hole will be filled with * trasnsaction commit. */ - if (bio_ctrl->wbc->sync_mode == WB_SYNC_ALL && - !bio_ctrl->wbc->for_sync) + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) ret = -EAGAIN; else ret = 0; @@ -2218,13 +1909,12 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, *eb_context = eb; - ret = lock_extent_buffer_for_io(eb, bio_ctrl); - if (ret <= 0) { + if (!lock_extent_buffer_for_io(eb, wbc)) { btrfs_revert_meta_write_pointer(cache, eb); if (cache) btrfs_put_block_group(cache); free_extent_buffer(eb); - return ret; + return 0; } if (cache) { /* @@ -2233,7 +1923,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, btrfs_schedule_zone_finish_bg(cache, eb); btrfs_put_block_group(cache); } - write_one_eb(eb, bio_ctrl); + write_one_eb(eb, wbc); free_extent_buffer(eb); return 1; } @@ -2242,11 +1932,6 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) { struct extent_buffer *eb_context = NULL; - struct btrfs_bio_ctrl bio_ctrl = { - .wbc = wbc, - .opf = REQ_OP_WRITE | wbc_to_write_flags(wbc), - .extent_locked = 0, - }; struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info; int ret = 0; int done = 0; @@ -2288,7 +1973,7 @@ retry: for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; - ret = submit_eb_page(&folio->page, &bio_ctrl, &eb_context); + ret = submit_eb_page(&folio->page, wbc, &eb_context); if (ret == 0) continue; if (ret < 0) { @@ -2349,8 +2034,6 @@ retry: ret = 0; if (!ret && BTRFS_FS_ERROR(fs_info)) ret = -EROFS; - submit_write_bio(&bio_ctrl, ret); - btrfs_zoned_meta_io_unlock(fs_info); return ret; } @@ -2520,38 +2203,31 @@ retry: * already been ran (aka, ordered extent inserted) and all pages are still * locked. */ -int extent_write_locked_range(struct inode *inode, u64 start, u64 end) +int extent_write_locked_range(struct inode *inode, u64 start, u64 end, + struct writeback_control *wbc) { bool found_error = false; int first_error = 0; int ret = 0; struct address_space *mapping = inode->i_mapping; - struct page *page; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + const u32 sectorsize = fs_info->sectorsize; + loff_t i_size = i_size_read(inode); u64 cur = start; - unsigned long nr_pages; - const u32 sectorsize = btrfs_sb(inode->i_sb)->sectorsize; - struct writeback_control wbc_writepages = { - .sync_mode = WB_SYNC_ALL, - .range_start = start, - .range_end = end + 1, - .no_cgroup_owner = 1, - }; struct btrfs_bio_ctrl bio_ctrl = { - .wbc = &wbc_writepages, - /* We're called from an async helper function */ - .opf = REQ_OP_WRITE | REQ_BTRFS_CGROUP_PUNT | - wbc_to_write_flags(&wbc_writepages), - .extent_locked = 1, + .wbc = wbc, + .opf = REQ_OP_WRITE | wbc_to_write_flags(wbc), }; + if (wbc->no_cgroup_owner) + bio_ctrl.opf |= REQ_BTRFS_CGROUP_PUNT; + ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(end + 1, sectorsize)); - nr_pages = (round_up(end, PAGE_SIZE) - round_down(start, PAGE_SIZE)) >> - PAGE_SHIFT; - wbc_writepages.nr_to_write = nr_pages * 2; - wbc_attach_fdatawrite_inode(&wbc_writepages, inode); while (cur <= end) { u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end); + struct page *page; + int nr = 0; page = find_get_page(mapping, cur >> PAGE_SHIFT); /* @@ -2562,19 +2238,31 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end) ASSERT(PageLocked(page)); ASSERT(PageDirty(page)); clear_page_dirty_for_io(page); - ret = __extent_writepage(page, &bio_ctrl); - ASSERT(ret <= 0); + + ret = __extent_writepage_io(BTRFS_I(inode), page, &bio_ctrl, + i_size, &nr); + if (ret == 1) + goto next_page; + + /* Make sure the mapping tag for page dirty gets cleared. */ + if (nr == 0) { + set_page_writeback(page); + end_page_writeback(page); + } + if (ret) + end_extent_writepage(page, ret, cur, cur_end); + btrfs_page_unlock_writer(fs_info, page, cur, cur_end + 1 - cur); if (ret < 0) { found_error = true; first_error = ret; } +next_page: put_page(page); cur = cur_end + 1; } submit_write_bio(&bio_ctrl, found_error ? ret : 0); - wbc_detach_inode(&wbc_writepages); if (found_error) return first_error; return ret; @@ -2588,7 +2276,6 @@ int extent_writepages(struct address_space *mapping, struct btrfs_bio_ctrl bio_ctrl = { .wbc = wbc, .opf = REQ_OP_WRITE | wbc_to_write_flags(wbc), - .extent_locked = 0, }; /* @@ -2679,8 +2366,7 @@ static int try_release_extent_state(struct extent_io_tree *tree, * The delalloc new bit will be cleared by ordered extent * completion. */ - ret = __clear_extent_bit(tree, start, end, clear_bits, NULL, - mask, NULL); + ret = __clear_extent_bit(tree, start, end, clear_bits, NULL, NULL); /* if clear_extent_bit failed for enomem reasons, * we can't allow the release to continue. @@ -3421,10 +3107,9 @@ static void __free_extent_buffer(struct extent_buffer *eb) kmem_cache_free(extent_buffer_cache, eb); } -int extent_buffer_under_io(const struct extent_buffer *eb) +static int extent_buffer_under_io(const struct extent_buffer *eb) { - return (atomic_read(&eb->io_pages) || - test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || + return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); } @@ -3557,11 +3242,9 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, init_rwsem(&eb->lock); btrfs_leak_debug_add_eb(eb); - INIT_LIST_HEAD(&eb->release_list); spin_lock_init(&eb->refs_lock); atomic_set(&eb->refs, 1); - atomic_set(&eb->io_pages, 0); ASSERT(len <= BTRFS_MAX_METADATA_BLOCKSIZE); @@ -3678,9 +3361,9 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) * adequately protected by the refcount, but the TREE_REF bit and * its corresponding reference are not. To protect against this * class of races, we call check_buffer_tree_ref from the codepaths - * which trigger io after they set eb->io_pages. Note that once io is - * initiated, TREE_REF can no longer be cleared, so that is the - * moment at which any such race is best fixed. + * which trigger io. Note that once io is initiated, TREE_REF can no + * longer be cleared, so that is the moment at which any such race is + * best fixed. */ refs = atomic_read(&eb->refs); if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) @@ -3939,7 +3622,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len)); eb->pages[i] = p; - if (!PageUptodate(p)) + if (!btrfs_page_test_uptodate(fs_info, p, eb->start, eb->len)) uptodate = 0; /* @@ -4142,13 +3825,12 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, continue; lock_page(page); btree_clear_page_dirty(page); - ClearPageError(page); unlock_page(page); } WARN_ON(atomic_read(&eb->refs) == 0); } -bool set_extent_buffer_dirty(struct extent_buffer *eb) +void set_extent_buffer_dirty(struct extent_buffer *eb) { int i; int num_pages; @@ -4183,13 +3865,14 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb) eb->start, eb->len); if (subpage) unlock_page(eb->pages[0]); + percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes, + eb->len, + eb->fs_info->dirty_metadata_batch); } #ifdef CONFIG_BTRFS_DEBUG for (i = 0; i < num_pages; i++) ASSERT(PageDirty(eb->pages[i])); #endif - - return was_dirty; } void clear_extent_buffer_uptodate(struct extent_buffer *eb) @@ -4242,84 +3925,54 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb) } } -static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, - int mirror_num, - struct btrfs_tree_parent_check *check) +static void extent_buffer_read_end_io(struct btrfs_bio *bbio) { + struct extent_buffer *eb = bbio->private; struct btrfs_fs_info *fs_info = eb->fs_info; - struct extent_io_tree *io_tree; - struct page *page = eb->pages[0]; - struct extent_state *cached_state = NULL; - struct btrfs_bio_ctrl bio_ctrl = { - .opf = REQ_OP_READ, - .mirror_num = mirror_num, - .parent_check = check, - }; - int ret; + bool uptodate = !bbio->bio.bi_status; + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + u32 bio_offset = 0; - ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags)); - ASSERT(PagePrivate(page)); - ASSERT(check); - io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; + eb->read_mirror = bbio->mirror_num; - if (wait == WAIT_NONE) { - if (!try_lock_extent(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state)) - return -EAGAIN; - } else { - ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state); - if (ret < 0) - return ret; - } + if (uptodate && + btrfs_validate_extent_buffer(eb, &bbio->parent_check) < 0) + uptodate = false; - if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) || - PageUptodate(page) || - btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) { - set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); - unlock_extent(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state); - return 0; + if (uptodate) { + set_extent_buffer_uptodate(eb); + } else { + clear_extent_buffer_uptodate(eb); + set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); } - clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); - eb->read_mirror = 0; - atomic_set(&eb->io_pages, 1); - check_buffer_tree_ref(eb); - bio_ctrl.end_io_func = end_bio_extent_readpage; + bio_for_each_segment_all(bvec, &bbio->bio, iter_all) { + u64 start = eb->start + bio_offset; + struct page *page = bvec->bv_page; + u32 len = bvec->bv_len; - btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len); + if (uptodate) + btrfs_page_set_uptodate(fs_info, page, start, len); + else + btrfs_page_clear_uptodate(fs_info, page, start, len); - btrfs_subpage_start_reader(fs_info, page, eb->start, eb->len); - submit_extent_page(&bio_ctrl, eb->start, page, eb->len, - eb->start - page_offset(page)); - submit_one_bio(&bio_ctrl); - if (wait != WAIT_COMPLETE) { - free_extent_state(cached_state); - return 0; + bio_offset += len; } - wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1, - EXTENT_LOCKED, &cached_state); - if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) - return -EIO; - return 0; + clear_bit(EXTENT_BUFFER_READING, &eb->bflags); + smp_mb__after_atomic(); + wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING); + free_extent_buffer(eb); + + bio_put(&bbio->bio); } int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, struct btrfs_tree_parent_check *check) { - int i; - struct page *page; - int locked_pages = 0; - int all_uptodate = 1; - int num_pages; - unsigned long num_reads = 0; - struct btrfs_bio_ctrl bio_ctrl = { - .opf = REQ_OP_READ, - .mirror_num = mirror_num, - .parent_check = check, - }; + int num_pages = num_extent_pages(eb), i; + struct btrfs_bio *bbio; if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; @@ -4332,87 +3985,39 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) return -EIO; - if (eb->fs_info->nodesize < PAGE_SIZE) - return read_extent_buffer_subpage(eb, wait, mirror_num, check); - - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - page = eb->pages[i]; - if (wait == WAIT_NONE) { - /* - * WAIT_NONE is only utilized by readahead. If we can't - * acquire the lock atomically it means either the eb - * is being read out or under modification. - * Either way the eb will be or has been cached, - * readahead can exit safely. - */ - if (!trylock_page(page)) - goto unlock_exit; - } else { - lock_page(page); - } - locked_pages++; - } - /* - * We need to firstly lock all pages to make sure that - * the uptodate bit of our pages won't be affected by - * clear_extent_buffer_uptodate(). - */ - for (i = 0; i < num_pages; i++) { - page = eb->pages[i]; - if (!PageUptodate(page)) { - num_reads++; - all_uptodate = 0; - } - } - - if (all_uptodate) { - set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); - goto unlock_exit; - } + /* Someone else is already reading the buffer, just wait for it. */ + if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) + goto done; clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = 0; - atomic_set(&eb->io_pages, num_reads); - /* - * It is possible for release_folio to clear the TREE_REF bit before we - * set io_pages. See check_buffer_tree_ref for a more detailed comment. - */ check_buffer_tree_ref(eb); - bio_ctrl.end_io_func = end_bio_extent_readpage; - for (i = 0; i < num_pages; i++) { - page = eb->pages[i]; - - if (!PageUptodate(page)) { - ClearPageError(page); - submit_extent_page(&bio_ctrl, page_offset(page), page, - PAGE_SIZE, 0); - } else { - unlock_page(page); - } + atomic_inc(&eb->refs); + + bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, + REQ_OP_READ | REQ_META, eb->fs_info, + extent_buffer_read_end_io, eb); + bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; + bbio->inode = BTRFS_I(eb->fs_info->btree_inode); + bbio->file_offset = eb->start; + memcpy(&bbio->parent_check, check, sizeof(*check)); + if (eb->fs_info->nodesize < PAGE_SIZE) { + __bio_add_page(&bbio->bio, eb->pages[0], eb->len, + eb->start - page_offset(eb->pages[0])); + } else { + for (i = 0; i < num_pages; i++) + __bio_add_page(&bbio->bio, eb->pages[i], PAGE_SIZE, 0); } + btrfs_submit_bio(bbio, mirror_num); - submit_one_bio(&bio_ctrl); - - if (wait != WAIT_COMPLETE) - return 0; - - for (i = 0; i < num_pages; i++) { - page = eb->pages[i]; - wait_on_page_locked(page); - if (!PageUptodate(page)) +done: + if (wait == WAIT_COMPLETE) { + wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return -EIO; } return 0; - -unlock_exit: - while (locked_pages > 0) { - locked_pages--; - page = eb->pages[locked_pages]; - unlock_page(page); - } - return 0; } static bool report_eb_range(const struct extent_buffer *eb, unsigned long start, @@ -4561,18 +4166,17 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb, * looked up. We don't want to complain in this case, as the page was * valid before, we just didn't write it out. Instead we want to catch * the case where we didn't actually read the block properly, which - * would have !PageUptodate && !PageError, as we clear PageError before - * reading. + * would have !PageUptodate and !EXTENT_BUFFER_WRITE_ERR. */ - if (fs_info->nodesize < PAGE_SIZE) { - bool uptodate, error; + if (test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) + return; - uptodate = btrfs_subpage_test_uptodate(fs_info, page, - eb->start, eb->len); - error = btrfs_subpage_test_error(fs_info, page, eb->start, eb->len); - WARN_ON(!uptodate && !error); + if (fs_info->nodesize < PAGE_SIZE) { + if (WARN_ON(!btrfs_subpage_test_uptodate(fs_info, page, + eb->start, eb->len))) + btrfs_subpage_dump_bitmap(fs_info, page, eb->start, eb->len); } else { - WARN_ON(!PageUptodate(page) && !PageError(page)); + WARN_ON(!PageUptodate(page)); } } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 4341ad978fb8..c5fae3a7d911 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -29,6 +29,8 @@ enum { /* write IO error */ EXTENT_BUFFER_WRITE_ERR, EXTENT_BUFFER_NO_CHECK, + /* Indicate that extent buffer pages a being read */ + EXTENT_BUFFER_READING, }; /* these are flags for __process_pages_contig */ @@ -38,7 +40,6 @@ enum { ENUM_BIT(PAGE_START_WRITEBACK), ENUM_BIT(PAGE_END_WRITEBACK), ENUM_BIT(PAGE_SET_ORDERED), - ENUM_BIT(PAGE_SET_ERROR), ENUM_BIT(PAGE_LOCK), }; @@ -79,7 +80,6 @@ struct extent_buffer { struct btrfs_fs_info *fs_info; spinlock_t refs_lock; atomic_t refs; - atomic_t io_pages; int read_mirror; struct rcu_head rcu_head; pid_t lock_owner; @@ -89,7 +89,6 @@ struct extent_buffer { struct rw_semaphore lock; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; - struct list_head release_list; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif @@ -179,7 +178,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask); int try_release_extent_buffer(struct page *page); int btrfs_read_folio(struct file *file, struct folio *folio); -int extent_write_locked_range(struct inode *inode, u64 start, u64 end); +int extent_write_locked_range(struct inode *inode, u64 start, u64 end, + struct writeback_control *wbc); int extent_writepages(struct address_space *mapping, struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping, @@ -262,10 +262,9 @@ void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long star void extent_buffer_bitmap_clear(const struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len); -bool set_extent_buffer_dirty(struct extent_buffer *eb); +void set_extent_buffer_dirty(struct extent_buffer *eb); void set_extent_buffer_uptodate(struct extent_buffer *eb); void clear_extent_buffer_uptodate(struct extent_buffer *eb); -int extent_buffer_under_io(const struct extent_buffer *eb); void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 138afa955370..0cdb3e86f29b 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -364,8 +364,9 @@ static void extent_map_device_set_bits(struct extent_map *em, unsigned bits) struct btrfs_io_stripe *stripe = &map->stripes[i]; struct btrfs_device *device = stripe->dev; - set_extent_bits_nowait(&device->alloc_state, stripe->physical, - stripe->physical + stripe_size - 1, bits); + set_extent_bit(&device->alloc_state, stripe->physical, + stripe->physical + stripe_size - 1, + bits | EXTENT_NOWAIT, NULL); } } @@ -380,8 +381,9 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits) struct btrfs_device *device = stripe->dev; __clear_extent_bit(&device->alloc_state, stripe->physical, - stripe->physical + stripe_size - 1, bits, - NULL, GFP_NOWAIT, NULL); + stripe->physical + stripe_size - 1, + bits | EXTENT_NOWAIT, + NULL, NULL); } } @@ -502,10 +504,10 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em) RB_CLEAR_NODE(&em->rb_node); } -void replace_extent_mapping(struct extent_map_tree *tree, - struct extent_map *cur, - struct extent_map *new, - int modified) +static void replace_extent_mapping(struct extent_map_tree *tree, + struct extent_map *cur, + struct extent_map *new, + int modified) { lockdep_assert_held_write(&tree->lock); @@ -959,3 +961,95 @@ int btrfs_replace_extent_map_range(struct btrfs_inode *inode, return ret; } + +/* + * Split off the first pre bytes from the extent_map at [start, start + len], + * and set the block_start for it to new_logical. + * + * This function is used when an ordered_extent needs to be split. + */ +int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre, + u64 new_logical) +{ + struct extent_map_tree *em_tree = &inode->extent_tree; + struct extent_map *em; + struct extent_map *split_pre = NULL; + struct extent_map *split_mid = NULL; + int ret = 0; + unsigned long flags; + + ASSERT(pre != 0); + ASSERT(pre < len); + + split_pre = alloc_extent_map(); + if (!split_pre) + return -ENOMEM; + split_mid = alloc_extent_map(); + if (!split_mid) { + ret = -ENOMEM; + goto out_free_pre; + } + + lock_extent(&inode->io_tree, start, start + len - 1, NULL); + write_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, len); + if (!em) { + ret = -EIO; + goto out_unlock; + } + + ASSERT(em->len == len); + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE); + ASSERT(test_bit(EXTENT_FLAG_PINNED, &em->flags)); + ASSERT(!test_bit(EXTENT_FLAG_LOGGING, &em->flags)); + ASSERT(!list_empty(&em->list)); + + flags = em->flags; + clear_bit(EXTENT_FLAG_PINNED, &em->flags); + + /* First, replace the em with a new extent_map starting from * em->start */ + split_pre->start = em->start; + split_pre->len = pre; + split_pre->orig_start = split_pre->start; + split_pre->block_start = new_logical; + split_pre->block_len = split_pre->len; + split_pre->orig_block_len = split_pre->block_len; + split_pre->ram_bytes = split_pre->len; + split_pre->flags = flags; + split_pre->compress_type = em->compress_type; + split_pre->generation = em->generation; + + replace_extent_mapping(em_tree, em, split_pre, 1); + + /* + * Now we only have an extent_map at: + * [em->start, em->start + pre] + */ + + /* Insert the middle extent_map. */ + split_mid->start = em->start + pre; + split_mid->len = em->len - pre; + split_mid->orig_start = split_mid->start; + split_mid->block_start = em->block_start + pre; + split_mid->block_len = split_mid->len; + split_mid->orig_block_len = split_mid->block_len; + split_mid->ram_bytes = split_mid->len; + split_mid->flags = flags; + split_mid->compress_type = em->compress_type; + split_mid->generation = em->generation; + add_extent_mapping(em_tree, split_mid, 1); + + /* Once for us */ + free_extent_map(em); + /* Once for the tree */ + free_extent_map(em); + +out_unlock: + write_unlock(&em_tree->lock); + unlock_extent(&inode->io_tree, start, start + len - 1, NULL); + free_extent_map(split_mid); +out_free_pre: + free_extent_map(split_pre); + return ret; +} diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index ad311864272a..35d27c756e08 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -90,10 +90,8 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, int add_extent_mapping(struct extent_map_tree *tree, struct extent_map *em, int modified); void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em); -void replace_extent_mapping(struct extent_map_tree *tree, - struct extent_map *cur, - struct extent_map *new, - int modified); +int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre, + u64 new_logical); struct extent_map *alloc_extent_map(void); void free_extent_map(struct extent_map *em); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index d1cd0a692f8e..696bf695d8eb 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -94,8 +94,8 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, if (btrfs_fs_incompat(inode->root->fs_info, NO_HOLES)) return 0; - return set_extent_bits(&inode->file_extent_tree, start, start + len - 1, - EXTENT_DIRTY); + return set_extent_bit(&inode->file_extent_tree, start, start + len - 1, + EXTENT_DIRTY, NULL); } /* @@ -438,9 +438,9 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio) BTRFS_DATA_RELOC_TREE_OBJECTID) { u64 file_offset = bbio->file_offset + bio_offset; - set_extent_bits(&inode->io_tree, file_offset, - file_offset + sectorsize - 1, - EXTENT_NODATASUM); + set_extent_bit(&inode->io_tree, file_offset, + file_offset + sectorsize - 1, + EXTENT_NODATASUM, NULL); } else { btrfs_warn_rl(fs_info, "csum hole found for disk bytenr range [%llu, %llu)", @@ -560,8 +560,8 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end, goto fail; } - sums->bytenr = start; - sums->len = (int)size; + sums->logical = start; + sums->len = size; offset = bytes_to_csum_size(fs_info, start - key.offset); @@ -721,20 +721,17 @@ fail: */ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) { + struct btrfs_ordered_extent *ordered = bbio->ordered; struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); struct bio *bio = &bbio->bio; - u64 offset = bbio->file_offset; struct btrfs_ordered_sum *sums; - struct btrfs_ordered_extent *ordered = NULL; char *data; struct bvec_iter iter; struct bio_vec bvec; int index; unsigned int blockcount; - unsigned long total_bytes = 0; - unsigned long this_sum_bytes = 0; int i; unsigned nofs_flag; @@ -749,61 +746,17 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) sums->len = bio->bi_iter.bi_size; INIT_LIST_HEAD(&sums->list); - sums->bytenr = bio->bi_iter.bi_sector << 9; + sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; index = 0; shash->tfm = fs_info->csum_shash; bio_for_each_segment(bvec, bio, iter) { - if (!ordered) { - ordered = btrfs_lookup_ordered_extent(inode, offset); - /* - * The bio range is not covered by any ordered extent, - * must be a code logic error. - */ - if (unlikely(!ordered)) { - WARN(1, KERN_WARNING - "no ordered extent for root %llu ino %llu offset %llu\n", - inode->root->root_key.objectid, - btrfs_ino(inode), offset); - kvfree(sums); - return BLK_STS_IOERR; - } - } - blockcount = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len + fs_info->sectorsize - 1); for (i = 0; i < blockcount; i++) { - if (!(bio->bi_opf & REQ_BTRFS_ONE_ORDERED) && - !in_range(offset, ordered->file_offset, - ordered->num_bytes)) { - unsigned long bytes_left; - - sums->len = this_sum_bytes; - this_sum_bytes = 0; - btrfs_add_ordered_sum(ordered, sums); - btrfs_put_ordered_extent(ordered); - - bytes_left = bio->bi_iter.bi_size - total_bytes; - - nofs_flag = memalloc_nofs_save(); - sums = kvzalloc(btrfs_ordered_sum_size(fs_info, - bytes_left), GFP_KERNEL); - memalloc_nofs_restore(nofs_flag); - if (!sums) - return BLK_STS_RESOURCE; - - sums->len = bytes_left; - ordered = btrfs_lookup_ordered_extent(inode, - offset); - ASSERT(ordered); /* Logic error */ - sums->bytenr = (bio->bi_iter.bi_sector << 9) - + total_bytes; - index = 0; - } - data = bvec_kmap_local(&bvec); crypto_shash_digest(shash, data + (i * fs_info->sectorsize), @@ -811,15 +764,28 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) sums->sums + index); kunmap_local(data); index += fs_info->csum_size; - offset += fs_info->sectorsize; - this_sum_bytes += fs_info->sectorsize; - total_bytes += fs_info->sectorsize; } } - this_sum_bytes = 0; + + bbio->sums = sums; btrfs_add_ordered_sum(ordered, sums); - btrfs_put_ordered_extent(ordered); + return 0; +} + +/* + * Nodatasum I/O on zoned file systems still requires an btrfs_ordered_sum to + * record the updated logical address on Zone Append completion. + * Allocate just the structure with an empty sums array here for that case. + */ +blk_status_t btrfs_alloc_dummy_sum(struct btrfs_bio *bbio) +{ + bbio->sums = kmalloc(sizeof(*bbio->sums), GFP_NOFS); + if (!bbio->sums) + return BLK_STS_RESOURCE; + bbio->sums->len = bbio->bio.bi_iter.bi_size; + bbio->sums->logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; + btrfs_add_ordered_sum(bbio->ordered, bbio->sums); return 0; } @@ -1086,7 +1052,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, again: next_offset = (u64)-1; found_next = 0; - bytenr = sums->bytenr + total_bytes; + bytenr = sums->logical + total_bytes; file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; file_key.offset = bytenr; file_key.type = BTRFS_EXTENT_CSUM_KEY; diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h index 6be8725cd574..4ec669b69008 100644 --- a/fs/btrfs/file-item.h +++ b/fs/btrfs/file-item.h @@ -50,6 +50,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums); blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio); +blk_status_t btrfs_alloc_dummy_sum(struct btrfs_bio *bbio); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit, bool nowait); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f649647392e0..ba5b0c9f2bbd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1651,7 +1651,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from, struct file *file = iocb->ki_filp; struct btrfs_inode *inode = BTRFS_I(file_inode(file)); ssize_t num_written, num_sync; - const bool sync = iocb_is_dsync(iocb); /* * If the fs flips readonly due to some impossible error, although we @@ -1664,9 +1663,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from, if (encoded && (iocb->ki_flags & IOCB_NOWAIT)) return -EOPNOTSUPP; - if (sync) - atomic_inc(&inode->sync_writers); - if (encoded) { num_written = btrfs_encoded_write(iocb, from, encoded); num_sync = encoded->len; @@ -1686,9 +1682,6 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from, num_written = num_sync; } - if (sync) - atomic_dec(&inode->sync_writers); - current->backing_dev_info = NULL; return num_written; } @@ -1733,9 +1726,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) * several segments of stripe length (currently 64K). */ blk_start_plug(&plug); - atomic_inc(&BTRFS_I(inode)->sync_writers); ret = btrfs_fdatawrite_range(inode, start, end); - atomic_dec(&BTRFS_I(inode)->sync_writers); blk_finish_plug(&plug); return ret; @@ -3709,7 +3700,8 @@ static int btrfs_file_open(struct inode *inode, struct file *filp) { int ret; - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC; + filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC | + FMODE_CAN_ODIRECT; ret = fsverity_file_open(inode, filp); if (ret) @@ -3825,7 +3817,7 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, .read_iter = btrfs_file_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .write_iter = btrfs_file_write_iter, .splice_write = iter_file_splice_write, .mmap = btrfs_file_mmap, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index cf98a3c05480..880800418075 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -292,25 +292,6 @@ out: return ret; } -int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *rsv) -{ - u64 needed_bytes; - int ret; - - /* 1 for slack space, 1 for updating the inode */ - needed_bytes = btrfs_calc_insert_metadata_size(fs_info, 1) + - btrfs_calc_metadata_size(fs_info, 1); - - spin_lock(&rsv->lock); - if (rsv->reserved < needed_bytes) - ret = -ENOSPC; - else - ret = 0; - spin_unlock(&rsv->lock); - return ret; -} - int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct inode *vfs_inode) @@ -923,27 +904,31 @@ static int copy_free_space_cache(struct btrfs_block_group *block_group, while (!ret && (n = rb_first(&ctl->free_space_offset)) != NULL) { info = rb_entry(n, struct btrfs_free_space, offset_index); if (!info->bitmap) { + const u64 offset = info->offset; + const u64 bytes = info->bytes; + unlink_free_space(ctl, info, true); - ret = btrfs_add_free_space(block_group, info->offset, - info->bytes); + spin_unlock(&ctl->tree_lock); kmem_cache_free(btrfs_free_space_cachep, info); + ret = btrfs_add_free_space(block_group, offset, bytes); + spin_lock(&ctl->tree_lock); } else { u64 offset = info->offset; u64 bytes = ctl->unit; - while (search_bitmap(ctl, info, &offset, &bytes, - false) == 0) { + ret = search_bitmap(ctl, info, &offset, &bytes, false); + if (ret == 0) { + bitmap_clear_bits(ctl, info, offset, bytes, true); + spin_unlock(&ctl->tree_lock); ret = btrfs_add_free_space(block_group, offset, bytes); - if (ret) - break; - bitmap_clear_bits(ctl, info, offset, bytes, true); - offset = info->offset; - bytes = ctl->unit; + spin_lock(&ctl->tree_lock); + } else { + free_bitmap(ctl, info); + ret = 0; } - free_bitmap(ctl, info); } - cond_resched(); + cond_resched_lock(&ctl->tree_lock); } return ret; } @@ -1037,7 +1022,9 @@ int load_free_space_cache(struct btrfs_block_group *block_group) block_group->bytes_super)); if (matched) { + spin_lock(&tmp_ctl.tree_lock); ret = copy_free_space_cache(block_group, &tmp_ctl); + spin_unlock(&tmp_ctl.tree_lock); /* * ret == 1 means we successfully loaded the free space cache, * so we need to re-set it here. @@ -1596,20 +1583,34 @@ static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl, return bitmap_start; } -static int tree_insert_offset(struct rb_root *root, u64 offset, - struct rb_node *node, int bitmap) +static int tree_insert_offset(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_cluster *cluster, + struct btrfs_free_space *new_entry) { - struct rb_node **p = &root->rb_node; + struct rb_root *root; + struct rb_node **p; struct rb_node *parent = NULL; - struct btrfs_free_space *info; + + lockdep_assert_held(&ctl->tree_lock); + + if (cluster) { + lockdep_assert_held(&cluster->lock); + root = &cluster->root; + } else { + root = &ctl->free_space_offset; + } + + p = &root->rb_node; while (*p) { + struct btrfs_free_space *info; + parent = *p; info = rb_entry(parent, struct btrfs_free_space, offset_index); - if (offset < info->offset) { + if (new_entry->offset < info->offset) { p = &(*p)->rb_left; - } else if (offset > info->offset) { + } else if (new_entry->offset > info->offset) { p = &(*p)->rb_right; } else { /* @@ -1625,7 +1626,7 @@ static int tree_insert_offset(struct rb_root *root, u64 offset, * found a bitmap, we want to go left, or before * logically. */ - if (bitmap) { + if (new_entry->bitmap) { if (info->bitmap) { WARN_ON_ONCE(1); return -EEXIST; @@ -1641,8 +1642,8 @@ static int tree_insert_offset(struct rb_root *root, u64 offset, } } - rb_link_node(node, parent, p); - rb_insert_color(node, root); + rb_link_node(&new_entry->offset_index, parent, p); + rb_insert_color(&new_entry->offset_index, root); return 0; } @@ -1705,6 +1706,8 @@ tree_search_offset(struct btrfs_free_space_ctl *ctl, struct rb_node *n = ctl->free_space_offset.rb_node; struct btrfs_free_space *entry = NULL, *prev = NULL; + lockdep_assert_held(&ctl->tree_lock); + /* find entry that is closest to the 'offset' */ while (n) { entry = rb_entry(n, struct btrfs_free_space, offset_index); @@ -1814,6 +1817,8 @@ static inline void unlink_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { + lockdep_assert_held(&ctl->tree_lock); + rb_erase(&info->offset_index, &ctl->free_space_offset); rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes); ctl->free_extents--; @@ -1832,9 +1837,10 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl, { int ret = 0; + lockdep_assert_held(&ctl->tree_lock); + ASSERT(info->bytes || info->bitmap); - ret = tree_insert_offset(&ctl->free_space_offset, info->offset, - &info->offset_index, (info->bitmap != NULL)); + ret = tree_insert_offset(ctl, NULL, info); if (ret) return ret; @@ -1862,6 +1868,8 @@ static void relink_bitmap_entry(struct btrfs_free_space_ctl *ctl, if (RB_EMPTY_NODE(&info->bytes_index)) return; + lockdep_assert_held(&ctl->tree_lock); + rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes); rb_add_cached(&info->bytes_index, &ctl->free_space_bytes, entry_less); } @@ -2447,6 +2455,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, u64 offset = info->offset; u64 bytes = info->bytes; const bool is_trimmed = btrfs_free_space_trimmed(info); + struct rb_node *right_prev = NULL; /* * first we want to see if there is free space adjacent to the range we @@ -2454,9 +2463,11 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, * cover the entire range */ right_info = tree_search_offset(ctl, offset + bytes, 0, 0); - if (right_info && rb_prev(&right_info->offset_index)) - left_info = rb_entry(rb_prev(&right_info->offset_index), - struct btrfs_free_space, offset_index); + if (right_info) + right_prev = rb_prev(&right_info->offset_index); + + if (right_prev) + left_info = rb_entry(right_prev, struct btrfs_free_space, offset_index); else if (!right_info) left_info = tree_search_offset(ctl, offset - 1, 0, 0); @@ -2969,9 +2980,10 @@ static void __btrfs_return_cluster_to_free_space( struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; - struct btrfs_free_space *entry; struct rb_node *node; + lockdep_assert_held(&ctl->tree_lock); + spin_lock(&cluster->lock); if (cluster->block_group != block_group) { spin_unlock(&cluster->lock); @@ -2984,15 +2996,14 @@ static void __btrfs_return_cluster_to_free_space( node = rb_first(&cluster->root); while (node) { - bool bitmap; + struct btrfs_free_space *entry; entry = rb_entry(node, struct btrfs_free_space, offset_index); node = rb_next(&entry->offset_index); rb_erase(&entry->offset_index, &cluster->root); RB_CLEAR_NODE(&entry->offset_index); - bitmap = (entry->bitmap != NULL); - if (!bitmap) { + if (!entry->bitmap) { /* Merging treats extents as if they were new */ if (!btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR]--; @@ -3010,8 +3021,7 @@ static void __btrfs_return_cluster_to_free_space( entry->bytes; } } - tree_insert_offset(&ctl->free_space_offset, - entry->offset, &entry->offset_index, bitmap); + tree_insert_offset(ctl, NULL, entry); rb_add_cached(&entry->bytes_index, &ctl->free_space_bytes, entry_less); } @@ -3324,6 +3334,8 @@ static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group, unsigned long total_found = 0; int ret; + lockdep_assert_held(&ctl->tree_lock); + i = offset_to_bit(entry->offset, ctl->unit, max_t(u64, offset, entry->offset)); want_bits = bytes_to_bits(bytes, ctl->unit); @@ -3385,8 +3397,7 @@ again: */ RB_CLEAR_NODE(&entry->bytes_index); - ret = tree_insert_offset(&cluster->root, entry->offset, - &entry->offset_index, 1); + ret = tree_insert_offset(ctl, cluster, entry); ASSERT(!ret); /* -EEXIST; Logic error */ trace_btrfs_setup_cluster(block_group, cluster, @@ -3414,6 +3425,8 @@ setup_cluster_no_bitmap(struct btrfs_block_group *block_group, u64 max_extent; u64 total_size = 0; + lockdep_assert_held(&ctl->tree_lock); + entry = tree_search_offset(ctl, offset, 0, 1); if (!entry) return -ENOSPC; @@ -3476,8 +3489,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group *block_group, rb_erase(&entry->offset_index, &ctl->free_space_offset); rb_erase_cached(&entry->bytes_index, &ctl->free_space_bytes); - ret = tree_insert_offset(&cluster->root, entry->offset, - &entry->offset_index, 0); + ret = tree_insert_offset(ctl, cluster, entry); total_size += entry->bytes; ASSERT(!ret); /* -EEXIST; Logic error */ } while (node && entry != last); @@ -3671,7 +3683,7 @@ static int do_trimming(struct btrfs_block_group *block_group, __btrfs_add_free_space(block_group, reserved_start, start - reserved_start, reserved_trim_state); - if (start + bytes < reserved_start + reserved_bytes) + if (end < reserved_end) __btrfs_add_free_space(block_group, end, reserved_end - end, reserved_trim_state); __btrfs_add_free_space(block_group, start, bytes, trim_state); diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index a855e0483e03..33b4da3271b1 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -101,8 +101,6 @@ int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_block_group *block_group); -int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *rsv); int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct inode *inode); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index b21da1446f2a..045ddce32eca 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1280,7 +1280,10 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info) goto abort; btrfs_global_root_delete(free_space_root); + + spin_lock(&fs_info->trans_lock); list_del(&free_space_root->dirty_list); + spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(free_space_root->node); btrfs_clear_buffer_dirty(trans, free_space_root->node); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 0d98fc5f6f44..203d2a267828 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -543,7 +543,6 @@ struct btrfs_fs_info { * A third pool does submit_bio to avoid deadlocking with the other two. */ struct btrfs_workqueue *workers; - struct btrfs_workqueue *hipri_workers; struct btrfs_workqueue *delalloc_workers; struct btrfs_workqueue *flush_workers; struct workqueue_struct *endio_workers; @@ -577,6 +576,7 @@ struct btrfs_fs_info { s32 dirty_metadata_batch; s32 delalloc_batch; + /* Protected by 'trans_lock'. */ struct list_head dirty_cowonly_roots; struct btrfs_fs_devices *fs_devices; @@ -643,7 +643,6 @@ struct btrfs_fs_info { */ refcount_t scrub_workers_refcnt; struct workqueue_struct *scrub_workers; - struct workqueue_struct *scrub_wr_completion_workers; struct btrfs_subpage_info *subpage_info; struct btrfs_discard_ctl discard_ctl; @@ -854,7 +853,7 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info, static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) { - return fs_info->zone_size > 0; + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0; } /* diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h index b80aeb715701..ede43b6c6559 100644 --- a/fs/btrfs/inode-item.h +++ b/fs/btrfs/inode-item.h @@ -60,6 +60,22 @@ struct btrfs_truncate_control { bool clear_extent_range; }; +/* + * btrfs_inode_item stores flags in a u64, btrfs_inode stores them in two + * separate u32s. These two functions convert between the two representations. + */ +static inline u64 btrfs_inode_combine_flags(u32 flags, u32 ro_flags) +{ + return (flags | ((u64)ro_flags << 32)); +} + +static inline void btrfs_inode_split_flags(u64 inode_item_flags, + u32 *flags, u32 *ro_flags) +{ + *flags = (u32)inode_item_flags; + *ro_flags = (u32)(inode_item_flags >> 32); +} + int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_truncate_control *control); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 19c707bc8801..dbbb67293e34 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -70,6 +70,7 @@ #include "verity.h" #include "super.h" #include "orphan.h" +#include "backref.h" struct btrfs_iget_args { u64 ino; @@ -100,6 +101,18 @@ struct btrfs_rename_ctx { u64 index; }; +/* + * Used by data_reloc_print_warning_inode() to pass needed info for filename + * resolution and output of error message. + */ +struct data_reloc_warn { + struct btrfs_path path; + struct btrfs_fs_info *fs_info; + u64 extent_item_size; + u64 logical; + int mirror_num; +}; + static const struct inode_operations btrfs_dir_inode_operations; static const struct inode_operations btrfs_symlink_inode_operations; static const struct inode_operations btrfs_special_inode_operations; @@ -122,12 +135,198 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start, u64 ram_bytes, int compress_type, int type); +static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, + u64 root, void *warn_ctx) +{ + struct data_reloc_warn *warn = warn_ctx; + struct btrfs_fs_info *fs_info = warn->fs_info; + struct extent_buffer *eb; + struct btrfs_inode_item *inode_item; + struct inode_fs_paths *ipath = NULL; + struct btrfs_root *local_root; + struct btrfs_key key; + unsigned int nofs_flag; + u32 nlink; + int ret; + + local_root = btrfs_get_fs_root(fs_info, root, true); + if (IS_ERR(local_root)) { + ret = PTR_ERR(local_root); + goto err; + } + + /* This makes the path point to (inum INODE_ITEM ioff). */ + key.objectid = inum; + key.type = BTRFS_INODE_ITEM_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, local_root, &key, &warn->path, 0, 0); + if (ret) { + btrfs_put_root(local_root); + btrfs_release_path(&warn->path); + goto err; + } + + eb = warn->path.nodes[0]; + inode_item = btrfs_item_ptr(eb, warn->path.slots[0], struct btrfs_inode_item); + nlink = btrfs_inode_nlink(eb, inode_item); + btrfs_release_path(&warn->path); + + nofs_flag = memalloc_nofs_save(); + ipath = init_ipath(4096, local_root, &warn->path); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(ipath)) { + btrfs_put_root(local_root); + ret = PTR_ERR(ipath); + ipath = NULL; + /* + * -ENOMEM, not a critical error, just output an generic error + * without filename. + */ + btrfs_warn(fs_info, +"checksum error at logical %llu mirror %u root %llu, inode %llu offset %llu", + warn->logical, warn->mirror_num, root, inum, offset); + return ret; + } + ret = paths_from_inode(inum, ipath); + if (ret < 0) + goto err; + + /* + * We deliberately ignore the bit ipath might have been too small to + * hold all of the paths here + */ + for (int i = 0; i < ipath->fspath->elem_cnt; i++) { + btrfs_warn(fs_info, +"checksum error at logical %llu mirror %u root %llu inode %llu offset %llu length %u links %u (path: %s)", + warn->logical, warn->mirror_num, root, inum, offset, + fs_info->sectorsize, nlink, + (char *)(unsigned long)ipath->fspath->val[i]); + } + + btrfs_put_root(local_root); + free_ipath(ipath); + return 0; + +err: + btrfs_warn(fs_info, +"checksum error at logical %llu mirror %u root %llu inode %llu offset %llu, path resolving failed with ret=%d", + warn->logical, warn->mirror_num, root, inum, offset, ret); + + free_ipath(ipath); + return ret; +} + +/* + * Do extra user-friendly error output (e.g. lookup all the affected files). + * + * Return true if we succeeded doing the backref lookup. + * Return false if such lookup failed, and has to fallback to the old error message. + */ +static void print_data_reloc_error(const struct btrfs_inode *inode, u64 file_off, + const u8 *csum, const u8 *csum_expected, + int mirror_num) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_path path = { 0 }; + struct btrfs_key found_key = { 0 }; + struct extent_buffer *eb; + struct btrfs_extent_item *ei; + const u32 csum_size = fs_info->csum_size; + u64 logical; + u64 flags; + u32 item_size; + int ret; + + mutex_lock(&fs_info->reloc_mutex); + logical = btrfs_get_reloc_bg_bytenr(fs_info); + mutex_unlock(&fs_info->reloc_mutex); + + if (logical == U64_MAX) { + btrfs_warn_rl(fs_info, "has data reloc tree but no running relocation"); + btrfs_warn_rl(fs_info, +"csum failed root %lld ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d", + inode->root->root_key.objectid, btrfs_ino(inode), file_off, + CSUM_FMT_VALUE(csum_size, csum), + CSUM_FMT_VALUE(csum_size, csum_expected), + mirror_num); + return; + } + + logical += file_off; + btrfs_warn_rl(fs_info, +"csum failed root %lld ino %llu off %llu logical %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d", + inode->root->root_key.objectid, + btrfs_ino(inode), file_off, logical, + CSUM_FMT_VALUE(csum_size, csum), + CSUM_FMT_VALUE(csum_size, csum_expected), + mirror_num); + + ret = extent_from_logical(fs_info, logical, &path, &found_key, &flags); + if (ret < 0) { + btrfs_err_rl(fs_info, "failed to lookup extent item for logical %llu: %d", + logical, ret); + return; + } + eb = path.nodes[0]; + ei = btrfs_item_ptr(eb, path.slots[0], struct btrfs_extent_item); + item_size = btrfs_item_size(eb, path.slots[0]); + if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { + unsigned long ptr = 0; + u64 ref_root; + u8 ref_level; + + while (true) { + ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, + item_size, &ref_root, + &ref_level); + if (ret < 0) { + btrfs_warn_rl(fs_info, + "failed to resolve tree backref for logical %llu: %d", + logical, ret); + break; + } + if (ret > 0) + break; + + btrfs_warn_rl(fs_info, +"csum error at logical %llu mirror %u: metadata %s (level %d) in tree %llu", + logical, mirror_num, + (ref_level ? "node" : "leaf"), + ref_level, ref_root); + } + btrfs_release_path(&path); + } else { + struct btrfs_backref_walk_ctx ctx = { 0 }; + struct data_reloc_warn reloc_warn = { 0 }; + + btrfs_release_path(&path); + + ctx.bytenr = found_key.objectid; + ctx.extent_item_pos = logical - found_key.objectid; + ctx.fs_info = fs_info; + + reloc_warn.logical = logical; + reloc_warn.extent_item_size = found_key.offset; + reloc_warn.mirror_num = mirror_num; + reloc_warn.fs_info = fs_info; + + iterate_extent_inodes(&ctx, true, + data_reloc_print_warning_inode, &reloc_warn); + } +} + static void __cold btrfs_print_data_csum_error(struct btrfs_inode *inode, u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num) { struct btrfs_root *root = inode->root; const u32 csum_size = root->fs_info->csum_size; + /* For data reloc tree, it's better to do a backref lookup instead. */ + if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) + return print_data_reloc_error(inode, logical_start, csum, + csum_expected, mirror_num); + /* Output without objectid, which is more meaningful */ if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID) { btrfs_warn_rl(root->fs_info, @@ -636,6 +835,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk) { struct btrfs_inode *inode = async_chunk->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct address_space *mapping = inode->vfs_inode.i_mapping; u64 blocksize = fs_info->sectorsize; u64 start = async_chunk->start; u64 end = async_chunk->end; @@ -750,7 +950,7 @@ again: /* Compression level is applied here and only here */ ret = btrfs_compress_pages( compress_type | (fs_info->compress_level << 4), - inode->vfs_inode.i_mapping, start, + mapping, start, pages, &nr_pages, &total_in, @@ -793,9 +993,9 @@ cont: unsigned long clear_flags = EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING; - unsigned long page_error_op; - page_error_op = ret < 0 ? PAGE_SET_ERROR : 0; + if (ret < 0) + mapping_set_error(mapping, -EIO); /* * inline extent creation worked or returned error, @@ -812,7 +1012,6 @@ cont: clear_flags, PAGE_UNLOCK | PAGE_START_WRITEBACK | - page_error_op | PAGE_END_WRITEBACK); /* @@ -934,6 +1133,12 @@ static int submit_uncompressed_range(struct btrfs_inode *inode, unsigned long nr_written = 0; int page_started = 0; int ret; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .range_start = start, + .range_end = end, + .no_cgroup_owner = 1, + }; /* * Call cow_file_range() to run the delalloc range directly, since we @@ -954,8 +1159,6 @@ static int submit_uncompressed_range(struct btrfs_inode *inode, const u64 page_start = page_offset(locked_page); const u64 page_end = page_start + PAGE_SIZE - 1; - btrfs_page_set_error(inode->root->fs_info, locked_page, - page_start, PAGE_SIZE); set_page_writeback(locked_page); end_page_writeback(locked_page); end_extent_writepage(locked_page, ret, page_start, page_end); @@ -965,7 +1168,10 @@ static int submit_uncompressed_range(struct btrfs_inode *inode, } /* All pages will be unlocked, including @locked_page */ - return extent_write_locked_range(&inode->vfs_inode, start, end); + wbc_attach_fdatawrite_inode(&wbc, &inode->vfs_inode); + ret = extent_write_locked_range(&inode->vfs_inode, start, end, &wbc); + wbc_detach_inode(&wbc); + return ret; } static int submit_one_async_extent(struct btrfs_inode *inode, @@ -976,6 +1182,7 @@ static int submit_one_async_extent(struct btrfs_inode *inode, struct extent_io_tree *io_tree = &inode->io_tree; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ordered_extent *ordered; struct btrfs_key ins; struct page *locked_page = NULL; struct extent_map *em; @@ -1037,7 +1244,7 @@ static int submit_one_async_extent(struct btrfs_inode *inode, } free_extent_map(em); - ret = btrfs_add_ordered_extent(inode, start, /* file_offset */ + ordered = btrfs_alloc_ordered_extent(inode, start, /* file_offset */ async_extent->ram_size, /* num_bytes */ async_extent->ram_size, /* ram_bytes */ ins.objectid, /* disk_bytenr */ @@ -1045,8 +1252,9 @@ static int submit_one_async_extent(struct btrfs_inode *inode, 0, /* offset */ 1 << BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); - if (ret) { + if (IS_ERR(ordered)) { btrfs_drop_extent_map_range(inode, start, end, false); + ret = PTR_ERR(ordered); goto out_free_reserve; } btrfs_dec_block_group_reservations(fs_info, ins.objectid); @@ -1055,11 +1263,7 @@ static int submit_one_async_extent(struct btrfs_inode *inode, extent_clear_unlock_delalloc(inode, start, end, NULL, EXTENT_LOCKED | EXTENT_DELALLOC, PAGE_UNLOCK | PAGE_START_WRITEBACK); - - btrfs_submit_compressed_write(inode, start, /* file_offset */ - async_extent->ram_size, /* num_bytes */ - ins.objectid, /* disk_bytenr */ - ins.offset, /* compressed_len */ + btrfs_submit_compressed_write(ordered, async_extent->pages, /* compressed_pages */ async_extent->nr_pages, async_chunk->write_flags, true); @@ -1074,12 +1278,13 @@ out_free_reserve: btrfs_dec_block_group_reservations(fs_info, ins.objectid); btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1); out_free: + mapping_set_error(inode->vfs_inode.i_mapping, -EIO); extent_clear_unlock_delalloc(inode, start, end, NULL, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | PAGE_START_WRITEBACK | - PAGE_END_WRITEBACK | PAGE_SET_ERROR); + PAGE_END_WRITEBACK); free_async_extent_pages(async_extent); goto done; } @@ -1287,6 +1492,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, min_alloc_size = fs_info->sectorsize; while (num_bytes > 0) { + struct btrfs_ordered_extent *ordered; + cur_alloc_size = num_bytes; ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, min_alloc_size, 0, alloc_hint, @@ -1311,16 +1518,18 @@ static noinline int cow_file_range(struct btrfs_inode *inode, } free_extent_map(em); - ret = btrfs_add_ordered_extent(inode, start, ram_size, ram_size, - ins.objectid, cur_alloc_size, 0, - 1 << BTRFS_ORDERED_REGULAR, - BTRFS_COMPRESS_NONE); - if (ret) + ordered = btrfs_alloc_ordered_extent(inode, start, ram_size, + ram_size, ins.objectid, cur_alloc_size, + 0, 1 << BTRFS_ORDERED_REGULAR, + BTRFS_COMPRESS_NONE); + if (IS_ERR(ordered)) { + ret = PTR_ERR(ordered); goto out_drop_extent_cache; + } if (btrfs_is_data_reloc_root(root)) { - ret = btrfs_reloc_clone_csums(inode, start, - cur_alloc_size); + ret = btrfs_reloc_clone_csums(ordered); + /* * Only drop cache here, and process as normal. * @@ -1337,6 +1546,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, start + ram_size - 1, false); } + btrfs_put_ordered_extent(ordered); btrfs_dec_block_group_reservations(fs_info, ins.objectid); @@ -1494,7 +1704,7 @@ static noinline void async_cow_submit(struct btrfs_work *work) * ->inode could be NULL if async_chunk_start has failed to compress, * in which case we don't have anything to submit, yet we need to * always adjust ->async_delalloc_pages as its paired with the init - * happening in cow_file_range_async + * happening in run_delalloc_compressed */ if (async_chunk->inode) submit_compressed_extents(async_chunk); @@ -1521,58 +1731,36 @@ static noinline void async_cow_free(struct btrfs_work *work) kvfree(async_cow); } -static int cow_file_range_async(struct btrfs_inode *inode, - struct writeback_control *wbc, - struct page *locked_page, - u64 start, u64 end, int *page_started, - unsigned long *nr_written) +static bool run_delalloc_compressed(struct btrfs_inode *inode, + struct writeback_control *wbc, + struct page *locked_page, + u64 start, u64 end, int *page_started, + unsigned long *nr_written) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc); struct async_cow *ctx; struct async_chunk *async_chunk; unsigned long nr_pages; - u64 cur_end; u64 num_chunks = DIV_ROUND_UP(end - start, SZ_512K); int i; - bool should_compress; unsigned nofs_flag; const blk_opf_t write_flags = wbc_to_write_flags(wbc); - unlock_extent(&inode->io_tree, start, end, NULL); - - if (inode->flags & BTRFS_INODE_NOCOMPRESS && - !btrfs_test_opt(fs_info, FORCE_COMPRESS)) { - num_chunks = 1; - should_compress = false; - } else { - should_compress = true; - } - nofs_flag = memalloc_nofs_save(); ctx = kvmalloc(struct_size(ctx, chunks, num_chunks), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); + if (!ctx) + return false; - if (!ctx) { - unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | - EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | - EXTENT_DO_ACCOUNTING; - unsigned long page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | - PAGE_END_WRITEBACK | PAGE_SET_ERROR; - - extent_clear_unlock_delalloc(inode, start, end, locked_page, - clear_bits, page_ops); - return -ENOMEM; - } + unlock_extent(&inode->io_tree, start, end, NULL); + set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); async_chunk = ctx->chunks; atomic_set(&ctx->num_chunks, num_chunks); for (i = 0; i < num_chunks; i++) { - if (should_compress) - cur_end = min(end, start + SZ_512K - 1); - else - cur_end = end; + u64 cur_end = min(end, start + SZ_512K - 1); /* * igrab is called higher up in the call chain, take only the @@ -1633,13 +1821,14 @@ static int cow_file_range_async(struct btrfs_inode *inode, start = cur_end + 1; } *page_started = 1; - return 0; + return true; } static noinline int run_delalloc_zoned(struct btrfs_inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, - unsigned long *nr_written) + unsigned long *nr_written, + struct writeback_control *wbc) { u64 done_offset = end; int ret; @@ -1671,8 +1860,8 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode, account_page_redirty(locked_page); } locked_page_done = true; - extent_write_locked_range(&inode->vfs_inode, start, done_offset); - + extent_write_locked_range(&inode->vfs_inode, start, done_offset, + wbc); start = done_offset + 1; } @@ -1864,7 +2053,7 @@ static int can_nocow_file_extent(struct btrfs_path *path, ret = btrfs_cross_ref_exist(root, btrfs_ino(inode), key->offset - args->extent_offset, - args->disk_bytenr, false, path); + args->disk_bytenr, args->strict, path); WARN_ON_ONCE(ret > 0 && is_freespace_inode); if (ret != 0) goto out; @@ -1947,6 +2136,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, nocow_args.writeback_path = true; while (1) { + struct btrfs_ordered_extent *ordered; struct btrfs_key found_key; struct btrfs_file_extent_item *fi; struct extent_buffer *leaf; @@ -1954,6 +2144,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, u64 ram_bytes; u64 nocow_end; int extent_type; + bool is_prealloc; nocow = false; @@ -2092,8 +2283,8 @@ out_check: } nocow_end = cur_offset + nocow_args.num_bytes - 1; - - if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) { + is_prealloc = extent_type == BTRFS_FILE_EXTENT_PREALLOC; + if (is_prealloc) { u64 orig_start = found_key.offset - nocow_args.extent_offset; struct extent_map *em; @@ -2109,29 +2300,22 @@ out_check: goto error; } free_extent_map(em); - ret = btrfs_add_ordered_extent(inode, - cur_offset, nocow_args.num_bytes, - nocow_args.num_bytes, - nocow_args.disk_bytenr, - nocow_args.num_bytes, 0, - 1 << BTRFS_ORDERED_PREALLOC, - BTRFS_COMPRESS_NONE); - if (ret) { + } + + ordered = btrfs_alloc_ordered_extent(inode, cur_offset, + nocow_args.num_bytes, nocow_args.num_bytes, + nocow_args.disk_bytenr, nocow_args.num_bytes, 0, + is_prealloc + ? (1 << BTRFS_ORDERED_PREALLOC) + : (1 << BTRFS_ORDERED_NOCOW), + BTRFS_COMPRESS_NONE); + if (IS_ERR(ordered)) { + if (is_prealloc) { btrfs_drop_extent_map_range(inode, cur_offset, nocow_end, false); - goto error; } - } else { - ret = btrfs_add_ordered_extent(inode, cur_offset, - nocow_args.num_bytes, - nocow_args.num_bytes, - nocow_args.disk_bytenr, - nocow_args.num_bytes, - 0, - 1 << BTRFS_ORDERED_NOCOW, - BTRFS_COMPRESS_NONE); - if (ret) - goto error; + ret = PTR_ERR(ordered); + goto error; } if (nocow) { @@ -2145,8 +2329,8 @@ out_check: * extent_clear_unlock_delalloc() in error handler * from freeing metadata of created ordered extent. */ - ret = btrfs_reloc_clone_csums(inode, cur_offset, - nocow_args.num_bytes); + ret = btrfs_reloc_clone_csums(ordered); + btrfs_put_ordered_extent(ordered); extent_clear_unlock_delalloc(inode, cur_offset, nocow_end, locked_page, EXTENT_LOCKED | @@ -2214,7 +2398,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page u64 start, u64 end, int *page_started, unsigned long *nr_written, struct writeback_control *wbc) { - int ret; + int ret = 0; const bool zoned = btrfs_is_zoned(inode->root->fs_info); /* @@ -2235,19 +2419,23 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); - } else if (!btrfs_inode_can_compress(inode) || - !inode_need_compress(inode, start, end)) { - if (zoned) - ret = run_delalloc_zoned(inode, locked_page, start, end, - page_started, nr_written); - else - ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1, NULL); - } else { - set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); - ret = cow_file_range_async(inode, wbc, locked_page, start, end, - page_started, nr_written); + goto out; } + + if (btrfs_inode_can_compress(inode) && + inode_need_compress(inode, start, end) && + run_delalloc_compressed(inode, wbc, locked_page, start, + end, page_started, nr_written)) + goto out; + + if (zoned) + ret = run_delalloc_zoned(inode, locked_page, start, end, + page_started, nr_written, wbc); + else + ret = cow_file_range(inode, locked_page, start, end, + page_started, nr_written, 1, NULL); + +out: ASSERT(ret <= 0); if (ret) btrfs_cleanup_ordered_extents(inode, locked_page, start, @@ -2515,125 +2703,42 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode, } } -/* - * Split off the first pre bytes from the extent_map at [start, start + len] - * - * This function is intended to be used only for extract_ordered_extent(). - */ -static int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre) -{ - struct extent_map_tree *em_tree = &inode->extent_tree; - struct extent_map *em; - struct extent_map *split_pre = NULL; - struct extent_map *split_mid = NULL; - int ret = 0; - unsigned long flags; - - ASSERT(pre != 0); - ASSERT(pre < len); - - split_pre = alloc_extent_map(); - if (!split_pre) - return -ENOMEM; - split_mid = alloc_extent_map(); - if (!split_mid) { - ret = -ENOMEM; - goto out_free_pre; - } - - lock_extent(&inode->io_tree, start, start + len - 1, NULL); - write_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - if (!em) { - ret = -EIO; - goto out_unlock; - } - - ASSERT(em->len == len); - ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); - ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE); - ASSERT(test_bit(EXTENT_FLAG_PINNED, &em->flags)); - ASSERT(!test_bit(EXTENT_FLAG_LOGGING, &em->flags)); - ASSERT(!list_empty(&em->list)); - - flags = em->flags; - clear_bit(EXTENT_FLAG_PINNED, &em->flags); - - /* First, replace the em with a new extent_map starting from * em->start */ - split_pre->start = em->start; - split_pre->len = pre; - split_pre->orig_start = split_pre->start; - split_pre->block_start = em->block_start; - split_pre->block_len = split_pre->len; - split_pre->orig_block_len = split_pre->block_len; - split_pre->ram_bytes = split_pre->len; - split_pre->flags = flags; - split_pre->compress_type = em->compress_type; - split_pre->generation = em->generation; - - replace_extent_mapping(em_tree, em, split_pre, 1); - - /* - * Now we only have an extent_map at: - * [em->start, em->start + pre] - */ - - /* Insert the middle extent_map. */ - split_mid->start = em->start + pre; - split_mid->len = em->len - pre; - split_mid->orig_start = split_mid->start; - split_mid->block_start = em->block_start + pre; - split_mid->block_len = split_mid->len; - split_mid->orig_block_len = split_mid->block_len; - split_mid->ram_bytes = split_mid->len; - split_mid->flags = flags; - split_mid->compress_type = em->compress_type; - split_mid->generation = em->generation; - add_extent_mapping(em_tree, split_mid, 1); - - /* Once for us */ - free_extent_map(em); - /* Once for the tree */ - free_extent_map(em); - -out_unlock: - write_unlock(&em_tree->lock); - unlock_extent(&inode->io_tree, start, start + len - 1, NULL); - free_extent_map(split_mid); -out_free_pre: - free_extent_map(split_pre); - return ret; -} - -int btrfs_extract_ordered_extent(struct btrfs_bio *bbio, - struct btrfs_ordered_extent *ordered) +static int btrfs_extract_ordered_extent(struct btrfs_bio *bbio, + struct btrfs_ordered_extent *ordered) { u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; u64 len = bbio->bio.bi_iter.bi_size; - struct btrfs_inode *inode = bbio->inode; - u64 ordered_len = ordered->num_bytes; - int ret = 0; + struct btrfs_ordered_extent *new; + int ret; /* Must always be called for the beginning of an ordered extent. */ if (WARN_ON_ONCE(start != ordered->disk_bytenr)) return -EINVAL; /* No need to split if the ordered extent covers the entire bio. */ - if (ordered->disk_num_bytes == len) + if (ordered->disk_num_bytes == len) { + refcount_inc(&ordered->refs); + bbio->ordered = ordered; return 0; - - ret = btrfs_split_ordered_extent(ordered, len); - if (ret) - return ret; + } /* * Don't split the extent_map for NOCOW extents, as we're writing into * a pre-existing one. */ - if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) - return 0; + if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) { + ret = split_extent_map(bbio->inode, bbio->file_offset, + ordered->num_bytes, len, + ordered->disk_bytenr); + if (ret) + return ret; + } - return split_extent_map(inode, bbio->file_offset, ordered_len, len); + new = btrfs_split_ordered_extent(ordered, len); + if (IS_ERR(new)) + return PTR_ERR(new); + bbio->ordered = new; + return 0; } /* @@ -2651,7 +2756,7 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, trans->adding_csums = true; if (!csum_root) csum_root = btrfs_csum_root(trans->fs_info, - sum->bytenr); + sum->logical); ret = btrfs_csum_file_blocks(trans, csum_root, sum); trans->adding_csums = false; if (ret) @@ -2689,8 +2794,7 @@ static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, ret = set_extent_bit(&inode->io_tree, search_start, search_start + em_len - 1, - EXTENT_DELALLOC_NEW, cached_state, - GFP_NOFS); + EXTENT_DELALLOC_NEW, cached_state); next: search_start = extent_map_end(em); free_extent_map(em); @@ -2723,8 +2827,8 @@ int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, return ret; } - return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, - cached_state); + return set_extent_bit(&inode->io_tree, start, end, + EXTENT_DELALLOC | extra_bits, cached_state); } /* see btrfs_writepage_start_hook for details on why this is required */ @@ -2847,7 +2951,6 @@ out_page: mapping_set_error(page->mapping, ret); end_extent_writepage(page, ret, page_start, page_end); clear_page_dirty_for_io(page); - SetPageError(page); } btrfs_page_clear_checked(inode->root->fs_info, page, page_start, PAGE_SIZE); unlock_page(page); @@ -3068,7 +3171,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans, * an ordered extent if the range of bytes in the file it covers are * fully written. */ -int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) +int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent) { struct btrfs_inode *inode = BTRFS_I(ordered_extent->inode); struct btrfs_root *root = inode->root; @@ -3103,15 +3206,9 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } - /* A valid ->physical implies a write on a sequential zone. */ - if (ordered_extent->physical != (u64)-1) { - btrfs_rewrite_logical_zoned(ordered_extent); - btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, - ordered_extent->disk_num_bytes); - } else if (btrfs_is_data_reloc_root(inode->root)) { + if (btrfs_is_zoned(fs_info)) btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, ordered_extent->disk_num_bytes); - } if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { truncated = true; @@ -3279,6 +3376,14 @@ out: return ret; } +int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered) +{ + if (btrfs_is_zoned(btrfs_sb(ordered->inode->i_sb)) && + !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) + btrfs_finish_ordered_zoned(ordered); + return btrfs_finish_one_ordered(ordered); +} + void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode, struct page *page, u64 start, u64 end, bool uptodate) @@ -4226,7 +4331,7 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry) } btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), - 0); + false); ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)), &fname.disk_name); @@ -4801,7 +4906,7 @@ again: if (only_release_metadata) set_extent_bit(&inode->io_tree, block_start, block_end, - EXTENT_NORESERVE, NULL, GFP_NOFS); + EXTENT_NORESERVE, NULL); out_unlock: if (ret) { @@ -7264,7 +7369,7 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start, static int btrfs_get_blocks_direct_write(struct extent_map **map, struct inode *inode, struct btrfs_dio_data *dio_data, - u64 start, u64 len, + u64 start, u64 *lenp, unsigned int iomap_flags) { const bool nowait = (iomap_flags & IOMAP_NOWAIT); @@ -7275,6 +7380,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, struct btrfs_block_group *bg; bool can_nocow = false; bool space_reserved = false; + u64 len = *lenp; u64 prev_len; int ret = 0; @@ -7345,15 +7451,19 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, free_extent_map(em); *map = NULL; - if (nowait) - return -EAGAIN; + if (nowait) { + ret = -EAGAIN; + goto out; + } /* * If we could not allocate data space before locking the file * range and we can't do a NOCOW write, then we have to fail. */ - if (!dio_data->data_space_reserved) - return -ENOSPC; + if (!dio_data->data_space_reserved) { + ret = -ENOSPC; + goto out; + } /* * We have to COW and we have already reserved data space before, @@ -7394,6 +7504,7 @@ out: btrfs_delalloc_release_extents(BTRFS_I(inode), len); btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true); } + *lenp = len; return ret; } @@ -7570,7 +7681,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (write) { ret = btrfs_get_blocks_direct_write(&em, inode, dio_data, - start, len, flags); + start, &len, flags); if (ret < 0) goto unlock_err; unlock_extents = true; @@ -7664,8 +7775,8 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, pos += submitted; length -= submitted; if (write) - btrfs_mark_ordered_io_finished(BTRFS_I(inode), NULL, - pos, length, false); + btrfs_finish_ordered_extent(dio_data->ordered, NULL, + pos, length, false); else unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1, NULL); @@ -7695,12 +7806,14 @@ static void btrfs_dio_end_io(struct btrfs_bio *bbio) dip->file_offset, dip->bytes, bio->bi_status); } - if (btrfs_op(bio) == BTRFS_MAP_WRITE) - btrfs_mark_ordered_io_finished(inode, NULL, dip->file_offset, - dip->bytes, !bio->bi_status); - else + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { + btrfs_finish_ordered_extent(bbio->ordered, NULL, + dip->file_offset, dip->bytes, + !bio->bi_status); + } else { unlock_extent(&inode->io_tree, dip->file_offset, dip->file_offset + dip->bytes - 1, NULL); + } bbio->bio.bi_private = bbio->private; iomap_dio_bio_end_io(bio); @@ -7736,7 +7849,8 @@ static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio, ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered); if (ret) { - btrfs_bio_end_io(bbio, errno_to_blk_status(ret)); + bbio->bio.bi_status = errno_to_blk_status(ret); + btrfs_dio_end_io(bbio); return; } } @@ -8230,7 +8344,7 @@ static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback) int ret; struct btrfs_trans_handle *trans; u64 mask = fs_info->sectorsize - 1; - u64 min_size = btrfs_calc_metadata_size(fs_info, 1); + const u64 min_size = btrfs_calc_metadata_size(fs_info, 1); if (!skip_writeback) { ret = btrfs_wait_ordered_range(&inode->vfs_inode, @@ -8287,7 +8401,15 @@ static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback) /* Migrate the slack space for the truncate to our reserve */ ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); - BUG_ON(ret); + /* + * We have reserved 2 metadata units when we started the transaction and + * min_size matches 1 unit, so this should never fail, but if it does, + * it's not critical we just fail truncation. + */ + if (WARN_ON(ret)) { + btrfs_end_transaction(trans); + goto out; + } trans->block_rsv = rsv; @@ -8335,7 +8457,14 @@ static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback) btrfs_block_rsv_release(fs_info, rsv, -1, NULL); ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv, min_size, false); - BUG_ON(ret); /* shouldn't happen */ + /* + * We have reserved 2 metadata units when we started the + * transaction and min_size matches 1 unit, so this should never + * fail, but if it does, it's not critical we just fail truncation. + */ + if (WARN_ON(ret)) + break; + trans->block_rsv = rsv; } @@ -8462,7 +8591,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->io_tree.inode = ei; extent_io_tree_init(fs_info, &ei->file_extent_tree, IO_TREE_INODE_FILE_EXTENT); - atomic_set(&ei->sync_writers, 0); mutex_init(&ei->log_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->delalloc_inodes); @@ -8633,7 +8761,7 @@ static int btrfs_getattr(struct mnt_idmap *idmap, inode_bytes = inode_get_bytes(inode); spin_unlock(&BTRFS_I(inode)->lock); stat->blocks = (ALIGN(inode_bytes, blocksize) + - ALIGN(delalloc_bytes, blocksize)) >> 9; + ALIGN(delalloc_bytes, blocksize)) >> SECTOR_SHIFT; return 0; } @@ -8789,9 +8917,9 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (old_dentry->d_parent != new_dentry->d_parent) { btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), - BTRFS_I(old_inode), 1); + BTRFS_I(old_inode), true); btrfs_record_unlink_dir(trans, BTRFS_I(new_dir), - BTRFS_I(new_inode), 1); + BTRFS_I(new_inode), true); } /* src is a subvolume */ @@ -9057,7 +9185,7 @@ static int btrfs_rename(struct mnt_idmap *idmap, if (old_dentry->d_parent != new_dentry->d_parent) btrfs_record_unlink_dir(trans, BTRFS_I(old_dir), - BTRFS_I(old_inode), 1); + BTRFS_I(old_inode), true); if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry); @@ -10164,6 +10292,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, struct extent_io_tree *io_tree = &inode->io_tree; struct extent_changeset *data_reserved = NULL; struct extent_state *cached_state = NULL; + struct btrfs_ordered_extent *ordered; int compression; size_t orig_count; u64 start, end; @@ -10340,14 +10469,15 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, } free_extent_map(em); - ret = btrfs_add_ordered_extent(inode, start, num_bytes, ram_bytes, + ordered = btrfs_alloc_ordered_extent(inode, start, num_bytes, ram_bytes, ins.objectid, ins.offset, encoded->unencoded_offset, (1 << BTRFS_ORDERED_ENCODED) | (1 << BTRFS_ORDERED_COMPRESSED), compression); - if (ret) { + if (IS_ERR(ordered)) { btrfs_drop_extent_map_range(inode, start, end, false); + ret = PTR_ERR(ordered); goto out_free_reserved; } btrfs_dec_block_group_reservations(fs_info, ins.objectid); @@ -10359,8 +10489,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, btrfs_delalloc_release_extents(inode, num_bytes); - btrfs_submit_compressed_write(inode, start, num_bytes, ins.objectid, - ins.offset, pages, nr_pages, 0, false); + btrfs_submit_compressed_write(ordered, pages, nr_pages, 0, false); ret = orig_count; goto out; @@ -10897,7 +11026,6 @@ static const struct address_space_operations btrfs_aops = { .read_folio = btrfs_read_folio, .writepages = btrfs_writepages, .readahead = btrfs_readahead, - .direct_IO = noop_direct_IO, .invalidate_folio = btrfs_invalidate_folio, .release_folio = btrfs_release_folio, .migrate_folio = btrfs_migrate_folio, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2fa36f694daa..a895d105464b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -649,6 +649,8 @@ static noinline int create_subvol(struct mnt_idmap *idmap, } trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; + /* Tree log can't currently deal with an inode which is a new root. */ + btrfs_set_log_full_commit(trans); ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit); if (ret) @@ -757,10 +759,7 @@ out: trans->bytes_reserved = 0; btrfs_subvolume_release_metadata(root, &block_rsv); - if (ret) - btrfs_end_transaction(trans); - else - ret = btrfs_commit_transaction(trans); + btrfs_end_transaction(trans); out_new_inode_args: btrfs_new_inode_args_destroy(&new_inode_args); out_inode: @@ -2672,7 +2671,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args_v2 *vol_args; struct block_device *bdev = NULL; - fmode_t mode; + void *holder; int ret; bool cancel = false; @@ -2709,7 +2708,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto err_drop; /* Exclusive operation is now claimed */ - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); btrfs_exclop_finish(fs_info); @@ -2724,7 +2723,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) err_drop: mnt_drop_write_file(file); if (bdev) - blkdev_put(bdev, mode); + blkdev_put(bdev, holder); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -2738,7 +2737,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args *vol_args; struct block_device *bdev = NULL; - fmode_t mode; + void *holder; int ret; bool cancel = false; @@ -2765,7 +2764,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, cancel); if (ret == 0) { - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); if (!ret) btrfs_info(fs_info, "disk deleted %s", vol_args->name); btrfs_exclop_finish(fs_info); @@ -2773,7 +2772,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) mnt_drop_write_file(file); if (bdev) - blkdev_put(bdev, mode); + blkdev_put(bdev, holder); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -3113,6 +3112,13 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root, struct btrfs_trans_handle *trans; u64 transid; + /* + * Start orphan cleanup here for the given root in case it hasn't been + * started already by other means. Errors are handled in the other + * functions during transaction commit. + */ + btrfs_orphan_cleanup(root); + trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT) @@ -3134,14 +3140,13 @@ out: static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info, void __user *argp) { - u64 transid; + /* By default wait for the current transaction. */ + u64 transid = 0; - if (argp) { + if (argp) if (copy_from_user(&transid, argp, sizeof(transid))) return -EFAULT; - } else { - transid = 0; /* current trans */ - } + return btrfs_wait_for_commit(fs_info, transid); } diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 3a496b0d3d2b..7979449a58d6 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -57,8 +57,8 @@ static struct btrfs_lockdep_keyset { u64 id; /* root objectid */ - /* Longest entry: btrfs-free-space-00 */ - char names[BTRFS_MAX_LEVEL][20]; + /* Longest entry: btrfs-block-group-00 */ + char names[BTRFS_MAX_LEVEL][24]; struct lock_class_key keys[BTRFS_MAX_LEVEL]; } btrfs_lockdep_keysets[] = { { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, @@ -72,6 +72,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, + { .id = BTRFS_BLOCK_GROUP_TREE_OBJECTID, DEFINE_NAME("block-group") }, { .id = 0, DEFINE_NAME("tree") }, }; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 3a095b9c6373..d3fcfc628a4f 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -88,9 +88,9 @@ struct list_head *lzo_alloc_workspace(unsigned int level) if (!workspace) return ERR_PTR(-ENOMEM); - workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); - workspace->buf = kvmalloc(WORKSPACE_BUF_LENGTH, GFP_KERNEL); - workspace->cbuf = kvmalloc(WORKSPACE_CBUF_LENGTH, GFP_KERNEL); + workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL | __GFP_NOWARN); + workspace->buf = kvmalloc(WORKSPACE_BUF_LENGTH, GFP_KERNEL | __GFP_NOWARN); + workspace->cbuf = kvmalloc(WORKSPACE_CBUF_LENGTH, GFP_KERNEL | __GFP_NOWARN); if (!workspace->mem || !workspace->buf || !workspace->cbuf) goto fail; diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c index 310a05cf95ef..23fc11af498a 100644 --- a/fs/btrfs/messages.c +++ b/fs/btrfs/messages.c @@ -252,14 +252,6 @@ void __cold _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, } #endif -#ifdef CONFIG_BTRFS_ASSERT -void __cold __noreturn btrfs_assertfail(const char *expr, const char *file, int line) -{ - pr_err("assertion failed: %s, in %s:%d\n", expr, file, line); - BUG(); -} -#endif - void __cold btrfs_print_v0_err(struct btrfs_fs_info *fs_info) { btrfs_err(fs_info, diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h index ac2d1982ba3d..deedc1a168e2 100644 --- a/fs/btrfs/messages.h +++ b/fs/btrfs/messages.h @@ -4,14 +4,23 @@ #define BTRFS_MESSAGES_H #include <linux/types.h> +#include <linux/printk.h> +#include <linux/bug.h> struct btrfs_fs_info; +/* + * We want to be able to override this in btrfs-progs. + */ +#ifdef __KERNEL__ + static inline __printf(2, 3) __cold void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...) { } +#endif + #ifdef CONFIG_PRINTK #define btrfs_printk(fs_info, fmt, args...) \ @@ -160,7 +169,11 @@ do { \ } while (0) #ifdef CONFIG_BTRFS_ASSERT -void __cold __noreturn btrfs_assertfail(const char *expr, const char *file, int line); + +#define btrfs_assertfail(expr, file, line) ({ \ + pr_err("assertion failed: %s, in %s:%d\n", (expr), (file), (line)); \ + BUG(); \ +}) #define ASSERT(expr) \ (likely(expr) ? (void)0 : btrfs_assertfail(#expr, __FILE__, __LINE__)) diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h index 768583a440e1..005751a12911 100644 --- a/fs/btrfs/misc.h +++ b/fs/btrfs/misc.h @@ -143,4 +143,24 @@ static inline struct rb_node *rb_simple_insert(struct rb_root *root, u64 bytenr, return NULL; } +static inline bool bitmap_test_range_all_set(const unsigned long *addr, + unsigned long start, + unsigned long nbits) +{ + unsigned long found_zero; + + found_zero = find_next_zero_bit(addr, start + nbits, start); + return (found_zero == start + nbits); +} + +static inline bool bitmap_test_range_all_zero(const unsigned long *addr, + unsigned long start, + unsigned long nbits) +{ + unsigned long found_set; + + found_set = find_next_bit(addr, start + nbits, start); + return (found_set == start + nbits); +} + #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index a9778a91511e..a629532283bc 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -146,35 +146,11 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree, return ret; } -/* - * Add an ordered extent to the per-inode tree. - * - * @inode: Inode that this extent is for. - * @file_offset: Logical offset in file where the extent starts. - * @num_bytes: Logical length of extent in file. - * @ram_bytes: Full length of unencoded data. - * @disk_bytenr: Offset of extent on disk. - * @disk_num_bytes: Size of extent on disk. - * @offset: Offset into unencoded data where file data starts. - * @flags: Flags specifying type of extent (1 << BTRFS_ORDERED_*). - * @compress_type: Compression algorithm used for data. - * - * Most of these parameters correspond to &struct btrfs_file_extent_item. The - * tree is given a single reference on the ordered extent that was inserted, and - * the returned pointer is given a second reference. - * - * Return: the new ordered extent or error pointer. - */ -struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( - struct btrfs_inode *inode, u64 file_offset, - u64 num_bytes, u64 ram_bytes, u64 disk_bytenr, - u64 disk_num_bytes, u64 offset, unsigned long flags, - int compress_type) +static struct btrfs_ordered_extent *alloc_ordered_extent( + struct btrfs_inode *inode, u64 file_offset, u64 num_bytes, + u64 ram_bytes, u64 disk_bytenr, u64 disk_num_bytes, + u64 offset, unsigned long flags, int compress_type) { - struct btrfs_root *root = inode->root; - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; - struct rb_node *node; struct btrfs_ordered_extent *entry; int ret; @@ -184,7 +160,6 @@ struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); if (ret < 0) return ERR_PTR(ret); - ret = 0; } else { /* * The ordered extent has reserved qgroup space, release now @@ -209,15 +184,7 @@ struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( entry->compress_type = compress_type; entry->truncated_len = (u64)-1; entry->qgroup_rsv = ret; - entry->physical = (u64)-1; - - ASSERT((flags & ~BTRFS_ORDERED_TYPE_FLAGS) == 0); entry->flags = flags; - - percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes, - fs_info->delalloc_batch); - - /* one ref for the tree */ refcount_set(&entry->refs, 1); init_waitqueue_head(&entry->wait); INIT_LIST_HEAD(&entry->list); @@ -226,15 +193,40 @@ struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( INIT_LIST_HEAD(&entry->work_list); init_completion(&entry->completion); + /* + * We don't need the count_max_extents here, we can assume that all of + * that work has been done at higher layers, so this is truly the + * smallest the extent is going to get. + */ + spin_lock(&inode->lock); + btrfs_mod_outstanding_extents(inode, 1); + spin_unlock(&inode->lock); + + return entry; +} + +static void insert_ordered_extent(struct btrfs_ordered_extent *entry) +{ + struct btrfs_inode *inode = BTRFS_I(entry->inode); + struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; + struct rb_node *node; + trace_btrfs_ordered_extent_add(inode, entry); + percpu_counter_add_batch(&fs_info->ordered_bytes, entry->num_bytes, + fs_info->delalloc_batch); + + /* One ref for the tree. */ + refcount_inc(&entry->refs); + spin_lock_irq(&tree->lock); - node = tree_insert(&tree->tree, file_offset, - &entry->rb_node); + node = tree_insert(&tree->tree, entry->file_offset, &entry->rb_node); if (node) btrfs_panic(fs_info, -EEXIST, "inconsistency in ordered tree at offset %llu", - file_offset); + entry->file_offset); spin_unlock_irq(&tree->lock); spin_lock(&root->ordered_extent_lock); @@ -248,43 +240,43 @@ struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( spin_unlock(&fs_info->ordered_root_lock); } spin_unlock(&root->ordered_extent_lock); - - /* - * We don't need the count_max_extents here, we can assume that all of - * that work has been done at higher layers, so this is truly the - * smallest the extent is going to get. - */ - spin_lock(&inode->lock); - btrfs_mod_outstanding_extents(inode, 1); - spin_unlock(&inode->lock); - - /* One ref for the returned entry to match semantics of lookup. */ - refcount_inc(&entry->refs); - - return entry; } /* - * Add a new btrfs_ordered_extent for the range, but drop the reference instead - * of returning it to the caller. + * Add an ordered extent to the per-inode tree. + * + * @inode: Inode that this extent is for. + * @file_offset: Logical offset in file where the extent starts. + * @num_bytes: Logical length of extent in file. + * @ram_bytes: Full length of unencoded data. + * @disk_bytenr: Offset of extent on disk. + * @disk_num_bytes: Size of extent on disk. + * @offset: Offset into unencoded data where file data starts. + * @flags: Flags specifying type of extent (1 << BTRFS_ORDERED_*). + * @compress_type: Compression algorithm used for data. + * + * Most of these parameters correspond to &struct btrfs_file_extent_item. The + * tree is given a single reference on the ordered extent that was inserted, and + * the returned pointer is given a second reference. + * + * Return: the new ordered extent or error pointer. */ -int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, - u64 num_bytes, u64 ram_bytes, u64 disk_bytenr, - u64 disk_num_bytes, u64 offset, unsigned long flags, - int compress_type) +struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( + struct btrfs_inode *inode, u64 file_offset, + u64 num_bytes, u64 ram_bytes, u64 disk_bytenr, + u64 disk_num_bytes, u64 offset, unsigned long flags, + int compress_type) { - struct btrfs_ordered_extent *ordered; - - ordered = btrfs_alloc_ordered_extent(inode, file_offset, num_bytes, - ram_bytes, disk_bytenr, - disk_num_bytes, offset, flags, - compress_type); + struct btrfs_ordered_extent *entry; - if (IS_ERR(ordered)) - return PTR_ERR(ordered); - btrfs_put_ordered_extent(ordered); + ASSERT((flags & ~BTRFS_ORDERED_TYPE_FLAGS) == 0); - return 0; + entry = alloc_ordered_extent(inode, file_offset, num_bytes, ram_bytes, + disk_bytenr, disk_num_bytes, offset, flags, + compress_type); + if (!IS_ERR(entry)) + insert_ordered_extent(entry); + return entry; } /* @@ -311,6 +303,90 @@ static void finish_ordered_fn(struct btrfs_work *work) btrfs_finish_ordered_io(ordered_extent); } +static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered, + struct page *page, u64 file_offset, + u64 len, bool uptodate) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + + lockdep_assert_held(&inode->ordered_tree.lock); + + if (page) { + ASSERT(page->mapping); + ASSERT(page_offset(page) <= file_offset); + ASSERT(file_offset + len <= page_offset(page) + PAGE_SIZE); + + /* + * Ordered (Private2) bit indicates whether we still have + * pending io unfinished for the ordered extent. + * + * If there's no such bit, we need to skip to next range. + */ + if (!btrfs_page_test_ordered(fs_info, page, file_offset, len)) + return false; + btrfs_page_clear_ordered(fs_info, page, file_offset, len); + } + + /* Now we're fine to update the accounting. */ + if (WARN_ON_ONCE(len > ordered->bytes_left)) { + btrfs_crit(fs_info, +"bad ordered extent accounting, root=%llu ino=%llu OE offset=%llu OE len=%llu to_dec=%llu left=%llu", + inode->root->root_key.objectid, btrfs_ino(inode), + ordered->file_offset, ordered->num_bytes, + len, ordered->bytes_left); + ordered->bytes_left = 0; + } else { + ordered->bytes_left -= len; + } + + if (!uptodate) + set_bit(BTRFS_ORDERED_IOERR, &ordered->flags); + + if (ordered->bytes_left) + return false; + + /* + * All the IO of the ordered extent is finished, we need to queue + * the finish_func to be executed. + */ + set_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags); + cond_wake_up(&ordered->wait); + refcount_inc(&ordered->refs); + trace_btrfs_ordered_extent_mark_finished(inode, ordered); + return true; +} + +static void btrfs_queue_ordered_fn(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_workqueue *wq = btrfs_is_free_space_inode(inode) ? + fs_info->endio_freespace_worker : fs_info->endio_write_workers; + + btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL); + btrfs_queue_work(wq, &ordered->work); +} + +bool btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, + struct page *page, u64 file_offset, u64 len, + bool uptodate) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + unsigned long flags; + bool ret; + + trace_btrfs_finish_ordered_extent(inode, file_offset, len, uptodate); + + spin_lock_irqsave(&inode->ordered_tree.lock, flags); + ret = can_finish_ordered_extent(ordered, page, file_offset, len, uptodate); + spin_unlock_irqrestore(&inode->ordered_tree.lock, flags); + + if (ret) + btrfs_queue_ordered_fn(ordered); + return ret; +} + /* * Mark all ordered extents io inside the specified range finished. * @@ -329,22 +405,11 @@ void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, u64 num_bytes, bool uptodate) { struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; - struct btrfs_fs_info *fs_info = inode->root->fs_info; - struct btrfs_workqueue *wq; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; unsigned long flags; u64 cur = file_offset; - if (btrfs_is_free_space_inode(inode)) - wq = fs_info->endio_freespace_worker; - else - wq = fs_info->endio_write_workers; - - if (page) - ASSERT(page->mapping && page_offset(page) <= file_offset && - file_offset + num_bytes <= page_offset(page) + PAGE_SIZE); - spin_lock_irqsave(&tree->lock, flags); while (cur < file_offset + num_bytes) { u64 entry_end; @@ -397,50 +462,9 @@ void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, ASSERT(end + 1 - cur < U32_MAX); len = end + 1 - cur; - if (page) { - /* - * Ordered (Private2) bit indicates whether we still - * have pending io unfinished for the ordered extent. - * - * If there's no such bit, we need to skip to next range. - */ - if (!btrfs_page_test_ordered(fs_info, page, cur, len)) { - cur += len; - continue; - } - btrfs_page_clear_ordered(fs_info, page, cur, len); - } - - /* Now we're fine to update the accounting */ - if (unlikely(len > entry->bytes_left)) { - WARN_ON(1); - btrfs_crit(fs_info, -"bad ordered extent accounting, root=%llu ino=%llu OE offset=%llu OE len=%llu to_dec=%u left=%llu", - inode->root->root_key.objectid, - btrfs_ino(inode), - entry->file_offset, - entry->num_bytes, - len, entry->bytes_left); - entry->bytes_left = 0; - } else { - entry->bytes_left -= len; - } - - if (!uptodate) - set_bit(BTRFS_ORDERED_IOERR, &entry->flags); - - /* - * All the IO of the ordered extent is finished, we need to queue - * the finish_func to be executed. - */ - if (entry->bytes_left == 0) { - set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); - cond_wake_up(&entry->wait); - refcount_inc(&entry->refs); - trace_btrfs_ordered_extent_mark_finished(inode, entry); + if (can_finish_ordered_extent(entry, page, cur, len, uptodate)) { spin_unlock_irqrestore(&tree->lock, flags); - btrfs_init_work(&entry->work, finish_ordered_fn, NULL, NULL); - btrfs_queue_work(wq, &entry->work); + btrfs_queue_ordered_fn(entry); spin_lock_irqsave(&tree->lock, flags); } cur += len; @@ -564,7 +588,7 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, freespace_inode = btrfs_is_free_space_inode(btrfs_inode); btrfs_lockdep_acquire(fs_info, btrfs_trans_pending_ordered); - /* This is paired with btrfs_add_ordered_extent. */ + /* This is paired with btrfs_alloc_ordered_extent. */ spin_lock(&btrfs_inode->lock); btrfs_mod_outstanding_extents(btrfs_inode, -1); spin_unlock(&btrfs_inode->lock); @@ -1117,17 +1141,22 @@ bool btrfs_try_lock_ordered_range(struct btrfs_inode *inode, u64 start, u64 end, } /* Split out a new ordered extent for this first @len bytes of @ordered. */ -int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 len) +struct btrfs_ordered_extent *btrfs_split_ordered_extent( + struct btrfs_ordered_extent *ordered, u64 len) { - struct inode *inode = ordered->inode; - struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; u64 file_offset = ordered->file_offset; u64 disk_bytenr = ordered->disk_bytenr; - unsigned long flags = ordered->flags & BTRFS_ORDERED_TYPE_FLAGS; + unsigned long flags = ordered->flags; + struct btrfs_ordered_sum *sum, *tmpsum; + struct btrfs_ordered_extent *new; struct rb_node *node; + u64 offset = 0; - trace_btrfs_ordered_extent_split(BTRFS_I(inode), ordered); + trace_btrfs_ordered_extent_split(inode, ordered); ASSERT(!(flags & (1U << BTRFS_ORDERED_COMPRESSED))); @@ -1136,18 +1165,27 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 len) * reduce the original extent to a zero length either. */ if (WARN_ON_ONCE(len >= ordered->num_bytes)) - return -EINVAL; - /* We cannot split once ordered extent is past end_bio. */ - if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) - return -EINVAL; + return ERR_PTR(-EINVAL); + /* We cannot split partially completed ordered extents. */ + if (ordered->bytes_left) { + ASSERT(!(flags & ~BTRFS_ORDERED_TYPE_FLAGS)); + if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) + return ERR_PTR(-EINVAL); + } /* We cannot split a compressed ordered extent. */ if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) - return -EINVAL; - /* Checksum list should be empty. */ - if (WARN_ON_ONCE(!list_empty(&ordered->list))) - return -EINVAL; + return ERR_PTR(-EINVAL); - spin_lock_irq(&tree->lock); + new = alloc_ordered_extent(inode, file_offset, len, len, disk_bytenr, + len, 0, flags, ordered->compress_type); + if (IS_ERR(new)) + return new; + + /* One ref for the tree. */ + refcount_inc(&new->refs); + + spin_lock_irq(&root->ordered_extent_lock); + spin_lock(&tree->lock); /* Remove from tree once */ node = &ordered->rb_node; rb_erase(node, &tree->tree); @@ -1159,26 +1197,48 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 len) ordered->disk_bytenr += len; ordered->num_bytes -= len; ordered->disk_num_bytes -= len; - ordered->bytes_left -= len; + + if (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)) { + ASSERT(ordered->bytes_left == 0); + new->bytes_left = 0; + } else { + ordered->bytes_left -= len; + } + + if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags)) { + if (ordered->truncated_len > len) { + ordered->truncated_len -= len; + } else { + new->truncated_len = ordered->truncated_len; + ordered->truncated_len = 0; + } + } + + list_for_each_entry_safe(sum, tmpsum, &ordered->list, list) { + if (offset == len) + break; + list_move_tail(&sum->list, &new->list); + offset += sum->len; + } /* Re-insert the node */ node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node); if (node) btrfs_panic(fs_info, -EEXIST, "zoned: inconsistency in ordered tree at offset %llu", - ordered->file_offset); + ordered->file_offset); - spin_unlock_irq(&tree->lock); - - /* - * The splitting extent is already counted and will be added again in - * btrfs_add_ordered_extent(). Subtract len to avoid double counting. - */ - percpu_counter_add_batch(&fs_info->ordered_bytes, -len, fs_info->delalloc_batch); + node = tree_insert(&tree->tree, new->file_offset, &new->rb_node); + if (node) + btrfs_panic(fs_info, -EEXIST, + "zoned: inconsistency in ordered tree at offset %llu", + new->file_offset); + spin_unlock(&tree->lock); - return btrfs_add_ordered_extent(BTRFS_I(inode), file_offset, len, len, - disk_bytenr, len, 0, flags, - ordered->compress_type); + list_add_tail(&new->root_extent_list, &root->ordered_extents); + root->nr_ordered_extents++; + spin_unlock_irq(&root->ordered_extent_lock); + return new; } int __init ordered_data_init(void) diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index f0f1138d23c3..173bd5c5df26 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -14,13 +14,13 @@ struct btrfs_ordered_inode_tree { }; struct btrfs_ordered_sum { - /* bytenr is the start of this extent on disk */ - u64 bytenr; - /* - * this is the length in bytes covered by the sums array below. + * Logical start address and length for of the blocks covered by + * the sums array. */ - int len; + u64 logical; + u32 len; + struct list_head list; /* last field is a variable length array of csums */ u8 sums[]; @@ -151,12 +151,6 @@ struct btrfs_ordered_extent { struct completion completion; struct btrfs_work flush_work; struct list_head work_list; - - /* - * Used to reverse-map physical address returned from ZONE_APPEND write - * command in a workqueue context - */ - u64 physical; }; static inline void @@ -167,11 +161,15 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t) t->last = NULL; } +int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent); int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent); void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry); void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, struct btrfs_ordered_extent *entry); +bool btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, + struct page *page, u64 file_offset, u64 len, + bool uptodate); void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, struct page *page, u64 file_offset, u64 num_bytes, bool uptodate); @@ -183,10 +181,6 @@ struct btrfs_ordered_extent *btrfs_alloc_ordered_extent( u64 num_bytes, u64 ram_bytes, u64 disk_bytenr, u64 disk_num_bytes, u64 offset, unsigned long flags, int compress_type); -int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, - u64 num_bytes, u64 ram_bytes, u64 disk_bytenr, - u64 disk_num_bytes, u64 offset, unsigned long flags, - int compress_type); void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, @@ -212,7 +206,8 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, struct extent_state **cached_state); bool btrfs_try_lock_ordered_range(struct btrfs_inode *inode, u64 start, u64 end, struct extent_state **cached_state); -int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 len); +struct btrfs_ordered_extent *btrfs_split_ordered_extent( + struct btrfs_ordered_extent *ordered, u64 len); int __init ordered_data_init(void); void __cold ordered_data_exit(void); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 497b9dbd8a13..aa06d9ca911d 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -49,7 +49,7 @@ const char *btrfs_root_name(const struct btrfs_key *key, char *buf) return buf; } -static void print_chunk(struct extent_buffer *eb, struct btrfs_chunk *chunk) +static void print_chunk(const struct extent_buffer *eb, struct btrfs_chunk *chunk) { int num_stripes = btrfs_chunk_num_stripes(eb, chunk); int i; @@ -62,7 +62,7 @@ static void print_chunk(struct extent_buffer *eb, struct btrfs_chunk *chunk) btrfs_stripe_offset_nr(eb, chunk, i)); } } -static void print_dev_item(struct extent_buffer *eb, +static void print_dev_item(const struct extent_buffer *eb, struct btrfs_dev_item *dev_item) { pr_info("\t\tdev item devid %llu total_bytes %llu bytes used %llu\n", @@ -70,7 +70,7 @@ static void print_dev_item(struct extent_buffer *eb, btrfs_device_total_bytes(eb, dev_item), btrfs_device_bytes_used(eb, dev_item)); } -static void print_extent_data_ref(struct extent_buffer *eb, +static void print_extent_data_ref(const struct extent_buffer *eb, struct btrfs_extent_data_ref *ref) { pr_cont("extent data backref root %llu objectid %llu offset %llu count %u\n", @@ -80,7 +80,7 @@ static void print_extent_data_ref(struct extent_buffer *eb, btrfs_extent_data_ref_count(eb, ref)); } -static void print_extent_item(struct extent_buffer *eb, int slot, int type) +static void print_extent_item(const struct extent_buffer *eb, int slot, int type) { struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; @@ -169,7 +169,7 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) WARN_ON(ptr > end); } -static void print_uuid_item(struct extent_buffer *l, unsigned long offset, +static void print_uuid_item(const struct extent_buffer *l, unsigned long offset, u32 item_size) { if (!IS_ALIGNED(item_size, sizeof(u64))) { @@ -191,7 +191,7 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset, * Helper to output refs and locking status of extent buffer. Useful to debug * race condition related problems. */ -static void print_eb_refs_lock(struct extent_buffer *eb) +static void print_eb_refs_lock(const struct extent_buffer *eb) { #ifdef CONFIG_BTRFS_DEBUG btrfs_info(eb->fs_info, "refs %u lock_owner %u current %u", @@ -199,7 +199,7 @@ static void print_eb_refs_lock(struct extent_buffer *eb) #endif } -void btrfs_print_leaf(struct extent_buffer *l) +void btrfs_print_leaf(const struct extent_buffer *l) { struct btrfs_fs_info *fs_info; int i; @@ -355,7 +355,7 @@ void btrfs_print_leaf(struct extent_buffer *l) } } -void btrfs_print_tree(struct extent_buffer *c, bool follow) +void btrfs_print_tree(const struct extent_buffer *c, bool follow) { struct btrfs_fs_info *fs_info; int i; u32 nr; diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h index 8c3e9319ec4e..c42bc666d5ee 100644 --- a/fs/btrfs/print-tree.h +++ b/fs/btrfs/print-tree.h @@ -9,8 +9,8 @@ /* Buffer size to contain tree name and possibly additional data (offset) */ #define BTRFS_ROOT_NAME_BUF_LEN 48 -void btrfs_print_leaf(struct extent_buffer *l); -void btrfs_print_tree(struct extent_buffer *c, bool follow); +void btrfs_print_leaf(const struct extent_buffer *l); +void btrfs_print_tree(const struct extent_buffer *c, bool follow); const char *btrfs_root_name(const struct btrfs_key *key, char *buf); #endif diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index f41da7ac360d..da1f84a0eb29 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1232,12 +1232,23 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) int ret = 0; /* - * We need to have subvol_sem write locked, to prevent races between - * concurrent tasks trying to disable quotas, because we will unlock - * and relock qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + * We need to have subvol_sem write locked to prevent races with + * snapshot creation. */ lockdep_assert_held_write(&fs_info->subvol_sem); + /* + * Lock the cleaner mutex to prevent races with concurrent relocation, + * because relocation may be building backrefs for blocks of the quota + * root while we are deleting the root. This is like dropping fs roots + * of deleted snapshots/subvolumes, we need the same protection. + * + * This also prevents races between concurrent tasks trying to disable + * quotas, because we will unlock and relock qgroup_ioctl_lock across + * BTRFS_FS_QUOTA_ENABLED changes. + */ + mutex_lock(&fs_info->cleaner_mutex); + mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; @@ -1301,7 +1312,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) goto out; } + spin_lock(&fs_info->trans_lock); list_del("a_root->dirty_list); + spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(quota_root->node); btrfs_clear_buffer_dirty(trans, quota_root->node); @@ -1317,6 +1330,7 @@ out: btrfs_end_transaction(trans); else if (trans) ret = btrfs_end_transaction(trans); + mutex_unlock(&fs_info->cleaner_mutex); return ret; } diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 2fab37f062de..f37b925d587f 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1079,7 +1079,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio, /* see if we can add this page onto our existing bio */ if (last) { - u64 last_end = last->bi_iter.bi_sector << 9; + u64 last_end = last->bi_iter.bi_sector << SECTOR_SHIFT; last_end += last->bi_iter.bi_size; /* @@ -1099,7 +1099,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio, bio = bio_alloc(stripe->dev->bdev, max(BTRFS_STRIPE_LEN >> PAGE_SHIFT, 1), op, GFP_NOFS); - bio->bi_iter.bi_sector = disk_start >> 9; + bio->bi_iter.bi_sector = disk_start >> SECTOR_SHIFT; bio->bi_private = rbio; __bio_add_page(bio, sector->page, sectorsize, sector->pgoff); @@ -2747,3 +2747,48 @@ void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio) if (!lock_stripe_add(rbio)) start_async_work(rbio, scrub_rbio_work_locked); } + +/* + * This is for scrub call sites where we already have correct data contents. + * This allows us to avoid reading data stripes again. + * + * Unfortunately here we have to do page copy, other than reusing the pages. + * This is due to the fact rbio has its own page management for its cache. + */ +void raid56_parity_cache_data_pages(struct btrfs_raid_bio *rbio, + struct page **data_pages, u64 data_logical) +{ + const u64 offset_in_full_stripe = data_logical - + rbio->bioc->full_stripe_logical; + const int page_index = offset_in_full_stripe >> PAGE_SHIFT; + const u32 sectorsize = rbio->bioc->fs_info->sectorsize; + const u32 sectors_per_page = PAGE_SIZE / sectorsize; + int ret; + + /* + * If we hit ENOMEM temporarily, but later at + * raid56_parity_submit_scrub_rbio() time it succeeded, we just do + * the extra read, not a big deal. + * + * If we hit ENOMEM later at raid56_parity_submit_scrub_rbio() time, + * the bio would got proper error number set. + */ + ret = alloc_rbio_data_pages(rbio); + if (ret < 0) + return; + + /* data_logical must be at stripe boundary and inside the full stripe. */ + ASSERT(IS_ALIGNED(offset_in_full_stripe, BTRFS_STRIPE_LEN)); + ASSERT(offset_in_full_stripe < (rbio->nr_data << BTRFS_STRIPE_LEN_SHIFT)); + + for (int page_nr = 0; page_nr < (BTRFS_STRIPE_LEN >> PAGE_SHIFT); page_nr++) { + struct page *dst = rbio->stripe_pages[page_nr + page_index]; + struct page *src = data_pages[page_nr]; + + memcpy_page(dst, 0, src, 0, PAGE_SIZE); + for (int sector_nr = sectors_per_page * page_index; + sector_nr < sectors_per_page * (page_index + 1); + sector_nr++) + rbio->stripe_sectors[sector_nr].uptodate = true; + } +} diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h index 0f7f31c8cb98..0e84c9c9293f 100644 --- a/fs/btrfs/raid56.h +++ b/fs/btrfs/raid56.h @@ -193,6 +193,9 @@ struct btrfs_raid_bio *raid56_parity_alloc_scrub_rbio(struct bio *bio, unsigned long *dbitmap, int stripe_nsectors); void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio); +void raid56_parity_cache_data_pages(struct btrfs_raid_bio *rbio, + struct page **data_pages, u64 data_logical); + int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info); void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 59a06499c647..25a3361caedc 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -174,8 +174,8 @@ static void mark_block_processed(struct reloc_control *rc, in_range(node->bytenr, rc->block_group->start, rc->block_group->length)) { blocksize = rc->extent_root->fs_info->nodesize; - set_extent_bits(&rc->processed_blocks, node->bytenr, - node->bytenr + blocksize - 1, EXTENT_DIRTY); + set_extent_bit(&rc->processed_blocks, node->bytenr, + node->bytenr + blocksize - 1, EXTENT_DIRTY, NULL); } node->processed = 1; } @@ -3051,9 +3051,9 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra, u64 boundary_end = boundary_start + fs_info->sectorsize - 1; - set_extent_bits(&BTRFS_I(inode)->io_tree, - boundary_start, boundary_end, - EXTENT_BOUNDARY); + set_extent_bit(&BTRFS_I(inode)->io_tree, + boundary_start, boundary_end, + EXTENT_BOUNDARY, NULL); } unlock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end, &cached_state); @@ -4342,29 +4342,25 @@ out: * cloning checksum properly handles the nodatasum extents. * it also saves CPU time to re-calculate the checksum. */ -int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len) +int btrfs_reloc_clone_csums(struct btrfs_ordered_extent *ordered) { + struct btrfs_inode *inode = BTRFS_I(ordered->inode); struct btrfs_fs_info *fs_info = inode->root->fs_info; - struct btrfs_root *csum_root; - struct btrfs_ordered_sum *sums; - struct btrfs_ordered_extent *ordered; - int ret; - u64 disk_bytenr; - u64 new_bytenr; + u64 disk_bytenr = ordered->file_offset + inode->index_cnt; + struct btrfs_root *csum_root = btrfs_csum_root(fs_info, disk_bytenr); LIST_HEAD(list); + int ret; - ordered = btrfs_lookup_ordered_extent(inode, file_pos); - BUG_ON(ordered->file_offset != file_pos || ordered->num_bytes != len); - - disk_bytenr = file_pos + inode->index_cnt; - csum_root = btrfs_csum_root(fs_info, disk_bytenr); ret = btrfs_lookup_csums_list(csum_root, disk_bytenr, - disk_bytenr + len - 1, &list, 0, false); + disk_bytenr + ordered->num_bytes - 1, + &list, 0, false); if (ret) - goto out; + return ret; while (!list_empty(&list)) { - sums = list_entry(list.next, struct btrfs_ordered_sum, list); + struct btrfs_ordered_sum *sums = + list_entry(list.next, struct btrfs_ordered_sum, list); + list_del_init(&sums->list); /* @@ -4379,14 +4375,11 @@ int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len) * disk_len vs real len like with real inodes since it's all * disk length. */ - new_bytenr = ordered->disk_bytenr + sums->bytenr - disk_bytenr; - sums->bytenr = new_bytenr; - + sums->logical = ordered->disk_bytenr + sums->logical - disk_bytenr; btrfs_add_ordered_sum(ordered, sums); } -out: - btrfs_put_ordered_extent(ordered); - return ret; + + return 0; } int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, @@ -4523,3 +4516,19 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, ret = clone_backref_node(trans, rc, root, reloc_root); return ret; } + +/* + * Get the current bytenr for the block group which is being relocated. + * + * Return U64_MAX if no running relocation. + */ +u64 btrfs_get_reloc_bg_bytenr(struct btrfs_fs_info *fs_info) +{ + u64 logical = U64_MAX; + + lockdep_assert_held(&fs_info->reloc_mutex); + + if (fs_info->reloc_ctl && fs_info->reloc_ctl->block_group) + logical = fs_info->reloc_ctl->block_group->start; + return logical; +} diff --git a/fs/btrfs/relocation.h b/fs/btrfs/relocation.h index 2041a86186de..77d69f6ae967 100644 --- a/fs/btrfs/relocation.h +++ b/fs/btrfs/relocation.h @@ -8,7 +8,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *r int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_recover_relocation(struct btrfs_fs_info *fs_info); -int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len); +int btrfs_reloc_clone_csums(struct btrfs_ordered_extent *ordered); int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer *cow); @@ -19,5 +19,6 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans, int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info); struct btrfs_root *find_reloc_root(struct btrfs_fs_info *fs_info, u64 bytenr); int btrfs_should_ignore_reloc_root(struct btrfs_root *root); +u64 btrfs_get_reloc_bg_bytenr(struct btrfs_fs_info *fs_info); #endif diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 7c666517d3d3..4cae41bd6de0 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -134,8 +134,14 @@ struct scrub_stripe { * The errors hit during the initial read of the stripe. * * Would be utilized for error reporting and repair. + * + * The remaining init_nr_* records the number of errors hit, only used + * by error reporting. */ unsigned long init_error_bitmap; + unsigned int init_nr_io_errors; + unsigned int init_nr_csum_errors; + unsigned int init_nr_meta_errors; /* * The following error bitmaps are all for the current status. @@ -171,7 +177,6 @@ struct scrub_ctx { struct btrfs_fs_info *fs_info; int first_free; int cur_stripe; - struct list_head csum_list; atomic_t cancel_req; int readonly; int sectors_per_bio; @@ -303,17 +308,6 @@ static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info) scrub_pause_off(fs_info); } -static void scrub_free_csums(struct scrub_ctx *sctx) -{ - while (!list_empty(&sctx->csum_list)) { - struct btrfs_ordered_sum *sum; - sum = list_first_entry(&sctx->csum_list, - struct btrfs_ordered_sum, list); - list_del(&sum->list); - kfree(sum); - } -} - static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) { int i; @@ -324,7 +318,6 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) for (i = 0; i < SCRUB_STRIPES_PER_SCTX; i++) release_scrub_stripe(&sctx->stripes[i]); - scrub_free_csums(sctx); kfree(sctx); } @@ -346,7 +339,6 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( refcount_set(&sctx->refs, 1); sctx->is_dev_replace = is_dev_replace; sctx->fs_info = fs_info; - INIT_LIST_HEAD(&sctx->csum_list); for (i = 0; i < SCRUB_STRIPES_PER_SCTX; i++) { int ret; @@ -473,11 +465,8 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * struct extent_buffer *eb; struct btrfs_extent_item *ei; struct scrub_warning swarn; - unsigned long ptr = 0; u64 flags = 0; - u64 ref_root; u32 item_size; - u8 ref_level = 0; int ret; /* Super block error, no need to search extent tree. */ @@ -507,19 +496,28 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * item_size = btrfs_item_size(eb, path->slots[0]); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - do { + unsigned long ptr = 0; + u8 ref_level; + u64 ref_root; + + while (true) { ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, item_size, &ref_root, &ref_level); + if (ret < 0) { + btrfs_warn(fs_info, + "failed to resolve tree backref for logical %llu: %d", + swarn.logical, ret); + break; + } + if (ret > 0) + break; btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", - errstr, swarn.logical, - btrfs_dev_name(dev), - swarn.physical, - ref_level ? "node" : "leaf", - ret < 0 ? -1 : ref_level, - ret < 0 ? -1 : ref_root); - } while (ret != 1); + errstr, swarn.logical, btrfs_dev_name(dev), + swarn.physical, (ref_level ? "node" : "leaf"), + ref_level, ref_root); + } btrfs_release_path(path); } else { struct btrfs_backref_walk_ctx ctx = { 0 }; @@ -540,48 +538,6 @@ out: btrfs_free_path(path); } -static inline int scrub_nr_raid_mirrors(struct btrfs_io_context *bioc) -{ - if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID5) - return 2; - else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID6) - return 3; - else - return (int)bioc->num_stripes; -} - -static inline void scrub_stripe_index_and_offset(u64 logical, u64 map_type, - u64 full_stripe_logical, - int nstripes, int mirror, - int *stripe_index, - u64 *stripe_offset) -{ - int i; - - if (map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - const int nr_data_stripes = (map_type & BTRFS_BLOCK_GROUP_RAID5) ? - nstripes - 1 : nstripes - 2; - - /* RAID5/6 */ - for (i = 0; i < nr_data_stripes; i++) { - const u64 data_stripe_start = full_stripe_logical + - (i * BTRFS_STRIPE_LEN); - - if (logical >= data_stripe_start && - logical < data_stripe_start + BTRFS_STRIPE_LEN) - break; - } - - *stripe_index = i; - *stripe_offset = (logical - full_stripe_logical) & - BTRFS_STRIPE_LEN_MASK; - } else { - /* The other RAID type */ - *stripe_index = mirror; - *stripe_offset = 0; - } -} - static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) { int ret = 0; @@ -918,8 +874,9 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, /* For scrub, our mirror_num should always start at 1. */ ASSERT(stripe->mirror_num >= 1); - ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, - stripe->logical, &mapped_len, &bioc); + ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, + stripe->logical, &mapped_len, &bioc, + NULL, NULL, 1); /* * If we failed, dev will be NULL, and later detailed reports * will just be skipped. @@ -1003,12 +960,9 @@ skip: sctx->stat.data_bytes_scrubbed += nr_data_sectors << fs_info->sectorsize_bits; sctx->stat.tree_bytes_scrubbed += nr_meta_sectors << fs_info->sectorsize_bits; sctx->stat.no_csum += nr_nodatacsum_sectors; - sctx->stat.read_errors += - bitmap_weight(&stripe->io_error_bitmap, stripe->nr_sectors); - sctx->stat.csum_errors += - bitmap_weight(&stripe->csum_error_bitmap, stripe->nr_sectors); - sctx->stat.verify_errors += - bitmap_weight(&stripe->meta_error_bitmap, stripe->nr_sectors); + sctx->stat.read_errors += stripe->init_nr_io_errors; + sctx->stat.csum_errors += stripe->init_nr_csum_errors; + sctx->stat.verify_errors += stripe->init_nr_meta_errors; sctx->stat.uncorrectable_errors += bitmap_weight(&stripe->error_bitmap, stripe->nr_sectors); sctx->stat.corrected_errors += nr_repaired_sectors; @@ -1041,6 +995,12 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work) scrub_verify_one_stripe(stripe, stripe->extent_sector_bitmap); /* Save the initial failed bitmap for later repair and report usage. */ stripe->init_error_bitmap = stripe->error_bitmap; + stripe->init_nr_io_errors = bitmap_weight(&stripe->io_error_bitmap, + stripe->nr_sectors); + stripe->init_nr_csum_errors = bitmap_weight(&stripe->csum_error_bitmap, + stripe->nr_sectors); + stripe->init_nr_meta_errors = bitmap_weight(&stripe->meta_error_bitmap, + stripe->nr_sectors); if (bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors)) goto out; @@ -1295,7 +1255,7 @@ static int get_raid56_logic_offset(u64 physical, int num, u32 stripe_index; u32 rot; - *offset = last_offset + (i << BTRFS_STRIPE_LEN_SHIFT); + *offset = last_offset + btrfs_stripe_nr_to_offset(i); stripe_nr = (u32)(*offset >> BTRFS_STRIPE_LEN_SHIFT) / data_stripes; @@ -1310,7 +1270,7 @@ static int get_raid56_logic_offset(u64 physical, int num, if (stripe_index < num) j++; } - *offset = last_offset + (j << BTRFS_STRIPE_LEN_SHIFT); + *offset = last_offset + btrfs_stripe_nr_to_offset(j); return 1; } @@ -1490,6 +1450,9 @@ static void scrub_stripe_reset_bitmaps(struct scrub_stripe *stripe) { stripe->extent_sector_bitmap = 0; stripe->init_error_bitmap = 0; + stripe->init_nr_io_errors = 0; + stripe->init_nr_csum_errors = 0; + stripe->init_nr_meta_errors = 0; stripe->error_bitmap = 0; stripe->io_error_bitmap = 0; stripe->csum_error_bitmap = 0; @@ -1703,7 +1666,7 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx) ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &sctx->stripes[0].state)); scrub_throttle_dev_io(sctx, sctx->stripes[0].dev, - nr_stripes << BTRFS_STRIPE_LEN_SHIFT); + btrfs_stripe_nr_to_offset(nr_stripes)); for (int i = 0; i < nr_stripes; i++) { stripe = &sctx->stripes[i]; scrub_submit_initial_read(sctx, stripe); @@ -1730,7 +1693,7 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx) break; } } - } else { + } else if (!sctx->readonly) { for (int i = 0; i < nr_stripes; i++) { unsigned long repaired; @@ -1826,7 +1789,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, bool all_empty = true; const int data_stripes = nr_data_stripes(map); unsigned long extent_bitmap = 0; - u64 length = data_stripes << BTRFS_STRIPE_LEN_SHIFT; + u64 length = btrfs_stripe_nr_to_offset(data_stripes); int ret; ASSERT(sctx->raid56_data_stripes); @@ -1841,13 +1804,13 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, data_stripes) >> BTRFS_STRIPE_LEN_SHIFT; stripe_index = (i + rot) % map->num_stripes; physical = map->stripes[stripe_index].physical + - (rot << BTRFS_STRIPE_LEN_SHIFT); + btrfs_stripe_nr_to_offset(rot); scrub_reset_stripe(stripe); set_bit(SCRUB_STRIPE_FLAG_NO_REPORT, &stripe->state); ret = scrub_find_fill_first_stripe(bg, map->stripes[stripe_index].dev, physical, 1, - full_stripe_start + (i << BTRFS_STRIPE_LEN_SHIFT), + full_stripe_start + btrfs_stripe_nr_to_offset(i), BTRFS_STRIPE_LEN, stripe); if (ret < 0) goto out; @@ -1857,7 +1820,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, */ if (ret > 0) { stripe->logical = full_stripe_start + - (i << BTRFS_STRIPE_LEN_SHIFT); + btrfs_stripe_nr_to_offset(i); stripe->dev = map->stripes[stripe_index].dev; stripe->mirror_num = 1; set_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state); @@ -1945,8 +1908,8 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, bio->bi_end_io = raid56_scrub_wait_endio; btrfs_bio_counter_inc_blocked(fs_info); - ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, full_stripe_start, - &length, &bioc); + ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, full_stripe_start, + &length, &bioc, NULL, NULL, 1); if (ret < 0) { btrfs_put_bioc(bioc); btrfs_bio_counter_dec(fs_info); @@ -1960,6 +1923,13 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, btrfs_bio_counter_dec(fs_info); goto out; } + /* Use the recovered stripes as cache to avoid read them from disk again. */ + for (int i = 0; i < data_stripes; i++) { + stripe = &sctx->raid56_data_stripes[i]; + + raid56_parity_cache_data_pages(rbio, stripe->pages, + full_stripe_start + (i << BTRFS_STRIPE_LEN_SHIFT)); + } raid56_parity_submit_scrub_rbio(rbio); wait_for_completion_io(&io_done); ret = blk_status_to_errno(bio->bi_status); @@ -2050,7 +2020,7 @@ static u64 simple_stripe_full_stripe_len(const struct map_lookup *map) ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)); - return (map->num_stripes / map->sub_stripes) << BTRFS_STRIPE_LEN_SHIFT; + return btrfs_stripe_nr_to_offset(map->num_stripes / map->sub_stripes); } /* Get the logical bytenr for the stripe */ @@ -2066,7 +2036,7 @@ static u64 simple_stripe_get_logical(struct map_lookup *map, * (stripe_index / sub_stripes) gives how many data stripes we need to * skip. */ - return ((stripe_index / map->sub_stripes) << BTRFS_STRIPE_LEN_SHIFT) + + return btrfs_stripe_nr_to_offset(stripe_index / map->sub_stripes) + bg->start; } @@ -2192,7 +2162,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, } if (profile & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { ret = scrub_simple_stripe(sctx, bg, map, scrub_dev, stripe_index); - offset = (stripe_index / map->sub_stripes) << BTRFS_STRIPE_LEN_SHIFT; + offset = btrfs_stripe_nr_to_offset(stripe_index / map->sub_stripes); goto out; } @@ -2207,7 +2177,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, /* Initialize @offset in case we need to go to out: label */ get_raid56_logic_offset(physical, stripe_index, map, &offset, NULL); - increment = nr_data_stripes(map) << BTRFS_STRIPE_LEN_SHIFT; + increment = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); /* * Due to the rotation, for RAID56 it's better to iterate each stripe @@ -2254,7 +2224,7 @@ next: } out: ret2 = flush_scrub_stripes(sctx); - if (!ret2) + if (!ret) ret = ret2; if (sctx->raid56_data_stripes) { for (int i = 0; i < nr_data_stripes(map); i++) @@ -2728,17 +2698,12 @@ static void scrub_workers_put(struct btrfs_fs_info *fs_info) if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, &fs_info->scrub_lock)) { struct workqueue_struct *scrub_workers = fs_info->scrub_workers; - struct workqueue_struct *scrub_wr_comp = - fs_info->scrub_wr_completion_workers; fs_info->scrub_workers = NULL; - fs_info->scrub_wr_completion_workers = NULL; mutex_unlock(&fs_info->scrub_lock); if (scrub_workers) destroy_workqueue(scrub_workers); - if (scrub_wr_comp) - destroy_workqueue(scrub_wr_comp); } } @@ -2749,7 +2714,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int is_dev_replace) { struct workqueue_struct *scrub_workers = NULL; - struct workqueue_struct *scrub_wr_comp = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; int ret = -ENOMEM; @@ -2757,21 +2721,17 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) return 0; - scrub_workers = alloc_workqueue("btrfs-scrub", flags, - is_dev_replace ? 1 : max_active); + if (is_dev_replace) + scrub_workers = alloc_ordered_workqueue("btrfs-scrub", flags); + else + scrub_workers = alloc_workqueue("btrfs-scrub", flags, max_active); if (!scrub_workers) - goto fail_scrub_workers; - - scrub_wr_comp = alloc_workqueue("btrfs-scrubwrc", flags, max_active); - if (!scrub_wr_comp) - goto fail_scrub_wr_completion_workers; + return -ENOMEM; mutex_lock(&fs_info->scrub_lock); if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { - ASSERT(fs_info->scrub_workers == NULL && - fs_info->scrub_wr_completion_workers == NULL); + ASSERT(fs_info->scrub_workers == NULL); fs_info->scrub_workers = scrub_workers; - fs_info->scrub_wr_completion_workers = scrub_wr_comp; refcount_set(&fs_info->scrub_workers_refcnt, 1); mutex_unlock(&fs_info->scrub_lock); return 0; @@ -2782,10 +2742,7 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, ret = 0; - destroy_workqueue(scrub_wr_comp); -fail_scrub_wr_completion_workers: destroy_workqueue(scrub_workers); -fail_scrub_workers: return ret; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index af2e153543a5..8bfd44750efe 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1774,9 +1774,21 @@ static int read_symlink(struct btrfs_root *root, ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); type = btrfs_file_extent_type(path->nodes[0], ei); + if (unlikely(type != BTRFS_FILE_EXTENT_INLINE)) { + ret = -EUCLEAN; + btrfs_crit(root->fs_info, +"send: found symlink extent that is not inline, ino %llu root %llu extent type %d", + ino, btrfs_root_id(root), type); + goto out; + } compression = btrfs_file_extent_compression(path->nodes[0], ei); - BUG_ON(type != BTRFS_FILE_EXTENT_INLINE); - BUG_ON(compression); + if (unlikely(compression != BTRFS_COMPRESS_NONE)) { + ret = -EUCLEAN; + btrfs_crit(root->fs_info, +"send: found symlink extent with compression, ino %llu root %llu compression type %d", + ino, btrfs_root_id(root), compression); + goto out; + } off = btrfs_file_extent_inline_start(ei); len = btrfs_file_extent_ram_bytes(path->nodes[0], ei); diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index dd46b978ac2c..1b999c6e4193 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -100,9 +100,6 @@ void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sector subpage_info->uptodate_offset = cur; cur += nr_bits; - subpage_info->error_offset = cur; - cur += nr_bits; - subpage_info->dirty_offset = cur; cur += nr_bits; @@ -367,28 +364,6 @@ void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info, unlock_page(page); } -static bool bitmap_test_range_all_set(unsigned long *addr, unsigned int start, - unsigned int nbits) -{ - unsigned int found_zero; - - found_zero = find_next_zero_bit(addr, start + nbits, start); - if (found_zero == start + nbits) - return true; - return false; -} - -static bool bitmap_test_range_all_zero(unsigned long *addr, unsigned int start, - unsigned int nbits) -{ - unsigned int found_set; - - found_set = find_next_bit(addr, start + nbits, start); - if (found_set == start + nbits) - return true; - return false; -} - #define subpage_calc_start_bit(fs_info, page, name, start, len) \ ({ \ unsigned int start_bit; \ @@ -438,35 +413,6 @@ void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info, spin_unlock_irqrestore(&subpage->lock, flags); } -void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info, - struct page *page, u64 start, u32 len) -{ - struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; - unsigned int start_bit = subpage_calc_start_bit(fs_info, page, - error, start, len); - unsigned long flags; - - spin_lock_irqsave(&subpage->lock, flags); - bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); - SetPageError(page); - spin_unlock_irqrestore(&subpage->lock, flags); -} - -void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info, - struct page *page, u64 start, u32 len) -{ - struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; - unsigned int start_bit = subpage_calc_start_bit(fs_info, page, - error, start, len); - unsigned long flags; - - spin_lock_irqsave(&subpage->lock, flags); - bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); - if (subpage_test_bitmap_all_zero(fs_info, subpage, error)) - ClearPageError(page); - spin_unlock_irqrestore(&subpage->lock, flags); -} - void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info, struct page *page, u64 start, u32 len) { @@ -628,7 +574,6 @@ bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ return ret; \ } IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate); -IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(writeback); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(ordered); @@ -696,7 +641,6 @@ bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info, \ } IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate, PageUptodate); -IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError); IMPLEMENT_BTRFS_PAGE_OPS(dirty, set_page_dirty, clear_page_dirty_for_io, PageDirty); IMPLEMENT_BTRFS_PAGE_OPS(writeback, set_page_writeback, end_page_writeback, @@ -767,3 +711,44 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page, /* Have writers, use proper subpage helper to end it */ btrfs_page_end_writer_lock(fs_info, page, start, len); } + +#define GET_SUBPAGE_BITMAP(subpage, subpage_info, name, dst) \ + bitmap_cut(dst, subpage->bitmaps, 0, \ + subpage_info->name##_offset, subpage_info->bitmap_nr_bits) + +void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage_info *subpage_info = fs_info->subpage_info; + struct btrfs_subpage *subpage; + unsigned long uptodate_bitmap; + unsigned long error_bitmap; + unsigned long dirty_bitmap; + unsigned long writeback_bitmap; + unsigned long ordered_bitmap; + unsigned long checked_bitmap; + unsigned long flags; + + ASSERT(PagePrivate(page) && page->private); + ASSERT(subpage_info); + subpage = (struct btrfs_subpage *)page->private; + + spin_lock_irqsave(&subpage->lock, flags); + GET_SUBPAGE_BITMAP(subpage, subpage_info, uptodate, &uptodate_bitmap); + GET_SUBPAGE_BITMAP(subpage, subpage_info, dirty, &dirty_bitmap); + GET_SUBPAGE_BITMAP(subpage, subpage_info, writeback, &writeback_bitmap); + GET_SUBPAGE_BITMAP(subpage, subpage_info, ordered, &ordered_bitmap); + GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap); + spin_unlock_irqrestore(&subpage->lock, flags); + + dump_page(page, "btrfs subpage dump"); + btrfs_warn(fs_info, +"start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl error=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", + start, len, page_offset(page), + subpage_info->bitmap_nr_bits, &uptodate_bitmap, + subpage_info->bitmap_nr_bits, &error_bitmap, + subpage_info->bitmap_nr_bits, &dirty_bitmap, + subpage_info->bitmap_nr_bits, &writeback_bitmap, + subpage_info->bitmap_nr_bits, &ordered_bitmap, + subpage_info->bitmap_nr_bits, &checked_bitmap); +} diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index 0e80ad336904..5cbf67ccbdeb 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -8,17 +8,17 @@ /* * Extra info for subpapge bitmap. * - * For subpage we pack all uptodate/error/dirty/writeback/ordered bitmaps into + * For subpage we pack all uptodate/dirty/writeback/ordered bitmaps into * one larger bitmap. * * This structure records how they are organized in the bitmap: * - * /- uptodate_offset /- error_offset /- dirty_offset + * /- uptodate_offset /- dirty_offset /- ordered_offset * | | | * v v v - * |u|u|u|u|........|u|u|e|e|.......|e|e| ... |o|o| + * |u|u|u|u|........|u|u|d|d|.......|d|d|o|o|.......|o|o| * |<- bitmap_nr_bits ->| - * |<--------------- total_nr_bits ---------------->| + * |<----------------- total_nr_bits ------------------>| */ struct btrfs_subpage_info { /* Number of bits for each bitmap */ @@ -32,7 +32,6 @@ struct btrfs_subpage_info { * @bitmap_size, which is calculated from PAGE_SIZE / sectorsize. */ unsigned int uptodate_offset; - unsigned int error_offset; unsigned int dirty_offset; unsigned int writeback_offset; unsigned int ordered_offset; @@ -141,7 +140,6 @@ bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info, \ struct page *page, u64 start, u32 len); DECLARE_BTRFS_SUBPAGE_OPS(uptodate); -DECLARE_BTRFS_SUBPAGE_OPS(error); DECLARE_BTRFS_SUBPAGE_OPS(dirty); DECLARE_BTRFS_SUBPAGE_OPS(writeback); DECLARE_BTRFS_SUBPAGE_OPS(ordered); @@ -154,5 +152,7 @@ void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info, struct page *page); void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page, u64 start, u32 len); +void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); #endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index ec18e2210602..f1dd172d8d5b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -849,8 +849,7 @@ out: * All other options will be parsed on much later in the mount process and * only when we need to allocate a new super block. */ -static int btrfs_parse_device_options(const char *options, fmode_t flags, - void *holder) +static int btrfs_parse_device_options(const char *options, blk_mode_t flags) { substring_t args[MAX_OPT_ARGS]; char *device_name, *opts, *orig, *p; @@ -884,8 +883,7 @@ static int btrfs_parse_device_options(const char *options, fmode_t flags, error = -ENOMEM; goto out; } - device = btrfs_scan_one_device(device_name, flags, - holder); + device = btrfs_scan_one_device(device_name, flags); kfree(device_name); if (IS_ERR(device)) { error = PTR_ERR(device); @@ -1442,12 +1440,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, struct btrfs_fs_devices *fs_devices = NULL; struct btrfs_fs_info *fs_info = NULL; void *new_sec_opts = NULL; - fmode_t mode = FMODE_READ; + blk_mode_t mode = sb_open_mode(flags); int error = 0; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - if (data) { error = security_sb_eat_lsm_opts(data, &new_sec_opts); if (error) @@ -1477,13 +1472,13 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, } mutex_lock(&uuid_mutex); - error = btrfs_parse_device_options(data, mode, fs_type); + error = btrfs_parse_device_options(data, mode); if (error) { mutex_unlock(&uuid_mutex); goto error_fs_info; } - device = btrfs_scan_one_device(device_name, mode, fs_type); + device = btrfs_scan_one_device(device_name, mode); if (IS_ERR(device)) { mutex_unlock(&uuid_mutex); error = PTR_ERR(device); @@ -1631,7 +1626,6 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, old_pool_size, new_pool_size); btrfs_workqueue_set_max(fs_info->workers, new_pool_size); - btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); workqueue_set_max_active(fs_info->endio_workers, new_pool_size); @@ -1841,6 +1835,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_clear_sb_rdonly(sb); set_bit(BTRFS_FS_OPEN, &fs_info->flags); + + /* + * If we've gone from readonly -> read/write, we need to get + * our sync/async discard lists in the right state. + */ + btrfs_discard_resume(fs_info); } out: /* @@ -2190,8 +2190,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case BTRFS_IOC_SCAN_DEV: mutex_lock(&uuid_mutex); - device = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_root_fs_type); + device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ); ret = PTR_ERR_OR_ZERO(device); mutex_unlock(&uuid_mutex); break; @@ -2205,8 +2204,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, break; case BTRFS_IOC_DEVICES_READY: mutex_lock(&uuid_mutex); - device = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_root_fs_type); + device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ); if (IS_ERR(device)) { mutex_unlock(&uuid_mutex); ret = PTR_ERR(device); diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index dfc5c7fa6038..f6bc6d738555 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -159,7 +159,7 @@ static int test_find_delalloc(u32 sectorsize) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(tmp, 0, sectorsize - 1, 0, NULL); + set_extent_bit(tmp, 0, sectorsize - 1, EXTENT_DELALLOC, NULL); start = 0; end = start + PAGE_SIZE - 1; found = find_lock_delalloc_range(inode, locked_page, &start, @@ -190,7 +190,7 @@ static int test_find_delalloc(u32 sectorsize) test_err("couldn't find the locked page"); goto out_bits; } - set_extent_delalloc(tmp, sectorsize, max_bytes - 1, 0, NULL); + set_extent_bit(tmp, sectorsize, max_bytes - 1, EXTENT_DELALLOC, NULL); start = test_start; end = start + PAGE_SIZE - 1; found = find_lock_delalloc_range(inode, locked_page, &start, @@ -245,7 +245,7 @@ static int test_find_delalloc(u32 sectorsize) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(tmp, max_bytes, total_dirty - 1, 0, NULL); + set_extent_bit(tmp, max_bytes, total_dirty - 1, EXTENT_DELALLOC, NULL); start = test_start; end = start + PAGE_SIZE - 1; found = find_lock_delalloc_range(inode, locked_page, &start, @@ -503,8 +503,8 @@ static int test_find_first_clear_extent_bit(void) * Set 1M-4M alloc/discard and 32M-64M thus leaving a hole between * 4M-32M */ - set_extent_bits(&tree, SZ_1M, SZ_4M - 1, - CHUNK_TRIMMED | CHUNK_ALLOCATED); + set_extent_bit(&tree, SZ_1M, SZ_4M - 1, + CHUNK_TRIMMED | CHUNK_ALLOCATED, NULL); find_first_clear_extent_bit(&tree, SZ_512K, &start, &end, CHUNK_TRIMMED | CHUNK_ALLOCATED); @@ -516,8 +516,8 @@ static int test_find_first_clear_extent_bit(void) } /* Now add 32M-64M so that we have a hole between 4M-32M */ - set_extent_bits(&tree, SZ_32M, SZ_64M - 1, - CHUNK_TRIMMED | CHUNK_ALLOCATED); + set_extent_bit(&tree, SZ_32M, SZ_64M - 1, + CHUNK_TRIMMED | CHUNK_ALLOCATED, NULL); /* * Request first hole starting at 12M, we should get 4M-32M @@ -548,7 +548,7 @@ static int test_find_first_clear_extent_bit(void) * Set 64M-72M with CHUNK_ALLOC flag, then search for CHUNK_TRIMMED flag * being unset in this range, we should get the entry in range 64M-72M */ - set_extent_bits(&tree, SZ_64M, SZ_64M + SZ_8M - 1, CHUNK_ALLOCATED); + set_extent_bit(&tree, SZ_64M, SZ_64M + SZ_8M - 1, CHUNK_ALLOCATED, NULL); find_first_clear_extent_bit(&tree, SZ_64M + SZ_1M, &start, &end, CHUNK_TRIMMED); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8b6a99b8d7f6..cf306351b148 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -374,8 +374,6 @@ loop: spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->dropped_roots_lock); - INIT_LIST_HEAD(&cur_trans->releasing_ebs); - spin_lock_init(&cur_trans->releasing_ebs_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES); @@ -1056,7 +1054,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info, u64 start = 0; u64 end; - atomic_inc(&BTRFS_I(fs_info->btree_inode)->sync_writers); while (!find_first_extent_bit(dirty_pages, start, &start, &end, mark, &cached_state)) { bool wait_writeback = false; @@ -1092,7 +1089,6 @@ int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info, cond_resched(); start = end + 1; } - atomic_dec(&BTRFS_I(fs_info->btree_inode)->sync_writers); return werr; } @@ -1688,7 +1684,10 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, * insert the directory item */ ret = btrfs_set_inode_index(BTRFS_I(parent_inode), &index); - BUG_ON(ret); /* -ENOMEM */ + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } /* check if there is a file/dir which has the same name. */ dir_item = btrfs_lookup_dir_item(NULL, parent_root, path, @@ -2484,13 +2483,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } - /* - * At this point, we should have written all the tree blocks allocated - * in this transaction. So it's now safe to free the redirtyied extent - * buffers. - */ - btrfs_free_redirty_list(cur_trans); - ret = write_all_supers(fs_info, 0); /* * the super is written, we can safely allow the tree-loggers diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index fa728ab80826..8e9fa23bd7fe 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -94,9 +94,6 @@ struct btrfs_transaction { */ atomic_t pending_ordered; wait_queue_head_t pending_wait; - - spinlock_t releasing_ebs_lock; - struct list_head releasing_ebs; }; enum { diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index e2b54793bf0c..038dfa8f1788 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -25,10 +25,10 @@ #include "compression.h" #include "volumes.h" #include "misc.h" -#include "btrfs_inode.h" #include "fs.h" #include "accessors.h" #include "file-item.h" +#include "inode-item.h" /* * Error message should follow the following format: @@ -857,10 +857,10 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, * * Thus it should be a good way to catch obvious bitflips. */ - if (unlikely(length >= ((u64)U32_MAX << BTRFS_STRIPE_LEN_SHIFT))) { + if (unlikely(length >= btrfs_stripe_nr_to_offset(U32_MAX))) { chunk_err(leaf, chunk, logical, "chunk length too large: have %llu limit %llu", - length, (u64)U32_MAX << BTRFS_STRIPE_LEN_SHIFT); + length, btrfs_stripe_nr_to_offset(U32_MAX)); return -EUCLEAN; } if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK | @@ -1620,9 +1620,10 @@ static int check_inode_ref(struct extent_buffer *leaf, /* * Common point to switch the item-specific validation. */ -static int check_leaf_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot, - struct btrfs_key *prev_key) +static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf, + struct btrfs_key *key, + int slot, + struct btrfs_key *prev_key) { int ret = 0; struct btrfs_chunk *chunk; @@ -1671,10 +1672,13 @@ static int check_leaf_item(struct extent_buffer *leaf, ret = check_extent_data_ref(leaf, key, slot); break; } - return ret; + + if (ret) + return BTRFS_TREE_BLOCK_INVALID_ITEM; + return BTRFS_TREE_BLOCK_CLEAN; } -static int check_leaf(struct extent_buffer *leaf, bool check_item_data) +enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf) { struct btrfs_fs_info *fs_info = leaf->fs_info; /* No valid key type is 0, so all key should be larger than this key */ @@ -1687,7 +1691,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) generic_err(leaf, 0, "invalid level for leaf, have %d expect 0", btrfs_header_level(leaf)); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_LEVEL; } /* @@ -1710,32 +1714,32 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) generic_err(leaf, 0, "invalid root, root %llu must never be empty", owner); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_NRITEMS; } /* Unknown tree */ if (unlikely(owner == 0)) { generic_err(leaf, 0, "invalid owner, root 0 is not defined"); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_OWNER; } /* EXTENT_TREE_V2 can have empty extent trees. */ if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) - return 0; + return BTRFS_TREE_BLOCK_CLEAN; if (unlikely(owner == BTRFS_EXTENT_TREE_OBJECTID)) { generic_err(leaf, 0, "invalid root, root %llu must never be empty", owner); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_NRITEMS; } - return 0; + return BTRFS_TREE_BLOCK_CLEAN; } if (unlikely(nritems == 0)) - return 0; + return BTRFS_TREE_BLOCK_CLEAN; /* * Check the following things to make sure this is a good leaf, and @@ -1751,7 +1755,6 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) for (slot = 0; slot < nritems; slot++) { u32 item_end_expected; u64 item_data_end; - int ret; btrfs_item_key_to_cpu(leaf, &key, slot); @@ -1762,7 +1765,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) prev_key.objectid, prev_key.type, prev_key.offset, key.objectid, key.type, key.offset); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_BAD_KEY_ORDER; } item_data_end = (u64)btrfs_item_offset(leaf, slot) + @@ -1781,7 +1784,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) generic_err(leaf, slot, "unexpected item end, have %llu expect %u", item_data_end, item_end_expected); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_OFFSETS; } /* @@ -1793,7 +1796,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) generic_err(leaf, slot, "slot end outside of leaf, have %llu expect range [0, %u]", item_data_end, BTRFS_LEAF_DATA_SIZE(fs_info)); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_OFFSETS; } /* Also check if the item pointer overlaps with btrfs item. */ @@ -1804,16 +1807,22 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) btrfs_item_nr_offset(leaf, slot) + sizeof(struct btrfs_item), btrfs_item_ptr_offset(leaf, slot)); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_OFFSETS; } - if (check_item_data) { + /* + * We only want to do this if WRITTEN is set, otherwise the leaf + * may be in some intermediate state and won't appear valid. + */ + if (btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_WRITTEN)) { + enum btrfs_tree_block_status ret; + /* * Check if the item size and content meet other * criteria */ ret = check_leaf_item(leaf, &key, slot, &prev_key); - if (unlikely(ret < 0)) + if (unlikely(ret != BTRFS_TREE_BLOCK_CLEAN)) return ret; } @@ -1822,21 +1831,21 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) prev_key.offset = key.offset; } - return 0; + return BTRFS_TREE_BLOCK_CLEAN; } -int btrfs_check_leaf_full(struct extent_buffer *leaf) +int btrfs_check_leaf(struct extent_buffer *leaf) { - return check_leaf(leaf, true); -} -ALLOW_ERROR_INJECTION(btrfs_check_leaf_full, ERRNO); + enum btrfs_tree_block_status ret; -int btrfs_check_leaf_relaxed(struct extent_buffer *leaf) -{ - return check_leaf(leaf, false); + ret = __btrfs_check_leaf(leaf); + if (unlikely(ret != BTRFS_TREE_BLOCK_CLEAN)) + return -EUCLEAN; + return 0; } +ALLOW_ERROR_INJECTION(btrfs_check_leaf, ERRNO); -int btrfs_check_node(struct extent_buffer *node) +enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node) { struct btrfs_fs_info *fs_info = node->fs_info; unsigned long nr = btrfs_header_nritems(node); @@ -1844,13 +1853,12 @@ int btrfs_check_node(struct extent_buffer *node) int slot; int level = btrfs_header_level(node); u64 bytenr; - int ret = 0; if (unlikely(level <= 0 || level >= BTRFS_MAX_LEVEL)) { generic_err(node, 0, "invalid level for node, have %d expect [1, %d]", level, BTRFS_MAX_LEVEL - 1); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_LEVEL; } if (unlikely(nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(fs_info))) { btrfs_crit(fs_info, @@ -1858,7 +1866,7 @@ int btrfs_check_node(struct extent_buffer *node) btrfs_header_owner(node), node->start, nr == 0 ? "small" : "large", nr, BTRFS_NODEPTRS_PER_BLOCK(fs_info)); - return -EUCLEAN; + return BTRFS_TREE_BLOCK_INVALID_NRITEMS; } for (slot = 0; slot < nr - 1; slot++) { @@ -1869,15 +1877,13 @@ int btrfs_check_node(struct extent_buffer *node) if (unlikely(!bytenr)) { generic_err(node, slot, "invalid NULL node pointer"); - ret = -EUCLEAN; - goto out; + return BTRFS_TREE_BLOCK_INVALID_BLOCKPTR; } if (unlikely(!IS_ALIGNED(bytenr, fs_info->sectorsize))) { generic_err(node, slot, "unaligned pointer, have %llu should be aligned to %u", bytenr, fs_info->sectorsize); - ret = -EUCLEAN; - goto out; + return BTRFS_TREE_BLOCK_INVALID_BLOCKPTR; } if (unlikely(btrfs_comp_cpu_keys(&key, &next_key) >= 0)) { @@ -1886,12 +1892,20 @@ int btrfs_check_node(struct extent_buffer *node) key.objectid, key.type, key.offset, next_key.objectid, next_key.type, next_key.offset); - ret = -EUCLEAN; - goto out; + return BTRFS_TREE_BLOCK_BAD_KEY_ORDER; } } -out: - return ret; + return BTRFS_TREE_BLOCK_CLEAN; +} + +int btrfs_check_node(struct extent_buffer *node) +{ + enum btrfs_tree_block_status ret; + + ret = __btrfs_check_node(node); + if (unlikely(ret != BTRFS_TREE_BLOCK_CLEAN)) + return -EUCLEAN; + return 0; } ALLOW_ERROR_INJECTION(btrfs_check_node, ERRNO); @@ -1949,3 +1963,61 @@ int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner) } return 0; } + +int btrfs_verify_level_key(struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + int found_level; + struct btrfs_key found_key; + int ret; + + found_level = btrfs_header_level(eb); + if (found_level != level) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree level check failed\n"); + btrfs_err(fs_info, +"tree level mismatch detected, bytenr=%llu level expected=%u has=%u", + eb->start, level, found_level); + return -EIO; + } + + if (!first_key) + return 0; + + /* + * For live tree block (new tree blocks in current transaction), + * we need proper lock context to avoid race, which is impossible here. + * So we only checks tree blocks which is read from disk, whose + * generation <= fs_info->last_trans_committed. + */ + if (btrfs_header_generation(eb) > fs_info->last_trans_committed) + return 0; + + /* We have @first_key, so this @eb must have at least one item */ + if (btrfs_header_nritems(eb) == 0) { + btrfs_err(fs_info, + "invalid tree nritems, bytenr=%llu nritems=0 expect >0", + eb->start); + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + return -EUCLEAN; + } + + if (found_level) + btrfs_node_key_to_cpu(eb, &found_key, 0); + else + btrfs_item_key_to_cpu(eb, &found_key, 0); + ret = btrfs_comp_cpu_keys(first_key, &found_key); + + if (ret) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: tree first key check failed\n"); + btrfs_err(fs_info, +"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)", + eb->start, parent_transid, first_key->objectid, + first_key->type, first_key->offset, + found_key.objectid, found_key.type, + found_key.offset); + } + return ret; +} diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h index bfb5efa4e01f..3c2a02a72f64 100644 --- a/fs/btrfs/tree-checker.h +++ b/fs/btrfs/tree-checker.h @@ -40,22 +40,33 @@ struct btrfs_tree_parent_check { u8 level; }; -/* - * Comprehensive leaf checker. - * Will check not only the item pointers, but also every possible member - * in item data. - */ -int btrfs_check_leaf_full(struct extent_buffer *leaf); +enum btrfs_tree_block_status { + BTRFS_TREE_BLOCK_CLEAN, + BTRFS_TREE_BLOCK_INVALID_NRITEMS, + BTRFS_TREE_BLOCK_INVALID_PARENT_KEY, + BTRFS_TREE_BLOCK_BAD_KEY_ORDER, + BTRFS_TREE_BLOCK_INVALID_LEVEL, + BTRFS_TREE_BLOCK_INVALID_FREE_SPACE, + BTRFS_TREE_BLOCK_INVALID_OFFSETS, + BTRFS_TREE_BLOCK_INVALID_BLOCKPTR, + BTRFS_TREE_BLOCK_INVALID_ITEM, + BTRFS_TREE_BLOCK_INVALID_OWNER, +}; /* - * Less strict leaf checker. - * Will only check item pointers, not reading item data. + * Exported simply for btrfs-progs which wants to have the + * btrfs_tree_block_status return codes. */ -int btrfs_check_leaf_relaxed(struct extent_buffer *leaf); +enum btrfs_tree_block_status __btrfs_check_leaf(struct extent_buffer *leaf); +enum btrfs_tree_block_status __btrfs_check_node(struct extent_buffer *node); + +int btrfs_check_leaf(struct extent_buffer *leaf); int btrfs_check_node(struct extent_buffer *node); int btrfs_check_chunk_valid(struct extent_buffer *leaf, struct btrfs_chunk *chunk, u64 logical); int btrfs_check_eb_owner(const struct extent_buffer *eb, u64 root_owner); +int btrfs_verify_level_key(struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid); #endif diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d2755d5e338b..365a1cc0a3c3 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -859,10 +859,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); csum_root = btrfs_csum_root(fs_info, - sums->bytenr); + sums->logical); if (!ret) ret = btrfs_del_csums(trans, csum_root, - sums->bytenr, + sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, @@ -3252,7 +3252,7 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, * Returns 1 if the inode was logged before in the transaction, 0 if it was not, * and < 0 on error. */ -static int inode_logged(struct btrfs_trans_handle *trans, +static int inode_logged(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path_in) { @@ -4056,14 +4056,14 @@ static int drop_inode_items(struct btrfs_trans_handle *trans, while (1) { ret = btrfs_search_slot(trans, log, &key, path, -1, 1); - BUG_ON(ret == 0); /* Logic error */ - if (ret < 0) - break; - - if (path->slots[0] == 0) + if (ret < 0) { break; + } else if (ret > 0) { + if (path->slots[0] == 0) + break; + path->slots[0]--; + } - path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); @@ -4221,7 +4221,7 @@ static int log_csums(struct btrfs_trans_handle *trans, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { - const u64 lock_end = sums->bytenr + sums->len - 1; + const u64 lock_end = sums->logical + sums->len - 1; struct extent_state *cached_state = NULL; int ret; @@ -4239,7 +4239,7 @@ static int log_csums(struct btrfs_trans_handle *trans, * file which happens to refer to the same extent as well. Such races * can leave checksum items in the log with overlapping ranges. */ - ret = lock_extent(&log_root->log_csum_range, sums->bytenr, lock_end, + ret = lock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); if (ret) return ret; @@ -4252,11 +4252,11 @@ static int log_csums(struct btrfs_trans_handle *trans, * some checksums missing in the fs/subvolume tree. So just delete (or * trim and adjust) any existing csum items in the log for this range. */ - ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + ret = btrfs_del_csums(trans, log_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, log_root, sums); - unlock_extent(&log_root->log_csum_range, sums->bytenr, lock_end, + unlock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); return ret; @@ -5303,7 +5303,7 @@ out: * multiple times when multiple tasks have joined the same log transaction. */ static bool need_log_inode(const struct btrfs_trans_handle *trans, - const struct btrfs_inode *inode) + struct btrfs_inode *inode) { /* * If a directory was not modified, no dentries added or removed, we can @@ -5321,7 +5321,7 @@ static bool need_log_inode(const struct btrfs_trans_handle *trans, * logged_trans will be 0, in which case we have to fully log it since * logged_trans is a transient field, not persisted. */ - if (inode->logged_trans == trans->transid && + if (inode_logged(trans, inode, NULL) == 1 && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return false; @@ -7309,7 +7309,7 @@ error: */ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - int for_rename) + bool for_rename) { /* * when we're logging a file, if it hasn't been renamed @@ -7325,18 +7325,25 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, inode->last_unlink_trans = trans->transid; mutex_unlock(&inode->log_mutex); + if (!for_rename) + return; + /* - * if this directory was already logged any new - * names for this file/dir will get recorded + * If this directory was already logged, any new names will be logged + * with btrfs_log_new_name() and old names will be deleted from the log + * tree with btrfs_del_dir_entries_in_log() or with + * btrfs_del_inode_ref_in_log(). */ - if (dir->logged_trans == trans->transid) + if (inode_logged(trans, dir, NULL) == 1) return; /* - * if the inode we're about to unlink was logged, - * the log will be properly updated for any new names + * If the inode we're about to unlink was logged before, the log will be + * properly updated with the new name with btrfs_log_new_name() and the + * old name removed with btrfs_del_dir_entries_in_log() or with + * btrfs_del_inode_ref_in_log(). */ - if (inode->logged_trans == trans->transid) + if (inode_logged(trans, inode, NULL) == 1) return; /* @@ -7346,13 +7353,6 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * properly. So, we have to be conservative and force commits * so the new name gets discovered. */ - if (for_rename) - goto record; - - /* we can safely do the unlink without any special recording */ - return; - -record: mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index bdeb5216718f..a550a8a375cd 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -100,7 +100,7 @@ void btrfs_end_log_trans(struct btrfs_root *root); void btrfs_pin_log_trans(struct btrfs_root *root); void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, - int for_rename); + bool for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir); void btrfs_log_new_name(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c index a555baa0143a..3df6153d5d5a 100644 --- a/fs/btrfs/tree-mod-log.c +++ b/fs/btrfs/tree-mod-log.c @@ -226,21 +226,32 @@ int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot, enum btrfs_mod_log_op op) { struct tree_mod_elem *tm; - int ret; + int ret = 0; if (!tree_mod_need_log(eb->fs_info, eb)) return 0; tm = alloc_tree_mod_elem(eb, slot, op); if (!tm) - return -ENOMEM; + ret = -ENOMEM; if (tree_mod_dont_log(eb->fs_info, eb)) { kfree(tm); + /* + * Don't error if we failed to allocate memory because we don't + * need to log. + */ return 0; + } else if (ret != 0) { + /* + * We previously failed to allocate memory and we need to log, + * so we have to fail. + */ + goto out_unlock; } ret = tree_mod_log_insert(eb->fs_info, tm); +out_unlock: write_unlock(&eb->fs_info->tree_mod_log_lock); if (ret) kfree(tm); @@ -248,6 +259,26 @@ int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot, return ret; } +static struct tree_mod_elem *tree_mod_log_alloc_move(struct extent_buffer *eb, + int dst_slot, int src_slot, + int nr_items) +{ + struct tree_mod_elem *tm; + + tm = kzalloc(sizeof(*tm), GFP_NOFS); + if (!tm) + return ERR_PTR(-ENOMEM); + + tm->logical = eb->start; + tm->slot = src_slot; + tm->move.dst_slot = dst_slot; + tm->move.nr_items = nr_items; + tm->op = BTRFS_MOD_LOG_MOVE_KEYS; + RB_CLEAR_NODE(&tm->node); + + return tm; +} + int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb, int dst_slot, int src_slot, int nr_items) @@ -262,35 +293,46 @@ int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb, return 0; tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), GFP_NOFS); - if (!tm_list) - return -ENOMEM; - - tm = kzalloc(sizeof(*tm), GFP_NOFS); - if (!tm) { + if (!tm_list) { ret = -ENOMEM; - goto free_tms; + goto lock; } - tm->logical = eb->start; - tm->slot = src_slot; - tm->move.dst_slot = dst_slot; - tm->move.nr_items = nr_items; - tm->op = BTRFS_MOD_LOG_MOVE_KEYS; + tm = tree_mod_log_alloc_move(eb, dst_slot, src_slot, nr_items); + if (IS_ERR(tm)) { + ret = PTR_ERR(tm); + tm = NULL; + goto lock; + } for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot, BTRFS_MOD_LOG_KEY_REMOVE_WHILE_MOVING); if (!tm_list[i]) { ret = -ENOMEM; - goto free_tms; + goto lock; } } - if (tree_mod_dont_log(eb->fs_info, eb)) +lock: + if (tree_mod_dont_log(eb->fs_info, eb)) { + /* + * Don't error if we failed to allocate memory because we don't + * need to log. + */ + ret = 0; goto free_tms; + } locked = true; /* + * We previously failed to allocate memory and we need to log, so we + * have to fail. + */ + if (ret != 0) + goto free_tms; + + /* * When we override something during the move, we log these removals. * This can only happen when we move towards the beginning of the * buffer, i.e. dst_slot < src_slot. @@ -310,10 +352,12 @@ int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb, return 0; free_tms: - for (i = 0; i < nr_items; i++) { - if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) - rb_erase(&tm_list[i]->node, &eb->fs_info->tree_mod_log); - kfree(tm_list[i]); + if (tm_list) { + for (i = 0; i < nr_items; i++) { + if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) + rb_erase(&tm_list[i]->node, &eb->fs_info->tree_mod_log); + kfree(tm_list[i]); + } } if (locked) write_unlock(&eb->fs_info->tree_mod_log_lock); @@ -363,14 +407,14 @@ int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root, GFP_NOFS); if (!tm_list) { ret = -ENOMEM; - goto free_tms; + goto lock; } for (i = 0; i < nritems; i++) { tm_list[i] = alloc_tree_mod_elem(old_root, i, BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING); if (!tm_list[i]) { ret = -ENOMEM; - goto free_tms; + goto lock; } } } @@ -378,7 +422,7 @@ int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root, tm = kzalloc(sizeof(*tm), GFP_NOFS); if (!tm) { ret = -ENOMEM; - goto free_tms; + goto lock; } tm->logical = new_root->start; @@ -387,14 +431,28 @@ int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root, tm->generation = btrfs_header_generation(old_root); tm->op = BTRFS_MOD_LOG_ROOT_REPLACE; - if (tree_mod_dont_log(fs_info, NULL)) +lock: + if (tree_mod_dont_log(fs_info, NULL)) { + /* + * Don't error if we failed to allocate memory because we don't + * need to log. + */ + ret = 0; goto free_tms; + } else if (ret != 0) { + /* + * We previously failed to allocate memory and we need to log, + * so we have to fail. + */ + goto out_unlock; + } if (tm_list) ret = tree_mod_log_free_eb(fs_info, tm_list, nritems); if (!ret) ret = tree_mod_log_insert(fs_info, tm); +out_unlock: write_unlock(&fs_info->tree_mod_log_lock); if (ret) goto free_tms; @@ -486,9 +544,14 @@ int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, struct btrfs_fs_info *fs_info = dst->fs_info; int ret = 0; struct tree_mod_elem **tm_list = NULL; - struct tree_mod_elem **tm_list_add, **tm_list_rem; + struct tree_mod_elem **tm_list_add = NULL; + struct tree_mod_elem **tm_list_rem = NULL; int i; bool locked = false; + struct tree_mod_elem *dst_move_tm = NULL; + struct tree_mod_elem *src_move_tm = NULL; + u32 dst_move_nr_items = btrfs_header_nritems(dst) - dst_offset; + u32 src_move_nr_items = btrfs_header_nritems(src) - (src_offset + nr_items); if (!tree_mod_need_log(fs_info, NULL)) return 0; @@ -498,8 +561,30 @@ int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, tm_list = kcalloc(nr_items * 2, sizeof(struct tree_mod_elem *), GFP_NOFS); - if (!tm_list) - return -ENOMEM; + if (!tm_list) { + ret = -ENOMEM; + goto lock; + } + + if (dst_move_nr_items) { + dst_move_tm = tree_mod_log_alloc_move(dst, dst_offset + nr_items, + dst_offset, dst_move_nr_items); + if (IS_ERR(dst_move_tm)) { + ret = PTR_ERR(dst_move_tm); + dst_move_tm = NULL; + goto lock; + } + } + if (src_move_nr_items) { + src_move_tm = tree_mod_log_alloc_move(src, src_offset, + src_offset + nr_items, + src_move_nr_items); + if (IS_ERR(src_move_tm)) { + ret = PTR_ERR(src_move_tm); + src_move_tm = NULL; + goto lock; + } + } tm_list_add = tm_list; tm_list_rem = tm_list + nr_items; @@ -508,21 +593,40 @@ int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, BTRFS_MOD_LOG_KEY_REMOVE); if (!tm_list_rem[i]) { ret = -ENOMEM; - goto free_tms; + goto lock; } tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset, BTRFS_MOD_LOG_KEY_ADD); if (!tm_list_add[i]) { ret = -ENOMEM; - goto free_tms; + goto lock; } } - if (tree_mod_dont_log(fs_info, NULL)) +lock: + if (tree_mod_dont_log(fs_info, NULL)) { + /* + * Don't error if we failed to allocate memory because we don't + * need to log. + */ + ret = 0; goto free_tms; + } locked = true; + /* + * We previously failed to allocate memory and we need to log, so we + * have to fail. + */ + if (ret != 0) + goto free_tms; + + if (dst_move_tm) { + ret = tree_mod_log_insert(fs_info, dst_move_tm); + if (ret) + goto free_tms; + } for (i = 0; i < nr_items; i++) { ret = tree_mod_log_insert(fs_info, tm_list_rem[i]); if (ret) @@ -531,6 +635,11 @@ int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, if (ret) goto free_tms; } + if (src_move_tm) { + ret = tree_mod_log_insert(fs_info, src_move_tm); + if (ret) + goto free_tms; + } write_unlock(&fs_info->tree_mod_log_lock); kfree(tm_list); @@ -538,10 +647,18 @@ int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, return 0; free_tms: - for (i = 0; i < nr_items * 2; i++) { - if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) - rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log); - kfree(tm_list[i]); + if (dst_move_tm && !RB_EMPTY_NODE(&dst_move_tm->node)) + rb_erase(&dst_move_tm->node, &fs_info->tree_mod_log); + kfree(dst_move_tm); + if (src_move_tm && !RB_EMPTY_NODE(&src_move_tm->node)) + rb_erase(&src_move_tm->node, &fs_info->tree_mod_log); + kfree(src_move_tm); + if (tm_list) { + for (i = 0; i < nr_items * 2; i++) { + if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node)) + rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log); + kfree(tm_list[i]); + } } if (locked) write_unlock(&fs_info->tree_mod_log_lock); @@ -562,22 +679,38 @@ int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb) nritems = btrfs_header_nritems(eb); tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), GFP_NOFS); - if (!tm_list) - return -ENOMEM; + if (!tm_list) { + ret = -ENOMEM; + goto lock; + } for (i = 0; i < nritems; i++) { tm_list[i] = alloc_tree_mod_elem(eb, i, BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING); if (!tm_list[i]) { ret = -ENOMEM; - goto free_tms; + goto lock; } } - if (tree_mod_dont_log(eb->fs_info, eb)) +lock: + if (tree_mod_dont_log(eb->fs_info, eb)) { + /* + * Don't error if we failed to allocate memory because we don't + * need to log. + */ + ret = 0; goto free_tms; + } else if (ret != 0) { + /* + * We previously failed to allocate memory and we need to log, + * so we have to fail. + */ + goto out_unlock; + } ret = tree_mod_log_free_eb(eb->fs_info, tm_list, nritems); +out_unlock: write_unlock(&eb->fs_info->tree_mod_log_lock); if (ret) goto free_tms; @@ -586,9 +719,11 @@ int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb) return 0; free_tms: - for (i = 0; i < nritems; i++) - kfree(tm_list[i]); - kfree(tm_list); + if (tm_list) { + for (i = 0; i < nritems; i++) + kfree(tm_list[i]); + kfree(tm_list); + } return ret; } @@ -664,10 +799,27 @@ static void tree_mod_log_rewind(struct btrfs_fs_info *fs_info, unsigned long o_dst; unsigned long o_src; unsigned long p_size = sizeof(struct btrfs_key_ptr); + /* + * max_slot tracks the maximum valid slot of the rewind eb at every + * step of the rewind. This is in contrast with 'n' which eventually + * matches the number of items, but can be wrong during moves or if + * removes overlap on already valid slots (which is probably separately + * a bug). We do this to validate the offsets of memmoves for rewinding + * moves and detect invalid memmoves. + * + * Since a rewind eb can start empty, max_slot is a signed integer with + * a special meaning for -1, which is that no slot is valid to move out + * of. Any other negative value is invalid. + */ + int max_slot; + int move_src_end_slot; + int move_dst_end_slot; n = btrfs_header_nritems(eb); + max_slot = n - 1; read_lock(&fs_info->tree_mod_log_lock); while (tm && tm->seq >= time_seq) { + ASSERT(max_slot >= -1); /* * All the operations are recorded with the operator used for * the modification. As we're going backwards, we do the @@ -684,6 +836,8 @@ static void tree_mod_log_rewind(struct btrfs_fs_info *fs_info, btrfs_set_node_ptr_generation(eb, tm->slot, tm->generation); n++; + if (tm->slot > max_slot) + max_slot = tm->slot; break; case BTRFS_MOD_LOG_KEY_REPLACE: BUG_ON(tm->slot >= n); @@ -693,14 +847,37 @@ static void tree_mod_log_rewind(struct btrfs_fs_info *fs_info, tm->generation); break; case BTRFS_MOD_LOG_KEY_ADD: + /* + * It is possible we could have already removed keys + * behind the known max slot, so this will be an + * overestimate. In practice, the copy operation + * inserts them in increasing order, and overestimating + * just means we miss some warnings, so it's OK. It + * isn't worth carefully tracking the full array of + * valid slots to check against when moving. + */ + if (tm->slot == max_slot) + max_slot--; /* if a move operation is needed it's in the log */ n--; break; case BTRFS_MOD_LOG_MOVE_KEYS: + ASSERT(tm->move.nr_items > 0); + move_src_end_slot = tm->move.dst_slot + tm->move.nr_items - 1; + move_dst_end_slot = tm->slot + tm->move.nr_items - 1; o_dst = btrfs_node_key_ptr_offset(eb, tm->slot); o_src = btrfs_node_key_ptr_offset(eb, tm->move.dst_slot); + if (WARN_ON(move_src_end_slot > max_slot || + tm->move.nr_items <= 0)) { + btrfs_warn(fs_info, +"move from invalid tree mod log slot eb %llu slot %d dst_slot %d nr_items %d seq %llu n %u max_slot %d", + eb->start, tm->slot, + tm->move.dst_slot, tm->move.nr_items, + tm->seq, n, max_slot); + } memmove_extent_buffer(eb, o_dst, o_src, tm->move.nr_items * p_size); + max_slot = move_dst_end_slot; break; case BTRFS_MOD_LOG_ROOT_REPLACE: /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 841e799dece5..73f9ea7672db 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -370,6 +370,8 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid, { struct btrfs_fs_devices *fs_devs; + ASSERT(fsid || !metadata_fsid); + fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL); if (!fs_devs) return ERR_PTR(-ENOMEM); @@ -380,18 +382,17 @@ static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid, INIT_LIST_HEAD(&fs_devs->alloc_list); INIT_LIST_HEAD(&fs_devs->fs_list); INIT_LIST_HEAD(&fs_devs->seed_list); - if (fsid) - memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE); - if (metadata_fsid) - memcpy(fs_devs->metadata_uuid, metadata_fsid, BTRFS_FSID_SIZE); - else if (fsid) - memcpy(fs_devs->metadata_uuid, fsid, BTRFS_FSID_SIZE); + if (fsid) { + memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE); + memcpy(fs_devs->metadata_uuid, + metadata_fsid ?: fsid, BTRFS_FSID_SIZE); + } return fs_devs; } -void btrfs_free_device(struct btrfs_device *device) +static void btrfs_free_device(struct btrfs_device *device) { WARN_ON(!list_empty(&device->post_commit_list)); rcu_string_free(device->name); @@ -426,6 +427,21 @@ void __exit btrfs_cleanup_fs_uuids(void) } } +static bool match_fsid_fs_devices(const struct btrfs_fs_devices *fs_devices, + const u8 *fsid, const u8 *metadata_fsid) +{ + if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) != 0) + return false; + + if (!metadata_fsid) + return true; + + if (memcmp(metadata_fsid, fs_devices->metadata_uuid, BTRFS_FSID_SIZE) != 0) + return false; + + return true; +} + static noinline struct btrfs_fs_devices *find_fsid( const u8 *fsid, const u8 *metadata_fsid) { @@ -435,19 +451,25 @@ static noinline struct btrfs_fs_devices *find_fsid( /* Handle non-split brain cases */ list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (metadata_fsid) { - if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0 - && memcmp(metadata_fsid, fs_devices->metadata_uuid, - BTRFS_FSID_SIZE) == 0) - return fs_devices; - } else { - if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0) - return fs_devices; - } + if (match_fsid_fs_devices(fs_devices, fsid, metadata_fsid)) + return fs_devices; } return NULL; } +/* + * First check if the metadata_uuid is different from the fsid in the given + * fs_devices. Then check if the given fsid is the same as the metadata_uuid + * in the fs_devices. If it is, return true; otherwise, return false. + */ +static inline bool check_fsid_changed(const struct btrfs_fs_devices *fs_devices, + const u8 *fsid) +{ + return memcmp(fs_devices->fsid, fs_devices->metadata_uuid, + BTRFS_FSID_SIZE) != 0 && + memcmp(fs_devices->metadata_uuid, fsid, BTRFS_FSID_SIZE) == 0; +} + static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( struct btrfs_super_block *disk_super) { @@ -461,14 +483,14 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( * at all and the CHANGING_FSID_V2 flag set. */ list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (fs_devices->fsid_change && - memcmp(disk_super->metadata_uuid, fs_devices->fsid, - BTRFS_FSID_SIZE) == 0 && - memcmp(fs_devices->fsid, fs_devices->metadata_uuid, - BTRFS_FSID_SIZE) == 0) { + if (!fs_devices->fsid_change) + continue; + + if (match_fsid_fs_devices(fs_devices, disk_super->metadata_uuid, + fs_devices->fsid)) return fs_devices; - } } + /* * Handle scanned device having completed its fsid change but * belonging to a fs_devices that was created by a device that @@ -476,13 +498,11 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( * CHANGING_FSID_V2 flag set. */ list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (fs_devices->fsid_change && - memcmp(fs_devices->metadata_uuid, - fs_devices->fsid, BTRFS_FSID_SIZE) != 0 && - memcmp(disk_super->metadata_uuid, fs_devices->metadata_uuid, - BTRFS_FSID_SIZE) == 0) { + if (!fs_devices->fsid_change) + continue; + + if (check_fsid_changed(fs_devices, disk_super->metadata_uuid)) return fs_devices; - } } return find_fsid(disk_super->fsid, disk_super->metadata_uuid); @@ -490,13 +510,13 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( static int -btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, +btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, int flush, struct block_device **bdev, struct btrfs_super_block **disk_super) { int ret; - *bdev = blkdev_get_by_path(device_path, flags, holder); + *bdev = blkdev_get_by_path(device_path, flags, holder, NULL); if (IS_ERR(*bdev)) { ret = PTR_ERR(*bdev); @@ -507,14 +527,14 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, sync_blockdev(*bdev); ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { - blkdev_put(*bdev, flags); + blkdev_put(*bdev, holder); goto error; } invalidate_bdev(*bdev); *disk_super = btrfs_read_dev_super(*bdev); if (IS_ERR(*disk_super)) { ret = PTR_ERR(*disk_super); - blkdev_put(*bdev, flags); + blkdev_put(*bdev, holder); goto error; } @@ -590,7 +610,7 @@ static int btrfs_free_stale_devices(dev_t devt, struct btrfs_device *skip_device * fs_devices->device_list_mutex here. */ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, - struct btrfs_device *device, fmode_t flags, + struct btrfs_device *device, blk_mode_t flags, void *holder) { struct block_device *bdev; @@ -642,7 +662,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, device->bdev = bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); - device->mode = flags; + device->holder = holder; fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && @@ -656,7 +676,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, error_free_page: btrfs_release_disk_super(disk_super); - blkdev_put(bdev, flags); + blkdev_put(bdev, holder); return -EINVAL; } @@ -673,18 +693,16 @@ static struct btrfs_fs_devices *find_fsid_inprogress( struct btrfs_fs_devices *fs_devices; list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid, - BTRFS_FSID_SIZE) != 0 && - memcmp(fs_devices->metadata_uuid, disk_super->fsid, - BTRFS_FSID_SIZE) == 0 && !fs_devices->fsid_change) { + if (fs_devices->fsid_change) + continue; + + if (check_fsid_changed(fs_devices, disk_super->fsid)) return fs_devices; - } } return find_fsid(disk_super->fsid, NULL); } - static struct btrfs_fs_devices *find_fsid_changed( struct btrfs_super_block *disk_super) { @@ -701,10 +719,7 @@ static struct btrfs_fs_devices *find_fsid_changed( */ list_for_each_entry(fs_devices, &fs_uuids, fs_list) { /* Changed UUIDs */ - if (memcmp(fs_devices->metadata_uuid, fs_devices->fsid, - BTRFS_FSID_SIZE) != 0 && - memcmp(fs_devices->metadata_uuid, disk_super->metadata_uuid, - BTRFS_FSID_SIZE) == 0 && + if (check_fsid_changed(fs_devices, disk_super->metadata_uuid) && memcmp(fs_devices->fsid, disk_super->fsid, BTRFS_FSID_SIZE) != 0) return fs_devices; @@ -735,11 +750,10 @@ static struct btrfs_fs_devices *find_fsid_reverted_metadata( * fs_devices equal to the FSID of the disk. */ list_for_each_entry(fs_devices, &fs_uuids, fs_list) { - if (memcmp(fs_devices->fsid, fs_devices->metadata_uuid, - BTRFS_FSID_SIZE) != 0 && - memcmp(fs_devices->metadata_uuid, disk_super->fsid, - BTRFS_FSID_SIZE) == 0 && - fs_devices->fsid_change) + if (!fs_devices->fsid_change) + continue; + + if (check_fsid_changed(fs_devices, disk_super->fsid)) return fs_devices; } @@ -790,12 +804,8 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (!fs_devices) { - if (has_metadata_uuid) - fs_devices = alloc_fs_devices(disk_super->fsid, - disk_super->metadata_uuid); - else - fs_devices = alloc_fs_devices(disk_super->fsid, NULL); - + fs_devices = alloc_fs_devices(disk_super->fsid, + has_metadata_uuid ? disk_super->metadata_uuid : NULL); if (IS_ERR(fs_devices)) return ERR_CAST(fs_devices); @@ -1057,7 +1067,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; if (device->bdev) { - blkdev_put(device->bdev, device->mode); + blkdev_put(device->bdev, device->holder); device->bdev = NULL; fs_devices->open_devices--; } @@ -1103,7 +1113,7 @@ static void btrfs_close_bdev(struct btrfs_device *device) invalidate_bdev(device->bdev); } - blkdev_put(device->bdev, device->mode); + blkdev_put(device->bdev, device->holder); } static void btrfs_close_one_device(struct btrfs_device *device) @@ -1207,14 +1217,12 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices) } static int open_fs_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder) + blk_mode_t flags, void *holder) { struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; - flags |= FMODE_EXCL; - list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, dev_list) { int ret; @@ -1257,7 +1265,7 @@ static int devid_cmp(void *priv, const struct list_head *a, } int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder) + blk_mode_t flags, void *holder) { int ret; @@ -1348,8 +1356,7 @@ int btrfs_forget_devices(dev_t devt) * and we are not allowed to call set_blocksize during the scan. The superblock * is read via pagecache */ -struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, - void *holder) +struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) { struct btrfs_super_block *disk_super; bool new_device_added = false; @@ -1368,16 +1375,16 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, */ /* - * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may - * initiate the device scan which may race with the user's mount - * or mkfs command, resulting in failure. - * Since the device scan is solely for reading purposes, there is - * no need for FMODE_EXCL. Additionally, the devices are read again + * Avoid an exclusive open here, as the systemd-udev may initiate the + * device scan which may race with the user's mount or mkfs command, + * resulting in failure. + * Since the device scan is solely for reading purposes, there is no + * need for an exclusive open. Additionally, the devices are read again * during the mount process. It is ok to get some inconsistent * values temporarily, as the device paths of the fsid are the only * required information for assembling the volume. */ - bdev = blkdev_get_by_path(path, flags, holder); + bdev = blkdev_get_by_path(path, flags, NULL, NULL); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -1401,7 +1408,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, btrfs_release_disk_super(disk_super); error_bdev_put: - blkdev_put(bdev, flags); + blkdev_put(bdev, NULL); return device; } @@ -1918,7 +1925,7 @@ static void update_dev_time(const char *device_path) return; now = current_time(d_inode(path.dentry)); - inode_update_time(d_inode(path.dentry), &now, S_MTIME | S_CTIME); + inode_update_time(d_inode(path.dentry), &now, S_MTIME | S_CTIME | S_VERSION); path_put(&path); } @@ -2088,7 +2095,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, fmode_t *mode) + struct block_device **bdev, void **holder) { struct btrfs_trans_handle *trans; struct btrfs_device *device; @@ -2227,7 +2234,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, } *bdev = device->bdev; - *mode = device->mode; + *holder = device->holder; synchronize_rcu(); btrfs_free_device(device); @@ -2381,7 +2388,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, return -ENOMEM; } - ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0, + ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0, &bdev, &disk_super); if (ret) { btrfs_put_dev_args_from_path(args); @@ -2395,7 +2402,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, else memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE); btrfs_release_disk_super(disk_super); - blkdev_put(bdev, FMODE_READ); + blkdev_put(bdev, NULL); return 0; } @@ -2628,8 +2635,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (sb_rdonly(sb) && !fs_devices->seeding) return -EROFS; - bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, - fs_info->bdev_holder); + bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -2691,7 +2698,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->commit_total_bytes = device->total_bytes; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->mode = FMODE_EXCL; + device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); @@ -2849,7 +2856,7 @@ error_free_zone: error_free_device: btrfs_free_device(device); error: - blkdev_put(bdev, FMODE_EXCL); + blkdev_put(bdev, fs_info->bdev_holder); if (locked) { mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); @@ -5125,7 +5132,7 @@ static void init_alloc_chunk_ctl_policy_regular( /* We don't want a chunk larger than 10% of writable space */ ctl->max_chunk_size = min(mult_perc(fs_devices->total_rw_bytes, 10), ctl->max_chunk_size); - ctl->dev_extent_min = ctl->dev_stripes << BTRFS_STRIPE_LEN_SHIFT; + ctl->dev_extent_min = btrfs_stripe_nr_to_offset(ctl->dev_stripes); } static void init_alloc_chunk_ctl_policy_zoned( @@ -5801,7 +5808,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, if (!WARN_ON(IS_ERR(em))) { map = em->map_lookup; if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) - len = nr_data_stripes(map) << BTRFS_STRIPE_LEN_SHIFT; + len = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); free_extent_map(em); } return len; @@ -5975,12 +5982,12 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info, stripe_nr = offset >> BTRFS_STRIPE_LEN_SHIFT; /* stripe_offset is the offset of this block in its stripe */ - stripe_offset = offset - (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset = offset - btrfs_stripe_nr_to_offset(stripe_nr); stripe_nr_end = round_up(offset + length, BTRFS_STRIPE_LEN) >> BTRFS_STRIPE_LEN_SHIFT; stripe_cnt = stripe_nr_end - stripe_nr; - stripe_end_offset = (stripe_nr_end << BTRFS_STRIPE_LEN_SHIFT) - + stripe_end_offset = btrfs_stripe_nr_to_offset(stripe_nr_end) - (offset + length); /* * after this, stripe_nr is the number of stripes on this @@ -6023,12 +6030,12 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info, for (i = 0; i < *num_stripes; i++) { stripes[i].physical = map->stripes[stripe_index].physical + - stripe_offset + (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset + btrfs_stripe_nr_to_offset(stripe_nr); stripes[i].dev = map->stripes[stripe_index].dev; if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { - stripes[i].length = stripes_per_dev << BTRFS_STRIPE_LEN_SHIFT; + stripes[i].length = btrfs_stripe_nr_to_offset(stripes_per_dev); if (i / sub_stripes < remaining_stripes) stripes[i].length += BTRFS_STRIPE_LEN; @@ -6163,17 +6170,10 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op, bioc->replace_nr_stripes = nr_extra_stripes; } -static bool need_full_stripe(enum btrfs_map_op op) -{ - return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS); -} - static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op, u64 offset, u32 *stripe_nr, u64 *stripe_offset, u64 *full_stripe_start) { - ASSERT(op != BTRFS_MAP_DISCARD); - /* * Stripe_nr is the stripe where this block falls. stripe_offset is * the offset of this block in its stripe. @@ -6183,8 +6183,8 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op, ASSERT(*stripe_offset < U32_MAX); if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - unsigned long full_stripe_len = nr_data_stripes(map) << - BTRFS_STRIPE_LEN_SHIFT; + unsigned long full_stripe_len = + btrfs_stripe_nr_to_offset(nr_data_stripes(map)); /* * For full stripe start, we use previously calculated @@ -6196,9 +6196,11 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op, * not ensured to be power of 2. */ *full_stripe_start = - rounddown(*stripe_nr, nr_data_stripes(map)) << - BTRFS_STRIPE_LEN_SHIFT; + btrfs_stripe_nr_to_offset( + rounddown(*stripe_nr, nr_data_stripes(map))); + ASSERT(*full_stripe_start + full_stripe_len > offset); + ASSERT(*full_stripe_start <= offset); /* * For writes to RAID56, allow to write a full stripe set, but * no straddling of stripe sets. @@ -6221,14 +6223,14 @@ static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup * { dst->dev = map->stripes[stripe_index].dev; dst->physical = map->stripes[stripe_index].physical + - stripe_offset + (stripe_nr << BTRFS_STRIPE_LEN_SHIFT); + stripe_offset + btrfs_stripe_nr_to_offset(stripe_nr); } -int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret, - struct btrfs_io_stripe *smap, int *mirror_num_ret, - int need_raid_map) +int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, + u64 logical, u64 *length, + struct btrfs_io_context **bioc_ret, + struct btrfs_io_stripe *smap, int *mirror_num_ret, + int need_raid_map) { struct extent_map *em; struct map_lookup *map; @@ -6251,7 +6253,6 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 max_len; ASSERT(bioc_ret); - ASSERT(op != BTRFS_MAP_DISCARD); num_copies = btrfs_num_copies(fs_info, logical, fs_info->sectorsize); if (mirror_num > num_copies) @@ -6283,21 +6284,21 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, if (map->type & BTRFS_BLOCK_GROUP_RAID0) { stripe_index = stripe_nr % map->num_stripes; stripe_nr /= map->num_stripes; - if (!need_full_stripe(op)) + if (op == BTRFS_MAP_READ) mirror_num = 1; } else if (map->type & BTRFS_BLOCK_GROUP_RAID1_MASK) { - if (need_full_stripe(op)) + if (op != BTRFS_MAP_READ) { num_stripes = map->num_stripes; - else if (mirror_num) + } else if (mirror_num) { stripe_index = mirror_num - 1; - else { + } else { stripe_index = find_live_mirror(fs_info, map, 0, dev_replace_is_ongoing); mirror_num = stripe_index + 1; } } else if (map->type & BTRFS_BLOCK_GROUP_DUP) { - if (need_full_stripe(op)) { + if (op != BTRFS_MAP_READ) { num_stripes = map->num_stripes; } else if (mirror_num) { stripe_index = mirror_num - 1; @@ -6311,7 +6312,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, stripe_index = (stripe_nr % factor) * map->sub_stripes; stripe_nr /= factor; - if (need_full_stripe(op)) + if (op != BTRFS_MAP_READ) num_stripes = map->sub_stripes; else if (mirror_num) stripe_index += mirror_num - 1; @@ -6324,7 +6325,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, } } else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { - if (need_raid_map && (need_full_stripe(op) || mirror_num > 1)) { + if (need_raid_map && (op != BTRFS_MAP_READ || mirror_num > 1)) { /* * Push stripe_nr back to the start of the full stripe * For those cases needing a full stripe, @stripe_nr @@ -6343,7 +6344,8 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, /* Return the length to the full stripe end */ *length = min(logical + *length, raid56_full_stripe_start + em->start + - (data_stripes << BTRFS_STRIPE_LEN_SHIFT)) - logical; + btrfs_stripe_nr_to_offset(data_stripes)) - + logical; stripe_index = 0; stripe_offset = 0; } else { @@ -6359,7 +6361,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, /* We distribute the parity blocks across stripes */ stripe_index = (stripe_nr + stripe_index) % map->num_stripes; - if (!need_full_stripe(op) && mirror_num <= 1) + if (op == BTRFS_MAP_READ && mirror_num <= 1) mirror_num = 1; } } else { @@ -6399,7 +6401,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, */ if (smap && num_alloc_stripes == 1 && !((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) && mirror_num > 1) && - (!need_full_stripe(op) || !dev_replace_is_ongoing || + (op == BTRFS_MAP_READ || !dev_replace_is_ongoing || !dev_replace->tgtdev)) { set_io_stripe(smap, map, stripe_index, stripe_offset, stripe_nr); *mirror_num_ret = mirror_num; @@ -6423,7 +6425,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, * It's still mostly the same as other profiles, just with extra rotation. */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map && - (need_full_stripe(op) || mirror_num > 1)) { + (op != BTRFS_MAP_READ || mirror_num > 1)) { /* * For RAID56 @stripe_nr is already the number of full stripes * before us, which is also the rotation value (needs to modulo @@ -6433,7 +6435,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, * modulo, to reduce one modulo call. */ bioc->full_stripe_logical = em->start + - ((stripe_nr * data_stripes) << BTRFS_STRIPE_LEN_SHIFT); + btrfs_stripe_nr_to_offset(stripe_nr * data_stripes); for (i = 0; i < num_stripes; i++) set_io_stripe(&bioc->stripes[i], map, (i + stripe_nr) % num_stripes, @@ -6450,11 +6452,11 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, } } - if (need_full_stripe(op)) + if (op != BTRFS_MAP_READ) max_errors = btrfs_chunk_max_errors(map); if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL && - need_full_stripe(op)) { + op != BTRFS_MAP_READ) { handle_ops_on_dev_replace(op, bioc, dev_replace, logical, &num_stripes, &max_errors); } @@ -6474,23 +6476,6 @@ out: return ret; } -int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret, int mirror_num) -{ - return __btrfs_map_block(fs_info, op, logical, length, bioc_ret, - NULL, &mirror_num, 0); -} - -/* For Scrub/replace */ -int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret) -{ - return __btrfs_map_block(fs_info, op, logical, length, bioc_ret, - NULL, NULL, 1); -} - static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args, const struct btrfs_fs_devices *fs_devices) { @@ -6910,7 +6895,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, if (IS_ERR(fs_devices)) return fs_devices; - ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder); + ret = open_fs_devices(fs_devices, BLK_OPEN_READ, fs_info->bdev_holder); if (ret) { free_fs_devices(fs_devices); return ERR_PTR(ret); @@ -8030,7 +8015,7 @@ static void map_raid56_repair_block(struct btrfs_io_context *bioc, for (i = 0; i < data_stripes; i++) { u64 stripe_start = bioc->full_stripe_logical + - (i << BTRFS_STRIPE_LEN_SHIFT); + btrfs_stripe_nr_to_offset(i); if (logical >= stripe_start && logical < stripe_start + BTRFS_STRIPE_LEN) @@ -8067,8 +8052,8 @@ int btrfs_map_repair_block(struct btrfs_fs_info *fs_info, ASSERT(mirror_num > 0); - ret = __btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length, - &bioc, smap, &mirror_ret, true); + ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical, &map_length, + &bioc, smap, &mirror_ret, true); if (ret < 0) return ret; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bf47a1a70813..b8c51f16ba86 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -94,8 +94,8 @@ struct btrfs_device { struct btrfs_zoned_device_info *zone_info; - /* the mode sent to blkdev_get */ - fmode_t mode; + /* block device holder for blkdev_get/put */ + void *holder; /* * Device's major-minor number. Must be set even if the device is not @@ -280,8 +280,19 @@ enum btrfs_read_policy { struct btrfs_fs_devices { u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ + + /* + * UUID written into the btree blocks: + * + * - If metadata_uuid != fsid then super block must have + * BTRFS_FEATURE_INCOMPAT_METADATA_UUID flag set. + * + * - Following shall be true at all times: + * - metadata_uuid == btrfs_header::fsid + * - metadata_uuid == btrfs_dev_item::fsid + */ u8 metadata_uuid[BTRFS_FSID_SIZE]; - bool fsid_change; + struct list_head fs_list; /* @@ -319,34 +330,32 @@ struct btrfs_fs_devices { */ struct btrfs_device *latest_dev; - /* all of the devices in the FS, protected by a mutex - * so we can safely walk it to write out the supers without - * worrying about add/remove by the multi-device code. - * Scrubbing super can kick off supers writing by holding - * this mutex lock. + /* + * All of the devices in the filesystem, protected by a mutex so we can + * safely walk it to write out the super blocks without worrying about + * adding/removing by the multi-device code. Scrubbing super block can + * kick off supers writing by holding this mutex lock. */ struct mutex device_list_mutex; /* List of all devices, protected by device_list_mutex */ struct list_head devices; - /* - * Devices which can satisfy space allocation. Protected by - * chunk_mutex - */ + /* Devices which can satisfy space allocation. Protected by * chunk_mutex. */ struct list_head alloc_list; struct list_head seed_list; - bool seeding; + /* Count fs-devices opened. */ int opened; - /* set when we find or add a device that doesn't have the - * nonrot flag set - */ + /* Set when we find or add a device that doesn't have the nonrot flag set. */ bool rotating; - /* Devices support TRIM/discard commands */ + /* Devices support TRIM/discard commands. */ bool discardable; + bool fsid_change; + /* The filesystem is a seed filesystem. */ + bool seeding; struct btrfs_fs_info *fs_info; /* sysfs kobjects */ @@ -357,7 +366,7 @@ struct btrfs_fs_devices { enum btrfs_chunk_allocation_policy chunk_alloc_policy; - /* Policy used to read the mirrored stripes */ + /* Policy used to read the mirrored stripes. */ enum btrfs_read_policy read_policy; }; @@ -547,15 +556,12 @@ struct btrfs_dev_lookup_args { enum btrfs_map_op { BTRFS_MAP_READ, BTRFS_MAP_WRITE, - BTRFS_MAP_DISCARD, BTRFS_MAP_GET_READ_MIRRORS, }; static inline enum btrfs_map_op btrfs_op(struct bio *bio) { switch (bio_op(bio)) { - case REQ_OP_DISCARD: - return BTRFS_MAP_DISCARD; case REQ_OP_WRITE: case REQ_OP_ZONE_APPEND: return BTRFS_MAP_WRITE; @@ -574,19 +580,24 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes) sizeof(struct btrfs_stripe) * (num_stripes - 1); } +/* + * Do the type safe converstion from stripe_nr to offset inside the chunk. + * + * @stripe_nr is u32, with left shift it can overflow u32 for chunks larger + * than 4G. This does the proper type cast to avoid overflow. + */ +static inline u64 btrfs_stripe_nr_to_offset(u32 stripe_nr) +{ + return (u64)stripe_nr << BTRFS_STRIPE_LEN_SHIFT; +} + void btrfs_get_bioc(struct btrfs_io_context *bioc); void btrfs_put_bioc(struct btrfs_io_context *bioc); int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret, int mirror_num); -int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret); -int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 *length, - struct btrfs_io_context **bioc_ret, - struct btrfs_io_stripe *smap, int *mirror_num_ret, - int need_raid_map); + struct btrfs_io_context **bioc_ret, + struct btrfs_io_stripe *smap, int *mirror_num_ret, + int need_raid_map); int btrfs_map_repair_block(struct btrfs_fs_info *fs_info, struct btrfs_io_stripe *smap, u64 logical, u32 length, int mirror_num); @@ -599,9 +610,8 @@ struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans, u64 type); void btrfs_mapping_tree_free(struct extent_map_tree *tree); int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder); -struct btrfs_device *btrfs_scan_one_device(const char *path, - fmode_t flags, void *holder); + blk_mode_t flags, void *holder); +struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags); int btrfs_forget_devices(dev_t devt); void btrfs_close_devices(struct btrfs_fs_devices *fs_devices); void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices); @@ -617,10 +627,9 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, const u64 *devid, const u8 *uuid, const char *path); void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args); -void btrfs_free_device(struct btrfs_device *device); int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, fmode_t *mode); + struct block_device **bdev, void **holder); void __exit btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 8acb05e176c5..6c231a116a29 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -63,7 +63,7 @@ struct list_head *zlib_alloc_workspace(unsigned int level) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL); + workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL | __GFP_NOWARN); workspace->level = level; workspace->buf = NULL; /* diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 39828af4a4e8..85b8b332add9 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -15,6 +15,7 @@ #include "transaction.h" #include "dev-replace.h" #include "space-info.h" +#include "super.h" #include "fs.h" #include "accessors.h" #include "bio.h" @@ -1057,7 +1058,7 @@ u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, /* Check if zones in the region are all empty */ if (btrfs_dev_is_sequential(device, pos) && - find_next_zero_bit(zinfo->empty_zones, end, begin) != end) { + !bitmap_test_range_all_set(zinfo->empty_zones, begin, nzones)) { pos += zinfo->zone_size; continue; } @@ -1156,23 +1157,23 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) struct btrfs_zoned_device_info *zinfo = device->zone_info; const u8 shift = zinfo->zone_size_shift; unsigned long begin = start >> shift; - unsigned long end = (start + size) >> shift; + unsigned long nbits = size >> shift; u64 pos; int ret; ASSERT(IS_ALIGNED(start, zinfo->zone_size)); ASSERT(IS_ALIGNED(size, zinfo->zone_size)); - if (end > zinfo->nr_zones) + if (begin + nbits > zinfo->nr_zones) return -ERANGE; /* All the zones are conventional */ - if (find_next_bit(zinfo->seq_zones, end, begin) == end) + if (bitmap_test_range_all_zero(zinfo->seq_zones, begin, nbits)) return 0; /* All the zones are sequential and empty */ - if (find_next_zero_bit(zinfo->seq_zones, end, begin) == end && - find_next_zero_bit(zinfo->empty_zones, end, begin) == end) + if (bitmap_test_range_all_set(zinfo->seq_zones, begin, nbits) && + bitmap_test_range_all_set(zinfo->empty_zones, begin, nbits)) return 0; for (pos = start; pos < start + size; pos += zinfo->zone_size) { @@ -1602,37 +1603,17 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb) { - struct btrfs_fs_info *fs_info = eb->fs_info; - - if (!btrfs_is_zoned(fs_info) || - btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) || - !list_empty(&eb->release_list)) + if (!btrfs_is_zoned(eb->fs_info) || + btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN)) return; + ASSERT(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + memzero_extent_buffer(eb, 0, eb->len); set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); set_extent_buffer_dirty(eb); - set_extent_bits_nowait(&trans->dirty_pages, eb->start, - eb->start + eb->len - 1, EXTENT_DIRTY); - - spin_lock(&trans->releasing_ebs_lock); - list_add_tail(&eb->release_list, &trans->releasing_ebs); - spin_unlock(&trans->releasing_ebs_lock); - atomic_inc(&eb->refs); -} - -void btrfs_free_redirty_list(struct btrfs_transaction *trans) -{ - spin_lock(&trans->releasing_ebs_lock); - while (!list_empty(&trans->releasing_ebs)) { - struct extent_buffer *eb; - - eb = list_first_entry(&trans->releasing_ebs, - struct extent_buffer, release_list); - list_del_init(&eb->release_list); - free_extent_buffer(eb); - } - spin_unlock(&trans->releasing_ebs_lock); + set_extent_bit(&trans->dirty_pages, eb->start, eb->start + eb->len - 1, + EXTENT_DIRTY | EXTENT_NOWAIT, NULL); } bool btrfs_use_zone_append(struct btrfs_bio *bbio) @@ -1677,63 +1658,89 @@ bool btrfs_use_zone_append(struct btrfs_bio *bbio) void btrfs_record_physical_zoned(struct btrfs_bio *bbio) { const u64 physical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; - struct btrfs_ordered_extent *ordered; + struct btrfs_ordered_sum *sum = bbio->sums; - ordered = btrfs_lookup_ordered_extent(bbio->inode, bbio->file_offset); - if (WARN_ON(!ordered)) - return; - - ordered->physical = physical; - btrfs_put_ordered_extent(ordered); + if (physical < bbio->orig_physical) + sum->logical -= bbio->orig_physical - physical; + else + sum->logical += physical - bbio->orig_physical; } -void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) +static void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered, + u64 logical) { - struct btrfs_inode *inode = BTRFS_I(ordered->inode); - struct btrfs_fs_info *fs_info = inode->root->fs_info; - struct extent_map_tree *em_tree; + struct extent_map_tree *em_tree = &BTRFS_I(ordered->inode)->extent_tree; struct extent_map *em; - struct btrfs_ordered_sum *sum; - u64 orig_logical = ordered->disk_bytenr; - struct map_lookup *map; - u64 physical = ordered->physical; - u64 chunk_start_phys; - u64 logical; - - em = btrfs_get_chunk_map(fs_info, orig_logical, 1); - if (IS_ERR(em)) - return; - map = em->map_lookup; - chunk_start_phys = map->stripes[0].physical; - - if (WARN_ON_ONCE(map->num_stripes > 1) || - WARN_ON_ONCE((map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) || - WARN_ON_ONCE(physical < chunk_start_phys) || - WARN_ON_ONCE(physical > chunk_start_phys + em->orig_block_len)) { - free_extent_map(em); - return; - } - logical = em->start + (physical - map->stripes[0].physical); - free_extent_map(em); - - if (orig_logical == logical) - return; ordered->disk_bytenr = logical; - em_tree = &inode->extent_tree; write_lock(&em_tree->lock); em = search_extent_mapping(em_tree, ordered->file_offset, ordered->num_bytes); em->block_start = logical; free_extent_map(em); write_unlock(&em_tree->lock); +} - list_for_each_entry(sum, &ordered->list, list) { - if (logical < orig_logical) - sum->bytenr -= orig_logical - logical; - else - sum->bytenr += logical - orig_logical; +static bool btrfs_zoned_split_ordered(struct btrfs_ordered_extent *ordered, + u64 logical, u64 len) +{ + struct btrfs_ordered_extent *new; + + if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags) && + split_extent_map(BTRFS_I(ordered->inode), ordered->file_offset, + ordered->num_bytes, len, logical)) + return false; + + new = btrfs_split_ordered_extent(ordered, len); + if (IS_ERR(new)) + return false; + new->disk_bytenr = logical; + btrfs_finish_one_ordered(new); + return true; +} + +void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_ordered_sum *sum = + list_first_entry(&ordered->list, typeof(*sum), list); + u64 logical = sum->logical; + u64 len = sum->len; + + while (len < ordered->disk_num_bytes) { + sum = list_next_entry(sum, list); + if (sum->logical == logical + len) { + len += sum->len; + continue; + } + if (!btrfs_zoned_split_ordered(ordered, logical, len)) { + set_bit(BTRFS_ORDERED_IOERR, &ordered->flags); + btrfs_err(fs_info, "failed to split ordered extent"); + goto out; + } + logical = sum->logical; + len = sum->len; + } + + if (ordered->disk_bytenr != logical) + btrfs_rewrite_logical_zoned(ordered, logical); + +out: + /* + * If we end up here for nodatasum I/O, the btrfs_ordered_sum structures + * were allocated by btrfs_alloc_dummy_sum only to record the logical + * addresses and don't contain actual checksums. We thus must free them + * here so that we don't attempt to log the csums later. + */ + if ((inode->flags & BTRFS_INODE_NODATASUM) || + test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state)) { + while ((sum = list_first_entry_or_null(&ordered->list, + typeof(*sum), list))) { + list_del(&sum->list); + kfree(sum); + } } } @@ -1792,8 +1799,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, int nmirrors; int i, ret; - ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, - &mapped_length, &bioc); + ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, + &mapped_length, &bioc, NULL, NULL, 1); if (ret || !bioc || mapped_length < PAGE_SIZE) { ret = -EIO; goto out_put_bioc; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index c0570d35fea2..27322b926038 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -30,6 +30,8 @@ struct btrfs_zoned_device_info { struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX]; }; +void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered); + #ifdef CONFIG_BLK_DEV_ZONED int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone); @@ -54,10 +56,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new); void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb); -void btrfs_free_redirty_list(struct btrfs_transaction *trans); bool btrfs_use_zone_append(struct btrfs_bio *bbio); void btrfs_record_physical_zoned(struct btrfs_bio *bbio); -void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, struct btrfs_block_group **cache_ret); @@ -179,7 +179,6 @@ static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { } static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb) { } -static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } static inline bool btrfs_use_zone_append(struct btrfs_bio *bbio) { @@ -190,9 +189,6 @@ static inline void btrfs_record_physical_zoned(struct btrfs_bio *bbio) { } -static inline void btrfs_rewrite_logical_zoned( - struct btrfs_ordered_extent *ordered) { } - static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, struct btrfs_block_group **cache_ret) diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index f798da267590..e7ac4ec809a4 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -356,7 +356,7 @@ struct list_head *zstd_alloc_workspace(unsigned int level) workspace->level = level; workspace->req_level = level; workspace->last_used = jiffies; - workspace->mem = kvmalloc(workspace->size, GFP_KERNEL); + workspace->mem = kvmalloc(workspace->size, GFP_KERNEL | __GFP_NOWARN); workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!workspace->mem || !workspace->buf) goto fail; diff --git a/fs/buffer.c b/fs/buffer.c index a7fc561758b1..93c7446d9221 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -111,7 +111,6 @@ void buffer_check_dirty_writeback(struct folio *folio, bh = bh->b_this_page; } while (bh != head); } -EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it @@ -2760,8 +2759,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); - BUG_ON(bio->bi_iter.bi_size != bh->b_size); + __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 82219a8f6084..d9d22d0ec38a 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -451,9 +451,10 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) ret = cachefiles_inject_write_error(); if (ret == 0) { - file = vfs_tmpfile_open(&nop_mnt_idmap, &parentpath, S_IFREG, - O_RDWR | O_LARGEFILE | O_DIRECT, - cache->cache_cred); + file = kernel_tmpfile_open(&nop_mnt_idmap, &parentpath, + S_IFREG | 0600, + O_RDWR | O_LARGEFILE | O_DIRECT, + cache->cache_cred); ret = PTR_ERR_OR_ZERO(file); } if (ret) { @@ -560,8 +561,8 @@ static bool cachefiles_open_file(struct cachefiles_object *object, */ path.mnt = cache->mnt; path.dentry = dentry; - file = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT, - d_backing_inode(dentry), cache->cache_cred); + file = kernel_file_open(&path, O_RDWR | O_LARGEFILE | O_DIRECT, + d_backing_inode(dentry), cache->cache_cred); if (IS_ERR(file)) { trace_cachefiles_vfs_error(object, d_backing_inode(dentry), PTR_ERR(file), diff --git a/fs/ceph/file.c b/fs/ceph/file.c index f4d8bf7dec88..4285f6cb5d3b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1746,6 +1746,69 @@ again: } /* + * Wrap filemap_splice_read with checks for cap bits on the inode. + * Atomically grab references, so that those bits are not released + * back to the MDS mid-read. + */ +static ssize_t ceph_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct ceph_file_info *fi = in->private_data; + struct inode *inode = file_inode(in); + struct ceph_inode_info *ci = ceph_inode(inode); + ssize_t ret; + int want = 0, got = 0; + CEPH_DEFINE_RW_CONTEXT(rw_ctx, 0); + + dout("splice_read %p %llx.%llx %llu~%zu trying to get caps on %p\n", + inode, ceph_vinop(inode), *ppos, len, inode); + + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + + if (ceph_has_inline_data(ci) || + (fi->flags & CEPH_F_SYNC)) + return copy_splice_read(in, ppos, pipe, len, flags); + + ceph_start_io_read(inode); + + want = CEPH_CAP_FILE_CACHE; + if (fi->fmode & CEPH_FILE_MODE_LAZY) + want |= CEPH_CAP_FILE_LAZYIO; + + ret = ceph_get_caps(in, CEPH_CAP_FILE_RD, want, -1, &got); + if (ret < 0) + goto out_end; + + if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) == 0) { + dout("splice_read/sync %p %llx.%llx %llu~%zu got cap refs on %s\n", + inode, ceph_vinop(inode), *ppos, len, + ceph_cap_string(got)); + + ceph_put_cap_refs(ci, got); + ceph_end_io_read(inode); + return copy_splice_read(in, ppos, pipe, len, flags); + } + + dout("splice_read %p %llx.%llx %llu~%zu got cap refs on %s\n", + inode, ceph_vinop(inode), *ppos, len, ceph_cap_string(got)); + + rw_ctx.caps = got; + ceph_add_rw_context(fi, &rw_ctx); + ret = filemap_splice_read(in, ppos, pipe, len, flags); + ceph_del_rw_context(fi, &rw_ctx); + + dout("splice_read %p %llx.%llx dropping cap refs on %s = %zd\n", + inode, ceph_vinop(inode), ceph_cap_string(got), ret); + + ceph_put_cap_refs(ci, got); +out_end: + ceph_end_io_read(inode); + return ret; +} + +/* * Take cap references to avoid releasing caps to MDS mid-write. * * If we are synchronous, and write with an old snap context, the OSD @@ -2593,7 +2656,7 @@ const struct file_operations ceph_file_fops = { .lock = ceph_lock, .setlease = simple_nosetlease, .flock = ceph_flock, - .splice_read = generic_file_splice_read, + .splice_read = ceph_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = ceph_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/fs/char_dev.c b/fs/char_dev.c index 13deb45f1ec6..950b6919fb87 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -150,7 +150,7 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, cd->major = major; cd->baseminor = baseminor; cd->minorct = minorct; - strlcpy(cd->name, name, sizeof(cd->name)); + strscpy(cd->name, name, sizeof(cd->name)); if (!prev) { cd->next = curr; diff --git a/fs/coda/file.c b/fs/coda/file.c index 3f3c81e6b1ab..12b26bd13564 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/uio.h> +#include <linux/splice.h> #include <linux/coda.h> #include "coda_psdev.h" @@ -94,6 +95,32 @@ finish_write: return ret; } +static ssize_t +coda_file_splice_read(struct file *coda_file, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *coda_inode = file_inode(coda_file); + struct coda_file_info *cfi = coda_ftoc(coda_file); + struct file *in = cfi->cfi_container; + loff_t ki_pos = *ppos; + ssize_t ret; + + ret = venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode), + &cfi->cfi_access_intent, + len, ki_pos, CODA_ACCESS_TYPE_READ); + if (ret) + goto finish_read; + + ret = vfs_splice_read(in, ppos, pipe, len, flags); + +finish_read: + venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode), + &cfi->cfi_access_intent, + len, ki_pos, CODA_ACCESS_TYPE_READ_FINISH); + return ret; +} + static void coda_vm_open(struct vm_area_struct *vma) { @@ -302,5 +329,5 @@ const struct file_operations coda_file_operations = { .open = coda_open, .release = coda_release, .fsync = coda_fsync, - .splice_read = generic_file_splice_read, + .splice_read = coda_file_splice_read, }; diff --git a/fs/coredump.c b/fs/coredump.c index 88740c51b942..9d235fa14ab9 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -648,7 +648,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) } else { struct mnt_idmap *idmap; struct inode *inode; - int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | + int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW | O_LARGEFILE | O_EXCL; if (cprm.limit < binfmt->min_coredump) diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 006ef68d7ff6..27c6597aa1be 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -473,7 +473,7 @@ static unsigned int cramfs_physmem_mmap_capabilities(struct file *file) static const struct file_operations cramfs_physmem_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .mmap = cramfs_physmem_mmap, #ifndef CONFIG_MMU .get_unmapped_area = cramfs_physmem_get_unmapped_area, diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 7ab5a7b7eef8..2d63da48635a 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -171,7 +171,7 @@ fscrypt_policy_flags(const union fscrypt_policy *policy) */ struct fscrypt_symlink_data { __le16 len; - char encrypted_path[1]; + char encrypted_path[]; } __packed; /** diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 9e786ae66a13..6238dbcadcad 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -255,10 +255,10 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target, * for now since filesystems will assume it is there and subtract it. */ if (!__fscrypt_fname_encrypted_size(policy, len, - max_len - sizeof(struct fscrypt_symlink_data), + max_len - sizeof(struct fscrypt_symlink_data) - 1, &disk_link->len)) return -ENAMETOOLONG; - disk_link->len += sizeof(struct fscrypt_symlink_data); + disk_link->len += sizeof(struct fscrypt_symlink_data) + 1; disk_link->name = NULL; return 0; @@ -289,7 +289,7 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, if (!sd) return -ENOMEM; } - ciphertext_len = disk_link->len - sizeof(*sd); + ciphertext_len = disk_link->len - sizeof(*sd) - 1; sd->len = cpu_to_le16(ciphertext_len); err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path, @@ -367,7 +367,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, * the ciphertext length, even though this is redundant with i_size. */ - if (max_size < sizeof(*sd)) + if (max_size < sizeof(*sd) + 1) return ERR_PTR(-EUCLEAN); sd = caddr; cstr.name = (unsigned char *)sd->encrypted_path; @@ -376,7 +376,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, if (cstr.len == 0) return ERR_PTR(-EUCLEAN); - if (cstr.len + sizeof(*sd) - 1 > max_size) + if (cstr.len + sizeof(*sd) > max_size) return ERR_PTR(-EUCLEAN); err = fscrypt_fname_alloc_buffer(cstr.len, &pstr); diff --git a/fs/d_path.c b/fs/d_path.c index 56a6ee4c6331..5f4da5c8d5db 100644 --- a/fs/d_path.c +++ b/fs/d_path.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" +#include "internal.h" struct prepend_buffer { char *buf; diff --git a/fs/direct-io.c b/fs/direct-io.c index 0b380bb8a81e..2ceb378b93c0 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -42,8 +42,8 @@ #include "internal.h" /* - * How many user pages to map in one call to get_user_pages(). This determines - * the size of a structure in the slab cache + * How many user pages to map in one call to iov_iter_extract_pages(). This + * determines the size of a structure in the slab cache */ #define DIO_PAGES 64 @@ -121,12 +121,13 @@ struct dio { struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ + bool is_pinned; /* T if we have pins on the pages */ void *private; /* copy from map_bh.b_private */ /* BIO completion state */ spinlock_t bio_lock; /* protects BIO fields below */ - int page_errors; /* errno from get_user_pages() */ + int page_errors; /* err from iov_iter_extract_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ bool should_dirty; /* if pages should be dirtied */ @@ -165,14 +166,14 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio) */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { + struct page **pages = dio->pages; const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; - ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, - &sdio->from); + ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX, + DIO_PAGES, 0, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { - struct page *page = ZERO_PAGE(0); /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid @@ -180,8 +181,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) */ if (dio->page_errors == 0) dio->page_errors = ret; - get_page(page); - dio->pages[0] = page; + dio->pages[0] = ZERO_PAGE(0); sdio->head = 0; sdio->tail = 1; sdio->from = 0; @@ -201,9 +201,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) /* * Get another userspace page. Returns an ERR_PTR on error. Pages are - * buffered inside the dio so that we can call get_user_pages() against a - * decent number of pages, less frequently. To provide nicer use of the - * L1 cache. + * buffered inside the dio so that we can call iov_iter_extract_pages() + * against a decent number of pages, less frequently. To provide nicer use of + * the L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, struct dio_submit *sdio) @@ -219,6 +219,18 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; } +static void dio_pin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + folio_add_pin(page_folio(page)); +} + +static void dio_unpin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + unpin_user_page(page); +} + /* * dio_complete() - called when all DIO BIO I/O has been completed * @@ -402,6 +414,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; + if (dio->is_pinned) + bio_set_flag(bio, BIO_PAGE_PINNED); sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } @@ -442,8 +456,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { - while (sdio->head < sdio->tail) - put_page(dio->pages[sdio->head++]); + if (dio->is_pinned) + unpin_user_pages(dio->pages + sdio->head, + sdio->tail - sdio->head); + sdio->head = sdio->tail; } /* @@ -674,7 +690,7 @@ out: * * Return zero on success. Non-zero means the caller needs to start a new BIO. */ -static inline int dio_bio_add_page(struct dio_submit *sdio) +static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio) { int ret; @@ -686,7 +702,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio) */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; - get_page(sdio->cur_page); + dio_pin_page(dio, sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; @@ -741,11 +757,11 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, goto out; } - if (dio_bio_add_page(sdio) != 0) { + if (dio_bio_add_page(dio, sdio) != 0) { dio_bio_submit(dio, sdio); ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret == 0) { - ret = dio_bio_add_page(sdio); + ret = dio_bio_add_page(dio, sdio); BUG_ON(ret != 0); } } @@ -802,13 +818,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } - get_page(page); /* It is in dio */ + dio_pin_page(dio, page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; @@ -823,7 +839,7 @@ out: ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; } return ret; @@ -924,7 +940,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, ret = get_more_blocks(dio, sdio, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } if (!buffer_mapped(map_bh)) @@ -969,7 +985,7 @@ do_holes: /* AKPM: eargh, -ENOTBLK is a hack */ if (dio_op == REQ_OP_WRITE) { - put_page(page); + dio_unpin_page(dio, page); return -ENOTBLK; } @@ -982,7 +998,7 @@ do_holes: if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ - put_page(page); + dio_unpin_page(dio, page); goto out; } zero_user(page, from, 1 << blkbits); @@ -1022,7 +1038,7 @@ do_holes: sdio->next_block_for_io, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } sdio->next_block_for_io += this_chunk_blocks; @@ -1037,8 +1053,8 @@ next_block: break; } - /* Drop the ref which was taken in get_user_pages() */ - put_page(page); + /* Drop the pin which was taken in get_user_pages() */ + dio_unpin_page(dio, page); } out: return ret; @@ -1133,6 +1149,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, /* will be released by direct_io_worker */ inode_lock(inode); } + dio->is_pinned = iov_iter_extract_will_pin(iter); /* Once we sampled i_size check for reads beyond EOF */ dio->i_size = i_size_read(inode); @@ -1257,7 +1274,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; - put_page(sdio.cur_page); + dio_unpin_page(dio, sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 268b74499c28..ce0a3c5ed0ca 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -44,6 +44,31 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, return rc; } +/* + * ecryptfs_splice_read_update_atime + * + * filemap_splice_read updates the atime of upper layer inode. But, it + * doesn't give us a chance to update the atime of the lower layer inode. This + * function is a wrapper to generic_file_read. It updates the atime of the + * lower level inode if generic_file_read returns without any errors. This is + * to be used only for file reads. The function to be used for directory reads + * is ecryptfs_read. + */ +static ssize_t ecryptfs_splice_read_update_atime(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + ssize_t rc; + const struct path *path; + + rc = filemap_splice_read(in, ppos, pipe, len, flags); + if (rc >= 0) { + path = ecryptfs_dentry_to_lower_path(in->f_path.dentry); + touch_atime(path); + } + return rc; +} + struct ecryptfs_getdents_callback { struct dir_context ctx; struct dir_context *caller; @@ -414,5 +439,5 @@ const struct file_operations ecryptfs_main_fops = { .release = ecryptfs_release, .fsync = ecryptfs_fsync, .fasync = ecryptfs_fasync, - .splice_read = generic_file_splice_read, + .splice_read = ecryptfs_splice_read_update_atime, }; diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 26fa170090b8..b1b846504027 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -89,8 +89,7 @@ static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi, int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, unsigned int padbufsize); -int z_erofs_decompress(struct z_erofs_decompress_req *rq, - struct page **pagepool); +extern const struct z_erofs_decompressor erofs_decompressors[]; /* prototypes for specific algorithms */ int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 6fe9a779fa91..db5e4b7636ec 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -448,5 +448,5 @@ const struct file_operations erofs_file_fops = { .llseek = generic_file_llseek, .read_iter = erofs_file_read_iter, .mmap = erofs_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 7021e2cf6146..2a29943fa5cc 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -363,7 +363,7 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, return 0; } -static struct z_erofs_decompressor decompressors[] = { +const struct z_erofs_decompressor erofs_decompressors[] = { [Z_EROFS_COMPRESSION_SHIFTED] = { .decompress = z_erofs_transform_plain, .name = "shifted" @@ -383,9 +383,3 @@ static struct z_erofs_decompressor decompressors[] = { }, #endif }; - -int z_erofs_decompress(struct z_erofs_decompress_req *rq, - struct page **pagepool) -{ - return decompressors[rq->alg].decompress(rq, pagepool); -} diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1e39c03357d1..36e32fa542f0 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -208,46 +208,12 @@ enum { EROFS_ZIP_CACHE_READAROUND }; -#define EROFS_LOCKED_MAGIC (INT_MIN | 0xE0F510CCL) - /* basic unit of the workstation of a super_block */ struct erofs_workgroup { - /* the workgroup index in the workstation */ pgoff_t index; - - /* overall workgroup reference count */ - atomic_t refcount; + struct lockref lockref; }; -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - if (val != atomic_cmpxchg(&grp->refcount, val, EROFS_LOCKED_MAGIC)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - /* - * other observers should notice all modifications - * in the freezing period. - */ - smp_mb(); - atomic_set(&grp->refcount, orig_val); - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - return atomic_cond_read_relaxed(&grp->refcount, - VAL != EROFS_LOCKED_MAGIC); -} - enum erofs_kmap_type { EROFS_NO_KMAP, /* don't map the buffer */ EROFS_KMAP, /* use kmap_local_page() to map the buffer */ @@ -486,7 +452,7 @@ static inline void erofs_pagepool_add(struct page **pagepool, struct page *page) void erofs_release_pages(struct page **pagepool); #ifdef CONFIG_EROFS_FS_ZIP -int erofs_workgroup_put(struct erofs_workgroup *grp); +void erofs_workgroup_put(struct erofs_workgroup *grp); struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb, pgoff_t index); struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb, @@ -500,7 +466,6 @@ int __init z_erofs_init_zip_subsystem(void); void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); -int erofs_try_to_free_cached_page(struct page *page); int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, struct z_erofs_lz4_cfgs *lz4, int len); @@ -511,6 +476,7 @@ void erofs_put_pcpubuf(void *ptr); int erofs_pcpubuf_growsize(unsigned int nrpages); void __init erofs_pcpubuf_init(void); void erofs_pcpubuf_exit(void); +int erofs_init_managed_cache(struct super_block *sb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -530,6 +496,7 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb, } static inline void erofs_pcpubuf_init(void) {} static inline void erofs_pcpubuf_exit(void) {} +static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; } #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 811ab66d805e..9d6a3c6158bd 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -19,6 +19,7 @@ #include <trace/events/erofs.h> static struct kmem_cache *erofs_inode_cachep __read_mostly; +struct file_system_type erofs_fs_type; void _erofs_err(struct super_block *sb, const char *function, const char *fmt, ...) @@ -253,8 +254,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, return PTR_ERR(fscache); dif->fscache = fscache; } else if (!sbi->devs->flatdev) { - bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, - sb->s_type); + bdev = blkdev_get_by_path(dif->path, BLK_OPEN_READ, sb->s_type, + NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); dif->bdev = bdev; @@ -599,68 +600,6 @@ static int erofs_fc_parse_param(struct fs_context *fc, return 0; } -#ifdef CONFIG_EROFS_FS_ZIP -static const struct address_space_operations managed_cache_aops; - -static bool erofs_managed_cache_release_folio(struct folio *folio, gfp_t gfp) -{ - bool ret = true; - struct address_space *const mapping = folio->mapping; - - DBG_BUGON(!folio_test_locked(folio)); - DBG_BUGON(mapping->a_ops != &managed_cache_aops); - - if (folio_test_private(folio)) - ret = erofs_try_to_free_cached_page(&folio->page); - - return ret; -} - -/* - * It will be called only on inode eviction. In case that there are still some - * decompression requests in progress, wait with rescheduling for a bit here. - * We could introduce an extra locking instead but it seems unnecessary. - */ -static void erofs_managed_cache_invalidate_folio(struct folio *folio, - size_t offset, size_t length) -{ - const size_t stop = length + offset; - - DBG_BUGON(!folio_test_locked(folio)); - - /* Check for potential overflow in debug mode */ - DBG_BUGON(stop > folio_size(folio) || stop < length); - - if (offset == 0 && stop == folio_size(folio)) - while (!erofs_managed_cache_release_folio(folio, GFP_NOFS)) - cond_resched(); -} - -static const struct address_space_operations managed_cache_aops = { - .release_folio = erofs_managed_cache_release_folio, - .invalidate_folio = erofs_managed_cache_invalidate_folio, -}; - -static int erofs_init_managed_cache(struct super_block *sb) -{ - struct erofs_sb_info *const sbi = EROFS_SB(sb); - struct inode *const inode = new_inode(sb); - - if (!inode) - return -ENOMEM; - - set_nlink(inode, 1); - inode->i_size = OFFSET_MAX; - - inode->i_mapping->a_ops = &managed_cache_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - sbi->managed_cache = inode; - return 0; -} -#else -static int erofs_init_managed_cache(struct super_block *sb) { return 0; } -#endif - static struct inode *erofs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { @@ -877,7 +816,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) fs_put_dax(dif->dax_dev, NULL); if (dif->bdev) - blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(dif->bdev, &erofs_fs_type); erofs_fscache_unregister_cookie(dif->fscache); dif->fscache = NULL; kfree(dif->path); @@ -1016,10 +955,8 @@ static int __init erofs_module_init(void) sizeof(struct erofs_inode), 0, SLAB_RECLAIM_ACCOUNT, erofs_inode_init_once); - if (!erofs_inode_cachep) { - err = -ENOMEM; - goto icache_err; - } + if (!erofs_inode_cachep) + return -ENOMEM; err = erofs_init_shrinker(); if (err) @@ -1054,7 +991,6 @@ lzma_err: erofs_exit_shrinker(); shrinker_err: kmem_cache_destroy(erofs_inode_cachep); -icache_err: return err; } diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index 46627cb69abe..cc6fb9e98899 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -4,7 +4,6 @@ * https://www.huawei.com/ */ #include "internal.h" -#include <linux/pagevec.h> struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp) { @@ -33,22 +32,21 @@ void erofs_release_pages(struct page **pagepool) /* global shrink count (for all mounted EROFS instances) */ static atomic_long_t erofs_global_shrink_cnt; -static int erofs_workgroup_get(struct erofs_workgroup *grp) +static bool erofs_workgroup_get(struct erofs_workgroup *grp) { - int o; + if (lockref_get_not_zero(&grp->lockref)) + return true; -repeat: - o = erofs_wait_on_workgroup_freezed(grp); - if (o <= 0) - return -1; - - if (atomic_cmpxchg(&grp->refcount, o, o + 1) != o) - goto repeat; + spin_lock(&grp->lockref.lock); + if (__lockref_is_dead(&grp->lockref)) { + spin_unlock(&grp->lockref.lock); + return false; + } - /* decrease refcount paired by erofs_workgroup_put */ - if (o == 1) + if (!grp->lockref.count++) atomic_long_dec(&erofs_global_shrink_cnt); - return 0; + spin_unlock(&grp->lockref.lock); + return true; } struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb, @@ -61,7 +59,7 @@ repeat: rcu_read_lock(); grp = xa_load(&sbi->managed_pslots, index); if (grp) { - if (erofs_workgroup_get(grp)) { + if (!erofs_workgroup_get(grp)) { /* prefer to relax rcu read side */ rcu_read_unlock(); goto repeat; @@ -80,11 +78,10 @@ struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb, struct erofs_workgroup *pre; /* - * Bump up a reference count before making this visible - * to others for the XArray in order to avoid potential - * UAF without serialized by xa_lock. + * Bump up before making this visible to others for the XArray in order + * to avoid potential UAF without serialized by xa_lock. */ - atomic_inc(&grp->refcount); + lockref_get(&grp->lockref); repeat: xa_lock(&sbi->managed_pslots); @@ -93,13 +90,13 @@ repeat: if (pre) { if (xa_is_err(pre)) { pre = ERR_PTR(xa_err(pre)); - } else if (erofs_workgroup_get(pre)) { + } else if (!erofs_workgroup_get(pre)) { /* try to legitimize the current in-tree one */ xa_unlock(&sbi->managed_pslots); cond_resched(); goto repeat; } - atomic_dec(&grp->refcount); + lockref_put_return(&grp->lockref); grp = pre; } xa_unlock(&sbi->managed_pslots); @@ -112,38 +109,34 @@ static void __erofs_workgroup_free(struct erofs_workgroup *grp) erofs_workgroup_free_rcu(grp); } -int erofs_workgroup_put(struct erofs_workgroup *grp) +void erofs_workgroup_put(struct erofs_workgroup *grp) { - int count = atomic_dec_return(&grp->refcount); + if (lockref_put_or_lock(&grp->lockref)) + return; - if (count == 1) + DBG_BUGON(__lockref_is_dead(&grp->lockref)); + if (grp->lockref.count == 1) atomic_long_inc(&erofs_global_shrink_cnt); - else if (!count) - __erofs_workgroup_free(grp); - return count; + --grp->lockref.count; + spin_unlock(&grp->lockref.lock); } static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, struct erofs_workgroup *grp) { - /* - * If managed cache is on, refcount of workgroups - * themselves could be < 0 (freezed). In other words, - * there is no guarantee that all refcounts > 0. - */ - if (!erofs_workgroup_try_to_freeze(grp, 1)) - return false; + int free = false; + + spin_lock(&grp->lockref.lock); + if (grp->lockref.count) + goto out; /* - * Note that all cached pages should be unattached - * before deleted from the XArray. Otherwise some - * cached pages could be still attached to the orphan - * old workgroup when the new one is available in the tree. + * Note that all cached pages should be detached before deleted from + * the XArray. Otherwise some cached pages could be still attached to + * the orphan old workgroup when the new one is available in the tree. */ - if (erofs_try_to_free_all_cached_pages(sbi, grp)) { - erofs_workgroup_unfreeze(grp, 1); - return false; - } + if (erofs_try_to_free_all_cached_pages(sbi, grp)) + goto out; /* * It's impossible to fail after the workgroup is freezed, @@ -152,10 +145,13 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, */ DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp); - /* last refcount should be connected with its managed pslot. */ - erofs_workgroup_unfreeze(grp, 0); - __erofs_workgroup_free(grp); - return true; + lockref_mark_dead(&grp->lockref); + free = true; +out: + spin_unlock(&grp->lockref.lock); + if (free) + __erofs_workgroup_free(grp); + return free; } static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi, diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index bbfe7ce170d2..40178b6e0688 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -7,32 +7,27 @@ #include <linux/security.h> #include "xattr.h" -static inline erofs_blk_t erofs_xattr_blkaddr(struct super_block *sb, - unsigned int xattr_id) -{ - return EROFS_SB(sb)->xattr_blkaddr + - erofs_blknr(sb, xattr_id * sizeof(__u32)); -} - -static inline unsigned int erofs_xattr_blkoff(struct super_block *sb, - unsigned int xattr_id) -{ - return erofs_blkoff(sb, xattr_id * sizeof(__u32)); -} - -struct xattr_iter { +struct erofs_xattr_iter { struct super_block *sb; struct erofs_buf buf; + erofs_off_t pos; void *kaddr; - erofs_blk_t blkaddr; - unsigned int ofs; + char *buffer; + int buffer_size, buffer_ofs; + + /* getxattr */ + int index, infix_len; + struct qstr name; + + /* listxattr */ + struct dentry *dentry; }; static int erofs_init_inode_xattrs(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); - struct xattr_iter it; + struct erofs_xattr_iter it; unsigned int i; struct erofs_xattr_ibody_header *ih; struct super_block *sb = inode->i_sb; @@ -81,17 +76,17 @@ static int erofs_init_inode_xattrs(struct inode *inode) } it.buf = __EROFS_BUF_INITIALIZER; - it.blkaddr = erofs_blknr(sb, erofs_iloc(inode) + vi->inode_isize); - it.ofs = erofs_blkoff(sb, erofs_iloc(inode) + vi->inode_isize); + erofs_init_metabuf(&it.buf, sb); + it.pos = erofs_iloc(inode) + vi->inode_isize; /* read in shared xattr array (non-atomic, see kmalloc below) */ - it.kaddr = erofs_read_metabuf(&it.buf, sb, it.blkaddr, EROFS_KMAP); + it.kaddr = erofs_bread(&it.buf, erofs_blknr(sb, it.pos), EROFS_KMAP); if (IS_ERR(it.kaddr)) { ret = PTR_ERR(it.kaddr); goto out_unlock; } - ih = (struct erofs_xattr_ibody_header *)(it.kaddr + it.ofs); + ih = it.kaddr + erofs_blkoff(sb, it.pos); vi->xattr_shared_count = ih->h_shared_count; vi->xattr_shared_xattrs = kmalloc_array(vi->xattr_shared_count, sizeof(uint), GFP_KERNEL); @@ -102,26 +97,20 @@ static int erofs_init_inode_xattrs(struct inode *inode) } /* let's skip ibody header */ - it.ofs += sizeof(struct erofs_xattr_ibody_header); + it.pos += sizeof(struct erofs_xattr_ibody_header); for (i = 0; i < vi->xattr_shared_count; ++i) { - if (it.ofs >= sb->s_blocksize) { - /* cannot be unaligned */ - DBG_BUGON(it.ofs != sb->s_blocksize); - - it.kaddr = erofs_read_metabuf(&it.buf, sb, ++it.blkaddr, - EROFS_KMAP); - if (IS_ERR(it.kaddr)) { - kfree(vi->xattr_shared_xattrs); - vi->xattr_shared_xattrs = NULL; - ret = PTR_ERR(it.kaddr); - goto out_unlock; - } - it.ofs = 0; + it.kaddr = erofs_bread(&it.buf, erofs_blknr(sb, it.pos), + EROFS_KMAP); + if (IS_ERR(it.kaddr)) { + kfree(vi->xattr_shared_xattrs); + vi->xattr_shared_xattrs = NULL; + ret = PTR_ERR(it.kaddr); + goto out_unlock; } - vi->xattr_shared_xattrs[i] = - le32_to_cpu(*(__le32 *)(it.kaddr + it.ofs)); - it.ofs += sizeof(__le32); + vi->xattr_shared_xattrs[i] = le32_to_cpu(*(__le32 *) + (it.kaddr + erofs_blkoff(sb, it.pos))); + it.pos += sizeof(__le32); } erofs_put_metabuf(&it.buf); @@ -134,287 +123,6 @@ out_unlock: return ret; } -/* - * the general idea for these return values is - * if 0 is returned, go on processing the current xattr; - * 1 (> 0) is returned, skip this round to process the next xattr; - * -err (< 0) is returned, an error (maybe ENOXATTR) occurred - * and need to be handled - */ -struct xattr_iter_handlers { - int (*entry)(struct xattr_iter *_it, struct erofs_xattr_entry *entry); - int (*name)(struct xattr_iter *_it, unsigned int processed, char *buf, - unsigned int len); - int (*alloc_buffer)(struct xattr_iter *_it, unsigned int value_sz); - void (*value)(struct xattr_iter *_it, unsigned int processed, char *buf, - unsigned int len); -}; - -static inline int xattr_iter_fixup(struct xattr_iter *it) -{ - if (it->ofs < it->sb->s_blocksize) - return 0; - - it->blkaddr += erofs_blknr(it->sb, it->ofs); - it->kaddr = erofs_read_metabuf(&it->buf, it->sb, it->blkaddr, - EROFS_KMAP); - if (IS_ERR(it->kaddr)) - return PTR_ERR(it->kaddr); - it->ofs = erofs_blkoff(it->sb, it->ofs); - return 0; -} - -static int inline_xattr_iter_begin(struct xattr_iter *it, - struct inode *inode) -{ - struct erofs_inode *const vi = EROFS_I(inode); - unsigned int xattr_header_sz, inline_xattr_ofs; - - xattr_header_sz = sizeof(struct erofs_xattr_ibody_header) + - sizeof(u32) * vi->xattr_shared_count; - if (xattr_header_sz >= vi->xattr_isize) { - DBG_BUGON(xattr_header_sz > vi->xattr_isize); - return -ENOATTR; - } - - inline_xattr_ofs = vi->inode_isize + xattr_header_sz; - - it->blkaddr = erofs_blknr(it->sb, erofs_iloc(inode) + inline_xattr_ofs); - it->ofs = erofs_blkoff(it->sb, erofs_iloc(inode) + inline_xattr_ofs); - it->kaddr = erofs_read_metabuf(&it->buf, inode->i_sb, it->blkaddr, - EROFS_KMAP); - if (IS_ERR(it->kaddr)) - return PTR_ERR(it->kaddr); - return vi->xattr_isize - xattr_header_sz; -} - -/* - * Regardless of success or failure, `xattr_foreach' will end up with - * `ofs' pointing to the next xattr item rather than an arbitrary position. - */ -static int xattr_foreach(struct xattr_iter *it, - const struct xattr_iter_handlers *op, - unsigned int *tlimit) -{ - struct erofs_xattr_entry entry; - unsigned int value_sz, processed, slice; - int err; - - /* 0. fixup blkaddr, ofs, ipage */ - err = xattr_iter_fixup(it); - if (err) - return err; - - /* - * 1. read xattr entry to the memory, - * since we do EROFS_XATTR_ALIGN - * therefore entry should be in the page - */ - entry = *(struct erofs_xattr_entry *)(it->kaddr + it->ofs); - if (tlimit) { - unsigned int entry_sz = erofs_xattr_entry_size(&entry); - - /* xattr on-disk corruption: xattr entry beyond xattr_isize */ - if (*tlimit < entry_sz) { - DBG_BUGON(1); - return -EFSCORRUPTED; - } - *tlimit -= entry_sz; - } - - it->ofs += sizeof(struct erofs_xattr_entry); - value_sz = le16_to_cpu(entry.e_value_size); - - /* handle entry */ - err = op->entry(it, &entry); - if (err) { - it->ofs += entry.e_name_len + value_sz; - goto out; - } - - /* 2. handle xattr name (ofs will finally be at the end of name) */ - processed = 0; - - while (processed < entry.e_name_len) { - if (it->ofs >= it->sb->s_blocksize) { - DBG_BUGON(it->ofs > it->sb->s_blocksize); - - err = xattr_iter_fixup(it); - if (err) - goto out; - it->ofs = 0; - } - - slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs, - entry.e_name_len - processed); - - /* handle name */ - err = op->name(it, processed, it->kaddr + it->ofs, slice); - if (err) { - it->ofs += entry.e_name_len - processed + value_sz; - goto out; - } - - it->ofs += slice; - processed += slice; - } - - /* 3. handle xattr value */ - processed = 0; - - if (op->alloc_buffer) { - err = op->alloc_buffer(it, value_sz); - if (err) { - it->ofs += value_sz; - goto out; - } - } - - while (processed < value_sz) { - if (it->ofs >= it->sb->s_blocksize) { - DBG_BUGON(it->ofs > it->sb->s_blocksize); - - err = xattr_iter_fixup(it); - if (err) - goto out; - it->ofs = 0; - } - - slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs, - value_sz - processed); - op->value(it, processed, it->kaddr + it->ofs, slice); - it->ofs += slice; - processed += slice; - } - -out: - /* xattrs should be 4-byte aligned (on-disk constraint) */ - it->ofs = EROFS_XATTR_ALIGN(it->ofs); - return err < 0 ? err : 0; -} - -struct getxattr_iter { - struct xattr_iter it; - - char *buffer; - int buffer_size, index, infix_len; - struct qstr name; -}; - -static int erofs_xattr_long_entrymatch(struct getxattr_iter *it, - struct erofs_xattr_entry *entry) -{ - struct erofs_sb_info *sbi = EROFS_SB(it->it.sb); - struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes + - (entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); - - if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count) - return -ENOATTR; - - if (it->index != pf->prefix->base_index || - it->name.len != entry->e_name_len + pf->infix_len) - return -ENOATTR; - - if (memcmp(it->name.name, pf->prefix->infix, pf->infix_len)) - return -ENOATTR; - - it->infix_len = pf->infix_len; - return 0; -} - -static int xattr_entrymatch(struct xattr_iter *_it, - struct erofs_xattr_entry *entry) -{ - struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - - /* should also match the infix for long name prefixes */ - if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX) - return erofs_xattr_long_entrymatch(it, entry); - - if (it->index != entry->e_name_index || - it->name.len != entry->e_name_len) - return -ENOATTR; - it->infix_len = 0; - return 0; -} - -static int xattr_namematch(struct xattr_iter *_it, - unsigned int processed, char *buf, unsigned int len) -{ - struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - - if (memcmp(buf, it->name.name + it->infix_len + processed, len)) - return -ENOATTR; - return 0; -} - -static int xattr_checkbuffer(struct xattr_iter *_it, - unsigned int value_sz) -{ - struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - int err = it->buffer_size < value_sz ? -ERANGE : 0; - - it->buffer_size = value_sz; - return !it->buffer ? 1 : err; -} - -static void xattr_copyvalue(struct xattr_iter *_it, - unsigned int processed, - char *buf, unsigned int len) -{ - struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - - memcpy(it->buffer + processed, buf, len); -} - -static const struct xattr_iter_handlers find_xattr_handlers = { - .entry = xattr_entrymatch, - .name = xattr_namematch, - .alloc_buffer = xattr_checkbuffer, - .value = xattr_copyvalue -}; - -static int inline_getxattr(struct inode *inode, struct getxattr_iter *it) -{ - int ret; - unsigned int remaining; - - ret = inline_xattr_iter_begin(&it->it, inode); - if (ret < 0) - return ret; - - remaining = ret; - while (remaining) { - ret = xattr_foreach(&it->it, &find_xattr_handlers, &remaining); - if (ret != -ENOATTR) - break; - } - return ret ? ret : it->buffer_size; -} - -static int shared_getxattr(struct inode *inode, struct getxattr_iter *it) -{ - struct erofs_inode *const vi = EROFS_I(inode); - struct super_block *const sb = it->it.sb; - unsigned int i, xsid; - int ret = -ENOATTR; - - for (i = 0; i < vi->xattr_shared_count; ++i) { - xsid = vi->xattr_shared_xattrs[i]; - it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid); - it->it.ofs = erofs_xattr_blkoff(sb, xsid); - it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, - it->it.blkaddr, EROFS_KMAP); - if (IS_ERR(it->it.kaddr)) - return PTR_ERR(it->it.kaddr); - - ret = xattr_foreach(&it->it, &find_xattr_handlers, NULL); - if (ret != -ENOATTR) - break; - } - return ret ? ret : it->buffer_size; -} - static bool erofs_xattr_user_list(struct dentry *dentry) { return test_opt(&EROFS_SB(dentry->d_sb)->opt, XATTR_USER); @@ -425,39 +133,6 @@ static bool erofs_xattr_trusted_list(struct dentry *dentry) return capable(CAP_SYS_ADMIN); } -int erofs_getxattr(struct inode *inode, int index, - const char *name, - void *buffer, size_t buffer_size) -{ - int ret; - struct getxattr_iter it; - - if (!name) - return -EINVAL; - - ret = erofs_init_inode_xattrs(inode); - if (ret) - return ret; - - it.index = index; - it.name.len = strlen(name); - if (it.name.len > EROFS_NAME_LEN) - return -ERANGE; - - it.it.buf = __EROFS_BUF_INITIALIZER; - it.name.name = name; - - it.buffer = buffer; - it.buffer_size = buffer_size; - - it.it.sb = inode->i_sb; - ret = inline_getxattr(inode, &it); - if (ret == -ENOATTR) - ret = shared_getxattr(inode, &it); - erofs_put_metabuf(&it.it.buf); - return ret; -} - static int erofs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) @@ -500,30 +175,49 @@ const struct xattr_handler *erofs_xattr_handlers[] = { NULL, }; -struct listxattr_iter { - struct xattr_iter it; - - struct dentry *dentry; - char *buffer; - int buffer_size, buffer_ofs; -}; +static int erofs_xattr_copy_to_buffer(struct erofs_xattr_iter *it, + unsigned int len) +{ + unsigned int slice, processed; + struct super_block *sb = it->sb; + void *src; + + for (processed = 0; processed < len; processed += slice) { + it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), + EROFS_KMAP); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); + + src = it->kaddr + erofs_blkoff(sb, it->pos); + slice = min_t(unsigned int, sb->s_blocksize - + erofs_blkoff(sb, it->pos), len - processed); + memcpy(it->buffer + it->buffer_ofs, src, slice); + it->buffer_ofs += slice; + it->pos += slice; + } + return 0; +} -static int xattr_entrylist(struct xattr_iter *_it, - struct erofs_xattr_entry *entry) +static int erofs_listxattr_foreach(struct erofs_xattr_iter *it) { - struct listxattr_iter *it = - container_of(_it, struct listxattr_iter, it); - unsigned int base_index = entry->e_name_index; - unsigned int prefix_len, infix_len = 0; + struct erofs_xattr_entry entry; + unsigned int base_index, name_total, prefix_len, infix_len = 0; const char *prefix, *infix = NULL; + int err; + + /* 1. handle xattr entry */ + entry = *(struct erofs_xattr_entry *) + (it->kaddr + erofs_blkoff(it->sb, it->pos)); + it->pos += sizeof(struct erofs_xattr_entry); - if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX) { - struct erofs_sb_info *sbi = EROFS_SB(_it->sb); + base_index = entry.e_name_index; + if (entry.e_name_index & EROFS_XATTR_LONG_PREFIX) { + struct erofs_sb_info *sbi = EROFS_SB(it->sb); struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes + - (entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); + (entry.e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count) - return 1; + return 0; infix = pf->prefix->infix; infix_len = pf->infix_len; base_index = pf->prefix->base_index; @@ -531,120 +225,228 @@ static int xattr_entrylist(struct xattr_iter *_it, prefix = erofs_xattr_prefix(base_index, it->dentry); if (!prefix) - return 1; + return 0; prefix_len = strlen(prefix); + name_total = prefix_len + infix_len + entry.e_name_len + 1; if (!it->buffer) { - it->buffer_ofs += prefix_len + infix_len + - entry->e_name_len + 1; - return 1; + it->buffer_ofs += name_total; + return 0; } - if (it->buffer_ofs + prefix_len + infix_len + - + entry->e_name_len + 1 > it->buffer_size) + if (it->buffer_ofs + name_total > it->buffer_size) return -ERANGE; memcpy(it->buffer + it->buffer_ofs, prefix, prefix_len); memcpy(it->buffer + it->buffer_ofs + prefix_len, infix, infix_len); it->buffer_ofs += prefix_len + infix_len; - return 0; -} -static int xattr_namelist(struct xattr_iter *_it, - unsigned int processed, char *buf, unsigned int len) -{ - struct listxattr_iter *it = - container_of(_it, struct listxattr_iter, it); + /* 2. handle xattr name */ + err = erofs_xattr_copy_to_buffer(it, entry.e_name_len); + if (err) + return err; - memcpy(it->buffer + it->buffer_ofs, buf, len); - it->buffer_ofs += len; + it->buffer[it->buffer_ofs++] = '\0'; return 0; } -static int xattr_skipvalue(struct xattr_iter *_it, - unsigned int value_sz) +static int erofs_getxattr_foreach(struct erofs_xattr_iter *it) { - struct listxattr_iter *it = - container_of(_it, struct listxattr_iter, it); + struct super_block *sb = it->sb; + struct erofs_xattr_entry entry; + unsigned int slice, processed, value_sz; - it->buffer[it->buffer_ofs++] = '\0'; - return 1; -} + /* 1. handle xattr entry */ + entry = *(struct erofs_xattr_entry *) + (it->kaddr + erofs_blkoff(sb, it->pos)); + it->pos += sizeof(struct erofs_xattr_entry); + value_sz = le16_to_cpu(entry.e_value_size); -static const struct xattr_iter_handlers list_xattr_handlers = { - .entry = xattr_entrylist, - .name = xattr_namelist, - .alloc_buffer = xattr_skipvalue, - .value = NULL -}; + /* should also match the infix for long name prefixes */ + if (entry.e_name_index & EROFS_XATTR_LONG_PREFIX) { + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes + + (entry.e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); + + if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count) + return -ENOATTR; + + if (it->index != pf->prefix->base_index || + it->name.len != entry.e_name_len + pf->infix_len) + return -ENOATTR; + + if (memcmp(it->name.name, pf->prefix->infix, pf->infix_len)) + return -ENOATTR; + + it->infix_len = pf->infix_len; + } else { + if (it->index != entry.e_name_index || + it->name.len != entry.e_name_len) + return -ENOATTR; -static int inline_listxattr(struct listxattr_iter *it) + it->infix_len = 0; + } + + /* 2. handle xattr name */ + for (processed = 0; processed < entry.e_name_len; processed += slice) { + it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), + EROFS_KMAP); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); + + slice = min_t(unsigned int, + sb->s_blocksize - erofs_blkoff(sb, it->pos), + entry.e_name_len - processed); + if (memcmp(it->name.name + it->infix_len + processed, + it->kaddr + erofs_blkoff(sb, it->pos), slice)) + return -ENOATTR; + it->pos += slice; + } + + /* 3. handle xattr value */ + if (!it->buffer) { + it->buffer_ofs = value_sz; + return 0; + } + + if (it->buffer_size < value_sz) + return -ERANGE; + + return erofs_xattr_copy_to_buffer(it, value_sz); +} + +static int erofs_xattr_iter_inline(struct erofs_xattr_iter *it, + struct inode *inode, bool getxattr) { + struct erofs_inode *const vi = EROFS_I(inode); + unsigned int xattr_header_sz, remaining, entry_sz; + erofs_off_t next_pos; int ret; - unsigned int remaining; - ret = inline_xattr_iter_begin(&it->it, d_inode(it->dentry)); - if (ret < 0) - return ret; + xattr_header_sz = sizeof(struct erofs_xattr_ibody_header) + + sizeof(u32) * vi->xattr_shared_count; + if (xattr_header_sz >= vi->xattr_isize) { + DBG_BUGON(xattr_header_sz > vi->xattr_isize); + return -ENOATTR; + } + + remaining = vi->xattr_isize - xattr_header_sz; + it->pos = erofs_iloc(inode) + vi->inode_isize + xattr_header_sz; - remaining = ret; while (remaining) { - ret = xattr_foreach(&it->it, &list_xattr_handlers, &remaining); - if (ret) + it->kaddr = erofs_bread(&it->buf, erofs_blknr(it->sb, it->pos), + EROFS_KMAP); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); + + entry_sz = erofs_xattr_entry_size(it->kaddr + + erofs_blkoff(it->sb, it->pos)); + /* xattr on-disk corruption: xattr entry beyond xattr_isize */ + if (remaining < entry_sz) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } + remaining -= entry_sz; + next_pos = it->pos + entry_sz; + + if (getxattr) + ret = erofs_getxattr_foreach(it); + else + ret = erofs_listxattr_foreach(it); + if ((getxattr && ret != -ENOATTR) || (!getxattr && ret)) break; + + it->pos = next_pos; } - return ret ? ret : it->buffer_ofs; + return ret; } -static int shared_listxattr(struct listxattr_iter *it) +static int erofs_xattr_iter_shared(struct erofs_xattr_iter *it, + struct inode *inode, bool getxattr) { - struct inode *const inode = d_inode(it->dentry); struct erofs_inode *const vi = EROFS_I(inode); - struct super_block *const sb = it->it.sb; - unsigned int i, xsid; - int ret = 0; + struct super_block *const sb = it->sb; + struct erofs_sb_info *sbi = EROFS_SB(sb); + unsigned int i; + int ret = -ENOATTR; for (i = 0; i < vi->xattr_shared_count; ++i) { - xsid = vi->xattr_shared_xattrs[i]; - it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid); - it->it.ofs = erofs_xattr_blkoff(sb, xsid); - it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, - it->it.blkaddr, EROFS_KMAP); - if (IS_ERR(it->it.kaddr)) - return PTR_ERR(it->it.kaddr); - - ret = xattr_foreach(&it->it, &list_xattr_handlers, NULL); - if (ret) + it->pos = erofs_pos(sb, sbi->xattr_blkaddr) + + vi->xattr_shared_xattrs[i] * sizeof(__le32); + it->kaddr = erofs_bread(&it->buf, erofs_blknr(sb, it->pos), + EROFS_KMAP); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); + + if (getxattr) + ret = erofs_getxattr_foreach(it); + else + ret = erofs_listxattr_foreach(it); + if ((getxattr && ret != -ENOATTR) || (!getxattr && ret)) break; } - return ret ? ret : it->buffer_ofs; + return ret; +} + +int erofs_getxattr(struct inode *inode, int index, const char *name, + void *buffer, size_t buffer_size) +{ + int ret; + struct erofs_xattr_iter it; + + if (!name) + return -EINVAL; + + ret = erofs_init_inode_xattrs(inode); + if (ret) + return ret; + + it.index = index; + it.name = (struct qstr)QSTR_INIT(name, strlen(name)); + if (it.name.len > EROFS_NAME_LEN) + return -ERANGE; + + it.sb = inode->i_sb; + it.buf = __EROFS_BUF_INITIALIZER; + erofs_init_metabuf(&it.buf, it.sb); + it.buffer = buffer; + it.buffer_size = buffer_size; + it.buffer_ofs = 0; + + ret = erofs_xattr_iter_inline(&it, inode, true); + if (ret == -ENOATTR) + ret = erofs_xattr_iter_shared(&it, inode, true); + erofs_put_metabuf(&it.buf); + return ret ? ret : it.buffer_ofs; } -ssize_t erofs_listxattr(struct dentry *dentry, - char *buffer, size_t buffer_size) +ssize_t erofs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { int ret; - struct listxattr_iter it; + struct erofs_xattr_iter it; + struct inode *inode = d_inode(dentry); - ret = erofs_init_inode_xattrs(d_inode(dentry)); + ret = erofs_init_inode_xattrs(inode); if (ret == -ENOATTR) return 0; if (ret) return ret; - it.it.buf = __EROFS_BUF_INITIALIZER; + it.sb = dentry->d_sb; + it.buf = __EROFS_BUF_INITIALIZER; + erofs_init_metabuf(&it.buf, it.sb); it.dentry = dentry; it.buffer = buffer; it.buffer_size = buffer_size; it.buffer_ofs = 0; - it.it.sb = dentry->d_sb; - - ret = inline_listxattr(&it); - if (ret >= 0 || ret == -ENOATTR) - ret = shared_listxattr(&it); - erofs_put_metabuf(&it.it.buf); - return ret; + ret = erofs_xattr_iter_inline(&it, inode, false); + if (!ret || ret == -ENOATTR) + ret = erofs_xattr_iter_shared(&it, inode, false); + if (ret == -ENOATTR) + ret = 0; + erofs_put_metabuf(&it.buf); + return ret ? ret : it.buffer_ofs; } void erofs_xattr_prefixes_cleanup(struct super_block *sb) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 160b3da43aec..5f1890e309c6 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -5,7 +5,6 @@ * Copyright (C) 2022 Alibaba Cloud */ #include "compress.h" -#include <linux/prefetch.h> #include <linux/psi.h> #include <linux/cpuhotplug.h> #include <trace/events/erofs.h> @@ -92,13 +91,8 @@ struct z_erofs_pcluster { struct z_erofs_bvec compressed_bvecs[]; }; -/* let's avoid the valid 32-bit kernel addresses */ - -/* the chained workgroup has't submitted io (still open) */ -#define Z_EROFS_PCLUSTER_TAIL ((void *)0x5F0ECAFE) -/* the chained workgroup has already submitted io */ -#define Z_EROFS_PCLUSTER_TAIL_CLOSED ((void *)0x5F0EDEAD) - +/* the end of a chain of pclusters */ +#define Z_EROFS_PCLUSTER_TAIL ((void *) 0x700 + POISON_POINTER_DELTA) #define Z_EROFS_PCLUSTER_NIL (NULL) struct z_erofs_decompressqueue { @@ -241,14 +235,20 @@ static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter, static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter, struct z_erofs_bvec *bvec, - struct page **candidate_bvpage) + struct page **candidate_bvpage, + struct page **pagepool) { - if (iter->cur == iter->nr) { - if (!*candidate_bvpage) - return -EAGAIN; - + if (iter->cur >= iter->nr) { + struct page *nextpage = *candidate_bvpage; + + if (!nextpage) { + nextpage = erofs_allocpage(pagepool, GFP_NOFS); + if (!nextpage) + return -ENOMEM; + set_page_private(nextpage, Z_EROFS_SHORTLIVED_PAGE); + } DBG_BUGON(iter->bvset->nextpage); - iter->bvset->nextpage = *candidate_bvpage; + iter->bvset->nextpage = nextpage; z_erofs_bvset_flip(iter); iter->bvset->nextpage = NULL; @@ -500,20 +500,6 @@ out_error_pcluster_pool: enum z_erofs_pclustermode { Z_EROFS_PCLUSTER_INFLIGHT, /* - * The current pclusters was the tail of an exist chain, in addition - * that the previous processed chained pclusters are all decided to - * be hooked up to it. - * A new chain will be created for the remaining pclusters which are - * not processed yet, so different from Z_EROFS_PCLUSTER_FOLLOWED, - * the next pcluster cannot reuse the whole page safely for inplace I/O - * in the following scenario: - * ________________________________________________________________ - * | tail (partial) page | head (partial) page | - * | (belongs to the next pcl) | (belongs to the current pcl) | - * |_______PCLUSTER_FOLLOWED______|________PCLUSTER_HOOKED__________| - */ - Z_EROFS_PCLUSTER_HOOKED, - /* * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it * could be dispatched into bypass queue later due to uptodated managed * pages. All related online pages cannot be reused for inplace I/O (or @@ -530,8 +516,8 @@ enum z_erofs_pclustermode { * ________________________________________________________________ * | tail (partial) page | head (partial) page | * | (of the current cl) | (of the previous collection) | - * | PCLUSTER_FOLLOWED or | | - * |_____PCLUSTER_HOOKED__|___________PCLUSTER_FOLLOWED____________| + * | | | + * |__PCLUSTER_FOLLOWED___|___________PCLUSTER_FOLLOWED____________| * * [ (*) the above page can be used as inplace I/O. ] */ @@ -543,12 +529,12 @@ struct z_erofs_decompress_frontend { struct erofs_map_blocks map; struct z_erofs_bvec_iter biter; + struct page *pagepool; struct page *candidate_bvpage; - struct z_erofs_pcluster *pcl, *tailpcl; + struct z_erofs_pcluster *pcl; z_erofs_next_pcluster_t owned_head; enum z_erofs_pclustermode mode; - bool readahead; /* used for applying cache strategy on the fly */ bool backmost; erofs_off_t headoffset; @@ -578,8 +564,7 @@ static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe) return false; } -static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, - struct page **pagepool) +static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe) { struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode)); struct z_erofs_pcluster *pcl = fe->pcl; @@ -620,7 +605,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, * succeeds or fallback to in-place I/O instead * to avoid any direct reclaim. */ - newpage = erofs_allocpage(pagepool, gfp); + newpage = erofs_allocpage(&fe->pagepool, gfp); if (!newpage) continue; set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE); @@ -633,7 +618,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, if (page) put_page(page); else if (newpage) - erofs_pagepool_add(pagepool, newpage); + erofs_pagepool_add(&fe->pagepool, newpage); } /* @@ -654,7 +639,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, DBG_BUGON(z_erofs_is_inline_pcluster(pcl)); /* - * refcount of workgroup is now freezed as 1, + * refcount of workgroup is now freezed as 0, * therefore no need to worry about available decompression users. */ for (i = 0; i < pcl->pclusterpages; ++i) { @@ -678,29 +663,73 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, return 0; } -int erofs_try_to_free_cached_page(struct page *page) +static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp) { - struct z_erofs_pcluster *const pcl = (void *)page_private(page); - int ret, i; + struct z_erofs_pcluster *pcl = folio_get_private(folio); + bool ret; + int i; - if (!erofs_workgroup_try_to_freeze(&pcl->obj, 1)) - return 0; + if (!folio_test_private(folio)) + return true; + + ret = false; + spin_lock(&pcl->obj.lockref.lock); + if (pcl->obj.lockref.count > 0) + goto out; - ret = 0; DBG_BUGON(z_erofs_is_inline_pcluster(pcl)); for (i = 0; i < pcl->pclusterpages; ++i) { - if (pcl->compressed_bvecs[i].page == page) { + if (pcl->compressed_bvecs[i].page == &folio->page) { WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL); - ret = 1; + ret = true; break; } } - erofs_workgroup_unfreeze(&pcl->obj, 1); if (ret) - detach_page_private(page); + folio_detach_private(folio); +out: + spin_unlock(&pcl->obj.lockref.lock); return ret; } +/* + * It will be called only on inode eviction. In case that there are still some + * decompression requests in progress, wait with rescheduling for a bit here. + * An extra lock could be introduced instead but it seems unnecessary. + */ +static void z_erofs_cache_invalidate_folio(struct folio *folio, + size_t offset, size_t length) +{ + const size_t stop = length + offset; + + /* Check for potential overflow in debug mode */ + DBG_BUGON(stop > folio_size(folio) || stop < length); + + if (offset == 0 && stop == folio_size(folio)) + while (!z_erofs_cache_release_folio(folio, GFP_NOFS)) + cond_resched(); +} + +static const struct address_space_operations z_erofs_cache_aops = { + .release_folio = z_erofs_cache_release_folio, + .invalidate_folio = z_erofs_cache_invalidate_folio, +}; + +int erofs_init_managed_cache(struct super_block *sb) +{ + struct inode *const inode = new_inode(sb); + + if (!inode) + return -ENOMEM; + + set_nlink(inode, 1); + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &z_erofs_cache_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + EROFS_SB(sb)->managed_cache = inode; + return 0; +} + static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe, struct z_erofs_bvec *bvec) { @@ -731,7 +760,8 @@ static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe, !fe->candidate_bvpage) fe->candidate_bvpage = bvec->page; } - ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage); + ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage, + &fe->pagepool); fe->pcl->vcnt += (ret >= 0); return ret; } @@ -750,19 +780,7 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f) return; } - /* - * type 2, link to the end of an existing open chain, be careful - * that its submission is controlled by the original attached chain. - */ - if (*owned_head != &pcl->next && pcl != f->tailpcl && - cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL, - *owned_head) == Z_EROFS_PCLUSTER_TAIL) { - *owned_head = Z_EROFS_PCLUSTER_TAIL; - f->mode = Z_EROFS_PCLUSTER_HOOKED; - f->tailpcl = NULL; - return; - } - /* type 3, it belongs to a chain, but it isn't the end of the chain */ + /* type 2, it belongs to an ongoing chain */ f->mode = Z_EROFS_PCLUSTER_INFLIGHT; } @@ -786,7 +804,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (IS_ERR(pcl)) return PTR_ERR(pcl); - atomic_set(&pcl->obj.refcount, 1); + spin_lock_init(&pcl->obj.lockref.lock); pcl->algorithmformat = map->m_algorithmformat; pcl->length = 0; pcl->partial = true; @@ -823,9 +841,6 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) goto err_out; } } - /* used to check tail merging loop due to corrupted images */ - if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL) - fe->tailpcl = pcl; fe->owned_head = &pcl->next; fe->pcl = pcl; return 0; @@ -846,7 +861,6 @@ static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe) /* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */ DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL); - DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED); if (!(map->m_flags & EROFS_MAP_META)) { grp = erofs_find_workgroup(fe->inode->i_sb, @@ -865,10 +879,6 @@ static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe) if (ret == -EEXIST) { mutex_lock(&fe->pcl->lock); - /* used to check tail merging loop due to corrupted images */ - if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL) - fe->tailpcl = fe->pcl; - z_erofs_try_to_claim_pcluster(fe); } else if (ret) { return ret; @@ -908,10 +918,8 @@ static bool z_erofs_collector_end(struct z_erofs_decompress_frontend *fe) z_erofs_bvec_iter_end(&fe->biter); mutex_unlock(&pcl->lock); - if (fe->candidate_bvpage) { - DBG_BUGON(z_erofs_is_shortlived_page(fe->candidate_bvpage)); + if (fe->candidate_bvpage) fe->candidate_bvpage = NULL; - } /* * if all pending pages are added, don't hold its reference @@ -958,7 +966,7 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos, } static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, - struct page *page, struct page **pagepool) + struct page *page) { struct inode *const inode = fe->inode; struct erofs_map_blocks *const map = &fe->map; @@ -1016,7 +1024,7 @@ repeat: fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } else { /* bind cache first when cached decompression is preferred */ - z_erofs_bind_cache(fe, pagepool); + z_erofs_bind_cache(fe); } hitted: /* @@ -1025,8 +1033,7 @@ hitted: * those chains are handled asynchronously thus the page cannot be used * for inplace I/O or bvpage (should be processed in a strict order.) */ - tight &= (fe->mode >= Z_EROFS_PCLUSTER_HOOKED && - fe->mode != Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE); + tight &= (fe->mode > Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE); cur = end - min_t(unsigned int, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { @@ -1056,24 +1063,13 @@ hitted: if (cur) tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED); -retry: err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) { .page = page, .offset = offset - map->m_la, .end = end, }), exclusive); - /* should allocate an additional short-lived page for bvset */ - if (err == -EAGAIN && !fe->candidate_bvpage) { - fe->candidate_bvpage = alloc_page(GFP_NOFS | __GFP_NOFAIL); - set_page_private(fe->candidate_bvpage, - Z_EROFS_SHORTLIVED_PAGE); - goto retry; - } - - if (err) { - DBG_BUGON(err == -EAGAIN && fe->candidate_bvpage); + if (err) goto out; - } z_erofs_onlinepage_split(page); /* bump up the number of spiltted parts of a page */ @@ -1104,7 +1100,7 @@ out: return err; } -static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi, +static bool z_erofs_is_sync_decompress(struct erofs_sb_info *sbi, unsigned int readahead_pages) { /* auto: enable for read_folio, disable for readahead */ @@ -1283,6 +1279,8 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, struct erofs_sb_info *const sbi = EROFS_SB(be->sb); struct z_erofs_pcluster *pcl = be->pcl; unsigned int pclusterpages = z_erofs_pclusterpages(pcl); + const struct z_erofs_decompressor *decompressor = + &erofs_decompressors[pcl->algorithmformat]; unsigned int i, inputsize; int err2; struct page *page; @@ -1326,7 +1324,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, else inputsize = pclusterpages * PAGE_SIZE; - err = z_erofs_decompress(&(struct z_erofs_decompress_req) { + err = decompressor->decompress(&(struct z_erofs_decompress_req) { .sb = be->sb, .in = be->compressed_pages, .out = be->decompressed_pages, @@ -1404,10 +1402,7 @@ static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, }; z_erofs_next_pcluster_t owned = io->head; - while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) { - /* impossible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */ - DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL); - /* impossible that 'owned' equals Z_EROFS_PCLUSTER_NIL */ + while (owned != Z_EROFS_PCLUSTER_TAIL) { DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL); be.pcl = container_of(owned, struct z_erofs_pcluster, next); @@ -1424,7 +1419,7 @@ static void z_erofs_decompressqueue_work(struct work_struct *work) container_of(work, struct z_erofs_decompressqueue, u.work); struct page *pagepool = NULL; - DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED); + DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL); z_erofs_decompress_queue(bgq, &pagepool); erofs_release_pages(&pagepool); kvfree(bgq); @@ -1452,7 +1447,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; /* Use (kthread_)work and sync decompression for atomic contexts only */ - if (in_atomic() || irqs_disabled()) { + if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) { #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD struct kthread_worker *worker; @@ -1612,7 +1607,7 @@ fg_out: q->sync = true; } q->sb = sb; - q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED; + q->head = Z_EROFS_PCLUSTER_TAIL; return q; } @@ -1630,11 +1625,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT]; z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS]; - DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED); - if (owned_head == Z_EROFS_PCLUSTER_TAIL) - owned_head = Z_EROFS_PCLUSTER_TAIL_CLOSED; - - WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL_CLOSED); + WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL); WRITE_ONCE(*submit_qtail, owned_head); WRITE_ONCE(*bypass_qtail, &pcl->next); @@ -1668,9 +1659,8 @@ static void z_erofs_decompressqueue_endio(struct bio *bio) } static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, - struct page **pagepool, struct z_erofs_decompressqueue *fgq, - bool *force_fg) + bool *force_fg, bool readahead) { struct super_block *sb = f->inode->i_sb; struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb)); @@ -1705,15 +1695,10 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, unsigned int i = 0; bool bypass = true; - /* no possible 'owned_head' equals the following */ - DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED); DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL); - pcl = container_of(owned_head, struct z_erofs_pcluster, next); + owned_head = READ_ONCE(pcl->next); - /* close the main owned chain at first */ - owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL, - Z_EROFS_PCLUSTER_TAIL_CLOSED); if (z_erofs_is_inline_pcluster(pcl)) { move_to_bypass_jobqueue(pcl, qtail, owned_head); continue; @@ -1731,8 +1716,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, do { struct page *page; - page = pickup_page_for_submission(pcl, i++, pagepool, - mc); + page = pickup_page_for_submission(pcl, i++, + &f->pagepool, mc); if (!page) continue; @@ -1761,7 +1746,7 @@ submit_bio_retry: bio->bi_iter.bi_sector = (sector_t)cur << (sb->s_blocksize_bits - 9); bio->bi_private = q[JQ_SUBMIT]; - if (f->readahead) + if (readahead) bio->bi_opf |= REQ_RAHEAD; ++nr_bios; } @@ -1797,16 +1782,16 @@ submit_bio_retry: } static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, - struct page **pagepool, bool force_fg) + bool force_fg, bool ra) { struct z_erofs_decompressqueue io[NR_JOBQUEUES]; if (f->owned_head == Z_EROFS_PCLUSTER_TAIL) return; - z_erofs_submit_queue(f, pagepool, io, &force_fg); + z_erofs_submit_queue(f, io, &force_fg, ra); /* handle bypass queue (no i/o pclusters) immediately */ - z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool); + z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool); if (!force_fg) return; @@ -1815,7 +1800,7 @@ static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ - z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); + z_erofs_decompress_queue(&io[JQ_SUBMIT], &f->pagepool); } /* @@ -1823,29 +1808,28 @@ static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, * approximate readmore strategies as a start. */ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, - struct readahead_control *rac, - erofs_off_t end, - struct page **pagepool, - bool backmost) + struct readahead_control *rac, bool backmost) { struct inode *inode = f->inode; struct erofs_map_blocks *map = &f->map; - erofs_off_t cur; + erofs_off_t cur, end, headoffset = f->headoffset; int err; if (backmost) { + if (rac) + end = headoffset + readahead_length(rac) - 1; + else + end = headoffset + PAGE_SIZE - 1; map->m_la = end; err = z_erofs_map_blocks_iter(inode, map, EROFS_GET_BLOCKS_READMORE); if (err) return; - /* expend ra for the trailing edge if readahead */ + /* expand ra for the trailing edge if readahead */ if (rac) { - loff_t newstart = readahead_pos(rac); - cur = round_up(map->m_la + map->m_llen, PAGE_SIZE); - readahead_expand(rac, newstart, cur - newstart); + readahead_expand(rac, headoffset, cur - headoffset); return; } end = round_up(end, PAGE_SIZE); @@ -1866,7 +1850,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, if (PageUptodate(page)) { unlock_page(page); } else { - err = z_erofs_do_read_page(f, page, pagepool); + err = z_erofs_do_read_page(f, page); if (err) erofs_err(inode->i_sb, "readmore error at page %lu @ nid %llu", @@ -1887,28 +1871,24 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio) struct inode *const inode = page->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); - struct page *pagepool = NULL; int err; trace_erofs_readpage(page, false); f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT; - z_erofs_pcluster_readmore(&f, NULL, f.headoffset + PAGE_SIZE - 1, - &pagepool, true); - err = z_erofs_do_read_page(&f, page, &pagepool); - z_erofs_pcluster_readmore(&f, NULL, 0, &pagepool, false); - + z_erofs_pcluster_readmore(&f, NULL, true); + err = z_erofs_do_read_page(&f, page); + z_erofs_pcluster_readmore(&f, NULL, false); (void)z_erofs_collector_end(&f); /* if some compressed cluster ready, need submit them anyway */ - z_erofs_runqueue(&f, &pagepool, - z_erofs_get_sync_decompress_policy(sbi, 0)); + z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, 0), false); if (err) erofs_err(inode->i_sb, "failed to read, err [%d]", err); erofs_put_metabuf(&f.map.buf); - erofs_release_pages(&pagepool); + erofs_release_pages(&f.pagepool); return err; } @@ -1917,14 +1897,12 @@ static void z_erofs_readahead(struct readahead_control *rac) struct inode *const inode = rac->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); - struct page *pagepool = NULL, *head = NULL, *page; + struct page *head = NULL, *page; unsigned int nr_pages; - f.readahead = true; f.headoffset = readahead_pos(rac); - z_erofs_pcluster_readmore(&f, rac, f.headoffset + - readahead_length(rac) - 1, &pagepool, true); + z_erofs_pcluster_readmore(&f, rac, true); nr_pages = readahead_count(rac); trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false); @@ -1940,20 +1918,19 @@ static void z_erofs_readahead(struct readahead_control *rac) /* traversal in reverse order */ head = (void *)page_private(page); - err = z_erofs_do_read_page(&f, page, &pagepool); + err = z_erofs_do_read_page(&f, page); if (err) erofs_err(inode->i_sb, "readahead error at page %lu @ nid %llu", page->index, EROFS_I(inode)->nid); put_page(page); } - z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false); + z_erofs_pcluster_readmore(&f, rac, false); (void)z_erofs_collector_end(&f); - z_erofs_runqueue(&f, &pagepool, - z_erofs_get_sync_decompress_policy(sbi, nr_pages)); + z_erofs_runqueue(&f, z_erofs_is_sync_decompress(sbi, nr_pages), true); erofs_put_metabuf(&f.map.buf); - erofs_release_pages(&pagepool); + erofs_release_pages(&f.pagepool); } const struct address_space_operations z_erofs_aops = { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index d37c5c89c728..1909ddafd9c7 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -22,8 +22,8 @@ struct z_erofs_maprecorder { bool partialref; }; -static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, - unsigned long lcn) +static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, + unsigned long lcn) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); @@ -129,7 +129,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, u8 *in, type; bool big_pcluster; - if (1 << amortizedshift == 4) + if (1 << amortizedshift == 4 && lclusterbits <= 14) vcnt = 2; else if (1 << amortizedshift == 2 && lclusterbits == 12) vcnt = 16; @@ -226,12 +226,11 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, return 0; } -static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, - unsigned long lcn, bool lookahead) +static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, + unsigned long lcn, bool lookahead) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const unsigned int lclusterbits = vi->z_logical_clusterbits; const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); unsigned int totalidx = erofs_iblks(inode); @@ -239,9 +238,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, unsigned int amortizedshift; erofs_off_t pos; - if (lclusterbits != 12) - return -EOPNOTSUPP; - if (lcn >= totalidx) return -EINVAL; @@ -281,23 +277,23 @@ out: return unpack_compacted_index(m, amortizedshift, pos, lookahead); } -static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m, - unsigned int lcn, bool lookahead) +static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, + unsigned int lcn, bool lookahead) { - const unsigned int datamode = EROFS_I(m->inode)->datalayout; - - if (datamode == EROFS_INODE_COMPRESSED_FULL) - return legacy_load_cluster_from_disk(m, lcn); - - if (datamode == EROFS_INODE_COMPRESSED_COMPACT) - return compacted_load_cluster_from_disk(m, lcn, lookahead); - - return -EINVAL; + switch (EROFS_I(m->inode)->datalayout) { + case EROFS_INODE_COMPRESSED_FULL: + return z_erofs_load_full_lcluster(m, lcn); + case EROFS_INODE_COMPRESSED_COMPACT: + return z_erofs_load_compact_lcluster(m, lcn, lookahead); + default: + return -EINVAL; + } } static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned int lookback_distance) { + struct super_block *sb = m->inode->i_sb; struct erofs_inode *const vi = EROFS_I(m->inode); const unsigned int lclusterbits = vi->z_logical_clusterbits; @@ -305,21 +301,15 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned long lcn = m->lcn - lookback_distance; int err; - /* load extent head logical cluster if needed */ - err = z_erofs_load_cluster_from_disk(m, lcn, false); + err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; switch (m->type) { case Z_EROFS_LCLUSTER_TYPE_NONHEAD: - if (!m->delta[0]) { - erofs_err(m->inode->i_sb, - "invalid lookback distance 0 @ nid %llu", - vi->nid); - DBG_BUGON(1); - return -EFSCORRUPTED; - } lookback_distance = m->delta[0]; + if (!lookback_distance) + goto err_bogus; continue; case Z_EROFS_LCLUSTER_TYPE_PLAIN: case Z_EROFS_LCLUSTER_TYPE_HEAD1: @@ -328,16 +318,15 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, m->map->m_la = (lcn << lclusterbits) | m->clusterofs; return 0; default: - erofs_err(m->inode->i_sb, - "unknown type %u @ lcn %lu of nid %llu", + erofs_err(sb, "unknown type %u @ lcn %lu of nid %llu", m->type, lcn, vi->nid); DBG_BUGON(1); return -EOPNOTSUPP; } } - - erofs_err(m->inode->i_sb, "bogus lookback distance @ nid %llu", - vi->nid); +err_bogus: + erofs_err(sb, "bogus lookback distance %u @ lcn %lu of nid %llu", + lookback_distance, m->lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } @@ -369,7 +358,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, if (m->compressedblks) goto out; - err = z_erofs_load_cluster_from_disk(m, lcn, false); + err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; @@ -401,9 +390,8 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, break; fallthrough; default: - erofs_err(m->inode->i_sb, - "cannot found CBLKCNT @ lcn %lu of nid %llu", - lcn, vi->nid); + erofs_err(sb, "cannot found CBLKCNT @ lcn %lu of nid %llu", lcn, + vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } @@ -411,9 +399,7 @@ out: map->m_plen = erofs_pos(sb, m->compressedblks); return 0; err_bonus_cblkcnt: - erofs_err(m->inode->i_sb, - "bogus CBLKCNT @ lcn %lu of nid %llu", - lcn, vi->nid); + erofs_err(sb, "bogus CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } @@ -434,7 +420,7 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) return 0; } - err = z_erofs_load_cluster_from_disk(m, lcn, true); + err = z_erofs_load_lcluster_from_disk(m, lcn, true); if (err) return err; @@ -481,7 +467,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, initial_lcn = ofs >> lclusterbits; endoff = ofs & ((1 << lclusterbits) - 1); - err = z_erofs_load_cluster_from_disk(&m, initial_lcn, false); + err = z_erofs_load_lcluster_from_disk(&m, initial_lcn, false); if (err) goto unmap_out; @@ -539,8 +525,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, if (flags & EROFS_GET_BLOCKS_FINDTAIL) { vi->z_tailextent_headlcn = m.lcn; /* for non-compact indexes, fragmentoff is 64 bits */ - if (fragment && - vi->datalayout == EROFS_INODE_COMPRESSED_FULL) + if (fragment && vi->datalayout == EROFS_INODE_COMPRESSED_FULL) vi->z_fragmentoff |= (u64)m.pblk << 32; } if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) { diff --git a/fs/eventfd.c b/fs/eventfd.c index 95850a13ce8d..8aa36cd37351 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -33,17 +33,17 @@ struct eventfd_ctx { /* * Every time that a write(2) is performed on an eventfd, the * value of the __u64 being written is added to "count" and a - * wakeup is performed on "wqh". A read(2) will return the "count" - * value to userspace, and will reset "count" to zero. The kernel - * side eventfd_signal() also, adds to the "count" counter and - * issue a wakeup. + * wakeup is performed on "wqh". If EFD_SEMAPHORE flag was not + * specified, a read(2) will return the "count" value to userspace, + * and will reset "count" to zero. The kernel side eventfd_signal() + * also, adds to the "count" counter and issue a wakeup. */ __u64 count; unsigned int flags; int id; }; -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask) +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask) { unsigned long flags; @@ -301,6 +301,8 @@ static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) (unsigned long long)ctx->count); spin_unlock_irq(&ctx->wqh.lock); seq_printf(m, "eventfd-id: %d\n", ctx->id); + seq_printf(m, "eventfd-semaphore: %d\n", + !!(ctx->flags & EFD_SEMAPHORE)); } #endif diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 980483455cc0..4b1b3362f697 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -536,7 +536,7 @@ static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, - unsigned pollflags) + __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } @@ -1805,7 +1805,11 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, { int ret = default_wake_function(wq_entry, mode, sync, key); - list_del_init(&wq_entry->entry); + /* + * Pairs with list_empty_careful in ep_poll, and ensures future loop + * iterations see the cause of this wakeup. + */ + list_del_init_careful(&wq_entry->entry); return ret; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index e99183a74611..3cbd270e0cba 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -389,7 +389,7 @@ const struct file_operations exfat_file_operations = { #endif .mmap = generic_file_mmap, .fsync = exfat_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 6b4bebe982ca..d1ae0f0a3726 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -192,7 +192,7 @@ const struct file_operations ext2_file_operations = { .release = ext2_release_file, .fsync = ext2_fsync, .get_unmapped_area = thp_get_unmapped_area, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index c1edde817be8..1f72f977c6db 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -324,17 +324,15 @@ static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info **grp_info; - long indexv, indexh; - - if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) { - ext4_error(sb, "invalid group %u", group); - return NULL; - } - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); - return grp_info[indexh]; + struct ext4_group_info **grp_info; + long indexv, indexh; + + if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) + return NULL; + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* @@ -886,7 +884,10 @@ static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, if (!ext4_bg_has_super(sb, group)) return 0; - return EXT4_SB(sb)->s_gdb_count; + if (ext4_has_feature_meta_bg(sb)) + return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg); + else + return EXT4_SB(sb)->s_gdb_count; } /** diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8104a21b001a..02fa8a64dc3f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2968,6 +2968,7 @@ int ext4_fileattr_set(struct mnt_idmap *idmap, int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); int ext4_update_overhead(struct super_block *sb, bool force); +int ext4_force_shutdown(struct super_block *sb, u32 flags); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index d101b3b0c7da..e8261900f4f3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -147,6 +147,17 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return generic_file_read_iter(iocb, to); } +static ssize_t ext4_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + return -EIO; + return filemap_splice_read(in, ppos, pipe, len, flags); +} + /* * Called when an inode is released. Note that this is different * from ext4_file_open: open gets called at every open, but release @@ -957,7 +968,7 @@ const struct file_operations ext4_file_operations = { .release = ext4_release_file, .fsync = ext4_sync_file, .get_unmapped_area = thp_get_unmapped_area, - .splice_read = generic_file_splice_read, + .splice_read = ext4_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, }; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f9a430152063..961284cc9b65 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -793,16 +793,9 @@ static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) } #endif -static int ext4_shutdown(struct super_block *sb, unsigned long arg) +int ext4_force_shutdown(struct super_block *sb, u32 flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); - __u32 flags; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (get_user(flags, (__u32 __user *)arg)) - return -EFAULT; if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; @@ -838,6 +831,19 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) return 0; } +static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg) +{ + u32 flags; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(flags, (__u32 __user *)arg)) + return -EFAULT; + + return ext4_force_shutdown(sb, flags); +} + struct getfsmap_info { struct super_block *gi_sb; struct fsmap_head __user *gi_data; @@ -1566,7 +1572,7 @@ resizefs_out: return ext4_ioctl_get_es_cache(filp, arg); case EXT4_IOC_SHUTDOWN: - return ext4_shutdown(sb, arg); + return ext4_ioctl_shutdown(sb, arg); case FS_IOC_ENABLE_VERITY: if (!ext4_has_feature_verity(sb)) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 45b579805c95..0caf6c730ce3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3834,19 +3834,10 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, return retval; } - /* - * We need to protect against old.inode directory getting converted - * from inline directory format into a normal one. - */ - if (S_ISDIR(old.inode->i_mode)) - inode_lock_nested(old.inode, I_MUTEX_NONDIR2); - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, &old.inlined); - if (IS_ERR(old.bh)) { - retval = PTR_ERR(old.bh); - goto unlock_moved_dir; - } + if (IS_ERR(old.bh)) + return PTR_ERR(old.bh); /* * Check for inode number is _not_ due to possible IO errors. @@ -4043,10 +4034,6 @@ release_bh: brelse(old.bh); brelse(new.bh); -unlock_moved_dir: - if (S_ISDIR(old.inode->i_mode)) - inode_unlock(old.inode); - return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 05fcecc36244..eaa5858d5285 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1096,6 +1096,15 @@ void ext4_update_dynamic_rev(struct super_block *sb) */ } +static void ext4_bdev_mark_dead(struct block_device *bdev) +{ + ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH); +} + +static const struct blk_holder_ops ext4_holder_ops = { + .mark_dead = ext4_bdev_mark_dead, +}; + /* * Open the external journal device */ @@ -1103,7 +1112,8 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; - bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, + &ext4_holder_ops); if (IS_ERR(bdev)) goto fail; return bdev; @@ -1118,17 +1128,12 @@ fail: /* * Release the journal device */ -static void ext4_blkdev_put(struct block_device *bdev) -{ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); -} - static void ext4_blkdev_remove(struct ext4_sb_info *sbi) { struct block_device *bdev; bdev = sbi->s_journal_bdev; if (bdev) { - ext4_blkdev_put(bdev); + blkdev_put(bdev, sbi->s_sb); sbi->s_journal_bdev = NULL; } } @@ -1449,6 +1454,11 @@ static void ext4_destroy_inode(struct inode *inode) EXT4_I(inode)->i_reserved_data_blocks); } +static void ext4_shutdown(struct super_block *sb) +{ + ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); +} + static void init_once(void *foo) { struct ext4_inode_info *ei = foo; @@ -1609,6 +1619,7 @@ static const struct super_operations ext4_sops = { .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, + .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, @@ -5899,7 +5910,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, out_journal: jbd2_journal_destroy(journal); out_bdev: - ext4_blkdev_put(bdev); + blkdev_put(bdev, sb); return NULL; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5ac53d2627d2..3fce122997ca 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4367,22 +4367,23 @@ out: return ret; } -static void f2fs_trace_rw_file_path(struct kiocb *iocb, size_t count, int rw) +static void f2fs_trace_rw_file_path(struct file *file, loff_t pos, size_t count, + int rw) { - struct inode *inode = file_inode(iocb->ki_filp); + struct inode *inode = file_inode(file); char *buf, *path; buf = f2fs_getname(F2FS_I_SB(inode)); if (!buf) return; - path = dentry_path_raw(file_dentry(iocb->ki_filp), buf, PATH_MAX); + path = dentry_path_raw(file_dentry(file), buf, PATH_MAX); if (IS_ERR(path)) goto free_buf; if (rw == WRITE) - trace_f2fs_datawrite_start(inode, iocb->ki_pos, count, + trace_f2fs_datawrite_start(inode, pos, count, current->pid, path, current->comm); else - trace_f2fs_dataread_start(inode, iocb->ki_pos, count, + trace_f2fs_dataread_start(inode, pos, count, current->pid, path, current->comm); free_buf: f2fs_putname(buf); @@ -4398,7 +4399,8 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return -EOPNOTSUPP; if (trace_f2fs_dataread_start_enabled()) - f2fs_trace_rw_file_path(iocb, iov_iter_count(to), READ); + f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos, + iov_iter_count(to), READ); if (f2fs_should_use_dio(inode, iocb, to)) { ret = f2fs_dio_read_iter(iocb, to); @@ -4413,6 +4415,30 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +static ssize_t f2fs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + const loff_t pos = *ppos; + ssize_t ret; + + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + + if (trace_f2fs_dataread_start_enabled()) + f2fs_trace_rw_file_path(in, pos, len, READ); + + ret = filemap_splice_read(in, ppos, pipe, len, flags); + if (ret > 0) + f2fs_update_iostat(F2FS_I_SB(inode), inode, + APP_BUFFERED_READ_IO, ret); + + if (trace_f2fs_dataread_end_enabled()) + trace_f2fs_dataread_end(inode, pos, ret); + return ret; +} + static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; @@ -4714,7 +4740,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = preallocated; } else { if (trace_f2fs_datawrite_start_enabled()) - f2fs_trace_rw_file_path(iocb, orig_count, WRITE); + f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos, + orig_count, WRITE); /* Do the actual write. */ ret = dio ? @@ -4919,7 +4946,7 @@ const struct file_operations f2fs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = f2fs_compat_ioctl, #endif - .splice_read = generic_file_splice_read, + .splice_read = f2fs_file_splice_read, .splice_write = iter_file_splice_write, .fadvise = f2fs_file_fadvise, }; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 77a71276ecb1..ad597b417fea 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -995,20 +995,12 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, goto out; } - /* - * Copied from ext4_rename: we need to protect against old.inode - * directory getting converted from inline directory format into - * a normal one. - */ - if (S_ISDIR(old_inode->i_mode)) - inode_lock_nested(old_inode, I_MUTEX_NONDIR2); - err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) err = PTR_ERR(old_page); - goto out_unlock_old; + goto out; } if (S_ISDIR(old_inode->i_mode)) { @@ -1116,9 +1108,6 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, f2fs_unlock_op(sbi); - if (S_ISDIR(old_inode->i_mode)) - inode_unlock(old_inode); - if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); @@ -1133,9 +1122,6 @@ out_dir: f2fs_put_page(old_dir_page, 0); out_old: f2fs_put_page(old_page, 0); -out_unlock_old: - if (S_ISDIR(old_inode->i_mode)) - inode_unlock(old_inode); out: iput(whiteout); return err; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 9f15b03037db..e34197a70dc1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1538,7 +1538,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) int i; for (i = 0; i < sbi->s_ndevs; i++) { - blkdev_put(FDEV(i).bdev, FMODE_EXCL); + blkdev_put(FDEV(i).bdev, sbi->sb->s_type); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif @@ -3993,6 +3993,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned int max_devices = MAX_DEVICES; unsigned int logical_blksize; + blk_mode_t mode = sb_open_mode(sbi->sb->s_flags); int i; /* Initialize single device information */ @@ -4024,8 +4025,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) if (max_devices == 1) { /* Single zoned block device mount */ FDEV(0).bdev = - blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, - sbi->sb->s_mode, sbi->sb->s_type); + blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, mode, + sbi->sb->s_type, NULL); } else { /* Multi-device mount */ memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN); @@ -4043,8 +4044,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) (FDEV(i).total_segments << sbi->log_blocks_per_seg) - 1; } - FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, - sbi->sb->s_mode, sbi->sb->s_type); + FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, mode, + sbi->sb->s_type, + NULL); } if (IS_ERR(FDEV(i).bdev)) return PTR_ERR(FDEV(i).bdev); diff --git a/fs/fat/file.c b/fs/fat/file.c index 795a4fad5c40..456477946dd9 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -209,7 +209,7 @@ const struct file_operations fat_file_operations = { .unlocked_ioctl = fat_generic_ioctl, .compat_ioctl = compat_ptr_ioctl, .fsync = fat_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = fat_fallocate, }; diff --git a/fs/file_table.c b/fs/file_table.c index 372653b92617..e06c68e2d757 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -44,18 +44,40 @@ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; +/* Container for backing file with optional real path */ +struct backing_file { + struct file file; + struct path real_path; +}; + +static inline struct backing_file *backing_file(struct file *f) +{ + return container_of(f, struct backing_file, file); +} + +struct path *backing_file_real_path(struct file *f) +{ + return &backing_file(f)->real_path; +} +EXPORT_SYMBOL_GPL(backing_file_real_path); + static void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_rcuhead); put_cred(f->f_cred); - kmem_cache_free(filp_cachep, f); + if (unlikely(f->f_mode & FMODE_BACKING)) + kfree(backing_file(f)); + else + kmem_cache_free(filp_cachep, f); } static inline void file_free(struct file *f) { security_file_free(f); - if (!(f->f_mode & FMODE_NOACCOUNT)) + if (unlikely(f->f_mode & FMODE_BACKING)) + path_put(backing_file_real_path(f)); + if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); call_rcu(&f->f_rcuhead, file_free_rcu); } @@ -131,20 +153,15 @@ static int __init init_fs_stat_sysctls(void) fs_initcall(init_fs_stat_sysctls); #endif -static struct file *__alloc_file(int flags, const struct cred *cred) +static int init_file(struct file *f, int flags, const struct cred *cred) { - struct file *f; int error; - f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); - if (unlikely(!f)) - return ERR_PTR(-ENOMEM); - f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { file_free_rcu(&f->f_rcuhead); - return ERR_PTR(error); + return error; } atomic_long_set(&f->f_count, 1); @@ -155,7 +172,7 @@ static struct file *__alloc_file(int flags, const struct cred *cred) f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ - return f; + return 0; } /* Find an unused file structure and return a pointer to it. @@ -172,6 +189,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; + int error; /* * Privileged users can go above max_files @@ -185,9 +203,15 @@ struct file *alloc_empty_file(int flags, const struct cred *cred) goto over; } - f = __alloc_file(flags, cred); - if (!IS_ERR(f)) - percpu_counter_inc(&nr_files); + f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); + if (unlikely(!f)) + return ERR_PTR(-ENOMEM); + + error = init_file(f, flags, cred); + if (unlikely(error)) + return ERR_PTR(error); + + percpu_counter_inc(&nr_files); return f; @@ -203,18 +227,51 @@ over: /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * - * Should not be used unless there's a very good reason to do so. + * This is only for kernel internal use, and the allocate file must not be + * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { - struct file *f = __alloc_file(flags, cred); + struct file *f; + int error; - if (!IS_ERR(f)) - f->f_mode |= FMODE_NOACCOUNT; + f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); + if (unlikely(!f)) + return ERR_PTR(-ENOMEM); + + error = init_file(f, flags, cred); + if (unlikely(error)) + return ERR_PTR(error); + + f->f_mode |= FMODE_NOACCOUNT; return f; } +/* + * Variant of alloc_empty_file() that allocates a backing_file container + * and doesn't check and modify nr_files. + * + * This is only for kernel internal use, and the allocate file must not be + * installed into file tables or such. + */ +struct file *alloc_empty_backing_file(int flags, const struct cred *cred) +{ + struct backing_file *ff; + int error; + + ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL); + if (unlikely(!ff)) + return ERR_PTR(-ENOMEM); + + error = init_file(&ff->file, flags, cred); + if (unlikely(error)) + return ERR_PTR(error); + + ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; + return &ff->file; +} + /** * alloc_file - allocate and initialize a 'struct file' * diff --git a/fs/fs_context.c b/fs/fs_context.c index 24ce12f0db32..851214d1d013 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -561,7 +561,8 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) return -ENOMEM; } - ctx->legacy_data[size++] = ','; + if (size) + ctx->legacy_data[size++] = ','; len = strlen(param->key); memcpy(ctx->legacy_data + size, param->key, len); size += len; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 89d97f6188e0..4553124f5406 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3252,7 +3252,7 @@ static const struct file_operations fuse_file_operations = { .lock = fuse_file_lock, .get_unmapped_area = thp_get_unmapped_area, .flock = fuse_file_flock, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index cb62c8f07d1e..1d679a3178ff 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1579,7 +1579,7 @@ const struct file_operations gfs2_file_fops = { .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = gfs2_file_splice_write, .setlease = simple_nosetlease, .fallocate = gfs2_fallocate, @@ -1610,7 +1610,7 @@ const struct file_operations gfs2_file_fops_nolock = { .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = gfs2_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 9af9ddb61ca0..cd962985b058 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -254,7 +254,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio = bio_alloc(sb->s_bdev, 1, REQ_OP_READ | REQ_META, GFP_NOFS); bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9); - bio_add_page(bio, page, PAGE_SIZE, 0); + __bio_add_page(bio, page, PAGE_SIZE, 0); bio->bi_end_io = end_bio_io_page; bio->bi_private = page; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 1f7bd068acf0..441d7fc952e3 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -694,7 +694,7 @@ static const struct file_operations hfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .fsync = hfs_file_fsync, .open = hfs_file_open, .release = hfs_file_release, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b21660475ac1..7d1a675e037d 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -372,7 +372,7 @@ static const struct file_operations hfsplus_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .fsync = hfsplus_file_fsync, .open = hfsplus_file_open, .release = hfsplus_file_release, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 28b4f15c19eb..87998df499f4 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -381,7 +381,7 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end, static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 88952d4a631e..1bb8d97cd9ae 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -259,7 +259,7 @@ const struct file_operations hpfs_file_ops = .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .unlocked_ioctl = hpfs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/fs/inode.c b/fs/inode.c index 577799b7855f..d37fad91c8da 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1104,9 +1104,51 @@ void discard_new_inode(struct inode *inode) EXPORT_SYMBOL(discard_new_inode); /** + * lock_two_inodes - lock two inodes (may be regular files but also dirs) + * + * Lock any non-NULL argument. The caller must make sure that if he is passing + * in two directories, one is not ancestor of the other. Zero, one or two + * objects may be locked by this function. + * + * @inode1: first inode to lock + * @inode2: second inode to lock + * @subclass1: inode lock subclass for the first lock obtained + * @subclass2: inode lock subclass for the second lock obtained + */ +void lock_two_inodes(struct inode *inode1, struct inode *inode2, + unsigned subclass1, unsigned subclass2) +{ + if (!inode1 || !inode2) { + /* + * Make sure @subclass1 will be used for the acquired lock. + * This is not strictly necessary (no current caller cares) but + * let's keep things consistent. + */ + if (!inode1) + swap(inode1, inode2); + goto lock; + } + + /* + * If one object is directory and the other is not, we must make sure + * to lock directory first as the other object may be its child. + */ + if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { + if (inode1 > inode2) + swap(inode1, inode2); + } else if (!S_ISDIR(inode1->i_mode)) + swap(inode1, inode2); +lock: + if (inode1) + inode_lock_nested(inode1, subclass1); + if (inode2 && inode2 != inode1) + inode_lock_nested(inode2, subclass2); +} + +/** * lock_two_nondirectories - take two i_mutexes on non-directory objects * - * Lock any non-NULL argument that is not a directory. + * Lock any non-NULL argument. Passed objects must not be directories. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock @@ -1114,13 +1156,9 @@ EXPORT_SYMBOL(discard_new_inode); */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { - if (inode1 > inode2) - swap(inode1, inode2); - - if (inode1 && !S_ISDIR(inode1->i_mode)) - inode_lock(inode1); - if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) - inode_lock_nested(inode2, I_MUTEX_NONDIR2); + WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); + WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); + lock_two_inodes(inode1, inode2, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); @@ -1131,10 +1169,14 @@ EXPORT_SYMBOL(lock_two_nondirectories); */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { - if (inode1 && !S_ISDIR(inode1->i_mode)) + if (inode1) { + WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); inode_unlock(inode1); - if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) + } + if (inode2 && inode2 != inode1) { + WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); inode_unlock(inode2); + } } EXPORT_SYMBOL(unlock_two_nondirectories); @@ -2264,7 +2306,8 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { - inode->i_fop = &def_blk_fops; + if (IS_ENABLED(CONFIG_BLOCK)) + inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; diff --git a/fs/internal.h b/fs/internal.h index bd3b2810a36b..f7a3dc111026 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -97,8 +97,9 @@ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ -extern struct file *alloc_empty_file(int, const struct cred *); -extern struct file *alloc_empty_file_noaccount(int, const struct cred *); +struct file *alloc_empty_file(int flags, const struct cred *cred); +struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); +struct file *alloc_empty_backing_file(int flags, const struct cred *cred); static inline void put_file_access(struct file *file) { @@ -121,6 +122,47 @@ extern bool mount_capable(struct fs_context *); int sb_init_dio_done_wq(struct super_block *sb); /* + * Prepare superblock for changing its read-only state (i.e., either remount + * read-write superblock read-only or vice versa). After this function returns + * mnt_is_readonly() will return true for any mount of the superblock if its + * caller is able to observe any changes done by the remount. This holds until + * sb_end_ro_state_change() is called. + */ +static inline void sb_start_ro_state_change(struct super_block *sb) +{ + WRITE_ONCE(sb->s_readonly_remount, 1); + /* + * For RO->RW transition, the barrier pairs with the barrier in + * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY + * cleared, it will see s_readonly_remount set. + * For RW->RO transition, the barrier pairs with the barrier in + * __mnt_want_write() before the mnt_is_readonly() check. The barrier + * makes sure if __mnt_want_write() sees MNT_WRITE_HOLD already + * cleared, it will see s_readonly_remount set. + */ + smp_wmb(); +} + +/* + * Ends section changing read-only state of the superblock. After this function + * returns if mnt_is_readonly() returns false, the caller will be able to + * observe all the changes remount did to the superblock. + */ +static inline void sb_end_ro_state_change(struct super_block *sb) +{ + /* + * This barrier provides release semantics that pairs with + * the smp_rmb() acquire semantics in mnt_is_readonly(). + * This barrier pair ensure that when mnt_is_readonly() sees + * 0 for sb->s_readonly_remount, it will also see all the + * preceding flag changes that were made during the RO state + * change. + */ + smp_wmb(); + WRITE_ONCE(sb->s_readonly_remount, 0); +} + +/* * open.c */ struct open_flags { @@ -152,6 +194,8 @@ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); +void lock_two_inodes(struct inode *inode1, struct inode *inode2, + unsigned subclass1, unsigned subclass2); /* * fs-writeback.c diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 063133ec77f4..0edab9deae2a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -312,7 +312,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, ctx->bio->bi_opf |= REQ_RAHEAD; ctx->bio->bi_iter.bi_sector = sector; ctx->bio->bi_end_io = iomap_read_end_io; - bio_add_folio(ctx->bio, folio, plen, poff); + bio_add_folio_nofail(ctx->bio, folio, plen, poff); } done: @@ -539,7 +539,7 @@ static int iomap_read_folio_sync(loff_t block_start, struct folio *folio, bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); - bio_add_folio(&bio, folio, plen, poff); + bio_add_folio_nofail(&bio, folio, plen, poff); return submit_bio_wait(&bio); } @@ -1582,7 +1582,7 @@ iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio, if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) { wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio); - bio_add_folio(wpc->ioend->io_bio, folio, len, poff); + bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff); } if (iop) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 019cc87d0fb3..08873f0627dd 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -203,7 +203,6 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - get_page(page); __bio_add_page(bio, page, len, 0); iomap_dio_submit_bio(iter, dio, bio, pos); } diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 837cd55fd4c5..6ae9d6fefb86 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -211,7 +211,10 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) ic->scan_dents = NULL; cond_resched(); } - jffs2_build_xattr_subsystem(c); + ret = jffs2_build_xattr_subsystem(c); + if (ret) + goto exit; + c->flags &= ~JFFS2_SB_FLAG_BUILDING; dbg_fsbuild("FS build complete\n"); diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 96b0275ce957..2345ca3f09ee 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -56,7 +56,7 @@ const struct file_operations jffs2_file_operations = .unlocked_ioctl=jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index aa4048a27f31..3b6bdc9a49e1 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -772,10 +772,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) } #define XREF_TMPHASH_SIZE (128) -void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) +int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_ref *ref, *_ref; - struct jffs2_xattr_ref *xref_tmphash[XREF_TMPHASH_SIZE]; + struct jffs2_xattr_ref **xref_tmphash; struct jffs2_xattr_datum *xd, *_xd; struct jffs2_inode_cache *ic; struct jffs2_raw_node_ref *raw; @@ -784,9 +784,12 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) BUG_ON(!(c->flags & JFFS2_SB_FLAG_BUILDING)); + xref_tmphash = kcalloc(XREF_TMPHASH_SIZE, + sizeof(struct jffs2_xattr_ref *), GFP_KERNEL); + if (!xref_tmphash) + return -ENOMEM; + /* Phase.1 : Merge same xref */ - for (i=0; i < XREF_TMPHASH_SIZE; i++) - xref_tmphash[i] = NULL; for (ref=c->xref_temp; ref; ref=_ref) { struct jffs2_xattr_ref *tmp; @@ -884,6 +887,8 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) "%u of xref (%u dead, %u orphan) found.\n", xdatum_count, xdatum_unchecked_count, xdatum_orphan_count, xref_count, xref_dead_count, xref_orphan_count); + kfree(xref_tmphash); + return 0; } struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 720007b2fd65..1b5030a3349d 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -71,7 +71,7 @@ static inline int is_xattr_ref_dead(struct jffs2_xattr_ref *ref) #ifdef CONFIG_JFFS2_FS_XATTR extern void jffs2_init_xattr_subsystem(struct jffs2_sb_info *c); -extern void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); +extern int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); extern void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c); extern struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, @@ -103,7 +103,7 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t); #else #define jffs2_init_xattr_subsystem(c) -#define jffs2_build_xattr_subsystem(c) +#define jffs2_build_xattr_subsystem(c) (0) #define jffs2_clear_xattr_subsystem(c) #define jffs2_xattr_do_crccheck_inode(c, ic) diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 2ee35be49de1..01b6912e60f8 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -144,7 +144,7 @@ const struct file_operations jfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fsync = jfs_fsync, .release = jfs_release, diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 695415cbfe98..e855b8fde76c 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1100,8 +1100,8 @@ int lmLogOpen(struct super_block *sb) * file systems to log may have n-to-1 relationship; */ - bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, - log); + bdev = blkdev_get_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + log, NULL); if (IS_ERR(bdev)) { rc = PTR_ERR(bdev); goto free; @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, log); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb) bdev = log->bdev; rc = lmLogShutdown(log); - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, log); kfree(log); @@ -1974,7 +1974,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bio = bio_alloc(log->bdev, 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; @@ -2115,7 +2115,7 @@ static void lbmStartIO(struct lbuf * bp) bio = bio_alloc(log->bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index b29d68b5eec5..494b9f4043cf 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -876,7 +876,7 @@ static int jfs_symlink(struct mnt_idmap *idmap, struct inode *dip, tid_t tid; ino_t ino = 0; struct component_name dname; - int ssize; /* source pathname size */ + u32 ssize; /* source pathname size */ struct btstack btstack; struct inode *ip = d_inode(dentry); s64 xlen = 0; @@ -957,7 +957,7 @@ static int jfs_symlink(struct mnt_idmap *idmap, struct inode *dip, if (ssize > sizeof (JFS_IP(ip)->i_inline)) JFS_IP(ip)->mode2 &= ~INLINEEA; - jfs_info("jfs_symlink: fast symlink added ssize:%d name:%s ", + jfs_info("jfs_symlink: fast symlink added ssize:%u name:%s ", ssize, name); } /* @@ -987,7 +987,7 @@ static int jfs_symlink(struct mnt_idmap *idmap, struct inode *dip, ip->i_size = ssize - 1; while (ssize) { /* This is kind of silly since PATH_MAX == 4K */ - int copy_size = min(ssize, PSIZE); + u32 copy_size = min_t(u32, ssize, PSIZE); mp = get_metapage(ip, xaddr, PSIZE, 1); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 40c4661f15b7..180906c36f51 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -1011,7 +1011,7 @@ const struct file_operations kernfs_file_fops = { .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 04ba95b83d16..22d3ff3818f5 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -355,7 +355,6 @@ static int lockd_get(void) int error; if (nlmsvc_serv) { - svc_get(nlmsvc_serv); nlmsvc_users++; return 0; } diff --git a/fs/minix/file.c b/fs/minix/file.c index 0dd05d47724a..906d192ab7f3 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -19,7 +19,7 @@ const struct file_operations minix_file_operations = { .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; static int minix_setattr(struct mnt_idmap *idmap, diff --git a/fs/namei.c b/fs/namei.c index e4fe0879ae55..91171da719c5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3028,8 +3028,8 @@ static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) return p; } - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + lock_two_inodes(p1->d_inode, p2->d_inode, + I_MUTEX_PARENT, I_MUTEX_PARENT2); return NULL; } @@ -3703,7 +3703,7 @@ static int vfs_tmpfile(struct mnt_idmap *idmap, } /** - * vfs_tmpfile_open - open a tmpfile for kernel internal use + * kernel_tmpfile_open - open a tmpfile for kernel internal use * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile @@ -3714,24 +3714,26 @@ static int vfs_tmpfile(struct mnt_idmap *idmap, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ -struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, - const struct path *parentpath, - umode_t mode, int open_flag, const struct cred *cred) +struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, + const struct path *parentpath, + umode_t mode, int open_flag, + const struct cred *cred) { struct file *file; int error; file = alloc_empty_file_noaccount(open_flag, cred); - if (!IS_ERR(file)) { - error = vfs_tmpfile(idmap, parentpath, file, mode); - if (error) { - fput(file); - file = ERR_PTR(error); - } + if (IS_ERR(file)) + return file; + + error = vfs_tmpfile(idmap, parentpath, file, mode); + if (error) { + fput(file); + file = ERR_PTR(error); } return file; } -EXPORT_SYMBOL(vfs_tmpfile_open); +EXPORT_SYMBOL(kernel_tmpfile_open); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, @@ -4731,7 +4733,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source (if it is not a directory). + * and source. * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4815,10 +4817,16 @@ int vfs_rename(struct renamedata *rd) take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); - if (!is_dir || (flags & RENAME_EXCHANGE)) - lock_two_nondirectories(source, target); - else if (target) - inode_lock(target); + /* + * Lock all moved children. Moved directories may need to change parent + * pointer so they need the lock to prevent against concurrent + * directory changes moving parent pointer. For regular files we've + * historically always done this. The lockdep locking subclasses are + * somewhat arbitrary but RENAME_EXCHANGE in particular can swap + * regular files and directories so it's difficult to tell which + * subclasses to use. + */ + lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) @@ -4866,9 +4874,9 @@ int vfs_rename(struct renamedata *rd) d_exchange(old_dentry, new_dentry); } out: - if (!is_dir || (flags & RENAME_EXCHANGE)) - unlock_two_nondirectories(source, target); - else if (target) + if (source) + inode_unlock(source); + if (target) inode_unlock(target); dput(new_dentry); if (!error) { diff --git a/fs/namespace.c b/fs/namespace.c index 54847db5b819..e157efc54023 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -309,9 +309,16 @@ static unsigned int mnt_get_writers(struct mount *mnt) static int mnt_is_readonly(struct vfsmount *mnt) { - if (mnt->mnt_sb->s_readonly_remount) + if (READ_ONCE(mnt->mnt_sb->s_readonly_remount)) return 1; - /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ + /* + * The barrier pairs with the barrier in sb_start_ro_state_change() + * making sure if we don't see s_readonly_remount set yet, we also will + * not see any superblock / mount flag changes done by remount. + * It also pairs with the barrier in sb_end_ro_state_change() + * assuring that if we see s_readonly_remount already cleared, we will + * see the values of superblock / mount flags updated by remount. + */ smp_rmb(); return __mnt_is_readonly(mnt); } @@ -364,9 +371,11 @@ int __mnt_want_write(struct vfsmount *m) } } /* - * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will - * be set to match its requirements. So we must not load that until - * MNT_WRITE_HOLD is cleared. + * The barrier pairs with the barrier sb_start_ro_state_change() making + * sure that if we see MNT_WRITE_HOLD cleared, we will also see + * s_readonly_remount set (or even SB_RDONLY / MNT_READONLY flags) in + * mnt_is_readonly() and bail in case we are racing with remount + * read-only. */ smp_rmb(); if (mnt_is_readonly(m)) { @@ -588,10 +597,8 @@ int sb_prepare_remount_readonly(struct super_block *sb) if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; - if (!err) { - sb->s_readonly_remount = 1; - smp_wmb(); - } + if (!err) + sb_start_ro_state_change(sb); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; @@ -658,9 +665,25 @@ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) return false; } -/* - * find the first mount at @dentry on vfsmount @mnt. - * call under rcu_read_lock() +/** + * __lookup_mnt - find first child mount + * @mnt: parent mount + * @dentry: mountpoint + * + * If @mnt has a child mount @c mounted @dentry find and return it. + * + * Note that the child mount @c need not be unique. There are cases + * where shadow mounts are created. For example, during mount + * propagation when a source mount @mnt whose root got overmounted by a + * mount @o after path lookup but before @namespace_sem could be + * acquired gets copied and propagated. So @mnt gets copied including + * @o. When @mnt is propagated to a destination mount @d that already + * has another mount @n mounted at the same mountpoint then the source + * mount @mnt will be tucked beneath @n, i.e., @n will be mounted on + * @mnt and @mnt mounted on @d. Now both @n and @o are mounted at @mnt + * on @dentry. + * + * Return: The first child of @mnt mounted @dentry or NULL. */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { @@ -910,6 +933,33 @@ void mnt_set_mountpoint(struct mount *mnt, hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } +/** + * mnt_set_mountpoint_beneath - mount a mount beneath another one + * + * @new_parent: the source mount + * @top_mnt: the mount beneath which @new_parent is mounted + * @new_mp: the new mountpoint of @top_mnt on @new_parent + * + * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and + * parent @top_mnt->mnt_parent and mount it on top of @new_parent at + * @new_mp. And mount @new_parent on the old parent and old + * mountpoint of @top_mnt. + * + * Context: This function expects namespace_lock() and lock_mount_hash() + * to have been acquired in that order. + */ +static void mnt_set_mountpoint_beneath(struct mount *new_parent, + struct mount *top_mnt, + struct mountpoint *new_mp) +{ + struct mount *old_top_parent = top_mnt->mnt_parent; + struct mountpoint *old_top_mp = top_mnt->mnt_mp; + + mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent); + mnt_change_mountpoint(new_parent, new_mp, top_mnt); +} + + static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, @@ -917,15 +967,42 @@ static void __attach_mnt(struct mount *mnt, struct mount *parent) list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } -/* - * vfsmount lock must be held for write +/** + * attach_mnt - mount a mount, attach to @mount_hashtable and parent's + * list of child mounts + * @parent: the parent + * @mnt: the new mount + * @mp: the new mountpoint + * @beneath: whether to mount @mnt beneath or on top of @parent + * + * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt + * to @parent's child mount list and to @mount_hashtable. + * + * If @beneath is true, remove @mnt from its current parent and + * mountpoint and mount it on @mp on @parent, and mount @parent on the + * old parent and old mountpoint of @mnt. Finally, attach @parent to + * @mnt_hashtable and @parent->mnt_parent->mnt_mounts. + * + * Note, when __attach_mnt() is called @mnt->mnt_parent already points + * to the correct parent. + * + * Context: This function expects namespace_lock() and lock_mount_hash() + * to have been acquired in that order. */ -static void attach_mnt(struct mount *mnt, - struct mount *parent, - struct mountpoint *mp) +static void attach_mnt(struct mount *mnt, struct mount *parent, + struct mountpoint *mp, bool beneath) { - mnt_set_mountpoint(parent, mp, mnt); - __attach_mnt(mnt, parent); + if (beneath) + mnt_set_mountpoint_beneath(mnt, parent, mp); + else + mnt_set_mountpoint(parent, mp, mnt); + /* + * Note, @mnt->mnt_parent has to be used. If @mnt was mounted + * beneath @parent then @mnt will need to be attached to + * @parent's old parent, not @parent. IOW, @mnt->mnt_parent + * isn't the same mount as @parent. + */ + __attach_mnt(mnt, mnt->mnt_parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) @@ -937,7 +1014,7 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); - attach_mnt(mnt, parent, mp); + attach_mnt(mnt, parent, mp, false); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); @@ -1767,6 +1844,19 @@ bool may_mount(void) return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } +/** + * path_mounted - check whether path is mounted + * @path: path to check + * + * Determine whether @path refers to the root of a mount. + * + * Return: true if @path is the root of a mount, false if not. + */ +static inline bool path_mounted(const struct path *path) +{ + return path->mnt->mnt_root == path->dentry; +} + static void warn_mandlock(void) { pr_warn_once("=======================================================\n" @@ -1782,7 +1872,7 @@ static int can_umount(const struct path *path, int flags) if (!may_mount()) return -EPERM; - if (path->dentry != path->mnt->mnt_root) + if (!path_mounted(path)) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; @@ -1925,7 +2015,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); - attach_mnt(q, parent, p->mnt_mp); + attach_mnt(q, parent, p->mnt_mp, false); unlock_mount_hash(); } } @@ -2134,12 +2224,17 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) return 0; } -/* - * @source_mnt : mount tree to be attached - * @nd : place the mount tree @source_mnt is attached - * @parent_nd : if non-null, detach the source_mnt from its parent and - * store the parent mount and mountpoint dentry. - * (done when source_mnt is moved) +enum mnt_tree_flags_t { + MNT_TREE_MOVE = BIT(0), + MNT_TREE_BENEATH = BIT(1), +}; + +/** + * attach_recursive_mnt - attach a source mount tree + * @source_mnt: mount tree to be attached + * @top_mnt: mount that @source_mnt will be mounted on or mounted beneath + * @dest_mp: the mountpoint @source_mnt will be mounted at + * @flags: modify how @source_mnt is supposed to be attached * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. @@ -2196,22 +2291,28 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. + * + * Context: The function expects namespace_lock() to be held. + * Return: If @source_mnt was successfully attached 0 is returned. + * Otherwise a negative error code is returned. */ static int attach_recursive_mnt(struct mount *source_mnt, - struct mount *dest_mnt, - struct mountpoint *dest_mp, - bool moving) + struct mount *top_mnt, + struct mountpoint *dest_mp, + enum mnt_tree_flags_t flags) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); - struct mnt_namespace *ns = dest_mnt->mnt_ns; + struct mnt_namespace *ns = top_mnt->mnt_ns; struct mountpoint *smp; - struct mount *child, *p; + struct mount *child, *dest_mnt, *p; struct hlist_node *n; - int err; + int err = 0; + bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH; - /* Preallocate a mountpoint in case the new mounts need - * to be tucked under other mounts. + /* + * Preallocate a mountpoint in case the new mounts need to be + * mounted beneath mounts on the same mountpoint. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) @@ -2224,29 +2325,41 @@ static int attach_recursive_mnt(struct mount *source_mnt, goto out; } + if (beneath) + dest_mnt = top_mnt->mnt_parent; + else + dest_mnt = top_mnt; + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); - lock_mount_hash(); - if (err) - goto out_cleanup_ids; + } + lock_mount_hash(); + if (err) + goto out_cleanup_ids; + + if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); - } else { - lock_mount_hash(); } + if (moving) { + if (beneath) + dest_mp = smp; unhash_mnt(source_mnt); - attach_mnt(source_mnt, dest_mnt, dest_mp); + attach_mnt(source_mnt, top_mnt, dest_mp, beneath); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } - mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); + if (beneath) + mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp); + else + mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } @@ -2286,33 +2399,101 @@ static int attach_recursive_mnt(struct mount *source_mnt, return err; } -static struct mountpoint *lock_mount(struct path *path) +/** + * do_lock_mount - lock mount and mountpoint + * @path: target path + * @beneath: whether the intention is to mount beneath @path + * + * Follow the mount stack on @path until the top mount @mnt is found. If + * the initial @path->{mnt,dentry} is a mountpoint lookup the first + * mount stacked on top of it. Then simply follow @{mnt,mnt->mnt_root} + * until nothing is stacked on top of it anymore. + * + * Acquire the inode_lock() on the top mount's ->mnt_root to protect + * against concurrent removal of the new mountpoint from another mount + * namespace. + * + * If @beneath is requested, acquire inode_lock() on @mnt's mountpoint + * @mp on @mnt->mnt_parent must be acquired. This protects against a + * concurrent unlink of @mp->mnt_dentry from another mount namespace + * where @mnt doesn't have a child mount mounted @mp. A concurrent + * removal of @mnt->mnt_root doesn't matter as nothing will be mounted + * on top of it for @beneath. + * + * In addition, @beneath needs to make sure that @mnt hasn't been + * unmounted or moved from its current mountpoint in between dropping + * @mount_lock and acquiring @namespace_sem. For the !@beneath case @mnt + * being unmounted would be detected later by e.g., calling + * check_mnt(mnt) in the function it's called from. For the @beneath + * case however, it's useful to detect it directly in do_lock_mount(). + * If @mnt hasn't been unmounted then @mnt->mnt_mountpoint still points + * to @mnt->mnt_mp->m_dentry. But if @mnt has been unmounted it will + * point to @mnt->mnt_root and @mnt->mnt_mp will be NULL. + * + * Return: Either the target mountpoint on the top mount or the top + * mount's mountpoint. + */ +static struct mountpoint *do_lock_mount(struct path *path, bool beneath) { - struct vfsmount *mnt; - struct dentry *dentry = path->dentry; -retry: - inode_lock(dentry->d_inode); - if (unlikely(cant_mount(dentry))) { - inode_unlock(dentry->d_inode); - return ERR_PTR(-ENOENT); - } - namespace_lock(); - mnt = lookup_mnt(path); - if (likely(!mnt)) { - struct mountpoint *mp = get_mountpoint(dentry); - if (IS_ERR(mp)) { + struct vfsmount *mnt = path->mnt; + struct dentry *dentry; + struct mountpoint *mp = ERR_PTR(-ENOENT); + + for (;;) { + struct mount *m; + + if (beneath) { + m = real_mount(mnt); + read_seqlock_excl(&mount_lock); + dentry = dget(m->mnt_mountpoint); + read_sequnlock_excl(&mount_lock); + } else { + dentry = path->dentry; + } + + inode_lock(dentry->d_inode); + if (unlikely(cant_mount(dentry))) { + inode_unlock(dentry->d_inode); + goto out; + } + + namespace_lock(); + + if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) { namespace_unlock(); inode_unlock(dentry->d_inode); - return mp; + goto out; } - return mp; + + mnt = lookup_mnt(path); + if (likely(!mnt)) + break; + + namespace_unlock(); + inode_unlock(dentry->d_inode); + if (beneath) + dput(dentry); + path_put(path); + path->mnt = mnt; + path->dentry = dget(mnt->mnt_root); } - namespace_unlock(); - inode_unlock(path->dentry->d_inode); - path_put(path); - path->mnt = mnt; - dentry = path->dentry = dget(mnt->mnt_root); - goto retry; + + mp = get_mountpoint(dentry); + if (IS_ERR(mp)) { + namespace_unlock(); + inode_unlock(dentry->d_inode); + } + +out: + if (beneath) + dput(dentry); + + return mp; +} + +static inline struct mountpoint *lock_mount(struct path *path) +{ + return do_lock_mount(path, false); } static void unlock_mount(struct mountpoint *where) @@ -2336,7 +2517,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; - return attach_recursive_mnt(mnt, p, mp, false); + return attach_recursive_mnt(mnt, p, mp, 0); } /* @@ -2367,7 +2548,7 @@ static int do_change_type(struct path *path, int ms_flags) int type; int err = 0; - if (path->dentry != path->mnt->mnt_root) + if (!path_mounted(path)) return -EINVAL; type = flags_to_propagation_type(ms_flags); @@ -2643,7 +2824,7 @@ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) if (!check_mnt(mnt)) return -EINVAL; - if (path->dentry != mnt->mnt.mnt_root) + if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) @@ -2682,7 +2863,7 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, if (!check_mnt(mnt)) return -EINVAL; - if (path->dentry != path->mnt->mnt_root) + if (!path_mounted(path)) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) @@ -2772,9 +2953,9 @@ static int do_set_group(struct path *from_path, struct path *to_path) err = -EINVAL; /* To and From paths should be mount roots */ - if (from_path->dentry != from_path->mnt->mnt_root) + if (!path_mounted(from_path)) goto out; - if (to_path->dentry != to_path->mnt->mnt_root) + if (!path_mounted(to_path)) goto out; /* Setting sharing groups is only allowed across same superblock */ @@ -2818,7 +2999,110 @@ out: return err; } -static int do_move_mount(struct path *old_path, struct path *new_path) +/** + * path_overmounted - check if path is overmounted + * @path: path to check + * + * Check if path is overmounted, i.e., if there's a mount on top of + * @path->mnt with @path->dentry as mountpoint. + * + * Context: This function expects namespace_lock() to be held. + * Return: If path is overmounted true is returned, false if not. + */ +static inline bool path_overmounted(const struct path *path) +{ + rcu_read_lock(); + if (unlikely(__lookup_mnt(path->mnt, path->dentry))) { + rcu_read_unlock(); + return true; + } + rcu_read_unlock(); + return false; +} + +/** + * can_move_mount_beneath - check that we can mount beneath the top mount + * @from: mount to mount beneath + * @to: mount under which to mount + * + * - Make sure that @to->dentry is actually the root of a mount under + * which we can mount another mount. + * - Make sure that nothing can be mounted beneath the caller's current + * root or the rootfs of the namespace. + * - Make sure that the caller can unmount the topmost mount ensuring + * that the caller could reveal the underlying mountpoint. + * - Ensure that nothing has been mounted on top of @from before we + * grabbed @namespace_sem to avoid creating pointless shadow mounts. + * - Prevent mounting beneath a mount if the propagation relationship + * between the source mount, parent mount, and top mount would lead to + * nonsensical mount trees. + * + * Context: This function expects namespace_lock() to be held. + * Return: On success 0, and on error a negative error code is returned. + */ +static int can_move_mount_beneath(const struct path *from, + const struct path *to, + const struct mountpoint *mp) +{ + struct mount *mnt_from = real_mount(from->mnt), + *mnt_to = real_mount(to->mnt), + *parent_mnt_to = mnt_to->mnt_parent; + + if (!mnt_has_parent(mnt_to)) + return -EINVAL; + + if (!path_mounted(to)) + return -EINVAL; + + if (IS_MNT_LOCKED(mnt_to)) + return -EINVAL; + + /* Avoid creating shadow mounts during mount propagation. */ + if (path_overmounted(from)) + return -EINVAL; + + /* + * Mounting beneath the rootfs only makes sense when the + * semantics of pivot_root(".", ".") are used. + */ + if (&mnt_to->mnt == current->fs->root.mnt) + return -EINVAL; + if (parent_mnt_to == current->nsproxy->mnt_ns->root) + return -EINVAL; + + for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent) + if (p == mnt_to) + return -EINVAL; + + /* + * If the parent mount propagates to the child mount this would + * mean mounting @mnt_from on @mnt_to->mnt_parent and then + * propagating a copy @c of @mnt_from on top of @mnt_to. This + * defeats the whole purpose of mounting beneath another mount. + */ + if (propagation_would_overmount(parent_mnt_to, mnt_to, mp)) + return -EINVAL; + + /* + * If @mnt_to->mnt_parent propagates to @mnt_from this would + * mean propagating a copy @c of @mnt_from on top of @mnt_from. + * Afterwards @mnt_from would be mounted on top of + * @mnt_to->mnt_parent and @mnt_to would be unmounted from + * @mnt->mnt_parent and remounted on @mnt_from. But since @c is + * already mounted on @mnt_from, @mnt_to would ultimately be + * remounted on top of @c. Afterwards, @mnt_from would be + * covered by a copy @c of @mnt_from and @c would be covered by + * @mnt_from itself. This defeats the whole purpose of mounting + * @mnt_from beneath @mnt_to. + */ + if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) + return -EINVAL; + + return 0; +} + +static int do_move_mount(struct path *old_path, struct path *new_path, + bool beneath) { struct mnt_namespace *ns; struct mount *p; @@ -2827,8 +3111,9 @@ static int do_move_mount(struct path *old_path, struct path *new_path) struct mountpoint *mp, *old_mp; int err; bool attached; + enum mnt_tree_flags_t flags = 0; - mp = lock_mount(new_path); + mp = do_lock_mount(new_path, beneath); if (IS_ERR(mp)) return PTR_ERR(mp); @@ -2836,6 +3121,8 @@ static int do_move_mount(struct path *old_path, struct path *new_path) p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); + if (attached) + flags |= MNT_TREE_MOVE; old_mp = old->mnt_mp; ns = old->mnt_ns; @@ -2855,7 +3142,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path) if (old->mnt.mnt_flags & MNT_LOCKED) goto out; - if (old_path->dentry != old_path->mnt->mnt_root) + if (!path_mounted(old_path)) goto out; if (d_is_dir(new_path->dentry) != @@ -2866,6 +3153,17 @@ static int do_move_mount(struct path *old_path, struct path *new_path) */ if (attached && IS_MNT_SHARED(parent)) goto out; + + if (beneath) { + err = can_move_mount_beneath(old_path, new_path, mp); + if (err) + goto out; + + err = -EINVAL; + p = p->mnt_parent; + flags |= MNT_TREE_BENEATH; + } + /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. @@ -2879,8 +3177,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path) if (p == old) goto out; - err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, - attached); + err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags); if (err) goto out; @@ -2912,7 +3209,7 @@ static int do_move_mount_old(struct path *path, const char *old_name) if (err) return err; - err = do_move_mount(&old_path, path); + err = do_move_mount(&old_path, path, false); path_put(&old_path); return err; } @@ -2937,8 +3234,7 @@ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, } /* Refuse the same filesystem on the same mount point */ - if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && - path->mnt->mnt_root == path->dentry) + if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path_mounted(path)) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) @@ -3079,13 +3375,10 @@ int finish_automount(struct vfsmount *m, const struct path *path) err = -ENOENT; goto discard_locked; } - rcu_read_lock(); - if (unlikely(__lookup_mnt(path->mnt, dentry))) { - rcu_read_unlock(); + if (path_overmounted(path)) { err = 0; goto discard_locked; } - rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); @@ -3777,6 +4070,10 @@ SYSCALL_DEFINE5(move_mount, if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; + if ((flags & (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) == + (MOVE_MOUNT_BENEATH | MOVE_MOUNT_SET_GROUP)) + return -EINVAL; + /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. @@ -3806,7 +4103,8 @@ SYSCALL_DEFINE5(move_mount, if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else - ret = do_move_mount(&from_path, &to_path); + ret = do_move_mount(&from_path, &to_path, + (flags & MOVE_MOUNT_BENEATH)); out_to: path_put(&to_path); @@ -3917,11 +4215,11 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; - if (root.mnt->mnt_root != root.dentry) + if (!path_mounted(&root)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ - if (new.mnt->mnt_root != new.dentry) + if (!path_mounted(&new)) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ @@ -3939,9 +4237,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ - attach_mnt(root_mnt, old_mnt, old_mp); + attach_mnt(root_mnt, old_mnt, old_mp, false); /* mount new_root on / */ - attach_mnt(new_mnt, root_parent, root_mp); + attach_mnt(new_mnt, root_parent, root_mp, false); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ @@ -4124,7 +4422,7 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) struct mount *mnt = real_mount(path->mnt); int err = 0; - if (path->dentry != mnt->mnt.mnt_root) + if (!path_mounted(path)) return -EINVAL; if (kattr->mnt_userns) { diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index fea5f8821da5..70f5563a8e81 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -35,7 +35,7 @@ bl_free_device(struct pnfs_block_dev *dev) } if (dev->bdev) - blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(dev->bdev, NULL); } } @@ -243,7 +243,8 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, if (!dev) return -EIO; - bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, + NULL); if (IS_ERR(bdev)) { printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); @@ -312,7 +313,8 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix) if (!devname) return ERR_PTR(-ENOMEM); - bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL); + bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, + NULL); if (IS_ERR(bdev)) { pr_warn("pNFS: failed to open device %s (%ld)\n", devname, PTR_ERR(bdev)); @@ -373,7 +375,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, return 0; out_blkdev_put: - blkdev_put(d->bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(d->bdev, NULL); return error; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f0edf5a36237..3855f3ce8d2d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -178,6 +178,27 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) } EXPORT_SYMBOL_GPL(nfs_file_read); +ssize_t +nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + ssize_t result; + + dprintk("NFS: splice_read(%pD2, %zu@%llu)\n", in, len, *ppos); + + nfs_start_io_read(inode); + result = nfs_revalidate_mapping(inode, in->f_mapping); + if (!result) { + result = filemap_splice_read(in, ppos, pipe, len, flags); + if (result > 0) + nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result); + } + nfs_end_io_read(inode); + return result; +} +EXPORT_SYMBOL_GPL(nfs_file_splice_read); + int nfs_file_mmap(struct file * file, struct vm_area_struct * vma) { @@ -879,7 +900,7 @@ const struct file_operations nfs_file_operations = { .fsync = nfs_file_fsync, .lock = nfs_lock, .flock = nfs_flock, - .splice_read = generic_file_splice_read, + .splice_read = nfs_file_splice_read, .splice_write = iter_file_splice_write, .check_flags = nfs_check_flags, .setlease = simple_nosetlease, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3cc027d3bd58..b5f21d35d30e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -416,6 +416,8 @@ static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); +ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, + size_t len, unsigned int flags); int nfs_file_mmap(struct file *, struct vm_area_struct *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 2563ed8580f3..4aeadd6e1a6d 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -454,7 +454,7 @@ const struct file_operations nfs4_file_operations = { .fsync = nfs_file_fsync, .lock = nfs_lock, .flock = nfs_flock, - .splice_read = generic_file_splice_read, + .splice_read = nfs_file_splice_read, .splice_write = iter_file_splice_write, .check_flags = nfs_check_flags, .setlease = nfs4_setlease, diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index f21259ead64b..4c9b87850ab1 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -80,6 +80,8 @@ enum { int nfsd_drc_slab_create(void); void nfsd_drc_slab_free(void); +int nfsd_net_reply_cache_init(struct nfsd_net *nn); +void nfsd_net_reply_cache_destroy(struct nfsd_net *nn); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *); diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index ae85257b4238..11a0eaa2f914 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -97,7 +97,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) goto out; err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; err = -ENOENT; @@ -107,7 +107,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) dprintk("found domain %s\n", buf); err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; fsidtype = simple_strtoul(buf, &ep, 10); if (*ep) @@ -593,7 +593,6 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) { /* client path expiry [flags anonuid anongid fsid] */ char *buf; - int len; int err; struct auth_domain *dom = NULL; struct svc_export exp = {}, *expp; @@ -609,8 +608,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) /* client */ err = -EINVAL; - len = qword_get(&mesg, buf, PAGE_SIZE); - if (len <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out; err = -ENOENT; @@ -620,7 +618,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) /* path */ err = -EINVAL; - if ((len = qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + if (qword_get(&mesg, buf, PAGE_SIZE) <= 0) goto out1; err = kern_path(buf, 0, &exp.ex_path); @@ -665,7 +663,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) goto out3; exp.ex_fsid = an_int; - while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { + while (qword_get(&mesg, buf, PAGE_SIZE) > 0) { if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); else if (strcmp(buf, "uuid") == 0) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index e6bb8eeb5bc2..fc8d5b7db9f8 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -151,8 +151,6 @@ nfsd3_proc_read(struct svc_rqst *rqstp) { struct nfsd3_readargs *argp = rqstp->rq_argp; struct nfsd3_readres *resp = rqstp->rq_resp; - unsigned int len; - int v; dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), @@ -166,17 +164,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp) if (argp->offset + argp->count > (u64)OFFSET_MAX) argp->count = (u64)OFFSET_MAX - argp->offset; - v = 0; - len = argp->count; resp->pages = rqstp->rq_next_page; - while (len > 0) { - struct page *page = *(rqstp->rq_next_page++); - - rqstp->rq_vec[v].iov_base = page_address(page); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } /* Obtain buffer pointer for payload. * 1 (status) + 22 (post_op_attr) + 1 (count) + 1 (eof) @@ -187,7 +175,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, v, &resp->count, &resp->eof); + &resp->count, &resp->eof); return rpc_success; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 3308dd671ef0..f32128955ec8 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -828,7 +828,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->len) < 0) return false; - xdr_write_pages(xdr, resp->pages, 0, resp->len); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, 0, + resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) return false; break; @@ -859,8 +860,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) return false; - xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, - resp->count); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, + rqstp->rq_res.page_base, + resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) return false; break; @@ -961,7 +963,8 @@ nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (!svcxdr_encode_cookieverf3(xdr, resp->verf)) return false; - xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); + svcxdr_encode_opaque_pages(rqstp, xdr, dirlist->pages, 0, + dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) return false; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 76db2fe29624..26b1343c8035 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2541,6 +2541,20 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, return p; } +static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, + struct timespec64 *tv) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 3); + if (!p) + return nfserr_resource; + + p = xdr_encode_hyper(p, (s64)tv->tv_sec); + *p = cpu_to_be32(tv->tv_nsec); + return nfs_ok; +} + /* * ctime (in NFSv4, time_metadata) is not writeable, and the client * doesn't really care what resolution could theoretically be stored by @@ -2566,12 +2580,16 @@ static __be32 *encode_time_delta(__be32 *p, struct inode *inode) return p; } -static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c) +static __be32 +nfsd4_encode_change_info4(struct xdr_stream *xdr, struct nfsd4_change_info *c) { - *p++ = cpu_to_be32(c->atomic); - p = xdr_encode_hyper(p, c->before_change); - p = xdr_encode_hyper(p, c->after_change); - return p; + if (xdr_stream_encode_bool(xdr, c->atomic) < 0) + return nfserr_resource; + if (xdr_stream_encode_u64(xdr, c->before_change) < 0) + return nfserr_resource; + if (xdr_stream_encode_u64(xdr, c->after_change) < 0) + return nfserr_resource; + return nfs_ok; } /* Encode as an array of strings the string given with components @@ -3348,11 +3366,9 @@ out_acl: p = xdr_encode_hyper(p, dummy64); } if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec); - *p++ = cpu_to_be32(stat.atime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.atime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_DELTA) { p = xdr_reserve_space(xdr, 12); @@ -3361,25 +3377,19 @@ out_acl: p = encode_time_delta(p, d_inode(dentry)); } if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec); - *p++ = cpu_to_be32(stat.ctime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.ctime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec); - *p++ = cpu_to_be32(stat.mtime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.mtime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_TIME_CREATE) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (s64)stat.btime.tv_sec); - *p++ = cpu_to_be32(stat.btime.tv_nsec); + status = nfsd4_encode_nfstime4(xdr, &stat.btime); + if (status) + goto out; } if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { u64 ino = stat.ino; @@ -3689,6 +3699,30 @@ fail: } static __be32 +nfsd4_encode_verifier4(struct xdr_stream *xdr, const nfs4_verifier *verf) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + memcpy(p, verf->data, sizeof(verf->data)); + return nfs_ok; +} + +static __be32 +nfsd4_encode_clientid4(struct xdr_stream *xdr, const clientid_t *clientid) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, sizeof(__be64)); + if (!p) + return nfserr_resource; + memcpy(p, clientid, sizeof(*clientid)); + return nfs_ok; +} + +static __be32 nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) { __be32 *p; @@ -3752,15 +3786,8 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_commit *commit = &u->commit; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, commit->co_verf.data, - NFS4_VERIFIER_SIZE); - return 0; + return nfsd4_encode_verifier4(resp->xdr, &commit->co_verf); } static __be32 @@ -3769,12 +3796,10 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - encode_cinfo(p, &create->cr_cinfo); + nfserr = nfsd4_encode_change_info4(xdr, &create->cr_cinfo); + if (nfserr) + return nfserr; return nfsd4_encode_bitmap(xdr, create->cr_bmval[0], create->cr_bmval[1], create->cr_bmval[2]); } @@ -3892,13 +3917,8 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &link->li_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &link->li_cinfo); } @@ -3913,11 +3933,11 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); if (nfserr) return nfserr; - p = xdr_reserve_space(xdr, 24); - if (!p) + nfserr = nfsd4_encode_change_info4(xdr, &open->op_cinfo); + if (nfserr) + return nfserr; + if (xdr_stream_encode_u32(xdr, open->op_rflags) < 0) return nfserr_resource; - p = encode_cinfo(p, &open->op_cinfo); - *p++ = cpu_to_be32(open->op_rflags); nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1], open->op_bmval[2]); @@ -3956,7 +3976,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_reserve_space(xdr, 32); if (!p) return nfserr_resource; - *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(open->op_recall); /* * TODO: space_limit's in delegations @@ -4018,6 +4038,11 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, return nfsd4_encode_stateid(xdr, &od->od_stateid); } +/* + * The operation of this function assumes that this is the only + * READ operation in the COMPOUND. If there are multiple READs, + * we use nfsd4_encode_readv(). + */ static __be32 nfsd4_encode_splice_read( struct nfsd4_compoundres *resp, struct nfsd4_read *read, @@ -4028,8 +4053,12 @@ static __be32 nfsd4_encode_splice_read( int status, space_left; __be32 nfserr; - /* Make sure there will be room for padding if needed */ - if (xdr->end - xdr->p < 1) + /* + * Make sure there is room at the end of buf->head for + * svcxdr_encode_opaque_pages() to create a tail buffer + * to XDR-pad the payload. + */ + if (xdr->iov != xdr->buf->head || xdr->end - xdr->p < 1) return nfserr_resource; nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp, @@ -4038,6 +4067,8 @@ static __be32 nfsd4_encode_splice_read( read->rd_length = maxcount; if (nfserr) goto out_err; + svcxdr_encode_opaque_pages(read->rd_rqstp, xdr, buf->pages, + buf->page_base, maxcount); status = svc_encode_result_payload(read->rd_rqstp, buf->head[0].iov_len, maxcount); if (status) { @@ -4045,31 +4076,19 @@ static __be32 nfsd4_encode_splice_read( goto out_err; } - buf->page_len = maxcount; - buf->len += maxcount; - xdr->page_ptr += (buf->page_base + maxcount + PAGE_SIZE - 1) - / PAGE_SIZE; - - /* Use rest of head for padding and remaining ops: */ - buf->tail[0].iov_base = xdr->p; - buf->tail[0].iov_len = 0; - xdr->iov = buf->tail; - if (maxcount&3) { - int pad = 4 - (maxcount&3); - - *(xdr->p++) = 0; - - buf->tail[0].iov_base += maxcount&3; - buf->tail[0].iov_len = pad; - buf->len += pad; - } - + /* + * Prepare to encode subsequent operations. + * + * xdr_truncate_encode() is not safe to use after a successful + * splice read has been done, so the following stream + * manipulations are open-coded. + */ space_left = min_t(int, (void *)xdr->end - (void *)xdr->p, buf->buflen - buf->len); buf->buflen = buf->len + space_left; xdr->end = (__be32 *)((void *)xdr->end + space_left); - return 0; + return nfs_ok; out_err: /* @@ -4090,13 +4109,13 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, __be32 zero = xdr_zero; __be32 nfserr; - read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount); - if (read->rd_vlen < 0) + if (xdr_reserve_space_vec(xdr, maxcount) < 0) return nfserr_resource; - nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, &maxcount, - &read->rd_eof); + nfserr = nfsd_iter_read(resp->rqstp, read->rd_fhp, file, + read->rd_offset, &maxcount, + xdr->buf->page_len & ~PAGE_MASK, + &read->rd_eof); read->rd_length = maxcount; if (nfserr) return nfserr; @@ -4213,15 +4232,9 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, int starting_len = xdr->buf->len; __be32 *p; - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - - /* XXX: Following NFSv3, we ignore the READDIR verifier for now. */ - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - xdr->buf->head[0].iov_len = (char *)xdr->p - - (char *)xdr->buf->head[0].iov_base; + nfserr = nfsd4_encode_verifier4(xdr, &readdir->rd_verf); + if (nfserr != nfs_ok) + return nfserr; /* * Number of bytes left for directory entries allowing for the @@ -4299,13 +4312,8 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &remove->rm_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &remove->rm_cinfo); } static __be32 @@ -4314,14 +4322,11 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 40); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &rename->rn_sinfo); - p = encode_cinfo(p, &rename->rn_tinfo); - return 0; + nfserr = nfsd4_encode_change_info4(xdr, &rename->rn_sinfo); + if (nfserr) + return nfserr; + return nfsd4_encode_change_info4(xdr, &rename->rn_tinfo); } static __be32 @@ -4448,23 +4453,25 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; - __be32 *p; if (!nfserr) { - p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8); - p = xdr_encode_opaque_fixed(p, &scd->se_confirm, - NFS4_VERIFIER_SIZE); - } - else if (nfserr == nfserr_clid_inuse) { - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); + nfserr = nfsd4_encode_clientid4(xdr, &scd->se_clientid); + if (nfserr != nfs_ok) + goto out; + nfserr = nfsd4_encode_verifier4(xdr, &scd->se_confirm); + } else if (nfserr == nfserr_clid_inuse) { + /* empty network id */ + if (xdr_stream_encode_u32(xdr, 0) < 0) { + nfserr = nfserr_resource; + goto out; + } + /* empty universal address */ + if (xdr_stream_encode_u32(xdr, 0) < 0) { + nfserr = nfserr_resource; + goto out; + } } +out: return nfserr; } @@ -4473,17 +4480,12 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_write *write = &u->write; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 16); - if (!p) + if (xdr_stream_encode_u32(resp->xdr, write->wr_bytes_written) < 0) return nfserr_resource; - *p++ = cpu_to_be32(write->wr_bytes_written); - *p++ = cpu_to_be32(write->wr_how_written); - p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, - NFS4_VERIFIER_SIZE); - return 0; + if (xdr_stream_encode_u32(resp->xdr, write->wr_how_written) < 0) + return nfserr_resource; + return nfsd4_encode_verifier4(resp->xdr, &write->wr_verifier); } static __be32 @@ -4505,20 +4507,15 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, server_scope = nn->nfsd_name; server_scope_sz = strlen(nn->nfsd_name); - p = xdr_reserve_space(xdr, - 8 /* eir_clientid */ + - 4 /* eir_sequenceid */ + - 4 /* eir_flags */ + - 4 /* spr_how */); - if (!p) + if (nfsd4_encode_clientid4(xdr, &exid->clientid) != nfs_ok) + return nfserr_resource; + if (xdr_stream_encode_u32(xdr, exid->seqid) < 0) + return nfserr_resource; + if (xdr_stream_encode_u32(xdr, exid->flags) < 0) return nfserr_resource; - p = xdr_encode_opaque_fixed(p, &exid->clientid, 8); - *p++ = cpu_to_be32(exid->seqid); - *p++ = cpu_to_be32(exid->flags); - - *p++ = cpu_to_be32(exid->spa_how); - + if (xdr_stream_encode_u32(xdr, exid->spa_how) < 0) + return nfserr_resource; switch (exid->spa_how) { case SP4_NONE: break; @@ -5099,15 +5096,8 @@ nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - - encode_cinfo(p, &setxattr->setxa_cinfo); - - return 0; + return nfsd4_encode_change_info4(xdr, &setxattr->setxa_cinfo); } /* @@ -5253,14 +5243,8 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - - p = encode_cinfo(p, &removexattr->rmxa_cinfo); - return 0; + return nfsd4_encode_change_info4(xdr, &removexattr->rmxa_cinfo); } typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u); @@ -5460,6 +5444,12 @@ status: release: if (opdesc && opdesc->op_release) opdesc->op_release(&op->u); + + /* + * Account for pages consumed while encoding this operation. + * The xdr_stream primitives don't manage rq_next_page. + */ + rqstp->rq_next_page = xdr->page_ptr + 1; } /* @@ -5528,9 +5518,6 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) p = resp->statusp; *p++ = resp->cstate.status; - - rqstp->rq_next_page = xdr->page_ptr + 1; - *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); p += XDR_QUADLEN(resp->taglen); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 041faa13b852..a8eda1c85829 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -148,12 +148,23 @@ void nfsd_drc_slab_free(void) kmem_cache_destroy(drc_slab); } -static int nfsd_reply_cache_stats_init(struct nfsd_net *nn) +/** + * nfsd_net_reply_cache_init - per net namespace reply cache set-up + * @nn: nfsd_net being initialized + * + * Returns zero on succes; otherwise a negative errno is returned. + */ +int nfsd_net_reply_cache_init(struct nfsd_net *nn) { return nfsd_percpu_counters_init(nn->counter, NFSD_NET_COUNTERS_NUM); } -static void nfsd_reply_cache_stats_destroy(struct nfsd_net *nn) +/** + * nfsd_net_reply_cache_destroy - per net namespace reply cache tear-down + * @nn: nfsd_net being freed + * + */ +void nfsd_net_reply_cache_destroy(struct nfsd_net *nn) { nfsd_percpu_counters_destroy(nn->counter, NFSD_NET_COUNTERS_NUM); } @@ -169,17 +180,13 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) hashsize = nfsd_hashsize(nn->max_drc_entries); nn->maskbits = ilog2(hashsize); - status = nfsd_reply_cache_stats_init(nn); - if (status) - goto out_nomem; - nn->nfsd_reply_cache_shrinker.scan_objects = nfsd_reply_cache_scan; nn->nfsd_reply_cache_shrinker.count_objects = nfsd_reply_cache_count; nn->nfsd_reply_cache_shrinker.seeks = 1; status = register_shrinker(&nn->nfsd_reply_cache_shrinker, "nfsd-reply:%s", nn->nfsd_name); if (status) - goto out_stats_destroy; + return status; nn->drc_hashtbl = kvzalloc(array_size(hashsize, sizeof(*nn->drc_hashtbl)), GFP_KERNEL); @@ -195,9 +202,6 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) return 0; out_shrinker: unregister_shrinker(&nn->nfsd_reply_cache_shrinker); -out_stats_destroy: - nfsd_reply_cache_stats_destroy(nn); -out_nomem: printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); return -ENOMEM; } @@ -217,7 +221,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) rp, nn); } } - nfsd_reply_cache_stats_destroy(nn); kvfree(nn->drc_hashtbl); nn->drc_hashtbl = NULL; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b4fd7a7062d5..1b8b1aab9a15 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -25,6 +25,7 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "trace.h" /* * We have a single directory with several nodes in it. @@ -109,12 +110,12 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu if (IS_ERR(data)) return PTR_ERR(data); - rv = write_op[ino](file, data, size); - if (rv >= 0) { - simple_transaction_set(file, rv); - rv = size; - } - return rv; + rv = write_op[ino](file, data, size); + if (rv < 0) + return rv; + + simple_transaction_set(file, rv); + return size; } static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) @@ -230,6 +231,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) if (rpc_pton(net, fo_path, size, sap, salen) == 0) return -EINVAL; + trace_nfsd_ctl_unlock_ip(net, buf); return nlmsvc_unlock_all_by_ip(sap); } @@ -263,7 +265,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) fo_path = buf; if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; - + trace_nfsd_ctl_unlock_fs(netns(file), fo_path); error = kern_path(fo_path, 0, &path); if (error) return error; @@ -324,7 +326,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) len = qword_get(&mesg, dname, size); if (len <= 0) return -EINVAL; - + path = dname+len+1; len = qword_get(&mesg, path, size); if (len <= 0) @@ -338,15 +340,17 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) return -EINVAL; maxsize = min(maxsize, NFS3_FHSIZE); - if (qword_get(&mesg, mesg, size)>0) + if (qword_get(&mesg, mesg, size) > 0) return -EINVAL; + trace_nfsd_ctl_filehandle(netns(file), dname, path, maxsize); + /* we have all the words, they are in buf.. */ dom = unix_domain_find(dname); if (!dom) return -ENOMEM; - len = exp_rootfh(netns(file), dom, path, &fh, maxsize); + len = exp_rootfh(netns(file), dom, path, &fh, maxsize); auth_domain_put(dom); if (len) return len; @@ -399,6 +403,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return rv; if (newthreads < 0) return -EINVAL; + trace_nfsd_ctl_threads(net, newthreads); rv = nfsd_svc(newthreads, net, file->f_cred); if (rv < 0) return rv; @@ -418,8 +423,8 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) * OR * * Input: - * buf: C string containing whitespace- - * separated unsigned integer values + * buf: C string containing whitespace- + * separated unsigned integer values * representing the number of NFSD * threads to start in each pool * size: non-zero length of C string in @buf @@ -471,6 +476,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) rv = -EINVAL; if (nthreads[i] < 0) goto out_free; + trace_nfsd_ctl_pool_threads(net, i, nthreads[i]); } rv = nfsd_set_nrthreads(i, nthreads, net); if (rv) @@ -526,7 +532,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) char *sep; struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id); - if (size>0) { + if (size > 0) { if (nn->nfsd_serv) /* Cannot change versions without updating * nn->nfsd_serv->sv_xdrsize, and reallocing @@ -536,6 +542,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) if (buf[size-1] != '\n') return -EINVAL; buf[size-1] = 0; + trace_nfsd_ctl_version(netns(file), buf); vers = mesg; len = qword_get(&mesg, vers, size); @@ -637,11 +644,11 @@ out: * OR * * Input: - * buf: C string containing whitespace- - * separated positive or negative - * integer values representing NFS - * protocol versions to enable ("+n") - * or disable ("-n") + * buf: C string containing whitespace- + * separated positive or negative + * integer values representing NFS + * protocol versions to enable ("+n") + * or disable ("-n") * size: non-zero length of C string in @buf * Output: * On success: status of zero or more protocol versions has @@ -689,6 +696,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred err = get_int(&mesg, &fd); if (err != 0 || fd < 0) return -EINVAL; + trace_nfsd_ctl_ports_addfd(net, fd); err = nfsd_create_serv(net); if (err != 0) @@ -705,7 +713,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred } /* - * A transport listener is added by writing it's transport name and + * A transport listener is added by writing its transport name and * a port number. */ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred) @@ -720,6 +728,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (port < 1 || port > USHRT_MAX) return -EINVAL; + trace_nfsd_ctl_ports_addxprt(net, transport, port); err = nfsd_create_serv(net); if (err != 0) @@ -832,9 +841,9 @@ int nfsd_max_blksize; * OR * * Input: - * buf: C string containing an unsigned - * integer value representing the new - * NFS blksize + * buf: C string containing an unsigned + * integer value representing the new + * NFS blksize * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C string @@ -853,6 +862,8 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) int rv = get_int(&mesg, &bsize); if (rv) return rv; + trace_nfsd_ctl_maxblksize(netns(file), bsize); + /* force bsize into allowed range and * required alignment. */ @@ -881,9 +892,9 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) * OR * * Input: - * buf: C string containing an unsigned - * integer value representing the new - * number of max connections + * buf: C string containing an unsigned + * integer value representing the new + * number of max connections * size: non-zero length of C string in @buf * Output: * On success: passed-in buffer filled with '\n'-terminated C string @@ -903,6 +914,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size) if (rv) return rv; + trace_nfsd_ctl_maxconn(netns(file), maxconn); nn->max_connections = maxconn; } @@ -913,6 +925,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size) static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time64_t *time, struct nfsd_net *nn) { + struct dentry *dentry = file_dentry(file); char *mesg = buf; int rv, i; @@ -922,6 +935,9 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, rv = get_int(&mesg, &i); if (rv) return rv; + trace_nfsd_ctl_time(netns(file), dentry->d_name.name, + dentry->d_name.len, i); + /* * Some sanity checking. We don't have a reason for * these particular numbers, but problems with the @@ -1014,6 +1030,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, len = qword_get(&mesg, recdir, size); if (len <= 0) return -EINVAL; + trace_nfsd_ctl_recoverydir(netns(file), recdir); status = nfs4_reset_recoverydir(recdir); if (status) @@ -1065,7 +1082,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) * OR * * Input: - * buf: any value + * buf: any value * size: non-zero length of C string in @buf * Output: * passed-in buffer filled with "Y" or "N" with a newline @@ -1087,7 +1104,7 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case '1': if (!nn->nfsd_serv) return -EBUSY; - nfsd4_end_grace(nn); + trace_nfsd_end_grace(netns(file)); break; default: return -EINVAL; @@ -1192,8 +1209,8 @@ static int __nfsd_symlink(struct inode *dir, struct dentry *dentry, * @content is assumed to be a NUL-terminated string that lives * longer than the symlink itself. */ -static void nfsd_symlink(struct dentry *parent, const char *name, - const char *content) +static void _nfsd_symlink(struct dentry *parent, const char *name, + const char *content) { struct inode *dir = parent->d_inode; struct dentry *dentry; @@ -1210,8 +1227,8 @@ out: inode_unlock(dir); } #else -static inline void nfsd_symlink(struct dentry *parent, const char *name, - const char *content) +static inline void _nfsd_symlink(struct dentry *parent, const char *name, + const char *content) { } @@ -1389,8 +1406,8 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) ret = simple_fill_super(sb, 0x6e667364, nfsd_files); if (ret) return ret; - nfsd_symlink(sb->s_root, "supported_krb5_enctypes", - "/proc/net/rpc/gss_krb5_enctypes"); + _nfsd_symlink(sb->s_root, "supported_krb5_enctypes", + "/proc/net/rpc/gss_krb5_enctypes"); dentry = nfsd_mkdir(sb->s_root, NULL, "clients"); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -1477,7 +1494,17 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; -static __net_init int nfsd_init_net(struct net *net) +/** + * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace + * @net: a freshly-created network namespace + * + * This information stays around as long as the network namespace is + * alive whether or not there is an NFSD instance running in the + * namespace. + * + * Returns zero on success, or a negative errno otherwise. + */ +static __net_init int nfsd_net_init(struct net *net) { int retval; struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -1488,6 +1515,9 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; + retval = nfsd_net_reply_cache_init(nn); + if (retval) + goto out_repcache_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; nfsd4_init_leases_net(nn); @@ -1496,22 +1526,32 @@ static __net_init int nfsd_init_net(struct net *net) return 0; +out_repcache_error: + nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); out_export_error: return retval; } -static __net_exit void nfsd_exit_net(struct net *net) +/** + * nfsd_net_exit - Release the nfsd_net portion of a net namespace + * @net: a network namespace that is about to be destroyed + * + */ +static __net_exit void nfsd_net_exit(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfsd_net_reply_cache_destroy(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); - nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); + nfsd_netns_free_versions(nn); } static struct pernet_operations nfsd_net_ops = { - .init = nfsd_init_net, - .exit = nfsd_exit_net, + .init = nfsd_net_init, + .exit = nfsd_net_exit, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), }; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index ccd8485fee04..e8e13ae72e3c 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -623,16 +623,9 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) inode = d_inode(fhp->fh_dentry); err = fh_getattr(fhp, &stat); - if (err) { - /* Grab the times from inode anyway */ - stat.mtime = inode->i_mtime; - stat.ctime = inode->i_ctime; - stat.size = inode->i_size; - if (v4 && IS_I_VERSION(inode)) { - stat.change_cookie = inode_query_iversion(inode); - stat.result_mask |= STATX_CHANGE_COOKIE; - } - } + if (err) + return; + if (v4) fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); @@ -660,15 +653,10 @@ void fh_fill_post_attrs(struct svc_fh *fhp) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); - if (err) { - fhp->fh_post_saved = false; - fhp->fh_post_attr.ctime = inode->i_ctime; - if (v4 && IS_I_VERSION(inode)) { - fhp->fh_post_attr.change_cookie = inode_query_iversion(inode); - fhp->fh_post_attr.result_mask |= STATX_CHANGE_COOKIE; - } - } else - fhp->fh_post_saved = true; + if (err) + return; + + fhp->fh_post_saved = true; if (v4) fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr, inode); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index c37195572fd0..a7315928a760 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -176,9 +176,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) { struct nfsd_readargs *argp = rqstp->rq_argp; struct nfsd_readres *resp = rqstp->rq_resp; - unsigned int len; u32 eof; - int v; dprintk("nfsd: READ %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -187,17 +185,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) argp->count = min_t(u32, argp->count, NFSSVC_MAXBLKSIZE_V2); argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen); - v = 0; - len = argp->count; resp->pages = rqstp->rq_next_page; - while (len > 0) { - struct page *page = *(rqstp->rq_next_page++); - - rqstp->rq_vec[v].iov_base = page_address(page); - rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE); - len -= rqstp->rq_vec[v].iov_len; - v++; - } /* Obtain buffer pointer for payload. 19 is 1 word for * status, 17 words for fattr, and 1 word for the byte count. @@ -207,7 +195,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) resp->count = argp->count; fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, - rqstp->rq_vec, v, &resp->count, &eof); + &resp->count, &eof); if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 9c7b1ef5be40..2154fa63c5f2 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -402,6 +402,11 @@ void nfsd_reset_write_verifier(struct nfsd_net *nn) write_sequnlock(&nn->writeverf_lock); } +/* + * Crank up a set of per-namespace resources for a new NFSD instance, + * including lockd, a duplicate reply cache, an open file cache + * instance, and a cache of NFSv4 state objects. + */ static int nfsd_startup_net(struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index caf6355b18fa..5777f40c7353 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -468,7 +468,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) case nfs_ok: if (xdr_stream_encode_u32(xdr, resp->len) < 0) return false; - xdr_write_pages(xdr, &resp->page, 0, resp->len); + svcxdr_encode_opaque_pages(rqstp, xdr, &resp->page, 0, + resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) return false; break; @@ -491,8 +492,9 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) return false; - xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, - resp->count); + svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages, + rqstp->rq_res.page_base, + resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) return false; break; @@ -511,7 +513,8 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return false; switch (resp->status) { case nfs_ok: - xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); + svcxdr_encode_opaque_pages(rqstp, xdr, dirlist->pages, 0, + dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) return false; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 72a906a053dc..2af74983f146 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1581,6 +1581,265 @@ TRACE_EVENT(nfsd_cb_recall_any_done, ) ); +TRACE_EVENT(nfsd_ctl_unlock_ip, + TP_PROTO( + const struct net *net, + const char *address + ), + TP_ARGS(net, address), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(address, address) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(address, address); + ), + TP_printk("address=%s", + __get_str(address) + ) +); + +TRACE_EVENT(nfsd_ctl_unlock_fs, + TP_PROTO( + const struct net *net, + const char *path + ), + TP_ARGS(net, path), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(path, path) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(path, path); + ), + TP_printk("path=%s", + __get_str(path) + ) +); + +TRACE_EVENT(nfsd_ctl_filehandle, + TP_PROTO( + const struct net *net, + const char *domain, + const char *path, + int maxsize + ), + TP_ARGS(net, domain, path, maxsize), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, maxsize) + __string(domain, domain) + __string(path, path) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->maxsize = maxsize; + __assign_str(domain, domain); + __assign_str(path, path); + ), + TP_printk("domain=%s path=%s maxsize=%d", + __get_str(domain), __get_str(path), __entry->maxsize + ) +); + +TRACE_EVENT(nfsd_ctl_threads, + TP_PROTO( + const struct net *net, + int newthreads + ), + TP_ARGS(net, newthreads), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, newthreads) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->newthreads = newthreads; + ), + TP_printk("newthreads=%d", + __entry->newthreads + ) +); + +TRACE_EVENT(nfsd_ctl_pool_threads, + TP_PROTO( + const struct net *net, + int pool, + int nrthreads + ), + TP_ARGS(net, pool, nrthreads), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, pool) + __field(int, nrthreads) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->pool = pool; + __entry->nrthreads = nrthreads; + ), + TP_printk("pool=%d nrthreads=%d", + __entry->pool, __entry->nrthreads + ) +); + +TRACE_EVENT(nfsd_ctl_version, + TP_PROTO( + const struct net *net, + const char *mesg + ), + TP_ARGS(net, mesg), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(mesg, mesg) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(mesg, mesg); + ), + TP_printk("%s", + __get_str(mesg) + ) +); + +TRACE_EVENT(nfsd_ctl_ports_addfd, + TP_PROTO( + const struct net *net, + int fd + ), + TP_ARGS(net, fd), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, fd) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->fd = fd; + ), + TP_printk("fd=%d", + __entry->fd + ) +); + +TRACE_EVENT(nfsd_ctl_ports_addxprt, + TP_PROTO( + const struct net *net, + const char *transport, + int port + ), + TP_ARGS(net, transport, port), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, port) + __string(transport, transport) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->port = port; + __assign_str(transport, transport); + ), + TP_printk("transport=%s port=%d", + __get_str(transport), __entry->port + ) +); + +TRACE_EVENT(nfsd_ctl_maxblksize, + TP_PROTO( + const struct net *net, + int bsize + ), + TP_ARGS(net, bsize), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, bsize) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->bsize = bsize; + ), + TP_printk("bsize=%d", + __entry->bsize + ) +); + +TRACE_EVENT(nfsd_ctl_maxconn, + TP_PROTO( + const struct net *net, + int maxconn + ), + TP_ARGS(net, maxconn), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, maxconn) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->maxconn = maxconn; + ), + TP_printk("maxconn=%d", + __entry->maxconn + ) +); + +TRACE_EVENT(nfsd_ctl_time, + TP_PROTO( + const struct net *net, + const char *name, + size_t namelen, + int time + ), + TP_ARGS(net, name, namelen, time), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(int, time) + __string_len(name, name, namelen) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __entry->time = time; + __assign_str_len(name, name, namelen); + ), + TP_printk("file=%s time=%d\n", + __get_str(name), __entry->time + ) +); + +TRACE_EVENT(nfsd_ctl_recoverydir, + TP_PROTO( + const struct net *net, + const char *recdir + ), + TP_ARGS(net, recdir), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __string(recdir, recdir) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + __assign_str(recdir, recdir); + ), + TP_printk("recdir=%s", + __get_str(recdir) + ) +); + +TRACE_EVENT(nfsd_end_grace, + TP_PROTO( + const struct net *net + ), + TP_ARGS(net), + TP_STRUCT__entry( + __field(unsigned int, netns_ino) + ), + TP_fast_assign( + __entry->netns_ino = net->ns.inum; + ), + TP_printk("nn=%d", __entry->netns_ino + ) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index db67f8e19344..59b7d60ae33e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -388,7 +388,9 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) iap->ia_mode &= ~S_ISGID; } else { /* set ATTR_KILL_* bits and let VFS handle it */ - iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID); + iap->ia_valid |= ATTR_KILL_SUID; + iap->ia_valid |= + setattr_should_drop_sgid(&nop_mnt_idmap, inode); } } } @@ -1001,6 +1003,18 @@ static __be32 nfsd_finish_read(struct svc_rqst *rqstp, struct svc_fh *fhp, } } +/** + * nfsd_splice_read - Perform a VFS read using a splice pipe + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @file: opened struct file of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @eof: OUT: set non-zero if operation reached the end of the file + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. + */ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, unsigned long *count, u32 *eof) @@ -1014,22 +1028,50 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ssize_t host_err; trace_nfsd_read_splice(rqstp, fhp, offset, *count); - rqstp->rq_next_page = rqstp->rq_respages + 1; host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err); } -__be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct file *file, loff_t offset, - struct kvec *vec, int vlen, unsigned long *count, - u32 *eof) +/** + * nfsd_iter_read - Perform a VFS read using an iterator + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @file: opened struct file of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @base: offset in first page of read buffer + * @eof: OUT: set non-zero if operation reached the end of the file + * + * Some filesystems or situations cannot use nfsd_splice_read. This + * function is the slightly less-performant fallback for those cases. + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. + */ +__be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct file *file, loff_t offset, unsigned long *count, + unsigned int base, u32 *eof) { + unsigned long v, total; struct iov_iter iter; loff_t ppos = offset; + struct page *page; ssize_t host_err; + v = 0; + total = *count; + while (total) { + page = *(rqstp->rq_next_page++); + rqstp->rq_vec[v].iov_base = page_address(page) + base; + rqstp->rq_vec[v].iov_len = min_t(size_t, total, PAGE_SIZE - base); + total -= rqstp->rq_vec[v].iov_len; + ++v; + base = 0; + } + WARN_ON_ONCE(v > ARRAY_SIZE(rqstp->rq_vec)); + trace_nfsd_read_vector(rqstp, fhp, offset, *count); - iov_iter_kvec(&iter, ITER_DEST, vec, vlen, *count); + iov_iter_kvec(&iter, ITER_DEST, rqstp->rq_vec, v, *count); host_err = vfs_iter_read(file, &iter, &ppos, 0); return nfsd_finish_read(rqstp, fhp, file, offset, count, eof, host_err); } @@ -1159,14 +1201,24 @@ out_nfserr: return nfserr; } -/* - * Read data from a file. count must contain the requested read count - * on entry. On return, *count contains the number of bytes actually read. +/** + * nfsd_read - Read data from a file + * @rqstp: RPC transaction context + * @fhp: file handle of file to be read + * @offset: starting byte offset + * @count: IN: requested number of bytes; OUT: number of bytes read + * @eof: OUT: set non-zero if operation reached the end of the file + * + * The caller must verify that there is enough space in @rqstp.rq_res + * to perform this operation. + * * N.B. After this call fhp needs an fh_put + * + * Returns nfs_ok on success, otherwise an nfserr stat value is + * returned. */ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count, - u32 *eof) + loff_t offset, unsigned long *count, u32 *eof) { struct nfsd_file *nf; struct file *file; @@ -1181,12 +1233,10 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) err = nfsd_splice_read(rqstp, fhp, file, offset, count, eof); else - err = nfsd_readv(rqstp, fhp, file, offset, vec, vlen, count, eof); + err = nfsd_iter_read(rqstp, fhp, file, offset, count, 0, eof); nfsd_file_put(nf); - trace_nfsd_read_done(rqstp, fhp, offset, *count); - return err; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 43fb57a301d3..a6890ea7b765 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -110,13 +110,12 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, unsigned long *count, u32 *eof); -__be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, +__be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, - struct kvec *vec, int vlen, - unsigned long *count, + unsigned long *count, unsigned int base, u32 *eof); -__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, - loff_t, struct kvec *, int, unsigned long *, +__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, + loff_t offset, unsigned long *count, u32 *eof); __be32 nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t, struct kvec *, int, unsigned long *, diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e956f886a1a1..5710833ac1cc 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -285,6 +285,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, if (nbh == NULL) { /* blocksize == pagesize */ xa_erase_irq(&btnc->i_pages, newkey); unlock_page(ctxt->bh->b_page); - } else - brelse(nbh); + } else { + /* + * When canceling a buffer that a prepare operation has + * allocated to copy a node block to another location, use + * nilfs_btnode_delete() to initialize and release the buffer + * so that the buffer flags will not be in an inconsistent + * state when it is reallocated. + */ + nilfs_btnode_delete(nbh); + } } diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a265d391ffe9..a9eb3487efb2 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -140,7 +140,7 @@ const struct file_operations nilfs_file_operations = { .open = generic_file_open, /* .release = nilfs_release_file, */ .fsync = nilfs_sync_file, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, }; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 5cf30827f244..b4e54d079b7d 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -370,7 +370,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) struct folio *folio = fbatch.folios[i]; folio_lock(folio); - nilfs_clear_dirty_page(&folio->page, silent); + + /* + * This folio may have been removed from the address + * space by truncation or invalidation when the lock + * was acquired. Skip processing in that case. + */ + if (likely(folio->mapping == mapping)) + nilfs_clear_dirty_page(&folio->page, silent); + folio_unlock(folio); } folio_batch_release(&fbatch); diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1362ccb64ec7..6e59dc19a732 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index ac949fd7603f..c2553024bd25 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -981,10 +981,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -998,6 +1001,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1780,6 +1785,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1791,6 +1797,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index dc359b56fdfa..2c6078a6b8ec 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -779,6 +779,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) goto out_header; sui->ncleansegs -= nsegs - newnsegs; + + /* + * If the sufile is successfully truncated, immediately adjust + * the segment allocation space while locking the semaphore + * "mi_sem" so that nilfs_sufile_alloc() never allocates + * segments in the truncated space. + */ + sui->allocmax = newnsegs - 1; + sui->allocmin = 0; } kaddr = kmap_atomic(header_bh->b_page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 77f1e5778d1c..0ef8c71bde8e 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + lock_buffer(nsbh); if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); + + if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; @@ -1278,14 +1299,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags, { struct nilfs_super_data sd; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; struct dentry *root_dentry; int err, s_new = false; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - - sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type); + sd.bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type, + NULL); if (IS_ERR(sd.bdev)) return ERR_CAST(sd.bdev); @@ -1319,7 +1337,6 @@ nilfs_mount(struct file_system_type *fs_type, int flags, s_new = true; /* New superblock instance created */ - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev); sb_set_blocksize(s, block_size(sd.bdev)); @@ -1357,7 +1374,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } if (!s_new) - blkdev_put(sd.bdev, mode); + blkdev_put(sd.bdev, fs_type); return root_dentry; @@ -1366,7 +1383,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, failed: if (!s_new) - blkdev_put(sd.bdev, mode); + blkdev_put(sd.bdev, fs_type); return ERR_PTR(err); } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 2894152a6b25..0f0667957c81 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -405,6 +405,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) 100)); } +/** + * nilfs_max_segment_count - calculate the maximum number of segments + * @nilfs: nilfs object + */ +static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) +{ + u64 max_count = U64_MAX; + + do_div(max_count, nilfs->ns_blocks_per_segment); + return min_t(u64, max_count, ULONG_MAX); +} + void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; @@ -414,6 +426,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { + u64 nsegments, nblocks; + if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_err(nilfs->ns_sb, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", @@ -457,7 +471,34 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; } - nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); + nsegments = le64_to_cpu(sbp->s_nsegments); + if (nsegments > nilfs_max_segment_count(nilfs)) { + nilfs_err(nilfs->ns_sb, + "segment count %llu exceeds upper limit (%llu segments)", + (unsigned long long)nsegments, + (unsigned long long)nilfs_max_segment_count(nilfs)); + return -EINVAL; + } + + nblocks = sb_bdev_nr_blocks(nilfs->ns_sb); + if (nblocks) { + u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; + /* + * To avoid failing to mount early device images without a + * second superblock, exclude that block count from the + * "min_block_count" calculation. + */ + + if (nblocks < min_block_count) { + nilfs_err(nilfs->ns_sb, + "total number of segment blocks %llu exceeds device size (%llu blocks)", + (unsigned long long)min_block_count, + (unsigned long long)nblocks); + return -EINVAL; + } + } + + nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } diff --git a/fs/no-block.c b/fs/no-block.c deleted file mode 100644 index 481c0f0ab4bd..000000000000 --- a/fs/no-block.c +++ /dev/null @@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* no-block.c: implementation of routines required for non-BLOCK configuration - * - * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/kernel.h> -#include <linux/fs.h> - -static int no_blkdev_open(struct inode * inode, struct file * filp) -{ - return -ENODEV; -} - -const struct file_operations def_blk_fops = { - .open = no_blkdev_open, - .llseek = noop_llseek, -}; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a3865bc4a0c6..f79408f9127a 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -2491,7 +2491,7 @@ conv_err_out: * byte offset @ofs inside the attribute with the constant byte @val. * * This function is effectively like memset() applied to an ntfs attribute. - * Note thie function actually only operates on the page cache pages belonging + * Note this function actually only operates on the page cache pages belonging * to the ntfs attribute and it marks them dirty after doing the memset(). * Thus it relies on the vm dirty page write code paths to cause the modified * pages to be written to the mft record/disk. diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index f9cb180b6f6b..761aaa0195d6 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -161,7 +161,7 @@ static int ntfs_decompress(struct page *dest_pages[], int completed_pages[], */ u8 *cb_end = cb_start + cb_size; /* End of cb. */ u8 *cb = cb_start; /* Current position in cb. */ - u8 *cb_sb_start = cb; /* Beginning of the current sb in the cb. */ + u8 *cb_sb_start; /* Beginning of the current sb in the cb. */ u8 *cb_sb_end; /* End of current sb / beginning of next sb. */ /* Variables for uncompressed data / destination. */ diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index c481b14e4fd9..e5e0ed58670b 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1992,7 +1992,7 @@ const struct file_operations ntfs_file_ops = { #endif /* NTFS_RW */ .mmap = generic_file_mmap, .open = ntfs_file_open, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; const struct inode_operations ntfs_file_inode_ops = { diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 48030899dc6e..0155f106ec34 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -1955,36 +1955,38 @@ undo_alloc: "attribute.%s", es); NVolSetErrors(vol); } - a = ctx->attr; + if (ntfs_rl_truncate_nolock(vol, &mft_ni->runlist, old_last_vcn)) { ntfs_error(vol->sb, "Failed to truncate mft data attribute " "runlist.%s", es); NVolSetErrors(vol); } - if (mp_rebuilt && !IS_ERR(ctx->mrec)) { - if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu( + if (ctx) { + a = ctx->attr; + if (mp_rebuilt && !IS_ERR(ctx->mrec)) { + if (ntfs_mapping_pairs_build(vol, (u8 *)a + le16_to_cpu( a->data.non_resident.mapping_pairs_offset), old_alen - le16_to_cpu( - a->data.non_resident.mapping_pairs_offset), + a->data.non_resident.mapping_pairs_offset), rl2, ll, -1, NULL)) { - ntfs_error(vol->sb, "Failed to restore mapping pairs " + ntfs_error(vol->sb, "Failed to restore mapping pairs " "array.%s", es); - NVolSetErrors(vol); - } - if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) { - ntfs_error(vol->sb, "Failed to restore attribute " + NVolSetErrors(vol); + } + if (ntfs_attr_record_resize(ctx->mrec, a, old_alen)) { + ntfs_error(vol->sb, "Failed to restore attribute " "record.%s", es); + NVolSetErrors(vol); + } + flush_dcache_mft_record_page(ctx->ntfs_ino); + mark_mft_record_dirty(ctx->ntfs_ino); + } else if (IS_ERR(ctx->mrec)) { + ntfs_error(vol->sb, "Failed to restore attribute search " + "context.%s", es); NVolSetErrors(vol); } - flush_dcache_mft_record_page(ctx->ntfs_ino); - mark_mft_record_dirty(ctx->ntfs_ino); - } else if (IS_ERR(ctx->mrec)) { - ntfs_error(vol->sb, "Failed to restore attribute search " - "context.%s", es); - NVolSetErrors(vol); - } - if (ctx) ntfs_attr_put_search_ctx(ctx); + } if (!IS_ERR(mrec)) unmap_mft_record(mft_ni); up_write(&mft_ni->runlist.lock); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 2643a08182e1..56a7d5bd33e4 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -1620,7 +1620,7 @@ read_partial_attrdef_page: memcpy((u8*)vol->attrdef + (index++ << PAGE_SHIFT), page_address(page), size); ntfs_unmap_page(page); - }; + } if (size == PAGE_SIZE) { size = i_size & ~PAGE_MASK; if (size) @@ -1689,7 +1689,7 @@ read_partial_upcase_page: memcpy((char*)vol->upcase + (index++ << PAGE_SHIFT), page_address(page), size); ntfs_unmap_page(page); - }; + } if (size == PAGE_SIZE) { size = i_size & ~PAGE_MASK; if (size) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 9a3d55c367d9..036efd85f60c 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -744,6 +744,35 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) return generic_file_read_iter(iocb, iter); } +static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = in->f_mapping->host; + struct ntfs_inode *ni = ntfs_i(inode); + + if (is_encrypted(ni)) { + ntfs_inode_warn(inode, "encrypted i/o not supported"); + return -EOPNOTSUPP; + } + +#ifndef CONFIG_NTFS3_LZX_XPRESS + if (ni->ni_flags & NI_FLAG_COMPRESSED_MASK) { + ntfs_inode_warn( + inode, + "activate CONFIG_NTFS3_LZX_XPRESS to read external compressed files"); + return -EOPNOTSUPP; + } +#endif + + if (is_dedup(ni)) { + ntfs_inode_warn(inode, "read deduplicated not supported"); + return -EOPNOTSUPP; + } + + return filemap_splice_read(in, ppos, pipe, len, flags); +} + /* * ntfs_get_frame_pages * @@ -1159,7 +1188,7 @@ const struct file_operations ntfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = ntfs_compat_ioctl, #endif - .splice_read = generic_file_splice_read, + .splice_read = ntfs_file_splice_read, .mmap = ntfs_file_mmap, .open = ntfs_file_open, .fsync = generic_file_fsync, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 60b97c92e2b2..21472e3ed182 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1503,7 +1503,7 @@ static void o2hb_region_release(struct config_item *item) } if (reg->hr_bdev) - blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE); + blkdev_put(reg->hr_bdev, NULL); kfree(reg->hr_slots); @@ -1786,7 +1786,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, goto out2; reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev, - FMODE_WRITE | FMODE_READ, NULL); + BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, + NULL); if (IS_ERR(reg->hr_bdev)) { ret = PTR_ERR(reg->hr_bdev); reg->hr_bdev = NULL; @@ -1893,7 +1894,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, out3: if (ret < 0) { - blkdev_put(reg->hr_bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(reg->hr_bdev, NULL); reg->hr_bdev = NULL; } out2: diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index efb09de4343d..91a194596552 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2100,14 +2100,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; + int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_KEEP_SIZE) + if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; + } else { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + return ret; + } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; @@ -2552,7 +2558,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, * * Take and drop the meta data lock to update inode fields * like i_size. This allows the checks down below - * generic_file_read_iter() a chance of actually working. + * copy_splice_read() a chance of actually working. */ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level, !nowait); @@ -2581,6 +2587,43 @@ bail: return ret; } +static ssize_t ocfs2_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + ssize_t ret = 0; + int lock_level = 0; + + trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry, + (unsigned long long)OCFS2_I(inode)->ip_blkno, + in->f_path.dentry->d_name.len, + in->f_path.dentry->d_name.name, + flags); + + /* + * We're fine letting folks race truncates and extending writes with + * read across the cluster, just like they can locally. Hence no + * rw_lock during read. + * + * Take and drop the meta data lock to update inode fields like i_size. + * This allows the checks down below filemap_splice_read() a chance of + * actually working. + */ + ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level, 1); + if (ret < 0) { + if (ret != -EAGAIN) + mlog_errno(ret); + goto bail; + } + ocfs2_inode_unlock(inode, lock_level); + + ret = filemap_splice_read(in, ppos, pipe, len, flags); + trace_filemap_splice_read_ret(ret); +bail: + return ret; +} + /* Refer generic_file_llseek_unlocked() */ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence) { @@ -2744,7 +2787,7 @@ const struct file_operations ocfs2_fops = { #endif .lock = ocfs2_lock, .flock = ocfs2_flock, - .splice_read = generic_file_splice_read, + .splice_read = ocfs2_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, .remap_file_range = ocfs2_remap_file_range, @@ -2790,7 +2833,7 @@ const struct file_operations ocfs2_fops_no_plocks = { .compat_ioctl = ocfs2_compat_ioctl, #endif .flock = ocfs2_flock, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, .remap_file_range = ocfs2_remap_file_range, diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index dc4bce1649c1..b8c3d1702076 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1319,6 +1319,8 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write); DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter); +DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_read); + DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file); DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_truncate_file_error); @@ -1470,6 +1472,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write, ); DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret); +DEFINE_OCFS2_INT_EVENT(filemap_splice_read_ret); /* End of trace events for fs/ocfs2/file.c. */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 0b0e6a132101..988d1c076861 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -952,8 +952,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (!sb_has_quota_loaded(sb, type)) continue; - oinfo = sb_dqinfo(sb, type)->dqi_priv; - cancel_delayed_work_sync(&oinfo->dqi_sync_work); + if (!sb_has_quota_suspended(sb, type)) { + oinfo = sb_dqinfo(sb, type)->dqi_priv; + cancel_delayed_work_sync(&oinfo->dqi_sync_work); + } inode = igrab(sb->s_dquot.files[type]); /* Turn off quotas. This will remove all dquot structures from * memory and so they will be automatically synced to global diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 0101f1f87b56..de8f57ee39ec 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -334,7 +334,7 @@ const struct file_operations omfs_file_operations = { .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; static int omfs_setattr(struct mnt_idmap *idmap, diff --git a/fs/open.c b/fs/open.c index 4478adcc4f3a..fb07b2840eb4 100644 --- a/fs/open.c +++ b/fs/open.c @@ -700,10 +700,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) return do_fchmodat(AT_FDCWD, filename, mode); } -/** - * setattr_vfsuid - check and set ia_fsuid attribute - * @kuid: new inode owner - * +/* * Check whether @kuid is valid and if so generate and set vfsuid_t in * ia_vfsuid. * @@ -718,10 +715,7 @@ static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid) return true; } -/** - * setattr_vfsgid - check and set ia_fsgid attribute - * @kgid: new inode owner - * +/* * Check whether @kgid is valid and if so generate and set vfsgid_t in * ia_vfsgid. * @@ -989,7 +983,6 @@ cleanup_file: * @file: file pointer * @dentry: pointer to dentry * @open: open callback - * @opened: state of open * * This can be used to finish opening a file passed to i_op->atomic_open(). * @@ -1043,7 +1036,6 @@ EXPORT_SYMBOL(file_path); * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized - * @cred: credentials to use */ int vfs_open(const struct path *path, struct file *file) { @@ -1116,23 +1108,77 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, } EXPORT_SYMBOL(dentry_create); -struct file *open_with_fake_path(const struct path *path, int flags, +/** + * kernel_file_open - open a file for kernel internal use + * @path: path of the file to open + * @flags: open flags + * @inode: the inode + * @cred: credentials for open + * + * Open a file for use by in-kernel consumers. The file is not accounted + * against nr_files and must not be installed into the file descriptor + * table. + * + * Return: Opened file on success, an error pointer on failure. + */ +struct file *kernel_file_open(const struct path *path, int flags, struct inode *inode, const struct cred *cred) { - struct file *f = alloc_empty_file_noaccount(flags, cred); - if (!IS_ERR(f)) { - int error; + struct file *f; + int error; - f->f_path = *path; - error = do_dentry_open(f, inode, NULL); - if (error) { - fput(f); - f = ERR_PTR(error); - } + f = alloc_empty_file_noaccount(flags, cred); + if (IS_ERR(f)) + return f; + + f->f_path = *path; + error = do_dentry_open(f, inode, NULL); + if (error) { + fput(f); + f = ERR_PTR(error); } return f; } -EXPORT_SYMBOL(open_with_fake_path); +EXPORT_SYMBOL_GPL(kernel_file_open); + +/** + * backing_file_open - open a backing file for kernel internal use + * @path: path of the file to open + * @flags: open flags + * @path: path of the backing file + * @cred: credentials for open + * + * Open a backing file for a stackable filesystem (e.g., overlayfs). + * @path may be on the stackable filesystem and backing inode on the + * underlying filesystem. In this case, we want to be able to return + * the @real_path of the backing inode. This is done by embedding the + * returned file into a container structure that also stores the path of + * the backing inode on the underlying filesystem, which can be + * retrieved using backing_file_real_path(). + */ +struct file *backing_file_open(const struct path *path, int flags, + const struct path *real_path, + const struct cred *cred) +{ + struct file *f; + int error; + + f = alloc_empty_backing_file(flags, cred); + if (IS_ERR(f)) + return f; + + f->f_path = *path; + path_get(real_path); + *backing_file_real_path(f) = *real_path; + error = do_dentry_open(f, d_inode(real_path->dentry), NULL); + if (error) { + fput(f); + f = ERR_PTR(error); + } + + return f; +} +EXPORT_SYMBOL_GPL(backing_file_open); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) @@ -1156,7 +1202,7 @@ inline struct open_how build_open_how(int flags, umode_t mode) inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; - u64 strip = FMODE_NONOTIFY | O_CLOEXEC; + u64 strip = __FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 1a4301a38aa7..d68372241b30 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -337,6 +337,26 @@ out: return ret; } +static ssize_t orangefs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + ssize_t ret; + + orangefs_stats.reads++; + + down_read(&inode->i_rwsem); + ret = orangefs_revalidate_mapping(inode); + if (ret) + goto out; + + ret = filemap_splice_read(in, ppos, pipe, len, flags); +out: + up_read(&inode->i_rwsem); + return ret; +} + static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter) { @@ -556,7 +576,7 @@ const struct file_operations orangefs_file_operations = { .lock = orangefs_lock, .mmap = orangefs_file_mmap, .open = generic_file_open, - .splice_read = generic_file_splice_read, + .splice_read = orangefs_file_splice_read, .splice_write = iter_file_splice_write, .flush = orangefs_flush, .release = orangefs_file_release, diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 7c04f033aadd..1f93a3ae113e 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -34,8 +34,8 @@ static char ovl_whatisit(struct inode *inode, struct inode *realinode) return 'm'; } -/* No atime modification nor notify on underlying */ -#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY) +/* No atime modification on underlying */ +#define OVL_OPEN_FLAGS (O_NOATIME) static struct file *ovl_open_realfile(const struct file *file, const struct path *realpath) @@ -61,8 +61,8 @@ static struct file *ovl_open_realfile(const struct file *file, if (!inode_owner_or_capable(real_idmap, realinode)) flags &= ~O_NOATIME; - realfile = open_with_fake_path(&file->f_path, flags, realinode, - current_cred()); + realfile = backing_file_open(&file->f_path, flags, realpath, + current_cred()); } revert_creds(old_cred); @@ -419,6 +419,27 @@ out_unlock: return ret; } +static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + const struct cred *old_cred; + struct fd real; + ssize_t ret; + + ret = ovl_real_fdget(in, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(in)->i_sb); + ret = vfs_splice_read(real.file, ppos, pipe, len, flags); + revert_creds(old_cred); + ovl_file_accessed(in); + + fdput(real); + return ret; +} + /* * Calling iter_file_splice_write() directly from overlay's f_op may deadlock * due to lock order inversion between pipe->mutex in iter_file_splice_write() @@ -695,7 +716,7 @@ const struct file_operations ovl_file_operations = { .fallocate = ovl_fallocate, .fadvise = ovl_fadvise, .flush = ovl_flush, - .splice_read = generic_file_splice_read, + .splice_read = ovl_splice_read, .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 4d0b278f5630..23686e8a06c4 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -329,8 +329,9 @@ static inline struct file *ovl_do_tmpfile(struct ovl_fs *ofs, struct dentry *dentry, umode_t mode) { struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = dentry }; - struct file *file = vfs_tmpfile_open(ovl_upper_mnt_idmap(ofs), &path, mode, - O_LARGEFILE | O_WRONLY, current_cred()); + struct file *file = kernel_tmpfile_open(ovl_upper_mnt_idmap(ofs), &path, + mode, O_LARGEFILE | O_WRONLY, + current_cred()); int err = PTR_ERR_OR_ZERO(file); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); diff --git a/fs/pnode.c b/fs/pnode.c index 3cede8b18c8b..e4d0340393d5 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -216,7 +216,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct hlist_head *list; -static inline bool peers(struct mount *m1, struct mount *m2) +static inline bool peers(const struct mount *m1, const struct mount *m2) { return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; } @@ -354,6 +354,46 @@ static inline int do_refcount_check(struct mount *mnt, int count) return mnt_get_count(mnt) > count; } +/** + * propagation_would_overmount - check whether propagation from @from + * would overmount @to + * @from: shared mount + * @to: mount to check + * @mp: future mountpoint of @to on @from + * + * If @from propagates mounts to @to, @from and @to must either be peers + * or one of the masters in the hierarchy of masters of @to must be a + * peer of @from. + * + * If the root of the @to mount is equal to the future mountpoint @mp of + * the @to mount on @from then @to will be overmounted by whatever is + * propagated to it. + * + * Context: This function expects namespace_lock() to be held and that + * @mp is stable. + * Return: If @from overmounts @to, true is returned, false if not. + */ +bool propagation_would_overmount(const struct mount *from, + const struct mount *to, + const struct mountpoint *mp) +{ + if (!IS_MNT_SHARED(from)) + return false; + + if (IS_MNT_NEW(to)) + return false; + + if (to->mnt.mnt_root != mp->m_dentry) + return false; + + for (const struct mount *m = to; m; m = m->mnt_master) { + if (peers(from, m)) + return true; + } + + return false; +} + /* * check if the mount 'mnt' can be unmounted successfully. * @mnt: the mount to be checked for unmount diff --git a/fs/pnode.h b/fs/pnode.h index 988f1aa9b02a..0b02a6393891 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -53,4 +53,7 @@ struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); int count_mounts(struct mnt_namespace *ns, struct mount *mnt); +bool propagation_would_overmount(const struct mount *from, + const struct mount *to, + const struct mountpoint *mp); #endif /* _LINUX_PNODE_H */ diff --git a/fs/proc/inode.c b/fs/proc/inode.c index f495fdb39151..67b09a1d9433 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -591,7 +591,7 @@ static const struct file_operations proc_iter_file_ops = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, .write = proc_reg_write, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, .mmap = proc_reg_mmap, @@ -617,7 +617,7 @@ static const struct file_operations proc_reg_file_ops_compat = { static const struct file_operations proc_iter_file_ops_compat = { .llseek = proc_reg_llseek, .read_iter = proc_reg_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .write = proc_reg_write, .poll = proc_reg_poll, .unlocked_ioctl = proc_reg_unlocked_ioctl, diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 8038833ff5b0..ae832e982003 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -868,7 +868,7 @@ static const struct file_operations proc_sys_file_operations = { .poll = proc_sys_poll, .read_iter = proc_sys_read, .write_iter = proc_sys_write, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .llseek = default_llseek, }; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 846f9455ae22..250eb5bf7b52 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -324,7 +324,7 @@ static int mountstats_open(struct inode *inode, struct file *file) const struct file_operations proc_mounts_operations = { .open = mounts_open, .read_iter = seq_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, @@ -333,7 +333,7 @@ const struct file_operations proc_mounts_operations = { const struct file_operations proc_mountinfo_operations = { .open = mountinfo_open, .read_iter = seq_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, .poll = mounts_poll, @@ -342,7 +342,7 @@ const struct file_operations proc_mountinfo_operations = { const struct file_operations proc_mountstats_operations = { .open = mountstats_open, .read_iter = seq_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .llseek = seq_lseek, .release = mounts_release, }; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 4ae0cfcd15f2..de8cf5d75f34 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -263,9 +263,9 @@ static __init const char *early_boot_devpath(const char *initial_devname) * same scheme to find the device that we use for mounting * the root file system. */ - dev_t dev = name_to_dev_t(initial_devname); + dev_t dev; - if (!dev) { + if (early_lookup_bdev(initial_devname, &dev)) { pr_err("failed to resolve '%s'!\n", initial_devname); return initial_devname; } diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 12af0490322f..c7a1aa3c882b 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -43,7 +43,7 @@ const struct file_operations ramfs_file_operations = { .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, .get_unmapped_area = ramfs_mmu_get_unmapped_area, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 9fbb9b5256f7..efb1b4c1a0a4 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -43,7 +43,7 @@ const struct file_operations ramfs_file_operations = { .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/read_write.c b/fs/read_write.c index a21ba3be7dbe..b07de77ef126 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -29,7 +29,7 @@ const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); diff --git a/fs/readdir.c b/fs/readdir.c index 9c53edb60c03..b264ce60114d 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -131,7 +131,7 @@ struct old_linux_dirent { unsigned long d_ino; unsigned long d_offset; unsigned short d_namlen; - char d_name[1]; + char d_name[]; }; struct readdir_callback { @@ -208,7 +208,7 @@ struct linux_dirent { unsigned long d_ino; unsigned long d_off; unsigned short d_reclen; - char d_name[1]; + char d_name[]; }; struct getdents_callback { @@ -388,7 +388,7 @@ struct compat_old_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_offset; unsigned short d_namlen; - char d_name[1]; + char d_name[]; }; struct compat_readdir_callback { @@ -460,7 +460,7 @@ struct compat_linux_dirent { compat_ulong_t d_ino; compat_ulong_t d_off; unsigned short d_reclen; - char d_name[1]; + char d_name[]; }; struct compat_getdents_callback { diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index b54cc7048f02..8eb3ad3e8ae9 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -247,7 +247,7 @@ const struct file_operations reiserfs_file_operations = { .fsync = reiserfs_sync_file, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 4d11d60f493c..479aa4a57602 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2589,7 +2589,12 @@ static void release_journal_dev(struct super_block *super, struct reiserfs_journal *journal) { if (journal->j_dev_bd != NULL) { - blkdev_put(journal->j_dev_bd, journal->j_dev_mode); + void *holder = NULL; + + if (journal->j_dev_bd->bd_dev != super->s_dev) + holder = journal; + + blkdev_put(journal->j_dev_bd, holder); journal->j_dev_bd = NULL; } } @@ -2598,9 +2603,10 @@ static int journal_init_dev(struct super_block *super, struct reiserfs_journal *journal, const char *jdev_name) { + blk_mode_t blkdev_mode = BLK_OPEN_READ; + void *holder = journal; int result; dev_t jdev; - fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL; result = 0; @@ -2608,16 +2614,15 @@ static int journal_init_dev(struct super_block *super, jdev = SB_ONDISK_JOURNAL_DEVICE(super) ? new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev; - if (bdev_read_only(super->s_bdev)) - blkdev_mode = FMODE_READ; + if (!bdev_read_only(super->s_bdev)) + blkdev_mode |= BLK_OPEN_WRITE; /* there is no "jdev" option and journal is on separate device */ if ((!jdev_name || !jdev_name[0])) { if (jdev == super->s_dev) - blkdev_mode &= ~FMODE_EXCL; - journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, - journal); - journal->j_dev_mode = blkdev_mode; + holder = NULL; + journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, holder, + NULL); if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; @@ -2631,8 +2636,8 @@ static int journal_init_dev(struct super_block *super, return 0; } - journal->j_dev_mode = blkdev_mode; - journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, journal); + journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, holder, + NULL); if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 1bccf6a2e908..55e85256aae8 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -300,7 +300,6 @@ struct reiserfs_journal { struct reiserfs_journal_cnode *j_first; struct block_device *j_dev_bd; - fmode_t j_dev_mode; /* first block on s_dev of reserved area journal */ int j_1st_reserved_block; diff --git a/fs/remap_range.c b/fs/remap_range.c index 1331a890f2f2..87ae4f0dc3aa 100644 --- a/fs/remap_range.c +++ b/fs/remap_range.c @@ -15,6 +15,7 @@ #include <linux/mount.h> #include <linux/fs.h> #include <linux/dax.h> +#include <linux/overflow.h> #include "internal.h" #include <linux/uaccess.h> @@ -101,10 +102,12 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in, static int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write) { + loff_t tmp; + if (unlikely(pos < 0 || len < 0)) return -EINVAL; - if (unlikely((loff_t) (pos + len) < 0)) + if (unlikely(check_add_overflow(pos, len, &tmp))) return -EINVAL; return security_file_permission(file, write ? MAY_WRITE : MAY_READ); diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index 4578dc45e50a..4520ca413867 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -78,7 +78,7 @@ static unsigned romfs_mmap_capabilities(struct file *file) const struct file_operations romfs_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .mmap = romfs_mmap, .get_unmapped_area = romfs_get_unmapped_area, .mmap_capabilities = romfs_mmap_capabilities, diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 5034b862cec2..b279f745466e 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/uaccess.h> +#include <uapi/linux/ethtool.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" @@ -130,12 +131,14 @@ cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan) struct TCP_Server_Info *server = chan->server; seq_printf(m, "\n\n\t\tChannel: %d ConnectionId: 0x%llx" - "\n\t\tNumber of credits: %d Dialect 0x%x" + "\n\t\tNumber of credits: %d,%d,%d Dialect 0x%x" "\n\t\tTCP status: %d Instance: %d" "\n\t\tLocal Users To Server: %d SecMode: 0x%x Req On Wire: %d" "\n\t\tIn Send: %d In MaxReq Wait: %d", i+1, server->conn_id, server->credits, + server->echo_credits, + server->oplock_credits, server->dialect, server->tcpStatus, server->reconnect_instance, @@ -146,18 +149,62 @@ cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan) atomic_read(&server->num_waiters)); } +static inline const char *smb_speed_to_str(size_t bps) +{ + size_t mbps = bps / 1000 / 1000; + + switch (mbps) { + case SPEED_10: + return "10Mbps"; + case SPEED_100: + return "100Mbps"; + case SPEED_1000: + return "1Gbps"; + case SPEED_2500: + return "2.5Gbps"; + case SPEED_5000: + return "5Gbps"; + case SPEED_10000: + return "10Gbps"; + case SPEED_14000: + return "14Gbps"; + case SPEED_20000: + return "20Gbps"; + case SPEED_25000: + return "25Gbps"; + case SPEED_40000: + return "40Gbps"; + case SPEED_50000: + return "50Gbps"; + case SPEED_56000: + return "56Gbps"; + case SPEED_100000: + return "100Gbps"; + case SPEED_200000: + return "200Gbps"; + case SPEED_400000: + return "400Gbps"; + case SPEED_800000: + return "800Gbps"; + default: + return "Unknown"; + } +} + static void cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface) { struct sockaddr_in *ipv4 = (struct sockaddr_in *)&iface->sockaddr; struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)&iface->sockaddr; - seq_printf(m, "\tSpeed: %zu bps\n", iface->speed); + seq_printf(m, "\tSpeed: %s\n", smb_speed_to_str(iface->speed)); seq_puts(m, "\t\tCapabilities: "); if (iface->rdma_capable) seq_puts(m, "rdma "); if (iface->rss_capable) seq_puts(m, "rss "); + if (!iface->rdma_capable && !iface->rss_capable) + seq_puts(m, "None"); seq_putc(m, '\n'); if (iface->sockaddr.ss_family == AF_INET) seq_printf(m, "\t\tIPv4: %pI4\n", &ipv4->sin_addr); @@ -350,8 +397,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) atomic_read(&server->smbd_conn->mr_used_count)); skip_rdma: #endif - seq_printf(m, "\nNumber of credits: %d Dialect 0x%x", - server->credits, server->dialect); + seq_printf(m, "\nNumber of credits: %d,%d,%d Dialect 0x%x", + server->credits, + server->echo_credits, + server->oplock_credits, + server->dialect); if (server->compress_algorithm == SMB3_COMPRESS_LZNT1) seq_printf(m, " COMPRESS_LZNT1"); else if (server->compress_algorithm == SMB3_COMPRESS_LZ77) diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 43a4d8603db3..4f4492eb975f 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1376,7 +1376,7 @@ const struct file_operations cifs_file_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .splice_read = cifs_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, @@ -1396,7 +1396,7 @@ const struct file_operations cifs_file_strict_ops = { .fsync = cifs_strict_fsync, .flush = cifs_flush, .mmap = cifs_file_strict_mmap, - .splice_read = cifs_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, @@ -1416,7 +1416,7 @@ const struct file_operations cifs_file_direct_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .splice_read = direct_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, @@ -1434,7 +1434,7 @@ const struct file_operations cifs_file_nobrl_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .splice_read = cifs_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, @@ -1452,7 +1452,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .fsync = cifs_strict_fsync, .flush = cifs_flush, .mmap = cifs_file_strict_mmap, - .splice_read = cifs_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, @@ -1470,7 +1470,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .splice_read = direct_splice_read, + .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 74cd6fafb33e..d7274eefc666 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -100,9 +100,6 @@ extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to); extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from); extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from); extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from); -extern ssize_t cifs_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags); extern int cifs_flock(struct file *pfile, int cmd, struct file_lock *plock); extern int cifs_lock(struct file *, int, struct file_lock *); extern int cifs_fsync(struct file *, loff_t, loff_t, int); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 0d84bb1a8cd9..b212a4e16b39 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -970,43 +970,6 @@ release_iface(struct kref *ref) kfree(iface); } -/* - * compare two interfaces a and b - * return 0 if everything matches. - * return 1 if a has higher link speed, or rdma capable, or rss capable - * return -1 otherwise. - */ -static inline int -iface_cmp(struct cifs_server_iface *a, struct cifs_server_iface *b) -{ - int cmp_ret = 0; - - WARN_ON(!a || !b); - if (a->speed == b->speed) { - if (a->rdma_capable == b->rdma_capable) { - if (a->rss_capable == b->rss_capable) { - cmp_ret = memcmp(&a->sockaddr, &b->sockaddr, - sizeof(a->sockaddr)); - if (!cmp_ret) - return 0; - else if (cmp_ret > 0) - return 1; - else - return -1; - } else if (a->rss_capable > b->rss_capable) - return 1; - else - return -1; - } else if (a->rdma_capable > b->rdma_capable) - return 1; - else - return -1; - } else if (a->speed > b->speed) - return 1; - else - return -1; -} - struct cifs_chan { unsigned int in_reconnect : 1; /* if session setup in progress for this channel */ struct TCP_Server_Info *server; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index c1c704990b98..d127aded2f28 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -87,6 +87,7 @@ extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx); extern int smb3_parse_opt(const char *options, const char *key, char **val); +extern int cifs_ipaddr_cmp(struct sockaddr *srcaddr, struct sockaddr *rhs); extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs); extern int cifs_discard_remaining_data(struct TCP_Server_Info *server); extern int cifs_call_async(struct TCP_Server_Info *server, diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 8e9a672320ab..9d16626e7a66 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1288,6 +1288,56 @@ next_pdu: module_put_and_kthread_exit(0); } +int +cifs_ipaddr_cmp(struct sockaddr *srcaddr, struct sockaddr *rhs) +{ + struct sockaddr_in *saddr4 = (struct sockaddr_in *)srcaddr; + struct sockaddr_in *vaddr4 = (struct sockaddr_in *)rhs; + struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr; + struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs; + + switch (srcaddr->sa_family) { + case AF_UNSPEC: + switch (rhs->sa_family) { + case AF_UNSPEC: + return 0; + case AF_INET: + case AF_INET6: + return 1; + default: + return -1; + } + case AF_INET: { + switch (rhs->sa_family) { + case AF_UNSPEC: + return -1; + case AF_INET: + return memcmp(saddr4, vaddr4, + sizeof(struct sockaddr_in)); + case AF_INET6: + return 1; + default: + return -1; + } + } + case AF_INET6: { + switch (rhs->sa_family) { + case AF_UNSPEC: + case AF_INET: + return -1; + case AF_INET6: + return memcmp(saddr6, + vaddr6, + sizeof(struct sockaddr_in6)); + default: + return -1; + } + } + default: + return -1; /* don't expect to be here */ + } +} + /* * Returns true if srcaddr isn't specified and rhs isn't specified, or * if srcaddr is specified and matches the IP address of the rhs argument @@ -4086,16 +4136,17 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); + if (tcon->status == TID_GOOD) { + spin_unlock(&tcon->tc_lock); + return 0; + } + if (tcon->status != TID_NEW && tcon->status != TID_NEED_TCON) { spin_unlock(&tcon->tc_lock); return -EHOSTDOWN; } - if (tcon->status == TID_GOOD) { - spin_unlock(&tcon->tc_lock); - return 0; - } tcon->status = TID_IN_TCON; spin_unlock(&tcon->tc_lock); diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 2f93bf8c3325..2390b2fedd6a 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -575,16 +575,17 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru /* only send once per connect */ spin_lock(&tcon->tc_lock); + if (tcon->status == TID_GOOD) { + spin_unlock(&tcon->tc_lock); + return 0; + } + if (tcon->status != TID_NEW && tcon->status != TID_NEED_TCON) { spin_unlock(&tcon->tc_lock); return -EHOSTDOWN; } - if (tcon->status == TID_GOOD) { - spin_unlock(&tcon->tc_lock); - return 0; - } tcon->status = TID_IN_TCON; spin_unlock(&tcon->tc_lock); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index df88b8c04d03..f30f6ddc4b81 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -4942,9 +4942,13 @@ oplock_break_ack: * disconnected since oplock already released by the server */ if (!oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + /* check for server null since can race with kill_sb calling tree disconnect */ + if (tcon->ses && tcon->ses->server) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, volatile_fid, net_fid, cinode); - cifs_dbg(FYI, "Oplock release rc = %d\n", rc); + cifs_dbg(FYI, "Oplock release rc = %d\n", rc); + } else + pr_warn_once("lease break not sent for unmounted share\n"); } cifs_done_oplock_break(cinode); @@ -5079,19 +5083,3 @@ const struct address_space_operations cifs_addr_ops_smallbuf = { .launder_folio = cifs_launder_folio, .migrate_folio = filemap_migrate_folio, }; - -/* - * Splice data from a file into a pipe. - */ -ssize_t cifs_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) -{ - if (unlikely(*ppos >= file_inode(in)->i_sb->s_maxbytes)) - return 0; - if (unlikely(!len)) - return 0; - if (in->f_flags & O_DIRECT) - return direct_splice_read(in, ppos, pipe, len, flags); - return filemap_splice_read(in, ppos, pipe, len, flags); -} diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 6e3be58cfe49..a8bb9d00d33a 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -34,6 +34,8 @@ static int change_conf(struct TCP_Server_Info *server) { server->credits += server->echo_credits + server->oplock_credits; + if (server->credits > server->max_credits) + server->credits = server->max_credits; server->oplock_credits = server->echo_credits = 0; switch (server->credits) { case 0: @@ -91,6 +93,7 @@ smb2_add_credits(struct TCP_Server_Info *server, server->conn_id, server->hostname, *val, add, server->in_flight); } + WARN_ON_ONCE(server->in_flight == 0); server->in_flight--; if (server->in_flight == 0 && ((optype & CIFS_OP_MASK) != CIFS_NEG_OP) && @@ -510,6 +513,43 @@ smb3_negotiate_rsize(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) return rsize; } +/* + * compare two interfaces a and b + * return 0 if everything matches. + * return 1 if a is rdma capable, or rss capable, or has higher link speed + * return -1 otherwise. + */ +static int +iface_cmp(struct cifs_server_iface *a, struct cifs_server_iface *b) +{ + int cmp_ret = 0; + + WARN_ON(!a || !b); + if (a->rdma_capable == b->rdma_capable) { + if (a->rss_capable == b->rss_capable) { + if (a->speed == b->speed) { + cmp_ret = cifs_ipaddr_cmp((struct sockaddr *) &a->sockaddr, + (struct sockaddr *) &b->sockaddr); + if (!cmp_ret) + return 0; + else if (cmp_ret > 0) + return 1; + else + return -1; + } else if (a->speed > b->speed) + return 1; + else + return -1; + } else if (a->rss_capable > b->rss_capable) + return 1; + else + return -1; + } else if (a->rdma_capable > b->rdma_capable) + return 1; + else + return -1; +} + static int parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, size_t buf_len, struct cifs_ses *ses, bool in_mount) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 7063b395d22f..17fe212ab895 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1305,7 +1305,12 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) } /* enough to enable echos and oplocks and one max size write */ - req->hdr.CreditRequest = cpu_to_le16(130); + if (server->credits >= server->max_credits) + req->hdr.CreditRequest = cpu_to_le16(0); + else + req->hdr.CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, 130)); /* only one of SMB2 signing flags may be set in SMB2 request */ if (server->sign) @@ -1899,7 +1904,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, rqst.rq_nvec = 2; /* Need 64 for max size write so ask for more in case not there yet */ - req->hdr.CreditRequest = cpu_to_le16(64); + if (server->credits >= server->max_credits) + req->hdr.CreditRequest = cpu_to_le16(0); + else + req->hdr.CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, 64)); rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); @@ -4227,6 +4237,7 @@ smb2_async_readv(struct cifs_readdata *rdata) struct TCP_Server_Info *server; struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink); unsigned int total_len; + int credit_request; cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n", __func__, rdata->offset, rdata->bytes); @@ -4258,7 +4269,13 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rdata->credits.value > 0) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8); + credit_request = le16_to_cpu(shdr->CreditCharge) + 8; + if (server->credits >= server->max_credits) + shdr->CreditRequest = cpu_to_le16(0); + else + shdr->CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, credit_request)); rc = adjust_credits(server, &rdata->credits, rdata->bytes); if (rc) @@ -4468,6 +4485,7 @@ smb2_async_writev(struct cifs_writedata *wdata, unsigned int total_len; struct cifs_io_parms _io_parms; struct cifs_io_parms *io_parms = NULL; + int credit_request; if (!wdata->server) server = wdata->server = cifs_pick_channel(tcon->ses); @@ -4572,7 +4590,13 @@ smb2_async_writev(struct cifs_writedata *wdata, if (wdata->credits.value > 0) { shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes, SMB2_MAX_BUFFER_SIZE)); - shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8); + credit_request = le16_to_cpu(shdr->CreditCharge) + 8; + if (server->credits >= server->max_credits) + shdr->CreditRequest = cpu_to_le16(0); + else + shdr->CreditRequest = cpu_to_le16( + min_t(int, server->max_credits - + server->credits, credit_request)); rc = adjust_credits(server, &wdata->credits, io_parms->length); if (rc) diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 24bdd5f4d3bc..0474d0bba0a2 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -55,7 +55,7 @@ alloc_mid(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) temp->pid = current->pid; temp->command = cpu_to_le16(smb_buffer->Command); cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command); - /* do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */ + /* easier to use jiffies */ /* when mid allocated can be before when sent */ temp->when_alloc = jiffies; temp->server = server; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index f9b2e0f19b03..ced7a9e916f0 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -185,24 +185,31 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, goto send; } - if (conn->ops->check_user_session) { - rc = conn->ops->check_user_session(work); - if (rc < 0) { - command = conn->ops->get_cmd_val(work); - conn->ops->set_rsp_status(work, - STATUS_USER_SESSION_DELETED); - goto send; - } else if (rc > 0) { - rc = conn->ops->get_ksmbd_tcon(work); + do { + if (conn->ops->check_user_session) { + rc = conn->ops->check_user_session(work); if (rc < 0) { - conn->ops->set_rsp_status(work, - STATUS_NETWORK_NAME_DELETED); + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_USER_SESSION_DELETED); goto send; + } else if (rc > 0) { + rc = conn->ops->get_ksmbd_tcon(work); + if (rc < 0) { + if (rc == -EINVAL) + conn->ops->set_rsp_status(work, + STATUS_INVALID_PARAMETER); + else + conn->ops->set_rsp_status(work, + STATUS_NETWORK_NAME_DELETED); + goto send; + } } } - } - do { rc = __process_request(work, conn, &command); if (rc == SERVER_HANDLER_ABORT) break; diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 0ffe663b7590..33b7e6c4ceff 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -351,9 +351,16 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) int command; __u32 clc_len; /* calculated length */ __u32 len = get_rfc1002_len(work->request_buf); + __u32 req_struct_size, next_cmd = le32_to_cpu(hdr->NextCommand); - if (le32_to_cpu(hdr->NextCommand) > 0) - len = le32_to_cpu(hdr->NextCommand); + if ((u64)work->next_smb2_rcv_hdr_off + next_cmd > len) { + pr_err("next command(%u) offset exceeds smb msg size\n", + next_cmd); + return 1; + } + + if (next_cmd > 0) + len = next_cmd; else if (work->next_smb2_rcv_hdr_off) len -= work->next_smb2_rcv_hdr_off; @@ -373,17 +380,9 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } if (smb2_req_struct_sizes[command] != pdu->StructureSize2) { - if (command != SMB2_OPLOCK_BREAK_HE && - (hdr->Status == 0 || pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2_LE)) { - /* error packets have 9 byte structure size */ - ksmbd_debug(SMB, - "Illegal request size %u for command %d\n", - le16_to_cpu(pdu->StructureSize2), command); - return 1; - } else if (command == SMB2_OPLOCK_BREAK_HE && - hdr->Status == 0 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && - le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { + if (command == SMB2_OPLOCK_BREAK_HE && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_20 && + le16_to_cpu(pdu->StructureSize2) != OP_BREAK_STRUCT_SIZE_21) { /* special case for SMB2.1 lease break message */ ksmbd_debug(SMB, "Illegal request size %d for oplock break\n", @@ -392,6 +391,14 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) } } + req_struct_size = le16_to_cpu(pdu->StructureSize2) + + __SMB2_HEADER_STRUCTURE_SIZE; + if (command == SMB2_LOCK_HE) + req_struct_size -= sizeof(struct smb2_lock_element); + + if (req_struct_size > len + 1) + return 1; + if (smb2_calc_size(hdr, &clc_len)) return 1; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 25c0ba04c59d..da1787c68ba0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -91,7 +91,6 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) unsigned int cmd = le16_to_cpu(req_hdr->Command); int tree_id; - work->tcon = NULL; if (cmd == SMB2_TREE_CONNECT_HE || cmd == SMB2_CANCEL_HE || cmd == SMB2_LOGOFF_HE) { @@ -105,10 +104,28 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work) } tree_id = le32_to_cpu(req_hdr->Id.SyncId.TreeId); + + /* + * If request is not the first in Compound request, + * Just validate tree id in header with work->tcon->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->tcon) { + pr_err("The first operation in the compound does not have tcon\n"); + return -EINVAL; + } + if (work->tcon->id != tree_id) { + pr_err("tree id(%u) is different with id(%u) in first operation\n", + tree_id, work->tcon->id); + return -EINVAL; + } + return 1; + } + work->tcon = ksmbd_tree_conn_lookup(work->sess, tree_id); if (!work->tcon) { pr_err("Invalid tid %d\n", tree_id); - return -EINVAL; + return -ENOENT; } return 1; @@ -547,7 +564,6 @@ int smb2_check_user_session(struct ksmbd_work *work) unsigned int cmd = conn->ops->get_cmd_val(work); unsigned long long sess_id; - work->sess = NULL; /* * SMB2_ECHO, SMB2_NEGOTIATE, SMB2_SESSION_SETUP command do not * require a session id, so no need to validate user session's for @@ -558,15 +574,33 @@ int smb2_check_user_session(struct ksmbd_work *work) return 0; if (!ksmbd_conn_good(conn)) - return -EINVAL; + return -EIO; sess_id = le64_to_cpu(req_hdr->SessionId); + + /* + * If request is not the first in Compound request, + * Just validate session id in header with work->sess->id. + */ + if (work->next_smb2_rcv_hdr_off) { + if (!work->sess) { + pr_err("The first operation in the compound does not have sess\n"); + return -EINVAL; + } + if (work->sess->id != sess_id) { + pr_err("session id(%llu) is different with the first operation(%lld)\n", + sess_id, work->sess->id); + return -EINVAL; + } + return 1; + } + /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); if (work->sess) return 1; ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); - return -EINVAL; + return -ENOENT; } static void destroy_previous_session(struct ksmbd_conn *conn, @@ -2249,7 +2283,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* delete the EA only when it exits */ if (rc > 0) { rc = ksmbd_vfs_remove_xattr(idmap, - path->dentry, + path, attr_name); if (rc < 0) { @@ -2263,8 +2297,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, /* if the EA doesn't exist, just do nothing. */ rc = 0; } else { - rc = ksmbd_vfs_setxattr(idmap, - path->dentry, attr_name, value, + rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, le16_to_cpu(eabuf->EaValueLength), 0); if (rc < 0) { ksmbd_debug(SMB, @@ -2321,8 +2354,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, return -EBADF; } - rc = ksmbd_vfs_setxattr(idmap, path->dentry, - xattr_stream_name, NULL, 0, 0); + rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0); if (rc < 0) pr_err("Failed to store XATTR stream name :%d\n", rc); return 0; @@ -2350,7 +2382,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) && !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, path->dentry, + err = ksmbd_vfs_remove_xattr(idmap, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", @@ -2397,8 +2429,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), - path->dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2972,7 +3003,7 @@ int smb2_open(struct ksmbd_work *work) struct inode *inode = d_inode(path.dentry); posix_acl_rc = ksmbd_vfs_inherit_posix_acl(idmap, - path.dentry, + &path, d_inode(path.dentry->d_parent)); if (posix_acl_rc) ksmbd_debug(SMB, "inherit posix acl failed : %d\n", posix_acl_rc); @@ -2988,7 +3019,7 @@ int smb2_open(struct ksmbd_work *work) if (rc) { if (posix_acl_rc) ksmbd_vfs_set_init_posix_acl(idmap, - path.dentry); + &path); if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { @@ -3028,7 +3059,7 @@ int smb2_open(struct ksmbd_work *work) rc = ksmbd_vfs_set_sd_xattr(conn, idmap, - path.dentry, + &path, pntsd, pntsd_size); kfree(pntsd); @@ -5464,7 +5495,7 @@ static int smb2_rename(struct ksmbd_work *work, goto out; rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp), - fp->filp->f_path.dentry, + &fp->filp->f_path, xattr_stream_name, NULL, 0, 0); if (rc < 0) { @@ -5629,8 +5660,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, - filp->f_path.dentry, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da); if (rc) ksmbd_debug(SMB, "failed to restore file attribute in EA\n"); @@ -7485,7 +7515,7 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, da.attr = le32_to_cpu(fp->f_ci->m_fattr); ret = ksmbd_vfs_set_dos_attrib_xattr(idmap, - fp->filp->f_path.dentry, &da); + &fp->filp->f_path, &da); if (ret) fp->f_ci->m_fattr = old_fattr; } diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 0a5862a61c77..ad919a4239d0 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1162,8 +1162,7 @@ pass: pntsd_size += sizeof(struct smb_acl) + nt_size; } - ksmbd_vfs_set_sd_xattr(conn, idmap, - path->dentry, pntsd, pntsd_size); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size); kfree(pntsd); } @@ -1383,7 +1382,7 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, newattrs.ia_valid |= ATTR_MODE; newattrs.ia_mode = (inode->i_mode & ~0777) | (fattr.cf_mode & 0777); - ksmbd_vfs_remove_acl_xattrs(idmap, path->dentry); + ksmbd_vfs_remove_acl_xattrs(idmap, path); /* Update posix acls */ if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && fattr.cf_dacls) { rc = set_posix_acl(idmap, path->dentry, @@ -1414,9 +1413,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { /* Update WinACL in xattr */ - ksmbd_vfs_remove_sd_xattrs(idmap, path->dentry); - ksmbd_vfs_set_sd_xattr(conn, idmap, - path->dentry, pntsd, ntsd_len); + ksmbd_vfs_remove_sd_xattrs(idmap, path); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len); } out: diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index f9fb778247e7..81489fdedd8e 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -170,6 +170,10 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) return err; } + err = mnt_want_write(path.mnt); + if (err) + goto out_err; + mode |= S_IFREG; err = vfs_create(mnt_idmap(path.mnt), d_inode(path.dentry), dentry, mode, true); @@ -179,6 +183,9 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } else { pr_err("File(%s): creation failed (err:%d)\n", name, err); } + mnt_drop_write(path.mnt); + +out_err: done_path_create(&path, dentry); return err; } @@ -209,30 +216,35 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) return err; } + err = mnt_want_write(path.mnt); + if (err) + goto out_err2; + idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); - if (err) { - goto out; - } else if (d_unhashed(dentry)) { + if (!err && d_unhashed(dentry)) { struct dentry *d; d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent, dentry->d_name.len); if (IS_ERR(d)) { err = PTR_ERR(d); - goto out; + goto out_err1; } if (unlikely(d_is_negative(d))) { dput(d); err = -ENOENT; - goto out; + goto out_err1; } ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d)); dput(d); } -out: + +out_err1: + mnt_drop_write(path.mnt); +out_err2: done_path_create(&path, dentry); if (err) pr_err("mkdir(%s): creation failed (err:%d)\n", name, err); @@ -443,7 +455,7 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, memcpy(&stream_buf[*pos], buf, count); err = ksmbd_vfs_setxattr(idmap, - fp->filp->f_path.dentry, + &fp->filp->f_path, fp->stream.name, (void *)stream_buf, size, @@ -589,6 +601,10 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) goto out_err; } + err = mnt_want_write(path->mnt); + if (err) + goto out_err; + idmap = mnt_idmap(path->mnt); if (S_ISDIR(d_inode(path->dentry)->i_mode)) { err = vfs_rmdir(idmap, d_inode(parent), path->dentry); @@ -599,6 +615,7 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) if (err) ksmbd_debug(VFS, "unlink failed, err %d\n", err); } + mnt_drop_write(path->mnt); out_err: ksmbd_revert_fsids(work); @@ -644,11 +661,16 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, goto out3; } + err = mnt_want_write(newpath.mnt); + if (err) + goto out3; + err = vfs_link(oldpath.dentry, mnt_idmap(newpath.mnt), d_inode(newpath.dentry), dentry, NULL); if (err) ksmbd_debug(VFS, "vfs_link failed err %d\n", err); + mnt_drop_write(newpath.mnt); out3: done_path_create(&newpath, dentry); @@ -694,6 +716,10 @@ retry: goto out2; } + err = mnt_want_write(old_path->mnt); + if (err) + goto out2; + trap = lock_rename_child(old_child, new_path.dentry); old_parent = dget(old_child->d_parent); @@ -757,6 +783,7 @@ out4: out3: dput(old_parent); unlock_rename(old_parent, new_path.dentry); + mnt_drop_write(old_path->mnt); out2: path_put(&new_path); @@ -897,19 +924,24 @@ ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap, * Return: 0 on success, otherwise error */ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *attr_name, + const struct path *path, const char *attr_name, void *attr_value, size_t attr_size, int flags) { int err; + err = mnt_want_write(path->mnt); + if (err) + return err; + err = vfs_setxattr(idmap, - dentry, + path->dentry, attr_name, attr_value, attr_size, flags); if (err) ksmbd_debug(VFS, "setxattr failed, err %d\n", err); + mnt_drop_write(path->mnt); return err; } @@ -1013,9 +1045,18 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, char *attr_name) + const struct path *path, char *attr_name) { - return vfs_removexattr(idmap, dentry, attr_name); + int err; + + err = mnt_want_write(path->mnt); + if (err) + return err; + + err = vfs_removexattr(idmap, path->dentry, attr_name); + mnt_drop_write(path->mnt); + + return err; } int ksmbd_vfs_unlink(struct file *filp) @@ -1024,6 +1065,10 @@ int ksmbd_vfs_unlink(struct file *filp) struct dentry *dir, *dentry = filp->f_path.dentry; struct mnt_idmap *idmap = file_mnt_idmap(filp); + err = mnt_want_write(filp->f_path.mnt); + if (err) + return err; + dir = dget_parent(dentry); err = ksmbd_vfs_lock_parent(dir, dentry); if (err) @@ -1041,6 +1086,7 @@ int ksmbd_vfs_unlink(struct file *filp) ksmbd_debug(VFS, "failed to delete, err %d\n", err); out: dput(dir); + mnt_drop_write(filp->f_path.mnt); return err; } @@ -1244,13 +1290,13 @@ struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, } int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry) + const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1258,6 +1304,10 @@ int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, goto out; } + err = mnt_want_write(path->mnt); + if (err) + goto out; + for (name = xattr_list; name - xattr_list < xattr_list_len; name += strlen(name) + 1) { ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); @@ -1266,25 +1316,26 @@ int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1) || !strncmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1)) { - err = vfs_remove_acl(idmap, dentry, name); + err = vfs_remove_acl(idmap, path->dentry, name); if (err) ksmbd_debug(SMB, "remove acl xattr failed : %s\n", name); } } + mnt_drop_write(path->mnt); + out: kvfree(xattr_list); return err; } -int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry) +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) { char *name, *xattr_list = NULL; ssize_t xattr_list_len; int err = 0; - xattr_list_len = ksmbd_vfs_listxattr(dentry, &xattr_list); + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; } else if (!xattr_list_len) { @@ -1297,7 +1348,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, dentry, name); + err = ksmbd_vfs_remove_xattr(idmap, path, name); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } @@ -1374,13 +1425,14 @@ out: int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct smb_ntsd *pntsd, int len) { int rc; struct ndr sd_ndr = {0}, acl_ndr = {0}; struct xattr_ntacl acl = {0}; struct xattr_smb_acl *smb_acl, *def_smb_acl = NULL; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); acl.version = 4; @@ -1432,7 +1484,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, goto out; } - rc = ksmbd_vfs_setxattr(idmap, dentry, + rc = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_SD, sd_ndr.data, sd_ndr.offset, 0); if (rc < 0) @@ -1522,7 +1574,7 @@ free_n_data: } int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct xattr_dos_attrib *da) { struct ndr n; @@ -1532,7 +1584,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, if (err) return err; - err = ksmbd_vfs_setxattr(idmap, dentry, XATTR_NAME_DOS_ATTRIBUTE, + err = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_DOS_ATTRIBUTE, (void *)n.data, n.offset, 0); if (err) ksmbd_debug(SMB, "failed to store dos attribute in xattr\n"); @@ -1769,10 +1821,11 @@ void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock) } int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry) + struct path *path) { struct posix_acl_state acl_state; struct posix_acl *acls; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); int rc; @@ -1802,6 +1855,11 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, return -ENOMEM; } posix_state_to_acl(&acl_state, acls->a_entries); + + rc = mnt_want_write(path->mnt); + if (rc) + goto out_err; + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1813,16 +1871,20 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + mnt_drop_write(path->mnt); + +out_err: free_acl_state(&acl_state); posix_acl_release(acls); return rc; } int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry, struct inode *parent_inode) + struct path *path, struct inode *parent_inode) { struct posix_acl *acls; struct posix_acl_entry *pace; + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); int rc, i; @@ -1841,6 +1903,10 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, } } + rc = mnt_want_write(path->mnt); + if (rc) + goto out_err; + rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1852,6 +1918,9 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } + mnt_drop_write(path->mnt); + +out_err: posix_acl_release(acls); return rc; } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index a4ae89f3230d..8c0931d4d531 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -108,12 +108,12 @@ ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name, int attr_name_len); int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, - struct dentry *dentry, const char *attr_name, + const struct path *path, const char *attr_name, void *attr_value, size_t attr_size, int flags); int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, char *attr_name); + const struct path *path, char *attr_name); int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *path, bool caseless); @@ -139,26 +139,25 @@ void ksmbd_vfs_posix_lock_wait(struct file_lock *flock); int ksmbd_vfs_posix_lock_wait_timeout(struct file_lock *flock, long timeout); void ksmbd_vfs_posix_lock_unblock(struct file_lock *flock); int ksmbd_vfs_remove_acl_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry); -int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, - struct dentry *dentry); + const struct path *path); +int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path); int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct smb_ntsd *pntsd, int len); int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd **pntsd); int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, - struct dentry *dentry, + const struct path *path, struct xattr_dos_attrib *da); int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da); int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry); + struct path *path); int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, - struct dentry *dentry, + struct path *path, struct inode *parent_inode); #endif /* __KSMBD_VFS_H__ */ diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 2d0138e72d78..f41f8d6108ce 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -252,7 +252,7 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) if (ksmbd_stream_fd(fp) && (ci->m_flags & S_DEL_ON_CLS_STREAM)) { ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), - filp->f_path.dentry, + &filp->f_path, fp->stream.name); if (err) pr_err("remove xattr failed : %s\n", diff --git a/fs/splice.c b/fs/splice.c index 3e06611d19ae..7a9565d8ec4f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -299,20 +299,36 @@ void splice_shrink_spd(struct splice_pipe_desc *spd) kfree(spd->partial); } -/* - * Splice data from an O_DIRECT file into pages and then add them to the output - * pipe. +/** + * copy_splice_read - Copy data from a file and splice the copy into a pipe + * @in: The file to read from + * @ppos: Pointer to the file position to read from + * @pipe: The pipe to splice into + * @len: The amount to splice + * @flags: The SPLICE_F_* flags + * + * This function allocates a bunch of pages sufficient to hold the requested + * amount of data (but limited by the remaining pipe capacity), passes it to + * the file's ->read_iter() to read into and then splices the used pages into + * the pipe. + * + * Return: On success, the number of bytes read will be returned and *@ppos + * will be updated if appropriate; 0 will be returned if there is no more data + * to be read; -EAGAIN will be returned if the pipe had no space, and some + * other negative error code will be returned on error. A short read may occur + * if the pipe has insufficient space, we reach the end of the data or we hit a + * hole. */ -ssize_t direct_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags) +ssize_t copy_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) { struct iov_iter to; struct bio_vec *bv; struct kiocb kiocb; struct page **pages; ssize_t ret; - size_t used, npages, chunk, remain, reclaim; + size_t used, npages, chunk, remain, keep = 0; int i; /* Work out how much data we can actually add into the pipe */ @@ -326,7 +342,7 @@ ssize_t direct_splice_read(struct file *in, loff_t *ppos, if (!bv) return -ENOMEM; - pages = (void *)(bv + npages); + pages = (struct page **)(bv + npages); npages = alloc_pages_bulk_array(GFP_USER, npages, pages); if (!npages) { kfree(bv); @@ -349,31 +365,25 @@ ssize_t direct_splice_read(struct file *in, loff_t *ppos, kiocb.ki_pos = *ppos; ret = call_read_iter(in, &kiocb, &to); - reclaim = npages * PAGE_SIZE; - remain = 0; if (ret > 0) { - reclaim -= ret; - remain = ret; + keep = DIV_ROUND_UP(ret, PAGE_SIZE); *ppos = kiocb.ki_pos; - file_accessed(in); - } else if (ret < 0) { - /* - * callers of ->splice_read() expect -EAGAIN on - * "can't put anything in there", rather than -EFAULT. - */ - if (ret == -EFAULT) - ret = -EAGAIN; } + /* + * Callers of ->splice_read() expect -EAGAIN on "can't put anything in + * there", rather than -EFAULT. + */ + if (ret == -EFAULT) + ret = -EAGAIN; + /* Free any pages that didn't get touched at all. */ - reclaim /= PAGE_SIZE; - if (reclaim) { - npages -= reclaim; - release_pages(pages + npages, reclaim); - } + if (keep < npages) + release_pages(pages + keep, npages - keep); /* Push the remaining pages into the pipe. */ - for (i = 0; i < npages; i++) { + remain = ret; + for (i = 0; i < keep; i++) { struct pipe_buffer *buf = pipe_head_buf(pipe); chunk = min_t(size_t, remain, PAGE_SIZE); @@ -390,50 +400,7 @@ ssize_t direct_splice_read(struct file *in, loff_t *ppos, kfree(bv); return ret; } -EXPORT_SYMBOL(direct_splice_read); - -/** - * generic_file_splice_read - splice data from file to a pipe - * @in: file to splice from - * @ppos: position in @in - * @pipe: pipe to splice to - * @len: number of bytes to splice - * @flags: splice modifier flags - * - * Description: - * Will read pages from given file and fill them into a pipe. Can be - * used as long as it has more or less sane ->read_iter(). - * - */ -ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) -{ - struct iov_iter to; - struct kiocb kiocb; - int ret; - - iov_iter_pipe(&to, ITER_DEST, pipe, len); - init_sync_kiocb(&kiocb, in); - kiocb.ki_pos = *ppos; - ret = call_read_iter(in, &kiocb, &to); - if (ret > 0) { - *ppos = kiocb.ki_pos; - file_accessed(in); - } else if (ret < 0) { - /* free what was emitted */ - pipe_discard_from(pipe, to.start_head); - /* - * callers of ->splice_read() expect -EAGAIN on - * "can't put anything in there", rather than -EFAULT. - */ - if (ret == -EFAULT) - ret = -EAGAIN; - } - - return ret; -} -EXPORT_SYMBOL(generic_file_splice_read); +EXPORT_SYMBOL(copy_splice_read); const struct pipe_buf_operations default_pipe_buf_ops = { .release = generic_pipe_buf_release, @@ -873,18 +840,32 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return out->f_op->splice_write(pipe, out, ppos, len, flags); } -/* - * Attempt to initiate a splice from a file to a pipe. +/** + * vfs_splice_read - Read data from a file and splice it into a pipe + * @in: File to splice from + * @ppos: Input file offset + * @pipe: Pipe to splice to + * @len: Number of bytes to splice + * @flags: Splice modifier flags (SPLICE_F_*) + * + * Splice the requested amount of data from the input file to the pipe. This + * is synchronous as the caller must hold the pipe lock across the entire + * operation. + * + * If successful, it returns the amount of data spliced, 0 if it hit the EOF or + * a hole and a negative error code otherwise. */ -static long do_splice_to(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +long vfs_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { unsigned int p_space; int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; + if (!len) + return 0; /* Don't try to read more the pipe has space for. */ p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); @@ -899,8 +880,15 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(!in->f_op->splice_read)) return warn_unsupported(in, "read"); + /* + * O_DIRECT and DAX don't deal with the pagecache, so we allocate a + * buffer, copy into it and splice that into the pipe. + */ + if ((in->f_flags & O_DIRECT) || IS_DAX(in->f_mapping->host)) + return copy_splice_read(in, ppos, pipe, len, flags); return in->f_op->splice_read(in, ppos, pipe, len, flags); } +EXPORT_SYMBOL_GPL(vfs_splice_read); /** * splice_direct_to_actor - splices data directly between two non-pipes @@ -970,7 +958,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - ret = do_splice_to(in, &pos, pipe, len, flags); + ret = vfs_splice_read(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1118,7 +1106,7 @@ long splice_file_to_pipe(struct file *in, pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) - ret = do_splice_to(in, offset, opipe, len, flags); + ret = vfs_splice_read(in, offset, opipe, len, flags); pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); diff --git a/fs/super.c b/fs/super.c index 34afe411cf2b..05ff6abddd3c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we + * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, @@ -595,7 +595,7 @@ retry: fc->s_fs_info = NULL; s->s_type = fc->fs_type; s->s_iflags |= fc->s_iflags; - strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id)); + strscpy(s->s_id, s->s_type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); @@ -674,7 +674,7 @@ retry: return ERR_PTR(err); } s->s_type = type; - strlcpy(s->s_id, type->name, sizeof(s->s_id)); + strscpy(s->s_id, type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); @@ -903,6 +903,7 @@ int reconfigure_super(struct fs_context *fc) struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; + bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) @@ -920,7 +921,7 @@ int reconfigure_super(struct fs_context *fc) bdev_read_only(sb->s_bdev)) return -EACCES; #endif - + remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } @@ -943,13 +944,18 @@ int reconfigure_super(struct fs_context *fc) */ if (remount_ro) { if (force) { - sb->s_readonly_remount = 1; - smp_wmb(); + sb_start_ro_state_change(sb); } else { retval = sb_prepare_remount_readonly(sb); if (retval) return retval; } + } else if (remount_rw) { + /* + * Protect filesystem's reconfigure code from writes from + * userspace until reconfigure finishes. + */ + sb_start_ro_state_change(sb); } if (fc->ops->reconfigure) { @@ -965,9 +971,7 @@ int reconfigure_super(struct fs_context *fc) WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | (fc->sb_flags & fc->sb_flags_mask))); - /* Needs to be ordered wrt mnt_is_readonly() */ - smp_wmb(); - sb->s_readonly_remount = 0; + sb_end_ro_state_change(sb); /* * Some filesystems modify their metadata via some other path than the @@ -982,7 +986,7 @@ int reconfigure_super(struct fs_context *fc) return 0; cancel_readonly: - sb->s_readonly_remount = 0; + sb_end_ro_state_change(sb); return retval; } @@ -1206,6 +1210,22 @@ int get_tree_keyed(struct fs_context *fc, EXPORT_SYMBOL(get_tree_keyed); #ifdef CONFIG_BLOCK +static void fs_mark_dead(struct block_device *bdev) +{ + struct super_block *sb; + + sb = get_super(bdev); + if (!sb) + return; + + if (sb->s_op->shutdown) + sb->s_op->shutdown(sb); + drop_super(sb); +} + +static const struct blk_holder_ops fs_holder_ops = { + .mark_dead = fs_mark_dead, +}; static int set_bdev_super(struct super_block *s, void *data) { @@ -1239,16 +1259,13 @@ int get_tree_bdev(struct fs_context *fc, { struct block_device *bdev; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; - if (!(fc->sb_flags & SB_RDONLY)) - mode |= FMODE_WRITE; - if (!fc->source) return invalf(fc, "No source specified"); - bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type); + bdev = blkdev_get_by_path(fc->source, sb_open_mode(fc->sb_flags), + fc->fs_type, &fs_holder_ops); if (IS_ERR(bdev)) { errorf(fc, "%s: Can't open blockdev", fc->source); return PTR_ERR(bdev); @@ -1262,7 +1279,7 @@ int get_tree_bdev(struct fs_context *fc, if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return -EBUSY; } @@ -1271,7 +1288,7 @@ int get_tree_bdev(struct fs_context *fc, s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) { - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return PTR_ERR(s); } @@ -1280,7 +1297,7 @@ int get_tree_bdev(struct fs_context *fc, if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { warnf(fc, "%pg: Can't mount, would change RO state", bdev); deactivate_locked_super(s); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return -EBUSY; } @@ -1292,10 +1309,9 @@ int get_tree_bdev(struct fs_context *fc, * holding an active reference. */ up_write(&s->s_umount); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); down_write(&s->s_umount); } else { - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fc->fs_type->name, s->s_id); @@ -1327,13 +1343,10 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, { struct block_device *bdev; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - - bdev = blkdev_get_by_path(dev_name, mode, fs_type); + bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type, + &fs_holder_ops); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -1369,10 +1382,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, * holding an active reference. */ up_write(&s->s_umount); - blkdev_put(bdev, mode); + blkdev_put(bdev, fs_type); down_write(&s->s_umount); } else { - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); @@ -1392,7 +1404,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, error_s: error = PTR_ERR(s); error_bdev: - blkdev_put(bdev, mode); + blkdev_put(bdev, fs_type); error: return ERR_PTR(error); } @@ -1401,13 +1413,11 @@ EXPORT_SYMBOL(mount_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; - fmode_t mode = sb->s_mode; bdev->bd_super = NULL; generic_shutdown_super(sb); sync_blockdev(bdev); - WARN_ON_ONCE(!(mode & FMODE_EXCL)); - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, sb->s_type); } EXPORT_SYMBOL(kill_block_super); diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index cdb3d632c63d..0140010aa0c3 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -52,7 +52,7 @@ static int sysv_handle_dirsync(struct inode *dir) } /* - * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the + * Calls to dir_get_page()/unmap_and_put_page() must be nested according to the * rules documented in mm/highmem.rst. * * NOTE: sysv_find_entry() and sysv_dotdot() act as calls to dir_get_page() @@ -103,11 +103,11 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit(ctx, name, strnlen(name,SYSV_NAMELEN), fs16_to_cpu(SYSV_SB(sb), de->inode), DT_UNKNOWN)) { - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); return 0; } } - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); } return 0; } @@ -131,7 +131,7 @@ static inline int namecompare(int len, int maxlen, * itself (as a parameter - res_dir). It does NOT read the inode of the * entry - you'll have to do that yourself if you want to. * - * On Success put_and_unmap_page() should be called on *res_page. + * On Success unmap_and_put_page() should be called on *res_page. * * sysv_find_entry() acts as a call to dir_get_page() and must be treated * accordingly for nesting purposes. @@ -166,7 +166,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_ name, de->name)) goto found; } - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); } if (++n >= npages) @@ -209,7 +209,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) goto out_page; de++; } - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); } BUG(); return -EINVAL; @@ -228,7 +228,7 @@ got_it: mark_inode_dirty(dir); err = sysv_handle_dirsync(dir); out_page: - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); return err; out_unlock: unlock_page(page); @@ -321,12 +321,12 @@ int sysv_empty_dir(struct inode * inode) if (de->name[1] != '.' || de->name[2]) goto not_empty; } - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); } return 1; not_empty: - put_and_unmap_page(page, kaddr); + unmap_and_put_page(page, kaddr); return 0; } @@ -352,7 +352,7 @@ int sysv_set_link(struct sysv_dir_entry *de, struct page *page, } /* - * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the + * Calls to dir_get_page()/unmap_and_put_page() must be nested according to the * rules documented in mm/highmem.rst. * * sysv_dotdot() acts as a call to dir_get_page() and must be treated @@ -376,7 +376,7 @@ ino_t sysv_inode_by_name(struct dentry *dentry) if (de) { res = fs16_to_cpu(SYSV_SB(dentry->d_sb), de->inode); - put_and_unmap_page(page, de); + unmap_and_put_page(page, de); } return res; } diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 50eb92557a0f..c645f60bdb7f 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -26,7 +26,7 @@ const struct file_operations sysv_file_operations = { .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; static int sysv_setattr(struct mnt_idmap *idmap, diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index b22764fe669c..58d7f43a1371 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -145,6 +145,10 @@ static int alloc_branch(struct inode *inode, */ parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + sysv_free_block(inode->i_sb, branch[n].key); + break; + } lock_buffer(bh); memset(bh->b_data, 0, blocksize); branch[n].bh = bh; diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 2b2dba4c4f56..fcf163fea3ad 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -164,7 +164,7 @@ static int sysv_unlink(struct inode * dir, struct dentry * dentry) inode->i_ctime = dir->i_ctime; inode_dec_link_count(inode); } - put_and_unmap_page(page, de); + unmap_and_put_page(page, de); return err; } @@ -227,7 +227,7 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (!new_de) goto out_dir; err = sysv_set_link(new_de, new_page, old_inode); - put_and_unmap_page(new_page, new_de); + unmap_and_put_page(new_page, new_de); if (err) goto out_dir; new_inode->i_ctime = current_time(new_inode); @@ -256,9 +256,9 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, out_dir: if (dir_de) - put_and_unmap_page(dir_page, dir_de); + unmap_and_put_page(dir_page, dir_de); out_old: - put_and_unmap_page(old_page, old_de); + unmap_and_put_page(old_page, old_de); out: return err; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 979ab1d9d0c3..6738fe43040b 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1669,7 +1669,7 @@ const struct file_operations ubifs_file_operations = { .mmap = ubifs_file_mmap, .fsync = ubifs_fsync, .unlocked_ioctl = ubifs_ioctl, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .open = fscrypt_file_open, #ifdef CONFIG_COMPAT diff --git a/fs/udf/file.c b/fs/udf/file.c index 8238f742377b..29daf5d5cb67 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -209,7 +209,7 @@ const struct file_operations udf_file_operations = { .write_iter = udf_file_write_iter, .release = udf_release_file, .fsync = generic_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index fd20423d3ed2..fd29a66e7241 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -793,11 +793,6 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (!empty_dir(new_inode)) goto out_oiter; } - /* - * We need to protect against old_inode getting converted from - * ICB to normal directory. - */ - inode_lock_nested(old_inode, I_MUTEX_NONDIR2); retval = udf_fiiter_find_entry(old_inode, &dotdot_name, &diriter); if (retval == -ENOENT) { @@ -806,10 +801,8 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, old_inode->i_ino); retval = -EFSCORRUPTED; } - if (retval) { - inode_unlock(old_inode); + if (retval) goto out_oiter; - } has_diriter = true; tloc = lelb_to_cpu(diriter.fi.icb.extLocation); if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) != @@ -889,7 +882,6 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, udf_dir_entry_len(&diriter.fi)); udf_fiiter_write_fi(&diriter, NULL); udf_fiiter_release(&diriter); - inode_unlock(old_inode); inode_dec_link_count(old_dir); if (new_inode) @@ -901,10 +893,8 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, } return 0; out_oiter: - if (has_diriter) { + if (has_diriter) udf_fiiter_release(&diriter); - inode_unlock(old_inode); - } udf_fiiter_release(&oiter); return retval; diff --git a/fs/ufs/file.c b/fs/ufs/file.c index 7e087581be7e..6558882a89ef 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -41,5 +41,5 @@ const struct file_operations ufs_file_operations = { .mmap = generic_file_mmap, .open = generic_file_open, .fsync = generic_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 0fd96d6e39ce..4e800bb7d2ab 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1332,6 +1332,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, bool basic_ioctls; unsigned long start, end, vma_end; struct vma_iterator vmi; + pgoff_t pgoff; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1459,6 +1460,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_iter_set(&vmi, start); prev = vma_prev(&vmi); + if (vma->vm_start < start) + prev = vma; ret = 0; for_each_vma_range(vmi, vma, end) { @@ -1482,8 +1485,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, vma->vm_pgoff, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), anon_vma_name(vma)); @@ -1563,6 +1567,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; + pgoff_t pgoff; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) @@ -1625,6 +1630,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, vma_iter_set(&vmi, start); prev = vma_prev(&vmi); + if (vma->vm_start < start) + prev = vma; + ret = 0; for_each_vma_range(vmi, vma, end) { cond_resched(); @@ -1662,8 +1670,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, uffd_wp_range(vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, vma->vm_pgoff, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index 572aa1c43b37..2307f8037efc 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -217,7 +217,7 @@ const struct file_operations vboxsf_reg_fops = { .open = vboxsf_file_open, .release = vboxsf_file_release, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, }; const struct inode_operations vboxsf_reg_iops = { diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig index a7ffd718f171..e1036e535352 100644 --- a/fs/verity/Kconfig +++ b/fs/verity/Kconfig @@ -39,14 +39,14 @@ config FS_VERITY_BUILTIN_SIGNATURES depends on FS_VERITY select SYSTEM_DATA_VERIFICATION help - Support verifying signatures of verity files against the X.509 - certificates that have been loaded into the ".fs-verity" - kernel keyring. + This option adds support for in-kernel verification of + fs-verity builtin signatures. - This is meant as a relatively simple mechanism that can be - used to provide an authenticity guarantee for verity files, as - an alternative to IMA appraisal. Userspace programs still - need to check that the verity bit is set in order to get an - authenticity guarantee. + Please take great care before using this feature. It is not + the only way to do signatures with fs-verity, and the + alternatives (such as userspace signature verification, and + IMA appraisal) can be much better. For details about the + limitations of this feature, see + Documentation/filesystems/fsverity.rst. If unsure, say N. diff --git a/fs/verity/enable.c b/fs/verity/enable.c index fc4c50e5219d..c284f46d1b53 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -7,6 +7,7 @@ #include "fsverity_private.h" +#include <crypto/hash.h> #include <linux/mount.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> @@ -20,7 +21,7 @@ struct block_buffer { /* Hash a block, writing the result to the next level's pending block buffer. */ static int hash_one_block(struct inode *inode, const struct merkle_tree_params *params, - struct ahash_request *req, struct block_buffer *cur) + struct block_buffer *cur) { struct block_buffer *next = cur + 1; int err; @@ -36,8 +37,7 @@ static int hash_one_block(struct inode *inode, /* Zero-pad the block if it's shorter than the block size. */ memset(&cur->data[cur->filled], 0, params->block_size - cur->filled); - err = fsverity_hash_block(params, inode, req, virt_to_page(cur->data), - offset_in_page(cur->data), + err = fsverity_hash_block(params, inode, cur->data, &next->data[next->filled]); if (err) return err; @@ -76,7 +76,6 @@ static int build_merkle_tree(struct file *filp, struct inode *inode = file_inode(filp); const u64 data_size = inode->i_size; const int num_levels = params->num_levels; - struct ahash_request *req; struct block_buffer _buffers[1 + FS_VERITY_MAX_LEVELS + 1] = {}; struct block_buffer *buffers = &_buffers[1]; unsigned long level_offset[FS_VERITY_MAX_LEVELS]; @@ -90,9 +89,6 @@ static int build_merkle_tree(struct file *filp, return 0; } - /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(params->hash_alg, GFP_KERNEL); - /* * Allocate the block buffers. Buffer "-1" is for data blocks. * Buffers 0 <= level < num_levels are for the actual tree levels. @@ -130,7 +126,7 @@ static int build_merkle_tree(struct file *filp, fsverity_err(inode, "Short read of file data"); goto out; } - err = hash_one_block(inode, params, req, &buffers[-1]); + err = hash_one_block(inode, params, &buffers[-1]); if (err) goto out; for (level = 0; level < num_levels; level++) { @@ -141,8 +137,7 @@ static int build_merkle_tree(struct file *filp, } /* Next block at @level is full */ - err = hash_one_block(inode, params, req, - &buffers[level]); + err = hash_one_block(inode, params, &buffers[level]); if (err) goto out; err = write_merkle_tree_block(inode, @@ -162,8 +157,7 @@ static int build_merkle_tree(struct file *filp, /* Finish all nonempty pending tree blocks. */ for (level = 0; level < num_levels; level++) { if (buffers[level].filled != 0) { - err = hash_one_block(inode, params, req, - &buffers[level]); + err = hash_one_block(inode, params, &buffers[level]); if (err) goto out; err = write_merkle_tree_block(inode, @@ -183,7 +177,6 @@ static int build_merkle_tree(struct file *filp, out: for (level = -1; level < num_levels; level++) kfree(buffers[level].data); - fsverity_free_hash_request(params->hash_alg, req); return err; } @@ -215,7 +208,7 @@ static int enable_verity(struct file *filp, } desc->salt_size = arg->salt_size; - /* Get the signature if the user provided one */ + /* Get the builtin signature if the user provided one */ if (arg->sig_size && copy_from_user(desc->signature, u64_to_user_ptr(arg->sig_ptr), arg->sig_size)) { diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index d34dcc033d72..49bf3a1eb2a0 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -11,9 +11,6 @@ #define pr_fmt(fmt) "fs-verity: " fmt #include <linux/fsverity.h> -#include <linux/mempool.h> - -struct ahash_request; /* * Implementation limit: maximum depth of the Merkle tree. For now 8 is plenty; @@ -23,11 +20,10 @@ struct ahash_request; /* A hash algorithm supported by fs-verity */ struct fsverity_hash_alg { - struct crypto_ahash *tfm; /* hash tfm, allocated on demand */ + struct crypto_shash *tfm; /* hash tfm, allocated on demand */ const char *name; /* crypto API name, e.g. sha256 */ unsigned int digest_size; /* digest size in bytes, e.g. 32 for SHA-256 */ unsigned int block_size; /* block size in bytes, e.g. 64 for SHA-256 */ - mempool_t req_pool; /* mempool with a preallocated hash request */ /* * The HASH_ALGO_* constant for this algorithm. This is different from * FS_VERITY_HASH_ALG_*, which uses a different numbering scheme. @@ -37,7 +33,7 @@ struct fsverity_hash_alg { /* Merkle tree parameters: hash algorithm, initial hash state, and topology */ struct merkle_tree_params { - struct fsverity_hash_alg *hash_alg; /* the hash algorithm */ + const struct fsverity_hash_alg *hash_alg; /* the hash algorithm */ const u8 *hashstate; /* initial hash state or NULL */ unsigned int digest_size; /* same as hash_alg->digest_size */ unsigned int block_size; /* size of data and tree blocks */ @@ -83,18 +79,13 @@ struct fsverity_info { extern struct fsverity_hash_alg fsverity_hash_algs[]; -struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, - unsigned int num); -struct ahash_request *fsverity_alloc_hash_request(struct fsverity_hash_alg *alg, - gfp_t gfp_flags); -void fsverity_free_hash_request(struct fsverity_hash_alg *alg, - struct ahash_request *req); -const u8 *fsverity_prepare_hash_state(struct fsverity_hash_alg *alg, +const struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, + unsigned int num); +const u8 *fsverity_prepare_hash_state(const struct fsverity_hash_alg *alg, const u8 *salt, size_t salt_size); int fsverity_hash_block(const struct merkle_tree_params *params, - const struct inode *inode, struct ahash_request *req, - struct page *page, unsigned int offset, u8 *out); -int fsverity_hash_buffer(struct fsverity_hash_alg *alg, + const struct inode *inode, const void *data, u8 *out); +int fsverity_hash_buffer(const struct fsverity_hash_alg *alg, const void *data, size_t size, u8 *out); void __init fsverity_check_hash_algs(void); diff --git a/fs/verity/hash_algs.c b/fs/verity/hash_algs.c index ea00dbedf756..c598d2035476 100644 --- a/fs/verity/hash_algs.c +++ b/fs/verity/hash_algs.c @@ -8,7 +8,6 @@ #include "fsverity_private.h" #include <crypto/hash.h> -#include <linux/scatterlist.h> /* The hash algorithms supported by fs-verity */ struct fsverity_hash_alg fsverity_hash_algs[] = { @@ -40,11 +39,11 @@ static DEFINE_MUTEX(fsverity_hash_alg_init_mutex); * * Return: pointer to the hash alg on success, else an ERR_PTR() */ -struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, - unsigned int num) +const struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, + unsigned int num) { struct fsverity_hash_alg *alg; - struct crypto_ahash *tfm; + struct crypto_shash *tfm; int err; if (num >= ARRAY_SIZE(fsverity_hash_algs) || @@ -63,11 +62,7 @@ struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, if (alg->tfm != NULL) goto out_unlock; - /* - * Using the shash API would make things a bit simpler, but the ahash - * API is preferable as it allows the use of crypto accelerators. - */ - tfm = crypto_alloc_ahash(alg->name, 0, 0); + tfm = crypto_alloc_shash(alg->name, 0, 0); if (IS_ERR(tfm)) { if (PTR_ERR(tfm) == -ENOENT) { fsverity_warn(inode, @@ -84,26 +79,20 @@ struct fsverity_hash_alg *fsverity_get_hash_alg(const struct inode *inode, } err = -EINVAL; - if (WARN_ON_ONCE(alg->digest_size != crypto_ahash_digestsize(tfm))) + if (WARN_ON_ONCE(alg->digest_size != crypto_shash_digestsize(tfm))) goto err_free_tfm; - if (WARN_ON_ONCE(alg->block_size != crypto_ahash_blocksize(tfm))) - goto err_free_tfm; - - err = mempool_init_kmalloc_pool(&alg->req_pool, 1, - sizeof(struct ahash_request) + - crypto_ahash_reqsize(tfm)); - if (err) + if (WARN_ON_ONCE(alg->block_size != crypto_shash_blocksize(tfm))) goto err_free_tfm; pr_info("%s using implementation \"%s\"\n", - alg->name, crypto_ahash_driver_name(tfm)); + alg->name, crypto_shash_driver_name(tfm)); /* pairs with smp_load_acquire() above */ smp_store_release(&alg->tfm, tfm); goto out_unlock; err_free_tfm: - crypto_free_ahash(tfm); + crypto_free_shash(tfm); alg = ERR_PTR(err); out_unlock: mutex_unlock(&fsverity_hash_alg_init_mutex); @@ -111,42 +100,6 @@ out_unlock: } /** - * fsverity_alloc_hash_request() - allocate a hash request object - * @alg: the hash algorithm for which to allocate the request - * @gfp_flags: memory allocation flags - * - * This is mempool-backed, so this never fails if __GFP_DIRECT_RECLAIM is set in - * @gfp_flags. However, in that case this might need to wait for all - * previously-allocated requests to be freed. So to avoid deadlocks, callers - * must never need multiple requests at a time to make forward progress. - * - * Return: the request object on success; NULL on failure (but see above) - */ -struct ahash_request *fsverity_alloc_hash_request(struct fsverity_hash_alg *alg, - gfp_t gfp_flags) -{ - struct ahash_request *req = mempool_alloc(&alg->req_pool, gfp_flags); - - if (req) - ahash_request_set_tfm(req, alg->tfm); - return req; -} - -/** - * fsverity_free_hash_request() - free a hash request object - * @alg: the hash algorithm - * @req: the hash request object to free - */ -void fsverity_free_hash_request(struct fsverity_hash_alg *alg, - struct ahash_request *req) -{ - if (req) { - ahash_request_zero(req); - mempool_free(req, &alg->req_pool); - } -} - -/** * fsverity_prepare_hash_state() - precompute the initial hash state * @alg: hash algorithm * @salt: a salt which is to be prepended to all data to be hashed @@ -155,27 +108,24 @@ void fsverity_free_hash_request(struct fsverity_hash_alg *alg, * Return: NULL if the salt is empty, otherwise the kmalloc()'ed precomputed * initial hash state on success or an ERR_PTR() on failure. */ -const u8 *fsverity_prepare_hash_state(struct fsverity_hash_alg *alg, +const u8 *fsverity_prepare_hash_state(const struct fsverity_hash_alg *alg, const u8 *salt, size_t salt_size) { u8 *hashstate = NULL; - struct ahash_request *req = NULL; + SHASH_DESC_ON_STACK(desc, alg->tfm); u8 *padded_salt = NULL; size_t padded_salt_size; - struct scatterlist sg; - DECLARE_CRYPTO_WAIT(wait); int err; + desc->tfm = alg->tfm; + if (salt_size == 0) return NULL; - hashstate = kmalloc(crypto_ahash_statesize(alg->tfm), GFP_KERNEL); + hashstate = kmalloc(crypto_shash_statesize(alg->tfm), GFP_KERNEL); if (!hashstate) return ERR_PTR(-ENOMEM); - /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(alg, GFP_KERNEL); - /* * Zero-pad the salt to the next multiple of the input size of the hash * algorithm's compression function, e.g. 64 bytes for SHA-256 or 128 @@ -190,26 +140,18 @@ const u8 *fsverity_prepare_hash_state(struct fsverity_hash_alg *alg, goto err_free; } memcpy(padded_salt, salt, salt_size); - - sg_init_one(&sg, padded_salt, padded_salt_size); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - ahash_request_set_crypt(req, &sg, NULL, padded_salt_size); - - err = crypto_wait_req(crypto_ahash_init(req), &wait); + err = crypto_shash_init(desc); if (err) goto err_free; - err = crypto_wait_req(crypto_ahash_update(req), &wait); + err = crypto_shash_update(desc, padded_salt, padded_salt_size); if (err) goto err_free; - err = crypto_ahash_export(req, hashstate); + err = crypto_shash_export(desc, hashstate); if (err) goto err_free; out: - fsverity_free_hash_request(alg, req); kfree(padded_salt); return hashstate; @@ -223,9 +165,7 @@ err_free: * fsverity_hash_block() - hash a single data or hash block * @params: the Merkle tree's parameters * @inode: inode for which the hashing is being done - * @req: preallocated hash request - * @page: the page containing the block to hash - * @offset: the offset of the block within @page + * @data: virtual address of a buffer containing the block to hash * @out: output digest, size 'params->digest_size' bytes * * Hash a single data or hash block. The hash is salted if a salt is specified @@ -234,33 +174,24 @@ err_free: * Return: 0 on success, -errno on failure */ int fsverity_hash_block(const struct merkle_tree_params *params, - const struct inode *inode, struct ahash_request *req, - struct page *page, unsigned int offset, u8 *out) + const struct inode *inode, const void *data, u8 *out) { - struct scatterlist sg; - DECLARE_CRYPTO_WAIT(wait); + SHASH_DESC_ON_STACK(desc, params->hash_alg->tfm); int err; - sg_init_table(&sg, 1); - sg_set_page(&sg, page, params->block_size, offset); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - ahash_request_set_crypt(req, &sg, out, params->block_size); + desc->tfm = params->hash_alg->tfm; if (params->hashstate) { - err = crypto_ahash_import(req, params->hashstate); + err = crypto_shash_import(desc, params->hashstate); if (err) { fsverity_err(inode, "Error %d importing hash state", err); return err; } - err = crypto_ahash_finup(req); + err = crypto_shash_finup(desc, data, params->block_size, out); } else { - err = crypto_ahash_digest(req); + err = crypto_shash_digest(desc, data, params->block_size, out); } - - err = crypto_wait_req(err, &wait); if (err) fsverity_err(inode, "Error %d computing block hash", err); return err; @@ -273,32 +204,12 @@ int fsverity_hash_block(const struct merkle_tree_params *params, * @size: size of data to hash, in bytes * @out: output digest, size 'alg->digest_size' bytes * - * Hash some data which is located in physically contiguous memory (i.e. memory - * allocated by kmalloc(), not by vmalloc()). No salt is used. - * * Return: 0 on success, -errno on failure */ -int fsverity_hash_buffer(struct fsverity_hash_alg *alg, +int fsverity_hash_buffer(const struct fsverity_hash_alg *alg, const void *data, size_t size, u8 *out) { - struct ahash_request *req; - struct scatterlist sg; - DECLARE_CRYPTO_WAIT(wait); - int err; - - /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(alg, GFP_KERNEL); - - sg_init_one(&sg, data, size); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - ahash_request_set_crypt(req, &sg, out, size); - - err = crypto_wait_req(crypto_ahash_digest(req), &wait); - - fsverity_free_hash_request(alg, req); - return err; + return crypto_shash_tfm_digest(alg->tfm, data, size, out); } void __init fsverity_check_hash_algs(void) diff --git a/fs/verity/measure.c b/fs/verity/measure.c index 5c79ea1b2468..eec5956141da 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -61,27 +61,42 @@ EXPORT_SYMBOL_GPL(fsverity_ioctl_measure); /** * fsverity_get_digest() - get a verity file's digest * @inode: inode to get digest of - * @digest: (out) pointer to the digest - * @alg: (out) pointer to the hash algorithm enumeration + * @raw_digest: (out) the raw file digest + * @alg: (out) the digest's algorithm, as a FS_VERITY_HASH_ALG_* value + * @halg: (out) the digest's algorithm, as a HASH_ALGO_* value * - * Return the file hash algorithm and digest of an fsverity protected file. - * Assumption: before calling this, the file must have been opened. + * Retrieves the fsverity digest of the given file. The file must have been + * opened at least once since the inode was last loaded into the inode cache; + * otherwise this function will not recognize when fsverity is enabled. * - * Return: 0 on success, -errno on failure + * The file's fsverity digest consists of @raw_digest in combination with either + * @alg or @halg. (The caller can choose which one of @alg or @halg to use.) + * + * IMPORTANT: Callers *must* make use of one of the two algorithm IDs, since + * @raw_digest is meaningless without knowing which algorithm it uses! fsverity + * provides no security guarantee for users who ignore the algorithm ID, even if + * they use the digest size (since algorithms can share the same digest size). + * + * Return: The size of the raw digest in bytes, or 0 if the file doesn't have + * fsverity enabled. */ int fsverity_get_digest(struct inode *inode, - u8 digest[FS_VERITY_MAX_DIGEST_SIZE], - enum hash_algo *alg) + u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE], + u8 *alg, enum hash_algo *halg) { const struct fsverity_info *vi; const struct fsverity_hash_alg *hash_alg; vi = fsverity_get_info(inode); if (!vi) - return -ENODATA; /* not a verity file */ + return 0; /* not a verity file */ hash_alg = vi->tree_params.hash_alg; - memcpy(digest, vi->file_digest, hash_alg->digest_size); - *alg = hash_alg->algo_id; - return 0; + memcpy(raw_digest, vi->file_digest, hash_alg->digest_size); + if (alg) + *alg = hash_alg - fsverity_hash_algs; + if (halg) + *halg = hash_alg->algo_id; + return hash_alg->digest_size; } +EXPORT_SYMBOL_GPL(fsverity_get_digest); diff --git a/fs/verity/open.c b/fs/verity/open.c index 52048b7630dc..1db5106a9c38 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -32,7 +32,7 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, unsigned int log_blocksize, const u8 *salt, size_t salt_size) { - struct fsverity_hash_alg *hash_alg; + const struct fsverity_hash_alg *hash_alg; int err; u64 blocks; u64 blocks_in_level[FS_VERITY_MAX_LEVELS]; @@ -156,9 +156,9 @@ out_err: /* * Compute the file digest by hashing the fsverity_descriptor excluding the - * signature and with the sig_size field set to 0. + * builtin signature and with the sig_size field set to 0. */ -static int compute_file_digest(struct fsverity_hash_alg *hash_alg, +static int compute_file_digest(const struct fsverity_hash_alg *hash_alg, struct fsverity_descriptor *desc, u8 *file_digest) { @@ -174,7 +174,7 @@ static int compute_file_digest(struct fsverity_hash_alg *hash_alg, /* * Create a new fsverity_info from the given fsverity_descriptor (with optional - * appended signature), and check the signature if present. The + * appended builtin signature), and check the signature if present. The * fsverity_descriptor must have already undergone basic validation. */ struct fsverity_info *fsverity_create_info(const struct inode *inode, @@ -319,8 +319,8 @@ static bool validate_fsverity_descriptor(struct inode *inode, } /* - * Read the inode's fsverity_descriptor (with optional appended signature) from - * the filesystem, and do basic validation of it. + * Read the inode's fsverity_descriptor (with optional appended builtin + * signature) from the filesystem, and do basic validation of it. */ int fsverity_get_descriptor(struct inode *inode, struct fsverity_descriptor **desc_ret) diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 2aefc5565152..f58432772d9e 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -105,7 +105,7 @@ static int fsverity_read_descriptor(struct inode *inode, if (res) return res; - /* don't include the signature */ + /* don't include the builtin signature */ desc_size = offsetof(struct fsverity_descriptor, signature); desc->sig_size = 0; @@ -131,7 +131,7 @@ static int fsverity_read_signature(struct inode *inode, } /* - * Include only the signature. Note that fsverity_get_descriptor() + * Include only the builtin signature. fsverity_get_descriptor() * already verified that sig_size is in-bounds. */ res = fsverity_read_buffer(buf, offset, length, desc->signature, diff --git a/fs/verity/signature.c b/fs/verity/signature.c index b8c51ad40d3a..72034bc71c9d 100644 --- a/fs/verity/signature.c +++ b/fs/verity/signature.c @@ -5,6 +5,14 @@ * Copyright 2019 Google LLC */ +/* + * This file implements verification of fs-verity builtin signatures. Please + * take great care before using this feature. It is not the only way to do + * signatures with fs-verity, and the alternatives (such as userspace signature + * verification, and IMA appraisal) can be much better. For details about the + * limitations of this feature, see Documentation/filesystems/fsverity.rst. + */ + #include "fsverity_private.h" #include <linux/cred.h> diff --git a/fs/verity/verify.c b/fs/verity/verify.c index e2508222750b..433cef51f5f6 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -12,38 +12,6 @@ static struct workqueue_struct *fsverity_read_workqueue; -static inline int cmp_hashes(const struct fsverity_info *vi, - const u8 *want_hash, const u8 *real_hash, - u64 data_pos, int level) -{ - const unsigned int hsize = vi->tree_params.digest_size; - - if (memcmp(want_hash, real_hash, hsize) == 0) - return 0; - - fsverity_err(vi->inode, - "FILE CORRUPTED! pos=%llu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN", - data_pos, level, - vi->tree_params.hash_alg->name, hsize, want_hash, - vi->tree_params.hash_alg->name, hsize, real_hash); - return -EBADMSG; -} - -static bool data_is_zeroed(struct inode *inode, struct page *page, - unsigned int len, unsigned int offset) -{ - void *virt = kmap_local_page(page); - - if (memchr_inv(virt + offset, 0, len)) { - kunmap_local(virt); - fsverity_err(inode, - "FILE CORRUPTED! Data past EOF is not zeroed"); - return false; - } - kunmap_local(virt); - return true; -} - /* * Returns true if the hash block with index @hblock_idx in the tree, located in * @hpage, has already been verified. @@ -122,9 +90,7 @@ static bool is_hash_block_verified(struct fsverity_info *vi, struct page *hpage, */ static bool verify_data_block(struct inode *inode, struct fsverity_info *vi, - struct ahash_request *req, struct page *data_page, - u64 data_pos, unsigned int dblock_offset_in_page, - unsigned long max_ra_pages) + const void *data, u64 data_pos, unsigned long max_ra_pages) { const struct merkle_tree_params *params = &vi->tree_params; const unsigned int hsize = params->digest_size; @@ -136,11 +102,11 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, struct { /* Page containing the hash block */ struct page *page; + /* Mapped address of the hash block (will be within @page) */ + const void *addr; /* Index of the hash block in the tree overall */ unsigned long index; - /* Byte offset of the hash block within @page */ - unsigned int offset_in_page; - /* Byte offset of the wanted hash within @page */ + /* Byte offset of the wanted hash relative to @addr */ unsigned int hoffset; } hblocks[FS_VERITY_MAX_LEVELS]; /* @@ -148,7 +114,9 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, * index of that block's hash within the current level. */ u64 hidx = data_pos >> params->log_blocksize; - int err; + + /* Up to 1 + FS_VERITY_MAX_LEVELS pages may be mapped at once */ + BUILD_BUG_ON(1 + FS_VERITY_MAX_LEVELS > KM_MAX_IDX); if (unlikely(data_pos >= inode->i_size)) { /* @@ -159,8 +127,12 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, * any part past EOF should be all zeroes. Therefore, we need * to verify that any data blocks fully past EOF are all zeroes. */ - return data_is_zeroed(inode, data_page, params->block_size, - dblock_offset_in_page); + if (memchr_inv(data, 0, params->block_size)) { + fsverity_err(inode, + "FILE CORRUPTED! Data past EOF is not zeroed"); + return false; + } + return true; } /* @@ -175,6 +147,7 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, unsigned int hblock_offset_in_page; unsigned int hoffset; struct page *hpage; + const void *haddr; /* * The index of the block in the current level; also the index @@ -192,30 +165,30 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, hblock_offset_in_page = (hblock_idx << params->log_blocksize) & ~PAGE_MASK; - /* Byte offset of the hash within the page */ - hoffset = hblock_offset_in_page + - ((hidx << params->log_digestsize) & - (params->block_size - 1)); + /* Byte offset of the hash within the block */ + hoffset = (hidx << params->log_digestsize) & + (params->block_size - 1); hpage = inode->i_sb->s_vop->read_merkle_tree_page(inode, hpage_idx, level == 0 ? min(max_ra_pages, params->tree_pages - hpage_idx) : 0); if (IS_ERR(hpage)) { - err = PTR_ERR(hpage); fsverity_err(inode, - "Error %d reading Merkle tree page %lu", - err, hpage_idx); - goto out; + "Error %ld reading Merkle tree page %lu", + PTR_ERR(hpage), hpage_idx); + goto error; } + haddr = kmap_local_page(hpage) + hblock_offset_in_page; if (is_hash_block_verified(vi, hpage, hblock_idx)) { - memcpy_from_page(_want_hash, hpage, hoffset, hsize); + memcpy(_want_hash, haddr + hoffset, hsize); want_hash = _want_hash; + kunmap_local(haddr); put_page(hpage); goto descend; } hblocks[level].page = hpage; + hblocks[level].addr = haddr; hblocks[level].index = hblock_idx; - hblocks[level].offset_in_page = hblock_offset_in_page; hblocks[level].hoffset = hoffset; hidx = next_hidx; } @@ -225,18 +198,14 @@ descend: /* Descend the tree verifying hash blocks. */ for (; level > 0; level--) { struct page *hpage = hblocks[level - 1].page; + const void *haddr = hblocks[level - 1].addr; unsigned long hblock_idx = hblocks[level - 1].index; - unsigned int hblock_offset_in_page = - hblocks[level - 1].offset_in_page; unsigned int hoffset = hblocks[level - 1].hoffset; - err = fsverity_hash_block(params, inode, req, hpage, - hblock_offset_in_page, real_hash); - if (err) - goto out; - err = cmp_hashes(vi, want_hash, real_hash, data_pos, level - 1); - if (err) - goto out; + if (fsverity_hash_block(params, inode, haddr, real_hash) != 0) + goto error; + if (memcmp(want_hash, real_hash, hsize) != 0) + goto corrupted; /* * Mark the hash block as verified. This must be atomic and * idempotent, as the same hash block might be verified by @@ -246,29 +215,39 @@ descend: set_bit(hblock_idx, vi->hash_block_verified); else SetPageChecked(hpage); - memcpy_from_page(_want_hash, hpage, hoffset, hsize); + memcpy(_want_hash, haddr + hoffset, hsize); want_hash = _want_hash; + kunmap_local(haddr); put_page(hpage); } /* Finally, verify the data block. */ - err = fsverity_hash_block(params, inode, req, data_page, - dblock_offset_in_page, real_hash); - if (err) - goto out; - err = cmp_hashes(vi, want_hash, real_hash, data_pos, -1); -out: - for (; level > 0; level--) - put_page(hblocks[level - 1].page); + if (fsverity_hash_block(params, inode, data, real_hash) != 0) + goto error; + if (memcmp(want_hash, real_hash, hsize) != 0) + goto corrupted; + return true; - return err == 0; +corrupted: + fsverity_err(inode, + "FILE CORRUPTED! pos=%llu, level=%d, want_hash=%s:%*phN, real_hash=%s:%*phN", + data_pos, level - 1, + params->hash_alg->name, hsize, want_hash, + params->hash_alg->name, hsize, real_hash); +error: + for (; level > 0; level--) { + kunmap_local(hblocks[level - 1].addr); + put_page(hblocks[level - 1].page); + } + return false; } static bool -verify_data_blocks(struct inode *inode, struct fsverity_info *vi, - struct ahash_request *req, struct folio *data_folio, - size_t len, size_t offset, unsigned long max_ra_pages) +verify_data_blocks(struct folio *data_folio, size_t len, size_t offset, + unsigned long max_ra_pages) { + struct inode *inode = data_folio->mapping->host; + struct fsverity_info *vi = inode->i_verity_info; const unsigned int block_size = vi->tree_params.block_size; u64 pos = (u64)data_folio->index << PAGE_SHIFT; @@ -278,11 +257,14 @@ verify_data_blocks(struct inode *inode, struct fsverity_info *vi, folio_test_uptodate(data_folio))) return false; do { - struct page *data_page = - folio_page(data_folio, offset >> PAGE_SHIFT); - - if (!verify_data_block(inode, vi, req, data_page, pos + offset, - offset & ~PAGE_MASK, max_ra_pages)) + void *data; + bool valid; + + data = kmap_local_folio(data_folio, offset); + valid = verify_data_block(inode, vi, data, pos + offset, + max_ra_pages); + kunmap_local(data); + if (!valid) return false; offset += block_size; len -= block_size; @@ -304,19 +286,7 @@ verify_data_blocks(struct inode *inode, struct fsverity_info *vi, */ bool fsverity_verify_blocks(struct folio *folio, size_t len, size_t offset) { - struct inode *inode = folio->mapping->host; - struct fsverity_info *vi = inode->i_verity_info; - struct ahash_request *req; - bool valid; - - /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(vi->tree_params.hash_alg, GFP_NOFS); - - valid = verify_data_blocks(inode, vi, req, folio, len, offset, 0); - - fsverity_free_hash_request(vi->tree_params.hash_alg, req); - - return valid; + return verify_data_blocks(folio, len, offset, 0); } EXPORT_SYMBOL_GPL(fsverity_verify_blocks); @@ -337,15 +307,9 @@ EXPORT_SYMBOL_GPL(fsverity_verify_blocks); */ void fsverity_verify_bio(struct bio *bio) { - struct inode *inode = bio_first_page_all(bio)->mapping->host; - struct fsverity_info *vi = inode->i_verity_info; - struct ahash_request *req; struct folio_iter fi; unsigned long max_ra_pages = 0; - /* This allocation never fails, since it's mempool-backed. */ - req = fsverity_alloc_hash_request(vi->tree_params.hash_alg, GFP_NOFS); - if (bio->bi_opf & REQ_RAHEAD) { /* * If this bio is for data readahead, then we also do readahead @@ -360,14 +324,12 @@ void fsverity_verify_bio(struct bio *bio) } bio_for_each_folio_all(fi, bio) { - if (!verify_data_blocks(inode, vi, req, fi.folio, fi.length, - fi.offset, max_ra_pages)) { + if (!verify_data_blocks(fi.folio, fi.length, fi.offset, + max_ra_pages)) { bio->bi_status = BLK_STS_IOERR; break; } } - - fsverity_free_hash_request(vi->tree_params.hash_alg, req); } EXPORT_SYMBOL_GPL(fsverity_verify_bio); #endif /* CONFIG_BLOCK */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index aede746541f8..08d632668e94 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -306,6 +306,34 @@ xfs_file_read_iter( return ret; } +STATIC ssize_t +xfs_file_splice_read( + struct file *in, + loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, + unsigned int flags) +{ + struct inode *inode = file_inode(in); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + ssize_t ret = 0; + + XFS_STATS_INC(mp, xs_read_calls); + + if (xfs_is_shutdown(mp)) + return -EIO; + + trace_xfs_file_splice_read(ip, *ppos, len); + + xfs_ilock(ip, XFS_IOLOCK_SHARED); + ret = filemap_splice_read(in, ppos, pipe, len, flags); + xfs_iunlock(ip, XFS_IOLOCK_SHARED); + if (ret > 0) + XFS_STATS_ADD(mp, xs_read_bytes, ret); + return ret; +} + /* * Common pre-write limit and setup checks. * @@ -1423,7 +1451,7 @@ const struct file_operations xfs_file_operations = { .llseek = xfs_file_llseek, .read_iter = xfs_file_read_iter, .write_iter = xfs_file_write_iter, - .splice_read = generic_file_splice_read, + .splice_read = xfs_file_splice_read, .splice_write = iter_file_splice_write, .iopoll = iocb_bio_iopoll, .unlocked_ioctl = xfs_file_ioctl, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 13851c0d640b..9ebb8333a308 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -534,6 +534,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of on-disk metadata"; + } else if (flags & SHUTDOWN_DEVICE_REMOVED) { + tag = XFS_PTAG_SHUTDOWN_IOERROR; + why = "Block device removal"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 6c09f89534d3..e2866e7fa60c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -458,12 +458,14 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ #define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ +#define SHUTDOWN_DEVICE_REMOVED (1u << 5) /* device removed underneath us */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ { SHUTDOWN_LOG_IO_ERROR, "log_io" }, \ { SHUTDOWN_FORCE_UMOUNT, "force_umount" }, \ - { SHUTDOWN_CORRUPT_INCORE, "corruption" } + { SHUTDOWN_CORRUPT_INCORE, "corruption" }, \ + { SHUTDOWN_DEVICE_REMOVED, "device_removed" } /* * Flags for xfs_mountfs diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4120bd1cba90..d910b141d52e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -377,6 +377,17 @@ disable_dax: return 0; } +static void +xfs_bdev_mark_dead( + struct block_device *bdev) +{ + xfs_force_shutdown(bdev->bd_holder, SHUTDOWN_DEVICE_REMOVED); +} + +static const struct blk_holder_ops xfs_holder_ops = { + .mark_dead = xfs_bdev_mark_dead, +}; + STATIC int xfs_blkdev_get( xfs_mount_t *mp, @@ -385,8 +396,8 @@ xfs_blkdev_get( { int error = 0; - *bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL, - mp); + *bdevp = blkdev_get_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, mp, + &xfs_holder_ops); if (IS_ERR(*bdevp)) { error = PTR_ERR(*bdevp); xfs_warn(mp, "Invalid device [%s], error=%d", name, error); @@ -397,10 +408,11 @@ xfs_blkdev_get( STATIC void xfs_blkdev_put( + struct xfs_mount *mp, struct block_device *bdev) { if (bdev) - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, mp); } STATIC void @@ -411,13 +423,13 @@ xfs_close_devices( struct block_device *logdev = mp->m_logdev_targp->bt_bdev; xfs_free_buftarg(mp->m_logdev_targp); - xfs_blkdev_put(logdev); + xfs_blkdev_put(mp, logdev); } if (mp->m_rtdev_targp) { struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev; xfs_free_buftarg(mp->m_rtdev_targp); - xfs_blkdev_put(rtdev); + xfs_blkdev_put(mp, rtdev); } xfs_free_buftarg(mp->m_ddev_targp); } @@ -492,10 +504,10 @@ xfs_open_devices( out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: - xfs_blkdev_put(rtdev); + xfs_blkdev_put(mp, rtdev); out_close_logdev: if (logdev && logdev != ddev) - xfs_blkdev_put(logdev); + xfs_blkdev_put(mp, logdev); return error; } @@ -1160,6 +1172,13 @@ xfs_fs_free_cached_objects( return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan); } +static void +xfs_fs_shutdown( + struct super_block *sb) +{ + xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED); +} + static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, @@ -1173,6 +1192,7 @@ static const struct super_operations xfs_super_operations = { .show_options = xfs_fs_show_options, .nr_cached_objects = xfs_fs_nr_cached_objects, .free_cached_objects = xfs_fs_free_cached_objects, + .shutdown = xfs_fs_shutdown, }; static int diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index cd4ca5b1fcb0..4db669203149 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1445,7 +1445,6 @@ DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); DEFINE_RW_EVENT(xfs_reflink_bounce_dio_write); - DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, int whichfork, struct xfs_bmbt_irec *irec), @@ -1535,6 +1534,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof); DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write); DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten); DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append); +DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 132f01d3461f..1451e7b48669 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -181,7 +181,6 @@ const struct address_space_operations zonefs_file_aops = { .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_page = generic_error_remove_page, - .direct_IO = noop_direct_IO, .swap_activate = zonefs_swap_activate, }; @@ -342,6 +341,77 @@ static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence) return generic_file_llseek_size(file, offset, whence, isize, isize); } +struct zonefs_zone_append_bio { + /* The target inode of the BIO */ + struct inode *inode; + + /* For sync writes, the target append write offset */ + u64 append_offset; + + /* + * This member must come last, bio_alloc_bioset will allocate enough + * bytes for entire zonefs_bio but relies on bio being last. + */ + struct bio bio; +}; + +static inline struct zonefs_zone_append_bio * +zonefs_zone_append_bio(struct bio *bio) +{ + return container_of(bio, struct zonefs_zone_append_bio, bio); +} + +static void zonefs_file_zone_append_dio_bio_end_io(struct bio *bio) +{ + struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); + struct zonefs_zone *z = zonefs_inode_zone(za_bio->inode); + sector_t za_sector; + + if (bio->bi_status != BLK_STS_OK) + goto bio_end; + + /* + * If the file zone was written underneath the file system, the zone + * append operation can still succedd (if the zone is not full) but + * the write append location will not be where we expect it to be. + * Check that we wrote where we intended to, that is, at z->z_wpoffset. + */ + za_sector = z->z_sector + (za_bio->append_offset >> SECTOR_SHIFT); + if (bio->bi_iter.bi_sector != za_sector) { + zonefs_warn(za_bio->inode->i_sb, + "Invalid write sector %llu for zone at %llu\n", + bio->bi_iter.bi_sector, z->z_sector); + bio->bi_status = BLK_STS_IOERR; + } + +bio_end: + iomap_dio_bio_end_io(bio); +} + +static void zonefs_file_zone_append_dio_submit_io(const struct iomap_iter *iter, + struct bio *bio, + loff_t file_offset) +{ + struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio); + struct inode *inode = iter->inode; + struct zonefs_zone *z = zonefs_inode_zone(inode); + + /* + * Issue a zone append BIO to process sync dio writes. The append + * file offset is saved to check the zone append write location + * on completion of the BIO. + */ + za_bio->inode = inode; + za_bio->append_offset = file_offset; + + bio->bi_opf &= ~REQ_OP_WRITE; + bio->bi_opf |= REQ_OP_ZONE_APPEND; + bio->bi_iter.bi_sector = z->z_sector; + bio->bi_end_io = zonefs_file_zone_append_dio_bio_end_io; + + submit_bio(bio); +} + static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, int error, unsigned int flags) { @@ -372,93 +442,17 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, return 0; } -static const struct iomap_dio_ops zonefs_write_dio_ops = { - .end_io = zonefs_file_write_dio_end_io, -}; +static struct bio_set zonefs_zone_append_bio_set; -static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) -{ - struct inode *inode = file_inode(iocb->ki_filp); - struct zonefs_zone *z = zonefs_inode_zone(inode); - struct block_device *bdev = inode->i_sb->s_bdev; - unsigned int max = bdev_max_zone_append_sectors(bdev); - pgoff_t start, end; - struct bio *bio; - ssize_t size = 0; - int nr_pages; - ssize_t ret; - - max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); - iov_iter_truncate(from, max); - - /* - * If the inode block size (zone write granularity) is smaller than the - * page size, we may be appending data belonging to the last page of the - * inode straddling inode->i_size, with that page already cached due to - * a buffered read or readahead. So make sure to invalidate that page. - * This will always be a no-op for the case where the block size is - * equal to the page size. - */ - start = iocb->ki_pos >> PAGE_SHIFT; - end = (iocb->ki_pos + iov_iter_count(from) - 1) >> PAGE_SHIFT; - if (invalidate_inode_pages2_range(inode->i_mapping, start, end)) - return -EBUSY; - - nr_pages = iov_iter_npages(from, BIO_MAX_VECS); - if (!nr_pages) - return 0; - - bio = bio_alloc(bdev, nr_pages, - REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS); - bio->bi_iter.bi_sector = z->z_sector; - bio->bi_ioprio = iocb->ki_ioprio; - if (iocb_is_dsync(iocb)) - bio->bi_opf |= REQ_FUA; - - ret = bio_iov_iter_get_pages(bio, from); - if (unlikely(ret)) - goto out_release; - - size = bio->bi_iter.bi_size; - task_io_account_write(size); - - if (iocb->ki_flags & IOCB_HIPRI) - bio_set_polled(bio, iocb); - - ret = submit_bio_wait(bio); - - /* - * If the file zone was written underneath the file system, the zone - * write pointer may not be where we expect it to be, but the zone - * append write can still succeed. So check manually that we wrote where - * we intended to, that is, at zi->i_wpoffset. - */ - if (!ret) { - sector_t wpsector = - z->z_sector + (z->z_wpoffset >> SECTOR_SHIFT); - - if (bio->bi_iter.bi_sector != wpsector) { - zonefs_warn(inode->i_sb, - "Corrupted write pointer %llu for zone at %llu\n", - bio->bi_iter.bi_sector, z->z_sector); - ret = -EIO; - } - } - - zonefs_file_write_dio_end_io(iocb, size, ret, 0); - trace_zonefs_file_dio_append(inode, size, ret); - -out_release: - bio_release_pages(bio, false); - bio_put(bio); - - if (ret >= 0) { - iocb->ki_pos += size; - return size; - } +static const struct iomap_dio_ops zonefs_zone_append_dio_ops = { + .submit_io = zonefs_file_zone_append_dio_submit_io, + .end_io = zonefs_file_write_dio_end_io, + .bio_set = &zonefs_zone_append_bio_set, +}; - return ret; -} +static const struct iomap_dio_ops zonefs_write_dio_ops = { + .end_io = zonefs_file_write_dio_end_io, +}; /* * Do not exceed the LFS limits nor the file zone size. If pos is under the @@ -539,6 +533,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) struct zonefs_inode_info *zi = ZONEFS_I(inode); struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; + const struct iomap_dio_ops *dio_ops; bool sync = is_sync_kiocb(iocb); bool append = false; ssize_t ret, count; @@ -582,20 +577,26 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) } if (append) { - ret = zonefs_file_dio_append(iocb, from); + unsigned int max = bdev_max_zone_append_sectors(sb->s_bdev); + + max = ALIGN_DOWN(max << SECTOR_SHIFT, sb->s_blocksize); + iov_iter_truncate(from, max); + + dio_ops = &zonefs_zone_append_dio_ops; } else { - /* - * iomap_dio_rw() may return ENOTBLK if there was an issue with - * page invalidation. Overwrite that error code with EBUSY to - * be consistent with zonefs_file_dio_append() return value for - * similar issues. - */ - ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, - &zonefs_write_dio_ops, 0, NULL, 0); - if (ret == -ENOTBLK) - ret = -EBUSY; + dio_ops = &zonefs_write_dio_ops; } + /* + * iomap_dio_rw() may return ENOTBLK if there was an issue with + * page invalidation. Overwrite that error code with EBUSY so that + * the user can make sense of the error. + */ + ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, + dio_ops, 0, NULL, 0); + if (ret == -ENOTBLK) + ret = -EBUSY; + if (zonefs_zone_is_seq(z) && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) @@ -752,6 +753,44 @@ inode_unlock: return ret; } +static ssize_t zonefs_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + struct zonefs_zone *z = zonefs_inode_zone(inode); + loff_t isize; + ssize_t ret = 0; + + /* Offline zones cannot be read */ + if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777))) + return -EPERM; + + if (*ppos >= z->z_capacity) + return 0; + + inode_lock_shared(inode); + + /* Limit read operations to written data */ + mutex_lock(&zi->i_truncate_mutex); + isize = i_size_read(inode); + if (*ppos >= isize) + len = 0; + else + len = min_t(loff_t, len, isize - *ppos); + mutex_unlock(&zi->i_truncate_mutex); + + if (len > 0) { + ret = filemap_splice_read(in, ppos, pipe, len, flags); + if (ret == -EIO) + zonefs_io_error(inode, false); + } + + inode_unlock_shared(inode); + return ret; +} + /* * Write open accounting is done only for sequential files. */ @@ -813,6 +852,7 @@ static int zonefs_file_open(struct inode *inode, struct file *file) { int ret; + file->f_mode |= FMODE_CAN_ODIRECT; ret = generic_file_open(inode, file); if (ret) return ret; @@ -896,7 +936,19 @@ const struct file_operations zonefs_file_operations = { .llseek = zonefs_file_llseek, .read_iter = zonefs_file_read_iter, .write_iter = zonefs_file_write_iter, - .splice_read = generic_file_splice_read, + .splice_read = zonefs_file_splice_read, .splice_write = iter_file_splice_write, .iopoll = iocb_bio_iopoll, }; + +int zonefs_file_bioset_init(void) +{ + return bioset_init(&zonefs_zone_append_bio_set, BIO_POOL_SIZE, + offsetof(struct zonefs_zone_append_bio, bio), + BIOSET_NEED_BVECS); +} + +void zonefs_file_bioset_exit(void) +{ + bioset_exit(&zonefs_zone_append_bio_set); +} diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 23b8b299c64e..bbe44a26a8e5 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1128,7 +1128,7 @@ static int zonefs_read_super(struct super_block *sb) bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = 0; - bio_add_page(&bio, page, PAGE_SIZE, 0); + __bio_add_page(&bio, page, PAGE_SIZE, 0); ret = submit_bio_wait(&bio); if (ret) @@ -1412,10 +1412,14 @@ static int __init zonefs_init(void) BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE); - ret = zonefs_init_inodecache(); + ret = zonefs_file_bioset_init(); if (ret) return ret; + ret = zonefs_init_inodecache(); + if (ret) + goto destroy_bioset; + ret = zonefs_sysfs_init(); if (ret) goto destroy_inodecache; @@ -1430,6 +1434,8 @@ sysfs_exit: zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); +destroy_bioset: + zonefs_file_bioset_exit(); return ret; } @@ -1439,6 +1445,7 @@ static void __exit zonefs_exit(void) unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); + zonefs_file_bioset_exit(); } MODULE_AUTHOR("Damien Le Moal"); diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index 8175652241b5..f663b8ebc2cb 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -279,6 +279,8 @@ extern const struct file_operations zonefs_dir_operations; extern const struct address_space_operations zonefs_file_aops; extern const struct file_operations zonefs_file_operations; int zonefs_file_truncate(struct inode *inode, loff_t isize); +int zonefs_file_bioset_init(void); +void zonefs_file_bioset_exit(void); /* In sysfs.c */ int zonefs_sysfs_register(struct super_block *sb); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index e6098a08c914..9ffdc0425bc2 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -761,6 +761,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_event_status *event_status)) ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)) +ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void)) ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void)) diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h deleted file mode 100644 index 69021830f078..000000000000 --- a/include/asm-generic/bugs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_BUGS_H -#define __ASM_GENERIC_BUGS_H -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* __ASM_GENERIC_BUGS_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index cebdf1ca415d..da9e5629ea43 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -839,6 +839,9 @@ #ifdef CONFIG_UNWINDER_ORC #define ORC_UNWIND_TABLE \ + .orc_header : AT(ADDR(.orc_header) - LOAD_OFFSET) { \ + BOUNDED_SECTION_BY(.orc_header, _orc_header) \ + } \ . = ALIGN(4); \ .orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.orc_unwind_ip, _orc_unwind_ip) \ diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index b43be0987b19..6b70d02bc5f9 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,13 +26,14 @@ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); +int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); + #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); u32 iort_msi_map_id(struct device *dev, u32 id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); -int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head); void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, diff --git a/include/linux/bio.h b/include/linux/bio.h index b3e7529ff55e..c4f5b5228105 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -229,7 +229,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count) static inline bool bio_flagged(struct bio *bio, unsigned int bit) { - return (bio->bi_flags & (1U << bit)) != 0; + return bio->bi_flags & (1U << bit); } static inline void bio_set_flag(struct bio *bio, unsigned int bit) @@ -465,14 +465,18 @@ extern void bio_uninit(struct bio *); void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); -int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); -bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); +int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, + unsigned off); +bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, + size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); @@ -488,7 +492,7 @@ void zero_fill_bio(struct bio *bio); static inline void bio_release_pages(struct bio *bio, bool mark_dirty) { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + if (bio_flagged(bio, BIO_PAGE_PINNED)) __bio_release_pages(bio, mark_dirty); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 06caacd77ed6..f401067ac03a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -28,8 +28,6 @@ typedef __u32 __bitwise req_flags_t; /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* may not be passed by ioscheduler */ -#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ @@ -38,12 +36,14 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* use hctx->sched_tags */ +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << 8)) +/* use an I/O scheduler for this request */ +#define RQF_USE_SCHED ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* elevator private data attached */ -#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* runtime pm request */ @@ -59,13 +59,11 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -/* queue has elevator attached */ -#define RQF_ELV ((__force req_flags_t)(1 << 22)) -#define RQF_RESV ((__force req_flags_t)(1 << 23)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, @@ -169,25 +167,20 @@ struct request { void *completion_data; }; - /* * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. + * more they have to dynamically allocate it. */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; union { struct __call_single_data csd; @@ -208,7 +201,7 @@ static inline enum req_op req_op(const struct request *req) static inline bool blk_rq_is_passthrough(struct request *rq) { - return blk_op_is_passthrough(req_op(rq)); + return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) @@ -746,8 +739,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; - - atomic_t active_queues; + unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; @@ -844,7 +836,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) @@ -860,7 +852,7 @@ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, int ioerror, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + if (!iob || (req->rq_flags & RQF_USE_SCHED) || ioerror || (req->end_io && !blk_rq_is_passthrough(req))) return false; @@ -1164,6 +1156,18 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); } +/** + * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. + * @rq: Request to examine. + * + * Note: REQ_OP_ZONE_APPEND requests do not require serialization. + */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return op_needs_zoned_write_locking(req_op(rq)) && + blk_rq_zone_is_seq(rq); +} + bool blk_req_needs_zone_write_lock(struct request *rq); bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); @@ -1194,6 +1198,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) return !blk_req_zone_is_write_locked(rq); } #else /* CONFIG_BLK_DEV_ZONED */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return false; +} + static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 740afe80f297..752a54e3284b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -55,6 +55,8 @@ struct block_device { struct super_block * bd_super; void * bd_claiming; void * bd_holder; + const struct blk_holder_ops *bd_holder_ops; + struct mutex bd_holder_lock; /* The counter of freeze processes */ int bd_fsfreeze_count; int bd_holders; @@ -323,7 +325,7 @@ struct bio { * bio flags */ enum { - BIO_NO_PAGE_REF, /* don't put release vec pages */ + BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_QUIET, /* Make BIO Quiet */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0ffe203a602..ed44a997f629 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -41,7 +41,7 @@ struct blk_stat_callback; struct blk_crypto_profile; extern const struct device_type disk_type; -extern struct device_type part_type; +extern const struct device_type part_type; extern struct class block_class; /* @@ -112,6 +112,19 @@ struct blk_integrity { unsigned char tag_size; }; +typedef unsigned int __bitwise blk_mode_t; + +/* open for reading */ +#define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) +/* open for writing */ +#define BLK_OPEN_WRITE ((__force blk_mode_t)(1 << 1)) +/* open exclusively (vs other exclusive openers */ +#define BLK_OPEN_EXCL ((__force blk_mode_t)(1 << 2)) +/* opened with O_NDELAY */ +#define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) +/* open for "writes" only for ioctls (specialy hack for floppy.c) */ +#define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) + struct gendisk { /* * major/first_minor/minors should not be set by any new driver, the @@ -187,6 +200,7 @@ struct gendisk { struct badblocks *bb; struct lockdep_map lockdep_map; u64 diskseq; + blk_mode_t open_mode; /* * Independent sector access ranges. This is always NULL for @@ -318,7 +332,6 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED - #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); @@ -328,33 +341,11 @@ extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); - -extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); -extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); - #else /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return 0; } - -static inline int blkdev_report_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - -static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - #endif /* CONFIG_BLK_DEV_ZONED */ /* @@ -392,6 +383,7 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; + struct mutex rq_qos_mutex; const struct blk_mq_ops *mq_ops; @@ -487,6 +479,7 @@ struct request_queue { * for flush operations */ struct blk_flush_queue *fq; + struct list_head flush_list; struct list_head requeue_list; spinlock_t requeue_lock; @@ -815,7 +808,7 @@ int __register_blkdev(unsigned int major, const char *name, __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); -bool bdev_check_media_change(struct block_device *bdev); +bool disk_check_media_change(struct gendisk *disk); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); @@ -836,7 +829,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); @@ -1281,15 +1273,18 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - blk_opf_t op) +/* Whether write serialization is required for @op on zoned devices. */ +static inline bool op_needs_zoned_write_locking(enum req_op op) { - if (!bdev_is_zoned(bdev)) - return false; - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; } +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + enum req_op op) +{ + return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); +} + static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1380,10 +1375,12 @@ struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); - int (*open) (struct block_device *, fmode_t); - void (*release) (struct gendisk *, fmode_t); - int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); + int (*open)(struct gendisk *disk, blk_mode_t mode); + void (*release)(struct gendisk *disk); + int (*ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); + int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); @@ -1410,7 +1407,7 @@ struct block_device_operations { }; #ifdef CONFIG_COMPAT -extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, +extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL @@ -1463,22 +1460,31 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -int bd_prepare_to_claim(struct block_device *bdev, void *holder); +struct blk_holder_ops { + void (*mark_dead)(struct block_device *bdev); +}; + +/* + * Return the correct open flags for blkdev_get_by_* for super block flags + * as stored in sb->s_flags. + */ +#define sb_open_mode(flags) \ + (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) + +struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops); +struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops); +int bd_prepare_to_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void blkdev_put(struct block_device *bdev, fmode_t mode); +void blkdev_put(struct block_device *bdev, void *holder); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); -struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); -void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, - loff_t lend); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1488,6 +1494,7 @@ int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); void printk_all_partitions(void); +int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1509,6 +1516,10 @@ static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) static inline void printk_all_partitions(void) { } +static inline int early_lookup_bdev(const char *pathname, dev_t *dev) +{ + return -EINVAL; +} #endif /* CONFIG_BLOCK */ int fsync_bdev(struct block_device *bdev); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cfbda114348c..122c62e561fc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -85,10 +85,14 @@ extern int blk_trace_remove(struct request_queue *q); # define blk_add_driver_data(rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) -# define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) # define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_note_message_enabled(q) (false) + +static inline int blk_trace_remove(struct request_queue *q) +{ + return -ENOTTY; +} #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_COMPAT diff --git a/include/linux/bsg.h b/include/linux/bsg.h index 1ac81c809da9..ee2df73edf83 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -9,7 +9,7 @@ struct device; struct request_queue; typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout); + bool open_for_write, unsigned int timeout); struct bsg_device *bsg_register_queue(struct request_queue *q, struct device *parent, const char *name, diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 67caa909e3e6..98c6fd0b39b6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -13,6 +13,7 @@ #include <linux/fs.h> /* not really needed, later.. */ #include <linux/list.h> +#include <linux/blkdev.h> #include <scsi/scsi_common.h> #include <uapi/linux/cdrom.h> @@ -61,9 +62,9 @@ struct cdrom_device_info { __u8 last_sense; __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ unsigned short mmc3_profile; /* current MMC3 profile */ - int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + bool opened_for_data; __s64 last_media_change_ms; }; @@ -101,11 +102,10 @@ int cdrom_read_tocentry(struct cdrom_device_info *cdi, struct cdrom_tocentry *entry); /* the general block_device operations structure: */ -extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode); -extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode); -extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode, unsigned int cmd, unsigned long arg); +int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode); +void cdrom_release(struct cdrom_device_info *cdi); +int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, + unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 8582a7142623..6e6e57ec69e8 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -184,8 +184,12 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void __noreturn arch_cpu_idle_dead(void); -int cpu_report_state(int cpu); -int cpu_check_up_prepare(int cpu); +#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT +void arch_cpu_finalize_init(void); +#else +static inline void arch_cpu_finalize_init(void) { } +#endif + void cpu_set_state_online(int cpu); void play_idle_precise(u64 duration_ns, u64 latency_ns); @@ -195,8 +199,6 @@ static inline void play_idle(unsigned long duration_us) } #ifdef CONFIG_HOTPLUG_CPU -bool cpu_wait_death(unsigned int cpu, int seconds); -bool cpu_report_death(void); void cpuhp_report_idle_dead(void); #else static inline void cpuhp_report_idle_dead(void) { } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0f1001dca0e0..25b6e6e6ba6b 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -133,6 +133,7 @@ enum cpuhp_state { CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, + CPUHP_BP_KICK_AP, CPUHP_BRINGUP_CPU, /* @@ -200,6 +201,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_HYPERV_ONLINE, CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, @@ -517,4 +519,20 @@ void cpuhp_online_idle(enum cpuhp_state state); static inline void cpuhp_online_idle(enum cpuhp_state state) { } #endif +struct task_struct; + +void cpuhp_ap_sync_alive(void); +void arch_cpuhp_sync_state_poll(void); +void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu); +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle); +bool arch_cpuhp_init_parallel_bringup(void); + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +void cpuhp_ap_report_dead(void); +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu); +#else +static inline void cpuhp_ap_report_dead(void) { } +static inline void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } +#endif + #endif diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a52d2b9a6846..69d0435c7ebb 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -166,17 +166,15 @@ void dm_error(const char *message); struct dm_dev { struct block_device *bdev; struct dax_device *dax_dev; - fmode_t mode; + blk_mode_t mode; char name[16]; }; -dev_t dm_get_dev_t(const char *path); - /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, +int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, struct dm_dev **result); void dm_put_device(struct dm_target *ti, struct dm_dev *d); @@ -545,7 +543,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); /* * First create an empty table. */ -int dm_table_create(struct dm_table **result, fmode_t mode, +int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md); /* @@ -588,7 +586,7 @@ void dm_sync_table(struct mapped_device *md); * Queries */ sector_t dm_table_get_size(struct dm_table *t); -fmode_t dm_table_get_mode(struct dm_table *t); +blk_mode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); const char *dm_table_device_name(struct dm_table *t); diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index c244267a6744..7738f458995f 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -126,7 +126,7 @@ int __must_check driver_register(struct device_driver *drv); void driver_unregister(struct device_driver *drv); struct device_driver *driver_find(const char *name, const struct bus_type *bus); -int driver_probe_done(void); +bool __init driver_probe_done(void); void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 36a486505b08..b9d83652c097 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -9,12 +9,12 @@ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H -#include <linux/fcntl.h> #include <linux/wait.h> #include <linux/err.h> #include <linux/percpu-defs.h> #include <linux/percpu.h> #include <linux/sched.h> +#include <uapi/linux/eventfd.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -23,10 +23,6 @@ * from eventfd, in order to leave a free define-space for * shared O_* flags. */ -#define EFD_SEMAPHORE (1 << 0) -#define EFD_CLOEXEC O_CLOEXEC -#define EFD_NONBLOCK O_NONBLOCK - #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) @@ -40,7 +36,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); diff --git a/include/linux/fs.h b/include/linux/fs.h index 133f0640fb24..ed5b32dc2625 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -119,13 +119,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) -/* File is opened with O_NDELAY (only set for block devices) */ -#define FMODE_NDELAY ((__force fmode_t)0x40) -/* File is opened with O_EXCL (only set for block devices) */ -#define FMODE_EXCL ((__force fmode_t)0x80) -/* File is opened using open(.., 3, ..) and is writeable only for ioctls - (specialy hack for floppy.c) */ -#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ @@ -171,6 +164,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports non-exclusive O_DIRECT writes from multiple threads */ #define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* File is embedded in backing_file object */ +#define FMODE_BACKING ((__force fmode_t)0x2000000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -956,29 +952,35 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } +/* + * f_{lock,count,pos_lock} members can be highly contended and share + * the same cacheline. f_{lock,mode} are very frequently used together + * and so share the same cacheline as well. The read-mostly + * f_{path,inode,op} are kept on a separate cacheline. + */ struct file { union { struct llist_node f_llist; struct rcu_head f_rcuhead; unsigned int f_iocb_flags; }; - struct path f_path; - struct inode *f_inode; /* cached value */ - const struct file_operations *f_op; /* * Protects f_ep, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; - atomic_long_t f_count; - unsigned int f_flags; fmode_t f_mode; + atomic_long_t f_count; struct mutex f_pos_lock; loff_t f_pos; + unsigned int f_flags; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; + struct path f_path; + struct inode *f_inode; /* cached value */ + const struct file_operations *f_op; u64 f_version; #ifdef CONFIG_SECURITY @@ -1215,7 +1217,6 @@ struct super_block { uuid_t s_uuid; /* UUID */ unsigned int s_max_links; - fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business @@ -1242,7 +1243,7 @@ struct super_block { */ atomic_long_t s_fsnotify_connectors; - /* Being remounted read-only */ + /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ @@ -1672,9 +1673,12 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap, WHITEOUT_DEV); } -struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, - const struct path *parentpath, - umode_t mode, int open_flag, const struct cred *cred); +struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, + const struct path *parentpath, + umode_t mode, int open_flag, + const struct cred *cred); +struct file *kernel_file_open(const struct path *path, int flags, + struct inode *inode, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -1932,6 +1936,7 @@ struct super_operations { struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); + void (*shutdown)(struct super_block *sb); }; /* @@ -2349,11 +2354,31 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } -extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern struct file *dentry_create(const struct path *path, int flags, - umode_t mode, const struct cred *cred); -extern struct file * open_with_fake_path(const struct path *, int, - struct inode*, const struct cred *); +struct file *dentry_open(const struct path *path, int flags, + const struct cred *creds); +struct file *dentry_create(const struct path *path, int flags, umode_t mode, + const struct cred *cred); +struct file *backing_file_open(const struct path *path, int flags, + const struct path *real_path, + const struct cred *cred); +struct path *backing_file_real_path(struct file *f); + +/* + * file_real_path - get the path corresponding to f_inode + * + * When opening a backing file for a stackable filesystem (e.g., + * overlayfs) f_path may be on the stackable filesystem and f_inode on + * the underlying filesystem. When the path associated with f_inode is + * needed, this helper should be used instead of accessing f_path + * directly. +*/ +static inline const struct path *file_real_path(struct file *f) +{ + if (unlikely(f->f_mode & FMODE_BACKING)) + return backing_file_real_path(f); + return &f->f_path; +} + static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); @@ -2669,7 +2694,7 @@ extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* - * Userspace may rely on the the inode number being non-zero. For example, glibc + * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with @@ -2752,11 +2777,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -ssize_t direct_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags); -extern ssize_t generic_file_splice_read(struct file *, loff_t *, - struct pipe_inode_info *, size_t, unsigned int); +ssize_t copy_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index bb8467cd11ae..ed48e4f1e755 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -91,11 +91,13 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) static inline int fsnotify_file(struct file *file, __u32 mask) { - const struct path *path = &file->f_path; + const struct path *path; if (file->f_mode & FMODE_NONOTIFY) return 0; + /* Overlayfs internal files have fake f_path */ + path = file_real_path(file); return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index e76605d5b36e..1eb7eae580be 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -143,8 +143,8 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); int fsverity_ioctl_measure(struct file *filp, void __user *arg); int fsverity_get_digest(struct inode *inode, - u8 digest[FS_VERITY_MAX_DIGEST_SIZE], - enum hash_algo *alg); + u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE], + u8 *alg, enum hash_algo *halg); /* open.c */ @@ -197,10 +197,14 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) } static inline int fsverity_get_digest(struct inode *inode, - u8 digest[FS_VERITY_MAX_DIGEST_SIZE], - enum hash_algo *alg) + u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE], + u8 *alg, enum hash_algo *halg) { - return -EOPNOTSUPP; + /* + * fsverity is not enabled in the kernel configuration, so always report + * that the file doesn't have fsverity enabled (digest size 0). + */ + return 0; } /* open.c */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 5c6db5533be6..67b8774eed8f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -252,6 +252,14 @@ struct gpio_irq_chip { bool initialized; /** + * @domain_is_allocated_externally: + * + * True it the irq_domain was allocated outside of gpiolib, in which + * case gpiolib won't free the irq_domain itself. + */ + bool domain_is_allocated_externally; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 4de1dbcd3ef6..68da30625a6c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -507,7 +507,7 @@ static inline void folio_zero_range(struct folio *folio, zero_user_segments(&folio->page, start, start + length, 0, 0); } -static inline void put_and_unmap_page(struct page *page, void *addr) +static inline void unmap_and_put_page(struct page *page, void *addr) { kunmap_local(addr); put_page(page); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 7fe31b2cd02f..bb9c666bd584 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -46,13 +46,23 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); -void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); +void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned), + unsigned flags); +/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */ +void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)); + +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ + __io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0); +} static inline void io_uring_files_cancel(void) { @@ -85,6 +95,10 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } +static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 1b2a20a42413..f04ce513fadb 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -211,6 +211,16 @@ struct io_ring_ctx { unsigned int compat: 1; enum task_work_notify_mode notify_method; + + /* + * If IORING_SETUP_NO_MMAP is used, then the below holds + * the gup'ed pages for the two rings, and the sqes. + */ + unsigned short n_ring_pages; + unsigned short n_sqe_pages; + struct page **ring_pages; + struct page **sqe_pages; + struct io_rings *rings; struct task_struct *submitter_task; struct percpu_ref refs; diff --git a/include/linux/irq.h b/include/linux/irq.h index b1b28affb32a..d8a6fdce9373 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -223,32 +223,35 @@ struct irq_data { * irq_chip::irq_set_affinity() when deactivated. * IRQD_IRQ_ENABLED_ON_SUSPEND - Interrupt is enabled on suspend by irq pm if * irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set. + * IRQD_RESEND_WHEN_IN_PROGRESS - Interrupt may fire when already in progress in which + * case it must be resent at the next available opportunity. */ enum { IRQD_TRIGGER_MASK = 0xf, - IRQD_SETAFFINITY_PENDING = (1 << 8), - IRQD_ACTIVATED = (1 << 9), - IRQD_NO_BALANCING = (1 << 10), - IRQD_PER_CPU = (1 << 11), - IRQD_AFFINITY_SET = (1 << 12), - IRQD_LEVEL = (1 << 13), - IRQD_WAKEUP_STATE = (1 << 14), - IRQD_MOVE_PCNTXT = (1 << 15), - IRQD_IRQ_DISABLED = (1 << 16), - IRQD_IRQ_MASKED = (1 << 17), - IRQD_IRQ_INPROGRESS = (1 << 18), - IRQD_WAKEUP_ARMED = (1 << 19), - IRQD_FORWARDED_TO_VCPU = (1 << 20), - IRQD_AFFINITY_MANAGED = (1 << 21), - IRQD_IRQ_STARTED = (1 << 22), - IRQD_MANAGED_SHUTDOWN = (1 << 23), - IRQD_SINGLE_TARGET = (1 << 24), - IRQD_DEFAULT_TRIGGER_SET = (1 << 25), - IRQD_CAN_RESERVE = (1 << 26), - IRQD_MSI_NOMASK_QUIRK = (1 << 27), - IRQD_HANDLE_ENFORCE_IRQCTX = (1 << 28), - IRQD_AFFINITY_ON_ACTIVATE = (1 << 29), - IRQD_IRQ_ENABLED_ON_SUSPEND = (1 << 30), + IRQD_SETAFFINITY_PENDING = BIT(8), + IRQD_ACTIVATED = BIT(9), + IRQD_NO_BALANCING = BIT(10), + IRQD_PER_CPU = BIT(11), + IRQD_AFFINITY_SET = BIT(12), + IRQD_LEVEL = BIT(13), + IRQD_WAKEUP_STATE = BIT(14), + IRQD_MOVE_PCNTXT = BIT(15), + IRQD_IRQ_DISABLED = BIT(16), + IRQD_IRQ_MASKED = BIT(17), + IRQD_IRQ_INPROGRESS = BIT(18), + IRQD_WAKEUP_ARMED = BIT(19), + IRQD_FORWARDED_TO_VCPU = BIT(20), + IRQD_AFFINITY_MANAGED = BIT(21), + IRQD_IRQ_STARTED = BIT(22), + IRQD_MANAGED_SHUTDOWN = BIT(23), + IRQD_SINGLE_TARGET = BIT(24), + IRQD_DEFAULT_TRIGGER_SET = BIT(25), + IRQD_CAN_RESERVE = BIT(26), + IRQD_MSI_NOMASK_QUIRK = BIT(27), + IRQD_HANDLE_ENFORCE_IRQCTX = BIT(28), + IRQD_AFFINITY_ON_ACTIVATE = BIT(29), + IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(30), + IRQD_RESEND_WHEN_IN_PROGRESS = BIT(31), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -448,6 +451,16 @@ static inline bool irqd_affinity_on_activate(struct irq_data *d) return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE; } +static inline void irqd_set_resend_when_in_progress(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_RESEND_WHEN_IN_PROGRESS; +} + +static inline bool irqd_needs_resend_when_in_progress(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_RESEND_WHEN_IN_PROGRESS; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/irqchip/mmp.h b/include/linux/irqchip/mmp.h deleted file mode 100644 index aa1813749a4f..000000000000 --- a/include/linux/irqchip/mmp.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQCHIP_MMP_H -#define __IRQCHIP_MMP_H - -extern struct irq_chip icu_irq_chip; - -extern void icu_init_irq(void); -extern void mmp2_init_icu(void); - -#endif /* __IRQCHIP_MMP_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 844a8e30e6de..d9451d456a73 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -102,6 +102,9 @@ struct irq_desc { int parent_irq; struct module *owner; const char *name; +#ifdef CONFIG_HARDIRQS_SW_RESEND + struct hlist_node resend_node; +#endif } ____cacheline_internodealigned_in_smp; #ifdef CONFIG_SPARSE_IRQ diff --git a/include/linux/libata.h b/include/linux/libata.h index 311cd93377c7..dd5797fb6305 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -836,7 +836,7 @@ struct ata_port { struct mutex scsi_scan_mutex; struct delayed_work hotplug_task; - struct work_struct scsi_rescan_task; + struct delayed_work scsi_rescan_task; unsigned int hsm_task_state; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 94d2be5848ae..4b9626cd83e4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1238,6 +1238,18 @@ static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev) return dev->priv.sriov.max_vfs; } +static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) +{ + /* LACP owner conditions: + * 1) Function is physical. + * 2) LAG is supported by FW. + * 3) LAG is managed by driver (currently the only option). + */ + return MLX5_CAP_GEN(dev, vport_group_manager) && + (MLX5_CAP_GEN(dev, num_lag_ports) > 1) && + MLX5_CAP_GEN(dev, lag_master); +} + static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 27ce77080c79..200068d98686 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1910,6 +1910,28 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, return page_maybe_dma_pinned(page); } +/** + * is_zero_page - Query if a page is a zero page + * @page: The page to query + * + * This returns true if @page is one of the permanent zero pages. + */ +static inline bool is_zero_page(const struct page *page) +{ + return is_zero_pfn(page_to_pfn(page)); +} + +/** + * is_zero_folio - Query if a folio is a zero page + * @folio: The folio to query + * + * This returns true if @folio is one of the permanent zero pages. + */ +static inline bool is_zero_folio(const struct folio *folio) +{ + return is_zero_page(&folio->page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_longterm_pinnable_page(struct page *page) @@ -1920,8 +1942,8 @@ static inline bool is_longterm_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - /* The zero page may always be pinned */ - if (is_zero_pfn(page_to_pfn(page))) + /* The zero page can be "pinned" but gets special handling. */ + if (is_zero_page(page)) return true; /* Coherent device memory must always allow eviction. */ @@ -2383,6 +2405,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, diff --git a/include/linux/mount.h b/include/linux/mount.h index 1ea326c368f7..4b81ea90440e 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -107,7 +107,6 @@ extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); -extern dev_t name_to_dev_t(const char *name); extern bool path_is_mountpoint(const struct path *path); extern bool our_mnt(struct vfsmount *mnt); diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 15cc9b95e32b..6e471436bba5 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -34,7 +34,7 @@ struct mtd_blktrans_dev { struct blk_mq_tag_set *tag_set; spinlock_t queue_lock; void *priv; - fmode_t file_mode; + bool writable; }; struct mtd_blktrans_ops { diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 2aba75145144..86544707236a 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -106,12 +106,22 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } +#ifdef CONFIG_TREE_SRCU #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ + .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } +#else +#define SRCU_NOTIFIER_INIT(name, pcpu) \ + { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .head = NULL, \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ + } +#endif #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index fa092b9be2fd..4109f1bd6128 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir { * @first_sgl: memory for 1st scatter/gather list segment for payload data * @sg_cnt: number of elements in the scatter/gather list * @io_dir: direction of the FCP request (see NVMEFC_FCP_xxx) - * @sqid: The nvme SQID the command is being issued on * @done: The callback routine the LLDD is to invoke upon completion of * the FCP operation. req argument is the pointer to the original * FCP IO operation. @@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir { * while processing the operation. The length of the buffer * corresponds to the fcprqst_priv_sz value specified in the * nvme_fc_port_template supplied by the LLDD. + * @sqid: The nvme SQID the command is being issued on * * Values set by the LLDD indicating completion status of the FCP operation. * Must be set prior to calling the done() callback. + * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @transferred_length: amount of payload data, in bytes, that were * transferred. Should equal payload_length on success. - * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @status: Completion status of the FCP operation. must be 0 upon success, * negative errno value upon failure (ex: -EIO). Note: this is * NOT a reflection of the NVME CQE completion status. Only the @@ -219,14 +219,14 @@ struct nvmefc_fcp_req { int sg_cnt; enum nvmefc_fcp_datadir io_dir; - __le16 sqid; - void (*done)(struct nvmefc_fcp_req *req); void *private; - u32 transferred_length; + __le16 sqid; + u16 rcv_rsplen; + u32 transferred_length; u32 status; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 95f33dadb2be..a99b1fcfc617 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -568,6 +568,7 @@ #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb +#define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d5628a7b5eaa..c8dcfdbda1f4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1845,9 +1845,9 @@ int perf_event_exit_cpu(unsigned int cpu); #define perf_event_exit_cpu NULL #endif -extern void __weak arch_perf_update_userpage(struct perf_event *event, - struct perf_event_mmap_page *userpg, - u64 now); +extern void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, + u64 now); #ifdef CONFIG_MMU extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d2c3f16cf6b1..02e0086b10f6 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -261,18 +261,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -#ifdef CONFIG_WATCH_QUEUE unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); -#endif /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ -#ifdef CONFIG_WATCH_QUEUE int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); -#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index f9c5ac80d59b..80cb00db42a4 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -156,7 +156,6 @@ struct pktcdvd_device { struct block_device *bdev; /* dev attached */ dev_t pkt_dev; /* our dev */ - char name[20]; struct packet_settings settings; struct packet_stats stats; int refcnt; /* Open count */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0260f5ea98fe..253f2676d93a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -158,6 +158,8 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); #endif /* CONFIG_PROC_PID_ARCH_STATUS */ +void arch_report_meminfo(struct seq_file *m); + #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 3c01c2bf84f5..505c908dbb81 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -196,11 +196,11 @@ enum { /* PCA9450_REG_LDO3_VOLT bits */ #define LDO3_EN_MASK 0xC0 -#define LDO3OUT_MASK 0x0F +#define LDO3OUT_MASK 0x1F /* PCA9450_REG_LDO4_VOLT bits */ #define LDO4_EN_MASK 0xC0 -#define LDO4OUT_MASK 0x0F +#define LDO4OUT_MASK 0x1F /* PCA9450_REG_LDO5_VOLT bits */ #define LDO5L_EN_MASK 0xC0 diff --git a/include/linux/root_dev.h b/include/linux/root_dev.h index 4e78651371ba..847c9a06101b 100644 --- a/include/linux/root_dev.h +++ b/include/linux/root_dev.h @@ -9,15 +9,8 @@ enum { Root_NFS = MKDEV(UNNAMED_MAJOR, 255), Root_CIFS = MKDEV(UNNAMED_MAJOR, 254), + Root_Generic = MKDEV(UNNAMED_MAJOR, 253), Root_RAM0 = MKDEV(RAMDISK_MAJOR, 0), - Root_RAM1 = MKDEV(RAMDISK_MAJOR, 1), - Root_FD0 = MKDEV(FLOPPY_MAJOR, 0), - Root_HDA1 = MKDEV(IDE0_MAJOR, 1), - Root_HDA2 = MKDEV(IDE0_MAJOR, 2), - Root_SDA1 = MKDEV(SCSI_DISK0_MAJOR, 1), - Root_SDA2 = MKDEV(SCSI_DISK0_MAJOR, 2), - Root_HDC1 = MKDEV(IDE1_MAJOR, 1), - Root_SR0 = MKDEV(SCSI_CDROM_MAJOR, 0), }; extern dev_t ROOT_DEV; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 20099268fa25..669e8cff40c7 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -135,7 +135,7 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - int posix_timer_id; + unsigned int next_posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ diff --git a/include/linux/splice.h b/include/linux/splice.h index a55179fd60fc..8f052c3dae95 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -76,6 +76,9 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *, struct splice_pipe_desc *); extern ssize_t add_to_pipe(struct pipe_inode_info *, struct pipe_buffer *); +long vfs_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, splice_direct_actor *); extern long do_splice(struct file *in, loff_t *off_in, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 762d7231e574..3b10636c51a9 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -509,6 +509,27 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp) } /** + * svcxdr_encode_opaque_pages - Insert pages into an xdr_stream + * @xdr: xdr_stream to be updated + * @pages: array of pages to insert + * @base: starting offset of first data byte in @pages + * @len: number of data bytes in @pages to insert + * + * After the @pages are added, the tail iovec is instantiated pointing + * to end of the head buffer, and the stream is set up to encode + * subsequent items into the tail. + */ +static inline void svcxdr_encode_opaque_pages(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct page **pages, + unsigned int base, + unsigned int len) +{ + xdr_write_pages(xdr, pages, base, len); + xdr->page_ptr = rqstp->rq_next_page - 1; +} + +/** * svcxdr_set_auth_slack - * @rqstp: RPC transaction * @slack: buffer space to reserve for the transaction's security flavor diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fbc4bd423b35..a5ee0af2a310 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -135,7 +135,6 @@ struct svc_rdma_recv_ctxt { struct ib_sge rc_recv_sge; void *rc_recv_buf; struct xdr_stream rc_stream; - bool rc_temp; u32 rc_byte_len; unsigned int rc_page_count; u32 rc_inv_rkey; @@ -155,12 +154,12 @@ struct svc_rdma_send_ctxt { struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; - struct completion sc_done; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; void *sc_xprt_buf; + int sc_page_count; int sc_cur_sge_no; - + struct page *sc_pages[RPCSVC_MAXPAGES]; struct ib_sge sc_sges[]; }; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 72014c9216fc..f89ec4b5ea16 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -242,8 +242,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); -extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, - size_t nbytes); +extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes); extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern void xdr_truncate_decode(struct xdr_stream *xdr, size_t len); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 33a0ee3bcb2e..24871f8ec8bb 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1280,6 +1280,7 @@ asmlinkage long sys_ni_syscall(void); #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ +asmlinkage long sys_ni_posix_timers(void); /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index bb9d3f5542f8..03d9c5ac01d1 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -44,7 +44,6 @@ struct time_namespace *copy_time_ns(unsigned long flags, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); -struct vdso_data *arch_get_vdso_data(void *vvar_page); struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) @@ -163,4 +162,6 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #endif +struct vdso_data *arch_get_vdso_data(void *vvar_page); + #endif /* _LINUX_TIMENS_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 044c1d8c230c..8e7d2c425340 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,7 +11,6 @@ #include <uapi/linux/uio.h> struct page; -struct pipe_inode_info; typedef unsigned int __bitwise iov_iter_extraction_t; @@ -25,7 +24,6 @@ enum iter_type { ITER_IOVEC, ITER_KVEC, ITER_BVEC, - ITER_PIPE, ITER_XARRAY, ITER_DISCARD, ITER_UBUF, @@ -74,7 +72,6 @@ struct iov_iter { const struct kvec *kvec; const struct bio_vec *bvec; struct xarray *xarray; - struct pipe_inode_info *pipe; void __user *ubuf; }; size_t count; @@ -82,10 +79,6 @@ struct iov_iter { }; union { unsigned long nr_segs; - struct { - unsigned int head; - unsigned int start_head; - }; loff_t xarray_start; }; }; @@ -133,11 +126,6 @@ static inline bool iov_iter_is_bvec(const struct iov_iter *i) return iov_iter_type(i) == ITER_BVEC; } -static inline bool iov_iter_is_pipe(const struct iov_iter *i) -{ - return iov_iter_type(i) == ITER_PIPE; -} - static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; @@ -286,19 +274,11 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, - size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); -ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index fc6bba20273b..45cd42f55d49 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -38,7 +38,7 @@ struct watch_filter { struct watch_queue { struct rcu_head rcu; struct watch_filter __rcu *filter; - struct pipe_inode_info *pipe; /* The pipe we're using as a buffer */ + struct pipe_inode_info *pipe; /* Pipe we use as a buffer, NULL if queue closed */ struct hlist_head watches; /* Contributory watches */ struct page **notes; /* Preallocated notifications */ unsigned long *notes_bitmap; /* Allocation bitmap for notes */ @@ -46,7 +46,6 @@ struct watch_queue { spinlock_t lock; unsigned int nr_notes; /* Number of notes */ unsigned int nr_pages; /* Number of pages in notes[] */ - bool defunct; /* T when queues closed */ }; /* diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3992c994787f..683efe29fa69 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -68,7 +68,6 @@ enum { WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -79,12 +78,6 @@ enum { WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, - - /* convenience constants */ - WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, - WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -94,6 +87,14 @@ enum { WORKER_DESC_LEN = 24, }; +/* Convenience constants - of type 'unsigned long', not 'enum'! */ +#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) +#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) + +#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) + struct work_struct { atomic_long_t data; struct list_head entry; diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index 367d5381217b..e7c44870f20d 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,10 +686,7 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected). - * @remove_mutex: mutex that avoids a race condition between a callback - * called when the hardware is disconnected and the - * file_operations of dvb_frontend. + * got disconnected. */ struct dvb_frontend { @@ -707,7 +704,6 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; - struct mutex remove_mutex; }; /** diff --git a/include/net/dsa.h b/include/net/dsa.h index 8903053fa5aa..ab0f0a5b0860 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -959,6 +959,14 @@ struct dsa_switch_ops { void (*port_disable)(struct dsa_switch *ds, int port); /* + * Compatibility between device trees defining multiple CPU ports and + * drivers which are not OK to use by default the numerically smallest + * CPU port of a switch for its local ports. This can return NULL, + * meaning "don't know/don't care". + */ + struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); + + /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ebb28ec5b6fa..f37f9f34430c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -268,7 +268,7 @@ int flow_offload_route_init(struct flow_offload *flow, int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow); + struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2e24ea1d744c..ee47d7143d99 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -462,7 +462,8 @@ struct nft_set_ops { const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); - + void (*commit)(const struct nft_set *set); + void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, @@ -471,7 +472,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; @@ -557,6 +559,7 @@ struct nft_set { u16 policy; u16 udlen; unsigned char *udata; + struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:14, @@ -807,6 +810,8 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch @@ -899,6 +904,7 @@ struct nft_expr_type { enum nft_trans_phase { NFT_TRANS_PREPARE, + NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE @@ -1007,7 +1013,10 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase); +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, @@ -1102,6 +1111,8 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_set_elem *elem); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, @@ -1138,11 +1149,17 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); +static inline bool nft_chain_binding(const struct nft_chain *chain) +{ + return chain->flags & NFT_CHAIN_BINDING; +} + static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } +int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_ctx *ctx); @@ -1556,6 +1573,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) * struct nft_trans - nf_tables object update in transaction * * @list: used internally + * @binding_list: list of objects with possible bindings * @msg_type: message type * @put_net: ctx->net needs to be put * @ctx: transaction context @@ -1563,6 +1581,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) */ struct nft_trans { struct list_head list; + struct list_head binding_list; int msg_type; bool put_net; struct nft_ctx ctx; @@ -1573,6 +1592,7 @@ struct nft_trans_rule { struct nft_rule *rule; struct nft_flow_rule *flow; u32 rule_id; + bool bound; }; #define nft_trans_rule(trans) \ @@ -1581,6 +1601,8 @@ struct nft_trans_rule { (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) +#define nft_trans_rule_bound(trans) \ + (((struct nft_trans_rule *)trans->data)->bound) struct nft_trans_set { struct nft_set *set; @@ -1605,15 +1627,19 @@ struct nft_trans_set { (((struct nft_trans_set *)trans->data)->gc_int) struct nft_trans_chain { + struct nft_chain *chain; bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; +#define nft_trans_chain(trans) \ + (((struct nft_trans_chain *)trans->data)->chain) #define nft_trans_chain_update(trans) \ (((struct nft_trans_chain *)trans->data)->update) #define nft_trans_chain_name(trans) \ @@ -1622,6 +1648,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_bound(trans) \ + (((struct nft_trans_chain *)trans->data)->bound) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id) #define nft_trans_basechain(trans) \ @@ -1698,6 +1726,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 27271f2b37cb..12eadecf8cd0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -137,6 +137,13 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc) refcount_inc(&qdisc->refcnt); } +static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return true; + return refcount_dec_if_one(&qdisc->refcnt); +} + /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ @@ -652,6 +659,7 @@ void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); +void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 33ee3f5936e6..151ca95dd08d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1054,6 +1054,7 @@ struct xfrm_offload { struct sec_path { int len; int olen; + int verified_cnt; struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index d808dc3d239e..811a0f11d0db 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -194,29 +194,6 @@ static inline enum ib_mtu iboe_get_mtu(int mtu) return 0; } -static inline int iboe_get_rate(struct net_device *dev) -{ - struct ethtool_link_ksettings cmd; - int err; - - rtnl_lock(); - err = __ethtool_get_link_ksettings(dev, &cmd); - rtnl_unlock(); - if (err) - return IB_RATE_PORT_CURRENT; - - if (cmd.base.speed >= 40000) - return IB_RATE_40_GBPS; - else if (cmd.base.speed >= 30000) - return IB_RATE_30_GBPS; - else if (cmd.base.speed >= 20000) - return IB_RATE_20_GBPS; - else if (cmd.base.speed >= 10000) - return IB_RATE_10_GBPS; - else - return IB_RATE_PORT_CURRENT; -} - static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h index beac64e38b87..a207c07da9d2 100644 --- a/include/scsi/scsi_ioctl.h +++ b/include/scsi/scsi_ioctl.h @@ -45,11 +45,11 @@ typedef struct scsi_fctargaddress { int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd, bool ndelay); -int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, +int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg); int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); +bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write); #endif /* __KERNEL__ */ #endif /* _SCSI_IOCTL_H */ diff --git a/include/soc/imx/timer.h b/include/soc/imx/timer.h deleted file mode 100644 index 25f29c6bbd0b..000000000000 --- a/include/soc/imx/timer.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2015 Linaro Ltd. - */ - -#ifndef __SOC_IMX_TIMER_H__ -#define __SOC_IMX_TIMER_H__ - -enum imx_gpt_type { - GPT_TYPE_IMX1, /* i.MX1 */ - GPT_TYPE_IMX21, /* i.MX21/27 */ - GPT_TYPE_IMX31, /* i.MX31/35/25/37/51/6Q */ - GPT_TYPE_IMX6DL, /* i.MX6DL/SX/SL */ -}; - -#endif /* __SOC_IMX_TIMER_H__ */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 7f4dfbdf12a6..40e60c33cc6f 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -246,6 +246,32 @@ DEFINE_EVENT(block_rq, block_rq_merge, ); /** + * block_io_start - insert a request for execution + * @rq: block IO operation request + * + * Called when block operation request @rq is queued for execution + */ +DEFINE_EVENT(block_rq, block_io_start, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** + * block_io_done - block IO operation request completed + * @rq: block IO operation request + * + * Called when block operation request @rq is completed + */ +DEFINE_EVENT(block_rq, block_io_done, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** * block_bio_complete - completed all work on the block operation * @q: queue holding the block operation * @bio: block operation completed diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 8ea9cea9bfeb..a8206f5332e9 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -661,6 +661,35 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_mark_finished, TP_ARGS(inode, ordered) ); +TRACE_EVENT(btrfs_finish_ordered_extent, + + TP_PROTO(const struct btrfs_inode *inode, u64 start, u64 len, + bool uptodate), + + TP_ARGS(inode, start, len, uptodate), + + TP_STRUCT__entry_btrfs( + __field( u64, ino ) + __field( u64, start ) + __field( u64, len ) + __field( bool, uptodate ) + __field( u64, root_objectid ) + ), + + TP_fast_assign_btrfs(inode->root->fs_info, + __entry->ino = btrfs_ino(inode); + __entry->start = start; + __entry->len = len; + __entry->uptodate = uptodate; + __entry->root_objectid = inode->root->root_key.objectid; + ), + + TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu uptodate=%d", + show_root_type(__entry->root_objectid), + __entry->ino, __entry->start, + __entry->len, !!__entry->uptodate) +); + DECLARE_EVENT_CLASS(btrfs__writepage, TP_PROTO(const struct page *page, const struct inode *inode, @@ -1982,25 +2011,27 @@ DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_insert, ); TRACE_EVENT(btrfs_inode_mod_outstanding_extents, - TP_PROTO(const struct btrfs_root *root, u64 ino, int mod), + TP_PROTO(const struct btrfs_root *root, u64 ino, int mod, unsigned outstanding), - TP_ARGS(root, ino, mod), + TP_ARGS(root, ino, mod, outstanding), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, ino ) __field( int, mod ) + __field( unsigned, outstanding ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->ino = ino; __entry->mod = mod; + __entry->outstanding = outstanding; ), - TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d", + TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d outstanding=%u", show_root_type(__entry->root_objectid), - __entry->ino, __entry->mod) + __entry->ino, __entry->mod, __entry->outstanding) ); DECLARE_EVENT_CLASS(btrfs__block_group, diff --git a/include/trace/events/csd.h b/include/trace/events/csd.h new file mode 100644 index 000000000000..67e9d01f80c2 --- /dev/null +++ b/include/trace/events/csd.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM csd + +#if !defined(_TRACE_CSD_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CSD_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(csd_queue_cpu, + + TP_PROTO(const unsigned int cpu, + unsigned long callsite, + smp_call_func_t func, + struct __call_single_data *csd), + + TP_ARGS(cpu, callsite, func, csd), + + TP_STRUCT__entry( + __field(unsigned int, cpu) + __field(void *, callsite) + __field(void *, func) + __field(void *, csd) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->callsite = (void *)callsite; + __entry->func = func; + __entry->csd = csd; + ), + + TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", + __entry->cpu, __entry->callsite, __entry->func, __entry->csd) + ); + +/* + * Tracepoints for a function which is called as an effect of smp_call_function.* + */ +DECLARE_EVENT_CLASS(csd_function, + + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + + TP_ARGS(func, csd), + + TP_STRUCT__entry( + __field(void *, func) + __field(void *, csd) + ), + + TP_fast_assign( + __entry->func = func; + __entry->csd = csd; + ), + + TP_printk("func=%ps, csd=%p", __entry->func, __entry->csd) +); + +DEFINE_EVENT(csd_function, csd_function_entry, + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + TP_ARGS(func, csd) +); + +DEFINE_EVENT(csd_function, csd_function_exit, + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + TP_ARGS(func, csd) +); + +#endif /* _TRACE_CSD_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 8f461e04e5f0..f8069ef2ee0f 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2112,6 +2112,14 @@ DEFINE_POST_CHUNK_EVENT(read); DEFINE_POST_CHUNK_EVENT(write); DEFINE_POST_CHUNK_EVENT(reply); +DEFINE_EVENT(svcrdma_post_chunk_class, svcrdma_cc_release, + TP_PROTO( + const struct rpc_rdma_cid *cid, + int sqecount + ), + TP_ARGS(cid, sqecount) +); + TRACE_EVENT(svcrdma_wc_read, TP_PROTO( const struct ib_wc *wc, diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 31bc7025cb44..69e42ef30979 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2104,31 +2104,46 @@ DEFINE_SVC_DEFERRED_EVENT(drop); DEFINE_SVC_DEFERRED_EVENT(queue); DEFINE_SVC_DEFERRED_EVENT(recv); -TRACE_EVENT(svcsock_new_socket, +DECLARE_EVENT_CLASS(svcsock_lifetime_class, TP_PROTO( + const void *svsk, const struct socket *socket ), - - TP_ARGS(socket), - + TP_ARGS(svsk, socket), TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(const void *, svsk) + __field(const void *, sk) __field(unsigned long, type) __field(unsigned long, family) - __field(bool, listener) + __field(unsigned long, state) ), - TP_fast_assign( + struct sock *sk = socket->sk; + + __entry->netns_ino = sock_net(sk)->ns.inum; + __entry->svsk = svsk; + __entry->sk = sk; __entry->type = socket->type; - __entry->family = socket->sk->sk_family; - __entry->listener = (socket->sk->sk_state == TCP_LISTEN); + __entry->family = sk->sk_family; + __entry->state = sk->sk_state; ), - - TP_printk("type=%s family=%s%s", - show_socket_type(__entry->type), + TP_printk("svsk=%p type=%s family=%s%s", + __entry->svsk, show_socket_type(__entry->type), rpc_show_address_family(__entry->family), - __entry->listener ? " (listener)" : "" + __entry->state == TCP_LISTEN ? " (listener)" : "" ) ); +#define DEFINE_SVCSOCK_LIFETIME_EVENT(name) \ + DEFINE_EVENT(svcsock_lifetime_class, name, \ + TP_PROTO( \ + const void *svsk, \ + const struct socket *socket \ + ), \ + TP_ARGS(svsk, socket)) + +DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_new); +DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_free); TRACE_EVENT(svcsock_marker, TP_PROTO( diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 3e8619c72f77..b4bc2828fa09 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -158,7 +158,11 @@ DEFINE_EVENT(timer_class, timer_cancel, { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ - { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) + { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ + { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ + { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ + { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ + { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 86b2a82da546..54e353c9f919 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(writeback_folio_template, strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); - __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index 5e2fb8481252..a5aff2eb5f70 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -7,42 +7,42 @@ /* Just the needed definitions for the RDB of an Amiga HD. */ struct RigidDiskBlock { - __u32 rdb_ID; + __be32 rdb_ID; __be32 rdb_SummedLongs; - __s32 rdb_ChkSum; - __u32 rdb_HostID; + __be32 rdb_ChkSum; + __be32 rdb_HostID; __be32 rdb_BlockBytes; - __u32 rdb_Flags; - __u32 rdb_BadBlockList; + __be32 rdb_Flags; + __be32 rdb_BadBlockList; __be32 rdb_PartitionList; - __u32 rdb_FileSysHeaderList; - __u32 rdb_DriveInit; - __u32 rdb_Reserved1[6]; - __u32 rdb_Cylinders; - __u32 rdb_Sectors; - __u32 rdb_Heads; - __u32 rdb_Interleave; - __u32 rdb_Park; - __u32 rdb_Reserved2[3]; - __u32 rdb_WritePreComp; - __u32 rdb_ReducedWrite; - __u32 rdb_StepRate; - __u32 rdb_Reserved3[5]; - __u32 rdb_RDBBlocksLo; - __u32 rdb_RDBBlocksHi; - __u32 rdb_LoCylinder; - __u32 rdb_HiCylinder; - __u32 rdb_CylBlocks; - __u32 rdb_AutoParkSeconds; - __u32 rdb_HighRDSKBlock; - __u32 rdb_Reserved4; + __be32 rdb_FileSysHeaderList; + __be32 rdb_DriveInit; + __be32 rdb_Reserved1[6]; + __be32 rdb_Cylinders; + __be32 rdb_Sectors; + __be32 rdb_Heads; + __be32 rdb_Interleave; + __be32 rdb_Park; + __be32 rdb_Reserved2[3]; + __be32 rdb_WritePreComp; + __be32 rdb_ReducedWrite; + __be32 rdb_StepRate; + __be32 rdb_Reserved3[5]; + __be32 rdb_RDBBlocksLo; + __be32 rdb_RDBBlocksHi; + __be32 rdb_LoCylinder; + __be32 rdb_HiCylinder; + __be32 rdb_CylBlocks; + __be32 rdb_AutoParkSeconds; + __be32 rdb_HighRDSKBlock; + __be32 rdb_Reserved4; char rdb_DiskVendor[8]; char rdb_DiskProduct[16]; char rdb_DiskRevision[4]; char rdb_ControllerVendor[8]; char rdb_ControllerProduct[16]; char rdb_ControllerRevision[4]; - __u32 rdb_Reserved5[10]; + __be32 rdb_Reserved5[10]; }; #define IDNAME_RIGIDDISK 0x5244534B /* "RDSK" */ @@ -50,16 +50,16 @@ struct RigidDiskBlock { struct PartitionBlock { __be32 pb_ID; __be32 pb_SummedLongs; - __s32 pb_ChkSum; - __u32 pb_HostID; + __be32 pb_ChkSum; + __be32 pb_HostID; __be32 pb_Next; - __u32 pb_Flags; - __u32 pb_Reserved1[2]; - __u32 pb_DevFlags; + __be32 pb_Flags; + __be32 pb_Reserved1[2]; + __be32 pb_DevFlags; __u8 pb_DriveName[32]; - __u32 pb_Reserved2[15]; + __be32 pb_Reserved2[15]; __be32 pb_Environment[17]; - __u32 pb_EReserved[15]; + __be32 pb_EReserved[15]; }; #define IDNAME_PARTITION 0x50415254 /* "PART" */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 1ebf8d455f07..73e2c10dc2cc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -783,7 +783,7 @@ enum { /* add new constants above here */ __ETHTOOL_A_STATS_GRP_CNT, - ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_CNT - 1) + ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_GRP_CNT - 1) }; enum { diff --git a/include/uapi/linux/eventfd.h b/include/uapi/linux/eventfd.h new file mode 100644 index 000000000000..2eb9ab6c32f3 --- /dev/null +++ b/include/uapi/linux/eventfd.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_EVENTFD_H +#define _UAPI_LINUX_EVENTFD_H + +#include <linux/fcntl.h> + +#define EFD_SEMAPHORE (1 << 0) +#define EFD_CLOEXEC O_CLOEXEC +#define EFD_NONBLOCK O_NONBLOCK + +#endif /* _UAPI_LINUX_EVENTFD_H */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0716cb17e436..f222d263bc55 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -173,6 +173,18 @@ enum { */ #define IORING_SETUP_DEFER_TASKRUN (1U << 13) +/* + * Application provides the memory for the rings + */ +#define IORING_SETUP_NO_MMAP (1U << 14) + +/* + * Register the ring fd in itself for use with + * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather + * than an fd. + */ +#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -406,7 +418,7 @@ struct io_sqring_offsets { __u32 dropped; __u32 array; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* @@ -425,7 +437,7 @@ struct io_cqring_offsets { __u32 cqes; __u32 flags; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 4d93967f8aea..8eb0d7b758d2 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -74,7 +74,8 @@ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ #define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ -#define MOVE_MOUNT__MASK 0x00000177 +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 /* * fsopen() flags. diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h index 6a5552dfd6af..987a3022dc5f 100644 --- a/include/uapi/linux/pktcdvd.h +++ b/include/uapi/linux/pktcdvd.h @@ -16,6 +16,7 @@ #include <linux/types.h> /* + * UNUSED: * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. */ #define PACKET_DEBUG 1 diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 640bf687b94a..4b8558db90e1 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -47,6 +47,14 @@ _IOWR('u', UBLK_CMD_END_USER_RECOVERY, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_GET_DEV_INFO2 \ _IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_GET_FEATURES \ + _IOR('u', 0x13, struct ublksrv_ctrl_cmd) + +/* + * 64bits are enough now, and it should be easy to extend in case of + * running out of feature flags + */ +#define UBLK_FEATURES_LEN 8 /* * IO commands, issued by ublk server, and handled by ublk driver. @@ -93,9 +101,29 @@ #define UBLKSRV_CMD_BUF_OFFSET 0 #define UBLKSRV_IO_BUF_OFFSET 0x80000000 -/* tag bit is 12bit, so at most 4096 IOs for each queue */ +/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */ #define UBLK_MAX_QUEUE_DEPTH 4096 +/* single IO buffer max size is 32MB */ +#define UBLK_IO_BUF_OFF 0 +#define UBLK_IO_BUF_BITS 25 +#define UBLK_IO_BUF_BITS_MASK ((1ULL << UBLK_IO_BUF_BITS) - 1) + +/* so at most 64K IOs for each queue */ +#define UBLK_TAG_OFF UBLK_IO_BUF_BITS +#define UBLK_TAG_BITS 16 +#define UBLK_TAG_BITS_MASK ((1ULL << UBLK_TAG_BITS) - 1) + +/* max 4096 queues */ +#define UBLK_QID_OFF (UBLK_TAG_OFF + UBLK_TAG_BITS) +#define UBLK_QID_BITS 12 +#define UBLK_QID_BITS_MASK ((1ULL << UBLK_QID_BITS) - 1) + +#define UBLK_MAX_NR_QUEUES (1U << UBLK_QID_BITS) + +#define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) +#define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) + /* * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space @@ -145,6 +173,9 @@ /* use ioctl encoding for uring command */ #define UBLK_F_CMD_IOCTL_ENCODE (1UL << 6) +/* Copy between request and user buffer by pread()/pwrite() */ +#define UBLK_F_USER_COPY (1UL << 7) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 diff --git a/init/do_mounts.c b/init/do_mounts.c index 811e94daf0a8..2a970f6ac68f 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -28,7 +28,6 @@ #include "do_mounts.h" int root_mountflags = MS_RDONLY | MS_SILENT; -static char * __initdata root_device_name; static char __initdata saved_root_name[64]; static int root_wait; @@ -60,240 +59,6 @@ static int __init readwrite(char *str) __setup("ro", readonly); __setup("rw", readwrite); -#ifdef CONFIG_BLOCK -struct uuidcmp { - const char *uuid; - int len; -}; - -/** - * match_dev_by_uuid - callback for finding a partition using its uuid - * @dev: device passed in by the caller - * @data: opaque pointer to the desired struct uuidcmp to match - * - * Returns 1 if the device matches, and 0 otherwise. - */ -static int match_dev_by_uuid(struct device *dev, const void *data) -{ - struct block_device *bdev = dev_to_bdev(dev); - const struct uuidcmp *cmp = data; - - if (!bdev->bd_meta_info || - strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len)) - return 0; - return 1; -} - -/** - * devt_from_partuuid - looks up the dev_t of a partition by its UUID - * @uuid_str: char array containing ascii UUID - * - * The function will return the first partition which contains a matching - * UUID value in its partition_meta_info struct. This does not search - * by filesystem UUIDs. - * - * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be - * extracted and used as an offset from the partition identified by the UUID. - * - * Returns the matching dev_t on success or 0 on failure. - */ -static dev_t devt_from_partuuid(const char *uuid_str) -{ - struct uuidcmp cmp; - struct device *dev = NULL; - dev_t devt = 0; - int offset = 0; - char *slash; - - cmp.uuid = uuid_str; - - slash = strchr(uuid_str, '/'); - /* Check for optional partition number offset attributes. */ - if (slash) { - char c = 0; - - /* Explicitly fail on poor PARTUUID syntax. */ - if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1) - goto clear_root_wait; - cmp.len = slash - uuid_str; - } else { - cmp.len = strlen(uuid_str); - } - - if (!cmp.len) - goto clear_root_wait; - - dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid); - if (!dev) - return 0; - - if (offset) { - /* - * Attempt to find the requested partition by adding an offset - * to the partition number found by UUID. - */ - devt = part_devt(dev_to_disk(dev), - dev_to_bdev(dev)->bd_partno + offset); - } else { - devt = dev->devt; - } - - put_device(dev); - return devt; - -clear_root_wait: - pr_err("VFS: PARTUUID= is invalid.\n" - "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n"); - if (root_wait) - pr_err("Disabling rootwait; root= is invalid.\n"); - root_wait = 0; - return 0; -} - -/** - * match_dev_by_label - callback for finding a partition using its label - * @dev: device passed in by the caller - * @data: opaque pointer to the label to match - * - * Returns 1 if the device matches, and 0 otherwise. - */ -static int match_dev_by_label(struct device *dev, const void *data) -{ - struct block_device *bdev = dev_to_bdev(dev); - const char *label = data; - - if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname)) - return 0; - return 1; -} - -static dev_t devt_from_partlabel(const char *label) -{ - struct device *dev; - dev_t devt = 0; - - dev = class_find_device(&block_class, NULL, label, &match_dev_by_label); - if (dev) { - devt = dev->devt; - put_device(dev); - } - - return devt; -} - -static dev_t devt_from_devname(const char *name) -{ - dev_t devt = 0; - int part; - char s[32]; - char *p; - - if (strlen(name) > 31) - return 0; - strcpy(s, name); - for (p = s; *p; p++) { - if (*p == '/') - *p = '!'; - } - - devt = blk_lookup_devt(s, 0); - if (devt) - return devt; - - /* - * Try non-existent, but valid partition, which may only exist after - * opening the device, like partitioned md devices. - */ - while (p > s && isdigit(p[-1])) - p--; - if (p == s || !*p || *p == '0') - return 0; - - /* try disk name without <part number> */ - part = simple_strtoul(p, NULL, 10); - *p = '\0'; - devt = blk_lookup_devt(s, part); - if (devt) - return devt; - - /* try disk name without p<part number> */ - if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p') - return 0; - p[-1] = '\0'; - return blk_lookup_devt(s, part); -} -#endif /* CONFIG_BLOCK */ - -static dev_t devt_from_devnum(const char *name) -{ - unsigned maj, min, offset; - dev_t devt = 0; - char *p, dummy; - - if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || - sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { - devt = MKDEV(maj, min); - if (maj != MAJOR(devt) || min != MINOR(devt)) - return 0; - } else { - devt = new_decode_dev(simple_strtoul(name, &p, 16)); - if (*p) - return 0; - } - - return devt; -} - -/* - * Convert a name into device number. We accept the following variants: - * - * 1) <hex_major><hex_minor> device number in hexadecimal represents itself - * no leading 0x, for example b302. - * 2) /dev/nfs represents Root_NFS (0xff) - * 3) /dev/<disk_name> represents the device number of disk - * 4) /dev/<disk_name><decimal> represents the device number - * of partition - device number of disk plus the partition number - * 5) /dev/<disk_name>p<decimal> - same as the above, that form is - * used when disk name of partitioned disk ends on a digit. - * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the - * unique id of a partition if the partition table provides it. - * The UUID may be either an EFI/GPT UUID, or refer to an MSDOS - * partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- - * filled hex representation of the 32-bit "NT disk signature", and PP - * is a zero-filled hex representation of the 1-based partition number. - * 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to - * a partition with a known unique id. - * 8) <major>:<minor> major and minor number of the device separated by - * a colon. - * 9) PARTLABEL=<name> with name being the GPT partition label. - * MSDOS partitions do not support labels! - * 10) /dev/cifs represents Root_CIFS (0xfe) - * - * If name doesn't have fall into the categories above, we return (0,0). - * block_class is used to check if something is a disk name. If the disk - * name contains slashes, the device name has them replaced with - * bangs. - */ -dev_t name_to_dev_t(const char *name) -{ - if (strcmp(name, "/dev/nfs") == 0) - return Root_NFS; - if (strcmp(name, "/dev/cifs") == 0) - return Root_CIFS; - if (strcmp(name, "/dev/ram") == 0) - return Root_RAM0; -#ifdef CONFIG_BLOCK - if (strncmp(name, "PARTUUID=", 9) == 0) - return devt_from_partuuid(name + 9); - if (strncmp(name, "PARTLABEL=", 10) == 0) - return devt_from_partlabel(name + 10); - if (strncmp(name, "/dev/", 5) == 0) - return devt_from_devname(name + 5); -#endif - return devt_from_devnum(name); -} -EXPORT_SYMBOL_GPL(name_to_dev_t); - static int __init root_dev_setup(char *line) { strscpy(saved_root_name, line, sizeof(saved_root_name)); @@ -338,7 +103,7 @@ __setup("rootfstype=", fs_names_setup); __setup("rootdelay=", root_delay_setup); /* This can return zero length strings. Caller should check */ -static int __init split_fs_names(char *page, size_t size, char *names) +static int __init split_fs_names(char *page, size_t size) { int count = 1; char *p = page; @@ -391,7 +156,7 @@ out: return ret; } -void __init mount_block_root(char *name, int flags) +void __init mount_root_generic(char *name, char *pretty_name, int flags) { struct page *page = alloc_page(GFP_KERNEL); char *fs_names = page_address(page); @@ -402,7 +167,7 @@ void __init mount_block_root(char *name, int flags) scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)", MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); if (root_fs_names) - num_fs = split_fs_names(fs_names, PAGE_SIZE, root_fs_names); + num_fs = split_fs_names(fs_names, PAGE_SIZE); else num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE); retry: @@ -425,7 +190,7 @@ retry: * and give them a list of the available devices */ printk("VFS: Cannot open root device \"%s\" or %s: error %d\n", - root_device_name, b, err); + pretty_name, b, err); printk("Please append a correct \"root=\" boot option; here are the available partitions:\n"); printk_all_partitions(); @@ -453,15 +218,14 @@ out: #define NFSROOT_TIMEOUT_MAX 30 #define NFSROOT_RETRY_MAX 5 -static int __init mount_nfs_root(void) +static void __init mount_nfs_root(void) { char *root_dev, *root_data; unsigned int timeout; - int try, err; + int try; - err = nfs_root_data(&root_dev, &root_data); - if (err != 0) - return 0; + if (nfs_root_data(&root_dev, &root_data)) + goto fail; /* * The server or network may not be ready, so try several @@ -470,10 +234,8 @@ static int __init mount_nfs_root(void) */ timeout = NFSROOT_TIMEOUT_MIN; for (try = 1; ; try++) { - err = do_mount_root(root_dev, "nfs", - root_mountflags, root_data); - if (err == 0) - return 1; + if (!do_mount_root(root_dev, "nfs", root_mountflags, root_data)) + return; if (try > NFSROOT_RETRY_MAX) break; @@ -483,9 +245,14 @@ static int __init mount_nfs_root(void) if (timeout > NFSROOT_TIMEOUT_MAX) timeout = NFSROOT_TIMEOUT_MAX; } - return 0; +fail: + pr_err("VFS: Unable to mount root fs via NFS.\n"); +} +#else +static inline void mount_nfs_root(void) +{ } -#endif +#endif /* CONFIG_ROOT_NFS */ #ifdef CONFIG_CIFS_ROOT @@ -495,22 +262,20 @@ extern int cifs_root_data(char **dev, char **opts); #define CIFSROOT_TIMEOUT_MAX 30 #define CIFSROOT_RETRY_MAX 5 -static int __init mount_cifs_root(void) +static void __init mount_cifs_root(void) { char *root_dev, *root_data; unsigned int timeout; - int try, err; + int try; - err = cifs_root_data(&root_dev, &root_data); - if (err != 0) - return 0; + if (cifs_root_data(&root_dev, &root_data)) + goto fail; timeout = CIFSROOT_TIMEOUT_MIN; for (try = 1; ; try++) { - err = do_mount_root(root_dev, "cifs", root_mountflags, - root_data); - if (err == 0) - return 1; + if (!do_mount_root(root_dev, "cifs", root_mountflags, + root_data)) + return; if (try > CIFSROOT_RETRY_MAX) break; @@ -519,9 +284,14 @@ static int __init mount_cifs_root(void) if (timeout > CIFSROOT_TIMEOUT_MAX) timeout = CIFSROOT_TIMEOUT_MAX; } - return 0; +fail: + pr_err("VFS: Unable to mount root fs via SMB.\n"); } -#endif +#else +static inline void mount_cifs_root(void) +{ +} +#endif /* CONFIG_CIFS_ROOT */ static bool __init fs_is_nodev(char *fstype) { @@ -536,7 +306,7 @@ static bool __init fs_is_nodev(char *fstype) return ret; } -static int __init mount_nodev_root(void) +static int __init mount_nodev_root(char *root_device_name) { char *fs_names, *fstype; int err = -EINVAL; @@ -545,7 +315,7 @@ static int __init mount_nodev_root(void) fs_names = (void *)__get_free_page(GFP_KERNEL); if (!fs_names) return -EINVAL; - num_fs = split_fs_names(fs_names, PAGE_SIZE, root_fs_names); + num_fs = split_fs_names(fs_names, PAGE_SIZE); for (i = 0, fstype = fs_names; i < num_fs; i++, fstype += strlen(fstype) + 1) { @@ -563,35 +333,84 @@ static int __init mount_nodev_root(void) return err; } -void __init mount_root(void) +#ifdef CONFIG_BLOCK +static void __init mount_block_root(char *root_device_name) { -#ifdef CONFIG_ROOT_NFS - if (ROOT_DEV == Root_NFS) { - if (!mount_nfs_root()) - printk(KERN_ERR "VFS: Unable to mount root fs via NFS.\n"); - return; + int err = create_dev("/dev/root", ROOT_DEV); + + if (err < 0) + pr_emerg("Failed to create /dev/root: %d\n", err); + mount_root_generic("/dev/root", root_device_name, root_mountflags); +} +#else +static inline void mount_block_root(char *root_device_name) +{ +} +#endif /* CONFIG_BLOCK */ + +void __init mount_root(char *root_device_name) +{ + switch (ROOT_DEV) { + case Root_NFS: + mount_nfs_root(); + break; + case Root_CIFS: + mount_cifs_root(); + break; + case Root_Generic: + mount_root_generic(root_device_name, root_device_name, + root_mountflags); + break; + case 0: + if (root_device_name && root_fs_names && + mount_nodev_root(root_device_name) == 0) + break; + fallthrough; + default: + mount_block_root(root_device_name); + break; } -#endif -#ifdef CONFIG_CIFS_ROOT - if (ROOT_DEV == Root_CIFS) { - if (!mount_cifs_root()) - printk(KERN_ERR "VFS: Unable to mount root fs via SMB.\n"); +} + +/* wait for any asynchronous scanning to complete */ +static void __init wait_for_root(char *root_device_name) +{ + if (ROOT_DEV != 0) return; - } -#endif - if (ROOT_DEV == 0 && root_device_name && root_fs_names) { - if (mount_nodev_root() == 0) - return; - } -#ifdef CONFIG_BLOCK - { - int err = create_dev("/dev/root", ROOT_DEV); - if (err < 0) - pr_emerg("Failed to create /dev/root: %d\n", err); - mount_block_root("/dev/root", root_mountflags); + pr_info("Waiting for root device %s...\n", root_device_name); + + while (!driver_probe_done() || + early_lookup_bdev(root_device_name, &ROOT_DEV) < 0) + msleep(5); + async_synchronize_full(); + +} + +static dev_t __init parse_root_device(char *root_device_name) +{ + int error; + dev_t dev; + + if (!strncmp(root_device_name, "mtd", 3) || + !strncmp(root_device_name, "ubi", 3)) + return Root_Generic; + if (strcmp(root_device_name, "/dev/nfs") == 0) + return Root_NFS; + if (strcmp(root_device_name, "/dev/cifs") == 0) + return Root_CIFS; + if (strcmp(root_device_name, "/dev/ram") == 0) + return Root_RAM0; + + error = early_lookup_bdev(root_device_name, &dev); + if (error) { + if (error == -EINVAL && root_wait) { + pr_err("Disabling rootwait; root= is invalid.\n"); + root_wait = 0; + } + return 0; } -#endif + return dev; } /* @@ -616,32 +435,15 @@ void __init prepare_namespace(void) md_run_setup(); - if (saved_root_name[0]) { - root_device_name = saved_root_name; - if (!strncmp(root_device_name, "mtd", 3) || - !strncmp(root_device_name, "ubi", 3)) { - mount_block_root(root_device_name, root_mountflags); - goto out; - } - ROOT_DEV = name_to_dev_t(root_device_name); - if (strncmp(root_device_name, "/dev/", 5) == 0) - root_device_name += 5; - } + if (saved_root_name[0]) + ROOT_DEV = parse_root_device(saved_root_name); - if (initrd_load()) + if (initrd_load(saved_root_name)) goto out; - /* wait for any asynchronous scanning to complete */ - if ((ROOT_DEV == 0) && root_wait) { - printk(KERN_INFO "Waiting for root device %s...\n", - saved_root_name); - while (driver_probe_done() != 0 || - (ROOT_DEV = name_to_dev_t(saved_root_name)) == 0) - msleep(5); - async_synchronize_full(); - } - - mount_root(); + if (root_wait) + wait_for_root(saved_root_name); + mount_root(saved_root_name); out: devtmpfs_mount(); init_mount(".", "/", NULL, MS_MOVE, NULL); diff --git a/init/do_mounts.h b/init/do_mounts.h index 7a29ac3e427b..15e372b00ce7 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -10,8 +10,8 @@ #include <linux/root_dev.h> #include <linux/init_syscalls.h> -void mount_block_root(char *name, int flags); -void mount_root(void); +void mount_root_generic(char *name, char *pretty_name, int flags); +void mount_root(char *root_device_name); extern int root_mountflags; static inline __init int create_dev(char *name, dev_t dev) @@ -33,11 +33,11 @@ static inline int rd_load_image(char *from) { return 0; } #endif #ifdef CONFIG_BLK_DEV_INITRD - -bool __init initrd_load(void); - +bool __init initrd_load(char *root_device_name); #else - -static inline bool initrd_load(void) { return false; } +static inline bool initrd_load(char *root_device_name) +{ + return false; + } #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 34731241377d..425f4bcf4b77 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -83,7 +83,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new) return 0; } -static void __init handle_initrd(void) +static void __init handle_initrd(char *root_device_name) { struct subprocess_info *info; static char *argv[] = { "linuxrc", NULL, }; @@ -95,7 +95,8 @@ static void __init handle_initrd(void) real_root_dev = new_encode_dev(ROOT_DEV); create_dev("/dev/root.old", Root_RAM0); /* mount initrd on rootfs' /root */ - mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); + mount_root_generic("/dev/root.old", root_device_name, + root_mountflags & ~MS_RDONLY); init_mkdir("/old", 0700); init_chdir("/old"); @@ -117,7 +118,7 @@ static void __init handle_initrd(void) init_chdir("/"); ROOT_DEV = new_decode_dev(real_root_dev); - mount_root(); + mount_root(root_device_name); printk(KERN_NOTICE "Trying to move old root to /initrd ... "); error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); @@ -133,7 +134,7 @@ static void __init handle_initrd(void) } } -bool __init initrd_load(void) +bool __init initrd_load(char *root_device_name) { if (mount_initrd) { create_dev("/dev/ram", Root_RAM0); @@ -145,7 +146,7 @@ bool __init initrd_load(void) */ if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) { init_unlink("/initrd.image"); - handle_initrd(); + handle_initrd(root_device_name); return true; } } diff --git a/init/main.c b/init/main.c index af50044deed5..32c65f28d84a 100644 --- a/init/main.c +++ b/init/main.c @@ -95,7 +95,6 @@ #include <linux/cache.h> #include <linux/rodata_test.h> #include <linux/jump_label.h> -#include <linux/mem_encrypt.h> #include <linux/kcsan.h> #include <linux/init_syscalls.h> #include <linux/stackdepot.h> @@ -103,7 +102,6 @@ #include <net/net_namespace.h> #include <asm/io.h> -#include <asm/bugs.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -787,8 +785,6 @@ void __init __weak thread_stack_cache_init(void) } #endif -void __init __weak mem_encrypt_init(void) { } - void __init __weak poking_init(void) { } void __init __weak pgtable_cache_init(void) { } @@ -1042,15 +1038,7 @@ asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(v sched_clock_init(); calibrate_delay(); - /* - * This needs to be called before any devices perform DMA - * operations that might use the SWIOTLB bounce buffers. It will - * mark the bounce buffers as decrypted so that their usage will - * not cause "plain-text" data to be decrypted when accessed. It - * must be called after late_time_init() so that Hyper-V x86/x64 - * hypercalls work when the SWIOTLB bounce buffers are decrypted. - */ - mem_encrypt_init(); + arch_cpu_finalize_init(); pid_idr_init(); anon_vma_init(); @@ -1078,8 +1066,6 @@ asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(v taskstats_init_early(); delayacct_init(); - check_bugs(); - acpi_subsystem_init(); arch_post_acpi_subsys_init(); kcsan_init(); diff --git a/io_uring/cancel.c b/io_uring/cancel.c index b4f5dfacc0c3..58c46c852bdd 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -216,13 +216,10 @@ static int __io_sync_cancel(struct io_uring_task *tctx, /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { - unsigned long file_ptr; - if (unlikely(fd >= ctx->nr_user_files)) return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; - cd->file = (struct file *) (file_ptr & FFS_MASK); + cd->file = io_file_from_index(&ctx->file_table, fd); if (!cd->file) return -EBADF; } diff --git a/io_uring/filetable.c b/io_uring/filetable.c index 0f6fa791a47d..e7d749991de4 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -78,10 +78,8 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); if (file_slot->file_ptr) { - struct file *old_file; - - old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); - ret = io_queue_rsrc_removal(ctx->file_data, slot_index, old_file); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + io_slot_file(file_slot)); if (ret) return ret; @@ -140,7 +138,6 @@ int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags, int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) { struct io_fixed_file *file_slot; - struct file *file; int ret; if (unlikely(!ctx->file_data)) @@ -153,8 +150,8 @@ int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset) if (!file_slot->file_ptr) return -EBADF; - file = (struct file *)(file_slot->file_ptr & FFS_MASK); - ret = io_queue_rsrc_removal(ctx->file_data, offset, file); + ret = io_queue_rsrc_removal(ctx->file_data, offset, + io_slot_file(file_slot)); if (ret) return ret; diff --git a/io_uring/filetable.h b/io_uring/filetable.h index 351111ff8882..b47adf170c31 100644 --- a/io_uring/filetable.h +++ b/io_uring/filetable.h @@ -5,10 +5,6 @@ #include <linux/file.h> #include <linux/io_uring_types.h> -#define FFS_NOWAIT 0x1UL -#define FFS_ISREG 0x2UL -#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) - bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files); void io_free_file_tables(struct io_file_table *table); @@ -43,21 +39,31 @@ io_fixed_file_slot(struct io_file_table *table, unsigned i) return &table->files[i]; } +#define FFS_NOWAIT 0x1UL +#define FFS_ISREG 0x2UL +#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) + +static inline unsigned int io_slot_flags(struct io_fixed_file *slot) +{ + return (slot->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT; +} + +static inline struct file *io_slot_file(struct io_fixed_file *slot) +{ + return (struct file *)(slot->file_ptr & FFS_MASK); +} + static inline struct file *io_file_from_index(struct io_file_table *table, int index) { - struct io_fixed_file *slot = io_fixed_file_slot(table, index); - - return (struct file *) (slot->file_ptr & FFS_MASK); + return io_slot_file(io_fixed_file_slot(table, index)); } static inline void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) { - unsigned long file_ptr = (unsigned long) file; - - file_ptr |= io_file_get_flags(file); - file_slot->file_ptr = file_ptr; + file_slot->file_ptr = (unsigned long)file | + (io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT); } static inline void io_reset_alloc_hint(struct io_ring_ctx *ctx) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index b2715988791e..399e9a15c38d 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -220,10 +220,12 @@ static void io_worker_exit(struct io_worker *worker) list_del_rcu(&worker->all_list); raw_spin_unlock(&wq->lock); io_wq_dec_running(worker); - worker->flags = 0; - preempt_disable(); - current->flags &= ~PF_IO_WORKER; - preempt_enable(); + /* + * this worker is a goner, clear ->worker_private to avoid any + * inc/dec running calls that could happen as part of exit from + * touching 'worker'. + */ + current->worker_private = NULL; kfree_rcu(worker, rcu); io_worker_ref_put(wq); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 3bca7a79efda..1b53a2ab0a27 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -95,6 +95,7 @@ #include "timeout.h" #include "poll.h" +#include "rw.h" #include "alloc_cache.h" #define IORING_MAX_ENTRIES 32768 @@ -145,8 +146,6 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all); -static void io_dismantle_req(struct io_kiocb *req); -static void io_clean_op(struct io_kiocb *req); static void io_queue_sqe(struct io_kiocb *req); static void io_move_task_work_from_local(struct io_ring_ctx *ctx); static void __io_submit_flush_completions(struct io_ring_ctx *ctx); @@ -367,6 +366,39 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } +static void io_clean_op(struct io_kiocb *req) +{ + if (req->flags & REQ_F_BUFFER_SELECTED) { + spin_lock(&req->ctx->completion_lock); + io_put_kbuf_comp(req); + spin_unlock(&req->ctx->completion_lock); + } + + if (req->flags & REQ_F_NEED_CLEANUP) { + const struct io_cold_def *def = &io_cold_defs[req->opcode]; + + if (def->cleanup) + def->cleanup(req); + } + if ((req->flags & REQ_F_POLLED) && req->apoll) { + kfree(req->apoll->double_poll); + kfree(req->apoll); + req->apoll = NULL; + } + if (req->flags & REQ_F_INFLIGHT) { + struct io_uring_task *tctx = req->task->io_uring; + + atomic_dec(&tctx->inflight_tracked); + } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + if (req->flags & REQ_F_ASYNC_DATA) { + kfree(req->async_data); + req->async_data = NULL; + } + req->flags &= ~IO_REQ_CLEAN_FLAGS; +} + static inline void io_req_track_inflight(struct io_kiocb *req) { if (!(req->flags & REQ_F_INFLIGHT)) { @@ -423,8 +455,8 @@ static void io_prep_async_work(struct io_kiocb *req) if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; - if (req->file && !io_req_ffs_set(req)) - req->flags |= io_file_get_flags(req->file) << REQ_F_SUPPORT_NOWAIT_BIT; + if (req->file && !(req->flags & REQ_F_FIXED_FILE)) + req->flags |= io_file_get_flags(req->file); if (req->file && (req->flags & REQ_F_ISREG)) { bool should_hash = def->hash_reg_file; @@ -594,42 +626,18 @@ void __io_commit_cqring_flush(struct io_ring_ctx *ctx) } static inline void __io_cq_lock(struct io_ring_ctx *ctx) - __acquires(ctx->completion_lock) { if (!ctx->task_complete) spin_lock(&ctx->completion_lock); } -static inline void __io_cq_unlock(struct io_ring_ctx *ctx) -{ - if (!ctx->task_complete) - spin_unlock(&ctx->completion_lock); -} - static inline void io_cq_lock(struct io_ring_ctx *ctx) __acquires(ctx->completion_lock) { spin_lock(&ctx->completion_lock); } -static inline void io_cq_unlock(struct io_ring_ctx *ctx) - __releases(ctx->completion_lock) -{ - spin_unlock(&ctx->completion_lock); -} - -/* keep it inlined for io_submit_flush_completions() */ static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx) - __releases(ctx->completion_lock) -{ - io_commit_cqring(ctx); - __io_cq_unlock(ctx); - io_commit_cqring_flush(ctx); - io_cqring_wake(ctx); -} - -static void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx) - __releases(ctx->completion_lock) { io_commit_cqring(ctx); @@ -641,13 +649,13 @@ static void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx) */ io_commit_cqring_flush(ctx); } else { - __io_cq_unlock(ctx); + spin_unlock(&ctx->completion_lock); io_commit_cqring_flush(ctx); io_cqring_wake(ctx); } } -void io_cq_unlock_post(struct io_ring_ctx *ctx) +static void io_cq_unlock_post(struct io_ring_ctx *ctx) __releases(ctx->completion_lock) { io_commit_cqring(ctx); @@ -662,10 +670,10 @@ static void io_cqring_overflow_kill(struct io_ring_ctx *ctx) struct io_overflow_cqe *ocqe; LIST_HEAD(list); - io_cq_lock(ctx); + spin_lock(&ctx->completion_lock); list_splice_init(&ctx->cq_overflow_list, &list); clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq); - io_cq_unlock(ctx); + spin_unlock(&ctx->completion_lock); while (!list_empty(&list)) { ocqe = list_first_entry(&list, struct io_overflow_cqe, list); @@ -722,29 +730,29 @@ static void io_cqring_overflow_flush(struct io_ring_ctx *ctx) } /* can be called by any task */ -static void io_put_task_remote(struct task_struct *task, int nr) +static void io_put_task_remote(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; - percpu_counter_sub(&tctx->inflight, nr); + percpu_counter_sub(&tctx->inflight, 1); if (unlikely(atomic_read(&tctx->in_cancel))) wake_up(&tctx->wait); - put_task_struct_many(task, nr); + put_task_struct(task); } /* used by a task to put its own references */ -static void io_put_task_local(struct task_struct *task, int nr) +static void io_put_task_local(struct task_struct *task) { - task->io_uring->cached_refs += nr; + task->io_uring->cached_refs++; } /* must to be called somewhat shortly after putting a request */ -static inline void io_put_task(struct task_struct *task, int nr) +static inline void io_put_task(struct task_struct *task) { if (likely(task == current)) - io_put_task_local(task, nr); + io_put_task_local(task); else - io_put_task_remote(task, nr); + io_put_task_remote(task); } void io_task_refs_refill(struct io_uring_task *tctx) @@ -934,20 +942,19 @@ bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags return __io_post_aux_cqe(ctx, user_data, res, cflags, true); } -bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags, +bool io_aux_cqe(const struct io_kiocb *req, bool defer, s32 res, u32 cflags, bool allow_overflow) { + struct io_ring_ctx *ctx = req->ctx; + u64 user_data = req->cqe.user_data; struct io_uring_cqe *cqe; - unsigned int length; if (!defer) return __io_post_aux_cqe(ctx, user_data, res, cflags, allow_overflow); - length = ARRAY_SIZE(ctx->submit_state.cqes); - lockdep_assert_held(&ctx->uring_lock); - if (ctx->submit_state.cqes_count == length) { + if (ctx->submit_state.cqes_count == ARRAY_SIZE(ctx->submit_state.cqes)) { __io_cq_lock(ctx); __io_flush_post_cqes(ctx); /* no need to flush - flush is deferred */ @@ -991,14 +998,18 @@ static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags) } } io_put_kbuf_comp(req); - io_dismantle_req(req); + if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS)) + io_clean_op(req); + if (!(req->flags & REQ_F_FIXED_FILE)) + io_put_file(req->file); + rsrc_node = req->rsrc_node; /* * Selected buffer deallocation in io_clean_op() assumes that * we don't hold ->completion_lock. Clean them here to avoid * deadlocks. */ - io_put_task_remote(req->task, 1); + io_put_task_remote(req->task); wq_list_add_head(&req->comp_list, &ctx->locked_free_list); ctx->locked_free_nr++; } @@ -1111,36 +1122,13 @@ __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) return true; } -static inline void io_dismantle_req(struct io_kiocb *req) -{ - unsigned int flags = req->flags; - - if (unlikely(flags & IO_REQ_CLEAN_FLAGS)) - io_clean_op(req); - if (!(flags & REQ_F_FIXED_FILE)) - io_put_file(req->file); -} - -static __cold void io_free_req_tw(struct io_kiocb *req, struct io_tw_state *ts) -{ - struct io_ring_ctx *ctx = req->ctx; - - if (req->rsrc_node) { - io_tw_lock(ctx, ts); - io_put_rsrc_node(ctx, req->rsrc_node); - } - io_dismantle_req(req); - io_put_task_remote(req->task, 1); - - spin_lock(&ctx->completion_lock); - wq_list_add_head(&req->comp_list, &ctx->locked_free_list); - ctx->locked_free_nr++; - spin_unlock(&ctx->completion_lock); -} - __cold void io_free_req(struct io_kiocb *req) { - req->io_task_work.func = io_free_req_tw; + /* refs were already put, restore them for io_req_task_complete() */ + req->flags &= ~REQ_F_REFCOUNT; + /* we only want to free it, don't post CQEs */ + req->flags |= REQ_F_CQE_SKIP; + req->io_task_work.func = io_req_task_complete; io_req_task_work_add(req); } @@ -1205,7 +1193,9 @@ static unsigned int handle_tw_list(struct llist_node *node, ts->locked = mutex_trylock(&(*ctx)->uring_lock); percpu_ref_get(&(*ctx)->refs); } - req->io_task_work.func(req, ts); + INDIRECT_CALL_2(req->io_task_work.func, + io_poll_task_func, io_req_rw_complete, + req, ts); node = next; count++; if (unlikely(need_resched())) { @@ -1303,7 +1293,7 @@ static __cold void io_fallback_tw(struct io_uring_task *tctx) } } -static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) +static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags) { struct io_ring_ctx *ctx = req->ctx; unsigned nr_wait, nr_tw, nr_tw_prev; @@ -1354,19 +1344,11 @@ static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE); } -void __io_req_task_work_add(struct io_kiocb *req, unsigned flags) +static void io_req_normal_work_add(struct io_kiocb *req) { struct io_uring_task *tctx = req->task->io_uring; struct io_ring_ctx *ctx = req->ctx; - if (!(flags & IOU_F_TWQ_FORCE_NORMAL) && - (ctx->flags & IORING_SETUP_DEFER_TASKRUN)) { - rcu_read_lock(); - io_req_local_work_add(req, flags); - rcu_read_unlock(); - return; - } - /* task_work already pending, we're done */ if (!llist_add(&req->io_task_work.node, &tctx->task_list)) return; @@ -1380,6 +1362,17 @@ void __io_req_task_work_add(struct io_kiocb *req, unsigned flags) io_fallback_tw(tctx); } +void __io_req_task_work_add(struct io_kiocb *req, unsigned flags) +{ + if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN) { + rcu_read_lock(); + io_req_local_work_add(req, flags); + rcu_read_unlock(); + } else { + io_req_normal_work_add(req); + } +} + static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx) { struct llist_node *node; @@ -1390,7 +1383,7 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx) io_task_work.node); node = node->next; - __io_req_task_work_add(req, IOU_F_TWQ_FORCE_NORMAL); + io_req_normal_work_add(req); } } @@ -1405,13 +1398,19 @@ static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts) if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags); again: - node = io_llist_xchg(&ctx->work_llist, NULL); + /* + * llists are in reverse order, flip it back the right way before + * running the pending items. + */ + node = llist_reverse_order(io_llist_xchg(&ctx->work_llist, NULL)); while (node) { struct llist_node *next = node->next; struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); prefetch(container_of(next, struct io_kiocb, io_task_work.node)); - req->io_task_work.func(req, ts); + INDIRECT_CALL_2(req->io_task_work.func, + io_poll_task_func, io_req_rw_complete, + req, ts); ret++; node = next; } @@ -1498,9 +1497,6 @@ void io_queue_next(struct io_kiocb *req) void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) __must_hold(&ctx->uring_lock) { - struct task_struct *task = NULL; - int task_refs = 0; - do { struct io_kiocb *req = container_of(node, struct io_kiocb, comp_list); @@ -1530,19 +1526,10 @@ void io_free_batch_list(struct io_ring_ctx *ctx, struct io_wq_work_node *node) io_req_put_rsrc_locked(req, ctx); - if (req->task != task) { - if (task) - io_put_task(task, task_refs); - task = req->task; - task_refs = 0; - } - task_refs++; + io_put_task(req->task); node = req->comp_list.next; io_req_add_to_cache(req, ctx); } while (node); - - if (task) - io_put_task(task, task_refs); } static void __io_submit_flush_completions(struct io_ring_ctx *ctx) @@ -1570,7 +1557,7 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) } } } - __io_cq_unlock_post_flush(ctx); + __io_cq_unlock_post(ctx); if (!wq_list_empty(&ctx->submit_state.compl_reqs)) { io_free_batch_list(ctx, state->compl_reqs.first); @@ -1578,22 +1565,6 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) } } -/* - * Drop reference to request, return next in chain (if there is one) if this - * was the last reference to this request. - */ -static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) -{ - struct io_kiocb *nxt = NULL; - - if (req_ref_put_and_test(req)) { - if (unlikely(req->flags & IO_REQ_LINK_FLAGS)) - nxt = io_req_find_next(req); - io_free_req(req); - } - return nxt; -} - static unsigned io_cqring_events(struct io_ring_ctx *ctx) { /* See comment at the top of this file */ @@ -1758,54 +1729,14 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) } } -static bool io_bdev_nowait(struct block_device *bdev) -{ - return !bdev || bdev_nowait(bdev); -} - -/* - * If we tracked the file through the SCM inflight mechanism, we could support - * any file. For now, just ensure that anything potentially problematic is done - * inline. - */ -static bool __io_file_supports_nowait(struct file *file, umode_t mode) -{ - if (S_ISBLK(mode)) { - if (IS_ENABLED(CONFIG_BLOCK) && - io_bdev_nowait(I_BDEV(file->f_mapping->host))) - return true; - return false; - } - if (S_ISSOCK(mode)) - return true; - if (S_ISREG(mode)) { - if (IS_ENABLED(CONFIG_BLOCK) && - io_bdev_nowait(file->f_inode->i_sb->s_bdev) && - !io_is_uring_fops(file)) - return true; - return false; - } - - /* any ->read/write should understand O_NONBLOCK */ - if (file->f_flags & O_NONBLOCK) - return true; - return file->f_mode & FMODE_NOWAIT; -} - -/* - * If we tracked the file through the SCM inflight mechanism, we could support - * any file. For now, just ensure that anything potentially problematic is done - * inline. - */ unsigned int io_file_get_flags(struct file *file) { - umode_t mode = file_inode(file)->i_mode; unsigned int res = 0; - if (S_ISREG(mode)) - res |= FFS_ISREG; - if (__io_file_supports_nowait(file, mode)) - res |= FFS_NOWAIT; + if (S_ISREG(file_inode(file)->i_mode)) + res |= REQ_F_ISREG; + if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT)) + res |= REQ_F_SUPPORT_NOWAIT; return res; } @@ -1891,39 +1822,6 @@ queue: spin_unlock(&ctx->completion_lock); } -static void io_clean_op(struct io_kiocb *req) -{ - if (req->flags & REQ_F_BUFFER_SELECTED) { - spin_lock(&req->ctx->completion_lock); - io_put_kbuf_comp(req); - spin_unlock(&req->ctx->completion_lock); - } - - if (req->flags & REQ_F_NEED_CLEANUP) { - const struct io_cold_def *def = &io_cold_defs[req->opcode]; - - if (def->cleanup) - def->cleanup(req); - } - if ((req->flags & REQ_F_POLLED) && req->apoll) { - kfree(req->apoll->double_poll); - kfree(req->apoll); - req->apoll = NULL; - } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } - if (req->flags & REQ_F_CREDS) - put_cred(req->creds); - if (req->flags & REQ_F_ASYNC_DATA) { - kfree(req->async_data); - req->async_data = NULL; - } - req->flags &= ~IO_REQ_CLEAN_FLAGS; -} - static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def, unsigned int issue_flags) { @@ -1986,9 +1884,14 @@ int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts) struct io_wq_work *io_wq_free_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + struct io_kiocb *nxt = NULL; - req = io_put_req_find_next(req); - return req ? &req->work : NULL; + if (req_ref_put_and_test(req)) { + if (req->flags & IO_REQ_LINK_FLAGS) + nxt = io_req_find_next(req); + io_free_req(req); + } + return nxt ? &nxt->work : NULL; } void io_wq_submit_work(struct io_wq_work *work) @@ -2060,19 +1963,17 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *slot; struct file *file = NULL; - unsigned long file_ptr; io_ring_submit_lock(ctx, issue_flags); if (unlikely((unsigned int)fd >= ctx->nr_user_files)) goto out; fd = array_index_nospec(fd, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; - file = (struct file *) (file_ptr & FFS_MASK); - file_ptr &= ~FFS_MASK; - /* mask in overlapping REQ_F and FFS bits */ - req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); + slot = io_fixed_file_slot(&ctx->file_table, fd); + file = io_slot_file(slot); + req->flags |= io_slot_flags(slot); io_req_set_rsrc_node(req, ctx, 0); out: io_ring_submit_unlock(ctx, issue_flags); @@ -2709,11 +2610,96 @@ static void io_mem_free(void *ptr) free_compound_page(page); } +static void io_pages_free(struct page ***pages, int npages) +{ + struct page **page_array; + int i; + + if (!pages) + return; + page_array = *pages; + for (i = 0; i < npages; i++) + unpin_user_page(page_array[i]); + kvfree(page_array); + *pages = NULL; +} + +static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, + unsigned long uaddr, size_t size) +{ + struct page **page_array; + unsigned int nr_pages; + int ret; + + *npages = 0; + + if (uaddr & (PAGE_SIZE - 1) || !size) + return ERR_PTR(-EINVAL); + + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (nr_pages > USHRT_MAX) + return ERR_PTR(-EINVAL); + page_array = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); + if (!page_array) + return ERR_PTR(-ENOMEM); + + ret = pin_user_pages_fast(uaddr, nr_pages, FOLL_WRITE | FOLL_LONGTERM, + page_array); + if (ret != nr_pages) { +err: + io_pages_free(&page_array, ret > 0 ? ret : 0); + return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT); + } + /* + * Should be a single page. If the ring is small enough that we can + * use a normal page, that is fine. If we need multiple pages, then + * userspace should use a huge page. That's the only way to guarantee + * that we get contigious memory, outside of just being lucky or + * (currently) having low memory fragmentation. + */ + if (page_array[0] != page_array[ret - 1]) + goto err; + *pages = page_array; + *npages = nr_pages; + return page_to_virt(page_array[0]); +} + +static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr, + size_t size) +{ + return __io_uaddr_map(&ctx->ring_pages, &ctx->n_ring_pages, uaddr, + size); +} + +static void *io_sqes_map(struct io_ring_ctx *ctx, unsigned long uaddr, + size_t size) +{ + return __io_uaddr_map(&ctx->sqe_pages, &ctx->n_sqe_pages, uaddr, + size); +} + +static void io_rings_free(struct io_ring_ctx *ctx) +{ + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) { + io_mem_free(ctx->rings); + io_mem_free(ctx->sq_sqes); + ctx->rings = NULL; + ctx->sq_sqes = NULL; + } else { + io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); + io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); + } +} + static void *io_mem_alloc(size_t size) { gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; + void *ret; - return (void *) __get_free_pages(gfp, get_order(size)); + ret = (void *) __get_free_pages(gfp, get_order(size)); + if (ret) + return ret; + return ERR_PTR(-ENOMEM); } static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries, @@ -2869,8 +2855,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) mmdrop(ctx->mm_account); ctx->mm_account = NULL; } - io_mem_free(ctx->rings); - io_mem_free(ctx->sq_sqes); + io_rings_free(ctx); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); @@ -3050,7 +3035,18 @@ static __cold void io_ring_exit_work(struct work_struct *work) /* there is little hope left, don't run it too often */ interval = HZ * 60; } - } while (!wait_for_completion_timeout(&ctx->ref_comp, interval)); + /* + * This is really an uninterruptible wait, as it has to be + * complete. But it's also run from a kworker, which doesn't + * take signals, so it's fine to make it interruptible. This + * avoids scenarios where we knowingly can wait much longer + * on completions, for example if someone does a SIGSTOP on + * a task that needs to finish task_work to make this loop + * complete. That's a synthetic situation that should not + * cause a stuck task backtrace, and hence a potential panic + * on stuck tasks if that is enabled. + */ + } while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval)); init_completion(&exit.completion); init_task_work(&exit.task_work, io_tctx_exit_cb); @@ -3074,7 +3070,12 @@ static __cold void io_ring_exit_work(struct work_struct *work) continue; mutex_unlock(&ctx->uring_lock); - wait_for_completion(&exit.completion); + /* + * See comment above for + * wait_for_completion_interruptible_timeout() on why this + * wait is marked as interruptible. + */ + wait_for_completion_interruptible(&exit.completion); mutex_lock(&ctx->uring_lock); } mutex_unlock(&ctx->uring_lock); @@ -3348,6 +3349,10 @@ static void *io_uring_validate_mmap_request(struct file *file, struct page *page; void *ptr; + /* Don't allow mmap if the ring was setup without it */ + if (ctx->flags & IORING_SETUP_NO_MMAP) + return ERR_PTR(-EINVAL); + switch (offset & IORING_OFF_MMAP_MASK) { case IORING_OFF_SQ_RING: case IORING_OFF_CQ_RING: @@ -3673,6 +3678,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, { struct io_rings *rings; size_t size, sq_array_offset; + void *ptr; /* make sure these are sane, as we already accounted them */ ctx->sq_entries = p->sq_entries; @@ -3682,9 +3688,13 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, if (size == SIZE_MAX) return -EOVERFLOW; - rings = io_mem_alloc(size); - if (!rings) - return -ENOMEM; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + rings = io_mem_alloc(size); + else + rings = io_rings_map(ctx, p->cq_off.user_addr, size); + + if (IS_ERR(rings)) + return PTR_ERR(rings); ctx->rings = rings; ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); @@ -3698,34 +3708,31 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, else size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { - io_mem_free(ctx->rings); - ctx->rings = NULL; + io_rings_free(ctx); return -EOVERFLOW; } - ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) { - io_mem_free(ctx->rings); - ctx->rings = NULL; - return -ENOMEM; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + ptr = io_mem_alloc(size); + else + ptr = io_sqes_map(ctx, p->sq_off.user_addr, size); + + if (IS_ERR(ptr)) { + io_rings_free(ctx); + return PTR_ERR(ptr); } + ctx->sq_sqes = ptr; return 0; } -static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) +static int io_uring_install_fd(struct file *file) { - int ret, fd; + int fd; fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (fd < 0) return fd; - - ret = __io_uring_add_tctx_node(ctx); - if (ret) { - put_unused_fd(fd); - return ret; - } fd_install(fd, file); return fd; } @@ -3765,6 +3772,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, struct io_uring_params __user *params) { struct io_ring_ctx *ctx; + struct io_uring_task *tctx; struct file *file; int ret; @@ -3776,6 +3784,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, entries = IORING_MAX_ENTRIES; } + if ((p->flags & IORING_SETUP_REGISTERED_FD_ONLY) + && !(p->flags & IORING_SETUP_NO_MMAP)) + return -EINVAL; + /* * Use twice as many entries for the CQ ring. It's possible for the * application to drive a higher depth than the size of the SQ ring, @@ -3887,7 +3899,6 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, if (ret) goto err; - memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); p->sq_off.tail = offsetof(struct io_rings, sq.tail); p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask); @@ -3895,8 +3906,10 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, p->sq_off.flags = offsetof(struct io_rings, sq_flags); p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; + p->sq_off.resv1 = 0; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + p->sq_off.user_addr = 0; - memset(&p->cq_off, 0, sizeof(p->cq_off)); p->cq_off.head = offsetof(struct io_rings, cq.head); p->cq_off.tail = offsetof(struct io_rings, cq.tail); p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask); @@ -3904,6 +3917,9 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); p->cq_off.flags = offsetof(struct io_rings, cq_flags); + p->cq_off.resv1 = 0; + if (!(ctx->flags & IORING_SETUP_NO_MMAP)) + p->cq_off.user_addr = 0; p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | @@ -3928,22 +3944,30 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, goto err; } + ret = __io_uring_add_tctx_node(ctx); + if (ret) + goto err_fput; + tctx = current->io_uring; + /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup */ - ret = io_uring_install_fd(ctx, file); - if (ret < 0) { - /* fput will clean it up */ - fput(file); - return ret; - } + if (p->flags & IORING_SETUP_REGISTERED_FD_ONLY) + ret = io_ring_add_registered_file(tctx, file, 0, IO_RINGFD_REG_MAX); + else + ret = io_uring_install_fd(file); + if (ret < 0) + goto err_fput; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: io_ring_ctx_wait_and_kill(ctx); return ret; +err_fput: + fput(file); + return ret; } /* @@ -3969,7 +3993,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL | IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG | IORING_SETUP_SQE128 | IORING_SETUP_CQE32 | - IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN)) + IORING_SETUP_SINGLE_ISSUER | IORING_SETUP_DEFER_TASKRUN | + IORING_SETUP_NO_MMAP | IORING_SETUP_REGISTERED_FD_ONLY)) return -EINVAL; return io_uring_create(entries, &p, params); diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 259bf798a390..d3606d30cf6f 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -16,9 +16,6 @@ #endif enum { - /* don't use deferred task_work */ - IOU_F_TWQ_FORCE_NORMAL = 1, - /* * A hint to not wake right away but delay until there are enough of * tw's queued to match the number of CQEs the task is waiting for. @@ -26,7 +23,7 @@ enum { * Must not be used wirh requests generating more than one CQE. * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. */ - IOU_F_TWQ_LAZY_WAKE = 2, + IOU_F_TWQ_LAZY_WAKE = 1, }; enum { @@ -47,7 +44,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx); void io_req_defer_failed(struct io_kiocb *req, s32 res); void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags); bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags); -bool io_aux_cqe(struct io_ring_ctx *ctx, bool defer, u64 user_data, s32 res, u32 cflags, +bool io_aux_cqe(const struct io_kiocb *req, bool defer, s32 res, u32 cflags, bool allow_overflow); void __io_commit_cqring_flush(struct io_ring_ctx *ctx); @@ -57,11 +54,6 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd); struct file *io_file_get_fixed(struct io_kiocb *req, int fd, unsigned issue_flags); -static inline bool io_req_ffs_set(struct io_kiocb *req) -{ - return req->flags & REQ_F_FIXED_FILE; -} - void __io_req_task_work_add(struct io_kiocb *req, unsigned flags); bool io_is_uring_fops(struct file *file); bool io_alloc_async_data(struct io_kiocb *req); @@ -75,6 +67,9 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); +int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, + int start, int end); + int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts); int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr); int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin); @@ -115,8 +110,6 @@ static inline void io_req_task_work_add(struct io_kiocb *req) #define io_for_each_link(pos, head) \ for (pos = (head); pos; pos = pos->link) -void io_cq_unlock_post(struct io_ring_ctx *ctx); - static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx, bool overflow) { diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 85fd7ce5f05b..cd6dcf634ba3 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -162,14 +162,12 @@ static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_fl struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); struct io_ring_ctx *ctx = req->ctx; struct file *file = NULL; - unsigned long file_ptr; int idx = msg->src_fd; io_ring_submit_lock(ctx, issue_flags); if (likely(idx < ctx->nr_user_files)) { idx = array_index_nospec(idx, ctx->nr_user_files); - file_ptr = io_fixed_file_slot(&ctx->file_table, idx)->file_ptr; - file = (struct file *) (file_ptr & FFS_MASK); + file = io_file_from_index(&ctx->file_table, idx); if (file) get_file(file); } diff --git a/io_uring/net.c b/io_uring/net.c index 89e839013837..a8e303796f16 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -65,6 +65,7 @@ struct io_sr_msg { u16 addr_len; u16 buf_group; void __user *addr; + void __user *msg_control; /* used only for send zerocopy */ struct io_kiocb *notif; }; @@ -195,11 +196,15 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + int ret; iomsg->msg.msg_name = &iomsg->addr; iomsg->free_iov = iomsg->fast_iov; - return sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, + ret = sendmsg_copy_msghdr(&iomsg->msg, sr->umsg, sr->msg_flags, &iomsg->free_iov); + /* save msg_control as sys_sendmsg() overwrites it */ + sr->msg_control = iomsg->msg.msg_control_user; + return ret; } int io_send_prep_async(struct io_kiocb *req) @@ -297,6 +302,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) if (req_has_async_data(req)) { kmsg = req->async_data; + kmsg->msg.msg_control_user = sr->msg_control; } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) @@ -320,6 +326,8 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) return io_setup_async_msg(req, kmsg, issue_flags); if (ret > 0 && io_net_retry(sock, flags)) { + kmsg->msg.msg_controllen = 0; + kmsg->msg.msg_control = NULL; sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg, issue_flags); @@ -616,9 +624,15 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) * again (for multishot). */ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, - unsigned int cflags, bool mshot_finished, + struct msghdr *msg, bool mshot_finished, unsigned issue_flags) { + unsigned int cflags; + + cflags = io_put_kbuf(req, issue_flags); + if (msg->msg_inq && msg->msg_inq != -1U) + cflags |= IORING_CQE_F_SOCK_NONEMPTY; + if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { io_req_set_res(req, *ret, cflags); *ret = IOU_OK; @@ -626,10 +640,18 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, } if (!mshot_finished) { - if (io_aux_cqe(req->ctx, issue_flags & IO_URING_F_COMPLETE_DEFER, - req->cqe.user_data, *ret, cflags | IORING_CQE_F_MORE, true)) { + if (io_aux_cqe(req, issue_flags & IO_URING_F_COMPLETE_DEFER, + *ret, cflags | IORING_CQE_F_MORE, true)) { io_recv_prep_retry(req); - return false; + /* Known not-empty or unknown state, retry */ + if (cflags & IORING_CQE_F_SOCK_NONEMPTY || + msg->msg_inq == -1U) + return false; + if (issue_flags & IO_URING_F_MULTISHOT) + *ret = IOU_ISSUE_SKIP_COMPLETE; + else + *ret = -EAGAIN; + return true; } /* Otherwise stop multishot but use the current result. */ } @@ -732,7 +754,6 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct io_async_msghdr iomsg, *kmsg; struct socket *sock; - unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -781,16 +802,20 @@ retry_multishot: flags = sr->msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; - if (flags & MSG_WAITALL) - min_ret = iov_iter_count(&kmsg->msg.msg_iter); kmsg->msg.msg_get_inq = 1; - if (req->flags & REQ_F_APOLL_MULTISHOT) + kmsg->msg.msg_inq = -1U; + if (req->flags & REQ_F_APOLL_MULTISHOT) { ret = io_recvmsg_multishot(sock, sr, kmsg, flags, &mshot_finished); - else + } else { + /* disable partial retry for recvmsg with cmsg attached */ + if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags); + } if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) { @@ -820,11 +845,7 @@ retry_multishot: else io_kbuf_recycle(req, issue_flags); - cflags = io_put_kbuf(req, issue_flags); - if (kmsg->msg.msg_inq) - cflags |= IORING_CQE_F_SOCK_NONEMPTY; - - if (!io_recv_finish(req, &ret, cflags, mshot_finished, issue_flags)) + if (!io_recv_finish(req, &ret, &kmsg->msg, mshot_finished, issue_flags)) goto retry_multishot; if (mshot_finished) { @@ -843,7 +864,6 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); struct msghdr msg; struct socket *sock; - unsigned int cflags; unsigned flags; int ret, min_ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -860,6 +880,14 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_control = NULL; + msg.msg_get_inq = 1; + msg.msg_controllen = 0; + msg.msg_iocb = NULL; + msg.msg_ubuf = NULL; + retry_multishot: if (io_do_buffer_select(req)) { void __user *buf; @@ -874,14 +902,8 @@ retry_multishot: if (unlikely(ret)) goto out_free; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = NULL; - msg.msg_get_inq = 1; + msg.msg_inq = -1U; msg.msg_flags = 0; - msg.msg_controllen = 0; - msg.msg_iocb = NULL; - msg.msg_ubuf = NULL; flags = sr->msg_flags; if (force_nonblock) @@ -921,11 +943,7 @@ out_free: else io_kbuf_recycle(req, issue_flags); - cflags = io_put_kbuf(req, issue_flags); - if (msg.msg_inq) - cflags |= IORING_CQE_F_SOCK_NONEMPTY; - - if (!io_recv_finish(req, &ret, cflags, ret <= 0, issue_flags)) + if (!io_recv_finish(req, &ret, &msg, ret <= 0, issue_flags)) goto retry_multishot; return ret; @@ -1297,7 +1315,6 @@ int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_accept(struct io_kiocb *req, unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; struct io_accept *accept = io_kiocb_to_cmd(req, struct io_accept); bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; @@ -1347,8 +1364,8 @@ retry: if (ret < 0) return ret; - if (io_aux_cqe(ctx, issue_flags & IO_URING_F_COMPLETE_DEFER, - req->cqe.user_data, ret, IORING_CQE_F_MORE, true)) + if (io_aux_cqe(req, issue_flags & IO_URING_F_COMPLETE_DEFER, ret, + IORING_CQE_F_MORE, true)) goto retry; return -ECANCELED; diff --git a/io_uring/poll.c b/io_uring/poll.c index c90e47dc1e29..d4597efe14a7 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -300,8 +300,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) __poll_t mask = mangle_poll(req->cqe.res & req->apoll_events); - if (!io_aux_cqe(req->ctx, ts->locked, req->cqe.user_data, - mask, IORING_CQE_F_MORE, false)) { + if (!io_aux_cqe(req, ts->locked, mask, + IORING_CQE_F_MORE, false)) { io_req_set_res(req, mask, 0); return IOU_POLL_REMOVE_POLL_USE_RES; } @@ -326,7 +326,7 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) return IOU_POLL_NO_ACTION; } -static void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) +void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) { int ret; @@ -977,8 +977,9 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) struct io_hash_bucket *bucket; struct io_kiocb *preq; int ret2, ret = 0; - struct io_tw_state ts = {}; + struct io_tw_state ts = { .locked = true }; + io_ring_submit_lock(ctx, issue_flags); preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket); ret2 = io_poll_disarm(preq); if (bucket) @@ -990,12 +991,10 @@ int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags) goto out; } - io_ring_submit_lock(ctx, issue_flags); preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table_locked, &bucket); ret2 = io_poll_disarm(preq); if (bucket) spin_unlock(&bucket->lock); - io_ring_submit_unlock(ctx, issue_flags); if (ret2) { ret = ret2; goto out; @@ -1019,7 +1018,7 @@ found: if (poll_update->update_user_data) preq->cqe.user_data = poll_update->new_user_data; - ret2 = io_poll_add(preq, issue_flags); + ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED); /* successfully updated, don't complete poll request */ if (!ret2 || ret2 == -EIOCBQUEUED) goto out; @@ -1027,9 +1026,9 @@ found: req_set_fail(preq); io_req_set_res(preq, -ECANCELED, 0); - ts.locked = !(issue_flags & IO_URING_F_UNLOCKED); io_req_task_complete(preq, &ts); out: + io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) { req_set_fail(req); return ret; diff --git a/io_uring/poll.h b/io_uring/poll.h index b2393b403a2c..ff4d5d753387 100644 --- a/io_uring/poll.h +++ b/io_uring/poll.h @@ -38,3 +38,5 @@ bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, bool cancel_all); void io_apoll_cache_free(struct io_cache_entry *entry); + +void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index d46f72a5ef73..a2dce7ef3a78 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -354,7 +354,6 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, __s32 __user *fds = u64_to_user_ptr(up->data); struct io_rsrc_data *data = ctx->file_data; struct io_fixed_file *file_slot; - struct file *file; int fd, i, err = 0; unsigned int done; @@ -382,15 +381,16 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, file_slot = io_fixed_file_slot(&ctx->file_table, i); if (file_slot->file_ptr) { - file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, i, file); + err = io_queue_rsrc_removal(data, i, + io_slot_file(file_slot)); if (err) break; file_slot->file_ptr = 0; io_file_bitmap_clear(&ctx->file_table, i); } if (fd != -1) { - file = fget(fd); + struct file *file = fget(fd); + if (!file) { err = -EBADF; break; diff --git a/io_uring/rw.c b/io_uring/rw.c index 3f118ed46e4f..1bce2208b65c 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -283,7 +283,7 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res) return res; } -static void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts) +void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts) { io_req_io_end(req); @@ -666,8 +666,8 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) if (unlikely(!file || !(file->f_mode & mode))) return -EBADF; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + if (!(req->flags & REQ_F_FIXED_FILE)) + req->flags |= io_file_get_flags(file); kiocb->ki_flags = file->f_iocb_flags; ret = kiocb_set_rw_flags(kiocb, rw->flags); diff --git a/io_uring/rw.h b/io_uring/rw.h index 3b733f4b610a..4b89f9659366 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -22,3 +22,4 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags); int io_writev_prep_async(struct io_kiocb *req); void io_readv_writev_cleanup(struct io_kiocb *req); void io_rw_fail(struct io_kiocb *req); +void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 3a8d1dd97e1b..c043fe93a3f2 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -208,31 +208,40 @@ void io_uring_unreg_ringfd(void) } } -static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, +int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file, int start, int end) { - struct file *file; int offset; - for (offset = start; offset < end; offset++) { offset = array_index_nospec(offset, IO_RINGFD_REG_MAX); if (tctx->registered_rings[offset]) continue; - file = fget(fd); - if (!file) { - return -EBADF; - } else if (!io_is_uring_fops(file)) { - fput(file); - return -EOPNOTSUPP; - } tctx->registered_rings[offset] = file; return offset; } - return -EBUSY; } +static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd, + int start, int end) +{ + struct file *file; + int offset; + + file = fget(fd); + if (!file) { + return -EBADF; + } else if (!io_is_uring_fops(file)) { + fput(file); + return -EOPNOTSUPP; + } + offset = io_ring_add_registered_file(tctx, file, start, end); + if (offset < 0) + fput(file); + return offset; +} + /* * Register a ring fd to avoid fdget/fdput for each io_uring_enter() * invocation. User passes in an array of struct io_uring_rsrc_update diff --git a/io_uring/timeout.c b/io_uring/timeout.c index fc950177e2e1..fb0547b35dcd 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -73,8 +73,8 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) if (!io_timeout_finish(timeout, data)) { bool filled; - filled = io_aux_cqe(ctx, ts->locked, req->cqe.user_data, -ETIME, - IORING_CQE_F_MORE, false); + filled = io_aux_cqe(req, ts->locked, -ETIME, IORING_CQE_F_MORE, + false); if (filled) { /* re-arm timer */ spin_lock_irq(&ctx->timeout_lock); @@ -594,7 +594,7 @@ int io_timeout(struct io_kiocb *req, unsigned int issue_flags) goto add; } - tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + tail = data_race(ctx->cached_cq_tail) - atomic_read(&ctx->cq_timeouts); timeout->target_seq = tail + off; /* Update the last seq here in case io_flush_timeouts() hasn't. diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 5e32db48696d..476c7877ce58 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -20,16 +20,24 @@ static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts) ioucmd->task_work_cb(ioucmd, issue_flags); } -void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned), + unsigned flags) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); ioucmd->task_work_cb = task_work_cb; req->io_task_work.func = io_uring_cmd_work; - io_req_task_work_add(req); + __io_req_task_work_add(req, flags); +} +EXPORT_SYMBOL_GPL(__io_uring_cmd_do_in_task); + +void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ + __io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE); } -EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task); +EXPORT_SYMBOL_GPL(io_uring_cmd_do_in_task_lazy); static inline void io_req_set_cqe32_extra(struct io_kiocb *req, u64 extra1, u64 extra2) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b682b8e4b50..72b32b7cd9cd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -744,13 +744,12 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset) return offset < btf->hdr.str_len; } -static bool __btf_name_char_ok(char c, bool first, bool dot_ok) +static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && - ((c == '.' && !dot_ok) || - c != '.')) + c != '.') return false; return true; } @@ -767,20 +766,20 @@ static const char *btf_str_by_offset(const struct btf *btf, u32 offset) return NULL; } -static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) +static bool __btf_name_valid(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit; - if (!__btf_name_char_ok(*src, true, dot_ok)) + if (!__btf_name_char_ok(*src, true)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { - if (!__btf_name_char_ok(*src, false, dot_ok)) + if (!__btf_name_char_ok(*src, false)) return false; src++; } @@ -788,17 +787,14 @@ static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok) return !*src; } -/* Only C-style identifier is permitted. This can be relaxed if - * necessary. - */ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, false); + return __btf_name_valid(btf, offset); } static bool btf_name_valid_section(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset, true); + return __btf_name_valid(btf, offset); } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) @@ -4422,7 +4418,7 @@ static s32 btf_var_check_meta(struct btf_verifier_env *env, } if (!t->name_off || - !__btf_name_valid(env->btf, t->name_off, true)) { + !__btf_name_valid(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0c21d0d8efe4..f1c8733f76b8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3440,6 +3440,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; + case BPF_PROG_TYPE_KPROBE: + if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && + attach_type != BPF_TRACE_KPROBE_MULTI) + return -EINVAL; + return 0; default: return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5871aa78d01a..cf5f230360f5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3868,6 +3868,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; } save_register_state(state, spi, reg, size); + /* Break the relation on a narrowing spill. */ + if (fls64(reg->umax_value) > BITS_PER_BYTE * size) + state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && insn->imm != 0 && env->bpf_capable) { struct bpf_reg_state fake_reg = {}; @@ -17214,9 +17217,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) } /* finally lock prog and jit images for all functions and - * populate kallsysm + * populate kallsysm. Begin at the first subprogram, since + * bpf_prog_load will add the kallsyms for the main program. */ - for (i = 0; i < env->subprog_cnt; i++) { + for (i = 1; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } @@ -17242,6 +17246,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; + prog->aux->extable = func[0]->aux->extable; + prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; bpf_prog_jit_attempt_done(prog); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 245cf62ce85a..4d42f0cbc11e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1798,7 +1798,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; - int ssid, i, ret; + int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); @@ -1842,7 +1842,8 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); - struct css_set *cset; + struct css_set *cset, *cset_pos; + struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); @@ -1860,9 +1861,22 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); - hash_for_each(css_set_table, i, cset, hlist) + WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); + list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], + e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); + /* + * all css_sets of scgrp together in same order to dcgrp, + * patch in-flight iterators to preserve correct iteration. + * since the iterator is always advanced right away and + * finished when it->cset_pos meets it->cset_head, so only + * update it->cset_head is enough here. + */ + list_for_each_entry(it, &cset->task_iters, iters_node) + if (it->cset_head == &scgrp->e_csets[ss->id]) + it->cset_head = &dcgrp->e_csets[ss->id]; + } spin_unlock_irq(&css_set_lock); if (ss->css_rstat_flush) { diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 936473203a6b..122dacb3a443 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -108,16 +108,18 @@ static int freezer_css_online(struct cgroup_subsys_state *css) struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer); + cpus_read_lock(); mutex_lock(&freezer_mutex); freezer->state |= CGROUP_FREEZER_ONLINE; if (parent && (parent->state & CGROUP_FREEZING)) { freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; - static_branch_inc(&freezer_active); + static_branch_inc_cpuslocked(&freezer_active); } mutex_unlock(&freezer_mutex); + cpus_read_unlock(); return 0; } @@ -132,14 +134,16 @@ static void freezer_css_offline(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); + cpus_read_lock(); mutex_lock(&freezer_mutex); if (freezer->state & CGROUP_FREEZING) - static_branch_dec(&freezer_active); + static_branch_dec_cpuslocked(&freezer_active); freezer->state = 0; mutex_unlock(&freezer_mutex); + cpus_read_unlock(); } static void freezer_css_free(struct cgroup_subsys_state *css) diff --git a/kernel/cpu.c b/kernel/cpu.c index f4a2c5845bcb..88a7ede322bd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> +#include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> @@ -59,6 +60,7 @@ * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation + * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ @@ -76,6 +78,7 @@ struct cpuhp_cpu_state { struct hlist_node *last; enum cpuhp_state cb_state; int result; + atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif @@ -276,6 +279,182 @@ static bool cpuhp_is_atomic_state(enum cpuhp_state state) return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } +/* Synchronization state management */ +enum cpuhp_sync_state { + SYNC_STATE_DEAD, + SYNC_STATE_KICKED, + SYNC_STATE_SHOULD_DIE, + SYNC_STATE_ALIVE, + SYNC_STATE_SHOULD_ONLINE, + SYNC_STATE_ONLINE, +}; + +#ifdef CONFIG_HOTPLUG_CORE_SYNC +/** + * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown + * @state: The synchronization state to set + * + * No synchronization point. Just update of the synchronization state, but implies + * a full barrier so that the AP changes are visible before the control CPU proceeds. + */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + (void)atomic_xchg(st, state); +} + +void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } + +static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, + enum cpuhp_sync_state next_state) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + ktime_t now, end, start = ktime_get(); + int sync; + + end = start + 10ULL * NSEC_PER_SEC; + + sync = atomic_read(st); + while (1) { + if (sync == state) { + if (!atomic_try_cmpxchg(st, &sync, next_state)) + continue; + return true; + } + + now = ktime_get(); + if (now > end) { + /* Timeout. Leave the state unchanged */ + return false; + } else if (now - start < NSEC_PER_MSEC) { + /* Poll for one millisecond */ + arch_cpuhp_sync_state_poll(); + } else { + usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE); + } + sync = atomic_read(st); + } + return true; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC */ +static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +/** + * cpuhp_ap_report_dead - Update synchronization state to DEAD + * + * No synchronization point. Just update of the synchronization state. + */ +void cpuhp_ap_report_dead(void) +{ + cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); +} + +void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } + +/* + * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down + * because the AP cannot issue complete() at this stage. + */ +static void cpuhp_bp_sync_dead(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + + do { + /* CPU can have reported dead already. Don't overwrite that! */ + if (sync == SYNC_STATE_DEAD) + break; + } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); + + if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { + /* CPU reached dead state. Invoke the cleanup function */ + arch_cpuhp_cleanup_dead_cpu(cpu); + return; + } + + /* No further action possible. Emit message and give up. */ + pr_err("CPU%u failed to report dead state\n", cpu); +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ +static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL +/** + * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive + * + * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits + * for the BP to release it. + */ +void cpuhp_ap_sync_alive(void) +{ + atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); + + cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); + + /* Wait for the control CPU to release it. */ + while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) + cpu_relax(); +} + +static bool cpuhp_can_boot_ap(unsigned int cpu) +{ + atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); + int sync = atomic_read(st); + +again: + switch (sync) { + case SYNC_STATE_DEAD: + /* CPU is properly dead */ + break; + case SYNC_STATE_KICKED: + /* CPU did not come up in previous attempt */ + break; + case SYNC_STATE_ALIVE: + /* CPU is stuck cpuhp_ap_sync_alive(). */ + break; + default: + /* CPU failed to report online or dead and is in limbo state. */ + return false; + } + + /* Prepare for booting */ + if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) + goto again; + + return true; +} + +void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } + +/* + * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up + * because the AP cannot issue complete() so early in the bringup. + */ +static int cpuhp_bp_sync_alive(unsigned int cpu) +{ + int ret = 0; + + if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) + return 0; + + if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { + pr_err("CPU%u failed to report alive state\n", cpu); + ret = -EIO; + } + + /* Let the architecture cleanup the kick alive mechanics. */ + arch_cpuhp_cleanup_kick_cpu(cpu); + return ret; +} +#else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ +static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } +static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } +#endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -470,8 +649,23 @@ bool cpu_smt_possible(void) cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); + +static inline bool cpuhp_smt_aware(void) +{ + return topology_smt_supported(); +} + +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_primary_thread_mask; +} #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +static inline bool cpuhp_smt_aware(void) { return false; } +static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) +{ + return cpu_present_mask; +} #endif static inline enum cpuhp_state @@ -558,7 +752,7 @@ static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, return ret; } -static int bringup_wait_for_ap(unsigned int cpu) +static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); @@ -579,38 +773,94 @@ static int bringup_wait_for_ap(unsigned int cpu) */ if (!cpu_smt_allowed(cpu)) return -ECANCELED; + return 0; +} + +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP +static int cpuhp_kick_ap_alive(unsigned int cpu) +{ + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; + + return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); +} + +static int cpuhp_bringup_ap(unsigned int cpu) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; + + /* + * Some architectures have to walk the irq descriptors to + * setup the vector space for the cpu which comes online. + * Prevent irq alloc/free across the bringup. + */ + irq_lock_sparse(); + + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + + ret = bringup_wait_for_ap_online(cpu); + if (ret) + goto out_unlock; + + irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); -} +out_unlock: + irq_unlock_sparse(); + return ret; +} +#else static int bringup_cpu(unsigned int cpu) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; - /* - * Reset stale stack state from the last time this CPU was online. - */ - scs_task_reset(idle); - kasan_unpoison_task_stack(idle); + if (!cpuhp_can_boot_ap(cpu)) + return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. - * Prevent irq alloc/free across the bringup. + * + * Prevent irq alloc/free across the bringup by acquiring the + * sparse irq lock. Hold it until the upcoming CPU completes the + * startup in cpuhp_online_idle() which allows to avoid + * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); - /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); - irq_unlock_sparse(); if (ret) - return ret; - return bringup_wait_for_ap(cpu); + goto out_unlock; + + ret = cpuhp_bp_sync_alive(cpu); + if (ret) + goto out_unlock; + + ret = bringup_wait_for_ap_online(cpu); + if (ret) + goto out_unlock; + + irq_unlock_sparse(); + + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(cpu, st, st->target); + +out_unlock: + irq_unlock_sparse(); + return ret; } +#endif static int finish_cpu(unsigned int cpu) { @@ -1099,6 +1349,8 @@ static int takedown_cpu(unsigned int cpu) /* This actually kills the CPU. */ __cpu_die(cpu); + cpuhp_bp_sync_dead(cpu); + tick_cleanup_dead_cpu(cpu); rcutree_migrate_callbacks(cpu); return 0; @@ -1345,8 +1597,10 @@ void cpuhp_online_idle(enum cpuhp_state state) if (state != CPUHP_AP_ONLINE_IDLE) return; + cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); + /* - * Unpart the stopper thread before we start the idle loop (and start + * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); @@ -1383,6 +1637,12 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = PTR_ERR(idle); goto out; } + + /* + * Reset stale stack state from the last time this CPU was online. + */ + scs_task_reset(idle); + kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; @@ -1502,18 +1762,96 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu) return 0; } -void bringup_nonboot_cpus(unsigned int setup_max_cpus) +static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, + enum cpuhp_state target) { unsigned int cpu; - for_each_present_cpu(cpu) { - if (num_online_cpus() >= setup_max_cpus) + for_each_cpu(cpu, mask) { + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + + if (cpu_up(cpu, target) && can_rollback_cpu(st)) { + /* + * If this failed then cpu_up() might have only + * rolled back to CPUHP_BP_KICK_AP for the final + * online. Clean it up. NOOP if already rolled back. + */ + WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); + } + + if (!--ncpus) break; - if (!cpu_online(cpu)) - cpu_up(cpu, CPUHP_ONLINE); } } +#ifdef CONFIG_HOTPLUG_PARALLEL +static bool __cpuhp_parallel_bringup __ro_after_init = true; + +static int __init parallel_bringup_parse_param(char *arg) +{ + return kstrtobool(arg, &__cpuhp_parallel_bringup); +} +early_param("cpuhp.parallel", parallel_bringup_parse_param); + +/* + * On architectures which have enabled parallel bringup this invokes all BP + * prepare states for each of the to be onlined APs first. The last state + * sends the startup IPI to the APs. The APs proceed through the low level + * bringup code in parallel and then wait for the control CPU to release + * them one by one for the final onlining procedure. + * + * This avoids waiting for each AP to respond to the startup IPI in + * CPUHP_BRINGUP_CPU. + */ +static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) +{ + const struct cpumask *mask = cpu_present_mask; + + if (__cpuhp_parallel_bringup) + __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); + if (!__cpuhp_parallel_bringup) + return false; + + if (cpuhp_smt_aware()) { + const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); + static struct cpumask tmp_mask __initdata; + + /* + * X86 requires to prevent that SMT siblings stopped while + * the primary thread does a microcode update for various + * reasons. Bring the primary threads up first. + */ + cpumask_and(&tmp_mask, mask, pmask); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); + /* Account for the online CPUs */ + ncpus -= num_online_cpus(); + if (!ncpus) + return true; + /* Create the mask for secondary CPUs */ + cpumask_andnot(&tmp_mask, mask, pmask); + mask = &tmp_mask; + } + + /* Bring the not-yet started CPUs up */ + cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); + cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); + return true; +} +#else +static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } +#endif /* CONFIG_HOTPLUG_PARALLEL */ + +void __init bringup_nonboot_cpus(unsigned int setup_max_cpus) +{ + /* Try parallel bringup optimization if enabled */ + if (cpuhp_bringup_cpus_parallel(setup_max_cpus)) + return; + + /* Full per CPU serialized bringup */ + cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE); +} + #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; @@ -1740,13 +2078,38 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, - /* Kicks the plugged cpu into life */ + +#ifdef CONFIG_HOTPLUG_SPLIT_STARTUP + /* + * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until + * the next step will release it. + */ + [CPUHP_BP_KICK_AP] = { + .name = "cpu:kick_ap", + .startup.single = cpuhp_kick_ap_alive, + }, + + /* + * Waits for the AP to reach cpuhp_ap_sync_alive() and then + * releases it for the complete bringup. + */ + [CPUHP_BRINGUP_CPU] = { + .name = "cpu:bringup", + .startup.single = cpuhp_bringup_ap, + .teardown.single = finish_cpu, + .cant_stop = true, + }, +#else + /* + * All-in-one CPU bringup state which includes the kick alive. + */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, +#endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", @@ -2723,6 +3086,7 @@ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); + atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 49e7bc871fec..ee8c0acf39df 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -306,6 +306,7 @@ static void __irq_disable(struct irq_desc *desc, bool mask); void irq_shutdown(struct irq_desc *desc) { if (irqd_is_started(&desc->irq_data)) { + clear_irq_resend(desc); desc->depth = 1; if (desc->irq_data.chip->irq_shutdown) { desc->irq_data.chip->irq_shutdown(&desc->irq_data); @@ -692,8 +693,16 @@ void handle_fasteoi_irq(struct irq_desc *desc) raw_spin_lock(&desc->lock); - if (!irq_may_run(desc)) + /* + * When an affinity change races with IRQ handling, the next interrupt + * can arrive on the new CPU before the original CPU has completed + * handling the previous one - it may need to be resent. + */ + if (!irq_may_run(desc)) { + if (irqd_needs_resend_when_in_progress(&desc->irq_data)) + desc->istate |= IRQS_PENDING; goto out; + } desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); @@ -715,6 +724,12 @@ void handle_fasteoi_irq(struct irq_desc *desc) cond_unmask_eoi_irq(desc, chip); + /* + * When the race described above happens this will resend the interrupt. + */ + if (unlikely(desc->istate & IRQS_PENDING)) + check_irq_resend(desc, false); + raw_spin_unlock(&desc->lock); return; out: diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index bbcaac64038e..5971a66be034 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -133,6 +133,8 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX), BIT_MASK_DESCR(IRQD_IRQ_ENABLED_ON_SUSPEND), + + BIT_MASK_DESCR(IRQD_RESEND_WHEN_IN_PROGRESS), }; static const struct irq_bit_descr irqdesc_states[] = { diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 5fdc0b557579..bdd35bb9c735 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -12,9 +12,9 @@ #include <linux/sched/clock.h> #ifdef CONFIG_SPARSE_IRQ -# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +# define MAX_SPARSE_IRQS INT_MAX #else -# define IRQ_BITMAP_BITS NR_IRQS +# define MAX_SPARSE_IRQS NR_IRQS #endif #define istate core_internal_state__do_not_mess_with_it @@ -47,9 +47,12 @@ enum { * detection * IRQS_POLL_INPROGRESS - polling in progress * IRQS_ONESHOT - irq is not unmasked in primary handler - * IRQS_REPLAY - irq is replayed + * IRQS_REPLAY - irq has been resent and will not be resent + * again until the handler has run and cleared + * this flag. * IRQS_WAITING - irq is waiting - * IRQS_PENDING - irq is pending and replayed later + * IRQS_PENDING - irq needs to be resent and should be resent + * at the next available opportunity. * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs * IRQS_SYSFS - descriptor has been added to sysfs @@ -113,6 +116,8 @@ irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ int check_irq_resend(struct irq_desc *desc, bool inject); +void clear_irq_resend(struct irq_desc *desc); +void irq_resend_init(struct irq_desc *desc); bool irq_wait_for_poll(struct irq_desc *desc); void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 240e145e969f..27ca1c866f29 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -12,8 +12,7 @@ #include <linux/export.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> -#include <linux/radix-tree.h> -#include <linux/bitmap.h> +#include <linux/maple_tree.h> #include <linux/irqdomain.h> #include <linux/sysfs.h> @@ -131,7 +130,40 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); -static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); +static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, + MT_FLAGS_ALLOC_RANGE | + MT_FLAGS_LOCK_EXTERN | + MT_FLAGS_USE_RCU, + sparse_irq_lock); + +static int irq_find_free_area(unsigned int from, unsigned int cnt) +{ + MA_STATE(mas, &sparse_irqs, 0, 0); + + if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) + return -ENOSPC; + return mas.index; +} + +static unsigned int irq_find_at_or_after(unsigned int offset) +{ + unsigned long index = offset; + struct irq_desc *desc = mt_find(&sparse_irqs, &index, nr_irqs); + + return desc ? irq_desc_get_irq(desc) : nr_irqs; +} + +static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) +{ + MA_STATE(mas, &sparse_irqs, irq, irq); + WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); +} + +static void delete_irq_desc(unsigned int irq) +{ + MA_STATE(mas, &sparse_irqs, irq, irq); + mas_erase(&mas); +} #ifdef CONFIG_SPARSE_IRQ @@ -344,26 +376,14 @@ static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ -static RADIX_TREE(irq_desc_tree, GFP_KERNEL); - -static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) -{ - radix_tree_insert(&irq_desc_tree, irq, desc); -} - struct irq_desc *irq_to_desc(unsigned int irq) { - return radix_tree_lookup(&irq_desc_tree, irq); + return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif -static void delete_irq_desc(unsigned int irq) -{ - radix_tree_delete(&irq_desc_tree, irq); -} - #ifdef CONFIG_SMP static void free_masks(struct irq_desc *desc) { @@ -415,6 +435,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); kobject_init(&desc->kobj, &irq_kobj_type); + irq_resend_init(desc); return desc; @@ -505,7 +526,6 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } - bitmap_set(allocated_irqs, start, cnt); return start; err: @@ -516,7 +536,7 @@ err: static int irq_expand_nr_irqs(unsigned int nr) { - if (nr > IRQ_BITMAP_BITS) + if (nr > MAX_SPARSE_IRQS) return -ENOMEM; nr_irqs = nr; return 0; @@ -534,18 +554,17 @@ int __init early_irq_init(void) printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); - if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) - nr_irqs = IRQ_BITMAP_BITS; + if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) + nr_irqs = MAX_SPARSE_IRQS; - if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) - initcnt = IRQ_BITMAP_BITS; + if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) + initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); - set_bit(i, allocated_irqs); irq_insert_desc(i, desc); } return arch_early_irq_init(); @@ -581,6 +600,7 @@ int __init early_irq_init(void) mutex_init(&desc[i].request_mutex); init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); + irq_resend_init(desc); } return arch_early_irq_init(); } @@ -599,6 +619,7 @@ static void free_desc(unsigned int irq) raw_spin_lock_irqsave(&desc->lock, flags); desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); raw_spin_unlock_irqrestore(&desc->lock, flags); + delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, @@ -611,8 +632,8 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; + irq_insert_desc(start + i, desc); } - bitmap_set(allocated_irqs, start, cnt); return start; } @@ -624,7 +645,7 @@ static int irq_expand_nr_irqs(unsigned int nr) void irq_mark_irq(unsigned int irq) { mutex_lock(&sparse_irq_lock); - bitmap_set(allocated_irqs, irq, 1); + irq_insert_desc(irq, irq_desc + irq); mutex_unlock(&sparse_irq_lock); } @@ -768,7 +789,6 @@ void irq_free_descs(unsigned int from, unsigned int cnt) for (i = 0; i < cnt; i++) free_desc(from + i); - bitmap_clear(allocated_irqs, from, cnt); mutex_unlock(&sparse_irq_lock); } EXPORT_SYMBOL_GPL(irq_free_descs); @@ -810,8 +830,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, mutex_lock(&sparse_irq_lock); - start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS, - from, cnt, 0); + start = irq_find_free_area(from, cnt); ret = -EEXIST; if (irq >=0 && start != irq) goto unlock; @@ -836,7 +855,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); */ unsigned int irq_get_next_irq(unsigned int offset) { - return find_next_bit(allocated_irqs, nr_irqs, offset); + return irq_find_at_or_after(offset); } struct irq_desc * diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index f34760a1e222..5bd01624e447 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1915,6 +1915,8 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #ifdef CONFIG_GENERIC_IRQ_DEBUGFS +#include "internals.h" + static struct dentry *domain_dir; static void diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 0c46e9fe3a89..edec335c0a7a 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -21,8 +21,9 @@ #ifdef CONFIG_HARDIRQS_SW_RESEND -/* Bitmap to handle software resend of interrupts: */ -static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); +/* hlist_head to handle software resend of interrupts: */ +static HLIST_HEAD(irq_resend_list); +static DEFINE_RAW_SPINLOCK(irq_resend_lock); /* * Run software resends of IRQ's @@ -30,18 +31,17 @@ static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); static void resend_irqs(struct tasklet_struct *unused) { struct irq_desc *desc; - int irq; - - while (!bitmap_empty(irqs_resend, nr_irqs)) { - irq = find_first_bit(irqs_resend, nr_irqs); - clear_bit(irq, irqs_resend); - desc = irq_to_desc(irq); - if (!desc) - continue; - local_irq_disable(); + + raw_spin_lock_irq(&irq_resend_lock); + while (!hlist_empty(&irq_resend_list)) { + desc = hlist_entry(irq_resend_list.first, struct irq_desc, + resend_node); + hlist_del_init(&desc->resend_node); + raw_spin_unlock(&irq_resend_lock); desc->handle_irq(desc); - local_irq_enable(); + raw_spin_lock(&irq_resend_lock); } + raw_spin_unlock_irq(&irq_resend_lock); } /* Tasklet to handle resend: */ @@ -49,8 +49,6 @@ static DECLARE_TASKLET(resend_tasklet, resend_irqs); static int irq_sw_resend(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); - /* * Validate whether this interrupt can be safely injected from * non interrupt context @@ -70,16 +68,31 @@ static int irq_sw_resend(struct irq_desc *desc) */ if (!desc->parent_irq) return -EINVAL; - irq = desc->parent_irq; } - /* Set it pending and activate the softirq: */ - set_bit(irq, irqs_resend); + /* Add to resend_list and activate the softirq: */ + raw_spin_lock(&irq_resend_lock); + hlist_add_head(&desc->resend_node, &irq_resend_list); + raw_spin_unlock(&irq_resend_lock); tasklet_schedule(&resend_tasklet); return 0; } +void clear_irq_resend(struct irq_desc *desc) +{ + raw_spin_lock(&irq_resend_lock); + hlist_del_init(&desc->resend_node); + raw_spin_unlock(&irq_resend_lock); +} + +void irq_resend_init(struct irq_desc *desc) +{ + INIT_HLIST_NODE(&desc->resend_node); +} #else +void clear_irq_resend(struct irq_desc *desc) {} +void irq_resend_init(struct irq_desc *desc) {} + static int irq_sw_resend(struct irq_desc *desc) { return -EINVAL; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f989f5f1933b..69ee4a29136f 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -901,10 +901,22 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi, } offset = ALIGN(offset, align); + + /* + * Check if the segment contains the entry point, if so, + * calculate the value of image->start based on it. + * If the compiler has produced more than one .text section + * (Eg: .text.hot), they are generally after the main .text + * section, and they shall not be used to calculate + * image->start. So do not re-calculate image->start if it + * is not set to the initial value, and warn the user so they + * have a chance to fix their purgatory's linker script. + */ if (sechdrs[i].sh_flags & SHF_EXECINSTR && pi->ehdr->e_entry >= sechdrs[i].sh_addr && pi->ehdr->e_entry < (sechdrs[i].sh_addr - + sechdrs[i].sh_size)) { + + sechdrs[i].sh_size) && + !WARN_ON(kbuf->image->start != pi->ehdr->e_entry)) { kbuf->image->start -= sechdrs[i].sh_addr; kbuf->image->start += kbuf->mem + offset; } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 30d1274f03f6..f62e89d0d906 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) "PM: hibernation: " fmt +#include <linux/blkdev.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/reboot.h> @@ -64,7 +65,6 @@ enum { static int hibernation_mode = HIBERNATION_SHUTDOWN; bool freezer_test_done; -bool snapshot_test; static const struct platform_hibernation_ops *hibernation_ops; @@ -684,26 +684,22 @@ static void power_down(void) cpu_relax(); } -static int load_image_and_restore(void) +static int load_image_and_restore(bool snapshot_test) { int error; unsigned int flags; - fmode_t mode = FMODE_READ; - - if (snapshot_test) - mode |= FMODE_EXCL; pm_pr_dbg("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); if (error) { - swsusp_close(mode); + swsusp_close(snapshot_test); goto Unlock; } error = swsusp_read(&flags); - swsusp_close(mode); + swsusp_close(snapshot_test); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); @@ -721,6 +717,7 @@ static int load_image_and_restore(void) */ int hibernate(void) { + bool snapshot_test = false; unsigned int sleep_flags; int error; @@ -748,9 +745,6 @@ int hibernate(void) if (error) goto Exit; - /* protected by system_transition_mutex */ - snapshot_test = false; - lock_device_hotplug(); /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); @@ -792,9 +786,9 @@ int hibernate(void) unlock_device_hotplug(); if (snapshot_test) { pm_pr_dbg("Checking hibernation image\n"); - error = swsusp_check(); + error = swsusp_check(snapshot_test); if (!error) - error = load_image_and_restore(); + error = load_image_and_restore(snapshot_test); } thaw_processes(); @@ -910,52 +904,10 @@ unlock: } EXPORT_SYMBOL_GPL(hibernate_quiet_exec); -/** - * software_resume - Resume from a saved hibernation image. - * - * This routine is called as a late initcall, when all devices have been - * discovered and initialized already. - * - * The image reading code is called to see if there is a hibernation image - * available for reading. If that is the case, devices are quiesced and the - * contents of memory is restored from the saved image. - * - * If this is successful, control reappears in the restored target kernel in - * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine - * attempts to recover gracefully and make the kernel return to the normal mode - * of operation. - */ -static int software_resume(void) +static int __init find_resume_device(void) { - int error; - - /* - * If the user said "noresume".. bail out early. - */ - if (noresume || !hibernation_available()) - return 0; - - /* - * name_to_dev_t() below takes a sysfs buffer mutex when sysfs - * is configured into the kernel. Since the regular hibernate - * trigger path is via sysfs which takes a buffer mutex before - * calling hibernate functions (which take system_transition_mutex) - * this can cause lockdep to complain about a possible ABBA deadlock - * which cannot happen since we're in the boot code here and - * sysfs can't be invoked yet. Therefore, we use a subclass - * here to avoid lockdep complaining. - */ - mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING); - - snapshot_test = false; - - if (swsusp_resume_device) - goto Check_image; - - if (!strlen(resume_file)) { - error = -ENOENT; - goto Unlock; - } + if (!strlen(resume_file)) + return -ENOENT; pm_pr_dbg("Checking hibernation image partition %s\n", resume_file); @@ -966,40 +918,41 @@ static int software_resume(void) } /* Check if the device is there */ - swsusp_resume_device = name_to_dev_t(resume_file); - if (!swsusp_resume_device) { - /* - * Some device discovery might still be in progress; we need - * to wait for this to finish. - */ - wait_for_device_probe(); - - if (resume_wait) { - while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0) - msleep(10); - async_synchronize_full(); - } + if (!early_lookup_bdev(resume_file, &swsusp_resume_device)) + return 0; - swsusp_resume_device = name_to_dev_t(resume_file); - if (!swsusp_resume_device) { - error = -ENODEV; - goto Unlock; - } + /* + * Some device discovery might still be in progress; we need to wait for + * this to finish. + */ + wait_for_device_probe(); + if (resume_wait) { + while (early_lookup_bdev(resume_file, &swsusp_resume_device)) + msleep(10); + async_synchronize_full(); } - Check_image: + return early_lookup_bdev(resume_file, &swsusp_resume_device); +} + +static int software_resume(void) +{ + int error; + pm_pr_dbg("Hibernation image partition %d:%d present\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pm_pr_dbg("Looking for hibernation image.\n"); - error = swsusp_check(); + + mutex_lock(&system_transition_mutex); + error = swsusp_check(false); if (error) goto Unlock; /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(false); goto Unlock; } @@ -1020,7 +973,7 @@ static int software_resume(void) goto Close_Finish; } - error = load_image_and_restore(); + error = load_image_and_restore(false); thaw_processes(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); @@ -1034,11 +987,43 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(false); goto Finish; } -late_initcall_sync(software_resume); +/** + * software_resume_initcall - Resume from a saved hibernation image. + * + * This routine is called as a late initcall, when all devices have been + * discovered and initialized already. + * + * The image reading code is called to see if there is a hibernation image + * available for reading. If that is the case, devices are quiesced and the + * contents of memory is restored from the saved image. + * + * If this is successful, control reappears in the restored target kernel in + * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine + * attempts to recover gracefully and make the kernel return to the normal mode + * of operation. + */ +static int __init software_resume_initcall(void) +{ + /* + * If the user said "noresume".. bail out early. + */ + if (noresume || !hibernation_available()) + return 0; + + if (!swsusp_resume_device) { + int error = find_resume_device(); + + if (error) + return error; + } + + return software_resume(); +} +late_initcall_sync(software_resume_initcall); static const char * const hibernation_modes[] = { @@ -1177,7 +1162,11 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, unsigned int sleep_flags; int len = n; char *name; - dev_t res; + dev_t dev; + int error; + + if (!hibernation_available()) + return 0; if (len && buf[len-1] == '\n') len--; @@ -1185,13 +1174,29 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, if (!name) return -ENOMEM; - res = name_to_dev_t(name); + error = lookup_bdev(name, &dev); + if (error) { + unsigned maj, min, offset; + char *p, dummy; + + if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || + sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, + &dummy) == 3) { + dev = MKDEV(maj, min); + if (maj != MAJOR(dev) || min != MINOR(dev)) + error = -EINVAL; + } else { + dev = new_decode_dev(simple_strtoul(name, &p, 16)); + if (*p) + error = -EINVAL; + } + } kfree(name); - if (!res) - return -EINVAL; + if (error) + return error; sleep_flags = lock_system_sleep(); - swsusp_resume_device = res; + swsusp_resume_device = dev; unlock_system_sleep(sleep_flags); pm_pr_dbg("Configured hibernation resume from disk to %u\n", diff --git a/kernel/power/power.h b/kernel/power/power.h index b83c8d5e188d..a8e0c44b804e 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -59,7 +59,6 @@ asmlinkage int swsusp_save(void); /* kernel/power/hibernate.c */ extern bool freezer_test_done; -extern bool snapshot_test; extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); @@ -174,11 +173,11 @@ extern int swsusp_swap_in_use(void); #define SF_HW_SIG 8 /* kernel/power/hibernate.c */ -extern int swsusp_check(void); +int swsusp_check(bool snapshot_test); extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); -extern void swsusp_close(fmode_t); +void swsusp_close(bool snapshot_test); #ifdef CONFIG_SUSPEND extern int swsusp_unmark(void); #endif diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 92e41ed292ad..f6ebcd00c410 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -356,14 +356,14 @@ static int swsusp_swap_check(void) return res; root_swap = res; - hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, FMODE_WRITE, - NULL); + hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, + BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(hib_resume_bdev)) return PTR_ERR(hib_resume_bdev); res = set_blocksize(hib_resume_bdev, PAGE_SIZE); if (res < 0) - blkdev_put(hib_resume_bdev, FMODE_WRITE); + blkdev_put(hib_resume_bdev, NULL); return res; } @@ -443,7 +443,7 @@ static int get_swap_writer(struct swap_map_handle *handle) err_rel: release_swap_writer(handle); err_close: - swsusp_close(FMODE_WRITE); + swsusp_close(false); return ret; } @@ -508,7 +508,7 @@ static int swap_writer_finish(struct swap_map_handle *handle, if (error) free_all_swap_pages(root_swap); release_swap_writer(handle); - swsusp_close(FMODE_WRITE); + swsusp_close(false); return error; } @@ -1510,21 +1510,19 @@ end: return error; } +static void *swsusp_holder; + /** * swsusp_check - Check for swsusp signature in the resume device */ -int swsusp_check(void) +int swsusp_check(bool snapshot_test) { + void *holder = snapshot_test ? &swsusp_holder : NULL; int error; - void *holder; - fmode_t mode = FMODE_READ; - if (snapshot_test) - mode |= FMODE_EXCL; - - hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - mode, &holder); + hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, BLK_OPEN_READ, + holder, NULL); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1551,7 +1549,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, mode); + blkdev_put(hib_resume_bdev, holder); else pr_debug("Image signature found, resuming\n"); } else { @@ -1568,14 +1566,14 @@ put: * swsusp_close - close swap device. */ -void swsusp_close(fmode_t mode) +void swsusp_close(bool snapshot_test) { if (IS_ERR(hib_resume_bdev)) { pr_debug("Image device not initialised\n"); return; } - blkdev_put(hib_resume_bdev, mode); + blkdev_put(hib_resume_bdev, snapshot_test ? &swsusp_holder : NULL); } /** diff --git a/kernel/smp.c b/kernel/smp.c index ab3e5dad6cfe..385179dae360 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -27,6 +27,9 @@ #include <linux/jump_label.h> #include <trace/events/ipi.h> +#define CREATE_TRACE_POINTS +#include <trace/events/csd.h> +#undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" @@ -121,6 +124,14 @@ send_call_function_ipi_mask(struct cpumask *mask) arch_send_call_function_ipi_mask(mask); } +static __always_inline void +csd_do_func(smp_call_func_t func, void *info, struct __call_single_data *csd) +{ + trace_csd_function_entry(func, csd); + func(info); + trace_csd_function_exit(func, csd); +} + #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); @@ -329,7 +340,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ - if (trace_ipi_send_cpu_enabled()) { + if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; @@ -337,7 +348,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; - trace_ipi_send_cpu(cpu, _RET_IP_, func); + trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* @@ -375,7 +386,7 @@ static int generic_exec_single(int cpu, struct __call_single_data *csd) csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); - func(info); + csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; @@ -477,7 +488,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) } csd_lock_record(csd); - func(info); + csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { @@ -508,7 +519,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) csd_lock_record(csd); csd_unlock(csd); - func(info); + csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); @@ -522,8 +533,10 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) /* * Third; only CSD_TYPE_TTWU is left, issue those. */ - if (entry) - sched_ttwu_pending(entry); + if (entry) { + csd = llist_entry(entry, typeof(*csd), node.llist); + csd_do_func(sched_ttwu_pending, entry, csd); + } } @@ -728,7 +741,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; - int nr_cpus = 0, nr_queued = 0; + int nr_cpus = 0; bool run_remote = false; bool run_local = false; @@ -786,22 +799,16 @@ static void smp_call_function_many_cond(const struct cpumask *mask, csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif + trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); + if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } - nr_queued++; } /* - * Trace each smp_function_call_*() as an IPI, actual IPIs - * will be traced with func==generic_smp_call_function_single_ipi(). - */ - if (nr_queued) - trace_ipi_send_cpumask(cfd->cpumask, _RET_IP_, func); - - /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. @@ -816,7 +823,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, unsigned long flags; local_irq_save(flags); - func(info); + csd_do_func(func, info, NULL); local_irq_restore(flags); } @@ -892,7 +899,7 @@ EXPORT_SYMBOL(setup_max_cpus); * SMP mode to <NUM>. */ -void __weak arch_disable_smp_support(void) { } +void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2c7396da470c..f47d8f375946 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -325,166 +325,3 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) cpus_read_unlock(); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); - -static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); - -/* - * Called to poll specified CPU's state, for example, when waiting for - * a CPU to come online. - */ -int cpu_report_state(int cpu) -{ - return atomic_read(&per_cpu(cpu_hotplug_state, cpu)); -} - -/* - * If CPU has died properly, set its state to CPU_UP_PREPARE and - * return success. Otherwise, return -EBUSY if the CPU died after - * cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN - * if cpu_wait_death() timed out and the CPU still hasn't gotten around - * to dying. In the latter two cases, the CPU might not be set up - * properly, but it is up to the arch-specific code to decide. - * Finally, -EIO indicates an unanticipated problem. - * - * Note that it is permissible to omit this call entirely, as is - * done in architectures that do no CPU-hotplug error checking. - */ -int cpu_check_up_prepare(int cpu) -{ - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) { - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); - return 0; - } - - switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) { - - case CPU_POST_DEAD: - - /* The CPU died properly, so just start it up again. */ - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); - return 0; - - case CPU_DEAD_FROZEN: - - /* - * Timeout during CPU death, so let caller know. - * The outgoing CPU completed its processing, but after - * cpu_wait_death() timed out and reported the error. The - * caller is free to proceed, in which case the state - * will be reset properly by cpu_set_state_online(). - * Proceeding despite this -EBUSY return makes sense - * for systems where the outgoing CPUs take themselves - * offline, with no post-death manipulation required from - * a surviving CPU. - */ - return -EBUSY; - - case CPU_BROKEN: - - /* - * The most likely reason we got here is that there was - * a timeout during CPU death, and the outgoing CPU never - * did complete its processing. This could happen on - * a virtualized system if the outgoing VCPU gets preempted - * for more than five seconds, and the user attempts to - * immediately online that same CPU. Trying again later - * might return -EBUSY above, hence -EAGAIN. - */ - return -EAGAIN; - - case CPU_UP_PREPARE: - /* - * Timeout while waiting for the CPU to show up. Allow to try - * again later. - */ - return 0; - - default: - - /* Should not happen. Famous last words. */ - return -EIO; - } -} - -/* - * Mark the specified CPU online. - * - * Note that it is permissible to omit this call entirely, as is - * done in architectures that do no CPU-hotplug error checking. - */ -void cpu_set_state_online(int cpu) -{ - (void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE); -} - -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Wait for the specified CPU to exit the idle loop and die. - */ -bool cpu_wait_death(unsigned int cpu, int seconds) -{ - int jf_left = seconds * HZ; - int oldstate; - bool ret = true; - int sleep_jf = 1; - - might_sleep(); - - /* The outgoing CPU will normally get done quite quickly. */ - if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD) - goto update_state_early; - udelay(5); - - /* But if the outgoing CPU dawdles, wait increasingly long times. */ - while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) { - schedule_timeout_uninterruptible(sleep_jf); - jf_left -= sleep_jf; - if (jf_left <= 0) - break; - sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10); - } -update_state_early: - oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); -update_state: - if (oldstate == CPU_DEAD) { - /* Outgoing CPU died normally, update state. */ - smp_mb(); /* atomic_read() before update. */ - atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD); - } else { - /* Outgoing CPU still hasn't died, set state accordingly. */ - if (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), - &oldstate, CPU_BROKEN)) - goto update_state; - ret = false; - } - return ret; -} - -/* - * Called by the outgoing CPU to report its successful death. Return - * false if this report follows the surviving CPU's timing out. - * - * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU - * timed out. This approach allows architectures to omit calls to - * cpu_check_up_prepare() and cpu_set_state_online() without defeating - * the next cpu_wait_death()'s polling loop. - */ -bool cpu_report_death(void) -{ - int oldstate; - int newstate; - int cpu = smp_processor_id(); - - oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); - do { - if (oldstate != CPU_BROKEN) - newstate = CPU_DEAD; - else - newstate = CPU_DEAD_FROZEN; - } while (!atomic_try_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), - &oldstate, newstate)); - return newstate == CPU_DEAD; -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ diff --git a/kernel/softirq.c b/kernel/softirq.c index 1b725510dd0f..807b34ccd797 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -80,21 +80,6 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } -/* - * If ksoftirqd is scheduled, we do not want to process pending softirqs - * right now. Let ksoftirqd handle this at its own rate, to get fairness, - * unless we're doing some of the synchronous softirqs. - */ -#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) -static bool ksoftirqd_running(unsigned long pending) -{ - struct task_struct *tsk = __this_cpu_read(ksoftirqd); - - if (pending & SOFTIRQ_NOW_MASK) - return false; - return tsk && task_is_running(tsk) && !__kthread_should_park(tsk); -} - #ifdef CONFIG_TRACE_IRQFLAGS DEFINE_PER_CPU(int, hardirqs_enabled); DEFINE_PER_CPU(int, hardirq_context); @@ -236,7 +221,7 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) goto out; pending = local_softirq_pending(); - if (!pending || ksoftirqd_running(pending)) + if (!pending) goto out; /* @@ -432,9 +417,6 @@ static inline bool should_wake_ksoftirqd(void) static inline void invoke_softirq(void) { - if (ksoftirqd_running(local_softirq_pending())) - return; - if (!force_irqthreads() || !__this_cpu_read(ksoftirqd)) { #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK /* @@ -468,7 +450,7 @@ asmlinkage __visible void do_softirq(void) pending = local_softirq_pending(); - if (pending && !ksoftirqd_running(pending)) + if (pending) do_softirq_own_stack(); local_irq_restore(flags); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 82b28ab0f328..8d9f13d847f0 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -751,7 +751,7 @@ static int alarm_timer_create(struct k_itimer *new_timer) static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now) { - struct task_struct *task = (struct task_struct *)alarm->data; + struct task_struct *task = alarm->data; alarm->data = NULL; if (task) @@ -847,7 +847,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, struct restart_block *restart = ¤t->restart_block; struct alarm alarm; ktime_t exp; - int ret = 0; + int ret; if (!alarmtimer_get_rtcdev()) return -EOPNOTSUPP; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index e8c08292defc..238262e4aba7 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -164,6 +164,7 @@ static inline bool is_migration_base(struct hrtimer_clock_base *base) static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) + __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; @@ -280,6 +281,7 @@ static inline bool is_migration_base(struct hrtimer_clock_base *base) static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) + __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; @@ -1013,6 +1015,7 @@ void hrtimers_resume_local(void) */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) + __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 808a247205a9..b924f0f096fa 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -35,20 +35,17 @@ #include "timekeeping.h" #include "posix-timers.h" -/* - * Management arrays for POSIX timers. Timers are now kept in static hash table - * with 512 entries. - * Timer ids are allocated by local routine, which selects proper hash head by - * key, constructed from current->signal address and per signal struct counter. - * This keeps timer ids unique per process, but now they can intersect between - * processes. - */ +static struct kmem_cache *posix_timers_cache; /* - * Lets keep our timers in a slab cache :-) + * Timers are managed in a hash table for lockless lookup. The hash key is + * constructed from current::signal and the timer ID and the timer is + * matched against current::signal and the timer ID when walking the hash + * bucket list. + * + * This allows checkpoint/restore to reconstruct the exact timer IDs for + * a process. */ -static struct kmem_cache *posix_timers_cache; - static DEFINE_HASHTABLE(posix_timers_hashtable, 9); static DEFINE_SPINLOCK(hash_lock); @@ -56,52 +53,12 @@ static const struct k_clock * const posix_clocks[]; static const struct k_clock *clockid_to_kclock(const clockid_t id); static const struct k_clock clock_realtime, clock_monotonic; -/* - * we assume that the new SIGEV_THREAD_ID shares no bits with the other - * SIGEV values. Here we put out an error if this assumption fails. - */ +/* SIGEV_THREAD_ID cannot share a bit with the other SIGEV values. */ #if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ - ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) + ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" #endif -/* - * The timer ID is turned into a timer address by idr_find(). - * Verifying a valid ID consists of: - * - * a) checking that idr_find() returns other than -1. - * b) checking that the timer id matches the one in the timer itself. - * c) that the timer owner is in the callers thread group. - */ - -/* - * CLOCKs: The POSIX standard calls for a couple of clocks and allows us - * to implement others. This structure defines the various - * clocks. - * - * RESOLUTION: Clock resolution is used to round up timer and interval - * times, NOT to report clock times, which are reported with as - * much resolution as the system can muster. In some cases this - * resolution may depend on the underlying clock hardware and - * may not be quantifiable until run time, and only then is the - * necessary code is written. The standard says we should say - * something about this issue in the documentation... - * - * FUNCTIONS: The CLOCKs structure defines possible functions to - * handle various clock functions. - * - * The standard POSIX timer management code assumes the - * following: 1.) The k_itimer struct (sched.h) is used for - * the timer. 2.) The list, it_lock, it_clock, it_id and - * it_pid fields are not modified by timer code. - * - * Permissions: It is assumed that the clock_settime() function defined - * for each clock will take care of permission checks. Some - * clocks may be set able by any user (i.e. local process - * clocks) others not. Currently the only set able clock we - * have is CLOCK_REALTIME and its high res counter part, both of - * which we beg off on and pass to do_sys_settimeofday(). - */ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags); #define lock_timer(tid, flags) \ @@ -121,9 +78,9 @@ static struct k_itimer *__posix_timers_find(struct hlist_head *head, { struct k_itimer *timer; - hlist_for_each_entry_rcu(timer, head, t_hash, - lockdep_is_held(&hash_lock)) { - if ((timer->it_signal == sig) && (timer->it_id == id)) + hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&hash_lock)) { + /* timer->it_signal can be set concurrently */ + if ((READ_ONCE(timer->it_signal) == sig) && (timer->it_id == id)) return timer; } return NULL; @@ -140,25 +97,30 @@ static struct k_itimer *posix_timer_by_id(timer_t id) static int posix_timer_add(struct k_itimer *timer) { struct signal_struct *sig = current->signal; - int first_free_id = sig->posix_timer_id; struct hlist_head *head; - int ret = -ENOENT; + unsigned int cnt, id; - do { + /* + * FIXME: Replace this by a per signal struct xarray once there is + * a plan to handle the resulting CRIU regression gracefully. + */ + for (cnt = 0; cnt <= INT_MAX; cnt++) { spin_lock(&hash_lock); - head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; - if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { + id = sig->next_posix_timer_id; + + /* Write the next ID back. Clamp it to the positive space */ + sig->next_posix_timer_id = (id + 1) & INT_MAX; + + head = &posix_timers_hashtable[hash(sig, id)]; + if (!__posix_timers_find(head, sig, id)) { hlist_add_head_rcu(&timer->t_hash, head); - ret = sig->posix_timer_id; + spin_unlock(&hash_lock); + return id; } - if (++sig->posix_timer_id < 0) - sig->posix_timer_id = 0; - if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) - /* Loop over all possible ids completed */ - ret = -EAGAIN; spin_unlock(&hash_lock); - } while (ret == -ENOENT); - return ret; + } + /* POSIX return code when no timer ID could be allocated */ + return -EAGAIN; } static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) @@ -166,7 +128,6 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) spin_unlock_irqrestore(&timr->it_lock, flags); } -/* Get clock_realtime */ static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_real_ts64(tp); @@ -178,7 +139,6 @@ static ktime_t posix_get_realtime_ktime(clockid_t which_clock) return ktime_get_real(); } -/* Set clock_realtime */ static int posix_clock_realtime_set(const clockid_t which_clock, const struct timespec64 *tp) { @@ -191,9 +151,6 @@ static int posix_clock_realtime_adj(const clockid_t which_clock, return do_adjtimex(t); } -/* - * Get monotonic time for posix timers - */ static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_ts64(tp); @@ -206,9 +163,6 @@ static ktime_t posix_get_monotonic_ktime(clockid_t which_clock) return ktime_get(); } -/* - * Get monotonic-raw time for posix timers - */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { ktime_get_raw_ts64(tp); @@ -216,7 +170,6 @@ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) return 0; } - static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_real_ts64(tp); @@ -267,9 +220,6 @@ static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) return 0; } -/* - * Initialize everything, well, just everything in Posix clocks/timers ;) - */ static __init int init_posix_timers(void) { posix_timers_cache = kmem_cache_create("posix_timers_cache", @@ -300,15 +250,9 @@ static void common_hrtimer_rearm(struct k_itimer *timr) } /* - * This function is exported for use by the signal deliver code. It is - * called just prior to the info block being released and passes that - * block to us. It's function is to update the overrun entry AND to - * restart the timer. It should only be called if the timer is to be - * restarted (i.e. we have flagged this in the sys_private entry of the - * info block). - * - * To protect against the timer going away while the interrupt is queued, - * we require that the it_requeue_pending flag be set. + * This function is called from the signal delivery code if + * info->si_sys_private is not zero, which indicates that the timer has to + * be rearmed. Restart the timer and update info::si_overrun. */ void posixtimer_rearm(struct kernel_siginfo *info) { @@ -357,18 +301,18 @@ int posix_timer_event(struct k_itimer *timr, int si_private) } /* - * This function gets called when a POSIX.1b interval timer expires. It - * is used as a callback from the kernel internal timer. The - * run_timer_list code ALWAYS calls with interrupts on. - - * This code is for CLOCK_REALTIME* and CLOCK_MONOTONIC* timers. + * This function gets called when a POSIX.1b interval timer expires from + * the HRTIMER interrupt (soft interrupt on RT kernels). + * + * Handles CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME and CLOCK_TAI + * based timers. */ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { + enum hrtimer_restart ret = HRTIMER_NORESTART; struct k_itimer *timr; unsigned long flags; int si_private = 0; - enum hrtimer_restart ret = HRTIMER_NORESTART; timr = container_of(timer, struct k_itimer, it.real.timer); spin_lock_irqsave(&timr->it_lock, flags); @@ -379,9 +323,10 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) if (posix_timer_event(timr, si_private)) { /* - * signal was not sent because of sig_ignor - * we will not get a call back to restart it AND - * it should be restarted. + * The signal was not queued due to SIG_IGN. As a + * consequence the timer is not going to be rearmed from + * the signal delivery path. But as a real signal handler + * can be installed later the timer must be rearmed here. */ if (timr->it_interval != 0) { ktime_t now = hrtimer_cb_get_time(timer); @@ -390,34 +335,35 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) * FIXME: What we really want, is to stop this * timer completely and restart it in case the * SIG_IGN is removed. This is a non trivial - * change which involves sighand locking - * (sigh !), which we don't want to do late in - * the release cycle. + * change to the signal handling code. + * + * For now let timers with an interval less than a + * jiffie expire every jiffie and recheck for a + * valid signal handler. + * + * This avoids interrupt starvation in case of a + * very small interval, which would expire the + * timer immediately again. + * + * Moving now ahead of time by one jiffie tricks + * hrtimer_forward() to expire the timer later, + * while it still maintains the overrun accuracy + * for the price of a slight inconsistency in the + * timer_gettime() case. This is at least better + * than a timer storm. * - * For now we just let timers with an interval - * less than a jiffie expire every jiffie to - * avoid softirq starvation in case of SIG_IGN - * and a very small interval, which would put - * the timer right back on the softirq pending - * list. By moving now ahead of time we trick - * hrtimer_forward() to expire the timer - * later, while we still maintain the overrun - * accuracy, but have some inconsistency in - * the timer_gettime() case. This is at least - * better than a starved softirq. A more - * complex fix which solves also another related - * inconsistency is already in the pipeline. + * Only required when high resolution timers are + * enabled as the periodic tick based timers are + * automatically aligned to the next tick. */ -#ifdef CONFIG_HIGH_RES_TIMERS - { - ktime_t kj = NSEC_PER_SEC / HZ; + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS)) { + ktime_t kj = TICK_NSEC; if (timr->it_interval < kj) now = ktime_add(now, kj); } -#endif - timr->it_overrun += hrtimer_forward(timer, now, - timr->it_interval); + + timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_requeue_pending; timr->it_active = 1; @@ -454,8 +400,8 @@ static struct pid *good_sigevent(sigevent_t * event) static struct k_itimer * alloc_posix_timer(void) { - struct k_itimer *tmr; - tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); + struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); + if (!tmr) return tmr; if (unlikely(!(tmr->sigq = sigqueue_alloc()))) { @@ -473,21 +419,21 @@ static void k_itimer_rcu_free(struct rcu_head *head) kmem_cache_free(posix_timers_cache, tmr); } -#define IT_ID_SET 1 -#define IT_ID_NOT_SET 0 -static void release_posix_timer(struct k_itimer *tmr, int it_id_set) +static void posix_timer_free(struct k_itimer *tmr) { - if (it_id_set) { - unsigned long flags; - spin_lock_irqsave(&hash_lock, flags); - hlist_del_rcu(&tmr->t_hash); - spin_unlock_irqrestore(&hash_lock, flags); - } put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); call_rcu(&tmr->rcu, k_itimer_rcu_free); } +static void posix_timer_unhash_and_free(struct k_itimer *tmr) +{ + spin_lock(&hash_lock); + hlist_del_rcu(&tmr->t_hash); + spin_unlock(&hash_lock); + posix_timer_free(tmr); +} + static int common_timer_create(struct k_itimer *new_timer) { hrtimer_init(&new_timer->it.real.timer, new_timer->it_clock, 0); @@ -501,7 +447,6 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, const struct k_clock *kc = clockid_to_kclock(which_clock); struct k_itimer *new_timer; int error, new_timer_id; - int it_id_set = IT_ID_NOT_SET; if (!kc) return -EINVAL; @@ -513,13 +458,18 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, return -EAGAIN; spin_lock_init(&new_timer->it_lock); + + /* + * Add the timer to the hash table. The timer is not yet valid + * because new_timer::it_signal is still NULL. The timer id is also + * not yet visible to user space. + */ new_timer_id = posix_timer_add(new_timer); if (new_timer_id < 0) { - error = new_timer_id; - goto out; + posix_timer_free(new_timer); + return new_timer_id; } - it_id_set = IT_ID_SET; new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; @@ -547,30 +497,33 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->sigq->info.si_tid = new_timer->it_id; new_timer->sigq->info.si_code = SI_TIMER; - if (copy_to_user(created_timer_id, - &new_timer_id, sizeof (new_timer_id))) { + if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) { error = -EFAULT; goto out; } - + /* + * After succesful copy out, the timer ID is visible to user space + * now but not yet valid because new_timer::signal is still NULL. + * + * Complete the initialization with the clock specific create + * callback. + */ error = kc->timer_create(new_timer); if (error) goto out; spin_lock_irq(¤t->sighand->siglock); - new_timer->it_signal = current->signal; + /* This makes the timer valid in the hash table */ + WRITE_ONCE(new_timer->it_signal, current->signal); list_add(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); - - return 0; /* - * In the case of the timer belonging to another task, after - * the task is unlocked, the timer is owned by the other task - * and may cease to exist at any time. Don't use or modify - * new_timer after the unlock call. + * After unlocking sighand::siglock @new_timer is subject to + * concurrent removal and cannot be touched anymore */ + return 0; out: - release_posix_timer(new_timer, it_id_set); + posix_timer_unhash_and_free(new_timer); return error; } @@ -604,13 +557,6 @@ COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, } #endif -/* - * Locking issues: We need to protect the result of the id look up until - * we get the timer locked down so it is not deleted under us. The - * removal is done under the idr spinlock so we use that here to bridge - * the find to the timer lock. To avoid a dead lock, the timer id MUST - * be release with out holding the timer lock. - */ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; @@ -622,10 +568,35 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) if ((unsigned long long)timer_id > INT_MAX) return NULL; + /* + * The hash lookup and the timers are RCU protected. + * + * Timers are added to the hash in invalid state where + * timr::it_signal == NULL. timer::it_signal is only set after the + * rest of the initialization succeeded. + * + * Timer destruction happens in steps: + * 1) Set timr::it_signal to NULL with timr::it_lock held + * 2) Release timr::it_lock + * 3) Remove from the hash under hash_lock + * 4) Call RCU for removal after the grace period + * + * Holding rcu_read_lock() accross the lookup ensures that + * the timer cannot be freed. + * + * The lookup validates locklessly that timr::it_signal == + * current::it_signal and timr::it_id == @timer_id. timr::it_id + * can't change, but timr::it_signal becomes NULL during + * destruction. + */ rcu_read_lock(); timr = posix_timer_by_id(timer_id); if (timr) { spin_lock_irqsave(&timr->it_lock, *flags); + /* + * Validate under timr::it_lock that timr::it_signal is + * still valid. Pairs with #1 above. + */ if (timr->it_signal == current->signal) { rcu_read_unlock(); return timr; @@ -652,20 +623,16 @@ static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now) } /* - * Get the time remaining on a POSIX.1b interval timer. This function - * is ALWAYS called with spin_lock_irq on the timer, thus it must not - * mess with irq. + * Get the time remaining on a POSIX.1b interval timer. * - * We have a couple of messes to clean up here. First there is the case - * of a timer that has a requeue pending. These timers should appear to - * be in the timer list with an expiry as if we were to requeue them - * now. + * Two issues to handle here: * - * The second issue is the SIGEV_NONE timer which may be active but is - * not really ever put in the timer list (to save system resources). - * This timer may be expired, and if so, we will do it here. Otherwise - * it is the same as a requeue pending timer WRT to what we should - * report. + * 1) The timer has a requeue pending. The return value must appear as + * if the timer has been requeued right now. + * + * 2) The timer is a SIGEV_NONE timer. These timers are never enqueued + * into the hrtimer queue and therefore never expired. Emulate expiry + * here taking #1 into account. */ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { @@ -681,8 +648,12 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) cur_setting->it_interval = ktime_to_timespec64(iv); } else if (!timr->it_active) { /* - * SIGEV_NONE oneshot timers are never queued. Check them - * below. + * SIGEV_NONE oneshot timers are never queued and therefore + * timr->it_active is always false. The check below + * vs. remaining time will handle this case. + * + * For all other timers there is nothing to update here, so + * return. */ if (!sig_none) return; @@ -691,18 +662,29 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) now = kc->clock_get_ktime(timr->it_clock); /* - * When a requeue is pending or this is a SIGEV_NONE timer move the - * expiry time forward by intervals, so expiry is > now. + * If this is an interval timer and either has requeue pending or + * is a SIGEV_NONE timer move the expiry time forward by intervals, + * so expiry is > now. */ if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none)) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); - /* Return 0 only, when the timer is expired and not pending */ + /* + * As @now is retrieved before a possible timer_forward() and + * cannot be reevaluated by the compiler @remaining is based on the + * same @now value. Therefore @remaining is consistent vs. @now. + * + * Consequently all interval timers, i.e. @iv > 0, cannot have a + * remaining time <= 0 because timer_forward() guarantees to move + * them forward so that the next timer expiry is > @now. + */ if (remaining <= 0) { /* - * A single shot SIGEV_NONE timer must return 0, when - * it is expired ! + * A single shot SIGEV_NONE timer must return 0, when it is + * expired! Timers which have a real signal delivery mode + * must return a remaining time greater than 0 because the + * signal has not yet been delivered. */ if (!sig_none) cur_setting->it_value.tv_nsec = 1; @@ -711,11 +693,10 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) } } -/* Get the time remaining on a POSIX.1b interval timer. */ static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) { - struct k_itimer *timr; const struct k_clock *kc; + struct k_itimer *timr; unsigned long flags; int ret = 0; @@ -765,20 +746,29 @@ SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, #endif -/* - * Get the number of overruns of a POSIX.1b interval timer. This is to - * be the overrun of the timer last delivered. At the same time we are - * accumulating overruns on the next timer. The overrun is frozen when - * the signal is delivered, either at the notify time (if the info block - * is not queued) or at the actual delivery time (as we are informed by - * the call back to posixtimer_rearm(). So all we need to do is - * to pick up the frozen overrun. +/** + * sys_timer_getoverrun - Get the number of overruns of a POSIX.1b interval timer + * @timer_id: The timer ID which identifies the timer + * + * The "overrun count" of a timer is one plus the number of expiration + * intervals which have elapsed between the first expiry, which queues the + * signal and the actual signal delivery. On signal delivery the "overrun + * count" is calculated and cached, so it can be returned directly here. + * + * As this is relative to the last queued signal the returned overrun count + * is meaningless outside of the signal delivery path and even there it + * does not accurately reflect the current state when user space evaluates + * it. + * + * Returns: + * -EINVAL @timer_id is invalid + * 1..INT_MAX The number of overruns related to the last delivered signal */ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) { struct k_itimer *timr; - int overrun; unsigned long flags; + int overrun; timr = lock_timer(timer_id, &flags); if (!timr) @@ -831,10 +821,18 @@ static void common_timer_wait_running(struct k_itimer *timer) } /* - * On PREEMPT_RT this prevent priority inversion against softirq kthread in - * case it gets preempted while executing a timer callback. See comments in - * hrtimer_cancel_wait_running. For PREEMPT_RT=n this just results in a - * cpu_relax(). + * On PREEMPT_RT this prevents priority inversion and a potential livelock + * against the ksoftirqd thread in case that ksoftirqd gets preempted while + * executing a hrtimer callback. + * + * See the comments in hrtimer_cancel_wait_running(). For PREEMPT_RT=n this + * just results in a cpu_relax(). + * + * For POSIX CPU timers with CONFIG_POSIX_CPU_TIMERS_TASK_WORK=n this is + * just a cpu_relax(). With CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y this + * prevents spinning on an eventually scheduled out task and a livelock + * when the task which tries to delete or disarm the timer has preempted + * the task which runs the expiry in task work context. */ static struct k_itimer *timer_wait_running(struct k_itimer *timer, unsigned long *flags) @@ -943,8 +941,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, const struct __kernel_itimerspec __user *, new_setting, struct __kernel_itimerspec __user *, old_setting) { - struct itimerspec64 new_spec, old_spec; - struct itimerspec64 *rtn = old_setting ? &old_spec : NULL; + struct itimerspec64 new_spec, old_spec, *rtn; int error = 0; if (!new_setting) @@ -953,6 +950,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, if (get_itimerspec64(&new_spec, new_setting)) return -EFAULT; + rtn = old_setting ? &old_spec : NULL; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old_setting) { if (put_itimerspec64(&old_spec, old_setting)) @@ -1026,38 +1024,71 @@ retry_delete: list_del(&timer->list); spin_unlock(¤t->sighand->siglock); /* - * This keeps any tasks waiting on the spin lock from thinking - * they got something (see the lock code above). + * A concurrent lookup could check timer::it_signal lockless. It + * will reevaluate with timer::it_lock held and observe the NULL. */ - timer->it_signal = NULL; + WRITE_ONCE(timer->it_signal, NULL); unlock_timer(timer, flags); - release_posix_timer(timer, IT_ID_SET); + posix_timer_unhash_and_free(timer); return 0; } /* - * return timer owned by the process, used by exit_itimers + * Delete a timer if it is armed, remove it from the hash and schedule it + * for RCU freeing. */ static void itimer_delete(struct k_itimer *timer) { -retry_delete: - spin_lock_irq(&timer->it_lock); + unsigned long flags; + /* + * irqsave is required to make timer_wait_running() work. + */ + spin_lock_irqsave(&timer->it_lock, flags); + +retry_delete: + /* + * Even if the timer is not longer accessible from other tasks + * it still might be armed and queued in the underlying timer + * mechanism. Worse, that timer mechanism might run the expiry + * function concurrently. + */ if (timer_delete_hook(timer) == TIMER_RETRY) { - spin_unlock_irq(&timer->it_lock); + /* + * Timer is expired concurrently, prevent livelocks + * and pointless spinning on RT. + * + * timer_wait_running() drops timer::it_lock, which opens + * the possibility for another task to delete the timer. + * + * That's not possible here because this is invoked from + * do_exit() only for the last thread of the thread group. + * So no other task can access and delete that timer. + */ + if (WARN_ON_ONCE(timer_wait_running(timer, &flags) != timer)) + return; + goto retry_delete; } list_del(&timer->list); - spin_unlock_irq(&timer->it_lock); - release_posix_timer(timer, IT_ID_SET); + /* + * Setting timer::it_signal to NULL is technically not required + * here as nothing can access the timer anymore legitimately via + * the hash table. Set it to NULL nevertheless so that all deletion + * paths are consistent. + */ + WRITE_ONCE(timer->it_signal, NULL); + + spin_unlock_irqrestore(&timer->it_lock, flags); + posix_timer_unhash_and_free(timer); } /* - * This is called by do_exit or de_thread, only when nobody else can - * modify the signal->posix_timers list. Yet we need sighand->siglock - * to prevent the race with /proc/pid/timers. + * Invoked from do_exit() when the last thread of a thread group exits. + * At that point no other task can access the timers of the dying + * task anymore. */ void exit_itimers(struct task_struct *tsk) { @@ -1067,10 +1098,12 @@ void exit_itimers(struct task_struct *tsk) if (list_empty(&tsk->signal->posix_timers)) return; + /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); list_replace_init(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); + /* The timers are not longer accessible via tsk::signal */ while (!list_empty(&timers)) { tmr = list_first_entry(&timers, struct k_itimer, list); itimer_delete(tmr); @@ -1089,6 +1122,10 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, if (get_timespec64(&new_tp, tp)) return -EFAULT; + /* + * Permission checks have to be done inside the clock specific + * setter callback. + */ return kc->clock_set(which_clock, &new_tp); } @@ -1139,6 +1176,79 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, return err; } +/** + * sys_clock_getres - Get the resolution of a clock + * @which_clock: The clock to get the resolution for + * @tp: Pointer to a a user space timespec64 for storage + * + * POSIX defines: + * + * "The clock_getres() function shall return the resolution of any + * clock. Clock resolutions are implementation-defined and cannot be set by + * a process. If the argument res is not NULL, the resolution of the + * specified clock shall be stored in the location pointed to by res. If + * res is NULL, the clock resolution is not returned. If the time argument + * of clock_settime() is not a multiple of res, then the value is truncated + * to a multiple of res." + * + * Due to the various hardware constraints the real resolution can vary + * wildly and even change during runtime when the underlying devices are + * replaced. The kernel also can use hardware devices with different + * resolutions for reading the time and for arming timers. + * + * The kernel therefore deviates from the POSIX spec in various aspects: + * + * 1) The resolution returned to user space + * + * For CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_BOOTTIME, CLOCK_TAI, + * CLOCK_REALTIME_ALARM, CLOCK_BOOTTIME_ALAREM and CLOCK_MONOTONIC_RAW + * the kernel differentiates only two cases: + * + * I) Low resolution mode: + * + * When high resolution timers are disabled at compile or runtime + * the resolution returned is nanoseconds per tick, which represents + * the precision at which timers expire. + * + * II) High resolution mode: + * + * When high resolution timers are enabled the resolution returned + * is always one nanosecond independent of the actual resolution of + * the underlying hardware devices. + * + * For CLOCK_*_ALARM the actual resolution depends on system + * state. When system is running the resolution is the same as the + * resolution of the other clocks. During suspend the actual + * resolution is the resolution of the underlying RTC device which + * might be way less precise than the clockevent device used during + * running state. + * + * For CLOCK_REALTIME_COARSE and CLOCK_MONOTONIC_COARSE the resolution + * returned is always nanoseconds per tick. + * + * For CLOCK_PROCESS_CPUTIME and CLOCK_THREAD_CPUTIME the resolution + * returned is always one nanosecond under the assumption that the + * underlying scheduler clock has a better resolution than nanoseconds + * per tick. + * + * For dynamic POSIX clocks (PTP devices) the resolution returned is + * always one nanosecond. + * + * 2) Affect on sys_clock_settime() + * + * The kernel does not truncate the time which is handed in to + * sys_clock_settime(). The kernel internal timekeeping is always using + * nanoseconds precision independent of the clocksource device which is + * used to read the time from. The resolution of that device only + * affects the presicion of the time returned by sys_clock_gettime(). + * + * Returns: + * 0 Success. @tp contains the resolution + * -EINVAL @which_clock is not a valid clock ID + * -EFAULT Copying the resolution to @tp faulted + * -ENODEV Dynamic POSIX clock is not backed by a device + * -EOPNOTSUPP Dynamic POSIX clock does not support getres() + */ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, struct __kernel_timespec __user *, tp) { @@ -1230,7 +1340,7 @@ SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, #endif /* - * nanosleep for monotonic and realtime clocks + * sys_clock_nanosleep() for CLOCK_REALTIME and CLOCK_TAI */ static int common_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) @@ -1242,8 +1352,13 @@ static int common_nsleep(const clockid_t which_clock, int flags, which_clock); } +/* + * sys_clock_nanosleep() for CLOCK_MONOTONIC and CLOCK_BOOTTIME + * + * Absolute nanosleeps for these clocks are time-namespace adjusted. + */ static int common_nsleep_timens(const clockid_t which_clock, int flags, - const struct timespec64 *rqtp) + const struct timespec64 *rqtp) { ktime_t texp = timespec64_to_ktime(*rqtp); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 65b8658da829..e9138cd7a0f5 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -218,19 +218,8 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - ktime_t next_p; - u32 rem; - tick_do_timer_cpu = cpu; - - next_p = ktime_get(); - div_u64_rem(next_p, TICK_NSEC, &rem); - if (rem) { - next_p -= rem; - next_p += TICK_NSEC; - } - - tick_next_period = next_p; + tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* * The boot CPU may be nohz_full, in which case set diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 52254679ec48..4df14db4da49 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -161,8 +161,19 @@ static ktime_t tick_init_jiffy_update(void) raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ - if (last_jiffies_update == 0) + if (last_jiffies_update == 0) { + u32 rem; + + /* + * Ensure that the tick is aligned to a multiple of + * TICK_NSEC. + */ + div_u64_rem(tick_next_period, TICK_NSEC, &rem); + if (rem) + tick_next_period += TICK_NSEC - rem; + last_jiffies_update = tick_next_period; + } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); @@ -1030,7 +1041,7 @@ static bool report_idle_softirq(void) return false; } - if (ratelimit < 10) + if (ratelimit >= 10) return false; /* On RT, softirqs handling may be waiting on some lock */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 64a4dde073ef..5d2c5678b66f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5199,7 +5199,7 @@ static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, .read_iter = seq_read_iter, - .splice_read = generic_file_splice_read, + .splice_read = copy_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release, diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index dbb14705d0d3..8df0550415e7 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -50,6 +50,18 @@ #define EVENT_STATUS_OTHER BIT(7) /* + * User register flags are not allowed yet, keep them here until we are + * ready to expose them out to the user ABI. + */ +enum user_reg_flag { + /* Event will not delete upon last reference closing */ + USER_EVENT_REG_PERSIST = 1U << 0, + + /* This value or above is currently non-ABI */ + USER_EVENT_REG_MAX = 1U << 1, +}; + +/* * Stores the system name, tables, and locks for a group of events. This * allows isolation for events by various means. */ @@ -85,8 +97,10 @@ struct user_event { struct hlist_node node; struct list_head fields; struct list_head validators; + struct work_struct put_work; refcount_t refcnt; int min_size; + int reg_flags; char status; }; @@ -165,76 +179,151 @@ typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, - struct user_event **newuser); + struct user_event **newuser, int reg_flags); static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); static struct user_event_mm *user_event_mm_get_all(struct user_event *user); static void user_event_mm_put(struct user_event_mm *mm); +static int destroy_user_event(struct user_event *user); static u32 user_event_key(char *name) { return jhash(name, strlen(name), 0); } -static void user_event_group_destroy(struct user_event_group *group) +static struct user_event *user_event_get(struct user_event *user) { - kfree(group->system_name); - kfree(group); + refcount_inc(&user->refcnt); + + return user; } -static char *user_event_group_system_name(struct user_namespace *user_ns) +static void delayed_destroy_user_event(struct work_struct *work) { - char *system_name; - int len = sizeof(USER_EVENTS_SYSTEM) + 1; + struct user_event *user = container_of( + work, struct user_event, put_work); - if (user_ns != &init_user_ns) { + mutex_lock(&event_mutex); + + if (!refcount_dec_and_test(&user->refcnt)) + goto out; + + if (destroy_user_event(user)) { /* - * Unexpected at this point: - * We only currently support init_user_ns. - * When we enable more, this will trigger a failure so log. + * The only reason this would fail here is if we cannot + * update the visibility of the event. In this case the + * event stays in the hashtable, waiting for someone to + * attempt to delete it later. */ - pr_warn("user_events: Namespace other than init_user_ns!\n"); - return NULL; + pr_warn("user_events: Unable to delete event\n"); + refcount_set(&user->refcnt, 1); } +out: + mutex_unlock(&event_mutex); +} - system_name = kmalloc(len, GFP_KERNEL); +static void user_event_put(struct user_event *user, bool locked) +{ + bool delete; - if (!system_name) - return NULL; + if (unlikely(!user)) + return; - snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM); + /* + * When the event is not enabled for auto-delete there will always + * be at least 1 reference to the event. During the event creation + * we initially set the refcnt to 2 to achieve this. In those cases + * the caller must acquire event_mutex and after decrement check if + * the refcnt is 1, meaning this is the last reference. When auto + * delete is enabled, there will only be 1 ref, IE: refcnt will be + * only set to 1 during creation to allow the below checks to go + * through upon the last put. The last put must always be done with + * the event mutex held. + */ + if (!locked) { + lockdep_assert_not_held(&event_mutex); + delete = refcount_dec_and_mutex_lock(&user->refcnt, &event_mutex); + } else { + lockdep_assert_held(&event_mutex); + delete = refcount_dec_and_test(&user->refcnt); + } - return system_name; + if (!delete) + return; + + /* + * We now have the event_mutex in all cases, which ensures that + * no new references will be taken until event_mutex is released. + * New references come through find_user_event(), which requires + * the event_mutex to be held. + */ + + if (user->reg_flags & USER_EVENT_REG_PERSIST) { + /* We should not get here when persist flag is set */ + pr_alert("BUG: Auto-delete engaged on persistent event\n"); + goto out; + } + + /* + * Unfortunately we have to attempt the actual destroy in a work + * queue. This is because not all cases handle a trace_event_call + * being removed within the class->reg() operation for unregister. + */ + INIT_WORK(&user->put_work, delayed_destroy_user_event); + + /* + * Since the event is still in the hashtable, we have to re-inc + * the ref count to 1. This count will be decremented and checked + * in the work queue to ensure it's still the last ref. This is + * needed because a user-process could register the same event in + * between the time of event_mutex release and the work queue + * running the delayed destroy. If we removed the item now from + * the hashtable, this would result in a timing window where a + * user process would fail a register because the trace_event_call + * register would fail in the tracing layers. + */ + refcount_set(&user->refcnt, 1); + + if (WARN_ON_ONCE(!schedule_work(&user->put_work))) { + /* + * If we fail we must wait for an admin to attempt delete or + * another register/close of the event, whichever is first. + */ + pr_warn("user_events: Unable to queue delayed destroy\n"); + } +out: + /* Ensure if we didn't have event_mutex before we unlock it */ + if (!locked) + mutex_unlock(&event_mutex); } -static inline struct user_event_group -*user_event_group_from_user_ns(struct user_namespace *user_ns) +static void user_event_group_destroy(struct user_event_group *group) { - if (user_ns == &init_user_ns) - return init_group; - - return NULL; + kfree(group->system_name); + kfree(group); } -static struct user_event_group *current_user_event_group(void) +static char *user_event_group_system_name(void) { - struct user_namespace *user_ns = current_user_ns(); - struct user_event_group *group = NULL; + char *system_name; + int len = sizeof(USER_EVENTS_SYSTEM) + 1; - while (user_ns) { - group = user_event_group_from_user_ns(user_ns); + system_name = kmalloc(len, GFP_KERNEL); - if (group) - break; + if (!system_name) + return NULL; - user_ns = user_ns->parent; - } + snprintf(system_name, len, "%s", USER_EVENTS_SYSTEM); - return group; + return system_name; } -static struct user_event_group -*user_event_group_create(struct user_namespace *user_ns) +static struct user_event_group *current_user_event_group(void) +{ + return init_group; +} + +static struct user_event_group *user_event_group_create(void) { struct user_event_group *group; @@ -243,7 +332,7 @@ static struct user_event_group if (!group) return NULL; - group->system_name = user_event_group_system_name(user_ns); + group->system_name = user_event_group_system_name(); if (!group->system_name) goto error; @@ -259,12 +348,13 @@ error: return NULL; }; -static void user_event_enabler_destroy(struct user_event_enabler *enabler) +static void user_event_enabler_destroy(struct user_event_enabler *enabler, + bool locked) { list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ - refcount_dec(&enabler->event->refcnt); + user_event_put(enabler->event, locked); kfree(enabler); } @@ -326,7 +416,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) /* User asked for enabler to be removed during fault */ if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) { - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, true); goto out; } @@ -501,14 +591,12 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, if (!enabler) return false; - enabler->event = orig->event; + enabler->event = user_event_get(orig->event); enabler->addr = orig->addr; /* Only dup part of value (ignore future flags, etc) */ enabler->values = orig->values & ENABLE_VAL_DUP_MASK; - refcount_inc(&enabler->event->refcnt); - /* Enablers not exposed yet, RCU not required */ list_add(&enabler->mm_enablers_link, &mm->enablers); @@ -625,7 +713,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) struct user_event_enabler *enabler, *next; list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, false); mmdrop(mm->mm); kfree(mm); @@ -780,7 +868,7 @@ retry: * exit or run exec(), which includes forks and clones. */ if (!*write_result) { - refcount_inc(&enabler->event->refcnt); + user_event_get(user); list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } @@ -803,7 +891,12 @@ out: static __always_inline __must_check bool user_event_last_ref(struct user_event *user) { - return refcount_read(&user->refcnt) == 1; + int last = 0; + + if (user->reg_flags & USER_EVENT_REG_PERSIST) + last = 1; + + return refcount_read(&user->refcnt) == last; } static __always_inline __must_check @@ -842,7 +935,8 @@ static struct list_head *user_event_get_fields(struct trace_event_call *call) * Upon success user_event has its ref count increased by 1. */ static int user_event_parse_cmd(struct user_event_group *group, - char *raw_command, struct user_event **newuser) + char *raw_command, struct user_event **newuser, + int reg_flags) { char *name = raw_command; char *args = strpbrk(name, " "); @@ -856,7 +950,7 @@ static int user_event_parse_cmd(struct user_event_group *group, if (flags) *flags++ = '\0'; - return user_event_parse(group, name, args, flags, newuser); + return user_event_parse(group, name, args, flags, newuser, reg_flags); } static int user_field_array_size(const char *type) @@ -1367,10 +1461,8 @@ static struct user_event *find_user_event(struct user_event_group *group, *outkey = key; hash_for_each_possible(group->register_table, user, node, key) - if (!strcmp(EVENT_NAME(user), name)) { - refcount_inc(&user->refcnt); - return user; - } + if (!strcmp(EVENT_NAME(user), name)) + return user_event_get(user); return NULL; } @@ -1432,7 +1524,7 @@ static void user_event_ftrace(struct user_event *user, struct iov_iter *i, if (unlikely(!entry)) return; - if (unlikely(!copy_nofault(entry + 1, i->count, i))) + if (unlikely(i->count != 0 && !copy_nofault(entry + 1, i->count, i))) goto discard; if (!list_empty(&user->validators) && @@ -1473,7 +1565,7 @@ static void user_event_perf(struct user_event *user, struct iov_iter *i, perf_fetch_caller_regs(regs); - if (unlikely(!copy_nofault(perf_entry + 1, i->count, i))) + if (unlikely(i->count != 0 && !copy_nofault(perf_entry + 1, i->count, i))) goto discard; if (!list_empty(&user->validators) && @@ -1584,12 +1676,12 @@ static int user_event_reg(struct trace_event_call *call, return ret; inc: - refcount_inc(&user->refcnt); + user_event_get(user); update_enable_bit_for(user); return 0; dec: update_enable_bit_for(user); - refcount_dec(&user->refcnt); + user_event_put(user, true); return 0; } @@ -1620,10 +1712,11 @@ static int user_event_create(const char *raw_command) mutex_lock(&group->reg_mutex); - ret = user_event_parse_cmd(group, name, &user); + /* Dyn events persist, otherwise they would cleanup immediately */ + ret = user_event_parse_cmd(group, name, &user, USER_EVENT_REG_PERSIST); if (!ret) - refcount_dec(&user->refcnt); + user_event_put(user, false); mutex_unlock(&group->reg_mutex); @@ -1745,6 +1838,8 @@ static bool user_event_match(const char *system, const char *event, if (match && argc > 0) match = user_fields_match(user, argc, argv); + else if (match && argc == 0) + match = list_empty(&user->fields); return match; } @@ -1781,11 +1876,17 @@ static int user_event_trace_register(struct user_event *user) */ static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, - struct user_event **newuser) + struct user_event **newuser, int reg_flags) { int ret; u32 key; struct user_event *user; + int argc = 0; + char **argv; + + /* User register flags are not ready yet */ + if (reg_flags != 0 || flags != NULL) + return -EINVAL; /* Prevent dyn_event from racing */ mutex_lock(&event_mutex); @@ -1793,13 +1894,35 @@ static int user_event_parse(struct user_event_group *group, char *name, mutex_unlock(&event_mutex); if (user) { - *newuser = user; - /* - * Name is allocated by caller, free it since it already exists. - * Caller only worries about failure cases for freeing. - */ - kfree(name); + if (args) { + argv = argv_split(GFP_KERNEL, args, &argc); + if (!argv) { + ret = -ENOMEM; + goto error; + } + + ret = user_fields_match(user, argc, (const char **)argv); + argv_free(argv); + + } else + ret = list_empty(&user->fields); + + if (ret) { + *newuser = user; + /* + * Name is allocated by caller, free it since it already exists. + * Caller only worries about failure cases for freeing. + */ + kfree(name); + } else { + ret = -EADDRINUSE; + goto error; + } + return 0; +error: + user_event_put(user, false); + return ret; } user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT); @@ -1852,8 +1975,15 @@ static int user_event_parse(struct user_event_group *group, char *name, if (ret) goto put_user_lock; - /* Ensure we track self ref and caller ref (2) */ - refcount_set(&user->refcnt, 2); + user->reg_flags = reg_flags; + + if (user->reg_flags & USER_EVENT_REG_PERSIST) { + /* Ensure we track self ref and caller ref (2) */ + refcount_set(&user->refcnt, 2); + } else { + /* Ensure we track only caller ref (1) */ + refcount_set(&user->refcnt, 1); + } dyn_event_init(&user->devent, &user_event_dops); dyn_event_add(&user->devent, &user->call); @@ -1885,7 +2015,7 @@ static int delete_user_event(struct user_event_group *group, char *name) if (!user) return -ENOENT; - refcount_dec(&user->refcnt); + user_event_put(user, true); if (!user_event_last_ref(user)) return -EBUSY; @@ -2044,9 +2174,7 @@ static int user_events_ref_add(struct user_event_file_info *info, for (i = 0; i < count; ++i) new_refs->events[i] = refs->events[i]; - new_refs->events[i] = user; - - refcount_inc(&user->refcnt); + new_refs->events[i] = user_event_get(user); rcu_assign_pointer(info->refs, new_refs); @@ -2077,8 +2205,8 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) if (ret) return ret; - /* Ensure no flags, since we don't support any yet */ - if (kreg->flags != 0) + /* Ensure only valid flags */ + if (kreg->flags & ~(USER_EVENT_REG_MAX-1)) return -EINVAL; /* Ensure supported size */ @@ -2150,7 +2278,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, return ret; } - ret = user_event_parse_cmd(info->group, name, &user); + ret = user_event_parse_cmd(info->group, name, &user, reg.flags); if (ret) { kfree(name); @@ -2160,7 +2288,7 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, ret = user_events_ref_add(info, user); /* No longer need parse ref, ref_add either worked or not */ - refcount_dec(&user->refcnt); + user_event_put(user, false); /* Positive number is index and valid */ if (ret < 0) @@ -2309,7 +2437,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) - user_event_enabler_destroy(enabler); + user_event_enabler_destroy(enabler, true); /* Removed at least one */ ret = 0; @@ -2367,7 +2495,6 @@ static int user_events_release(struct inode *node, struct file *file) struct user_event_file_info *info = file->private_data; struct user_event_group *group; struct user_event_refs *refs; - struct user_event *user; int i; if (!info) @@ -2391,12 +2518,9 @@ static int user_events_release(struct inode *node, struct file *file) * The underlying user_events are ref counted, and cannot be freed. * After this decrement, the user_events may be freed elsewhere. */ - for (i = 0; i < refs->count; ++i) { - user = refs->events[i]; + for (i = 0; i < refs->count; ++i) + user_event_put(refs->events[i], false); - if (user) - refcount_dec(&user->refcnt); - } out: file->private_data = NULL; @@ -2577,7 +2701,7 @@ static int __init trace_events_user_init(void) if (!fault_cache) return -ENOMEM; - init_group = user_event_group_create(&init_user_ns); + init_group = user_event_group_create(); if (!init_group) { kmem_cache_destroy(fault_cache); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 15f05faaae44..1e33f367783e 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -847,7 +847,7 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c int ret; void *pos; - list_for_each_entry(field, head, link) { + list_for_each_entry_reverse(field, head, link) { trace_seq_printf(&iter->seq, " %s=", field->name); if (field->offset + field->size > iter->ent_size) { trace_seq_puts(&iter->seq, "<OVERFLOW>"); diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index e91cb4c2833f..d0b6b390ee42 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -42,7 +42,7 @@ MODULE_AUTHOR("Red Hat, Inc."); static inline bool lock_wqueue(struct watch_queue *wqueue) { spin_lock_bh(&wqueue->lock); - if (unlikely(wqueue->defunct)) { + if (unlikely(!wqueue->pipe)) { spin_unlock_bh(&wqueue->lock); return false; } @@ -104,9 +104,6 @@ static bool post_one_notification(struct watch_queue *wqueue, unsigned int head, tail, mask, note, offset, len; bool done = false; - if (!pipe) - return false; - spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; @@ -603,8 +600,11 @@ void watch_queue_clear(struct watch_queue *wqueue) rcu_read_lock(); spin_lock_bh(&wqueue->lock); - /* Prevent new notifications from being stored. */ - wqueue->defunct = true; + /* + * This pipe can be freed by callers like free_pipe_info(). + * Removing this reference also prevents new notifications. + */ + wqueue->pipe = NULL; while (!hlist_empty(&wqueue->watches)) { watch = hlist_entry(wqueue->watches.first, struct watch, queue_node); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4666a1a92a31..c913e333cce8 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -705,12 +705,17 @@ static void clear_work_data(struct work_struct *work) set_work_data(work, WORK_STRUCT_NO_POOL, 0); } +static inline struct pool_workqueue *work_struct_pwq(unsigned long data) +{ + return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); +} + static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + return work_struct_pwq(data); else return NULL; } @@ -738,8 +743,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work) assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) @@ -760,8 +764,7 @@ static int get_work_pool_id(struct work_struct *work) unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 984985c39c9b..a517256a270b 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -498,6 +498,15 @@ static void debug_print_object(struct debug_obj *obj, char *msg) const struct debug_obj_descr *descr = obj->descr; static int limit; + /* + * Don't report if lookup_object_or_alloc() by the current thread + * failed because lookup_object_or_alloc()/debug_objects_oom() by a + * concurrent thread turned off debug_objects_enabled and cleared + * the hash buckets. + */ + if (!debug_objects_enabled) + return; + if (limit < 5 && descr != descr_test) { void *hint = descr->debug_hint ? descr->debug_hint(obj->object) : NULL; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 960223ed9199..b667b1e2f688 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -14,8 +14,6 @@ #include <linux/scatterlist.h> #include <linux/instrumented.h> -#define PIPE_PARANOIA /* for now */ - /* covers ubuf and kbuf alike */ #define iterate_buf(i, n, base, len, off, __p, STEP) { \ size_t __maybe_unused off = 0; \ @@ -198,150 +196,6 @@ static int copyin(void *to, const void __user *from, size_t n) return res; } -#ifdef PIPE_PARANOIA -static bool sanity(const struct iov_iter *i) -{ - struct pipe_inode_info *pipe = i->pipe; - unsigned int p_head = pipe->head; - unsigned int p_tail = pipe->tail; - unsigned int p_occupancy = pipe_occupancy(p_head, p_tail); - unsigned int i_head = i->head; - unsigned int idx; - - if (i->last_offset) { - struct pipe_buffer *p; - if (unlikely(p_occupancy == 0)) - goto Bad; // pipe must be non-empty - if (unlikely(i_head != p_head - 1)) - goto Bad; // must be at the last buffer... - - p = pipe_buf(pipe, i_head); - if (unlikely(p->offset + p->len != abs(i->last_offset))) - goto Bad; // ... at the end of segment - } else { - if (i_head != p_head) - goto Bad; // must be right after the last buffer - } - return true; -Bad: - printk(KERN_ERR "idx = %d, offset = %d\n", i_head, i->last_offset); - printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n", - p_head, p_tail, pipe->ring_size); - for (idx = 0; idx < pipe->ring_size; idx++) - printk(KERN_ERR "[%p %p %d %d]\n", - pipe->bufs[idx].ops, - pipe->bufs[idx].page, - pipe->bufs[idx].offset, - pipe->bufs[idx].len); - WARN_ON(1); - return false; -} -#else -#define sanity(i) true -#endif - -static struct page *push_anon(struct pipe_inode_info *pipe, unsigned size) -{ - struct page *page = alloc_page(GFP_USER); - if (page) { - struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++); - *buf = (struct pipe_buffer) { - .ops = &default_pipe_buf_ops, - .page = page, - .offset = 0, - .len = size - }; - } - return page; -} - -static void push_page(struct pipe_inode_info *pipe, struct page *page, - unsigned int offset, unsigned int size) -{ - struct pipe_buffer *buf = pipe_buf(pipe, pipe->head++); - *buf = (struct pipe_buffer) { - .ops = &page_cache_pipe_buf_ops, - .page = page, - .offset = offset, - .len = size - }; - get_page(page); -} - -static inline int last_offset(const struct pipe_buffer *buf) -{ - if (buf->ops == &default_pipe_buf_ops) - return buf->len; // buf->offset is 0 for those - else - return -(buf->offset + buf->len); -} - -static struct page *append_pipe(struct iov_iter *i, size_t size, - unsigned int *off) -{ - struct pipe_inode_info *pipe = i->pipe; - int offset = i->last_offset; - struct pipe_buffer *buf; - struct page *page; - - if (offset > 0 && offset < PAGE_SIZE) { - // some space in the last buffer; add to it - buf = pipe_buf(pipe, pipe->head - 1); - size = min_t(size_t, size, PAGE_SIZE - offset); - buf->len += size; - i->last_offset += size; - i->count -= size; - *off = offset; - return buf->page; - } - // OK, we need a new buffer - *off = 0; - size = min_t(size_t, size, PAGE_SIZE); - if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) - return NULL; - page = push_anon(pipe, size); - if (!page) - return NULL; - i->head = pipe->head - 1; - i->last_offset = size; - i->count -= size; - return page; -} - -static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - struct pipe_inode_info *pipe = i->pipe; - unsigned int head = pipe->head; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - if (!sanity(i)) - return 0; - - if (offset && i->last_offset == -offset) { // could we merge it? - struct pipe_buffer *buf = pipe_buf(pipe, head - 1); - if (buf->page == page) { - buf->len += bytes; - i->last_offset -= bytes; - i->count -= bytes; - return bytes; - } - } - if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) - return 0; - - push_page(pipe, page, offset, bytes); - i->last_offset = -(offset + bytes); - i->head = head; - i->count -= bytes; - return bytes; -} - /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator @@ -446,46 +300,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_init); -// returns the offset in partial buffer (if any) -static inline unsigned int pipe_npages(const struct iov_iter *i, int *npages) -{ - struct pipe_inode_info *pipe = i->pipe; - int used = pipe->head - pipe->tail; - int off = i->last_offset; - - *npages = max((int)pipe->max_usage - used, 0); - - if (off > 0 && off < PAGE_SIZE) { // anon and not full - (*npages)++; - return off; - } - return 0; -} - -static size_t copy_pipe_to_iter(const void *addr, size_t bytes, - struct iov_iter *i) -{ - unsigned int off, chunk; - - if (unlikely(bytes > i->count)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - - if (!sanity(i)) - return 0; - - for (size_t n = bytes; n; n -= chunk) { - struct page *page = append_pipe(i, n, &off); - chunk = min_t(size_t, n, PAGE_SIZE - off); - if (!page) - return bytes - n; - memcpy_to_page(page, off, addr, chunk); - addr += chunk; - } - return bytes; -} - static __wsum csum_and_memcpy(void *to, const void *from, size_t len, __wsum sum, size_t off) { @@ -493,44 +307,10 @@ static __wsum csum_and_memcpy(void *to, const void *from, size_t len, return csum_block_add(sum, next, off); } -static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, - struct iov_iter *i, __wsum *sump) -{ - __wsum sum = *sump; - size_t off = 0; - unsigned int chunk, r; - - if (unlikely(bytes > i->count)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - - if (!sanity(i)) - return 0; - - while (bytes) { - struct page *page = append_pipe(i, bytes, &r); - char *p; - - if (!page) - break; - chunk = min_t(size_t, bytes, PAGE_SIZE - r); - p = kmap_local_page(page); - sum = csum_and_memcpy(p + r, addr + off, chunk, sum, off); - kunmap_local(p); - off += chunk; - bytes -= chunk; - } - *sump = sum; - return off; -} - size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; - if (unlikely(iov_iter_is_pipe(i))) - return copy_pipe_to_iter(addr, bytes, i); if (user_backed_iter(i)) might_fault(); iterate_and_advance(i, bytes, base, len, off, @@ -552,42 +332,6 @@ static int copyout_mc(void __user *to, const void *from, size_t n) return n; } -static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, - struct iov_iter *i) -{ - size_t xfer = 0; - unsigned int off, chunk; - - if (unlikely(bytes > i->count)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - - if (!sanity(i)) - return 0; - - while (bytes) { - struct page *page = append_pipe(i, bytes, &off); - unsigned long rem; - char *p; - - if (!page) - break; - chunk = min_t(size_t, bytes, PAGE_SIZE - off); - p = kmap_local_page(page); - rem = copy_mc_to_kernel(p + off, addr + xfer, chunk); - chunk -= rem; - kunmap_local(p); - xfer += chunk; - bytes -= chunk; - if (rem) { - iov_iter_revert(i, rem); - break; - } - } - return xfer; -} - /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address @@ -607,9 +351,8 @@ static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * - * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. - * Compare to copy_to_iter() where only ITER_IOVEC attempts might return - * a short copy. + * * ITER_KVEC and ITER_BVEC can return short copies. Compare to + * copy_to_iter() where only ITER_IOVEC attempts might return a short copy. * * Return: number of bytes copied (may be %0) */ @@ -617,8 +360,6 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; - if (unlikely(iov_iter_is_pipe(i))) - return copy_mc_pipe_to_iter(addr, bytes, i); if (user_backed_iter(i)) might_fault(); __iterate_and_advance(i, bytes, base, len, off, @@ -732,8 +473,6 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, return 0; if (WARN_ON_ONCE(i->data_source)) return 0; - if (unlikely(iov_iter_is_pipe(i))) - return copy_page_to_iter_pipe(page, offset, bytes, i); page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { @@ -764,8 +503,6 @@ size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t byte return 0; if (WARN_ON_ONCE(i->data_source)) return 0; - if (unlikely(iov_iter_is_pipe(i))) - return copy_page_to_iter_pipe(page, offset, bytes, i); page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { @@ -818,36 +555,8 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, } EXPORT_SYMBOL(copy_page_from_iter); -static size_t pipe_zero(size_t bytes, struct iov_iter *i) -{ - unsigned int chunk, off; - - if (unlikely(bytes > i->count)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - - if (!sanity(i)) - return 0; - - for (size_t n = bytes; n; n -= chunk) { - struct page *page = append_pipe(i, n, &off); - char *p; - - if (!page) - return bytes - n; - chunk = min_t(size_t, n, PAGE_SIZE - off); - p = kmap_local_page(page); - memset(p + off, 0, chunk); - kunmap_local(p); - } - return bytes; -} - size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (unlikely(iov_iter_is_pipe(i))) - return pipe_zero(bytes, i); iterate_and_advance(i, bytes, base, len, count, clear_user(base, len), memset(base, 0, len) @@ -878,32 +587,6 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t byt } EXPORT_SYMBOL(copy_page_from_iter_atomic); -static void pipe_advance(struct iov_iter *i, size_t size) -{ - struct pipe_inode_info *pipe = i->pipe; - int off = i->last_offset; - - if (!off && !size) { - pipe_discard_from(pipe, i->start_head); // discard everything - return; - } - i->count -= size; - while (1) { - struct pipe_buffer *buf = pipe_buf(pipe, i->head); - if (off) /* make it relative to the beginning of buffer */ - size += abs(off) - buf->offset; - if (size <= buf->len) { - buf->len = size; - i->last_offset = last_offset(buf); - break; - } - size -= buf->len; - i->head++; - off = 0; - } - pipe_discard_from(pipe, i->head + 1); // discard everything past this one -} - static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { const struct bio_vec *bvec, *end; @@ -955,8 +638,6 @@ void iov_iter_advance(struct iov_iter *i, size_t size) iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); - } else if (iov_iter_is_pipe(i)) { - pipe_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } @@ -970,26 +651,6 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; - if (unlikely(iov_iter_is_pipe(i))) { - struct pipe_inode_info *pipe = i->pipe; - unsigned int head = pipe->head; - - while (head > i->start_head) { - struct pipe_buffer *b = pipe_buf(pipe, --head); - if (unroll < b->len) { - b->len -= unroll; - i->last_offset = last_offset(b); - i->head = head; - return; - } - unroll -= b->len; - pipe_buf_release(pipe, b); - pipe->head--; - } - i->last_offset = 0; - i->head = head; - return; - } if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { @@ -1079,24 +740,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_bvec); -void iov_iter_pipe(struct iov_iter *i, unsigned int direction, - struct pipe_inode_info *pipe, - size_t count) -{ - BUG_ON(direction != READ); - WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size)); - *i = (struct iov_iter){ - .iter_type = ITER_PIPE, - .data_source = false, - .pipe = pipe, - .head = pipe->head, - .start_head = pipe->head, - .last_offset = 0, - .count = count - }; -} -EXPORT_SYMBOL(iov_iter_pipe); - /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. @@ -1224,19 +867,6 @@ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, if (iov_iter_is_bvec(i)) return iov_iter_aligned_bvec(i, addr_mask, len_mask); - if (iov_iter_is_pipe(i)) { - size_t size = i->count; - - if (size & len_mask) - return false; - if (size && i->last_offset > 0) { - if (i->last_offset & addr_mask) - return false; - } - - return true; - } - if (iov_iter_is_xarray(i)) { if (i->count & len_mask) return false; @@ -1307,14 +937,6 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); - if (iov_iter_is_pipe(i)) { - size_t size = i->count; - - if (size && i->last_offset > 0) - return size | i->last_offset; - return size; - } - if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; @@ -1367,36 +989,6 @@ static int want_pages_array(struct page ***res, size_t size, return count; } -static ssize_t pipe_get_pages(struct iov_iter *i, - struct page ***pages, size_t maxsize, unsigned maxpages, - size_t *start) -{ - unsigned int npages, count, off, chunk; - struct page **p; - size_t left; - - if (!sanity(i)) - return -EFAULT; - - *start = off = pipe_npages(i, &npages); - if (!npages) - return -EFAULT; - count = want_pages_array(pages, maxsize, off, min(npages, maxpages)); - if (!count) - return -ENOMEM; - p = *pages; - for (npages = 0, left = maxsize ; npages < count; npages++, left -= chunk) { - struct page *page = append_pipe(i, left, &off); - if (!page) - break; - chunk = min_t(size_t, left, PAGE_SIZE - off); - get_page(*p++ = page); - } - if (!npages) - return -EFAULT; - return maxsize - left; -} - static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { @@ -1490,8 +1082,7 @@ static struct page *first_bvec_segment(const struct iov_iter *i, static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, - unsigned int maxpages, size_t *start, - iov_iter_extraction_t extraction_flags) + unsigned int maxpages, size_t *start) { unsigned int n, gup_flags = 0; @@ -1501,8 +1092,6 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; - if (extraction_flags & ITER_ALLOW_P2PDMA) - gup_flags |= FOLL_PCI_P2PDMA; if (likely(user_backed_iter(i))) { unsigned long addr; @@ -1547,56 +1136,36 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, } return maxsize; } - if (iov_iter_is_pipe(i)) - return pipe_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; } -ssize_t iov_iter_get_pages(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start, iov_iter_extraction_t extraction_flags) +ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, + size_t maxsize, unsigned maxpages, size_t *start) { if (!maxpages) return 0; BUG_ON(!pages); - return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, - start, extraction_flags); -} -EXPORT_SYMBOL_GPL(iov_iter_get_pages); - -ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start) -{ - return iov_iter_get_pages(i, pages, maxsize, maxpages, start, 0); + return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages2); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start, iov_iter_extraction_t extraction_flags) +ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, + struct page ***pages, size_t maxsize, size_t *start) { ssize_t len; *pages = NULL; - len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start, - extraction_flags); + len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start); if (len <= 0) { kvfree(*pages); *pages = NULL; } return len; } -EXPORT_SYMBOL_GPL(iov_iter_get_pages_alloc); - -ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, - struct page ***pages, size_t maxsize, size_t *start) -{ - return iov_iter_get_pages_alloc(i, pages, maxsize, start, 0); -} EXPORT_SYMBOL(iov_iter_get_pages_alloc2); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, @@ -1638,9 +1207,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, } sum = csum_shift(csstate->csum, csstate->off); - if (unlikely(iov_iter_is_pipe(i))) - bytes = csum_and_copy_to_pipe_iter(addr, bytes, i, &sum); - else iterate_and_advance(i, bytes, base, len, off, ({ + iterate_and_advance(i, bytes, base, len, off, ({ next = csum_and_copy_to_user(addr + off, base, len); sum = csum_block_add(sum, next, off); next ? 0 : len; @@ -1725,15 +1292,6 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); - if (iov_iter_is_pipe(i)) { - int npages; - - if (!sanity(i)) - return 0; - - pipe_npages(i, &npages); - return min(npages, maxpages); - } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); @@ -1746,10 +1304,6 @@ EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; - if (unlikely(iov_iter_is_pipe(new))) { - WARN_ON(1); - return NULL; - } if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 049ba132f7ef..1a31065b2036 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -27,6 +27,8 @@ #include <linux/string.h> #include <linux/xarray.h> +#include "radix-tree.h" + /* * Radix tree node cache. */ diff --git a/lib/radix-tree.h b/lib/radix-tree.h new file mode 100644 index 000000000000..40d5c03e2b09 --- /dev/null +++ b/lib/radix-tree.h @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* radix-tree helpers that are only shared with xarray */ + +struct kmem_cache; +struct rcu_head; + +extern struct kmem_cache *radix_tree_node_cachep; +extern void radix_tree_node_rcu_free(struct rcu_head *head); diff --git a/lib/raid6/neon.h b/lib/raid6/neon.h new file mode 100644 index 000000000000..2ca41ee9b499 --- /dev/null +++ b/lib/raid6/neon.h @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +void raid6_neon1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon1_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon2_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon4_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon8_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp, + uint8_t *dq, const uint8_t *pbmul, + const uint8_t *qmul); + +void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq, + const uint8_t *qmul); + + diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc index b7c68030da4f..355270af0cd6 100644 --- a/lib/raid6/neon.uc +++ b/lib/raid6/neon.uc @@ -25,6 +25,7 @@ */ #include <arm_neon.h> +#include "neon.h" typedef uint8x16_t unative_t; diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c index d6fba8bf8c0a..1bfc14174d4d 100644 --- a/lib/raid6/recov_neon.c +++ b/lib/raid6/recov_neon.c @@ -8,6 +8,7 @@ #ifdef __KERNEL__ #include <asm/neon.h> +#include "neon.h" #else #define kernel_neon_begin() #define kernel_neon_end() @@ -19,13 +20,6 @@ static int raid6_has_neon(void) return cpu_has_neon(); } -void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp, - uint8_t *dq, const uint8_t *pbmul, - const uint8_t *qmul); - -void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq, - const uint8_t *qmul); - static void raid6_2data_recov_neon(int disks, size_t bytes, int faila, int failb, void **ptrs) { diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c index 90eb80d43790..f9e7e8f5a151 100644 --- a/lib/raid6/recov_neon_inner.c +++ b/lib/raid6/recov_neon_inner.c @@ -5,6 +5,7 @@ */ #include <arm_neon.h> +#include "neon.h" #ifdef CONFIG_ARM /* diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 9dd9745d365f..3718d9886407 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -369,7 +369,7 @@ vm_map_ram_test(void) int i; map_nr_pages = nr_pages > 0 ? nr_pages:1; - pages = kmalloc(map_nr_pages * sizeof(struct page), GFP_KERNEL); + pages = kcalloc(map_nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) return -1; diff --git a/lib/xarray.c b/lib/xarray.c index ea9ce1f0b386..2071a3718f4e 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -12,6 +12,8 @@ #include <linux/slab.h> #include <linux/xarray.h> +#include "radix-tree.h" + /* * Coding conventions in this file: * @@ -247,10 +249,6 @@ void *xas_load(struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_load); -/* Move the radix tree node cache here */ -extern struct kmem_cache *radix_tree_node_cachep; -extern void radix_tree_node_rcu_free(struct rcu_head *head); - #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) diff --git a/mm/damon/core.c b/mm/damon/core.c index d9ef62047bf5..91cff7f2997e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -551,6 +551,8 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) return -EINVAL; if (attrs->min_nr_regions > attrs->max_nr_regions) return -EINVAL; + if (attrs->sample_interval > attrs->aggr_interval) + return -EINVAL; damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; diff --git a/mm/filemap.c b/mm/filemap.c index b4c9bd368b7e..00f01d8ead47 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1760,7 +1760,9 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). - * In the rare case of index wrap-around, 0 will be returned. + * In the rare case of index wrap-around, 0 will be returned. 0 will also + * be returned if index == 0 and there is a gap at the index. We can not + * wrap-around if passed index == 0. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1770,12 +1772,13 @@ pgoff_t page_cache_next_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == 0) - break; + return xas.xa_index; + if (xas.xa_index == 0 && index != 0) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index + 1; } EXPORT_SYMBOL(page_cache_next_miss); @@ -1796,7 +1799,9 @@ EXPORT_SYMBOL(page_cache_next_miss); * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). - * In the rare case of wrap-around, ULONG_MAX will be returned. + * In the rare case of wrap-around, ULONG_MAX will be returned. ULONG_MAX + * will also be returned if index == ULONG_MAX and there is a gap at the + * index. We can not wrap-around if passed index == ULONG_MAX. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) @@ -1806,12 +1811,13 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) - break; - if (xas.xa_index == ULONG_MAX) - break; + return xas.xa_index; + if (xas.xa_index == ULONG_MAX && index != ULONG_MAX) + return xas.xa_index; } - return xas.xa_index; + /* No gaps in range and no wrap-around, return index beyond range */ + return xas.xa_index - 1; } EXPORT_SYMBOL(page_cache_prev_miss); @@ -2687,8 +2693,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; - error = filemap_get_pages(iocb, iter->count, &fbatch, - iov_iter_is_pipe(iter)); + error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; @@ -2872,9 +2877,24 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, return spliced; } -/* - * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into - * a pipe. +/** + * filemap_splice_read - Splice data from a file's pagecache into a pipe + * @in: The file to read from + * @ppos: Pointer to the file position to read from + * @pipe: The pipe to splice into + * @len: The amount to splice + * @flags: The SPLICE_F_* flags + * + * This function gets folios from a file's pagecache and splices them into the + * pipe. Readahead will be called as necessary to fill more folios. This may + * be used for blockdevs also. + * + * Return: On success, the number of bytes read will be returned and *@ppos + * will be updated if appropriate; 0 will be returned if there is no more data + * to be read; -EAGAIN will be returned if the pipe had no space, and some + * other negative error code will be returned on error. A short read may occur + * if the pipe has insufficient space, we reach the end of the data or we hit a + * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, @@ -2887,6 +2907,9 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, bool writably_mapped; int i, error = 0; + if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) + return 0; + init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; @@ -2900,7 +2923,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, do { cond_resched(); - if (*ppos >= i_size_read(file_inode(in))) + if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; @@ -2916,7 +2939,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ - isize = i_size_read(file_inode(in)); + isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); @@ -51,7 +51,8 @@ static inline void sanity_check_pinned_pages(struct page **pages, struct page *page = *pages; struct folio *folio = page_folio(page); - if (!folio_test_anon(folio)) + if (is_zero_page(page) || + !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); @@ -132,6 +133,13 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) struct folio *folio; /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return page_folio(page); + + /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. @@ -180,6 +188,8 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { + if (is_zero_folio(folio)) + return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); @@ -225,6 +235,13 @@ int __must_check try_grab_page(struct page *page, unsigned int flags) folio_ref_inc(folio); else if (flags & FOLL_PIN) { /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return 0; + + /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. @@ -258,6 +275,33 @@ void unpin_user_page(struct page *page) } EXPORT_SYMBOL(unpin_user_page); +/** + * folio_add_pin - Try to get an additional pin on a pinned folio + * @folio: The folio to be pinned + * + * Get an additional pin on a folio we already have a pin on. Makes no change + * if the folio is a zero_page. + */ +void folio_add_pin(struct folio *folio) +{ + if (is_zero_folio(folio)) + return; + + /* + * Similar to try_grab_folio(): be sure to *also* increment the normal + * page refcount field at least once, so that the page really is + * pinned. + */ + if (folio_test_large(folio)) { + WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); + folio_ref_inc(folio); + atomic_inc(&folio->_pincount); + } else { + WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + } +} + static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { @@ -3079,6 +3123,9 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) @@ -3110,6 +3157,9 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -3143,6 +3193,9 @@ EXPORT_SYMBOL(pin_user_pages_remote); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -3161,6 +3214,9 @@ EXPORT_SYMBOL(pin_user_pages); * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) diff --git a/mm/gup_test.c b/mm/gup_test.c index 8ae7307a1bb6..c0421b786dcd 100644 --- a/mm/gup_test.c +++ b/mm/gup_test.c @@ -381,6 +381,7 @@ static int gup_test_release(struct inode *inode, struct file *file) static const struct file_operations gup_test_fops = { .open = nonseekable_open, .unlocked_ioctl = gup_test_ioctl, + .compat_ioctl = compat_ptr_ioctl, .release = gup_test_release, }; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6b9d39d65b73..2d0d58fb4e7f 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2070,7 +2070,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); - xas_set(&xas, index); VM_BUG_ON_PAGE(page != xas_load(&xas), page); diff --git a/mm/memfd.c b/mm/memfd.c index 69b90c31d38c..e763e76f1106 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -371,12 +371,15 @@ SYSCALL_DEFINE2(memfd_create, inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; - *file_seals |= F_SEAL_EXEC; + if (file_seals) { + *file_seals &= ~F_SEAL_SEAL; + *file_seals |= F_SEAL_EXEC; + } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); - *file_seals &= ~F_SEAL_SEAL; + if (file_seals) + *file_seals &= ~F_SEAL_SEAL; } fd_install(fd, file); diff --git a/mm/mmap.c b/mm/mmap.c index 13678edaa22c..d600404580b2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2318,21 +2318,6 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, return __split_vma(vmi, vma, addr, new_below); } -static inline int munmap_sidetree(struct vm_area_struct *vma, - struct ma_state *mas_detach) -{ - vma_start_write(vma); - mas_set_range(mas_detach, vma->vm_start, vma->vm_end - 1); - if (mas_store_gfp(mas_detach, vma, GFP_KERNEL)) - return -ENOMEM; - - vma_mark_detached(vma, true); - if (vma->vm_flags & VM_LOCKED) - vma->vm_mm->locked_vm -= vma_pages(vma); - - return 0; -} - /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator @@ -2354,6 +2339,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct maple_tree mt_detach; int count = 0; int error = -ENOMEM; + unsigned long locked_vm = 0; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); @@ -2399,9 +2385,13 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, if (error) goto end_split_failed; } - error = munmap_sidetree(next, &mas_detach); - if (error) - goto munmap_sidetree_failed; + vma_start_write(next); + mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1); + if (mas_store_gfp(&mas_detach, next, GFP_KERNEL)) + goto munmap_gather_failed; + vma_mark_detached(next, true); + if (next->vm_flags & VM_LOCKED) + locked_vm += vma_pages(next); count++; #ifdef CONFIG_DEBUG_VM_MAPLE_TREE @@ -2447,10 +2437,12 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, } #endif /* Point of no return */ + error = -ENOMEM; vma_iter_set(vmi, start); if (vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL)) - return -ENOMEM; + goto clear_tree_failed; + mm->locked_vm -= locked_vm; mm->map_count -= count; /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or @@ -2480,9 +2472,14 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, validate_mm(mm); return downgrade ? 1 : 0; +clear_tree_failed: userfaultfd_error: -munmap_sidetree_failed: +munmap_gather_failed: end_split_failed: + mas_set(&mas_detach, 0); + mas_for_each(&mas_detach, next, end) + vma_mark_detached(next, false); + __mt_destroy(&mt_detach); start_split_failed: map_count_exceeded: diff --git a/mm/mprotect.c b/mm/mprotect.c index 92d3d3ca390a..c59e7561698c 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -867,7 +867,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } tlb_finish_mmu(&tlb); - if (!error && vma_iter_end(&vmi) < end) + if (!error && tmp < end) error = -ENOMEM; out: diff --git a/mm/page_io.c b/mm/page_io.c index 87b682d18850..684cd3c7b59b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -338,7 +338,7 @@ static void swap_writepage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc)); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); bio_associate_blkg_from_page(&bio, page); count_swpout_vm_event(page); @@ -360,7 +360,7 @@ static void swap_writepage_bdev_async(struct page *page, GFP_NOIO); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_write; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); bio_associate_blkg_from_page(bio, page); count_swpout_vm_event(page); @@ -468,7 +468,7 @@ static void swap_readpage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); /* * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. @@ -488,7 +488,7 @@ static void swap_readpage_bdev_async(struct page *page, bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_read; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); count_vm_event(PSWPIN); submit_bio(bio); } diff --git a/mm/shmem.c b/mm/shmem.c index e40a08c5c6d7..1f504ed982cf 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2731,6 +2731,138 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) return retval ? retval : error; } +static bool zero_pipe_buf_get(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return true; +} + +static void zero_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ +} + +static bool zero_pipe_buf_try_steal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return false; +} + +static const struct pipe_buf_operations zero_pipe_buf_ops = { + .release = zero_pipe_buf_release, + .try_steal = zero_pipe_buf_try_steal, + .get = zero_pipe_buf_get, +}; + +static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe, + loff_t fpos, size_t size) +{ + size_t offset = fpos & ~PAGE_MASK; + + size = min_t(size_t, size, PAGE_SIZE - offset); + + if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + struct pipe_buffer *buf = pipe_head_buf(pipe); + + *buf = (struct pipe_buffer) { + .ops = &zero_pipe_buf_ops, + .page = ZERO_PAGE(0), + .offset = offset, + .len = size, + }; + pipe->head++; + } + + return size; +} + +static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags) +{ + struct inode *inode = file_inode(in); + struct address_space *mapping = inode->i_mapping; + struct folio *folio = NULL; + size_t total_spliced = 0, used, npages, n, part; + loff_t isize; + int error = 0; + + /* Work out how much data we can actually add into the pipe */ + used = pipe_occupancy(pipe->head, pipe->tail); + npages = max_t(ssize_t, pipe->max_usage - used, 0); + len = min_t(size_t, len, npages * PAGE_SIZE); + + do { + if (*ppos >= i_size_read(inode)) + break; + + error = shmem_get_folio(inode, *ppos / PAGE_SIZE, &folio, SGP_READ); + if (error) { + if (error == -EINVAL) + error = 0; + break; + } + if (folio) { + folio_unlock(folio); + + if (folio_test_hwpoison(folio)) { + error = -EIO; + break; + } + } + + /* + * i_size must be checked after we know the pages are Uptodate. + * + * Checking i_size after the check allows us to calculate + * the correct value for "nr", which means the zero-filled + * part of the page is not copied back to userspace (unless + * another truncate extends the file - this is desired though). + */ + isize = i_size_read(inode); + if (unlikely(*ppos >= isize)) + break; + part = min_t(loff_t, isize - *ppos, len); + + if (folio) { + /* + * If users can be writing to this page using arbitrary + * virtual addresses, take care about potential aliasing + * before reading the page on the kernel side. + */ + if (mapping_writably_mapped(mapping)) + flush_dcache_folio(folio); + folio_mark_accessed(folio); + /* + * Ok, we have the page, and it's up-to-date, so we can + * now splice it into the pipe. + */ + n = splice_folio_into_pipe(pipe, folio, *ppos, part); + folio_put(folio); + folio = NULL; + } else { + n = splice_zeropage_into_pipe(pipe, *ppos, len); + } + + if (!n) + break; + len -= n; + total_spliced += n; + *ppos += n; + in->f_ra.prev_pos = *ppos; + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + break; + + cond_resched(); + } while (len); + + if (folio) + folio_put(folio); + + file_accessed(in); + return total_spliced ? total_spliced : error; +} + static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; @@ -3971,7 +4103,7 @@ static const struct file_operations shmem_file_operations = { .read_iter = shmem_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, - .splice_read = generic_file_splice_read, + .splice_read = shmem_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index fe10436d9911..3ab53fad8876 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -5,12 +5,10 @@ #include <linux/seq_file.h> #include <linux/shrinker.h> #include <linux/memcontrol.h> -#include <linux/srcu.h> /* defined in vmscan.c */ -extern struct mutex shrinker_mutex; +extern struct rw_semaphore shrinker_rwsem; extern struct list_head shrinker_list; -extern struct srcu_struct shrinker_srcu; static DEFINE_IDA(shrinker_debugfs_ida); static struct dentry *shrinker_debugfs_root; @@ -51,13 +49,18 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret = 0, nid, srcu_idx; + int ret, nid; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + kfree(count_per_node); + return ret; + } + rcu_read_lock(); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -88,7 +91,8 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); + up_read(&shrinker_rwsem); kfree(count_per_node); return ret; @@ -111,8 +115,9 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, .gfp_mask = GFP_KERNEL, }; struct mem_cgroup *memcg = NULL; - int nid, srcu_idx; + int nid; char kbuf[72]; + ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -141,7 +146,11 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - srcu_idx = srcu_read_lock(&shrinker_srcu); + ret = down_read_killable(&shrinker_rwsem); + if (ret) { + mem_cgroup_put(memcg); + return ret; + } sc.nid = nid; sc.memcg = memcg; @@ -150,7 +159,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); mem_cgroup_put(memcg); return size; @@ -168,7 +177,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -211,7 +220,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); old = shrinker->name; shrinker->name = new; @@ -229,7 +238,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); kfree_const(old); @@ -242,7 +251,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); kfree_const(shrinker->name); shrinker->name = NULL; @@ -271,14 +280,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 274bbf797480..6bc83060df9a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2539,7 +2539,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, p); } inode_lock(inode); @@ -2770,7 +2770,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); + BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; @@ -3221,7 +3221,7 @@ bad_swap: p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(p->bdev, p); } inode = NULL; destroy_swap_extents(p); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9683573f1225..1d13d71687d7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3098,11 +3098,20 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, * allocation request, free them via vfree() if any. */ if (area->nr_pages != nr_small_pages) { - /* vm_area_alloc_pages() can also fail due to a fatal signal */ - if (!fatal_signal_pending(current)) + /* + * vm_area_alloc_pages() can fail due to insufficient memory but + * also:- + * + * - a pending fatal signal + * - insufficient huge page-order pages + * + * Since we always retry allocations at order-0 in the huge page + * case a warning for either is spurious. + */ + if (!fatal_signal_pending(current) && page_order == 0) warn_alloc(gfp_mask, NULL, - "vmalloc error: size %lu, page order %u, failed to allocate pages", - area->nr_pages * PAGE_SIZE, page_order); + "vmalloc error: size %lu, failed to allocate pages", + area->nr_pages * PAGE_SIZE); goto fail; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 6d0cd2840cf0..5bf98d0a22c9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,7 @@ #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> -#include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -57,7 +57,6 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> -#include <linux/srcu.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -190,9 +189,7 @@ struct scan_control { int vm_swappiness = 60; LIST_HEAD(shrinker_list); -DEFINE_MUTEX(shrinker_mutex); -DEFINE_SRCU(shrinker_srcu); -static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0); +DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -211,21 +208,8 @@ static inline int shrinker_defer_size(int nr_items) static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { - return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu, - lockdep_is_held(&shrinker_mutex)); -} - -static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg, - int nid) -{ - return srcu_dereference(memcg->nodeinfo[nid]->shrinker_info, - &shrinker_srcu); -} - -static void free_shrinker_info_rcu(struct rcu_head *head) -{ - kvfree(container_of(head, struct shrinker_info, rcu)); + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_rwsem)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, @@ -266,7 +250,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); - call_srcu(&shrinker_srcu, &old->rcu, free_shrinker_info_rcu); + kvfree_rcu(old, rcu); } return 0; @@ -292,7 +276,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) int nid, size, ret = 0; int map_size, defer_size = 0; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); map_size = shrinker_map_size(shrinker_nr_max); defer_size = shrinker_defer_size(shrinker_nr_max); size = map_size + defer_size; @@ -308,7 +292,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) info->map_nr_max = shrinker_nr_max; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -324,7 +308,7 @@ static int expand_shrinker_info(int new_id) if (!root_mem_cgroup) goto out; - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); map_size = shrinker_map_size(new_nr_max); defer_size = shrinker_defer_size(new_nr_max); @@ -352,16 +336,15 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; - int srcu_idx; - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + rcu_read_lock(); + info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id, info->map); } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + rcu_read_unlock(); } } @@ -374,7 +357,8 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) if (mem_cgroup_disabled()) return -ENOSYS; - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); + /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -388,7 +372,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) shrinker->id = id; ret = 0; unlock: - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return ret; } @@ -398,7 +382,7 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - lockdep_assert_held(&shrinker_mutex); + lockdep_assert_held(&shrinker_rwsem); idr_remove(&shrinker_idr, id); } @@ -408,7 +392,7 @@ static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); } @@ -417,7 +401,7 @@ static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_srcu(memcg, nid); + info = shrinker_info_protected(memcg, nid); return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } @@ -433,7 +417,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - mutex_lock(&shrinker_mutex); + down_read(&shrinker_rwsem); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -442,7 +426,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) atomic_long_add(nr, &parent_info->nr_deferred[i]); } } - mutex_unlock(&shrinker_mutex); + up_read(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -743,9 +727,9 @@ void free_prealloced_shrinker(struct shrinker *shrinker) shrinker->name = NULL; #endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - mutex_lock(&shrinker_mutex); + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); return; } @@ -755,11 +739,11 @@ void free_prealloced_shrinker(struct shrinker *shrinker) void register_shrinker_prepared(struct shrinker *shrinker) { - mutex_lock(&shrinker_mutex); - list_add_tail_rcu(&shrinker->list, &shrinker_list); + down_write(&shrinker_rwsem); + list_add_tail(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); - mutex_unlock(&shrinker_mutex); + up_write(&shrinker_rwsem); } static int __register_shrinker(struct shrinker *shrinker) @@ -810,16 +794,13 @@ void unregister_shrinker(struct shrinker *shrinker) if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - mutex_lock(&shrinker_mutex); - list_del_rcu(&shrinker->list); + down_write(&shrinker_rwsem); + list_del(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); - mutex_unlock(&shrinker_mutex); - - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); + up_write(&shrinker_rwsem); shrinker_debugfs_remove(debugfs_entry, debugfs_id); @@ -831,13 +812,15 @@ EXPORT_SYMBOL(unregister_shrinker); /** * synchronize_shrinkers - Wait for all running shrinkers to complete. * - * This is useful to guarantee that all shrinker invocations have seen an - * update, before freeing memory. + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. */ void synchronize_shrinkers(void) { - atomic_inc(&shrinker_srcu_generation); - synchronize_srcu(&shrinker_srcu); + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); } EXPORT_SYMBOL(synchronize_shrinkers); @@ -946,20 +929,19 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, { struct shrinker_info *info; unsigned long ret, freed = 0; - int srcu_idx, generation; - int i = 0; + int i; if (!mem_cgroup_online(memcg)) return 0; -again: - srcu_idx = srcu_read_lock(&shrinker_srcu); - info = shrinker_info_srcu(memcg, nid); + if (!down_read_trylock(&shrinker_rwsem)) + return 0; + + info = shrinker_info_protected(memcg, nid); if (unlikely(!info)) goto unlock; - generation = atomic_read(&shrinker_srcu_generation); - for_each_set_bit_from(i, info->map, info->map_nr_max) { + for_each_set_bit(i, info->map, info->map_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1005,14 +987,14 @@ again: set_shrinker_bit(memcg, nid, i); } freed += ret; - if (atomic_read(&shrinker_srcu_generation) != generation) { - srcu_read_unlock(&shrinker_srcu, srcu_idx); - i++; - goto again; + + if (rwsem_is_contended(&shrinker_rwsem)) { + freed = freed ? : 1; + break; } } unlock: - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ @@ -1049,7 +1031,6 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, { unsigned long ret, freed = 0; struct shrinker *shrinker; - int srcu_idx, generation; /* * The root memcg might be allocated even though memcg is disabled @@ -1061,11 +1042,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - srcu_idx = srcu_read_lock(&shrinker_srcu); + if (!down_read_trylock(&shrinker_rwsem)) + goto out; - generation = atomic_read(&shrinker_srcu_generation); - list_for_each_entry_srcu(shrinker, &shrinker_list, list, - srcu_read_lock_held(&shrinker_srcu)) { + list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1076,14 +1056,19 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; freed += ret; - - if (atomic_read(&shrinker_srcu_generation) != generation) { + /* + * Bail out if someone want to register a new shrinker to + * prevent the registration from being stalled for long periods + * by parallel ongoing shrinking. + */ + if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } - srcu_read_unlock(&shrinker_srcu, srcu_idx); + up_read(&shrinker_rwsem); +out: cond_resched(); return freed; } diff --git a/mm/zswap.c b/mm/zswap.c index 59da2a415fbb..30092d9a3b23 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1174,9 +1174,16 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, goto reject; } + /* + * XXX: zswap reclaim does not work with cgroups yet. Without a + * cgroup-aware entry LRU, we will push out entries system-wide based on + * local cgroup limits. + */ objcg = get_obj_cgroup_from_page(page); - if (objcg && !obj_cgroup_may_zswap(objcg)) - goto shrink; + if (objcg && !obj_cgroup_may_zswap(objcg)) { + ret = -ENOMEM; + goto reject; + } /* reclaim space if needed */ if (zswap_is_full()) { diff --git a/net/core/sock.c b/net/core/sock.c index 24f2761bdb1d..6e5662ca00fe 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1362,12 +1362,6 @@ set_sndbuf: __sock_set_mark(sk, val); break; case SO_RCVMARK: - if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && - !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - sock_valbool_flag(sk, SOCK_RCVMARK, valbool); break; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a06b5641287a..b0ebf853cb07 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -191,6 +191,9 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) struct dccp_sock *dp = dccp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + pr_warn_once("DCCP is deprecated and scheduled to be removed in 2025, " + "please contact the netdev mailing list\n"); + icsk->icsk_rto = DCCP_TIMEOUT_INIT; icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index ab1afe67fd18..1afed89e03c0 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -403,6 +403,24 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) return 0; } +static struct dsa_port * +dsa_switch_preferred_default_local_cpu_port(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp; + + if (!ds->ops->preferred_default_local_cpu_port) + return NULL; + + cpu_dp = ds->ops->preferred_default_local_cpu_port(ds); + if (!cpu_dp) + return NULL; + + if (WARN_ON(!dsa_port_is_cpu(cpu_dp) || cpu_dp->ds != ds)) + return NULL; + + return cpu_dp; +} + /* Perform initial assignment of CPU ports to user ports and DSA links in the * fabric, giving preference to CPU ports local to each switch. Default to * using the first CPU port in the switch tree if the port does not have a CPU @@ -410,12 +428,16 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) */ static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) { - struct dsa_port *cpu_dp, *dp; + struct dsa_port *preferred_cpu_dp, *cpu_dp, *dp; list_for_each_entry(cpu_dp, &dst->ports, list) { if (!dsa_port_is_cpu(cpu_dp)) continue; + preferred_cpu_dp = dsa_switch_preferred_default_local_cpu_port(cpu_dp->ds); + if (preferred_cpu_dp && preferred_cpu_dp != cpu_dp) + continue; + /* Prefer a local CPU port */ dsa_switch_for_each_port(dp, cpu_dp->ds) { /* Prefer the first local CPU port found */ diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h index 8aeaadca844f..4dac965c99df 100644 --- a/net/handshake/handshake.h +++ b/net/handshake/handshake.h @@ -31,7 +31,6 @@ struct handshake_req { struct list_head hr_list; struct rhash_head hr_rhash; unsigned long hr_flags; - struct file *hr_file; const struct handshake_proto *hr_proto; struct sock *hr_sk; void (*hr_odestruct)(struct sock *sk); diff --git a/net/handshake/request.c b/net/handshake/request.c index d78d41abb3d9..94d5cef3e048 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -239,7 +239,6 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; - req->hr_file = sock->file; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); @@ -335,9 +334,6 @@ bool handshake_req_cancel(struct sock *sk) return false; } - /* Request accepted and waiting for DONE */ - fput(req->hr_file); - out_true: trace_handshake_cancel(net, req, sk); diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index e5d8439b9e45..c16db0b326fa 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -13,7 +13,7 @@ #define MAXNAME 32 #define WPAN_PHY_ENTRY __array(char, wpan_phy_name, MAXNAME) -#define WPAN_PHY_ASSIGN strlcpy(__entry->wpan_phy_name, \ +#define WPAN_PHY_ASSIGN strscpy(__entry->wpan_phy_name, \ wpan_phy_name(wpan_phy), \ MAXNAME) #define WPAN_PHY_PR_FMT "%s" diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 3969fa805679..ee848be59e65 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -340,6 +340,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 56d94d23b9e0..143f93a12f25 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -22,6 +22,8 @@ static int udplite_sk_init(struct sock *sk) { udp_init_sock(sk); udp_sk(sk)->pcflag = UDPLITE_BIT; + pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, " + "please contact the netdev mailing list\n"); return 0; } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index ad2afeef4f10..eac206a290d0 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -164,6 +164,7 @@ drop: kfree_skb(skb); return 0; } +EXPORT_SYMBOL(xfrm4_udp_encap_rcv); int xfrm4_rcv(struct sk_buff *skb) { diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 75c02992c520..772340268997 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -374,6 +374,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index c4835dbdfcff..f804c11e2146 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -114,7 +114,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || - (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if && + l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if)) return -EINVAL; ipcm6_init_sk(&ipc6, np); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 3bab0cc13697..8e010d07917a 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -8,6 +8,8 @@ * Changes: * Fixes: */ +#define pr_fmt(fmt) "UDPLite6: " fmt + #include <linux/export.h> #include <linux/proc_fs.h> #include "udp_impl.h" @@ -16,6 +18,8 @@ static int udplitev6_sk_init(struct sock *sk) { udpv6_init_sock(sk); udp_sk(sk)->pcflag = UDPLITE_BIT; + pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, " + "please contact the netdev mailing list\n"); return 0; } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 04cbeefd8982..4907ab241d6b 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -86,6 +86,9 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) __be32 *udpdata32; __u16 encap_type = up->encap_type; + if (skb->protocol == htons(ETH_P_IP)) + return xfrm4_udp_encap_rcv(sk, skb); + /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 86b2036d73ff..f2d08dbccfb7 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4865,11 +4865,16 @@ static int ieee80211_add_intf_link(struct wiphy *wiphy, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + int res; if (wdev->use_4addr) return -EOPNOTSUPP; - return ieee80211_vif_set_links(sdata, wdev->valid_links); + mutex_lock(&sdata->local->mtx); + res = ieee80211_vif_set_links(sdata, wdev->valid_links); + mutex_unlock(&sdata->local->mtx); + + return res; } static void ieee80211_del_intf_link(struct wiphy *wiphy, @@ -4878,7 +4883,9 @@ static void ieee80211_del_intf_link(struct wiphy *wiphy, { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + mutex_lock(&sdata->local->mtx); ieee80211_vif_set_links(sdata, wdev->valid_links); + mutex_unlock(&sdata->local->mtx); } static int sta_add_link_station(struct ieee80211_local *local, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b0372e76f373..4159fb65038b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2312,7 +2312,7 @@ ieee802_11_parse_elems(const u8 *start, size_t len, bool action, return ieee802_11_parse_elems_crc(start, len, action, 0, 0, bss); } -void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos); +void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id); extern const int ieee802_1d_to_ac[8]; diff --git a/net/mac80211/link.c b/net/mac80211/link.c index e82db88a47f8..40f030b8ece9 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -2,7 +2,7 @@ /* * MLO link handling * - * Copyright (C) 2022 Intel Corporation + * Copyright (C) 2022-2023 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -409,6 +409,7 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, IEEE80211_CHANCTX_SHARED); WARN_ON_ONCE(ret); + ieee80211_mgd_set_link_qos_params(link); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_ERP_PREAMBLE | @@ -423,7 +424,6 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, BSS_CHANGED_TWT | BSS_CHANGED_HE_OBSS_PD | BSS_CHANGED_HE_BSS_COLOR); - ieee80211_mgd_set_link_qos_params(link); } old_active = sdata->vif.active_links; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index bd8d6f9545f5..5a4303130ef2 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1372,10 +1372,11 @@ static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, ieee80211_add_non_inheritance_elem(skb, outer_present_elems, link_present_elems); - ieee80211_fragment_element(skb, subelem_len); + ieee80211_fragment_element(skb, subelem_len, + IEEE80211_MLE_SUBELEM_FRAGMENT); } - ieee80211_fragment_element(skb, ml_elem_len); + ieee80211_fragment_element(skb, ml_elem_len, WLAN_EID_FRAGMENT); } static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index d996aa2579df..fc6e130364da 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2110,7 +2110,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* either the frame has been decrypted or will be dropped */ status->flag |= RX_FLAG_DECRYPTED; - if (unlikely(ieee80211_is_beacon(fc) && result == RX_DROP_UNUSABLE && + if (unlikely(ieee80211_is_beacon(fc) && (result & RX_DROP_UNUSABLE) && rx->sdata->dev)) cfg80211_rx_unprot_mlme_mgmt(rx->sdata->dev, skb->data, skb->len); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 7f1c7f67014b..13b522dab0a3 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4445,7 +4445,7 @@ static void ieee80211_mlo_multicast_tx(struct net_device *dev, struct sk_buff *skb) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - unsigned long links = sdata->vif.valid_links; + unsigned long links = sdata->vif.active_links; unsigned int link; u32 ctrl_flags = IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX; @@ -6040,7 +6040,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (WARN_ON_ONCE(link == ARRAY_SIZE(sdata->vif.link_conf))) - link = ffs(sdata->vif.valid_links) - 1; + link = ffs(sdata->vif.active_links) - 1; } IEEE80211_SKB_CB(skb)->control.flags |= @@ -6076,7 +6076,7 @@ void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata, band = chanctx_conf->def.chan->band; } else { WARN_ON(link_id >= 0 && - !(sdata->vif.valid_links & BIT(link_id))); + !(sdata->vif.active_links & BIT(link_id))); /* MLD transmissions must not rely on the band */ band = 0; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 4bf76150925d..3bd07a0a782f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5049,7 +5049,7 @@ u8 *ieee80211_ie_build_eht_cap(u8 *pos, return pos; } -void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos) +void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id) { unsigned int elem_len; @@ -5069,7 +5069,7 @@ void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos) memmove(len_pos + 255 + 3, len_pos + 255 + 1, elem_len); /* place the fragment ID */ len_pos += 255 + 1; - *len_pos = WLAN_EID_FRAGMENT; + *len_pos = frag_id; /* and point to fragment length to update later */ len_pos++; } diff --git a/net/mac802154/trace.h b/net/mac802154/trace.h index 689396d6c76a..1574ecc48075 100644 --- a/net/mac802154/trace.h +++ b/net/mac802154/trace.h @@ -14,7 +14,7 @@ #define MAXNAME 32 #define LOCAL_ENTRY __array(char, wpan_phy_name, MAXNAME) -#define LOCAL_ASSIGN strlcpy(__entry->wpan_phy_name, \ +#define LOCAL_ASSIGN strscpy(__entry->wpan_phy_name, \ wpan_phy_name(local->hw.phy), MAXNAME) #define LOCAL_PR_FMT "%s" #define LOCAL_PR_ARG __entry->wpan_phy_name diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 59f8f3124855..1224dfca5bf3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1047,6 +1047,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; + inet_sk_state_store(newsk, TCP_LISTEN); err = kernel_listen(ssock, backlog); if (err) return err; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 67311e7d5b21..a6c7f2d24909 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -44,7 +44,7 @@ enum { static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; static void __mptcp_destroy_sock(struct sock *sk); -static void __mptcp_check_send_data_fin(struct sock *sk); +static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); static struct net_device mptcp_napi_dev; @@ -424,8 +424,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - return !__mptcp_check_fallback(msk) && - ((1 << sk->sk_state) & + return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } @@ -583,9 +582,6 @@ static bool mptcp_check_data_fin(struct sock *sk) u64 rcv_data_fin_seq; bool ret = false; - if (__mptcp_check_fallback(msk)) - return ret; - /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options @@ -623,7 +619,8 @@ static bool mptcp_check_data_fin(struct sock *sk) } ret = true; - mptcp_send_ack(msk); + if (!__mptcp_check_fallback(msk)) + mptcp_send_ack(msk); mptcp_close_wake_up(sk); } return ret; @@ -850,12 +847,12 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) return true; } -static void __mptcp_flush_join_list(struct sock *sk) +static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list) { struct mptcp_subflow_context *tmp, *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) { + list_for_each_entry_safe(subflow, tmp, join_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); @@ -897,49 +894,6 @@ bool mptcp_schedule_work(struct sock *sk) return false; } -void mptcp_subflow_eof(struct sock *sk) -{ - if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags)) - mptcp_schedule_work(sk); -} - -static void mptcp_check_for_eof(struct mptcp_sock *msk) -{ - struct mptcp_subflow_context *subflow; - struct sock *sk = (struct sock *)msk; - int receivers = 0; - - mptcp_for_each_subflow(msk, subflow) - receivers += !subflow->rx_eof; - if (receivers) - return; - - if (!(sk->sk_shutdown & RCV_SHUTDOWN)) { - /* hopefully temporary hack: propagate shutdown status - * to msk, when all subflows agree on it - */ - WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); - - smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ - sk->sk_data_ready(sk); - } - - switch (sk->sk_state) { - case TCP_ESTABLISHED: - inet_sk_state_store(sk, TCP_CLOSE_WAIT); - break; - case TCP_FIN_WAIT1: - inet_sk_state_store(sk, TCP_CLOSING); - break; - case TCP_FIN_WAIT2: - inet_sk_state_store(sk, TCP_CLOSE); - break; - default: - return; - } - mptcp_close_wake_up(sk); -} - static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; @@ -1609,7 +1563,7 @@ out: if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); if (do_check_data_fin) - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) @@ -1727,7 +1681,13 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) *copied_syn = 0; } else if (ret && ret != -EINPROGRESS) { - mptcp_disconnect(sk, 0); + /* The disconnect() op called by tcp_sendmsg_fastopen()/ + * __inet_stream_connect() can fail, due to looking check, + * see mptcp_disconnect(). + * Attempt it again outside the problematic scope. + */ + if (!mptcp_disconnect(sk, 0)) + sk->sk_socket->state = SS_UNCONNECTED; } inet_sk(sk)->defer_connect = 0; @@ -2158,9 +2118,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, break; } - if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) - mptcp_check_for_eof(msk); - if (sk->sk_shutdown & RCV_SHUTDOWN) { /* race breaker: the shutdown could be after the * previous receive queue check @@ -2389,7 +2346,10 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - tcp_disconnect(ssk, 0); + /* The MPTCP code never wait on the subflow sockets, TCP-level + * disconnect should never fail + */ + WARN_ON_ONCE(tcp_disconnect(ssk, 0)); msk->subflow->state = SS_UNCONNECTED; mptcp_subflow_ctx_reset(subflow); release_sock(ssk); @@ -2408,13 +2368,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) { - tcp_set_state(ssk, TCP_CLOSE); - mptcp_subflow_queue_clean(sk, ssk); - inet_csk_listen_stop(ssk); - mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); - } - __tcp_close(ssk, 0); /* close acquired an extra ref */ @@ -2671,16 +2624,12 @@ static void mptcp_worker(struct work_struct *work) if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; - mptcp_check_data_fin_ack(sk); - mptcp_check_fastclose(msk); mptcp_pm_nl_work(msk); - if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) - mptcp_check_for_eof(msk); - - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); + mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) @@ -2812,13 +2761,19 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) break; fallthrough; case TCP_SYN_SENT: - tcp_disconnect(ssk, O_NONBLOCK); + WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK)); break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { pr_debug("Fallback"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); + + /* simulate the data_fin ack reception to let the state + * machine move forward + */ + WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); + mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); @@ -2858,7 +2813,7 @@ static int mptcp_close_state(struct sock *sk) return next & TCP_ACTION_FIN; } -static void __mptcp_check_send_data_fin(struct sock *sk) +static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); @@ -2876,19 +2831,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk) WRITE_ONCE(msk->snd_nxt, msk->write_seq); - /* fallback socket will not get data_fin/ack, can move to the next - * state now - */ - if (__mptcp_check_fallback(msk)) { - WRITE_ONCE(msk->snd_una, msk->write_seq); - if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { - inet_sk_state_store(sk, TCP_CLOSE); - mptcp_close_wake_up(sk); - } else if (sk->sk_state == TCP_FIN_WAIT1) { - inet_sk_state_store(sk, TCP_FIN_WAIT2); - } - } - mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); @@ -2908,7 +2850,7 @@ static void __mptcp_wr_shutdown(struct sock *sk) WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1); - __mptcp_check_send_data_fin(sk); + mptcp_check_send_data_fin(sk); } static void __mptcp_destroy_sock(struct sock *sk) @@ -2953,10 +2895,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk) return EPOLLIN | EPOLLRDNORM; } -static void mptcp_listen_inuse_dec(struct sock *sk) +static void mptcp_check_listen_stop(struct sock *sk) { - if (inet_sk_state_load(sk) == TCP_LISTEN) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + struct sock *ssk; + + if (inet_sk_state_load(sk) != TCP_LISTEN) + return; + + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + ssk = mptcp_sk(sk)->first; + if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) + return; + + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); + tcp_set_state(ssk, TCP_CLOSE); + release_sock(ssk); } bool __mptcp_close(struct sock *sk, long timeout) @@ -2969,7 +2925,7 @@ bool __mptcp_close(struct sock *sk, long timeout) WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { - mptcp_listen_inuse_dec(sk); + mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); goto cleanup; } @@ -3073,15 +3029,20 @@ static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under - * msk->firstsocket lock). Do nothing and leave the cleanup to the - * caller. + * msk->firstsocket lock). */ if (msk->fastopening) - return 0; + return -EBUSY; - mptcp_listen_inuse_dec(sk); + mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); mptcp_stop_timer(sk); @@ -3140,6 +3101,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif + nsk->sk_wait_pending = 0; __mptcp_init_sock(nsk); msk = mptcp_sk(nsk); @@ -3327,9 +3289,14 @@ static void mptcp_release_cb(struct sock *sk) for (;;) { unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | msk->push_pending; + struct list_head join_list; + if (!flags) break; + INIT_LIST_HEAD(&join_list); + list_splice_init(&msk->join_list, &join_list); + /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope @@ -3340,8 +3307,9 @@ static void mptcp_release_cb(struct sock *sk) msk->push_pending = 0; msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); + if (flags & BIT(MPTCP_FLUSH_JOIN_LIST)) - __mptcp_flush_join_list(sk); + __mptcp_flush_join_list(sk, &join_list); if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 70c957bc56a8..d3783a7056e1 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -113,7 +113,6 @@ /* MPTCP socket atomic flags */ #define MPTCP_NOSPACE 1 #define MPTCP_WORK_RTX 2 -#define MPTCP_WORK_EOF 3 #define MPTCP_FALLBACK_DONE 4 #define MPTCP_WORK_CLOSE_SUBFLOW 5 @@ -476,14 +475,13 @@ struct mptcp_subflow_context { send_mp_fail : 1, send_fastclose : 1, send_infinite_map : 1, - rx_eof : 1, remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 8; + __unused : 9; enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -720,7 +718,6 @@ static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit) void __mptcp_check_push(struct sock *sk, struct sock *ssk); void __mptcp_data_acked(struct sock *sk); void __mptcp_error_report(struct sock *sk); -void mptcp_subflow_eof(struct sock *sk); bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit); static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4688daa6b38b..d9c8b21c6076 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1749,14 +1749,16 @@ static void subflow_state_change(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct sock *parent = subflow->conn; + struct mptcp_sock *msk; __subflow_state_change(sk); + msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); - mptcp_rcv_space_init(mptcp_sk(parent), sk); - pr_fallback(mptcp_sk(parent)); + mptcp_rcv_space_init(msk, sk); + pr_fallback(msk); subflow->conn_finished = 1; mptcp_set_connected(parent); } @@ -1772,11 +1774,12 @@ static void subflow_state_change(struct sock *sk) subflow_sched_work_if_closed(mptcp_sk(parent), sk); - if (__mptcp_check_fallback(mptcp_sk(parent)) && - !subflow->rx_eof && subflow_is_done(sk)) { - subflow->rx_eof = 1; - mptcp_subflow_eof(parent); - } + /* when the fallback subflow closes the rx side, trigger a 'dummy' + * ingress data fin, so that the msk state will follow along + */ + if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk && + mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) + mptcp_schedule_work(parent); } void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index feb1d7fcb09f..a80b960223e1 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -1207,6 +1207,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, skb->transport_header = skb->network_header; skb_set_inner_ipproto(skb, next_protocol); + skb_set_inner_mac_header(skb, skb_inner_network_offset(skb)); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { bool check = false; @@ -1349,6 +1350,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb->transport_header = skb->network_header; skb_set_inner_ipproto(skb, next_protocol); + skb_set_inner_mac_header(skb, skb_inner_network_offset(skb)); if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { bool check = false; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 04bd0ed4d2ae..b0ef48b21dcb 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -317,12 +317,12 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow) + struct flow_offload *flow, bool force) { u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (timeout - READ_ONCE(flow->timeout) > HZ) + if (force || timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); else return; @@ -334,6 +334,12 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_refresh); +static bool nf_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -423,7 +429,8 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct)) + nf_ct_is_dying(flow->ct) || + nf_flow_is_outdated(flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 19efba1e51ef..3bbaf9c7ea46 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -384,7 +384,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); thoff -= offset; @@ -650,7 +650,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0519d45ede6b..4c7937fd803f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -151,6 +151,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, return NULL; INIT_LIST_HEAD(&trans->list); + INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; trans->ctx = *ctx; @@ -163,13 +164,20 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } -static void nft_trans_destroy(struct nft_trans *trans) +static void nft_trans_list_del(struct nft_trans *trans) { list_del(&trans->list); + list_del(&trans->binding_list); +} + +static void nft_trans_destroy(struct nft_trans *trans) +{ + nft_trans_list_del(trans); kfree(trans); } -static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, + bool bind) { struct nftables_pernet *nft_net; struct net *net = ctx->net; @@ -183,16 +191,80 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) - nft_trans_set_bound(trans) = true; + nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) - nft_trans_elem_set_bound(trans) = true; + nft_trans_elem_set_bound(trans) = bind; break; } } } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, true); +} + +static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, false); +} + +static void __nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain, bool bind) +{ + struct nftables_pernet *nft_net; + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_chain_binding(chain)) + return; + + nft_net = nft_pernet(net); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain(trans) == chain) + nft_trans_chain_bound(trans) = bind; + break; + case NFT_MSG_NEWRULE: + if (trans->ctx.chain == chain) + nft_trans_rule_bound(trans) = bind; + break; + } + } +} + +static void nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, true); +} + +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + if (!nft_chain_binding(chain)) + return 0; + + if (nft_chain_binding(ctx->chain)) + return -EOPNOTSUPP; + + if (chain->bound) + return -EBUSY; + + chain->bound = true; + chain->use++; + nft_chain_trans_bind(ctx, chain); + + return 0; +} + +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, false); +} + static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { @@ -292,6 +364,19 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr { struct nftables_pernet *nft_net = nft_pernet(net); + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (!nft_trans_set_update(trans) && + nft_set_is_anonymous(nft_trans_set(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + } + list_add_tail(&trans->list, &nft_net->commit_list); } @@ -338,8 +423,9 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } - + nft_trans_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); + return trans; } @@ -357,8 +443,7 @@ static int nft_delchain(struct nft_ctx *ctx) return 0; } -static void nft_rule_expr_activate(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr; @@ -371,9 +456,8 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } } -static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule, - enum nft_trans_phase phase) +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; @@ -495,6 +579,58 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_deactivate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_deactivate(ctx->net, set, elem); + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + nft_setelem_data_deactivate(ctx->net, set, &elem); + break; + } +} + +static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_deactivate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); + + nft_map_catchall_deactivate(ctx, set); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -503,6 +639,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); ctx->table->use--; @@ -2226,7 +2365,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, return 0; } -static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err; @@ -2528,6 +2667,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_basechain(trans) = basechain; INIT_LIST_HEAD(&nft_trans_chain_hooks(trans)); list_splice(&hook.list, &nft_trans_chain_hooks(trans)); + if (nla[NFTA_CHAIN_HOOK]) + module_put(hook.type->owner); nft_trans_commit_list_add_tail(ctx->net, trans); @@ -2670,21 +2811,18 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); } -static int nft_delchain_hook(struct nft_ctx *ctx, struct nft_chain *chain, +static int nft_delchain_hook(struct nft_ctx *ctx, + struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { + const struct nft_chain *chain = &basechain->chain; const struct nlattr * const *nla = ctx->nla; struct nft_chain_hook chain_hook = {}; - struct nft_base_chain *basechain; struct nft_hook *this, *hook; LIST_HEAD(chain_del_list); struct nft_trans *trans; int err; - if (!nft_is_base_chain(chain)) - return -EOPNOTSUPP; - - basechain = nft_base_chain(chain); err = nft_chain_parse_hook(ctx->net, basechain, nla, &chain_hook, ctx->family, chain->flags, extack); if (err < 0) @@ -2769,7 +2907,12 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, if (chain->flags & NFT_CHAIN_HW_OFFLOAD) return -EOPNOTSUPP; - return nft_delchain_hook(&ctx, chain, extack); + if (nft_is_base_chain(chain)) { + struct nft_base_chain *basechain = nft_base_chain(chain); + + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) + return nft_delchain_hook(&ctx, basechain, extack); + } } if (info->nlh->nlmsg_flags & NLM_F_NONREC && @@ -3490,8 +3633,7 @@ err_fill_rule_info: return err; } -static void nf_tables_rule_destroy(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next; @@ -3508,7 +3650,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) +static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -3596,12 +3738,6 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, return 0; } -struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); @@ -3844,7 +3980,8 @@ err_destroy_flow_rule: if (flow) nft_flow_rule_destroy(flow); err_release_rule: - nf_tables_rule_release(&ctx, rule); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); + nf_tables_rule_destroy(&ctx, rule); err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { @@ -4776,6 +4913,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout); if (err) return err; @@ -4784,6 +4924,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } @@ -4830,6 +4974,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags); if (err < 0) return err; @@ -4919,6 +5066,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, set->num_exprs = num_exprs; set->handle = nf_tables_alloc_handle(table); + INIT_LIST_HEAD(&set->pending_update); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) @@ -4932,7 +5080,7 @@ err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); err_set_destroy: - ops->destroy(set); + ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: @@ -4947,7 +5095,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); - nft_set_elem_destroy(set, catchall->elem, true); + nf_tables_set_elem_destroy(ctx, set, catchall->elem); kfree_rcu(catchall, rcu); } } @@ -4962,7 +5110,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(ctx, set->exprs[i]); - set->ops->destroy(set); + set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); kfree(set->name); kvfree(set); @@ -5127,10 +5275,60 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } } +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_activate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_activate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_catchall_activate(const struct nft_ctx *ctx, + struct nft_set *set) +{ + u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_elem_catchall *catchall; + struct nft_set_elem elem; + struct nft_set_ext *ext; + + list_for_each_entry(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + if (!nft_set_elem_active(ext, genmask)) + continue; + + elem.priv = catchall->elem; + nft_setelem_data_activate(ctx->net, set, &elem); + break; + } +} + +static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_activate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); + + nft_map_catchall_activate(ctx, set); +} + void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (nft_set_is_anonymous(set)) + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(ctx, set); + nft_clear(ctx->net, set); + } set->use++; } @@ -5141,14 +5339,28 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, enum nft_trans_phase phase) { switch (phase) { - case NFT_TRANS_PREPARE: + case NFT_TRANS_PREPARE_ERROR: + nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); set->use--; + break; + case NFT_TRANS_PREPARE: + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + + nft_deactivate_next(ctx->net, set); + } + set->use--; return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: + if (nft_set_is_anonymous(set) && + set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + set->use--; fallthrough; default: @@ -5901,6 +6113,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, __nft_set_elem_expr_destroy(ctx, expr); } +/* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { @@ -5922,11 +6135,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_setelem_data_deactivate() already deals - * with the refcounting from the preparation phase. +/* Destroy element. References have been already dropped in the preparation + * path via nft_setelem_data_deactivate(). */ -static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); @@ -6489,19 +6702,19 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (flags) *nft_set_ext_flags(ext) = flags; + if (obj) { + *nft_set_ext_obj(ext) = obj; + obj->use++; + } if (ulen > 0) { if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) { err = -EINVAL; - goto err_elem_userdata; + goto err_elem_free; } udata = nft_set_ext_userdata(ext); udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } - if (obj) { - *nft_set_ext_obj(ext) = obj; - obj->use++; - } err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs); if (err < 0) goto err_elem_free; @@ -6556,10 +6769,7 @@ err_set_full: err_element_clash: kfree(trans); err_elem_free: - if (obj) - obj->use--; -err_elem_userdata: - nf_tables_set_elem_destroy(ctx, set, elem.priv); + nft_set_elem_destroy(set, elem.priv, true); err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); @@ -6603,7 +6813,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -6636,7 +6847,6 @@ static int nf_tables_newsetelem(struct sk_buff *skb, void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; - struct nft_rule *rule; if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { @@ -6644,15 +6854,6 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_GOTO: chain = data->verdict.chain; chain->use++; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use++; - list_for_each_entry(rule, &chain->rules, list) - chain->use++; - - nft_chain_add(chain->table, chain); break; } } @@ -6887,7 +7088,9 @@ static int nf_tables_delsetelem(struct sk_buff *skb, set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -7669,6 +7872,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, enum nft_trans_phase phase) { switch (phase) { + case NFT_TRANS_PREPARE_ERROR: case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -8941,7 +9145,7 @@ static void nf_tables_trans_destroy_work(struct work_struct *w) synchronize_rcu(); list_for_each_entry_safe(trans, next, &head, list) { - list_del(&trans->list); + nft_trans_list_del(trans); nft_commit_release(trans); } } @@ -9275,10 +9479,25 @@ static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) } } +static void nft_set_commit_update(struct list_head *set_update_list) +{ + struct nft_set *set, *next; + + list_for_each_entry_safe(set, next, set_update_list, pending_update) { + list_del_init(&set->pending_update); + + if (!set->ops->commit) + continue; + + set->ops->commit(set); + } +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; @@ -9291,6 +9510,27 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } + list_for_each_entry(trans, &nft_net->binding_list, binding_list) { + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (!nft_trans_set_update(trans) && + nft_set_is_anonymous(nft_trans_set(trans)) && + !nft_trans_set_bound(trans)) { + pr_warn_once("nftables ruleset with unbound set\n"); + return -EINVAL; + } + break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans)) && + !nft_trans_chain_bound(trans)) { + pr_warn_once("nftables ruleset with unbound chain\n"); + return -EINVAL; + } + break; + } + } + /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) return -EAGAIN; @@ -9453,6 +9693,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_NEWSETELEM); + if (te->set->ops->commit && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -9467,6 +9712,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) atomic_dec(&te->set->nelems); te->set->ndeact--; } + if (te->set->ops->commit && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { @@ -9529,6 +9779,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } } + nft_set_commit_update(&set_update_list); + nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); @@ -9588,10 +9840,25 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } +static void nft_set_abort_update(struct list_head *set_update_list) +{ + struct nft_set *set, *next; + + list_for_each_entry_safe(set, next, set_update_list, pending_update) { + list_del_init(&set->pending_update); + + if (!set->ops->abort) + continue; + + set->ops->abort(set); + } +} + static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + LIST_HEAD(set_update_list); struct nft_trans_elem *te; if (action == NFNL_ABORT_VALIDATE && @@ -9633,7 +9900,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { - if (nft_chain_is_bound(trans->ctx.chain)) { + if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } @@ -9656,6 +9923,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: + if (nft_trans_rule_bound(trans)) { + nft_trans_destroy(trans); + break; + } trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, @@ -9690,6 +9961,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); + if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -9701,6 +9975,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) atomic_dec(&te->set->nelems); + + if (te->set->ops->abort && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: @@ -9711,6 +9991,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) if (!nft_setelem_is_catchall(te->set, &te->elem)) te->set->ndeact--; + if (te->set->ops->abort && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: @@ -9753,11 +10038,13 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } } + nft_set_abort_update(&set_update_list); + synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { - list_del(&trans->list); + nft_trans_list_del(trans); nf_tables_abort_release(trans); } @@ -10206,22 +10493,12 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; - struct nft_rule *rule; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; chain->use--; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use--; - list_for_each_entry(rule, &chain->rules, list) - chain->use--; - - nft_chain_del(chain); break; } } @@ -10456,6 +10733,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) list_for_each_entry_safe(set, ns, &table->sets, list) { list_del(&set->list); table->use--; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(&ctx, set); + nft_set_destroy(&ctx, set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { @@ -10540,6 +10820,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index ae7146475d17..c9fbe0f707b5 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -533,7 +533,8 @@ ack: * processed, this avoids that the same error is * reported several times when replaying the batch. */ - if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { + if (err == -ENOMEM || + nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index ee6840bd5933..8f1bfa6ccc2d 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -439,3 +439,4 @@ module_init(nfnl_osf_init); module_exit(nfnl_osf_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index c9d2f7c29f53..3d76ebfe8939 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -76,11 +76,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, switch (priv->data.verdict.code) { case NFT_JUMP: case NFT_GOTO: - if (nft_chain_is_bound(chain)) { - err = -EBUSY; - goto err1; - } - chain->bound = true; + err = nf_tables_bind_chain(ctx, chain); + if (err < 0) + return err; break; default: break; @@ -98,6 +96,31 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_activate(&chain_ctx, rule); + + nft_clear(ctx->net, chain); + break; + default: + break; + } + } return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } @@ -107,6 +130,43 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_deactivate(&chain_ctx, rule, phase); + + switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + nf_tables_unbind_chain(ctx, chain); + fallthrough; + case NFT_TRANS_PREPARE: + nft_deactivate_next(ctx->net, chain); + break; + default: + nft_chain_del(chain); + chain->bound = false; + chain->table->use--; + break; + } + break; + default: + break; + } + } if (phase == NFT_TRANS_COMMIT) return; @@ -131,15 +191,27 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, case NFT_GOTO: chain = data->verdict.chain; - if (!nft_chain_is_bound(chain)) + if (!nft_chain_binding(chain)) + break; + + /* Rule construction failed, but chain is already bound: + * let the transaction records release this chain and its rules. + */ + if (chain->bound) { + chain->use--; break; + } + /* Rule has been deleted, release chain and its rules. */ chain_ctx = *ctx; chain_ctx.chain = chain; - list_for_each_entry_safe(rule, n, &chain->rules, list) - nf_tables_rule_release(&chain_ctx, rule); - + chain->use--; + list_for_each_entry_safe(rule, n, &chain->rules, list) { + chain->use--; + list_del(&rule->list); + nf_tables_rule_destroy(&chain_ctx, rule); + } nf_tables_chain_destroy(&chain_ctx); break; default: diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 96081ac8d2b4..1e5e7a181e0b 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -271,13 +271,14 @@ static int nft_bitmap_init(const struct nft_set *set, return 0; } -static void nft_bitmap_destroy(const struct nft_set *set) +static void nft_bitmap_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be, *n; list_for_each_entry_safe(be, n, &priv->list, head) - nft_set_elem_destroy(set, be, true); + nf_tables_set_elem_destroy(ctx, set, be); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 76de6c8d9865..0b73cb0e752f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -400,19 +400,31 @@ static int nft_rhash_init(const struct nft_set *set, return 0; } +struct nft_rhash_ctx { + const struct nft_ctx ctx; + const struct nft_set *set; +}; + static void nft_rhash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy(arg, ptr, true); + struct nft_rhash_ctx *rhash_ctx = arg; + + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); } -static void nft_rhash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_ctx rhash_ctx = { + .ctx = *ctx, + .set = set, + }; cancel_delayed_work_sync(&priv->gc_work); rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, - (void *)set); + (void *)&rhash_ctx); } /* Number of buckets is stored in u32, so cap our result to 1U<<31 */ @@ -643,7 +655,8 @@ static int nft_hash_init(const struct nft_set *set, return 0; } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; @@ -653,7 +666,7 @@ static void nft_hash_destroy(const struct nft_set *set) for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nft_set_elem_destroy(set, he, true); + nf_tables_set_elem_destroy(ctx, set, he); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 06d46d182634..0452ee586c1c 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1600,17 +1600,10 @@ static void pipapo_free_fields(struct nft_pipapo_match *m) } } -/** - * pipapo_reclaim_match - RCU callback to free fields from old matching data - * @rcu: RCU head - */ -static void pipapo_reclaim_match(struct rcu_head *rcu) +static void pipapo_free_match(struct nft_pipapo_match *m) { - struct nft_pipapo_match *m; int i; - m = container_of(rcu, struct nft_pipapo_match, rcu); - for_each_possible_cpu(i) kfree(*per_cpu_ptr(m->scratch, i)); @@ -1625,7 +1618,19 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) } /** - * pipapo_commit() - Replace lookup data with current working copy + * pipapo_reclaim_match - RCU callback to free fields from old matching data + * @rcu: RCU head + */ +static void pipapo_reclaim_match(struct rcu_head *rcu) +{ + struct nft_pipapo_match *m; + + m = container_of(rcu, struct nft_pipapo_match, rcu); + pipapo_free_match(m); +} + +/** + * nft_pipapo_commit() - Replace lookup data with current working copy * @set: nftables API set representation * * While at it, check if we should perform garbage collection on the working @@ -1635,7 +1640,7 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * We also need to create a new working copy for subsequent insertions and * deletions. */ -static void pipapo_commit(const struct nft_set *set) +static void nft_pipapo_commit(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *new_clone, *old; @@ -1660,6 +1665,26 @@ static void pipapo_commit(const struct nft_set *set) priv->clone = new_clone; } +static void nft_pipapo_abort(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *new_clone, *m; + + if (!priv->dirty) + return; + + m = rcu_dereference(priv->match); + + new_clone = pipapo_clone(m); + if (IS_ERR(new_clone)) + return; + + priv->dirty = false; + + pipapo_free_match(priv->clone); + priv->clone = new_clone; +} + /** * nft_pipapo_activate() - Mark element reference as active given key, commit * @net: Network namespace @@ -1667,8 +1692,7 @@ static void pipapo_commit(const struct nft_set *set) * @elem: nftables API element representation containing key data * * On insertion, elements are added to a copy of the matching data currently - * in use for lookups, and not directly inserted into current lookup data, so - * we'll take care of that by calling pipapo_commit() here. Both + * in use for lookups, and not directly inserted into current lookup data. Both * nft_pipapo_insert() and nft_pipapo_activate() are called once for each * element, hence we can't purpose either one as a real commit operation. */ @@ -1684,8 +1708,6 @@ static void nft_pipapo_activate(const struct net *net, nft_set_elem_change_active(net, set, &e->ext); nft_set_elem_clear_busy(&e->ext); - - pipapo_commit(set); } /** @@ -1931,7 +1953,6 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, if (i == m->field_count) { priv->dirty = true; pipapo_drop(m, rulemap); - pipapo_commit(set); return; } @@ -1953,12 +1974,16 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); struct nft_pipapo_match *m; struct nft_pipapo_field *f; int i, r; rcu_read_lock(); - m = rcu_dereference(priv->match); + if (iter->genmask == nft_genmask_cur(net)) + m = rcu_dereference(priv->match); + else + m = priv->clone; if (unlikely(!m)) goto out; @@ -2127,10 +2152,12 @@ out_scratch: /** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ -static void nft_set_pipapo_match_destroy(const struct nft_set *set, +static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; @@ -2147,15 +2174,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set, e = f->mt[r].e; - nft_set_elem_destroy(set, e, true); + nf_tables_set_elem_destroy(ctx, set, e); } } /** * nft_pipapo_destroy() - Free private data for set and all committed elements + * @ctx: context * @set: nftables API set representation */ -static void nft_pipapo_destroy(const struct nft_set *set) +static void nft_pipapo_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; @@ -2165,7 +2194,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2182,7 +2211,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) m = priv->clone; if (priv->dirty) - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); @@ -2230,6 +2259,8 @@ const struct nft_set_type nft_set_pipapo_type = { .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, + .commit = nft_pipapo_commit, + .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; @@ -2252,6 +2283,8 @@ const struct nft_set_type nft_set_pipapo_avx2_type = { .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, + .commit = nft_pipapo_commit, + .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 2f114aa10f1a..5c05c9b990fb 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -664,7 +664,8 @@ static int nft_rbtree_init(const struct nft_set *set, return 0; } -static void nft_rbtree_destroy(const struct nft_set *set) +static void nft_rbtree_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; @@ -675,7 +676,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe, true); + nf_tables_set_elem_destroy(ctx, set, rbe); } } diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index e1990baf3a3b..dc9485854002 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -71,4 +71,3 @@ MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>"); MODULE_DESCRIPTION("Passive OS fingerprint matching."); MODULE_ALIAS("ipt_osf"); MODULE_ALIAS("ip6t_osf"); -MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 54c083003947..27511c90a26f 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -857,7 +857,8 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, offset -= iter->startbit; idx = offset / NETLBL_CATMAP_MAPSIZE; - iter->bitmap[idx] |= bitmap << (offset % NETLBL_CATMAP_MAPSIZE); + iter->bitmap[idx] |= (NETLBL_CATMAP_MAPTYPE)bitmap + << (offset % NETLBL_CATMAP_MAPSIZE); return 0; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 9cc0bc7c71ed..abc71a06d634 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -610,6 +610,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; + bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; @@ -647,6 +648,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, * established state, then don't refresh. */ return false; + force_refresh = true; } if (tcph && (unlikely(tcph->fin || tcph->rst))) { @@ -660,7 +662,12 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, else ctinfo = IP_CT_ESTABLISHED_REPLY; - flow_offload_refresh(nf_ft, flow); + flow_offload_refresh(nf_ft, flow, force_refresh); + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { + /* Process this flow in SW to allow promoting to ASSURED */ + return false; + } + nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index fc945c7e4123..c819b812a899 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -13,7 +13,10 @@ #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/slab.h> +#include <net/ipv6.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_pedit.h> @@ -327,28 +330,58 @@ static bool offset_valid(struct sk_buff *skb, int offset) return true; } -static void pedit_skb_hdr_offset(struct sk_buff *skb, +static int pedit_l4_skb_offset(struct sk_buff *skb, int *hoffset, const int header_type) +{ + const int noff = skb_network_offset(skb); + int ret = -EINVAL; + struct iphdr _iph; + + switch (skb->protocol) { + case htons(ETH_P_IP): { + const struct iphdr *iph = skb_header_pointer(skb, noff, sizeof(_iph), &_iph); + + if (!iph) + goto out; + *hoffset = noff + iph->ihl * 4; + ret = 0; + break; + } + case htons(ETH_P_IPV6): + ret = ipv6_find_hdr(skb, hoffset, header_type, NULL, NULL) == header_type ? 0 : -EINVAL; + break; + } +out: + return ret; +} + +static int pedit_skb_hdr_offset(struct sk_buff *skb, enum pedit_header_type htype, int *hoffset) { + int ret = -EINVAL; /* 'htype' is validated in the netlink parsing */ switch (htype) { case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: - if (skb_mac_header_was_set(skb)) + if (skb_mac_header_was_set(skb)) { *hoffset = skb_mac_offset(skb); + ret = 0; + } break; case TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK: case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: *hoffset = skb_network_offset(skb); + ret = 0; break; case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_TCP); + break; case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: - if (skb_transport_header_was_set(skb)) - *hoffset = skb_transport_offset(skb); + ret = pedit_l4_skb_offset(skb, hoffset, IPPROTO_UDP); break; default: break; } + return ret; } TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, @@ -384,6 +417,7 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, int hoffset = 0; u32 *ptr, hdata; u32 val; + int rc; if (tkey_ex) { htype = tkey_ex->htype; @@ -392,7 +426,11 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb, tkey_ex++; } - pedit_skb_hdr_offset(skb, htype, &hoffset); + rc = pedit_skb_hdr_offset(skb, htype, &hoffset); + if (rc) { + pr_info_ratelimited("tc action pedit unable to extract header offset for header type (0x%x)\n", htype); + goto bad; + } if (tkey->offmask) { u8 *d, _d; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c877a6343fd4..a193cc7b3241 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -657,8 +657,8 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, { struct tcf_block *block = chain->block; const struct tcf_proto_ops *tmplt_ops; + unsigned int refcnt, non_act_refcnt; bool free_block = false; - unsigned int refcnt; void *tmplt_priv; mutex_lock(&block->lock); @@ -678,13 +678,15 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, * save these to temporary variables. */ refcnt = --chain->refcnt; + non_act_refcnt = refcnt - chain->action_refcnt; tmplt_ops = chain->tmplt_ops; tmplt_priv = chain->tmplt_priv; - /* The last dropped non-action reference will trigger notification. */ - if (refcnt - chain->action_refcnt == 0 && !by_act) { - tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain->index, - block, NULL, 0, 0, false); + if (non_act_refcnt == chain->explicitly_created && !by_act) { + if (non_act_refcnt == 0) + tc_chain_notify_delete(tmplt_ops, tmplt_priv, + chain->index, block, NULL, 0, 0, + false); /* Last reference to chain, no need to lock. */ chain->flushing = false; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 4e2e269f121f..d15d50de7980 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -718,13 +718,19 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) { - int err; + int err, ifindex = -1; err = tcf_exts_validate_ex(net, tp, tb, est, &n->exts, flags, fl_flags, extack); if (err < 0) return err; + if (tb[TCA_U32_INDEV]) { + ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); + if (ifindex < 0) + return -EINVAL; + } + if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; @@ -759,13 +765,9 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, tcf_bind_filter(tp, &n->res, base); } - if (tb[TCA_U32_INDEV]) { - int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); - if (ret < 0) - return -EINVAL; - n->ifindex = ret; - } + if (ifindex >= 0) + n->ifindex = ifindex; + return 0; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e4b6452318c0..aa6b1fe65151 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1079,17 +1079,29 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (parent == NULL) { unsigned int i, num_q, ingress; + struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { - num_q = 1; ingress = 1; - if (!dev_ingress_queue(dev)) { + dev_queue = dev_ingress_queue(dev); + if (!dev_queue) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; } + + q = rtnl_dereference(dev_queue->qdisc_sleeping); + + /* This is the counterpart of that qdisc_refcount_inc_nz() call in + * __tcf_qdisc_find() for filter requests. + */ + if (!qdisc_refcount_dec_if_one(q)) { + NL_SET_ERR_MSG(extack, + "Current ingress or clsact Qdisc has ongoing filter requests"); + return -EBUSY; + } } if (dev->flags & IFF_UP) @@ -1100,18 +1112,26 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if (new && new->ops->attach && !ingress) goto skip; - for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = dev_ingress_queue(dev); - - if (!ingress) + if (!ingress) { + for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); + old = dev_graft_qdisc(dev_queue, new); - old = dev_graft_qdisc(dev_queue, new); - if (new && i > 0) - qdisc_refcount_inc(new); - - if (!ingress) + if (new && i > 0) + qdisc_refcount_inc(new); qdisc_put(old); + } + } else { + old = dev_graft_qdisc(dev_queue, NULL); + + /* {ingress,clsact}_destroy() @old before grafting @new to avoid + * unprotected concurrent accesses to net_device::miniq_{in,e}gress + * pointer(s) in mini_qdisc_pair_swap(). + */ + qdisc_notify(net, skb, n, classid, old, new, extack); + qdisc_destroy(old); + + dev_graft_qdisc(dev_queue, new); } skip: @@ -1125,8 +1145,6 @@ skip: if (new && new->ops->attach) new->ops->attach(new); - } else { - notify_and_destroy(net, skb, n, classid, old, new, extack); } if (dev->flags & IFF_UP) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3248259eba32..5d7e23f4cc0e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1046,7 +1046,7 @@ static void qdisc_free_cb(struct rcu_head *head) qdisc_free(q); } -static void qdisc_destroy(struct Qdisc *qdisc) +static void __qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; @@ -1070,6 +1070,14 @@ static void qdisc_destroy(struct Qdisc *qdisc) call_rcu(&qdisc->rcu, qdisc_free_cb); } +void qdisc_destroy(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return; + + __qdisc_destroy(qdisc); +} + void qdisc_put(struct Qdisc *qdisc) { if (!qdisc) @@ -1079,7 +1087,7 @@ void qdisc_put(struct Qdisc *qdisc) !refcount_dec_and_test(&qdisc->refcnt)) return; - qdisc_destroy(qdisc); + __qdisc_destroy(qdisc); } EXPORT_SYMBOL(qdisc_put); @@ -1094,7 +1102,7 @@ void qdisc_put_unlocked(struct Qdisc *qdisc) !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) return; - qdisc_destroy(qdisc); + __qdisc_destroy(qdisc); rtnl_unlock(); } EXPORT_SYMBOL(qdisc_put_unlocked); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6ef3021e1169..e79be1b3e74d 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -966,6 +966,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; @@ -974,7 +975,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; - return ret; + goto unlock; } } else { q->loss_model = CLG_RANDOM; @@ -1041,6 +1042,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); +unlock: + sch_tree_unlock(sch); return ret; get_table_failure: @@ -1050,7 +1053,8 @@ get_table_failure: */ q->clg = old_clg; q->loss_model = old_loss_model; - return ret; + + goto unlock; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index dd7dea2f6e83..cf0e61ed9225 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -797,6 +797,9 @@ static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); + if (q->cur_txq[tc] >= dev->num_tx_queues) + q->cur_txq[tc] = first_txq; + if (skb) return skb; } while (q->cur_txq[tc] != first_txq); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 7fbeb99d8d32..23d6633966b1 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1250,7 +1250,10 @@ static int sctp_side_effects(enum sctp_event_type event_type, default: pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n", status, state, event_type, subtype.chunk); - BUG(); + error = status; + if (error >= 0) + error = -EINVAL; + WARN_ON_ONCE(1); break; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 97f1155a2045..08fdf1251f46 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4482,7 +4482,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, SCTP_AUTH_NEW_KEY, GFP_ATOMIC); if (!ev) - return -ENOMEM; + return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); diff --git a/net/socket.c b/net/socket.c index b7e01d0fe082..e46b162f1182 100644 --- a/net/socket.c +++ b/net/socket.c @@ -471,6 +471,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) return file; } + file->f_mode |= FMODE_NOWAIT; sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); @@ -1093,7 +1094,7 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct socket *sock = file->private_data; if (unlikely(!sock->ops->splice_read)) - return generic_file_splice_read(file, ppos, pipe, len, flags); + return copy_splice_read(file, ppos, pipe, len, flags); return sock->ops->splice_read(sock, ppos, pipe, len, flags); } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 79967b6925bd..e7c101290425 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -109,15 +109,15 @@ param_get_pool_mode(char *buf, const struct kernel_param *kp) switch (*ip) { case SVC_POOL_AUTO: - return strlcpy(buf, "auto\n", 20); + return sysfs_emit(buf, "auto\n"); case SVC_POOL_GLOBAL: - return strlcpy(buf, "global\n", 20); + return sysfs_emit(buf, "global\n"); case SVC_POOL_PERCPU: - return strlcpy(buf, "percpu\n", 20); + return sysfs_emit(buf, "percpu\n"); case SVC_POOL_PERNODE: - return strlcpy(buf, "pernode\n", 20); + return sysfs_emit(buf, "pernode\n"); default: - return sprintf(buf, "%d\n", *ip); + return sysfs_emit(buf, "%d\n", *ip); } } @@ -597,34 +597,25 @@ svc_destroy(struct kref *ref) } EXPORT_SYMBOL_GPL(svc_destroy); -/* - * Allocate an RPC server's buffer space. - * We allocate pages and place them in rq_pages. - */ -static int +static bool svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) { - unsigned int pages, arghi; + unsigned long pages, ret; /* bc_xprt uses fore channel allocated buffers */ if (svc_is_backchannel(rqstp)) - return 1; + return true; pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply. * We assume one is at most one page */ - arghi = 0; WARN_ON_ONCE(pages > RPCSVC_MAXPAGES); if (pages > RPCSVC_MAXPAGES) pages = RPCSVC_MAXPAGES; - while (pages) { - struct page *p = alloc_pages_node(node, GFP_KERNEL, 0); - if (!p) - break; - rqstp->rq_pages[arghi++] = p; - pages--; - } - return pages == 0; + + ret = alloc_pages_bulk_array_node(GFP_KERNEL, node, pages, + rqstp->rq_pages); + return ret == pages; } /* @@ -1173,6 +1164,7 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi */ static void svc_unregister(const struct svc_serv *serv, struct net *net) { + struct sighand_struct *sighand; struct svc_program *progp; unsigned long flags; unsigned int i; @@ -1189,9 +1181,12 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) } } - spin_lock_irqsave(¤t->sighand->siglock, flags); + rcu_read_lock(); + sighand = rcu_dereference(current->sighand); + spin_lock_irqsave(&sighand->siglock, flags); recalc_sigpending(); - spin_unlock_irqrestore(¤t->sighand->siglock, flags); + spin_unlock_irqrestore(&sighand->siglock, flags); + rcu_read_unlock(); } /* diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 13a14897bc17..62c7919ea610 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -74,13 +74,18 @@ static LIST_HEAD(svc_xprt_class_list); * that no other thread will be using the transport or will * try to set XPT_DEAD. */ + +/** + * svc_reg_xprt_class - Register a server-side RPC transport class + * @xcl: New transport class to be registered + * + * Returns zero on success; otherwise a negative errno is returned. + */ int svc_reg_xprt_class(struct svc_xprt_class *xcl) { struct svc_xprt_class *cl; int res = -EEXIST; - dprintk("svc: Adding svc transport class '%s'\n", xcl->xcl_name); - INIT_LIST_HEAD(&xcl->xcl_list); spin_lock(&svc_xprt_class_lock); /* Make sure there isn't already a class with the same name */ @@ -96,9 +101,13 @@ out: } EXPORT_SYMBOL_GPL(svc_reg_xprt_class); +/** + * svc_unreg_xprt_class - Unregister a server-side RPC transport class + * @xcl: Transport class to be unregistered + * + */ void svc_unreg_xprt_class(struct svc_xprt_class *xcl) { - dprintk("svc: Removing svc transport class '%s'\n", xcl->xcl_name); spin_lock(&svc_xprt_class_lock); list_del_init(&xcl->xcl_list); spin_unlock(&svc_xprt_class_lock); @@ -685,8 +694,9 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) } for (filled = 0; filled < pages; filled = ret) { - ret = alloc_pages_bulk_array(GFP_KERNEL, pages, - rqstp->rq_pages); + ret = alloc_pages_bulk_array_node(GFP_KERNEL, + rqstp->rq_pool->sp_id, + pages, rqstp->rq_pages); if (ret > filled) /* Made progress, don't sleep yet */ continue; @@ -843,15 +853,11 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) svc_xprt_received(xprt); } else if (svc_xprt_reserve_slot(rqstp, xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ - dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", - rqstp, rqstp->rq_pool->sp_id, xprt, - kref_read(&xprt->xpt_ref)); rqstp->rq_deferred = svc_deferred_dequeue(xprt); if (rqstp->rq_deferred) len = svc_deferred_recv(rqstp); else len = xprt->xpt_ops->xpo_recvfrom(rqstp); - rqstp->rq_stime = ktime_get(); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); } else @@ -894,6 +900,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) err = -EAGAIN; if (len <= 0) goto out_release; + trace_svc_xdr_recvfrom(&rqstp->rq_arg); clear_bit(XPT_OLD, &xprt->xpt_flags); @@ -902,6 +909,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (serv->sv_stats) serv->sv_stats->netcnt++; + rqstp->rq_stime = ktime_get(); return len; out_release: rqstp->rq_res.len = 0; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index f77cebe2c071..5f519fc0541b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -826,12 +826,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) trace_sk_data_ready(sk); - if (svsk) { - /* Refer to svc_setup_socket() for details. */ - rmb(); - svsk->sk_odata(sk); - } - /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -840,13 +834,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk) * when one of child sockets become ESTABLISHED. * 2) data_ready method of the child socket may be called * when it receives data before the socket is accepted. - * In case of 2, we should ignore it silently. + * In case of 2, we should ignore it silently and DO NOT + * dereference svsk. */ - if (sk->sk_state == TCP_LISTEN) { - if (svsk) { - set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); - } + if (sk->sk_state != TCP_LISTEN) + return; + + if (svsk) { + /* Refer to svc_setup_socket() for details. */ + rmb(); + svsk->sk_odata(sk); + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); + svc_xprt_enqueue(&svsk->sk_xprt); } } @@ -887,13 +886,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_accept(sock, &newsock, O_NONBLOCK); if (err < 0) { - if (err == -ENOMEM) - printk(KERN_WARNING "%s: no more sockets!\n", - serv->sv_name); - else if (err != -EAGAIN) - net_warn_ratelimited("%s: accept failed (err %d)!\n", - serv->sv_name, -err); - trace_svcsock_accept_err(xprt, serv->sv_name, err); + if (err != -EAGAIN) + trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL))) @@ -1464,7 +1458,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, svsk->sk_owspace = inet->sk_write_space; /* * This barrier is necessary in order to prevent race condition - * with svc_data_ready(), svc_listen_data_ready() and others + * with svc_data_ready(), svc_tcp_listen_data_ready(), and others * when calling callbacks above. */ wmb(); @@ -1476,7 +1470,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, else svc_tcp_init(svsk, serv); - trace_svcsock_new_socket(sock); + trace_svcsock_new(svsk, sock); return svsk; } @@ -1657,6 +1651,8 @@ static void svc_sock_free(struct svc_xprt *xprt) struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); struct socket *sock = svsk->sk_sock; + trace_svcsock_free(svsk, sock); + tls_handshake_cancel(sock->sk); if (sock->file) sockfd_put(sock); diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 36835b2f5446..2a22e78af116 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1070,22 +1070,22 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) } EXPORT_SYMBOL_GPL(xdr_reserve_space); - /** * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending * @xdr: pointer to xdr_stream - * @vec: pointer to a kvec array * @nbytes: number of bytes to reserve * - * Reserves enough buffer space to encode 'nbytes' of data and stores the - * pointers in 'vec'. The size argument passed to xdr_reserve_space() is - * determined based on the number of bytes remaining in the current page to - * avoid invalidating iov_base pointers when xdr_commit_encode() is called. + * The size argument passed to xdr_reserve_space() is determined based + * on the number of bytes remaining in the current page to avoid + * invalidating iov_base pointers when xdr_commit_encode() is called. + * + * Return values: + * %0: success + * %-EMSGSIZE: not enough space is available in @xdr */ -int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes) +int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes) { - int thislen; - int v = 0; + size_t thislen; __be32 *p; /* @@ -1097,21 +1097,19 @@ int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbyte xdr->end = xdr->p; } + /* XXX: Let's find a way to make this more efficient */ while (nbytes) { thislen = xdr->buf->page_len % PAGE_SIZE; thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen); p = xdr_reserve_space(xdr, thislen); if (!p) - return -EIO; + return -EMSGSIZE; - vec[v].iov_base = p; - vec[v].iov_len = thislen; - v++; nbytes -= thislen; } - return v; + return 0; } EXPORT_SYMBOL_GPL(xdr_reserve_space_vec); diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index aa2227a7e552..7420a2c990c7 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -93,13 +93,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, */ get_page(virt_to_page(rqst->rq_buffer)); sctxt->sc_send_wr.opcode = IB_WR_SEND; - ret = svc_rdma_send(rdma, sctxt); - if (ret < 0) - return ret; - - ret = wait_for_completion_killable(&sctxt->sc_done); - svc_rdma_send_ctxt_put(rdma, sctxt); - return ret; + return svc_rdma_send(rdma, sctxt); } /* Server-side transport endpoint wants a whole page for its send diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index a22fe7587fa6..85c8bcaebb80 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -125,14 +125,15 @@ static void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma, static struct svc_rdma_recv_ctxt * svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma) { + int node = ibdev_to_node(rdma->sc_cm_id->device); struct svc_rdma_recv_ctxt *ctxt; dma_addr_t addr; void *buffer; - ctxt = kmalloc(sizeof(*ctxt), GFP_KERNEL); + ctxt = kmalloc_node(sizeof(*ctxt), GFP_KERNEL, node); if (!ctxt) goto fail0; - buffer = kmalloc(rdma->sc_max_req_size, GFP_KERNEL); + buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node); if (!buffer) goto fail1; addr = ib_dma_map_single(rdma->sc_pd->device, buffer, @@ -155,7 +156,6 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma) ctxt->rc_recv_sge.length = rdma->sc_max_req_size; ctxt->rc_recv_sge.lkey = rdma->sc_pd->local_dma_lkey; ctxt->rc_recv_buf = buffer; - ctxt->rc_temp = false; return ctxt; fail2: @@ -232,10 +232,7 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, pcl_free(&ctxt->rc_write_pcl); pcl_free(&ctxt->rc_reply_pcl); - if (!ctxt->rc_temp) - llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts); - else - svc_rdma_recv_ctxt_destroy(rdma, ctxt); + llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts); } /** @@ -258,7 +255,7 @@ void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) } static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma, - unsigned int wanted, bool temp) + unsigned int wanted) { const struct ib_recv_wr *bad_wr = NULL; struct svc_rdma_recv_ctxt *ctxt; @@ -275,7 +272,6 @@ static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma, break; trace_svcrdma_post_recv(ctxt); - ctxt->rc_temp = temp; ctxt->rc_recv_wr.next = recv_chain; recv_chain = &ctxt->rc_recv_wr; rdma->sc_pending_recvs++; @@ -309,7 +305,7 @@ err_free: */ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) { - return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true); + return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests); } /** @@ -343,7 +339,7 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) * client reconnects. */ if (rdma->sc_pending_recvs < rdma->sc_max_requests) - if (!svc_rdma_refresh_recvs(rdma, rdma->sc_recv_batch, false)) + if (!svc_rdma_refresh_recvs(rdma, rdma->sc_recv_batch)) goto dropped; /* All wc fields are now known to be valid */ @@ -775,9 +771,6 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt, * * The next ctxt is removed from the "receive" lists. * - * - If the ctxt completes a Read, then finish assembling the Call - * message and return the number of bytes in the message. - * * - If the ctxt completes a Receive, then construct the Call * message from the contents of the Receive buffer. * @@ -786,7 +779,8 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt, * in the message. * * - If there are Read chunks in this message, post Read WRs to - * pull that payload and return 0. + * pull that payload. When the Read WRs complete, build the + * full message and return the number of bytes in it. */ int svc_rdma_recvfrom(struct svc_rqst *rqstp) { @@ -796,6 +790,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svc_rdma_recv_ctxt *ctxt; int ret; + /* Prevent svc_xprt_release() from releasing pages in rq_pages + * when returning 0 or an error. + */ + rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_next_page = rqstp->rq_respages; + rqstp->rq_xprt_ctxt = NULL; ctxt = NULL; @@ -819,12 +819,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) DMA_FROM_DEVICE); svc_rdma_build_arg_xdr(rqstp, ctxt); - /* Prevent svc_xprt_release from releasing pages in rq_pages - * if we return 0 or an error. - */ - rqstp->rq_respages = rqstp->rq_pages; - rqstp->rq_next_page = rqstp->rq_respages; - ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg, ctxt); if (ret < 0) goto out_err; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 11cf7c646644..e460e25a1d6d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -62,8 +62,8 @@ svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) if (node) { ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); } else { - ctxt = kmalloc(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), - GFP_KERNEL); + ctxt = kmalloc_node(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), + GFP_KERNEL, ibdev_to_node(rdma->sc_cm_id->device)); if (!ctxt) goto out_noctx; @@ -84,8 +84,7 @@ out_noctx: return NULL; } -static void __svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, - struct svc_rdma_rw_ctxt *ctxt, +static void __svc_rdma_put_rw_ctxt(struct svc_rdma_rw_ctxt *ctxt, struct llist_head *list) { sg_free_table_chained(&ctxt->rw_sg_table, SG_CHUNK_SIZE); @@ -95,7 +94,7 @@ static void __svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, struct svc_rdma_rw_ctxt *ctxt) { - __svc_rdma_put_rw_ctxt(rdma, ctxt, &rdma->sc_rw_ctxts); + __svc_rdma_put_rw_ctxt(ctxt, &rdma->sc_rw_ctxts); } /** @@ -191,6 +190,8 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, struct svc_rdma_rw_ctxt *ctxt; LLIST_HEAD(free); + trace_svcrdma_cc_release(&cc->cc_cid, cc->cc_sqecount); + first = last = NULL; while ((ctxt = svc_rdma_next_ctxt(&cc->cc_rwctxts)) != NULL) { list_del(&ctxt->rw_list); @@ -198,7 +199,7 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, ctxt->rw_sg_table.sgl, ctxt->rw_nents, dir); - __svc_rdma_put_rw_ctxt(rdma, ctxt, &free); + __svc_rdma_put_rw_ctxt(ctxt, &free); ctxt->rw_node.next = first; first = &ctxt->rw_node; @@ -234,7 +235,8 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, { struct svc_rdma_write_info *info; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kmalloc_node(sizeof(*info), GFP_KERNEL, + ibdev_to_node(rdma->sc_cm_id->device)); if (!info) return info; @@ -304,7 +306,8 @@ svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma) { struct svc_rdma_read_info *info; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kmalloc_node(sizeof(*info), GFP_KERNEL, + ibdev_to_node(rdma->sc_cm_id->device)); if (!info) return info; @@ -351,8 +354,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) return; } -/* This function sleeps when the transport's Send Queue is congested. - * +/* * Assumptions: * - If ib_post_send() succeeds, only one completion is expected, * even if one or more WRs are flushed. This is true when posting @@ -367,6 +369,8 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) struct ib_cqe *cqe; int ret; + might_sleep(); + if (cc->cc_sqecount > rdma->sc_sq_depth) return -EINVAL; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 22a871e6fe4d..c6644cca52c5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -123,18 +123,17 @@ static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma, static struct svc_rdma_send_ctxt * svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) { + int node = ibdev_to_node(rdma->sc_cm_id->device); struct svc_rdma_send_ctxt *ctxt; dma_addr_t addr; void *buffer; - size_t size; int i; - size = sizeof(*ctxt); - size += rdma->sc_max_send_sges * sizeof(struct ib_sge); - ctxt = kmalloc(size, GFP_KERNEL); + ctxt = kmalloc_node(struct_size(ctxt, sc_sges, rdma->sc_max_send_sges), + GFP_KERNEL, node); if (!ctxt) goto fail0; - buffer = kmalloc(rdma->sc_max_req_size, GFP_KERNEL); + buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node); if (!buffer) goto fail1; addr = ib_dma_map_single(rdma->sc_pd->device, buffer, @@ -148,7 +147,6 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe; ctxt->sc_send_wr.sg_list = ctxt->sc_sges; ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED; - init_completion(&ctxt->sc_done); ctxt->sc_cqe.done = svc_rdma_wc_send; ctxt->sc_xprt_buf = buffer; xdr_buf_init(&ctxt->sc_hdrbuf, ctxt->sc_xprt_buf, @@ -214,6 +212,7 @@ out: ctxt->sc_send_wr.num_sge = 0; ctxt->sc_cur_sge_no = 0; + ctxt->sc_page_count = 0; return ctxt; out_empty: @@ -228,6 +227,8 @@ out_empty: * svc_rdma_send_ctxt_put - Return send_ctxt to free list * @rdma: controlling svcxprt_rdma * @ctxt: object to return to the free list + * + * Pages left in sc_pages are DMA unmapped and released. */ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt) @@ -235,6 +236,9 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, struct ib_device *device = rdma->sc_cm_id->device; unsigned int i; + if (ctxt->sc_page_count) + release_pages(ctxt->sc_pages, ctxt->sc_page_count); + /* The first SGE contains the transport header, which * remains mapped until @ctxt is destroyed. */ @@ -281,12 +285,12 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe); svc_rdma_wake_send_waiters(rdma, 1); - complete(&ctxt->sc_done); if (unlikely(wc->status != IB_WC_SUCCESS)) goto flushed; trace_svcrdma_wc_send(wc, &ctxt->sc_cid); + svc_rdma_send_ctxt_put(rdma, ctxt); return; flushed: @@ -294,6 +298,7 @@ flushed: trace_svcrdma_wc_send_err(wc, &ctxt->sc_cid); else trace_svcrdma_wc_send_flush(wc, &ctxt->sc_cid); + svc_rdma_send_ctxt_put(rdma, ctxt); svc_xprt_deferred_close(&rdma->sc_xprt); } @@ -310,7 +315,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt) struct ib_send_wr *wr = &ctxt->sc_send_wr; int ret; - reinit_completion(&ctxt->sc_done); + might_sleep(); /* Sync the transport header buffer */ ib_dma_sync_single_for_device(rdma->sc_pd->device, @@ -799,6 +804,25 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, svc_rdma_xb_dma_map, &args); } +/* The svc_rqst and all resources it owns are released as soon as + * svc_rdma_sendto returns. Transfer pages under I/O to the ctxt + * so they are released by the Send completion handler. + */ +static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, + struct svc_rdma_send_ctxt *ctxt) +{ + int i, pages = rqstp->rq_next_page - rqstp->rq_respages; + + ctxt->sc_page_count += pages; + for (i = 0; i < pages; i++) { + ctxt->sc_pages[i] = rqstp->rq_respages[i]; + rqstp->rq_respages[i] = NULL; + } + + /* Prevent svc_xprt_release from releasing pages in rq_pages */ + rqstp->rq_next_page = rqstp->rq_respages; +} + /* Prepare the portion of the RPC Reply that will be transmitted * via RDMA Send. The RPC-over-RDMA transport header is prepared * in sc_sges[0], and the RPC xdr_buf is prepared in following sges. @@ -828,6 +852,8 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, if (ret < 0) return ret; + svc_rdma_save_io_pages(rqstp, sctxt); + if (rctxt->rc_inv_rkey) { sctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV; sctxt->sc_send_wr.ex.invalidate_rkey = rctxt->rc_inv_rkey; @@ -835,13 +861,7 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, sctxt->sc_send_wr.opcode = IB_WR_SEND; } - ret = svc_rdma_send(rdma, sctxt); - if (ret < 0) - return ret; - - ret = wait_for_completion_killable(&sctxt->sc_done); - svc_rdma_send_ctxt_put(rdma, sctxt); - return ret; + return svc_rdma_send(rdma, sctxt); } /** @@ -907,8 +927,7 @@ void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len; if (svc_rdma_send(rdma, sctxt)) goto put_ctxt; - - wait_for_completion_killable(&sctxt->sc_done); + return; put_ctxt: svc_rdma_send_ctxt_put(rdma, sctxt); @@ -976,17 +995,16 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp); if (ret < 0) goto put_ctxt; - - /* Prevent svc_xprt_release() from releasing the page backing - * rq_res.head[0].iov_base. It's no longer being accessed by - * the I/O device. */ - rqstp->rq_respages++; return 0; reply_chunk: if (ret != -E2BIG && ret != -EINVAL) goto put_ctxt; + /* Send completion releases payload pages that were part + * of previously posted RDMA Writes. + */ + svc_rdma_save_io_pages(rqstp, sctxt); svc_rdma_send_error_msg(rdma, sctxt, rctxt, ret); return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index ca04f7a6a085..2abd895046ee 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -64,7 +64,7 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, - struct net *net); + struct net *net, int node); static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct net *net, struct sockaddr *sa, int salen, @@ -123,14 +123,14 @@ static void qp_event_handler(struct ib_event *event, void *context) } static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, - struct net *net) + struct net *net, int node) { - struct svcxprt_rdma *cma_xprt = kzalloc(sizeof *cma_xprt, GFP_KERNEL); + struct svcxprt_rdma *cma_xprt; - if (!cma_xprt) { - dprintk("svcrdma: failed to create new transport\n"); + cma_xprt = kzalloc_node(sizeof(*cma_xprt), GFP_KERNEL, node); + if (!cma_xprt) return NULL; - } + svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv); INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); @@ -193,9 +193,9 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, struct svcxprt_rdma *newxprt; struct sockaddr *sa; - /* Create a new transport */ newxprt = svc_rdma_create_xprt(listen_xprt->sc_xprt.xpt_server, - listen_xprt->sc_xprt.xpt_net); + listen_xprt->sc_xprt.xpt_net, + ibdev_to_node(new_cma_id->device)); if (!newxprt) return; newxprt->sc_cm_id = new_cma_id; @@ -304,7 +304,7 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, if (sa->sa_family != AF_INET && sa->sa_family != AF_INET6) return ERR_PTR(-EAFNOSUPPORT); - cma_xprt = svc_rdma_create_xprt(serv, net); + cma_xprt = svc_rdma_create_xprt(serv, net, NUMA_NO_NODE); if (!cma_xprt) return ERR_PTR(-ENOMEM); set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 53881406e200..cdcd2731860b 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1258,7 +1258,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) struct tipc_nl_msg msg; struct tipc_media *media; struct sk_buff *rep; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; @@ -1307,7 +1307,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) int err; char *name; struct tipc_media *m; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 2e497cf26ef2..69b508743e57 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018, 2021-2022 Intel Corporation + * Copyright (C) 2018, 2021-2023 Intel Corporation */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS @@ -1441,8 +1441,8 @@ rdev_del_intf_link(struct cfg80211_registered_device *rdev, unsigned int link_id) { trace_rdev_del_intf_link(&rdev->wiphy, wdev, link_id); - if (rdev->ops->add_intf_link) - rdev->ops->add_intf_link(&rdev->wiphy, wdev, link_id); + if (rdev->ops->del_intf_link) + rdev->ops->del_intf_link(&rdev->wiphy, wdev, link_id); trace_rdev_return_void(&rdev->wiphy); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 949e1fb3bec6..26f11e4746c0 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2404,11 +2404,8 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: - wiphy_lock(wiphy); ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); - wiphy_unlock(wiphy); - if (!ret) return ret; break; diff --git a/net/wireless/util.c b/net/wireless/util.c index 3bc0c3072e78..9755ef281040 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -2558,6 +2558,13 @@ void cfg80211_remove_links(struct wireless_dev *wdev) { unsigned int link_id; + /* + * links are controlled by upper layers (userspace/cfg) + * only for AP mode, so only remove them here for AP + */ + if (wdev->iftype != NL80211_IFTYPE_AP) + return; + wdev_lock(wdev); if (wdev->valid_links) { for_each_valid_link(wdev, link_id) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 39fb91ff23d9..815b38080401 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -131,6 +131,7 @@ struct sec_path *secpath_set(struct sk_buff *skb) memset(sp->ovec, 0, sizeof(sp->ovec)); sp->olen = 0; sp->len = 0; + sp->verified_cnt = 0; return sp; } @@ -330,11 +331,10 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x, { switch (x->props.mode) { case XFRM_MODE_BEET: - switch (XFRM_MODE_SKB_CB(skb)->protocol) { - case IPPROTO_IPIP: - case IPPROTO_BEETPH: + switch (x->sel.family) { + case AF_INET: return xfrm4_remove_beet_encap(x, skb); - case IPPROTO_IPV6: + case AF_INET6: return xfrm6_remove_beet_encap(x, skb); } break; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc469027..35279c220bd7 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6d15788b5123..e7617c9959c3 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1831,6 +1831,7 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -1869,6 +1870,7 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -3349,6 +3351,13 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { + if (idx < sp->verified_cnt) { + /* Secpath entry previously verified, consider optional and + * continue searching + */ + continue; + } + if (start == -1) start = -2-idx; break; @@ -3723,6 +3732,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. + * Upon success, marks secpath entries as having been + * verified to allow them to be skipped in future policy + * checks (e.g. nested tunnels). */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); @@ -3741,6 +3753,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_pols_put(pols, npols); + sp->verified_cnt = k; + return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); diff --git a/rust/alloc/README.md b/rust/alloc/README.md index c89c753720b5..eb6f22e94ebf 100644 --- a/rust/alloc/README.md +++ b/rust/alloc/README.md @@ -10,6 +10,9 @@ upstream. In general, only additions should be performed (e.g. new methods). Eventually, changes should make it into upstream so that, at some point, this fork can be dropped from the kernel tree. +The Rust upstream version on top of which these files are based matches +the output of `scripts/min-tool-version.sh rustc`. + ## Rationale diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs index ca224a541770..acf22d45e6f2 100644 --- a/rust/alloc/alloc.rs +++ b/rust/alloc/alloc.rs @@ -22,21 +22,24 @@ use core::marker::Destruct; mod tests; extern "Rust" { - // These are the magic symbols to call the global allocator. rustc generates + // These are the magic symbols to call the global allocator. rustc generates // them to call `__rg_alloc` etc. if there is a `#[global_allocator]` attribute // (the code expanding that attribute macro generates those functions), or to call - // the default implementations in libstd (`__rdl_alloc` etc. in `library/std/src/alloc.rs`) + // the default implementations in std (`__rdl_alloc` etc. in `library/std/src/alloc.rs`) // otherwise. - // The rustc fork of LLVM also special-cases these function names to be able to optimize them + // The rustc fork of LLVM 14 and earlier also special-cases these function names to be able to optimize them // like `malloc`, `realloc`, and `free`, respectively. #[rustc_allocator] - #[rustc_allocator_nounwind] + #[rustc_nounwind] fn __rust_alloc(size: usize, align: usize) -> *mut u8; - #[rustc_allocator_nounwind] + #[rustc_deallocator] + #[rustc_nounwind] fn __rust_dealloc(ptr: *mut u8, size: usize, align: usize); - #[rustc_allocator_nounwind] + #[rustc_reallocator] + #[rustc_nounwind] fn __rust_realloc(ptr: *mut u8, old_size: usize, align: usize, new_size: usize) -> *mut u8; - #[rustc_allocator_nounwind] + #[rustc_allocator_zeroed] + #[rustc_nounwind] fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8; } @@ -72,11 +75,14 @@ pub use std::alloc::Global; /// # Examples /// /// ``` -/// use std::alloc::{alloc, dealloc, Layout}; +/// use std::alloc::{alloc, dealloc, handle_alloc_error, Layout}; /// /// unsafe { /// let layout = Layout::new::<u16>(); /// let ptr = alloc(layout); +/// if ptr.is_null() { +/// handle_alloc_error(layout); +/// } /// /// *(ptr as *mut u16) = 42; /// assert_eq!(*(ptr as *mut u16), 42); @@ -349,7 +355,7 @@ pub(crate) const unsafe fn box_free<T: ?Sized, A: ~const Allocator + ~const Dest #[cfg(not(no_global_oom_handling))] extern "Rust" { - // This is the magic symbol to call the global alloc error handler. rustc generates + // This is the magic symbol to call the global alloc error handler. rustc generates // it to call `__rg_oom` if there is a `#[alloc_error_handler]`, or to call the // default implementations below (`__rdl_oom`) otherwise. fn __rust_alloc_error_handler(size: usize, align: usize) -> !; @@ -394,25 +400,24 @@ pub use std::alloc::handle_alloc_error; #[allow(unused_attributes)] #[unstable(feature = "alloc_internals", issue = "none")] pub mod __alloc_error_handler { - use crate::alloc::Layout; - - // called via generated `__rust_alloc_error_handler` - - // if there is no `#[alloc_error_handler]` + // called via generated `__rust_alloc_error_handler` if there is no + // `#[alloc_error_handler]`. #[rustc_std_internal_symbol] - pub unsafe extern "C-unwind" fn __rdl_oom(size: usize, _align: usize) -> ! { - panic!("memory allocation of {size} bytes failed") - } - - // if there is an `#[alloc_error_handler]` - #[rustc_std_internal_symbol] - pub unsafe extern "C-unwind" fn __rg_oom(size: usize, align: usize) -> ! { - let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + pub unsafe fn __rdl_oom(size: usize, _align: usize) -> ! { extern "Rust" { - #[lang = "oom"] - fn oom_impl(layout: Layout) -> !; + // This symbol is emitted by rustc next to __rust_alloc_error_handler. + // Its value depends on the -Zoom={panic,abort} compiler option. + static __rust_alloc_error_handler_should_panic: u8; + } + + #[allow(unused_unsafe)] + if unsafe { __rust_alloc_error_handler_should_panic != 0 } { + panic!("memory allocation of {size} bytes failed") + } else { + core::panicking::panic_nounwind_fmt(format_args!( + "memory allocation of {size} bytes failed" + )) } - unsafe { oom_impl(layout) } } } diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs index dcfe87b14f3a..14af9860c36c 100644 --- a/rust/alloc/boxed.rs +++ b/rust/alloc/boxed.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT -//! A pointer type for heap allocation. +//! The `Box<T>` type for heap allocation. //! //! [`Box<T>`], casually referred to as a 'box', provides the simplest form of //! heap allocation in Rust. Boxes provide ownership for this allocation, and @@ -124,7 +124,21 @@ //! definition is just using `T*` can lead to undefined behavior, as //! described in [rust-lang/unsafe-code-guidelines#198][ucg#198]. //! +//! # Considerations for unsafe code +//! +//! **Warning: This section is not normative and is subject to change, possibly +//! being relaxed in the future! It is a simplified summary of the rules +//! currently implemented in the compiler.** +//! +//! The aliasing rules for `Box<T>` are the same as for `&mut T`. `Box<T>` +//! asserts uniqueness over its content. Using raw pointers derived from a box +//! after that box has been mutated through, moved or borrowed as `&mut T` +//! is not allowed. For more guidance on working with box from unsafe code, see +//! [rust-lang/unsafe-code-guidelines#326][ucg#326]. +//! +//! //! [ucg#198]: https://github.com/rust-lang/unsafe-code-guidelines/issues/198 +//! [ucg#326]: https://github.com/rust-lang/unsafe-code-guidelines/issues/326 //! [dereferencing]: core::ops::Deref //! [`Box::<T>::from_raw(value)`]: Box::from_raw //! [`Global`]: crate::alloc::Global @@ -139,12 +153,14 @@ use core::async_iter::AsyncIterator; use core::borrow; use core::cmp::Ordering; use core::convert::{From, TryFrom}; +use core::error::Error; use core::fmt; use core::future::Future; use core::hash::{Hash, Hasher}; #[cfg(not(no_global_oom_handling))] use core::iter::FromIterator; use core::iter::{FusedIterator, Iterator}; +use core::marker::Tuple; use core::marker::{Destruct, Unpin, Unsize}; use core::mem; use core::ops::{ @@ -163,6 +179,8 @@ use crate::raw_vec::RawVec; #[cfg(not(no_global_oom_handling))] use crate::str::from_boxed_utf8_unchecked; #[cfg(not(no_global_oom_handling))] +use crate::string::String; +#[cfg(not(no_global_oom_handling))] use crate::vec::Vec; #[cfg(not(no_thin))] @@ -172,7 +190,7 @@ pub use thin::ThinBox; #[cfg(not(no_thin))] mod thin; -/// A pointer type for heap allocation. +/// A pointer type that uniquely owns a heap allocation of type `T`. /// /// See the [module-level documentation](../../std/boxed/index.html) for more. #[lang = "owned_box"] @@ -196,12 +214,13 @@ impl<T> Box<T> { /// ``` /// let five = Box::new(5); /// ``` - #[cfg(not(no_global_oom_handling))] + #[cfg(all(not(no_global_oom_handling)))] #[inline(always)] #[stable(feature = "rust1", since = "1.0.0")] #[must_use] pub fn new(x: T) -> Self { - box x + #[rustc_box] + Box::new(x) } /// Constructs a new box with uninitialized contents. @@ -256,14 +275,21 @@ impl<T> Box<T> { Self::new_zeroed_in(Global) } - /// Constructs a new `Pin<Box<T>>`. If `T` does not implement `Unpin`, then + /// Constructs a new `Pin<Box<T>>`. If `T` does not implement [`Unpin`], then /// `x` will be pinned in memory and unable to be moved. + /// + /// Constructing and pinning of the `Box` can also be done in two steps: `Box::pin(x)` + /// does the same as <code>[Box::into_pin]\([Box::new]\(x))</code>. Consider using + /// [`into_pin`](Box::into_pin) if you already have a `Box<T>`, or if you want to + /// construct a (pinned) `Box` in a different way than with [`Box::new`]. #[cfg(not(no_global_oom_handling))] #[stable(feature = "pin", since = "1.33.0")] #[must_use] #[inline(always)] pub fn pin(x: T) -> Pin<Box<T>> { - (box x).into() + (#[rustc_box] + Box::new(x)) + .into() } /// Allocates memory on the heap then places `x` into it, @@ -543,8 +569,13 @@ impl<T, A: Allocator> Box<T, A> { unsafe { Ok(Box::from_raw_in(ptr.as_ptr(), alloc)) } } - /// Constructs a new `Pin<Box<T, A>>`. If `T` does not implement `Unpin`, then + /// Constructs a new `Pin<Box<T, A>>`. If `T` does not implement [`Unpin`], then /// `x` will be pinned in memory and unable to be moved. + /// + /// Constructing and pinning of the `Box` can also be done in two steps: `Box::pin_in(x, alloc)` + /// does the same as <code>[Box::into_pin]\([Box::new_in]\(x, alloc))</code>. Consider using + /// [`into_pin`](Box::into_pin) if you already have a `Box<T, A>`, or if you want to + /// construct a (pinned) `Box` in a different way than with [`Box::new_in`]. #[cfg(not(no_global_oom_handling))] #[unstable(feature = "allocator_api", issue = "32838")] #[rustc_const_unstable(feature = "const_box", issue = "92521")] @@ -926,6 +957,7 @@ impl<T: ?Sized> Box<T> { /// [`Layout`]: crate::Layout #[stable(feature = "box_raw", since = "1.4.0")] #[inline] + #[must_use = "call `drop(Box::from_raw(ptr))` if you intend to drop the `Box`"] pub unsafe fn from_raw(raw: *mut T) -> Self { unsafe { Self::from_raw_in(raw, Global) } } @@ -1160,19 +1192,44 @@ impl<T: ?Sized, A: Allocator> Box<T, A> { unsafe { &mut *mem::ManuallyDrop::new(b).0.as_ptr() } } - /// Converts a `Box<T>` into a `Pin<Box<T>>` + /// Converts a `Box<T>` into a `Pin<Box<T>>`. If `T` does not implement [`Unpin`], then + /// `*boxed` will be pinned in memory and unable to be moved. /// /// This conversion does not allocate on the heap and happens in place. /// /// This is also available via [`From`]. - #[unstable(feature = "box_into_pin", issue = "62370")] + /// + /// Constructing and pinning a `Box` with <code>Box::into_pin([Box::new]\(x))</code> + /// can also be written more concisely using <code>[Box::pin]\(x)</code>. + /// This `into_pin` method is useful if you already have a `Box<T>`, or you are + /// constructing a (pinned) `Box` in a different way than with [`Box::new`]. + /// + /// # Notes + /// + /// It's not recommended that crates add an impl like `From<Box<T>> for Pin<T>`, + /// as it'll introduce an ambiguity when calling `Pin::from`. + /// A demonstration of such a poor impl is shown below. + /// + /// ```compile_fail + /// # use std::pin::Pin; + /// struct Foo; // A type defined in this crate. + /// impl From<Box<()>> for Pin<Foo> { + /// fn from(_: Box<()>) -> Pin<Foo> { + /// Pin::new(Foo) + /// } + /// } + /// + /// let foo = Box::new(()); + /// let bar = Pin::from(foo); + /// ``` + #[stable(feature = "box_into_pin", since = "1.63.0")] #[rustc_const_unstable(feature = "const_box", issue = "92521")] pub const fn into_pin(boxed: Self) -> Pin<Self> where A: 'static, { // It's not possible to move or replace the insides of a `Pin<Box<T>>` - // when `T: !Unpin`, so it's safe to pin it directly without any + // when `T: !Unpin`, so it's safe to pin it directly without any // additional requirements. unsafe { Pin::new_unchecked(boxed) } } @@ -1190,7 +1247,8 @@ unsafe impl<#[may_dangle] T: ?Sized, A: Allocator> Drop for Box<T, A> { impl<T: Default> Default for Box<T> { /// Creates a `Box<T>`, with the `Default` value for T. fn default() -> Self { - box T::default() + #[rustc_box] + Box::new(T::default()) } } @@ -1408,9 +1466,17 @@ impl<T: ?Sized, A: Allocator> const From<Box<T, A>> for Pin<Box<T, A>> where A: 'static, { - /// Converts a `Box<T>` into a `Pin<Box<T>>` + /// Converts a `Box<T>` into a `Pin<Box<T>>`. If `T` does not implement [`Unpin`], then + /// `*boxed` will be pinned in memory and unable to be moved. /// /// This conversion does not allocate on the heap and happens in place. + /// + /// This is also available via [`Box::into_pin`]. + /// + /// Constructing and pinning a `Box` with <code><Pin<Box\<T>>>::from([Box::new]\(x))</code> + /// can also be written more concisely using <code>[Box::pin]\(x)</code>. + /// This `From` implementation is useful if you already have a `Box<T>`, or you are + /// constructing a (pinned) `Box` in a different way than with [`Box::new`]. fn from(boxed: Box<T, A>) -> Self { Box::into_pin(boxed) } @@ -1422,7 +1488,7 @@ impl<T: Copy> From<&[T]> for Box<[T]> { /// Converts a `&[T]` into a `Box<[T]>` /// /// This conversion allocates on the heap - /// and performs a copy of `slice`. + /// and performs a copy of `slice` and its contents. /// /// # Examples /// ```rust @@ -1554,10 +1620,27 @@ impl<T, const N: usize> From<[T; N]> for Box<[T]> { /// println!("{boxed:?}"); /// ``` fn from(array: [T; N]) -> Box<[T]> { - box array + #[rustc_box] + Box::new(array) } } +/// Casts a boxed slice to a boxed array. +/// +/// # Safety +/// +/// `boxed_slice.len()` must be exactly `N`. +unsafe fn boxed_slice_as_array_unchecked<T, A: Allocator, const N: usize>( + boxed_slice: Box<[T], A>, +) -> Box<[T; N], A> { + debug_assert_eq!(boxed_slice.len(), N); + + let (ptr, alloc) = Box::into_raw_with_allocator(boxed_slice); + // SAFETY: Pointer and allocator came from an existing box, + // and our safety condition requires that the length is exactly `N` + unsafe { Box::from_raw_in(ptr as *mut [T; N], alloc) } +} + #[stable(feature = "boxed_slice_try_from", since = "1.43.0")] impl<T, const N: usize> TryFrom<Box<[T]>> for Box<[T; N]> { type Error = Box<[T]>; @@ -1573,13 +1656,46 @@ impl<T, const N: usize> TryFrom<Box<[T]>> for Box<[T; N]> { /// `boxed_slice.len()` does not equal `N`. fn try_from(boxed_slice: Box<[T]>) -> Result<Self, Self::Error> { if boxed_slice.len() == N { - Ok(unsafe { Box::from_raw(Box::into_raw(boxed_slice) as *mut [T; N]) }) + Ok(unsafe { boxed_slice_as_array_unchecked(boxed_slice) }) } else { Err(boxed_slice) } } } +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "boxed_array_try_from_vec", since = "1.66.0")] +impl<T, const N: usize> TryFrom<Vec<T>> for Box<[T; N]> { + type Error = Vec<T>; + + /// Attempts to convert a `Vec<T>` into a `Box<[T; N]>`. + /// + /// Like [`Vec::into_boxed_slice`], this is in-place if `vec.capacity() == N`, + /// but will require a reallocation otherwise. + /// + /// # Errors + /// + /// Returns the original `Vec<T>` in the `Err` variant if + /// `boxed_slice.len()` does not equal `N`. + /// + /// # Examples + /// + /// This can be used with [`vec!`] to create an array on the heap: + /// + /// ``` + /// let state: Box<[f32; 100]> = vec![1.0; 100].try_into().unwrap(); + /// assert_eq!(state.len(), 100); + /// ``` + fn try_from(vec: Vec<T>) -> Result<Self, Self::Error> { + if vec.len() == N { + let boxed_slice = vec.into_boxed_slice(); + Ok(unsafe { boxed_slice_as_array_unchecked(boxed_slice) }) + } else { + Err(vec) + } + } +} + impl<A: Allocator> Box<dyn Any, A> { /// Attempt to downcast the box to a concrete type. /// @@ -1869,7 +1985,7 @@ impl<I: ExactSizeIterator + ?Sized, A: Allocator> ExactSizeIterator for Box<I, A impl<I: FusedIterator + ?Sized, A: Allocator> FusedIterator for Box<I, A> {} #[stable(feature = "boxed_closure_impls", since = "1.35.0")] -impl<Args, F: FnOnce<Args> + ?Sized, A: Allocator> FnOnce<Args> for Box<F, A> { +impl<Args: Tuple, F: FnOnce<Args> + ?Sized, A: Allocator> FnOnce<Args> for Box<F, A> { type Output = <F as FnOnce<Args>>::Output; extern "rust-call" fn call_once(self, args: Args) -> Self::Output { @@ -1878,20 +1994,20 @@ impl<Args, F: FnOnce<Args> + ?Sized, A: Allocator> FnOnce<Args> for Box<F, A> { } #[stable(feature = "boxed_closure_impls", since = "1.35.0")] -impl<Args, F: FnMut<Args> + ?Sized, A: Allocator> FnMut<Args> for Box<F, A> { +impl<Args: Tuple, F: FnMut<Args> + ?Sized, A: Allocator> FnMut<Args> for Box<F, A> { extern "rust-call" fn call_mut(&mut self, args: Args) -> Self::Output { <F as FnMut<Args>>::call_mut(self, args) } } #[stable(feature = "boxed_closure_impls", since = "1.35.0")] -impl<Args, F: Fn<Args> + ?Sized, A: Allocator> Fn<Args> for Box<F, A> { +impl<Args: Tuple, F: Fn<Args> + ?Sized, A: Allocator> Fn<Args> for Box<F, A> { extern "rust-call" fn call(&self, args: Args) -> Self::Output { <F as Fn<Args>>::call(self, args) } } -#[unstable(feature = "coerce_unsized", issue = "27732")] +#[unstable(feature = "coerce_unsized", issue = "18598")] impl<T: ?Sized + Unsize<U>, U: ?Sized, A: Allocator> CoerceUnsized<Box<U, A>> for Box<T, A> {} #[unstable(feature = "dispatch_from_dyn", issue = "none")] @@ -1973,8 +2089,7 @@ impl<T: ?Sized, A: Allocator> AsMut<T> for Box<T, A> { * could have a method to project a Pin<T> from it. */ #[stable(feature = "pin", since = "1.33.0")] -#[rustc_const_unstable(feature = "const_box", issue = "92521")] -impl<T: ?Sized, A: Allocator> const Unpin for Box<T, A> where A: 'static {} +impl<T: ?Sized, A: Allocator> Unpin for Box<T, A> where A: 'static {} #[unstable(feature = "generator_trait", issue = "43122")] impl<G: ?Sized + Generator<R> + Unpin, R, A: Allocator> Generator<R> for Box<G, A> @@ -2026,3 +2141,292 @@ impl<S: ?Sized + AsyncIterator + Unpin> AsyncIterator for Box<S> { (**self).size_hint() } } + +impl dyn Error { + #[inline] + #[stable(feature = "error_downcast", since = "1.3.0")] + #[rustc_allow_incoherent_impl] + /// Attempts to downcast the box to a concrete type. + pub fn downcast<T: Error + 'static>(self: Box<Self>) -> Result<Box<T>, Box<dyn Error>> { + if self.is::<T>() { + unsafe { + let raw: *mut dyn Error = Box::into_raw(self); + Ok(Box::from_raw(raw as *mut T)) + } + } else { + Err(self) + } + } +} + +impl dyn Error + Send { + #[inline] + #[stable(feature = "error_downcast", since = "1.3.0")] + #[rustc_allow_incoherent_impl] + /// Attempts to downcast the box to a concrete type. + pub fn downcast<T: Error + 'static>(self: Box<Self>) -> Result<Box<T>, Box<dyn Error + Send>> { + let err: Box<dyn Error> = self; + <dyn Error>::downcast(err).map_err(|s| unsafe { + // Reapply the `Send` marker. + mem::transmute::<Box<dyn Error>, Box<dyn Error + Send>>(s) + }) + } +} + +impl dyn Error + Send + Sync { + #[inline] + #[stable(feature = "error_downcast", since = "1.3.0")] + #[rustc_allow_incoherent_impl] + /// Attempts to downcast the box to a concrete type. + pub fn downcast<T: Error + 'static>(self: Box<Self>) -> Result<Box<T>, Box<Self>> { + let err: Box<dyn Error> = self; + <dyn Error>::downcast(err).map_err(|s| unsafe { + // Reapply the `Send + Sync` marker. + mem::transmute::<Box<dyn Error>, Box<dyn Error + Send + Sync>>(s) + }) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, E: Error + 'a> From<E> for Box<dyn Error + 'a> { + /// Converts a type of [`Error`] into a box of dyn [`Error`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::fmt; + /// use std::mem; + /// + /// #[derive(Debug)] + /// struct AnError; + /// + /// impl fmt::Display for AnError { + /// fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + /// write!(f, "An error") + /// } + /// } + /// + /// impl Error for AnError {} + /// + /// let an_error = AnError; + /// assert!(0 == mem::size_of_val(&an_error)); + /// let a_boxed_error = Box::<dyn Error>::from(an_error); + /// assert!(mem::size_of::<Box<dyn Error>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(err: E) -> Box<dyn Error + 'a> { + Box::new(err) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, E: Error + Send + Sync + 'a> From<E> for Box<dyn Error + Send + Sync + 'a> { + /// Converts a type of [`Error`] + [`Send`] + [`Sync`] into a box of + /// dyn [`Error`] + [`Send`] + [`Sync`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::fmt; + /// use std::mem; + /// + /// #[derive(Debug)] + /// struct AnError; + /// + /// impl fmt::Display for AnError { + /// fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + /// write!(f, "An error") + /// } + /// } + /// + /// impl Error for AnError {} + /// + /// unsafe impl Send for AnError {} + /// + /// unsafe impl Sync for AnError {} + /// + /// let an_error = AnError; + /// assert!(0 == mem::size_of_val(&an_error)); + /// let a_boxed_error = Box::<dyn Error + Send + Sync>::from(an_error); + /// assert!( + /// mem::size_of::<Box<dyn Error + Send + Sync>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(err: E) -> Box<dyn Error + Send + Sync + 'a> { + Box::new(err) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl From<String> for Box<dyn Error + Send + Sync> { + /// Converts a [`String`] into a box of dyn [`Error`] + [`Send`] + [`Sync`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// + /// let a_string_error = "a string error".to_string(); + /// let a_boxed_error = Box::<dyn Error + Send + Sync>::from(a_string_error); + /// assert!( + /// mem::size_of::<Box<dyn Error + Send + Sync>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + #[inline] + fn from(err: String) -> Box<dyn Error + Send + Sync> { + struct StringError(String); + + impl Error for StringError { + #[allow(deprecated)] + fn description(&self) -> &str { + &self.0 + } + } + + impl fmt::Display for StringError { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(&self.0, f) + } + } + + // Purposefully skip printing "StringError(..)" + impl fmt::Debug for StringError { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&self.0, f) + } + } + + Box::new(StringError(err)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "string_box_error", since = "1.6.0")] +impl From<String> for Box<dyn Error> { + /// Converts a [`String`] into a box of dyn [`Error`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// + /// let a_string_error = "a string error".to_string(); + /// let a_boxed_error = Box::<dyn Error>::from(a_string_error); + /// assert!(mem::size_of::<Box<dyn Error>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(str_err: String) -> Box<dyn Error> { + let err1: Box<dyn Error + Send + Sync> = From::from(str_err); + let err2: Box<dyn Error> = err1; + err2 + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a> From<&str> for Box<dyn Error + Send + Sync + 'a> { + /// Converts a [`str`] into a box of dyn [`Error`] + [`Send`] + [`Sync`]. + /// + /// [`str`]: prim@str + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// + /// let a_str_error = "a str error"; + /// let a_boxed_error = Box::<dyn Error + Send + Sync>::from(a_str_error); + /// assert!( + /// mem::size_of::<Box<dyn Error + Send + Sync>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + #[inline] + fn from(err: &str) -> Box<dyn Error + Send + Sync + 'a> { + From::from(String::from(err)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "string_box_error", since = "1.6.0")] +impl From<&str> for Box<dyn Error> { + /// Converts a [`str`] into a box of dyn [`Error`]. + /// + /// [`str`]: prim@str + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// + /// let a_str_error = "a str error"; + /// let a_boxed_error = Box::<dyn Error>::from(a_str_error); + /// assert!(mem::size_of::<Box<dyn Error>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(err: &str) -> Box<dyn Error> { + From::from(String::from(err)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_box_error", since = "1.22.0")] +impl<'a, 'b> From<Cow<'b, str>> for Box<dyn Error + Send + Sync + 'a> { + /// Converts a [`Cow`] into a box of dyn [`Error`] + [`Send`] + [`Sync`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// use std::borrow::Cow; + /// + /// let a_cow_str_error = Cow::from("a str error"); + /// let a_boxed_error = Box::<dyn Error + Send + Sync>::from(a_cow_str_error); + /// assert!( + /// mem::size_of::<Box<dyn Error + Send + Sync>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(err: Cow<'b, str>) -> Box<dyn Error + Send + Sync + 'a> { + From::from(String::from(err)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_box_error", since = "1.22.0")] +impl<'a> From<Cow<'a, str>> for Box<dyn Error> { + /// Converts a [`Cow`] into a box of dyn [`Error`]. + /// + /// # Examples + /// + /// ``` + /// use std::error::Error; + /// use std::mem; + /// use std::borrow::Cow; + /// + /// let a_cow_str_error = Cow::from("a str error"); + /// let a_boxed_error = Box::<dyn Error>::from(a_cow_str_error); + /// assert!(mem::size_of::<Box<dyn Error>>() == mem::size_of_val(&a_boxed_error)) + /// ``` + fn from(err: Cow<'a, str>) -> Box<dyn Error> { + From::from(String::from(err)) + } +} + +#[stable(feature = "box_error", since = "1.8.0")] +impl<T: core::error::Error> core::error::Error for Box<T> { + #[allow(deprecated, deprecated_in_future)] + fn description(&self) -> &str { + core::error::Error::description(&**self) + } + + #[allow(deprecated)] + fn cause(&self) -> Option<&dyn core::error::Error> { + core::error::Error::cause(&**self) + } + + fn source(&self) -> Option<&(dyn core::error::Error + 'static)> { + core::error::Error::source(&**self) + } +} diff --git a/rust/alloc/collections/mod.rs b/rust/alloc/collections/mod.rs index 1eec265b28f8..2506065d158a 100644 --- a/rust/alloc/collections/mod.rs +++ b/rust/alloc/collections/mod.rs @@ -141,7 +141,7 @@ impl Display for TryReserveError { " because the computed capacity exceeded the collection's maximum" } TryReserveErrorKind::AllocError { .. } => { - " because the memory allocator returned a error" + " because the memory allocator returned an error" } }; fmt.write_str(reason) @@ -154,3 +154,6 @@ trait SpecExtend<I: IntoIterator> { /// Extends `self` with the contents of the given iterator. fn spec_extend(&mut self, iter: I); } + +#[stable(feature = "try_reserve", since = "1.57.0")] +impl core::error::Error for TryReserveError {} diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs index 3aebf83c9967..5f374378b0d4 100644 --- a/rust/alloc/lib.rs +++ b/rust/alloc/lib.rs @@ -5,7 +5,7 @@ //! This library provides smart pointers and collections for managing //! heap-allocated values. //! -//! This library, like libcore, normally doesn’t need to be used directly +//! This library, like core, normally doesn’t need to be used directly //! since its contents are re-exported in the [`std` crate](../std/index.html). //! Crates that use the `#![no_std]` attribute however will typically //! not depend on `std`, so they’d use this crate instead. @@ -58,10 +58,6 @@ //! [`Rc`]: rc //! [`RefCell`]: core::cell -// To run liballoc tests without x.py without ending up with two copies of liballoc, Miri needs to be -// able to "empty" this crate. See <https://github.com/rust-lang/miri-test-libstd/issues/4>. -// rustc itself never sets the feature, so this line has no affect there. -#![cfg(any(not(feature = "miri-test-libstd"), test, doctest))] #![allow(unused_attributes)] #![stable(feature = "alloc", since = "1.36.0")] #![doc( @@ -75,23 +71,30 @@ any(not(feature = "miri-test-libstd"), test, doctest), no_global_oom_handling, not(no_global_oom_handling), + not(no_rc), + not(no_sync), target_has_atomic = "ptr" ))] #![no_std] #![needs_allocator] +// To run alloc tests without x.py without ending up with two copies of alloc, Miri needs to be +// able to "empty" this crate. See <https://github.com/rust-lang/miri-test-libstd/issues/4>. +// rustc itself never sets the feature, so this line has no affect there. +#![cfg(any(not(feature = "miri-test-libstd"), test, doctest))] // // Lints: #![deny(unsafe_op_in_unsafe_fn)] +#![deny(fuzzy_provenance_casts)] #![warn(deprecated_in_future)] #![warn(missing_debug_implementations)] #![warn(missing_docs)] #![allow(explicit_outlives_requirements)] // // Library features: -#![cfg_attr(not(no_global_oom_handling), feature(alloc_c_string))] #![feature(alloc_layout_extra)] #![feature(allocator_api)] #![feature(array_chunks)] +#![feature(array_into_iter_constructors)] #![feature(array_methods)] #![feature(array_windows)] #![feature(assert_matches)] @@ -99,39 +102,53 @@ #![feature(coerce_unsized)] #![cfg_attr(not(no_global_oom_handling), feature(const_alloc_error))] #![feature(const_box)] -#![cfg_attr(not(no_global_oom_handling), feature(const_btree_new))] +#![cfg_attr(not(no_global_oom_handling), feature(const_btree_len))] #![cfg_attr(not(no_borrow), feature(const_cow_is_borrowed))] #![feature(const_convert)] #![feature(const_size_of_val)] #![feature(const_align_of_val)] #![feature(const_ptr_read)] +#![feature(const_maybe_uninit_zeroed)] #![feature(const_maybe_uninit_write)] #![feature(const_maybe_uninit_as_mut_ptr)] #![feature(const_refs_to_cell)] -#![feature(core_c_str)] #![feature(core_intrinsics)] -#![feature(core_ffi_c)] +#![feature(core_panic)] #![feature(const_eval_select)] #![feature(const_pin)] +#![feature(const_waker)] #![feature(cstr_from_bytes_until_nul)] #![feature(dispatch_from_dyn)] +#![feature(error_generic_member_access)] +#![feature(error_in_core)] #![feature(exact_size_is_empty)] #![feature(extend_one)] #![feature(fmt_internals)] #![feature(fn_traits)] #![feature(hasher_prefixfree_extras)] +#![feature(inline_const)] #![feature(inplace_iteration)] +#![cfg_attr(test, feature(is_sorted))] #![feature(iter_advance_by)] +#![feature(iter_next_chunk)] +#![feature(iter_repeat_n)] #![feature(layout_for_ptr)] #![feature(maybe_uninit_slice)] +#![feature(maybe_uninit_uninit_array)] +#![feature(maybe_uninit_uninit_array_transpose)] #![cfg_attr(test, feature(new_uninit))] #![feature(nonnull_slice_from_raw_parts)] #![feature(pattern)] +#![feature(pointer_byte_offsets)] +#![feature(provide_any)] #![feature(ptr_internals)] #![feature(ptr_metadata)] #![feature(ptr_sub_ptr)] #![feature(receiver_trait)] +#![feature(saturating_int_impl)] #![feature(set_ptr_value)] +#![feature(sized_type_properties)] +#![feature(slice_from_ptr_range)] #![feature(slice_group_by)] #![feature(slice_ptr_get)] #![feature(slice_ptr_len)] @@ -141,15 +158,17 @@ #![feature(trusted_len)] #![feature(trusted_random_access)] #![feature(try_trait_v2)] +#![feature(tuple_trait)] #![feature(unchecked_math)] #![feature(unicode_internals)] #![feature(unsize)] +#![feature(utf8_chunks)] +#![feature(std_internals)] // // Language features: #![feature(allocator_internals)] #![feature(allow_internal_unstable)] #![feature(associated_type_bounds)] -#![feature(box_syntax)] #![feature(cfg_sanitize)] #![feature(const_deref)] #![feature(const_mut_refs)] @@ -163,19 +182,21 @@ #![cfg_attr(not(test), feature(generator_trait))] #![feature(hashmap_internals)] #![feature(lang_items)] -#![feature(let_else)] #![feature(min_specialization)] #![feature(negative_impls)] #![feature(never_type)] -#![feature(nll)] // Not necessary, but here to test the `nll` feature. #![feature(rustc_allow_const_fn_unstable)] #![feature(rustc_attrs)] +#![feature(pointer_is_aligned)] #![feature(slice_internals)] #![feature(staged_api)] +#![feature(stmt_expr_attributes)] #![cfg_attr(test, feature(test))] #![feature(unboxed_closures)] #![feature(unsized_fn_params)] #![feature(c_unwind)] +#![feature(with_negative_coherence)] +#![cfg_attr(test, feature(panic_update_hook))] // // Rustdoc features: #![feature(doc_cfg)] @@ -192,6 +213,8 @@ extern crate std; #[cfg(test)] extern crate test; +#[cfg(test)] +mod testing; // Module with internal macros used by other modules (needs to be included before other modules). #[cfg(not(no_macros))] @@ -218,7 +241,7 @@ mod boxed { #[cfg(not(no_borrow))] pub mod borrow; pub mod collections; -#[cfg(not(no_global_oom_handling))] +#[cfg(all(not(no_rc), not(no_sync), not(no_global_oom_handling)))] pub mod ffi; #[cfg(not(no_fmt))] pub mod fmt; @@ -229,10 +252,9 @@ pub mod slice; pub mod str; #[cfg(not(no_string))] pub mod string; -#[cfg(not(no_sync))] -#[cfg(target_has_atomic = "ptr")] +#[cfg(all(not(no_rc), not(no_sync), target_has_atomic = "ptr"))] pub mod sync; -#[cfg(all(not(no_global_oom_handling), target_has_atomic = "ptr"))] +#[cfg(all(not(no_global_oom_handling), not(no_rc), not(no_sync), target_has_atomic = "ptr"))] pub mod task; #[cfg(test)] mod tests; @@ -243,3 +265,20 @@ pub mod vec; pub mod __export { pub use core::format_args; } + +#[cfg(test)] +#[allow(dead_code)] // Not used in all configurations +pub(crate) mod test_helpers { + /// Copied from `std::test_helpers::test_rng`, since these tests rely on the + /// seed not being the same for every RNG invocation too. + pub(crate) fn test_rng() -> rand_xorshift::XorShiftRng { + use std::hash::{BuildHasher, Hash, Hasher}; + let mut hasher = std::collections::hash_map::RandomState::new().build_hasher(); + std::panic::Location::caller().hash(&mut hasher); + let hc64 = hasher.finish(); + let seed_vec = + hc64.to_le_bytes().into_iter().chain(0u8..8).collect::<crate::vec::Vec<u8>>(); + let seed: [u8; 16] = seed_vec.as_slice().try_into().unwrap(); + rand::SeedableRng::from_seed(seed) + } +} diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs index eb77db5def55..5db87eac53b7 100644 --- a/rust/alloc/raw_vec.rs +++ b/rust/alloc/raw_vec.rs @@ -5,7 +5,7 @@ use core::alloc::LayoutError; use core::cmp; use core::intrinsics; -use core::mem::{self, ManuallyDrop, MaybeUninit}; +use core::mem::{self, ManuallyDrop, MaybeUninit, SizedTypeProperties}; use core::ops::Drop; use core::ptr::{self, NonNull, Unique}; use core::slice; @@ -177,7 +177,7 @@ impl<T, A: Allocator> RawVec<T, A> { #[cfg(not(no_global_oom_handling))] fn allocate_in(capacity: usize, init: AllocInit, alloc: A) -> Self { // Don't allocate here because `Drop` will not deallocate when `capacity` is 0. - if mem::size_of::<T>() == 0 || capacity == 0 { + if T::IS_ZST || capacity == 0 { Self::new_in(alloc) } else { // We avoid `unwrap_or_else` here because it bloats the amount of @@ -212,7 +212,7 @@ impl<T, A: Allocator> RawVec<T, A> { fn try_allocate_in(capacity: usize, init: AllocInit, alloc: A) -> Result<Self, TryReserveError> { // Don't allocate here because `Drop` will not deallocate when `capacity` is 0. - if mem::size_of::<T>() == 0 || capacity == 0 { + if T::IS_ZST || capacity == 0 { return Ok(Self::new_in(alloc)); } @@ -262,7 +262,7 @@ impl<T, A: Allocator> RawVec<T, A> { /// This will always be `usize::MAX` if `T` is zero-sized. #[inline(always)] pub fn capacity(&self) -> usize { - if mem::size_of::<T>() == 0 { usize::MAX } else { self.cap } + if T::IS_ZST { usize::MAX } else { self.cap } } /// Returns a shared reference to the allocator backing this `RawVec`. @@ -271,7 +271,7 @@ impl<T, A: Allocator> RawVec<T, A> { } fn current_memory(&self) -> Option<(NonNull<u8>, Layout)> { - if mem::size_of::<T>() == 0 || self.cap == 0 { + if T::IS_ZST || self.cap == 0 { None } else { // We have an allocated chunk of memory, so we can bypass runtime @@ -419,7 +419,7 @@ impl<T, A: Allocator> RawVec<T, A> { // This is ensured by the calling contexts. debug_assert!(additional > 0); - if mem::size_of::<T>() == 0 { + if T::IS_ZST { // Since we return a capacity of `usize::MAX` when `elem_size` is // 0, getting to here necessarily means the `RawVec` is overfull. return Err(CapacityOverflow.into()); @@ -445,7 +445,7 @@ impl<T, A: Allocator> RawVec<T, A> { // `grow_amortized`, but this method is usually instantiated less often so // it's less critical. fn grow_exact(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> { - if mem::size_of::<T>() == 0 { + if T::IS_ZST { // Since we return a capacity of `usize::MAX` when the type size is // 0, getting to here necessarily means the `RawVec` is overfull. return Err(CapacityOverflow.into()); @@ -460,7 +460,7 @@ impl<T, A: Allocator> RawVec<T, A> { Ok(()) } - #[allow(dead_code)] + #[cfg(not(no_global_oom_handling))] fn shrink(&mut self, cap: usize) -> Result<(), TryReserveError> { assert!(cap <= self.capacity(), "Tried to shrink to a larger capacity"); diff --git a/rust/alloc/slice.rs b/rust/alloc/slice.rs index e444e97fa145..245e01590df7 100644 --- a/rust/alloc/slice.rs +++ b/rust/alloc/slice.rs @@ -1,84 +1,14 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT -//! A dynamically-sized view into a contiguous sequence, `[T]`. +//! Utilities for the slice primitive type. //! //! *[See also the slice primitive type](slice).* //! -//! Slices are a view into a block of memory represented as a pointer and a -//! length. +//! Most of the structs in this module are iterator types which can only be created +//! using a certain function. For example, `slice.iter()` yields an [`Iter`]. //! -//! ``` -//! // slicing a Vec -//! let vec = vec![1, 2, 3]; -//! let int_slice = &vec[..]; -//! // coercing an array to a slice -//! let str_slice: &[&str] = &["one", "two", "three"]; -//! ``` -//! -//! Slices are either mutable or shared. The shared slice type is `&[T]`, -//! while the mutable slice type is `&mut [T]`, where `T` represents the element -//! type. For example, you can mutate the block of memory that a mutable slice -//! points to: -//! -//! ``` -//! let x = &mut [1, 2, 3]; -//! x[1] = 7; -//! assert_eq!(x, &[1, 7, 3]); -//! ``` -//! -//! Here are some of the things this module contains: -//! -//! ## Structs -//! -//! There are several structs that are useful for slices, such as [`Iter`], which -//! represents iteration over a slice. -//! -//! ## Trait Implementations -//! -//! There are several implementations of common traits for slices. Some examples -//! include: -//! -//! * [`Clone`] -//! * [`Eq`], [`Ord`] - for slices whose element type are [`Eq`] or [`Ord`]. -//! * [`Hash`] - for slices whose element type is [`Hash`]. -//! -//! ## Iteration -//! -//! The slices implement `IntoIterator`. The iterator yields references to the -//! slice elements. -//! -//! ``` -//! let numbers = &[0, 1, 2]; -//! for n in numbers { -//! println!("{n} is a number!"); -//! } -//! ``` -//! -//! The mutable slice yields mutable references to the elements: -//! -//! ``` -//! let mut scores = [7, 8, 9]; -//! for score in &mut scores[..] { -//! *score += 1; -//! } -//! ``` -//! -//! This iterator yields mutable references to the slice's elements, so while -//! the element type of the slice is `i32`, the element type of the iterator is -//! `&mut i32`. -//! -//! * [`.iter`] and [`.iter_mut`] are the explicit methods to return the default -//! iterators. -//! * Further methods that return iterators are [`.split`], [`.splitn`], -//! [`.chunks`], [`.windows`] and more. -//! -//! [`Hash`]: core::hash::Hash -//! [`.iter`]: slice::iter -//! [`.iter_mut`]: slice::iter_mut -//! [`.split`]: slice::split -//! [`.splitn`]: slice::splitn -//! [`.chunks`]: slice::chunks -//! [`.windows`]: slice::windows +//! A few functions are provided to create a slice from a value reference +//! or from a raw pointer. #![stable(feature = "rust1", since = "1.0.0")] // Many of the usings in this module are only used in the test configuration. // It's cleaner to just turn off the unused_imports warning than to fix them. @@ -88,20 +18,23 @@ use core::borrow::{Borrow, BorrowMut}; #[cfg(not(no_global_oom_handling))] use core::cmp::Ordering::{self, Less}; #[cfg(not(no_global_oom_handling))] -use core::mem; -#[cfg(not(no_global_oom_handling))] -use core::mem::size_of; +use core::mem::{self, SizedTypeProperties}; #[cfg(not(no_global_oom_handling))] use core::ptr; +#[cfg(not(no_global_oom_handling))] +use core::slice::sort; use crate::alloc::Allocator; #[cfg(not(no_global_oom_handling))] -use crate::alloc::Global; +use crate::alloc::{self, Global}; #[cfg(not(no_global_oom_handling))] use crate::borrow::ToOwned; use crate::boxed::Box; use crate::vec::Vec; +#[cfg(test)] +mod tests; + #[unstable(feature = "slice_range", issue = "76393")] pub use core::slice::range; #[unstable(feature = "array_chunks", issue = "74985")] @@ -116,6 +49,8 @@ pub use core::slice::EscapeAscii; pub use core::slice::SliceIndex; #[stable(feature = "from_ref", since = "1.28.0")] pub use core::slice::{from_mut, from_ref}; +#[unstable(feature = "slice_from_ptr_range", issue = "89792")] +pub use core::slice::{from_mut_ptr_range, from_ptr_range}; #[stable(feature = "rust1", since = "1.0.0")] pub use core::slice::{from_raw_parts, from_raw_parts_mut}; #[stable(feature = "rust1", since = "1.0.0")] @@ -275,7 +210,7 @@ impl<T> [T] { where T: Ord, { - merge_sort(self, |a, b| a.lt(b)); + stable_sort(self, T::lt); } /// Sorts the slice with a comparator function. @@ -331,7 +266,7 @@ impl<T> [T] { where F: FnMut(&T, &T) -> Ordering, { - merge_sort(self, |a, b| compare(a, b) == Less); + stable_sort(self, |a, b| compare(a, b) == Less); } /// Sorts the slice with a key extraction function. @@ -374,7 +309,7 @@ impl<T> [T] { F: FnMut(&T) -> K, K: Ord, { - merge_sort(self, |a, b| f(a).lt(&f(b))); + stable_sort(self, |a, b| f(a).lt(&f(b))); } /// Sorts the slice with a key extraction function. @@ -530,7 +465,7 @@ impl<T> [T] { hack::into_vec(self) } - /// Creates a vector by repeating a slice `n` times. + /// Creates a vector by copying a slice `n` times. /// /// # Panics /// @@ -725,7 +660,7 @@ impl [u8] { /// /// ```error /// error[E0207]: the type parameter `T` is not constrained by the impl trait, self type, or predica -/// --> src/liballoc/slice.rs:608:6 +/// --> library/alloc/src/slice.rs:608:6 /// | /// 608 | impl<T: Clone, V: Borrow<[T]>> Concat for [V] { /// | ^ unconstrained type parameter @@ -836,14 +771,14 @@ impl<T: Clone, V: Borrow<[T]>> Join<&[T]> for [V] { //////////////////////////////////////////////////////////////////////////////// #[stable(feature = "rust1", since = "1.0.0")] -impl<T> Borrow<[T]> for Vec<T> { +impl<T, A: Allocator> Borrow<[T]> for Vec<T, A> { fn borrow(&self) -> &[T] { &self[..] } } #[stable(feature = "rust1", since = "1.0.0")] -impl<T> BorrowMut<[T]> for Vec<T> { +impl<T, A: Allocator> BorrowMut<[T]> for Vec<T, A> { fn borrow_mut(&mut self) -> &mut [T] { &mut self[..] } @@ -881,324 +816,52 @@ impl<T: Clone> ToOwned for [T] { // Sorting //////////////////////////////////////////////////////////////////////////////// -/// Inserts `v[0]` into pre-sorted sequence `v[1..]` so that whole `v[..]` becomes sorted. -/// -/// This is the integral subroutine of insertion sort. +#[inline] #[cfg(not(no_global_oom_handling))] -fn insert_head<T, F>(v: &mut [T], is_less: &mut F) +fn stable_sort<T, F>(v: &mut [T], mut is_less: F) where F: FnMut(&T, &T) -> bool, { - if v.len() >= 2 && is_less(&v[1], &v[0]) { - unsafe { - // There are three ways to implement insertion here: - // - // 1. Swap adjacent elements until the first one gets to its final destination. - // However, this way we copy data around more than is necessary. If elements are big - // structures (costly to copy), this method will be slow. - // - // 2. Iterate until the right place for the first element is found. Then shift the - // elements succeeding it to make room for it and finally place it into the - // remaining hole. This is a good method. - // - // 3. Copy the first element into a temporary variable. Iterate until the right place - // for it is found. As we go along, copy every traversed element into the slot - // preceding it. Finally, copy data from the temporary variable into the remaining - // hole. This method is very good. Benchmarks demonstrated slightly better - // performance than with the 2nd method. - // - // All methods were benchmarked, and the 3rd showed best results. So we chose that one. - let tmp = mem::ManuallyDrop::new(ptr::read(&v[0])); - - // Intermediate state of the insertion process is always tracked by `hole`, which - // serves two purposes: - // 1. Protects integrity of `v` from panics in `is_less`. - // 2. Fills the remaining hole in `v` in the end. - // - // Panic safety: - // - // If `is_less` panics at any point during the process, `hole` will get dropped and - // fill the hole in `v` with `tmp`, thus ensuring that `v` still holds every object it - // initially held exactly once. - let mut hole = InsertionHole { src: &*tmp, dest: &mut v[1] }; - ptr::copy_nonoverlapping(&v[1], &mut v[0], 1); - - for i in 2..v.len() { - if !is_less(&v[i], &*tmp) { - break; - } - ptr::copy_nonoverlapping(&v[i], &mut v[i - 1], 1); - hole.dest = &mut v[i]; - } - // `hole` gets dropped and thus copies `tmp` into the remaining hole in `v`. - } - } - - // When dropped, copies from `src` into `dest`. - struct InsertionHole<T> { - src: *const T, - dest: *mut T, - } - - impl<T> Drop for InsertionHole<T> { - fn drop(&mut self) { - unsafe { - ptr::copy_nonoverlapping(self.src, self.dest, 1); - } - } + if T::IS_ZST { + // Sorting has no meaningful behavior on zero-sized types. Do nothing. + return; } -} - -/// Merges non-decreasing runs `v[..mid]` and `v[mid..]` using `buf` as temporary storage, and -/// stores the result into `v[..]`. -/// -/// # Safety -/// -/// The two slices must be non-empty and `mid` must be in bounds. Buffer `buf` must be long enough -/// to hold a copy of the shorter slice. Also, `T` must not be a zero-sized type. -#[cfg(not(no_global_oom_handling))] -unsafe fn merge<T, F>(v: &mut [T], mid: usize, buf: *mut T, is_less: &mut F) -where - F: FnMut(&T, &T) -> bool, -{ - let len = v.len(); - let v = v.as_mut_ptr(); - let (v_mid, v_end) = unsafe { (v.add(mid), v.add(len)) }; - // The merge process first copies the shorter run into `buf`. Then it traces the newly copied - // run and the longer run forwards (or backwards), comparing their next unconsumed elements and - // copying the lesser (or greater) one into `v`. - // - // As soon as the shorter run is fully consumed, the process is done. If the longer run gets - // consumed first, then we must copy whatever is left of the shorter run into the remaining - // hole in `v`. - // - // Intermediate state of the process is always tracked by `hole`, which serves two purposes: - // 1. Protects integrity of `v` from panics in `is_less`. - // 2. Fills the remaining hole in `v` if the longer run gets consumed first. - // - // Panic safety: - // - // If `is_less` panics at any point during the process, `hole` will get dropped and fill the - // hole in `v` with the unconsumed range in `buf`, thus ensuring that `v` still holds every - // object it initially held exactly once. - let mut hole; + let elem_alloc_fn = |len: usize| -> *mut T { + // SAFETY: Creating the layout is safe as long as merge_sort never calls this with len > + // v.len(). Alloc in general will only be used as 'shadow-region' to store temporary swap + // elements. + unsafe { alloc::alloc(alloc::Layout::array::<T>(len).unwrap_unchecked()) as *mut T } + }; - if mid <= len - mid { - // The left run is shorter. + let elem_dealloc_fn = |buf_ptr: *mut T, len: usize| { + // SAFETY: Creating the layout is safe as long as merge_sort never calls this with len > + // v.len(). The caller must ensure that buf_ptr was created by elem_alloc_fn with the same + // len. unsafe { - ptr::copy_nonoverlapping(v, buf, mid); - hole = MergeHole { start: buf, end: buf.add(mid), dest: v }; + alloc::dealloc(buf_ptr as *mut u8, alloc::Layout::array::<T>(len).unwrap_unchecked()); } + }; - // Initially, these pointers point to the beginnings of their arrays. - let left = &mut hole.start; - let mut right = v_mid; - let out = &mut hole.dest; - - while *left < hole.end && right < v_end { - // Consume the lesser side. - // If equal, prefer the left run to maintain stability. - unsafe { - let to_copy = if is_less(&*right, &**left) { - get_and_increment(&mut right) - } else { - get_and_increment(left) - }; - ptr::copy_nonoverlapping(to_copy, get_and_increment(out), 1); - } - } - } else { - // The right run is shorter. + let run_alloc_fn = |len: usize| -> *mut sort::TimSortRun { + // SAFETY: Creating the layout is safe as long as merge_sort never calls this with an + // obscene length or 0. unsafe { - ptr::copy_nonoverlapping(v_mid, buf, len - mid); - hole = MergeHole { start: buf, end: buf.add(len - mid), dest: v_mid }; + alloc::alloc(alloc::Layout::array::<sort::TimSortRun>(len).unwrap_unchecked()) + as *mut sort::TimSortRun } + }; - // Initially, these pointers point past the ends of their arrays. - let left = &mut hole.dest; - let right = &mut hole.end; - let mut out = v_end; - - while v < *left && buf < *right { - // Consume the greater side. - // If equal, prefer the right run to maintain stability. - unsafe { - let to_copy = if is_less(&*right.offset(-1), &*left.offset(-1)) { - decrement_and_get(left) - } else { - decrement_and_get(right) - }; - ptr::copy_nonoverlapping(to_copy, decrement_and_get(&mut out), 1); - } - } - } - // Finally, `hole` gets dropped. If the shorter run was not fully consumed, whatever remains of - // it will now be copied into the hole in `v`. - - unsafe fn get_and_increment<T>(ptr: &mut *mut T) -> *mut T { - let old = *ptr; - *ptr = unsafe { ptr.offset(1) }; - old - } - - unsafe fn decrement_and_get<T>(ptr: &mut *mut T) -> *mut T { - *ptr = unsafe { ptr.offset(-1) }; - *ptr - } - - // When dropped, copies the range `start..end` into `dest..`. - struct MergeHole<T> { - start: *mut T, - end: *mut T, - dest: *mut T, - } - - impl<T> Drop for MergeHole<T> { - fn drop(&mut self) { - // `T` is not a zero-sized type, and these are pointers into a slice's elements. - unsafe { - let len = self.end.sub_ptr(self.start); - ptr::copy_nonoverlapping(self.start, self.dest, len); - } - } - } -} - -/// This merge sort borrows some (but not all) ideas from TimSort, which is described in detail -/// [here](https://github.com/python/cpython/blob/main/Objects/listsort.txt). -/// -/// The algorithm identifies strictly descending and non-descending subsequences, which are called -/// natural runs. There is a stack of pending runs yet to be merged. Each newly found run is pushed -/// onto the stack, and then some pairs of adjacent runs are merged until these two invariants are -/// satisfied: -/// -/// 1. for every `i` in `1..runs.len()`: `runs[i - 1].len > runs[i].len` -/// 2. for every `i` in `2..runs.len()`: `runs[i - 2].len > runs[i - 1].len + runs[i].len` -/// -/// The invariants ensure that the total running time is *O*(*n* \* log(*n*)) worst-case. -#[cfg(not(no_global_oom_handling))] -fn merge_sort<T, F>(v: &mut [T], mut is_less: F) -where - F: FnMut(&T, &T) -> bool, -{ - // Slices of up to this length get sorted using insertion sort. - const MAX_INSERTION: usize = 20; - // Very short runs are extended using insertion sort to span at least this many elements. - const MIN_RUN: usize = 10; - - // Sorting has no meaningful behavior on zero-sized types. - if size_of::<T>() == 0 { - return; - } - - let len = v.len(); - - // Short arrays get sorted in-place via insertion sort to avoid allocations. - if len <= MAX_INSERTION { - if len >= 2 { - for i in (0..len - 1).rev() { - insert_head(&mut v[i..], &mut is_less); - } - } - return; - } - - // Allocate a buffer to use as scratch memory. We keep the length 0 so we can keep in it - // shallow copies of the contents of `v` without risking the dtors running on copies if - // `is_less` panics. When merging two sorted runs, this buffer holds a copy of the shorter run, - // which will always have length at most `len / 2`. - let mut buf = Vec::with_capacity(len / 2); - - // In order to identify natural runs in `v`, we traverse it backwards. That might seem like a - // strange decision, but consider the fact that merges more often go in the opposite direction - // (forwards). According to benchmarks, merging forwards is slightly faster than merging - // backwards. To conclude, identifying runs by traversing backwards improves performance. - let mut runs = vec![]; - let mut end = len; - while end > 0 { - // Find the next natural run, and reverse it if it's strictly descending. - let mut start = end - 1; - if start > 0 { - start -= 1; - unsafe { - if is_less(v.get_unchecked(start + 1), v.get_unchecked(start)) { - while start > 0 && is_less(v.get_unchecked(start), v.get_unchecked(start - 1)) { - start -= 1; - } - v[start..end].reverse(); - } else { - while start > 0 && !is_less(v.get_unchecked(start), v.get_unchecked(start - 1)) - { - start -= 1; - } - } - } - } - - // Insert some more elements into the run if it's too short. Insertion sort is faster than - // merge sort on short sequences, so this significantly improves performance. - while start > 0 && end - start < MIN_RUN { - start -= 1; - insert_head(&mut v[start..end], &mut is_less); - } - - // Push this run onto the stack. - runs.push(Run { start, len: end - start }); - end = start; - - // Merge some pairs of adjacent runs to satisfy the invariants. - while let Some(r) = collapse(&runs) { - let left = runs[r + 1]; - let right = runs[r]; - unsafe { - merge( - &mut v[left.start..right.start + right.len], - left.len, - buf.as_mut_ptr(), - &mut is_less, - ); - } - runs[r] = Run { start: left.start, len: left.len + right.len }; - runs.remove(r + 1); - } - } - - // Finally, exactly one run must remain in the stack. - debug_assert!(runs.len() == 1 && runs[0].start == 0 && runs[0].len == len); - - // Examines the stack of runs and identifies the next pair of runs to merge. More specifically, - // if `Some(r)` is returned, that means `runs[r]` and `runs[r + 1]` must be merged next. If the - // algorithm should continue building a new run instead, `None` is returned. - // - // TimSort is infamous for its buggy implementations, as described here: - // http://envisage-project.eu/timsort-specification-and-verification/ - // - // The gist of the story is: we must enforce the invariants on the top four runs on the stack. - // Enforcing them on just top three is not sufficient to ensure that the invariants will still - // hold for *all* runs in the stack. - // - // This function correctly checks invariants for the top four runs. Additionally, if the top - // run starts at index 0, it will always demand a merge operation until the stack is fully - // collapsed, in order to complete the sort. - #[inline] - fn collapse(runs: &[Run]) -> Option<usize> { - let n = runs.len(); - if n >= 2 - && (runs[n - 1].start == 0 - || runs[n - 2].len <= runs[n - 1].len - || (n >= 3 && runs[n - 3].len <= runs[n - 2].len + runs[n - 1].len) - || (n >= 4 && runs[n - 4].len <= runs[n - 3].len + runs[n - 2].len)) - { - if n >= 3 && runs[n - 3].len < runs[n - 1].len { Some(n - 3) } else { Some(n - 2) } - } else { - None + let run_dealloc_fn = |buf_ptr: *mut sort::TimSortRun, len: usize| { + // SAFETY: The caller must ensure that buf_ptr was created by elem_alloc_fn with the same + // len. + unsafe { + alloc::dealloc( + buf_ptr as *mut u8, + alloc::Layout::array::<sort::TimSortRun>(len).unwrap_unchecked(), + ); } - } + }; - #[derive(Clone, Copy)] - struct Run { - start: usize, - len: usize, - } + sort::merge_sort(v, &mut is_less, elem_alloc_fn, elem_dealloc_fn, run_alloc_fn, run_dealloc_fn); } diff --git a/rust/alloc/vec/drain.rs b/rust/alloc/vec/drain.rs index b6a5f98e4fcd..d503d2f478ce 100644 --- a/rust/alloc/vec/drain.rs +++ b/rust/alloc/vec/drain.rs @@ -3,7 +3,7 @@ use crate::alloc::{Allocator, Global}; use core::fmt; use core::iter::{FusedIterator, TrustedLen}; -use core::mem; +use core::mem::{self, ManuallyDrop, SizedTypeProperties}; use core::ptr::{self, NonNull}; use core::slice::{self}; @@ -67,6 +67,77 @@ impl<'a, T, A: Allocator> Drain<'a, T, A> { pub fn allocator(&self) -> &A { unsafe { self.vec.as_ref().allocator() } } + + /// Keep unyielded elements in the source `Vec`. + /// + /// # Examples + /// + /// ``` + /// #![feature(drain_keep_rest)] + /// + /// let mut vec = vec!['a', 'b', 'c']; + /// let mut drain = vec.drain(..); + /// + /// assert_eq!(drain.next().unwrap(), 'a'); + /// + /// // This call keeps 'b' and 'c' in the vec. + /// drain.keep_rest(); + /// + /// // If we wouldn't call `keep_rest()`, + /// // `vec` would be empty. + /// assert_eq!(vec, ['b', 'c']); + /// ``` + #[unstable(feature = "drain_keep_rest", issue = "101122")] + pub fn keep_rest(self) { + // At this moment layout looks like this: + // + // [head] [yielded by next] [unyielded] [yielded by next_back] [tail] + // ^-- start \_________/-- unyielded_len \____/-- self.tail_len + // ^-- unyielded_ptr ^-- tail + // + // Normally `Drop` impl would drop [unyielded] and then move [tail] to the `start`. + // Here we want to + // 1. Move [unyielded] to `start` + // 2. Move [tail] to a new start at `start + len(unyielded)` + // 3. Update length of the original vec to `len(head) + len(unyielded) + len(tail)` + // a. In case of ZST, this is the only thing we want to do + // 4. Do *not* drop self, as everything is put in a consistent state already, there is nothing to do + let mut this = ManuallyDrop::new(self); + + unsafe { + let source_vec = this.vec.as_mut(); + + let start = source_vec.len(); + let tail = this.tail_start; + + let unyielded_len = this.iter.len(); + let unyielded_ptr = this.iter.as_slice().as_ptr(); + + // ZSTs have no identity, so we don't need to move them around. + let needs_move = mem::size_of::<T>() != 0; + + if needs_move { + let start_ptr = source_vec.as_mut_ptr().add(start); + + // memmove back unyielded elements + if unyielded_ptr != start_ptr { + let src = unyielded_ptr; + let dst = start_ptr; + + ptr::copy(src, dst, unyielded_len); + } + + // memmove back untouched tail + if tail != (start + unyielded_len) { + let src = source_vec.as_ptr().add(tail); + let dst = start_ptr.add(unyielded_len); + ptr::copy(src, dst, this.tail_len); + } + } + + source_vec.set_len(start + unyielded_len + this.tail_len); + } + } } #[stable(feature = "vec_drain_as_slice", since = "1.46.0")] @@ -133,7 +204,7 @@ impl<T, A: Allocator> Drop for Drain<'_, T, A> { let mut vec = self.vec; - if mem::size_of::<T>() == 0 { + if T::IS_ZST { // ZSTs have no identity, so we don't need to move them around, we only need to drop the correct amount. // this can be achieved by manipulating the Vec length instead of moving values out from `iter`. unsafe { @@ -154,9 +225,9 @@ impl<T, A: Allocator> Drop for Drain<'_, T, A> { } // as_slice() must only be called when iter.len() is > 0 because - // vec::Splice modifies vec::Drain fields and may grow the vec which would invalidate - // the iterator's internal pointers. Creating a reference to deallocated memory - // is invalid even when it is zero-length + // it also gets touched by vec::Splice which may turn it into a dangling pointer + // which would make it and the vec pointer point to different allocations which would + // lead to invalid pointer arithmetic below. let drop_ptr = iter.as_slice().as_ptr(); unsafe { diff --git a/rust/alloc/vec/drain_filter.rs b/rust/alloc/vec/drain_filter.rs index b04fce041622..4b019220657d 100644 --- a/rust/alloc/vec/drain_filter.rs +++ b/rust/alloc/vec/drain_filter.rs @@ -1,8 +1,9 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT use crate::alloc::{Allocator, Global}; -use core::ptr::{self}; -use core::slice::{self}; +use core::mem::{self, ManuallyDrop}; +use core::ptr; +use core::slice; use super::Vec; @@ -56,6 +57,61 @@ where pub fn allocator(&self) -> &A { self.vec.allocator() } + + /// Keep unyielded elements in the source `Vec`. + /// + /// # Examples + /// + /// ``` + /// #![feature(drain_filter)] + /// #![feature(drain_keep_rest)] + /// + /// let mut vec = vec!['a', 'b', 'c']; + /// let mut drain = vec.drain_filter(|_| true); + /// + /// assert_eq!(drain.next().unwrap(), 'a'); + /// + /// // This call keeps 'b' and 'c' in the vec. + /// drain.keep_rest(); + /// + /// // If we wouldn't call `keep_rest()`, + /// // `vec` would be empty. + /// assert_eq!(vec, ['b', 'c']); + /// ``` + #[unstable(feature = "drain_keep_rest", issue = "101122")] + pub fn keep_rest(self) { + // At this moment layout looks like this: + // + // _____________________/-- old_len + // / \ + // [kept] [yielded] [tail] + // \_______/ ^-- idx + // \-- del + // + // Normally `Drop` impl would drop [tail] (via .for_each(drop), ie still calling `pred`) + // + // 1. Move [tail] after [kept] + // 2. Update length of the original vec to `old_len - del` + // a. In case of ZST, this is the only thing we want to do + // 3. Do *not* drop self, as everything is put in a consistent state already, there is nothing to do + let mut this = ManuallyDrop::new(self); + + unsafe { + // ZSTs have no identity, so we don't need to move them around. + let needs_move = mem::size_of::<T>() != 0; + + if needs_move && this.idx < this.old_len && this.del > 0 { + let ptr = this.vec.as_mut_ptr(); + let src = ptr.add(this.idx); + let dst = src.sub(this.del); + let tail_len = this.old_len - this.idx; + src.copy_to(dst, tail_len); + } + + let new_len = this.old_len - this.del; + this.vec.set_len(new_len); + } + } } #[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] diff --git a/rust/alloc/vec/into_iter.rs b/rust/alloc/vec/into_iter.rs index f7a50e76691e..34a2a70d6ded 100644 --- a/rust/alloc/vec/into_iter.rs +++ b/rust/alloc/vec/into_iter.rs @@ -3,14 +3,16 @@ #[cfg(not(no_global_oom_handling))] use super::AsVecIntoIter; use crate::alloc::{Allocator, Global}; +#[cfg(not(no_global_oom_handling))] +use crate::collections::VecDeque; use crate::raw_vec::RawVec; +use core::array; use core::fmt; -use core::intrinsics::arith_offset; use core::iter::{ FusedIterator, InPlaceIterable, SourceIter, TrustedLen, TrustedRandomAccessNoCoerce, }; use core::marker::PhantomData; -use core::mem::{self, ManuallyDrop}; +use core::mem::{self, ManuallyDrop, MaybeUninit, SizedTypeProperties}; #[cfg(not(no_global_oom_handling))] use core::ops::Deref; use core::ptr::{self, NonNull}; @@ -40,7 +42,9 @@ pub struct IntoIter< // to avoid dropping the allocator twice we need to wrap it into ManuallyDrop pub(super) alloc: ManuallyDrop<A>, pub(super) ptr: *const T, - pub(super) end: *const T, + pub(super) end: *const T, // If T is a ZST, this is actually ptr+len. This encoding is picked so that + // ptr == end is a quick test for the Iterator being empty, that works + // for both ZST and non-ZST. } #[stable(feature = "vec_intoiter_debug", since = "1.13.0")] @@ -97,13 +101,16 @@ impl<T, A: Allocator> IntoIter<T, A> { } /// Drops remaining elements and relinquishes the backing allocation. + /// This method guarantees it won't panic before relinquishing + /// the backing allocation. /// /// This is roughly equivalent to the following, but more efficient /// /// ``` /// # let mut into_iter = Vec::<u8>::with_capacity(10).into_iter(); + /// let mut into_iter = std::mem::replace(&mut into_iter, Vec::new().into_iter()); /// (&mut into_iter).for_each(core::mem::drop); - /// unsafe { core::ptr::write(&mut into_iter, Vec::new().into_iter()); } + /// std::mem::forget(into_iter); /// ``` /// /// This method is used by in-place iteration, refer to the vec::in_place_collect @@ -120,15 +127,45 @@ impl<T, A: Allocator> IntoIter<T, A> { self.ptr = self.buf.as_ptr(); self.end = self.buf.as_ptr(); + // Dropping the remaining elements can panic, so this needs to be + // done only after updating the other fields. unsafe { ptr::drop_in_place(remaining); } } /// Forgets to Drop the remaining elements while still allowing the backing allocation to be freed. - #[allow(dead_code)] pub(crate) fn forget_remaining_elements(&mut self) { - self.ptr = self.end; + // For th ZST case, it is crucial that we mutate `end` here, not `ptr`. + // `ptr` must stay aligned, while `end` may be unaligned. + self.end = self.ptr; + } + + #[cfg(not(no_global_oom_handling))] + #[inline] + pub(crate) fn into_vecdeque(self) -> VecDeque<T, A> { + // Keep our `Drop` impl from dropping the elements and the allocator + let mut this = ManuallyDrop::new(self); + + // SAFETY: This allocation originally came from a `Vec`, so it passes + // all those checks. We have `this.buf` ≤ `this.ptr` ≤ `this.end`, + // so the `sub_ptr`s below cannot wrap, and will produce a well-formed + // range. `end` ≤ `buf + cap`, so the range will be in-bounds. + // Taking `alloc` is ok because nothing else is going to look at it, + // since our `Drop` impl isn't going to run so there's no more code. + unsafe { + let buf = this.buf.as_ptr(); + let initialized = if T::IS_ZST { + // All the pointers are the same for ZSTs, so it's fine to + // say that they're all at the beginning of the "allocation". + 0..this.len() + } else { + this.ptr.sub_ptr(buf)..this.end.sub_ptr(buf) + }; + let cap = this.cap; + let alloc = ManuallyDrop::take(&mut this.alloc); + VecDeque::from_contiguous_raw_parts_in(buf, initialized, cap, alloc) + } } } @@ -150,19 +187,18 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> { #[inline] fn next(&mut self) -> Option<T> { - if self.ptr as *const _ == self.end { + if self.ptr == self.end { None - } else if mem::size_of::<T>() == 0 { - // purposefully don't use 'ptr.offset' because for - // vectors with 0-size elements this would return the - // same pointer. - self.ptr = unsafe { arith_offset(self.ptr as *const i8, 1) as *mut T }; + } else if T::IS_ZST { + // `ptr` has to stay where it is to remain aligned, so we reduce the length by 1 by + // reducing the `end`. + self.end = self.end.wrapping_byte_sub(1); // Make up a value of this ZST. Some(unsafe { mem::zeroed() }) } else { let old = self.ptr; - self.ptr = unsafe { self.ptr.offset(1) }; + self.ptr = unsafe { self.ptr.add(1) }; Some(unsafe { ptr::read(old) }) } @@ -170,7 +206,7 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> { #[inline] fn size_hint(&self) -> (usize, Option<usize>) { - let exact = if mem::size_of::<T>() == 0 { + let exact = if T::IS_ZST { self.end.addr().wrapping_sub(self.ptr.addr()) } else { unsafe { self.end.sub_ptr(self.ptr) } @@ -182,11 +218,9 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> { fn advance_by(&mut self, n: usize) -> Result<(), usize> { let step_size = self.len().min(n); let to_drop = ptr::slice_from_raw_parts_mut(self.ptr as *mut T, step_size); - if mem::size_of::<T>() == 0 { - // SAFETY: due to unchecked casts of unsigned amounts to signed offsets the wraparound - // effectively results in unsigned pointers representing positions 0..usize::MAX, - // which is valid for ZSTs. - self.ptr = unsafe { arith_offset(self.ptr as *const i8, step_size as isize) as *mut T } + if T::IS_ZST { + // See `next` for why we sub `end` here. + self.end = self.end.wrapping_byte_sub(step_size); } else { // SAFETY: the min() above ensures that step_size is in bounds self.ptr = unsafe { self.ptr.add(step_size) }; @@ -206,6 +240,43 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> { self.len() } + #[inline] + fn next_chunk<const N: usize>(&mut self) -> Result<[T; N], core::array::IntoIter<T, N>> { + let mut raw_ary = MaybeUninit::uninit_array(); + + let len = self.len(); + + if T::IS_ZST { + if len < N { + self.forget_remaining_elements(); + // Safety: ZSTs can be conjured ex nihilo, only the amount has to be correct + return Err(unsafe { array::IntoIter::new_unchecked(raw_ary, 0..len) }); + } + + self.end = self.end.wrapping_byte_sub(N); + // Safety: ditto + return Ok(unsafe { raw_ary.transpose().assume_init() }); + } + + if len < N { + // Safety: `len` indicates that this many elements are available and we just checked that + // it fits into the array. + unsafe { + ptr::copy_nonoverlapping(self.ptr, raw_ary.as_mut_ptr() as *mut T, len); + self.forget_remaining_elements(); + return Err(array::IntoIter::new_unchecked(raw_ary, 0..len)); + } + } + + // Safety: `len` is larger than the array size. Copy a fixed amount here to fully initialize + // the array. + return unsafe { + ptr::copy_nonoverlapping(self.ptr, raw_ary.as_mut_ptr() as *mut T, N); + self.ptr = self.ptr.add(N); + Ok(raw_ary.transpose().assume_init()) + }; + } + unsafe fn __iterator_get_unchecked(&mut self, i: usize) -> Self::Item where Self: TrustedRandomAccessNoCoerce, @@ -219,7 +290,7 @@ impl<T, A: Allocator> Iterator for IntoIter<T, A> { // that `T: Copy` so reading elements from the buffer doesn't invalidate // them for `Drop`. unsafe { - if mem::size_of::<T>() == 0 { mem::zeroed() } else { ptr::read(self.ptr.add(i)) } + if T::IS_ZST { mem::zeroed() } else { ptr::read(self.ptr.add(i)) } } } } @@ -230,14 +301,14 @@ impl<T, A: Allocator> DoubleEndedIterator for IntoIter<T, A> { fn next_back(&mut self) -> Option<T> { if self.end == self.ptr { None - } else if mem::size_of::<T>() == 0 { + } else if T::IS_ZST { // See above for why 'ptr.offset' isn't used - self.end = unsafe { arith_offset(self.end as *const i8, -1) as *mut T }; + self.end = self.end.wrapping_byte_sub(1); // Make up a value of this ZST. Some(unsafe { mem::zeroed() }) } else { - self.end = unsafe { self.end.offset(-1) }; + self.end = unsafe { self.end.sub(1) }; Some(unsafe { ptr::read(self.end) }) } @@ -246,14 +317,12 @@ impl<T, A: Allocator> DoubleEndedIterator for IntoIter<T, A> { #[inline] fn advance_back_by(&mut self, n: usize) -> Result<(), usize> { let step_size = self.len().min(n); - if mem::size_of::<T>() == 0 { + if T::IS_ZST { // SAFETY: same as for advance_by() - self.end = unsafe { - arith_offset(self.end as *const i8, step_size.wrapping_neg() as isize) as *mut T - } + self.end = self.end.wrapping_byte_sub(step_size); } else { // SAFETY: same as for advance_by() - self.end = unsafe { self.end.offset(step_size.wrapping_neg() as isize) }; + self.end = unsafe { self.end.sub(step_size) }; } let to_drop = ptr::slice_from_raw_parts_mut(self.end as *mut T, step_size); // SAFETY: same as for advance_by() diff --git a/rust/alloc/vec/is_zero.rs b/rust/alloc/vec/is_zero.rs index 377f3d172777..d928dcf90e80 100644 --- a/rust/alloc/vec/is_zero.rs +++ b/rust/alloc/vec/is_zero.rs @@ -1,10 +1,13 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT +use core::num::{Saturating, Wrapping}; + use crate::boxed::Box; #[rustc_specialization_trait] pub(super) unsafe trait IsZero { - /// Whether this value's representation is all zeros + /// Whether this value's representation is all zeros, + /// or can be represented with all zeroes. fn is_zero(&self) -> bool; } @@ -19,12 +22,14 @@ macro_rules! impl_is_zero { }; } +impl_is_zero!(i8, |x| x == 0); // It is needed to impl for arrays and tuples of i8. impl_is_zero!(i16, |x| x == 0); impl_is_zero!(i32, |x| x == 0); impl_is_zero!(i64, |x| x == 0); impl_is_zero!(i128, |x| x == 0); impl_is_zero!(isize, |x| x == 0); +impl_is_zero!(u8, |x| x == 0); // It is needed to impl for arrays and tuples of u8. impl_is_zero!(u16, |x| x == 0); impl_is_zero!(u32, |x| x == 0); impl_is_zero!(u64, |x| x == 0); @@ -55,16 +60,42 @@ unsafe impl<T: IsZero, const N: usize> IsZero for [T; N] { #[inline] fn is_zero(&self) -> bool { // Because this is generated as a runtime check, it's not obvious that - // it's worth doing if the array is really long. The threshold here - // is largely arbitrary, but was picked because as of 2022-05-01 LLVM - // can const-fold the check in `vec![[0; 32]; n]` but not in - // `vec![[0; 64]; n]`: https://godbolt.org/z/WTzjzfs5b + // it's worth doing if the array is really long. The threshold here + // is largely arbitrary, but was picked because as of 2022-07-01 LLVM + // fails to const-fold the check in `vec![[1; 32]; n]` + // See https://github.com/rust-lang/rust/pull/97581#issuecomment-1166628022 // Feel free to tweak if you have better evidence. - N <= 32 && self.iter().all(IsZero::is_zero) + N <= 16 && self.iter().all(IsZero::is_zero) + } +} + +// This is recursive macro. +macro_rules! impl_for_tuples { + // Stopper + () => { + // No use for implementing for empty tuple because it is ZST. + }; + ($first_arg:ident $(,$rest:ident)*) => { + unsafe impl <$first_arg: IsZero, $($rest: IsZero,)*> IsZero for ($first_arg, $($rest,)*){ + #[inline] + fn is_zero(&self) -> bool{ + // Destructure tuple to N references + // Rust allows to hide generic params by local variable names. + #[allow(non_snake_case)] + let ($first_arg, $($rest,)*) = self; + + $first_arg.is_zero() + $( && $rest.is_zero() )* + } + } + + impl_for_tuples!($($rest),*); } } +impl_for_tuples!(A, B, C, D, E, F, G, H); + // `Option<&T>` and `Option<Box<T>>` are guaranteed to represent `None` as null. // For fat pointers, the bytes that would be the pointer metadata in the `Some` // variant are padding in the `None` variant, so ignoring them and @@ -118,3 +149,56 @@ impl_is_zero_option_of_nonzero!( NonZeroUsize, NonZeroIsize, ); + +macro_rules! impl_is_zero_option_of_num { + ($($t:ty,)+) => {$( + unsafe impl IsZero for Option<$t> { + #[inline] + fn is_zero(&self) -> bool { + const { + let none: Self = unsafe { core::mem::MaybeUninit::zeroed().assume_init() }; + assert!(none.is_none()); + } + self.is_none() + } + } + )+}; +} + +impl_is_zero_option_of_num!(u8, u16, u32, u64, u128, i8, i16, i32, i64, i128, usize, isize,); + +unsafe impl<T: IsZero> IsZero for Wrapping<T> { + #[inline] + fn is_zero(&self) -> bool { + self.0.is_zero() + } +} + +unsafe impl<T: IsZero> IsZero for Saturating<T> { + #[inline] + fn is_zero(&self) -> bool { + self.0.is_zero() + } +} + +macro_rules! impl_for_optional_bool { + ($($t:ty,)+) => {$( + unsafe impl IsZero for $t { + #[inline] + fn is_zero(&self) -> bool { + // SAFETY: This is *not* a stable layout guarantee, but + // inside `core` we're allowed to rely on the current rustc + // behaviour that options of bools will be one byte with + // no padding, so long as they're nested less than 254 deep. + let raw: u8 = unsafe { core::mem::transmute(*self) }; + raw == 0 + } + } + )+}; +} +impl_for_optional_bool! { + Option<bool>, + Option<Option<bool>>, + Option<Option<Option<bool>>>, + // Could go further, but not worth the metadata overhead +} diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs index fe4fff5064bc..94995913566b 100644 --- a/rust/alloc/vec/mod.rs +++ b/rust/alloc/vec/mod.rs @@ -61,12 +61,12 @@ use core::cmp::Ordering; use core::convert::TryFrom; use core::fmt; use core::hash::{Hash, Hasher}; -use core::intrinsics::{arith_offset, assume}; +use core::intrinsics::assume; use core::iter; #[cfg(not(no_global_oom_handling))] use core::iter::FromIterator; use core::marker::PhantomData; -use core::mem::{self, ManuallyDrop, MaybeUninit}; +use core::mem::{self, ManuallyDrop, MaybeUninit, SizedTypeProperties}; use core::ops::{self, Index, IndexMut, Range, RangeBounds}; use core::ptr::{self, NonNull}; use core::slice::{self, SliceIndex}; @@ -75,7 +75,7 @@ use crate::alloc::{Allocator, Global}; #[cfg(not(no_borrow))] use crate::borrow::{Cow, ToOwned}; use crate::boxed::Box; -use crate::collections::TryReserveError; +use crate::collections::{TryReserveError, TryReserveErrorKind}; use crate::raw_vec::RawVec; #[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] @@ -127,7 +127,7 @@ use self::set_len_on_drop::SetLenOnDrop; mod set_len_on_drop; #[cfg(not(no_global_oom_handling))] -use self::in_place_drop::InPlaceDrop; +use self::in_place_drop::{InPlaceDrop, InPlaceDstBufDrop}; #[cfg(not(no_global_oom_handling))] mod in_place_drop; @@ -169,7 +169,7 @@ mod spec_extend; /// vec[0] = 7; /// assert_eq!(vec[0], 7); /// -/// vec.extend([1, 2, 3].iter().copied()); +/// vec.extend([1, 2, 3]); /// /// for x in &vec { /// println!("{x}"); @@ -428,17 +428,25 @@ impl<T> Vec<T> { Vec { buf: RawVec::NEW, len: 0 } } - /// Constructs a new, empty `Vec<T>` with the specified capacity. + /// Constructs a new, empty `Vec<T>` with at least the specified capacity. /// - /// The vector will be able to hold exactly `capacity` elements without - /// reallocating. If `capacity` is 0, the vector will not allocate. + /// The vector will be able to hold at least `capacity` elements without + /// reallocating. This method is allowed to allocate for more elements than + /// `capacity`. If `capacity` is 0, the vector will not allocate. /// /// It is important to note that although the returned vector has the - /// *capacity* specified, the vector will have a zero *length*. For an - /// explanation of the difference between length and capacity, see + /// minimum *capacity* specified, the vector will have a zero *length*. For + /// an explanation of the difference between length and capacity, see /// *[Capacity and reallocation]*. /// + /// If it is important to know the exact allocated capacity of a `Vec`, + /// always use the [`capacity`] method after construction. + /// + /// For `Vec<T>` where `T` is a zero-sized type, there will be no allocation + /// and the capacity will always be `usize::MAX`. + /// /// [Capacity and reallocation]: #capacity-and-reallocation + /// [`capacity`]: Vec::capacity /// /// # Panics /// @@ -451,19 +459,24 @@ impl<T> Vec<T> { /// /// // The vector contains no items, even though it has capacity for more /// assert_eq!(vec.len(), 0); - /// assert_eq!(vec.capacity(), 10); + /// assert!(vec.capacity() >= 10); /// /// // These are all done without reallocating... /// for i in 0..10 { /// vec.push(i); /// } /// assert_eq!(vec.len(), 10); - /// assert_eq!(vec.capacity(), 10); + /// assert!(vec.capacity() >= 10); /// /// // ...but this may make the vector reallocate /// vec.push(11); /// assert_eq!(vec.len(), 11); /// assert!(vec.capacity() >= 11); + /// + /// // A vector of a zero-sized type will always over-allocate, since no + /// // allocation is necessary + /// let vec_units = Vec::<()>::with_capacity(10); + /// assert_eq!(vec_units.capacity(), usize::MAX); /// ``` #[cfg(not(no_global_oom_handling))] #[inline] @@ -473,17 +486,25 @@ impl<T> Vec<T> { Self::with_capacity_in(capacity, Global) } - /// Tries to construct a new, empty `Vec<T>` with the specified capacity. + /// Tries to construct a new, empty `Vec<T>` with at least the specified capacity. /// - /// The vector will be able to hold exactly `capacity` elements without - /// reallocating. If `capacity` is 0, the vector will not allocate. + /// The vector will be able to hold at least `capacity` elements without + /// reallocating. This method is allowed to allocate for more elements than + /// `capacity`. If `capacity` is 0, the vector will not allocate. /// /// It is important to note that although the returned vector has the - /// *capacity* specified, the vector will have a zero *length*. For an - /// explanation of the difference between length and capacity, see + /// minimum *capacity* specified, the vector will have a zero *length*. For + /// an explanation of the difference between length and capacity, see /// *[Capacity and reallocation]*. /// + /// If it is important to know the exact allocated capacity of a `Vec`, + /// always use the [`capacity`] method after construction. + /// + /// For `Vec<T>` where `T` is a zero-sized type, there will be no allocation + /// and the capacity will always be `usize::MAX`. + /// /// [Capacity and reallocation]: #capacity-and-reallocation + /// [`capacity`]: Vec::capacity /// /// # Examples /// @@ -492,14 +513,14 @@ impl<T> Vec<T> { /// /// // The vector contains no items, even though it has capacity for more /// assert_eq!(vec.len(), 0); - /// assert_eq!(vec.capacity(), 10); + /// assert!(vec.capacity() >= 10); /// /// // These are all done without reallocating... /// for i in 0..10 { /// vec.push(i); /// } /// assert_eq!(vec.len(), 10); - /// assert_eq!(vec.capacity(), 10); + /// assert!(vec.capacity() >= 10); /// /// // ...but this may make the vector reallocate /// vec.push(11); @@ -508,6 +529,11 @@ impl<T> Vec<T> { /// /// let mut result = Vec::try_with_capacity(usize::MAX); /// assert!(result.is_err()); + /// + /// // A vector of a zero-sized type will always over-allocate, since no + /// // allocation is necessary + /// let vec_units = Vec::<()>::try_with_capacity(10).unwrap(); + /// assert_eq!(vec_units.capacity(), usize::MAX); /// ``` #[inline] #[stable(feature = "kernel", since = "1.0.0")] @@ -515,15 +541,15 @@ impl<T> Vec<T> { Self::try_with_capacity_in(capacity, Global) } - /// Creates a `Vec<T>` directly from the raw components of another vector. + /// Creates a `Vec<T>` directly from a pointer, a capacity, and a length. /// /// # Safety /// /// This is highly unsafe, due to the number of invariants that aren't /// checked: /// - /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>` - /// (at least, it's highly likely to be incorrect if it wasn't). + /// * `ptr` must have been allocated using the global allocator, such as via + /// the [`alloc::alloc`] function. /// * `T` needs to have the same alignment as what `ptr` was allocated with. /// (`T` having a less strict alignment is not sufficient, the alignment really /// needs to be equal to satisfy the [`dealloc`] requirement that memory must be @@ -532,6 +558,14 @@ impl<T> Vec<T> { /// to be the same size as the pointer was allocated with. (Because similar to /// alignment, [`dealloc`] must be called with the same layout `size`.) /// * `length` needs to be less than or equal to `capacity`. + /// * The first `length` values must be properly initialized values of type `T`. + /// * `capacity` needs to be the capacity that the pointer was allocated with. + /// * The allocated size in bytes must be no larger than `isize::MAX`. + /// See the safety documentation of [`pointer::offset`]. + /// + /// These requirements are always upheld by any `ptr` that has been allocated + /// via `Vec<T>`. Other allocation sources are allowed if the invariants are + /// upheld. /// /// Violating these may cause problems like corrupting the allocator's /// internal data structures. For example it is normally **not** safe @@ -552,6 +586,7 @@ impl<T> Vec<T> { /// function. /// /// [`String`]: crate::string::String + /// [`alloc::alloc`]: crate::alloc::alloc /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc /// /// # Examples @@ -574,8 +609,8 @@ impl<T> Vec<T> { /// /// unsafe { /// // Overwrite memory with 4, 5, 6 - /// for i in 0..len as isize { - /// ptr::write(p.offset(i), 4 + i); + /// for i in 0..len { + /// ptr::write(p.add(i), 4 + i); /// } /// /// // Put everything back together into a Vec @@ -583,6 +618,32 @@ impl<T> Vec<T> { /// assert_eq!(rebuilt, [4, 5, 6]); /// } /// ``` + /// + /// Using memory that was allocated elsewhere: + /// + /// ```rust + /// #![feature(allocator_api)] + /// + /// use std::alloc::{AllocError, Allocator, Global, Layout}; + /// + /// fn main() { + /// let layout = Layout::array::<u32>(16).expect("overflow cannot happen"); + /// + /// let vec = unsafe { + /// let mem = match Global.allocate(layout) { + /// Ok(mem) => mem.cast::<u32>().as_ptr(), + /// Err(AllocError) => return, + /// }; + /// + /// mem.write(1_000_000); + /// + /// Vec::from_raw_parts_in(mem, 1, 16, Global) + /// }; + /// + /// assert_eq!(vec, &[1_000_000]); + /// assert_eq!(vec.capacity(), 16); + /// } + /// ``` #[inline] #[stable(feature = "rust1", since = "1.0.0")] pub unsafe fn from_raw_parts(ptr: *mut T, length: usize, capacity: usize) -> Self { @@ -611,18 +672,26 @@ impl<T, A: Allocator> Vec<T, A> { Vec { buf: RawVec::new_in(alloc), len: 0 } } - /// Constructs a new, empty `Vec<T, A>` with the specified capacity with the provided - /// allocator. + /// Constructs a new, empty `Vec<T, A>` with at least the specified capacity + /// with the provided allocator. /// - /// The vector will be able to hold exactly `capacity` elements without - /// reallocating. If `capacity` is 0, the vector will not allocate. + /// The vector will be able to hold at least `capacity` elements without + /// reallocating. This method is allowed to allocate for more elements than + /// `capacity`. If `capacity` is 0, the vector will not allocate. /// /// It is important to note that although the returned vector has the - /// *capacity* specified, the vector will have a zero *length*. For an - /// explanation of the difference between length and capacity, see + /// minimum *capacity* specified, the vector will have a zero *length*. For + /// an explanation of the difference between length and capacity, see /// *[Capacity and reallocation]*. /// + /// If it is important to know the exact allocated capacity of a `Vec`, + /// always use the [`capacity`] method after construction. + /// + /// For `Vec<T, A>` where `T` is a zero-sized type, there will be no allocation + /// and the capacity will always be `usize::MAX`. + /// /// [Capacity and reallocation]: #capacity-and-reallocation + /// [`capacity`]: Vec::capacity /// /// # Panics /// @@ -652,6 +721,11 @@ impl<T, A: Allocator> Vec<T, A> { /// vec.push(11); /// assert_eq!(vec.len(), 11); /// assert!(vec.capacity() >= 11); + /// + /// // A vector of a zero-sized type will always over-allocate, since no + /// // allocation is necessary + /// let vec_units = Vec::<(), System>::with_capacity_in(10, System); + /// assert_eq!(vec_units.capacity(), usize::MAX); /// ``` #[cfg(not(no_global_oom_handling))] #[inline] @@ -660,18 +734,26 @@ impl<T, A: Allocator> Vec<T, A> { Vec { buf: RawVec::with_capacity_in(capacity, alloc), len: 0 } } - /// Tries to construct a new, empty `Vec<T, A>` with the specified capacity + /// Tries to construct a new, empty `Vec<T, A>` with at least the specified capacity /// with the provided allocator. /// - /// The vector will be able to hold exactly `capacity` elements without - /// reallocating. If `capacity` is 0, the vector will not allocate. + /// The vector will be able to hold at least `capacity` elements without + /// reallocating. This method is allowed to allocate for more elements than + /// `capacity`. If `capacity` is 0, the vector will not allocate. /// /// It is important to note that although the returned vector has the - /// *capacity* specified, the vector will have a zero *length*. For an - /// explanation of the difference between length and capacity, see + /// minimum *capacity* specified, the vector will have a zero *length*. For + /// an explanation of the difference between length and capacity, see /// *[Capacity and reallocation]*. /// + /// If it is important to know the exact allocated capacity of a `Vec`, + /// always use the [`capacity`] method after construction. + /// + /// For `Vec<T, A>` where `T` is a zero-sized type, there will be no allocation + /// and the capacity will always be `usize::MAX`. + /// /// [Capacity and reallocation]: #capacity-and-reallocation + /// [`capacity`]: Vec::capacity /// /// # Examples /// @@ -700,6 +782,11 @@ impl<T, A: Allocator> Vec<T, A> { /// /// let mut result = Vec::try_with_capacity_in(usize::MAX, System); /// assert!(result.is_err()); + /// + /// // A vector of a zero-sized type will always over-allocate, since no + /// // allocation is necessary + /// let vec_units = Vec::<(), System>::try_with_capacity_in(10, System).unwrap(); + /// assert_eq!(vec_units.capacity(), usize::MAX); /// ``` #[inline] #[stable(feature = "kernel", since = "1.0.0")] @@ -707,21 +794,31 @@ impl<T, A: Allocator> Vec<T, A> { Ok(Vec { buf: RawVec::try_with_capacity_in(capacity, alloc)?, len: 0 }) } - /// Creates a `Vec<T, A>` directly from the raw components of another vector. + /// Creates a `Vec<T, A>` directly from a pointer, a capacity, a length, + /// and an allocator. /// /// # Safety /// /// This is highly unsafe, due to the number of invariants that aren't /// checked: /// - /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>` - /// (at least, it's highly likely to be incorrect if it wasn't). - /// * `T` needs to have the same size and alignment as what `ptr` was allocated with. + /// * `ptr` must be [*currently allocated*] via the given allocator `alloc`. + /// * `T` needs to have the same alignment as what `ptr` was allocated with. /// (`T` having a less strict alignment is not sufficient, the alignment really /// needs to be equal to satisfy the [`dealloc`] requirement that memory must be /// allocated and deallocated with the same layout.) + /// * The size of `T` times the `capacity` (ie. the allocated size in bytes) needs + /// to be the same size as the pointer was allocated with. (Because similar to + /// alignment, [`dealloc`] must be called with the same layout `size`.) /// * `length` needs to be less than or equal to `capacity`. - /// * `capacity` needs to be the capacity that the pointer was allocated with. + /// * The first `length` values must be properly initialized values of type `T`. + /// * `capacity` needs to [*fit*] the layout size that the pointer was allocated with. + /// * The allocated size in bytes must be no larger than `isize::MAX`. + /// See the safety documentation of [`pointer::offset`]. + /// + /// These requirements are always upheld by any `ptr` that has been allocated + /// via `Vec<T, A>`. Other allocation sources are allowed if the invariants are + /// upheld. /// /// Violating these may cause problems like corrupting the allocator's /// internal data structures. For example it is **not** safe @@ -739,6 +836,8 @@ impl<T, A: Allocator> Vec<T, A> { /// /// [`String`]: crate::string::String /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc + /// [*currently allocated*]: crate::alloc::Allocator#currently-allocated-memory + /// [*fit*]: crate::alloc::Allocator#memory-fitting /// /// # Examples /// @@ -768,8 +867,8 @@ impl<T, A: Allocator> Vec<T, A> { /// /// unsafe { /// // Overwrite memory with 4, 5, 6 - /// for i in 0..len as isize { - /// ptr::write(p.offset(i), 4 + i); + /// for i in 0..len { + /// ptr::write(p.add(i), 4 + i); /// } /// /// // Put everything back together into a Vec @@ -777,6 +876,29 @@ impl<T, A: Allocator> Vec<T, A> { /// assert_eq!(rebuilt, [4, 5, 6]); /// } /// ``` + /// + /// Using memory that was allocated elsewhere: + /// + /// ```rust + /// use std::alloc::{alloc, Layout}; + /// + /// fn main() { + /// let layout = Layout::array::<u32>(16).expect("overflow cannot happen"); + /// let vec = unsafe { + /// let mem = alloc(layout).cast::<u32>(); + /// if mem.is_null() { + /// return; + /// } + /// + /// mem.write(1_000_000); + /// + /// Vec::from_raw_parts(mem, 1, 16) + /// }; + /// + /// assert_eq!(vec, &[1_000_000]); + /// assert_eq!(vec.capacity(), 16); + /// } + /// ``` #[inline] #[unstable(feature = "allocator_api", issue = "32838")] pub unsafe fn from_raw_parts_in(ptr: *mut T, length: usize, capacity: usize, alloc: A) -> Self { @@ -869,13 +991,14 @@ impl<T, A: Allocator> Vec<T, A> { (ptr, len, capacity, alloc) } - /// Returns the number of elements the vector can hold without + /// Returns the total number of elements the vector can hold without /// reallocating. /// /// # Examples /// /// ``` - /// let vec: Vec<i32> = Vec::with_capacity(10); + /// let mut vec: Vec<i32> = Vec::with_capacity(10); + /// vec.push(42); /// assert_eq!(vec.capacity(), 10); /// ``` #[inline] @@ -885,10 +1008,10 @@ impl<T, A: Allocator> Vec<T, A> { } /// Reserves capacity for at least `additional` more elements to be inserted - /// in the given `Vec<T>`. The collection may reserve more space to avoid - /// frequent reallocations. After calling `reserve`, capacity will be - /// greater than or equal to `self.len() + additional`. Does nothing if - /// capacity is already sufficient. + /// in the given `Vec<T>`. The collection may reserve more space to + /// speculatively avoid frequent reallocations. After calling `reserve`, + /// capacity will be greater than or equal to `self.len() + additional`. + /// Does nothing if capacity is already sufficient. /// /// # Panics /// @@ -907,10 +1030,12 @@ impl<T, A: Allocator> Vec<T, A> { self.buf.reserve(self.len, additional); } - /// Reserves the minimum capacity for exactly `additional` more elements to - /// be inserted in the given `Vec<T>`. After calling `reserve_exact`, - /// capacity will be greater than or equal to `self.len() + additional`. - /// Does nothing if the capacity is already sufficient. + /// Reserves the minimum capacity for at least `additional` more elements to + /// be inserted in the given `Vec<T>`. Unlike [`reserve`], this will not + /// deliberately over-allocate to speculatively avoid frequent allocations. + /// After calling `reserve_exact`, capacity will be greater than or equal to + /// `self.len() + additional`. Does nothing if the capacity is already + /// sufficient. /// /// Note that the allocator may give the collection more space than it /// requests. Therefore, capacity can not be relied upon to be precisely @@ -936,10 +1061,11 @@ impl<T, A: Allocator> Vec<T, A> { } /// Tries to reserve capacity for at least `additional` more elements to be inserted - /// in the given `Vec<T>`. The collection may reserve more space to avoid + /// in the given `Vec<T>`. The collection may reserve more space to speculatively avoid /// frequent reallocations. After calling `try_reserve`, capacity will be - /// greater than or equal to `self.len() + additional`. Does nothing if - /// capacity is already sufficient. + /// greater than or equal to `self.len() + additional` if it returns + /// `Ok(())`. Does nothing if capacity is already sufficient. This method + /// preserves the contents even if an error occurs. /// /// # Errors /// @@ -971,10 +1097,11 @@ impl<T, A: Allocator> Vec<T, A> { self.buf.try_reserve(self.len, additional) } - /// Tries to reserve the minimum capacity for exactly `additional` - /// elements to be inserted in the given `Vec<T>`. After calling - /// `try_reserve_exact`, capacity will be greater than or equal to - /// `self.len() + additional` if it returns `Ok(())`. + /// Tries to reserve the minimum capacity for at least `additional` + /// elements to be inserted in the given `Vec<T>`. Unlike [`try_reserve`], + /// this will not deliberately over-allocate to speculatively avoid frequent + /// allocations. After calling `try_reserve_exact`, capacity will be greater + /// than or equal to `self.len() + additional` if it returns `Ok(())`. /// Does nothing if the capacity is already sufficient. /// /// Note that the allocator may give the collection more space than it @@ -1066,7 +1193,8 @@ impl<T, A: Allocator> Vec<T, A> { /// Converts the vector into [`Box<[T]>`][owned slice]. /// - /// Note that this will drop any excess capacity. + /// If the vector has excess capacity, its items will be moved into a + /// newly-allocated buffer with exactly the right capacity. /// /// [owned slice]: Box /// @@ -1199,7 +1327,8 @@ impl<T, A: Allocator> Vec<T, A> { self } - /// Returns a raw pointer to the vector's buffer. + /// Returns a raw pointer to the vector's buffer, or a dangling raw pointer + /// valid for zero sized reads if the vector didn't allocate. /// /// The caller must ensure that the vector outlives the pointer this /// function returns, or else it will end up pointing to garbage. @@ -1236,7 +1365,8 @@ impl<T, A: Allocator> Vec<T, A> { ptr } - /// Returns an unsafe mutable pointer to the vector's buffer. + /// Returns an unsafe mutable pointer to the vector's buffer, or a dangling + /// raw pointer valid for zero sized reads if the vector didn't allocate. /// /// The caller must ensure that the vector outlives the pointer this /// function returns, or else it will end up pointing to garbage. @@ -1440,9 +1570,6 @@ impl<T, A: Allocator> Vec<T, A> { } let len = self.len(); - if index > len { - assert_failed(index, len); - } // space for the new element if len == self.buf.capacity() { @@ -1454,9 +1581,15 @@ impl<T, A: Allocator> Vec<T, A> { // The spot to put the new value { let p = self.as_mut_ptr().add(index); - // Shift everything over to make space. (Duplicating the - // `index`th element into two consecutive places.) - ptr::copy(p, p.offset(1), len - index); + if index < len { + // Shift everything over to make space. (Duplicating the + // `index`th element into two consecutive places.) + ptr::copy(p, p.add(1), len - index); + } else if index == len { + // No elements need shifting. + } else { + assert_failed(index, len); + } // Write it in, overwriting the first copy of the `index`th // element. ptr::write(p, element); @@ -1513,7 +1646,7 @@ impl<T, A: Allocator> Vec<T, A> { ret = ptr::read(ptr); // Shift everything down to fill in that spot. - ptr::copy(ptr.offset(1), ptr, len - index - 1); + ptr::copy(ptr.add(1), ptr, len - index - 1); } self.set_len(len - 1); ret @@ -1562,11 +1695,11 @@ impl<T, A: Allocator> Vec<T, A> { /// /// ``` /// let mut vec = vec![1, 2, 3, 4]; - /// vec.retain_mut(|x| if *x > 3 { - /// false - /// } else { + /// vec.retain_mut(|x| if *x <= 3 { /// *x += 1; /// true + /// } else { + /// false /// }); /// assert_eq!(vec, [2, 3, 4]); /// ``` @@ -1854,6 +1987,51 @@ impl<T, A: Allocator> Vec<T, A> { Ok(()) } + /// Appends an element if there is sufficient spare capacity, otherwise an error is returned + /// with the element. + /// + /// Unlike [`push`] this method will not reallocate when there's insufficient capacity. + /// The caller should use [`reserve`] or [`try_reserve`] to ensure that there is enough capacity. + /// + /// [`push`]: Vec::push + /// [`reserve`]: Vec::reserve + /// [`try_reserve`]: Vec::try_reserve + /// + /// # Examples + /// + /// A manual, panic-free alternative to [`FromIterator`]: + /// + /// ``` + /// #![feature(vec_push_within_capacity)] + /// + /// use std::collections::TryReserveError; + /// fn from_iter_fallible<T>(iter: impl Iterator<Item=T>) -> Result<Vec<T>, TryReserveError> { + /// let mut vec = Vec::new(); + /// for value in iter { + /// if let Err(value) = vec.push_within_capacity(value) { + /// vec.try_reserve(1)?; + /// // this cannot fail, the previous line either returned or added at least 1 free slot + /// let _ = vec.push_within_capacity(value); + /// } + /// } + /// Ok(vec) + /// } + /// assert_eq!(from_iter_fallible(0..100), Ok(Vec::from_iter(0..100))); + /// ``` + #[inline] + #[unstable(feature = "vec_push_within_capacity", issue = "100486")] + pub fn push_within_capacity(&mut self, value: T) -> Result<(), T> { + if self.len == self.buf.capacity() { + return Err(value); + } + unsafe { + let end = self.as_mut_ptr().add(self.len); + ptr::write(end, value); + self.len += 1; + } + Ok(()) + } + /// Removes the last element from a vector and returns it, or [`None`] if it /// is empty. /// @@ -1886,7 +2064,7 @@ impl<T, A: Allocator> Vec<T, A> { /// /// # Panics /// - /// Panics if the number of elements in the vector overflows a `usize`. + /// Panics if the new capacity exceeds `isize::MAX` bytes. /// /// # Examples /// @@ -1980,9 +2158,7 @@ impl<T, A: Allocator> Vec<T, A> { unsafe { // set self.vec length's to start, to be safe in case Drain is leaked self.set_len(start); - // Use the borrow in the IterMut to indicate borrowing behavior of the - // whole Drain iterator (like &mut T). - let range_slice = slice::from_raw_parts_mut(self.as_mut_ptr().add(start), end - start); + let range_slice = slice::from_raw_parts(self.as_ptr().add(start), end - start); Drain { tail_start: end, tail_len: len - end, @@ -2145,7 +2321,7 @@ impl<T, A: Allocator> Vec<T, A> { { let len = self.len(); if new_len > len { - self.extend_with(new_len - len, ExtendFunc(f)); + self.extend_trusted(iter::repeat_with(f).take(new_len - len)); } else { self.truncate(new_len); } @@ -2174,7 +2350,6 @@ impl<T, A: Allocator> Vec<T, A> { /// static_ref[0] += 1; /// assert_eq!(static_ref, &[2, 2, 3]); /// ``` - #[cfg(not(no_global_oom_handling))] #[stable(feature = "vec_leak", since = "1.47.0")] #[inline] pub fn leak<'a>(self) -> &'a mut [T] @@ -2469,7 +2644,7 @@ impl<T: Clone, A: Allocator> Vec<T, A> { self.reserve(range.len()); // SAFETY: - // - `slice::range` guarantees that the given range is valid for indexing self + // - `slice::range` guarantees that the given range is valid for indexing self unsafe { self.spec_extend_from_within(range); } @@ -2501,7 +2676,7 @@ impl<T, A: Allocator, const N: usize> Vec<[T; N], A> { #[unstable(feature = "slice_flatten", issue = "95629")] pub fn into_flattened(self) -> Vec<T, A> { let (ptr, len, cap, alloc) = self.into_raw_parts_with_alloc(); - let (new_len, new_cap) = if mem::size_of::<T>() == 0 { + let (new_len, new_cap) = if T::IS_ZST { (len.checked_mul(N).expect("vec len overflow"), usize::MAX) } else { // SAFETY: @@ -2537,16 +2712,6 @@ impl<T: Clone> ExtendWith<T> for ExtendElement<T> { } } -struct ExtendFunc<F>(F); -impl<T, F: FnMut() -> T> ExtendWith<T> for ExtendFunc<F> { - fn next(&mut self) -> T { - (self.0)() - } - fn last(mut self) -> T { - (self.0)() - } -} - impl<T, A: Allocator> Vec<T, A> { #[cfg(not(no_global_oom_handling))] /// Extend the vector by `n` values, using the given generator. @@ -2563,7 +2728,7 @@ impl<T, A: Allocator> Vec<T, A> { // Write all elements except the last one for _ in 1..n { ptr::write(ptr, value.next()); - ptr = ptr.offset(1); + ptr = ptr.add(1); // Increment the length in every step in case next() panics local_len.increment_len(1); } @@ -2592,7 +2757,7 @@ impl<T, A: Allocator> Vec<T, A> { // Write all elements except the last one for _ in 1..n { ptr::write(ptr, value.next()); - ptr = ptr.offset(1); + ptr = ptr.add(1); // Increment the length in every step in case next() panics local_len.increment_len(1); } @@ -2664,7 +2829,7 @@ impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> { let (this, spare, len) = unsafe { self.split_at_spare_mut_with_len() }; // SAFETY: - // - caller guaratees that src is a valid index + // - caller guarantees that src is a valid index let to_clone = unsafe { this.get_unchecked(src) }; iter::zip(to_clone, spare) @@ -2683,13 +2848,13 @@ impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> { let (init, spare) = self.split_at_spare_mut(); // SAFETY: - // - caller guaratees that `src` is a valid index + // - caller guarantees that `src` is a valid index let source = unsafe { init.get_unchecked(src) }; // SAFETY: // - Both pointers are created from unique slice references (`&mut [_]`) // so they are valid and do not overlap. - // - Elements are :Copy so it's OK to to copy them, without doing + // - Elements are :Copy so it's OK to copy them, without doing // anything with the original values // - `count` is equal to the len of `source`, so source is valid for // `count` reads @@ -2712,6 +2877,7 @@ impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> { impl<T, A: Allocator> ops::Deref for Vec<T, A> { type Target = [T]; + #[inline] fn deref(&self) -> &[T] { unsafe { slice::from_raw_parts(self.as_ptr(), self.len) } } @@ -2719,6 +2885,7 @@ impl<T, A: Allocator> ops::Deref for Vec<T, A> { #[stable(feature = "rust1", since = "1.0.0")] impl<T, A: Allocator> ops::DerefMut for Vec<T, A> { + #[inline] fn deref_mut(&mut self) -> &mut [T] { unsafe { slice::from_raw_parts_mut(self.as_mut_ptr(), self.len) } } @@ -2764,7 +2931,7 @@ impl<T: Clone, A: Allocator + Clone> Clone for Vec<T, A> { // HACK(japaric): with cfg(test) the inherent `[T]::to_vec` method, which is // required for this method definition, is not available. Instead use the - // `slice::to_vec` function which is only available with cfg(test) + // `slice::to_vec` function which is only available with cfg(test) // NB see the slice::hack module in slice.rs for more information #[cfg(test)] fn clone(&self) -> Self { @@ -2845,19 +3012,22 @@ impl<T, A: Allocator> IntoIterator for Vec<T, A> { /// /// ``` /// let v = vec!["a".to_string(), "b".to_string()]; - /// for s in v.into_iter() { - /// // s has type String, not &String - /// println!("{s}"); - /// } + /// let mut v_iter = v.into_iter(); + /// + /// let first_element: Option<String> = v_iter.next(); + /// + /// assert_eq!(first_element, Some("a".to_string())); + /// assert_eq!(v_iter.next(), Some("b".to_string())); + /// assert_eq!(v_iter.next(), None); /// ``` #[inline] - fn into_iter(self) -> IntoIter<T, A> { + fn into_iter(self) -> Self::IntoIter { unsafe { let mut me = ManuallyDrop::new(self); let alloc = ManuallyDrop::new(ptr::read(me.allocator())); let begin = me.as_mut_ptr(); - let end = if mem::size_of::<T>() == 0 { - arith_offset(begin as *const i8, me.len() as isize) as *const T + let end = if T::IS_ZST { + begin.wrapping_byte_add(me.len()) } else { begin.add(me.len()) as *const T }; @@ -2879,7 +3049,7 @@ impl<'a, T, A: Allocator> IntoIterator for &'a Vec<T, A> { type Item = &'a T; type IntoIter = slice::Iter<'a, T>; - fn into_iter(self) -> slice::Iter<'a, T> { + fn into_iter(self) -> Self::IntoIter { self.iter() } } @@ -2889,7 +3059,7 @@ impl<'a, T, A: Allocator> IntoIterator for &'a mut Vec<T, A> { type Item = &'a mut T; type IntoIter = slice::IterMut<'a, T>; - fn into_iter(self) -> slice::IterMut<'a, T> { + fn into_iter(self) -> Self::IntoIter { self.iter_mut() } } @@ -2969,6 +3139,69 @@ impl<T, A: Allocator> Vec<T, A> { Ok(()) } + // specific extend for `TrustedLen` iterators, called both by the specializations + // and internal places where resolving specialization makes compilation slower + #[cfg(not(no_global_oom_handling))] + fn extend_trusted(&mut self, iterator: impl iter::TrustedLen<Item = T>) { + let (low, high) = iterator.size_hint(); + if let Some(additional) = high { + debug_assert_eq!( + low, + additional, + "TrustedLen iterator's size hint is not exact: {:?}", + (low, high) + ); + self.reserve(additional); + unsafe { + let ptr = self.as_mut_ptr(); + let mut local_len = SetLenOnDrop::new(&mut self.len); + iterator.for_each(move |element| { + ptr::write(ptr.add(local_len.current_len()), element); + // Since the loop executes user code which can panic we have to update + // the length every step to correctly drop what we've written. + // NB can't overflow since we would have had to alloc the address space + local_len.increment_len(1); + }); + } + } else { + // Per TrustedLen contract a `None` upper bound means that the iterator length + // truly exceeds usize::MAX, which would eventually lead to a capacity overflow anyway. + // Since the other branch already panics eagerly (via `reserve()`) we do the same here. + // This avoids additional codegen for a fallback code path which would eventually + // panic anyway. + panic!("capacity overflow"); + } + } + + // specific extend for `TrustedLen` iterators, called both by the specializations + // and internal places where resolving specialization makes compilation slower + fn try_extend_trusted(&mut self, iterator: impl iter::TrustedLen<Item = T>) -> Result<(), TryReserveError> { + let (low, high) = iterator.size_hint(); + if let Some(additional) = high { + debug_assert_eq!( + low, + additional, + "TrustedLen iterator's size hint is not exact: {:?}", + (low, high) + ); + self.try_reserve(additional)?; + unsafe { + let ptr = self.as_mut_ptr(); + let mut local_len = SetLenOnDrop::new(&mut self.len); + iterator.for_each(move |element| { + ptr::write(ptr.add(local_len.current_len()), element); + // Since the loop executes user code which can panic we have to update + // the length every step to correctly drop what we've written. + // NB can't overflow since we would have had to alloc the address space + local_len.increment_len(1); + }); + } + Ok(()) + } else { + Err(TryReserveErrorKind::CapacityOverflow.into()) + } + } + /// Creates a splicing iterator that replaces the specified range in the vector /// with the given `replace_with` iterator and yields the removed items. /// `replace_with` does not need to be the same length as `range`. @@ -3135,6 +3368,8 @@ unsafe impl<#[may_dangle] T, A: Allocator> Drop for Vec<T, A> { #[rustc_const_unstable(feature = "const_default_impls", issue = "87864")] impl<T> const Default for Vec<T> { /// Creates an empty `Vec<T>`. + /// + /// The vector will not allocate until elements are pushed onto it. fn default() -> Vec<T> { Vec::new() } @@ -3227,12 +3462,15 @@ impl<T, const N: usize> From<[T; N]> for Vec<T> { /// ``` #[cfg(not(test))] fn from(s: [T; N]) -> Vec<T> { - <[T]>::into_vec(box s) + <[T]>::into_vec( + #[rustc_box] + Box::new(s), + ) } #[cfg(test)] fn from(s: [T; N]) -> Vec<T> { - crate::slice::into_vec(box s) + crate::slice::into_vec(Box::new(s)) } } @@ -3261,7 +3499,7 @@ where } } -// note: test pulls in libstd, which causes errors here +// note: test pulls in std, which causes errors here #[cfg(not(test))] #[stable(feature = "vec_from_box", since = "1.18.0")] impl<T, A: Allocator> From<Box<[T], A>> for Vec<T, A> { @@ -3279,7 +3517,7 @@ impl<T, A: Allocator> From<Box<[T], A>> for Vec<T, A> { } } -// note: test pulls in libstd, which causes errors here +// note: test pulls in std, which causes errors here #[cfg(not(no_global_oom_handling))] #[cfg(not(test))] #[stable(feature = "box_from_vec", since = "1.20.0")] @@ -3294,6 +3532,14 @@ impl<T, A: Allocator> From<Vec<T, A>> for Box<[T], A> { /// ``` /// assert_eq!(Box::from(vec![1, 2, 3]), vec![1, 2, 3].into_boxed_slice()); /// ``` + /// + /// Any excess capacity is removed: + /// ``` + /// let mut vec = Vec::with_capacity(10); + /// vec.extend([1, 2, 3]); + /// + /// assert_eq!(Box::from(vec), vec![1, 2, 3].into_boxed_slice()); + /// ``` fn from(v: Vec<T, A>) -> Self { v.into_boxed_slice() } diff --git a/rust/alloc/vec/set_len_on_drop.rs b/rust/alloc/vec/set_len_on_drop.rs index 448bf5076a0b..d3c7297b80ec 100644 --- a/rust/alloc/vec/set_len_on_drop.rs +++ b/rust/alloc/vec/set_len_on_drop.rs @@ -20,6 +20,11 @@ impl<'a> SetLenOnDrop<'a> { pub(super) fn increment_len(&mut self, increment: usize) { self.local_len += increment; } + + #[inline] + pub(super) fn current_len(&self) -> usize { + self.local_len + } } impl Drop for SetLenOnDrop<'_> { diff --git a/rust/alloc/vec/spec_extend.rs b/rust/alloc/vec/spec_extend.rs index 5ce2d00991bc..a6a735201e59 100644 --- a/rust/alloc/vec/spec_extend.rs +++ b/rust/alloc/vec/spec_extend.rs @@ -1,12 +1,11 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT use crate::alloc::Allocator; -use crate::collections::{TryReserveError, TryReserveErrorKind}; +use crate::collections::TryReserveError; use core::iter::TrustedLen; -use core::ptr::{self}; use core::slice::{self}; -use super::{IntoIter, SetLenOnDrop, Vec}; +use super::{IntoIter, Vec}; // Specialization trait used for Vec::extend #[cfg(not(no_global_oom_handling))] @@ -44,36 +43,7 @@ where I: TrustedLen<Item = T>, { default fn spec_extend(&mut self, iterator: I) { - // This is the case for a TrustedLen iterator. - let (low, high) = iterator.size_hint(); - if let Some(additional) = high { - debug_assert_eq!( - low, - additional, - "TrustedLen iterator's size hint is not exact: {:?}", - (low, high) - ); - self.reserve(additional); - unsafe { - let mut ptr = self.as_mut_ptr().add(self.len()); - let mut local_len = SetLenOnDrop::new(&mut self.len); - iterator.for_each(move |element| { - ptr::write(ptr, element); - ptr = ptr.offset(1); - // Since the loop executes user code which can panic we have to bump the pointer - // after each step. - // NB can't overflow since we would have had to alloc the address space - local_len.increment_len(1); - }); - } - } else { - // Per TrustedLen contract a `None` upper bound means that the iterator length - // truly exceeds usize::MAX, which would eventually lead to a capacity overflow anyway. - // Since the other branch already panics eagerly (via `reserve()`) we do the same here. - // This avoids additional codegen for a fallback code path which would eventually - // panic anyway. - panic!("capacity overflow"); - } + self.extend_trusted(iterator) } } @@ -82,32 +52,7 @@ where I: TrustedLen<Item = T>, { default fn try_spec_extend(&mut self, iterator: I) -> Result<(), TryReserveError> { - // This is the case for a TrustedLen iterator. - let (low, high) = iterator.size_hint(); - if let Some(additional) = high { - debug_assert_eq!( - low, - additional, - "TrustedLen iterator's size hint is not exact: {:?}", - (low, high) - ); - self.try_reserve(additional)?; - unsafe { - let mut ptr = self.as_mut_ptr().add(self.len()); - let mut local_len = SetLenOnDrop::new(&mut self.len); - iterator.for_each(move |element| { - ptr::write(ptr, element); - ptr = ptr.offset(1); - // Since the loop executes user code which can panic we have to bump the pointer - // after each step. - // NB can't overflow since we would have had to alloc the address space - local_len.increment_len(1); - }); - } - Ok(()) - } else { - Err(TryReserveErrorKind::CapacityOverflow.into()) - } + self.try_extend_trusted(iterator) } } diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 50e7a76d5455..3e601ce2548d 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -6,6 +6,7 @@ * Sorted alphabetically. */ +#include <linux/errname.h> #include <linux/slab.h> #include <linux/refcount.h> #include <linux/wait.h> diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index 7b246454e009..9bcbea04dac3 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -9,7 +9,6 @@ //! using this crate. #![no_std] -#![feature(core_ffi_c)] // See <https://github.com/rust-lang/rust-bindgen/issues/1651>. #![cfg_attr(test, allow(deref_nullptr))] #![cfg_attr(test, allow(unaligned_references))] diff --git a/rust/helpers.c b/rust/helpers.c index 81e80261d597..bb594da56137 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -21,6 +21,7 @@ #include <linux/bug.h> #include <linux/build_bug.h> #include <linux/err.h> +#include <linux/errname.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/spinlock.h> @@ -110,6 +111,12 @@ long rust_helper_PTR_ERR(__force const void *ptr) } EXPORT_SYMBOL_GPL(rust_helper_PTR_ERR); +const char *rust_helper_errname(int err) +{ + return errname(err); +} +EXPORT_SYMBOL_GPL(rust_helper_errname); + struct task_struct *rust_helper_get_current(void) { return current; diff --git a/rust/kernel/build_assert.rs b/rust/kernel/build_assert.rs index 659542393c09..9e37120bc69c 100644 --- a/rust/kernel/build_assert.rs +++ b/rust/kernel/build_assert.rs @@ -67,6 +67,8 @@ macro_rules! build_error { /// assert!(n > 1); // Run-time check /// } /// ``` +/// +/// [`static_assert!`]: crate::static_assert! #[macro_export] macro_rules! build_assert { ($cond:expr $(,)?) => {{ diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 5f4114b30b94..05fcab6abfe6 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -4,16 +4,20 @@ //! //! C header: [`include/uapi/asm-generic/errno-base.h`](../../../include/uapi/asm-generic/errno-base.h) +use crate::str::CStr; + use alloc::{ alloc::{AllocError, LayoutError}, collections::TryReserveError, }; use core::convert::From; +use core::fmt; use core::num::TryFromIntError; use core::str::Utf8Error; /// Contains the C-compatible error codes. +#[rustfmt::skip] pub mod code { macro_rules! declare_err { ($err:tt $(,)? $($doc:expr),+) => { @@ -58,6 +62,25 @@ pub mod code { declare_err!(EPIPE, "Broken pipe."); declare_err!(EDOM, "Math argument out of domain of func."); declare_err!(ERANGE, "Math result not representable."); + declare_err!(ERESTARTSYS, "Restart the system call."); + declare_err!(ERESTARTNOINTR, "System call was interrupted by a signal and will be restarted."); + declare_err!(ERESTARTNOHAND, "Restart if no handler."); + declare_err!(ENOIOCTLCMD, "No ioctl command."); + declare_err!(ERESTART_RESTARTBLOCK, "Restart by calling sys_restart_syscall."); + declare_err!(EPROBE_DEFER, "Driver requests probe retry."); + declare_err!(EOPENSTALE, "Open found a stale dentry."); + declare_err!(ENOPARAM, "Parameter not supported."); + declare_err!(EBADHANDLE, "Illegal NFS file handle."); + declare_err!(ENOTSYNC, "Update synchronization mismatch."); + declare_err!(EBADCOOKIE, "Cookie is stale."); + declare_err!(ENOTSUPP, "Operation is not supported."); + declare_err!(ETOOSMALL, "Buffer or request is too small."); + declare_err!(ESERVERFAULT, "An untranslatable error occurred."); + declare_err!(EBADTYPE, "Type not supported by server."); + declare_err!(EJUKEBOX, "Request initiated, but will not complete before timeout."); + declare_err!(EIOCBQUEUED, "iocb queued, will get completion event."); + declare_err!(ERECALLCONFLICT, "Conflict with recalled state."); + declare_err!(ENOGRACE, "NFS file lock reclaim refused."); } /// Generic integer kernel error. @@ -113,6 +136,42 @@ impl Error { // SAFETY: self.0 is a valid error due to its invariant. unsafe { bindings::ERR_PTR(self.0.into()) as *mut _ } } + + /// Returns a string representing the error, if one exists. + #[cfg(not(testlib))] + pub fn name(&self) -> Option<&'static CStr> { + // SAFETY: Just an FFI call, there are no extra safety requirements. + let ptr = unsafe { bindings::errname(-self.0) }; + if ptr.is_null() { + None + } else { + // SAFETY: The string returned by `errname` is static and `NUL`-terminated. + Some(unsafe { CStr::from_char_ptr(ptr) }) + } + } + + /// Returns a string representing the error, if one exists. + /// + /// When `testlib` is configured, this always returns `None` to avoid the dependency on a + /// kernel function so that tests that use this (e.g., by calling [`Result::unwrap`]) can still + /// run in userspace. + #[cfg(testlib)] + pub fn name(&self) -> Option<&'static CStr> { + None + } +} + +impl fmt::Debug for Error { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + match self.name() { + // Print out number if no name can be found. + None => f.debug_tuple("Error").field(&-self.0).finish(), + // SAFETY: These strings are ASCII-only. + Some(name) => f + .debug_tuple(unsafe { core::str::from_utf8_unchecked(name) }) + .finish(), + } + } } impl From<AllocError> for Error { @@ -177,7 +236,7 @@ impl From<core::convert::Infallible> for Error { /// Note that even if a function does not return anything when it succeeds, /// it should still be modeled as returning a `Result` rather than /// just an [`Error`]. -pub type Result<T = ()> = core::result::Result<T, Error>; +pub type Result<T = (), E = Error> = core::result::Result<T, E>; /// Converts an integer as returned by a C kernel function to an error if it's negative, and /// `Ok(())` otherwise. diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 4ebfb08dab11..b4332a4ec1f4 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -197,6 +197,7 @@ //! [`Opaque`]: kernel::types::Opaque //! [`Opaque::ffi_init`]: kernel::types::Opaque::ffi_init //! [`pin_data`]: ::macros::pin_data +//! [`pin_init!`]: crate::pin_init! use crate::{ error::{self, Error}, @@ -255,6 +256,8 @@ pub mod macros; /// A normal `let` binding with optional type annotation. The expression is expected to implement /// [`PinInit`]/[`Init`] with the error type [`Infallible`]. If you want to use a different error /// type, then use [`stack_try_pin_init!`]. +/// +/// [`stack_try_pin_init!`]: crate::stack_try_pin_init! #[macro_export] macro_rules! stack_pin_init { (let $var:ident $(: $t:ty)? = $val:expr) => { @@ -804,6 +807,8 @@ macro_rules! try_pin_init { /// /// This initializer is for initializing data in-place that might later be moved. If you want to /// pin-initialize, use [`pin_init!`]. +/// +/// [`try_init!`]: crate::try_init! // For a detailed example of how this macro works, see the module documentation of the hidden // module `__internal` inside of `init/__internal.rs`. #[macro_export] diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs index 541cfad1d8be..00aa4e956c0a 100644 --- a/rust/kernel/init/macros.rs +++ b/rust/kernel/init/macros.rs @@ -16,8 +16,9 @@ //! //! We will look at the following example: //! -//! ```rust +//! ```rust,ignore //! # use kernel::init::*; +//! # use core::pin::Pin; //! #[pin_data] //! #[repr(C)] //! struct Bar<T> { @@ -71,11 +72,12 @@ //! //! Here is the definition of `Bar` from our example: //! -//! ```rust +//! ```rust,ignore //! # use kernel::init::*; //! #[pin_data] //! #[repr(C)] //! struct Bar<T> { +//! #[pin] //! t: T, //! pub x: usize, //! } @@ -83,7 +85,7 @@ //! //! This expands to the following code: //! -//! ```rust +//! ```rust,ignore //! // Firstly the normal definition of the struct, attributes are preserved: //! #[repr(C)] //! struct Bar<T> { @@ -116,20 +118,22 @@ //! unsafe fn t<E>( //! self, //! slot: *mut T, -//! init: impl ::kernel::init::Init<T, E>, +//! // Since `t` is `#[pin]`, this is `PinInit`. +//! init: impl ::kernel::init::PinInit<T, E>, //! ) -> ::core::result::Result<(), E> { -//! unsafe { ::kernel::init::Init::__init(init, slot) } +//! unsafe { ::kernel::init::PinInit::__pinned_init(init, slot) } //! } //! pub unsafe fn x<E>( //! self, //! slot: *mut usize, +//! // Since `x` is not `#[pin]`, this is `Init`. //! init: impl ::kernel::init::Init<usize, E>, //! ) -> ::core::result::Result<(), E> { //! unsafe { ::kernel::init::Init::__init(init, slot) } //! } //! } //! // Implement the internal `HasPinData` trait that associates `Bar` with the pin-data struct -//! // that we constructed beforehand. +//! // that we constructed above. //! unsafe impl<T> ::kernel::init::__internal::HasPinData for Bar<T> { //! type PinData = __ThePinData<T>; //! unsafe fn __pin_data() -> Self::PinData { @@ -160,6 +164,8 @@ //! struct __Unpin<'__pin, T> { //! __phantom_pin: ::core::marker::PhantomData<fn(&'__pin ()) -> &'__pin ()>, //! __phantom: ::core::marker::PhantomData<fn(Bar<T>) -> Bar<T>>, +//! // Our only `#[pin]` field is `t`. +//! t: T, //! } //! #[doc(hidden)] //! impl<'__pin, T> @@ -193,7 +199,7 @@ //! //! Here is the impl on `Bar` defining the new function: //! -//! ```rust +//! ```rust,ignore //! impl<T> Bar<T> { //! fn new(t: T) -> impl PinInit<Self> { //! pin_init!(Self { t, x: 0 }) @@ -203,7 +209,7 @@ //! //! This expands to the following code: //! -//! ```rust +//! ```rust,ignore //! impl<T> Bar<T> { //! fn new(t: T) -> impl PinInit<Self> { //! { @@ -232,25 +238,31 @@ //! // that will refer to this struct instead of the one defined above. //! struct __InitOk; //! // This is the expansion of `t,`, which is syntactic sugar for `t: t,`. -//! unsafe { ::core::ptr::write(&raw mut (*slot).t, t) }; +//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).t), t) }; //! // Since initialization could fail later (not in this case, since the error -//! // type is `Infallible`) we will need to drop this field if it fails. This -//! // `DropGuard` will drop the field when it gets dropped and has not yet -//! // been forgotten. We make a reference to it, so users cannot `mem::forget` -//! // it from the initializer, since the name is the same as the field. +//! // type is `Infallible`) we will need to drop this field if there is an +//! // error later. This `DropGuard` will drop the field when it gets dropped +//! // and has not yet been forgotten. We make a reference to it, so users +//! // cannot `mem::forget` it from the initializer, since the name is the same +//! // as the field (including hygiene). //! let t = &unsafe { -//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).t) +//! ::kernel::init::__internal::DropGuard::new( +//! ::core::addr_of_mut!((*slot).t), +//! ) //! }; //! // Expansion of `x: 0,`: //! // Since this can be an arbitrary expression we cannot place it inside of //! // the `unsafe` block, so we bind it here. //! let x = 0; -//! unsafe { ::core::ptr::write(&raw mut (*slot).x, x) }; +//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).x), x) }; +//! // We again create a `DropGuard`. //! let x = &unsafe { -//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).x) +//! ::kernel::init::__internal::DropGuard::new( +//! ::core::addr_of_mut!((*slot).x), +//! ) //! }; //! -//! // Here we use the type checker to ensuer that every field has been +//! // Here we use the type checker to ensure that every field has been //! // initialized exactly once, since this is `if false` it will never get //! // executed, but still type-checked. //! // Additionally we abuse `slot` to automatically infer the correct type for @@ -272,7 +284,7 @@ //! }; //! } //! // Since initialization has successfully completed, we can now forget the -//! // guards. +//! // guards. This is not `mem::forget`, since we only have `&DropGuard`. //! unsafe { ::kernel::init::__internal::DropGuard::forget(t) }; //! unsafe { ::kernel::init::__internal::DropGuard::forget(x) }; //! } @@ -280,7 +292,7 @@ //! // `__InitOk` that we need to return. //! Ok(__InitOk) //! }); -//! // Change the return type of the closure. +//! // Change the return type from `__InitOk` to `()`. //! let init = move |slot| -> ::core::result::Result<(), ::core::convert::Infallible> { //! init(slot).map(|__InitOk| ()) //! }; @@ -299,7 +311,7 @@ //! Since we already took a look at `#[pin_data]` on `Bar`, this section will only explain the //! differences/new things in the expansion of the `Foo` definition: //! -//! ```rust +//! ```rust,ignore //! #[pin_data(PinnedDrop)] //! struct Foo { //! a: usize, @@ -310,7 +322,7 @@ //! //! This expands to the following code: //! -//! ```rust +//! ```rust,ignore //! struct Foo { //! a: usize, //! b: Bar<u32>, @@ -330,8 +342,6 @@ //! unsafe fn b<E>( //! self, //! slot: *mut Bar<u32>, -//! // Note that this is `PinInit` instead of `Init`, this is because `b` is -//! // structurally pinned, as marked by the `#[pin]` attribute. //! init: impl ::kernel::init::PinInit<Bar<u32>, E>, //! ) -> ::core::result::Result<(), E> { //! unsafe { ::kernel::init::PinInit::__pinned_init(init, slot) } @@ -359,14 +369,13 @@ //! struct __Unpin<'__pin> { //! __phantom_pin: ::core::marker::PhantomData<fn(&'__pin ()) -> &'__pin ()>, //! __phantom: ::core::marker::PhantomData<fn(Foo) -> Foo>, -//! // Since this field is `#[pin]`, it is listed here. //! b: Bar<u32>, //! } //! #[doc(hidden)] //! impl<'__pin> ::core::marker::Unpin for Foo where __Unpin<'__pin>: ::core::marker::Unpin {} //! // Since we specified `PinnedDrop` as the argument to `#[pin_data]`, we expect `Foo` to //! // implement `PinnedDrop`. Thus we do not need to prevent `Drop` implementations like -//! // before, instead we implement it here and delegate to `PinnedDrop`. +//! // before, instead we implement `Drop` here and delegate to `PinnedDrop`. //! impl ::core::ops::Drop for Foo { //! fn drop(&mut self) { //! // Since we are getting dropped, no one else has a reference to `self` and thus we @@ -388,7 +397,7 @@ //! //! Here is the `PinnedDrop` impl for `Foo`: //! -//! ```rust +//! ```rust,ignore //! #[pinned_drop] //! impl PinnedDrop for Foo { //! fn drop(self: Pin<&mut Self>) { @@ -399,7 +408,7 @@ //! //! This expands to the following code: //! -//! ```rust +//! ```rust,ignore //! // `unsafe`, full path and the token parameter are added, everything else stays the same. //! unsafe impl ::kernel::init::PinnedDrop for Foo { //! fn drop(self: Pin<&mut Self>, _: ::kernel::init::__internal::OnlyCallFromDrop) { @@ -410,10 +419,10 @@ //! //! ## `pin_init!` on `Foo` //! -//! Since we already took a look at `pin_init!` on `Bar`, this section will only explain the -//! differences/new things in the expansion of `pin_init!` on `Foo`: +//! Since we already took a look at `pin_init!` on `Bar`, this section will only show the expansion +//! of `pin_init!` on `Foo`: //! -//! ```rust +//! ```rust,ignore //! let a = 42; //! let initializer = pin_init!(Foo { //! a, @@ -423,7 +432,7 @@ //! //! This expands to the following code: //! -//! ```rust +//! ```rust,ignore //! let a = 42; //! let initializer = { //! struct __InitOk; @@ -438,13 +447,15 @@ //! >(data, move |slot| { //! { //! struct __InitOk; -//! unsafe { ::core::ptr::write(&raw mut (*slot).a, a) }; -//! let a = &unsafe { ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).a) }; +//! unsafe { ::core::ptr::write(::core::addr_of_mut!((*slot).a), a) }; +//! let a = &unsafe { +//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).a)) +//! }; //! let b = Bar::new(36); -//! // Here we use `data` to access the correct field and require that `b` is of type -//! // `PinInit<Bar<u32>, Infallible>`. -//! unsafe { data.b(&raw mut (*slot).b, b)? }; -//! let b = &unsafe { ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).b) }; +//! unsafe { data.b(::core::addr_of_mut!((*slot).b), b)? }; +//! let b = &unsafe { +//! ::kernel::init::__internal::DropGuard::new(::core::addr_of_mut!((*slot).b)) +//! }; //! //! #[allow(unreachable_code, clippy::diverging_sub_expression)] //! if false { diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 676995d4e460..85b261209977 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -14,12 +14,8 @@ #![no_std] #![feature(allocator_api)] #![feature(coerce_unsized)] -#![feature(core_ffi_c)] #![feature(dispatch_from_dyn)] -#![feature(explicit_generic_args_with_impl_trait)] -#![feature(generic_associated_types)] #![feature(new_uninit)] -#![feature(pin_macro)] #![feature(receiver_trait)] #![feature(unsize)] diff --git a/rust/kernel/std_vendor.rs b/rust/kernel/std_vendor.rs index b3e68b24a8c6..388d6a5147a2 100644 --- a/rust/kernel/std_vendor.rs +++ b/rust/kernel/std_vendor.rs @@ -137,6 +137,8 @@ /// [`std::dbg`]: https://doc.rust-lang.org/std/macro.dbg.html /// [`eprintln`]: https://doc.rust-lang.org/std/macro.eprintln.html /// [`printk`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html +/// [`pr_info`]: crate::pr_info! +/// [`pr_debug`]: crate::pr_debug! #[macro_export] macro_rules! dbg { // NOTE: We cannot use `concat!` to make a static string as a format argument diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index cd3d2a6cf1fc..c9dd3bf59e34 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -2,6 +2,7 @@ //! String representations. +use alloc::alloc::AllocError; use alloc::vec::Vec; use core::fmt::{self, Write}; use core::ops::{self, Deref, Index}; @@ -199,6 +200,12 @@ impl CStr { pub unsafe fn as_str_unchecked(&self) -> &str { unsafe { core::str::from_utf8_unchecked(self.as_bytes()) } } + + /// Convert this [`CStr`] into a [`CString`] by allocating memory and + /// copying over the string data. + pub fn to_cstring(&self) -> Result<CString, AllocError> { + CString::try_from(self) + } } impl fmt::Display for CStr { @@ -584,6 +591,21 @@ impl Deref for CString { } } +impl<'a> TryFrom<&'a CStr> for CString { + type Error = AllocError; + + fn try_from(cstr: &'a CStr) -> Result<CString, AllocError> { + let mut buf = Vec::new(); + + buf.try_extend_from_slice(cstr.as_bytes_with_nul()) + .map_err(|_| AllocError)?; + + // INVARIANT: The `CStr` and `CString` types have the same invariants for + // the string data, and we copied it over without changes. + Ok(CString { buf }) + } +} + /// A convenience alias for [`core::format_args`]. #[macro_export] macro_rules! fmt { diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index e6d206242465..a89843cacaad 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -146,13 +146,15 @@ impl<T: ?Sized + Unsize<U>, U: ?Sized> core::ops::DispatchFromDyn<Arc<U>> for Ar // SAFETY: It is safe to send `Arc<T>` to another thread when the underlying `T` is `Sync` because // it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, it needs -// `T` to be `Send` because any thread that has an `Arc<T>` may ultimately access `T` directly, for -// example, when the reference count reaches zero and `T` is dropped. +// `T` to be `Send` because any thread that has an `Arc<T>` may ultimately access `T` using a +// mutable reference when the reference count reaches zero and `T` is dropped. unsafe impl<T: ?Sized + Sync + Send> Send for Arc<T> {} -// SAFETY: It is safe to send `&Arc<T>` to another thread when the underlying `T` is `Sync` for the -// same reason as above. `T` needs to be `Send` as well because a thread can clone an `&Arc<T>` -// into an `Arc<T>`, which may lead to `T` being accessed by the same reasoning as above. +// SAFETY: It is safe to send `&Arc<T>` to another thread when the underlying `T` is `Sync` +// because it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, +// it needs `T` to be `Send` because any thread that has a `&Arc<T>` may clone it and get an +// `Arc<T>` on that thread, so the thread may ultimately access `T` using a mutable reference when +// the reference count reaches zero and `T` is dropped. unsafe impl<T: ?Sized + Sync + Send> Sync for Arc<T> {} impl<T> Arc<T> { @@ -185,7 +187,7 @@ impl<T> Arc<T> { /// Use the given initializer to in-place initialize a `T`. /// - /// This is equivalent to [`pin_init`], since an [`Arc`] is always pinned. + /// This is equivalent to [`Arc<T>::pin_init`], since an [`Arc`] is always pinned. #[inline] pub fn init<E>(init: impl Init<T, E>) -> error::Result<Self> where @@ -221,6 +223,11 @@ impl<T: ?Sized> Arc<T> { // reference can be created. unsafe { ArcBorrow::new(self.ptr) } } + + /// Compare whether two [`Arc`] pointers reference the same underlying object. + pub fn ptr_eq(this: &Self, other: &Self) -> bool { + core::ptr::eq(this.ptr.as_ptr(), other.ptr.as_ptr()) + } } impl<T: 'static> ForeignOwnable for Arc<T> { @@ -259,6 +266,12 @@ impl<T: ?Sized> Deref for Arc<T> { } } +impl<T: ?Sized> AsRef<T> for Arc<T> { + fn as_ref(&self) -> &T { + self.deref() + } +} + impl<T: ?Sized> Clone for Arc<T> { fn clone(&self) -> Self { // INVARIANT: C `refcount_inc` saturates the refcount, so it cannot overflow to zero. diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs index 526d29a0ae27..7eda15e5f1b3 100644 --- a/rust/kernel/task.rs +++ b/rust/kernel/task.rs @@ -64,8 +64,14 @@ macro_rules! current { #[repr(transparent)] pub struct Task(pub(crate) Opaque<bindings::task_struct>); -// SAFETY: It's OK to access `Task` through references from other threads because we're either -// accessing properties that don't change (e.g., `pid`, `group_leader`) or that are properly +// SAFETY: By design, the only way to access a `Task` is via the `current` function or via an +// `ARef<Task>` obtained through the `AlwaysRefCounted` impl. This means that the only situation in +// which a `Task` can be accessed mutably is when the refcount drops to zero and the destructor +// runs. It is safe for that to happen on any thread, so it is ok for this type to be `Send`. +unsafe impl Send for Task {} + +// SAFETY: It's OK to access `Task` through shared references from other threads because we're +// either accessing properties that don't change (e.g., `pid`, `group_leader`) or that are properly // synchronised by C code (e.g., `signal_pending`). unsafe impl Sync for Task {} diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index 29db59d6119a..1e5380b16ed5 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -321,6 +321,19 @@ pub struct ARef<T: AlwaysRefCounted> { _p: PhantomData<T>, } +// SAFETY: It is safe to send `ARef<T>` to another thread when the underlying `T` is `Sync` because +// it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, it needs +// `T` to be `Send` because any thread that has an `ARef<T>` may ultimately access `T` using a +// mutable reference, for example, when the reference count reaches zero and `T` is dropped. +unsafe impl<T: AlwaysRefCounted + Sync + Send> Send for ARef<T> {} + +// SAFETY: It is safe to send `&ARef<T>` to another thread when the underlying `T` is `Sync` +// because it effectively means sharing `&T` (which is safe because `T` is `Sync`); additionally, +// it needs `T` to be `Send` because any thread that has a `&ARef<T>` may clone it and get an +// `ARef<T>` on that thread, so the thread may ultimately access `T` using a mutable reference, for +// example, when the reference count reaches zero and `T` is dropped. +unsafe impl<T: AlwaysRefCounted + Sync + Send> Sync for ARef<T> {} + impl<T: AlwaysRefCounted> ARef<T> { /// Creates a new instance of [`ARef`]. /// diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs index b2bdd4d8c958..afb0f2e3a36a 100644 --- a/rust/macros/helpers.rs +++ b/rust/macros/helpers.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{token_stream, Group, TokenTree}; +use proc_macro::{token_stream, Group, Punct, Spacing, TokenStream, TokenTree}; pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option<String> { if let Some(TokenTree::Ident(ident)) = it.next() { @@ -69,3 +69,87 @@ pub(crate) fn expect_end(it: &mut token_stream::IntoIter) { panic!("Expected end"); } } + +pub(crate) struct Generics { + pub(crate) impl_generics: Vec<TokenTree>, + pub(crate) ty_generics: Vec<TokenTree>, +} + +/// Parses the given `TokenStream` into `Generics` and the rest. +/// +/// The generics are not present in the rest, but a where clause might remain. +pub(crate) fn parse_generics(input: TokenStream) -> (Generics, Vec<TokenTree>) { + // `impl_generics`, the declared generics with their bounds. + let mut impl_generics = vec![]; + // Only the names of the generics, without any bounds. + let mut ty_generics = vec![]; + // Tokens not related to the generics e.g. the `where` token and definition. + let mut rest = vec![]; + // The current level of `<`. + let mut nesting = 0; + let mut toks = input.into_iter(); + // If we are at the beginning of a generic parameter. + let mut at_start = true; + for tt in &mut toks { + match tt.clone() { + TokenTree::Punct(p) if p.as_char() == '<' => { + if nesting >= 1 { + // This is inside of the generics and part of some bound. + impl_generics.push(tt); + } + nesting += 1; + } + TokenTree::Punct(p) if p.as_char() == '>' => { + // This is a parsing error, so we just end it here. + if nesting == 0 { + break; + } else { + nesting -= 1; + if nesting >= 1 { + // We are still inside of the generics and part of some bound. + impl_generics.push(tt); + } + if nesting == 0 { + break; + } + } + } + tt => { + if nesting == 1 { + // Here depending on the token, it might be a generic variable name. + match &tt { + // Ignore const. + TokenTree::Ident(i) if i.to_string() == "const" => {} + TokenTree::Ident(_) if at_start => { + ty_generics.push(tt.clone()); + // We also already push the `,` token, this makes it easier to append + // generics. + ty_generics.push(TokenTree::Punct(Punct::new(',', Spacing::Alone))); + at_start = false; + } + TokenTree::Punct(p) if p.as_char() == ',' => at_start = true, + // Lifetimes begin with `'`. + TokenTree::Punct(p) if p.as_char() == '\'' && at_start => { + ty_generics.push(tt.clone()); + } + _ => {} + } + } + if nesting >= 1 { + impl_generics.push(tt); + } else if nesting == 0 { + // If we haven't entered the generics yet, we still want to keep these tokens. + rest.push(tt); + } + } + } + } + rest.extend(toks); + ( + Generics { + impl_generics, + ty_generics, + }, + rest, + ) +} diff --git a/rust/macros/pin_data.rs b/rust/macros/pin_data.rs index 954149d77181..6d58cfda9872 100644 --- a/rust/macros/pin_data.rs +++ b/rust/macros/pin_data.rs @@ -1,79 +1,127 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT -use proc_macro::{Punct, Spacing, TokenStream, TokenTree}; +use crate::helpers::{parse_generics, Generics}; +use proc_macro::{Group, Punct, Spacing, TokenStream, TokenTree}; pub(crate) fn pin_data(args: TokenStream, input: TokenStream) -> TokenStream { // This proc-macro only does some pre-parsing and then delegates the actual parsing to // `kernel::__pin_data!`. - // - // In here we only collect the generics, since parsing them in declarative macros is very - // elaborate. We also do not need to analyse their structure, we only need to collect them. - // `impl_generics`, the declared generics with their bounds. - let mut impl_generics = vec![]; - // Only the names of the generics, without any bounds. - let mut ty_generics = vec![]; - // Tokens not related to the generics e.g. the `impl` token. - let mut rest = vec![]; - // The current level of `<`. - let mut nesting = 0; - let mut toks = input.into_iter(); - // If we are at the beginning of a generic parameter. - let mut at_start = true; - for tt in &mut toks { - match tt.clone() { - TokenTree::Punct(p) if p.as_char() == '<' => { - if nesting >= 1 { - impl_generics.push(tt); - } - nesting += 1; - } - TokenTree::Punct(p) if p.as_char() == '>' => { - if nesting == 0 { - break; - } else { - nesting -= 1; - if nesting >= 1 { - impl_generics.push(tt); - } - if nesting == 0 { - break; - } + let ( + Generics { + impl_generics, + ty_generics, + }, + rest, + ) = parse_generics(input); + // The struct definition might contain the `Self` type. Since `__pin_data!` will define a new + // type with the same generics and bounds, this poses a problem, since `Self` will refer to the + // new type as opposed to this struct definition. Therefore we have to replace `Self` with the + // concrete name. + + // Errors that occur when replacing `Self` with `struct_name`. + let mut errs = TokenStream::new(); + // The name of the struct with ty_generics. + let struct_name = rest + .iter() + .skip_while(|tt| !matches!(tt, TokenTree::Ident(i) if i.to_string() == "struct")) + .nth(1) + .and_then(|tt| match tt { + TokenTree::Ident(_) => { + let tt = tt.clone(); + let mut res = vec![tt]; + if !ty_generics.is_empty() { + // We add this, so it is maximally compatible with e.g. `Self::CONST` which + // will be replaced by `StructName::<$generics>::CONST`. + res.push(TokenTree::Punct(Punct::new(':', Spacing::Joint))); + res.push(TokenTree::Punct(Punct::new(':', Spacing::Alone))); + res.push(TokenTree::Punct(Punct::new('<', Spacing::Alone))); + res.extend(ty_generics.iter().cloned()); + res.push(TokenTree::Punct(Punct::new('>', Spacing::Alone))); } + Some(res) } - tt => { - if nesting == 1 { - match &tt { - TokenTree::Ident(i) if i.to_string() == "const" => {} - TokenTree::Ident(_) if at_start => { - ty_generics.push(tt.clone()); - ty_generics.push(TokenTree::Punct(Punct::new(',', Spacing::Alone))); - at_start = false; - } - TokenTree::Punct(p) if p.as_char() == ',' => at_start = true, - TokenTree::Punct(p) if p.as_char() == '\'' && at_start => { - ty_generics.push(tt.clone()); - } - _ => {} - } - } - if nesting >= 1 { - impl_generics.push(tt); - } else if nesting == 0 { - rest.push(tt); - } + _ => None, + }) + .unwrap_or_else(|| { + // If we did not find the name of the struct then we will use `Self` as the replacement + // and add a compile error to ensure it does not compile. + errs.extend( + "::core::compile_error!(\"Could not locate type name.\");" + .parse::<TokenStream>() + .unwrap(), + ); + "Self".parse::<TokenStream>().unwrap().into_iter().collect() + }); + let impl_generics = impl_generics + .into_iter() + .flat_map(|tt| replace_self_and_deny_type_defs(&struct_name, tt, &mut errs)) + .collect::<Vec<_>>(); + let mut rest = rest + .into_iter() + .flat_map(|tt| { + // We ignore top level `struct` tokens, since they would emit a compile error. + if matches!(&tt, TokenTree::Ident(i) if i.to_string() == "struct") { + vec![tt] + } else { + replace_self_and_deny_type_defs(&struct_name, tt, &mut errs) } - } - } - rest.extend(toks); + }) + .collect::<Vec<_>>(); // This should be the body of the struct `{...}`. let last = rest.pop(); - quote!(::kernel::__pin_data! { + let mut quoted = quote!(::kernel::__pin_data! { parse_input: @args(#args), @sig(#(#rest)*), @impl_generics(#(#impl_generics)*), @ty_generics(#(#ty_generics)*), @body(#last), - }) + }); + quoted.extend(errs); + quoted +} + +/// Replaces `Self` with `struct_name` and errors on `enum`, `trait`, `struct` `union` and `impl` +/// keywords. +/// +/// The error is appended to `errs` to allow normal parsing to continue. +fn replace_self_and_deny_type_defs( + struct_name: &Vec<TokenTree>, + tt: TokenTree, + errs: &mut TokenStream, +) -> Vec<TokenTree> { + match tt { + TokenTree::Ident(ref i) + if i.to_string() == "enum" + || i.to_string() == "trait" + || i.to_string() == "struct" + || i.to_string() == "union" + || i.to_string() == "impl" => + { + errs.extend( + format!( + "::core::compile_error!(\"Cannot use `{i}` inside of struct definition with \ + `#[pin_data]`.\");" + ) + .parse::<TokenStream>() + .unwrap() + .into_iter() + .map(|mut tok| { + tok.set_span(tt.span()); + tok + }), + ); + vec![tt] + } + TokenTree::Ident(i) if i.to_string() == "Self" => struct_name.clone(), + TokenTree::Literal(_) | TokenTree::Punct(_) | TokenTree::Ident(_) => vec![tt], + TokenTree::Group(g) => vec![TokenTree::Group(Group::new( + g.delimiter(), + g.stream() + .into_iter() + .flat_map(|tt| replace_self_and_deny_type_defs(struct_name, tt, errs)) + .collect(), + ))], + } } diff --git a/rust/macros/quote.rs b/rust/macros/quote.rs index c8e08b3c1e4c..dddbb4e6f4cb 100644 --- a/rust/macros/quote.rs +++ b/rust/macros/quote.rs @@ -39,12 +39,14 @@ impl ToTokens for TokenStream { /// [`quote_spanned!`](https://docs.rs/quote/latest/quote/macro.quote_spanned.html) macro from the /// `quote` crate but provides only just enough functionality needed by the current `macros` crate. macro_rules! quote_spanned { - ($span:expr => $($tt:tt)*) => { - #[allow(clippy::vec_init_then_push)] - { - let mut tokens = ::std::vec::Vec::new(); - let span = $span; - quote_spanned!(@proc tokens span $($tt)*); + ($span:expr => $($tt:tt)*) => {{ + let mut tokens; + #[allow(clippy::vec_init_then_push)] + { + tokens = ::std::vec::Vec::new(); + let span = $span; + quote_spanned!(@proc tokens span $($tt)*); + } ::proc_macro::TokenStream::from_iter(tokens) }}; (@proc $v:ident $span:ident) => {}; diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs index 29f69f3a52de..0caad902ba40 100644 --- a/rust/uapi/lib.rs +++ b/rust/uapi/lib.rs @@ -8,7 +8,6 @@ //! userspace APIs. #![no_std] -#![feature(core_ffi_c)] // See <https://github.com/rust-lang/rust-bindgen/issues/1651>. #![cfg_attr(test, allow(deref_nullptr))] #![cfg_attr(test, allow(unaligned_references))] diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 9f94fc83f086..78175231c969 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -277,7 +277,7 @@ $(obj)/%.lst: $(src)/%.c FORCE # Compile Rust sources (.rs) # --------------------------------------------------------------------------- -rust_allowed_features := core_ffi_c,explicit_generic_args_with_impl_trait,new_uninit,pin_macro +rust_allowed_features := new_uninit rust_common_cmd = \ RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 471300ba176c..50a92c4e9984 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -48,12 +48,12 @@ if IS_BUILTIN(CONFIG_COMMON_CLK): LX_GDBPARSED(CLK_GET_RATE_NOCACHE) /* linux/fs.h */ -LX_VALUE(SB_RDONLY) -LX_VALUE(SB_SYNCHRONOUS) -LX_VALUE(SB_MANDLOCK) -LX_VALUE(SB_DIRSYNC) -LX_VALUE(SB_NOATIME) -LX_VALUE(SB_NODIRATIME) +LX_GDBPARSED(SB_RDONLY) +LX_GDBPARSED(SB_SYNCHRONOUS) +LX_GDBPARSED(SB_MANDLOCK) +LX_GDBPARSED(SB_DIRSYNC) +LX_GDBPARSED(SB_NOATIME) +LX_GDBPARSED(SB_NODIRATIME) /* linux/htimer.h */ LX_GDBPARSED(hrtimer_resolution) diff --git a/scripts/gfp-translate b/scripts/gfp-translate index b2ce416d944b..6c9aed17cf56 100755 --- a/scripts/gfp-translate +++ b/scripts/gfp-translate @@ -63,11 +63,11 @@ fi # Extract GFP flags from the kernel source TMPFILE=`mktemp -t gfptranslate-XXXXXX` || exit 1 -grep -q ___GFP $SOURCE/include/linux/gfp.h +grep -q ___GFP $SOURCE/include/linux/gfp_types.h if [ $? -eq 0 ]; then - grep "^#define ___GFP" $SOURCE/include/linux/gfp.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE + grep "^#define ___GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE else - grep "^#define __GFP" $SOURCE/include/linux/gfp.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE + grep "^#define __GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE fi # Parse the flags diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 20d483ec6f5f..131be76d2130 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -27,7 +27,7 @@ llvm) fi ;; rustc) - echo 1.62.0 + echo 1.68.2 ;; bindgen) echo 0.56.0 diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index d4531d09984d..c12150f96b88 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1979,6 +1979,11 @@ static void add_header(struct buffer *b, struct module *mod) buf_printf(b, "#include <linux/vermagic.h>\n"); buf_printf(b, "#include <linux/compiler.h>\n"); buf_printf(b, "\n"); + buf_printf(b, "#ifdef CONFIG_UNWINDER_ORC\n"); + buf_printf(b, "#include <asm/orc_header.h>\n"); + buf_printf(b, "ORC_HEADER;\n"); + buf_printf(b, "#endif\n"); + buf_printf(b, "\n"); buf_printf(b, "BUILD_SALT;\n"); buf_printf(b, "BUILD_LTO_INFO;\n"); buf_printf(b, "\n"); diff --git a/scripts/orc_hash.sh b/scripts/orc_hash.sh new file mode 100644 index 000000000000..466611aa0053 --- /dev/null +++ b/scripts/orc_hash.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Copyright (c) Meta Platforms, Inc. and affiliates. + +set -e + +printf '%s' '#define ORC_HASH ' + +awk ' +/^#define ORC_(REG|TYPE)_/ { print } +/^struct orc_entry {$/ { p=1 } +p { print } +/^}/ { p=0 }' | + sha1sum | + cut -d " " -f 1 | + sed 's/\([0-9a-f]\{2\}\)/0x\1,/g' diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index d3662f4acadc..ce541b0ee1d3 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -202,19 +202,19 @@ int ima_get_action(struct mnt_idmap *idmap, struct inode *inode, allowed_algos); } -static int ima_get_verity_digest(struct integrity_iint_cache *iint, - struct ima_max_digest_data *hash) +static bool ima_get_verity_digest(struct integrity_iint_cache *iint, + struct ima_max_digest_data *hash) { - enum hash_algo verity_alg; - int ret; + enum hash_algo alg; + int digest_len; /* * On failure, 'measure' policy rules will result in a file data * hash containing 0's. */ - ret = fsverity_get_digest(iint->inode, hash->digest, &verity_alg); - if (ret) - return ret; + digest_len = fsverity_get_digest(iint->inode, hash->digest, NULL, &alg); + if (digest_len == 0) + return false; /* * Unlike in the case of actually calculating the file hash, in @@ -223,9 +223,9 @@ static int ima_get_verity_digest(struct integrity_iint_cache *iint, * mismatch between the verity algorithm and the xattr signature * algorithm, if one exists, will be detected later. */ - hash->hdr.algo = verity_alg; - hash->hdr.length = hash_digest_size[verity_alg]; - return 0; + hash->hdr.algo = alg; + hash->hdr.length = digest_len; + return true; } /* @@ -276,16 +276,9 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, memset(&hash.digest, 0, sizeof(hash.digest)); if (iint->flags & IMA_VERITY_REQUIRED) { - result = ima_get_verity_digest(iint, &hash); - switch (result) { - case 0: - break; - case -ENODATA: + if (!ima_get_verity_digest(iint, &hash)) { audit_cause = "no-verity-digest"; - break; - default: - audit_cause = "invalid-verity-digest"; - break; + result = -ENODATA; } } else if (buf) { result = ima_calc_buffer_hash(buf, size, &hash.hdr); diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c index 07efb38f58ac..f2940b29595f 100644 --- a/sound/core/seq/oss/seq_oss_midi.c +++ b/sound/core/seq/oss/seq_oss_midi.c @@ -37,6 +37,7 @@ struct seq_oss_midi { struct snd_midi_event *coder; /* MIDI event coder */ struct seq_oss_devinfo *devinfo; /* assigned OSSseq device */ snd_use_lock_t use_lock; + struct mutex open_mutex; }; @@ -172,6 +173,7 @@ snd_seq_oss_midi_check_new_port(struct snd_seq_port_info *pinfo) mdev->flags = pinfo->capability; mdev->opened = 0; snd_use_lock_init(&mdev->use_lock); + mutex_init(&mdev->open_mutex); /* copy and truncate the name of synth device */ strscpy(mdev->name, pinfo->name, sizeof(mdev->name)); @@ -322,15 +324,17 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) int perm; struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; + int err; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; + mutex_lock(&mdev->open_mutex); /* already used? */ if (mdev->opened && mdev->devinfo != dp) { - snd_use_lock_free(&mdev->use_lock); - return -EBUSY; + err = -EBUSY; + goto unlock; } perm = 0; @@ -340,14 +344,14 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) perm |= PERM_READ; perm &= mdev->flags; if (perm == 0) { - snd_use_lock_free(&mdev->use_lock); - return -ENXIO; + err = -ENXIO; + goto unlock; } /* already opened? */ if ((mdev->opened & perm) == perm) { - snd_use_lock_free(&mdev->use_lock); - return 0; + err = 0; + goto unlock; } perm &= ~mdev->opened; @@ -372,13 +376,17 @@ snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) } if (! mdev->opened) { - snd_use_lock_free(&mdev->use_lock); - return -ENXIO; + err = -ENXIO; + goto unlock; } mdev->devinfo = dp; + err = 0; + + unlock: + mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); - return 0; + return err; } /* @@ -393,10 +401,9 @@ snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; - if (! mdev->opened || mdev->devinfo != dp) { - snd_use_lock_free(&mdev->use_lock); - return 0; - } + mutex_lock(&mdev->open_mutex); + if (!mdev->opened || mdev->devinfo != dp) + goto unlock; memset(&subs, 0, sizeof(subs)); if (mdev->opened & PERM_WRITE) { @@ -415,6 +422,8 @@ snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) mdev->opened = 0; mdev->devinfo = NULL; + unlock: + mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a5d55a7063d3..dabfdecece26 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9527,6 +9527,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), @@ -9552,6 +9553,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), + SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), @@ -11740,6 +11742,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON), SND_PCI_QUIRK(0x1b35, 0x1234, "CZC ET26", ALC662_FIXUP_CZC_ET26), SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T), + SND_PCI_QUIRK(0x1c6c, 0x1239, "Compaq N14JP6-V2", ALC897_FIXUP_HP_HSMIC_VERB), #if 0 /* Below is a quirk table taken from the old code. diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 6faf4a43eaf5..144f082c63fd 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -1347,7 +1347,7 @@ static int sof_card_dai_links_create(struct device *dev, if ((SDW_PART_ID(adr_link->adr_d[i].adr) != SDW_PART_ID(adr_link->adr_d[j].adr)) || (SDW_MFG_ID(adr_link->adr_d[i].adr) != - SDW_MFG_ID(adr_link->adr_d[i].adr))) { + SDW_MFG_ID(adr_link->adr_d[j].adr))) { append_codec_type = true; goto out; } diff --git a/sound/soc/tegra/tegra_pcm.c b/sound/soc/tegra/tegra_pcm.c index 468c8e77de21..0b69cebc9a33 100644 --- a/sound/soc/tegra/tegra_pcm.c +++ b/sound/soc/tegra/tegra_pcm.c @@ -117,6 +117,9 @@ int tegra_pcm_open(struct snd_soc_component *component, return ret; } + /* Set wait time to 500ms by default */ + substream->wait_time = 500; + return 0; } EXPORT_SYMBOL_GPL(tegra_pcm_open); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index eec5232f9fb2..08bf535ed163 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -650,6 +650,10 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream) goto unlock; } + ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D0); + if (ret < 0) + goto unlock; + again: if (subs->sync_endpoint) { ret = snd_usb_endpoint_prepare(chip, subs->sync_endpoint); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 3ecd1ba7fd4b..6cf55b7f7a04 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2191,6 +2191,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x2ab6, /* T+A devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x3336, /* HEM devices */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x3353, /* Khadas devices */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x3842, /* EVGA */ diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h index c5573eaa5bb9..1c1b7550fa55 100644 --- a/tools/arch/x86/include/asm/nops.h +++ b/tools/arch/x86/include/asm/nops.h @@ -34,6 +34,8 @@ #define BYTES_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x3e,BYTES_NOP7 +#define ASM_NOP_MAX 8 + #else /* @@ -47,6 +49,9 @@ * 6: osp nopl 0x00(%eax,%eax,1) * 7: nopl 0x00000000(%eax) * 8: nopl 0x00000000(%eax,%eax,1) + * 9: cs nopl 0x00000000(%eax,%eax,1) + * 10: osp cs nopl 0x00000000(%eax,%eax,1) + * 11: osp osp cs nopl 0x00000000(%eax,%eax,1) */ #define BYTES_NOP1 0x90 #define BYTES_NOP2 0x66,BYTES_NOP1 @@ -56,6 +61,15 @@ #define BYTES_NOP6 0x66,BYTES_NOP5 #define BYTES_NOP7 0x0f,0x1f,0x80,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00 +#define BYTES_NOP9 0x2e,BYTES_NOP8 +#define BYTES_NOP10 0x66,BYTES_NOP9 +#define BYTES_NOP11 0x66,BYTES_NOP10 + +#define ASM_NOP9 _ASM_BYTES(BYTES_NOP9) +#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10) +#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11) + +#define ASM_NOP_MAX 11 #endif /* CONFIG_64BIT */ @@ -68,8 +82,6 @@ #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7) #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8) -#define ASM_NOP_MAX 8 - #ifndef __ASSEMBLY__ extern const unsigned char * const x86_nops[]; #endif diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 7c97b7391279..799ad6bb72e5 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -42,13 +42,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, struct instruction *insn, struct reloc *reloc) { - /* - * The x86 alternatives code adjusts the offsets only when it - * encounters a branch instruction at the very beginning of the - * replacement group. - */ - return insn->offset == special_alt->new_off && - (insn->type == INSN_CALL || is_jump(insn)); + return true; } /* diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 0fcf99c91400..c19b1103e4ec 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -204,7 +204,6 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__ubsan_handle_builtin_unreachable", "arch_call_rest_init", "arch_cpu_idle_dead", - "btrfs_assertfail", "cpu_bringup_and_idle", "cpu_startup_entry", "do_exit", diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index caf32a9b9608..7527f738b4a1 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ - -fsanitize=undefined +CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \ + -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray maple @@ -49,6 +49,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \ ../../../include/linux/xarray.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ + ../../../lib/radix-tree.h \ ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c new file mode 100644 index 000000000000..3afd9f775f68 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_subprogs_extable.skel.h" + +void test_subprogs_extable(void) +{ + const int read_sz = 456; + struct test_subprogs_extable *skel; + int err; + + skel = test_subprogs_extable__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + err = test_subprogs_extable__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + ASSERT_OK(trigger_module_test_read(read_sz), "trigger_read"); + + ASSERT_NEQ(skel->bss->triggered, 0, "verify at least one program ran"); + + test_subprogs_extable__detach(skel); + +cleanup: + test_subprogs_extable__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c new file mode 100644 index 000000000000..e2a21fbd4e44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} test_array SEC(".maps"); + +unsigned int triggered; + +static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return 1; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 136e5530b72c..6115520154e3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -371,4 +371,83 @@ __naked void and_then_at_fp_8(void) " ::: __clobber_all); } +SEC("xdp") +__description("32-bit spill of 64-bit reg should clear ID") +__failure __msg("math between ctx pointer and 4294967295 is not allowed") +__naked void spill_32bit_of_64bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + r1 = 0xffffffff; \ + r1 <<= 32; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 32-bit spill r1 to stack - should clear the ID! */\ + *(u32*)(r10 - 8) = r1; \ + /* 32-bit fill r2 from stack. */ \ + r2 = *(u32*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 32; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffffffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 32-bit reg should clear ID") +__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed") +__naked void spill_16bit_of_32bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + w1 = 0xffff0000; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 16-bit spill r1 to stack - should clear the ID! */\ + *(u16*)(r10 - 8) = r1; \ + /* 16-bit fill r2 from stack. */ \ + r2 = *(u16*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 16; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index d8bff2005dfc..5fd49ad0c696 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -249,7 +249,7 @@ /** * FIXTURE_SETUP() - Prepares the setup function for the fixture. - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -275,7 +275,7 @@ /** * FIXTURE_TEARDOWN() - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -388,7 +388,7 @@ if (setjmp(_metadata->env) == 0) { \ fixture_name##_setup(_metadata, &self, variant->data); \ /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ + if (!_metadata->passed || _metadata->skip) \ return; \ _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 23af4633f0f4..4f0c50c33ba7 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -5,12 +5,15 @@ LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(ARCH),) + ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +endif # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -65,7 +68,7 @@ TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) @@ -87,13 +90,13 @@ TEST_GEN_PROGS += $(BINARIES_64) endif else -ifneq (,$(findstring $(MACHINE),ppc64)) +ifneq (,$(findstring $(ARCH),ppc64)) TEST_GEN_PROGS += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs @@ -112,7 +115,7 @@ $(TEST_GEN_PROGS): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c09..ee6880ac3e5e 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -92,6 +92,13 @@ NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) +# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities @@ -1216,7 +1223,7 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" - ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -1270,9 +1277,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server @@ -2772,7 +2781,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done - ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2842,9 +2851,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh index 432fe8469851..48584a51388f 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -84,8 +84,9 @@ h2_destroy() router_rp1_200_create() { - ip link add name $rp1.200 up \ - link $rp1 addrgenmode eui64 type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 ip stats set dev $rp1.200 l3_stats on @@ -256,9 +257,11 @@ reapply_config() router_rp1_200_destroy - ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode none ip stats set dev $rp1.200 l3_stats on - ip link set dev $rp1.200 up addrgenmode eui64 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh index c5095da7f6bf..aec752a22e9e 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh @@ -93,12 +93,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index 9ff22f28032d..0cf4c47a46f9 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -90,12 +90,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 38021a0dd527..6032f9b23c4c 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 4eacdb1ab962..fa9e09ad97d9 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -55,16 +55,20 @@ __chk_nr() { local command="$1" local expected=$2 - local msg nr + local msg="$3" + local skip="${4:-SKIP}" + local nr - shift 2 - msg=$* nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + echo "[ skip ] Feature probably not supported" + else + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + fi else echo "[ ok ]" fi @@ -76,12 +80,12 @@ __chk_msk_nr() local condition=$1 shift 1 - __chk_nr "ss -inmHMN $ns | $condition" $* + __chk_nr "ss -inmHMN $ns | $condition" "$@" } chk_msk_nr() { - __chk_msk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" "$@" } wait_msk_nr() @@ -119,37 +123,26 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_msk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" "$@" } chk_msk_remote_key_nr() { - __chk_msk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" "$@" } __chk_listen() { local filter="$1" local expected=$2 + local msg="$3" - shift 2 - msg=$* - - nr=$(ss -N $ns -Ml "$filter" | grep -c LISTEN) - printf "%-50s" "$msg" - - if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt - else - echo "[ ok ]" - fi + __chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0 } chk_msk_listen() { lport=$1 - local msg="check for listen socket" # destination port search should always return empty list __chk_listen "dport $lport" 0 "listen match for dport $lport" @@ -167,10 +160,9 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 + local msg="$2" local listen_nr - shift 1 - listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -181,7 +173,7 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected $* + __chk_nr get_msk_inuse $expected "$msg" 0 } # $1: ns, $2: port diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index c1f7bac19942..773dd770a567 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -144,6 +144,7 @@ cleanup() } mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then @@ -695,6 +696,15 @@ run_test_transparent() return 0 fi + # IP(V6)_TRANSPARENT has been added after TOS support which came with + # the required infrastructure in MPTCP sockopt code. To support TOS, the + # following function has been exported (T). Not great but better than + # checking for a specific kernel version. + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then + echo "INFO: ${msg} not supported by the kernel: SKIP" + return + fi + ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { @@ -767,6 +777,11 @@ run_tests_peekmode() run_tests_mptfo() { + if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then + echo "INFO: TFO not supported by the kernel: SKIP" + return + fi + echo "INFO: with MPTFO start" ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1 @@ -787,6 +802,11 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + cat $cin $cin $cin > "$cin".disconnect # force do_transfer to cope with the multiple tranmissions diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 29f0c99d9a46..0ae8cafde439 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -25,6 +25,8 @@ capout="" ns1="" ns2="" ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) capture=0 @@ -82,7 +84,7 @@ init_partial() ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.mptcp.pm_type=0 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if [ $checksum -eq 1 ]; then @@ -140,13 +142,18 @@ cleanup_partial() check_tools() { mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip fi - if ! iptables -V &> /dev/null; then + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip fi @@ -185,6 +192,32 @@ cleanup() cleanup_partial } +# $1: msg +print_title() +{ + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" +} + +# [ $1: fail msg ] +mark_as_skipped() +{ + local msg="${1:-"Feature not supported"}" + + mptcp_lib_fail_if_expected_feature "${msg}" + + print_title "[ skip ] ${msg}" + printf "\n" +} + +# $@: condition +continue_if() +{ + if ! "${@}"; then + mark_as_skipped + return 1 + fi +} + skip_test() { if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then @@ -228,6 +261,19 @@ reset() return 0 } +# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + # $1: test name reset_with_cookies() { @@ -247,17 +293,21 @@ reset_with_add_addr_timeout() reset "${1}" || return 1 - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - ip netns exec $ns2 $tables -A OUTPUT -p tcp \ - -m tcp --tcp-option 30 \ - -m bpf --bytecode \ - "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ - -j DROP + + if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP; then + mark_as_skipped "unable to set the 'add addr' rule" + return 1 + fi } # $1: test name @@ -301,22 +351,17 @@ reset_with_allow_join_id0() # tc action pedit offset 162 out of bounds # # Netfilter is used to mark packets with enough data. -reset_with_fail() +setup_fail_rules() { - reset "${1}" || return 1 - - ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 - ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 - check_invert=1 validate_checksum=1 - local i="$2" - local ip="${3:-4}" + local i="$1" + local ip="${2:-4}" local tables - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns2 $tables \ @@ -326,15 +371,32 @@ reset_with_fail() -p tcp \ -m length --length 150:9999 \ -m statistic --mode nth --packet 1 --every 99999 \ - -j MARK --set-mark 42 || exit 1 + -j MARK --set-mark 42 || return ${ksft_skip} - tc -n $ns2 qdisc add dev ns2eth$i clsact || exit 1 + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ - index 100 || exit 1 + index 100 || return ${ksft_skip} +} + +reset_with_fail() +{ + reset_check_counter "${1}" "MPTcpExtInfiniteMapTx" || return 1 + shift + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 + + local rc=0 + setup_fail_rules "${@}" || rc=$? + + if [ ${rc} -eq ${ksft_skip} ]; then + mark_as_skipped "unable to set the 'fail' rules" + return 1 + fi } reset_with_events() @@ -349,6 +411,25 @@ reset_with_events() evts_ns2_pid=$! } +reset_with_tcp_filter() +{ + reset "${1}" || return 1 + shift + + local ns="${!1}" + local src="${2}" + local target="${3}" + + if ! ip netns exec "${ns}" ${iptables} \ + -A INPUT \ + -s "${src}" \ + -p tcp \ + -j "${target}"; then + mark_as_skipped "unable to set the filter rules" + return 1 + fi +} + fail_test() { ret=1 @@ -467,11 +548,25 @@ wait_local_port_listen() done } -rm_addr_count() +# $1: ns ; $2: counter +get_counter() { - local ns=${1} + local ns="${1}" + local counter="${2}" + local count - ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -494,11 +589,11 @@ wait_mpj() local ns="${1}" local cnt old_cnt - old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -698,15 +793,6 @@ pm_nl_check_endpoint() fi } -filter_tcp_from() -{ - local ns="${1}" - local src="${2}" - local target="${3}" - - ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" -} - do_transfer() { local listener_ns="$1" @@ -1157,12 +1243,13 @@ chk_csum_nr() fi printf "%-${nr_blank}s %s" " " "sum" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi - if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test @@ -1171,12 +1258,13 @@ chk_csum_nr() echo -n "[ ok ]" fi echo -n " - csum " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi - if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test @@ -1218,12 +1306,13 @@ chk_fail_nr() fi printf "%-${nr_blank}s %s" " " "ftx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi - if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test @@ -1233,12 +1322,13 @@ chk_fail_nr() fi echo -n " - failrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi - if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test @@ -1270,10 +1360,11 @@ chk_fclose_nr() fi printf "%-${nr_blank}s %s" " " "ctx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_tx" ] && extra_msg="$extra_msg,tx=$count" - if [ "$count" != "$fclose_tx" ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test dump_stats=1 @@ -1282,10 +1373,11 @@ chk_fclose_nr() fi echo -n " - fclzrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_rx" ] && extra_msg="$extra_msg,rx=$count" - if [ "$count" != "$fclose_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test dump_stats=1 @@ -1316,9 +1408,10 @@ chk_rst_nr() fi printf "%-${nr_blank}s %s" " " "rtx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count -lt $rst_tx ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test dump_stats=1 @@ -1327,9 +1420,10 @@ chk_rst_nr() fi echo -n " - rstrx " - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" -lt "$rst_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test dump_stats=1 @@ -1350,9 +1444,10 @@ chk_infi_nr() local dump_stats printf "%-${nr_blank}s %s" " " "itx" - count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_tx" ]; then + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test dump_stats=1 @@ -1361,9 +1456,10 @@ chk_infi_nr() fi echo -n " - infirx" - count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test dump_stats=1 @@ -1395,9 +1491,10 @@ chk_join_nr() fi printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test dump_stats=1 @@ -1407,9 +1504,10 @@ chk_join_nr() echo -n " - synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation @@ -1425,9 +1523,10 @@ chk_join_nr() fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test dump_stats=1 @@ -1459,12 +1558,12 @@ chk_stale_nr() local recover_nr printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') - [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') - [ -z "$recover_nr" ] && recover_nr=0 - if [ $stale_nr -lt $stale_min ] || + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ @@ -1500,12 +1599,12 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) printf "%-${nr_blank}s %s" " " "add" - count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test dump_stats=1 @@ -1514,9 +1613,10 @@ chk_add_nr() fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test dump_stats=1 @@ -1526,9 +1626,10 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$port_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test dump_stats=1 @@ -1537,10 +1638,10 @@ chk_add_nr() fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test @@ -1550,10 +1651,10 @@ chk_add_nr() fi echo -n " - synack" - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test @@ -1563,10 +1664,10 @@ chk_add_nr() fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test @@ -1576,10 +1677,10 @@ chk_add_nr() fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test @@ -1589,10 +1690,10 @@ chk_add_nr() fi echo -n " - ack " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test @@ -1636,9 +1737,10 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test dump_stats=1 @@ -1647,29 +1749,27 @@ chk_rm_nr() fi echo -n " - rmsf " - count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ -n "$simult" ]; then + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then local cnt suffix - cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable - [ -z "$cnt" ] && cnt=0 count=$((count + cnt)) [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo "[ ok ] $suffix" + echo -n "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test dump_stats=1 fi - return - fi - if [ "$count" != "$rm_subflow_nr" ]; then + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test dump_stats=1 @@ -1690,9 +1790,10 @@ chk_prio_nr() local dump_stats printf "%-${nr_blank}s %s" " " "ptx" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_tx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test dump_stats=1 @@ -1701,9 +1802,10 @@ chk_prio_nr() fi echo -n " - prx " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test dump_stats=1 @@ -1819,7 +1921,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + cnt=$(get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1912,23 +2014,23 @@ subflows_error_tests() fi # multiple subflows, with subflow creation error - if reset "multi subflows, with failing subflow"; then + if reset_with_tcp_filter "multi subflows, with failing subflow" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 fi # multiple subflows, with subflow timeout on MPJ - if reset "multi subflows, with subflow timeout"; then + if reset_with_tcp_filter "multi subflows, with subflow timeout" ns1 10.0.3.2 DROP && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 DROP run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 fi @@ -1936,11 +2038,11 @@ subflows_error_tests() # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - if reset "multi subflows, fair usage on close"; then + if reset_with_tcp_filter "multi subflows, fair usage on close" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & # mpj subflow will be in TW after the reset @@ -2040,11 +2142,18 @@ signal_address_tests() # the peer could possibly miss some addr notification, allow retransmission ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr 3 3 3 - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + # It is not directly linked to the commit introducing this + # symbol but for the parent one which is linked anyway. + if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + chk_join_nr 3 3 2 + chk_add_nr 4 4 + else + chk_join_nr 3 3 3 + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi fi } @@ -2285,7 +2394,12 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr 3 3 3 - chk_rm_nr 0 3 simult + + if mptcp_lib_kversion_ge 5.18; then + chk_rm_nr 0 3 simult + else + chk_rm_nr 3 3 + fi fi # addresses flush @@ -2523,7 +2637,8 @@ v4mapped_tests() mixed_tests() { - if reset "IPv4 sockets do not use IPv6 addresses"; then + if reset "IPv4 sockets do not use IPv6 addresses" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal @@ -2532,7 +2647,8 @@ mixed_tests() fi # Need an IPv6 mptcp socket to allow subflows of both families - if reset "simult IPv4 and IPv6 subflows"; then + if reset "simult IPv4 and IPv6 subflows" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.1.1 flags signal @@ -2541,7 +2657,8 @@ mixed_tests() fi # cross families subflows will not be created even in fullmesh mode - if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh @@ -2552,7 +2669,8 @@ mixed_tests() # fullmesh still tries to create all the possibly subflows with # matching family - if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2565,7 +2683,8 @@ mixed_tests() backup_tests() { # single subflow, backup - if reset "single subflow, backup"; then + if reset "single subflow, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup @@ -2575,7 +2694,8 @@ backup_tests() fi # single address, backup - if reset "single address, backup"; then + if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 @@ -2586,7 +2706,8 @@ backup_tests() fi # single address with port, backup - if reset "single address with port, backup"; then + if reset "single address with port, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 @@ -2596,14 +2717,16 @@ backup_tests() chk_prio_nr 1 1 fi - if reset "mpc backup"; then + if reset "mpc backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc backup both sides"; then + if reset "mpc backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow @@ -2611,14 +2734,16 @@ backup_tests() chk_prio_nr 1 1 fi - if reset "mpc switch to backup"; then + if reset "mpc switch to backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc switch to backup both sides"; then + if reset "mpc switch to backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup @@ -2644,38 +2769,41 @@ verify_listener_events() local family local saddr local sport + local name if [ $e_type = $LISTENER_CREATED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CREATE_LISTENER %s:%s"\ - $e_saddr $e_sport + name="LISTENER_CREATED" elif [ $e_type = $LISTENER_CLOSED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CLOSE_LISTENER %s:%s "\ - $e_saddr $e_sport + name="LISTENER_CLOSED" + else + name="$e_type" fi - type=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport" + + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + printf "[skip]: event not supported\n" + return + fi + + type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') + family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') + sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') else - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') fi if [ $type ] && [ $type = $e_type ] && [ $family ] && [ $family = $e_family ] && [ $saddr ] && [ $saddr = $e_saddr ] && [ $sport ] && [ $sport = $e_sport ]; then - stdbuf -o0 -e0 printf "[ ok ]\n" + echo "[ ok ]" return 0 fi fail_test - stdbuf -o0 -e0 printf "[fail]\n" + echo "[fail]" } add_addr_ports_tests() @@ -2981,7 +3109,8 @@ fullmesh_tests() fi # set fullmesh flag - if reset "set fullmesh flag test"; then + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -2991,7 +3120,8 @@ fullmesh_tests() fi # set nofullmesh flag - if reset "set nofullmesh flag test"; then + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 @@ -3001,7 +3131,8 @@ fullmesh_tests() fi # set backup,fullmesh flags - if reset "set backup,fullmesh flags test"; then + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -3012,7 +3143,8 @@ fullmesh_tests() fi # set nobackup,nofullmesh flags - if reset "set nobackup,nofullmesh flags test"; then + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh @@ -3025,14 +3157,14 @@ fullmesh_tests() fastclose_tests() { - if reset "fastclose test"; then + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client chk_join_nr 0 0 0 chk_fclose_nr 1 1 chk_rst_nr 1 1 invert fi - if reset "fastclose server test"; then + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert @@ -3070,7 +3202,8 @@ fail_tests() userspace_tests() { # userspace pm type prevents add_addr - if reset "userspace pm type prevents add_addr"; then + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3081,7 +3214,8 @@ userspace_tests() fi # userspace pm type does not echo add_addr without daemon - if reset "userspace pm no echo w/o daemon"; then + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3092,7 +3226,8 @@ userspace_tests() fi # userspace pm type rejects join - if reset "userspace pm type rejects join"; then + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3102,7 +3237,8 @@ userspace_tests() fi # userspace pm type does not send join - if reset "userspace pm type does not send join"; then + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3112,7 +3248,8 @@ userspace_tests() fi # userspace pm type prevents mp_prio - if reset "userspace pm type prevents mp_prio"; then + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3123,7 +3260,8 @@ userspace_tests() fi # userspace pm type prevents rm_addr - if reset "userspace pm type prevents rm_addr"; then + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 @@ -3135,7 +3273,8 @@ userspace_tests() fi # userspace pm add & remove address - if reset_with_events "userspace pm add & remove address"; then + if reset_with_events "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow @@ -3146,7 +3285,8 @@ userspace_tests() fi # userspace pm create destroy subflow - if reset_with_events "userspace pm create destroy subflow"; then + if reset_with_events "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow @@ -3158,8 +3298,10 @@ userspace_tests() endpoint_tests() { + # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr - if reset "implicit EP"; then + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -3179,7 +3321,8 @@ endpoint_tests() kill_tests_wait fi - if reset "delete and re-add"; then + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 3286536b79d5..f32045b23b89 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -38,3 +38,67 @@ mptcp_lib_check_mptcp() { exit ${KSFT_SKIP} fi } + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index ae61f39556ca..b35148edbf02 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -87,6 +87,10 @@ struct so_state { uint64_t tcpi_rcv_delta; }; +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + static void die_perror(const char *msg) { perror(msg); @@ -349,13 +353,14 @@ static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); assert(olen <= sizeof(ti)); - assert(ti.d.size_user == ti.d.size_kernel); - assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.size_kernel > 0); + assert(ti.d.size_user == + MIN(ti.d.size_kernel, sizeof(struct tcp_info))); assert(ti.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct tcp_info)); + assert(olen == ti.d.size_user); if (ti.ti[0].tcpi_bytes_sent == w && ti.ti[0].tcpi_bytes_received == r) @@ -401,13 +406,14 @@ static void do_getsockopt_subflow_addrs(int fd) die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); assert(olen <= sizeof(addrs)); - assert(addrs.d.size_user == addrs.d.size_kernel); - assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.size_kernel > 0); + assert(addrs.d.size_user == + MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs))); assert(addrs.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct mptcp_subflow_addrs)); + assert(olen == addrs.d.size_user); llen = sizeof(local); ret = getsockname(fd, (struct sockaddr *)&local, &llen); diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index ff5adbb9c7f2..f295a371ff14 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -87,6 +87,7 @@ cleanup() } mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then @@ -186,9 +187,14 @@ do_transfer() local_addr="0.0.0.0" fi + cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ ${local_addr} < "$sin" > "$sout" & local spid=$! @@ -196,7 +202,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ $connect_addr < "$cin" > "$cout" & local cpid=$! @@ -253,6 +259,11 @@ do_mptcp_sockopt_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? @@ -307,6 +318,11 @@ do_tcpinq_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + local args for args in "-t tcp" "-r tcp"; do do_tcpinq_test $args diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 32f7533e0919..d02e0d63a8f9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -73,8 +73,12 @@ check() } check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 subflows 2" "defaults limits" +fi ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -121,12 +125,10 @@ ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "rcv addrs above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "subflows above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 @@ -176,14 +178,19 @@ subflow,backup 10.0.1.1" "set flags (backup)" ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,fullmesh 10.0.1.1" " (fullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nofullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi exit $ret diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 8092399d911f..98d9e4d2d3fc 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -4,11 +4,17 @@ . "$(dirname "${0}")/mptcp_lib.sh" mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" - exit 1 + exit ${KSFT_SKIP} fi ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED @@ -909,6 +915,11 @@ test_listener() { print_title "Listener tests" + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + stdbuf -o0 -e0 printf "LISTENER events \t[SKIP] Not supported\n" + return + fi + # Capture events on the network namespace running the client :>$client_evts diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247..ff36844d14b4 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,8 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +static int fips_enabled; + struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; @@ -235,7 +237,7 @@ FIXTURE_VARIANT(tls) { uint16_t tls_version; uint16_t cipher_type; - bool nopad; + bool nopad, fips_non_compliant; }; FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) @@ -254,24 +256,28 @@ FIXTURE_VARIANT_ADD(tls, 12_chacha) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_chacha) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_GCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_CCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) @@ -311,6 +317,9 @@ FIXTURE_SETUP(tls) int one = 1; int ret; + if (fips_enabled && variant->fips_non_compliant) + SKIP(return, "Unsupported cipher in FIPS mode"); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); @@ -1865,4 +1874,17 @@ TEST(prequeue) { close(cfd); } +static void __attribute__((constructor)) fips_check(void) { + int res; + FILE *f; + + f = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (f) { + res = fscanf(f, "%d", &fips_enabled); + if (res != 1) + ksft_print_msg("ERROR: Couldn't read /proc/sys/crypto/fips_enabled\n"); + fclose(f); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh index 184da81f554f..452638ae8aed 100755 --- a/tools/testing/selftests/net/vrf-xfrm-tests.sh +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -264,60 +264,60 @@ setup_xfrm() ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ${devarg} ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ${devarg} ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} } diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 198ad5f32187..cfa9562f3cd8 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -502,11 +502,11 @@ int main(int argc, char *argv[]) interval = t2 - t1; offset = (t2 + t1) / 2 - tp; - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i)->sec, (pct+2*i)->nsec); - printf("phc time: %lld.%u\n", + printf("phc time: %lld.%09u\n", (pct+2*i+1)->sec, (pct+2*i+1)->nsec); - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i+2)->sec, (pct+2*i+2)->nsec); printf("system/phc clock time offset is %" PRId64 " ns\n" "system clock time delay is %" PRId64 " ns\n", diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 4638c63a339f..6e73b09c20c8 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -6,20 +6,18 @@ CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_NAT=m +CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y # # Queueing/Scheduling # -CONFIG_NET_SCH_ATM=m CONFIG_NET_SCH_CAKE=m -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m @@ -57,8 +55,6 @@ CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json index ba2f5e79cdbf..e21c7f22c6d4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json @@ -58,10 +58,10 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 10", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 100", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 10ms", + "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 100ms", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root", diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index afb0cd86fa3d..eb357bd7923c 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -2,5 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 modprobe netdevsim +modprobe sch_teql ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 8879a7b04c6a..d6979a48478f 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,42 +16,140 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; -const char *clear = "!u:__test_event"; +const char *abi_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; -static int Append(const char *value) +static bool wait_for_delete(void) { - int fd = open(dyn_file, O_RDWR | O_APPEND); - int ret = write(fd, value, strlen(value)); + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + +static int reg_event(int fd, int *check, int bit, const char *value) +{ + struct user_reg reg = {0}; + + reg.size = sizeof(reg); + reg.name_args = (__u64)value; + reg.enable_bit = bit; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); + + if (ioctl(fd, DIAG_IOCSREG, ®) == -1) + return -1; + + return 0; +} + +static int unreg_event(int fd, int *check, int bit) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = bit; + unreg.disable_addr = (__u64)check; + + return ioctl(fd, DIAG_IOCSUNREG, &unreg); +} + +static int parse(int *check, const char *value) +{ + int fd = open(abi_file, O_RDWR); + int ret; + + if (fd == -1) + return -1; + + /* Until we have persist flags via dynamic events, use the base name */ + if (value[0] != 'u' || value[1] != ':') { + close(fd); + return -1; + } + + ret = reg_event(fd, check, 31, value + 2); + + if (ret != -1) { + if (unreg_event(fd, check, 31) == -1) + printf("WARN: Couldn't unreg event\n"); + } close(fd); + return ret; } -#define CLEAR() \ +static int check_match(int *check, const char *first, const char *second, bool *match) +{ + int fd = open(abi_file, O_RDWR); + int ret = -1; + + if (fd == -1) + return -1; + + if (reg_event(fd, check, 31, first) == -1) + goto cleanup; + + if (reg_event(fd, check, 30, second) == -1) { + if (errno == EADDRINUSE) { + /* Name is in use, with different fields */ + *match = false; + ret = 0; + } + + goto cleanup; + } + + *match = true; + ret = 0; +cleanup: + unreg_event(fd, check, 31); + unreg_event(fd, check, 30); + + close(fd); + + wait_for_delete(); + + return ret; +} + +#define TEST_MATCH(x, y) \ do { \ - int ret = Append(clear); \ - if (ret == -1) \ - ASSERT_EQ(ENOENT, errno); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(true, match); \ } while (0) -#define TEST_PARSE(x) \ +#define TEST_NMATCH(x, y) \ do { \ - ASSERT_NE(-1, Append(x)); \ - CLEAR(); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(false, match); \ } while (0) -#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) +#define TEST_PARSE(x) ASSERT_NE(-1, parse(&self->check, x)) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, parse(&self->check, x)) FIXTURE(user) { + int check; }; FIXTURE_SETUP(user) { - CLEAR(); } FIXTURE_TEARDOWN(user) { - CLEAR(); + wait_for_delete(); } TEST_F(user, basic_types) { @@ -95,33 +193,30 @@ TEST_F(user, size_types) { TEST_NPARSE("u:__test_event char a 20"); } -TEST_F(user, flags) { - /* Should work */ - TEST_PARSE("u:__test_event:BPF_ITER u32 a"); - /* Forward compat */ - TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); -} - TEST_F(user, matching) { - /* Register */ - ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); - /* Should not match */ - TEST_NPARSE("!u:__test_event struct custom b"); - /* Should match */ - TEST_PARSE("!u:__test_event struct custom a"); - /* Multi field reg */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Non matching cases */ - TEST_NPARSE("!u:__test_event u32 a"); - TEST_NPARSE("!u:__test_event u32 b"); - TEST_NPARSE("!u:__test_event u32 a; u32 "); - TEST_NPARSE("!u:__test_event u32 a; u32 a"); - /* Matching case */ - TEST_PARSE("!u:__test_event u32 a; u32 b"); - /* Register */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Ensure trailing semi-colon case */ - TEST_PARSE("!u:__test_event u32 a; u32 b;"); + /* Single name matches */ + TEST_MATCH("__test_event u32 a", + "__test_event u32 a"); + + /* Multiple names match */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b"); + + /* Multiple names match with dangling ; */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b;"); + + /* Single name doesn't match */ + TEST_NMATCH("__test_event u32 a", + "__test_event u32 b"); + + /* Multiple names don't match */ + TEST_NMATCH("__test_event u32 a; u32 b", + "__test_event u32 b; u32 a"); + + /* Types don't match */ + TEST_NMATCH("__test_event u64 a; u64 b", + "__test_event u32 a; u32 b"); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 7c99cef94a65..eb6904d89f14 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -102,30 +102,56 @@ err: return -1; } +static bool wait_for_delete(void) +{ + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + static int clear(int *check) { struct user_unreg unreg = {0}; + int fd; unreg.size = sizeof(unreg); unreg.disable_bit = 31; unreg.disable_addr = (__u64)check; - int fd = open(data_file, O_RDWR); + fd = open(data_file, O_RDWR); if (fd == -1) return -1; if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) if (errno != ENOENT) - return -1; - - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) - return -1; + goto fail; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) { + if (errno == EBUSY) { + if (!wait_for_delete()) + goto fail; + } else if (errno != ENOENT) + goto fail; + } close(fd); return 0; +fail: + close(fd); + + return -1; } static int check_print_fmt(const char *event, const char *expected, int *check) @@ -155,9 +181,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); - close(fd); - if (ret != 0) { + close(fd); printf("Reg failed in fmt\n"); return ret; } @@ -165,6 +190,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + close(fd); + if (ret != 0) return ret; @@ -228,6 +255,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Multiple registers to same name but different args should fail */ + reg.enable_bit = 29; + reg.name_args = (__u64)"__test_event u32 field1;"; + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); @@ -250,10 +283,10 @@ TEST_F(user, register_events) { unreg.disable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); - /* Delete should work only after close and unregister */ + /* Delete should have been auto-done after close and unregister */ close(self->data_fd); - self->data_fd = open(data_file, O_RDWR); - ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + ASSERT_EQ(true, wait_for_delete()); } TEST_F(user, write_events) { @@ -310,6 +343,39 @@ TEST_F(user, write_events) { ASSERT_EQ(EINVAL, errno); } +TEST_F(user, write_empty_events) { + struct user_reg reg = {0}; + struct iovec io[1]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Event should now be enabled */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + TEST_F(user, write_fault) { struct user_reg reg = {0}; struct iovec io[2]; diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index a070258d4449..8b09be566fa2 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -81,6 +81,32 @@ static int get_offset(void) return offset; } +static int clear(int *check) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + FIXTURE(user) { int data_fd; int check; @@ -93,6 +119,9 @@ FIXTURE_SETUP(user) { FIXTURE_TEARDOWN(user) { close(self->data_fd); + + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, perf_write) { @@ -160,6 +189,59 @@ TEST_F(user, perf_write) { ASSERT_EQ(0, self->check); } +TEST_F(user, perf_empty_events) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); + int id, fd; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, ®.write_index, + sizeof(reg.write_index))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 479802a892d4..65f94f592ff8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -686,6 +686,24 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn return __kvm_handle_hva_range(kvm, &range); } + +static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +{ + /* + * Skipping invalid memslots is correct if and only change_pte() is + * surrounded by invalidate_range_{start,end}(), which is currently + * guaranteed by the primary MMU. If that ever changes, KVM needs to + * unmap the memslot instead of skipping the memslot to ensure that KVM + * doesn't hold references to the old PFN. + */ + WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count)); + + if (range->slot->flags & KVM_MEMSLOT_INVALID) + return false; + + return kvm_set_spte_gfn(kvm, range); +} + static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address, @@ -707,7 +725,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, if (!READ_ONCE(kvm->mmu_invalidate_in_progress)) return; - kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn); + kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn); } void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start, |