diff options
Diffstat (limited to 'arch/riscv')
83 files changed, 2587 insertions, 729 deletions
diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild index afa83e307a2e..d25ad1c19f88 100644 --- a/arch/riscv/Kbuild +++ b/arch/riscv/Kbuild @@ -5,7 +5,7 @@ obj-$(CONFIG_BUILTIN_DTB) += boot/dts/ obj-y += errata/ obj-$(CONFIG_KVM) += kvm/ -obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/ +obj-$(CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY) += purgatory/ # for cleaning subdir- += boot diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 4c07b9189c86..5138dce1a0b4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -35,6 +35,7 @@ config RISCV select ARCH_HAS_SET_MEMORY if MMU select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL + select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_VDSO_DATA @@ -42,18 +43,20 @@ config RISCV select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_CFI_CLANG select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_SUPPORTS_PER_VMA_LOCK if MMU select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USES_CFI_TRAPS if CFI_CLANG select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL - select ARCH_WANT_OPTIMIZE_VMEMMAP + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU @@ -62,6 +65,7 @@ config RISCV select COMMON_CLK select CPU_PM if CPU_IDLE || HIBERNATION select EDAC_SUPPORT + select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP @@ -130,6 +134,7 @@ config RISCV select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_POSIX_CPU_TIMERS_TASK_WORK + select HAVE_PREEMPT_DYNAMIC_KEY if !XIP_KERNEL select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RETHOOK if !XIP_KERNEL select HAVE_RSEQ @@ -267,6 +272,7 @@ config RISCV_DMA_NONCOHERENT select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB select DMA_DIRECT_REMAP config AS_HAS_INSN @@ -570,24 +576,30 @@ config TOOLCHAIN_HAS_ZIHINTPAUSE config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI def_bool y # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc - depends on AS_IS_GNU && AS_VERSION >= 23800 - help - Newer binutils versions default to ISA spec version 20191213 which - moves some instructions from the I extension to the Zicsr and Zifencei - extensions. + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd + depends on AS_IS_GNU && AS_VERSION >= 23600 + help + Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer + 20191213 version, which moves some instructions from the I extension to + the Zicsr and Zifencei extensions. This requires explicitly specifying + Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr + and Zifencei are supported in binutils from version 2.36 onwards. + To make life easier, and avoid forcing toolchains that default to a + newer ISA spec to version 2.2, relax the check to binutils >= 2.36. + For clang < 17 or GCC < 11.3.0, for which this is not possible or need + special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC. config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 - depends on CC_IS_CLANG && CLANG_VERSION < 170000 + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300) help - Certain versions of clang do not support zicsr and zifencei via -march - but newer versions of binutils require it for the reasons noted in the - help text of CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI. This - option causes an older ISA spec compatible with these older versions - of clang to be passed to GAS, which has the same result as passing zicsr - and zifencei to -march. + Certain versions of clang and GCC do not support zicsr and zifencei via + -march. This option causes an older ISA spec compatible with these older + versions of clang and GCC to be passed to GAS, which has the same result + as passing zicsr and zifencei to -march. config FPU bool "FPU support" @@ -650,48 +662,30 @@ config RISCV_BOOT_SPINWAIT If unsure what to do here, say N. -config KEXEC - bool "Kexec system call" - depends on MMU +config ARCH_SUPPORTS_KEXEC + def_bool MMU + +config ARCH_SELECTS_KEXEC + def_bool y + depends on KEXEC select HOTPLUG_CPU if SMP - select KEXEC_CORE - help - kexec is a system call that implements the ability to shutdown your - current kernel, and to start another kernel. It is like a reboot - but it is independent of the system firmware. And like a reboot - you can start any kernel with it, not just Linux. - The name comes from the similarity to the exec system call. +config ARCH_SUPPORTS_KEXEC_FILE + def_bool 64BIT && MMU -config KEXEC_FILE - bool "kexec file based systmem call" - depends on 64BIT && MMU +config ARCH_SELECTS_KEXEC_FILE + def_bool y + depends on KEXEC_FILE select HAVE_IMA_KEXEC if IMA - select KEXEC_CORE select KEXEC_ELF - help - This is new version of kexec system call. This system call is - file based and takes file descriptors as system call argument - for kernel and initramfs as opposed to list of segments as - accepted by previous system call. - If you don't know what to do here, say Y. - -config ARCH_HAS_KEXEC_PURGATORY +config ARCH_SUPPORTS_KEXEC_PURGATORY def_bool KEXEC_FILE depends on CRYPTO=y depends on CRYPTO_SHA256=y -config CRASH_DUMP - bool "Build kdump crash kernel" - help - Generate crash dump after being started by kexec. This should - be normally only set in special crash dump kernels which are - loaded in the main kernel with kexec-tools into a specially - reserved region and then later executed after a crash by - kdump/kexec. - - For more details see Documentation/admin-guide/kdump/kdump.rst +config ARCH_SUPPORTS_CRASH_DUMP + def_bool y config COMPAT bool "Kernel support for 32-bit U-mode" @@ -848,6 +842,24 @@ config XIP_PHYS_ADDR be linked for and stored to. This address is dependent on your own flash usage. +config RISCV_ISA_FALLBACK + bool "Permit falling back to parsing riscv,isa for extension support by default" + default y + help + Parsing the "riscv,isa" devicetree property has been deprecated and + replaced by a list of explicitly defined strings. For compatibility + with existing platforms, the kernel will fall back to parsing the + "riscv,isa" property if the replacements are not found. + + Selecting N here will result in a kernel that does not use the + fallback, unless the commandline "riscv_isa_fallback" parameter is + present. + + Please see the dt-binding, located at + Documentation/devicetree/bindings/riscv/extensions.yaml for details + on the replacement properties, "riscv,isa-base" and + "riscv,isa-extensions". + endmenu # "Boot options" config BUILTIN_DTB diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6ec6d52a4180..1329e060c548 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -87,9 +87,6 @@ endif ifeq ($(CONFIG_CMODEL_MEDANY),y) KBUILD_CFLAGS += -mcmodel=medany endif -ifeq ($(CONFIG_PERF_EVENTS),y) - KBUILD_CFLAGS += -fno-omit-frame-pointer -endif # Avoid generating .eh_frame sections. KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi index 1bb1e5cae602..822f022eec2d 100644 --- a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi +++ b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi @@ -53,6 +53,18 @@ #interrupt-cells = <3>; /omit-if-no-ref/ + can0_pins: can0-pins { + pins = "PB2", "PB3"; + function = "can0"; + }; + + /omit-if-no-ref/ + can1_pins: can1-pins { + pins = "PB4", "PB5"; + function = "can1"; + }; + + /omit-if-no-ref/ clk_pg11_pin: clk-pg11-pin { pins = "PG11"; function = "clk"; @@ -144,6 +156,16 @@ #reset-cells = <1>; }; + gpadc: adc@2009000 { + compatible = "allwinner,sun20i-d1-gpadc"; + reg = <0x2009000 0x400>; + clocks = <&ccu CLK_BUS_GPADC>; + resets = <&ccu RST_BUS_GPADC>; + interrupts = <SOC_PERIPHERAL_IRQ(57) IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + #io-channel-cells = <1>; + }; + dmic: dmic@2031000 { compatible = "allwinner,sun20i-d1-dmic", "allwinner,sun50i-h6-dmic"; @@ -346,6 +368,28 @@ #size-cells = <0>; }; + can0: can@2504000 { + compatible = "allwinner,sun20i-d1-can"; + reg = <0x02504000 0x400>; + interrupts = <SOC_PERIPHERAL_IRQ(21) IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_CAN0>; + resets = <&ccu RST_BUS_CAN0>; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + status = "disabled"; + }; + + can1: can@2504400 { + compatible = "allwinner,sun20i-d1-can"; + reg = <0x02504400 0x400>; + interrupts = <SOC_PERIPHERAL_IRQ(22) IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_CAN1>; + resets = <&ccu RST_BUS_CAN1>; + pinctrl-names = "default"; + pinctrl-0 = <&can1_pins>; + status = "disabled"; + }; + syscon: syscon@3000000 { compatible = "allwinner,sun20i-d1-system-control"; reg = <0x3000000 0x1000>; diff --git a/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi index d6f18754eb5d..c62debc7ca7e 100644 --- a/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi +++ b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi @@ -22,6 +22,7 @@ status = "disabled"; }; +#if (!SW_ET0_EN_N) ð0 { status = "disabled"; @@ -30,6 +31,7 @@ /delete-property/ interrupts; }; }; +#endif ð1 { status = "disabled"; diff --git a/arch/riscv/boot/dts/starfive/Makefile b/arch/riscv/boot/dts/starfive/Makefile index 170956846d49..0141504c0f5c 100644 --- a/arch/riscv/boot/dts/starfive/Makefile +++ b/arch/riscv/boot/dts/starfive/Makefile @@ -1,4 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 +# Enables support for device-tree overlays +DTC_FLAGS_jh7100-beaglev-starlight := -@ +DTC_FLAGS_jh7100-starfive-visionfive-v1 := -@ +DTC_FLAGS_jh7110-starfive-visionfive-2-v1.2a := -@ +DTC_FLAGS_jh7110-starfive-visionfive-2-v1.3b := -@ + dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-beaglev-starlight.dtb dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-starfive-visionfive-v1.dtb diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi index 4218621ea3b9..35ab54fb235f 100644 --- a/arch/riscv/boot/dts/starfive/jh7100.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi @@ -80,6 +80,31 @@ }; }; + thermal-zones { + cpu-thermal { + polling-delay-passive = <250>; + polling-delay = <15000>; + + thermal-sensors = <&sfctemp>; + + trips { + cpu_alert0 { + /* milliCelsius */ + temperature = <75000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu_crit { + /* milliCelsius */ + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; + osc_sys: osc_sys { compatible = "fixed-clock"; #clock-cells = <0>; @@ -248,5 +273,17 @@ resets = <&rstgen JH7100_RSTN_WDTIMER_APB>, <&rstgen JH7100_RSTN_WDT>; }; + + sfctemp: temperature-sensor@124a0000 { + compatible = "starfive,jh7100-temp"; + reg = <0x0 0x124a0000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_TEMP_SENSE>, + <&clkgen JH7100_CLK_TEMP_APB>; + clock-names = "sense", "bus"; + resets = <&rstgen JH7100_RSTN_TEMP_SENSE>, + <&rstgen JH7100_RSTN_TEMP_APB>; + reset-names = "sense", "bus"; + #thermal-sensor-cells = <0>; + }; }; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts index 4af3300f3cf3..205a13d8c8b1 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts @@ -11,3 +11,16 @@ model = "StarFive VisionFive 2 v1.2A"; compatible = "starfive,visionfive-2-v1.2a", "starfive,jh7110"; }; + +&gmac1 { + phy-mode = "rmii"; + assigned-clocks = <&syscrg JH7110_SYSCLK_GMAC1_TX>, + <&syscrg JH7110_SYSCLK_GMAC1_RX>; + assigned-clock-parents = <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>, + <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>; +}; + +&phy0 { + rx-internal-delay-ps = <1900>; + tx-internal-delay-ps = <1350>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts index 9230cc3d8946..d4ea4a2c0b9b 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts @@ -11,3 +11,34 @@ model = "StarFive VisionFive 2 v1.3B"; compatible = "starfive,visionfive-2-v1.3b", "starfive,jh7110"; }; + +&gmac0 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; +}; + +&gmac1 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&syscrg JH7110_SYSCLK_GMAC1_TX>; + assigned-clock-parents = <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>; +}; + +&phy0 { + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; +}; + +&phy1 { + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-100-inverted; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + rx-internal-delay-ps = <300>; + tx-internal-delay-ps = <0>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index fa0061eb33a7..d79f94432b27 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -11,10 +11,14 @@ / { aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; i2c0 = &i2c0; i2c2 = &i2c2; i2c5 = &i2c5; i2c6 = &i2c6; + mmc0 = &mmc0; + mmc1 = &mmc1; serial0 = &uart0; }; @@ -38,6 +42,10 @@ }; }; +&dvp_clk { + clock-frequency = <74250000>; +}; + &gmac0_rgmii_rxin { clock-frequency = <125000000>; }; @@ -54,6 +62,10 @@ clock-frequency = <50000000>; }; +&hdmitx0_pixelclk { + clock-frequency = <297000000>; +}; + &i2srx_bclk_ext { clock-frequency = <12288000>; }; @@ -86,6 +98,38 @@ clock-frequency = <49152000>; }; +&gmac0 { + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; +}; + +&gmac1 { + phy-handle = <&phy1>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy1: ethernet-phy@1 { + reg = <0>; + }; + }; +}; + &i2c0 { clock-frequency = <100000>; i2c-sda-hold-time-ns = <300>; @@ -123,12 +167,28 @@ #interrupt-cells = <1>; regulators { + vcc_3v3: dcdc1 { + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc_3v3"; + }; + vdd_cpu: dcdc2 { regulator-always-on; regulator-min-microvolt = <500000>; regulator-max-microvolt = <1540000>; regulator-name = "vdd-cpu"; }; + + emmc_vdd: aldo4 { + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-name = "emmc_vdd"; + }; }; }; }; @@ -143,6 +203,83 @@ status = "okay"; }; +&mmc0 { + max-frequency = <100000000>; + bus-width = <8>; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + non-removable; + cap-mmc-hw-reset; + post-power-on-delay-ms = <200>; + pinctrl-names = "default"; + pinctrl-0 = <&mmc0_pins>; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; + status = "okay"; +}; + +&mmc1 { + max-frequency = <100000000>; + bus-width = <4>; + no-sdio; + no-mmc; + broken-cd; + cap-sd-highspeed; + post-power-on-delay-ms = <200>; + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; + status = "okay"; +}; + +&qspi { + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + nor_flash: flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + cdns,read-delay = <5>; + spi-max-frequency = <12000000>; + cdns,tshsl-ns = <1>; + cdns,tsd2d-ns = <1>; + cdns,tchsh-ns = <1>; + cdns,tslch-ns = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + spl@0 { + reg = <0x0 0x80000>; + }; + uboot-env@f0000 { + reg = <0xf0000 0x10000>; + }; + uboot@100000 { + reg = <0x100000 0x400000>; + }; + reserved-data@600000 { + reg = <0x600000 0x1000000>; + }; + }; + }; +}; + +&spi0 { + pinctrl-names = "default"; + pinctrl-0 = <&spi0_pins>; + status = "okay"; + + spi_dev0: spi@0 { + compatible = "rohm,dh2228fv"; + reg = <0>; + spi-max-frequency = <10000000>; + }; +}; + &sysgpio { i2c0_pins: i2c0-0 { i2c-pins { @@ -200,6 +337,109 @@ }; }; + mmc0_pins: mmc0-0 { + rst-pins { + pinmux = <GPIOMUX(62, GPOUT_SYS_SDIO0_RST, + GPOEN_ENABLE, + GPI_NONE)>; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mmc-pins { + pinmux = <PINMUX(64, 0)>, + <PINMUX(65, 0)>, + <PINMUX(66, 0)>, + <PINMUX(67, 0)>, + <PINMUX(68, 0)>, + <PINMUX(69, 0)>, + <PINMUX(70, 0)>, + <PINMUX(71, 0)>, + <PINMUX(72, 0)>, + <PINMUX(73, 0)>; + bias-pull-up; + drive-strength = <12>; + input-enable; + }; + }; + + mmc1_pins: mmc1-0 { + clk-pins { + pinmux = <GPIOMUX(10, GPOUT_SYS_SDIO1_CLK, + GPOEN_ENABLE, + GPI_NONE)>; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mmc-pins { + pinmux = <GPIOMUX(9, GPOUT_SYS_SDIO1_CMD, + GPOEN_SYS_SDIO1_CMD, + GPI_SYS_SDIO1_CMD)>, + <GPIOMUX(11, GPOUT_SYS_SDIO1_DATA0, + GPOEN_SYS_SDIO1_DATA0, + GPI_SYS_SDIO1_DATA0)>, + <GPIOMUX(12, GPOUT_SYS_SDIO1_DATA1, + GPOEN_SYS_SDIO1_DATA1, + GPI_SYS_SDIO1_DATA1)>, + <GPIOMUX(7, GPOUT_SYS_SDIO1_DATA2, + GPOEN_SYS_SDIO1_DATA2, + GPI_SYS_SDIO1_DATA2)>, + <GPIOMUX(8, GPOUT_SYS_SDIO1_DATA3, + GPOEN_SYS_SDIO1_DATA3, + GPI_SYS_SDIO1_DATA3)>; + bias-pull-up; + drive-strength = <12>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + spi0_pins: spi0-0 { + mosi-pins { + pinmux = <GPIOMUX(52, GPOUT_SYS_SPI0_TXD, + GPOEN_ENABLE, + GPI_NONE)>; + bias-disable; + input-disable; + input-schmitt-disable; + }; + + miso-pins { + pinmux = <GPIOMUX(53, GPOUT_LOW, + GPOEN_DISABLE, + GPI_SYS_SPI0_RXD)>; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + + sck-pins { + pinmux = <GPIOMUX(48, GPOUT_SYS_SPI0_CLK, + GPOEN_ENABLE, + GPI_SYS_SPI0_CLK)>; + bias-disable; + input-disable; + input-schmitt-disable; + }; + + ss-pins { + pinmux = <GPIOMUX(48, GPOUT_SYS_SPI0_FSS, + GPOEN_ENABLE, + GPI_SYS_SPI0_FSS)>; + bias-disable; + input-disable; + input-schmitt-disable; + }; + }; + uart0_pins: uart0-0 { tx-pins { pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX, @@ -223,6 +463,46 @@ slew-rate = <0>; }; }; + + tdm_pins: tdm-0 { + tx-pins { + pinmux = <GPIOMUX(44, GPOUT_SYS_TDM_TXD, + GPOEN_ENABLE, + GPI_NONE)>; + bias-pull-up; + drive-strength = <2>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pinmux = <GPIOMUX(61, GPOUT_HIGH, + GPOEN_DISABLE, + GPI_SYS_TDM_RXD)>; + input-enable; + }; + + sync-pins { + pinmux = <GPIOMUX(63, GPOUT_HIGH, + GPOEN_DISABLE, + GPI_SYS_TDM_SYNC)>; + input-enable; + }; + + pcmclk-pins { + pinmux = <GPIOMUX(38, GPOUT_HIGH, + GPOEN_DISABLE, + GPI_SYS_TDM_CLK)>; + input-enable; + }; + }; +}; + +&tdm { + pinctrl-names = "default"; + pinctrl-0 = <&tdm_pins>; + status = "okay"; }; &uart0 { @@ -231,6 +511,10 @@ status = "okay"; }; +&usb0 { + dr_mode = "peripheral"; +}; + &U74_1 { cpu-supply = <&vdd_cpu>; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi index ec2e70011a73..e85464c328d0 100644 --- a/arch/riscv/boot/dts/starfive/jh7110.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi @@ -6,7 +6,9 @@ /dts-v1/; #include <dt-bindings/clock/starfive,jh7110-crg.h> +#include <dt-bindings/power/starfive,jh7110-pmu.h> #include <dt-bindings/reset/starfive,jh7110-crg.h> +#include <dt-bindings/thermal/thermal.h> / { compatible = "starfive,jh7110"; @@ -56,6 +58,7 @@ operating-points-v2 = <&cpu_opp>; clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; clock-names = "cpu"; + #cooling-cells = <2>; cpu1_intc: interrupt-controller { compatible = "riscv,cpu-intc"; @@ -85,6 +88,7 @@ operating-points-v2 = <&cpu_opp>; clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; clock-names = "cpu"; + #cooling-cells = <2>; cpu2_intc: interrupt-controller { compatible = "riscv,cpu-intc"; @@ -114,6 +118,7 @@ operating-points-v2 = <&cpu_opp>; clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; clock-names = "cpu"; + #cooling-cells = <2>; cpu3_intc: interrupt-controller { compatible = "riscv,cpu-intc"; @@ -143,6 +148,7 @@ operating-points-v2 = <&cpu_opp>; clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; clock-names = "cpu"; + #cooling-cells = <2>; cpu4_intc: interrupt-controller { compatible = "riscv,cpu-intc"; @@ -197,6 +203,47 @@ }; }; + thermal-zones { + cpu-thermal { + polling-delay-passive = <250>; + polling-delay = <15000>; + + thermal-sensors = <&sfctemp>; + + cooling-maps { + map0 { + trip = <&cpu_alert0>; + cooling-device = + <&U74_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu_alert0: cpu_alert0 { + /* milliCelsius */ + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu_crit { + /* milliCelsius */ + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; + + dvp_clk: dvp-clock { + compatible = "fixed-clock"; + clock-output-names = "dvp_clk"; + #clock-cells = <0>; + }; gmac0_rgmii_rxin: gmac0-rgmii-rxin-clock { compatible = "fixed-clock"; clock-output-names = "gmac0_rgmii_rxin"; @@ -221,6 +268,12 @@ #clock-cells = <0>; }; + hdmitx0_pixelclk: hdmitx0-pixel-clock { + compatible = "fixed-clock"; + clock-output-names = "hdmitx0_pixelclk"; + #clock-cells = <0>; + }; + i2srx_bclk_ext: i2srx-bclk-ext-clock { compatible = "fixed-clock"; clock-output-names = "i2srx_bclk_ext"; @@ -263,6 +316,13 @@ #clock-cells = <0>; }; + stmmac_axi_setup: stmmac-axi-config { + snps,lpi_en; + snps,wr_osr_lmt = <15>; + snps,rd_osr_lmt = <15>; + snps,blen = <256 128 64 32 0 0 0>; + }; + tdm_ext: tdm-ext-clock { compatible = "fixed-clock"; clock-output-names = "tdm_ext"; @@ -386,6 +446,149 @@ status = "disabled"; }; + spi0: spi@10060000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10060000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI0_APB>, + <&syscrg JH7110_SYSCLK_SPI0_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI0_APB>; + interrupts = <38>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi1: spi@10070000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10070000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI1_APB>, + <&syscrg JH7110_SYSCLK_SPI1_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI1_APB>; + interrupts = <39>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi2: spi@10080000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10080000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI2_APB>, + <&syscrg JH7110_SYSCLK_SPI2_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI2_APB>; + interrupts = <40>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + tdm: tdm@10090000 { + compatible = "starfive,jh7110-tdm"; + reg = <0x0 0x10090000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_TDM_AHB>, + <&syscrg JH7110_SYSCLK_TDM_APB>, + <&syscrg JH7110_SYSCLK_TDM_INTERNAL>, + <&syscrg JH7110_SYSCLK_TDM_TDM>, + <&syscrg JH7110_SYSCLK_MCLK_INNER>, + <&tdm_ext>; + clock-names = "tdm_ahb", "tdm_apb", + "tdm_internal", "tdm", + "mclk_inner", "tdm_ext"; + resets = <&syscrg JH7110_SYSRST_TDM_AHB>, + <&syscrg JH7110_SYSRST_TDM_APB>, + <&syscrg JH7110_SYSRST_TDM_CORE>; + dmas = <&dma 20>, <&dma 21>; + dma-names = "rx","tx"; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + usb0: usb@10100000 { + compatible = "starfive,jh7110-usb"; + ranges = <0x0 0x0 0x10100000 0x100000>; + #address-cells = <1>; + #size-cells = <1>; + starfive,stg-syscon = <&stg_syscon 0x4>; + clocks = <&stgcrg JH7110_STGCLK_USB0_LPM>, + <&stgcrg JH7110_STGCLK_USB0_STB>, + <&stgcrg JH7110_STGCLK_USB0_APB>, + <&stgcrg JH7110_STGCLK_USB0_AXI>, + <&stgcrg JH7110_STGCLK_USB0_UTMI_APB>; + clock-names = "lpm", "stb", "apb", "axi", "utmi_apb"; + resets = <&stgcrg JH7110_STGRST_USB0_PWRUP>, + <&stgcrg JH7110_STGRST_USB0_APB>, + <&stgcrg JH7110_STGRST_USB0_AXI>, + <&stgcrg JH7110_STGRST_USB0_UTMI_APB>; + reset-names = "pwrup", "apb", "axi", "utmi_apb"; + status = "disabled"; + + usb_cdns3: usb@0 { + compatible = "cdns,usb3"; + reg = <0x0 0x10000>, + <0x10000 0x10000>, + <0x20000 0x10000>; + reg-names = "otg", "xhci", "dev"; + interrupts = <100>, <108>, <110>; + interrupt-names = "host", "peripheral", "otg"; + phys = <&usbphy0>; + phy-names = "cdns3,usb2-phy"; + }; + }; + + usbphy0: phy@10200000 { + compatible = "starfive,jh7110-usb-phy"; + reg = <0x0 0x10200000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_USB_125M>, + <&stgcrg JH7110_STGCLK_USB0_APP_125>; + clock-names = "125m", "app_125m"; + #phy-cells = <0>; + }; + + pciephy0: phy@10210000 { + compatible = "starfive,jh7110-pcie-phy"; + reg = <0x0 0x10210000 0x0 0x10000>; + #phy-cells = <0>; + }; + + pciephy1: phy@10220000 { + compatible = "starfive,jh7110-pcie-phy"; + reg = <0x0 0x10220000 0x0 0x10000>; + #phy-cells = <0>; + }; + + stgcrg: clock-controller@10230000 { + compatible = "starfive,jh7110-stgcrg"; + reg = <0x0 0x10230000 0x0 0x10000>; + clocks = <&osc>, + <&syscrg JH7110_SYSCLK_HIFI4_CORE>, + <&syscrg JH7110_SYSCLK_STG_AXIAHB>, + <&syscrg JH7110_SYSCLK_USB_125M>, + <&syscrg JH7110_SYSCLK_CPU_BUS>, + <&syscrg JH7110_SYSCLK_HIFI4_AXI>, + <&syscrg JH7110_SYSCLK_NOCSTG_BUS>, + <&syscrg JH7110_SYSCLK_APB_BUS>; + clock-names = "osc", "hifi4_core", + "stg_axiahb", "usb_125m", + "cpu_bus", "hifi4_axi", + "nocstg_bus", "apb_bus"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + stg_syscon: syscon@10240000 { + compatible = "starfive,jh7110-stg-syscon", "syscon"; + reg = <0x0 0x10240000 0x0 0x1000>; + }; + uart3: serial@12000000 { compatible = "snps,dw-apb-uart"; reg = <0x0 0x12000000 0x0 0x10000>; @@ -473,6 +676,97 @@ status = "disabled"; }; + spi3: spi@12070000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12070000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI3_APB>, + <&syscrg JH7110_SYSCLK_SPI3_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI3_APB>; + interrupts = <52>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi4: spi@12080000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12080000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI4_APB>, + <&syscrg JH7110_SYSCLK_SPI4_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI4_APB>; + interrupts = <53>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi5: spi@12090000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12090000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI5_APB>, + <&syscrg JH7110_SYSCLK_SPI5_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI5_APB>; + interrupts = <54>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi6: spi@120a0000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x120A0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI6_APB>, + <&syscrg JH7110_SYSCLK_SPI6_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI6_APB>; + interrupts = <55>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + sfctemp: temperature-sensor@120e0000 { + compatible = "starfive,jh7110-temp"; + reg = <0x0 0x120e0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_TEMP_CORE>, + <&syscrg JH7110_SYSCLK_TEMP_APB>; + clock-names = "sense", "bus"; + resets = <&syscrg JH7110_SYSRST_TEMP_CORE>, + <&syscrg JH7110_SYSRST_TEMP_APB>; + reset-names = "sense", "bus"; + #thermal-sensor-cells = <0>; + }; + + qspi: spi@13010000 { + compatible = "starfive,jh7110-qspi", "cdns,qspi-nor"; + reg = <0x0 0x13010000 0x0 0x10000>, + <0x0 0x21000000 0x0 0x400000>; + interrupts = <25>; + clocks = <&syscrg JH7110_SYSCLK_QSPI_REF>, + <&syscrg JH7110_SYSCLK_QSPI_AHB>, + <&syscrg JH7110_SYSCLK_QSPI_APB>; + clock-names = "ref", "ahb", "apb"; + resets = <&syscrg JH7110_SYSRST_QSPI_APB>, + <&syscrg JH7110_SYSRST_QSPI_AHB>, + <&syscrg JH7110_SYSRST_QSPI_REF>; + reset-names = "qspi", "qspi-ocp", "rstc_ref"; + cdns,fifo-depth = <256>; + cdns,fifo-width = <4>; + cdns,trigger-address = <0x0>; + status = "disabled"; + }; + syscrg: clock-controller@13020000 { compatible = "starfive,jh7110-syscrg"; reg = <0x0 0x13020000 0x0 0x10000>; @@ -480,16 +774,31 @@ <&gmac1_rgmii_rxin>, <&i2stx_bclk_ext>, <&i2stx_lrck_ext>, <&i2srx_bclk_ext>, <&i2srx_lrck_ext>, - <&tdm_ext>, <&mclk_ext>; + <&tdm_ext>, <&mclk_ext>, + <&pllclk JH7110_PLLCLK_PLL0_OUT>, + <&pllclk JH7110_PLLCLK_PLL1_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>; clock-names = "osc", "gmac1_rmii_refin", "gmac1_rgmii_rxin", "i2stx_bclk_ext", "i2stx_lrck_ext", "i2srx_bclk_ext", "i2srx_lrck_ext", - "tdm_ext", "mclk_ext"; + "tdm_ext", "mclk_ext", + "pll0_out", "pll1_out", "pll2_out"; #clock-cells = <1>; #reset-cells = <1>; }; + sys_syscon: syscon@13030000 { + compatible = "starfive,jh7110-sys-syscon", "syscon", "simple-mfd"; + reg = <0x0 0x13030000 0x0 0x1000>; + + pllclk: clock-controller { + compatible = "starfive,jh7110-pll"; + clocks = <&osc>; + #clock-cells = <1>; + }; + }; + sysgpio: pinctrl@13040000 { compatible = "starfive,jh7110-sys-pinctrl"; reg = <0x0 0x13040000 0x0 0x10000>; @@ -512,6 +821,155 @@ <&syscrg JH7110_SYSRST_WDT_CORE>; }; + crypto: crypto@16000000 { + compatible = "starfive,jh7110-crypto"; + reg = <0x0 0x16000000 0x0 0x4000>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>, + <&stgcrg JH7110_STGCLK_SEC_MISC_AHB>; + clock-names = "hclk", "ahb"; + interrupts = <28>; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + dmas = <&sdma 1 2>, <&sdma 0 2>; + dma-names = "tx", "rx"; + }; + + sdma: dma-controller@16008000 { + compatible = "arm,pl080", "arm,primecell"; + arm,primecell-periphid = <0x00041080>; + reg = <0x0 0x16008000 0x0 0x4000>; + interrupts = <29>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>; + clock-names = "apb_pclk"; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + lli-bus-interface-ahb1; + mem-bus-interface-ahb1; + memcpy-burst-size = <256>; + memcpy-bus-width = <32>; + #dma-cells = <2>; + }; + + rng: rng@1600c000 { + compatible = "starfive,jh7110-trng"; + reg = <0x0 0x1600C000 0x0 0x4000>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>, + <&stgcrg JH7110_STGCLK_SEC_MISC_AHB>; + clock-names = "hclk", "ahb"; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + interrupts = <30>; + }; + + mmc0: mmc@16010000 { + compatible = "starfive,jh7110-mmc"; + reg = <0x0 0x16010000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SDIO0_AHB>, + <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; + clock-names = "biu","ciu"; + resets = <&syscrg JH7110_SYSRST_SDIO0_AHB>; + reset-names = "reset"; + interrupts = <74>; + fifo-depth = <32>; + fifo-watermark-aligned; + data-addr = <0>; + starfive,sysreg = <&sys_syscon 0x14 0x1a 0x7c000000>; + status = "disabled"; + }; + + mmc1: mmc@16020000 { + compatible = "starfive,jh7110-mmc"; + reg = <0x0 0x16020000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SDIO1_AHB>, + <&syscrg JH7110_SYSCLK_SDIO1_SDCARD>; + clock-names = "biu","ciu"; + resets = <&syscrg JH7110_SYSRST_SDIO1_AHB>; + reset-names = "reset"; + interrupts = <75>; + fifo-depth = <32>; + fifo-watermark-aligned; + data-addr = <0>; + starfive,sysreg = <&sys_syscon 0x9c 0x1 0x3e>; + status = "disabled"; + }; + + gmac0: ethernet@16030000 { + compatible = "starfive,jh7110-dwmac", "snps,dwmac-5.20"; + reg = <0x0 0x16030000 0x0 0x10000>; + clocks = <&aoncrg JH7110_AONCLK_GMAC0_AXI>, + <&aoncrg JH7110_AONCLK_GMAC0_AHB>, + <&syscrg JH7110_SYSCLK_GMAC0_PTP>, + <&aoncrg JH7110_AONCLK_GMAC0_TX_INV>, + <&syscrg JH7110_SYSCLK_GMAC0_GTXC>; + clock-names = "stmmaceth", "pclk", "ptp_ref", + "tx", "gtx"; + resets = <&aoncrg JH7110_AONRST_GMAC0_AXI>, + <&aoncrg JH7110_AONRST_GMAC0_AHB>; + reset-names = "stmmaceth", "ahb"; + interrupts = <7>, <6>, <5>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + rx-fifo-depth = <2048>; + tx-fifo-depth = <2048>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <256>; + snps,fixed-burst; + snps,no-pbl-x8; + snps,force_thresh_dma_mode; + snps,axi-config = <&stmmac_axi_setup>; + snps,tso; + snps,en-tx-lpi-clockgating; + snps,txpbl = <16>; + snps,rxpbl = <16>; + starfive,syscon = <&aon_syscon 0xc 0x12>; + status = "disabled"; + }; + + gmac1: ethernet@16040000 { + compatible = "starfive,jh7110-dwmac", "snps,dwmac-5.20"; + reg = <0x0 0x16040000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_GMAC1_AXI>, + <&syscrg JH7110_SYSCLK_GMAC1_AHB>, + <&syscrg JH7110_SYSCLK_GMAC1_PTP>, + <&syscrg JH7110_SYSCLK_GMAC1_TX_INV>, + <&syscrg JH7110_SYSCLK_GMAC1_GTXC>; + clock-names = "stmmaceth", "pclk", "ptp_ref", + "tx", "gtx"; + resets = <&syscrg JH7110_SYSRST_GMAC1_AXI>, + <&syscrg JH7110_SYSRST_GMAC1_AHB>; + reset-names = "stmmaceth", "ahb"; + interrupts = <78>, <77>, <76>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + rx-fifo-depth = <2048>; + tx-fifo-depth = <2048>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <256>; + snps,fixed-burst; + snps,no-pbl-x8; + snps,force_thresh_dma_mode; + snps,axi-config = <&stmmac_axi_setup>; + snps,tso; + snps,en-tx-lpi-clockgating; + snps,txpbl = <16>; + snps,rxpbl = <16>; + starfive,syscon = <&sys_syscon 0x90 0x2>; + status = "disabled"; + }; + + dma: dma-controller@16050000 { + compatible = "starfive,jh7110-axi-dma"; + reg = <0x0 0x16050000 0x0 0x10000>; + clocks = <&stgcrg JH7110_STGCLK_DMA1P_AXI>, + <&stgcrg JH7110_STGCLK_DMA1P_AHB>; + clock-names = "core-clk", "cfgr-clk"; + resets = <&stgcrg JH7110_STGRST_DMA1P_AXI>, + <&stgcrg JH7110_STGRST_DMA1P_AHB>; + interrupts = <73>; + #dma-cells = <1>; + dma-channels = <4>; + snps,dma-masters = <1>; + snps,data-width = <3>; + snps,block-size = <65536 65536 65536 65536>; + snps,priority = <0 1 2 3>; + snps,axi-max-burst-len = <16>; + }; + aoncrg: clock-controller@17000000 { compatible = "starfive,jh7110-aoncrg"; reg = <0x0 0x17000000 0x0 0x10000>; @@ -529,6 +987,12 @@ #reset-cells = <1>; }; + aon_syscon: syscon@17010000 { + compatible = "starfive,jh7110-aon-syscon", "syscon"; + reg = <0x0 0x17010000 0x0 0x1000>; + #power-domain-cells = <1>; + }; + aongpio: pinctrl@17020000 { compatible = "starfive,jh7110-aon-pinctrl"; reg = <0x0 0x17020000 0x0 0x10000>; @@ -546,5 +1010,40 @@ interrupts = <111>; #power-domain-cells = <1>; }; + + ispcrg: clock-controller@19810000 { + compatible = "starfive,jh7110-ispcrg"; + reg = <0x0 0x19810000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_ISP_TOP_CORE>, + <&syscrg JH7110_SYSCLK_ISP_TOP_AXI>, + <&syscrg JH7110_SYSCLK_NOC_BUS_ISP_AXI>, + <&dvp_clk>; + clock-names = "isp_top_core", "isp_top_axi", + "noc_bus_isp_axi", "dvp_clk"; + resets = <&syscrg JH7110_SYSRST_ISP_TOP>, + <&syscrg JH7110_SYSRST_ISP_TOP_AXI>, + <&syscrg JH7110_SYSRST_NOC_BUS_ISP_AXI>; + #clock-cells = <1>; + #reset-cells = <1>; + power-domains = <&pwrc JH7110_PD_ISP>; + }; + + voutcrg: clock-controller@295c0000 { + compatible = "starfive,jh7110-voutcrg"; + reg = <0x0 0x295c0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_VOUT_SRC>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_AHB>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_AXI>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_HDMITX0_MCLK>, + <&syscrg JH7110_SYSCLK_I2STX0_BCLK>, + <&hdmitx0_pixelclk>; + clock-names = "vout_src", "vout_top_ahb", + "vout_top_axi", "vout_top_hdmitx0_mclk", + "i2stx0_bclk", "hdmitx0_pixelclk"; + resets = <&syscrg JH7110_SYSRST_VOUT_TOP_SRC>; + #clock-cells = <1>; + #reset-cells = <1>; + power-domains = <&pwrc JH7110_PD_VOUT>; + }; }; }; diff --git a/arch/riscv/boot/dts/thead/Makefile b/arch/riscv/boot/dts/thead/Makefile index e311fc9a5939..b55a17127c2b 100644 --- a/arch/riscv/boot/dts/thead/Makefile +++ b/arch/riscv/boot/dts/thead/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -dtb-$(CONFIG_ARCH_THEAD) += th1520-lichee-pi-4a.dtb +dtb-$(CONFIG_ARCH_THEAD) += th1520-lichee-pi-4a.dtb th1520-beaglev-ahead.dtb diff --git a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts new file mode 100644 index 000000000000..70e8042c8304 --- /dev/null +++ b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> + * Copyright (C) 2023 Drew Fustini <dfustini@baylibre.com> + */ + +/dts-v1/; + +#include "th1520.dtsi" + +/ { + model = "BeagleV Ahead"; + compatible = "beagle,beaglev-ahead", "thead,th1520"; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + serial5 = &uart5; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x00000000 0x1 0x00000000>; + + }; +}; + +&osc { + clock-frequency = <24000000>; +}; + +&osc_32k { + clock-frequency = <32768>; +}; + +&apb_clk { + clock-frequency = <62500000>; +}; + +&uart_sclk { + clock-frequency = <100000000>; +}; + +&dmac0 { + status = "okay"; +}; + +&uart0 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi index 4b0249ac710f..a802ab110429 100644 --- a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi +++ b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (GPL-2.0 OR MIT) /* * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> */ diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts index a1248b2ee3a3..9a3884a73e13 100644 --- a/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts +++ b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (GPL-2.0 OR MIT) /* * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> */ diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index 56a73134b49e..ce708183b6f6 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (GPL-2.0 OR MIT) /* * Copyright (C) 2021 Alibaba Group Holding Limited. * Copyright (C) 2023 Jisheng Zhang <jszhang@kernel.org> diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 0a0107460a5c..ab86ec3b9eab 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -192,7 +192,7 @@ CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_OVERLAY_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig index e36fffd6fb18..146c46d0525b 100644 --- a/arch/riscv/configs/nommu_k210_defconfig +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -21,7 +21,7 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_IO_URING is not set # CONFIG_ADVISE_SYSCALLS is not set # CONFIG_KALLSYMS is not set -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLUB=y diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index c1ad85f0a4f7..95d8d1808f19 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -13,7 +13,7 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_IO_URING is not set # CONFIG_ADVISE_SYSCALLS is not set # CONFIG_KALLSYMS is not set -CONFIG_EMBEDDED=y +CONFIG_EXPERT=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLUB=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 38760e4296cf..89b601e253a6 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -98,7 +98,7 @@ CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index be84b14f0118..0554ed4bf087 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -120,11 +120,3 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) local_flush_icache_all(); } - -void thead_feature_probe_func(unsigned int cpu, - unsigned long archid, - unsigned long impid) -{ - if ((archid == 0) && (impid == 0)) - per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_FAST; -} diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h index f71ce21ff684..d5604d2073bc 100644 --- a/arch/riscv/include/asm/acpi.h +++ b/arch/riscv/include/asm/acpi.h @@ -19,7 +19,7 @@ typedef u64 phys_cpuid_t; #define PHYS_CPUID_INVALID INVALID_HARTID /* ACPI table mapping after acpi_permanent_mmap is set */ -void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); #define acpi_os_ioremap acpi_os_ioremap #define acpi_strict 1 /* No out-of-spec workarounds on RISC-V */ diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index b8c55fb3ab2c..721ec275ce57 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -146,7 +146,7 @@ * vendor_id: The CPU vendor ID. * patch_id: The patch ID (erratum ID or cpufeature ID). * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old - * content will alwyas be executed. + * content will always be executed. */ #define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \ _ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k) diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index 6a41537826a7..58ccd2f8cab7 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -30,7 +30,6 @@ #define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset) #define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset) -void probe_vendor_features(unsigned int cpu); void __init apply_boot_alternatives(void); void __init apply_early_boot_alternatives(void); void apply_module_alternatives(void *start, size_t length); @@ -53,15 +52,11 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); -void thead_feature_probe_func(unsigned int cpu, unsigned long archid, - unsigned long impid); - void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned int stage); #else /* CONFIG_RISCV_ALTERNATIVE */ -static inline void probe_vendor_features(unsigned int cpu) { } static inline void apply_boot_alternatives(void) { } static inline void apply_early_boot_alternatives(void) { } static inline void apply_module_alternatives(void *start, size_t length) { } diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h index d3036df23ccb..2174fe7bac9a 100644 --- a/arch/riscv/include/asm/cache.h +++ b/arch/riscv/include/asm/cache.h @@ -13,6 +13,7 @@ #ifdef CONFIG_RISCV_DMA_NONCOHERENT #define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_KMALLOC_MINALIGN (8) #endif /* @@ -23,4 +24,17 @@ #define ARCH_SLAB_MINALIGN 16 #endif +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +extern int dma_cache_alignment; +#define dma_get_cache_alignment dma_get_cache_alignment +static inline int dma_get_cache_alignment(void) +{ + return dma_cache_alignment; +} +#endif + +#endif /* __ASSEMBLY__ */ + #endif /* _ASM_RISCV_CACHE_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 8091b8bf4883..3cb53c4df27c 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -15,20 +15,19 @@ static inline void local_flush_icache_all(void) #define PG_dcache_clean PG_arch_1 -static inline void flush_dcache_page(struct page *page) +static inline void flush_dcache_folio(struct folio *folio) { - /* - * HugeTLB pages are always fully mapped and only head page will be - * set PG_dcache_clean (see comments in flush_icache_pte()). - */ - if (PageHuge(page)) - page = compound_head(page); - - if (test_bit(PG_dcache_clean, &page->flags)) - clear_bit(PG_dcache_clean, &page->flags); + if (test_bit(PG_dcache_clean, &folio->flags)) + clear_bit(PG_dcache_clean, &folio->flags); } +#define flush_dcache_folio flush_dcache_folio #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 +static inline void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); +} + /* * RISC-V doesn't have an instruction to flush parts of the instruction cache, * so instead we just flush the whole thing. @@ -37,6 +36,10 @@ static inline void flush_dcache_page(struct page *page) #define flush_icache_user_page(vma, pg, addr, len) \ flush_icache_mm(vma->vm_mm, 0) +#ifdef CONFIG_64BIT +#define flush_cache_vmap(start, end) flush_tlb_kernel_range(start, end) +#endif + #ifndef CONFIG_SMP #define flush_icache_all() local_flush_icache_all() @@ -55,8 +58,10 @@ void riscv_init_cbo_blocksizes(void); #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); +void __init riscv_set_dma_cache_alignment(void); #else static inline void riscv_noncoherent_supported(void) {} +static inline void riscv_set_dma_cache_alignment(void) {} #endif /* diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h new file mode 100644 index 000000000000..56bf9d69d5e3 --- /dev/null +++ b/arch/riscv/include/asm/cfi.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_CFI_H +#define _ASM_RISCV_CFI_H + +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2023 Google LLC + */ + +#include <linux/cfi.h> + +#ifdef CONFIG_CFI_CLANG +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#else +static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_NONE; +} +#endif /* CONFIG_CFI_CLANG */ + +#endif /* _ASM_RISCV_CFI_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 23fed53b8815..d0345bd659c9 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -30,4 +30,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; +void check_unaligned_access(int cpu); + #endif diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 29e9a0d84b16..8a6a128ec57f 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -21,12 +21,6 @@ extern void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool); -#define arch_efi_call_virt_setup() ({ \ - sync_kernel_mappings(efi_mm.pgd); \ - efi_virtmap_load(); \ - }) -#define arch_efi_call_virt_teardown() efi_virtmap_unload() - #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) /* Load initrd anywhere in system RAM */ @@ -46,8 +40,8 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_min_align() -void efi_virtmap_load(void); -void efi_virtmap_unload(void); +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); unsigned long stext_offset(void); diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index c24280774caf..b3b2dfbdf945 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -41,6 +41,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); #define compat_elf_check_arch compat_elf_check_arch #define CORE_DUMP_USE_REGSET +#define ELF_FDPIC_CORE_EFLAGS 0 #define ELF_EXEC_PAGESIZE (PAGE_SIZE) /* @@ -49,7 +50,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); * the loader. We need to make sure that it is out of the way of the program * that it will "exec", and that there is sufficient room for the brk. */ -#define ELF_ET_DYN_BASE ((TASK_SIZE / 3) * 2) +#define ELF_ET_DYN_BASE ((DEFAULT_MAP_WINDOW / 3) * 2) #ifdef CONFIG_64BIT #ifdef CONFIG_COMPAT @@ -69,6 +70,13 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); #define ELF_HWCAP riscv_get_elf_hwcap() extern unsigned long elf_hwcap; +#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr, dynamic_addr) \ + do { \ + (_r)->a1 = _exec_map_addr; \ + (_r)->a2 = _interp_map_addr; \ + (_r)->a3 = dynamic_addr; \ + } while (0) + /* * This yields a string that ld.so will use to load implementation * specific libraries for optimization. This is more specific in @@ -78,7 +86,6 @@ extern unsigned long elf_hwcap; #define COMPAT_ELF_PLATFORM (NULL) -#ifdef CONFIG_MMU #define ARCH_DLINFO \ do { \ /* \ @@ -115,6 +122,8 @@ do { \ else \ NEW_AUX_ENT(AT_IGNORE, 0); \ } while (0) + +#ifdef CONFIG_MMU #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; extern int arch_setup_additional_pages(struct linux_binprm *bprm, diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index ce1ebda1a49a..34e24f078cc1 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -2,6 +2,7 @@ #ifndef _ASM_RISCV_HUGETLB_H #define _ASM_RISCV_HUGETLB_H +#include <asm/cacheflush.h> #include <asm/page.h> static inline void arch_clear_hugepage_flags(struct page *page) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index f041bfa7f6a0..b7b58258f6c7 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -14,12 +14,17 @@ #include <uapi/asm/hwcap.h> #define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_b ('b' - 'a') #define RISCV_ISA_EXT_c ('c' - 'a') #define RISCV_ISA_EXT_d ('d' - 'a') #define RISCV_ISA_EXT_f ('f' - 'a') #define RISCV_ISA_EXT_h ('h' - 'a') #define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_j ('j' - 'a') +#define RISCV_ISA_EXT_k ('k' - 'a') #define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_p ('p' - 'a') +#define RISCV_ISA_EXT_q ('q' - 'a') #define RISCV_ISA_EXT_s ('s' - 'a') #define RISCV_ISA_EXT_u ('u' - 'a') #define RISCV_ISA_EXT_v ('v' - 'a') @@ -55,7 +60,6 @@ #define RISCV_ISA_EXT_ZIHPM 42 #define RISCV_ISA_EXT_MAX 64 -#define RISCV_ISA_EXT_NAME_LEN_MAX 32 #ifdef CONFIG_RISCV_M_MODE #define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA @@ -70,12 +74,15 @@ unsigned long riscv_get_elf_hwcap(void); struct riscv_isa_ext_data { - /* Name of the extension displayed to userspace via /proc/cpuinfo */ - char uprop[RISCV_ISA_EXT_NAME_LEN_MAX]; - /* The logical ISA extension ID */ - unsigned int isa_ext_id; + const unsigned int id; + const char *name; + const char *property; }; +extern const struct riscv_isa_ext_data riscv_isa_ext[]; +extern const size_t riscv_isa_ext_count; +extern bool riscv_isa_fallback; + unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); #define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h index 4e1505cef8aa..06e439eeef9a 100644 --- a/arch/riscv/include/asm/insn.h +++ b/arch/riscv/include/asm/insn.h @@ -63,6 +63,7 @@ #define RVG_RS1_OPOFF 15 #define RVG_RS2_OPOFF 20 #define RVG_RD_OPOFF 7 +#define RVG_RS1_MASK GENMASK(4, 0) #define RVG_RD_MASK GENMASK(4, 0) /* The bit field of immediate value in RVC J instruction */ @@ -110,6 +111,7 @@ #define RVC_INSN_FUNCT4_OPOFF 12 #define RVC_INSN_FUNCT3_MASK GENMASK(15, 13) #define RVC_INSN_FUNCT3_OPOFF 13 +#define RVC_INSN_J_RS1_MASK GENMASK(11, 7) #define RVC_INSN_J_RS2_MASK GENMASK(6, 2) #define RVC_INSN_OPCODE_MASK GENMASK(1, 0) #define RVC_ENCODE_FUNCT3(f_) (RVC_FUNCT3_##f_ << RVC_INSN_FUNCT3_OPOFF) @@ -129,6 +131,7 @@ #define RVC_C2_RS1_OPOFF 7 #define RVC_C2_RS2_OPOFF 2 #define RVC_C2_RD_OPOFF 7 +#define RVC_C2_RS1_MASK GENMASK(4, 0) /* parts of opcode for RVG*/ #define RVG_OPCODE_FENCE 0x0f @@ -245,8 +248,6 @@ __RISCV_INSN_FUNCS(c_jal, RVC_MASK_C_JAL, RVC_MATCH_C_JAL) __RISCV_INSN_FUNCS(auipc, RVG_MASK_AUIPC, RVG_MATCH_AUIPC) __RISCV_INSN_FUNCS(jalr, RVG_MASK_JALR, RVG_MATCH_JALR) __RISCV_INSN_FUNCS(jal, RVG_MASK_JAL, RVG_MATCH_JAL) -__RISCV_INSN_FUNCS(c_jr, RVC_MASK_C_JR, RVC_MATCH_C_JR) -__RISCV_INSN_FUNCS(c_jalr, RVC_MASK_C_JALR, RVC_MATCH_C_JALR) __RISCV_INSN_FUNCS(c_j, RVC_MASK_C_J, RVC_MATCH_C_J) __RISCV_INSN_FUNCS(beq, RVG_MASK_BEQ, RVG_MATCH_BEQ) __RISCV_INSN_FUNCS(bne, RVG_MASK_BNE, RVG_MATCH_BNE) @@ -273,11 +274,27 @@ static __always_inline bool riscv_insn_is_branch(u32 code) return (code & RV_INSN_OPCODE_MASK) == RVG_OPCODE_BRANCH; } +static __always_inline bool riscv_insn_is_c_jr(u32 code) +{ + return (code & RVC_MASK_C_JR) == RVC_MATCH_C_JR && + (code & RVC_INSN_J_RS1_MASK) != 0; +} + +static __always_inline bool riscv_insn_is_c_jalr(u32 code) +{ + return (code & RVC_MASK_C_JALR) == RVC_MATCH_C_JALR && + (code & RVC_INSN_J_RS1_MASK) != 0; +} + #define RV_IMM_SIGN(x) (-(((x) >> 31) & 1)) #define RVC_IMM_SIGN(x) (-(((x) >> 12) & 1)) #define RV_X(X, s, mask) (((X) >> (s)) & (mask)) #define RVC_X(X, s, mask) RV_X(X, s, mask) +#define RV_EXTRACT_RS1_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X(x_, RVG_RS1_OPOFF, RVG_RS1_MASK)); }) + #define RV_EXTRACT_RD_REG(x) \ ({typeof(x) x_ = (x); \ (RV_X(x_, RVG_RD_OPOFF, RVG_RD_MASK)); }) @@ -305,6 +322,10 @@ static __always_inline bool riscv_insn_is_branch(u32 code) (RV_X(x_, RV_B_IMM_11_OPOFF, RV_B_IMM_11_MASK) << RV_B_IMM_11_OFF) | \ (RV_IMM_SIGN(x_) << RV_B_IMM_SIGN_OFF); }) +#define RVC_EXTRACT_C2_RS1_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X(x_, RVC_C2_RS1_OPOFF, RVC_C2_RS1_MASK)); }) + #define RVC_EXTRACT_JTYPE_IMM(x) \ ({typeof(x) x_ = (x); \ (RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \ diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 0099dc116168..355504b37f8e 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -20,6 +20,10 @@ typedef struct { /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; #endif +#ifdef CONFIG_BINFMT_ELF_FDPIC + unsigned long exec_fdpic_loadmap; + unsigned long interp_fdpic_loadmap; +#endif } mm_context_t; void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 59dc12b5b7e8..d169a4f41a2e 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -153,10 +153,10 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #endif /* __PAGETABLE_PMD_FOLDED */ -#define __pte_free_tlb(tlb, pte, buf) \ -do { \ - pgtable_pte_page_dtor(pte); \ - tlb_remove_page((tlb), pte); \ +#define __pte_free_tlb(tlb, pte, buf) \ +do { \ + pagetable_pte_dtor(page_ptdesc(pte)); \ + tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\ } while (0) #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 75970ee2bda2..b2ba3f79cfe9 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -62,11 +62,16 @@ * struct pages to map half the virtual address space. Then * position vmemmap directly below the VMALLOC region. */ +#define VA_BITS_SV32 32 #ifdef CONFIG_64BIT +#define VA_BITS_SV39 39 +#define VA_BITS_SV48 48 +#define VA_BITS_SV57 57 + #define VA_BITS (pgtable_l5_enabled ? \ - 57 : (pgtable_l4_enabled ? 48 : 39)) + VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39)) #else -#define VA_BITS 32 +#define VA_BITS VA_BITS_SV32 #endif #define VMEMMAP_SHIFT \ @@ -111,11 +116,27 @@ #include <asm/page.h> #include <asm/tlbflush.h> #include <linux/mm_types.h> +#include <asm/compat.h> #define __page_val_to_pfn(_val) (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT) #ifdef CONFIG_64BIT #include <asm/pgtable-64.h> + +#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1)) +#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1)) +#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1)) + +#ifdef CONFIG_COMPAT +#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) +#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39) +#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64) +#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64) +#else +#define MMAP_VA_BITS ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) +#define MMAP_MIN_VA_BITS (VA_BITS_SV39) +#endif /* CONFIG_COMPAT */ + #else #include <asm/pgtable-32.h> #endif /* CONFIG_64BIT */ @@ -188,6 +209,8 @@ extern struct pt_alloc_ops pt_ops __initdata; #define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) extern pgd_t swapper_pg_dir[]; +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_present(pmd_t pmd) @@ -378,7 +401,7 @@ static inline pte_t pte_wrprotect(pte_t pte) /* static inline pte_t pte_mkread(pte_t pte) */ -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_WRITE); } @@ -445,8 +468,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) /* Commit new configuration to MMU hardware */ -static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) { /* * The kernel assumes that TLBs don't cache invalid entries, but @@ -455,8 +479,11 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, * Relying on flush_tlb_fix_spurious_fault would suffice, but * the extra traps reduce performance. So, eagerly SFENCE.VMA. */ - local_flush_tlb_page(address); + while (nr--) + local_flush_tlb_page(address + nr * PAGE_SIZE); } +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define __HAVE_ARCH_UPDATE_MMU_TLB #define update_mmu_tlb update_mmu_cache @@ -487,8 +514,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) void flush_icache_pte(pte_t pte); -static inline void __set_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pteval) +static inline void __set_pte_at(pte_t *ptep, pte_t pteval) { if (pte_present(pteval) && pte_exec(pteval)) flush_icache_pte(pteval); @@ -496,17 +522,25 @@ static inline void __set_pte_at(struct mm_struct *mm, set_pte(ptep, pteval); } -static inline void set_pte_at(struct mm_struct *mm, - unsigned long addr, pte_t *ptep, pte_t pteval) +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval, unsigned int nr) { - page_table_check_pte_set(mm, addr, ptep, pteval); - __set_pte_at(mm, addr, ptep, pteval); + page_table_check_ptes_set(mm, ptep, pteval, nr); + + for (;;) { + __set_pte_at(ptep, pteval); + if (--nr == 0) + break; + ptep++; + pte_val(pteval) += 1 << _PAGE_PFN_SHIFT; + } } +#define set_ptes set_ptes static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - __set_pte_at(mm, addr, ptep, __pte(0)); + __set_pte_at(ptep, __pte(0)); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS @@ -515,7 +549,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, pte_t entry, int dirty) { if (!pte_same(*ptep, entry)) - set_pte_at(vma->vm_mm, address, ptep, entry); + __set_pte_at(ptep, entry); /* * update_mmu_cache will unconditionally execute, handling both * the case that the PTE changed and the spurious fault case. @@ -529,7 +563,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } @@ -664,9 +698,9 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pte_pmd(pte_mkyoung(pmd_pte(pmd))); } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { - return pte_pmd(pte_mkwrite(pmd_pte(pmd))); + return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))); } static inline pmd_t pmd_wrprotect(pmd_t pmd) @@ -687,15 +721,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); - return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); + page_table_check_pmd_set(mm, pmdp, pmd); + return __set_pte_at((pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); - return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); + page_table_check_pud_set(mm, pudp, pud); + return __set_pte_at((pte_t *)pudp, pud_pte(pud)); } #ifdef CONFIG_PAGE_TABLE_CHECK @@ -742,7 +776,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, { pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0)); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -758,7 +792,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd))); } @@ -830,14 +864,16 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32. * Note that PGDIR_SIZE must evenly divide TASK_SIZE. * Task size is: - * - 0x9fc00000 (~2.5GB) for RV32. - * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu - * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu + * - 0x9fc00000 (~2.5GB) for RV32. + * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu + * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu + * - 0x100000000000000 ( 64PB) for RV64 using SV57 mmu * * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V * Instruction Set Manual Volume II: Privileged Architecture" states that * "load and store effective addresses, which are 64bits, must have bits * 63–48 all equal to bit 47, or else a page-fault exception will occur." + * Similarly for SV57, bits 63–57 must be equal to bit 56. */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index c950a8d9edef..3e23e1786d05 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -13,19 +13,59 @@ #include <asm/ptrace.h> +#ifdef CONFIG_64BIT +#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1)) +#define STACK_TOP_MAX TASK_SIZE_64 + +#define arch_get_mmap_end(addr, len, flags) \ +({ \ + unsigned long mmap_end; \ + typeof(addr) _addr = (addr); \ + if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \ + mmap_end = STACK_TOP_MAX; \ + else if ((_addr) >= VA_USER_SV57) \ + mmap_end = STACK_TOP_MAX; \ + else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \ + mmap_end = VA_USER_SV48; \ + else \ + mmap_end = VA_USER_SV39; \ + mmap_end; \ +}) + +#define arch_get_mmap_base(addr, base) \ +({ \ + unsigned long mmap_base; \ + typeof(addr) _addr = (addr); \ + typeof(base) _base = (base); \ + unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base); \ + if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \ + mmap_base = (_base); \ + else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) \ + mmap_base = VA_USER_SV57 - rnd_gap; \ + else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \ + mmap_base = VA_USER_SV48 - rnd_gap; \ + else \ + mmap_base = VA_USER_SV39 - rnd_gap; \ + mmap_base; \ +}) + +#else +#define DEFAULT_MAP_WINDOW TASK_SIZE +#define STACK_TOP_MAX TASK_SIZE +#endif +#define STACK_ALIGN 16 + +#define STACK_TOP DEFAULT_MAP_WINDOW + /* * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) - -#define STACK_TOP TASK_SIZE #ifdef CONFIG_64BIT -#define STACK_TOP_MAX TASK_SIZE_64 +#define TASK_UNMAPPED_BASE PAGE_ALIGN((UL(1) << MMAP_MIN_VA_BITS) / 3) #else -#define STACK_TOP_MAX TASK_SIZE +#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) #endif -#define STACK_ALIGN 16 #ifndef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 0148c6bd9675..121fff429dce 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -75,7 +75,7 @@ static inline int syscall_get_arch(struct task_struct *task) #endif } -typedef long (*syscall_t)(ulong, ulong, ulong, ulong, ulong, ulong, ulong); +typedef long (*syscall_t)(const struct pt_regs *); static inline void syscall_handler(struct pt_regs *regs, ulong syscall) { syscall_t fn; @@ -87,8 +87,7 @@ static inline void syscall_handler(struct pt_regs *regs, ulong syscall) #endif fn = sys_call_table[syscall]; - regs->a0 = fn(regs->orig_a0, regs->a1, regs->a2, - regs->a3, regs->a4, regs->a5, regs->a6); + regs->a0 = fn(regs); } static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..1d7942c8a6cb --- /dev/null +++ b/arch/riscv/include/asm/syscall_wrapper.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - riscv specific wrappers to syscall definitions + * + * Based on arch/arm64/include/syscall_wrapper.h + */ + +#ifndef __ASM_SYSCALL_WRAPPER_H +#define __ASM_SYSCALL_WRAPPER_H + +#include <asm/ptrace.h> + +asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); + +#define SC_RISCV_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->orig_a0,,regs->a1,,regs->a2 \ + ,,regs->a3,,regs->a4,,regs->a5,,regs->a6) + +#ifdef CONFIG_COMPAT + +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__riscv_compat_sys##name, ERRNO); \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs) \ + { \ + return __se_compat_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define COMPAT_SYSCALL_DEFINE0(sname) \ + asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(__riscv_compat_sys_##sname, ERRNO); \ + asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL_COMPAT(name) \ + asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs); \ + asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#define COMPAT_SYS_NI(name) \ + SYSCALL_ALIAS(__riscv_compat_sys_##name, sys_ni_posix_timers); + +#endif /* CONFIG_COMPAT */ + +#define __SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __riscv_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__riscv_sys##name, ERRNO); \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long __riscv_sys##name(const struct pt_regs *regs) \ + { \ + return __se_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(__riscv_sys_##sname, ERRNO); \ + asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs); \ + asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#define SYS_NI(name) SYSCALL_ALIAS(__riscv_sys_##name, sys_ni_posix_timers); + +#endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index 3d78930cab51..c5ee07b3df07 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -70,8 +70,9 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" "csrr %3, " __stringify(CSR_VCSR) "\n\t" + "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr) : :); + "=r" (dest->vcsr), "=r" (dest->vlenb) : :); } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 58d3e447f191..924d01b56c9a 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -3,12 +3,14 @@ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +extern bool pgtable_l4_enabled, pgtable_l5_enabled; + #define IOREMAP_MAX_ORDER (PUD_SHIFT) #define arch_vmap_pud_supported arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { - return true; + return pgtable_l4_enabled || pgtable_l5_enabled; } #define arch_vmap_pmd_supported arch_vmap_pmd_supported diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..7d0b32e3b701 --- /dev/null +++ b/arch/riscv/include/uapi/asm/bitsperlong.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H +#define _UAPI_ASM_RISCV_BITSPERLONG_H + +#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8) + +#include <asm-generic/bitsperlong.h> + +#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */ diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index e17c550986a6..6d2d9afaabea 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -10,6 +10,11 @@ #include <linux/types.h> +#define PTRACE_GETFDPIC 33 + +#define PTRACE_GETFDPIC_EXEC 0 +#define PTRACE_GETFDPIC_INTERP 1 + /* * User-mode register state for core dumps, ptrace, sigcontext * @@ -97,6 +102,7 @@ struct __riscv_v_ext_state { unsigned long vl; unsigned long vtype; unsigned long vcsr; + unsigned long vlenb; void *datap; /* * In signal handler, datap will be set a correct user stack offset diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index 8c8712aa9551..cd4f175dc837 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -25,7 +25,7 @@ struct __sc_riscv_v_state { * Signal context structure * * This contains the context saved before a signal handler is invoked; - * it is restored by sys_sigreturn / sys_rt_sigreturn. + * it is restored by sys_rt_sigreturn. */ struct sigcontext { struct user_regs_struct sc_regs; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 506cc4a9a45a..95cf25d48405 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -38,6 +38,7 @@ extra-y += vmlinux.lds obj-y += head.o obj-y += soc.o obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o +obj-y += copy-unaligned.o obj-y += cpu.o obj-y += cpufeature.o obj-y += entry.o @@ -91,6 +92,8 @@ obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_CFI_CLANG) += cfi.o + obj-$(CONFIG_EFI) += efi.o obj-$(CONFIG_COMPAT) += compat_syscall_table.o obj-$(CONFIG_COMPAT) += compat_signal.o diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 5ee03ebab80e..56cb2c986c48 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -215,9 +215,9 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) early_iounmap(map, size); } -void *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { - return memremap(phys, size, MEMREMAP_WB); + return (void __iomem *)memremap(phys, size, MEMREMAP_WB); } #ifdef CONFIG_PCI diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 6b75788c18e6..85056153fa23 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -27,8 +27,6 @@ struct cpu_manufacturer_info_t { void (*patch_func)(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); - void (*feature_probe_func)(unsigned int cpu, unsigned long archid, - unsigned long impid); }; static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) @@ -43,7 +41,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info cpu_mfr_info->imp_id = sbi_get_mimpid(); #endif - cpu_mfr_info->feature_probe_func = NULL; switch (cpu_mfr_info->vendor_id) { #ifdef CONFIG_ERRATA_SIFIVE case SIFIVE_VENDOR_ID: @@ -53,7 +50,6 @@ static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info #ifdef CONFIG_ERRATA_THEAD case THEAD_VENDOR_ID: cpu_mfr_info->patch_func = thead_errata_patch_func; - cpu_mfr_info->feature_probe_func = thead_feature_probe_func; break; #endif default: @@ -143,20 +139,6 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, } } -/* Called on each CPU as it starts */ -void probe_vendor_features(unsigned int cpu) -{ - struct cpu_manufacturer_info_t cpu_mfr_info; - - riscv_fill_cpu_mfr_info(&cpu_mfr_info); - if (!cpu_mfr_info.feature_probe_func) - return; - - cpu_mfr_info.feature_probe_func(cpu, - cpu_mfr_info.arch_id, - cpu_mfr_info.imp_id); -} - /* * This is called very early in the boot process (directly after we run * a feature detect on the boot CPU). No need to worry about other CPUs @@ -211,7 +193,6 @@ void __init apply_boot_alternatives(void) /* If called on non-boot cpu things could go wrong */ WARN_ON(smp_processor_id() != 0); - probe_vendor_features(0); _apply_alternatives((struct alt_entry *)__alt_start, (struct alt_entry *)__alt_end, RISCV_ALTERNATIVES_BOOT); diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c new file mode 100644 index 000000000000..820158d7a291 --- /dev/null +++ b/arch/riscv/kernel/cfi.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2023 Google LLC + */ +#include <asm/cfi.h> +#include <asm/insn.h> + +/* + * Returns the target address and the expected type when regs->epc points + * to a compiler-generated CFI trap. + */ +static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, + u32 *type) +{ + unsigned long *regs_ptr = (unsigned long *)regs; + int rs1_num; + u32 insn; + + *target = *type = 0; + + /* + * The compiler generates the following instruction sequence + * for indirect call checks: + * + *  lw t1, -4(<reg>) + * lui t2, <hi20> + * addiw t2, t2, <lo12> + * beq t1, t2, .Ltmp1 + * ebreak ; <- regs->epc + * .Ltmp1: + * jalr <reg> + * + * We can read the expected type and the target address from the + * registers passed to the beq/jalr instructions. + */ + if (get_kernel_nofault(insn, (void *)regs->epc - 4)) + return false; + if (!riscv_insn_is_beq(insn)) + return false; + + *type = (u32)regs_ptr[RV_EXTRACT_RS1_REG(insn)]; + + if (get_kernel_nofault(insn, (void *)regs->epc) || + get_kernel_nofault(insn, (void *)regs->epc + GET_INSN_LENGTH(insn))) + return false; + + if (riscv_insn_is_jalr(insn)) + rs1_num = RV_EXTRACT_RS1_REG(insn); + else if (riscv_insn_is_c_jalr(insn)) + rs1_num = RVC_EXTRACT_C2_RS1_REG(insn); + else + return false; + + *target = regs_ptr[rs1_num]; + + return true; +} + +/* + * Checks if the ebreak trap is because of a CFI failure, and handles the trap + * if needed. Returns a bug_trap_type value similarly to report_bug. + */ +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + unsigned long target; + u32 type; + + if (!is_cfi_trap(regs->epc)) + return BUG_TRAP_TYPE_NONE; + + if (!decode_cfi_insn(regs, &target, &type)) + return report_cfi_failure_noaddr(regs, regs->epc); + + return report_cfi_failure(regs, regs->epc, &target, type); +} diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c index 651f2b009c28..ad7f2d712f5f 100644 --- a/arch/riscv/kernel/compat_syscall_table.c +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -9,11 +9,15 @@ #include <asm/syscall.h> #undef __SYSCALL -#define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include <asm/unistd.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, asmlinkage long compat_sys_rt_sigreturn(void); void * const compat_sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 189345773e7e..b86e5e2c3aea 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -11,7 +11,13 @@ compat_vdso-syms += flush_icache COMPAT_CC := $(CC) COMPAT_LD := $(LD) -COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif COMPAT_LD_FLAGS := -melf32lriscv # Disable attributes, as they're useless and break the build. diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S new file mode 100644 index 000000000000..cfdecfbaad62 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.S @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos Inc. */ + +#include <linux/linkage.h> +#include <asm/asm.h> + + .text + +/* void __riscv_copy_words_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using word loads and stores. */ +/* Note: The size is truncated to a multiple of 8 * SZREG */ +ENTRY(__riscv_copy_words_unaligned) + andi a4, a2, ~((8*SZREG)-1) + beqz a4, 2f + add a3, a1, a4 +1: + REG_L a4, 0(a1) + REG_L a5, SZREG(a1) + REG_L a6, 2*SZREG(a1) + REG_L a7, 3*SZREG(a1) + REG_L t0, 4*SZREG(a1) + REG_L t1, 5*SZREG(a1) + REG_L t2, 6*SZREG(a1) + REG_L t3, 7*SZREG(a1) + REG_S a4, 0(a0) + REG_S a5, SZREG(a0) + REG_S a6, 2*SZREG(a0) + REG_S a7, 3*SZREG(a0) + REG_S t0, 4*SZREG(a0) + REG_S t1, 5*SZREG(a0) + REG_S t2, 6*SZREG(a0) + REG_S t3, 7*SZREG(a0) + addi a0, a0, 8*SZREG + addi a1, a1, 8*SZREG + bltu a1, a3, 1b + +2: + ret +END(__riscv_copy_words_unaligned) + +/* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using only byte accesses. */ +/* Note: The size is truncated to a multiple of 8 */ +ENTRY(__riscv_copy_bytes_unaligned) + andi a4, a2, ~(8-1) + beqz a4, 2f + add a3, a1, a4 +1: + lb a4, 0(a1) + lb a5, 1(a1) + lb a6, 2(a1) + lb a7, 3(a1) + lb t0, 4(a1) + lb t1, 5(a1) + lb t2, 6(a1) + lb t3, 7(a1) + sb a4, 0(a0) + sb a5, 1(a0) + sb a6, 2(a0) + sb a7, 3(a0) + sb t0, 4(a0) + sb t1, 5(a0) + sb t2, 6(a0) + sb t3, 7(a0) + addi a0, a0, 8 + addi a1, a1, 8 + bltu a1, a3, 1b + +2: + ret +END(__riscv_copy_bytes_unaligned) diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h new file mode 100644 index 000000000000..e3d70d35b708 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos, Inc. + */ +#ifndef __RISCV_KERNEL_COPY_UNALIGNED_H +#define __RISCV_KERNEL_COPY_UNALIGNED_H + +#include <linux/types.h> + +void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size); +void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size); + +#endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index a2fc952318e9..c17dacb1141c 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -17,6 +17,11 @@ #include <asm/smp.h> #include <asm/pgtable.h> +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} + /* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node. @@ -41,7 +46,7 @@ int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) return 0; } -int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) +int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) { const char *isa; @@ -61,16 +66,53 @@ int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *har return -ENODEV; } + if (of_property_read_string(node, "riscv,isa-base", &isa)) + goto old_interface; + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv32i", *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv64i", *hart); + return -ENODEV; + } + + if (!of_property_present(node, "riscv,isa-extensions")) + return -ENODEV; + + if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "m") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "a") < 0) { + pr_warn("CPU with hartid=%lu does not support ima", *hart); + return -ENODEV; + } + + return 0; + +old_interface: + if (!riscv_isa_fallback) { + pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"", + *hart); + return -ENODEV; + } + if (of_property_read_string(node, "riscv,isa", &isa)) { - pr_warn("CPU with hartid=%lu has no \"riscv,isa\" property\n", *hart); + pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n", + *hart); return -ENODEV; } - if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv32ima", *hart); return -ENODEV; + } - if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv64ima", *hart); return -ENODEV; + } return 0; } @@ -160,132 +202,46 @@ arch_initcall(riscv_cpuinfo_init); #ifdef CONFIG_PROC_FS -#define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ - { \ - .uprop = #UPROP, \ - .isa_ext_id = EXTID, \ - } - -/* - * The canonical order of ISA extension names in the ISA string is defined in - * chapter 27 of the unprivileged specification. - * - * Ordinarily, for in-kernel data structures, this order is unimportant but - * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. - * - * The specification uses vague wording, such as should, when it comes to - * ordering, so for our purposes the following rules apply: - * - * 1. All multi-letter extensions must be separated from other extensions by an - * underscore. - * - * 2. Additional standard extensions (starting with 'Z') must be sorted after - * single-letter extensions and before any higher-privileged extensions. - - * 3. The first letter following the 'Z' conventionally indicates the most - * closely related alphabetical extension category, IMAFDQLCBKJTPVH. - * If multiple 'Z' extensions are named, they must be ordered first by - * category, then alphabetically within a category. - * - * 3. Standard supervisor-level extensions (starting with 'S') must be listed - * after standard unprivileged extensions. If multiple supervisor-level - * extensions are listed, they must be ordered alphabetically. - * - * 4. Standard machine-level extensions (starting with 'Zxm') must be listed - * after any lower-privileged, standard extensions. If multiple - * machine-level extensions are listed, they must be ordered - * alphabetically. - * - * 5. Non-standard extensions (starting with 'X') must be listed after all - * standard extensions. If multiple non-standard extensions are listed, they - * must be ordered alphabetically. - * - * An example string following the order is: - * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux - * - * New entries to this struct should follow the ordering rules described above. - */ -static struct riscv_isa_ext_data isa_ext_arr[] = { - __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), - __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), - __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), - __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), - __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), - __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), - __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), - __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), - __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), - __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), - __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), - __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), - __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), - __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), - __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), - __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), - __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), - __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), -}; - -static void print_isa_ext(struct seq_file *f) +static void print_isa(struct seq_file *f) { - struct riscv_isa_ext_data *edata; - int i = 0, arr_sz; - - arr_sz = ARRAY_SIZE(isa_ext_arr) - 1; + seq_puts(f, "isa\t\t: "); - /* No extension support available */ - if (arr_sz <= 0) - return; + if (IS_ENABLED(CONFIG_32BIT)) + seq_write(f, "rv32", 4); + else + seq_write(f, "rv64", 4); - for (i = 0; i <= arr_sz; i++) { - edata = &isa_ext_arr[i]; - if (!__riscv_isa_extension_available(NULL, edata->isa_ext_id)) + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (!__riscv_isa_extension_available(NULL, riscv_isa_ext[i].id)) continue; - seq_printf(f, "_%s", edata->uprop); - } -} - -/* - * These are the only valid base (single letter) ISA extensions as per the spec. - * It also specifies the canonical order in which it appears in the spec. - * Some of the extension may just be a place holder for now (B, K, P, J). - * This should be updated once corresponding extensions are ratified. - */ -static const char base_riscv_exts[13] = "imafdqcbkjpvh"; -static void print_isa(struct seq_file *f, const char *isa) -{ - int i; + /* Only multi-letter extensions are split by underscores */ + if (strnlen(riscv_isa_ext[i].name, 2) != 1) + seq_puts(f, "_"); - seq_puts(f, "isa\t\t: "); - /* Print the rv[64/32] part */ - seq_write(f, isa, 4); - for (i = 0; i < sizeof(base_riscv_exts); i++) { - if (__riscv_isa_extension_available(NULL, base_riscv_exts[i] - 'a')) - /* Print only enabled the base ISA extensions */ - seq_write(f, &base_riscv_exts[i], 1); + seq_printf(f, "%s", riscv_isa_ext[i].name); } - print_isa_ext(f); + seq_puts(f, "\n"); } static void print_mmu(struct seq_file *f) { - char sv_type[16]; + const char *sv_type; #ifdef CONFIG_MMU #if defined(CONFIG_32BIT) - strncpy(sv_type, "sv32", 5); + sv_type = "sv32"; #elif defined(CONFIG_64BIT) if (pgtable_l5_enabled) - strncpy(sv_type, "sv57", 5); + sv_type = "sv57"; else if (pgtable_l4_enabled) - strncpy(sv_type, "sv48", 5); + sv_type = "sv48"; else - strncpy(sv_type, "sv39", 5); + sv_type = "sv39"; #endif #else - strncpy(sv_type, "none", 5); + sv_type = "none"; #endif /* CONFIG_MMU */ seq_printf(f, "mmu\t\t: %s\n", sv_type); } @@ -316,27 +272,21 @@ static int c_show(struct seq_file *m, void *v) unsigned long cpu_id = (unsigned long)v - 1; struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); struct device_node *node; - const char *compat, *isa; + const char *compat; seq_printf(m, "processor\t: %lu\n", cpu_id); seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id)); + print_isa(m); + print_mmu(m); if (acpi_disabled) { node = of_get_cpu_node(cpu_id, NULL); - if (!of_property_read_string(node, "riscv,isa", &isa)) - print_isa(m, isa); - print_mmu(m); if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); of_node_put(node); - } else { - if (!acpi_get_riscv_isa(NULL, cpu_id, &isa)) - print_isa(m, isa); - - print_mmu(m); } seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index bdcf460ea53d..1cfbba65d11a 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -13,18 +13,24 @@ #include <linux/memory.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> #include <asm/acpi.h> #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> +#include <asm/hwprobe.h> #include <asm/patch.h> #include <asm/processor.h> #include <asm/vector.h> +#include "copy-unaligned.h" + #define NUM_ALPHA_EXTS ('z' - 'a' + 1) +#define MISALIGNED_ACCESS_JIFFIES_LG2 1 +#define MISALIGNED_BUFFER_SIZE 0x4000 +#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) + unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ @@ -99,29 +105,252 @@ static bool riscv_isa_extension_check(int id) return true; } -void __init riscv_fill_hwcap(void) +#define __RISCV_ISA_EXT_DATA(_name, _id) { \ + .name = #_name, \ + .property = #_name, \ + .id = _id, \ +} + +/* + * The canonical order of ISA extension names in the ISA string is defined in + * chapter 27 of the unprivileged specification. + * + * Ordinarily, for in-kernel data structures, this order is unimportant but + * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. + * + * The specification uses vague wording, such as should, when it comes to + * ordering, so for our purposes the following rules apply: + * + * 1. All multi-letter extensions must be separated from other extensions by an + * underscore. + * + * 2. Additional standard extensions (starting with 'Z') must be sorted after + * single-letter extensions and before any higher-privileged extensions. + * + * 3. The first letter following the 'Z' conventionally indicates the most + * closely related alphabetical extension category, IMAFDQLCBKJTPVH. + * If multiple 'Z' extensions are named, they must be ordered first by + * category, then alphabetically within a category. + * + * 3. Standard supervisor-level extensions (starting with 'S') must be listed + * after standard unprivileged extensions. If multiple supervisor-level + * extensions are listed, they must be ordered alphabetically. + * + * 4. Standard machine-level extensions (starting with 'Zxm') must be listed + * after any lower-privileged, standard extensions. If multiple + * machine-level extensions are listed, they must be ordered + * alphabetically. + * + * 5. Non-standard extensions (starting with 'X') must be listed after all + * standard extensions. If multiple non-standard extensions are listed, they + * must be ordered alphabetically. + * + * An example string following the order is: + * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux + * + * New entries to this struct should follow the ordering rules described above. + */ +const struct riscv_isa_ext_data riscv_isa_ext[] = { + __RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i), + __RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m), + __RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a), + __RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f), + __RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d), + __RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q), + __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), + __RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b), + __RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k), + __RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j), + __RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p), + __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), + __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), + __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), + __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), + __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), + __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), + __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), + __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), + __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), + __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), + __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), +}; + +const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); + +static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo, + unsigned long *isa2hwcap, const char *isa) +{ + /* + * For all possible cpus, we have already validated in + * the boot process that they at least contain "rv" and + * whichever of "32"/"64" this kernel supports, and so this + * section can be skipped. + */ + isa += 4; + + while (*isa) { + const char *ext = isa++; + const char *ext_end = isa; + bool ext_long = false, ext_err = false; + + switch (*ext) { + case 's': + /* + * Workaround for invalid single-letter 's' & 'u'(QEMU). + * No need to set the bit in riscv_isa as 's' & 'u' are + * not valid ISA extensions. It works until multi-letter + * extension starting with "Su" appears. + */ + if (ext[-1] != '_' && ext[1] == 'u') { + ++isa; + ext_err = true; + break; + } + fallthrough; + case 'S': + case 'x': + case 'X': + case 'z': + case 'Z': + /* + * Before attempting to parse the extension itself, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + * + * Next, as the extensions version is currently ignored, we + * eliminate that portion. This is done by parsing backwards from + * the end of the extension, removing any numbers. This may be a + * major or minor number however, so the process is repeated if a + * minor number was found. + * + * ext_end is intended to represent the first character *after* the + * name portion of an extension, but will be decremented to the last + * character itself while eliminating the extensions version number. + * A simple re-increment solves this problem. + */ + ext_long = true; + for (; *isa && *isa != '_'; ++isa) + if (unlikely(!isalnum(*isa))) + ext_err = true; + + ext_end = isa; + if (unlikely(ext_err)) + break; + + if (!isdigit(ext_end[-1])) + break; + + while (isdigit(*--ext_end)) + ; + + if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { + ++ext_end; + break; + } + + while (isdigit(*--ext_end)) + ; + + ++ext_end; + break; + default: + /* + * Things are a little easier for single-letter extensions, as they + * are parsed forwards. + * + * After checking that our starting position is valid, we need to + * ensure that, when isa was incremented at the start of the loop, + * that it arrived at the start of the next extension. + * + * If we are already on a non-digit, there is nothing to do. Either + * we have a multi-letter extension's _, or the start of an + * extension. + * + * Otherwise we have found the current extension's major version + * number. Parse past it, and a subsequent p/minor version number + * if present. The `p` extension must not appear immediately after + * a number, so there is no fear of missing it. + * + */ + if (unlikely(!isalpha(*ext))) { + ext_err = true; + break; + } + + if (!isdigit(*isa)) + break; + + while (isdigit(*++isa)) + ; + + if (tolower(*isa) != 'p') + break; + + if (!isdigit(*++isa)) { + --isa; + break; + } + + while (isdigit(*++isa)) + ; + + break; + } + + /* + * The parser expects that at the start of an iteration isa points to the + * first character of the next extension. As we stop parsing an extension + * on meeting a non-alphanumeric character, an extra increment is needed + * where the succeeding extension is a multi-letter prefixed with an "_". + */ + if (*isa == '_') + ++isa; + +#define SET_ISA_EXT_MAP(name, bit) \ + do { \ + if ((ext_end - ext == strlen(name)) && \ + !strncasecmp(ext, name, strlen(name)) && \ + riscv_isa_extension_check(bit)) \ + set_bit(bit, isainfo->isa); \ + } while (false) \ + + if (unlikely(ext_err)) + continue; + if (!ext_long) { + int nr = tolower(*ext) - 'a'; + + if (riscv_isa_extension_check(nr)) { + *this_hwcap |= isa2hwcap[nr]; + set_bit(nr, isainfo->isa); + } + } else { + for (int i = 0; i < riscv_isa_ext_count; i++) + SET_ISA_EXT_MAP(riscv_isa_ext[i].name, + riscv_isa_ext[i].id); + } +#undef SET_ISA_EXT_MAP + } +} + +static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) { struct device_node *node; const char *isa; - char print_str[NUM_ALPHA_EXTS + 1]; - int i, j, rc; - unsigned long isa2hwcap[26] = {0}; + int rc; struct acpi_table_header *rhct; acpi_status status; unsigned int cpu; - isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; - isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; - isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A; - isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; - isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; - isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; - isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; - - elf_hwcap = 0; - - bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); - if (!acpi_disabled) { status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); if (ACPI_FAILURE(status)) @@ -153,176 +382,7 @@ void __init riscv_fill_hwcap(void) } } - /* - * For all possible cpus, we have already validated in - * the boot process that they at least contain "rv" and - * whichever of "32"/"64" this kernel supports, and so this - * section can be skipped. - */ - isa += 4; - - while (*isa) { - const char *ext = isa++; - const char *ext_end = isa; - bool ext_long = false, ext_err = false; - - switch (*ext) { - case 's': - /* - * Workaround for invalid single-letter 's' & 'u'(QEMU). - * No need to set the bit in riscv_isa as 's' & 'u' are - * not valid ISA extensions. It works until multi-letter - * extension starting with "Su" appears. - */ - if (ext[-1] != '_' && ext[1] == 'u') { - ++isa; - ext_err = true; - break; - } - fallthrough; - case 'S': - case 'x': - case 'X': - case 'z': - case 'Z': - /* - * Before attempting to parse the extension itself, we find its end. - * As multi-letter extensions must be split from other multi-letter - * extensions with an "_", the end of a multi-letter extension will - * either be the null character or the "_" at the start of the next - * multi-letter extension. - * - * Next, as the extensions version is currently ignored, we - * eliminate that portion. This is done by parsing backwards from - * the end of the extension, removing any numbers. This may be a - * major or minor number however, so the process is repeated if a - * minor number was found. - * - * ext_end is intended to represent the first character *after* the - * name portion of an extension, but will be decremented to the last - * character itself while eliminating the extensions version number. - * A simple re-increment solves this problem. - */ - ext_long = true; - for (; *isa && *isa != '_'; ++isa) - if (unlikely(!isalnum(*isa))) - ext_err = true; - - ext_end = isa; - if (unlikely(ext_err)) - break; - - if (!isdigit(ext_end[-1])) - break; - - while (isdigit(*--ext_end)) - ; - - if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { - ++ext_end; - break; - } - - while (isdigit(*--ext_end)) - ; - - ++ext_end; - break; - default: - /* - * Things are a little easier for single-letter extensions, as they - * are parsed forwards. - * - * After checking that our starting position is valid, we need to - * ensure that, when isa was incremented at the start of the loop, - * that it arrived at the start of the next extension. - * - * If we are already on a non-digit, there is nothing to do. Either - * we have a multi-letter extension's _, or the start of an - * extension. - * - * Otherwise we have found the current extension's major version - * number. Parse past it, and a subsequent p/minor version number - * if present. The `p` extension must not appear immediately after - * a number, so there is no fear of missing it. - * - */ - if (unlikely(!isalpha(*ext))) { - ext_err = true; - break; - } - - if (!isdigit(*isa)) - break; - - while (isdigit(*++isa)) - ; - - if (tolower(*isa) != 'p') - break; - - if (!isdigit(*++isa)) { - --isa; - break; - } - - while (isdigit(*++isa)) - ; - - break; - } - - /* - * The parser expects that at the start of an iteration isa points to the - * first character of the next extension. As we stop parsing an extension - * on meeting a non-alphanumeric character, an extra increment is needed - * where the succeeding extension is a multi-letter prefixed with an "_". - */ - if (*isa == '_') - ++isa; - -#define SET_ISA_EXT_MAP(name, bit) \ - do { \ - if ((ext_end - ext == sizeof(name) - 1) && \ - !strncasecmp(ext, name, sizeof(name) - 1) && \ - riscv_isa_extension_check(bit)) \ - set_bit(bit, isainfo->isa); \ - } while (false) \ - - if (unlikely(ext_err)) - continue; - if (!ext_long) { - int nr = tolower(*ext) - 'a'; - - if (riscv_isa_extension_check(nr)) { - this_hwcap |= isa2hwcap[nr]; - set_bit(nr, isainfo->isa); - } - } else { - /* sorted alphabetically */ - SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA); - SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA); - SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); - SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC); - SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); - SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT); - SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); - SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA); - SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); - SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS); - SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); - SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ); - SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE); - } -#undef SET_ISA_EXT_MAP - } - - /* - * Linux requires the following extensions, so we may as well - * always set them. - */ - set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); - set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); + riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa); /* * These ones were as they were part of the base ISA when the @@ -330,6 +390,8 @@ void __init riscv_fill_hwcap(void) * unconditionally where `i` is in riscv,isa on DT systems. */ if (acpi_disabled) { + set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); set_bit(RISCV_ISA_EXT_ZICNTR, isainfo->isa); set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa); } @@ -352,9 +414,107 @@ void __init riscv_fill_hwcap(void) if (!acpi_disabled && rhct) acpi_put_table((struct acpi_table_header *)rhct); +} + +static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) { + unsigned long this_hwcap = 0; + struct device_node *cpu_node; + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + continue; + } + + if (!of_property_present(cpu_node, "riscv,isa-extensions")) { + of_node_put(cpu_node); + continue; + } + + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + riscv_isa_ext[i].property) < 0) + continue; + + if (!riscv_isa_extension_check(riscv_isa_ext[i].id)) + continue; + + /* Only single letter extensions get set in hwcap */ + if (strnlen(riscv_isa_ext[i].name, 2) == 1) + this_hwcap |= isa2hwcap[riscv_isa_ext[i].id]; + + set_bit(riscv_isa_ext[i].id, isainfo->isa); + } + + of_node_put(cpu_node); + + /* + * All "okay" harts should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + } - /* We don't support systems with F but without D, so mask those out - * here. */ + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + return -ENOENT; + + return 0; +} + +#ifdef CONFIG_RISCV_ISA_FALLBACK +bool __initdata riscv_isa_fallback = true; +#else +bool __initdata riscv_isa_fallback; +static int __init riscv_isa_fallback_setup(char *__unused) +{ + riscv_isa_fallback = true; + return 1; +} +early_param("riscv_isa_fallback", riscv_isa_fallback_setup); +#endif + +void __init riscv_fill_hwcap(void) +{ + char print_str[NUM_ALPHA_EXTS + 1]; + unsigned long isa2hwcap[26] = {0}; + int i, j; + + isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I; + isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M; + isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A; + isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F; + isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D; + isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C; + isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V; + + if (!acpi_disabled) { + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } else { + int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap); + + if (ret && riscv_isa_fallback) { + pr_info("Falling back to deprecated \"riscv,isa\"\n"); + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } + } + + /* + * We don't support systems with F but without D, so mask those out + * here. + */ if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { pr_info("This kernel does not support systems with F but not D\n"); elf_hwcap &= ~COMPAT_HWCAP_ISA_F; @@ -396,6 +556,103 @@ unsigned long riscv_get_elf_hwcap(void) return hwcap; } +void check_unaligned_access(int cpu) +{ + u64 start_cycles, end_cycles; + u64 word_cycles; + u64 byte_cycles; + int ratio; + unsigned long start_jiffies, now; + struct page *page; + void *dst; + void *src; + long speed = RISCV_HWPROBE_MISALIGNED_SLOW; + + page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE)); + if (!page) { + pr_warn("Can't alloc pages to measure memcpy performance"); + return; + } + + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)page_address(page) | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + word_cycles = -1ULL; + /* Do a warmup. */ + __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + preempt_disable(); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + /* + * For a fixed amount of time, repeatedly try the function, and take + * the best time in cycles as the measurement. + */ + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + /* Ensure the CSR read can't reorder WRT to the copy. */ + mb(); + __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE); + /* Ensure the copy ends before the end time is snapped. */ + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < word_cycles) + word_cycles = end_cycles - start_cycles; + } + + byte_cycles = -1ULL; + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + start_jiffies = jiffies; + while ((now = jiffies) == start_jiffies) + cpu_relax(); + + while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) { + start_cycles = get_cycles64(); + mb(); + __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE); + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < byte_cycles) + byte_cycles = end_cycles - start_cycles; + } + + preempt_enable(); + + /* Don't divide by zero. */ + if (!word_cycles || !byte_cycles) { + pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", + cpu); + + goto out; + } + + if (word_cycles < byte_cycles) + speed = RISCV_HWPROBE_MISALIGNED_FAST; + + ratio = div_u64((byte_cycles * 100), word_cycles); + pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n", + cpu, + ratio / 100, + ratio % 100, + (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow"); + + per_cpu(misaligned_access_speed, cpu) = speed; + +out: + __free_pages(page, get_order(MISALIGNED_BUFFER_SIZE)); +} + +static int check_unaligned_access_boot_cpu(void) +{ + check_unaligned_access(0); + return 0; +} + +arch_initcall(check_unaligned_access_boot_cpu); + #ifdef CONFIG_RISCV_ALTERNATIVE /* * Alternative patch sites consider 48 bits when determining when to patch diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index b351a3c01355..55f1d7856b54 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -18,4 +18,6 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); #endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); + vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", + kernel_map.va_kernel_pa_offset); } diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 5372b708fae2..f4099059ed8f 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -260,7 +260,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, cmdline = modified_cmdline; } -#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY +#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY /* Add purgatory to the image */ kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; @@ -274,14 +274,14 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf, sizeof(kernel_start), 0); if (ret) pr_err("Error update purgatory ret=%d\n", ret); -#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */ +#endif /* CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY */ /* Add the initrd to the image */ if (initrd != NULL) { kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; - kbuf.top_down = false; + kbuf.top_down = true; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) @@ -425,6 +425,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, * sym, instead of searching the whole relsec. */ case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: case R_RISCV_CALL: *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | ENCODE_UJTYPE_IMM(val - addr); diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11c3b94c4534..3710ea5d160f 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -289,10 +289,6 @@ clear_bss: blt a3, a4, clear_bss clear_bss_done: #endif - /* Save hart ID and DTB physical address */ - mv s0, a0 - mv s1, a1 - la a2, boot_cpu_hartid XIP_FIXUP_OFFSET a2 REG_S a0, (a2) @@ -306,7 +302,7 @@ clear_bss_done: la a0, __dtb_start XIP_FIXUP_OFFSET a0 #else - mv a0, s1 + mv a0, a1 #endif /* CONFIG_BUILTIN_DTB */ call setup_vm #ifdef CONFIG_MMU diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index d0577cc6a081..a8efa053c4a5 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -84,6 +84,9 @@ void do_softirq_own_stack(void) : [sp] "r" (sp) : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", "t4", "t5", "t6", +#ifndef CONFIG_FRAME_POINTER + "s0", +#endif "memory"); } else #endif diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 8a6e5a9e842a..8818a8fa9ff3 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm.h> #include <asm/csr.h> #include <asm/unistd.h> @@ -47,15 +48,19 @@ addi sp, sp, 4*SZREG .endm -ENTRY(ftrace_stub) +SYM_TYPED_FUNC_START(ftrace_stub) #ifdef CONFIG_DYNAMIC_FTRACE .global MCOUNT_NAME .set MCOUNT_NAME, ftrace_stub #endif ret -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + ENTRY(return_to_handler) /* * On implementing the frame point test, the ideal way is to compare the diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c index 64f6183b4717..65d9590bfb9f 100644 --- a/arch/riscv/kernel/probes/decode-insn.c +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -29,13 +29,14 @@ riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) * TODO: the REJECTED ones below need to be implemented */ #ifdef CONFIG_RISCV_ISA_C - RISCV_INSN_REJECTED(c_j, insn); - RISCV_INSN_REJECTED(c_jr, insn); RISCV_INSN_REJECTED(c_jal, insn); - RISCV_INSN_REJECTED(c_jalr, insn); - RISCV_INSN_REJECTED(c_beqz, insn); - RISCV_INSN_REJECTED(c_bnez, insn); RISCV_INSN_REJECTED(c_ebreak, insn); + + RISCV_INSN_SET_SIMULATE(c_j, insn); + RISCV_INSN_SET_SIMULATE(c_jr, insn); + RISCV_INSN_SET_SIMULATE(c_jalr, insn); + RISCV_INSN_SET_SIMULATE(c_beqz, insn); + RISCV_INSN_SET_SIMULATE(c_bnez, insn); #endif RISCV_INSN_SET_SIMULATE(jal, insn); diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index 7441ac8a6843..d3099d67816d 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -188,3 +188,108 @@ bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *r return true; } + +bool __kprobes simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 15 13 12 2 1 0 + * | funct3 | offset[11|4|9:8|10|6|7|3:1|5] | opcode | + * 3 11 2 + */ + + s32 offset; + + offset = ((opcode >> 3) & 0x7) << 1; + offset |= ((opcode >> 11) & 0x1) << 4; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 7) & 0x1) << 6; + offset |= ((opcode >> 6) & 0x1) << 7; + offset |= ((opcode >> 9) & 0x3) << 8; + offset |= ((opcode >> 8) & 0x1) << 10; + offset |= ((opcode >> 12) & 0x1) << 11; + + instruction_pointer_set(regs, addr + sign_extend32(offset, 11)); + + return true; +} + +static bool __kprobes simulate_c_jr_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_jalr) +{ + /* + * 15 12 11 7 6 2 1 0 + * | funct4 | rs1 | rs2 | op | + * 4 5 5 2 + */ + + unsigned long jump_addr; + + u32 rs1 = (opcode >> 7) & 0x1f; + + if (rs1 == 0) /* C.JR is only valid when rs1 != x0 */ + return false; + + if (!rv_insn_reg_get_val(regs, rs1, &jump_addr)) + return false; + + if (is_jalr && !rv_insn_reg_set_val(regs, 1, addr + 2)) + return false; + + instruction_pointer_set(regs, jump_addr); + + return true; +} + +bool __kprobes simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, false); +} + +bool __kprobes simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, true); +} + +static bool __kprobes simulate_c_bnez_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_bnez) +{ + /* + * 15 13 12 10 9 7 6 2 1 0 + * | funct3 | offset[8|4:3] | rs1' | offset[7:6|2:1|5] | op | + * 3 3 3 5 2 + */ + + s32 offset; + u32 rs1; + unsigned long rs1_val; + + rs1 = 0x8 | ((opcode >> 7) & 0x7); + + if (!rv_insn_reg_get_val(regs, rs1, &rs1_val)) + return false; + + if ((rs1_val != 0 && is_bnez) || (rs1_val == 0 && !is_bnez)) { + offset = ((opcode >> 3) & 0x3) << 1; + offset |= ((opcode >> 10) & 0x3) << 3; + offset |= ((opcode >> 2) & 0x1) << 5; + offset |= ((opcode >> 5) & 0x3) << 6; + offset |= ((opcode >> 12) & 0x1) << 8; + offset = sign_extend32(offset, 8); + } else { + offset = 2; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, true); +} + +bool __kprobes simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, false); +} diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h index 61e35db31001..44ebbc444db9 100644 --- a/arch/riscv/kernel/probes/simulate-insn.h +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -24,5 +24,10 @@ bool simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs); bool simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs); #endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 1d572cf3140f..487303e3ef22 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -25,9 +25,6 @@ enum riscv_regset { #ifdef CONFIG_FPU REGSET_F, #endif -#ifdef CONFIG_RISCV_ISA_V - REGSET_V, -#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -84,61 +81,6 @@ static int riscv_fpr_set(struct task_struct *target, } #endif -#ifdef CONFIG_RISCV_ISA_V -static int riscv_vr_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) -{ - struct __riscv_v_ext_state *vstate = &target->thread.vstate; - - if (!riscv_v_vstate_query(task_pt_regs(target))) - return -EINVAL; - - /* - * Ensure the vector registers have been saved to the memory before - * copying them to membuf. - */ - if (target == current) - riscv_v_vstate_save(current, task_pt_regs(current)); - - /* Copy vector header from vstate. */ - membuf_write(&to, vstate, offsetof(struct __riscv_v_ext_state, datap)); - membuf_zero(&to, sizeof(vstate->datap)); - - /* Copy all the vector registers from vstate. */ - return membuf_write(&to, vstate->datap, riscv_v_vsize); -} - -static int riscv_vr_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret, size; - struct __riscv_v_ext_state *vstate = &target->thread.vstate; - - if (!riscv_v_vstate_query(task_pt_regs(target))) - return -EINVAL; - - /* Copy rest of the vstate except datap */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate, 0, - offsetof(struct __riscv_v_ext_state, datap)); - if (unlikely(ret)) - return ret; - - /* Skip copy datap. */ - size = sizeof(vstate->datap); - count -= size; - ubuf += size; - - /* Copy all the vector registers. */ - pos = 0; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, - 0, riscv_v_vsize); - return ret; -} -#endif - static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -158,17 +100,6 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_fpr_set, }, #endif -#ifdef CONFIG_RISCV_ISA_V - [REGSET_V] = { - .core_note_type = NT_RISCV_VECTOR, - .align = 16, - .n = ((32 * RISCV_MAX_VLENB) + - sizeof(struct __riscv_v_ext_state)) / sizeof(__u32), - .size = sizeof(__u32), - .regset_get = riscv_vr_get, - .set = riscv_vr_set, - }, -#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 971fe776e2f8..32c2e1eb71bd 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -178,6 +178,11 @@ static void __init init_resources(void) if (ret < 0) goto error; } + if (crashk_low_res.start != crashk_low_res.end) { + ret = add_resource(&iomem_resource, &crashk_low_res); + if (ret < 0) + goto error; + } #endif #ifdef CONFIG_CRASH_DUMP @@ -311,6 +316,7 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && riscv_isa_extension_available(NULL, ZICBOM)) riscv_noncoherent_supported(); + riscv_set_dma_cache_alignment(); } static int __init topology_init(void) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 85bbce0f758c..40420afbb1a0 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -61,11 +61,6 @@ int riscv_hartid_to_cpuid(unsigned long hartid) return -ENOENT; } -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == cpuid_to_hartid_map(cpu); -} - static void ipi_stop(void) { set_cpu_online(smp_processor_id(), false); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index f4d6acb38dd0..1b8da4e40a4d 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -26,6 +26,7 @@ #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> #include <asm/cpu_ops.h> +#include <asm/cpufeature.h> #include <asm/irq.h> #include <asm/mmu_context.h> #include <asm/numa.h> @@ -245,7 +246,7 @@ asmlinkage __visible void smp_callin(void) numa_add_cpu(curr_cpuid); set_cpu_online(curr_cpuid, 1); - probe_vendor_features(curr_cpuid); + check_unaligned_access(curr_cpuid); if (has_vector()) { if (riscv_v_setup_vsize()) diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index 12b52afe09a4..f7960c7c5f9e 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -5,6 +5,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> @@ -58,7 +59,7 @@ ENTRY(__cpu_suspend_enter) ret END(__cpu_suspend_enter) -ENTRY(__cpu_resume_enter) +SYM_TYPED_FUNC_START(__cpu_resume_enter) /* Load the global pointer */ .option push .option norelax @@ -94,4 +95,4 @@ ENTRY(__cpu_resume_enter) /* Return to C code */ ret -END(__cpu_resume_enter) +SYM_FUNC_END(__cpu_resume_enter) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 26ef5526bfb4..473159b5f303 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -335,3 +335,9 @@ SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, return do_riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags); } + +/* Not defined using SYSCALL_DEFINE0 to avoid error injection */ +asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused) +{ + return -ENOSYS; +} diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index 44b1420a2270..dda913764903 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -10,9 +10,13 @@ #include <asm/syscall.h> #undef __SYSCALL -#define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include <asm/unistd.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, void * const sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = sys_ni_syscall, + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f910dfccbf5d..19807c4d3805 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -21,6 +21,7 @@ #include <asm/asm-prototypes.h> #include <asm/bug.h> +#include <asm/cfi.h> #include <asm/csr.h> #include <asm/processor.h> #include <asm/ptrace.h> @@ -271,7 +272,8 @@ void handle_break(struct pt_regs *regs) == NOTIFY_STOP) return; #endif - else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN) + else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) regs->epc += get_break_insn_length(regs->epc); else die(regs, "Kernel BUG"); @@ -297,7 +299,7 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) { if (user_mode(regs)) { - ulong syscall = regs->a7; + long syscall = regs->a7; regs->epc += 4; regs->orig_a0 = regs->a0; @@ -306,9 +308,9 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) syscall = syscall_enter_from_user_mode(regs, syscall); - if (syscall < NR_syscalls) + if (syscall >= 0 && syscall < NR_syscalls) syscall_handler(regs, syscall); - else + else if (syscall != -1) regs->a0 = -ENOSYS; syscall_exit_to_user_mode(regs); @@ -372,6 +374,9 @@ asmlinkage void noinstr do_irq(struct pt_regs *regs) : [sp] "r" (sp), [regs] "r" (regs) : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", "t4", "t5", "t6", +#ifndef CONFIG_FRAME_POINTER + "s0", +#endif "memory"); } else #endif diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index ec486e5369d9..09b47ebacf2e 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -17,8 +17,11 @@ ENTRY(__asm_copy_from_user) li t6, SR_SUM csrs CSR_STATUS, t6 - /* Save for return value */ - mv t5, a2 + /* + * Save the terminal address which will be used to compute the number + * of bytes copied in case of a fixup exception. + */ + add t5, a0, a2 /* * Register allocation for code below: @@ -176,7 +179,7 @@ ENTRY(__asm_copy_from_user) 10: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, t5 + sub a0, t5, a0 ret ENDPROC(__asm_copy_to_user) ENDPROC(__asm_copy_from_user) @@ -228,7 +231,7 @@ ENTRY(__clear_user) 11: /* Disable access to user memory */ csrc CSR_STATUS, t6 - mv a0, a1 + sub a0, a3, a0 ret ENDPROC(__clear_user) EXPORT_SYMBOL(__clear_user) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index fbc59b3f69f2..f1387272a551 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -82,18 +82,11 @@ void flush_icache_mm(struct mm_struct *mm, bool local) #ifdef CONFIG_MMU void flush_icache_pte(pte_t pte) { - struct page *page = pte_page(pte); + struct folio *folio = page_folio(pte_page(pte)); - /* - * HugeTLB pages are always fully mapped, so only setting head page's - * PG_dcache_clean flag is enough. - */ - if (PageHuge(page)) - page = compound_head(page); - - if (!test_bit(PG_dcache_clean, &page->flags)) { + if (!test_bit(PG_dcache_clean, &folio->flags)) { flush_icache_all(); - set_bit(PG_dcache_clean, &page->flags); + set_bit(PG_dcache_clean, &folio->flags); } } #endif /* CONFIG_MMU */ diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index 12e22e7330e7..217fd4de6134 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -67,7 +67,7 @@ static void __flush_context(void) lockdep_assert_held(&context_lock); /* Update the list of reserved ASIDs and the ASID bitmap. */ - bitmap_clear(context_asid_map, 0, num_asids); + bitmap_zero(context_asid_map, num_asids); /* Mark already active ASIDs as used */ for_each_possible_cpu(i) { diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index 06b8fea58e20..f269990e26c3 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -11,6 +11,8 @@ #include <asm/cacheflush.h> static bool noncoherent_supported __ro_after_init; +int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN; +EXPORT_SYMBOL_GPL(dma_cache_alignment); static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size) { @@ -120,3 +122,9 @@ void riscv_noncoherent_supported(void) "Non-coherent DMA support enabled without a block size\n"); noncoherent_supported = true; } + +void __init riscv_set_dma_cache_alignment(void) +{ + if (!noncoherent_supported) + dma_cache_alignment = 1; +} diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 6ea2cce4cc17..6115d7514972 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -283,7 +283,6 @@ void handle_page_fault(struct pt_regs *regs) flags |= FAULT_FLAG_WRITE; else if (cause == EXC_INST_PAGE_FAULT) flags |= FAULT_FLAG_INSTRUCTION; -#ifdef CONFIG_PER_VMA_LOCK if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -297,7 +296,8 @@ void handle_page_fault(struct pt_regs *regs) } fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); @@ -311,7 +311,6 @@ void handle_page_fault(struct pt_regs *regs) return; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ retry: vma = lock_mm_and_find_vma(mm, addr, regs); @@ -368,9 +367,7 @@ retry: mmap_read_unlock(mm); -#ifdef CONFIG_PER_VMA_LOCK done: -#endif if (unlikely(fault & VM_FAULT_ERROR)) { tsk->thread.bad_cause = cause; mm_fault_error(regs, addr, fault); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 70fb31960b63..943c18d6ef4d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -26,12 +26,13 @@ #include <linux/kfence.h> #include <asm/fixmap.h> -#include <asm/tlbflush.h> -#include <asm/sections.h> -#include <asm/soc.h> #include <asm/io.h> -#include <asm/ptdump.h> #include <asm/numa.h> +#include <asm/pgtable.h> +#include <asm/ptdump.h> +#include <asm/sections.h> +#include <asm/soc.h> +#include <asm/tlbflush.h> #include "../kernel/head.h" @@ -214,8 +215,13 @@ static void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); phys_ram_end = memblock_end_of_DRAM(); + + /* + * Make sure we align the start of the memory on a PMD boundary so that + * at worst, we map the linear mapping with PMD mappings. + */ if (!IS_ENABLED(CONFIG_XIP_KERNEL)) - phys_ram_base = memblock_start_of_DRAM(); + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -353,12 +359,10 @@ static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va) static phys_addr_t __init alloc_pte_late(uintptr_t va) { - unsigned long vaddr; + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr || !pgtable_pte_page_ctor(virt_to_page((void *)vaddr))); - - return __pa(vaddr); + BUG_ON(!ptdesc || !pagetable_pte_ctor(ptdesc)); + return __pa((pte_t *)ptdesc_address(ptdesc)); } static void __init create_pte_mapping(pte_t *ptep, @@ -436,12 +440,10 @@ static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) static phys_addr_t __init alloc_pmd_late(uintptr_t va) { - unsigned long vaddr; - - vaddr = __get_free_page(GFP_KERNEL); - BUG_ON(!vaddr || !pgtable_pmd_page_ctor(virt_to_page((void *)vaddr))); + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0); - return __pa(vaddr); + BUG_ON(!ptdesc || !pagetable_pmd_ctor(ptdesc)); + return __pa((pmd_t *)ptdesc_address(ptdesc)); } static void __init create_pmd_mapping(pmd_t *pmdp, @@ -1297,6 +1299,28 @@ static inline void setup_vm_final(void) } #endif /* CONFIG_MMU */ +/* Reserve 128M low memory by default for swiotlb buffer */ +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) + +static int __init reserve_crashkernel_low(unsigned long long low_size) +{ + unsigned long long low_base; + + low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit); + if (!low_base) { + pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); + return -ENOMEM; + } + + pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + low_base, low_base + low_size, low_size >> 20); + + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + + return 0; +} + /* * reserve_crashkernel() - reserves memory for crash kernel * @@ -1308,8 +1332,12 @@ static void __init reserve_crashkernel(void) { unsigned long long crash_base = 0; unsigned long long crash_size = 0; + unsigned long long crash_low_size = 0; unsigned long search_start = memblock_start_of_DRAM(); - unsigned long search_end = memblock_end_of_DRAM(); + unsigned long search_end = (unsigned long)dma32_phys_limit; + char *cmdline = boot_command_line; + bool fixed_base = false; + bool high = false; int ret = 0; @@ -1325,14 +1353,36 @@ static void __init reserve_crashkernel(void) return; } - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base); - if (ret || !crash_size) + if (ret == -ENOENT) { + /* Fallback to crashkernel=X,[high,low] */ + ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base); + if (ret || !crash_size) + return; + + /* + * crashkernel=Y,low is valid only when crashkernel=X,high + * is passed. + */ + ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); + if (ret == -ENOENT) + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + else if (ret) + return; + + search_start = (unsigned long)dma32_phys_limit; + search_end = memblock_end_of_DRAM(); + high = true; + } else if (ret || !crash_size) { + /* Invalid argument value specified */ return; + } crash_size = PAGE_ALIGN(crash_size); if (crash_base) { + fixed_base = true; search_start = crash_base; search_end = crash_base + crash_size; } @@ -1345,12 +1395,37 @@ static void __init reserve_crashkernel(void) * swiotlb can work on the crash kernel. */ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, - min(search_end, (unsigned long) SZ_4G)); + search_start, search_end); if (crash_base == 0) { - /* Try again without restricting region to 32bit addressible memory */ + /* + * For crashkernel=size[KMG]@offset[KMG], print out failure + * message if can't reserve the specified region. + */ + if (fixed_base) { + pr_warn("crashkernel: allocating failed with given size@offset\n"); + return; + } + + if (high) { + /* + * For crashkernel=size[KMG],high, if the first attempt was + * for high memory, fall back to low memory. + */ + search_start = memblock_start_of_DRAM(); + search_end = (unsigned long)dma32_phys_limit; + } else { + /* + * For crashkernel=size[KMG], if the first attempt was for + * low memory, fall back to high memory, the minimum required + * low memory will be reserved later. + */ + search_start = (unsigned long)dma32_phys_limit; + search_end = memblock_end_of_DRAM(); + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + } + crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, - search_start, search_end); + search_start, search_end); if (crash_base == 0) { pr_warn("crashkernel: couldn't allocate %lldKB\n", crash_size >> 10); @@ -1358,6 +1433,12 @@ static void __init reserve_crashkernel(void) } } + if ((crash_base >= dma32_phys_limit) && crash_low_size && + reserve_crashkernel_low(crash_low_size)) { + memblock_phys_free(crash_base, crash_size); + return; + } + pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 8fc0efcf905c..5e39dcf23fdb 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -22,10 +22,9 @@ * region is not and then we have to go down to the PUD level. */ -extern pgd_t early_pg_dir[PTRS_PER_PGD]; -pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; -p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; -pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; +static pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; +static p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; +static pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end) { @@ -439,7 +438,7 @@ static void __init kasan_shallow_populate(void *start, void *end) kasan_shallow_populate_pgd(vaddr, vend); } -static void create_tmp_mapping(void) +static void __init create_tmp_mapping(void) { void *ptr; p4d_t *base_p4d; diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ea3d61de065b..161d0b34c2cb 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -102,6 +102,7 @@ static const struct mm_walk_ops pageattr_ops = { .pmd_entry = pageattr_pmd_entry, .pte_entry = pageattr_pte_entry, .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index bf9802a63061..d21c6c92a683 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -69,7 +69,7 @@ struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ int ninsns; - int body_len; + int prologue_len; int epilogue_offset; int *offset; /* BPF to RV */ int nexentries; @@ -216,8 +216,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) int from, to; off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; return ninsns_rvoff(to - from); } @@ -431,11 +431,21 @@ static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2) return rv_r_insn(1, rs2, rs1, 3, rd, 0x33); } +static inline u32 rv_div(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x33); +} + static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); } +static inline u32 rv_rem(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x33); +} + static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); @@ -501,6 +511,16 @@ static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1) return rv_bge(rs2, rs1, imm12_1); } +static inline u32 rv_lb(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x03); +} + +static inline u32 rv_lh(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x03); +} + static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) { return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); @@ -766,11 +786,21 @@ static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); } +static inline u32 rv_divw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x3b); +} + static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); } +static inline u32 rv_remw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x3b); +} + static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) { return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index c648864c8cd1..8423f4ddf8f5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -13,6 +13,8 @@ #include <asm/patch.h> #include "bpf_jit.h" +#define RV_FENTRY_NINSNS 2 + #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ @@ -241,7 +243,7 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) if (!is_tail_call) emit_mv(RV_REG_A0, RV_REG_A5, ctx); emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA, - is_tail_call ? 20 : 0, /* skip reserved nops and TCC init */ + is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */ ctx); } @@ -578,7 +580,8 @@ static int add_exception_handler(const struct bpf_insn *insn, unsigned long pc; off_t offset; - if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM) + if (!ctx->insns || !ctx->prog->aux->extable || + (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX)) return 0; if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries)) @@ -618,32 +621,7 @@ static int add_exception_handler(const struct bpf_insn *insn, return 0; } -static int gen_call_or_nops(void *target, void *ip, u32 *insns) -{ - s64 rvoff; - int i, ret; - struct rv_jit_context ctx; - - ctx.ninsns = 0; - ctx.insns = (u16 *)insns; - - if (!target) { - for (i = 0; i < 4; i++) - emit(rv_nop(), &ctx); - return 0; - } - - rvoff = (s64)(target - (ip + 4)); - emit(rv_sd(RV_REG_SP, -8, RV_REG_RA), &ctx); - ret = emit_jump_and_link(RV_REG_RA, rvoff, false, &ctx); - if (ret) - return ret; - emit(rv_ld(RV_REG_RA, -8, RV_REG_SP), &ctx); - - return 0; -} - -static int gen_jump_or_nops(void *target, void *ip, u32 *insns) +static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) { s64 rvoff; struct rv_jit_context ctx; @@ -658,38 +636,35 @@ static int gen_jump_or_nops(void *target, void *ip, u32 *insns) } rvoff = (s64)(target - ip); - return emit_jump_and_link(RV_REG_ZERO, rvoff, false, &ctx); + return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx); } int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type, void *old_addr, void *new_addr) { - u32 old_insns[4], new_insns[4]; + u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS]; bool is_call = poke_type == BPF_MOD_CALL; - int (*gen_insns)(void *target, void *ip, u32 *insns); - int ninsns = is_call ? 4 : 2; int ret; - if (!is_bpf_text_address((unsigned long)ip)) + if (!is_kernel_text((unsigned long)ip) && + !is_bpf_text_address((unsigned long)ip)) return -ENOTSUPP; - gen_insns = is_call ? gen_call_or_nops : gen_jump_or_nops; - - ret = gen_insns(old_addr, ip, old_insns); + ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call); if (ret) return ret; - if (memcmp(ip, old_insns, ninsns * 4)) + if (memcmp(ip, old_insns, RV_FENTRY_NINSNS * 4)) return -EFAULT; - ret = gen_insns(new_addr, ip, new_insns); + ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call); if (ret) return ret; cpus_read_lock(); mutex_lock(&text_mutex); - if (memcmp(ip, new_insns, ninsns * 4)) - ret = patch_text(ip, new_insns, ninsns); + if (memcmp(ip, new_insns, RV_FENTRY_NINSNS * 4)) + ret = patch_text(ip, new_insns, RV_FENTRY_NINSNS); mutex_unlock(&text_mutex); cpus_read_unlock(); @@ -787,8 +762,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, int i, ret, offset; int *branches_off = NULL; int stack_size = 0, nregs = m->nr_args; - int retaddr_off, fp_off, retval_off, args_off; - int nregs_off, ip_off, run_ctx_off, sreg_off; + int retval_off, args_off, nregs_off, ip_off, run_ctx_off, sreg_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; @@ -796,13 +770,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, bool save_ret; u32 insn; - /* Generated trampoline stack layout: + /* Two types of generated trampoline stack layout: * - * FP - 8 [ RA of parent func ] return address of parent + * 1. trampoline called from function entry + * -------------------------------------- + * FP + 8 [ RA to parent func ] return address to parent * function - * FP - retaddr_off [ RA of traced func ] return address of traced + * FP + 0 [ FP of parent func ] frame pointer of parent * function - * FP - fp_off [ FP of parent func ] + * FP - 8 [ T0 to traced func ] return address of traced + * function + * FP - 16 [ FP of traced func ] frame pointer of traced + * function + * -------------------------------------- + * + * 2. trampoline called directly + * -------------------------------------- + * FP - 8 [ RA to caller func ] return address to caller + * function + * FP - 16 [ FP of caller func ] frame pointer of caller + * function + * -------------------------------------- * * FP - retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or * BPF_TRAMP_F_RET_FENTRY_RET @@ -833,14 +821,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, if (nregs > 8) return -ENOTSUPP; - /* room for parent function return address */ - stack_size += 8; - - stack_size += 8; - retaddr_off = stack_size; - - stack_size += 8; - fp_off = stack_size; + /* room of trampoline frame to store return address and frame pointer */ + stack_size += 16; save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); if (save_ret) { @@ -867,12 +849,29 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, stack_size = round_up(stack_size, 16); - emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); - - emit_sd(RV_REG_SP, stack_size - retaddr_off, RV_REG_RA, ctx); - emit_sd(RV_REG_SP, stack_size - fp_off, RV_REG_FP, ctx); - - emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + if (func_addr) { + /* For the trampoline called from function entry, + * the frame of traced function and the frame of + * trampoline need to be considered. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -16, ctx); + emit_sd(RV_REG_SP, 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, 0, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, 16, ctx); + + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_T0, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } else { + /* For the trampoline called directly, just handle + * the frame of trampoline. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } /* callee saved register S1 to pass start time */ emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx); @@ -890,7 +889,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, /* skip to actual body of traced function */ if (flags & BPF_TRAMP_F_SKIP_FRAME) - orig_call += 16; + orig_call += RV_FENTRY_NINSNS * 4; if (flags & BPF_TRAMP_F_CALL_ORIG) { emit_imm(RV_REG_A0, (const s64)im, ctx); @@ -967,17 +966,30 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx); - if (flags & BPF_TRAMP_F_SKIP_FRAME) - /* return address of parent function */ - emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx); - else - /* return address of traced function */ - emit_ld(RV_REG_RA, stack_size - retaddr_off, RV_REG_SP, ctx); + if (func_addr) { + /* trampoline called from function entry */ + emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); - emit_ld(RV_REG_FP, stack_size - fp_off, RV_REG_SP, ctx); - emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + emit_ld(RV_REG_RA, 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, 0, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, 16, ctx); - emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* return to parent function */ + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + else + /* return to traced function */ + emit_jalr(RV_REG_ZERO, RV_REG_T0, 0, ctx); + } else { + /* trampoline called directly */ + emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + } ret = ctx->ninsns; out: @@ -1035,7 +1047,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_zext_32(rd, ctx); break; } - emit_mv(rd, rs, ctx); + switch (insn->off) { + case 0: + emit_mv(rd, rs, ctx); + break; + case 8: + case 16: + emit_slli(RV_REG_T1, rs, 64 - insn->off, ctx); + emit_srai(rd, RV_REG_T1, 64 - insn->off, ctx); + break; + case 32: + emit_addiw(rd, rs, 0, ctx); + break; + } if (!is64 && !aux->verifier_zext) emit_zext_32(rd, ctx); break; @@ -1083,13 +1107,19 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: - emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); + if (off) + emit(is64 ? rv_div(rd, rd, rs) : rv_divw(rd, rd, rs), ctx); + else + emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) emit_zext_32(rd, ctx); break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); + if (off) + emit(is64 ? rv_rem(rd, rd, rs) : rv_remw(rd, rd, rs), ctx); + else + emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); if (!is64 && !aux->verifier_zext) emit_zext_32(rd, ctx); break; @@ -1138,6 +1168,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, break; case BPF_ALU | BPF_END | BPF_FROM_BE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: emit_li(RV_REG_T2, 0, ctx); emit_andi(RV_REG_T1, rd, 0xff, ctx); @@ -1260,16 +1291,24 @@ out_be: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: emit_imm(RV_REG_T1, imm, ctx); - emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : - rv_divuw(rd, rd, RV_REG_T1), ctx); + if (off) + emit(is64 ? rv_div(rd, rd, RV_REG_T1) : + rv_divw(rd, rd, RV_REG_T1), ctx); + else + emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : + rv_divuw(rd, rd, RV_REG_T1), ctx); if (!is64 && !aux->verifier_zext) emit_zext_32(rd, ctx); break; case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: emit_imm(RV_REG_T1, imm, ctx); - emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : - rv_remuw(rd, rd, RV_REG_T1), ctx); + if (off) + emit(is64 ? rv_rem(rd, rd, RV_REG_T1) : + rv_remw(rd, rd, RV_REG_T1), ctx); + else + emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : + rv_remuw(rd, rd, RV_REG_T1), ctx); if (!is64 && !aux->verifier_zext) emit_zext_32(rd, ctx); break; @@ -1303,7 +1342,11 @@ out_be: /* JUMP off */ case BPF_JMP | BPF_JA: - rvoff = rv_offset(i, off, ctx); + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(code) == BPF_JMP) + rvoff = rv_offset(i, off, ctx); + else + rvoff = rv_offset(i, imm, ctx); ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); if (ret) return ret; @@ -1475,7 +1518,7 @@ out_be: return 1; } - /* LDX: dst = *(size *)(src + off) */ + /* LDX: dst = *(unsigned size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: @@ -1484,14 +1527,28 @@ out_be: case BPF_LDX | BPF_PROBE_MEM | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + /* LDSX: dst = *(signed size *)(src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: { int insn_len, insns_start; + bool sign_ext; + + sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX; switch (BPF_SIZE(code)) { case BPF_B: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lbu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lb(rd, off, rs), ctx); + else + emit(rv_lbu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1499,15 +1556,19 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lb(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_H: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lhu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lh(rd, off, rs), ctx); + else + emit(rv_lhu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1515,15 +1576,19 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lh(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_W: if (is_12b_int(off)) { insns_start = ctx->ninsns; - emit(rv_lwu(rd, off, rs), ctx); + if (sign_ext) + emit(rv_lw(rd, off, rs), ctx); + else + emit(rv_lwu(rd, off, rs), ctx); insn_len = ctx->ninsns - insns_start; break; } @@ -1531,10 +1596,11 @@ out_be: emit_imm(RV_REG_T1, off, ctx); emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); insns_start = ctx->ninsns; - emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + if (sign_ext) + emit(rv_lw(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); insn_len = ctx->ninsns - insns_start; - if (insn_is_zext(&insn[1])) - return 1; break; case BPF_DW: if (is_12b_int(off)) { @@ -1555,6 +1621,9 @@ out_be: ret = add_exception_handler(insn, ctx, rd, insn_len); if (ret) return ret; + + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; break; } /* speculation barrier */ @@ -1691,8 +1760,8 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx) store_offset = stack_adjust - 8; - /* reserve 4 nop insns */ - for (i = 0; i < 4; i++) + /* nops reserved for auipc+jalr pair */ + for (i = 0; i < RV_FENTRY_NINSNS; i++) emit(rv_nop(), ctx); /* First instruction is always setting the tail-call-counter diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 737baf8715da..7a26a3e1c73c 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -44,7 +44,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) unsigned int prog_size = 0, extable_size = 0; bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; - int pass = 0, prev_ninsns = 0, prologue_len, i; + int pass = 0, prev_ninsns = 0, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; @@ -83,6 +83,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + + if (build_body(ctx, extra_pass, NULL)) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { prev_ninsns += 32; ctx->offset[i] = prev_ninsns; @@ -91,12 +97,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) for (i = 0; i < NR_JIT_ITERATIONS; i++) { pass++; ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + ctx->prologue_len = ctx->ninsns; + if (build_body(ctx, extra_pass, ctx->offset)) { prog = orig_prog; goto out_offset; } - ctx->body_len = ctx->ninsns; - bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -162,10 +171,8 @@ skip_init_ctx: if (!prog->is_func || extra_pass) { bpf_jit_binary_lock_ro(jit_data->header); - prologue_len = ctx->epilogue_offset - ctx->body_len; for (i = 0; i < prog->len; i++) - ctx->offset[i] = ninsns_rvoff(prologue_len + - ctx->offset[i]); + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index dc20e166983e..9e6476719abb 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -77,6 +77,10 @@ ifdef CONFIG_STACKPROTECTOR_STRONG PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong endif +ifdef CONFIG_CFI_CLANG +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) +endif + CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) |