diff options
87 files changed, 2376 insertions, 656 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 5a92d89a1bd4..ade4e6ec23e0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -113,7 +113,7 @@ the GPE dispatcher. This facility can be used to prevent such uncontrolled GPE floodings. - Format: <int> + Format: <byte> acpi_no_auto_serialize [HW,ACPI] Disable auto-serialization of AML methods diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt index 49183add44e7..ebb37b34dcfc 100644 --- a/Documentation/virt/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -5,7 +5,7 @@ The Definitive KVM (Kernel-based Virtual Machine) API Documentation ---------------------- The kvm API is a set of ioctls that are issued to control various aspects -of a virtual machine. The ioctls belong to three classes: +of a virtual machine. The ioctls belong to the following classes: - System ioctls: These query and set global attributes which affect the whole kvm subsystem. In addition a system ioctl is used to create @@ -4149,6 +4149,24 @@ Valid values for 'action': #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +4.121 KVM_PPC_SVM_OFF + +Capability: basic +Architectures: powerpc +Type: vm ioctl +Parameters: none +Returns: 0 on successful completion, +Errors: + EINVAL: if ultravisor failed to terminate the secure guest + ENOMEM: if hypervisor failed to allocate new radix page tables for guest + +This ioctl is used to turn off the secure mode of the guest or transition +the guest from secure mode to normal mode. This is invoked when the guest +is reset. This has no effect if called for a normal guest. + +This ioctl issues an ultravisor call to terminate the secure guest, +unpins the VPA pages and releases all the device pages that are used to +track the secure pages by hypervisor. 5. The kvm_run structure ------------------------ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 4d7b671c8ff4..26108ea785c2 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -29,6 +29,7 @@ config ARC select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DEBUG_KMEMLEAK select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_IOREMAP_PROT select HAVE_KERNEL_GZIP @@ -45,6 +46,7 @@ config ARC select OF_EARLY_FLATTREE select PCI_SYSCALL if PCI select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING + select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32 config ARCH_HAS_CACHE_LINE_SIZE def_bool y @@ -524,6 +526,13 @@ config ARC_DW2_UNWIND config ARC_DBG_TLB_PARANOIA bool "Paranoia Checks in Low Level TLB Handlers" +config ARC_DBG_JUMP_LABEL + bool "Paranoid checks in Static Keys (jump labels) code" + depends on JUMP_LABEL + default y if STATIC_KEYS_SELFTEST + help + Enable paranoid checks and self-test of both ARC-specific and generic + part of static keys (jump labels) related code. endif config ARC_BUILTIN_DTB_NAME diff --git a/arch/arc/Makefile b/arch/arc/Makefile index f1c44cccf8d6..20e9ab6cc521 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -3,7 +3,7 @@ # Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) # -KBUILD_DEFCONFIG := nsim_hs_defconfig +KBUILD_DEFCONFIG := haps_hs_smp_defconfig ifeq ($(CROSS_COMPILE),) CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 6ec1fcdfc0d7..79ec27c043c1 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -28,6 +28,12 @@ clock-frequency = <750000000>; }; + input_clk: input-clk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <33333333>; + }; + core_intc: arc700-intc@cpu { compatible = "snps,arc700-intc"; interrupt-controller; diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts index 305a7f9658e0..c4cfc5f4f427 100644 --- a/arch/arc/boot/dts/axs101.dts +++ b/arch/arc/boot/dts/axs101.dts @@ -14,6 +14,6 @@ compatible = "snps,axs101", "snps,arc-sdp"; chosen { - bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1"; + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 print-fatal-signals=1"; }; }; diff --git a/arch/arc/boot/dts/axs103_idu.dts b/arch/arc/boot/dts/axs103_idu.dts index 46c9136cbf2b..a934b92a8c30 100644 --- a/arch/arc/boot/dts/axs103_idu.dts +++ b/arch/arc/boot/dts/axs103_idu.dts @@ -17,6 +17,6 @@ compatible = "snps,axs103", "snps,arc-sdp"; chosen { - bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 print-fatal-signals=1 consoleblank=0 video=1280x720@60"; + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 print-fatal-signals=1 consoleblank=0"; }; }; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 08bcfed6b80f..f9a5c9ddcae7 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -61,12 +61,13 @@ clock-frequency = <25000000>; #clock-cells = <0>; }; + }; - pguclk: pguclk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <74250000>; - }; + pguclk: pguclk@10080 { + compatible = "snps,axs10x-pgu-pll-clock"; + reg = <0x10080 0x10>, <0x110 0x10>; + #clock-cells = <0>; + clocks = <&input_clk>; }; gmac: ethernet@18000 { diff --git a/arch/arc/boot/dts/haps_hs.dts b/arch/arc/boot/dts/haps_hs.dts index 44bc522fdec8..60d578e2781f 100644 --- a/arch/arc/boot/dts/haps_hs.dts +++ b/arch/arc/boot/dts/haps_hs.dts @@ -9,13 +9,15 @@ / { model = "snps,zebu_hs"; compatible = "snps,zebu_hs"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; interrupt-parent = <&core_intc>; memory { device_type = "memory"; - reg = <0x80000000 0x20000000>; /* 512 */ + /* CONFIG_LINUX_RAM_BASE needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ + 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ }; chosen { @@ -31,8 +33,9 @@ #address-cells = <1>; #size-cells = <1>; - /* child and parent address space 1:1 mapped */ - ranges; + /* only perip space at end of low mem accessible + bus addr, parent bus addr, size */ + ranges = <0x80000000 0x0 0x80000000 0x80000000>; core_clk: core_clk { #clock-cells = <0>; @@ -47,7 +50,7 @@ }; uart0: serial@f0000000 { - compatible = "ns8250"; + compatible = "ns16550a"; reg = <0xf0000000 0x2000>; interrupts = <24>; clock-frequency = <50000000>; diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts index 4d6971cf5f9f..738c76cd07b3 100644 --- a/arch/arc/boot/dts/haps_hs_idu.dts +++ b/arch/arc/boot/dts/haps_hs_idu.dts @@ -54,7 +54,6 @@ }; uart0: serial@f0000000 { - /* compatible = "ns8250"; Doesn't use FIFOs */ compatible = "ns16550a"; reg = <0xf0000000 0x2000>; interrupt-parent = <&idu_intc>; diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 63dbaab1247d..f8832a15e174 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -14,11 +14,11 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 print-fatal-signals=1"; }; aliases { - serial0 = &arcuart0; + serial0 = &uart0; }; fpga { @@ -41,29 +41,15 @@ #interrupt-cells = <1>; }; - arcuart0: serial@c0fc1000 { - compatible = "snps,arc-uart"; - reg = <0xc0fc1000 0x100>; - interrupts = <5>; - clock-frequency = <80000000>; - current-speed = <115200>; - status = "okay"; - }; - - ethernet@c0fc2000 { - compatible = "snps,arc-emac"; - reg = <0xc0fc2000 0x3c>; - interrupts = <6>; - mac-address = [ 00 11 22 33 44 55 ]; - clock-frequency = <80000000>; - max-speed = <100>; - phy = <&phy0>; - - #address-cells = <1>; - #size-cells = <0>; - phy0: ethernet-phy@0 { - reg = <1>; - }; + uart0: serial@f0000000 { + compatible = "ns16550a"; + reg = <0xf0000000 0x2000>; + interrupts = <24>; + clock-frequency = <50000000>; + baud = <115200>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test = <1>; }; arcpct0: pct { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts deleted file mode 100644 index 851798a5f4e3..000000000000 --- a/arch/arc/boot/dts/nsim_hs.dts +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) - */ -/dts-v1/; - -/include/ "skeleton_hs.dtsi" - -/ { - model = "snps,nsim_hs"; - compatible = "snps,nsim_hs"; - #address-cells = <2>; - #size-cells = <2>; - interrupt-parent = <&core_intc>; - - memory { - device_type = "memory"; - /* CONFIG_LINUX_RAM_BASE needs to match low mem start */ - reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ - 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ - }; - - chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; - }; - - aliases { - serial0 = &arcuart0; - }; - - fpga { - compatible = "simple-bus"; - #address-cells = <1>; - #size-cells = <1>; - - /* only perip space at end of low mem accessible - bus addr, parent bus addr, size */ - ranges = <0x80000000 0x0 0x80000000 0x80000000>; - - core_clk: core_clk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <80000000>; - }; - - core_intc: core-interrupt-controller { - compatible = "snps,archs-intc"; - interrupt-controller; - #interrupt-cells = <1>; - }; - - arcuart0: serial@c0fc1000 { - compatible = "snps,arc-uart"; - reg = <0xc0fc1000 0x100>; - interrupts = <24>; - clock-frequency = <80000000>; - current-speed = <115200>; - status = "okay"; - }; - - arcpct0: pct { - compatible = "snps,archs-pct"; - #interrupt-cells = <1>; - interrupts = <20>; - }; - }; -}; diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts deleted file mode 100644 index 6c559a0bd1f5..000000000000 --- a/arch/arc/boot/dts/nsim_hs_idu.dts +++ /dev/null @@ -1,65 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) - */ -/dts-v1/; - -/include/ "skeleton_hs_idu.dtsi" - -/ { - model = "snps,nsim_hs-smp"; - compatible = "snps,nsim_hs"; - interrupt-parent = <&core_intc>; - - chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; - }; - - aliases { - serial0 = &arcuart0; - }; - - fpga { - compatible = "simple-bus"; - #address-cells = <1>; - #size-cells = <1>; - - /* child and parent address space 1:1 mapped */ - ranges; - - core_clk: core_clk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <80000000>; - }; - - core_intc: core-interrupt-controller { - compatible = "snps,archs-intc"; - interrupt-controller; - #interrupt-cells = <1>; - }; - - idu_intc: idu-interrupt-controller { - compatible = "snps,archs-idu-intc"; - interrupt-controller; - interrupt-parent = <&core_intc>; - #interrupt-cells = <1>; - }; - - arcuart0: serial@c0fc1000 { - compatible = "snps,arc-uart"; - reg = <0xc0fc1000 0x100>; - interrupt-parent = <&idu_intc>; - interrupts = <0>; - clock-frequency = <80000000>; - current-speed = <115200>; - status = "okay"; - }; - - arcpct0: pct { - compatible = "snps,archs-pct"; - #interrupt-cells = <1>; - interrupts = <20>; - }; - }; -}; diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 47ff8a97e42d..7337cdf4ffdd 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -4,6 +4,7 @@ CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NAMESPACES=y @@ -15,13 +16,9 @@ CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y +CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs" CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs" -CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y @@ -30,9 +27,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y @@ -42,21 +36,12 @@ CONFIG_DEVTMPFS_MOUNT=y CONFIG_VIRTIO_BLK=y CONFIG_NETDEVICES=y CONFIG_VIRTIO_NET=y -# CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_VENDOR_BROADCOM is not set -# CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_MARVELL is not set -# CONFIG_NET_VENDOR_MICREL is not set -# CONFIG_NET_VENDOR_NATSEMI is not set -# CONFIG_NET_VENDOR_SEEQ is not set -# CONFIG_NET_VENDOR_STMICRO is not set -# CONFIG_NET_VENDOR_VIA is not set -# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_ETHERNET is not set # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y -CONFIG_MOUSE_PS2_TOUCHKIT=y -# CONFIG_SERIO_SERPORT is not set -CONFIG_SERIO_ARC_PS2=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y @@ -66,9 +51,6 @@ CONFIG_SERIAL_8250_DW=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -CONFIG_FB=y -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_LOGO=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 9685fd5f57a4..bc927221afc0 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -4,6 +4,7 @@ CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NAMESPACES=y @@ -16,15 +17,11 @@ CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y +CONFIG_SMP=y +CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ISA_ARCV2=y -CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu" -CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y @@ -33,9 +30,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_DEVTMPFS=y @@ -43,21 +37,12 @@ CONFIG_DEVTMPFS=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y -# CONFIG_NET_VENDOR_ARC is not set -# CONFIG_NET_VENDOR_BROADCOM is not set -# CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_NET_VENDOR_MARVELL is not set -# CONFIG_NET_VENDOR_MICREL is not set -# CONFIG_NET_VENDOR_NATSEMI is not set -# CONFIG_NET_VENDOR_SEEQ is not set -# CONFIG_NET_VENDOR_STMICRO is not set -# CONFIG_NET_VENDOR_VIA is not set -# CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_ETHERNET is not set # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y -CONFIG_MOUSE_PS2_TOUCHKIT=y -# CONFIG_SERIO_SERPORT is not set -CONFIG_SERIO_ARC_PS2=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y @@ -67,9 +52,6 @@ CONFIG_SERIAL_8250_DW=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -CONFIG_FB=y -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_LOGO=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 2b9b11474640..326f6cde7826 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -4,6 +4,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NAMESPACES=y @@ -17,13 +18,10 @@ CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_ISA_ARCOMPACT=y +CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" -CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y @@ -37,15 +35,18 @@ CONFIG_DEVTMPFS=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y -CONFIG_ARC_EMAC=y -CONFIG_LXT_PHY=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +# CONFIG_ETHERNET is not set +# CONFIG_WLAN is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -CONFIG_SERIAL_ARC=y -CONFIG_SERIAL_ARC_CONSOLE=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set # CONFIG_HID is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig deleted file mode 100644 index bab3dd255841..000000000000 --- a/arch/arc/configs/nsim_hs_defconfig +++ /dev/null @@ -1,60 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -# CONFIG_CROSS_MEMORY_ATTACH is not set -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_NAMESPACES=y -# CONFIG_UTS_NS is not set -# CONFIG_PID_NS is not set -CONFIG_BLK_DEV_INITRD=y -CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE_O3=y -CONFIG_KALLSYMS_ALL=y -CONFIG_EMBEDDED=y -CONFIG_PERF_EVENTS=y -# CONFIG_SLUB_DEBUG is not set -# CONFIG_COMPAT_BRK is not set -CONFIG_KPROBES=y -CONFIG_MODULES=y -CONFIG_MODULE_FORCE_LOAD=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs" -CONFIG_PREEMPT=y -# CONFIG_COMPACTION is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_UNIX_DIAG=y -CONFIG_NET_KEY=y -CONFIG_INET=y -# CONFIG_IPV6 is not set -CONFIG_DEVTMPFS=y -# CONFIG_STANDALONE is not set -# CONFIG_PREVENT_FIRMWARE_BUILD is not set -# CONFIG_BLK_DEV is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_LEGACY_PTYS is not set -CONFIG_SERIAL_ARC=y -CONFIG_SERIAL_ARC_CONSOLE=y -# CONFIG_HW_RANDOM is not set -# CONFIG_HWMON is not set -# CONFIG_HID is not set -# CONFIG_USB_SUPPORT is not set -# CONFIG_IOMMU_SUPPORT is not set -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_TMPFS=y -# CONFIG_MISC_FILESYSTEMS is not set -CONFIG_NFS_FS=y -# CONFIG_ENABLE_MUST_CHECK is not set -# CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig deleted file mode 100644 index 90d2d50fb8dc..000000000000 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ /dev/null @@ -1,58 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -# CONFIG_SWAP is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_NAMESPACES=y -# CONFIG_UTS_NS is not set -# CONFIG_PID_NS is not set -CONFIG_BLK_DEV_INITRD=y -CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE_O3=y -CONFIG_KALLSYMS_ALL=y -CONFIG_EMBEDDED=y -CONFIG_PERF_EVENTS=y -# CONFIG_SLUB_DEBUG is not set -# CONFIG_COMPAT_BRK is not set -CONFIG_KPROBES=y -CONFIG_MODULES=y -CONFIG_MODULE_FORCE_LOAD=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -# CONFIG_IOSCHED_DEADLINE is not set -# CONFIG_IOSCHED_CFQ is not set -CONFIG_ISA_ARCV2=y -CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" -CONFIG_PREEMPT=y -# CONFIG_COMPACTION is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_UNIX_DIAG=y -CONFIG_NET_KEY=y -CONFIG_INET=y -# CONFIG_IPV6 is not set -CONFIG_DEVTMPFS=y -# CONFIG_STANDALONE is not set -# CONFIG_PREVENT_FIRMWARE_BUILD is not set -# CONFIG_BLK_DEV is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_LEGACY_PTYS is not set -CONFIG_SERIAL_ARC=y -CONFIG_SERIAL_ARC_CONSOLE=y -# CONFIG_HW_RANDOM is not set -# CONFIG_HWMON is not set -# CONFIG_HID is not set -# CONFIG_USB_SUPPORT is not set -# CONFIG_IOMMU_SUPPORT is not set -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_TMPFS=y -# CONFIG_MISC_FILESYSTEMS is not set -CONFIG_NFS_FS=y -# CONFIG_ENABLE_MUST_CHECK is not set diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 918804c7c1a4..d8ece4292388 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -25,6 +25,8 @@ #ifndef __ASSEMBLY__ +#include <linux/build_bug.h> + /* Uncached access macros */ #define arc_read_uncached_32(ptr) \ ({ \ diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index 66a292335ee6..c3aa775878dc 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -130,7 +130,7 @@ * to be saved again on kernel mode stack, as part of pt_regs. *-------------------------------------------------------------*/ .macro PROLOG_FREEUP_REG reg, mem -#ifdef CONFIG_SMP +#ifndef ARC_USE_SCRATCH_REG sr \reg, [ARC_REG_SCRATCH_DATA0] #else st \reg, [\mem] @@ -138,7 +138,7 @@ .endm .macro PROLOG_RESTORE_REG reg, mem -#ifdef CONFIG_SMP +#ifndef ARC_USE_SCRATCH_REG lr \reg, [ARC_REG_SCRATCH_DATA0] #else ld \reg, [\mem] diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h new file mode 100644 index 000000000000..9d9618079739 --- /dev/null +++ b/arch/arc/include/asm/jump_label.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARC_JUMP_LABEL_H +#define _ASM_ARC_JUMP_LABEL_H + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + +#define JUMP_LABEL_NOP_SIZE 4 + +/* + * NOTE about '.balign 4': + * + * To make atomic update of patched instruction available we need to guarantee + * that this instruction doesn't cross L1 cache line boundary. + * + * As of today we simply align instruction which can be patched by 4 byte using + * ".balign 4" directive. In that case patched instruction is aligned with one + * 16-bit NOP_S if this is required. + * However 'align by 4' directive is much stricter than it actually required. + * It's enough that our 32-bit instruction don't cross L1 cache line boundary / + * L1 I$ fetch block boundary which can be achieved by using + * ".bundle_align_mode" assembler directive. That will save us from adding + * useless NOP_S padding in most of the cases. + * + * TODO: switch to ".bundle_align_mode" directive using whin it will be + * supported by ARC toolchain. + */ + +static __always_inline bool arch_static_branch(struct static_key *key, + bool branch) +{ + asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + "1: \n" + "nop \n" + ".pushsection __jump_table, \"aw\" \n" + ".word 1b, %l[l_yes], %c0 \n" + ".popsection \n" + : : "i" (&((char *)key)[branch]) : : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key *key, + bool branch) +{ + asm_volatile_goto(".balign "__stringify(JUMP_LABEL_NOP_SIZE)" \n" + "1: \n" + "b %l[l_yes] \n" + ".pushsection __jump_table, \"aw\" \n" + ".word 1b, %l[l_yes], %c0 \n" + ".popsection \n" + : : "i" (&((char *)key)[branch]) : : l_yes); + + return false; +l_yes: + return true; +} + +typedef u32 jump_label_t; + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif /* __ASSEMBLY__ */ +#endif diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index 98cadf1a09ac..26b731d32a2b 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -40,6 +40,10 @@ #define ARC_REG_SCRATCH_DATA0 0x46c #endif +#if defined(CONFIG_ISA_ARCV2) || !defined(CONFIG_SMP) +#define ARC_USE_SCRATCH_REG +#endif + /* Bits in MMU PID register */ #define __TLB_ENABLE (1 << 31) #define __PROG_ENABLE (1 << 30) @@ -63,6 +67,8 @@ #if (CONFIG_ARC_MMU_VER >= 2) #define TLBWriteNI 0x5 /* write JTLB without inv uTLBs */ #define TLBIVUTLB 0x6 /* explicitly inv uTLBs */ +#else +#define TLBWriteNI TLBWrite /* Not present in hardware, fallback */ #endif #if (CONFIG_ARC_MMU_VER >= 4) diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 035470816be5..3a5e6a5b9ed6 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -144,7 +144,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ cpumask_set_cpu(cpu, mm_cpumask(next)); -#ifndef CONFIG_SMP +#ifdef ARC_USE_SCRATCH_REG /* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */ write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); #endif diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index b917b596f7fb..9019ed9f9c94 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -350,7 +350,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, * Thus use this macro only when you are certain that "current" is current * e.g. when dealing with signal frame setup code etc */ -#ifndef CONFIG_SMP +#ifdef ARC_USE_SCRATCH_REG #define pgd_offset_fast(mm, addr) \ ({ \ pgd_t *pgd_base = (pgd_t *) read_aux_reg(ARC_REG_SCRATCH_DATA0); \ diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile index de6251132310..e784f5396dda 100644 --- a/arch/arc/kernel/Makefile +++ b/arch/arc/kernel/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_ARC_EMUL_UNALIGNED) += unaligned.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_ARC_METAWARE_HLINK) += arc_hostlink.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_ARC_FPU_SAVE_RESTORE) += fpu.o CFLAGS_fpu.o += -mdpfp diff --git a/arch/arc/kernel/jump_label.c b/arch/arc/kernel/jump_label.c new file mode 100644 index 000000000000..b8600dc325b5 --- /dev/null +++ b/arch/arc/kernel/jump_label.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/jump_label.h> + +#include "asm/cacheflush.h" + +#define JUMPLABEL_ERR "ARC: jump_label: ERROR: " + +/* Halt system on fatal error to make debug easier */ +#define arc_jl_fatal(format...) \ +({ \ + pr_err(JUMPLABEL_ERR format); \ + BUG(); \ +}) + +static inline u32 arc_gen_nop(void) +{ + /* 1x 32bit NOP in middle endian */ + return 0x7000264a; +} + +/* + * Atomic update of patched instruction is only available if this + * instruction doesn't cross L1 cache line boundary. You can read about + * the way we achieve this in arc/include/asm/jump_label.h + */ +static inline void instruction_align_assert(void *addr, int len) +{ + unsigned long a = (unsigned long)addr; + + if ((a >> L1_CACHE_SHIFT) != ((a + len - 1) >> L1_CACHE_SHIFT)) + arc_jl_fatal("instruction (addr %px) cross L1 cache line border", + addr); +} + +/* + * ARCv2 'Branch unconditionally' instruction: + * 00000ssssssssss1SSSSSSSSSSNRtttt + * s S[n:0] lower bits signed immediate (number is bitfield size) + * S S[m:n+1] upper bits signed immediate (number is bitfield size) + * t S[24:21] upper bits signed immediate (branch unconditionally far) + * N N <.d> delay slot mode + * R R Reserved + */ +static inline u32 arc_gen_branch(jump_label_t pc, jump_label_t target) +{ + u32 instruction_l, instruction_r; + u32 pcl = pc & GENMASK(31, 2); + u32 u_offset = target - pcl; + u32 s, S, t; + + /* + * Offset in 32-bit branch instruction must to fit into s25. + * Something is terribly broken if we get such huge offset within one + * function. + */ + if ((s32)u_offset < -16777216 || (s32)u_offset > 16777214) + arc_jl_fatal("gen branch with offset (%d) not fit in s25", + (s32)u_offset); + + /* + * All instructions are aligned by 2 bytes so we should never get offset + * here which is not 2 bytes aligned. + */ + if (u_offset & 0x1) + arc_jl_fatal("gen branch with offset (%d) unaligned to 2 bytes", + (s32)u_offset); + + s = (u_offset >> 1) & GENMASK(9, 0); + S = (u_offset >> 11) & GENMASK(9, 0); + t = (u_offset >> 21) & GENMASK(3, 0); + + /* 00000ssssssssss1 */ + instruction_l = (s << 1) | 0x1; + /* SSSSSSSSSSNRtttt */ + instruction_r = (S << 6) | t; + + return (instruction_r << 16) | (instruction_l & GENMASK(15, 0)); +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_t *instr_addr = (jump_label_t *)entry->code; + u32 instr; + + instruction_align_assert(instr_addr, JUMP_LABEL_NOP_SIZE); + + if (type == JUMP_LABEL_JMP) + instr = arc_gen_branch(entry->code, entry->target); + else + instr = arc_gen_nop(); + + WRITE_ONCE(*instr_addr, instr); + flush_icache_range(entry->code, entry->code + JUMP_LABEL_NOP_SIZE); +} + +void arch_jump_label_transform_static(struct jump_entry *entry, + enum jump_label_type type) +{ + /* + * We use only one NOP type (1x, 4 byte) in arch_static_branch, so + * there's no need to patch an identical NOP over the top of it here. + * The generic code calls 'arch_jump_label_transform' if the NOP needs + * to be replaced by a branch, so 'arch_jump_label_transform_static' is + * never called with type other than JUMP_LABEL_NOP. + */ + BUG_ON(type != JUMP_LABEL_NOP); +} + +#ifdef CONFIG_ARC_DBG_JUMP_LABEL +#define SELFTEST_MSG "ARC: instruction generation self-test: " + +struct arc_gen_branch_testdata { + jump_label_t pc; + jump_label_t target_address; + u32 expected_instr; +}; + +static __init int branch_gen_test(const struct arc_gen_branch_testdata *test) +{ + u32 instr_got; + + instr_got = arc_gen_branch(test->pc, test->target_address); + if (instr_got == test->expected_instr) + return 0; + + pr_err(SELFTEST_MSG "FAIL:\n arc_gen_branch(0x%08x, 0x%08x) != 0x%08x, got 0x%08x\n", + test->pc, test->target_address, + test->expected_instr, instr_got); + + return -EFAULT; +} + +/* + * Offset field in branch instruction is not continuous. Test all + * available offset field and sign combinations. Test data is generated + * from real working code. + */ +static const struct arc_gen_branch_testdata arcgenbr_test_data[] __initconst = { + {0x90007548, 0x90007514, 0xffcf07cd}, /* tiny (-52) offs */ + {0x9000c9c0, 0x9000c782, 0xffcf05c3}, /* tiny (-574) offs */ + {0x9000cc1c, 0x9000c782, 0xffcf0367}, /* tiny (-1178) offs */ + {0x9009dce0, 0x9009d106, 0xff8f0427}, /* small (-3034) offs */ + {0x9000f5de, 0x90007d30, 0xfc0f0755}, /* big (-30892) offs */ + {0x900a2444, 0x90035f64, 0xc9cf0321}, /* huge (-443616) offs */ + {0x90007514, 0x9000752c, 0x00000019}, /* tiny (+24) offs */ + {0x9001a578, 0x9001a77a, 0x00000203}, /* tiny (+514) offs */ + {0x90031ed8, 0x90032634, 0x0000075d}, /* tiny (+1884) offs */ + {0x9008c7f2, 0x9008d3f0, 0x00400401}, /* small (+3072) offs */ + {0x9000bb38, 0x9003b340, 0x17c00009}, /* big (+194568) offs */ + {0x90008f44, 0x90578d80, 0xb7c2063d} /* huge (+5701180) offs */ +}; + +static __init int instr_gen_test(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(arcgenbr_test_data); i++) + if (branch_gen_test(&arcgenbr_test_data[i])) + return -EFAULT; + + pr_info(SELFTEST_MSG "OK\n"); + + return 0; +} +early_initcall(instr_gen_test); + +#endif /* CONFIG_ARC_DBG_JUMP_LABEL */ diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 10025e199353..c340acd989a0 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -118,6 +118,33 @@ static inline void __tlb_entry_erase(void) write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); } +static void utlb_invalidate(void) +{ +#if (CONFIG_ARC_MMU_VER >= 2) + +#if (CONFIG_ARC_MMU_VER == 2) + /* MMU v2 introduced the uTLB Flush command. + * There was however an obscure hardware bug, where uTLB flush would + * fail when a prior probe for J-TLB (both totally unrelated) would + * return lkup err - because the entry didn't exist in MMU. + * The Workround was to set Index reg with some valid value, prior to + * flush. This was fixed in MMU v3 + */ + unsigned int idx; + + /* make sure INDEX Reg is valid */ + idx = read_aux_reg(ARC_REG_TLBINDEX); + + /* If not write some dummy val */ + if (unlikely(idx & TLB_LKUP_ERR)) + write_aux_reg(ARC_REG_TLBINDEX, 0xa); +#endif + + write_aux_reg(ARC_REG_TLBCOMMAND, TLBIVUTLB); +#endif + +} + #if (CONFIG_ARC_MMU_VER < 4) static inline unsigned int tlb_entry_lkup(unsigned long vaddr_n_asid) @@ -149,44 +176,6 @@ static void tlb_entry_erase(unsigned int vaddr_n_asid) } } -/**************************************************************************** - * ARC700 MMU caches recently used J-TLB entries (RAM) as uTLBs (FLOPs) - * - * New IVUTLB cmd in MMU v2 explictly invalidates the uTLB - * - * utlb_invalidate ( ) - * -For v2 MMU calls Flush uTLB Cmd - * -For v1 MMU does nothing (except for Metal Fix v1 MMU) - * This is because in v1 TLBWrite itself invalidate uTLBs - ***************************************************************************/ - -static void utlb_invalidate(void) -{ -#if (CONFIG_ARC_MMU_VER >= 2) - -#if (CONFIG_ARC_MMU_VER == 2) - /* MMU v2 introduced the uTLB Flush command. - * There was however an obscure hardware bug, where uTLB flush would - * fail when a prior probe for J-TLB (both totally unrelated) would - * return lkup err - because the entry didn't exist in MMU. - * The Workround was to set Index reg with some valid value, prior to - * flush. This was fixed in MMU v3 hence not needed any more - */ - unsigned int idx; - - /* make sure INDEX Reg is valid */ - idx = read_aux_reg(ARC_REG_TLBINDEX); - - /* If not write some dummy val */ - if (unlikely(idx & TLB_LKUP_ERR)) - write_aux_reg(ARC_REG_TLBINDEX, 0xa); -#endif - - write_aux_reg(ARC_REG_TLBCOMMAND, TLBIVUTLB); -#endif - -} - static void tlb_entry_insert(unsigned int pd0, pte_t pd1) { unsigned int idx; @@ -219,11 +208,6 @@ static void tlb_entry_insert(unsigned int pd0, pte_t pd1) #else /* CONFIG_ARC_MMU_VER >= 4) */ -static void utlb_invalidate(void) -{ - /* No need since uTLB is always in sync with JTLB */ -} - static void tlb_entry_erase(unsigned int vaddr_n_asid) { write_aux_reg(ARC_REG_TLBPD0, vaddr_n_asid | _PAGE_PRESENT); @@ -267,7 +251,7 @@ noinline void local_flush_tlb_all(void) for (entry = 0; entry < num_tlb; entry++) { /* write this entry to the TLB */ write_aux_reg(ARC_REG_TLBINDEX, entry); - write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); + write_aux_reg(ARC_REG_TLBCOMMAND, TLBWriteNI); } if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { @@ -278,7 +262,7 @@ noinline void local_flush_tlb_all(void) for (entry = stlb_idx; entry < stlb_idx + 16; entry++) { write_aux_reg(ARC_REG_TLBINDEX, entry); - write_aux_reg(ARC_REG_TLBCOMMAND, TLBWrite); + write_aux_reg(ARC_REG_TLBCOMMAND, TLBWriteNI); } } @@ -355,8 +339,6 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, } } - utlb_invalidate(); - local_irq_restore(flags); } @@ -385,8 +367,6 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) start += PAGE_SIZE; } - utlb_invalidate(); - local_irq_restore(flags); } @@ -407,7 +387,6 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) { tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm, cpu)); - utlb_invalidate(); } local_irq_restore(flags); @@ -868,7 +847,7 @@ void arc_mmu_init(void) write_aux_reg(ARC_REG_PID, MMU_ENABLE); /* In smp we use this reg for interrupt 1 scratch */ -#ifndef CONFIG_SMP +#ifdef ARC_USE_SCRATCH_REG /* swapper_pg_dir is the pgd for the kernel, used by vmalloc */ write_aux_reg(ARC_REG_SCRATCH_DATA0, swapper_pg_dir); #endif diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index c55d95dd2f39..2efaf6ca0c06 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -122,17 +122,27 @@ ex_saved_reg1: #else /* ARCv2 */ .macro TLBMISS_FREEUP_REGS +#ifdef CONFIG_ARC_HAS_LL64 + std r0, [sp, -16] + std r2, [sp, -8] +#else PUSH r0 PUSH r1 PUSH r2 PUSH r3 +#endif .endm .macro TLBMISS_RESTORE_REGS +#ifdef CONFIG_ARC_HAS_LL64 + ldd r0, [sp, -16] + ldd r2, [sp, -8] +#else POP r3 POP r2 POP r1 POP r0 +#endif .endm #endif @@ -193,7 +203,7 @@ ex_saved_reg1: lr r2, [efa] -#ifndef CONFIG_SMP +#ifdef ARC_USE_SCRATCH_REG lr r1, [ARC_REG_SCRATCH_DATA0] ; current pgd #else GET_CURR_TASK_ON_CPU r1 @@ -282,11 +292,7 @@ ex_saved_reg1: sr TLBGetIndex, [ARC_REG_TLBCOMMAND] /* Commit the Write */ -#if (CONFIG_ARC_MMU_VER >= 2) /* introduced in v2 */ sr TLBWriteNI, [ARC_REG_TLBCOMMAND] -#else - sr TLBWrite, [ARC_REG_TLBCOMMAND] -#endif #else sr TLBInsertEntry, [ARC_REG_TLBCOMMAND] @@ -370,9 +376,7 @@ ENTRY(EV_TLBMissD) ;---------------------------------------------------------------- ; UPDATE_PTE: Let Linux VM know that page was accessed/dirty - lr r3, [ecr] or r0, r0, _PAGE_ACCESSED ; Accessed bit always - btst_s r3, ECR_C_BIT_DTLB_ST_MISS ; See if it was a Write Access ? or.nz r0, r0, _PAGE_DIRTY ; if Write, set Dirty bit as well st_s r0, [r1] ; Write back PTE diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c index 3765dedcd319..2bde2a6e336a 100644 --- a/arch/arc/plat-sim/platform.c +++ b/arch/arc/plat-sim/platform.c @@ -21,7 +21,6 @@ static const char *simulation_compat[] __initconst = { "snps,nsim", "snps,nsimosci", #else - "snps,nsim_hs", "snps,nsimosci_hs", "snps,zebu_hs", #endif diff --git a/arch/ia64/include/asm/irqflags.h b/arch/ia64/include/asm/irqflags.h index d97f8435be4f..1dc30f12e545 100644 --- a/arch/ia64/include/asm/irqflags.h +++ b/arch/ia64/include/asm/irqflags.h @@ -36,11 +36,7 @@ static inline void arch_maybe_save_ip(unsigned long flags) static inline unsigned long arch_local_save_flags(void) { ia64_stop(); -#ifdef CONFIG_PARAVIRT - return ia64_get_psr_i(); -#else return ia64_getreg(_IA64_REG_PSR); -#endif } static inline unsigned long arch_local_irq_save(void) diff --git a/arch/ia64/include/uapi/asm/gcc_intrin.h b/arch/ia64/include/uapi/asm/gcc_intrin.h index c60696fd1e37..ecfa3eadb217 100644 --- a/arch/ia64/include/uapi/asm/gcc_intrin.h +++ b/arch/ia64/include/uapi/asm/gcc_intrin.h @@ -31,7 +31,7 @@ extern void ia64_bad_param_for_setreg (void); extern void ia64_bad_param_for_getreg (void); -#define ia64_native_setreg(regnum, val) \ +#define ia64_setreg(regnum, val) \ ({ \ switch (regnum) { \ case _IA64_REG_PSR_L: \ @@ -60,7 +60,7 @@ extern void ia64_bad_param_for_getreg (void); } \ }) -#define ia64_native_getreg(regnum) \ +#define ia64_getreg(regnum) \ ({ \ __u64 ia64_intri_res; \ \ @@ -384,7 +384,7 @@ extern void ia64_bad_param_for_getreg (void); #define ia64_invala() asm volatile ("invala" ::: "memory") -#define ia64_native_thash(addr) \ +#define ia64_thash(addr) \ ({ \ unsigned long ia64_intri_res; \ asm volatile ("thash %0=%1" : "=r"(ia64_intri_res) : "r" (addr)); \ @@ -437,10 +437,10 @@ extern void ia64_bad_param_for_getreg (void); #define ia64_set_pmd(index, val) \ asm volatile ("mov pmd[%0]=%1" :: "r"(index), "r"(val) : "memory") -#define ia64_native_set_rr(index, val) \ +#define ia64_set_rr(index, val) \ asm volatile ("mov rr[%0]=%1" :: "r"(index), "r"(val) : "memory"); -#define ia64_native_get_cpuid(index) \ +#define ia64_get_cpuid(index) \ ({ \ unsigned long ia64_intri_res; \ asm volatile ("mov %0=cpuid[%r1]" : "=r"(ia64_intri_res) : "rO"(index)); \ @@ -476,33 +476,33 @@ extern void ia64_bad_param_for_getreg (void); }) -#define ia64_native_get_pmd(index) \ +#define ia64_get_pmd(index) \ ({ \ unsigned long ia64_intri_res; \ asm volatile ("mov %0=pmd[%1]" : "=r"(ia64_intri_res) : "r"(index)); \ ia64_intri_res; \ }) -#define ia64_native_get_rr(index) \ +#define ia64_get_rr(index) \ ({ \ unsigned long ia64_intri_res; \ asm volatile ("mov %0=rr[%1]" : "=r"(ia64_intri_res) : "r" (index)); \ ia64_intri_res; \ }) -#define ia64_native_fc(addr) asm volatile ("fc %0" :: "r"(addr) : "memory") +#define ia64_fc(addr) asm volatile ("fc %0" :: "r"(addr) : "memory") #define ia64_sync_i() asm volatile (";; sync.i" ::: "memory") -#define ia64_native_ssm(mask) asm volatile ("ssm %0":: "i"((mask)) : "memory") -#define ia64_native_rsm(mask) asm volatile ("rsm %0":: "i"((mask)) : "memory") +#define ia64_ssm(mask) asm volatile ("ssm %0":: "i"((mask)) : "memory") +#define ia64_rsm(mask) asm volatile ("rsm %0":: "i"((mask)) : "memory") #define ia64_sum(mask) asm volatile ("sum %0":: "i"((mask)) : "memory") #define ia64_rum(mask) asm volatile ("rum %0":: "i"((mask)) : "memory") #define ia64_ptce(addr) asm volatile ("ptc.e %0" :: "r"(addr)) -#define ia64_native_ptcga(addr, size) \ +#define ia64_ptcga(addr, size) \ do { \ asm volatile ("ptc.ga %0,%1" :: "r"(addr), "r"(size) : "memory"); \ ia64_dv_serialize_data(); \ @@ -607,7 +607,7 @@ do { \ } \ }) -#define ia64_native_intrin_local_irq_restore(x) \ +#define ia64_intrin_local_irq_restore(x) \ do { \ asm volatile (";; cmp.ne p6,p7=%0,r0;;" \ "(p6) ssm psr.i;" \ diff --git a/arch/ia64/include/uapi/asm/intel_intrin.h b/arch/ia64/include/uapi/asm/intel_intrin.h index ab649691545a..dc1884dc54b5 100644 --- a/arch/ia64/include/uapi/asm/intel_intrin.h +++ b/arch/ia64/include/uapi/asm/intel_intrin.h @@ -17,8 +17,8 @@ * intrinsic */ -#define ia64_native_getreg __getReg -#define ia64_native_setreg __setReg +#define ia64_getreg __getReg +#define ia64_setreg __setReg #define ia64_hint __hint #define ia64_hint_pause __hint_pause @@ -40,10 +40,10 @@ #define ia64_invala_fr __invala_fr #define ia64_nop __nop #define ia64_sum __sum -#define ia64_native_ssm __ssm +#define ia64_ssm __ssm #define ia64_rum __rum -#define ia64_native_rsm __rsm -#define ia64_native_fc __fc +#define ia64_rsm __rsm +#define ia64_fc __fc #define ia64_ldfs __ldfs #define ia64_ldfd __ldfd @@ -89,17 +89,17 @@ __setIndReg(_IA64_REG_INDR_PMC, index, val) #define ia64_set_pmd(index, val) \ __setIndReg(_IA64_REG_INDR_PMD, index, val) -#define ia64_native_set_rr(index, val) \ +#define ia64_set_rr(index, val) \ __setIndReg(_IA64_REG_INDR_RR, index, val) -#define ia64_native_get_cpuid(index) \ +#define ia64_get_cpuid(index) \ __getIndReg(_IA64_REG_INDR_CPUID, index) #define __ia64_get_dbr(index) __getIndReg(_IA64_REG_INDR_DBR, index) #define ia64_get_ibr(index) __getIndReg(_IA64_REG_INDR_IBR, index) #define ia64_get_pkr(index) __getIndReg(_IA64_REG_INDR_PKR, index) #define ia64_get_pmc(index) __getIndReg(_IA64_REG_INDR_PMC, index) -#define ia64_native_get_pmd(index) __getIndReg(_IA64_REG_INDR_PMD, index) -#define ia64_native_get_rr(index) __getIndReg(_IA64_REG_INDR_RR, index) +#define ia64_get_pmd(index) __getIndReg(_IA64_REG_INDR_PMD, index) +#define ia64_get_rr(index) __getIndReg(_IA64_REG_INDR_RR, index) #define ia64_srlz_d __dsrlz #define ia64_srlz_i __isrlz @@ -121,16 +121,16 @@ #define ia64_ld8_acq __ld8_acq #define ia64_sync_i __synci -#define ia64_native_thash __thash -#define ia64_native_ttag __ttag +#define ia64_thash __thash +#define ia64_ttag __ttag #define ia64_itcd __itcd #define ia64_itci __itci #define ia64_itrd __itrd #define ia64_itri __itri #define ia64_ptce __ptce #define ia64_ptcl __ptcl -#define ia64_native_ptcg __ptcg -#define ia64_native_ptcga __ptcga +#define ia64_ptcg __ptcg +#define ia64_ptcga __ptcga #define ia64_ptri __ptri #define ia64_ptrd __ptrd #define ia64_dep_mi _m64_dep_mi @@ -147,13 +147,13 @@ #define ia64_lfetch_fault __lfetch_fault #define ia64_lfetch_fault_excl __lfetch_fault_excl -#define ia64_native_intrin_local_irq_restore(x) \ +#define ia64_intrin_local_irq_restore(x) \ do { \ if ((x) != 0) { \ - ia64_native_ssm(IA64_PSR_I); \ + ia64_ssm(IA64_PSR_I); \ ia64_srlz_d(); \ } else { \ - ia64_native_rsm(IA64_PSR_I); \ + ia64_rsm(IA64_PSR_I); \ } \ } while (0) diff --git a/arch/ia64/include/uapi/asm/intrinsics.h b/arch/ia64/include/uapi/asm/intrinsics.h index aecc217eca63..a0e0a064f5b1 100644 --- a/arch/ia64/include/uapi/asm/intrinsics.h +++ b/arch/ia64/include/uapi/asm/intrinsics.h @@ -21,15 +21,13 @@ #endif #include <asm/cmpxchg.h> -#define ia64_native_get_psr_i() (ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I) - -#define ia64_native_set_rr0_to_rr4(val0, val1, val2, val3, val4) \ +#define ia64_set_rr0_to_rr4(val0, val1, val2, val3, val4) \ do { \ - ia64_native_set_rr(0x0000000000000000UL, (val0)); \ - ia64_native_set_rr(0x2000000000000000UL, (val1)); \ - ia64_native_set_rr(0x4000000000000000UL, (val2)); \ - ia64_native_set_rr(0x6000000000000000UL, (val3)); \ - ia64_native_set_rr(0x8000000000000000UL, (val4)); \ + ia64_set_rr(0x0000000000000000UL, (val0)); \ + ia64_set_rr(0x2000000000000000UL, (val1)); \ + ia64_set_rr(0x4000000000000000UL, (val2)); \ + ia64_set_rr(0x6000000000000000UL, (val3)); \ + ia64_set_rr(0x8000000000000000UL, (val4)); \ } while (0) /* @@ -85,41 +83,4 @@ extern unsigned long __bad_increment_for_ia64_fetch_and_add (void); #endif - -#ifndef __ASSEMBLY__ - -#define IA64_INTRINSIC_API(name) ia64_native_ ## name -#define IA64_INTRINSIC_MACRO(name) ia64_native_ ## name - - -/************************************************/ -/* Instructions paravirtualized for correctness */ -/************************************************/ -/* fc, thash, get_cpuid, get_pmd, get_eflags, set_eflags */ -/* Note that "ttag" and "cover" are also privilege-sensitive; "ttag" - * is not currently used (though it may be in a long-format VHPT system!) - */ -#define ia64_fc IA64_INTRINSIC_API(fc) -#define ia64_thash IA64_INTRINSIC_API(thash) -#define ia64_get_cpuid IA64_INTRINSIC_API(get_cpuid) -#define ia64_get_pmd IA64_INTRINSIC_API(get_pmd) - - -/************************************************/ -/* Instructions paravirtualized for performance */ -/************************************************/ -#define ia64_ssm IA64_INTRINSIC_MACRO(ssm) -#define ia64_rsm IA64_INTRINSIC_MACRO(rsm) -#define ia64_getreg IA64_INTRINSIC_MACRO(getreg) -#define ia64_setreg IA64_INTRINSIC_API(setreg) -#define ia64_set_rr IA64_INTRINSIC_API(set_rr) -#define ia64_get_rr IA64_INTRINSIC_API(get_rr) -#define ia64_ptcga IA64_INTRINSIC_API(ptcga) -#define ia64_get_psr_i IA64_INTRINSIC_API(get_psr_i) -#define ia64_intrin_local_irq_restore \ - IA64_INTRINSIC_API(intrin_local_irq_restore) -#define ia64_set_rr0_to_rr4 IA64_INTRINSIC_API(set_rr0_to_rr4) - -#endif /* !__ASSEMBLY__ */ - #endif /* _UAPI_ASM_IA64_INTRINSICS_H */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e446bb5b3f8d..1ec34e16ed65 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -452,6 +452,23 @@ config PPC_TRANSACTIONAL_MEM help Support user-mode Transactional Memory on POWERPC. +config PPC_UV + bool "Ultravisor support" + depends on KVM_BOOK3S_HV_POSSIBLE + select ZONE_DEVICE + select DEV_PAGEMAP_OPS + select DEVICE_PRIVATE + select MEMORY_HOTPLUG + select MEMORY_HOTREMOVE + default n + help + This option paravirtualizes the kernel to run in POWER platforms that + supports the Protected Execution Facility (PEF). On such platforms, + the ultravisor firmware runs at a privilege level above the + hypervisor. + + If unsure, say "N". + config LD_HEAD_STUB_CATCH bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT depends on PPC64 diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 11112023e327..13bd870609c3 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -342,6 +342,15 @@ #define H_TLB_INVALIDATE 0xF808 #define H_COPY_TOFROM_GUEST 0xF80C +/* Flags for H_SVM_PAGE_IN */ +#define H_PAGE_IN_SHARED 0x1 + +/* Platform-specific hcalls used by the Ultravisor */ +#define H_SVM_PAGE_IN 0xEF00 +#define H_SVM_PAGE_OUT 0xEF04 +#define H_SVM_INIT_START 0xEF08 +#define H_SVM_INIT_DONE 0xEF0C + /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 #define H_SET_MODE_RESOURCE_SET_DAWR 2 diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h new file mode 100644 index 000000000000..50204e228f16 --- /dev/null +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_KVM_BOOK3S_UVMEM_H__ +#define __ASM_KVM_BOOK3S_UVMEM_H__ + +#ifdef CONFIG_PPC_UV +int kvmppc_uvmem_init(void); +void kvmppc_uvmem_free(void); +int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot); +void kvmppc_uvmem_slot_free(struct kvm *kvm, + const struct kvm_memory_slot *slot); +unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_page_out(struct kvm *kvm, + unsigned long gra, + unsigned long flags, + unsigned long page_shift); +unsigned long kvmppc_h_svm_init_start(struct kvm *kvm); +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm); +int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm); +#else +static inline int kvmppc_uvmem_init(void) +{ + return 0; +} + +static inline void kvmppc_uvmem_free(void) { } + +static inline int +kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + return 0; +} + +static inline void +kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) { } + +static inline unsigned long +kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long +kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gra, + unsigned long flags, unsigned long page_shift) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + +static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + return H_UNSUPPORTED; +} + +static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) +{ + return -EFAULT; +} + +static inline void +kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm) { } +#endif /* CONFIG_PPC_UV */ +#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 4273e799203d..0a398f2321c2 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -275,6 +275,10 @@ struct kvm_hpt_info { struct kvm_resize_hpt; +/* Flag values for kvm_arch.secure_guest */ +#define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */ +#define KVMPPC_SECURE_INIT_DONE 0x2 /* H_SVM_INIT_DONE completed */ + struct kvm_arch { unsigned int lpid; unsigned int smt_mode; /* # vcpus per virtual core */ @@ -330,6 +334,8 @@ struct kvm_arch { #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + struct mutex uvmem_lock; + struct list_head uvmem_pfns; struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; int max_nested_lpid; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d63f649fe713..3d2f871241a8 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -322,6 +322,7 @@ struct kvmppc_ops { int size); int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, int size); + int (*svm_off)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/ultravisor-api.h b/arch/powerpc/include/asm/ultravisor-api.h index 4fcda1d5793d..b66f6db7be6c 100644 --- a/arch/powerpc/include/asm/ultravisor-api.h +++ b/arch/powerpc/include/asm/ultravisor-api.h @@ -26,8 +26,14 @@ #define UV_WRITE_PATE 0xF104 #define UV_RETURN 0xF11C #define UV_ESM 0xF110 +#define UV_REGISTER_MEM_SLOT 0xF120 +#define UV_UNREGISTER_MEM_SLOT 0xF124 +#define UV_PAGE_IN 0xF128 +#define UV_PAGE_OUT 0xF12C #define UV_SHARE_PAGE 0xF130 #define UV_UNSHARE_PAGE 0xF134 #define UV_UNSHARE_ALL_PAGES 0xF140 +#define UV_PAGE_INVAL 0xF138 +#define UV_SVM_TERMINATE 0xF13C #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */ diff --git a/arch/powerpc/include/asm/ultravisor.h b/arch/powerpc/include/asm/ultravisor.h index b1bc2e043ed4..790b0e63681f 100644 --- a/arch/powerpc/include/asm/ultravisor.h +++ b/arch/powerpc/include/asm/ultravisor.h @@ -46,4 +46,40 @@ static inline int uv_unshare_all_pages(void) return ucall_norets(UV_UNSHARE_ALL_PAGES); } +static inline int uv_page_in(u64 lpid, u64 src_ra, u64 dst_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_IN, lpid, src_ra, dst_gpa, flags, + page_shift); +} + +static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags, + u64 page_shift) +{ + return ucall_norets(UV_PAGE_OUT, lpid, dst_ra, src_gpa, flags, + page_shift); +} + +static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size, + u64 flags, u64 slotid) +{ + return ucall_norets(UV_REGISTER_MEM_SLOT, lpid, start_gpa, + size, flags, slotid); +} + +static inline int uv_unregister_mem_slot(u64 lpid, u64 slotid) +{ + return ucall_norets(UV_UNREGISTER_MEM_SLOT, lpid, slotid); +} + +static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift) +{ + return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift); +} + +static inline int uv_svm_terminate(u64 lpid) +{ + return ucall_norets(UV_SVM_TERMINATE, lpid); +} + #endif /* _ASM_POWERPC_ULTRAVISOR_H */ diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 4c67cc79de7c..2bfeaa13befb 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -71,6 +71,9 @@ kvm-hv-y += \ book3s_64_mmu_radix.o \ book3s_hv_nested.o +kvm-hv-$(CONFIG_PPC_UV) += \ + book3s_hv_uvmem.o + kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \ book3s_hv_tm.o diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 2d415c36a61d..da857c8ba6e4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -19,6 +19,8 @@ #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/pte-walk.h> +#include <asm/ultravisor.h> +#include <asm/kvm_book3s_uvmem.h> /* * Supported radix tree geometry. @@ -915,6 +917,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (!(dsisr & DSISR_PRTABLE_FAULT)) gpa |= ea & 0xfff; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return kvmppc_send_page_to_uv(kvm, gfn); + /* Get the corresponding memslot */ memslot = gfn_to_memslot(kvm, gfn); @@ -972,6 +977,11 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gpa = gfn << PAGE_SHIFT; unsigned int shift; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) { + uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT); + return 0; + } + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep)) kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot, @@ -989,6 +999,9 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, int ref = 0; unsigned long old, *rmapp; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ref; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) { old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0, @@ -1013,6 +1026,9 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned int shift; int ref = 0; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ref; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) ref = 1; @@ -1030,6 +1046,9 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm, int ret = 0; unsigned long old, *rmapp; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return ret; + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) { ret = 1; @@ -1082,6 +1101,12 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm, unsigned long gpa; unsigned int shift; + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START) + kvmppc_uvmem_drop_pages(memslot, kvm); + + if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) + return; + gpa = memslot->base_gfn << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); for (n = memslot->npages; n; --n) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec5c0379296a..dc53578193ee 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -72,6 +72,9 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/hw_breakpoint.h> +#include <asm/kvm_host.h> +#include <asm/kvm_book3s_uvmem.h> +#include <asm/ultravisor.h> #include "book3s.h" @@ -1070,6 +1073,25 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 5), kvmppc_get_gpr(vcpu, 6)); break; + case H_SVM_PAGE_IN: + ret = kvmppc_h_svm_page_in(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + break; + case H_SVM_PAGE_OUT: + ret = kvmppc_h_svm_page_out(vcpu->kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + break; + case H_SVM_INIT_START: + ret = kvmppc_h_svm_init_start(vcpu->kvm); + break; + case H_SVM_INIT_DONE: + ret = kvmppc_h_svm_init_done(vcpu->kvm); + break; + default: return RESUME_HOST; } @@ -4494,6 +4516,29 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, if (change == KVM_MR_FLAGS_ONLY && kvm_is_radix(kvm) && ((new->flags ^ old->flags) & KVM_MEM_LOG_DIRTY_PAGES)) kvmppc_radix_flush_memslot(kvm, old); + /* + * If UV hasn't yet called H_SVM_INIT_START, don't register memslots. + */ + if (!kvm->arch.secure_guest) + return; + + switch (change) { + case KVM_MR_CREATE: + if (kvmppc_uvmem_slot_init(kvm, new)) + return; + uv_register_mem_slot(kvm->arch.lpid, + new->base_gfn << PAGE_SHIFT, + new->npages * PAGE_SIZE, + 0, new->id); + break; + case KVM_MR_DELETE: + uv_unregister_mem_slot(kvm->arch.lpid, old->id); + kvmppc_uvmem_slot_free(kvm, old); + break; + default: + /* TODO: Handle KVM_MR_MOVE */ + break; + } } /* @@ -4767,6 +4812,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) char buf[32]; int ret; + mutex_init(&kvm->arch.uvmem_lock); + INIT_LIST_HEAD(&kvm->arch.uvmem_pfns); mutex_init(&kvm->arch.mmu_setup_lock); /* Allocate the guest's logical partition ID */ @@ -4936,8 +4983,10 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvm->arch.process_table = 0; + uv_svm_terminate(kvm->arch.lpid); kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } + kvmppc_free_lpid(kvm->arch.lpid); kvmppc_free_pimap(kvm); @@ -5377,6 +5426,94 @@ static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr, return rc; } +static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) +{ + unpin_vpa(kvm, vpa); + vpa->gpa = 0; + vpa->pinned_addr = NULL; + vpa->dirty = false; + vpa->update_pending = 0; +} + +/* + * IOCTL handler to turn off secure mode of guest + * + * - Release all device pages + * - Issue ucall to terminate the guest on the UV side + * - Unpin the VPA pages. + * - Reinit the partition scoped page tables + */ +static int kvmhv_svm_off(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int mmu_was_ready; + int srcu_idx; + int ret = 0; + int i; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return ret; + + mutex_lock(&kvm->arch.mmu_setup_lock); + mmu_was_ready = kvm->arch.mmu_ready; + if (kvm->arch.mmu_ready) { + kvm->arch.mmu_ready = 0; + /* order mmu_ready vs. vcpus_running */ + smp_mb(); + if (atomic_read(&kvm->arch.vcpus_running)) { + kvm->arch.mmu_ready = 1; + ret = -EBUSY; + goto out; + } + } + + srcu_idx = srcu_read_lock(&kvm->srcu); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_memory_slot *memslot; + struct kvm_memslots *slots = __kvm_memslots(kvm, i); + + if (!slots) + continue; + + kvm_for_each_memslot(memslot, slots) { + kvmppc_uvmem_drop_pages(memslot, kvm); + uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); + } + } + srcu_read_unlock(&kvm->srcu, srcu_idx); + + ret = uv_svm_terminate(kvm->arch.lpid); + if (ret != U_SUCCESS) { + ret = -EINVAL; + goto out; + } + + /* + * When secure guest is reset, all the guest pages are sent + * to UV via UV_PAGE_IN before the non-boot vcpus get a + * chance to run and unpin their VPA pages. Unpinning of all + * VPA pages is done here explicitly so that VPA pages + * can be migrated to the secure side. + * + * This is required to for the secure SMP guest to reboot + * correctly. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + spin_lock(&vcpu->arch.vpa_update_lock); + unpin_vpa_reset(kvm, &vcpu->arch.dtl); + unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow); + unpin_vpa_reset(kvm, &vcpu->arch.vpa); + spin_unlock(&vcpu->arch.vpa_update_lock); + } + + kvmppc_setup_partition_table(kvm); + kvm->arch.secure_guest = 0; + kvm->arch.mmu_ready = mmu_was_ready; +out: + mutex_unlock(&kvm->arch.mmu_setup_lock); + return ret; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -5420,6 +5557,7 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .svm_off = kvmhv_svm_off, }; static int kvm_init_subcore_bitmap(void) @@ -5528,11 +5666,16 @@ static int kvmppc_book3s_init_hv(void) no_mixing_hpt_and_radix = true; } + r = kvmppc_uvmem_init(); + if (r < 0) + pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r); + return r; } static void kvmppc_book3s_exit_hv(void) { + kvmppc_uvmem_free(); kvmppc_free_host_rm_ops(); if (kvmppc_radix_possible()) kvmppc_radix_exit(); diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c new file mode 100644 index 000000000000..2de264fc3156 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -0,0 +1,785 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Secure pages management: Migration of pages between normal and secure + * memory of KVM guests. + * + * Copyright 2018 Bharata B Rao, IBM Corp. <bharata@linux.ibm.com> + */ + +/* + * A pseries guest can be run as secure guest on Ultravisor-enabled + * POWER platforms. On such platforms, this driver will be used to manage + * the movement of guest pages between the normal memory managed by + * hypervisor (HV) and secure memory managed by Ultravisor (UV). + * + * The page-in or page-out requests from UV will come to HV as hcalls and + * HV will call back into UV via ultracalls to satisfy these page requests. + * + * Private ZONE_DEVICE memory equal to the amount of secure memory + * available in the platform for running secure guests is hotplugged. + * Whenever a page belonging to the guest becomes secure, a page from this + * private device memory is used to represent and track that secure page + * on the HV side. Some pages (like virtio buffers, VPA pages etc) are + * shared between UV and HV. However such pages aren't represented by + * device private memory and mappings to shared memory exist in both + * UV and HV page tables. + */ + +/* + * Notes on locking + * + * kvm->arch.uvmem_lock is a per-guest lock that prevents concurrent + * page-in and page-out requests for the same GPA. Concurrent accesses + * can either come via UV (guest vCPUs requesting for same page) + * or when HV and guest simultaneously access the same page. + * This mutex serializes the migration of page from HV(normal) to + * UV(secure) and vice versa. So the serialization points are around + * migrate_vma routines and page-in/out routines. + * + * Per-guest mutex comes with a cost though. Mainly it serializes the + * fault path as page-out can occur when HV faults on accessing secure + * guest pages. Currently UV issues page-in requests for all the guest + * PFNs one at a time during early boot (UV_ESM uvcall), so this is + * not a cause for concern. Also currently the number of page-outs caused + * by HV touching secure pages is very very low. If an when UV supports + * overcommitting, then we might see concurrent guest driven page-outs. + * + * Locking order + * + * 1. kvm->srcu - Protects KVM memslots + * 2. kvm->mm->mmap_sem - find_vma, migrate_vma_pages and helpers, ksm_madvise + * 3. kvm->arch.uvmem_lock - protects read/writes to uvmem slots thus acting + * as sync-points for page-in/out + */ + +/* + * Notes on page size + * + * Currently UV uses 2MB mappings internally, but will issue H_SVM_PAGE_IN + * and H_SVM_PAGE_OUT hcalls in PAGE_SIZE(64K) granularity. HV tracks + * secure GPAs at 64K page size and maintains one device PFN for each + * 64K secure GPA. UV_PAGE_IN and UV_PAGE_OUT calls by HV are also issued + * for 64K page at a time. + * + * HV faulting on secure pages: When HV touches any secure page, it + * faults and issues a UV_PAGE_OUT request with 64K page size. Currently + * UV splits and remaps the 2MB page if necessary and copies out the + * required 64K page contents. + * + * Shared pages: Whenever guest shares a secure page, UV will split and + * remap the 2MB page if required and issue H_SVM_PAGE_IN with 64K page size. + * + * HV invalidating a page: When a regular page belonging to secure + * guest gets unmapped, HV informs UV with UV_PAGE_INVAL of 64K + * page size. Using 64K page size is correct here because any non-secure + * page will essentially be of 64K page size. Splitting by UV during sharing + * and page-out ensures this. + * + * Page fault handling: When HV handles page fault of a page belonging + * to secure guest, it sends that to UV with a 64K UV_PAGE_IN request. + * Using 64K size is correct here too as UV would have split the 2MB page + * into 64k mappings and would have done page-outs earlier. + * + * In summary, the current secure pages handling code in HV assumes + * 64K page size and in fact fails any page-in/page-out requests of + * non-64K size upfront. If and when UV starts supporting multiple + * page-sizes, we need to break this assumption. + */ + +#include <linux/pagemap.h> +#include <linux/migrate.h> +#include <linux/kvm_host.h> +#include <linux/ksm.h> +#include <asm/ultravisor.h> +#include <asm/mman.h> +#include <asm/kvm_ppc.h> + +static struct dev_pagemap kvmppc_uvmem_pgmap; +static unsigned long *kvmppc_uvmem_bitmap; +static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock); + +#define KVMPPC_UVMEM_PFN (1UL << 63) + +struct kvmppc_uvmem_slot { + struct list_head list; + unsigned long nr_pfns; + unsigned long base_pfn; + unsigned long *pfns; +}; + +struct kvmppc_uvmem_page_pvt { + struct kvm *kvm; + unsigned long gpa; + bool skip_page_out; +}; + +int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + struct kvmppc_uvmem_slot *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns))); + if (!p->pfns) { + kfree(p); + return -ENOMEM; + } + p->nr_pfns = slot->npages; + p->base_pfn = slot->base_gfn; + + mutex_lock(&kvm->arch.uvmem_lock); + list_add(&p->list, &kvm->arch.uvmem_pfns); + mutex_unlock(&kvm->arch.uvmem_lock); + + return 0; +} + +/* + * All device PFNs are already released by the time we come here. + */ +void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) +{ + struct kvmppc_uvmem_slot *p, *next; + + mutex_lock(&kvm->arch.uvmem_lock); + list_for_each_entry_safe(p, next, &kvm->arch.uvmem_pfns, list) { + if (p->base_pfn == slot->base_gfn) { + vfree(p->pfns); + list_del(&p->list); + kfree(p); + break; + } + } + mutex_unlock(&kvm->arch.uvmem_lock); +} + +static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, + struct kvm *kvm) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + unsigned long index = gfn - p->base_pfn; + + p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN; + return; + } + } +} + +static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + p->pfns[gfn - p->base_pfn] = 0; + return; + } + } +} + +static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, + unsigned long *uvmem_pfn) +{ + struct kvmppc_uvmem_slot *p; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { + if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { + unsigned long index = gfn - p->base_pfn; + + if (p->pfns[index] & KVMPPC_UVMEM_PFN) { + if (uvmem_pfn) + *uvmem_pfn = p->pfns[index] & + ~KVMPPC_UVMEM_PFN; + return true; + } else + return false; + } + } + return false; +} + +unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int ret = H_SUCCESS; + int srcu_idx; + + if (!kvmppc_uvmem_bitmap) + return H_UNSUPPORTED; + + /* Only radix guests can be secure guests */ + if (!kvm_is_radix(kvm)) + return H_UNSUPPORTED; + + srcu_idx = srcu_read_lock(&kvm->srcu); + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { + if (kvmppc_uvmem_slot_init(kvm, memslot)) { + ret = H_PARAMETER; + goto out; + } + ret = uv_register_mem_slot(kvm->arch.lpid, + memslot->base_gfn << PAGE_SHIFT, + memslot->npages * PAGE_SIZE, + 0, memslot->id); + if (ret < 0) { + kvmppc_uvmem_slot_free(kvm, memslot); + ret = H_PARAMETER; + goto out; + } + } + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START; +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; + pr_info("LPID %d went secure\n", kvm->arch.lpid); + return H_SUCCESS; +} + +/* + * Drop device pages that we maintain for the secure guest + * + * We first mark the pages to be skipped from UV_PAGE_OUT when there + * is HV side fault on these pages. Next we *get* these pages, forcing + * fault on them, do fault time migration to replace the device PTEs in + * QEMU page table with normal PTEs from newly allocated pages. + */ +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, + struct kvm *kvm) +{ + int i; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn, uvmem_pfn; + unsigned long gfn = free->base_gfn; + + for (i = free->npages; i; --i, ++gfn) { + struct page *uvmem_page; + + mutex_lock(&kvm->arch.uvmem_lock); + if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + mutex_unlock(&kvm->arch.uvmem_lock); + continue; + } + + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + mutex_unlock(&kvm->arch.uvmem_lock); + + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + continue; + kvm_release_pfn_clean(pfn); + } +} + +/* + * Get a free device PFN from the pool + * + * Called when a normal page is moved to secure memory (UV_PAGE_IN). Device + * PFN will be used to keep track of the secure page on HV side. + * + * Called with kvm->arch.uvmem_lock held + */ +static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) +{ + struct page *dpage = NULL; + unsigned long bit, uvmem_pfn; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn_last, pfn_first; + + pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT; + pfn_last = pfn_first + + (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT); + + spin_lock(&kvmppc_uvmem_bitmap_lock); + bit = find_first_zero_bit(kvmppc_uvmem_bitmap, + pfn_last - pfn_first); + if (bit >= (pfn_last - pfn_first)) + goto out; + bitmap_set(kvmppc_uvmem_bitmap, bit, 1); + spin_unlock(&kvmppc_uvmem_bitmap_lock); + + pvt = kzalloc(sizeof(*pvt), GFP_KERNEL); + if (!pvt) + goto out_clear; + + uvmem_pfn = bit + pfn_first; + kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); + + pvt->gpa = gpa; + pvt->kvm = kvm; + + dpage = pfn_to_page(uvmem_pfn); + dpage->zone_device_data = pvt; + get_page(dpage); + lock_page(dpage); + return dpage; +out_clear: + spin_lock(&kvmppc_uvmem_bitmap_lock); + bitmap_clear(kvmppc_uvmem_bitmap, bit, 1); +out: + spin_unlock(&kvmppc_uvmem_bitmap_lock); + return NULL; +} + +/* + * Alloc a PFN from private device memory pool and copy page from normal + * memory to secure memory using UV_PAGE_IN uvcall. + */ +static int +kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long gpa, struct kvm *kvm, + unsigned long page_shift, bool *downgrade) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *spage; + unsigned long pfn; + struct page *dpage; + int ret = 0; + + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + + /* + * We come here with mmap_sem write lock held just for + * ksm_madvise(), otherwise we only need read mmap_sem. + * Hence downgrade to read lock once ksm_madvise() is done. + */ + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + MADV_UNMERGEABLE, &vma->vm_flags); + downgrade_write(&kvm->mm->mmap_sem); + *downgrade = true; + if (ret) + return ret; + + ret = migrate_vma_setup(&mig); + if (ret) + return ret; + + if (!(*mig.src & MIGRATE_PFN_MIGRATE)) { + ret = -1; + goto out_finalize; + } + + dpage = kvmppc_uvmem_get_page(gpa, kvm); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + pfn = *mig.src >> MIGRATE_PFN_SHIFT; + spage = migrate_pfn_to_page(*mig.src); + if (spage) + uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, + page_shift); + + *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + migrate_vma_pages(&mig); +out_finalize: + migrate_vma_finalize(&mig); + return ret; +} + +/* + * Shares the page with HV, thus making it a normal page. + * + * - If the page is already secure, then provision a new page and share + * - If the page is a normal page, share the existing page + * + * In the former case, uses dev_pagemap_ops.migrate_to_ram handler + * to unmap the device page from QEMU's page tables. + */ +static unsigned long +kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) +{ + + int ret = H_PARAMETER; + struct page *uvmem_page; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + unsigned long gfn = gpa >> page_shift; + int srcu_idx; + unsigned long uvmem_pfn; + + srcu_idx = srcu_read_lock(&kvm->srcu); + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + } + +retry: + mutex_unlock(&kvm->arch.uvmem_lock); + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + goto out; + + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = true; + kvm_release_pfn_clean(pfn); + goto retry; + } + + if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift)) + ret = H_SUCCESS; + kvm_release_pfn_clean(pfn); + mutex_unlock(&kvm->arch.uvmem_lock); +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +/* + * H_SVM_PAGE_IN: Move page from normal memory to secure memory. + * + * H_PAGE_IN_SHARED flag makes the page shared which means that the same + * memory in is visible from both UV and HV. + */ +unsigned long +kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, + unsigned long flags, unsigned long page_shift) +{ + bool downgrade = false; + unsigned long start, end; + struct vm_area_struct *vma; + int srcu_idx; + unsigned long gfn = gpa >> page_shift; + int ret; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + if (page_shift != PAGE_SHIFT) + return H_P3; + + if (flags & ~H_PAGE_IN_SHARED) + return H_P2; + + if (flags & H_PAGE_IN_SHARED) + return kvmppc_share_page(kvm, gpa, page_shift); + + ret = H_PARAMETER; + srcu_idx = srcu_read_lock(&kvm->srcu); + down_write(&kvm->mm->mmap_sem); + + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + goto out; + + mutex_lock(&kvm->arch.uvmem_lock); + /* Fail the page-in request of an already paged-in page */ + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL)) + goto out_unlock; + + end = start + (1UL << page_shift); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + goto out_unlock; + + if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, + &downgrade)) + ret = H_SUCCESS; +out_unlock: + mutex_unlock(&kvm->arch.uvmem_lock); +out: + if (downgrade) + up_read(&kvm->mm->mmap_sem); + else + up_write(&kvm->mm->mmap_sem); + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +/* + * Provision a new page on HV side and copy over the contents + * from secure memory using UV_PAGE_OUT uvcall. + */ +static int +kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) +{ + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *dpage, *spage; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + int ret = U_SUCCESS; + + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + + mutex_lock(&kvm->arch.uvmem_lock); + /* The requested page is already paged-out, nothing to do */ + if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) + goto out; + + ret = migrate_vma_setup(&mig); + if (ret) + return ret; + + spage = migrate_pfn_to_page(*mig.src); + if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) + goto out_finalize; + + if (!is_zone_device_page(spage)) + goto out_finalize; + + dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + lock_page(dpage); + pvt = spage->zone_device_data; + pfn = page_to_pfn(dpage); + + /* + * This function is used in two cases: + * - When HV touches a secure page, for which we do UV_PAGE_OUT + * - When a secure page is converted to shared page, we *get* + * the page to essentially unmap the device page. In this + * case we skip page-out. + */ + if (!pvt->skip_page_out) + ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + + if (ret == U_SUCCESS) + *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + else { + unlock_page(dpage); + __free_page(dpage); + goto out_finalize; + } + + migrate_vma_pages(&mig); +out_finalize: + migrate_vma_finalize(&mig); +out: + mutex_unlock(&kvm->arch.uvmem_lock); + return ret; +} + +/* + * Fault handler callback that gets called when HV touches any page that + * has been moved to secure memory, we ask UV to give back the page by + * issuing UV_PAGE_OUT uvcall. + * + * This eventually results in dropping of device PFN and the newly + * provisioned page/PFN gets populated in QEMU page tables. + */ +static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) +{ + struct kvmppc_uvmem_page_pvt *pvt = vmf->page->zone_device_data; + + if (kvmppc_svm_page_out(vmf->vma, vmf->address, + vmf->address + PAGE_SIZE, PAGE_SHIFT, + pvt->kvm, pvt->gpa)) + return VM_FAULT_SIGBUS; + else + return 0; +} + +/* + * Release the device PFN back to the pool + * + * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT. + * Gets called with kvm->arch.uvmem_lock held. + */ +static void kvmppc_uvmem_page_free(struct page *page) +{ + unsigned long pfn = page_to_pfn(page) - + (kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT); + struct kvmppc_uvmem_page_pvt *pvt; + + spin_lock(&kvmppc_uvmem_bitmap_lock); + bitmap_clear(kvmppc_uvmem_bitmap, pfn, 1); + spin_unlock(&kvmppc_uvmem_bitmap_lock); + + pvt = page->zone_device_data; + page->zone_device_data = NULL; + kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + kfree(pvt); +} + +static const struct dev_pagemap_ops kvmppc_uvmem_ops = { + .page_free = kvmppc_uvmem_page_free, + .migrate_to_ram = kvmppc_uvmem_migrate_to_ram, +}; + +/* + * H_SVM_PAGE_OUT: Move page from secure memory to normal memory. + */ +unsigned long +kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa, + unsigned long flags, unsigned long page_shift) +{ + unsigned long gfn = gpa >> page_shift; + unsigned long start, end; + struct vm_area_struct *vma; + int srcu_idx; + int ret; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + if (page_shift != PAGE_SHIFT) + return H_P3; + + if (flags) + return H_P2; + + ret = H_PARAMETER; + srcu_idx = srcu_read_lock(&kvm->srcu); + down_read(&kvm->mm->mmap_sem); + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + goto out; + + end = start + (1UL << page_shift); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + goto out; + + if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa)) + ret = H_SUCCESS; +out: + up_read(&kvm->mm->mmap_sem); + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + +int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) +{ + unsigned long pfn; + int ret = U_SUCCESS; + + pfn = gfn_to_pfn(kvm, gfn); + if (is_error_noslot_pfn(pfn)) + return -EFAULT; + + mutex_lock(&kvm->arch.uvmem_lock); + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL)) + goto out; + + ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT, + 0, PAGE_SHIFT); +out: + kvm_release_pfn_clean(pfn); + mutex_unlock(&kvm->arch.uvmem_lock); + return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT; +} + +static u64 kvmppc_get_secmem_size(void) +{ + struct device_node *np; + int i, len; + const __be32 *prop; + u64 size = 0; + + np = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware"); + if (!np) + goto out; + + prop = of_get_property(np, "secure-memory-ranges", &len); + if (!prop) + goto out_put; + + for (i = 0; i < len / (sizeof(*prop) * 4); i++) + size += of_read_number(prop + (i * 4) + 2, 2); + +out_put: + of_node_put(np); +out: + return size; +} + +int kvmppc_uvmem_init(void) +{ + int ret = 0; + unsigned long size; + struct resource *res; + void *addr; + unsigned long pfn_last, pfn_first; + + size = kvmppc_get_secmem_size(); + if (!size) { + /* + * Don't fail the initialization of kvm-hv module if + * the platform doesn't export ibm,uv-firmware node. + * Let normal guests run on such PEF-disabled platform. + */ + pr_info("KVMPPC-UVMEM: No support for secure guests\n"); + goto out; + } + + res = request_free_mem_region(&iomem_resource, size, "kvmppc_uvmem"); + if (IS_ERR(res)) { + ret = PTR_ERR(res); + goto out; + } + + kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE; + kvmppc_uvmem_pgmap.res = *res; + kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops; + addr = memremap_pages(&kvmppc_uvmem_pgmap, NUMA_NO_NODE); + if (IS_ERR(addr)) { + ret = PTR_ERR(addr); + goto out_free_region; + } + + pfn_first = res->start >> PAGE_SHIFT; + pfn_last = pfn_first + (resource_size(res) >> PAGE_SHIFT); + kvmppc_uvmem_bitmap = kcalloc(BITS_TO_LONGS(pfn_last - pfn_first), + sizeof(unsigned long), GFP_KERNEL); + if (!kvmppc_uvmem_bitmap) { + ret = -ENOMEM; + goto out_unmap; + } + + pr_info("KVMPPC-UVMEM: Secure Memory size 0x%lx\n", size); + return ret; +out_unmap: + memunmap_pages(&kvmppc_uvmem_pgmap); +out_free_region: + release_mem_region(res->start, size); +out: + return ret; +} + +void kvmppc_uvmem_free(void) +{ + memunmap_pages(&kvmppc_uvmem_pgmap); + release_mem_region(kvmppc_uvmem_pgmap.res.start, + resource_size(&kvmppc_uvmem_pgmap.res)); + kfree(kvmppc_uvmem_bitmap); +} diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9e085e931d74..416fb3d2a1d0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -31,6 +31,8 @@ #include <asm/hvcall.h> #include <asm/plpar_wrappers.h> #endif +#include <asm/ultravisor.h> +#include <asm/kvm_host.h> #include "timing.h" #include "irq.h" @@ -2413,6 +2415,16 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + case KVM_PPC_SVM_OFF: { + struct kvm *kvm = filp->private_data; + + r = 0; + if (!kvm->arch.kvm_ops->svm_off) + goto out; + + r = kvm->arch.kvm_ops->svm_off(kvm); + break; + } default: { struct kvm *kvm = filp->private_data; r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg); diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 536c0ef4aee8..634759ac8c71 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -1,13 +1,13 @@ menu "SoC selection" config SOC_SIFIVE - bool "SiFive SoCs" - select SERIAL_SIFIVE - select SERIAL_SIFIVE_CONSOLE - select CLK_SIFIVE - select CLK_SIFIVE_FU540_PRCI - select SIFIVE_PLIC - help - This enables support for SiFive SoC platform hardware. + bool "SiFive SoCs" + select SERIAL_SIFIVE + select SERIAL_SIFIVE_CONSOLE + select CLK_SIFIVE + select CLK_SIFIVE_FU540_PRCI + select SIFIVE_PLIC + help + This enables support for SiFive SoC platform hardware. endmenu diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 420a0dbef386..e2ff95cb3390 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -100,4 +100,28 @@ CONFIG_9P_FS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_PGFLAGS=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_DEBUG_TIMEKEEPING=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_RWSEMS=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_STACKTRACE=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PLIST=y +CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set +CONFIG_RCU_EQS_DEBUG=y +CONFIG_DEBUG_BLOCK_EXT_DEVT=y +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_MEMTEST=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 87ee6e62b64b..eb519407c841 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -97,4 +97,28 @@ CONFIG_9P_FS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_FS=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_VM_PGFLAGS=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_PER_CPU_MAPS=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_DEBUG_TIMEKEEPING=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_RWSEMS=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_STACKTRACE=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PLIST=y +CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set +CONFIG_RCU_EQS_DEBUG=y +CONFIG_DEBUG_BLOCK_EXT_DEVT=y +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_MEMTEST=y diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b2fe9d1be833..69f6678db7f3 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -46,6 +46,37 @@ static void setup_zero_page(void) memset((void *)empty_zero_page, 0, PAGE_SIZE); } +#ifdef CONFIG_DEBUG_VM +static inline void print_mlk(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld kB)\n", name, b, t, + (((t) - (b)) >> 10)); +} + +static inline void print_mlm(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld MB)\n", name, b, t, + (((t) - (b)) >> 20)); +} + +static void print_vm_layout(void) +{ + pr_notice("Virtual kernel memory layout:\n"); + print_mlk("fixmap", (unsigned long)FIXADDR_START, + (unsigned long)FIXADDR_TOP); + print_mlm("pci io", (unsigned long)PCI_IO_START, + (unsigned long)PCI_IO_END); + print_mlm("vmemmap", (unsigned long)VMEMMAP_START, + (unsigned long)VMEMMAP_END); + print_mlm("vmalloc", (unsigned long)VMALLOC_START, + (unsigned long)VMALLOC_END); + print_mlm("lowmem", (unsigned long)PAGE_OFFSET, + (unsigned long)high_memory); +} +#else +static void print_vm_layout(void) { } +#endif /* CONFIG_DEBUG_VM */ + void __init mem_init(void) { #ifdef CONFIG_FLATMEM @@ -56,6 +87,7 @@ void __init mem_init(void) memblock_free_all(); mem_init_print_info(NULL); + print_vm_layout(); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c index dbd2cdec2ddb..b0f9c8f8fd14 100644 --- a/arch/sh/kernel/cpu/shmobile/cpuidle.c +++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c @@ -67,7 +67,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C2", .desc = "SuperH Sleep Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, { .exit_latency = 2300, @@ -76,7 +76,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C3", .desc = "SuperH Mobile Standby Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, }, .safe_state_index = 0, @@ -86,10 +86,10 @@ static struct cpuidle_driver cpuidle_driver = { int __init sh_mobile_setup_cpuidle(void) { if (sh_mobile_sleep_supported & SUSP_SH_SF) - cpuidle_driver.states[1].disabled = false; + cpuidle_driver.states[1].flags = CPUIDLE_FLAG_NONE; if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) - cpuidle_driver.states[2].disabled = false; + cpuidle_driver.states[2].flags = CPUIDLE_FLAG_NONE; return cpuidle_register(&cpuidle_driver, NULL); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c0aa07487eb8..cfafa320a8cf 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -504,7 +504,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, r = -E2BIG; - if (*nent >= maxnent) + if (WARN_ON(*nent >= maxnent)) goto out; do_host_cpuid(entry, function, 0); @@ -778,6 +778,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, case 0x8000001a: case 0x8000001e: break; + /* Support memory encryption cpuid if host supports it */ + case 0x8000001F: + if (!boot_cpu_has(X86_FEATURE_SEV)) + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; /*Add support for Centaur's CPUID instruction*/ case 0xC0000000: /*Just support up to 0xC0000004 now*/ @@ -810,6 +815,9 @@ out: static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, int *nent, int maxnent, unsigned int type) { + if (*nent >= maxnent) + return -E2BIG; + if (type == KVM_GET_EMULATED_CPUID) return __do_cpuid_func_emulated(entry, func, nent, maxnent); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 362e874297e4..122d4ce3b1ab 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5958,13 +5958,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) if (npt_enabled) entry->edx |= F(NPT); - break; - case 0x8000001F: - /* Support memory encryption cpuid if host supports it */ - if (boot_cpu_has(X86_FEATURE_SEV)) - cpuid(0x8000001f, &entry->eax, &entry->ebx, - &entry->ecx, &entry->edx); - } } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1b9ab4166397..e3394c839dea 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6666,7 +6666,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_vpid(vmx->vpid); nested_vmx_free_vcpu(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); - kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); @@ -6723,12 +6722,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit_vcpu; } - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); - BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0]) - > PAGE_SIZE); - - if (!vmx->guest_msrs) - goto free_pml; + BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS); for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; @@ -6760,7 +6754,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) err = alloc_loaded_vmcs(&vmx->vmcs01); if (err < 0) - goto free_msrs; + goto free_pml; msr_bitmap = vmx->vmcs01.msr_bitmap; vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R); @@ -6822,8 +6816,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) free_vmcs: free_loaded_vmcs(vmx->loaded_vmcs); -free_msrs: - kfree(vmx->guest_msrs); free_pml: vmx_destroy_pml_buffer(vmx); uninit_vcpu: diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7c1b978b2df4..a4f7f737c5d4 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -22,6 +22,12 @@ extern u32 get_umwait_control_msr(void); #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) +#ifdef CONFIG_X86_64 +#define NR_SHARED_MSRS 7 +#else +#define NR_SHARED_MSRS 4 +#endif + #define NR_LOADSTORE_MSRS 8 struct vmx_msrs { @@ -206,7 +212,7 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; - struct shared_msr_entry *guest_msrs; + struct shared_msr_entry guest_msrs[NR_SHARED_MSRS]; int nmsrs; int save_nmsrs; bool guest_msrs_ready; diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 4fb97511a16f..002838d23b86 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -104,9 +104,9 @@ config ACPI_PROCFS_POWER depends on X86 && PROC_FS help For backwards compatibility, this option allows - deprecated power /proc/acpi/ directories to exist, even when - they have been replaced by functions in /sys. - The deprecated directories (and their replacements) include: + deprecated power /proc/acpi/ directories to exist, even when + they have been replaced by functions in /sys. + The deprecated directories (and their replacements) include: /proc/acpi/battery/* (/sys/class/power_supply/*) and /proc/acpi/ac_adapter/* (sys/class/power_supply/*). This option has no effect on /proc/acpi/ directories @@ -448,7 +448,7 @@ config ACPI_CUSTOM_METHOD config ACPI_BGRT bool "Boottime Graphics Resource Table support" depends on EFI && (X86 || ARM64) - help + help This driver adds support for exposing the ACPI Boottime Graphics Resource Table, which allows the operating system to obtain data from the firmware boot splash. It will appear under diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 48bc96d45bab..54002670cb7a 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -153,7 +153,7 @@ int acpi_bus_get_private_data(acpi_handle handle, void **data) { acpi_status status; - if (!*data) + if (!data) return -EINVAL; status = acpi_get_data(handle, acpi_bus_private_data_handler, data); diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index d27b01c0323d..b758b45737f5 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -79,6 +79,19 @@ MODULE_DEVICE_TABLE(acpi, button_device_ids); static const struct dmi_system_id dmi_lid_quirks[] = { { /* + * Acer Switch 10 SW5-012. _LID method messes with home and + * power button GPIO IRQ settings causing an interrupt storm on + * both GPIOs. This is unfixable without a DSDT override, so we + * have to disable the lid-switch functionality altogether :| + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED, + }, + { + /* * Asus T200TA, _LID keeps reporting closed after every second * openening of the lid. Causing immediate re-suspend after * opening every other open. Using LID_INIT_OPEN fixes this. diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 4fd84fbdac29..d05be13c1022 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -533,26 +533,10 @@ static void acpi_ec_enable_event(struct acpi_ec *ec) } #ifdef CONFIG_PM_SLEEP -static bool acpi_ec_query_flushed(struct acpi_ec *ec) +static void __acpi_ec_flush_work(void) { - bool flushed; - unsigned long flags; - - spin_lock_irqsave(&ec->lock, flags); - flushed = !ec->nr_pending_queries; - spin_unlock_irqrestore(&ec->lock, flags); - return flushed; -} - -static void __acpi_ec_flush_event(struct acpi_ec *ec) -{ - /* - * When ec_freeze_events is true, we need to flush events in - * the proper position before entering the noirq stage. - */ - wait_event(ec->wait, acpi_ec_query_flushed(ec)); - if (ec_query_wq) - flush_workqueue(ec_query_wq); + flush_scheduled_work(); /* flush ec->work */ + flush_workqueue(ec_query_wq); /* flush queries */ } static void acpi_ec_disable_event(struct acpi_ec *ec) @@ -562,15 +546,21 @@ static void acpi_ec_disable_event(struct acpi_ec *ec) spin_lock_irqsave(&ec->lock, flags); __acpi_ec_disable_event(ec); spin_unlock_irqrestore(&ec->lock, flags); - __acpi_ec_flush_event(ec); + + /* + * When ec_freeze_events is true, we need to flush events in + * the proper position before entering the noirq stage. + */ + __acpi_ec_flush_work(); } void acpi_ec_flush_work(void) { - if (first_ec) - __acpi_ec_flush_event(first_ec); + /* Without ec_query_wq there is nothing to flush. */ + if (!ec_query_wq) + return; - flush_scheduled_work(); + __acpi_ec_flush_work(); } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index a2e844a8e9ed..41168c027a5a 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -374,19 +374,21 @@ void *__ref acpi_os_map_memory(acpi_physical_address phys, acpi_size size) } EXPORT_SYMBOL_GPL(acpi_os_map_memory); -static void acpi_os_drop_map_ref(struct acpi_ioremap *map) +/* Must be called with mutex_lock(&acpi_ioremap_lock) */ +static unsigned long acpi_os_drop_map_ref(struct acpi_ioremap *map) { - if (!--map->refcount) + unsigned long refcount = --map->refcount; + + if (!refcount) list_del_rcu(&map->list); + return refcount; } static void acpi_os_map_cleanup(struct acpi_ioremap *map) { - if (!map->refcount) { - synchronize_rcu_expedited(); - acpi_unmap(map->phys, map->virt); - kfree(map); - } + synchronize_rcu_expedited(); + acpi_unmap(map->phys, map->virt); + kfree(map); } /** @@ -406,6 +408,7 @@ static void acpi_os_map_cleanup(struct acpi_ioremap *map) void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) { struct acpi_ioremap *map; + unsigned long refcount; if (!acpi_permanent_mmap) { __acpi_unmap_table(virt, size); @@ -419,10 +422,11 @@ void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) WARN(true, PREFIX "%s: bad address %p\n", __func__, virt); return; } - acpi_os_drop_map_ref(map); + refcount = acpi_os_drop_map_ref(map); mutex_unlock(&acpi_ioremap_lock); - acpi_os_map_cleanup(map); + if (!refcount) + acpi_os_map_cleanup(map); } EXPORT_SYMBOL_GPL(acpi_os_unmap_iomem); @@ -457,6 +461,7 @@ void acpi_os_unmap_generic_address(struct acpi_generic_address *gas) { u64 addr; struct acpi_ioremap *map; + unsigned long refcount; if (gas->space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY) return; @@ -472,10 +477,11 @@ void acpi_os_unmap_generic_address(struct acpi_generic_address *gas) mutex_unlock(&acpi_ioremap_lock); return; } - acpi_os_drop_map_ref(map); + refcount = acpi_os_drop_map_ref(map); mutex_unlock(&acpi_ioremap_lock); - acpi_os_map_cleanup(map); + if (!refcount) + acpi_os_map_cleanup(map); } EXPORT_SYMBOL(acpi_os_unmap_generic_address); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 2af937a8b1c5..6747a279621b 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -977,6 +977,16 @@ static int acpi_s2idle_prepare_late(void) return 0; } +static void acpi_s2idle_sync(void) +{ + /* + * The EC driver uses the system workqueue and an additional special + * one, so those need to be flushed too. + */ + acpi_ec_flush_work(); + acpi_os_wait_events_complete(); /* synchronize Notify handling */ +} + static void acpi_s2idle_wake(void) { /* @@ -1001,13 +1011,8 @@ static void acpi_s2idle_wake(void) * should be missed by canceling the wakeup here. */ pm_system_cancel_wakeup(); - /* - * The EC driver uses the system workqueue and an additional - * special one, so those need to be flushed too. - */ - acpi_os_wait_events_complete(); /* synchronize EC GPE processing */ - acpi_ec_flush_work(); - acpi_os_wait_events_complete(); /* synchronize Notify handling */ + + acpi_s2idle_sync(); rearm_wake_irq(acpi_sci_irq); } @@ -1024,6 +1029,13 @@ static void acpi_s2idle_restore_early(void) static void acpi_s2idle_restore(void) { + /* + * Drain pending events before restoring the working-state configuration + * of GPEs. + */ + acpi_os_wait_events_complete(); /* synchronize GPE processing */ + acpi_s2idle_sync(); + s2idle_wakeup = false; acpi_enable_all_runtime_gpes(); diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 75948a3f1a20..c60d2c6d31d6 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -819,14 +819,14 @@ end: * interface: * echo unmask > /sys/firmware/acpi/interrupts/gpe00 */ -#define ACPI_MASKABLE_GPE_MAX 0xFF +#define ACPI_MASKABLE_GPE_MAX 0x100 static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata; static int __init acpi_gpe_set_masked_gpes(char *val) { u8 gpe; - if (kstrtou8(val, 0, &gpe) || gpe > ACPI_MASKABLE_GPE_MAX) + if (kstrtou8(val, 0, &gpe)) return -EINVAL; set_bit(gpe, acpi_masked_gpes_map); @@ -838,7 +838,7 @@ void __init acpi_gpe_apply_masked_gpes(void) { acpi_handle handle; acpi_status status; - u8 gpe; + u16 gpe; for_each_set_bit(gpe, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) { status = acpi_get_gpe_device(gpe, &handle); diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 28b92e3cc570..c3b3b5c0b0da 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -148,6 +148,10 @@ config DEBUG_TEST_DRIVER_REMOVE unusable. You should say N here unless you are explicitly looking to test this functionality. +config PM_QOS_KUNIT_TEST + bool "KUnit Test for PM QoS features" + depends on KUNIT + config HMEM_REPORTING bool default n diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile index ec5bb190b9d0..8fdd0073eeeb 100644 --- a/drivers/base/power/Makefile +++ b/drivers/base/power/Makefile @@ -4,5 +4,6 @@ obj-$(CONFIG_PM_SLEEP) += main.o wakeup.o wakeup_stats.o obj-$(CONFIG_PM_TRACE_RTC) += trace.o obj-$(CONFIG_PM_GENERIC_DOMAINS) += domain.o domain_governor.o obj-$(CONFIG_HAVE_CLK) += clock_ops.o +obj-$(CONFIG_PM_QOS_KUNIT_TEST) += qos-test.o ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG diff --git a/drivers/base/power/qos-test.c b/drivers/base/power/qos-test.c new file mode 100644 index 000000000000..3115db08d56b --- /dev/null +++ b/drivers/base/power/qos-test.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 NXP + */ +#include <kunit/test.h> +#include <linux/pm_qos.h> + +/* Basic test for aggregating two "min" requests */ +static void freq_qos_test_min(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req1, req2; + int ret; + + freq_constraints_init(&qos); + memset(&req1, 0, sizeof(req1)); + memset(&req2, 0, sizeof(req2)); + + ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MIN, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MIN, 2000); + KUNIT_EXPECT_EQ(test, ret, 1); + + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000); + + ret = freq_qos_remove_request(&req2); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000); + + ret = freq_qos_remove_request(&req1); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); +} + +/* Test that requests for MAX_DEFAULT_VALUE have no effect */ +static void freq_qos_test_maxdef(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req1, req2; + int ret; + + freq_constraints_init(&qos); + memset(&req1, 0, sizeof(req1)); + memset(&req2, 0, sizeof(req2)); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), + FREQ_QOS_MAX_DEFAULT_VALUE); + + ret = freq_qos_add_request(&qos, &req1, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + KUNIT_EXPECT_EQ(test, ret, 0); + ret = freq_qos_add_request(&qos, &req2, FREQ_QOS_MAX, + FREQ_QOS_MAX_DEFAULT_VALUE); + KUNIT_EXPECT_EQ(test, ret, 0); + + /* Add max 1000 */ + ret = freq_qos_update_request(&req1, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000); + + /* Add max 2000, no impact */ + ret = freq_qos_update_request(&req2, 2000); + KUNIT_EXPECT_EQ(test, ret, 0); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 1000); + + /* Remove max 1000, new max 2000 */ + ret = freq_qos_remove_request(&req1); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MAX), 2000); +} + +/* + * Test that a freq_qos_request can be added again after removal + * + * This issue was solved by commit 05ff1ba412fd ("PM: QoS: Invalidate frequency + * QoS requests after removal") + */ +static void freq_qos_test_readd(struct kunit *test) +{ + struct freq_constraints qos; + struct freq_qos_request req; + int ret; + + freq_constraints_init(&qos); + memset(&req, 0, sizeof(req)); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); + + /* Add */ + ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 1000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 1000); + + /* Remove */ + ret = freq_qos_remove_request(&req); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), + FREQ_QOS_MIN_DEFAULT_VALUE); + + /* Add again */ + ret = freq_qos_add_request(&qos, &req, FREQ_QOS_MIN, 2000); + KUNIT_EXPECT_EQ(test, ret, 1); + KUNIT_EXPECT_EQ(test, freq_qos_read_value(&qos, FREQ_QOS_MIN), 2000); +} + +static struct kunit_case pm_qos_test_cases[] = { + KUNIT_CASE(freq_qos_test_min), + KUNIT_CASE(freq_qos_test_maxdef), + KUNIT_CASE(freq_qos_test_readd), + {}, +}; + +static struct kunit_suite pm_qos_test_module = { + .name = "qos-kunit-test", + .test_cases = pm_qos_test_cases, +}; +kunit_test_suite(pm_qos_test_module); diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 350dcafd751f..8e93167f1783 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -115,10 +115,20 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) spin_lock_irqsave(&dev->power.lock, flags); - if (type == DEV_PM_QOS_RESUME_LATENCY) { + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); - } else { + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); + break; + default: WARN_ON(1); ret = 0; } @@ -159,6 +169,10 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_apply(&req->data.freq, action, value); + break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -209,6 +223,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; + freq_constraints_init(&qos->freq); + INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -269,6 +285,20 @@ void dev_pm_qos_constraints_destroy(struct device *dev) memset(req, 0, sizeof(*req)); } + c = &qos->freq.min_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + + c = &qos->freq.max_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -314,11 +344,22 @@ static int __dev_pm_qos_add_request(struct device *dev, ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); - if (!ret) { - req->dev = dev; - req->type = type; + if (ret) + return ret; + + req->dev = dev; + req->type = type; + if (req->type == DEV_PM_QOS_MIN_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MIN, value); + else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MAX, value); + else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); - } + return ret; } @@ -382,6 +423,10 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + curr_value = req->data.freq.pnode.prio; + break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; @@ -507,6 +552,14 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; @@ -546,6 +599,14 @@ int dev_pm_qos_remove_notifier(struct device *dev, ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; diff --git a/drivers/cpufreq/Kconfig.powerpc b/drivers/cpufreq/Kconfig.powerpc index 35b4f700f054..58151ca56695 100644 --- a/drivers/cpufreq/Kconfig.powerpc +++ b/drivers/cpufreq/Kconfig.powerpc @@ -48,9 +48,9 @@ config PPC_PASEMI_CPUFREQ PWRficient processors. config POWERNV_CPUFREQ - tristate "CPU frequency scaling for IBM POWERNV platform" - depends on PPC_POWERNV - default y - help + tristate "CPU frequency scaling for IBM POWERNV platform" + depends on PPC_POWERNV + default y + help This adds support for CPU frequency switching on IBM POWERNV platform diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index dfa6457deaf6..a6528388952e 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -4,17 +4,17 @@ # config X86_INTEL_PSTATE - bool "Intel P state control" - depends on X86 - select ACPI_PROCESSOR if ACPI - select ACPI_CPPC_LIB if X86_64 && ACPI && SCHED_MC_PRIO - help - This driver provides a P state for Intel core processors. + bool "Intel P state control" + depends on X86 + select ACPI_PROCESSOR if ACPI + select ACPI_CPPC_LIB if X86_64 && ACPI && SCHED_MC_PRIO + help + This driver provides a P state for Intel core processors. The driver implements an internal governor and will become - the scaling driver and governor for Sandy bridge processors. + the scaling driver and governor for Sandy bridge processors. When this driver is enabled it will become the preferred - scaling driver for Sandy bridge processors. + scaling driver for Sandy bridge processors. If in doubt, say N. diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index 88727b7c0d59..c0aeedd66f02 100644 --- a/drivers/cpuidle/Kconfig +++ b/drivers/cpuidle/Kconfig @@ -16,7 +16,7 @@ config CPU_IDLE if CPU_IDLE config CPU_IDLE_MULTIPLE_DRIVERS - bool + bool config CPU_IDLE_GOV_LADDER bool "Ladder governor (for periodic timer tick)" @@ -63,13 +63,13 @@ source "drivers/cpuidle/Kconfig.powerpc" endmenu config HALTPOLL_CPUIDLE - tristate "Halt poll cpuidle driver" - depends on X86 && KVM_GUEST - default y - help - This option enables halt poll cpuidle driver, which allows to poll - before halting in the guest (more efficient than polling in the - host via halt_poll_ns for some scenarios). + tristate "Halt poll cpuidle driver" + depends on X86 && KVM_GUEST + default y + help + This option enables halt poll cpuidle driver, which allows to poll + before halting in the guest (more efficient than polling in the + host via halt_poll_ns for some scenarios). endif diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm index d8530475493c..a224d33dda7f 100644 --- a/drivers/cpuidle/Kconfig.arm +++ b/drivers/cpuidle/Kconfig.arm @@ -3,15 +3,15 @@ # ARM CPU Idle drivers # config ARM_CPUIDLE - bool "Generic ARM/ARM64 CPU idle Driver" - select DT_IDLE_STATES + bool "Generic ARM/ARM64 CPU idle Driver" + select DT_IDLE_STATES select CPU_IDLE_MULTIPLE_DRIVERS - help - Select this to enable generic cpuidle driver for ARM. - It provides a generic idle driver whose idle states are configured - at run-time through DT nodes. The CPUidle suspend backend is - initialized by calling the CPU operations init idle hook - provided by architecture code. + help + Select this to enable generic cpuidle driver for ARM. + It provides a generic idle driver whose idle states are configured + at run-time through DT nodes. The CPUidle suspend backend is + initialized by calling the CPU operations init idle hook + provided by architecture code. config ARM_PSCI_CPUIDLE bool "PSCI CPU idle Driver" @@ -65,21 +65,21 @@ config ARM_U8500_CPUIDLE bool "Cpu Idle Driver for the ST-E u8500 processors" depends on ARCH_U8500 && !ARM64 help - Select this to enable cpuidle for ST-E u8500 processors + Select this to enable cpuidle for ST-E u8500 processors. config ARM_AT91_CPUIDLE bool "Cpu Idle Driver for the AT91 processors" default y depends on ARCH_AT91 && !ARM64 help - Select this to enable cpuidle for AT91 processors + Select this to enable cpuidle for AT91 processors. config ARM_EXYNOS_CPUIDLE bool "Cpu Idle Driver for the Exynos processors" depends on ARCH_EXYNOS && !ARM64 select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP help - Select this to enable cpuidle for Exynos processors + Select this to enable cpuidle for Exynos processors. config ARM_MVEBU_V7_CPUIDLE bool "CPU Idle Driver for mvebu v7 family processors" diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 569dbac443bd..0005be5ea2b4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -572,7 +572,7 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) return -EINVAL; for (i = 0; i < drv->state_count; i++) - if (drv->states[i].disabled) + if (drv->states[i].flags & CPUIDLE_FLAG_UNUSABLE) dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; per_cpu(cpuidle_devices, dev->cpu) = dev; diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 9f1ace9c53da..f7e83613ae94 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -53,7 +53,6 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv) state->target_residency_ns = 0; state->power_usage = -1; state->enter = poll_idle; - state->disabled = false; state->flags = CPUIDLE_FLAG_POLLING; } EXPORT_SYMBOL_GPL(cpuidle_poll_state_init); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index f840e61e5a27..425149e8bab0 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -921,7 +921,9 @@ int devfreq_suspend_device(struct devfreq *devfreq) } if (devfreq->suspend_freq) { + mutex_lock(&devfreq->lock); ret = devfreq_set_target(devfreq, devfreq->suspend_freq, 0); + mutex_unlock(&devfreq->lock); if (ret) return ret; } @@ -949,7 +951,9 @@ int devfreq_resume_device(struct devfreq *devfreq) return 0; if (devfreq->resume_freq) { + mutex_lock(&devfreq->lock); ret = devfreq_set_target(devfreq, devfreq->resume_freq, 0); + mutex_unlock(&devfreq->lock); if (ret) return ret; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 347b08b56042..75fd2a7b0842 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1291,8 +1291,8 @@ static void sklh_idle_state_table_update(void) return; } - skl_cstates[5].disabled = 1; /* C8-SKL */ - skl_cstates[6].disabled = 1; /* C9-SKL */ + skl_cstates[5].flags |= CPUIDLE_FLAG_UNUSABLE; /* C8-SKL */ + skl_cstates[6].flags |= CPUIDLE_FLAG_UNUSABLE; /* C9-SKL */ } /* * intel_idle_state_table_update() @@ -1355,7 +1355,7 @@ static void __init intel_idle_cpuidle_driver_init(void) continue; /* if state marked as disabled, skip it */ - if (cpuidle_state_table[cstate].disabled != 0) { + if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_UNUSABLE) { pr_debug("state %s is disabled\n", cpuidle_state_table[cstate].name); continue; diff --git a/drivers/power/avs/Kconfig b/drivers/power/avs/Kconfig index b5a217b828dc..089b6244b716 100644 --- a/drivers/power/avs/Kconfig +++ b/drivers/power/avs/Kconfig @@ -13,9 +13,9 @@ menuconfig POWER_AVS Say Y here to enable Adaptive Voltage Scaling class support. config ROCKCHIP_IODOMAIN - tristate "Rockchip IO domain support" - depends on POWER_AVS && ARCH_ROCKCHIP && OF - help - Say y here to enable support io domains on Rockchip SoCs. It is - necessary for the io domain setting of the SoC to match the - voltage supplied by the regulators. + tristate "Rockchip IO domain support" + depends on POWER_AVS && ARCH_ROCKCHIP && OF + help + Say y here to enable support io domains on Rockchip SoCs. It is + necessary for the io domain setting of the SoC to match the + voltage supplied by the regulators. diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 2dbe46b7c213..1dabe36bd011 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -54,7 +54,6 @@ struct cpuidle_state { unsigned int exit_latency; /* in US */ int power_usage; /* in mW */ unsigned int target_residency; /* in US */ - bool disabled; /* disabled on all CPUs */ int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, @@ -77,6 +76,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ #define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index ebf5ef17cc2a..19eafca5680e 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,6 +34,8 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 +#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 +#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE FREQ_QOS_MAX_DEFAULT_VALUE #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -49,21 +51,6 @@ struct pm_qos_flags_request { s32 flags; /* Do not change to 64 bit */ }; -enum dev_pm_qos_req_type { - DEV_PM_QOS_RESUME_LATENCY = 1, - DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_FLAGS, -}; - -struct dev_pm_qos_request { - enum dev_pm_qos_req_type type; - union { - struct plist_node pnode; - struct pm_qos_flags_request flr; - } data; - struct device *dev; -}; - enum pm_qos_type { PM_QOS_UNITIALIZED, PM_QOS_MAX, /* return the largest value */ @@ -90,9 +77,51 @@ struct pm_qos_flags { s32 effective_flags; /* Do not change to 64 bit */ }; + +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + + +enum dev_pm_qos_req_type { + DEV_PM_QOS_RESUME_LATENCY = 1, + DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_MIN_FREQUENCY, + DEV_PM_QOS_MAX_FREQUENCY, + DEV_PM_QOS_FLAGS, +}; + +struct dev_pm_qos_request { + enum dev_pm_qos_req_type type; + union { + struct plist_node pnode; + struct pm_qos_flags_request flr; + struct freq_qos_request freq; + } data; + struct device *dev; +}; + struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; + struct freq_constraints freq; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; @@ -191,6 +220,10 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + case DEV_PM_QOS_MIN_FREQUENCY: + return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; + case DEV_PM_QOS_MAX_FREQUENCY: + return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -255,27 +288,6 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif -#define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) - -enum freq_qos_req_type { - FREQ_QOS_MIN = 1, - FREQ_QOS_MAX, -}; - -struct freq_constraints { - struct pm_qos_constraints min_freq; - struct blocking_notifier_head min_freq_notifiers; - struct pm_qos_constraints max_freq; - struct blocking_notifier_head max_freq_notifiers; -}; - -struct freq_qos_request { - enum freq_qos_req_type type; - struct plist_node pnode; - struct freq_constraints *qos; -}; - static inline int freq_qos_request_active(struct freq_qos_request *req) { return !IS_ERR_OR_NULL(req->qos); @@ -291,6 +303,8 @@ int freq_qos_add_request(struct freq_constraints *qos, enum freq_qos_req_type type, s32 value); int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); int freq_qos_remove_request(struct freq_qos_request *req); +int freq_qos_apply(struct freq_qos_request *req, + enum pm_qos_req_action action, s32 value); int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 7089760d4c7a..472b33d23a10 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -757,6 +757,7 @@ static inline void ftrace_test_probe_##call(void) \ #undef __get_str #undef __get_bitmask #undef __print_array +#undef __print_hex_dump #undef TP_printk #define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e6f17c8e2dba..f0a16b4adbbd 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1348,6 +1348,7 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) /* Available with KVM_CAP_PMU_EVENT_FILTER */ #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) +#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a45cba7df0ae..83edf8698118 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -714,8 +714,10 @@ s32 freq_qos_read_value(struct freq_constraints *qos, * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. + * + * This is only meant to be called from inside pm_qos, not drivers. */ -static int freq_qos_apply(struct freq_qos_request *req, +int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cdf5afa87f65..25a0fcfa7a5d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -671,6 +671,15 @@ config HIST_TRIGGERS See Documentation/trace/histogram.rst. If in doubt, say N. +config TRACE_EVENT_INJECT + bool "Trace event injection" + depends on TRACING + help + Allow user-space to inject a specific trace event into the ring + buffer. This is mainly used for testing purpose. + + If unsure, say N. + config MMIOTRACE_TEST tristate "Test module for mmiotrace" depends on MMIOTRACE && m diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c2b2148bb1d2..0e63db62225f 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 66358d66c933..4bf050fcfe3b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -11,6 +11,7 @@ #include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/irq_work.h> +#include <linux/security.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kthread.h> /* for self test */ @@ -5068,6 +5069,11 @@ static __init int test_ringbuffer(void) int cpu; int ret = 0; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Lockdown is enabled, skipping ring buffer tests\n"); + return 0; + } + pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 02a23a6e5e00..23459d53d576 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1888,6 +1888,12 @@ int __init register_tracer(struct tracer *type) return -1; } + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } + mutex_lock(&trace_types_lock); tracing_selftest_running = true; @@ -8789,6 +8795,11 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return ERR_PTR(-EPERM); + } + /* The top level trace array uses NULL as parent */ if (tr->dir) return NULL; @@ -9231,6 +9242,12 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* * Make sure we don't accidently add more trace options * than we have bits for. diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ca7fccafbcbb..63bf60f79398 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1601,6 +1601,7 @@ extern struct list_head ftrace_events; extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; +extern const struct file_operations event_inject_fops; #ifdef CONFIG_HIST_TRIGGERS extern int register_trigger_hist_cmd(void); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6b3a69e9aa6a..c6de3cebc127 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2044,6 +2044,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); +#ifdef CONFIG_TRACE_EVENT_INJECT + if (call->event.type && call->class->reg) + trace_create_file("inject", 0200, file->dir, file, + &event_inject_fops); +#endif + return 0; } diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c new file mode 100644 index 000000000000..d43710718ee5 --- /dev/null +++ b/kernel/trace/trace_events_inject.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace_events_inject - trace event injection + * + * Copyright (C) 2019 Cong Wang <cwang@twitter.com> + */ + +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/rculist.h> + +#include "trace.h" + +static int +trace_inject_entry(struct trace_event_file *file, void *rec, int len) +{ + struct trace_event_buffer fbuffer; + struct ring_buffer *buffer; + int written = 0; + void *entry; + + rcu_read_lock_sched(); + buffer = file->tr->trace_buffer.buffer; + entry = trace_event_buffer_reserve(&fbuffer, file, len); + if (entry) { + memcpy(entry, rec, len); + written = len; + trace_event_buffer_commit(&fbuffer); + } + rcu_read_unlock_sched(); + + return written; +} + +static int +parse_field(char *str, struct trace_event_call *call, + struct ftrace_event_field **pf, u64 *pv) +{ + struct ftrace_event_field *field; + char *field_name; + int s, i = 0; + int len; + u64 val; + + if (!str[i]) + return 0; + /* First find the field to associate to */ + while (isspace(str[i])) + i++; + s = i; + while (isalnum(str[i]) || str[i] == '_') + i++; + len = i - s; + if (!len) + return -EINVAL; + + field_name = kmemdup_nul(str + s, len, GFP_KERNEL); + if (!field_name) + return -ENOMEM; + field = trace_find_event_field(call, field_name); + kfree(field_name); + if (!field) + return -ENOENT; + + *pf = field; + while (isspace(str[i])) + i++; + if (str[i] != '=') + return -EINVAL; + i++; + while (isspace(str[i])) + i++; + s = i; + if (isdigit(str[i]) || str[i] == '-') { + char *num, c; + int ret; + + /* Make sure the field is not a string */ + if (is_string_field(field)) + return -EINVAL; + + if (str[i] == '-') + i++; + + /* We allow 0xDEADBEEF */ + while (isalnum(str[i])) + i++; + num = str + s; + c = str[i]; + if (c != '\0' && !isspace(c)) + return -EINVAL; + str[i] = '\0'; + /* Make sure it is a value */ + if (field->is_signed) + ret = kstrtoll(num, 0, &val); + else + ret = kstrtoull(num, 0, &val); + str[i] = c; + if (ret) + return ret; + + *pv = val; + return i; + } else if (str[i] == '\'' || str[i] == '"') { + char q = str[i]; + + /* Make sure the field is OK for strings */ + if (!is_string_field(field)) + return -EINVAL; + + for (i++; str[i]; i++) { + if (str[i] == '\\' && str[i + 1]) { + i++; + continue; + } + if (str[i] == q) + break; + } + if (!str[i]) + return -EINVAL; + + /* Skip quotes */ + s++; + len = i - s; + if (len >= MAX_FILTER_STR_VAL) + return -EINVAL; + + *pv = (unsigned long)(str + s); + str[i] = 0; + /* go past the last quote */ + i++; + return i; + } + + return -EINVAL; +} + +static int trace_get_entry_size(struct trace_event_call *call) +{ + struct ftrace_event_field *field; + struct list_head *head; + int size = 0; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (field->size + field->offset > size) + size = field->size + field->offset; + } + + return size; +} + +static void *trace_alloc_entry(struct trace_event_call *call, int *size) +{ + int entry_size = trace_get_entry_size(call); + struct ftrace_event_field *field; + struct list_head *head; + void *entry = NULL; + + /* We need an extra '\0' at the end. */ + entry = kzalloc(entry_size + 1, GFP_KERNEL); + if (!entry) + return NULL; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (!is_string_field(field)) + continue; + if (field->filter_type == FILTER_STATIC_STRING) + continue; + if (field->filter_type == FILTER_DYN_STRING) { + u32 *str_item; + int str_loc = entry_size & 0xffff; + + str_item = (u32 *)(entry + field->offset); + *str_item = str_loc; /* string length is 0. */ + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = ""; + } + } + + *size = entry_size + 1; + return entry; +} + +#define INJECT_STRING "STATIC STRING CAN NOT BE INJECTED" + +/* Caller is responsible to free the *pentry. */ +static int parse_entry(char *str, struct trace_event_call *call, void **pentry) +{ + struct ftrace_event_field *field; + unsigned long irq_flags; + void *entry = NULL; + int entry_size; + u64 val; + int len; + + entry = trace_alloc_entry(call, &entry_size); + *pentry = entry; + if (!entry) + return -ENOMEM; + + local_save_flags(irq_flags); + tracing_generic_entry_update(entry, call->event.type, irq_flags, + preempt_count()); + + while ((len = parse_field(str, call, &field, &val)) > 0) { + if (is_function_field(field)) + return -EINVAL; + + if (is_string_field(field)) { + char *addr = (char *)(unsigned long) val; + + if (field->filter_type == FILTER_STATIC_STRING) { + strlcpy(entry + field->offset, addr, field->size); + } else if (field->filter_type == FILTER_DYN_STRING) { + int str_len = strlen(addr) + 1; + int str_loc = entry_size & 0xffff; + u32 *str_item; + + entry_size += str_len; + *pentry = krealloc(entry, entry_size, GFP_KERNEL); + if (!*pentry) { + kfree(entry); + return -ENOMEM; + } + entry = *pentry; + + strlcpy(entry + (entry_size - str_len), addr, str_len); + str_item = (u32 *)(entry + field->offset); + *str_item = (str_len << 16) | str_loc; + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = INJECT_STRING; + } + } else { + switch (field->size) { + case 1: { + u8 tmp = (u8) val; + + memcpy(entry + field->offset, &tmp, 1); + break; + } + case 2: { + u16 tmp = (u16) val; + + memcpy(entry + field->offset, &tmp, 2); + break; + } + case 4: { + u32 tmp = (u32) val; + + memcpy(entry + field->offset, &tmp, 4); + break; + } + case 8: + memcpy(entry + field->offset, &val, 8); + break; + default: + return -EINVAL; + } + } + + str += len; + } + + if (len < 0) + return len; + + return entry_size; +} + +static ssize_t +event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_event_call *call; + struct trace_event_file *file; + int err = -ENODEV, size; + void *entry = NULL; + char *buf; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = memdup_user_nul(ubuf, cnt); + if (IS_ERR(buf)) + return PTR_ERR(buf); + strim(buf); + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) { + call = file->event_call; + size = parse_entry(buf, call, &entry); + if (size < 0) + err = size; + else + err = trace_inject_entry(file, entry, size); + } + mutex_unlock(&event_mutex); + + kfree(entry); + kfree(buf); + + if (err < 0) + return err; + + *ppos += err; + return cnt; +} + +static ssize_t +event_inject_read(struct file *file, char __user *buf, size_t size, + loff_t *ppos) +{ + return -EPERM; +} + +const struct file_operations event_inject_fops = { + .open = tracing_open_generic, + .read = event_inject_read, + .write = event_inject_write, +}; @@ -2478,6 +2478,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } +EXPORT_SYMBOL_GPL(ksm_madvise); int __ksm_enter(struct mm_struct *mm) { |