diff options
Diffstat (limited to 'arch')
168 files changed, 1845 insertions, 917 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6d5eb8267e42..b4441b0764d7 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -9,6 +9,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SG_CHAIN @@ -28,8 +29,12 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_DEBUG_STACKOVERFLOW select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_GENERIC_DMA_COHERENT select HAVE_IOREMAP_PROT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_MEMBLOCK @@ -44,11 +49,6 @@ config ARC select OF_EARLY_FLATTREE select OF_RESERVED_MEM select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_GENERIC_DMA_COHERENT - select HAVE_KERNEL_GZIP - select HAVE_KERNEL_LZMA - select ARCH_HAS_PTE_SPECIAL config ARCH_HAS_CACHE_LINE_SIZE def_bool y diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb026196aaab..99cce77ab98f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -43,10 +43,7 @@ ifdef CONFIG_ARC_CURR_IN_REG LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -upto_gcc44 := $(call cc-ifversion, -le, 0404, y) -atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) - -cflags-$(atleast_gcc44) += -fsection-anchors +cflags-y += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape @@ -82,11 +79,6 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) -# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". Default arc-elf32-ld is OK -ldflags-$(upto_gcc44) += -marclinux - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index dc91c663bcc0..d75d65ddf8e3 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -94,6 +94,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * The DW APB ICTL intc on MB is connected to CPU intc via a * DT "invisible" DW APB GPIO block, configured to simply pass thru * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 69ff4895f2ba..a05bb737ea63 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -101,6 +101,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * This INTC is actually connected to DW APB GPIO * which acts as a wire between MB INTC and CPU INTC. * GPIO INTC is configured in platform init code diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 47b74fbc403c..37bafd44e36d 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -9,6 +9,10 @@ */ / { + aliases { + ethernet = &gmac; + }; + axs10x_mb { compatible = "simple-bus"; #address-cells = <1>; @@ -68,7 +72,7 @@ }; }; - ethernet@0x18000 { + gmac: ethernet@0x18000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = < 0x18000 0x2000 >; @@ -81,6 +85,7 @@ max-speed = <100>; resets = <&creg_rst 5>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 006aa3de5348..ef149f59929a 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -25,6 +25,10 @@ bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; + aliases { + ethernet = &gmac; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -163,7 +167,7 @@ #clock-cells = <0>; }; - ethernet@8000 { + gmac: ethernet@8000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; @@ -176,6 +180,8 @@ phy-handle = <&phy0>; resets = <&cgu_rst HSDK_ETH_RESET>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ + dma-coherent; mdio { #address-cells = <1>; @@ -194,12 +200,14 @@ compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; + dma-coherent; }; ehci@40000 { compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; + dma-coherent; }; mmc@a000 { @@ -212,6 +220,7 @@ clock-names = "biu", "ciu"; interrupts = <12>; bus-width = <4>; + dma-coherent; }; }; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index a635ea972304..41bc08be6a3b 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -63,7 +61,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index aa507e423075..1e1c4a8011b5 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -64,7 +62,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index eba07f468654..6b0c0cfd5c30 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -65,7 +63,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 098b19fbaa51..240dd2cd5148 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -57,7 +56,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 0104c404d897..14ae7e5acc7c 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -60,7 +59,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 6491be0ddbc9..1dec2b4bc5e6 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 7c9c706ae7f6..31ba224bbfb4 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -59,7 +59,6 @@ CONFIG_NETCONSOLE=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 99e05cf63fca..8e0b8b134cd9 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -44,7 +43,6 @@ CONFIG_LXT_PHY=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index 0dc4f9b737e7..739b90e5e893 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -45,7 +44,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index be3c30a15e54..b5895bdf3a93 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 3a74b9b21772..f14eeff7d308 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -48,7 +47,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index ea2834b4dc1d..025298a48305 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -47,7 +46,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 80a5a1b4924b..df7b77b13b82 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -58,7 +57,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 2cc87f909747..a7f65313f84a 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -57,7 +57,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index f629493929ea..db47c3541f15 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -53,7 +52,6 @@ CONFIG_NATIONAL_PHY=y CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 21f0ca26a05d..a8ac5e917d9a 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4e0072730241..158af079838d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -84,7 +84,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: llock %[orig], [%[ctr]] \n" \ " " #asm_op " %[val], %[orig], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ + " bnz 1b \n" \ : [val] "=&r" (val), \ [orig] "=&r" (orig) \ : [ctr] "r" (&v->counter), \ diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h new file mode 100644 index 000000000000..c946c0a83e76 --- /dev/null +++ b/arch/arc/include/asm/dma-mapping.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// (C) 2018 Synopsys, Inc. (www.synopsys.com) + +#ifndef ASM_ARC_DMA_MAPPING_H +#define ASM_ARC_DMA_MAPPING_H + +#include <asm-generic/dma-mapping.h> + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent); +#define arch_setup_dma_ops arch_setup_dma_ops + +#endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 783b20354f8b..e8d9fb452346 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -83,9 +83,6 @@ done: static void show_faulting_vma(unsigned long address, char *buf) { struct vm_area_struct *vma; - struct inode *inode; - unsigned long ino = 0; - dev_t dev = 0; char *nm = buf; struct mm_struct *active_mm = current->active_mm; @@ -99,12 +96,10 @@ static void show_faulting_vma(unsigned long address, char *buf) * if the container VMA is not found */ if (vma && (vma->vm_start <= address)) { - struct file *file = vma->vm_file; - if (file) { - nm = file_path(file, buf, PAGE_SIZE - 1); - inode = file_inode(vma->vm_file); - dev = inode->i_sb->s_dev; - ino = inode->i_ino; + if (vma->vm_file) { + nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1); + if (IS_ERR(nm)) + nm = "?"; } pr_info(" @off 0x%lx in [%s]\n" " VMA: 0x%08lx to 0x%08lx\n", diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 25c631942500..f2701c13a66b 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n", perip_base, - IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency ")); + IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) ")); return buf; } @@ -897,15 +897,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz) } /* - * DMA ops for systems with IOC - * IOC hardware snoops all DMA traffic keeping the caches consistent with - * memory - eliding need for any explicit cache maintenance of DMA buffers - */ -static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {} - -/* * Exported DMA API */ void dma_cache_wback_inv(phys_addr_t start, unsigned long sz) @@ -1153,6 +1144,19 @@ noinline void __init arc_ioc_setup(void) { unsigned int ioc_base, mem_sz; + /* + * As for today we don't support both IOC and ZONE_HIGHMEM enabled + * simultaneously. This happens because as of today IOC aperture covers + * only ZONE_NORMAL (low mem) and any dma transactions outside this + * region won't be HW coherent. + * If we want to use both IOC and ZONE_HIGHMEM we can use + * bounce_buffer to handle dma transactions to HIGHMEM. + * Also it is possible to modify dma_direct cache ops or increase IOC + * aperture size if we are planning to use HIGHMEM without PAE. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + panic("IOC and HIGHMEM can't be used simultaneously"); + /* Flush + invalidate + disable L1 dcache */ __dc_disable(); @@ -1264,11 +1268,7 @@ void __init arc_cache_init_master(void) if (is_isa_arcv2() && ioc_enable) arc_ioc_setup(); - if (is_isa_arcv2() && ioc_enable) { - __dma_cache_wback_inv = __dma_cache_wback_inv_ioc; - __dma_cache_inv = __dma_cache_inv_ioc; - __dma_cache_wback = __dma_cache_wback_ioc; - } else if (is_isa_arcv2() && l2_line_sz && slc_enable) { + if (is_isa_arcv2() && l2_line_sz && slc_enable) { __dma_cache_wback_inv = __dma_cache_wback_inv_slc; __dma_cache_inv = __dma_cache_inv_slc; __dma_cache_wback = __dma_cache_wback_slc; @@ -1277,6 +1277,12 @@ void __init arc_cache_init_master(void) __dma_cache_inv = __dma_cache_inv_l1; __dma_cache_wback = __dma_cache_wback_l1; } + /* + * In case of IOC (say IOC+SLC case), pointers above could still be set + * but end up not being relevant as the first function in chain is not + * called at all for @dma_direct_ops + * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() + */ } void __ref arc_cache_init(void) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index ec47e6079f5d..c75d5c3470e3 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -6,20 +6,17 @@ * published by the Free Software Foundation. */ -/* - * DMA Coherent API Notes - * - * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessing it using a kernel virtual address, with - * Cache bit off in the TLB entry. - * - * The default DMA address == Phy address which is 0x8000_0000 based. - */ - #include <linux/dma-noncoherent.h> #include <asm/cache.h> #include <asm/cacheflush.h> +/* + * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c) + * - hardware IOC not available (or "dma-coherent" not set for device in DT) + * - But still handle both coherent and non-coherent requests from caller + * + * For DMA coherent hardware (IOC) generic code suffices + */ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { @@ -27,42 +24,29 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; phys_addr_t paddr; void *kvaddr; - int need_coh = 1, need_kvaddr = 0; - - page = alloc_pages(gfp, order); - if (!page) - return NULL; + bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT); /* - * IOC relies on all data (even coherent DMA data) being in cache - * Thus allocate normal cached memory - * - * The gains with IOC are two pronged: - * -For streaming data, elides need for cache maintenance, saving - * cycles in flush code, and bus bandwidth as all the lines of a - * buffer need to be flushed out to memory - * -For coherent data, Read/Write to buffers terminate early in cache - * (vs. always going to memory - thus are faster) + * __GFP_HIGHMEM flag is cleared by upper layer functions + * (in include/linux/dma-mapping.h) so we should never get a + * __GFP_HIGHMEM here. */ - if ((is_isa_arcv2() && ioc_enable) || - (attrs & DMA_ATTR_NON_CONSISTENT)) - need_coh = 0; + BUG_ON(gfp & __GFP_HIGHMEM); - /* - * - A coherent buffer needs MMU mapping to enforce non-cachability - * - A highmem page needs a virtual handle (hence MMU mapping) - * independent of cachability - */ - if (PageHighMem(page) || need_coh) - need_kvaddr = 1; + page = alloc_pages(gfp, order); + if (!page) + return NULL; /* This is linear addr (0x8000_0000 based) */ paddr = page_to_phys(page); *dma_handle = paddr; - /* This is kernel Virtual address (0x7000_0000 based) */ - if (need_kvaddr) { + /* + * A coherent buffer needs MMU mapping to enforce non-cachability. + * kvaddr is kernel Virtual address (0x7000_0000 based). + */ + if (need_coh) { kvaddr = ioremap_nocache(paddr, size); if (kvaddr == NULL) { __free_pages(page, order); @@ -93,12 +77,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, { phys_addr_t paddr = dma_handle; struct page *page = virt_to_page(paddr); - int is_non_coh = 1; - - is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || - (is_isa_arcv2() && ioc_enable); - if (PageHighMem(page) || !is_non_coh) + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) iounmap((void __force __iomem *)vaddr); __free_pages(page, get_order(size)); @@ -185,3 +165,23 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, break; } } + +/* + * Plug in coherent or noncoherent dma ops + */ +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) +{ + /* + * IOC hardware snoops all DMA traffic keeping the caches consistent + * with memory - eliding need for any explicit cache maintenance of + * DMA buffers - so we can use dma_direct cache ops. + */ + if (is_isa_arcv2() && ioc_enable && coherent) { + set_dma_ops(dev, &dma_direct_ops); + dev_info(dev, "use dma_direct_ops cache ops\n"); + } else { + set_dma_ops(dev, &dma_noncoherent_ops); + dev_info(dev, "use dma_noncoherent_ops cache ops\n"); + } +} diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi index 7cb235ef0fb6..6e9e1c2f9def 100644 --- a/arch/arm/boot/dts/sama5d3_emac.dtsi +++ b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 79906cecb091..3ad482d2f1eb 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -223,7 +223,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 29e75b47becd..1b1a0e95c751 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -763,7 +763,6 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK config HOLES_IN_ZONE def_bool y - depends on NUMA source kernel/Kconfig.hz diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 6e9f33d14930..067d8937d5af 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -417,7 +417,7 @@ static int gcm_encrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -437,11 +437,18 @@ static int gcm_encrypt(struct aead_request *req) NULL); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv, nrounds); + if (walk.nbytes > AES_BLOCK_SIZE) { + crypto_inc(iv, AES_BLOCK_SIZE); + __aes_arm64_encrypt(ctx->aes_key.key_enc, + ks + AES_BLOCK_SIZE, iv, + nrounds); + } + } } /* handle the tail */ @@ -545,7 +552,7 @@ static int gcm_decrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -564,11 +571,21 @@ static int gcm_decrypt(struct aead_request *req) } while (--blocks > 0); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { + if (walk.nbytes > AES_BLOCK_SIZE) { + u8 *iv2 = iv + AES_BLOCK_SIZE; + + memcpy(iv2, iv, AES_BLOCK_SIZE); + crypto_inc(iv2, AES_BLOCK_SIZE); + + __aes_arm64_encrypt(ctx->aes_key.key_enc, iv2, + iv2, nrounds); + } __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv, nrounds); + } } /* handle the tail */ diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c index b7fb5274b250..0c4fc223f225 100644 --- a/arch/arm64/crypto/sm4-ce-glue.c +++ b/arch/arm64/crypto/sm4-ce-glue.c @@ -69,5 +69,5 @@ static void __exit sm4_ce_mod_fini(void) crypto_unregister_alg(&sm4_ce_alg); } -module_cpu_feature_match(SM3, sm4_ce_mod_init); +module_cpu_feature_match(SM4, sm4_ce_mod_init); module_exit(sm4_ce_mod_fini); diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 1b5e0e843c3a..7e2b3e360086 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -28,7 +28,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm goto("1: nop\n\t" + asm_volatile_goto("1: nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" @@ -42,7 +42,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm goto("1: b %l[l_yes]\n\t" + asm_volatile_goto("1: b %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f26055f2306e..3d6d7336f871 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -61,8 +61,7 @@ struct kvm_arch { u64 vmid_gen; u32 vmid; - /* 1-level 2nd stage table and lock */ - spinlock_t pgd_lock; + /* 1-level 2nd stage table, protected by kvm->mmu_lock */ pgd_t *pgd; /* VTTBR value associated with above pgd and vmid */ @@ -357,7 +356,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 95ac7374d723..4c8b13bede80 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c new file mode 100644 index 000000000000..ca4c3e12d8c5 --- /dev/null +++ b/arch/arm64/kernel/crash_core.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + */ + +#include <linux/crash_core.h> +#include <asm/memory.h> + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); +} diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index f6a5c6bc1434..922add8adb74 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) } } #endif /* CONFIG_HIBERNATION */ - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(VA_BITS); - /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ - vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", - kimage_voffset); - vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", - PHYS_OFFSET); - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); -} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d496ef579859..ca46153d7915 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; val &= ~CPACR_EL1_ZEN; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val &= ~CPACR_EL1_FPEN; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cpacr_el1); @@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) val = CPTR_EL2_DEFAULT; val |= CPTR_EL2_TTA | CPTR_EL2_TZ; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val |= CPTR_EL2_TFP; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cptr_el2); } @@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); - __activate_traps_fpsimd32(vcpu); if (has_vhe()) activate_traps_vhe(vcpu); else diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 65f86271f02b..8080c9f489c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -985,8 +985,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pmd_present(pmd) || !pmd_table(pmd)) { + if (!pmd_present(pmd)) + return 1; + if (!pmd_table(pmd)) { VM_WARN_ON(!pmd_table(pmd)); return 1; } @@ -1007,8 +1008,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pud_present(pud) || !pud_table(pud)) { + if (!pud_present(pud)) + return 1; + if (!pud_table(pud)) { VM_WARN_ON(!pud_table(pud)); return 1; } diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 5e4a59b3ec1b..2691a1857d20 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -211,7 +211,7 @@ static inline long ffz(int x) * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline long fls(int x) +static inline int fls(int x) { int r; @@ -232,7 +232,7 @@ static inline long fls(int x) * the libc and compiler builtin ffs routines, therefore * differs in spirit from the above ffz (man ffs). */ -static inline long ffs(int x) +static inline int ffs(int x) { int r; diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 77459df34e2e..7ebe7ad19d15 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, panic("Can't create %s() memory pool!", __func__); else gen_pool_add(coherent_pool, - pfn_to_virt(max_low_pfn), + (unsigned long)pfn_to_virt(max_low_pfn), hexagon_coherent_pool_size, -1); } diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 3534aa6a4dc2..1b083c500b9a 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -98,11 +98,10 @@ static time64_t pmu_read_time(void) if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) return 0; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); - time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) | - (req.reply[3] << 8) | req.reply[4]); + time = (u32)((req.reply[0] << 24) | (req.reply[1] << 16) | + (req.reply[2] << 8) | req.reply[3]); return time - RTC_OFFSET; } @@ -116,8 +115,7 @@ static void pmu_write_time(time64_t time) (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) return; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); } static __u8 pmu_read_pram(int offset) diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 70dde040779b..f5453d944ff5 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -172,7 +172,7 @@ void __init cf_bootmem_alloc(void) high_memory = (void *)_ramend; /* Reserve kernel text/data/bss */ - memblock_reserve(memstart, memstart - _rambase); + memblock_reserve(_rambase, memstart - _rambase); m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index a9af1d2dcd69..2c1c53d12179 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -931,7 +931,6 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, bool write); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h index 4901833498f7..8441b2698e64 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h +++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h @@ -40,6 +40,7 @@ struct ltq_dma_channel { int desc; /* the current descriptor */ struct ltq_dma_desc *desc_base; /* the descriptor base */ int phys; /* physical addr */ + struct device *dev; }; enum { diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 019035d7225c..8f845f6e5f42 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/ioport.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> @@ -20,6 +21,7 @@ #include <asm/abi.h> #include <asm/mips-cps.h> +#include <asm/page.h> #include <asm/vdso.h> /* Kernel-provided data used by the VDSO. */ @@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vvar_size = gic_size + PAGE_SIZE; size = vvar_size + image->size; + /* + * Find a region that's large enough for us to perform the + * colour-matching alignment below. + */ + if (cpu_has_dc_aliases) + size += shm_align_mask + 1; + base = get_unmapped_area(NULL, 0, size, 0, 0); if (IS_ERR_VALUE(base)) { ret = base; goto out; } + /* + * If we suffer from dcache aliasing, ensure that the VDSO data page + * mapping is coloured the same as the kernel's mapping of that memory. + * This ensures that when the kernel updates the VDSO data userland + * will observe it without requiring cache invalidations. + */ + if (cpu_has_dc_aliases) { + base = __ALIGN_MASK(base, shm_align_mask); + base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask; + } + data_addr = base + gic_size; vdso_addr = data_addr + PAGE_SIZE; diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index ee64db032793..d8dcdb350405 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,16 +512,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - - kvm_mips_callbacks->flush_shadow_all(kvm); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 4b9fbb6744ad..664f2f7f55c1 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -130,7 +130,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch) unsigned long flags; ch->desc = 0; - ch->desc_base = dma_zalloc_coherent(NULL, + ch->desc_base = dma_zalloc_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, &ch->phys, GFP_ATOMIC); @@ -182,7 +182,7 @@ ltq_dma_free(struct ltq_dma_channel *ch) if (!ch->desc_base) return; ltq_dma_close(ch); - dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE, + dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, ch->desc_base, ch->phys); } EXPORT_SYMBOL_GPL(ltq_dma_free); diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 1d4248fa55e9..7068f341133d 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -40,6 +40,10 @@ config NDS32 select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE help Andes(nds32) Linux support. diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 63f4f173e5f4..3509fac10491 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := defconfig comma = , +ifdef CONFIG_FUNCTION_TRACER +arch-y += -malways-save-lp -mno-relax +endif + KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog) KBUILD_CFLAGS += -mcmodel=large diff --git a/arch/nds32/include/asm/elf.h b/arch/nds32/include/asm/elf.h index 56c479058802..f5f9cf7e0544 100644 --- a/arch/nds32/include/asm/elf.h +++ b/arch/nds32/include/asm/elf.h @@ -121,9 +121,9 @@ struct elf32_hdr; */ #define ELF_CLASS ELFCLASS32 #ifdef __NDS32_EB__ -#define ELF_DATA ELFDATA2MSB; +#define ELF_DATA ELFDATA2MSB #else -#define ELF_DATA ELFDATA2LSB; +#define ELF_DATA ELFDATA2LSB #endif #define ELF_ARCH EM_NDS32 #define USE_ELF_CORE_DUMP diff --git a/arch/nds32/include/asm/ftrace.h b/arch/nds32/include/asm/ftrace.h new file mode 100644 index 000000000000..2f96cc96aa35 --- /dev/null +++ b/arch/nds32/include/asm/ftrace.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_NDS32_FTRACE_H +#define __ASM_NDS32_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER + +#define HAVE_FUNCTION_GRAPH_FP_TEST + +#define MCOUNT_ADDR ((unsigned long)(_mcount)) +/* mcount call is composed of three instructions: + * sethi + ori + jral + */ +#define MCOUNT_INSN_SIZE 12 + +extern void _mcount(unsigned long parent_ip); + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define FTRACE_ADDR ((unsigned long)_ftrace_caller) + +#ifdef __NDS32_EL__ +#define INSN_NOP 0x09000040 +#define INSN_SIZE(insn) (((insn & 0x00000080) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0x000000fe) == 0x00000046) +#define ENDIAN_CONVERT(insn) be32_to_cpu(insn) +#else /* __NDS32_EB__ */ +#define INSN_NOP 0x40000009 +#define INSN_SIZE(insn) (((insn & 0x80000000) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0xfe000000) == 0x46000000) +#define ENDIAN_CONVERT(insn) (insn) +#endif + +extern void _ftrace_caller(unsigned long parent_ip); +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} +struct dyn_arch_ftrace { +}; + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* __ASM_NDS32_FTRACE_H */ diff --git a/arch/nds32/include/asm/nds32.h b/arch/nds32/include/asm/nds32.h index 19b19394a936..68c38151c3e4 100644 --- a/arch/nds32/include/asm/nds32.h +++ b/arch/nds32/include/asm/nds32.h @@ -17,6 +17,7 @@ #else #define FP_OFFSET (-2) #endif +#define LP_OFFSET (-1) extern void __init early_trap_init(void); static inline void GIE_ENABLE(void) diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 18a009f3804d..362a32d9bd16 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -38,7 +38,7 @@ struct exception_table_entry { extern int fixup_exception(struct pt_regs *regs); #define KERNEL_DS ((mm_segment_t) { ~0UL }) -#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) +#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) #define get_ds() (KERNEL_DS) #define get_fs() (current_thread_info()->addr_limit) @@ -49,11 +49,11 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a) == (b)) +#define segment_eq(a, b) ((a) == (b)) #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size)) -#define access_ok(type, addr, size) \ +#define access_ok(type, addr, size) \ __range_ok((unsigned long)addr, (unsigned long)size) /* * Single-value transfer routines. They automatically use the right @@ -75,70 +75,73 @@ static inline void set_fs(mm_segment_t fs) * versions are void (ie, don't return a value as such). */ -#define get_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_READ, p, sizeof(*p)))) { \ - __e = __get_user(x,p); \ - } else \ - x = 0; \ - __e; \ -}) -#define __get_user(x,ptr) \ +#define get_user __get_user \ + +#define __get_user(x, ptr) \ ({ \ long __gu_err = 0; \ - __get_user_err((x),(ptr),__gu_err); \ + __get_user_check((x), (ptr), __gu_err); \ __gu_err; \ }) -#define __get_user_error(x,ptr,err) \ +#define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x),(ptr),err); \ - (void) 0; \ + __get_user_check((x), (ptr), (err)); \ + (void)0; \ }) -#define __get_user_err(x,ptr,err) \ +#define __get_user_check(x, ptr, err) \ +({ \ + const __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ +}) + +#define __get_user_err(x, ptr, err) \ do { \ - unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("lbi",__gu_val,__gu_addr,err); \ + __get_user_asm("lbi", __gu_val, (ptr), (err)); \ break; \ case 2: \ - __get_user_asm("lhi",__gu_val,__gu_addr,err); \ + __get_user_asm("lhi", __gu_val, (ptr), (err)); \ break; \ case 4: \ - __get_user_asm("lwi",__gu_val,__gu_addr,err); \ + __get_user_asm("lwi", __gu_val, (ptr), (err)); \ break; \ case 8: \ - __get_user_asm_dword(__gu_val,__gu_addr,err); \ + __get_user_asm_dword(__gu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ break; \ } \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " move %1, #0\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err), "=&r" (x) \ - : "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __get_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " move %1, #0\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err), "=&r" (x) \ + : "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __gu_reg_oper0 "%H1" @@ -149,61 +152,66 @@ do { \ #endif #define __get_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ - "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT) \ - : "cc") -#define put_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_WRITE, p, sizeof(*p)))) { \ - __e = __put_user(x,p); \ - } \ - __e; \ -}) -#define __put_user(x,ptr) \ + __asm__ __volatile__ ( \ + "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ + "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err), "=&r"(x) \ + : "r"(addr), "i"(-EFAULT) \ + : "cc") + +#define put_user __put_user \ + +#define __put_user(x, ptr) \ ({ \ long __pu_err = 0; \ - __put_user_err((x),(ptr),__pu_err); \ + __put_user_err((x), (ptr), __pu_err); \ __pu_err; \ }) -#define __put_user_error(x,ptr,err) \ +#define __put_user_error(x, ptr, err) \ +({ \ + __put_user_err((x), (ptr), (err)); \ + (void)0; \ +}) + +#define __put_user_check(x, ptr, err) \ ({ \ - __put_user_err((x),(ptr),err); \ - (void) 0; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) -#define __put_user_err(x,ptr,err) \ +#define __put_user_err(x, ptr, err) \ do { \ - unsigned long __pu_addr = (unsigned long)(ptr); \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("sbi",__pu_val,__pu_addr,err); \ + __put_user_asm("sbi", __pu_val, (ptr), (err)); \ break; \ case 2: \ - __put_user_asm("shi",__pu_val,__pu_addr,err); \ + __put_user_asm("shi", __pu_val, (ptr), (err)); \ break; \ case 4: \ - __put_user_asm("swi",__pu_val,__pu_addr,err); \ + __put_user_asm("swi", __pu_val, (ptr), (err)); \ break; \ case 8: \ - __put_user_asm_dword(__pu_val,__pu_addr,err); \ + __put_user_asm_dword(__pu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ @@ -211,22 +219,22 @@ do { \ } \ } while (0) -#define __put_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err) \ - : "r" (x), "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __put_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err) \ + : "r" (x), "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __pu_reg_oper0 "%H2" @@ -237,23 +245,24 @@ do { \ #endif #define __put_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ - "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err) \ - : "r"(addr), "r"(x), "i"(-EFAULT) \ - : "cc") + __asm__ __volatile__ ( \ + "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ + "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err) \ + : "r"(addr), "r"(x), "i"(-EFAULT) \ + : "cc") + extern unsigned long __arch_clear_user(void __user * addr, unsigned long n); extern long strncpy_from_user(char *dest, const char __user * src, long count); extern __must_check long strlen_user(const char __user * str); diff --git a/arch/nds32/kernel/Makefile b/arch/nds32/kernel/Makefile index 42792743e8b9..27cded39fa66 100644 --- a/arch/nds32/kernel/Makefile +++ b/arch/nds32/kernel/Makefile @@ -21,3 +21,9 @@ extra-y := head.o vmlinux.lds obj-y += vdso/ + +obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +endif diff --git a/arch/nds32/kernel/atl2c.c b/arch/nds32/kernel/atl2c.c index 0c6d031a1c4a..0c5386e72098 100644 --- a/arch/nds32/kernel/atl2c.c +++ b/arch/nds32/kernel/atl2c.c @@ -9,7 +9,8 @@ void __iomem *atl2c_base; static const struct of_device_id atl2c_ids[] __initconst = { - {.compatible = "andestech,atl2c",} + {.compatible = "andestech,atl2c",}, + {} }; static int __init atl2c_of_init(void) diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S index b8ae4e9a6b93..21a144071566 100644 --- a/arch/nds32/kernel/ex-entry.S +++ b/arch/nds32/kernel/ex-entry.S @@ -118,7 +118,7 @@ common_exception_handler: /* interrupt */ 2: #ifdef CONFIG_TRACE_IRQFLAGS - jal trace_hardirqs_off + jal __trace_hardirqs_off #endif move $r0, $sp sethi $lp, hi20(ret_from_intr) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 03e4f7788a18..f00af92f7e22 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -138,8 +138,8 @@ no_work_pending: #ifdef CONFIG_TRACE_IRQFLAGS lwi $p0, [$sp+(#IPSW_OFFSET)] andi $p0, $p0, #0x1 - la $r10, trace_hardirqs_off - la $r9, trace_hardirqs_on + la $r10, __trace_hardirqs_off + la $r9, __trace_hardirqs_on cmovz $r9, $p0, $r10 jral $r9 #endif diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c new file mode 100644 index 000000000000..a0a9679ad5de --- /dev/null +++ b/arch/nds32/kernel/ftrace.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ftrace.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> + +#ifndef CONFIG_DYNAMIC_FTRACE +extern void (*ftrace_trace_function)(unsigned long, unsigned long, + struct ftrace_ops*, struct pt_regs*); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern void ftrace_graph_caller(void); + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void _mcount(unsigned long parent_ip) +{ + /* save all state by the compiler prologue */ + + unsigned long ip = (unsigned long)__builtin_return_address(0); + + if (ftrace_trace_function != ftrace_stub) + ftrace_trace_function(ip - MCOUNT_INSN_SIZE, parent_ip, + NULL, NULL); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_return != (trace_func_graph_ret_t)ftrace_stub + || ftrace_graph_entry != ftrace_graph_entry_stub) + ftrace_graph_caller(); +#endif + + /* restore all state by the compiler epilogue */ +} +EXPORT_SYMBOL(_mcount); + +#else /* CONFIG_DYNAMIC_FTRACE */ + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void __naked _mcount(unsigned long parent_ip) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} +EXPORT_SYMBOL(_mcount); + +#define XSTR(s) STR(s) +#define STR(s) #s +void _ftrace_caller(unsigned long parent_ip) +{ + /* save all state needed by the compiler prologue */ + + /* + * prepare arguments for real tracing function + * first arg : __builtin_return_address(0) - MCOUNT_INSN_SIZE + * second arg : parent_ip + */ + __asm__ __volatile__ ( + "move $r1, %0 \n\t" + "addi $r0, %1, #-" XSTR(MCOUNT_INSN_SIZE) "\n\t" + : + : "r" (parent_ip), "r" (__builtin_return_address(0))); + + /* a placeholder for the call to a real tracing function */ + __asm__ __volatile__ ( + "ftrace_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* a placeholder for the call to ftrace_graph_caller */ + __asm__ __volatile__ ( + "ftrace_graph_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); +#endif + /* restore all state needed by the compiler epilogue */ +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} + +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + +static unsigned long gen_sethi_insn(unsigned long addr) +{ + unsigned long opcode = 0x46000000; + unsigned long imm = addr >> 12; + unsigned long rt_num = 0xf << 20; + + return ENDIAN_CONVERT(opcode | rt_num | imm); +} + +static unsigned long gen_ori_insn(unsigned long addr) +{ + unsigned long opcode = 0x58000000; + unsigned long imm = addr & 0x0000fff; + unsigned long rt_num = 0xf << 20; + unsigned long ra_num = 0xf << 15; + + return ENDIAN_CONVERT(opcode | rt_num | ra_num | imm); +} + +static unsigned long gen_jral_insn(unsigned long addr) +{ + unsigned long opcode = 0x4a000001; + unsigned long rt_num = 0x1e << 20; + unsigned long rb_num = 0xf << 10; + + return ENDIAN_CONVERT(opcode | rt_num | rb_num); +} + +static void ftrace_gen_call_insn(unsigned long *call_insns, + unsigned long addr) +{ + call_insns[0] = gen_sethi_insn(addr); /* sethi $r15, imm20u */ + call_insns[1] = gen_ori_insn(addr); /* ori $r15, $r15, imm15u */ + call_insns[2] = gen_jral_insn(addr); /* jral $lp, $r15 */ +} + +static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + unsigned long orig_insn[3]; + + if (validate) { + if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) + return -EINVAL; + } + + if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +static int ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + int ret; + + ret = __ftrace_modify_code(pc, old_insn, new_insn, validate); + if (ret) + return ret; + + flush_icache_range(pc, pc + MCOUNT_INSN_SIZE); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc = (unsigned long)&ftrace_call; + unsigned long old_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long new_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + if (func != ftrace_stub) + ftrace_gen_call_insn(new_insn, (unsigned long)func); + + return ftrace_modify_code(pc, old_insn, new_insn, false); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, nop_insn, call_insn, true); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + struct ftrace_graph_ent trace; + unsigned long old; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return; + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer, NULL); + + if (err == -EBUSY) + return; + + *parent = return_hooker; +} + +noinline void ftrace_graph_caller(void) +{ + unsigned long *parent_ip = + (unsigned long *)(__builtin_frame_address(2) - 4); + + unsigned long selfpc = + (unsigned long)(__builtin_return_address(1) - MCOUNT_INSN_SIZE); + + unsigned long frame_pointer = + (unsigned long)__builtin_frame_address(3); + + prepare_ftrace_return(parent_ip, selfpc, frame_pointer); +} + +extern unsigned long ftrace_return_to_handler(unsigned long frame_pointer); +void __naked return_to_handler(void) +{ + __asm__ __volatile__ ( + /* save state needed by the ABI */ + "smw.adm $r0,[$sp],$r1,#0x0 \n\t" + + /* get original return address */ + "move $r0, $fp \n\t" + "bal ftrace_return_to_handler\n\t" + "move $lp, $r0 \n\t" + + /* restore state nedded by the ABI */ + "lmw.bim $r0,[$sp],$r1,#0x0 \n\t"); +} + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_graph_call; + +static int ftrace_modify_graph_caller(bool enable) +{ + unsigned long pc = (unsigned long)&ftrace_graph_call; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, (unsigned long)ftrace_graph_caller); + + if (enable) + return ftrace_modify_code(pc, nop_insn, call_insn, true); + else + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + +#ifdef CONFIG_TRACE_IRQFLAGS +noinline void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +noinline void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +#endif /* CONFIG_TRACE_IRQFLAGS */ diff --git a/arch/nds32/kernel/module.c b/arch/nds32/kernel/module.c index 4167283d8293..1e31829cbc2a 100644 --- a/arch/nds32/kernel/module.c +++ b/arch/nds32/kernel/module.c @@ -40,7 +40,7 @@ void do_reloc16(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { @@ -70,7 +70,7 @@ void do_reloc32(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c index 8b231e910ea6..d974c0c1c65f 100644 --- a/arch/nds32/kernel/stacktrace.c +++ b/arch/nds32/kernel/stacktrace.c @@ -4,6 +4,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <linux/ftrace.h> void save_stack_trace(struct stack_trace *trace) { @@ -16,6 +17,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long *fpn; int skip = trace->skip; int savesched; + int graph_idx = 0; if (tsk == current) { __asm__ __volatile__("\tori\t%0, $fp, #0\n":"=r"(fpn)); @@ -29,10 +31,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) && (fpn >= (unsigned long *)TASK_SIZE)) { unsigned long lpp, fpp; - lpp = fpn[-1]; + lpp = fpn[LP_OFFSET]; fpp = fpn[FP_OFFSET]; if (!__kernel_text_address(lpp)) break; + else + lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL); if (savesched || !in_sched_functions(lpp)) { if (skip) { diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index a6205fd4db52..1496aab48998 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -8,6 +8,7 @@ #include <linux/kdebug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> +#include <linux/ftrace.h> #include <asm/proc-fns.h> #include <asm/unistd.h> @@ -94,28 +95,6 @@ static void dump_instr(struct pt_regs *regs) set_fs(fs); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#include <linux/ftrace.h> -static void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ - if (*addr == (unsigned long)return_to_handler) { - int index = tsk->curr_ret_stack; - - if (tsk->ret_stack && index >= *graph) { - index -= *graph; - *addr = tsk->ret_stack[index].ret; - (*graph)++; - } - } -} -#else -static inline void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ -} -#endif - #define LOOP_TIMES (100) static void __dump(struct task_struct *tsk, unsigned long *base_reg) { @@ -126,7 +105,8 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) while (!kstack_end(base_reg)) { ret_addr = *base_reg++; if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -137,15 +117,12 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) !((unsigned long)base_reg & 0x3) && ((unsigned long)base_reg >= TASK_SIZE)) { unsigned long next_fp; -#if !defined(NDS32_ABI_2) - ret_addr = base_reg[0]; - next_fp = base_reg[1]; -#else - ret_addr = base_reg[-1]; + ret_addr = base_reg[LP_OFFSET]; next_fp = base_reg[FP_OFFSET]; -#endif if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -196,11 +173,10 @@ void die(const char *str, struct pt_regs *regs, int err) pr_emerg("CPU: %i\n", smp_processor_id()); show_regs(regs); pr_emerg("Process %s (pid: %d, stack limit = 0x%p)\n", - tsk->comm, tsk->pid, task_thread_info(tsk) + 1); + tsk->comm, tsk->pid, end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { - dump_mem("Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_thread_info(tsk)); + dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK); dump_instr(regs); dump_stack(); } diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S index 288313b886ef..9e90f30a181d 100644 --- a/arch/nds32/kernel/vmlinux.lds.S +++ b/arch/nds32/kernel/vmlinux.lds.S @@ -13,14 +13,26 @@ OUTPUT_ARCH(nds32) ENTRY(_stext_lma) jiffies = jiffies_64; +#if defined(CONFIG_GCOV_KERNEL) +#define NDS32_EXIT_KEEP(x) x +#else +#define NDS32_EXIT_KEEP(x) +#endif + SECTIONS { _stext_lma = TEXTADDR - LOAD_OFFSET; . = TEXTADDR; __init_begin = .; HEAD_TEXT_SECTION + .exit.text : { + NDS32_EXIT_KEEP(EXIT_TEXT) + } INIT_TEXT_SECTION(PAGE_SIZE) INIT_DATA_SECTION(16) + .exit.data : { + NDS32_EXIT_KEEP(EXIT_DATA) + } PERCPU_SECTION(L1_CACHE_BYTES) __init_end = .; diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index 7a49f0d28d14..f1da8a7b17ff 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -3,15 +3,6 @@ config TRACE_IRQFLAGS_SUPPORT def_bool y -config DEBUG_STACK_USAGE - bool "Enable stack utilization instrumentation" - depends on DEBUG_KERNEL - help - Enables the display of the minimum amount of free stack which each - task has ever had available in the sysrq-T and sysrq-P debug output. - - This option will slow down process creation somewhat. - config EARLY_PRINTK bool "Activate early kernel debugging" default y diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index db0b6eebbfa5..a80669209155 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -177,7 +177,6 @@ config PPC select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT - select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_CBPF_JIT if !PPC64 diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 13a688fc8cd0..2fdc865ca374 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start, return hash__vmemmap_remove_mapping(start, page_size); } #endif -struct page *realmode_pfn_to_page(unsigned long pfn); static inline pte_t pmd_pte(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index ab3a4fba38e3..3d4b88cb8599 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); -extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b2f89b621b15..b694d6af1150 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 1a951b00465d..1fffbba8d6a5 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,6 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern unsigned long long memory_limit; +extern bool init_mem_is_free; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index ea04dfb8c092..2d8fc8c9da7a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1314,9 +1314,7 @@ EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100) #ifdef CONFIG_PPC_DENORMALISATION mfspr r10,SPRN_HSRR1 - mfspr r11,SPRN_HSRR0 /* save HSRR0 */ andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ - addi r11,r11,-4 /* HSRR0 is next instruction */ bne+ denorm_assist #endif @@ -1382,6 +1380,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) */ XVCPSGNDP32(32) denorm_done: + mfspr r11,SPRN_HSRR0 + subi r11,r11,4 mtspr SPRN_HSRR0,r11 mtcrf 0x80,r9 ld r9,PACA_EXGEN+EX_R9(r13) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index af7a20dc6e09..19b4c628f3be 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); -#ifdef CONFIG_PPC_BOOK3S_64 -long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret; - - ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - - if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) { - struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT); - - if (likely(pg)) { - SetPageDirty(pg); - } else { - tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - ret = -EFAULT; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm); -#endif - int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 6bffbc5affe7..7716374786bd 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -176,13 +176,27 @@ _GLOBAL(tm_reclaim) std r1, PACATMSCRATCH(r13) ld r1, PACAR1(r13) - /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + /* + * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is + * clobbered by an exception once we turn on MSR_RI below. + */ + ld r11, PACATMSCRATCH(r13) + std r11, GPR1(r1) + + /* + * Store r13 away so we can free up the scratch SPR for the SLB fault + * handler (needed once we start accessing the thread_struct). + */ + GET_SCRATCH0(r11) + std r11, GPR13(r1) + /* Reset MSR RI so we can take SLB faults again */ li r11, MSR_RI mtmsrd r11, 1 + /* Store the PPR in r11 and reset to decent value */ mfspr r11, SPRN_PPR HMT_MEDIUM @@ -207,11 +221,11 @@ _GLOBAL(tm_reclaim) SAVE_GPR(8, r7) /* user r8 */ SAVE_GPR(9, r7) /* user r9 */ SAVE_GPR(10, r7) /* user r10 */ - ld r3, PACATMSCRATCH(r13) /* user r1 */ + ld r3, GPR1(r1) /* user r1 */ ld r4, GPR7(r1) /* user r7 */ ld r5, GPR11(r1) /* user r11 */ ld r6, GPR12(r1) /* user r12 */ - GET_SCRATCH0(8) /* user r13 */ + ld r8, GPR13(r1) /* user r13 */ std r3, GPR1(r7) std r4, GPR7(r7) std r5, GPR11(r7) diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 3c0e8fb2b773..68e14afecac8 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long pp, key; unsigned long v, orig_v, gr; __be64 *hptep; - int index; + long int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0af1c0aea1fe..933c574e1cf7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr) { struct kvm *kvm = vcpu->kvm; - unsigned long mmu_seq, pte_size; - unsigned long gpa, gfn, hva, pfn; + unsigned long mmu_seq; + unsigned long gpa, gfn, hva; struct kvm_memory_slot *memslot; struct page *page = NULL; long ret; @@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ hva = gfn_to_hva_memslot(memslot, gfn); if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) { - pfn = page_to_pfn(page); upgrade_write = true; } else { + unsigned long pfn; + /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, writing, upgrade_p); @@ -639,63 +640,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - /* See if we can insert a 1GB or 2MB large PTE here */ - level = 0; - if (page && PageCompound(page)) { - pte_size = PAGE_SIZE << compound_order(compound_head(page)); - if (pte_size >= PUD_SIZE && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1); - } else if (pte_size >= PMD_SIZE && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); - } - } - /* - * Compute the PTE value that we need to insert. + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. */ - if (page) { - pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE | - _PAGE_ACCESSED; - if (writing || upgrade_write) - pgflags |= _PAGE_WRITE | _PAGE_DIRTY; - pte = pfn_pte(pfn, __pgprot(pgflags)); + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + pte = *ptep; + local_irq_enable(); + + /* Get pte level from shift/size */ + if (shift == PUD_SHIFT && + (gpa & (PUD_SIZE - PAGE_SIZE)) == + (hva & (PUD_SIZE - PAGE_SIZE))) { + level = 2; + } else if (shift == PMD_SHIFT && + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { + level = 1; } else { - /* - * Read the PTE from the process' radix tree and use that - * so we get the attribute bits. - */ - local_irq_disable(); - ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - pte = *ptep; - local_irq_enable(); - if (shift == PUD_SHIFT && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - } else if (shift == PMD_SHIFT && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - } else if (shift && shift != PAGE_SHIFT) { - /* Adjust PFN */ - unsigned long mask = (1ul << shift) - PAGE_SIZE; - pte = __pte(pte_val(pte) | (hva & mask)); - } - pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); - if (writing || upgrade_write) { - if (pte_val(pte) & _PAGE_WRITE) - pte = __pte(pte_val(pte) | _PAGE_DIRTY); - } else { - pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + level = 0; + if (shift > PAGE_SHIFT) { + /* + * If the pte maps more than one page, bring over + * bits from the virtual address to get the real + * address of the specific single page we want. + */ + unsigned long rpnmask = (1ul << shift) - PAGE_SIZE; + pte = __pte(pte_val(pte) | (hva & rpnmask)); } } + pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); + if (writing || upgrade_write) { + if (pte_val(pte) & _PAGE_WRITE) + pte = __pte(pte_val(pte) | _PAGE_DIRTY); + } else { + pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + } + /* Allocate space in the tree and write the PTE */ ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); @@ -725,10 +708,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, gpa, shift); kvmppc_radix_tlbie_page(kvm, gpa, shift); if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) { - unsigned long npages = 1; + unsigned long psize = PAGE_SIZE; if (shift) - npages = 1ul << (shift - PAGE_SHIFT); - kvmppc_update_dirty_map(memslot, gfn, npages); + psize = 1ul << shift; + kvmppc_update_dirty_map(memslot, gfn, psize); } } return 0; diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 506a4d400458..6821ead4b4eb 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry) +static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) +{ + long ret; + + ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL))) { + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); + /* + * kvmppc_rm_tce_iommu_do_map() updates the UA cache after + * calling this so we still get here a valid UA. + */ + if (pua && *pua) + mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua)); + } + + return ret; +} + +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry) { unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir)) + if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir)) /* * real mode xchg can fail if struct page crosses * a page boundary @@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret) - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_CLOSED; - ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); if (ret) { mm_iommu_mapped_dec(mem); /* @@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry, tce); @@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, goto unlock_exit; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry + i, tce); @@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } } diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 886ed94b9c13..d05c8af4ac51 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -443,6 +443,9 @@ _GLOBAL(csum_ipv6_magic) addc r0, r8, r9 ld r10, 0(r4) ld r11, 8(r4) +#ifdef CONFIG_CPU_LITTLE_ENDIAN + rotldi r5, r5, 8 +#endif adde r0, r0, r10 add r5, r5, r7 adde r0, r0, r11 diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 850f3b8f4da5..6ae2777c220d 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -28,6 +28,12 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr, { int err; + /* Make sure we aren't patching a freed init section */ + if (init_mem_is_free && init_section_contains(exec_addr, 4)) { + pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr); + return 0; + } + __put_user_size(instr, patch_addr, 4, err); if (err) return err; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 51ce091914f9..7a9886f98b0c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr, { } -/* - * We do not have access to the sparsemem vmemmap, so we fallback to - * walking the list of sparsemem blocks which we already maintain for - * the sake of crashdump. In the long run, we might want to maintain - * a tree if performance of that linear walk becomes a problem. - * - * realmode_pfn_to_page functions can fail due to: - * 1) As real sparsemem blocks do not lay in RAM continously (they - * are in virtual address space which is not available in the real mode), - * the requested page struct can be split between blocks so get_page/put_page - * may fail. - * 2) When huge pages are used, the get_page/put_page API will fail - * in real mode as the linked addresses in the page struct are virtual - * too. - */ -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct vmemmap_backing *vmem_back; - struct page *page; - unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; - unsigned long pg_va = (unsigned long) pfn_to_page(pfn); - - for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) { - if (pg_va < vmem_back->virt_addr) - continue; - - /* After vmemmap_list entry free is possible, need check all */ - if ((pg_va + sizeof(struct page)) <= - (vmem_back->virt_addr + page_size)) { - page = (struct page *) (vmem_back->phys + pg_va - - vmem_back->virt_addr); - return page; - } - } - - /* Probably that page struct is split between real pages */ - return NULL; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - -#else - -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct page *page = pfn_to_page(pfn); - return page; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5c8530d0c611..04ccb274a620 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -63,6 +63,7 @@ #endif unsigned long long memory_limit; +bool init_mem_is_free; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; @@ -396,6 +397,7 @@ void free_initmem(void) { ppc_md.progress = ppc_printk_progress; mark_initmem_nx(); + init_mem_is_free = true; free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index c9ee9e23845f..56c2234cc6ae 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -18,11 +18,15 @@ #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/swap.h> +#include <linux/sizes.h> #include <asm/mmu_context.h> #include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); +#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY 0x1 +#define MM_IOMMU_TABLE_GROUP_PAGE_MASK ~(SZ_4K - 1) + struct mm_iommu_table_group_mem_t { struct list_head next; struct rcu_head rcu; @@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) if (!page) continue; + if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY) + SetPageDirty(page); + put_page(page); mem->hpas[i] = 0; } @@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm); struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries) @@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; - *hpa = *va | (ua & ~PAGE_MASK); + *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } @@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (!pa) return -EFAULT; - *hpa = *pa | (ua & ~PAGE_MASK); + *hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } -EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm); + +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) +{ + struct mm_iommu_table_group_mem_t *mem; + long entry; + void *va; + unsigned long *pa; + + mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE); + if (!mem) + return; + + entry = (ua - mem->ua) >> PAGE_SHIFT; + va = &mem->hpas[entry]; + + pa = (void *) vmalloc_to_phys(va); + if (!pa) + return; + + *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY; +} long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem) { diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 35ac5422903a..59d07bd5374a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1204,7 +1204,9 @@ int find_and_online_cpu_nid(int cpu) int new_nid; /* Use associativity from first thread for all siblings */ - vphn_get_associativity(cpu, associativity); + if (vphn_get_associativity(cpu, associativity)) + return cpu_to_node(cpu); + new_nid = associativity_to_nid(associativity); if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; @@ -1452,7 +1454,8 @@ static struct timer_list topology_timer; static void reset_topology_timer(void) { - mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); + if (vphn_enabled) + mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index 333b1f80c435..b271b283c785 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -45,7 +45,7 @@ static void scan_pkey_feature(void) * Since any pkey can be used for data or execute, we will just treat * all keys as equal and track them as one entity. */ - pkeys_total = be32_to_cpu(vals[0]); + pkeys_total = vals[0]; pkeys_devtree_defined = true; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index 6c5db1acbe8d..fe9691040f54 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -276,7 +276,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, level_shift = entries_shift + 3; level_shift = max_t(unsigned int, level_shift, PAGE_SHIFT); - if ((level_shift - 3) * levels + page_shift >= 60) + if ((level_shift - 3) * levels + page_shift >= 55) return -EINVAL; /* Allocate TCE table */ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..c9fecd120d18 --- /dev/null +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PROTOTYPES_H + +#include <linux/ftrace.h> +#include <asm-generic/asm-prototypes.h> + +#endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index c229509288ea..439dc7072e05 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -14,6 +14,10 @@ #ifndef _ASM_RISCV_TLB_H #define _ASM_RISCV_TLB_H +struct mmu_gather; + +static void tlb_flush(struct mmu_gather *tlb); + #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index db20dc630e7e..aee603123030 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -85,15 +85,8 @@ atomic_t hart_lottery; #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { - extern char __initramfs_start[]; - extern unsigned long __initramfs_size; unsigned long size; - if (__initramfs_size > 0) { - initrd_start = (unsigned long)(&__initramfs_start); - initrd_end = initrd_start + __initramfs_size; - } - if (initrd_start >= initrd_end) { printk(KERN_INFO "initrd not found or empty"); goto disable; diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 568026ccf6e8..fb03a4482ad6 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -65,24 +65,11 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, uintptr_t, flags) { -#ifdef CONFIG_SMP - struct mm_struct *mm = current->mm; - bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0; -#endif - /* Check the reserved flags. */ if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) return -EINVAL; - /* - * Without CONFIG_SMP flush_icache_mm is a just a flush_icache_all(), - * which generates unused variable warnings all over this function. - */ -#ifdef CONFIG_SMP - flush_icache_mm(mm, local); -#else - flush_icache_all(); -#endif + flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL); return 0; } diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 80b27294c1de..ab9a0ebecc19 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, walk->dst.virt.addr, walk->src.virt.addr, n); if (k) ret = blkcipher_walk_done(desc, walk, nbytes - k); - if (n < k) { + if (k < n) { if (__cbc_paes_set_key(ctx) != 0) return blkcipher_walk_done(desc, walk, -EIO); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index f31a15044c24..a8418e1379eb 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,7 +16,13 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context allocates 4K page tables. */ + /* + * The following bitfields need a down_write on the mm + * semaphore when they are written to. As they are only + * written once, they can be read without a lock. + * + * The mmu context allocates 4K page tables. + */ unsigned int alloc_pgste:1; /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 91ad4a9425c0..ac5da6b0b862 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_S390_HPAGE_1M: r = 0; - if (hpage) + if (hpage && !kvm_is_ucontrol(kvm)) r = 1; break; case KVM_CAP_S390_MEM_OP: @@ -691,11 +691,13 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; - else if (!hpage || kvm->arch.use_cmma) + else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) r = -EINVAL; else { r = 0; + down_write(&kvm->mm->mmap_sem); kvm->mm->context.allow_gmap_hpage_1m = 1; + up_write(&kvm->mm->mmap_sem); /* * We might have to create fake 4k page * tables. To avoid that the hardware works on diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d68f10441a16..8679bd74d337 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -280,9 +280,11 @@ retry: goto retry; } } - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; vcpu->run->s.regs.gprs[reg1] &= ~0xff; vcpu->run->s.regs.gprs[reg1] |= key; return 0; @@ -324,9 +326,11 @@ retry: goto retry; } } - if (rc < 0) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; kvm_s390_set_psw_cc(vcpu, rc); return 0; } @@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc < 0) + return rc; + start += PAGE_SIZE; } if (m3 & (SSKE_MC | SSKE_MR)) { @@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc == -EAGAIN) + continue; + if (rc < 0) + return rc; } + start += PAGE_SIZE; } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 63844b95c22c..a2b28cd1e3fe 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return set_validity_icpt(scb_s, 0x0039U); /* copy only the wrapping keys */ - if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56)) + if (read_guest_real(vcpu, crycb_addr + 72, + vsie_page->crycb.dea_wrapping_key_mask, 56)) return set_validity_icpt(scb_s, 0x0035U); scb_s->ecb3 |= ecb3_flags; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bb44990c8212..911c7ded35f1 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); + if (!vma) + continue; /* * We do not discard pages that are backed by * hugetlbfs, so we don't have to refault them. */ - if (vma && is_vm_hugetlb_page(vma)) + if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range(vma, vmaddr, size); diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 3641a294ed54..e4abe9b8f97a 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/dma-mapping.h> #include <asm/leon.h> #include <asm/leon_amba.h> @@ -381,6 +382,9 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; + if (of_device_register(op)) { printk("%s: Could not register of device.\n", dp->full_name); diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 44e4d4435bed..6df6086968c6 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -2,6 +2,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mod_devicetable.h> @@ -675,6 +676,8 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, dev_set_name(&op->dev, "root"); else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; if (of_device_register(op)) { printk("%s: Could not register of device.\n", diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c5ff296bc5d1..1a0be022f91d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2843,7 +2843,7 @@ config X86_SYSFB This option, if enabled, marks VGA/VBE/EFI framebuffers as generic framebuffers so the new generic system-framebuffer drivers can be used on x86. If the framebuffer is not compatible with the generic - modes, it is adverticed as fallback platform framebuffer so legacy + modes, it is advertised as fallback platform framebuffer so legacy drivers like efifb, vesafb and uvesafb can pick it up. If this option is not selected, all system framebuffers are always marked as fallback platform framebuffers as usual. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94859241bc3e..8f6e7eb8ae9f 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -175,22 +175,6 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER endif endif -ifndef CC_HAVE_ASM_GOTO - $(error Compiler lacks asm-goto support.) -endif - -# -# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a -# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way -# to test for this bug at compile-time because the test case needs to execute, -# which is a no-go for cross compilers. So check the GCC version instead. -# -ifdef CONFIG_JUMP_LABEL - ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1) - ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1) - endif -endif - ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) # This compiler flag is not supported by Clang: KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) @@ -312,6 +296,13 @@ PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ +archprepare: checkbin +checkbin: +ifndef CC_HAVE_ASM_GOTO + @echo Compiler lacks asm-goto support. + @exit 1 +endif + archclean: $(Q)rm -rf $(objtree)/arch/i386 $(Q)rm -rf $(objtree)/arch/x86_64 diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index eaa843a52907..a480356e0ed8 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -25,20 +25,6 @@ ENTRY(get_sev_encryption_bit) push %ebx push %ecx push %edx - push %edi - - /* - * RIP-relative addressing is needed to access the encryption bit - * variable. Since we are running in 32-bit mode we need this call/pop - * sequence to get the proper relative addressing. - */ - call 1f -1: popl %edi - subl $1b, %edi - - movl enc_bit(%edi), %eax - cmpl $0, %eax - jge .Lsev_exit /* Check if running under a hypervisor */ movl $1, %eax @@ -69,15 +55,12 @@ ENTRY(get_sev_encryption_bit) movl %ebx, %eax andl $0x3f, %eax /* Return the encryption bit location */ - movl %eax, enc_bit(%edi) jmp .Lsev_exit .Lno_sev: xor %eax, %eax - movl %eax, enc_bit(%edi) .Lsev_exit: - pop %edi pop %edx pop %ecx pop %ebx @@ -113,8 +96,6 @@ ENTRY(set_sev_encryption_mask) ENDPROC(set_sev_encryption_mask) .data -enc_bit: - .int 0xffffffff #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index acd11b3bf639..2a356b948720 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 2071c3d1ae07..dbe8bb980da1 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index b5f2a8fd5a71..8bebda2de92f 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 9bd139569b41..cb2deb61c5d9 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -223,34 +223,34 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff pcmpeqd TWOONE(%rip), \TMP2 pand POLY(%rip), \TMP2 pxor \TMP2, \TMP3 - movdqa \TMP3, HashKey(%arg2) + movdqu \TMP3, HashKey(%arg2) movdqa \TMP3, \TMP5 pshufd $78, \TMP3, \TMP1 pxor \TMP3, \TMP1 - movdqa \TMP1, HashKey_k(%arg2) + movdqu \TMP1, HashKey_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^2<<1 (mod poly) - movdqa \TMP5, HashKey_2(%arg2) + movdqu \TMP5, HashKey_2(%arg2) # HashKey_2 = HashKey^2<<1 (mod poly) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_2_k(%arg2) + movdqu \TMP1, HashKey_2_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_3(%arg2) + movdqu \TMP5, HashKey_3(%arg2) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_3_k(%arg2) + movdqu \TMP1, HashKey_3_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_4(%arg2) + movdqu \TMP5, HashKey_4(%arg2) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_4_k(%arg2) + movdqu \TMP1, HashKey_4_k(%arg2) .endm # GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding. @@ -271,7 +271,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, - movdqa HashKey(%arg2), %xmm13 + movdqu HashKey(%arg2), %xmm13 CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ %xmm4, %xmm5, %xmm6 @@ -997,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -1016,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%arg2), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -1031,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -1044,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%arg2), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -1058,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -1074,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%arg2), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -1092,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -1121,7 +1121,7 @@ aes_loop_par_enc_done\@: AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%arg2), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK @@ -1205,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -1224,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%arg2), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -1239,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -1252,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%arg2), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -1266,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -1282,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%arg2), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -1300,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -1329,7 +1329,7 @@ aes_loop_par_dec_done\@: AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%arg2), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK @@ -1405,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM1, \TMP6 pshufd $78, \XMM1, \TMP2 pxor \XMM1, \TMP2 - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP6 # TMP6 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM1 # XMM1 = a0*b0 - movdqa HashKey_4_k(%arg2), \TMP4 + movdqu HashKey_4_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqa \XMM1, \XMMDst movdqa \TMP2, \XMM1 # result in TMP6, XMMDst, XMM1 @@ -1418,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM2, \TMP1 pshufd $78, \XMM2, \TMP2 pxor \XMM2, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM2 # XMM2 = a0*b0 - movdqa HashKey_3_k(%arg2), \TMP4 + movdqu HashKey_3_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM2, \XMMDst @@ -1433,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM3, \TMP1 pshufd $78, \XMM3, \TMP2 pxor \XMM3, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM3 # XMM3 = a0*b0 - movdqa HashKey_2_k(%arg2), \TMP4 + movdqu HashKey_2_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM3, \XMMDst @@ -1446,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM4, \TMP1 pshufd $78, \XMM4, \TMP2 pxor \XMM4, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM4 # XMM4 = a0*b0 - movdqa HashKey_k(%arg2), \TMP4 + movdqu HashKey_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM4, \XMMDst diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 95cf857d2cbb..f40244eaf14d 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); static int __init crypto_morus1280_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 615fb7bc9a32..9afaf8f8565a 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); static int __init crypto_morus640_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 5f4829f10129..dfb2f7c0d019 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,7 +2465,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs perf_callchain_store(entry, regs->ip); - if (!current->mm) + if (!nmi_uaccess_okay()) return; if (perf_callchain_user32(regs, entry)) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f3e006bed9a7..c88ed39582a1 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.lbr_sel_mask = LBR_SEL_MASK; x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + /* Knights Landing does have MISPREDICT bit */ + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP) + x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5b0f613428c2..2c43e3055948 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) { - struct ipi_arg_ex **arg; - struct ipi_arg_ex *ipi_arg; + struct hv_send_ipi_ex **arg; + struct hv_send_ipi_ex *ipi_arg; unsigned long flags; int nr_bank = 0; int ret = 1; @@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) return false; local_irq_save(flags); - arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); ipi_arg = *arg; if (unlikely(!ipi_arg)) @@ -135,7 +135,7 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex ipi_arg; + struct hv_send_ipi ipi_arg; int ret = 1; trace_hyperv_send_ipi_mask(mask, vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b143717b92b3..ce84388e540c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); } +#define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable @@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } +#define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable @@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } +#define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test @@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } +#define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test @@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } +#define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative @@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); } +#define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index ef959f02d070..6a5b0ec460da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_add_unless - add unless the number is a given value @@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) "S" (v) : "ecx", "edx", "memory"); return r; } +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; @@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) "S" (v) : "ecx", "memory"); return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #undef alternative_atomic64 #undef __alternative_atomic64 diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 4343d9b4f30e..5f851d92eecd 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); } +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable @@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test @@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test @@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative @@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } +#define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index e203169931c7..6390bd8c141b 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -14,6 +14,16 @@ #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +/* + * Exposed to assembly code for setting up initial page tables. Cannot be + * calculated in assembly code (fixmap entries are an enum), but is sanity + * checked in the actual fixmap C code to make sure that the fixmap is + * covered fully. + */ +#define FIXMAP_PMD_NUM 2 +/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */ +#define FIXMAP_PMD_TOP 507 + #ifndef __ASSEMBLY__ #include <linux/kernel.h> #include <asm/acpi.h> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index e977b6b3a538..00e01d215f74 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -726,19 +726,21 @@ struct hv_enlightened_vmcs { #define HV_STIMER_AUTOENABLE (1ULL << 3) #define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) -struct ipi_arg_non_ex { - u32 vector; - u32 reserved; - u64 cpu_mask; -}; - struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; }; -struct ipi_arg_ex { +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +/* HvCallSendSyntheticClusterIpiEx hypercall */ +struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c14f2a74b2be..15450a675031 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -33,7 +33,8 @@ extern inline unsigned long native_save_fl(void) return flags; } -static inline void native_restore_fl(unsigned long flags) +extern inline void native_restore_fl(unsigned long flags); +extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 395c9631e000..75f1e35e7c15 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -22,10 +22,20 @@ enum die_val { DIE_NMIUNKNOWN, }; +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); -extern void __show_regs(struct pt_regs *regs, int all); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00ddb0c9e612..09b2e3e2cf1b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -869,6 +869,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + bool guest_can_read_msr_platform_info; }; struct kvm_vm_stat { @@ -1022,6 +1024,7 @@ struct kvm_x86_ops { void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); + bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); @@ -1055,6 +1058,7 @@ struct kvm_x86_ops { bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1237,19 +1241,12 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_RETRY (1 << 3) -#define EMULTYPE_NO_REEXECUTE (1 << 4) -#define EMULTYPE_NO_UD_ON_FAIL (1 << 5) -#define EMULTYPE_VMWARE (1 << 6) -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, - int emulation_type, void *insn, int insn_len); - -static inline int emulate_instruction(struct kvm_vcpu *vcpu, - int emulation_type) -{ - return x86_emulate_instruction(vcpu, 0, - emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); -} +#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_NO_UD_ON_FAIL (1 << 4) +#define EMULTYPE_VMWARE (1 << 5) +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -1450,7 +1447,6 @@ asmlinkage void kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "") #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -1463,7 +1459,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); u64 kvm_get_arch_capabilities(void); @@ -1490,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c0643831706e..616f8e637bc3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void __init mem_encrypt_free_decrypted_mem(void); bool sme_active(void); bool sev_active(void); +#define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +#define __bss_decrypted + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* @@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; #define __sme_pa(x) (__pa(x) | sme_me_mask) #define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) +extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 24c6cf5f16b7..60d0f9015317 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); -#endif *pmdp = pmd; } @@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); -#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); -#endif return __pud(xchg((pudval_t *)xp, 0)); } #else diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index a564084c6141..f8b1ad2c3828 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PGTABLE_3LEVEL_H #define _ASM_X86_PGTABLE_3LEVEL_H +#include <asm/atomic64_32.h> + /* * Intel Physical Address Extension (PAE) Mode - three-level page * tables on PPro+ CPUs. @@ -150,10 +152,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep) { pte_t res; - /* xchg acts as a barrier before the setting of the high bits */ - res.pte_low = xchg(&ptep->pte_low, 0); - res.pte_high = ptep->pte_high; - ptep->pte_high = 0; + res.pte = (pteval_t)arch_atomic64_xchg((atomic64_t *)ptep, 0); return res; } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e4ffa565a69f..690c0307afed 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); return old; } } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f773d5e6c8cc..9c85b54bf03c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> +#include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; @@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; -extern pte_t level1_fixmap_pgt[512]; +extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt @@ -55,15 +56,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); -static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { - *ptep = native_make_pte(0); + WRITE_ONCE(*ptep, pte); } -static inline void native_set_pte(pte_t *ptep, pte_t pte) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -73,7 +74,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -109,7 +110,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -137,13 +138,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); - *p4dp = native_make_p4d(native_pgd_val(pgd)); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) @@ -153,7 +154,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgtbl(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c24297268ebc..d53c54b842da 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -132,6 +132,8 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; + /* Address space bits used by the cache internally */ + u8 x86_cache_bits; unsigned initialized : 1; } __randomize_layout; @@ -183,7 +185,7 @@ extern void cpu_detect(struct cpuinfo_x86 *c); static inline unsigned long long l1tf_pfn_limit(void) { - return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT); + return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } extern void early_cpu_init(void); diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 5f9012ff52ed..33d3c88a7225 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -39,6 +39,7 @@ extern void do_signal(struct pt_regs *regs); #define __ARCH_HAS_SA_RESTORER +#include <asm/asm.h> #include <uapi/asm/sigcontext.h> #ifdef __i386__ @@ -86,9 +87,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig) static inline int __gen_sigismember(sigset_t *set, int _sig) { - unsigned char ret; - asm("btl %2,%1\n\tsetc %0" - : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc"); + bool ret; + asm("btl %2,%1" CC_SET(c) + : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1)); return ret; } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index b6dc698f992a..f335aad404a4 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -111,6 +111,6 @@ static inline unsigned long caller_frame_pointer(void) return (unsigned long)frame; } -void show_opcodes(u8 *rip, const char *loglvl); +void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 29c9da6c62fc..58ce5288878e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -175,8 +175,16 @@ struct tlb_state { * are on. This means that it may not match current->active_mm, * which will contain the previous user mm when we're in lazy TLB * mode even if we've already switched back to swapper_pg_dir. + * + * During switch_mm_irqs_off(), loaded_mm will be set to + * LOADED_MM_SWITCHING during the brief interrupts-off window + * when CR3 and loaded_mm would otherwise be inconsistent. This + * is for nmi_uaccess_okay()'s benefit. */ struct mm_struct *loaded_mm; + +#define LOADED_MM_SWITCHING ((struct mm_struct *)1) + u16 loaded_mm_asid; u16 next_asid; /* last user mm's ctx id */ @@ -246,6 +254,38 @@ struct tlb_state { }; DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); +/* + * Blindly accessing user memory from NMI context can be dangerous + * if we're in the middle of switching the current user task or + * switching the loaded mm. It can also be dangerous if we + * interrupted some kernel code that was temporarily using a + * different mm. + */ +static inline bool nmi_uaccess_okay(void) +{ + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + struct mm_struct *current_mm = current->mm; + + VM_WARN_ON_ONCE(!loaded_mm); + + /* + * The condition we want to check is + * current_mm->pgd == __va(read_cr3_pa()). This may be slow, though, + * if we're running in a VM with shadow paging, and nmi_uaccess_okay() + * is supposed to be reasonably fast. + * + * Instead, we check the almost equivalent but somewhat conservative + * condition below, and we rely on the fact that switch_mm_irqs_off() + * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3. + */ + if (loaded_mm != current_mm) + return false; + + VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa())); + + return true; +} + /* Initialize cr4 shadow for this CPU. */ static inline void cr4_init_shadow(void) { diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index fb856c9f0449..53748541c487 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -93,7 +93,7 @@ static inline unsigned int __getcpu(void) * * If RDPID is available, use it. */ - alternative_io ("lsl %[p],%[seg]", + alternative_io ("lsl %[seg],%[p]", ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */ X86_FEATURE_RDPID, [p] "=a" (p), [seg] "r" (__PER_CPU_SEG)); diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 86299efa804a..fd23d5778ea1 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -377,6 +377,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 014f214da581..b9d5e7c9ef43 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -684,8 +684,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. - * - * Note: Must be called under text_mutex. */ void *text_poke(void *addr, const void *opcode, size_t len) { @@ -700,6 +698,8 @@ void *text_poke(void *addr, const void *opcode, size_t len) */ BUG_ON(!after_bootmem); + lockdep_assert_held(&text_mutex); + if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -782,8 +782,6 @@ int poke_int3_handler(struct pt_regs *regs) * - replace the first byte (int3) by the first byte of * replacing opcode * - sync cores - * - * Note: must be called under text_mutex. */ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { @@ -792,6 +790,9 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) bp_int3_handler = handler; bp_int3_addr = (u8 *)addr + sizeof(int3); bp_patching_in_progress = true; + + lockdep_assert_held(&text_mutex); + /* * Corresponding read barrier in int3 notifier for making sure the * in_progress and handler are correctly ordered wrt. patching. diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..7654febd5102 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ec00d1ff5098..f7151cd03cb0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS static int proc_apm_show(struct seq_file *m, void *v) { unsigned short bx; @@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v) units); return 0; } +#endif static int apm(void *unused) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4c2313d0b9ca..40bdaea97fe7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -668,6 +668,45 @@ EXPORT_SYMBOL_GPL(l1tf_mitigation); enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); +/* + * These CPUs all support 44bits physical address space internally in the + * cache but CPUID can report a smaller number of physical address bits. + * + * The L1TF mitigation uses the top most address bit for the inversion of + * non present PTEs. When the installed memory reaches into the top most + * address bit due to memory holes, which has been observed on machines + * which report 36bits physical address bits and have 32G RAM installed, + * then the mitigation range check in l1tf_select_mitigation() triggers. + * This is a false positive because the mitigation is still possible due to + * the fact that the cache uses 44bit internally. Use the cache bits + * instead of the reported physical bits and adjust them on the affected + * machines to 44bit if the reported bits are less than 44. + */ +static void override_cache_bits(struct cpuinfo_x86 *c) +{ + if (c->x86 != 6) + return; + + switch (c->x86_model) { + case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_WESTMERE: + case INTEL_FAM6_SANDYBRIDGE: + case INTEL_FAM6_IVYBRIDGE: + case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL_ULT: + case INTEL_FAM6_HASWELL_GT3E: + case INTEL_FAM6_BROADWELL_CORE: + case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + if (c->x86_cache_bits < 44) + c->x86_cache_bits = 44; + break; + } +} + static void __init l1tf_select_mitigation(void) { u64 half_pa; @@ -675,6 +714,8 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + override_cache_bits(&boot_cpu_data); + switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: case L1TF_MITIGATION_FLUSH_NOWARN: @@ -694,11 +735,6 @@ static void __init l1tf_select_mitigation(void) return; #endif - /* - * This is extremely unlikely to happen because almost all - * systems have far more MAX_PA/2 than RAM can be fit into - * DIMM slots. - */ half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 84dee5ab745a..44c4ef3d989b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -919,6 +919,7 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c) else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) c->x86_phys_bits = 36; #endif + c->x86_cache_bits = c->x86_phys_bits; } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 401e8c133108..fc3c07fe7df5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -150,6 +150,9 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return false; + if (c->x86 != 6) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 4e588f36228f..285eb3ec4200 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -423,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (void *data, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index af358ca05160..0f53049719cd 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; - char *buf = _buf; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -struct rdt_cbm_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - struct rdt_cbm_parse_data *data = _data; struct rdtgroup *rdtgrp = data->rdtgrp; u32 cbm_val; @@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) static int parse_line(char *line, struct rdt_resource *r, struct rdtgroup *rdtgrp) { - struct rdt_cbm_parse_data data; + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index b799c00bef09..1b8e86a5d5e1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -111,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (!closid_allocated(i)) continue; mode = rdtgroup_mode_by_closid(i); @@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { ctrl_b = (unsigned long *)ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && @@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; struct rdt_resource *r; + bool has_cache = false; struct rdt_domain *d; for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; list_for_each_entry(d, &r->domains, list) { if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); return false; + } } } + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + return true; } @@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, rdtgrp->mode = RDT_MODE_SHAREABLE; } else if (!strcmp(buf, "exclusive")) { if (!rdtgroup_mode_test_exclusive(rdtgrp)) { - rdt_last_cmd_printf("schemata overlaps\n"); ret = -EINVAL; goto out; } @@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; - bool sep = false; - u32 cbm; + bool sep; + u32 ctrl; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } for_each_alloc_enabled_rdt_resource(r) { + sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { if (sep) @@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - cbm = d->ctrl_val[rdtgrp->closid]; - size = rdtgroup_cbm_to_size(r, d, cbm); + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); } seq_printf(s, "%d=%u", d->id, size); sep = true; @@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; list_for_each_entry(d, &r->domains, list) { d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; ret = update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("failed to initialize allocations\n"); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9c8652974f8e..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -17,6 +17,7 @@ #include <linux/bug.h> #include <linux/nmi.h> #include <linux/sysfs.h> +#include <linux/kasan.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> @@ -89,14 +90,24 @@ static void printk_stack_address(unsigned long address, int reliable, * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random * guesstimate in attempt to achieve all of the above. */ -void show_opcodes(u8 *rip, const char *loglvl) +void show_opcodes(struct pt_regs *regs, const char *loglvl) { #define PROLOGUE_SIZE 42 #define EPILOGUE_SIZE 21 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; + unsigned long prologue = regs->ip - PROLOGUE_SIZE; + bool bad_ip; - if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) { + /* + * Make sure userspace isn't trying to trick us into dumping kernel + * memory by pointing the userspace instruction pointer at it. + */ + bad_ip = user_mode(regs) && + __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); + + if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue, + OPCODE_BUFSIZE)) { printk("%sCode: Bad RIP value.\n", loglvl); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" @@ -112,7 +123,7 @@ void show_ip(struct pt_regs *regs, const char *loglvl) #else printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip); #endif - show_opcodes((u8 *)regs->ip, loglvl); + show_opcodes(regs, loglvl); } void show_iret_regs(struct pt_regs *regs) @@ -135,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -333,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -346,7 +357,10 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * We're not going to return, but we might be on an IST stack or * have very little stack space left. Rewind the stack and kill * the task. + * Before we rewind the stack, we have to tell KASAN that we're going to + * reuse the task stack and that existing poisons are invalid. */ + kasan_unpoison_task_stack(current); rewind_stack_do_exit(signr); } NOKPROBE_SYMBOL(oops_end); @@ -393,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index f260e452e4f8..e8c8c5d78dbd 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -7,11 +7,17 @@ #include <linux/eisa.h> #include <linux/io.h> +#include <xen/xen.h> + static __init int eisa_bus_probe(void) { - void __iomem *p = ioremap(0x0FFFD9, 4); + void __iomem *p; + + if (xen_pv_domain() && !xen_initial_domain()) + return 0; - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + p = ioremap(0x0FFFD9, 4); + if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; iounmap(p); return 0; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8047379e575a..ddee1f0870c4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -35,6 +35,7 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> /* * Manage page tables very early on. @@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[511] += load_delta; pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; + for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) + pmd[i] += load_delta; /* * Set up the identity mapping for the switchover. These @@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr, sme_encrypt_kernel(bp); /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (mem_encrypt_active()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 15ebc2fc166e..a3618cf04cf6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,6 +24,7 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/fixmap.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt) KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 + .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 + pgtno = 0 + .rept (FIXMAP_PMD_NUM) + .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \ + + _PAGE_TABLE_NOENC; + pgtno = pgtno + 1 + .endr + /* 6 MB reserved space + a 2MB hole */ + .fill 4,8,0 NEXT_PAGE(level1_fixmap_pgt) + .rept (FIXMAP_PMD_NUM) .fill 512,8,0 + .endr #undef PMDS diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e6764648af3..013fe3d21dbb 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h> #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +static struct pvclock_vsyscall_time_info *hvclock_mem; static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { @@ -236,6 +238,45 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (sev_active()) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + static int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 @@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void) kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif + + kvmclock_init_mem(); + return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); @@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu) /* Use the static page for the first CPUs, allocate otherwise */ if (cpu < HVC_BOOT_ARRAY_SIZE) p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; else - p = kzalloc(sizeof(*p), GFP_KERNEL); + return -ENOMEM; per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index afdb303285f8..8dc69d82567e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); - if (!all) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..ea5ea850348d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,7 @@ __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 12cbe2b88c0f..738bf42b0218 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -111,8 +111,10 @@ int arch_register_cpu(int num) /* * Currently CPU0 is only hotpluggable on Intel platforms. Other * vendors can add hotplug support later. + * Xen PV guests don't support CPU0 hotplug at all. */ - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL || + boot_cpu_has(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..6490f618e096 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a419f86..5dd3317d761f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,6 +65,23 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. Make this section PMD-aligned + * to avoid splitting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define BSS_DECRYPTED \ + . = ALIGN(PMD_SIZE); \ + __start_bss_decrypted = .; \ + *(.bss..decrypted); \ + . = ALIGN(PAGE_SIZE); \ + __start_bss_decrypted_unused = .; \ + . = ALIGN(PMD_SIZE); \ + __end_bss_decrypted = .; \ + #else #define X86_ALIGN_RODATA_BEGIN @@ -74,6 +91,7 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END +#define BSS_DECRYPTED #endif @@ -355,6 +373,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) + BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0cefba28c864..fbb0e6df121b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -548,7 +548,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, } int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { int i; @@ -571,18 +571,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (min > map->max_apic_id) + goto out; /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + for_each_set_bit(i, &ipi_bitmap_low, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } min += cluster_size; - for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + + if (min > map->max_apic_id) + goto out; + + for_each_set_bit(i, &ipi_bitmap_high, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } +out: rcu_read_unlock(); return count; } @@ -1331,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read); static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { - return kvm_apic_hw_enabled(apic) && - addr >= apic->base_address && - addr < apic->base_address + LAPIC_MMIO_LENGTH; + return addr >= apic->base_address && + addr < apic->base_address + LAPIC_MMIO_LENGTH; } static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, @@ -1345,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + memset(data, 0xff, len); + return 0; + } + kvm_lapic_reg_read(apic, offset, len, data); return 0; @@ -1904,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + return 0; + } + /* * APIC register must be aligned on 128-bits boundary. * 32/64/128 bits registers must be accessed thru 32 bits. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a282321329b5..d7e9bce6ff61 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -899,7 +899,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { /* * Make sure the write to vcpu->mode is not reordered in front of - * reads to sptes. If it does, kvm_commit_zap_page() can see us + * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. */ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); @@ -1853,11 +1853,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -5217,7 +5212,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = EMULTYPE_RETRY; + int r, emulation_type = 0; enum emulation_result er; bool direct = vcpu->arch.mmu.direct_map; @@ -5230,10 +5225,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_PF_EMULATE) { - emulation_type = 0; + if (r == RET_PF_EMULATE) goto emulate; - } } if (r == RET_PF_INVALID) { @@ -5260,8 +5253,19 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, return 1; } - if (mmio_info_in_cache(vcpu, cr2, direct)) - emulation_type = 0; + /* + * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still + * optimistically try to just unprotect the page and let the processor + * re-execute the instruction that caused the page fault. Do not allow + * retrying MMIO emulation, as it's not only pointless but could also + * cause us to enter an infinite loop because the processor will keep + * faulting on the non-existent MMIO address. Retrying an instruction + * from a nested guest is also pointless and dangerous as we are only + * explicitly shadowing L1's page tables, i.e. unprotecting something + * for L1 isn't going to magically fix whatever issue cause L2 to fail. + */ + if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. @@ -5413,7 +5417,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) { MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - kvm_init_mmu(vcpu, true); + /* + * kvm_mmu_setup() is called only on vCPU initialization. + * Therefore, no need to reset mmu roots as they are not yet + * initialized. + */ + kvm_init_mmu(vcpu, false); } static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6276140044d0..d96092b35936 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -776,7 +776,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (emulate_instruction(vcpu, EMULTYPE_SKIP) != + if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void) min_sev_asid = cpuid_edx(0x8000001F); /* Initialize SEV ASID bitmap */ - sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), - sizeof(unsigned long), GFP_KERNEL); + sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; @@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void) int cpu; if (svm_sev_enabled()) - kfree(sev_asid_bitmap); + bitmap_free(sev_asid_bitmap); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -2715,7 +2714,7 @@ static int gp_interception(struct vcpu_svm *svm) WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -2819,7 +2818,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -3861,7 +3860,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3869,13 +3868,13 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } static int rsm_interception(struct vcpu_svm *svm) { - return x86_emulate_instruction(&svm->vcpu, 0, 0, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, + rsm_ins_bytes, 2) == EMULATE_DONE; } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4700,7 +4699,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); } return ret; @@ -6747,7 +6746,7 @@ e_free: static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) { unsigned long vaddr, vaddr_end, next_vaddr; - unsigned long dst_vaddr, dst_vaddr_end; + unsigned long dst_vaddr; struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; @@ -6763,7 +6762,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) size = debug.len; vaddr_end = vaddr + size; dst_vaddr = debug.dst_uaddr; - dst_vaddr_end = dst_vaddr + size; for (; vaddr < vaddr_end; vaddr = next_vaddr) { int len, s_off, d_off; @@ -7150,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .check_intercept = svm_check_intercept, .handle_external_intr = svm_handle_external_intr, + .request_immediate_exit = __kvm_request_immediate_exit, + .sched_in = svm_sched_in, .pmu_ops = &amd_pmu_ops, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1d26f3c4985b..06412ba46aa3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -397,6 +397,7 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + bool hv_timer_armed; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; @@ -1019,6 +1020,8 @@ struct vcpu_vmx { int ple_window; bool ple_window_dirty; + bool req_immediate_exit; + /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; + vmx->req_immediate_exit = false; + if (vmx->loaded_cpu_state) return; @@ -5393,9 +5398,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) * To use VMXON (and later other VMX instructions), a guest * must first be able to turn on cr4.VMXE (see handle_vmon()). * So basically the check on whether to allow nested VMX - * is here. + * is here. We operate under the default treatment of SMM, + * so VMX cannot be enabled under SMM. */ - if (!nested_vmx_allowed(vcpu)) + if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) return 1; } @@ -6183,6 +6189,27 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic_page; + u32 vppr; + int rvi; + + if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || + !nested_cpu_has_vid(get_vmcs12(vcpu)) || + WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) + return false; + + rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff; + + vapic_page = kmap(vmx->nested.virtual_apic_page); + vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); + kunmap(vmx->nested.virtual_apic_page); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, bool nested) { @@ -6983,7 +7010,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -7054,7 +7081,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -7157,7 +7184,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -7231,7 +7258,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_cr(struct kvm_vcpu *vcpu) @@ -7480,7 +7507,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -7547,7 +7574,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -7704,8 +7731,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return kvm_skip_emulated_instruction(vcpu); else - return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, - NULL, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == + EMULATE_DONE; } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -7748,7 +7775,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = emulate_instruction(vcpu, 0); + err = kvm_emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -7966,6 +7993,9 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + if (!cpu_has_vmx_preemption_timer()) + kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { u64 vmx_msr; @@ -9208,7 +9238,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - kvm_lapic_expired_hv_timer(vcpu); + if (!to_vmx(vcpu)->req_immediate_exit) + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -10595,24 +10626,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val); + if (!vmx->loaded_vmcs->hv_timer_armed) + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = true; +} + +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->hv_deadline_tsc == -1) + if (vmx->req_immediate_exit) { + vmx_arm_hv_timer(vmx, 0); return; + } - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* sure to be 32 bit only because checked on set_hv_timer */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; + if (vmx->hv_deadline_tsc != -1) { + tscl = rdtsc(); + if (vmx->hv_deadline_tsc > tscl) + /* set_hv_timer ensures the delta fits in 32-bits */ + delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> + cpu_preemption_timer_multi); + else + delta_tsc = 0; + + vmx_arm_hv_timer(vmx, delta_tsc); + return; + } - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); + if (vmx->loaded_vmcs->hv_timer_armed) + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = false; } static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -10672,7 +10722,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); - vmx_arm_hv_timer(vcpu); + vmx_update_hv_timer(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -11427,16 +11477,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vcpu->arch.virtual_tsc_khz == 0) - return; - - /* Make sure short timeouts reliably trigger an immediate vmexit. - * hrtimer_start does not guarantee this. */ - if (preemption_timeout <= 1) { + /* + * A timer value of zero is architecturally guaranteed to cause + * a VMExit prior to executing any instructions in the guest. + */ + if (preemption_timeout == 0) { vmx_preemption_timer_fn(&vmx->nested.preemption_timer); return; } + if (vcpu->arch.virtual_tsc_khz == 0) + return; + preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); @@ -11646,11 +11698,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 15:8 should be zero in posted_intr_nv, * the descriptor address has been already checked * in nested_get_vmcs12_pages. + * + * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && (!nested_cpu_has_vid(vmcs12) || !nested_exit_intr_ack_set(vcpu) || - vmcs12->posted_intr_nv & 0xff00)) + (vmcs12->posted_intr_nv & 0xff00) || + (vmcs12->posted_intr_desc_addr & 0x3f) || + (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -12076,11 +12132,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control = vmcs12->pin_based_vm_exec_control; - /* Preemption timer setting is only taken from vmcs01. */ - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + /* Preemption timer setting is computed directly in vmx_vcpu_run. */ exec_control |= vmcs_config.pin_based_exec_ctrl; - if (vmx->hv_deadline_tsc == -1) - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + vmx->loaded_vmcs->hv_timer_armed = false; /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { @@ -12318,6 +12373,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -12537,8 +12595,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; + u32 vmcs01_cpu_exec_ctrl; int r = 0; + vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -12575,6 +12636,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) } /* + * If L1 had a pending IRQ/NMI until it executed + * VMLAUNCH/VMRESUME which wasn't delivered because it was + * disallowed (e.g. interrupts disabled), L0 needs to + * evaluate if this pending event should cause an exit from L2 + * to L1 or delivered directly to L2 (e.g. In case L1 don't + * intercept EXTERNAL_INTERRUPT). + * + * Usually this would be handled by L0 requesting a + * IRQ/NMI window by setting VMCS accordingly. However, + * this setting was done on VMCS01 and now VMCS02 is active + * instead. Thus, we force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ + if (vmcs01_cpu_exec_ctrl & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -12841,6 +12921,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } +static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + to_vmx(vcpu)->req_immediate_exit = true; +} + static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) { ktime_t remaining = @@ -13231,12 +13316,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (vmx->hv_deadline_tsc == -1) - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - else - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -13440,18 +13520,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->hv_deadline_tsc = -1; - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif @@ -13932,6 +14006,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; + /* + * SMM temporarily disables VMX, so we cannot be in guest mode, + * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags + * must be zero. + */ + if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags) + return -EINVAL; + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; @@ -13988,9 +14070,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, check_vmentry_postreqs(vcpu, vmcs12, &exit_qual)) return -EINVAL; - if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING) - vmx->nested.nested_run_pending = 1; - vmx->nested.dirty_vmcs12 = true; ret = enter_vmx_non_root_mode(vcpu, NULL); if (ret) @@ -14078,6 +14157,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, @@ -14111,6 +14191,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, + .request_immediate_exit = vmx_request_immediate_exit, .sched_in = vmx_sched_in, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 506bd2b4b8bb..edbf00ec56b3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated || - data & ~MSR_PLATFORM_INFO_CPUID_FAULT || (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && cpuid_fault_enabled(vcpu))) return 1; @@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: + if (!msr_info->host_initiated && + !vcpu->kvm->arch.guest_can_read_msr_platform_info) + return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: @@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_GET_MSR_FEATURES: + case KVM_CAP_MSR_PLATFORM_INFO: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); + r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) - return -EFAULT; + break; r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) - return r; + break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) - return -EFAULT; - return -E2BIG; + r = -EFAULT; + else + r = -E2BIG; + break; } + r = 0; break; } @@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!kvm_x86_ops->set_nested_state) break; + r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) - return -EFAULT; + break; + r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) - return -EINVAL; + break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE)) - return -EINVAL; + break; /* nested_run_pending implies guest_mode. */ if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING) - return -EINVAL; + break; r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); break; @@ -4350,6 +4359,10 @@ split_irqchip_unlock: kvm->arch.pause_in_guest = true; r = 0; break; + case KVM_CAP_MSR_PLATFORM_INFO: + kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -4987,7 +5000,7 @@ int handle_ud(struct kvm_vcpu *vcpu) emul_type = 0; } - er = emulate_instruction(vcpu, emul_type); + er = kvm_emulate_instruction(vcpu, emul_type); if (er == EMULATE_USER_EXIT) return 0; if (er != EMULATE_DONE) @@ -5870,7 +5883,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, gpa_t gpa = cr2; kvm_pfn_t pfn; - if (emulation_type & EMULTYPE_NO_REEXECUTE) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (!vcpu->arch.mmu.direct_map) { @@ -5958,7 +5974,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6276,7 +6295,19 @@ restart: return r; } -EXPORT_SYMBOL_GPL(x86_emulate_instruction); + +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) +{ + return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction); + +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len) +{ + return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) @@ -7343,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + smp_send_reschedule(vcpu->cpu); +} +EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); + /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7547,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - smp_send_reschedule(vcpu->cpu); + kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -7734,7 +7771,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r != EMULATE_DONE) return 0; @@ -7811,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +/* Swap (qemu) user FPU context for the guest FPU context. */ +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); + preempt_enable(); + trace_kvm_fpu(1); +} + +/* When vcpu_run ends, restore user space FPU context. */ +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); + ++vcpu->stat.fpu_reload; + trace_kvm_fpu(0); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -8159,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8388,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -/* Swap (qemu) user FPU context for the guest FPU context. */ -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); - trace_kvm_fpu(1); -} - -/* When vcpu_run ends, restore user space FPU context. */ -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); - preempt_enable(); - ++vcpu->stat.fpu_reload; - trace_kvm_fpu(0); -} - void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; @@ -8834,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); + kvm->arch.guest_can_read_msr_platform_info = true; + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); @@ -9182,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_page_track_flush_slot(kvm, slot); } +static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + return (is_guest_mode(vcpu) && + kvm_x86_ops->guest_apic_has_interrupt && + kvm_x86_ops->guest_apic_has_interrupt(vcpu)); +} + static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) @@ -9206,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)) + (kvm_cpu_has_interrupt(vcpu) || + kvm_guest_apic_has_interrupt(vcpu))) return true; if (kvm_hv_has_stimer_pending(vcpu)) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 257f27620bc2..67b9568613f3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -274,6 +274,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); +int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, + int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index c8c6ad0d58b8..3f435d7fca5e 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -7,6 +7,8 @@ #include <linux/uaccess.h> #include <linux/export.h> +#include <asm/tlbflush.h> + /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. @@ -19,6 +21,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) if (__range_not_ok(from, n, TASK_SIZE)) return n; + if (!nmi_uaccess_okay()) + return n; + /* * Even though this function is typically called from NMI/IRQ context * disable pagefaults so that its behaviour is consistent even when diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b9123c497e0a..47bebfe6efa7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -837,7 +837,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, printk(KERN_CONT "\n"); - show_opcodes((u8 *)regs->ip, loglvl); + show_opcodes(regs, loglvl); } static void diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7a8fc26c1115..faca978ebf9d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end) set_memory_np_noalias(begin_ul, len_pages); } +void __weak mem_encrypt_free_decrypted_mem(void) { } + void __ref free_initmem(void) { e820__reallocate_tables(); + mem_encrypt_free_decrypted_mem(); + free_kernel_image_pages(&__init_begin, &__init_end); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index b2de398d1fd3..006f373f54ab 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -348,6 +348,30 @@ bool sev_active(void) EXPORT_SYMBOL(sev_active); /* Architecture __weak replacement functions */ +void __init mem_encrypt_free_decrypted_mem(void) +{ + unsigned long vaddr, vaddr_end, npages; + int r; + + vaddr = (unsigned long)__start_bss_decrypted_unused; + vaddr_end = (unsigned long)__end_bss_decrypted; + npages = (vaddr_end - vaddr) >> PAGE_SHIFT; + + /* + * The unused memory range was mapped decrypted, change the encryption + * attribute from decrypted to encrypted before freeing it. + */ + if (mem_encrypt_active()) { + r = set_memory_encrypted(vaddr, npages); + if (r) { + pr_warn("failed to free unused decrypted pages\n"); + return; + } + } + + free_init_pages("unused decrypted", vaddr, vaddr_end); +} + void __init mem_encrypt_init(void) { if (!sme_me_mask) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 8d6c34fe49be..51a5a69ecac9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1420,6 +1420,29 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) return 0; } +/* + * Machine check recovery code needs to change cache mode of poisoned + * pages to UC to avoid speculative access logging another error. But + * passing the address of the 1:1 mapping to set_memory_uc() is a fine + * way to encourage a speculative access. So we cheat and flip the top + * bit of the address. This works fine for the code that updates the + * page tables. But at the end of the process we need to flush the cache + * and the non-canonical address causes a #GP fault when used by the + * CLFLUSH instruction. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long make_addr_canonical_again(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + + static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, @@ -1465,7 +1488,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * Save address for cache flush. *addr is modified in the call * to __change_page_attr_set_clr() below. */ - baddr = *addr; + baddr = make_addr_canonical_again(*addr); } /* Must avoid aliasing mappings in the highmem code */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e848a4811785..089e78c4effd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - *pgdp = native_make_pgd(0); + pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, @@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); +#ifdef CONFIG_X86_64 + /* + * Ensure that the static initial page tables are covering the + * fixmap completely. + */ + BUILD_BUG_ON(__end_of_permanent_fixed_addresses > + (FIXMAP_PMD_NUM * PTRS_PER_PTE)); +#endif + if (idx >= __end_of_fixed_addresses) { BUG(); return; diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 31341ae7309f..c1fc1ae6b429 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -248,7 +248,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) * * Returns a pointer to a PTE on success, or NULL on failure. */ -static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) +static pte_t *pti_user_pagetable_walk_pte(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 9517d1b2a281..e96b99eb800c 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -305,6 +305,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + /* Let nmi_uaccess_okay() know that we're changing CR3. */ + this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); + barrier(); + if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); @@ -335,6 +339,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (next != &init_mm) this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + /* Make sure we write CR3 before loaded_mm. */ + barrier(); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 324b93328b37..9959657127f4 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -85,12 +85,7 @@ pgd_t * __init efi_call_phys_prolog(void) void __init efi_call_phys_epilog(pgd_t *save_pgd) { - struct desc_ptr gdt_descr; - - gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0); - gdt_descr.size = GDT_SIZE - 1; - load_gdt(&gdt_descr); - + load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 45b700ac5fe7..dd461c0167ef 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -435,14 +435,13 @@ static void xen_set_pud(pud_t *ptr, pud_t val) static void xen_set_pte_atomic(pte_t *ptep, pte_t pte) { trace_xen_mmu_set_pte_atomic(ptep, pte); - set_64bit((u64 *)ptep, native_pte_val(pte)); + __xen_set_pte(ptep, pte); } static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { trace_xen_mmu_pte_clear(mm, addr, ptep); - if (!xen_batched_set_pte(ptep, native_make_pte(0))) - native_pte_clear(mm, addr, ptep); + __xen_set_pte(ptep, native_make_pte(0)); } static void xen_pmd_clear(pmd_t *pmdp) @@ -1570,7 +1569,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & pte_val_ma(pte)); #endif - native_set_pte(ptep, pte); + __xen_set_pte(ptep, pte); } /* Early in boot, while setting up the initial pagetable, assume @@ -1908,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); - /* L3_k[511][506] -> level1_fixmap_pgt */ + /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */ convert_pfn_mfn(level2_fixmap_pgt); /* We get [511][511] and have Xen's version of level2_kernel_pgt */ @@ -1953,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + for (i = 0; i < FIXMAP_PMD_NUM; i++) { + set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE, + PAGE_KERNEL_RO); + } /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, @@ -2061,7 +2064,6 @@ void __init xen_relocate_p2m(void) pud_t *pud; pgd_t *pgd; unsigned long *new_p2m; - int save_pud; size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; @@ -2091,7 +2093,6 @@ void __init xen_relocate_p2m(void) pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); - save_pud = n_pud; for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { pud = early_memremap(pud_phys, PAGE_SIZE); clear_page(pud); diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 7d00d4ad44d4..95997e6c0696 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) { int err, ret = IRQ_NONE; - struct pt_regs regs; + struct pt_regs regs = {0}; const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); uint8_t xenpmu_flags = get_xenpmu_flags(); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 04d038f3b6fa..b9ad83a0ee5d 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,6 +4,7 @@ config ZONE_DMA config XTENSA def_bool y + select ARCH_HAS_SG_CHAIN select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_COHERENT_DMA_MMAP if !MMU diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile index 295c120ed099..d67e30faff9c 100644 --- a/arch/xtensa/Makefile +++ b/arch/xtensa/Makefile @@ -64,11 +64,7 @@ endif vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y)) plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y)) -ifeq ($(KBUILD_SRC),) -KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs)) -else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs)) -endif KBUILD_DEFCONFIG := iss_defconfig diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index f4bbb28026f8..58709e89a8ed 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -78,23 +78,28 @@ static struct notifier_block iss_panic_block = { void __init platform_setup(char **p_cmdline) { + static void *argv[COMMAND_LINE_SIZE / sizeof(void *)] __initdata; + static char cmdline[COMMAND_LINE_SIZE] __initdata; int argc = simc_argc(); int argv_size = simc_argv_size(); if (argc > 1) { - void **argv = alloc_bootmem(argv_size); - char *cmdline = alloc_bootmem(argv_size); - int i; + if (argv_size > sizeof(argv)) { + pr_err("%s: command line too long: argv_size = %d\n", + __func__, argv_size); + } else { + int i; - cmdline[0] = 0; - simc_argv((void *)argv); + cmdline[0] = 0; + simc_argv((void *)argv); - for (i = 1; i < argc; ++i) { - if (i > 1) - strcat(cmdline, " "); - strcat(cmdline, argv[i]); + for (i = 1; i < argc; ++i) { + if (i > 1) + strcat(cmdline, " "); + strcat(cmdline, argv[i]); + } + *p_cmdline = cmdline; } - *p_cmdline = cmdline; } atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block); |