diff options
Diffstat (limited to 'arch/x86')
230 files changed, 4281 insertions, 3116 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index aff152c87cf4..5a82bac5e0bc 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,6 +1,7 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +tools/insn_decoder_test purgatory/kexec-purgatory.c purgatory/purgatory.ro diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 63bf349b2b24..27fede438959 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -54,7 +54,6 @@ config X86 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 - select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_REFCOUNT @@ -83,6 +82,7 @@ config X86 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG select DCACHE_WORD_ACCESS + select DMA_DIRECT_OPS select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS @@ -393,17 +393,6 @@ config X86_FEATURE_NAMES If in doubt, say Y. -config X86_FAST_FEATURE_TESTS - bool "Fast CPU feature tests" if EMBEDDED - default y - ---help--- - Some fast-paths in the kernel depend on the capabilities of the CPU. - Say Y here for the kernel to patch in the appropriate code at runtime - based on the capabilities of the CPU. The infrastructure for patching - code at runtime takes up some additional space; space-constrained - embedded systems may wish to say N here to produce smaller, slightly - slower code. - config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) @@ -423,12 +412,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config X86_BIGSMP - bool "Support for big SMP systems with more than 8 CPUs" - depends on X86_32 && SMP - ---help--- - This option is needed for the systems that have more than 8 CPUs - config GOLDFISH def_bool y depends on X86_GOLDFISH @@ -436,6 +419,7 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" default y + select STACK_VALIDATION if HAVE_STACK_VALIDATION help Compile kernel with the retpoline compiler options to guard against kernel-to-user data leaks by avoiding speculative indirect @@ -460,6 +444,12 @@ config INTEL_RDT Say N if unsure. if X86_32 +config X86_BIGSMP + bool "Support for big SMP systems with more than 8 CPUs" + depends on SMP + ---help--- + This option is needed for the systems that have more than 8 CPUs + config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" default y @@ -690,6 +680,7 @@ config X86_SUPPORTS_MEMORY_FAILURE config STA2X11 bool "STA2X11 Companion Chip Support" depends on X86_32_NON_STANDARD && PCI + select ARCH_HAS_PHYS_TO_DMA select X86_DEV_DMA_OPS select X86_DMA_REMAP select SWIOTLB @@ -949,25 +940,66 @@ config MAXSMP Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. +# +# The maximum number of CPUs supported: +# +# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT, +# and which can be configured interactively in the +# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. +# +# The ranges are different on 32-bit and 64-bit kernels, depending on +# hardware capabilities and scalability features of the kernel. +# +# ( If MAXSMP is enabled we just use the highest possible value and disable +# interactive configuration. ) +# + +config NR_CPUS_RANGE_BEGIN + int + default NR_CPUS_RANGE_END if MAXSMP + default 1 if !SMP + default 2 + +config NR_CPUS_RANGE_END + int + depends on X86_32 + default 64 if SMP && X86_BIGSMP + default 8 if SMP && !X86_BIGSMP + default 1 if !SMP + +config NR_CPUS_RANGE_END + int + depends on X86_64 + default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK) + default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK) + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_32 + default 32 if X86_BIGSMP + default 8 if SMP + default 1 if !SMP + +config NR_CPUS_DEFAULT + int + depends on X86_64 + default 8192 if MAXSMP + default 64 if SMP + default 1 if !SMP + config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP - range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 64 if SMP && X86_32 && X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 - range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 - default "1" if !SMP - default "8192" if MAXSMP - default "32" if SMP && X86_BIGSMP - default "8" if SMP && X86_32 - default "64" if SMP + range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END + default NR_CPUS_DEFAULT ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. + This is purely to save memory: each supported CPU adds about 8KB + to the kernel image. config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" @@ -1363,7 +1395,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 + depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE ---help--- Select this if you have a 32-bit processor and more than 4 @@ -1430,6 +1462,8 @@ config X86_PAE config X86_5LEVEL bool "Enable 5-level page tables support" + select DYNAMIC_MEMORY_LAYOUT + select SPARSEMEM_VMEMMAP depends on X86_64 ---help--- 5-level paging enables access to larger address space: @@ -1438,8 +1472,8 @@ config X86_5LEVEL It will be supported by future Intel CPUs. - Note: a kernel with this option enabled can only be booted - on machines that support the feature. + A kernel with the option enabled can be booted on machines that + support 4- or 5-level paging. See Documentation/x86/x86_64/5level-paging.txt for more information. @@ -1564,10 +1598,6 @@ config ARCH_HAVE_MEMORY_PRESENT def_bool y depends on X86_32 && DISCONTIGMEM -config NEED_NODE_MEMMAP_SIZE - def_bool y - depends on X86_32 && (DISCONTIGMEM || SPARSEMEM) - config ARCH_FLATMEM_ENABLE def_bool y depends on X86_32 && !NUMA @@ -2143,10 +2173,17 @@ config PHYSICAL_ALIGN Don't change this unless you know what you are doing. +config DYNAMIC_MEMORY_LAYOUT + bool + ---help--- + This option makes base addresses of vmalloc and vmemmap as well as + __PAGE_OFFSET movable during boot. + config RANDOMIZE_MEMORY bool "Randomize the kernel memory sections" depends on X86_64 depends on RANDOMIZE_BASE + select DYNAMIC_MEMORY_LAYOUT default RANDOMIZE_BASE ---help--- Randomizes the base virtual address of kernel memory sections @@ -2265,7 +2302,7 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[native|emulate|none]. + line parameter vsyscall=[emulate|none]. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2273,15 +2310,6 @@ choice If unsure, select "Emulate". - config LEGACY_VSYSCALL_NATIVE - bool "Native" - help - Actual executable code is located in the fixed vsyscall - address mapping, implementing time() efficiently. Since - this makes the mapping executable, it can be used during - security vulnerability exploitation (traditionally as - ROP gadgets). This configuration is not recommended. - config LEGACY_VSYSCALL_EMULATE bool "Emulate" help @@ -2599,8 +2627,10 @@ config PCI_DIRECT depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC || PCI_GOMMCONFIG)) config PCI_MMCONFIG - def_bool y - depends on X86_32 && PCI && (ACPI || SFI) && (PCI_GOMMCONFIG || PCI_GOANY) + bool "Support mmconfig PCI config space access" if X86_64 + default y + depends on PCI && (ACPI || SFI || JAILHOUSE_GUEST) + depends on X86_64 || (PCI_GOANY || PCI_GOMMCONFIG) config PCI_OLPC def_bool y @@ -2615,9 +2645,9 @@ config PCI_DOMAINS def_bool y depends on PCI -config PCI_MMCONFIG - bool "Support mmconfig PCI config space access" - depends on X86_64 && PCI && ACPI +config MMCONF_FAM10H + def_bool y + depends on X86_64 && PCI_MMCONFIG && ACPI config PCI_CNB20LE_QUIRK bool "Read CNB20LE Host Bridge Windows" if EXPERT diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 65a9a4716e34..638411f22267 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -315,19 +315,6 @@ config X86_L1_CACHE_SHIFT default "4" if MELAN || M486 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX -config X86_PPRO_FENCE - bool "PentiumPro memory ordering errata workaround" - depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1 - ---help--- - Old PentiumPro multiprocessor systems had errata that could cause - memory operations to violate the x86 ordering standard in rare cases. - Enabling this option will attempt to work around some (but not all) - occurrences of this problem, at the cost of much heavier spinlock and - memory barrier operations. - - If unsure, say n here. Even distro kernels should think twice before - enabling this: there are few systems, and an unlikely bug. - config X86_F00F_BUG def_bool y depends on M586MMX || M586TSC || M586 || M486 @@ -374,7 +361,7 @@ config X86_TSC config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM + depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 # this should be set for all -march=.. options where the compiler # generates cmov. @@ -385,7 +372,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && X86_P6_NOP + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index fad55160dcb9..60135cbd905c 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -31,8 +31,7 @@ endif CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS)) -REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ - -DDISABLE_BRANCH_PROFILING \ +REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse @@ -181,6 +180,10 @@ 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 @@ -223,6 +226,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) LDFLAGS := -m elf_$(UTS_MACHINE) +# +# The 64-bit kernel must be aligned to 2MB. Pass -z max-page-size=0x200000 to +# the linker to force 2MB page size regardless of the default page size used +# by the linker. +# +ifdef CONFIG_X86_64 +LDFLAGS += $(call ld-option, -z max-page-size=0x200000) +endif + # Speed up the build KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release @@ -232,10 +244,9 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE - RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) - ifneq ($(RETPOLINE_CFLAGS),) - KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE - endif +ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE +endif endif archscripts: scripts_basic diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f25e1530e064..fa42f895fdde 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -26,7 +26,7 @@ KCOV_INSTRUMENT := n targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 -KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ -O2 +KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 @@ -78,7 +78,7 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 - vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o + vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o endif diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 353e20c3f114..47d3efff6805 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -421,9 +421,10 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) } } +static const efi_char16_t apple[] = L"Apple"; + static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t const apple[] = { 'A', 'p', 'p', 'l', 'e', 0 }; efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) efi_table_attr(efi_system_table, fw_vendor, sys_table); @@ -439,7 +440,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) struct efi_uga_draw_protocol *uga = NULL, *first_uga; efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; - u32 *handles = (u32 *)uga_handle;; + u32 *handles = (u32 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; @@ -484,7 +485,7 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height) struct efi_uga_draw_protocol *uga = NULL, *first_uga; efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID; unsigned long nr_ugas; - u64 *handles = (u64 *)uga_handle;; + u64 *handles = (u64 *)uga_handle; efi_status_t status = EFI_INVALID_PARAMETER; int i; diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index fc313e29fe2c..fca012baba19 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -33,6 +33,7 @@ #include <asm/processor-flags.h> #include <asm/asm-offsets.h> #include <asm/bootparam.h> +#include "pgtable.h" /* * Locally defined symbols should be marked hidden: @@ -304,55 +305,77 @@ ENTRY(startup_64) /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp -#ifdef CONFIG_X86_5LEVEL /* - * Check if we need to enable 5-level paging. - * RSI holds real mode data and need to be preserved across - * a function call. + * At this point we are in long mode with 4-level paging enabled, + * but we might want to enable 5-level paging or vice versa. + * + * The problem is that we cannot do it directly. Setting or clearing + * CR4.LA57 in long mode would trigger #GP. So we need to switch off + * long mode and paging first. + * + * We also need a trampoline in lower memory to switch over from + * 4- to 5-level paging for cases when the bootloader puts the kernel + * above 4G, but didn't enable 5-level paging for us. + * + * The same trampoline can be used to switch from 5- to 4-level paging + * mode, like when starting 4-level paging kernel via kexec() when + * original kernel worked in 5-level paging mode. + * + * For the trampoline, we need the top page table to reside in lower + * memory as we don't have a way to load 64-bit values into CR3 in + * 32-bit mode. + * + * We go though the trampoline even if we don't have to: if we're + * already in a desired paging mode. This way the trampoline code gets + * tested on every boot. */ - pushq %rsi - call l5_paging_required - popq %rsi - /* If l5_paging_required() returned zero, we're done here. */ - cmpq $0, %rax - je lvl5 + /* Make sure we have GDT with 32-bit code segment */ + leaq gdt(%rip), %rax + movq %rax, gdt64+2(%rip) + lgdt gdt64(%rip) /* - * At this point we are in long mode with 4-level paging enabled, - * but we want to enable 5-level paging. + * paging_prepare() sets up the trampoline and checks if we need to + * enable 5-level paging. * - * The problem is that we cannot do it directly. Setting LA57 in - * long mode would trigger #GP. So we need to switch off long mode - * first. + * Address of the trampoline is returned in RAX. + * Non zero RDX on return means we need to enable 5-level paging. * - * NOTE: This is not going to work if bootloader put us above 4G - * limit. - * - * The first step is go into compatibility mode. + * RSI holds real mode data and needs to be preserved across + * this function call. */ + pushq %rsi + call paging_prepare + popq %rsi - /* Clear additional page table */ - leaq lvl5_pgtable(%rbx), %rdi - xorq %rax, %rax - movq $(PAGE_SIZE/8), %rcx - rep stosq + /* Save the trampoline address in RCX */ + movq %rax, %rcx /* - * Setup current CR3 as the first and only entry in a new top level - * page table. + * Load the address of trampoline_return() into RDI. + * It will be used by the trampoline to return to the main code. */ - movq %cr3, %rdi - leaq 0x7 (%rdi), %rax - movq %rax, lvl5_pgtable(%rbx) + leaq trampoline_return(%rip), %rdi /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ pushq $__KERNEL32_CS - leaq compatible_mode(%rip), %rax + leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax pushq %rax lretq -lvl5: -#endif +trampoline_return: + /* Restore the stack, the 32-bit trampoline uses its own stack */ + leaq boot_stack_end(%rbx), %rsp + + /* + * cleanup_trampoline() would restore trampoline memory. + * + * RSI holds real mode data and needs to be preserved across + * this function call. + */ + pushq %rsi + call cleanup_trampoline + popq %rsi /* Zero EFLAGS */ pushq $0 @@ -490,46 +513,82 @@ relocated: jmp *%rax .code32 -#ifdef CONFIG_X86_5LEVEL -compatible_mode: - /* Setup data and stack segments */ +/* + * This is the 32-bit trampoline that will be copied over to low memory. + * + * RDI contains the return address (might be above 4G). + * ECX contains the base address of the trampoline memory. + * Non zero RDX on return means we need to enable 5-level paging. + */ +ENTRY(trampoline_32bit_src) + /* Set up data and stack segments */ movl $__KERNEL_DS, %eax movl %eax, %ds movl %eax, %ss + /* Set up new stack */ + leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp + /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 - /* Point CR3 to 5-level paging */ - leal lvl5_pgtable(%ebx), %eax - movl %eax, %cr3 + /* Check what paging mode we want to be in after the trampoline */ + cmpl $0, %edx + jz 1f - /* Enable PAE and LA57 mode */ + /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ + movl %cr4, %eax + testl $X86_CR4_LA57, %eax + jnz 3f + jmp 2f +1: + /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ movl %cr4, %eax - orl $(X86_CR4_PAE | X86_CR4_LA57), %eax + testl $X86_CR4_LA57, %eax + jz 3f +2: + /* Point CR3 to the trampoline's new top level page table */ + leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax + movl %eax, %cr3 +3: + /* Enable PAE and LA57 (if required) paging modes */ + movl $X86_CR4_PAE, %eax + cmpl $0, %edx + jz 1f + orl $X86_CR4_LA57, %eax +1: movl %eax, %cr4 - /* Calculate address we are running at */ - call 1f -1: popl %edi - subl $1b, %edi + /* Calculate address of paging_enabled() once we are executing in the trampoline */ + leal paging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax - /* Prepare stack for far return to Long Mode */ + /* Prepare the stack for far return to Long Mode */ pushl $__KERNEL_CS - leal lvl5(%edi), %eax - push %eax + pushl %eax - /* Enable paging back */ + /* Enable paging again */ movl $(X86_CR0_PG | X86_CR0_PE), %eax movl %eax, %cr0 lret -#endif + .code64 +paging_enabled: + /* Return from the trampoline */ + jmp *%rdi + + /* + * The trampoline code has a size limit. + * Make sure we fail to compile if the trampoline code grows + * beyond TRAMPOLINE_32BIT_CODE_SIZE bytes. + */ + .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE + + .code32 no_longmode: - /* This isn't an x86-64 CPU so hang */ + /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: hlt jmp 1b @@ -537,6 +596,11 @@ no_longmode: #include "../../kernel/verify_cpu.S" .data +gdt64: + .word gdt_end - gdt + .long 0 + .word 0 + .quad 0 gdt: .word gdt_end - gdt .long gdt @@ -585,7 +649,3 @@ boot_stack_end: .balign 4096 pgtable: .fill BOOT_PGT_SIZE, 1, 0 -#ifdef CONFIG_X86_5LEVEL -lvl5_pgtable: - .fill PAGE_SIZE, 1, 0 -#endif diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 8199a6187251..66e42a098d70 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -46,6 +46,12 @@ #define STATIC #include <linux/decompress/mm.h> +#ifdef CONFIG_X86_5LEVEL +unsigned int pgtable_l5_enabled __ro_after_init; +unsigned int pgdir_shift __ro_after_init = 39; +unsigned int ptrs_per_p4d __ro_after_init = 1; +#endif + extern unsigned long get_cmd_line_ptr(void); /* Simplified build-specific string for starting entropy. */ @@ -723,6 +729,14 @@ void choose_random_location(unsigned long input, return; } +#ifdef CONFIG_X86_5LEVEL + if (__read_cr4() & X86_CR4_LA57) { + pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; + } +#endif + boot_params->hdr.loadflags |= KASLR_FLAG; /* Prepare to add new identity pagetables on demand. */ diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/kaslr_64.c index b5e5e02f8cde..522d11431433 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/kaslr_64.c @@ -16,13 +16,6 @@ #define __pa(x) ((unsigned long)(x)) #define __va(x) ((void *)((unsigned long)(x))) -/* - * The pgtable.h and mm/ident_map.c includes make use of the SME related - * information which is not used in the compressed image support. Un-define - * the SME support to avoid any compile and link errors. - */ -#undef CONFIG_AMD_MEM_ENCRYPT - /* No PAGE_TABLE_ISOLATION support needed either: */ #undef CONFIG_PAGE_TABLE_ISOLATION @@ -85,13 +78,14 @@ static struct x86_mapping_info mapping_info; /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { - unsigned long sev_me_mask = get_sev_encryption_mask(); + /* If running as an SEV guest, the encryption mask is required. */ + set_sev_encryption_mask(); /* Init mapping_info with run-time function/buffer pointers. */ mapping_info.alloc_pgt_page = alloc_pgt_page; mapping_info.context = &pgt_data; - mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sev_me_mask; - mapping_info.kernpg_flag = _KERNPG_TABLE | sev_me_mask; + mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask; + mapping_info.kernpg_flag = _KERNPG_TABLE; /* * It should be impossible for this not to already be true, diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index 54f5f6625a73..eaa843a52907 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -88,9 +88,7 @@ ENTRY(get_sev_encryption_bit) ENDPROC(get_sev_encryption_bit) .code64 -ENTRY(get_sev_encryption_mask) - xor %rax, %rax - +ENTRY(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp push %rdx @@ -101,9 +99,7 @@ ENTRY(get_sev_encryption_mask) testl %eax, %eax jz .Lno_sev_mask - xor %rdx, %rdx - bts %rax, %rdx /* Create the encryption mask */ - mov %rdx, %rax /* ... and return it */ + bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -112,9 +108,16 @@ ENTRY(get_sev_encryption_mask) pop %rbp #endif + xor %rax, %rax ret -ENDPROC(get_sev_encryption_mask) +ENDPROC(set_sev_encryption_mask) .data enc_bit: .int 0xffffffff + +#ifdef CONFIG_AMD_MEM_ENCRYPT + .balign 8 +GLOBAL(sme_me_mask) + .quad 0 +#endif diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 98761a1576ce..8dd1d5ccae58 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -14,6 +14,7 @@ #include "misc.h" #include "error.h" +#include "pgtable.h" #include "../string.h" #include "../voffset.h" @@ -169,16 +170,6 @@ void __puthex(unsigned long value) } } -static bool l5_supported(void) -{ - /* Check if leaf 7 is supported. */ - if (native_cpuid_eax(0) < 7) - return 0; - - /* Check if la57 is supported. */ - return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)); -} - #if CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) @@ -309,6 +300,10 @@ static void parse_elf(void *output) switch (phdr->p_type) { case PT_LOAD: +#ifdef CONFIG_X86_64 + if ((phdr->p_align % 0x200000) != 0) + error("Alignment of LOAD segment isn't multiple of 2MB"); +#endif #ifdef CONFIG_RELOCATABLE dest = output; dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR); @@ -372,12 +367,6 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, console_init(); debug_putstr("early console in extract_kernel\n"); - if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) { - error("This linux kernel as configured requires 5-level paging\n" - "This CPU does not support the required 'cr4.la57' feature\n" - "Unable to boot - please use a kernel appropriate for your CPU\n"); - } - free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; @@ -388,6 +377,11 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, debug_putaddr(output_len); debug_putaddr(kernel_total_size); +#ifdef CONFIG_X86_64 + /* Report address of 32-bit trampoline */ + debug_putaddr(trampoline_32bit); +#endif + /* * The memory hole needed for the kernel is the larger of either * the entire decompressed kernel plus relocation table, or the diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 9d323dc6b159..9e11be4cae19 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -12,6 +12,11 @@ #undef CONFIG_PARAVIRT_SPINLOCKS #undef CONFIG_KASAN +#ifdef CONFIG_X86_5LEVEL +/* cpu_feature_enabled() cannot be used that early */ +#define pgtable_l5_enabled __pgtable_l5_enabled +#endif + #include <linux/linkage.h> #include <linux/screen_info.h> #include <linux/elf.h> @@ -109,6 +114,6 @@ static inline void console_init(void) { } #endif -unsigned long get_sev_encryption_mask(void); +void set_sev_encryption_mask(void); #endif diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h new file mode 100644 index 000000000000..91f75638f6e6 --- /dev/null +++ b/arch/x86/boot/compressed/pgtable.h @@ -0,0 +1,20 @@ +#ifndef BOOT_COMPRESSED_PAGETABLE_H +#define BOOT_COMPRESSED_PAGETABLE_H + +#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE) + +#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 + +#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE +#define TRAMPOLINE_32BIT_CODE_SIZE 0x60 + +#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE + +#ifndef __ASSEMBLER__ + +extern unsigned long *trampoline_32bit; + +extern void trampoline_32bit_src(void *return_ptr); + +#endif /* __ASSEMBLER__ */ +#endif /* BOOT_COMPRESSED_PAGETABLE_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index b4469a37e9a1..32af1cbcd903 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,4 +1,6 @@ #include <asm/processor.h> +#include "pgtable.h" +#include "../string.h" /* * __force_order is used by special_insns.h asm code to force instruction @@ -9,20 +11,144 @@ */ unsigned long __force_order; -int l5_paging_required(void) +#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */ +#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */ + +struct paging_config { + unsigned long trampoline_start; + unsigned long l5_required; +}; + +/* Buffer to preserve trampoline memory */ +static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; + +/* + * The page table is going to be used instead of page table in the trampoline + * memory. + * + * It must not be in BSS as BSS is cleared after cleanup_trampoline(). + */ +static char top_pgtable[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data); + +/* + * Trampoline address will be printed by extract_kernel() for debugging + * purposes. + * + * Avoid putting the pointer into .bss as it will be cleared between + * paging_prepare() and extract_kernel(). + */ +unsigned long *trampoline_32bit __section(.data); + +struct paging_config paging_prepare(void) { - /* Check if leaf 7 is supported. */ + struct paging_config paging_config = {}; + unsigned long bios_start, ebda_start; + + /* + * Check if LA57 is desired and supported. + * + * There are two parts to the check: + * - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y + * - if the machine supports 5-level paging: + * + CPUID leaf 7 is supported + * + the leaf has the feature bit set + * + * That's substitute for boot_cpu_has() in early boot code. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL) && + native_cpuid_eax(0) >= 7 && + (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) { + paging_config.l5_required = 1; + } + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; - if (native_cpuid_eax(0) < 7) - return 0; + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + /* Place the trampoline just below the end of low memory, aligned to 4k */ + paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; + paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + + trampoline_32bit = (unsigned long *)paging_config.trampoline_start; + + /* Preserve trampoline memory */ + memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE); + + /* Clear trampoline memory first */ + memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE); + + /* Copy trampoline code in place */ + memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), + &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE); + + /* + * The code below prepares page table in trampoline memory. + * + * The new page table will be used by trampoline code for switching + * from 4- to 5-level paging or vice versa. + * + * If switching is not required, the page table is unused: trampoline + * code wouldn't touch CR3. + */ + + /* + * We are not going to use the page table in trampoline memory if we + * are already in the desired paging mode. + */ + if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57)) + goto out; + + if (paging_config.l5_required) { + /* + * For 4- to 5-level paging transition, set up current CR3 as + * the first and the only entry in a new top-level page table. + */ + trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC; + } else { + unsigned long src; + + /* + * For 5- to 4-level paging transition, copy page table pointed + * by first entry in the current top-level page table as our + * new top-level page table. + * + * We cannot just point to the page table from trampoline as it + * may be above 4G. + */ + src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; + memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long), + (void *)src, PAGE_SIZE); + } + +out: + return paging_config; +} + +void cleanup_trampoline(void) +{ + void *trampoline_pgtable; - /* Check if la57 is supported. */ - if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) - return 0; + trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET; - /* Check if 5-level paging has already been enabled. */ - if (native_read_cr4() & X86_CR4_LA57) - return 0; + /* + * Move the top level page table out of trampoline memory, + * if it's there. + */ + if ((void *)__native_read_cr3() == trampoline_pgtable) { + memcpy(top_pgtable, trampoline_pgtable, PAGE_SIZE); + native_write_cr3((unsigned long)top_pgtable); + } - return 1; + /* Restore trampoline memory */ + memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE); } diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3f48f695d5e6..be63330c5511 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,80 +97,78 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 - .macro ALLOC_PT_GPREGS_ON_STACK - addq $-(15*8), %rsp - .endm - - .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 - .if \r11 - movq %r11, 6*8+\offset(%rsp) - .endif - .if \r8910 - movq %r10, 7*8+\offset(%rsp) - movq %r9, 8*8+\offset(%rsp) - movq %r8, 9*8+\offset(%rsp) - .endif - .if \rax - movq %rax, 10*8+\offset(%rsp) +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 + /* + * Push registers and sanitize registers of values that a + * speculation attack might otherwise want to exploit. The + * lower registers are likely clobbered well before they + * could be put to use in a speculative execution gadget. + * Interleave XOR with PUSH for better uop scheduling: + */ + .if \save_ret + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ + movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */ + .else + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ .endif - .if \rcx - movq %rcx, 11*8+\offset(%rsp) + pushq \rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq \rax /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + xorl %r8d, %r8d /* nospec r8 */ + pushq %r9 /* pt_regs->r9 */ + xorl %r9d, %r9d /* nospec r9 */ + pushq %r10 /* pt_regs->r10 */ + xorl %r10d, %r10d /* nospec r10 */ + pushq %r11 /* pt_regs->r11 */ + xorl %r11d, %r11d /* nospec r11*/ + pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx*/ + pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp*/ + pushq %r12 /* pt_regs->r12 */ + xorl %r12d, %r12d /* nospec r12*/ + pushq %r13 /* pt_regs->r13 */ + xorl %r13d, %r13d /* nospec r13*/ + pushq %r14 /* pt_regs->r14 */ + xorl %r14d, %r14d /* nospec r14*/ + pushq %r15 /* pt_regs->r15 */ + xorl %r15d, %r15d /* nospec r15*/ + UNWIND_HINT_REGS + .if \save_ret + pushq %rsi /* return address on top of stack */ .endif - movq %rdx, 12*8+\offset(%rsp) - movq %rsi, 13*8+\offset(%rsp) - movq %rdi, 14*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - .macro SAVE_C_REGS offset=0 - SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 - SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 - .endm - .macro SAVE_C_REGS_EXCEPT_R891011 - SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RCX_R891011 - SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 - .endm - .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 - SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 - .endm - - .macro SAVE_EXTRA_REGS offset=0 - movq %r15, 0*8+\offset(%rsp) - movq %r14, 1*8+\offset(%rsp) - movq %r13, 2*8+\offset(%rsp) - movq %r12, 3*8+\offset(%rsp) - movq %rbp, 4*8+\offset(%rsp) - movq %rbx, 5*8+\offset(%rsp) - UNWIND_HINT_REGS offset=\offset - .endm - - .macro POP_EXTRA_REGS +.endm + +.macro POP_REGS pop_rdi=1 skip_r11rcx=0 popq %r15 popq %r14 popq %r13 popq %r12 popq %rbp popq %rbx - .endm - - .macro POP_C_REGS + .if \skip_r11rcx + popq %rsi + .else popq %r11 + .endif popq %r10 popq %r9 popq %r8 popq %rax + .if \skip_r11rcx + popq %rsi + .else popq %rcx + .endif popq %rdx popq %rsi + .if \pop_rdi popq %rdi - .endm - - .macro icebp - .byte 0xf1 - .endm + .endif +.endm /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The @@ -178,17 +176,12 @@ For 32-bit we have the following conventions - kernel is built with * is just setting the LSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * - * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts * the original rbp. */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 #ifdef CONFIG_FRAME_POINTER - .if \ptregs_offset - leaq \ptregs_offset(%rsp), %rbp - .else - mov %rsp, %rbp - .endif - orq $0x1, %rbp + leaq 1+\ptregs_offset(%rsp), %rbp #endif .endm diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 16c2c022540d..6ad064c8cf35 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,8 +252,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %ebx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 30c8c5344c4a..936e19642eab 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -55,7 +55,7 @@ END(native_usergs_sysret64) .macro TRACE_IRQS_FLAGS flags:req #ifdef CONFIG_TRACE_IRQFLAGS - bt $9, \flags /* interrupts off? */ + btl $9, \flags /* interrupts off? */ jnc 1f TRACE_IRQS_ON 1: @@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64) swapgs /* - * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it * is not required to switch CR3. */ movq %rsp, PER_CPU_VAR(rsp_scratch) @@ -227,22 +227,8 @@ ENTRY(entry_SYSCALL_64) pushq %rcx /* pt_regs->ip */ GLOBAL(entry_SYSCALL_64_after_hwframe) pushq %rax /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq $-ENOSYS /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + + PUSH_AND_CLEAR_REGS rax=$-ENOSYS TRACE_IRQS_OFF @@ -274,8 +260,13 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) * Change top bits to match most significant bit (47th or 56th bit * depending on paging mode) in the address. */ +#ifdef CONFIG_X86_5LEVEL + ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \ + "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57 +#else shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx +#endif /* If this changed %rcx, it was not canonical */ cmpq %rcx, %r11 @@ -321,15 +312,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ UNWIND_HINT_EMPTY - POP_EXTRA_REGS - popq %rsi /* skip r11 */ - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rsi /* skip rcx */ - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 skip_r11rcx=1 /* * Now all regs are restored except RSP and RDI. @@ -386,8 +369,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %rbx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ @@ -471,9 +453,19 @@ END(irq_entries_start) * * The invariant is that, if irq_count != -1, then the IRQ stack is in use. */ -.macro ENTER_IRQ_STACK regs=1 old_rsp +.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0 DEBUG_ENTRY_ASSERT_IRQS_OFF + + .if \save_ret + /* + * If save_ret is set, the original stack contains one additional + * entry -- the return address. Therefore, move the address one + * entry below %rsp to \old_rsp. + */ + leaq 8(%rsp), \old_rsp + .else movq %rsp, \old_rsp + .endif .if \regs UNWIND_HINT_REGS base=\old_rsp @@ -519,6 +511,15 @@ END(irq_entries_start) .if \regs UNWIND_HINT_REGS indirect=1 .endif + + .if \save_ret + /* + * Push the return address to the stack. This return address can + * be found at the "real" original RSP, which was offset by 8 at + * the beginning of this macro. + */ + pushq -8(\old_rsp) + .endif .endm /* @@ -542,29 +543,65 @@ END(irq_entries_start) .endm /* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. + * Interrupt entry helper function. * - * Entry runs with interrupts off. + * Entry runs with interrupts off. Stack layout at entry: + * +----------------------------------------------------+ + * | regs->ss | + * | regs->rsp | + * | regs->eflags | + * | regs->cs | + * | regs->ip | + * +----------------------------------------------------+ + * | regs->orig_ax = ~(interrupt number) | + * +----------------------------------------------------+ + * | return address | + * +----------------------------------------------------+ */ - -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func +ENTRY(interrupt_entry) + UNWIND_HINT_FUNC + ASM_CLAC cld - testb $3, CS-ORIG_RAX(%rsp) + testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - call switch_to_thread_stack + + /* + * Switch to the thread stack. The IRET frame and orig_ax are + * on the stack, as well as the return address. RDI..R12 are + * not (yet) on the stack and space has not (yet) been + * allocated for them. + */ + pushq %rdi + + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + /* + * We have RDI, return address, and orig_ax on the stack on + * top of the IRET frame. That means offset=24 + */ + UNWIND_HINT_IRET_REGS base=%rdi offset=24 + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi 1: - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS - ENCODE_FRAME_POINTER + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 - testb $3, CS(%rsp) + testb $3, CS+8(%rsp) jz 1f /* @@ -572,7 +609,7 @@ END(irq_entries_start) * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode - * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * (which can take locks). Since TRACE_IRQS_OFF is idempotent, * the simplest way to handle it is to just call it twice if * we enter from user mode. There's no reason to optimize this since * TRACE_IRQS_OFF is a no-op if lockdep is off. @@ -582,12 +619,15 @@ END(irq_entries_start) CALL_enter_from_user_mode 1: - ENTER_IRQ_STACK old_rsp=%rdi + ENTER_IRQ_STACK old_rsp=%rdi save_ret=1 /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func /* rdi points to pt_regs */ - .endm + ret +END(interrupt_entry) + + +/* Interrupt entry/exit. */ /* * The interrupt stubs push (~vector+0x80) onto the stack and @@ -595,9 +635,10 @@ END(irq_entries_start) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ - interrupt do_IRQ + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call do_IRQ /* rdi points to pt_regs */ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_ANY) @@ -622,15 +663,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - POP_EXTRA_REGS - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi + POP_REGS pop_rdi=0 /* * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. @@ -688,8 +721,7 @@ GLOBAL(restore_regs_and_return_to_kernel) ud2 1: #endif - POP_EXTRA_REGS - POP_C_REGS + POP_REGS addq $8, %rsp /* skip regs->orig_ax */ /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -799,10 +831,11 @@ END(common_interrupt) .macro apicinterrupt3 num sym do_sym ENTRY(\sym) UNWIND_HINT_IRET_REGS - ASM_CLAC pushq $~(\num) .Lcommon_\sym: - interrupt \do_sym + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call \do_sym /* rdi points to pt_regs */ jmp ret_from_intr END(\sym) .endm @@ -865,34 +898,6 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) -/* - * Switch to the thread stack. This is called with the IRET frame and - * orig_ax on the stack. (That is, RDI..R12 are not on the stack and - * space has not been allocated for them.) - */ -ENTRY(switch_to_thread_stack) - UNWIND_HINT_FUNC - - pushq %rdi - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI - - pushq 7*8(%rdi) /* regs->ss */ - pushq 6*8(%rdi) /* regs->rsp */ - pushq 5*8(%rdi) /* regs->eflags */ - pushq 4*8(%rdi) /* regs->cs */ - pushq 3*8(%rdi) /* regs->ip */ - pushq 2*8(%rdi) /* regs->orig_ax */ - pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC - - movq (%rdi), %rdi - ret -END(switch_to_thread_stack) - .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 @@ -908,10 +913,8 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - ALLOC_PT_GPREGS_ON_STACK - .if \paranoid < 2 - testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */ jnz .Lfrom_usermode_switch_stack_\@ .endif @@ -1121,9 +1124,7 @@ ENTRY(xen_failsafe_callback) addq $0x30, %rsp UNWIND_HINT_IRET_REGS pushq $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS + PUSH_AND_CLEAR_REGS ENCODE_FRAME_POINTER jmp error_exit END(xen_failsafe_callback) @@ -1142,7 +1143,7 @@ apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \ #endif /* CONFIG_HYPERV */ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN @@ -1170,8 +1171,7 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx @@ -1211,21 +1211,20 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* - * Save all registers in pt_regs, and switch gs if needed. + * Save all registers in pt_regs, and switch GS if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 + PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 - xorl %ebx, %ebx testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1406,22 +1405,7 @@ ENTRY(nmi) pushq 1*8(%rdx) /* pt_regs->rip */ UNWIND_HINT_IRET_REGS pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - UNWIND_HINT_REGS + PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER /* @@ -1631,7 +1615,6 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit @@ -1655,8 +1638,7 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - POP_EXTRA_REGS - POP_C_REGS + POP_REGS /* * Skip orig_ax and the "outermost" frame to point RSP at the "iret" diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 98d5358e4041..08425c42f8b7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ + xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ + xorl %r15d, %r15d /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -278,9 +298,9 @@ sysret32_from_system_call: */ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d swapgs sysretl END(entry_SYSCALL_compat) @@ -327,26 +347,47 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax + /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ - /* switch to thread stack expects orig_ax to be pushed */ - call switch_to_thread_stack + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - pushq %rdi /* pt_regs->di */ + pushq 6*8(%rdi) /* regs->ss */ + pushq 5*8(%rdi) /* regs->rsp */ + pushq 4*8(%rdi) /* regs->eflags */ + pushq 3*8(%rdi) /* regs->cs */ + pushq 2*8(%rdi) /* regs->ip */ + pushq 1*8(%rdi) /* regs->orig_ax */ + + pushq (%rdi) /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -363,15 +404,3 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) - -ENTRY(stub32_clone) - /* - * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). - * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). - * - * The native 64-bit kernel's sys_clone() implements the latter, - * so we need to swap arguments here before calling it: - */ - xchg %r8, %rcx - jmp sys_clone -ENDPROC(stub32_clone) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 448ac2161112..c58f75b088c5 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,12 +8,12 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork sys_fork +2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open 6 i386 close sys_close -7 i386 waitpid sys_waitpid sys32_waitpid +7 i386 waitpid sys_waitpid 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink @@ -78,7 +78,7 @@ 69 i386 ssetmask sys_ssetmask 70 i386 setreuid sys_setreuid16 71 i386 setregid sys_setregid16 -72 i386 sigsuspend sys_sigsuspend sys_sigsuspend +72 i386 sigsuspend sys_sigsuspend 73 i386 sigpending sys_sigpending compat_sys_sigpending 74 i386 sethostname sys_sethostname 75 i386 setrlimit sys_setrlimit compat_sys_setrlimit @@ -96,7 +96,7 @@ 87 i386 swapon sys_swapon 88 i386 reboot sys_reboot 89 i386 readdir sys_old_readdir compat_sys_old_readdir -90 i386 mmap sys_old_mmap sys32_mmap +90 i386 mmap sys_old_mmap compat_sys_x86_mmap 91 i386 munmap sys_munmap 92 i386 truncate sys_truncate compat_sys_truncate 93 i386 ftruncate sys_ftruncate compat_sys_ftruncate @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn -120 i386 clone sys_clone stub32_clone +120 i386 clone sys_clone compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt @@ -137,7 +137,7 @@ 128 i386 init_module sys_init_module 129 i386 delete_module sys_delete_module 130 i386 get_kernel_syms -131 i386 quotactl sys_quotactl sys32_quotactl +131 i386 quotactl sys_quotactl compat_sys_quotactl32 132 i386 getpgid sys_getpgid 133 i386 fchdir sys_fchdir 134 i386 bdflush sys_bdflush @@ -186,8 +186,8 @@ 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend -180 i386 pread64 sys_pread64 sys32_pread -181 i386 pwrite64 sys_pwrite64 sys32_pwrite +180 i386 pread64 sys_pread64 compat_sys_x86_pread +181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite 182 i386 chown sys_chown16 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget @@ -196,14 +196,14 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork sys_vfork +190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 sys32_truncate64 -194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 -195 i386 stat64 sys_stat64 sys32_stat64 -196 i386 lstat64 sys_lstat64 sys32_lstat64 -197 i386 fstat64 sys_fstat64 sys32_fstat64 +193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64 +194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_x86_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64 198 i386 lchown32 sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid @@ -231,7 +231,7 @@ # 222 is unused # 223 is unused 224 i386 gettid sys_gettid -225 i386 readahead sys_readahead sys32_readahead +225 i386 readahead sys_readahead compat_sys_x86_readahead 226 i386 setxattr sys_setxattr 227 i386 lsetxattr sys_lsetxattr 228 i386 fsetxattr sys_fsetxattr @@ -256,7 +256,7 @@ 247 i386 io_getevents sys_io_getevents compat_sys_io_getevents 248 i386 io_submit sys_io_submit compat_sys_io_submit 249 i386 io_cancel sys_io_cancel -250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie @@ -278,7 +278,7 @@ 269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 270 i386 tgkill sys_tgkill 271 i386 utimes sys_utimes compat_sys_utimes -272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind 275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -306,7 +306,7 @@ 297 i386 mknodat sys_mknodat 298 i386 fchownat sys_fchownat 299 i386 futimesat sys_futimesat compat_sys_futimesat -300 i386 fstatat64 sys_fstatat64 sys32_fstatat +300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat 302 i386 renameat sys_renameat 303 i386 linkat sys_linkat @@ -320,7 +320,7 @@ 311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list 313 i386 splice sys_splice -314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice compat_sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages @@ -330,7 +330,7 @@ 321 i386 signalfd sys_signalfd compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create 323 i386 eventfd sys_eventfd -324 i386 fallocate sys_fallocate sys32_fallocate +324 i386 fallocate sys_fallocate compat_sys_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 7780bbfb06ef..9242b28418d5 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -5,8 +5,6 @@ #undef CONFIG_OPTIMIZE_INLINING #endif -#undef CONFIG_X86_PPRO_FENCE - #ifdef CONFIG_X86_64 /* diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 577fa8adb785..317be365bce3 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,10 +42,8 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = -#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) - NATIVE; -#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) +static enum { EMULATE, NONE } vsyscall_mode = +#ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #else EMULATE; @@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); - /* This should be unreachable in NATIVE mode. */ - if (WARN_ON(vsyscall_mode == NATIVE)) - return false; - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -355,7 +347,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); #if CONFIG_PGTABLE_LEVELS >= 5 - p4d->p4d |= _PAGE_USER; + set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); #endif pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); @@ -370,9 +362,7 @@ void __init map_vsyscall(void) if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 140d33288e78..a6006e7bb729 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -48,7 +48,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -struct static_key rdpmc_always_available = STATIC_KEY_INIT_FALSE; +DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -990,7 +990,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, if (!dogrp) return n; - list_for_each_entry(event, &leader->sibling_list, group_entry) { + for_each_sibling_event(event, leader) { if (!is_x86_event(event) || event->state <= PERF_EVENT_STATE_OFF) continue; @@ -1156,16 +1156,13 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || - local64_read(&hwc->prev_count) != (u64)-left) { - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); - } + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Due to erratum on certan cpu we need @@ -1884,6 +1881,8 @@ early_initcall(init_hw_perf_events); static inline void x86_pmu_read(struct perf_event *event) { + if (x86_pmu.read) + return x86_pmu.read(event); x86_perf_event_update(event); } @@ -2118,7 +2117,8 @@ static int x86_pmu_event_init(struct perf_event *event) event->destroy(event); } - if (READ_ONCE(x86_pmu.attr_rdpmc)) + if (READ_ONCE(x86_pmu.attr_rdpmc) && + !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; @@ -2206,9 +2206,9 @@ static ssize_t set_attr_rdpmc(struct device *cdev, * but only root can trigger it, so it's okay. */ if (val == 2) - static_key_slow_inc(&rdpmc_always_available); + static_branch_inc(&rdpmc_always_available_key); else - static_key_slow_dec(&rdpmc_always_available); + static_branch_dec(&rdpmc_always_available_key); on_each_cpu(refresh_pce, NULL, 1); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 731153a4681e..607bf565a90c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2060,6 +2060,14 @@ static void intel_pmu_del_event(struct perf_event *event) intel_pmu_pebs_del(event); } +static void intel_pmu_read_event(struct perf_event *event) +{ + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_auto_reload_read(event); + else + x86_perf_event_update(event); +} + static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { int idx = hwc->idx - INTEL_PMC_IDX_FIXED; @@ -2201,16 +2209,23 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 status; int handled; + int pmu_enabled; cpuc = this_cpu_ptr(&cpu_hw_events); /* + * Save the PMU state. + * It needs to be restored when leaving the handler. + */ + pmu_enabled = cpuc->enabled; + /* * No known reason to not always do late ACK, * but just in case do it opt-in. */ if (!x86_pmu.late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); + cpuc->enabled = 0; __intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); @@ -2320,7 +2335,8 @@ again: done: /* Only restore PMU state when it's active. See x86_pmu_disable(). */ - if (cpuc->enabled) + cpuc->enabled = pmu_enabled; + if (pmu_enabled) __intel_pmu_enable_all(0, true); intel_bts_enable_local(); @@ -2952,9 +2968,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event) return intel_pebs_aliases_precdist(event); } -static unsigned long intel_pmu_free_running_flags(struct perf_event *event) +static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) { - unsigned long flags = x86_pmu.free_running_flags; + unsigned long flags = x86_pmu.large_pebs_flags; if (event->attr.use_clockid) flags &= ~PERF_SAMPLE_TIME; @@ -2976,8 +2992,8 @@ static int intel_pmu_hw_config(struct perf_event *event) if (!event->attr.freq) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & - ~intel_pmu_free_running_flags(event))) - event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + ~intel_pmu_large_pebs_flags(event))) + event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); @@ -3188,13 +3204,13 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, * Therefore the effective (average) period matches the requested period, * despite coarser hardware granularity. */ -static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +static u64 bdw_limit_period(struct perf_event *event, u64 left) { if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == X86_CONFIG(.event=0xc0, .umask=0x01)) { if (left < 128) left = 128; - left &= ~0x3fu; + left &= ~0x3fULL; } return left; } @@ -3460,7 +3476,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32-bit width, @@ -3495,6 +3511,7 @@ static __initconst const struct x86_pmu intel_pmu = { .disable = intel_pmu_disable_event, .add = intel_pmu_add_event, .del = intel_pmu_del_event, + .read = intel_pmu_read_event, .hw_config = intel_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, @@ -3502,7 +3519,7 @@ static __initconst const struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of @@ -3559,7 +3576,7 @@ static int intel_snb_pebs_broken(int cpu) break; case INTEL_FAM6_SANDYBRIDGE_X: - switch (cpu_data(cpu).x86_mask) { + switch (cpu_data(cpu).x86_stepping) { case 6: rev = 0x618; break; case 7: rev = 0x70c; break; } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 72db0664a53d..9aca448bb8e6 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,50 +40,51 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM + * Available model: SLM,AMT,GLM,CNL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, + CNL * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, + * SKL,KNL,GLM,CNL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 - * Available model: SNB,IVB,HSW,BDW,SKL + * Available model: SNB,IVB,HSW,BDW,SKL,CNL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM + * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL - * GLM + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, + * GLM,CNL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM + * SKL,KNL,GLM,CNL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT only + * Available model: HSW ULT,CNL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT only + * Available model: HSW ULT,CNL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT, GLM + * Available model: HSW ULT,GLM,CNL * Scope: Package (physical package) * */ @@ -486,6 +487,21 @@ static const struct cstate_model hswult_cstates __initconst = { BIT(PERF_CSTATE_PKG_C10_RES), }; +static const struct cstate_model cnl_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + static const struct cstate_model slm_cstates __initconst = { .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | BIT(PERF_CSTATE_CORE_C6_RES), @@ -557,6 +573,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 18c25ab28557..da6780122786 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs++; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs--; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -1153,6 +1153,7 @@ static void setup_pebs_sample_data(struct perf_event *event, if (pebs == NULL) return; + regs->flags &= ~PERF_EFLAGS_EXACT; sample_type = event->attr.sample_type; dsrc = sample_type & PERF_SAMPLE_DATA_SRC; @@ -1197,7 +1198,6 @@ static void setup_pebs_sample_data(struct perf_event *event, */ *regs = *iregs; regs->flags = pebs->flags; - set_linear_ip(regs, pebs->ip); if (sample_type & PERF_SAMPLE_REGS_INTR) { regs->ax = pebs->ax; @@ -1233,13 +1233,22 @@ static void setup_pebs_sample_data(struct perf_event *event, #endif } - if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs->ip = pebs->real_ip; - regs->flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) - regs->flags |= PERF_EFLAGS_EXACT; - else - regs->flags &= ~PERF_EFLAGS_EXACT; + if (event->attr.precise_ip > 1) { + /* Haswell and later have the eventing IP, so use it: */ + if (x86_pmu.intel_cap.pebs_format >= 2) { + set_linear_ip(regs, pebs->real_ip); + regs->flags |= PERF_EFLAGS_EXACT; + } else { + /* Otherwise use PEBS off-by-1 IP: */ + set_linear_ip(regs, pebs->ip); + + /* ... and try to fix it up using the LBR entries: */ + if (intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; + } + } else + set_linear_ip(regs, pebs->ip); + if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && x86_pmu.intel_cap.pebs_format >= 1) @@ -1306,17 +1315,93 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) return NULL; } +void intel_pmu_auto_reload_read(struct perf_event *event) +{ + WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)); + + perf_pmu_disable(event->pmu); + intel_pmu_drain_pebs_buffer(); + perf_pmu_enable(event->pmu); +} + +/* + * Special variant of intel_pmu_save_and_restart() for auto-reload. + */ +static int +intel_pmu_save_and_restart_reload(struct perf_event *event, int count) +{ + struct hw_perf_event *hwc = &event->hw; + int shift = 64 - x86_pmu.cntval_bits; + u64 period = hwc->sample_period; + u64 prev_raw_count, new_raw_count; + s64 new, old; + + WARN_ON(!period); + + /* + * drain_pebs() only happens when the PMU is disabled. + */ + WARN_ON(this_cpu_read(cpu_hw_events.enabled)); + + prev_raw_count = local64_read(&hwc->prev_count); + rdpmcl(hwc->event_base_rdpmc, new_raw_count); + local64_set(&hwc->prev_count, new_raw_count); + + /* + * Since the counter increments a negative counter value and + * overflows on the sign switch, giving the interval: + * + * [-period, 0] + * + * the difference between two consequtive reads is: + * + * A) value2 - value1; + * when no overflows have happened in between, + * + * B) (0 - value1) + (value2 - (-period)); + * when one overflow happened in between, + * + * C) (0 - value1) + (n - 1) * (period) + (value2 - (-period)); + * when @n overflows happened in between. + * + * Here A) is the obvious difference, B) is the extension to the + * discrete interval, where the first term is to the top of the + * interval and the second term is from the bottom of the next + * interval and C) the extension to multiple intervals, where the + * middle term is the whole intervals covered. + * + * An equivalent of C, by reduction, is: + * + * value2 - value1 + n * period + */ + new = ((s64)(new_raw_count << shift) >> shift); + old = ((s64)(prev_raw_count << shift) >> shift); + local64_add(new - old + count * period, &event->count); + + perf_event_update_userpage(event); + + return 0; +} + static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *base, void *top, int bit, int count) { + struct hw_perf_event *hwc = &event->hw; struct perf_sample_data data; struct pt_regs regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - if (!intel_pmu_save_and_restart(event) && - !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + /* + * Now, auto-reload is only enabled in fixed period mode. + * The reload value is always hwc->sample_period. + * May need to change it, if auto-reload is enabled in + * freq mode later. + */ + intel_pmu_save_and_restart_reload(event, count); + } else if (!intel_pmu_save_and_restart(event)) return; while (count > 1) { @@ -1368,8 +1453,11 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; n = top - at; - if (n <= 0) + if (n <= 0) { + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); return; + } __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } @@ -1392,8 +1480,22 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(base >= top)) + if (unlikely(base >= top)) { + /* + * The drain_pebs() could be called twice in a short period + * for auto-reload event in pmu::read(). There are no + * overflows have happened in between. + * It needs to call intel_pmu_save_and_restart_reload() to + * update the event->count for this case. + */ + for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, + x86_pmu.max_pebs_events) { + event = cpuc->events[bit]; + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + intel_pmu_save_and_restart_reload(event, 0); + } return; + } for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; @@ -1530,7 +1632,7 @@ void __init intel_ds_init(void) x86_pmu.pebs_record_size = sizeof(struct pebs_record_skl); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; - x86_pmu.free_running_flags |= PERF_SAMPLE_TIME; + x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; default: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index ae64d0b69729..cf372b90557e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1186,7 +1186,7 @@ void __init intel_pmu_lbr_init_atom(void) * on PMU interrupt */ if (boot_cpu_data.x86_model == 28 - && boot_cpu_data.x86_mask < 10) { + && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; } diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index a5604c352930..408879b0c0d4 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -234,7 +234,7 @@ static __initconst const struct x86_pmu p6_pmu = { static __init void p6_pmu_rdpmc_quirk(void) { - if (boot_cpu_data.x86_mask < 9) { + if (boot_cpu_data.x86_stepping < 9) { /* * PPro erratum 26; fixed in stepping 9 and above. */ diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 81fd41d5a0d9..3b993942a0e4 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1186,8 +1186,12 @@ static int pt_event_addr_filters_validate(struct list_head *filters) int range = 0; list_for_each_entry(filter, filters, entry) { - /* PT doesn't support single address triggers */ - if (!filter->range || !filter->size) + /* + * PT doesn't support single address triggers and + * 'start' filters. + */ + if (!filter->size || + filter->action == PERF_ADDR_FILTER_ACTION_START) return -EOPNOTSUPP; if (!filter->inode) { @@ -1227,7 +1231,10 @@ static void pt_event_addr_filters_sync(struct perf_event *event) filters->filter[range].msr_a = msr_a; filters->filter[range].msr_b = msr_b; - filters->filter[range].config = filter->filter ? 1 : 2; + if (filter->action == PERF_ADDR_FILTER_ACTION_FILTER) + filters->filter[range].config = 1; + else + filters->filter[range].config = 2; range++; } diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index a2efb490f743..32f3e9423e99 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -774,6 +774,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init), diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7874c980d569..a7956fc7ca1d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -354,7 +354,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, if (!dogrp) return n; - list_for_each_entry(event, &leader->sibling_list, group_entry) { + for_each_sibling_event(event, leader) { if (!is_box_event(box, event) || event->state <= PERF_EVENT_STATE_OFF) continue; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 6d8044ab1060..c98b943e58b4 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3), EVENT_EXTRA_END }; @@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = { NULL, }; +/* + * To determine the number of CHAs, it should read bits 27:0 in the CAPID6 + * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083. + */ +#define SKX_CAPID6 0x9c +#define SKX_CHA_BIT_MASK GENMASK(27, 0) + static int skx_count_chabox(void) { - struct pci_dev *chabox_dev = NULL; - int bus, count = 0; + struct pci_dev *dev = NULL; + u32 val = 0; - while (1) { - chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev); - if (!chabox_dev) - break; - if (count == 0) - bus = chabox_dev->bus->number; - if (bus != chabox_dev->bus->number) - break; - count++; - } + dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev); + if (!dev) + goto out; - pci_dev_put(chabox_dev); - return count; + pci_read_config_dword(dev, SKX_CAPID6, &val); + val &= SKX_CHA_BIT_MASK; +out: + pci_dev_put(dev); + return hweight32(val); } void skx_uncore_cpu_init(void) @@ -3606,7 +3610,7 @@ static struct intel_uncore_type skx_uncore_imc = { }; static struct attribute *skx_upi_uncore_formats_attr[] = { - &format_attr_event_ext.attr, + &format_attr_event.attr, &format_attr_umask_ext.attr, &format_attr_edge.attr, &format_attr_inv.attr, diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 18e2628e2d8f..e7edf19e64c2 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -188,10 +188,11 @@ static inline u64 msr_read_counter(struct perf_event *event) if (event->hw.event_base) rdmsrl(event->hw.event_base, now); else - rdtscll(now); + now = rdtsc_ordered(); return now; } + static void msr_event_update(struct perf_event *event) { u64 prev, now; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 78f91ec1056e..9f3711470ec1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -69,7 +69,7 @@ struct event_constraint { #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ struct amd_nb { @@ -88,7 +88,7 @@ struct amd_nb { * REGS_USER can be handled for events limited to ring 3. * */ -#define PEBS_FREERUNNING_FLAGS \ +#define LARGE_PEBS_FLAGS \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ @@ -520,6 +520,7 @@ struct x86_pmu { void (*disable)(struct perf_event *); void (*add)(struct perf_event *); void (*del)(struct perf_event *); + void (*read)(struct perf_event *event); int (*hw_config)(struct perf_event *event); int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; @@ -557,7 +558,7 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; - unsigned (*limit_period)(struct perf_event *event, unsigned l); + u64 (*limit_period)(struct perf_event *event, u64 l); /* * sysfs attrs @@ -608,7 +609,7 @@ struct x86_pmu { struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); int max_pebs_events; - unsigned long free_running_flags; + unsigned long large_pebs_flags; /* * Intel LBR @@ -923,6 +924,8 @@ void intel_pmu_pebs_disable_all(void); void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); +void intel_pmu_auto_reload_read(struct perf_event *event); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 41c671854642..86b1341cba9a 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -33,7 +33,6 @@ #include <asm/vdso.h> #include <asm/sigframe.h> #include <asm/sighandling.h> -#include <asm/sys_ia32.h> #include <asm/smap.h> /* diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 96cd33bbfc85..11ef7b7c9cc8 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -41,27 +41,28 @@ #include <linux/highuid.h> #include <linux/sysctl.h> #include <linux/slab.h> +#include <linux/sched/task.h> #include <asm/mman.h> #include <asm/types.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <asm/vgtod.h> -#include <asm/sys_ia32.h> +#include <asm/ia32.h> #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(const char __user *filename, - unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { - return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); + return ksys_truncate(filename, + ((loff_t) offset_high << 32) | offset_low); } -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { - return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); + return ksys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } /* @@ -96,8 +97,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -107,8 +108,8 @@ asmlinkage long sys32_stat64(const char __user *filename, return ret; } -asmlinkage long sys32_lstat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -117,7 +118,8 @@ asmlinkage long sys32_lstat64(const char __user *filename, return ret; } -asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -126,8 +128,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, + const char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -153,7 +156,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) +COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -163,29 +166,23 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) if (a.offset & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset>>PAGE_SHIFT); } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, - int options) -{ - return compat_sys_wait4(pid, stat_addr, options, NULL); -} - /* warning: next two assume little endian */ -asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { - return sys_pread64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); + return ksys_pread64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, - u32 count, u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { - return sys_pwrite64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); + return ksys_pwrite64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); } @@ -193,40 +190,53 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, - __u32 len_low, __u32 len_high, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) +{ + return ksys_fadvise64_64(fd, + (((u64)offset_high)<<32) | offset_low, + (((u64)len_high)<<32) | len_low, + advice); +} + +COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) { - return sys_fadvise64_64(fd, - (((u64)offset_high)<<32) | offset_low, - (((u64)len_high)<<32) | len_low, - advice); + return ksys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } -asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, - size_t count) +COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) { - return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); + return ksys_sync_file_range(fd, + ((u64)off_hi << 32) | off_low, + ((u64)n_hi << 32) | n_low, flags); } -asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi, - unsigned n_low, unsigned n_hi, int flags) +COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) { - return sys_sync_file_range(fd, - ((u64)off_hi << 32) | off_low, - ((u64)n_hi << 32) | n_low, flags); + return ksys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, + len, advice); } -asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) { - return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, - len, advice); + return ksys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, + ((u64)len_hi << 32) | len_lo); } -asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, - unsigned offset_hi, unsigned len_lo, - unsigned len_hi) +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) { - return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, - ((u64)len_hi << 32) | len_lo); + return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr, + tls_val); } diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 44f5d79d5105..a303d7b7d763 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -31,6 +31,7 @@ #include <asm/mmu.h> #include <asm/mpspec.h> #include <asm/realmode.h> +#include <asm/x86_init.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -94,7 +95,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) if (boot_cpu_data.x86 == 0x0F && boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86_model <= 0x05 && - boot_cpu_data.x86_mask < 0x0A) + boot_cpu_data.x86_stepping < 0x0A) return 1; else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) return 1; @@ -133,6 +134,14 @@ static inline bool acpi_has_cpu_in_madt(void) return !!acpi_lapic; } +#define ACPI_HAVE_ARCH_GET_ROOT_POINTER +static inline u64 acpi_arch_get_root_pointer(void) +{ + return x86_init.acpi.get_root_pointer(); +} + +void acpi_generic_reduced_hw_init(void); + #else /* !CONFIG_ACPI */ #define acpi_lapic 0 @@ -142,6 +151,8 @@ static inline void acpi_noirq_set(void) { } static inline void acpi_disable_pci(void) { } static inline void disable_acpi(void) { } +static inline void acpi_generic_reduced_hw_init(void) { } + #endif /* !CONFIG_ACPI */ #define ARCH_HAS_POWER_INIT 1 diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index cf5961ca8677..4cd6a3b71824 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -218,13 +218,11 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ -{ \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ - [new2] "i" (newfunc2), ## input); \ -} + [new2] "i" (newfunc2), ## input) /* * use this macro(s) if you need more than one output parameter diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 98722773391d..40a3d3642f3a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -138,7 +138,6 @@ extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void apic_intr_mode_init(void); -extern void setup_local_APIC(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); @@ -183,6 +182,7 @@ static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop static inline void lapic_update_tsc_freq(void) { } +static inline void init_bsp_APIC(void) { } static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } @@ -304,12 +304,6 @@ struct apic { u32 irq_delivery_mode; u32 irq_dest_mode; - /* Functions and data related to vector allocation */ - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, - const struct cpumask *mask); - int (*cpu_mask_to_apicid)(const struct cpumask *cpumask, - struct irq_data *irqdata, - unsigned int *apicid); u32 (*calc_dest_apicid)(unsigned int cpu); /* ICR related functions */ @@ -499,17 +493,7 @@ extern void default_setup_apic_routing(void); extern u32 apic_default_calc_apicid(unsigned int cpu); extern u32 apic_flat_calc_apicid(unsigned int cpu); -extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask, - struct irq_data *irqdata, - unsigned int *apicid); -extern int default_cpu_mask_to_apicid(const struct cpumask *cpumask, - struct irq_data *irqdata, - unsigned int *apicid); extern bool default_check_apicid_used(physid_mask_t *map, int apicid); -extern void flat_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask); -extern void default_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask); extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern int default_cpu_present_to_apicid(int mps_cpu); extern int default_check_phys_apicid_present(int phys_apicid); diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 4d4015ddcf26..c356098b6fb9 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,6 +7,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include <asm/nospec-branch.h> + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 4d111616524b..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,7 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -asmlinkage void __fill_rsb(void); -asmlinkage void __clear_rsb(void); - #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 72759f131cc5..0db6bec95489 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -17,36 +17,40 @@ #define ATOMIC_INIT(i) { (i) } /** - * atomic_read - read atomic variable + * arch_atomic_read - read atomic variable * @v: pointer of type atomic_t * * Atomically reads the value of @v. */ -static __always_inline int atomic_read(const atomic_t *v) +static __always_inline int arch_atomic_read(const atomic_t *v) { + /* + * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, + * it's non-inlined function that increases binary size and stack usage. + */ return READ_ONCE((v)->counter); } /** - * atomic_set - set atomic variable + * arch_atomic_set - set atomic variable * @v: pointer of type atomic_t * @i: required value * * Atomically sets the value of @v to @i. */ -static __always_inline void atomic_set(atomic_t *v, int i) +static __always_inline void arch_atomic_set(atomic_t *v, int i) { WRITE_ONCE(v->counter, i); } /** - * atomic_add - add integer to atomic variable + * arch_atomic_add - add integer to atomic variable * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v. */ -static __always_inline void atomic_add(int i, atomic_t *v) +static __always_inline void arch_atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) @@ -54,13 +58,13 @@ static __always_inline void atomic_add(int i, atomic_t *v) } /** - * atomic_sub - subtract integer from atomic variable + * arch_atomic_sub - subtract integer from atomic variable * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v. */ -static __always_inline void atomic_sub(int i, atomic_t *v) +static __always_inline void arch_atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) @@ -68,7 +72,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v) } /** - * atomic_sub_and_test - subtract value from variable and test result + * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * @@ -76,63 +80,63 @@ static __always_inline void atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) +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); } /** - * atomic_inc - increment atomic variable + * arch_atomic_inc - increment atomic variable * @v: pointer of type atomic_t * * Atomically increments @v by 1. */ -static __always_inline void atomic_inc(atomic_t *v) +static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } /** - * atomic_dec - decrement atomic variable + * arch_atomic_dec - decrement atomic variable * @v: pointer of type atomic_t * * Atomically decrements @v by 1. */ -static __always_inline void atomic_dec(atomic_t *v) +static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } /** - * atomic_dec_and_test - decrement and test + * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ -static __always_inline bool atomic_dec_and_test(atomic_t *v) +static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } /** - * atomic_inc_and_test - increment and test + * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ -static __always_inline bool atomic_inc_and_test(atomic_t *v) +static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } /** - * atomic_add_negative - add and test if negative + * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * @@ -140,65 +144,65 @@ static __always_inline bool atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static __always_inline bool atomic_add_negative(int i, atomic_t *v) +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); } /** - * atomic_add_return - add integer and return + * arch_atomic_add_return - add integer and return * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns @i + @v */ -static __always_inline int atomic_add_return(int i, atomic_t *v) +static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } /** - * atomic_sub_return - subtract integer and return + * arch_atomic_sub_return - subtract integer and return * @v: pointer of type atomic_t * @i: integer value to subtract * * Atomically subtracts @i from @v and returns @v - @i */ -static __always_inline int atomic_sub_return(int i, atomic_t *v) +static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { - return atomic_add_return(-i, v); + return arch_atomic_add_return(-i, v); } -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) +#define arch_atomic_inc_return(v) (arch_atomic_add_return(1, v)) +#define arch_atomic_dec_return(v) (arch_atomic_sub_return(1, v)) -static __always_inline int atomic_fetch_add(int i, atomic_t *v) +static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { return xadd(&v->counter, i); } -static __always_inline int atomic_fetch_sub(int i, atomic_t *v) +static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { return xadd(&v->counter, -i); } -static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) +static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { - return cmpxchg(&v->counter, old, new); + return arch_cmpxchg(&v->counter, old, new); } -#define atomic_try_cmpxchg atomic_try_cmpxchg -static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg +static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { return try_cmpxchg(&v->counter, old, new); } -static inline int atomic_xchg(atomic_t *v, int new) +static inline int arch_atomic_xchg(atomic_t *v, int new) { return xchg(&v->counter, new); } -static inline void atomic_and(int i, atomic_t *v) +static inline void arch_atomic_and(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "andl %1,%0" : "+m" (v->counter) @@ -206,16 +210,16 @@ static inline void atomic_and(int i, atomic_t *v) : "memory"); } -static inline int atomic_fetch_and(int i, atomic_t *v) +static inline int arch_atomic_fetch_and(int i, atomic_t *v) { - int val = atomic_read(v); + int val = arch_atomic_read(v); - do { } while (!atomic_try_cmpxchg(v, &val, val & i)); + do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); return val; } -static inline void atomic_or(int i, atomic_t *v) +static inline void arch_atomic_or(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "orl %1,%0" : "+m" (v->counter) @@ -223,16 +227,16 @@ static inline void atomic_or(int i, atomic_t *v) : "memory"); } -static inline int atomic_fetch_or(int i, atomic_t *v) +static inline int arch_atomic_fetch_or(int i, atomic_t *v) { - int val = atomic_read(v); + int val = arch_atomic_read(v); - do { } while (!atomic_try_cmpxchg(v, &val, val | i)); + do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); return val; } -static inline void atomic_xor(int i, atomic_t *v) +static inline void arch_atomic_xor(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "xorl %1,%0" : "+m" (v->counter) @@ -240,17 +244,17 @@ static inline void atomic_xor(int i, atomic_t *v) : "memory"); } -static inline int atomic_fetch_xor(int i, atomic_t *v) +static inline int arch_atomic_fetch_xor(int i, atomic_t *v) { - int val = atomic_read(v); + int val = arch_atomic_read(v); - do { } while (!atomic_try_cmpxchg(v, &val, val ^ i)); + do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); return val; } /** - * __atomic_add_unless - add unless the number is already a given value + * __arch_atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -258,14 +262,14 @@ static inline int atomic_fetch_xor(int i, atomic_t *v) * Atomically adds @a to @v, so long as @v was not already @u. * Returns the old value of @v. */ -static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u) { - int c = atomic_read(v); + int c = arch_atomic_read(v); do { if (unlikely(c == u)) break; - } while (!atomic_try_cmpxchg(v, &c, c + a)); + } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); return c; } @@ -276,4 +280,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) # include <asm/atomic64_64.h> #endif +#include <asm-generic/atomic-instrumented.h> + #endif /* _ASM_X86_ATOMIC_H */ diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 97c46b8169b7..46e1ef17d92d 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -62,7 +62,7 @@ ATOMIC64_DECL(add_unless); #undef ATOMIC64_EXPORT /** - * atomic64_cmpxchg - cmpxchg atomic64 variable + * arch_atomic64_cmpxchg - cmpxchg atomic64 variable * @v: pointer to type atomic64_t * @o: expected value * @n: new value @@ -71,20 +71,21 @@ ATOMIC64_DECL(add_unless); * the old value. */ -static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n) +static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o, + long long n) { - return cmpxchg64(&v->counter, o, n); + return arch_cmpxchg64(&v->counter, o, n); } /** - * atomic64_xchg - xchg atomic64 variable + * arch_atomic64_xchg - xchg atomic64 variable * @v: pointer to type atomic64_t * @n: value to assign * * Atomically xchgs the value of @v to @n and returns * the old value. */ -static inline long long atomic64_xchg(atomic64_t *v, long long n) +static inline long long arch_atomic64_xchg(atomic64_t *v, long long n) { long long o; unsigned high = (unsigned)(n >> 32); @@ -96,13 +97,13 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n) } /** - * atomic64_set - set atomic64 variable + * arch_atomic64_set - set atomic64 variable * @v: pointer to type atomic64_t * @i: value to assign * * Atomically sets the value of @v to @n. */ -static inline void atomic64_set(atomic64_t *v, long long i) +static inline void arch_atomic64_set(atomic64_t *v, long long i) { unsigned high = (unsigned)(i >> 32); unsigned low = (unsigned)i; @@ -112,12 +113,12 @@ static inline void atomic64_set(atomic64_t *v, long long i) } /** - * atomic64_read - read atomic64 variable + * arch_atomic64_read - read atomic64 variable * @v: pointer to type atomic64_t * * Atomically reads the value of @v and returns it. */ -static inline long long atomic64_read(const atomic64_t *v) +static inline long long arch_atomic64_read(const atomic64_t *v) { long long r; alternative_atomic64(read, "=&A" (r), "c" (v) : "memory"); @@ -125,13 +126,13 @@ static inline long long atomic64_read(const atomic64_t *v) } /** - * atomic64_add_return - add and return + * arch_atomic64_add_return - add and return * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v and returns @i + *@v */ -static inline long long atomic64_add_return(long long i, atomic64_t *v) +static inline long long arch_atomic64_add_return(long long i, atomic64_t *v) { alternative_atomic64(add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -142,7 +143,7 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v) /* * Other variants with different arithmetic operators: */ -static inline long long atomic64_sub_return(long long i, atomic64_t *v) +static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v) { alternative_atomic64(sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -150,7 +151,7 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v) return i; } -static inline long long atomic64_inc_return(atomic64_t *v) +static inline long long arch_atomic64_inc_return(atomic64_t *v) { long long a; alternative_atomic64(inc_return, "=&A" (a), @@ -158,7 +159,7 @@ static inline long long atomic64_inc_return(atomic64_t *v) return a; } -static inline long long atomic64_dec_return(atomic64_t *v) +static inline long long arch_atomic64_dec_return(atomic64_t *v) { long long a; alternative_atomic64(dec_return, "=&A" (a), @@ -167,13 +168,13 @@ static inline long long atomic64_dec_return(atomic64_t *v) } /** - * atomic64_add - add integer to atomic64 variable + * arch_atomic64_add - add integer to atomic64 variable * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v. */ -static inline long long atomic64_add(long long i, atomic64_t *v) +static inline long long arch_atomic64_add(long long i, atomic64_t *v) { __alternative_atomic64(add, add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -182,13 +183,13 @@ static inline long long atomic64_add(long long i, atomic64_t *v) } /** - * atomic64_sub - subtract the atomic64 variable + * arch_atomic64_sub - subtract the atomic64 variable * @i: integer value to subtract * @v: pointer to type atomic64_t * * Atomically subtracts @i from @v. */ -static inline long long atomic64_sub(long long i, atomic64_t *v) +static inline long long arch_atomic64_sub(long long i, atomic64_t *v) { __alternative_atomic64(sub, sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), @@ -197,7 +198,7 @@ static inline long long atomic64_sub(long long i, atomic64_t *v) } /** - * atomic64_sub_and_test - subtract value from variable and test result + * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer to type atomic64_t * @@ -205,46 +206,46 @@ static inline long long atomic64_sub(long long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -static inline int atomic64_sub_and_test(long long i, atomic64_t *v) +static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v) { - return atomic64_sub_return(i, v) == 0; + return arch_atomic64_sub_return(i, v) == 0; } /** - * atomic64_inc - increment atomic64 variable + * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ -static inline void atomic64_inc(atomic64_t *v) +static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } /** - * atomic64_dec - decrement atomic64 variable + * arch_atomic64_dec - decrement atomic64 variable * @v: pointer to type atomic64_t * * Atomically decrements @v by 1. */ -static inline void atomic64_dec(atomic64_t *v) +static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } /** - * atomic64_dec_and_test - decrement and test + * arch_atomic64_dec_and_test - decrement and test * @v: pointer to type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ -static inline int atomic64_dec_and_test(atomic64_t *v) +static inline int arch_atomic64_dec_and_test(atomic64_t *v) { - return atomic64_dec_return(v) == 0; + return arch_atomic64_dec_return(v) == 0; } /** @@ -255,13 +256,13 @@ static inline int atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline int atomic64_inc_and_test(atomic64_t *v) +static inline int arch_atomic64_inc_and_test(atomic64_t *v) { - return atomic64_inc_return(v) == 0; + return arch_atomic64_inc_return(v) == 0; } /** - * atomic64_add_negative - add and test if negative + * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer to type atomic64_t * @@ -269,13 +270,13 @@ static inline int atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int atomic64_add_negative(long long i, atomic64_t *v) +static inline int arch_atomic64_add_negative(long long i, atomic64_t *v) { - return atomic64_add_return(i, v) < 0; + return arch_atomic64_add_return(i, v) < 0; } /** - * atomic64_add_unless - add unless the number is a given value + * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -283,7 +284,8 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns non-zero if the add was done, zero otherwise. */ -static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) +static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, + long long u) { unsigned low = (unsigned)u; unsigned high = (unsigned)(u >> 32); @@ -294,7 +296,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u) } -static inline int atomic64_inc_not_zero(atomic64_t *v) +static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; alternative_atomic64(inc_not_zero, "=&a" (r), @@ -302,7 +304,7 @@ static inline int atomic64_inc_not_zero(atomic64_t *v) return r; } -static inline long long atomic64_dec_if_positive(atomic64_t *v) +static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; alternative_atomic64(dec_if_positive, "=&A" (r), @@ -313,70 +315,70 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) #undef alternative_atomic64 #undef __alternative_atomic64 -static inline void atomic64_and(long long i, atomic64_t *v) +static inline void arch_atomic64_and(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c & i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c) c = old; } -static inline long long atomic64_fetch_and(long long i, atomic64_t *v) +static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c & i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c) c = old; return old; } -static inline void atomic64_or(long long i, atomic64_t *v) +static inline void arch_atomic64_or(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c | i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c) c = old; } -static inline long long atomic64_fetch_or(long long i, atomic64_t *v) +static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c | i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c) c = old; return old; } -static inline void atomic64_xor(long long i, atomic64_t *v) +static inline void arch_atomic64_xor(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c) c = old; } -static inline long long atomic64_fetch_xor(long long i, atomic64_t *v) +static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c) c = old; return old; } -static inline long long atomic64_fetch_add(long long i, atomic64_t *v) +static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v) { long long old, c = 0; - while ((old = atomic64_cmpxchg(v, c, c + i)) != c) + while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c) c = old; return old; } -#define atomic64_fetch_sub(i, v) atomic64_fetch_add(-(i), (v)) +#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), (v)) #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 738495caf05f..6106b59d3260 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -11,37 +11,37 @@ #define ATOMIC64_INIT(i) { (i) } /** - * atomic64_read - read atomic64 variable + * arch_atomic64_read - read atomic64 variable * @v: pointer of type atomic64_t * * Atomically reads the value of @v. * Doesn't imply a read memory barrier. */ -static inline long atomic64_read(const atomic64_t *v) +static inline long arch_atomic64_read(const atomic64_t *v) { return READ_ONCE((v)->counter); } /** - * atomic64_set - set atomic64 variable + * arch_atomic64_set - set atomic64 variable * @v: pointer to type atomic64_t * @i: required value * * Atomically sets the value of @v to @i. */ -static inline void atomic64_set(atomic64_t *v, long i) +static inline void arch_atomic64_set(atomic64_t *v, long i) { WRITE_ONCE(v->counter, i); } /** - * atomic64_add - add integer to atomic64 variable + * arch_atomic64_add - add integer to atomic64 variable * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v. */ -static __always_inline void atomic64_add(long i, atomic64_t *v) +static __always_inline void arch_atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) @@ -49,13 +49,13 @@ static __always_inline void atomic64_add(long i, atomic64_t *v) } /** - * atomic64_sub - subtract the atomic64 variable + * arch_atomic64_sub - subtract the atomic64 variable * @i: integer value to subtract * @v: pointer to type atomic64_t * * Atomically subtracts @i from @v. */ -static inline void atomic64_sub(long i, atomic64_t *v) +static inline void arch_atomic64_sub(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) @@ -63,7 +63,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) } /** - * atomic64_sub_and_test - subtract value from variable and test result + * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer to type atomic64_t * @@ -71,18 +71,18 @@ static inline void atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -static inline bool atomic64_sub_and_test(long i, atomic64_t *v) +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); } /** - * atomic64_inc - increment atomic64 variable + * arch_atomic64_inc - increment atomic64 variable * @v: pointer to type atomic64_t * * Atomically increments @v by 1. */ -static __always_inline void atomic64_inc(atomic64_t *v) +static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) @@ -90,12 +90,12 @@ static __always_inline void atomic64_inc(atomic64_t *v) } /** - * atomic64_dec - decrement atomic64 variable + * arch_atomic64_dec - decrement atomic64 variable * @v: pointer to type atomic64_t * * Atomically decrements @v by 1. */ -static __always_inline void atomic64_dec(atomic64_t *v) +static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) @@ -103,33 +103,33 @@ static __always_inline void atomic64_dec(atomic64_t *v) } /** - * atomic64_dec_and_test - decrement and test + * arch_atomic64_dec_and_test - decrement and test * @v: pointer to type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ -static inline bool atomic64_dec_and_test(atomic64_t *v) +static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } /** - * atomic64_inc_and_test - increment and test + * arch_atomic64_inc_and_test - increment and test * @v: pointer to type atomic64_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ -static inline bool atomic64_inc_and_test(atomic64_t *v) +static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } /** - * atomic64_add_negative - add and test if negative + * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer to type atomic64_t * @@ -137,59 +137,59 @@ static inline bool atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline bool atomic64_add_negative(long i, atomic64_t *v) +static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } /** - * atomic64_add_return - add and return + * arch_atomic64_add_return - add and return * @i: integer value to add * @v: pointer to type atomic64_t * * Atomically adds @i to @v and returns @i + @v */ -static __always_inline long atomic64_add_return(long i, atomic64_t *v) +static __always_inline long arch_atomic64_add_return(long i, atomic64_t *v) { return i + xadd(&v->counter, i); } -static inline long atomic64_sub_return(long i, atomic64_t *v) +static inline long arch_atomic64_sub_return(long i, atomic64_t *v) { - return atomic64_add_return(-i, v); + return arch_atomic64_add_return(-i, v); } -static inline long atomic64_fetch_add(long i, atomic64_t *v) +static inline long arch_atomic64_fetch_add(long i, atomic64_t *v) { return xadd(&v->counter, i); } -static inline long atomic64_fetch_sub(long i, atomic64_t *v) +static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v) { return xadd(&v->counter, -i); } -#define atomic64_inc_return(v) (atomic64_add_return(1, (v))) -#define atomic64_dec_return(v) (atomic64_sub_return(1, (v))) +#define arch_atomic64_inc_return(v) (arch_atomic64_add_return(1, (v))) +#define arch_atomic64_dec_return(v) (arch_atomic64_sub_return(1, (v))) -static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new) +static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new) { - return cmpxchg(&v->counter, old, new); + return arch_cmpxchg(&v->counter, old, new); } -#define atomic64_try_cmpxchg atomic64_try_cmpxchg -static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new) +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg +static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new) { return try_cmpxchg(&v->counter, old, new); } -static inline long atomic64_xchg(atomic64_t *v, long new) +static inline long arch_atomic64_xchg(atomic64_t *v, long new) { return xchg(&v->counter, new); } /** - * atomic64_add_unless - add unless the number is a given value + * arch_atomic64_add_unless - add unless the number is a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. @@ -197,37 +197,37 @@ static inline long atomic64_xchg(atomic64_t *v, long new) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static inline bool atomic64_add_unless(atomic64_t *v, long a, long u) +static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u) { - s64 c = atomic64_read(v); + s64 c = arch_atomic64_read(v); do { if (unlikely(c == u)) return false; - } while (!atomic64_try_cmpxchg(v, &c, c + a)); + } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); return true; } -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0) /* - * atomic64_dec_if_positive - decrement by 1 if old value positive + * arch_atomic64_dec_if_positive - decrement by 1 if old value positive * @v: pointer of type atomic_t * * The function returns the old value of *v minus 1, even if * the atomic variable, v, was not decremented. */ -static inline long atomic64_dec_if_positive(atomic64_t *v) +static inline long arch_atomic64_dec_if_positive(atomic64_t *v) { - s64 dec, c = atomic64_read(v); + s64 dec, c = arch_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; - } while (!atomic64_try_cmpxchg(v, &c, dec)); + } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); return dec; } -static inline void atomic64_and(long i, atomic64_t *v) +static inline void arch_atomic64_and(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "andq %1,%0" : "+m" (v->counter) @@ -235,16 +235,16 @@ static inline void atomic64_and(long i, atomic64_t *v) : "memory"); } -static inline long atomic64_fetch_and(long i, atomic64_t *v) +static inline long arch_atomic64_fetch_and(long i, atomic64_t *v) { - s64 val = atomic64_read(v); + s64 val = arch_atomic64_read(v); do { - } while (!atomic64_try_cmpxchg(v, &val, val & i)); + } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); return val; } -static inline void atomic64_or(long i, atomic64_t *v) +static inline void arch_atomic64_or(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "orq %1,%0" : "+m" (v->counter) @@ -252,16 +252,16 @@ static inline void atomic64_or(long i, atomic64_t *v) : "memory"); } -static inline long atomic64_fetch_or(long i, atomic64_t *v) +static inline long arch_atomic64_fetch_or(long i, atomic64_t *v) { - s64 val = atomic64_read(v); + s64 val = arch_atomic64_read(v); do { - } while (!atomic64_try_cmpxchg(v, &val, val | i)); + } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); return val; } -static inline void atomic64_xor(long i, atomic64_t *v) +static inline void arch_atomic64_xor(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "xorq %1,%0" : "+m" (v->counter) @@ -269,12 +269,12 @@ static inline void atomic64_xor(long i, atomic64_t *v) : "memory"); } -static inline long atomic64_fetch_xor(long i, atomic64_t *v) +static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v) { - s64 val = atomic64_read(v); + s64 val = arch_atomic64_read(v); do { - } while (!atomic64_try_cmpxchg(v, &val, val ^ i)); + } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); return val; } diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 30d406146016..042b5e892ed1 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -40,7 +40,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, asm ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) - :"r"(size),"r" (index) + :"g"(size),"r" (index) :"cc"); return mask; } @@ -52,11 +52,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ "lfence", X86_FEATURE_LFENCE_RDTSC) -#ifdef CONFIG_X86_PPRO_FENCE -#define dma_rmb() rmb() -#else #define dma_rmb() barrier() -#endif #define dma_wmb() barrier() #ifdef CONFIG_X86_32 @@ -68,30 +64,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -#if defined(CONFIG_X86_PPRO_FENCE) - -/* - * For this option x86 doesn't have a strong TSO memory - * model and we should fall back to full barriers. - */ - -#define __smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - __smp_mb(); \ - WRITE_ONCE(*p, v); \ -} while (0) - -#define __smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - __smp_mb(); \ - ___p1; \ -}) - -#else /* regular x86 TSO memory ordering */ - #define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ @@ -107,8 +79,6 @@ do { \ ___p1; \ }) -#endif - /* Atomic operations are already serializing on x86 */ #define __smp_mb__before_atomic() barrier() #define __smp_mb__after_atomic() barrier() diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 3fa039855b8f..9f645ba57dbb 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)CONST_MASK(nr)) : "memory"); } else { - asm volatile(LOCK_PREFIX "bts %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); } } @@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long *addr) */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); } /** @@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)~CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btr %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -137,7 +137,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); } static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -182,7 +182,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long * */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); } /** @@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btc %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -217,7 +217,8 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), + *addr, "Ir", nr, "%0", c); } /** @@ -246,7 +247,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1" + asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -263,7 +264,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), + *addr, "Ir", nr, "%0", c); } /** @@ -286,7 +288,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1" + asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -298,7 +300,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1" + asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -316,7 +318,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), + *addr, "Ir", nr, "%0", c); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) @@ -329,7 +332,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1" + asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 34d99af43994..6804d6642767 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -5,23 +5,20 @@ #include <linux/stringify.h> /* - * Since some emulators terminate on UD2, we cannot use it for WARN. - * Since various instruction decoders disagree on the length of UD1, - * we cannot use it either. So use UD0 for WARN. + * Despite that some emulators terminate on UD2, we use it for WARN(). * - * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas - * our kernel decoder thinks it takes a ModRM byte, which seems consistent - * with various things like the Intel SDM instruction encoding rules) + * Since various instruction decoders/specs disagree on the encoding of + * UD0/UD1. */ -#define ASM_UD0 ".byte 0x0f, 0xff" +#define ASM_UD0 ".byte 0x0f, 0xff" /* + ModRM (for Intel) */ #define ASM_UD1 ".byte 0x0f, 0xb9" /* + ModRM */ #define ASM_UD2 ".byte 0x0f, 0x0b" #define INSN_UD0 0xff0f #define INSN_UD2 0x0b0f -#define LEN_UD0 2 +#define LEN_UD2 2 #ifdef CONFIG_GENERIC_BUG @@ -77,7 +74,11 @@ do { \ unreachable(); \ } while (0) -#define __WARN_FLAGS(flags) _BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags)) +#define __WARN_FLAGS(flags) \ +do { \ + _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ + annotate_reachable(); \ +} while (0) #include <asm-generic/bug.h> diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 56bd436ed01b..e3efd8a06066 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -145,13 +145,13 @@ extern void __add_wrong_size(void) # include <asm/cmpxchg_64.h> #endif -#define cmpxchg(ptr, old, new) \ +#define arch_cmpxchg(ptr, old, new) \ __cmpxchg(ptr, old, new, sizeof(*(ptr))) -#define sync_cmpxchg(ptr, old, new) \ +#define arch_sync_cmpxchg(ptr, old, new) \ __sync_cmpxchg(ptr, old, new, sizeof(*(ptr))) -#define cmpxchg_local(ptr, old, new) \ +#define arch_cmpxchg_local(ptr, old, new) \ __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) @@ -221,7 +221,7 @@ extern void __add_wrong_size(void) #define __try_cmpxchg(ptr, pold, new, size) \ __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) -#define try_cmpxchg(ptr, pold, new) \ +#define try_cmpxchg(ptr, pold, new) \ __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) /* @@ -250,10 +250,10 @@ extern void __add_wrong_size(void) __ret; \ }) -#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \ +#define arch_cmpxchg_double(p1, p2, o1, o2, n1, n2) \ __cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2) -#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ +#define arch_cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \ __cmpxchg_double(, p1, p2, o1, o2, n1, n2) #endif /* ASM_X86_CMPXCHG_H */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 1732704f0445..1a2eafca7038 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -36,10 +36,10 @@ static inline void set_64bit(volatile u64 *ptr, u64 value) } #ifdef CONFIG_X86_CMPXCHG64 -#define cmpxchg64(ptr, o, n) \ +#define arch_cmpxchg64(ptr, o, n) \ ((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \ (unsigned long long)(n))) -#define cmpxchg64_local(ptr, o, n) \ +#define arch_cmpxchg64_local(ptr, o, n) \ ((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \ (unsigned long long)(n))) #endif @@ -76,7 +76,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) * to simulate the cmpxchg8b on the 80386 and 80486 CPU. */ -#define cmpxchg64(ptr, o, n) \ +#define arch_cmpxchg64(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ __typeof__(*(ptr)) __old = (o); \ @@ -93,7 +93,7 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) __ret; }) -#define cmpxchg64_local(ptr, o, n) \ +#define arch_cmpxchg64_local(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ __typeof__(*(ptr)) __old = (o); \ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 03cad196a301..bfca3b346c74 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -7,13 +7,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) *ptr = val; } -#define cmpxchg64(ptr, o, n) \ +#define arch_cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg((ptr), (o), (n)); \ }) -#define cmpxchg64_local(ptr, o, n) \ +#define arch_cmpxchg64_local(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ cmpxchg_local((ptr), (o), (n)); \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 70eddb3922ff..b27da9602a6d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -140,7 +140,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) -#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). * These will statically patch the target code for additional @@ -148,45 +147,46 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline __pure bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P1\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P0\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" - : : "i" (bit), "i" (X86_FEATURE_ALWAYS), - [bitnum] "i" (1 << (bit & 7)), - [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) - : : t_yes, t_no); - t_yes: - return true; - t_no: - return false; + asm_volatile_goto("1: jmp 6f\n" + "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 4f - .\n" /* repl offset */ + " .word %P[always]\n" /* always replace */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ + ".previous\n" + ".section .altinstr_replacement,\"ax\"\n" + "4: jmp %l[t_no]\n" + "5:\n" + ".previous\n" + ".section .altinstructions,\"a\"\n" + " .long 1b - .\n" /* src offset */ + " .long 0\n" /* no replacement */ + " .word %P[feature]\n" /* feature bit */ + " .byte 3b - 1b\n" /* src len */ + " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ + ".previous\n" + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" + : : [feature] "i" (bit), + [always] "i" (X86_FEATURE_ALWAYS), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; } #define static_cpu_has(bit) \ @@ -195,13 +195,6 @@ static __always_inline __pure bool _static_cpu_has(u16 bit) boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) -#else -/* - * Fall back to dynamic for gcc versions which don't support asm goto. Should be - * a minority now anyway. - */ -#define static_cpu_has(bit) boot_cpu_has(bit) -#endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..d554c11e01ff 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -315,6 +316,7 @@ #define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ #define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ #define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ @@ -327,6 +329,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 5e12c63b47aa..a8f6c809d9b1 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -6,6 +6,9 @@ struct dev_archdata { #if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU) void *iommu; /* hook for IOMMU specific extension */ #endif +#ifdef CONFIG_STA2X11 + bool is_sta2x11; +#endif }; #if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h index 1295bc622ebe..1a19251eaac9 100644 --- a/arch/x86/include/asm/dma-direct.h +++ b/arch/x86/include/asm/dma-direct.h @@ -2,29 +2,8 @@ #ifndef ASM_X86_DMA_DIRECT_H #define ASM_X86_DMA_DIRECT_H 1 -#include <linux/mem_encrypt.h> - -#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size); -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr); -#else -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return 0; - - return addr + size - 1 <= *dev->dma_mask; -} - -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - return __sme_set(paddr); -} +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) -{ - return __sme_clr(daddr); -} -#endif /* CONFIG_X86_DMA_REMAP */ #endif /* ASM_X86_DMA_DIRECT_H */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 6277c83c0eb1..89ce4bfd241f 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -36,37 +36,4 @@ int arch_dma_supported(struct device *dev, u64 mask); bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); #define arch_dma_alloc_attrs arch_dma_alloc_attrs -extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag, - unsigned long attrs); - -extern void dma_generic_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_addr, - unsigned long attrs); - -static inline unsigned long dma_alloc_coherent_mask(struct device *dev, - gfp_t gfp) -{ - unsigned long dma_mask = 0; - - dma_mask = dev->coherent_dma_mask; - if (!dma_mask) - dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32); - - return dma_mask; -} - -static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) -{ - unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp); - - if (dma_mask <= DMA_BIT_MASK(24)) - gfp |= GFP_DMA; -#ifdef CONFIG_X86_64 - if (dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) - gfp |= GFP_DMA32; -#endif - return gfp; -} - #endif diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 85f6ccb80b91..cec5fae23eb3 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -6,6 +6,8 @@ #include <asm/pgtable.h> #include <asm/processor-flags.h> #include <asm/tlb.h> +#include <asm/nospec-branch.h> +#include <asm/mmu_context.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -36,8 +38,18 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); -#define arch_efi_call_virt_setup() kernel_fpu_begin() -#define arch_efi_call_virt_teardown() kernel_fpu_end() +#define arch_efi_call_virt_setup() \ +({ \ + kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ +}) + +#define arch_efi_call_virt_teardown() \ +({ \ + firmware_restrict_branch_speculation_end(); \ + kernel_fpu_end(); \ +}) + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. @@ -58,14 +70,13 @@ extern asmlinkage u64 efi_call(void *fp, ...); #define efi_call_phys(f, args...) efi_call((f), args) /* - * Scratch space used for switching the pagetable in the EFI stub + * struct efi_scratch - Scratch space used while switching to/from efi_mm + * @phys_stack: stack used during EFI Mixed Mode + * @prev_mm: store/restore stolen mm_struct while switching to/from efi_mm */ struct efi_scratch { - u64 r15; - u64 prev_cr3; - pgd_t *efi_pgt; - bool use_pgd; - u64 phys_stack; + u64 phys_stack; + struct mm_struct *prev_mm; } __packed; #define arch_efi_call_virt_setup() \ @@ -73,12 +84,10 @@ struct efi_scratch { efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ \ - if (efi_scratch.use_pgd) { \ - efi_scratch.prev_cr3 = __read_cr3(); \ - write_cr3((unsigned long)efi_scratch.efi_pgt); \ - __flush_tlb_all(); \ - } \ + if (!efi_enabled(EFI_OLD_MEMMAP)) \ + efi_switch_mm(&efi_mm); \ }) #define arch_efi_call_virt(p, f, args...) \ @@ -86,11 +95,10 @@ struct efi_scratch { #define arch_efi_call_virt_teardown() \ ({ \ - if (efi_scratch.use_pgd) { \ - write_cr3(efi_scratch.prev_cr3); \ - __flush_tlb_all(); \ - } \ + if (!efi_enabled(EFI_OLD_MEMMAP)) \ + efi_switch_mm(efi_scratch.prev_mm); \ \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ }) @@ -131,6 +139,7 @@ extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); +extern void efi_switch_mm(struct mm_struct *mm); struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 2851077b6051..32e666e1231e 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -36,6 +36,7 @@ extern asmlinkage void kvm_posted_intr_wakeup_ipi(void); extern asmlinkage void kvm_posted_intr_nested_ipi(void); extern asmlinkage void error_interrupt(void); extern asmlinkage void irq_work_interrupt(void); +extern asmlinkage void uv_bau_message_intr1(void); extern asmlinkage void spurious_interrupt(void); extern asmlinkage void thermal_interrupt(void); diff --git a/arch/x86/include/asm/intel_pconfig.h b/arch/x86/include/asm/intel_pconfig.h new file mode 100644 index 000000000000..3cb002b1d0f9 --- /dev/null +++ b/arch/x86/include/asm/intel_pconfig.h @@ -0,0 +1,65 @@ +#ifndef _ASM_X86_INTEL_PCONFIG_H +#define _ASM_X86_INTEL_PCONFIG_H + +#include <asm/asm.h> +#include <asm/processor.h> + +enum pconfig_target { + INVALID_TARGET = 0, + MKTME_TARGET = 1, + PCONFIG_TARGET_NR +}; + +int pconfig_target_supported(enum pconfig_target target); + +enum pconfig_leaf { + MKTME_KEY_PROGRAM = 0, + PCONFIG_LEAF_INVALID, +}; + +#define PCONFIG ".byte 0x0f, 0x01, 0xc5" + +/* Defines and structure for MKTME_KEY_PROGRAM of PCONFIG instruction */ + +/* mktme_key_program::keyid_ctrl COMMAND, bits [7:0] */ +#define MKTME_KEYID_SET_KEY_DIRECT 0 +#define MKTME_KEYID_SET_KEY_RANDOM 1 +#define MKTME_KEYID_CLEAR_KEY 2 +#define MKTME_KEYID_NO_ENCRYPT 3 + +/* mktme_key_program::keyid_ctrl ENC_ALG, bits [23:8] */ +#define MKTME_AES_XTS_128 (1 << 8) + +/* Return codes from the PCONFIG MKTME_KEY_PROGRAM */ +#define MKTME_PROG_SUCCESS 0 +#define MKTME_INVALID_PROG_CMD 1 +#define MKTME_ENTROPY_ERROR 2 +#define MKTME_INVALID_KEYID 3 +#define MKTME_INVALID_ENC_ALG 4 +#define MKTME_DEVICE_BUSY 5 + +/* Hardware requires the structure to be 256 byte alinged. Otherwise #GP(0). */ +struct mktme_key_program { + u16 keyid; + u32 keyid_ctrl; + u8 __rsvd[58]; + u8 key_field_1[64]; + u8 key_field_2[64]; +} __packed __aligned(256); + +static inline int mktme_key_program(struct mktme_key_program *key_program) +{ + unsigned long rax = MKTME_KEY_PROGRAM; + + if (!pconfig_target_supported(MKTME_TARGET)) + return -ENXIO; + + asm volatile(PCONFIG + : "=a" (rax), "=b" (key_program) + : "0" (rax), "1" (key_program) + : "memory", "cc"); + + return rax; +} + +#endif /* _ASM_X86_INTEL_PCONFIG_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 95e948627fd0..f6e5b9375d8c 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -232,21 +232,6 @@ extern void set_iounmap_nonlazy(void); */ #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) -/* - * Cache management - * - * This needed for two cases - * 1. Out of order aware processors - * 2. Accidentally out of order processors (PPro errata #51) - */ - -static inline void flush_write_buffers(void) -{ -#if defined(CONFIG_X86_PPRO_FENCE) - asm volatile("lock; addl $0,0(%%esp)": : :"memory"); -#endif -} - #endif /* __KERNEL__ */ extern void native_io_delay(void); diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index a8834dd546cd..fd20a2334885 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -183,16 +183,17 @@ extern void disable_ioapic_support(void); extern void __init io_apic_init_mappings(void); extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg); -extern void native_disable_io_apic(void); +extern void native_restore_boot_irq_mode(void); static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { - return x86_io_apic_ops.read(apic, reg); + return x86_apic_ops.io_apic_read(apic, reg); } extern void setup_IO_APIC(void); extern void enable_IO_APIC(void); -extern void disable_IO_APIC(void); +extern void clear_IO_APIC(void); +extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); #else /* !CONFIG_X86_IO_APIC */ @@ -228,10 +229,11 @@ static inline void mp_save_irq(struct mpc_intsrc *m) { } static inline void disable_ioapic_support(void) { } static inline void io_apic_init_mappings(void) { } #define native_io_apic_read NULL -#define native_disable_io_apic NULL +#define native_restore_boot_irq_mode NULL static inline void setup_IO_APIC(void) { } static inline void enable_IO_APIC(void) { } +static inline void restore_boot_irq_mode(void) { } #endif diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 1e5d5d92eb40..baedab8ac538 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -2,13 +2,10 @@ #ifndef _ASM_X86_IOMMU_H #define _ASM_X86_IOMMU_H -extern const struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_pass_through; -int x86_dma_supported(struct device *dev, u64 mask); - /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h index 875b54376689..b885a961a150 100644 --- a/arch/x86/include/asm/jailhouse_para.h +++ b/arch/x86/include/asm/jailhouse_para.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL2.0 */ /* - * Jailhouse paravirt_ops implementation + * Jailhouse paravirt detection * * Copyright (c) Siemens AG, 2015-2017 * diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 460991e3b529..db7ba2feb947 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -5,10 +5,6 @@ unsigned long kaslr_get_random_long(const char *purpose); #ifdef CONFIG_RANDOMIZE_MEMORY -extern unsigned long page_offset_base; -extern unsigned long vmalloc_base; -extern unsigned long vmemmap_base; - void kernel_randomize_memory(void); #else static inline void kernel_randomize_memory(void) { } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd6f57a54a26..b605a5b6a30c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -507,6 +507,7 @@ struct kvm_vcpu_arch { u64 smi_count; bool tpr_access_reporting; u64 ia32_xss; + u64 microcode_version; /* * Paging state of the vcpu @@ -1095,6 +1096,8 @@ struct kvm_x86_ops { int (*mem_enc_op)(struct kvm *kvm, void __user *argp); int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); + + int (*get_msr_feature)(struct kvm_msr_entry *entry); }; struct kvm_arch_async_pf { @@ -1464,7 +1467,4 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); - #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 96ea4b5ba658..8c7b3e5a2d01 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -138,58 +138,6 @@ struct mce_log_buffer { struct mce entry[MCE_LOG_LEN]; }; -struct mca_config { - bool dont_log_ce; - bool cmci_disabled; - bool lmce_disabled; - bool ignore_ce; - bool disabled; - bool ser; - bool recovery; - bool bios_cmci_threshold; - u8 banks; - s8 bootlog; - int tolerant; - int monarch_timeout; - int panic_timeout; - u32 rip_msr; -}; - -struct mce_vendor_flags { - /* - * Indicates that overflow conditions are not fatal, when set. - */ - __u64 overflow_recov : 1, - - /* - * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and - * Recovery. It indicates support for data poisoning in HW and deferred - * error interrupts. - */ - succor : 1, - - /* - * (AMD) SMCA: This bit indicates support for Scalable MCA which expands - * the register space for each MCA bank and also increases number of - * banks. Also, to accommodate the new banks and registers, the MCA - * register space is moved to a new MSR range. - */ - smca : 1, - - __reserved_0 : 61; -}; - -struct mca_msr_regs { - u32 (*ctl) (int bank); - u32 (*status) (int bank); - u32 (*addr) (int bank); - u32 (*misc) (int bank); -}; - -extern struct mce_vendor_flags mce_flags; - -extern struct mca_msr_regs msr_ops; - enum mce_notifier_prios { MCE_PRIO_FIRST = INT_MAX, MCE_PRIO_SRAO = INT_MAX - 1, @@ -346,6 +294,7 @@ enum smca_bank_types { SMCA_IF, /* Instruction Fetch */ SMCA_L2_CACHE, /* L2 Cache */ SMCA_DE, /* Decoder Unit */ + SMCA_RESERVED, /* Reserved */ SMCA_EX, /* Execution Unit */ SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 22c5f3e6f820..c0643831706e 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -22,6 +22,7 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; +extern bool sev_enabled; void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, unsigned long decrypted_kernel_vaddr, @@ -48,8 +49,6 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); -void swiotlb_set_mem_attributes(void *vaddr, unsigned long size); - bool sme_active(void); bool sev_active(void); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 55520cec8b27..2b7cc5397f80 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -6,20 +6,6 @@ #include <linux/earlycpio.h> #include <linux/initrd.h> -#define native_rdmsr(msr, val1, val2) \ -do { \ - u64 __val = __rdmsr((msr)); \ - (void)((val1) = (u32)__val); \ - (void)((val2) = (u32)(__val >> 32)); \ -} while (0) - -#define native_wrmsr(msr, low, high) \ - __wrmsr(msr, low, high) - -#define native_wrmsrl(msr, val) \ - __wrmsr((msr), (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)) - struct ucode_patch { struct list_head plist; void *data; /* Intel uses only this one */ @@ -37,7 +23,13 @@ struct cpu_signature { struct device; -enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +enum ucode_state { + UCODE_OK = 0, + UCODE_NEW, + UCODE_UPDATED, + UCODE_NFOUND, + UCODE_ERROR, +}; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -54,7 +46,7 @@ struct microcode_ops { * are being called. * See also the "Synchronization" section in microcode_core.c. */ - int (*apply_microcode) (int cpu); + enum ucode_state (*apply_microcode) (int cpu); int (*collect_cpu_info) (int cpu, struct cpu_signature *csig); }; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c931b88982a0..57e3785d0d26 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -24,11 +24,12 @@ static inline void paravirt_activate_mm(struct mm_struct *prev, #endif /* !CONFIG_PARAVIRT */ #ifdef CONFIG_PERF_EVENTS -extern struct static_key rdpmc_always_available; + +DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); static inline void load_mm_cr4(struct mm_struct *mm) { - if (static_key_false(&rdpmc_always_available) || + if (static_branch_unlikely(&rdpmc_always_available_key) || atomic_read(&mm->context.perf_rdpmc_allowed)) cr4_set_bits(X86_CR4_PCE); else @@ -74,6 +75,7 @@ static inline void *ldt_slot_va(int slot) return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); #else BUG(); + return (void *)fix_to_virt(FIX_HOLE); #endif } diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 30df295f6d94..04addd6e0a4a 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -108,6 +108,20 @@ static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) : : "c" (msr), "a"(low), "d" (high) : "memory"); } +#define native_rdmsr(msr, val1, val2) \ +do { \ + u64 __val = __rdmsr((msr)); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ +} while (0) + +#define native_wrmsr(msr, low, high) \ + __wrmsr(msr, low, high) + +#define native_wrmsrl(msr, val) \ + __wrmsr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)) + static inline unsigned long long native_read_msr(unsigned int msr) { unsigned long long val; @@ -218,9 +232,6 @@ static __always_inline unsigned long long rdtsc_ordered(void) return rdtsc(); } -/* Deprecated, keep it for a cycle for easier merging: */ -#define rdtscll(now) do { (now) = rdtsc_ordered(); } while (0) - static inline unsigned long long native_read_pmc(int counter) { DECLARE_ARGS(val, low, high); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4d57894635f2..f928ad9b143f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -6,6 +6,51 @@ #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> +#include <asm/msr-index.h> + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; #ifdef __ASSEMBLY__ @@ -23,6 +68,18 @@ .endm /* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +.macro ANNOTATE_RETPOLINE_SAFE + .Lannotate_\@: + .pushsection .discard.retpoline_safe + _ASM_PTR .Lannotate_\@ + .popsection +.endm + +/* * These are the bare retpoline primitives for indirect jmp and call. * Do not use these directly; they only exist to make the ALTERNATIVE * invocation below less ugly. @@ -58,9 +115,9 @@ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(jmp *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD #else jmp *\reg #endif @@ -69,18 +126,25 @@ .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(call *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ - __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD #else call *\reg #endif .endm -/* This clobbers the BX register */ -.macro FILL_RETURN_BUFFER nr:req ftr:req + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call __clear_rsb", \ftr + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: #endif .endm @@ -92,6 +156,12 @@ ".long 999b - .\n\t" \ ".popsection\n\t" +#define ANNOTATE_RETPOLINE_SAFE \ + "999:\n\t" \ + ".pushsection .discard.retpoline_safe\n\t" \ + _ASM_PTR " 999b\n\t" \ + ".popsection\n\t" + #if defined(CONFIG_X86_64) && defined(RETPOLINE) /* @@ -101,6 +171,7 @@ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE) @@ -112,7 +183,10 @@ * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ -# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ +# define CALL_NOSPEC \ + ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ @@ -155,20 +229,90 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - alternative_input("", - "call __fill_rsb", - X86_FEATURE_RETPOLINE, - ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } +#define alternative_msr_write(_msr, _val, _feature) \ + asm volatile(ALTERNATIVE("", \ + "movl %[msr], %%ecx\n\t" \ + "movl %[val], %%eax\n\t" \ + "movl $0, %%edx\n\t" \ + "wrmsr", \ + _feature) \ + : : [msr] "i" (_msr), [val] "i" (_val) \ + : "eax", "ecx", "edx", "memory") + static inline void indirect_branch_prediction_barrier(void) { - alternative_input("", - "call __ibp_barrier", - X86_FEATURE_USE_IBPB, - ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory")); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); } +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) + */ +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) + +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) + #endif /* __ASSEMBLY__ */ + +/* + * Below is used in the eBPF JIT compiler and emits the byte sequence + * for the following assembly: + * + * With retpolines configured: + * + * callq do_rop + * spec_trap: + * pause + * lfence + * jmp spec_trap + * do_rop: + * mov %rax,(%rsp) + * retq + * + * Without retpolines configured: + * + * jmp *%rax + */ +#ifdef CONFIG_RETPOLINE +# define RETPOLINE_RAX_BPF_JIT_SIZE 17 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT1_off32(0xE8, 7); /* callq do_rop */ \ + /* spec_trap: */ \ + EMIT2(0xF3, 0x90); /* pause */ \ + EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ + EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ + /* do_rop: */ \ + EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \ + EMIT1(0xC3); /* retq */ +#else +# define RETPOLINE_RAX_BPF_JIT_SIZE 2 +# define RETPOLINE_RAX_BPF_JIT() \ + EMIT2(0xFF, 0xE0); /* jmp *%rax */ +#endif + #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 4baa6bceb232..939b1cff4a7b 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -11,6 +11,10 @@ extern unsigned long max_pfn; extern unsigned long phys_base; +extern unsigned long page_offset_base; +extern unsigned long vmalloc_base; +extern unsigned long vmemmap_base; + static inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; @@ -47,15 +51,11 @@ static inline void clear_page(void *page) clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "0" (page) - : "memory", "rax", "rcx"); + : "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); -#ifdef CONFIG_X86_MCE -#define arch_unmap_kpfn arch_unmap_kpfn -#endif - #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index e1407312c412..2c5a966dc222 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -37,26 +37,24 @@ * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's * what Xen requires. */ -#ifdef CONFIG_X86_5LEVEL -#define __PAGE_OFFSET_BASE _AC(0xff10000000000000, UL) -#else -#define __PAGE_OFFSET_BASE _AC(0xffff880000000000, UL) -#endif +#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL) -#ifdef CONFIG_RANDOMIZE_MEMORY +#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT #define __PAGE_OFFSET page_offset_base #else -#define __PAGE_OFFSET __PAGE_OFFSET_BASE -#endif /* CONFIG_RANDOMIZE_MEMORY */ +#define __PAGE_OFFSET __PAGE_OFFSET_BASE_L4 +#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ #define __START_KERNEL_map _AC(0xffffffff80000000, UL) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ -#ifdef CONFIG_X86_5LEVEL + #define __PHYSICAL_MASK_SHIFT 52 -#define __VIRTUAL_MASK_SHIFT 56 + +#ifdef CONFIG_X86_5LEVEL +#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled ? 56 : 47) #else -#define __PHYSICAL_MASK_SHIFT 46 #define __VIRTUAL_MASK_SHIFT 47 #endif diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 892df375b615..9be2bf13825b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -7,6 +7,7 @@ #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #include <asm/paravirt_types.h> @@ -297,9 +298,9 @@ static inline void __flush_tlb_global(void) { PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); } -static inline void __flush_tlb_single(unsigned long addr) +static inline void __flush_tlb_one_user(unsigned long addr) { - PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr); + PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, @@ -567,17 +568,22 @@ static inline p4dval_t p4d_val(p4d_t p4d) return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d); } -static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) { - pgdval_t val = native_pgd_val(pgd); - - PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val); + PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd)); } -static inline void pgd_clear(pgd_t *pgdp) -{ - set_pgd(pgdp, __pgd(0)); -} +#define set_pgd(pgdp, pgdval) do { \ + if (pgtable_l5_enabled) \ + __set_pgd(pgdp, pgdval); \ + else \ + set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \ +} while (0) + +#define pgd_clear(pgdp) do { \ + if (pgtable_l5_enabled) \ + set_pgd(pgdp, __pgd(0)); \ +} while (0) #endif /* CONFIG_PGTABLE_LEVELS == 5 */ @@ -879,23 +885,27 @@ extern void default_banner(void); #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx #else /* !CONFIG_X86_32 */ @@ -917,21 +927,25 @@ extern void default_banner(void); */ #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ ) #define GET_CR2_INTO_RAX \ - call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 6ec54d01972d..180bc0bff0fb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -43,6 +43,7 @@ #include <asm/desc_defs.h> #include <asm/kmap_types.h> #include <asm/pgtable_types.h> +#include <asm/nospec-branch.h> struct page; struct thread_struct; @@ -217,7 +218,7 @@ struct pv_mmu_ops { /* TLB operations */ void (*flush_tlb_user)(void); void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_one_user)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, const struct flush_tlb_info *info); @@ -392,7 +393,9 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%c[paravirt_opptr];" +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index eb66fa9cd0fc..959d618dbb17 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -151,6 +151,8 @@ extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, phys_addr_t addr); extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end); extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus); +extern struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, + int end, u64 addr); extern struct list_head pci_mmcfg_list; diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index ba3c523aaf16..a06b07399d17 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1" + asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index aff42e1da6ee..263c142a6a6c 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -167,6 +167,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { + if (!pgtable_l5_enabled) + return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } @@ -191,7 +193,8 @@ extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - ___p4d_free_tlb(tlb, p4d); + if (pgtable_l5_enabled) + ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 876b4c77d983..6a59a6d0cc50 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -44,5 +44,6 @@ typedef union { */ #define PTRS_PER_PTE 512 +#define MAX_POSSIBLE_PHYSMEM_BITS 36 #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 63c2552b6b65..89d5c8886c85 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -65,7 +65,7 @@ extern pmdval_t early_pmd_flags; #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) -#define pgd_clear(pgd) native_pgd_clear(pgd) +#define pgd_clear(pgd) (pgtable_l5_enabled ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d @@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v | set); + return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v & ~clear); + return native_make_pmd(v & ~clear); } static inline pmd_t pmd_mkold(pmd_t pmd) @@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); - return __pud(v | set); + return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); - return __pud(v & ~clear); + return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) @@ -859,6 +859,8 @@ static inline unsigned long p4d_index(unsigned long address) #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { + if (!pgtable_l5_enabled) + return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } @@ -876,6 +878,8 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { + if (!pgtable_l5_enabled) + return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } @@ -883,6 +887,9 @@ static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; + if (!pgtable_l5_enabled) + return 0; + if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; @@ -891,6 +898,8 @@ static inline int pgd_bad(pgd_t pgd) static inline int pgd_none(pgd_t pgd) { + if (!pgtable_l5_enabled) + return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e67c0620aec2..88a056b01db4 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -32,6 +32,9 @@ extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } void paging_init(void); +void sync_initial_page_table(void); + +static inline int pgd_large(pgd_t pgd) { return 0; } /* * Define this if things work differently on an i386 and an i486: @@ -61,7 +64,7 @@ void paging_init(void); #define kpte_clear_flush(ptep, vaddr) \ do { \ pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ + __flush_tlb_one_kernel((vaddr)); \ } while (0) #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index 0777e18a1d23..e3225e83db7d 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -15,6 +15,8 @@ # include <asm/pgtable-2level_types.h> #endif +#define pgtable_l5_enabled 0 + #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 81462e9a34f6..877bc27718ae 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); +static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ @@ -217,29 +218,26 @@ static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { -#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL) - p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd); -#else - *p4dp = p4d; -#endif + pgd_t pgd; + + if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { + *p4dp = p4d; + return; + } + + pgd = native_make_pgd(native_p4d_val(p4d)); + pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd); + *p4dp = native_make_p4d(native_pgd_val(pgd)); } static inline void native_p4d_clear(p4d_t *p4d) { -#ifdef CONFIG_X86_5LEVEL native_set_p4d(p4d, native_make_p4d(0)); -#else - native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)}); -#endif } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION *pgdp = pti_set_user_pgd(pgdp, pgd); -#else - *pgdp = pgd; -#endif } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 6b8f73dcbc2c..d5c21a382475 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -20,6 +20,18 @@ typedef unsigned long pgprotval_t; typedef struct { pteval_t pte; } pte_t; +#ifdef CONFIG_X86_5LEVEL +extern unsigned int __pgtable_l5_enabled; +#ifndef pgtable_l5_enabled +#define pgtable_l5_enabled cpu_feature_enabled(X86_FEATURE_LA57) +#endif +#else +#define pgtable_l5_enabled 0 +#endif + +extern unsigned int pgdir_shift; +extern unsigned int ptrs_per_p4d; + #endif /* !__ASSEMBLY__ */ #define SHARED_KERNEL_PMD 0 @@ -29,24 +41,28 @@ typedef struct { pteval_t pte; } pte_t; /* * PGDIR_SHIFT determines what a top-level page table entry can map */ -#define PGDIR_SHIFT 48 +#define PGDIR_SHIFT pgdir_shift #define PTRS_PER_PGD 512 /* * 4th level page in 5-level paging case */ -#define P4D_SHIFT 39 -#define PTRS_PER_P4D 512 -#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) -#define P4D_MASK (~(P4D_SIZE - 1)) +#define P4D_SHIFT 39 +#define MAX_PTRS_PER_P4D 512 +#define PTRS_PER_P4D ptrs_per_p4d +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE - 1)) + +#define MAX_POSSIBLE_PHYSMEM_BITS 52 #else /* CONFIG_X86_5LEVEL */ /* * PGDIR_SHIFT determines what a top-level page table entry can map */ -#define PGDIR_SHIFT 39 -#define PTRS_PER_PGD 512 +#define PGDIR_SHIFT 39 +#define PTRS_PER_PGD 512 +#define MAX_PTRS_PER_P4D 1 #endif /* CONFIG_X86_5LEVEL */ @@ -82,31 +98,33 @@ typedef struct { pteval_t pte; } pte_t; * range must not overlap with anything except the KASAN shadow area, which * is correct as KASAN disables KASLR. */ -#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#define MAXMEM (1UL << MAX_PHYSMEM_BITS) -#ifdef CONFIG_X86_5LEVEL -# define VMALLOC_SIZE_TB _AC(12800, UL) -# define __VMALLOC_BASE _AC(0xffa0000000000000, UL) -# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) -# define LDT_PGD_ENTRY _AC(-112, UL) -# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) -#else -# define VMALLOC_SIZE_TB _AC(32, UL) -# define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) -# define LDT_PGD_ENTRY _AC(-3, UL) -# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) -#endif +#define LDT_PGD_ENTRY_L4 -3UL +#define LDT_PGD_ENTRY_L5 -112UL +#define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) +#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) + +#define __VMALLOC_BASE_L4 0xffffc90000000000 +#define __VMALLOC_BASE_L5 0xffa0000000000000 + +#define VMALLOC_SIZE_TB_L4 32UL +#define VMALLOC_SIZE_TB_L5 12800UL + +#define __VMEMMAP_BASE_L4 0xffffea0000000000 +#define __VMEMMAP_BASE_L5 0xffd4000000000000 -#ifdef CONFIG_RANDOMIZE_MEMORY +#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT # define VMALLOC_START vmalloc_base +# define VMALLOC_SIZE_TB (pgtable_l5_enabled ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4) # define VMEMMAP_START vmemmap_base #else -# define VMALLOC_START __VMALLOC_BASE -# define VMEMMAP_START __VMEMMAP_BASE -#endif /* CONFIG_RANDOMIZE_MEMORY */ +# define VMALLOC_START __VMALLOC_BASE_L4 +# define VMALLOC_SIZE_TB VMALLOC_SIZE_TB_L4 +# define VMEMMAP_START __VMEMMAP_BASE_L4 +#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ -#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) +#define VMALLOC_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1) #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) /* The module sections ends with the start of the fixmap */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 3696398a9475..acfe755562a6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -174,7 +174,6 @@ enum page_cache_mode { #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -206,7 +205,6 @@ enum page_cache_mode { #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) @@ -323,6 +321,11 @@ static inline pudval_t native_pud_val(pud_t pud) #else #include <asm-generic/pgtable-nopud.h> +static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); @@ -344,6 +347,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) #else #include <asm-generic/pgtable-nopmd.h> +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 793bae7e7ce3..b0ccd4847a58 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -91,7 +91,7 @@ struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; - __u8 x86_mask; + __u8 x86_stepping; #ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; @@ -109,7 +109,7 @@ struct cpuinfo_x86 { char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ - int x86_cache_size; + unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ /* Cache QoS architectural values: */ int x86_cache_max_rmid; /* max index */ @@ -977,7 +977,5 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); - -void __ibp_barrier(void); - +void microcode_check(void); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4e44250e7d0d..4cf11d88d3b3 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -17,7 +17,7 @@ #define _REFCOUNT_EXCEPTION \ ".pushsection .text..refcount\n" \ "111:\tlea %[counter], %%" _ASM_CX "\n" \ - "112:\t" ASM_UD0 "\n" \ + "112:\t" ASM_UD2 "\n" \ ASM_UNREACHABLE \ ".popsection\n" \ "113:\n" \ @@ -67,13 +67,13 @@ static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "er", i, "%0", e); + r->refs.counter, "er", i, "%0", e, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "%0", e); + r->refs.counter, "%0", e, "cx"); } static __always_inline __must_check diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index fb3a6de7440b..6847d85400a8 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -53,12 +53,6 @@ # define NEED_MOVBE 0 #endif -#ifdef CONFIG_X86_5LEVEL -# define NEED_LA57 (1<<(X86_FEATURE_LA57 & 31)) -#else -# define NEED_LA57 0 -#endif - #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT /* Paravirtualized systems may not have PSE or PGE available */ @@ -104,7 +98,7 @@ #define REQUIRED_MASK13 0 #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 -#define REQUIRED_MASK16 (NEED_LA57) +#define REQUIRED_MASK16 0 #define REQUIRED_MASK17 0 #define REQUIRED_MASK18 0 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index f91c365e57c3..4914a3e7c803 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -2,8 +2,7 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc -#define __CLOBBERS_MEM "memory" -#define __CLOBBERS_MEM_CC_CX "memory", "cc", "cx" +#define __CLOBBERS_MEM(clb...) "memory", ## clb #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) @@ -40,18 +39,19 @@ do { \ #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM) + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) -#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc) \ +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\ __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX) + __CLOBBERS_MEM(clobbers)) #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ - __CLOBBERS_MEM, vcon (val)) + __CLOBBERS_MEM(), vcon (val)) -#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc) \ +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \ + clobbers...) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX, vcon (val)) + __CLOBBERS_MEM(clobbers), vcon (val)) #endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index d6baf23782bc..5c019d23d06b 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; +extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..f75bff8f9d82 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); +void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); @@ -176,16 +177,6 @@ static inline int wbinvd_on_all_cpus(void) extern unsigned disabled_cpus; #ifdef CONFIG_X86_LOCAL_APIC - -#ifndef CONFIG_X86_64 -static inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); -} - -#endif - extern int hard_smp_processor_id(void); #else /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 4fc1e9d3c43e..4617a2bf123c 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -27,13 +27,8 @@ # endif #else /* CONFIG_X86_32 */ # define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */ -# ifdef CONFIG_X86_5LEVEL -# define MAX_PHYSADDR_BITS 52 -# define MAX_PHYSMEM_BITS 52 -# else -# define MAX_PHYSADDR_BITS 44 -# define MAX_PHYSMEM_BITS 46 -# endif +# define MAX_PHYSADDR_BITS (pgtable_l5_enabled ? 52 : 44) +# define MAX_PHYSMEM_BITS (pgtable_l5_enabled ? 52 : 46) #endif #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f73706878772..133d9425fced 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -87,8 +87,6 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs) void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl); -extern unsigned int code_bytes; - /* The form of the top of the frame on the stack */ struct stack_frame { struct stack_frame *next_frame; diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 1c6a6cb230ff..ff6c92eff035 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -27,12 +27,4 @@ static inline void pci_swiotlb_late_init(void) { } #endif - -extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs); -extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_addr, - unsigned long attrs); - #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h deleted file mode 100644 index 82c34ee25a65..000000000000 --- a/arch/x86/include/asm/sys_ia32.h +++ /dev/null @@ -1,55 +0,0 @@ -/* - * sys_ia32.h - Linux ia32 syscall interfaces - * - * Copyright (c) 2008 Jaswinder Singh Rajput - * - * This file is released under the GPLv2. - * See the file COPYING for more details. - */ - -#ifndef _ASM_X86_SYS_IA32_H -#define _ASM_X86_SYS_IA32_H - -#ifdef CONFIG_COMPAT - -#include <linux/compiler.h> -#include <linux/linkage.h> -#include <linux/types.h> -#include <linux/signal.h> -#include <asm/compat.h> -#include <asm/ia32.h> - -/* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); -asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); - -asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, const char __user *, - struct stat64 __user *, int); -struct mmap_arg_struct32; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); - -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); - -asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); - -long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); -long sys32_vm86_warning(void); - -asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); -asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, - unsigned, unsigned, int); -asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int); -asmlinkage long sys32_fallocate(int, int, unsigned, - unsigned, unsigned, unsigned); - -/* ia32/ia32_signal.c */ -asmlinkage long sys32_sigreturn(void); -asmlinkage long sys32_rt_sigreturn(void); - -#endif /* CONFIG_COMPAT */ - -#endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index bad25bb80679..ae6e05fdc24b 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -17,6 +17,7 @@ /* Common in X86_32 and X86_64 */ /* kernel/ioport.c */ +long ksys_ioperm(unsigned long from, unsigned long num, int turn_on); asmlinkage long sys_ioperm(unsigned long, unsigned long, int); asmlinkage long sys_iopl(unsigned int); @@ -34,7 +35,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *); #ifdef CONFIG_X86_32 /* kernel/signal.c */ -asmlinkage unsigned long sys_sigreturn(void); +asmlinkage long sys_sigreturn(void); /* kernel/vm86_32.c */ struct vm86_struct; diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 2b8f18ca5874..84137c22fdfa 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -140,7 +140,7 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #else #define __flush_tlb() __native_flush_tlb() #define __flush_tlb_global() __native_flush_tlb_global() -#define __flush_tlb_single(addr) __native_flush_tlb_single(addr) +#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif static inline bool tlb_defer_switch_to_init_mm(void) @@ -400,7 +400,7 @@ static inline void __native_flush_tlb_global(void) /* * flush one page in the user mapping */ -static inline void __native_flush_tlb_single(unsigned long addr) +static inline void __native_flush_tlb_one_user(unsigned long addr) { u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); @@ -437,18 +437,31 @@ static inline void __flush_tlb_all(void) /* * flush one page in the kernel mapping */ -static inline void __flush_tlb_one(unsigned long addr) +static inline void __flush_tlb_one_kernel(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); + + /* + * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its + * paravirt equivalent. Even with PCID, this is sufficient: we only + * use PCID if we also use global PTEs for the kernel mapping, and + * INVLPG flushes global translations across all address spaces. + * + * If PTI is on, then the kernel is mapped with non-global PTEs, and + * __flush_tlb_one_user() will flush the given address for the current + * kernel address space and for its usermode counterpart, but it does + * not flush it for other address spaces. + */ + __flush_tlb_one_user(addr); if (!static_cpu_has(X86_FEATURE_PTI)) return; /* - * __flush_tlb_single() will have cleared the TLB entry for this ASID, - * but since kernel space is replicated across all, we must also - * invalidate all others. + * See above. We need to propagate the flush to all other address + * spaces. In principle, we only need to propagate it to kernelmode + * address spaces, but the extra bookkeeping we would need is not + * worth it. */ invalidate_other_asid(); } diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index cf5d53c3f9ea..2701d221583a 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -31,6 +31,7 @@ static inline cycles_t get_cycles(void) } extern struct system_counterval_t convert_art_to_tsc(u64 art); +extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); extern void tsc_early_delay_calibrate(void); extern void tsc_init(void); diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index ecb9ddef128f..62c79e26a59a 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -3833,7 +3833,7 @@ union uvh_rh_gam_mmioh_overlay_config0_mmr_u { #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR") #define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR") #define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1603000UL -#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x483000UL +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x484000UL #define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR ( \ is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \ is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR : \ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 8b6780751132..5db8b0b10766 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -352,6 +352,7 @@ enum vmcs_field { #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ +#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index fc2f082ac635..199e15bd3ec5 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -131,6 +131,16 @@ struct x86_hyper_init { }; /** + * struct x86_init_acpi - x86 ACPI init functions + * @get_root_pointer: get RSDP address + * @reduced_hw_early_init: hardware reduced platform early init + */ +struct x86_init_acpi { + u64 (*get_root_pointer)(void); + void (*reduced_hw_early_init)(void); +}; + +/** * struct x86_init_ops - functions for platform specific setup * */ @@ -144,6 +154,7 @@ struct x86_init_ops { struct x86_init_iommu iommu; struct x86_init_pci pci; struct x86_hyper_init hyper; + struct x86_init_acpi acpi; }; /** @@ -274,16 +285,16 @@ struct x86_msi_ops { void (*restore_msi_irqs)(struct pci_dev *dev); }; -struct x86_io_apic_ops { - unsigned int (*read) (unsigned int apic, unsigned int reg); - void (*disable)(void); +struct x86_apic_ops { + unsigned int (*io_apic_read) (unsigned int apic, unsigned int reg); + void (*restore)(void); }; extern struct x86_init_ops x86_init; extern struct x86_cpuinit_ops x86_cpuinit; extern struct x86_platform_ops x86_platform; extern struct x86_msi_ops x86_msi; -extern struct x86_io_apic_ops x86_io_apic_ops; +extern struct x86_apic_ops x86_apic_ops; extern void x86_early_init_platform_quirks(void); extern void x86_init_noop(void); diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 197c2e6c7376..099414345865 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -241,24 +241,24 @@ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 struct hv_reenlightenment_control { - u64 vector:8; - u64 reserved1:8; - u64 enabled:1; - u64 reserved2:15; - u64 target_vp:32; + __u64 vector:8; + __u64 reserved1:8; + __u64 enabled:1; + __u64 reserved2:15; + __u64 target_vp:32; }; #define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 #define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 struct hv_tsc_emulation_control { - u64 enabled:1; - u64 reserved:63; + __u64 enabled:1; + __u64 reserved:63; }; struct hv_tsc_emulation_status { - u64 inprogress:1; - u64 reserved:63; + __u64 inprogress:1; + __u64 reserved:63; }; #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 7a2ade4aa235..6cfa9c8cb7d6 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -26,6 +26,7 @@ #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 +#define KVM_FEATURE_ASYNC_PF_VMEXIT 10 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 91723461dc1f..955c2a2e1cf9 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -5,31 +5,36 @@ #include <linux/types.h> #include <linux/ioctl.h> -/* Fields are zero when not available */ +/* + * Fields are zero when not available. Also, this struct is shared with + * userspace mcelog and thus must keep existing fields at current offsets. + * Only add new fields to the end of the structure + */ struct mce { - __u64 status; - __u64 misc; - __u64 addr; - __u64 mcgstatus; - __u64 ip; - __u64 tsc; /* cpu time stamp counter */ - __u64 time; /* wall time_t when error was detected */ - __u8 cpuvendor; /* cpu vendor as encoded in system.h */ - __u8 inject_flags; /* software inject flags */ - __u8 severity; + __u64 status; /* Bank's MCi_STATUS MSR */ + __u64 misc; /* Bank's MCi_MISC MSR */ + __u64 addr; /* Bank's MCi_ADDR MSR */ + __u64 mcgstatus; /* Machine Check Global Status MSR */ + __u64 ip; /* Instruction Pointer when the error happened */ + __u64 tsc; /* CPU time stamp counter */ + __u64 time; /* Wall time_t when error was detected */ + __u8 cpuvendor; /* Kernel's X86_VENDOR enum */ + __u8 inject_flags; /* Software inject flags */ + __u8 severity; /* Error severity */ __u8 pad; - __u32 cpuid; /* CPUID 1 EAX */ - __u8 cs; /* code segment */ - __u8 bank; /* machine check bank */ - __u8 cpu; /* cpu number; obsolete; use extcpu now */ - __u8 finished; /* entry is valid */ - __u32 extcpu; /* linux cpu number that detected the error */ - __u32 socketid; /* CPU socket ID */ - __u32 apicid; /* CPU initial apic ID */ - __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */ - __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ - __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ - __u64 ppin; /* Protected Processor Inventory Number */ + __u32 cpuid; /* CPUID 1 EAX */ + __u8 cs; /* Code segment */ + __u8 bank; /* Machine check bank reporting the error */ + __u8 cpu; /* CPU number; obsoleted by extcpu */ + __u8 finished; /* Entry is valid */ + __u32 extcpu; /* Linux CPU number that detected the error */ + __u32 socketid; /* CPU socket ID */ + __u32 apicid; /* CPU initial APIC ID */ + __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */ + __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ + __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ + __u64 ppin; /* Protected Processor Inventory Number */ + __u32 microcode; /* Microcode revision */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 29786c87e864..02d6f5cf4e70 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -57,7 +57,7 @@ obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o -obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o +obj-y += alternative.o i8253.o hw_breakpoint.o obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o @@ -146,6 +146,6 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o - obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o + obj-$(CONFIG_MMCONF_FAM10H) += mmconf-fam10h_64.o obj-y += vsmp_64.o endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2aa92094b59d..7a37d9357bc4 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1376,17 +1376,21 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) * * We initialize the Hardware-reduced ACPI model here: */ +void __init acpi_generic_reduced_hw_init(void) +{ + /* + * Override x86_init functions and bypass legacy PIC in + * hardware reduced ACPI mode. + */ + x86_init.timers.timer_init = x86_init_noop; + x86_init.irqs.pre_vector_init = x86_init_noop; + legacy_pic = &null_legacy_pic; +} + static void __init acpi_reduced_hw_init(void) { - if (acpi_gbl_reduced_hardware) { - /* - * Override x86_init functions and bypass legacy pic - * in Hardware-reduced ACPI mode - */ - x86_init.timers.timer_init = x86_init_noop; - x86_init.irqs.pre_vector_init = x86_init_noop; - legacy_pic = &null_legacy_pic; - } + if (acpi_gbl_reduced_hardware) + x86_init.acpi.reduced_hw_early_init(); } /* diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index ecd486cb06ab..f299d8a479bb 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -480,30 +480,21 @@ static void * gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, unsigned long attrs) { - dma_addr_t paddr; - unsigned long align_mask; - struct page *page; - - if (force_iommu && !(flag & GFP_DMA)) { - flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - page = alloc_pages(flag | __GFP_ZERO, get_order(size)); - if (!page) - return NULL; - - align_mask = (1UL << get_order(size)) - 1; - paddr = dma_map_area(dev, page_to_phys(page), size, - DMA_BIDIRECTIONAL, align_mask); - - flush_gart(); - if (paddr != bad_dma_addr) { - *dma_addr = paddr; - return page_address(page); - } - __free_pages(page, get_order(size)); - } else - return dma_generic_alloc_coherent(dev, size, dma_addr, flag, - attrs); + void *vaddr; + + vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs); + if (!vaddr || + !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24)) + return vaddr; + *dma_addr = dma_map_area(dev, virt_to_phys(vaddr), size, + DMA_BIDIRECTIONAL, (1UL << get_order(size)) - 1); + flush_gart(); + if (unlikely(*dma_addr == bad_dma_addr)) + goto out_free; + return vaddr; +out_free: + dma_direct_free(dev, size, vaddr, *dma_addr, attrs); return NULL; } @@ -513,7 +504,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, unsigned long attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0); - dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); + dma_direct_free(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -705,7 +696,7 @@ static const struct dma_map_ops gart_dma_ops = { .alloc = gart_alloc_coherent, .free = gart_free_coherent, .mapping_error = gart_mapping_error, - .dma_supported = x86_dma_supported, + .dma_supported = dma_direct_supported, }; static void gart_iommu_shutdown(void) diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 6db28f17ff28..c88e0b127810 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -235,7 +235,7 @@ int amd_cache_northbridges(void) if (boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model >= 0x8 && (boot_cpu_data.x86_model > 0x9 || - boot_cpu_data.x86_mask >= 0x1)) + boot_cpu_data.x86_stepping >= 0x1)) amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE; if (boot_cpu_data.x86 == 0x15) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 25ddf02598d2..2aabd4cb0e3f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -546,7 +546,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static u32 hsx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ case 0x04: return 0x0f; /* EX */ } @@ -556,7 +556,7 @@ static u32 hsx_deadline_rev(void) static u32 bdx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; case 0x03: return 0x0700000e; case 0x04: return 0x0f00000c; @@ -568,7 +568,7 @@ static u32 bdx_deadline_rev(void) static u32 skx_deadline_rev(void) { - switch (boot_cpu_data.x86_mask) { + switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; case 0x04: return 0x02000014; } @@ -1408,22 +1408,69 @@ static void lapic_setup_esr(void) oldvalue, value); } +static void apic_pending_intr_clear(void) +{ + long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned long long tsc = 0, ntsc; + unsigned int queued; + unsigned long value; + int i, j, acked = 0; + + if (boot_cpu_has(X86_FEATURE_TSC)) + tsc = rdtsc(); + /* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now CPU has serviced that pending interrupt and + * it might not have done the ack_APIC_irq() because it thought, + * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it + * does not clear the ISR bit and cpu thinks it has already serivced + * the interrupt. Hence a vector might get locked. It was noticed + * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + */ + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for_each_set_bit(j, &value, 32) { + ack_APIC_irq(); + acked++; + } + } + if (acked > 256) { + pr_err("LAPIC pending interrupts after %d EOI\n", acked); + break; + } + if (queued) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { + ntsc = rdtsc(); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else { + max_loops--; + } + } + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); +} + /** * setup_local_APIC - setup the local APIC * * Used to setup local APIC while initializing BSP or bringing up APs. * Always called with preemption disabled. */ -void setup_local_APIC(void) +static void setup_local_APIC(void) { int cpu = smp_processor_id(); - unsigned int value, queued; - int i, j, acked = 0; - unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned int value; +#ifdef CONFIG_X86_32 + int logical_apicid, ldr_apicid; +#endif - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1460,11 +1507,11 @@ void setup_local_APIC(void) * initialized during get_smp_config(), make sure it matches the * actual value. */ - i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = - logical_smp_processor_id(); + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; #endif /* @@ -1475,45 +1522,7 @@ void setup_local_APIC(void) value &= ~APIC_TPRI_MASK; apic_write(APIC_TASKPRI, value); - /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. - */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) { - ack_APIC_irq(); - acked++; - } - } - } - if (acked > 256) { - printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", - acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); - } else - max_loops--; - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + apic_pending_intr_clear(); /* * Now that we are all set up, enable the APIC @@ -1570,7 +1579,7 @@ void setup_local_APIC(void) * TODO: set up through-local-APIC from through-I/O-APIC? --macro */ value = apic_read(APIC_LVT0) & APIC_LVT_MASKED; - if (!cpu && (pic_mode || !value)) { + if (!cpu && (pic_mode || !value || skip_ioapic_setup)) { value = APIC_DM_EXTINT; apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu); } else { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8ad2e410974f..7553819c74c3 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -587,7 +587,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) mpc_ioapic_id(apic), pin); } -static void clear_IO_APIC (void) +void clear_IO_APIC (void) { int apic, pin; @@ -1410,7 +1410,7 @@ void __init enable_IO_APIC(void) clear_IO_APIC(); } -void native_disable_io_apic(void) +void native_restore_boot_irq_mode(void) { /* * If the i8259 is routed through an IOAPIC @@ -1438,20 +1438,12 @@ void native_disable_io_apic(void) disconnect_bsp_APIC(ioapic_i8259.pin != -1); } -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) +void restore_boot_irq_mode(void) { - /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - if (!nr_legacy_irqs()) return; - x86_io_apic_ops.disable(); + x86_apic_ops.restore(); } #ifdef CONFIG_X86_32 @@ -1603,7 +1595,7 @@ static void __init delay_with_tsc(void) do { rep_nop(); now = rdtsc(); - } while ((now - start) < 40000000000UL / HZ && + } while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end)); } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3cc471beb50b..bb6f7a2148d7 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -134,21 +134,40 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, { struct apic_chip_data *apicd = apic_chip_data(irqd); struct irq_desc *desc = irq_data_to_desc(irqd); + bool managed = irqd_affinity_is_managed(irqd); lockdep_assert_held(&vector_lock); trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector, apicd->cpu); - /* Setup the vector move, if required */ - if (apicd->vector && cpu_online(apicd->cpu)) { + /* + * If there is no vector associated or if the associated vector is + * the shutdown vector, which is associated to make PCI/MSI + * shutdown mode work, then there is nothing to release. Clear out + * prev_vector for this and the offlined target case. + */ + apicd->prev_vector = 0; + if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR) + goto setnew; + /* + * If the target CPU of the previous vector is online, then mark + * the vector as move in progress and store it for cleanup when the + * first interrupt on the new vector arrives. If the target CPU is + * offline then the regular release mechanism via the cleanup + * vector is not possible and the vector can be immediately freed + * in the underlying matrix allocator. + */ + if (cpu_online(apicd->cpu)) { apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; } else { - apicd->prev_vector = 0; + irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, + managed); } +setnew: apicd->vector = newvec; apicd->cpu = newcpu; BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec])); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index f8d9d69994e6..e2829bf40e4a 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -14,7 +14,7 @@ int x2apic_phys; static struct apic apic_x2apic_phys; -static int set_x2apic_phys_mode(char *arg) +static int __init set_x2apic_phys_mode(char *arg) { x2apic_phys = 1; return 0; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 46b675aaf20b..f11910b44638 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1176,16 +1176,25 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) uv_gre_table = gre; for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { + unsigned long size = ((unsigned long)(gre->limit - lgre) + << UV_GAM_RANGE_SHFT); + int order = 0; + char suffix[] = " KMGTPE"; + + while (size > 9999 && order < sizeof(suffix)) { + size /= 1024; + order++; + } + if (!index) { pr_info("UV: GAM Range Table...\n"); pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - ((unsigned long)(gre->limit - lgre)) >> - (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ + size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fa1261eefa16..f91ba53e06c8 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,7 +18,7 @@ void foo(void) OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); - OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); + OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 570e8bb1f386..a66229f51b12 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,7 +28,7 @@ obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5bddbdcbc4a3..12bc0a1139da 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -119,7 +119,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if (c->x86_model == 6 && c->x86_mask == 1) { + if (c->x86_model == 6 && c->x86_stepping == 1) { const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); @@ -149,7 +149,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) /* K6 with old style WHCR */ if (c->x86_model < 8 || - (c->x86_model == 8 && c->x86_mask < 8)) { + (c->x86_model == 8 && c->x86_stepping < 8)) { /* We can only write allocate on the low 508Mb */ if (mbytes > 508) mbytes = 508; @@ -168,7 +168,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) return; } - if ((c->x86_model == 8 && c->x86_mask > 7) || + if ((c->x86_model == 8 && c->x86_stepping > 7) || c->x86_model == 9 || c->x86_model == 13) { /* The more serious chips .. */ @@ -221,7 +221,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx * As per AMD technical note 27212 0.2 */ - if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { + if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", @@ -241,12 +241,12 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * but they are not certified as MP capable. */ /* Athlon 660/661 is valid. */ - if ((c->x86_model == 6) && ((c->x86_mask == 0) || - (c->x86_mask == 1))) + if ((c->x86_model == 6) && ((c->x86_stepping == 0) || + (c->x86_stepping == 1))) return; /* Duron 670 is valid */ - if ((c->x86_model == 7) && (c->x86_mask == 0)) + if ((c->x86_model == 7) && (c->x86_stepping == 0)) return; /* @@ -256,8 +256,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for * more. */ - if (((c->x86_model == 6) && (c->x86_mask >= 2)) || - ((c->x86_model == 7) && (c->x86_mask >= 1)) || + if (((c->x86_model == 6) && (c->x86_stepping >= 2)) || + ((c->x86_model == 7) && (c->x86_stepping >= 1)) || (c->x86_model > 7)) if (cpu_has(c, X86_FEATURE_MP)) return; @@ -628,7 +628,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) /* Set MTRR capability flag if appropriate */ if (c->x86 == 5) if (c->x86_model == 13 || c->x86_model == 9 || - (c->x86_model == 8 && c->x86_mask >= 8)) + (c->x86_model == 8 && c->x86_stepping >= 8)) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) @@ -716,7 +716,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c) static void init_amd_gh(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_64 +#ifdef CONFIG_MMCONF_FAM10H /* do this for boot cpu */ if (c == &boot_cpu_data) check_enable_amd_mmconf_dmi(); @@ -795,7 +795,7 @@ static void init_amd_zn(struct cpuinfo_x86 *c) * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. */ - if (c->x86_model <= 1 && c->x86_mask <= 1) + if (c->x86_model <= 1 && c->x86_stepping <= 1) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -906,11 +906,11 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { /* Duron Rev A0 */ - if (c->x86_model == 3 && c->x86_mask == 0) + if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; /* Tbird rev A1/A2 */ if (c->x86_model == 4 && - (c->x86_mask == 0 || c->x86_mask == 1)) + (c->x86_stepping == 0 || c->x86_stepping == 1)) size = 256; } return size; @@ -1047,7 +1047,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) } /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_mask; + ms = (cpu->x86_model << 4) | cpu->x86_stepping; while ((range = *erratum++)) if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && (ms >= AMD_MODEL_RANGE_START(range)) && diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 71949bf2de5a..bfca937bdcc3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -162,8 +162,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, - sizeof(arg)); + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; @@ -175,8 +174,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } } @@ -185,8 +183,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", - mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -256,14 +253,14 @@ static void __init spectre_v2_select_mitigation(void) goto retpoline_auto; break; } - pr_err("kernel not compiled with retpoline; no mitigation available!"); + pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); return; retpoline_auto: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : @@ -281,7 +278,7 @@ retpoline_auto: pr_info("%s\n", spectre_v2_strings[mode]); /* - * If neither SMEP or KPTI are available, there is a risk of + * If neither SMEP nor PTI are available, there is a risk of * hitting userspace addresses in the RSB after a context switch * from a shallow call stack to a deeper one. To prevent this fill * the entire RSB, even when using IBRS. @@ -295,21 +292,29 @@ retpoline_auto: if ((!boot_cpu_has(X86_FEATURE_PTI) && !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) { setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Filling RSB on context switch\n"); + pr_info("Spectre v2 mitigation: Filling RSB on context switch\n"); } /* Initialize Indirect Branch Prediction Barrier if supported */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Enabling Indirect Branch Prediction Barrier\n"); + pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); + } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); } } #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return sprintf(buf, "Not affected\n"); @@ -318,28 +323,21 @@ ssize_t cpu_show_meltdown(struct device *dev, return sprintf(buf, "Vulnerable\n"); } -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) return sprintf(buf, "Not affected\n"); return sprintf(buf, "Mitigation: __user pointer sanitization\n"); } -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", spectre_v2_module_string()); } #endif - -void __ibp_barrier(void) -{ - __wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0); -} -EXPORT_SYMBOL_GPL(__ibp_barrier); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index c578cd29c2d2..e5ec0f11c0de 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -140,7 +140,7 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: - switch (c->x86_mask) { + switch (c->x86_stepping) { default: name = "2"; break; @@ -215,7 +215,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) * - Note, it seems this may only be in engineering samples. */ if ((c->x86 == 6) && (c->x86_model == 9) && - (c->x86_mask == 1) && (size == 65)) + (c->x86_stepping == 1) && (size == 65)) size -= 1; return size; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d63f4b5706e4..348cf4821240 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -731,7 +731,7 @@ void cpu_detect(struct cpuinfo_x86 *c) cpuid(0x00000001, &tfms, &misc, &junk, &cap0); c->x86 = x86_family(tfms); c->x86_model = x86_model(tfms); - c->x86_mask = x86_stepping(tfms); + c->x86_stepping = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -1184,9 +1184,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) int i; c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; + c->x86_cache_size = 0; c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; @@ -1378,8 +1378,8 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); - if (c->x86_mask || c->cpuid_level >= 0) - pr_cont(", stepping: 0x%x)\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + pr_cont(", stepping: 0x%x)\n", c->x86_stepping); else pr_cont(")\n"); } @@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void) return 0; } core_initcall(init_cpu_syscore); + +/* + * The microcode loader calls this upon late microcode load to recheck features, + * only when microcode has been updated. Caller holds microcode_mutex and CPU + * hotplug lock. + */ +void microcode_check(void) +{ + struct cpuinfo_x86 info; + + perf_check_microcode(); + + /* Reload CPUID max function as it might've changed. */ + info.cpuid_level = cpuid_eax(0); + + /* + * Copy all capability leafs to pick up the synthetic ones so that + * memcmp() below doesn't fail on that. The ones coming from CPUID will + * get overwritten in get_cpu_cap(). + */ + memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); + + get_cpu_cap(&info); + + if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + return; + + pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); + pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); +} diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6b4bb335641f..8949b7ae6d92 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -215,7 +215,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* common case step number/rev -- exceptions handled below */ c->x86_model = (dir1 >> 4) + 1; - c->x86_mask = dir1 & 0xf; + c->x86_stepping = dir1 & 0xf; /* Now cook; the original recipe is by Channing Corn, from Cyrix. * We do the same thing for each generation: we work out diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 319bf989fad1..b9693b80fc21 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -105,7 +105,7 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) /* * Early microcode releases for the Spectre v2 mitigation were broken. * Information taken from; - * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf * - https://kb.vmware.com/s/article/52345 * - Microcode revisions observed in the wild * - Release note from 20180108 microcode release @@ -116,15 +116,13 @@ struct sku_microcode { u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x84 }, - { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x84 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0B, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_DESKTOP, 0x09, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x0A, 0x80 }, + { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_MOBILE, 0x03, 0xc2 }, - { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, @@ -136,8 +134,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, - /* Updated in the 20180108 release; blacklist until we know otherwise */ - { INTEL_FAM6_ATOM_GEMINI_LAKE, 0x01, 0x22 }, /* Observed in the wild */ { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, @@ -147,9 +143,16 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && - c->x86_mask == spectre_bad_microcodes[i].stepping) + c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } return false; @@ -196,7 +199,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -212,7 +215,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* CPUID workaround for 0F33/0F34 CPU */ if (c->x86 == 0xF && c->x86_model == 0x3 - && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4)) c->x86_phys_bits = 36; /* @@ -310,7 +313,7 @@ int ppro_with_ram_bug(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask < 8) { + boot_cpu_data.x86_stepping < 8) { pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } @@ -327,7 +330,7 @@ static void intel_smp_check(struct cpuinfo_x86 *c) * Mask B, Pentium, but not Pentium MMX */ if (c->x86 == 5 && - c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_stepping >= 1 && c->x86_stepping <= 4 && c->x86_model <= 3) { /* * Remember we have B step Pentia with bugs @@ -370,7 +373,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until * model 3 mask 3 */ - if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633) + if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633) clear_cpu_cap(c, X86_FEATURE_SEP); /* @@ -388,7 +391,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * P4 Xeon erratum 037 workaround. * Hardware prefetcher may cause stale data to be loaded into the cache. */ - if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) { + if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) { if (msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) { pr_info("CPU: C0 stepping P4 Xeon detected.\n"); @@ -403,7 +406,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Specification Update"). */ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 && - (c->x86_mask < 0x6 || c->x86_mask == 0xb)) + (c->x86_stepping < 0x6 || c->x86_stepping == 0xb)) set_cpu_bug(c, X86_BUG_11AP); @@ -506,6 +509,90 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) } } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void init_intel_energy_perf(struct cpuinfo_x86 *c) { u64 epb; @@ -650,7 +737,7 @@ static void init_intel(struct cpuinfo_x86 *c) case 6: if (l2 == 128) p = "Celeron (Mendocino)"; - else if (c->x86_mask == 0 || c->x86_mask == 5) + else if (c->x86_stepping == 0 || c->x86_stepping == 5) p = "Celeron-A"; break; @@ -676,6 +763,9 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_VMX)) detect_vmx_virtcap(c); + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme(c); + init_intel_energy_perf(c); init_intel_misc_features(c); diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c new file mode 100644 index 000000000000..0771a905b286 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_pconfig.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel PCONFIG instruction support. + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Kirill A. Shutemov <kirill.shutemov@linux.intel.com> + */ + +#include <asm/cpufeature.h> +#include <asm/intel_pconfig.h> + +#define PCONFIG_CPUID 0x1b + +#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1) + +/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */ +enum { + PCONFIG_CPUID_SUBLEAF_INVALID = 0, + PCONFIG_CPUID_SUBLEAF_TARGETID = 1, +}; + +/* Bitmask of supported targets */ +static u64 targets_supported __read_mostly; + +int pconfig_target_supported(enum pconfig_target target) +{ + /* + * We would need to re-think the implementation once we get > 64 + * PCONFIG targets. Spec allows up to 2^32 targets. + */ + BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64); + + if (WARN_ON_ONCE(target >= 64)) + return 0; + return targets_supported & (1ULL << target); +} + +static int __init intel_pconfig_init(void) +{ + int subleaf; + + if (!boot_cpu_has(X86_FEATURE_PCONFIG)) + return 0; + + /* + * Scan subleafs of PCONFIG CPUID leaf. + * + * Subleafs of the same type need not to be consecutive. + * + * Stop on the first invalid subleaf type. All subleafs after the first + * invalid are invalid too. + */ + for (subleaf = 0; subleaf < INT_MAX; subleaf++) { + struct cpuid_regs regs; + + cpuid_count(PCONFIG_CPUID, subleaf, + ®s.eax, ®s.ebx, ®s.ecx, ®s.edx); + + switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) { + case PCONFIG_CPUID_SUBLEAF_INVALID: + /* Stop on the first invalid subleaf */ + goto out; + case PCONFIG_CPUID_SUBLEAF_TARGETID: + /* Mark supported PCONFIG targets */ + if (regs.ebx < 64) + targets_supported |= (1ULL << regs.ebx); + if (regs.ecx < 64) + targets_supported |= (1ULL << regs.ecx); + if (regs.edx < 64) + targets_supported |= (1ULL << regs.edx); + break; + default: + /* Unknown CPUID.PCONFIG subleaf: ignore */ + break; + } + } +out: + return 0; +} +arch_initcall(intel_pconfig_init); diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 410629f10ad3..589b948e6e01 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -819,7 +819,7 @@ static __init void rdt_quirks(void) cache_alloc_hsw_probe(); break; case INTEL_FAM6_SKYLAKE_X: - if (boot_cpu_data.x86_mask <= 4) + if (boot_cpu_data.x86_stepping <= 4) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); } } diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index bdab7d2f51af..fca759d272a1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1804,6 +1804,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, goto out_common_fail; } closid = ret; + ret = 0; rdtgrp->closid = closid; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 231ad23b24a9..475cb4f5f14f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -491,7 +491,7 @@ static void do_inject(void) unsigned int cpu = i_mce.extcpu; u8 b = i_mce.bank; - rdtscll(i_mce.tsc); + i_mce.tsc = rdtsc_ordered(); if (i_mce.misc) i_mce.status |= MCI_STATUS_MISCV; diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index aa0d5df9dc60..374d1aa66952 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -113,6 +113,76 @@ static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif +#ifndef CONFIG_X86_64 +/* + * On 32-bit systems it would be difficult to safely unmap a poison page + * from the kernel 1:1 map because there are no non-canonical addresses that + * we can use to refer to the address without risking a speculative access. + * However, this isn't much of an issue because: + * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which + * are only mapped into the kernel as needed + * 2) Few people would run a 32-bit kernel on a machine that supports + * recoverable errors because they have too much memory to boot 32-bit. + */ +static inline void mce_unmap_kpfn(unsigned long pfn) {} +#define mce_unmap_kpfn mce_unmap_kpfn +#endif + +struct mca_config { + bool dont_log_ce; + bool cmci_disabled; + bool ignore_ce; + + __u64 lmce_disabled : 1, + disabled : 1, + ser : 1, + recovery : 1, + bios_cmci_threshold : 1, + __reserved : 59; + + u8 banks; + s8 bootlog; + int tolerant; + int monarch_timeout; + int panic_timeout; + u32 rip_msr; +}; + extern struct mca_config mca_cfg; +struct mce_vendor_flags { + /* + * Indicates that overflow conditions are not fatal, when set. + */ + __u64 overflow_recov : 1, + + /* + * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and + * Recovery. It indicates support for data poisoning in HW and deferred + * error interrupts. + */ + succor : 1, + + /* + * (AMD) SMCA: This bit indicates support for Scalable MCA which expands + * the register space for each MCA bank and also increases number of + * banks. Also, to accommodate the new banks and registers, the MCA + * register space is moved to a new MSR range. + */ + smca : 1, + + __reserved_0 : 61; +}; + +extern struct mce_vendor_flags mce_flags; + +struct mca_msr_regs { + u32 (*ctl) (int bank); + u32 (*status) (int bank); + u32 (*addr) (int bank); + u32 (*misc) (int bank); +}; + +extern struct mca_msr_regs msr_ops; + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3a8e88a611eb..42cf2880d0ed 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -56,6 +56,9 @@ static DEFINE_MUTEX(mce_log_mutex); +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -105,6 +108,10 @@ static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn); +#endif + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -126,6 +133,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -234,7 +243,7 @@ static void __print_mce(struct mce *m) m->cs, m->ip); if (m->cs == __KERNEL_CS) - pr_cont("{%pS}", (void *)m->ip); + pr_cont("{%pS}", (void *)(unsigned long)m->ip); pr_cont("\n"); } @@ -258,13 +267,15 @@ static void __print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); } static void print_mce(struct mce *m) { __print_mce(m); - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); + + if (m->cpuvendor != X86_VENDOR_AMD) + pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } #define PANIC_TIMEOUT 5 /* 5 seconds */ @@ -590,7 +601,8 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; - memory_failure(pfn, 0); + if (!memory_failure(pfn, 0)) + mce_unmap_kpfn(pfn); } return NOTIFY_OK; @@ -1057,12 +1069,13 @@ static int do_memory_failure(struct mce *m) ret = memory_failure(m->addr >> PAGE_SHIFT, flags); if (ret) pr_err("Memory error not recovered"); + else + mce_unmap_kpfn(m->addr >> PAGE_SHIFT); return ret; } -#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) - -void arch_unmap_kpfn(unsigned long pfn) +#ifndef mce_unmap_kpfn +static void mce_unmap_kpfn(unsigned long pfn) { unsigned long decoy_addr; @@ -1073,7 +1086,7 @@ void arch_unmap_kpfn(unsigned long pfn) * We would like to just call: * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); * but doing that would radically increase the odds of a - * speculative access to the posion page because we'd have + * speculative access to the poison page because we'd have * the virtual address of the kernel 1:1 mapping sitting * around in registers. * Instead we get tricky. We create a non-canonical address @@ -1082,23 +1095,10 @@ void arch_unmap_kpfn(unsigned long pfn) * a legal address. */ -/* - * Build time check to see if we have a spare virtual bit. Don't want - * to leave this until run time because most developers don't have a - * system that can exercise this code path. This will only become a - * problem if/when we move beyond 5-level page tables. - * - * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD) - */ -#if PGDIR_SHIFT + 9 < 63 decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); -#else -#error "no unused virtual bit available" -#endif if (set_memory_np(decoy_addr, 1)) pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - } #endif @@ -1506,7 +1506,7 @@ static int __mcheck_cpu_cap_init(void) mca_cfg.rip_msr = MSR_IA32_MCG_EIP; if (cap & MCG_SER_P) - mca_cfg.ser = true; + mca_cfg.ser = 1; return 0; } @@ -1814,12 +1814,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) return; if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; return; } if (mce_gen_pool_init()) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; pr_emerg("Couldn't allocate MCE records pool!\n"); return; } @@ -1897,11 +1897,11 @@ static int __init mcheck_enable(char *str) if (*str == '=') str++; if (!strcmp(str, "off")) - cfg->disabled = true; + cfg->disabled = 1; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; else if (!strcmp(str, "no_lmce")) - cfg->lmce_disabled = true; + cfg->lmce_disabled = 1; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) @@ -1909,9 +1909,9 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) cfg->bootlog = (str[0] == 'b'); else if (!strcmp(str, "bios_cmci_threshold")) - cfg->bios_cmci_threshold = true; + cfg->bios_cmci_threshold = 1; else if (!strcmp(str, "recovery")) - cfg->recovery = true; + cfg->recovery = 1; else if (isdigit(str[0])) { if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); @@ -2081,6 +2081,7 @@ static ssize_t set_ignore_ce(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ @@ -2093,6 +2094,8 @@ static ssize_t set_ignore_ce(struct device *s, on_each_cpu(mce_enable_ce, (void *)1, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2105,6 +2108,7 @@ static ssize_t set_cmci_disabled(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ @@ -2116,6 +2120,8 @@ static ssize_t set_cmci_disabled(struct device *s, on_each_cpu(mce_enable_ce, NULL, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2123,8 +2129,19 @@ static ssize_t store_int_with_restart(struct device *s, struct device_attribute *attr, const char *buf, size_t size) { - ssize_t ret = device_store_int(s, attr, buf, size); + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + if (check_interval < 1) + check_interval = 1; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + return ret; } @@ -2328,6 +2345,12 @@ static __init int mcheck_init_device(void) { int err; + /* + * Check if we have a spare virtual bit. This will only become + * a problem if/when we move beyond 5-level page tables. + */ + MAYBE_BUILD_BUG_ON(__VIRTUAL_MASK_SHIFT >= 63); + if (!mce_available(&boot_cpu_data)) { err = -EIO; goto err_out; @@ -2376,7 +2399,7 @@ device_initcall_sync(mcheck_init_device); */ static int __init mcheck_disable(char *str) { - mca_cfg.disabled = true; + mca_cfg.disabled = 1; return 1; } __setup("nomce", mcheck_disable); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 0f32ad242324..f7666eef4a87 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -82,6 +82,7 @@ static struct smca_bank_name smca_names[] = { [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, + [SMCA_RESERVED] = { "reserved", "Reserved" }, [SMCA_EX] = { "execution_unit", "Execution Unit" }, [SMCA_FP] = { "floating_point", "Floating Point Unit" }, [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, @@ -110,14 +111,14 @@ const char *smca_get_long_name(enum smca_bank_types t) } EXPORT_SYMBOL_GPL(smca_get_long_name); -static enum smca_bank_types smca_get_bank_type(struct mce *m) +static enum smca_bank_types smca_get_bank_type(unsigned int bank) { struct smca_bank *b; - if (m->bank >= N_SMCA_BANK_TYPES) + if (bank >= MAX_NR_BANKS) return N_SMCA_BANK_TYPES; - b = &smca_banks[m->bank]; + b = &smca_banks[bank]; if (!b->hwid) return N_SMCA_BANK_TYPES; @@ -127,6 +128,9 @@ static enum smca_bank_types smca_get_bank_type(struct mce *m) static struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype, xec_bitmap } */ + /* Reserved type */ + { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 }, + /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, @@ -427,35 +431,58 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } +static u32 smca_get_block_address(unsigned int cpu, unsigned int bank, + unsigned int block) +{ + u32 low, high; + u32 addr = 0; + + if (smca_get_bank_type(bank) == SMCA_RESERVED) + return addr; + + if (!block) + return MSR_AMD64_SMCA_MCx_MISC(bank); + + /* + * For SMCA enabled processors, BLKPTR field of the first MISC register + * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). + */ + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + return addr; + + if (!(low & MCI_CONFIG_MCAX)) + return addr; + + if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + (low & MASK_BLKPTR_LO)) + return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + + return addr; +} + static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high, unsigned int bank, unsigned int block) { u32 addr = 0, offset = 0; - if (mce_flags.smca) { - if (!block) { - addr = MSR_AMD64_SMCA_MCx_MISC(bank); - } else { - /* - * For SMCA enabled processors, BLKPTR field of the - * first MISC register (MCx_MISC0) indicates presence of - * additional MISC register set (MISC1-4). - */ - u32 low, high; + if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) + return addr; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) - return addr; + /* Get address from already initialized block. */ + if (per_cpu(threshold_banks, cpu)) { + struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank]; - if (!(low & MCI_CONFIG_MCAX)) - return addr; + if (bankp && bankp->blocks) { + struct threshold_block *blockp = &bankp->blocks[block]; - if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && - (low & MASK_BLKPTR_LO)) - addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + if (blockp) + return blockp->address; } - return addr; } + if (mce_flags.smca) + return smca_get_block_address(cpu, bank, block); + /* Fall back to method we used for older processors: */ switch (block) { case 0: @@ -760,7 +787,7 @@ bool amd_mce_is_memory_error(struct mce *m) u8 xec = (m->status >> 16) & 0x1f; if (mce_flags.smca) - return smca_get_bank_type(m) == SMCA_UMC && xec == 0x0; + return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1063,7 +1090,7 @@ static struct kobj_type threshold_ktype = { static const char *get_name(unsigned int bank, struct threshold_block *b) { - unsigned int bank_type; + enum smca_bank_types bank_type; if (!mce_flags.smca) { if (b && bank == 4) @@ -1072,11 +1099,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return th_names[bank]; } - if (!smca_banks[bank].hwid) + bank_type = smca_get_bank_type(bank); + if (bank_type >= N_SMCA_BANK_TYPES) return NULL; - bank_type = smca_banks[bank].hwid->bank_type; - if (b && bank_type == SMCA_UMC) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 330b8462d426..48179928ff38 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return -EINVAL; ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); - if (ret != UCODE_OK) + if (ret > UCODE_UPDATED) return -EINVAL; return 0; @@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -static int apply_microcode_amd(int cpu) +static enum ucode_state apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; @@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu) p = find_patch(cpu); if (!p) - return 0; + return UCODE_NFOUND; mc_amd = p->data; uci->mc = p->data; @@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu) if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; uci->cpu_sig.rev = rev; - return 0; + return UCODE_OK; } if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); - return -1; + return UCODE_ERROR; } pr_info("CPU%d: new patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu) uci->cpu_sig.rev = mc_amd->hdr.patch_id; c->microcode = mc_amd->hdr.patch_id; - return 0; + return UCODE_UPDATED; } static int install_equiv_cpu_table(const u8 *buf) @@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, static enum ucode_state load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { + struct ucode_patch *p; enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); ret = __load_microcode_amd(family, data, size); - - if (ret != UCODE_OK) + if (ret != UCODE_OK) { cleanup(); + return ret; + } -#ifdef CONFIG_X86_32 - /* save BSP's matching patch for early load */ - if (save) { - struct ucode_patch *p = find_patch(0); - if (p) { - memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), - PATCH_MAX_SIZE)); - } + p = find_patch(0); + if (!p) { + return ret; + } else { + if (boot_cpu_data.microcode == p->patch_id) + return ret; + + ret = UCODE_NEW; } -#endif + + /* save BSP's matching patch for early load */ + if (!save) + return ret; + + memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); + memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE)); + return ret; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 319dd65f98a2..10c4fc2c91f8 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -22,13 +22,16 @@ #define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/mutex.h> #include <linux/cpu.h> +#include <linux/nmi.h> #include <linux/fs.h> #include <linux/mm.h> @@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); +/* + * Serialize late loading so that CPUs get updated one-by-one. + */ +static DEFINE_SPINLOCK(update_lock); + struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu) return ret; } -struct apply_microcode_ctx { - int err; -}; - static void apply_microcode_local(void *arg) { - struct apply_microcode_ctx *ctx = arg; + enum ucode_state *err = arg; - ctx->err = microcode_ops->apply_microcode(smp_processor_id()); + *err = microcode_ops->apply_microcode(smp_processor_id()); } static int apply_microcode_on_target(int cpu) { - struct apply_microcode_ctx ctx = { .err = 0 }; + enum ucode_state err; int ret; - ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1); - if (!ret) - ret = ctx.err; - + ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); + if (!ret) { + if (err == UCODE_ERROR) + ret = 1; + } return ret; } @@ -489,31 +494,124 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static int reload_for_cpu(int cpu) +/* + * Late loading dance. Why the heavy-handed stomp_machine effort? + * + * - HT siblings must be idle and not execute other code while the other sibling + * is loading microcode in order to avoid any negative interactions caused by + * the loading. + * + * - In addition, microcode update on the cores must be serialized until this + * requirement can be relaxed in the future. Right now, this is conservative + * and good. + */ +#define SPINUNIT 100 /* 100 nsec */ + +static int check_online_cpus(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; - int err = 0; + if (num_online_cpus() == num_present_cpus()) + return 0; - if (!uci->valid) - return err; + pr_err("Not all CPUs online, aborting microcode update.\n"); - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - return err; + return -EINVAL; +} + +static atomic_t late_cpus_in; +static atomic_t late_cpus_out; + +static int __wait_for_cpus(atomic_t *t, long long timeout) +{ + int all_cpus = num_online_cpus(); + + atomic_inc(t); + + while (atomic_read(t) < all_cpus) { + if (timeout < SPINUNIT) { + pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", + all_cpus - atomic_read(t)); + return 1; + } + + ndelay(SPINUNIT); + timeout -= SPINUNIT; + + touch_nmi_watchdog(); + } + return 0; +} + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) +{ + int cpu = smp_processor_id(); + enum ucode_state err; + int ret = 0; + + /* + * Wait for all CPUs to arrive. A load will not be attempted unless all + * CPUs show up. + * */ + if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) + return -1; + + spin_lock(&update_lock); + apply_microcode_local(&err); + spin_unlock(&update_lock); + + if (err > UCODE_NFOUND) { + pr_warn("Error reloading microcode on CPU %d\n", cpu); + return -1; + /* siblings return UCODE_OK because their engine got updated already */ + } else if (err == UCODE_UPDATED || err == UCODE_OK) { + ret = 1; + } else { + return ret; + } + + /* + * Increase the wait timeout to a safe value here since we're + * serializing the microcode update and that could take a while on a + * large number of CPUs. And that is fine as the *actual* timeout will + * be determined by the last CPU finished updating and thus cut short. + */ + if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus())) + panic("Timeout during microcode update!\n"); + + return ret; +} + +/* + * Reload microcode late on all CPUs. Wait for a sec until they + * all gather together. + */ +static int microcode_reload_late(void) +{ + int ret; + + atomic_set(&late_cpus_in, 0); + atomic_set(&late_cpus_out, 0); + + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (ret > 0) + microcode_check(); + + return ret; } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + enum ucode_state tmp_ret = UCODE_OK; + int bsp = boot_cpu_data.cpu_index; unsigned long val; - int cpu; - ssize_t ret = 0, tmp_ret; + ssize_t ret = 0; ret = kstrtoul(buf, 0, &val); if (ret) @@ -522,23 +620,24 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_NEW) + return size; + get_online_cpus(); - mutex_lock(µcode_mutex); - for_each_online_cpu(cpu) { - tmp_ret = reload_for_cpu(cpu); - if (tmp_ret != 0) - pr_warn("Error reloading microcode on CPU %d\n", cpu); - /* save retval of the first encountered reload error */ - if (!ret) - ret = tmp_ret; - } - if (!ret) - perf_check_microcode(); + ret = check_online_cpus(); + if (ret) + goto put; + + mutex_lock(µcode_mutex); + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); + +put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret; @@ -606,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) if (system_state != SYSTEM_RUNNING) return UCODE_NFOUND; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, - refresh_fw); - - if (ustate == UCODE_OK) { + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, refresh_fw); + if (ustate == UCODE_NEW) { pr_debug("CPU%d updated upon init\n", cpu); apply_microcode_on_target(cpu); } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index f7c55b0e753a..32b8e5724f96 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) return 0; } -static int apply_microcode_intel(int cpu) +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; - struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; static int prev_rev; u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) - return -1; + return UCODE_ERROR; - uci = ucode_cpu_info + cpu; - mc = uci->mc; + /* Look for a newer patch in our cache: */ + mc = find_patch(uci); if (!mc) { - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); + mc = uci->mc; if (!mc) - return 0; + return UCODE_NFOUND; } + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + c->microcode = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu) if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); - return -1; + return UCODE_ERROR; } if (rev != prev_rev) { @@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu) prev_rev = rev; } - c = &cpu_data(cpu); - uci->cpu_sig.rev = rev; c->microcode = rev; - return 0; + return UCODE_UPDATED; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, @@ -830,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, unsigned int leftover = size; unsigned int curr_mc_size = 0, new_mc_size = 0; unsigned int csig, cpf; + enum ucode_state ret = UCODE_OK; while (leftover) { struct microcode_header_intel mc_header; @@ -871,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, new_mc = mc; new_mc_size = mc_size; mc = NULL; /* trigger new vmalloc */ + ret = UCODE_NEW; } ucode_ptr += mc_size; @@ -900,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); - return UCODE_OK; + return ret; } static int get_ucode_fw(void *to, const void *from, size_t n) @@ -921,7 +955,7 @@ static bool is_blacklisted(unsigned int cpu) */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && - c->x86_mask == 0x01 && + c->x86_stepping == 0x01 && llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); @@ -944,7 +978,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, return UCODE_NFOUND; sprintf(name, "intel-ucode/%02x-%02x-%02x", - c->x86, c->x86_model, c->x86_mask); + c->x86, c->x86_model, c->x86_stepping); if (request_firmware_direct(&firmware, name, device)) { pr_debug("data file %s load failed\n", name); @@ -982,7 +1016,7 @@ static struct microcode_ops microcode_intel_ops = { static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) { - u64 llc_size = c->x86_cache_size * 1024; + u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fdc55215d44d..e12ee86906c6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -859,7 +859,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, */ if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && - boot_cpu_data.x86_mask <= 7) { + boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 40d5a8a75212..7468de429087 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -711,8 +711,8 @@ void __init mtrr_bp_init(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 == 0xF && boot_cpu_data.x86_model == 0x3 && - (boot_cpu_data.x86_mask == 0x3 || - boot_cpu_data.x86_mask == 0x4)) + (boot_cpu_data.x86_stepping == 0x3 || + boot_cpu_data.x86_stepping == 0x4)) phys_addr = 36; size_or_mask = SIZE_OR_MASK_BITS(phys_addr); diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7ecedafa1c8..2c8522a39ed5 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -72,8 +72,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) c->x86_model, c->x86_model_id[0] ? c->x86_model_id : "unknown"); - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); + if (c->x86_stepping || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_stepping); else seq_puts(m, "stepping\t: unknown\n"); if (c->microcode) @@ -91,8 +91,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) } /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + if (c->x86_cache_size) + seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size); show_cpuinfo_core(m, c, cpu); show_cpuinfo_misc(m, c); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 0931a105ffe1..1d300f96df4b 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -40,6 +40,7 @@ #include <linux/notifier.h> #include <linux/uaccess.h> #include <linux/gfp.h> +#include <linux/completion.h> #include <asm/processor.h> #include <asm/msr.h> @@ -47,19 +48,27 @@ static struct class *cpuid_class; static enum cpuhp_state cpuhp_cpuid_state; +struct cpuid_regs_done { + struct cpuid_regs regs; + struct completion done; +}; + static void cpuid_smp_cpuid(void *cmd_block) { - struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block; + struct cpuid_regs_done *cmd = cmd_block; + + cpuid_count(cmd->regs.eax, cmd->regs.ecx, + &cmd->regs.eax, &cmd->regs.ebx, + &cmd->regs.ecx, &cmd->regs.edx); - cpuid_count(cmd->eax, cmd->ecx, - &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); + complete(&cmd->done); } static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char __user *tmp = buf; - struct cpuid_regs cmd; + struct cpuid_regs_done cmd; int cpu = iminor(file_inode(file)); u64 pos = *ppos; ssize_t bytes = 0; @@ -68,19 +77,28 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, if (count % 16) return -EINVAL; /* Invalid chunk size */ + init_completion(&cmd.done); for (; count; count -= 16) { - cmd.eax = pos; - cmd.ecx = pos >> 32; - err = smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1); + call_single_data_t csd = { + .func = cpuid_smp_cpuid, + .info = &cmd, + }; + + cmd.regs.eax = pos; + cmd.regs.ecx = pos >> 32; + + err = smp_call_function_single_async(cpu, &csd); if (err) break; - if (copy_to_user(tmp, &cmd, 16)) { + wait_for_completion(&cmd.done); + if (copy_to_user(tmp, &cmd.regs, 16)) { err = -EFAULT; break; } tmp += 16; bytes += 16; *ppos = ++pos; + reinit_completion(&cmd.done); } return bytes ? bytes : err; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 10e74d4778a1..1f6680427ff0 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -199,9 +199,10 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); - disable_IO_APIC(); + clear_IO_APIC(); #endif lapic_shutdown(); + restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 25de5f6ca997..f39f3a06c26f 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -11,6 +11,7 @@ #include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/of_irq.h> +#include <linux/libfdt.h> #include <linux/slab.h> #include <linux/pci.h> #include <linux/of_pci.h> @@ -130,34 +131,52 @@ static void __init dtb_setup_hpet(void) #endif } +#ifdef CONFIG_X86_LOCAL_APIC + +static void __init dtb_cpu_setup(void) +{ + struct device_node *dn; + u32 apic_id, version; + int ret; + + version = GET_APIC_VERSION(apic_read(APIC_LVR)); + for_each_node_by_type(dn, "cpu") { + ret = of_property_read_u32(dn, "reg", &apic_id); + if (ret < 0) { + pr_warn("%pOF: missing local APIC ID\n", dn); + continue; + } + generic_processor_info(apic_id, version); + } +} + static void __init dtb_lapic_setup(void) { -#ifdef CONFIG_X86_LOCAL_APIC struct device_node *dn; struct resource r; + unsigned long lapic_addr = APIC_DEFAULT_PHYS_BASE; int ret; dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic"); - if (!dn) - return; - - ret = of_address_to_resource(dn, 0, &r); - if (WARN_ON(ret)) - return; + if (dn) { + ret = of_address_to_resource(dn, 0, &r); + if (WARN_ON(ret)) + return; + lapic_addr = r.start; + } /* Did the boot loader setup the local APIC ? */ if (!boot_cpu_has(X86_FEATURE_APIC)) { - if (apic_force_enable(r.start)) + if (apic_force_enable(lapic_addr)) return; } smp_found_config = 1; pic_mode = 1; - register_lapic_address(r.start); - generic_processor_info(boot_cpu_physical_apicid, - GET_APIC_VERSION(apic_read(APIC_LVR))); -#endif + register_lapic_address(lapic_addr); } +#endif /* CONFIG_X86_LOCAL_APIC */ + #ifdef CONFIG_X86_IO_APIC static unsigned int ioapic_id; @@ -194,19 +213,22 @@ static struct of_ioapic_type of_ioapic_type[] = static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { - struct of_phandle_args *irq_data = (void *)arg; + struct irq_fwspec *fwspec = (struct irq_fwspec *)arg; struct of_ioapic_type *it; struct irq_alloc_info tmp; + int type_index; - if (WARN_ON(irq_data->args_count < 2)) + if (WARN_ON(fwspec->param_count < 2)) return -EINVAL; - if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type)) + + type_index = fwspec->param[1]; + if (type_index >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = &of_ioapic_type[irq_data->args[1]]; + it = &of_ioapic_type[type_index]; ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); - tmp.ioapic_pin = irq_data->args[0]; + tmp.ioapic_pin = fwspec->param[0]; return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } @@ -255,11 +277,14 @@ static void __init dtb_ioapic_setup(void) {} static void __init dtb_apic_setup(void) { +#ifdef CONFIG_X86_LOCAL_APIC dtb_lapic_setup(); + dtb_cpu_setup(); +#endif dtb_ioapic_setup(); } -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE static void __init x86_flattree_get_config(void) { u32 size, map_len; @@ -270,14 +295,15 @@ static void __init x86_flattree_get_config(void) map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - initial_boot_params = dt = early_memremap(initial_dtb, map_len); - size = of_get_flat_dt_size(); + dt = early_memremap(initial_dtb, map_len); + size = fdt_totalsize(dt); if (map_len < size) { early_memunmap(dt, map_len); - initial_boot_params = dt = early_memremap(initial_dtb, size); + dt = early_memremap(initial_dtb, size); map_len = size; } + early_init_dt_verify(dt); unflatten_and_copy_device_tree(); early_memunmap(dt, map_len); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index a2d8a3908670..18fa9d74c182 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -24,7 +24,7 @@ int panic_on_unrecovered_nmi; int panic_on_io_nmi; -unsigned int code_bytes = 64; +static unsigned int code_bytes = 64; static int die_counter; bool in_task_stack(unsigned long *stack, struct task_struct *task, @@ -375,3 +375,50 @@ static int __init code_bytes_setup(char *s) return 1; } __setup("code_bytes=", code_bytes_setup); + +void show_regs(struct pt_regs *regs) +{ + bool all = true; + int i; + + show_regs_print_info(KERN_DEFAULT); + + if (IS_ENABLED(CONFIG_X86_32)) + all = !user_mode(regs); + + __show_regs(regs, all); + + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (!user_mode(regs)) { + unsigned int code_prologue = code_bytes * 43 / 64; + unsigned int code_len = code_bytes; + unsigned char c; + u8 *ip; + + show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT); + + printk(KERN_DEFAULT "Code: "); + + ip = (u8 *)regs->ip - code_prologue; + if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { + /* try starting at IP */ + ip = (u8 *)regs->ip; + code_len = code_len - code_prologue + 1; + } + for (i = 0; i < code_len; i++, ip++) { + if (ip < (u8 *)PAGE_OFFSET || + probe_kernel_address(ip, c)) { + pr_cont(" Bad RIP value."); + break; + } + if (ip == (u8 *)regs->ip) + pr_cont("<%02x> ", c); + else + pr_cont("%02x ", c); + } + } + pr_cont("\n"); +} diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 04170f63e3a1..cd53f3030e40 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -127,45 +127,3 @@ unknown: info->type = STACK_TYPE_UNKNOWN; return -EINVAL; } - -void show_regs(struct pt_regs *regs) -{ - int i; - - show_regs_print_info(KERN_EMERG); - __show_regs(regs, !user_mode(regs)); - - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (!user_mode(regs)) { - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; - unsigned char c; - u8 *ip; - - show_trace_log_lvl(current, regs, NULL, KERN_EMERG); - - pr_emerg("Code:"); - - ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - /* try starting at IP */ - ip = (u8 *)regs->ip; - code_len = code_len - code_prologue + 1; - } - for (i = 0; i < code_len; i++, ip++) { - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { - pr_cont(" Bad EIP value."); - break; - } - if (ip == (u8 *)regs->ip) - pr_cont(" <%02x>", c); - else - pr_cont(" %02x", c); - } - } - pr_cont("\n"); -} diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 563e28d14f2c..5cdb9e84da57 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -149,45 +149,3 @@ unknown: info->type = STACK_TYPE_UNKNOWN; return -EINVAL; } - -void show_regs(struct pt_regs *regs) -{ - int i; - - show_regs_print_info(KERN_DEFAULT); - __show_regs(regs, 1); - - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (!user_mode(regs)) { - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; - unsigned char c; - u8 *ip; - - show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT); - - printk(KERN_DEFAULT "Code: "); - - ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - /* try starting at IP */ - ip = (u8 *)regs->ip; - code_len = code_len - code_prologue + 1; - } - for (i = 0; i < code_len; i++, ip++) { - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { - pr_cont(" Bad RIP value."); - break; - } - if (ip == (u8 *)regs->ip) - pr_cont("<%02x> ", c); - else - pr_cont("%02x ", c); - } - } - pr_cont("\n"); -} diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 71c11ad5643e..6a2cb1442e05 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -924,6 +924,24 @@ static int __init parse_memmap_one(char *p) } else if (*p == '!') { start_at = memparse(p+1, &p); e820__range_add(start_at, mem_size, E820_TYPE_PRAM); + } else if (*p == '%') { + enum e820_type from = 0, to = 0; + + start_at = memparse(p + 1, &p); + if (*p == '-') + from = simple_strtoull(p + 1, &p, 0); + if (*p == '+') + to = simple_strtoull(p + 1, &p, 0); + if (*p != '\0') + return -EINVAL; + if (from && to) + e820__range_update(start_at, mem_size, from, to); + else if (to) + e820__range_add(start_at, mem_size, to); + else if (from) + e820__range_remove(start_at, mem_size, from, 1); + else + e820__range_remove(start_at, mem_size, 0, 0); } else { e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7ba5d819ebe3..0c855deee165 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -32,6 +32,11 @@ #include <asm/microcode.h> #include <asm/kasan.h> +#ifdef CONFIG_X86_5LEVEL +#undef pgtable_l5_enabled +#define pgtable_l5_enabled __pgtable_l5_enabled +#endif + /* * Manage page tables very early on. */ @@ -39,6 +44,24 @@ extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +#ifdef CONFIG_X86_5LEVEL +unsigned int __pgtable_l5_enabled __ro_after_init; +EXPORT_SYMBOL(__pgtable_l5_enabled); +unsigned int pgdir_shift __ro_after_init = 39; +EXPORT_SYMBOL(pgdir_shift); +unsigned int ptrs_per_p4d __ro_after_init = 1; +EXPORT_SYMBOL(ptrs_per_p4d); +#endif + +#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT +unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4; +EXPORT_SYMBOL(page_offset_base); +unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4; +EXPORT_SYMBOL(vmalloc_base); +unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; +EXPORT_SYMBOL(vmemmap_base); +#endif + #define __head __section(.head.text) static void __head *fixup_pointer(void *ptr, unsigned long physaddr) @@ -46,6 +69,41 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr) return ptr - (void *)_text + (void *)physaddr; } +static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr) +{ + return fixup_pointer(ptr, physaddr); +} + +#ifdef CONFIG_X86_5LEVEL +static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) +{ + return fixup_pointer(ptr, physaddr); +} + +static bool __head check_la57_support(unsigned long physaddr) +{ + if (native_cpuid_eax(0) < 7) + return false; + + if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + return false; + + *fixup_int(&pgtable_l5_enabled, physaddr) = 1; + *fixup_int(&pgdir_shift, physaddr) = 48; + *fixup_int(&ptrs_per_p4d, physaddr) = 512; + *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5; + *fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5; + *fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5; + + return true; +} +#else +static bool __head check_la57_support(unsigned long physaddr) +{ + return false; +} +#endif + unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { @@ -55,9 +113,12 @@ unsigned long __head __startup_64(unsigned long physaddr, p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; + bool la57; int i; unsigned int *next_pgt_ptr; + la57 = check_la57_support(physaddr); + /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) for (;;); @@ -81,9 +142,14 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Fixup the physical addresses in the page table */ pgd = fixup_pointer(&early_top_pgt, physaddr); - pgd[pgd_index(__START_KERNEL_map)] += load_delta; - - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p = pgd + pgd_index(__START_KERNEL_map); + if (la57) + *p = (unsigned long)level4_kernel_pgt; + else + *p = (unsigned long)level3_kernel_pgt; + *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; + + if (la57) { p4d = fixup_pointer(&level4_kernel_pgt, physaddr); p4d[511] += load_delta; } @@ -108,7 +174,7 @@ unsigned long __head __startup_64(unsigned long physaddr, pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + if (la57) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; @@ -154,8 +220,7 @@ unsigned long __head __startup_64(unsigned long physaddr, * Fixup phys_base - remove the memory encryption mask to obtain * the true physical address. */ - p = fixup_pointer(&phys_base, physaddr); - *p += load_delta - sme_get_me_mask(); + *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); /* Encrypt the kernel and related (if SME is active) */ sme_encrypt_kernel(bp); @@ -206,7 +271,7 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + if (!pgtable_l5_enabled) p4d_p = pgd_p; else if (pgd) p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); @@ -322,7 +387,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0); BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0); BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); - BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == + MAYBE_BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == (__START_KERNEL & PGDIR_MASK))); BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c29020907886..b59e4fb40fd9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -37,7 +37,7 @@ #define X86 new_cpu_data+CPUINFO_x86 #define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor #define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_STEPPING new_cpu_data+CPUINFO_x86_stepping #define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math #define X86_CPUID new_cpu_data+CPUINFO_cpuid_level #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability @@ -332,7 +332,7 @@ ENTRY(startup_32_smp) shrb $4,%al movb %al,X86_MODEL andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK + movb %cl,X86_STEPPING movl %edx,X86_CAPABILITY .Lis486: diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 04a625f0fcda..48385c1074a5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -23,6 +23,7 @@ #include <asm/nops.h> #include "../entry/calling.h" #include <asm/export.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -38,12 +39,12 @@ * */ +#define l4_index(x) (((x) >> 39) & 511) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) -PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) -PGD_START_KERNEL = pgd_index(__START_KERNEL_map) -#endif +L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) +L4_START_KERNEL = l4_index(__START_KERNEL_map) + L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -124,7 +125,10 @@ ENTRY(secondary_startup_64) /* Enable PAE mode, PGE and LA57 */ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL + testl $1, __pgtable_l5_enabled(%rip) + jz 1f orl $X86_CR4_LA57, %ecx +1: #endif movq %rcx, %cr4 @@ -134,6 +138,7 @@ ENTRY(secondary_startup_64) /* Ensure I am executing from virtual addresses */ movq $1f, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax 1: UNWIND_HINT_EMPTY @@ -372,12 +377,7 @@ GLOBAL(name) __INITDATA NEXT_PGD_PAGE(early_top_pgt) - .fill 511,8,0 -#ifdef CONFIG_X86_5LEVEL - .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC -#else - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC -#endif + .fill 512,8,0 .fill PTI_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) @@ -388,9 +388,9 @@ NEXT_PAGE(early_dynamic_pgts) #if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) NEXT_PGD_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 + .org init_top_pgt + L4_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC - .org init_top_pgt + PGD_START_KERNEL*8, 0 + .org init_top_pgt + L4_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC .fill PTI_USER_PGD_FILL,8,0 diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 56d99be3706a..2c3a1b4294eb 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -140,6 +140,9 @@ static const __initconst struct idt_data apic_idts[] = { # ifdef CONFIG_IRQ_WORK INTG(IRQ_WORK_VECTOR, irq_work_interrupt), # endif +#ifdef CONFIG_X86_UV + INTG(UV_BAU_MESSAGE, uv_bau_message_intr1), +#endif INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt), INTG(ERROR_APIC_VECTOR, error_interrupt), #endif @@ -160,7 +163,6 @@ static const __initconst struct idt_data early_pf_idts[] = { */ static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), - INTG(X86_TRAP_BP, int3), }; #endif @@ -183,7 +185,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), - SISTG(X86_TRAP_BP, int3, DEBUG_STACK), ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK), #ifdef CONFIG_X86_MCE ISTG(X86_TRAP_MC, &machine_check, MCE_STACK), diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 2f723301eb58..0fe1c8782208 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -23,7 +23,7 @@ /* * this changes the io permissions bitmap in the current task. */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +long ksys_ioperm(unsigned long from, unsigned long num, int turn_on) { struct thread_struct *t = ¤t->thread; struct tss_struct *tss; @@ -96,6 +96,11 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) return 0; } +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) +{ + return ksys_ioperm(from, num, turn_on); +} + /* * sys_iopl has to be used when you want to access the IO ports * beyond the 0x3ff range: to get the full 65536 ports bitmapped diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index a539410c4ea9..772196c1b8c4 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -61,9 +61,14 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) + /* + * Try to set up the through-local-APIC virtual wire mode earlier. + * + * On some 32-bit UP machines, whose APIC has been disabled by BIOS + * and then got re-enabled by "lapic", it hangs at boot time without this. + */ init_bsp_APIC(); -#endif + legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index b68fd895235a..fa183a131edc 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -124,6 +124,14 @@ static int __init jailhouse_pci_arch_init(void) if (pcibios_last_bus < 0) pcibios_last_bus = 0xff; +#ifdef CONFIG_PCI_MMCONFIG + if (setup_data.pci_mmconfig_base) { + pci_mmconfig_add(0, 0, pcibios_last_bus, + setup_data.pci_mmconfig_base); + pci_mmcfg_arch_init(); + } +#endif + return 0; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd36f3c33cd0..0715f827607c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler); bool arch_within_kprobe_blacklist(unsigned long addr) { + bool is_in_entry_trampoline_section = false; + +#ifdef CONFIG_X86_64 + is_in_entry_trampoline_section = + (addr >= (unsigned long)__entry_trampoline_start && + addr < (unsigned long)__entry_trampoline_end); +#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end); + addr < (unsigned long)__entry_text_end) || + is_in_entry_trampoline_section; } int __init arch_init_kprobes(void) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4e37d1a851a6..fae86e36e399 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -49,7 +49,7 @@ static int kvmapf = 1; -static int parse_no_kvmapf(char *arg) +static int __init parse_no_kvmapf(char *arg) { kvmapf = 0; return 0; @@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg) early_param("no-kvmapf", parse_no_kvmapf); static int steal_acc = 1; -static int parse_no_stealacc(char *arg) +static int __init parse_no_stealacc(char *arg) { steal_acc = 0; return 0; @@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); static int kvmclock_vsyscall = 1; -static int parse_no_kvmclock_vsyscall(char *arg) +static int __init parse_no_kvmclock_vsyscall(char *arg) { kvmclock_vsyscall = 0; return 0; @@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void) #endif pa |= KVM_ASYNC_PF_ENABLED; - /* Async page fault support for L1 hypervisor is optional */ - if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, - (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; + + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); @@ -545,7 +545,8 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void) { int cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index edfede768688..60cdec6628b0 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -195,11 +195,11 @@ void machine_kexec(struct kimage *image) /* * We need to put APICs in legacy mode so that we can * get timer interrupts in second kernel. kexec/kdump - * paths already have calls to disable_IO_APIC() in - * one form or other. kexec jump path also need - * one. + * paths already have calls to restore_boot_irq_mode() + * in one form or other. kexec jump path also need one. */ - disable_IO_APIC(); + clear_IO_APIC(); + restore_boot_irq_mode(); #endif } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1f790cf9d38f..93bd4fb603d1 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -293,11 +293,11 @@ void machine_kexec(struct kimage *image) /* * We need to put APICs in legacy mode so that we can * get timer interrupts in second kernel. kexec/kdump - * paths already have calls to disable_IO_APIC() in - * one form or other. kexec jump path also need - * one. + * paths already have calls to restore_boot_irq_mode() + * in one form or other. kexec jump path also need one. */ - disable_IO_APIC(); + clear_IO_APIC(); + restore_boot_irq_mode(); #endif } @@ -350,6 +350,7 @@ void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); VMCOREINFO_SYMBOL(init_top_pgt); + VMCOREINFO_NUMBER(pgtable_l5_enabled); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); @@ -542,6 +543,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: value -= (u64)address; *(u32 *)location = value; break; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index da0c160e5589..f58336af095c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -191,6 +191,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, goto overflow; break; case R_X86_64_PC32: + case R_X86_64_PLT32: if (*(u32 *)loc != 0) goto invalid_relocation; val -= (u64)loc; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 27d0a1712663..f1c5eb99d445 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -410,7 +410,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01; processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping; processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 041096bdef86..99dc79e76bdc 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -200,9 +200,9 @@ static void native_flush_tlb_global(void) __native_flush_tlb_global(); } -static void native_flush_tlb_single(unsigned long addr) +static void native_flush_tlb_one_user(unsigned long addr) { - __native_flush_tlb_single(addr); + __native_flush_tlb_one_user(addr); } struct static_key paravirt_steal_enabled; @@ -401,7 +401,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_single = native_flush_tlb_single, + .flush_tlb_one_user = native_flush_tlb_one_user, .flush_tlb_others = native_flush_tlb_others, .pgd_alloc = __paravirt_pgd_alloc, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 35c461f21815..bbfc8b1e9104 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/crash_dump.h> #include <linux/dma-mapping.h> +#include <linux/dma-direct.h> #include <linux/bitmap.h> #include <linux/pci_ids.h> #include <linux/pci.h> @@ -445,8 +446,6 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, npages = size >> PAGE_SHIFT; order = get_order(size); - flag &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - /* alloc enough pages (and possibly more) */ ret = (void *)__get_free_pages(flag, order); if (!ret) @@ -493,7 +492,7 @@ static const struct dma_map_ops calgary_dma_ops = { .map_page = calgary_map_page, .unmap_page = calgary_unmap_page, .mapping_error = calgary_mapping_error, - .dma_supported = x86_dma_supported, + .dma_supported = dma_direct_supported, }; static inline void __iomem * busno_to_bbar(unsigned char num) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index df7ab02f959f..14437116ffea 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -18,7 +18,7 @@ static int forbid_dac __read_mostly; -const struct dma_map_ops *dma_ops = &nommu_dma_ops; +const struct dma_map_ops *dma_ops = &dma_direct_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -76,70 +76,12 @@ void __init pci_iommu_alloc(void) } } } -void *dma_generic_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_addr, gfp_t flag, - unsigned long attrs) -{ - unsigned long dma_mask; - struct page *page; - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - dma_addr_t addr; - - dma_mask = dma_alloc_coherent_mask(dev, flag); - -again: - page = NULL; - /* CMA can be used only in the context which permits sleeping */ - if (gfpflags_allow_blocking(flag)) { - page = dma_alloc_from_contiguous(dev, count, get_order(size), - flag); - if (page) { - addr = phys_to_dma(dev, page_to_phys(page)); - if (addr + size > dma_mask) { - dma_release_from_contiguous(dev, page, count); - page = NULL; - } - } - } - /* fallback */ - if (!page) - page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); - if (!page) - return NULL; - - addr = phys_to_dma(dev, page_to_phys(page)); - if (addr + size > dma_mask) { - __free_pages(page, get_order(size)); - - if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) { - flag = (flag & ~GFP_DMA32) | GFP_DMA; - goto again; - } - - return NULL; - } - memset(page_address(page), 0, size); - *dma_addr = addr; - return page_address(page); -} - -void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs) -{ - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct page *page = virt_to_page(vaddr); - - if (!dma_release_from_contiguous(dev, page, count)) - free_pages((unsigned long)vaddr, get_order(size)); -} bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) { if (!*dev) *dev = &x86_dma_fallback_dev; - *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); - if (!is_device_dma_capable(*dev)) return false; return true; @@ -245,16 +187,6 @@ int arch_dma_supported(struct device *dev, u64 mask) } EXPORT_SYMBOL(arch_dma_supported); -int x86_dma_supported(struct device *dev, u64 mask) -{ - /* Copied from i386. Doesn't make much sense, because it will - only work for pci_alloc_coherent. - The caller just has to use GFP_DMA in this case. */ - if (mask < DMA_BIT_MASK(24)) - return 0; - return 1; -} - static int __init pci_iommu_init(void) { struct iommu_table_entry *p; diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 618285e475c6..ac7ea3a8242f 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -37,7 +37,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) return NOMMU_MAPPING_ERROR; - flush_write_buffers(); return bus; } @@ -72,25 +71,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return 0; s->dma_length = s->length; } - flush_write_buffers(); return nents; } -static void nommu_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, - enum dma_data_direction dir) -{ - flush_write_buffers(); -} - - -static void nommu_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, - enum dma_data_direction dir) -{ - flush_write_buffers(); -} - static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) { return dma_addr == NOMMU_MAPPING_ERROR; @@ -101,8 +84,6 @@ const struct dma_map_ops nommu_dma_ops = { .free = dma_generic_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, - .sync_single_for_device = nommu_sync_single_for_device, - .sync_sg_for_device = nommu_sync_sg_for_device, .is_phys = 1, .mapping_error = nommu_mapping_error, .dma_supported = x86_dma_supported, diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 0ee0f8f34251..661583662430 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -17,52 +17,6 @@ int swiotlb __read_mostly; -void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs) -{ - void *vaddr; - - /* - * Don't print a warning when the first allocation attempt fails. - * swiotlb_alloc_coherent() will print a warning when the DMA - * memory allocation ultimately failed. - */ - flags |= __GFP_NOWARN; - - vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, - attrs); - if (vaddr) - return vaddr; - - return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); -} - -void x86_swiotlb_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_addr, - unsigned long attrs) -{ - if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) - swiotlb_free_coherent(dev, size, vaddr, dma_addr); - else - dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); -} - -static const struct dma_map_ops x86_swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, - .alloc = x86_swiotlb_alloc_coherent, - .free = x86_swiotlb_free_coherent, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .dma_supported = NULL, -}; - /* * pci_swiotlb_detect_override - set swiotlb to 1 if necessary * @@ -112,7 +66,7 @@ void __init pci_swiotlb_init(void) { if (swiotlb) { swiotlb_init(0); - dma_ops = &x86_swiotlb_dma_ops; + dma_ops = &swiotlb_dma_ops; } } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2126b9d27c34..725624b6c0c0 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -666,7 +666,7 @@ void native_machine_shutdown(void) * Even without the erratum, it still makes sense to quiet IO APIC * before disabling Local APIC. */ - disable_IO_APIC(); + clear_IO_APIC(); #endif #ifdef CONFIG_SMP @@ -680,6 +680,7 @@ void native_machine_shutdown(void) #endif lapic_shutdown(); + restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 69ac9cb9cac6..f7b82ed7b5b5 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -41,11 +41,11 @@ EXPORT_SYMBOL(rtc_lock); */ int mach_set_rtc_mmss(const struct timespec *now) { - unsigned long nowtime = now->tv_sec; + unsigned long long nowtime = now->tv_sec; struct rtc_time tm; int retval = 0; - rtc_time_to_tm(nowtime, &tm); + rtc_time64_to_tm(nowtime, &tm); if (!rtc_valid_tm(&tm)) { retval = mc146818_set_time(&tm); if (retval) @@ -53,7 +53,7 @@ int mach_set_rtc_mmss(const struct timespec *now) __func__, retval); } else { printk(KERN_ERR - "%s: Invalid RTC value: write of %lx to RTC failed\n", + "%s: Invalid RTC value: write of %llx to RTC failed\n", __func__, nowtime); retval = -EINVAL; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1ae67e982af7..6285697b6e56 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -189,9 +189,7 @@ struct ist_info ist_info; #endif #else -struct cpuinfo_x86 boot_cpu_data __read_mostly = { - .x86_phys_bits = MAX_PHYSMEM_BITS, -}; +struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); #endif @@ -851,6 +849,7 @@ void __init setup_arch(char **cmdline_p) __flush_tlb_all(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); + boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS; #endif /* @@ -1204,20 +1203,13 @@ void __init setup_arch(char **cmdline_p) kasan_init(); -#ifdef CONFIG_X86_32 - /* sync back kernel address range */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. + * Sync back kernel address range. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); tboot_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 497aa766fab3..ea554f812ee1 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); -#ifdef CONFIG_X86_32 /* * Sync back kernel address range again. We already did this in * setup_arch(), but percpu data also needs to be available in * the smpboot asm. We can't reliably pick up percpu mappings * using vmalloc_fault(), because exception dispatch needs * percpu data. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 4cdc0b27ec82..da270b95fe4d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -25,6 +25,7 @@ #include <linux/user-return-notifier.h> #include <linux/uprobes.h> #include <linux/context_tracking.h> +#include <linux/syscalls.h> #include <asm/processor.h> #include <asm/ucontext.h> @@ -601,7 +602,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, * Do a signal return; undo the signal stack. */ #ifdef CONFIG_X86_32 -asmlinkage unsigned long sys_sigreturn(void) +SYSCALL_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe __user *frame; @@ -633,7 +634,7 @@ badframe: } #endif /* CONFIG_X86_32 */ -asmlinkage long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ac057f9b0763..0d930d8987cc 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int)); #define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name)) + BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8); + + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8); /* * Ensure that the size of each si_field never changes. * If it does, it is a sign that the @@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void) CHECK_CSI_SIZE (_kill, 2*sizeof(int)); CHECK_SI_SIZE (_kill, 2*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + CHECK_CSI_OFFSET(_timer); CHECK_CSI_SIZE (_timer, 3*sizeof(int)); CHECK_SI_SIZE (_timer, 6*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_rt); CHECK_CSI_SIZE (_rt, 3*sizeof(int)); CHECK_SI_SIZE (_rt, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_sigchld); CHECK_CSI_SIZE (_sigchld, 5*sizeof(int)); CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C); + #ifdef CONFIG_X86_X32_ABI CHECK_CSI_OFFSET(_sigchld_x32); CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int)); /* no _sigchld_x32 in the generic siginfo_t */ + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20); #endif CHECK_CSI_OFFSET(_sigfault); CHECK_CSI_SIZE (_sigfault, 4*sizeof(int)); CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); + + BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); + + BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18); + + BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); + CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10); + CHECK_CSI_OFFSET(_sigsys); CHECK_CSI_SIZE (_sigsys, 3*sizeof(int)); CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14); + /* any new si_fields should be added here */ } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6f27facbaa9b..ff99e2b6fc54 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1281,11 +1281,10 @@ void __init native_smp_prepare_boot_cpu(void) cpu_set_state_online(me); } -void __init native_smp_cpus_done(unsigned int max_cpus) +void __init calculate_max_logical_packages(void) { int ncpus; - pr_debug("Boot done\n"); /* * Today neither Intel nor AMD support heterogenous systems so * extrapolate the boot cpu's data to all packages. @@ -1293,6 +1292,13 @@ void __init native_smp_cpus_done(unsigned int max_cpus) ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); pr_info("Max logical packages: %u\n", __max_logical_packages); +} + +void __init native_smp_cpus_done(unsigned int max_cpus) +{ + pr_debug("Boot done\n"); + + calculate_max_logical_packages(); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); @@ -1430,8 +1436,8 @@ static void remove_siblinginfo(int cpu) cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); - c->phys_proc_id = 0; c->cpu_core_id = 0; + c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 676774b9bb8d..a3f15ed545b5 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -97,7 +97,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, if (off & ~PAGE_MASK) goto out; - error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); out: return error; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 446c9ef8cfc3..03f3d7695dac 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -181,7 +181,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) break; case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD0; + regs->ip += LEN_UD2; return 1; } @@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code) } NOKPROBE_SYMBOL(do_general_protection); -/* May run on IST stack. */ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { #ifdef CONFIG_DYNAMIC_FTRACE @@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; + /* + * Use ist_enter despite the fact that we don't use an IST stack. + * We can be called from a kprobe in non-CONTEXT_KERNEL kernel + * mode or even during context tracking state changes. + * + * This means that we can't schedule. That's okay. + */ ist_enter(regs); RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) SIGTRAP) == NOTIFY_STOP) goto exit; - /* - * Let others (NMI) know that the debug stack is in use - * as we may switch to the interrupt stack. - */ - debug_stack_usage_inc(); cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); cond_local_irq_disable(regs); - debug_stack_usage_dec(); + exit: ist_exit(regs); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index fb4302738410..ef32297ff17e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1179,6 +1179,45 @@ struct system_counterval_t convert_art_to_tsc(u64 art) } EXPORT_SYMBOL(convert_art_to_tsc); +/** + * convert_art_ns_to_tsc() - Convert ART in nanoseconds to TSC. + * @art_ns: ART (Always Running Timer) in unit of nanoseconds + * + * PTM requires all timestamps to be in units of nanoseconds. When user + * software requests a cross-timestamp, this function converts system timestamp + * to TSC. + * + * This is valid when CPU feature flag X86_FEATURE_TSC_KNOWN_FREQ is set + * indicating the tsc_khz is derived from CPUID[15H]. Drivers should check + * that this flag is set before conversion to TSC is attempted. + * + * Return: + * struct system_counterval_t - system counter value with the pointer to the + * corresponding clocksource + * @cycles: System counter value + * @cs: Clocksource corresponding to system counter value. Used + * by timekeeping code to verify comparibility of two cycle + * values. + */ + +struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) +{ + u64 tmp, res, rem; + + rem = do_div(art_ns, USEC_PER_SEC); + + res = art_ns * tsc_khz; + tmp = rem * tsc_khz; + + do_div(tmp, USEC_PER_SEC); + res += tmp; + + return (struct system_counterval_t) { .cs = art_related_clocksource, + .cycles = res}; +} +EXPORT_SYMBOL(convert_art_ns_to_tsc); + + static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 1f9188f5357c..feb28fee6cea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -5,7 +5,6 @@ #include <asm/unwind.h> #include <asm/orc_types.h> #include <asm/orc_lookup.h> -#include <asm/sections.h> #define orc_warn(fmt, ...) \ printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) @@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + if (init_kernel_text(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 5edb27f1a2c4..9d0b5af7db91 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -727,7 +727,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) return; check_vip: - if (VEFLAGS & X86_EFLAGS_VIP) { + if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) == + (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) { save_v86_state(regs, VM86_STI); return; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9b138a06c1a4..795f3a80e576 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -102,7 +102,6 @@ SECTIONS _stext = .; /* bootstrapping code */ HEAD_TEXT - . = ALIGN(8); TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT @@ -118,9 +117,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_start) = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_end) = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif @@ -198,7 +199,7 @@ SECTIONS . = __vvar_beginning_hack + PAGE_SIZE; } :data - . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); + . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); /* Init code and data - will be freed after init */ . = ALIGN(PAGE_SIZE); @@ -366,8 +367,8 @@ SECTIONS . = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */ _end = .; - STABS_DEBUG - DWARF_DEBUG + STABS_DEBUG + DWARF_DEBUG /* Sections to be discarded */ DISCARDS diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 1151ccd72ce9..ebda84a91510 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -8,6 +8,7 @@ #include <linux/export.h> #include <linux/pci.h> +#include <asm/acpi.h> #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> @@ -26,10 +27,11 @@ void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } -int __init iommu_init_noop(void) { return 0; } -void iommu_shutdown_noop(void) { } -bool __init bool_x86_init_noop(void) { return false; } -void x86_op_int_noop(int cpu) { } +static int __init iommu_init_noop(void) { return 0; } +static void iommu_shutdown_noop(void) { } +static bool __init bool_x86_init_noop(void) { return false; } +static void x86_op_int_noop(int cpu) { } +static u64 u64_x86_init_noop(void) { return 0; } /* * The platform setup functions are preset with the default functions @@ -91,6 +93,11 @@ struct x86_init_ops x86_init __initdata = { .x2apic_available = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, }, + + .acpi = { + .get_root_pointer = u64_x86_init_noop, + .reduced_hw_early_init = acpi_generic_reduced_hw_init, + }, }; struct x86_cpuinit_ops x86_cpuinit = { @@ -146,7 +153,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev) } #endif -struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = { - .read = native_io_apic_read, - .disable = native_disable_io_apic, +struct x86_apic_ops x86_apic_ops __ro_after_init = { + .io_apic_read = native_io_apic_read, + .restore = native_restore_boot_irq_mode, }; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a0c5a69bc7c4..b671fc2d0422 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -607,7 +607,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | - (1 << KVM_FEATURE_PV_TLB_FLUSH); + (1 << KVM_FEATURE_PV_TLB_FLUSH) | + (1 << KVM_FEATURE_ASYNC_PF_VMEXIT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 924ac8ce9d50..391dda8d43b7 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2002,14 +2002,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { - struct kvm_lapic *apic; + struct kvm_lapic *apic = vcpu->arch.apic; int i; - apic_debug("%s\n", __func__); + if (!apic) + return; - ASSERT(vcpu); - apic = vcpu->arch.apic; - ASSERT(apic != NULL); + apic_debug("%s\n", __func__); /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2165,7 +2164,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2569,7 +2567,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu, true); kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eca1d04aeb8..763bb3bade63 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, else pte_access &= ~ACC_WRITE_MASK; + if (!kvm_is_mmio_pfn(pfn)) + spte |= shadow_me_mask; + spte |= (u64)pfn << PAGE_SHIFT; - spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { @@ -3029,7 +3031,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return RET_PF_RETRY; } - return -EFAULT; + return RET_PF_EMULATE; } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, @@ -5080,7 +5082,7 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ -static bool +static __always_inline bool slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) @@ -5110,7 +5112,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, return flush; } -static bool +static __always_inline bool slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, int start_level, int end_level, bool lock_flush_tlb) @@ -5121,7 +5123,7 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5129,7 +5131,7 @@ slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5137,7 +5139,7 @@ slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } -static bool +static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b3e488a74828..9d2043f94e29 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -178,6 +178,8 @@ struct vcpu_svm { uint64_t sysenter_eip; uint64_t tsc_aux; + u64 msr_decfg; + u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; @@ -300,6 +302,8 @@ module_param(vgif, int, 0444); static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); module_param(sev, int, 0444); +static u8 rsm_ins_bytes[] = "\x0f\xaa"; + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -1383,6 +1387,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest()) { set_intercept(svm, INTERCEPT_MONITOR); @@ -1902,6 +1907,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; if (!init_event) { @@ -3699,6 +3705,12 @@ static int emulate_on_interception(struct vcpu_svm *svm) return 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; +} + static int rdpmc_interception(struct vcpu_svm *svm) { int err; @@ -3860,6 +3872,22 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +static int svm_get_msr_feature(struct kvm_msr_entry *msr) +{ + msr->data = 0; + + switch (msr->index) { + case MSR_F10H_DECFG: + if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + break; + default: + return 1; + } + + return 0; +} + static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3935,9 +3963,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->spec_ctrl; break; - case MSR_IA32_UCODE_REV: - msr_info->data = 0x01000065; - break; case MSR_F15H_IC_CFG: { int family, model; @@ -3955,6 +3980,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; + case MSR_F10H_DECFG: + msr_info->data = svm->msr_decfg; + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -4133,6 +4161,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_F10H_DECFG: { + struct kvm_msr_entry msr_entry; + + msr_entry.index = msr->index; + if (svm_get_msr_feature(&msr_entry)) + return 1; + + /* Check the supported bits */ + if (data & ~msr_entry.data) + return 1; + + /* Don't allow the guest to change a bit, #GP */ + if (!msr->host_initiated && (data ^ msr_entry.data)) + return 1; + + svm->msr_decfg = data; + break; + } case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); @@ -4541,7 +4587,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = npf_interception, - [SVM_EXIT_RSM] = emulate_on_interception, + [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, }; @@ -5355,7 +5401,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5464,11 +5510,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -6236,16 +6282,18 @@ e_free: static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { + void __user *measure = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &kvm->arch.sev_info; struct sev_data_launch_measure *data; struct kvm_sev_launch_measure params; + void __user *p = NULL; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -6256,17 +6304,13 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - if (params.uaddr) { + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } - if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { - ret = -EFAULT; - goto e_free; - } - ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) @@ -6290,13 +6334,13 @@ cmd: goto e_free_blob; if (blob) { - if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); @@ -6597,7 +6641,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) struct page **pages; void *blob, *hdr; unsigned long n; - int ret; + int ret, offset; if (!sev_guest(kvm)) return -ENOTTY; @@ -6623,6 +6667,10 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!data) goto e_unpin_memory; + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data->guest_address = __sme_page_pa(pages[0]) + offset; + data->guest_len = params.guest_len; + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); if (IS_ERR(blob)) { ret = PTR_ERR(blob); @@ -6637,8 +6685,8 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) ret = PTR_ERR(hdr); goto e_free_blob; } - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; + data->hdr_address = __psp_pa(hdr); + data->hdr_len = params.hdr_len; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); @@ -6821,6 +6869,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_unblocking = svm_vcpu_unblocking, .update_bp_intercept = update_bp_intercept, + .get_msr_feature = svm_get_msr_feature, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f427723dc7db..92496b9b5f2b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1044,6 +1044,13 @@ static inline bool is_machine_check(u32 intr_info) (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); } +/* Undocumented: icebp/int1 */ +static inline bool is_icebp(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) + == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); +} + static inline bool cpu_has_vmx_msr_bitmap(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS; @@ -3226,6 +3233,11 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, return !(val & ~valid_bits); } +static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +{ + return 1; +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -4485,7 +4497,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; - } else + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); @@ -5765,6 +5778,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6171,7 +6185,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; vcpu->arch.dr6 |= dr6 | DR6_RTM; - if (!(dr6 & ~DR6_RESERVED)) /* icebp */ + if (is_icebp(intr_info)) skip_emulated_instruction(vcpu); kvm_queue_exception(vcpu, DB_VECTOR); @@ -9452,7 +9466,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -9587,11 +9601,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -10136,7 +10150,10 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); + else vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10224,8 +10241,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * updated to reflect this when L1 (or its L2s) actually write to * the MSR. */ - bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); - bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -10693,6 +10710,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control, vmcs12_exec_ctrl; + if (vmx->nested.dirty_vmcs12) { + prepare_vmcs02_full(vcpu, vmcs12, from_vmentry); + vmx->nested.dirty_vmcs12 = false; + } + /* * First, the fields that are shadowed. This must be kept in sync * with vmx_shadow_fields.h. @@ -10930,11 +10952,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */ vmx_set_efer(vcpu, vcpu->arch.efer); - if (vmx->nested.dirty_vmcs12) { - prepare_vmcs02_full(vcpu, vmcs12, from_vmentry); - vmx->nested.dirty_vmcs12 = false; - } - /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), entry_failure_code)) @@ -11196,7 +11213,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (ret) return ret; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken + * by event injection, halt vcpu. + */ + if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; @@ -12287,6 +12309,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .vcpu_put = vmx_vcpu_put, .update_bp_intercept = update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8a0b545ac20..18b5ca7a3197 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1049,6 +1049,45 @@ static u32 emulated_msrs[] = { static unsigned num_emulated_msrs; +/* + * List of msr numbers which are used to expose MSR-based features that + * can be used by a hypervisor to validate requested CPU features. + */ +static u32 msr_based_features[] = { + MSR_F10H_DECFG, + MSR_IA32_UCODE_REV, +}; + +static unsigned int num_msr_based_features; + +static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +{ + switch (msr->index) { + case MSR_IA32_UCODE_REV: + rdmsrl(msr->index, msr->data); + break; + default: + if (kvm_x86_ops->get_msr_feature(msr)) + return 1; + } + return 0; +} + +static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct kvm_msr_entry msr; + int r; + + msr.index = index; + r = kvm_get_msr_feature(&msr); + if (r) + return r; + + *data = msr.data; + + return 0; +} + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -2222,7 +2261,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_AMD64_NB_CFG: - case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: @@ -2230,6 +2268,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_DC_CFG: break; + case MSR_IA32_UCODE_REV: + if (msr_info->host_initiated) + vcpu->arch.microcode_version = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2525,7 +2567,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - msr_info->data = 0x100000000ULL; + msr_info->data = vcpu->arch.microcode_version; break; case MSR_MTRRcap: case 0x200 ... 0x2ff: @@ -2680,13 +2722,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i, idx; + int i; - idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - srcu_read_unlock(&vcpu->kvm->srcu, idx); return i; } @@ -2785,6 +2825,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_GET_MSR_FEATURES: r = 1; break; case KVM_CAP_ADJUST_CLOCK: @@ -2899,6 +2940,31 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; r = 0; break; + case KVM_GET_MSR_FEATURE_INDEX_LIST: { + struct kvm_msr_list __user *user_msr_list = argp; + struct kvm_msr_list msr_list; + unsigned int n; + + r = -EFAULT; + if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) + goto out; + n = msr_list.nmsrs; + msr_list.nmsrs = num_msr_based_features; + if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) + goto out; + r = -E2BIG; + if (n < msr_list.nmsrs) + goto out; + r = -EFAULT; + if (copy_to_user(user_msr_list->indices, &msr_based_features, + num_msr_based_features * sizeof(u32))) + goto out; + r = 0; + break; + } + case KVM_GET_MSRS: + r = msr_io(NULL, argp, do_get_msr_feature, 1); + break; } default: r = -EINVAL; @@ -3636,12 +3702,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_MSRS: + case KVM_GET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_get_msr, 1); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; - case KVM_SET_MSRS: + } + case KVM_SET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_set_msr, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; + } case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; @@ -4464,6 +4536,19 @@ static void kvm_init_msr_list(void) j++; } num_emulated_msrs = j; + + for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + struct kvm_msr_entry msr; + + msr.index = msr_based_features[i]; + if (kvm_get_msr_feature(&msr)) + continue; + + if (j < i) + msr_based_features[j] = msr_based_features[i]; + j++; + } + num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -8017,6 +8102,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + kvm_lapic_reset(vcpu, init_event); + vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -8460,10 +8547,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) return r; } - if (!size) { - r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); - WARN_ON(r < 0); - } + if (!size) + vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); return 0; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 91e9700cc6dc..25a972c61b0a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -28,7 +28,6 @@ lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RETPOLINE) += retpoline.o -OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 81b1635d67de..88acd349911b 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,6 +1,4 @@ #include <linux/linkage.h> -#include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> #include <asm/export.h> /* diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c index d6f848d1211d..2dd1fe13a37b 100644 --- a/arch/x86/lib/cpu.c +++ b/arch/x86/lib/cpu.c @@ -18,7 +18,7 @@ unsigned int x86_model(unsigned int sig) { unsigned int fam, model; - fam = x86_family(sig); + fam = x86_family(sig); model = (sig >> 4) & 0xf; diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 7b881d03d0dd..3cdf06128d13 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -7,6 +7,7 @@ asmlinkage void just_return_func(void); asm( ".type just_return_func, @function\n" + ".globl just_return_func\n" "just_return_func:\n" " ret\n" ".size just_return_func, .-just_return_func\n" diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index 693cce0be82d..fee8b9c0520c 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -2,6 +2,7 @@ #include <linux/export.h> #include <linux/preempt.h> #include <linux/smp.h> +#include <linux/completion.h> #include <asm/msr.h> static void __rdmsr_on_cpu(void *info) @@ -143,13 +144,19 @@ void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) } EXPORT_SYMBOL(wrmsr_on_cpus); +struct msr_info_completion { + struct msr_info msr; + struct completion done; +}; + /* These "safe" variants are slower and should be used when the target MSR may not actually exist. */ static void __rdmsr_safe_on_cpu(void *info) { - struct msr_info *rv = info; + struct msr_info_completion *rv = info; - rv->err = rdmsr_safe(rv->msr_no, &rv->reg.l, &rv->reg.h); + rv->msr.err = rdmsr_safe(rv->msr.msr_no, &rv->msr.reg.l, &rv->msr.reg.h); + complete(&rv->done); } static void __wrmsr_safe_on_cpu(void *info) @@ -161,17 +168,26 @@ static void __wrmsr_safe_on_cpu(void *info) int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { + struct msr_info_completion rv; + call_single_data_t csd = { + .func = __rdmsr_safe_on_cpu, + .info = &rv, + }; int err; - struct msr_info rv; memset(&rv, 0, sizeof(rv)); + init_completion(&rv.done); + rv.msr.msr_no = msr_no; - rv.msr_no = msr_no; - err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); - *l = rv.reg.l; - *h = rv.reg.h; + err = smp_call_function_single_async(cpu, &csd); + if (!err) { + wait_for_completion(&rv.done); + err = rv.msr.err; + } + *l = rv.msr.reg.l; + *h = rv.msr.reg.h; - return err ? err : rv.err; + return err; } EXPORT_SYMBOL(rdmsr_safe_on_cpu); @@ -209,16 +225,13 @@ EXPORT_SYMBOL(wrmsrl_safe_on_cpu); int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { + u32 low, high; int err; - struct msr_info rv; - memset(&rv, 0, sizeof(rv)); + err = rdmsr_safe_on_cpu(cpu, msr_no, &low, &high); + *q = (u64)high << 32 | low; - rv.msr_no = msr_no; - err = smp_call_function_single(cpu, __rdmsr_safe_on_cpu, &rv, 1); - *q = rv.reg.q; - - return err ? err : rv.err; + return err; } EXPORT_SYMBOL(rdmsrl_safe_on_cpu); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 480edc3a5e03..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,7 +7,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> -#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -47,58 +46,3 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif - -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * Google experimented with loop-unrolling and this turned out to be - * the optimal version - two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -.macro STUFF_RSB nr:req sp:req - mov $(\nr / 2), %_ASM_BX - .align 16 -771: - call 772f -773: /* speculation trap */ - pause - lfence - jmp 773b - .align 16 -772: - call 774f -775: /* speculation trap */ - pause - lfence - jmp 775b - .align 16 -774: - dec %_ASM_BX - jnz 771b - add $((BITS_PER_LONG/8) * \nr), \sp -.endm - -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -ENTRY(__fill_rsb) - STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP - ret -END(__fill_rsb) -EXPORT_SYMBOL_GPL(__fill_rsb) - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ - -ENTRY(__clear_rsb) - STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP - ret -END(__clear_rsb) -EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 27e9e90a8d35..4b101dd6e52f 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,12 +1,15 @@ # SPDX-License-Identifier: GPL-2.0 -# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c -KCOV_INSTRUMENT_tlb.o := n -KCOV_INSTRUMENT_mem_encrypt.o := n +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt*.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n +KCOV_INSTRUMENT_mem_encrypt_identity.o := n -KASAN_SANITIZE_mem_encrypt.o := n +KASAN_SANITIZE_mem_encrypt.o := n +KASAN_SANITIZE_mem_encrypt_identity.o := n ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_mem_encrypt.o = -pg +CFLAGS_REMOVE_mem_encrypt.o = -pg +CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ @@ -16,6 +19,7 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_physaddr.o := $(nostackp) CFLAGS_setup_nx.o := $(nostackp) +CFLAGS_mem_encrypt_identity.o := $(nostackp) CFLAGS_fault.o := -I$(src)/../include/asm/trace @@ -47,4 +51,5 @@ obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index b9283cc27622..476d810639a8 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void) for_each_possible_cpu(cpu) setup_cpu_entry_area(cpu); + + /* + * This is the last essential update to swapper_pgdir which needs + * to be synchronized to initial_page_table on 32bit. + */ + sync_initial_page_table(); } diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index 421f2664ffa0..225fe2f0bfec 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -1,4 +1,5 @@ #include <linux/debugfs.h> +#include <linux/efi.h> #include <linux/module.h> #include <linux/seq_file.h> #include <asm/pgtable.h> @@ -72,6 +73,30 @@ static const struct file_operations ptdump_curusr_fops = { }; #endif +#if defined(CONFIG_EFI) && defined(CONFIG_X86_64) +static struct dentry *pe_efi; + +static int ptdump_show_efi(struct seq_file *m, void *v) +{ + if (efi_mm.pgd) + ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false); + return 0; +} + +static int ptdump_open_efi(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show_efi, NULL); +} + +static const struct file_operations ptdump_efi_fops = { + .owner = THIS_MODULE, + .open = ptdump_open_efi, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + static struct dentry *dir, *pe_knl, *pe_curknl; static int __init pt_dump_debug_init(void) @@ -96,6 +121,13 @@ static int __init pt_dump_debug_init(void) if (!pe_curusr) goto err; #endif + +#if defined(CONFIG_EFI) && defined(CONFIG_X86_64) + pe_efi = debugfs_create_file("efi", 0400, dir, NULL, &ptdump_efi_fops); + if (!pe_efi) + goto err; +#endif + return 0; err: debugfs_remove_recursive(dir); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 2a4849e92831..62a7e9f65dec 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -29,6 +29,7 @@ struct pg_state { int level; pgprot_t current_prot; + pgprotval_t effective_prot; unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; @@ -85,11 +86,15 @@ static struct addr_marker address_markers[] = { [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" }, [VMEMMAP_START_NR] = { 0UL, "Vmemmap" }, #ifdef CONFIG_KASAN - [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" }, - [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" }, + /* + * These fields get initialized with the (dynamic) + * KASAN_SHADOW_{START,END} values in pt_dump_init(). + */ + [KASAN_SHADOW_START_NR] = { 0UL, "KASAN shadow" }, + [KASAN_SHADOW_END_NR] = { 0UL, "KASAN shadow end" }, #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL - [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" }, + [LDT_NR] = { 0UL, "LDT remap" }, #endif [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" }, #ifdef CONFIG_X86_ESPFIX64 @@ -231,9 +236,9 @@ static unsigned long normalize_addr(unsigned long u) * print what we collected so far. */ static void note_page(struct seq_file *m, struct pg_state *st, - pgprot_t new_prot, int level) + pgprot_t new_prot, pgprotval_t new_eff, int level) { - pgprotval_t prot, cur; + pgprotval_t prot, cur, eff; static const char units[] = "BKMGTPE"; /* @@ -243,23 +248,24 @@ static void note_page(struct seq_file *m, struct pg_state *st, */ prot = pgprot_val(new_prot); cur = pgprot_val(st->current_prot); + eff = st->effective_prot; if (!st->level) { /* First entry */ st->current_prot = new_prot; + st->effective_prot = new_eff; st->level = level; st->marker = address_markers; st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); - } else if (prot != cur || level != st->level || + } else if (prot != cur || new_eff != eff || level != st->level || st->current_address >= st->marker[1].start_address) { const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; - pgprotval_t pr = pgprot_val(st->current_prot); - if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) { + if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) { WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %p/%pS\n", (void *)st->start_address, @@ -313,21 +319,30 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->start_address = st->current_address; st->current_prot = new_prot; + st->effective_prot = new_eff; st->level = level; } } -static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P) +static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2) +{ + return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) | + ((prot1 | prot2) & _PAGE_NX); +} + +static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, + pgprotval_t eff_in, unsigned long P) { int i; pte_t *start; - pgprotval_t prot; + pgprotval_t prot, eff; start = (pte_t *)pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { prot = pte_flags(*start); + eff = effective_prot(eff_in, prot); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, __pgprot(prot), 5); + note_page(m, st, __pgprot(prot), eff, 5); start++; } } @@ -344,12 +359,10 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, void *pt) { if (__pa(pt) == __pa(kasan_zero_pmd) || -#ifdef CONFIG_X86_5LEVEL - __pa(pt) == __pa(kasan_zero_p4d) || -#endif + (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) || __pa(pt) == __pa(kasan_zero_pud)) { pgprotval_t prot = pte_flags(kasan_zero_pte[0]); - note_page(m, st, __pgprot(prot), 5); + note_page(m, st, __pgprot(prot), 0, 5); return true; } return false; @@ -364,42 +377,45 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, #if PTRS_PER_PMD > 1 -static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P) +static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, + pgprotval_t eff_in, unsigned long P) { int i; pmd_t *start, *pmd_start; - pgprotval_t prot; + pgprotval_t prot, eff; pmd_start = start = (pmd_t *)pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { + prot = pmd_flags(*start); + eff = effective_prot(eff_in, prot); if (pmd_large(*start) || !pmd_present(*start)) { - prot = pmd_flags(*start); - note_page(m, st, __pgprot(prot), 4); + note_page(m, st, __pgprot(prot), eff, 4); } else if (!kasan_page_table(m, st, pmd_start)) { - walk_pte_level(m, st, *start, + walk_pte_level(m, st, *start, eff, P + i * PMD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 4); + note_page(m, st, __pgprot(0), 0, 4); start++; } } #else -#define walk_pmd_level(m,s,a,p) walk_pte_level(m,s,__pmd(pud_val(a)),p) +#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p) #define pud_large(a) pmd_large(__pmd(pud_val(a))) #define pud_none(a) pmd_none(__pmd(pud_val(a))) #endif #if PTRS_PER_PUD > 1 -static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P) +static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, + pgprotval_t eff_in, unsigned long P) { int i; pud_t *start, *pud_start; - pgprotval_t prot; + pgprotval_t prot, eff; pud_t *prev_pud = NULL; pud_start = start = (pud_t *)p4d_page_vaddr(addr); @@ -407,15 +423,16 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { + prot = pud_flags(*start); + eff = effective_prot(eff_in, prot); if (pud_large(*start) || !pud_present(*start)) { - prot = pud_flags(*start); - note_page(m, st, __pgprot(prot), 3); + note_page(m, st, __pgprot(prot), eff, 3); } else if (!kasan_page_table(m, st, pud_start)) { - walk_pmd_level(m, st, *start, + walk_pmd_level(m, st, *start, eff, P + i * PUD_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 3); + note_page(m, st, __pgprot(0), 0, 3); prev_pud = start; start++; @@ -423,43 +440,43 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, } #else -#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),p) +#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p) #define p4d_large(a) pud_large(__pud(p4d_val(a))) #define p4d_none(a) pud_none(__pud(p4d_val(a))) #endif -#if PTRS_PER_P4D > 1 - -static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P) +static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, + pgprotval_t eff_in, unsigned long P) { int i; p4d_t *start, *p4d_start; - pgprotval_t prot; + pgprotval_t prot, eff; + + if (PTRS_PER_P4D == 1) + return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P); p4d_start = start = (p4d_t *)pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_P4D; i++) { st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT); if (!p4d_none(*start)) { + prot = p4d_flags(*start); + eff = effective_prot(eff_in, prot); if (p4d_large(*start) || !p4d_present(*start)) { - prot = p4d_flags(*start); - note_page(m, st, __pgprot(prot), 2); + note_page(m, st, __pgprot(prot), eff, 2); } else if (!kasan_page_table(m, st, p4d_start)) { - walk_pud_level(m, st, *start, + walk_pud_level(m, st, *start, eff, P + i * P4D_LEVEL_MULT); } } else - note_page(m, st, __pgprot(0), 2); + note_page(m, st, __pgprot(0), 0, 2); start++; } } -#else -#define walk_p4d_level(m,s,a,p) walk_pud_level(m,s,__p4d(pgd_val(a)),p) -#define pgd_large(a) p4d_large(__p4d(pgd_val(a))) -#define pgd_none(a) p4d_none(__p4d(pgd_val(a))) -#endif +#define pgd_large(a) (pgtable_l5_enabled ? pgd_large(a) : p4d_large(__p4d(pgd_val(a)))) +#define pgd_none(a) (pgtable_l5_enabled ? pgd_none(a) : p4d_none(__p4d(pgd_val(a)))) static inline bool is_hypervisor_range(int idx) { @@ -483,7 +500,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, #else pgd_t *start = swapper_pg_dir; #endif - pgprotval_t prot; + pgprotval_t prot, eff; int i; struct pg_state st = {}; @@ -499,15 +516,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); if (!pgd_none(*start) && !is_hypervisor_range(i)) { + prot = pgd_flags(*start); +#ifdef CONFIG_X86_PAE + eff = _PAGE_USER | _PAGE_RW; +#else + eff = prot; +#endif if (pgd_large(*start) || !pgd_present(*start)) { - prot = pgd_flags(*start); - note_page(m, &st, __pgprot(prot), 1); + note_page(m, &st, __pgprot(prot), eff, 1); } else { - walk_p4d_level(m, &st, *start, + walk_p4d_level(m, &st, *start, eff, i * PGD_LEVEL_MULT); } } else - note_page(m, &st, __pgprot(0), 1); + note_page(m, &st, __pgprot(0), 0, 1); cond_resched(); start++; @@ -515,7 +537,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, /* Flush out the last page */ st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); - note_page(m, &st, __pgprot(0), 0); + note_page(m, &st, __pgprot(0), 0, 0); if (!checkwx) return; if (st.wx_pages) @@ -570,6 +592,13 @@ static int __init pt_dump_init(void) address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET; address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START; +#ifdef CONFIG_MODIFY_LDT_SYSCALL + address_markers[LDT_NR].start_address = LDT_BASE_ADDR; +#endif +#ifdef CONFIG_KASAN + address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START; + address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END; +#endif #endif #ifdef CONFIG_X86_32 address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 800de815519c..73bd8c95ac71 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -330,7 +330,7 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; - if (pmd_huge(*pmd_k)) + if (pmd_large(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); @@ -417,11 +417,11 @@ void vmalloc_sync_all(void) */ static noinline int vmalloc_fault(unsigned long address) { - pgd_t *pgd, *pgd_ref; - p4d_t *p4d, *p4d_ref; - pud_t *pud, *pud_ref; - pmd_t *pmd, *pmd_ref; - pte_t *pte, *pte_ref; + pgd_t *pgd, *pgd_k; + p4d_t *p4d, *p4d_k; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) @@ -435,73 +435,51 @@ static noinline int vmalloc_fault(unsigned long address) * case just flush: */ pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address); - pgd_ref = pgd_offset_k(address); - if (pgd_none(*pgd_ref)) + pgd_k = pgd_offset_k(address); + if (pgd_none(*pgd_k)) return -1; - if (CONFIG_PGTABLE_LEVELS > 4) { + if (pgtable_l5_enabled) { if (pgd_none(*pgd)) { - set_pgd(pgd, *pgd_ref); + set_pgd(pgd, *pgd_k); arch_flush_lazy_mmu_mode(); } else { - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_k)); } } /* With 4-level paging, copying happens on the p4d level. */ p4d = p4d_offset(pgd, address); - p4d_ref = p4d_offset(pgd_ref, address); - if (p4d_none(*p4d_ref)) + p4d_k = p4d_offset(pgd_k, address); + if (p4d_none(*p4d_k)) return -1; - if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) { - set_p4d(p4d, *p4d_ref); + if (p4d_none(*p4d) && !pgtable_l5_enabled) { + set_p4d(p4d, *p4d_k); arch_flush_lazy_mmu_mode(); } else { - BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_ref)); + BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_k)); } - /* - * Below here mismatches are bugs because these lower tables - * are shared: - */ BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4); pud = pud_offset(p4d, address); - pud_ref = pud_offset(p4d_ref, address); - if (pud_none(*pud_ref)) + if (pud_none(*pud)) return -1; - if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) - BUG(); - - if (pud_huge(*pud)) + if (pud_large(*pud)) return 0; pmd = pmd_offset(pud, address); - pmd_ref = pmd_offset(pud_ref, address); - if (pmd_none(*pmd_ref)) + if (pmd_none(*pmd)) return -1; - if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) - BUG(); - - if (pmd_huge(*pmd)) + if (pmd_large(*pmd)) return 0; - pte_ref = pte_offset_kernel(pmd_ref, address); - if (!pte_present(*pte_ref)) - return -1; - pte = pte_offset_kernel(pmd, address); - - /* - * Don't use pte_page here, because the mappings can point - * outside mem_map, and the NUMA hash lookup cannot handle - * that: - */ - if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref)) - BUG(); + if (!pte_present(*pte)) + return -1; return 0; } @@ -699,7 +677,6 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, printk(KERN_CONT "paging request"); printk(KERN_CONT " at %px\n", (void *) address); - printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip); dump_pagetable(address); } @@ -1248,10 +1225,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, tsk = current; mm = tsk->mm; - /* - * Detect and handle instructions that would cause a page fault for - * both a tracked kernel page and a userspace page. - */ prefetchw(&mm->mmap_sem); if (unlikely(kmmio_fault(regs, address))) diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index ab33a32df2a8..9aa22be8331e 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -120,7 +120,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, result = ident_p4d_init(info, p4d, addr, next); if (result) return result; - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + if (pgtable_l5_enabled) { set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag)); } else { /* diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 79cb066f40c0..396e1f0151ac 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ +void __init sync_initial_page_table(void) +{ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); +} + void __init native_pagetable_init(void) { unsigned long pfn, va; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 1ab42c852069..45241de66785 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -88,12 +88,7 @@ static int __init nonx32_setup(char *str) } __setup("noexec32=", nonx32_setup); -/* - * When memory was added make sure all the processes MM have - * suitable PGD entries in the local PGD level page. - */ -#ifdef CONFIG_X86_5LEVEL -void sync_global_pgds(unsigned long start, unsigned long end) +static void sync_global_pgds_l5(unsigned long start, unsigned long end) { unsigned long addr; @@ -129,8 +124,8 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(&pgd_lock); } } -#else -void sync_global_pgds(unsigned long start, unsigned long end) + +static void sync_global_pgds_l4(unsigned long start, unsigned long end) { unsigned long addr; @@ -143,7 +138,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) * With folded p4d, pgd_none() is always false, we need to * handle synchonization on p4d level. */ - BUILD_BUG_ON(pgd_none(*pgd_ref)); + MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref)); p4d_ref = p4d_offset(pgd_ref, addr); if (p4d_none(*p4d_ref)) @@ -173,7 +168,18 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(&pgd_lock); } } -#endif + +/* + * When memory was added make sure all the processes MM have + * suitable PGD entries in the local PGD level page. + */ +void sync_global_pgds(unsigned long start, unsigned long end) +{ + if (pgtable_l5_enabled) + sync_global_pgds_l5(start, end); + else + sync_global_pgds_l4(start, end); +} /* * NOTE: This function is marked __ref because it calls __init function @@ -256,7 +262,7 @@ static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) @@ -632,7 +638,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, unsigned long vaddr = (unsigned long)__va(paddr); int i = p4d_index(vaddr); - if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + if (!pgtable_l5_enabled) return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask); for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) { @@ -712,7 +718,7 @@ kernel_physical_mapping_init(unsigned long paddr_start, page_size_mask); spin_lock(&init_mm.page_table_lock); - if (IS_ENABLED(CONFIG_X86_5LEVEL)) + if (pgtable_l5_enabled) pgd_populate(&init_mm, pgd, p4d); else p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d); @@ -800,17 +806,11 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, #define PAGE_INUSE 0xFD -static void __meminit free_pagetable(struct page *page, int order, - struct vmem_altmap *altmap) +static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; - if (altmap) { - vmem_altmap_free(altmap, nr_pages); - return; - } - /* bootmem page has reserved flag */ if (PageReserved(page)) { __ClearPageReserved(page); @@ -826,9 +826,17 @@ static void __meminit free_pagetable(struct page *page, int order, free_pages((unsigned long)page_address(page), order); } -static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd, +static void __meminit free_hugepage_table(struct page *page, struct vmem_altmap *altmap) { + if (altmap) + vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE); + else + free_pagetable(page, get_order(PMD_SIZE)); +} + +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ pte_t *pte; int i; @@ -839,14 +847,13 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd, } /* free a pte talbe */ - free_pagetable(pmd_page(*pmd), 0, altmap); + free_pagetable(pmd_page(*pmd), 0); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, - struct vmem_altmap *altmap) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) { pmd_t *pmd; int i; @@ -858,14 +865,13 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, } /* free a pmd talbe */ - free_pagetable(pud_page(*pud), 0, altmap); + free_pagetable(pud_page(*pud), 0); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, - struct vmem_altmap *altmap) +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) { pud_t *pud; int i; @@ -877,7 +883,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, } /* free a pud talbe */ - free_pagetable(p4d_page(*p4d), 0, altmap); + free_pagetable(p4d_page(*p4d), 0); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); spin_unlock(&init_mm.page_table_lock); @@ -885,7 +891,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, - struct vmem_altmap *altmap, bool direct) + bool direct) { unsigned long next, pages = 0; pte_t *pte; @@ -916,7 +922,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, * freed when offlining, or simplely not in use. */ if (!direct) - free_pagetable(pte_page(*pte), 0, altmap); + free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -939,7 +945,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, page_addr = page_address(pte_page(*pte)); if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { - free_pagetable(pte_page(*pte), 0, altmap); + free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -974,9 +980,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) - free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE), - altmap); + free_hugepage_table(pmd_page(*pmd), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -989,9 +994,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, page_addr = page_address(pmd_page(*pmd)); if (!memchr_inv(page_addr, PAGE_INUSE, PMD_SIZE)) { - free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE), - altmap); + free_hugepage_table(pmd_page(*pmd), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -1003,8 +1007,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next, altmap, direct); - free_pte_table(pte_base, pmd, altmap); + remove_pte_table(pte_base, addr, next, direct); + free_pte_table(pte_base, pmd); } /* Call free_pmd_table() in remove_pud_table(). */ @@ -1033,8 +1037,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, IS_ALIGNED(next, PUD_SIZE)) { if (!direct) free_pagetable(pud_page(*pud), - get_order(PUD_SIZE), - altmap); + get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1048,8 +1051,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!memchr_inv(page_addr, PAGE_INUSE, PUD_SIZE)) { free_pagetable(pud_page(*pud), - get_order(PUD_SIZE), - altmap); + get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1062,7 +1064,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, pmd_base = pmd_offset(pud, 0); remove_pmd_table(pmd_base, addr, next, direct, altmap); - free_pmd_table(pmd_base, pud, altmap); + free_pmd_table(pmd_base, pud); } if (direct) @@ -1093,8 +1095,8 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, * 5-level case we should free them. This code will have to change * to adapt for boot-time switching between 4 and 5 level page tables. */ - if (CONFIG_PGTABLE_LEVELS == 5) - free_pud_table(pud_base, p4d, altmap); + if (pgtable_l5_enabled) + free_pud_table(pud_base, p4d); } if (direct) @@ -1193,8 +1195,8 @@ void __init mem_init(void) register_page_bootmem_info(); /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, - PAGE_SIZE, KCORE_OTHER); + if (get_gate_vma(&init_mm)) + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER); mem_init_print_info(NULL); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c45b6ec5357b..e2db83bebc3b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -820,5 +820,5 @@ void __init __early_set_fixmap(enum fixed_addresses idx, set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags)); else pte_clear(&init_mm, addr, pte); - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index af6f2f9c6a26..d8ff013ea9d0 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,6 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt + +#ifdef CONFIG_X86_5LEVEL +/* Too early to use cpu_feature_enabled() */ +#define pgtable_l5_enabled __pgtable_l5_enabled +#endif + #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> @@ -19,7 +25,7 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; -static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); +static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); static __init void *early_alloc(size_t size, int nid, bool panic) { @@ -176,10 +182,10 @@ static void __init clear_pgds(unsigned long start, * With folded p4d, pgd_clear() is nop, use p4d_clear() * instead. */ - if (CONFIG_PGTABLE_LEVELS < 5) - p4d_clear(p4d_offset(pgd, start)); - else + if (pgtable_l5_enabled) pgd_clear(pgd); + else + p4d_clear(p4d_offset(pgd, start)); } pgd = pgd_offset_k(start); @@ -191,7 +197,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr) { unsigned long p4d; - if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + if (!pgtable_l5_enabled) return (p4d_t *)pgd; p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK; @@ -272,7 +278,7 @@ void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PUD; i++) kasan_zero_pud[i] = __pud(pud_val); - for (i = 0; IS_ENABLED(CONFIG_X86_5LEVEL) && i < PTRS_PER_P4D; i++) + for (i = 0; pgtable_l5_enabled && i < PTRS_PER_P4D; i++) kasan_zero_p4d[i] = __p4d(p4d_val); kasan_map_early_shadow(early_top_pgt); @@ -303,7 +309,7 @@ void __init kasan_init(void) * bunch of things like kernel code, modules, EFI mapping, etc. * We need to take extra steps to not overwrite them. */ - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + if (pgtable_l5_enabled) { void *ptr; ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END)); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index aedebd2ebf1e..615cc03ced84 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -34,23 +34,12 @@ #define TB_SHIFT 40 /* - * Virtual address start and end range for randomization. - * * The end address could depend on more configuration options to make the * highest amount of space for randomization available, but that's too hard * to keep straight and caused issues already. */ -static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; -/* Default values */ -unsigned long page_offset_base = __PAGE_OFFSET_BASE; -EXPORT_SYMBOL(page_offset_base); -unsigned long vmalloc_base = __VMALLOC_BASE; -EXPORT_SYMBOL(vmalloc_base); -unsigned long vmemmap_base = __VMEMMAP_BASE; -EXPORT_SYMBOL(vmemmap_base); - /* * Memory regions randomized by KASLR (except modules that use a separate logic * earlier during boot). The list is ordered based on virtual addresses. This @@ -60,8 +49,8 @@ static __initdata struct kaslr_memory_region { unsigned long *base; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT) /* Maximum */ }, - { &vmalloc_base, VMALLOC_SIZE_TB }, + { &page_offset_base, 0 }, + { &vmalloc_base, 0 }, { &vmemmap_base, 1 }, }; @@ -84,11 +73,14 @@ static inline bool kaslr_memory_enabled(void) void __init kernel_randomize_memory(void) { size_t i; - unsigned long vaddr = vaddr_start; + unsigned long vaddr_start, vaddr; unsigned long rand, memory_tb; struct rnd_state rand_state; unsigned long remain_entropy; + vaddr_start = pgtable_l5_enabled ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4; + vaddr = vaddr_start; + /* * These BUILD_BUG_ON checks ensure the memory layout is consistent * with the vaddr_start/vaddr_end variables. These checks are very @@ -101,6 +93,9 @@ void __init kernel_randomize_memory(void) if (!kaslr_memory_enabled()) return; + kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT); + kaslr_regions[1].size_tb = VMALLOC_SIZE_TB; + /* * Update Physical memory mapping to available and * add padding if needed (especially for memory hotplug support). @@ -129,7 +124,7 @@ void __init kernel_randomize_memory(void) */ entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); prandom_bytes_state(&rand_state, &rand, sizeof(rand)); - if (IS_ENABLED(CONFIG_X86_5LEVEL)) + if (pgtable_l5_enabled) entropy = (rand % (entropy + 1)) & P4D_MASK; else entropy = (rand % (entropy + 1)) & PUD_MASK; @@ -141,7 +136,7 @@ void __init kernel_randomize_memory(void) * randomization alignment. */ vaddr += get_padding(&kaslr_regions[i]); - if (IS_ENABLED(CONFIG_X86_5LEVEL)) + if (pgtable_l5_enabled) vaddr = round_up(vaddr + 1, P4D_SIZE); else vaddr = round_up(vaddr + 1, PUD_SIZE); @@ -217,7 +212,7 @@ void __meminit init_trampoline(void) return; } - if (IS_ENABLED(CONFIG_X86_5LEVEL)) + if (pgtable_l5_enabled) init_trampoline_p4d(); else init_trampoline_pud(); diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 58477ec3d66d..7c8686709636 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -168,7 +168,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->addr); + __flush_tlb_one_kernel(f->addr); return 0; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 1a53071e2e17..b2de398d1fd3 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -25,17 +25,12 @@ #include <asm/bootparam.h> #include <asm/set_memory.h> #include <asm/cacheflush.h> -#include <asm/sections.h> #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/cmdline.h> #include "mm_internal.h" -static char sme_cmdline_arg[] __initdata = "mem_encrypt"; -static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; - /* * Since SME related variables are set early in the boot process they must * reside in the .data section so as not to be zeroed out when the .bss @@ -46,7 +41,7 @@ EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); -static bool sev_enabled __section(.data); +bool sev_enabled __section(.data); /* Buffer used for early in-place encryption by BSP, no locking needed */ static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -200,67 +195,6 @@ void __init sme_early_init(void) swiotlb_force = SWIOTLB_FORCE; } -static void *sev_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - unsigned long dma_mask; - unsigned int order; - struct page *page; - void *vaddr = NULL; - - dma_mask = dma_alloc_coherent_mask(dev, gfp); - order = get_order(size); - - /* - * Memory will be memset to zero after marking decrypted, so don't - * bother clearing it before. - */ - gfp &= ~__GFP_ZERO; - - page = alloc_pages_node(dev_to_node(dev), gfp, order); - if (page) { - dma_addr_t addr; - - /* - * Since we will be clearing the encryption bit, check the - * mask with it already cleared. - */ - addr = __sme_clr(phys_to_dma(dev, page_to_phys(page))); - if ((addr + size) > dma_mask) { - __free_pages(page, get_order(size)); - } else { - vaddr = page_address(page); - *dma_handle = addr; - } - } - - if (!vaddr) - vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp); - - if (!vaddr) - return NULL; - - /* Clear the SME encryption bit for DMA use if not swiotlb area */ - if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) { - set_memory_decrypted((unsigned long)vaddr, 1 << order); - memset(vaddr, 0, PAGE_SIZE << order); - *dma_handle = __sme_clr(*dma_handle); - } - - return vaddr; -} - -static void sev_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - /* Set the SME encryption bit for re-use if not swiotlb area */ - if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle))) - set_memory_encrypted((unsigned long)vaddr, - 1 << get_order(size)); - - swiotlb_free_coherent(dev, size, vaddr, dma_handle); -} - static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) { pgprot_t old_prot, new_prot; @@ -413,20 +347,6 @@ bool sev_active(void) } EXPORT_SYMBOL(sev_active); -static const struct dma_map_ops sev_dma_ops = { - .alloc = sev_alloc, - .free = sev_free, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, -}; - /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { @@ -437,12 +357,11 @@ void __init mem_encrypt_init(void) swiotlb_update_mem_attributes(); /* - * With SEV, DMA operations cannot use encryption. New DMA ops - * are required in order to mark the DMA areas as decrypted or - * to use bounce buffers. + * With SEV, DMA operations cannot use encryption, we need to use + * SWIOTLB to bounce buffer DMA operation. */ if (sev_active()) - dma_ops = &sev_dma_ops; + dma_ops = &swiotlb_dma_ops; /* * With SEV, we need to unroll the rep string I/O instructions. @@ -455,582 +374,3 @@ void __init mem_encrypt_init(void) : "Secure Memory Encryption (SME)"); } -void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) -{ - WARN(PAGE_ALIGN(size) != size, - "size is not page-aligned (%#lx)\n", size); - - /* Make the SWIOTLB buffer area decrypted */ - set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); -} - -struct sme_populate_pgd_data { - void *pgtable_area; - pgd_t *pgd; - - pmdval_t pmd_flags; - pteval_t pte_flags; - unsigned long paddr; - - unsigned long vaddr; - unsigned long vaddr_end; -}; - -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) -{ - unsigned long pgd_start, pgd_end, pgd_size; - pgd_t *pgd_p; - - pgd_start = ppd->vaddr & PGDIR_MASK; - pgd_end = ppd->vaddr_end & PGDIR_MASK; - - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - - pgd_p = ppd->pgd + pgd_index(ppd->vaddr); - - memset(pgd_p, 0, pgd_size); -} - -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS _KERNPG_TABLE_NOENC - -#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) - -#define PMD_FLAGS_DEC PMD_FLAGS_LARGE -#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ - (_PAGE_PAT | _PAGE_PWT)) - -#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) - -#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) - -#define PTE_FLAGS_DEC PTE_FLAGS -#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ - (_PAGE_PAT | _PAGE_PWT)) - -#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) - -static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) -{ - pgd_t *pgd_p; - p4d_t *p4d_p; - pud_t *pud_p; - pmd_t *pmd_p; - - pgd_p = ppd->pgd + pgd_index(ppd->vaddr); - if (native_pgd_val(*pgd_p)) { - if (IS_ENABLED(CONFIG_X86_5LEVEL)) - p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); - else - pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); - } else { - pgd_t pgd; - - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = ppd->pgtable_area; - memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; - - pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); - } else { - pud_p = ppd->pgtable_area; - memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; - - pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); - } - native_set_pgd(pgd_p, pgd); - } - - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(ppd->vaddr); - if (native_p4d_val(*p4d_p)) { - pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); - } else { - p4d_t p4d; - - pud_p = ppd->pgtable_area; - memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; - - p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); - native_set_p4d(p4d_p, p4d); - } - } - - pud_p += pud_index(ppd->vaddr); - if (native_pud_val(*pud_p)) { - if (native_pud_val(*pud_p) & _PAGE_PSE) - return NULL; - - pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); - } else { - pud_t pud; - - pmd_p = ppd->pgtable_area; - memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; - - pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); - native_set_pud(pud_p, pud); - } - - return pmd_p; -} - -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) -{ - pmd_t *pmd_p; - - pmd_p = sme_prepare_pgd(ppd); - if (!pmd_p) - return; - - pmd_p += pmd_index(ppd->vaddr); - if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); -} - -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) -{ - pmd_t *pmd_p; - pte_t *pte_p; - - pmd_p = sme_prepare_pgd(ppd); - if (!pmd_p) - return; - - pmd_p += pmd_index(ppd->vaddr); - if (native_pmd_val(*pmd_p)) { - if (native_pmd_val(*pmd_p) & _PAGE_PSE) - return; - - pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); - } else { - pmd_t pmd; - - pte_p = ppd->pgtable_area; - memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); - ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; - - pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); - native_set_pmd(pmd_p, pmd); - } - - pte_p += pte_index(ppd->vaddr); - if (!native_pte_val(*pte_p)) - native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); -} - -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) -{ - while (ppd->vaddr < ppd->vaddr_end) { - sme_populate_pgd_large(ppd); - - ppd->vaddr += PMD_PAGE_SIZE; - ppd->paddr += PMD_PAGE_SIZE; - } -} - -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) -{ - while (ppd->vaddr < ppd->vaddr_end) { - sme_populate_pgd(ppd); - - ppd->vaddr += PAGE_SIZE; - ppd->paddr += PAGE_SIZE; - } -} - -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, - pmdval_t pmd_flags, pteval_t pte_flags) -{ - unsigned long vaddr_end; - - ppd->pmd_flags = pmd_flags; - ppd->pte_flags = pte_flags; - - /* Save original end value since we modify the struct value */ - vaddr_end = ppd->vaddr_end; - - /* If start is not 2MB aligned, create PTE entries */ - ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); - __sme_map_range_pte(ppd); - - /* Create PMD entries */ - ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; - __sme_map_range_pmd(ppd); - - /* If end is not 2MB aligned, create PTE entries */ - ppd->vaddr_end = vaddr_end; - __sme_map_range_pte(ppd); -} - -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) -{ - __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); -} - -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) -{ - __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); -} - -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) -{ - __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); -} - -static unsigned long __init sme_pgtable_calc(unsigned long len) -{ - unsigned long p4d_size, pud_size, pmd_size, pte_size; - unsigned long total; - - /* - * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. Those mappings will be covered mostly - * by 2MB PMD entries so we can conservatively calculate the required - * number of P4D, PUD and PMD structures needed to perform the - * mappings. For mappings that are not 2MB aligned, PTE mappings - * would be needed for the start and end portion of the address range - * that fall outside of the 2MB alignment. This results in, at most, - * two extra pages to hold PTE entries for each range that is mapped. - * Incrementing the count for each covers the case where the addresses - * cross entries. - */ - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; - p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; - pud_size = (ALIGN(len, P4D_SIZE) / P4D_SIZE) + 1; - pud_size *= sizeof(pud_t) * PTRS_PER_PUD; - } else { - p4d_size = 0; - pud_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; - pud_size *= sizeof(pud_t) * PTRS_PER_PUD; - } - pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; - pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; - pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - - total = p4d_size + pud_size + pmd_size + pte_size; - - /* - * Now calculate the added pagetable structures needed to populate - * the new pagetables. - */ - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; - p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D; - pud_size = ALIGN(total, P4D_SIZE) / P4D_SIZE; - pud_size *= sizeof(pud_t) * PTRS_PER_PUD; - } else { - p4d_size = 0; - pud_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE; - pud_size *= sizeof(pud_t) * PTRS_PER_PUD; - } - pmd_size = ALIGN(total, PUD_SIZE) / PUD_SIZE; - pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; - - total += p4d_size + pud_size + pmd_size; - - return total; -} - -void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp) -{ - unsigned long workarea_start, workarea_end, workarea_len; - unsigned long execute_start, execute_end, execute_len; - unsigned long kernel_start, kernel_end, kernel_len; - unsigned long initrd_start, initrd_end, initrd_len; - struct sme_populate_pgd_data ppd; - unsigned long pgtable_area_len; - unsigned long decrypted_base; - - if (!sme_active()) - return; - - /* - * Prepare for encrypting the kernel and initrd by building new - * pagetables with the necessary attributes needed to encrypt the - * kernel in place. - * - * One range of virtual addresses will map the memory occupied - * by the kernel and initrd as encrypted. - * - * Another range of virtual addresses will map the memory occupied - * by the kernel and initrd as decrypted and write-protected. - * - * The use of write-protect attribute will prevent any of the - * memory from being cached. - */ - - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); - kernel_len = kernel_end - kernel_start; - - initrd_start = 0; - initrd_end = 0; - initrd_len = 0; -#ifdef CONFIG_BLK_DEV_INITRD - initrd_len = (unsigned long)bp->hdr.ramdisk_size | - ((unsigned long)bp->ext_ramdisk_size << 32); - if (initrd_len) { - initrd_start = (unsigned long)bp->hdr.ramdisk_image | - ((unsigned long)bp->ext_ramdisk_image << 32); - initrd_end = PAGE_ALIGN(initrd_start + initrd_len); - initrd_len = initrd_end - initrd_start; - } -#endif - - /* Set the encryption workarea to be immediately after the kernel */ - workarea_start = kernel_end; - - /* - * Calculate required number of workarea bytes needed: - * executable encryption area size: - * stack page (PAGE_SIZE) - * encryption routine page (PAGE_SIZE) - * intermediate copy buffer (PMD_PAGE_SIZE) - * pagetable structures for the encryption of the kernel - * pagetable structures for workarea (in case not currently mapped) - */ - execute_start = workarea_start; - execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE; - execute_len = execute_end - execute_start; - - /* - * One PGD for both encrypted and decrypted mappings and a set of - * PUDs and PMDs for each of the encrypted and decrypted mappings. - */ - pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; - pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; - if (initrd_len) - pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; - - /* PUDs and PMDs needed in the current pagetables for the workarea */ - pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); - - /* - * The total workarea includes the executable encryption area and - * the pagetable area. The start of the workarea is already 2MB - * aligned, align the end of the workarea on a 2MB boundary so that - * we don't try to create/allocate PTE entries from the workarea - * before it is mapped. - */ - workarea_len = execute_len + pgtable_area_len; - workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); - - /* - * Set the address to the start of where newly created pagetable - * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable - * structures are created when the workarea is added to the current - * pagetables and when the new encrypted and decrypted kernel - * mappings are populated. - */ - ppd.pgtable_area = (void *)execute_end; - - /* - * Make sure the current pagetable structure has entries for - * addressing the workarea. - */ - ppd.pgd = (pgd_t *)native_read_cr3_pa(); - ppd.paddr = workarea_start; - ppd.vaddr = workarea_start; - ppd.vaddr_end = workarea_end; - sme_map_range_decrypted(&ppd); - - /* Flush the TLB - no globals so cr3 is enough */ - native_write_cr3(__native_read_cr3()); - - /* - * A new pagetable structure is being built to allow for the kernel - * and initrd to be encrypted. It starts with an empty PGD that will - * then be populated with new PUDs and PMDs as the encrypted and - * decrypted kernel mappings are created. - */ - ppd.pgd = ppd.pgtable_area; - memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); - ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; - - /* - * A different PGD index/entry must be used to get different - * pagetable entries for the decrypted mapping. Choose the next - * PGD index and convert it to a virtual address to be used as - * the base of the mapping. - */ - decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); - if (initrd_len) { - unsigned long check_base; - - check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); - decrypted_base = max(decrypted_base, check_base); - } - decrypted_base <<= PGDIR_SHIFT; - - /* Add encrypted kernel (identity) mappings */ - ppd.paddr = kernel_start; - ppd.vaddr = kernel_start; - ppd.vaddr_end = kernel_end; - sme_map_range_encrypted(&ppd); - - /* Add decrypted, write-protected kernel (non-identity) mappings */ - ppd.paddr = kernel_start; - ppd.vaddr = kernel_start + decrypted_base; - ppd.vaddr_end = kernel_end + decrypted_base; - sme_map_range_decrypted_wp(&ppd); - - if (initrd_len) { - /* Add encrypted initrd (identity) mappings */ - ppd.paddr = initrd_start; - ppd.vaddr = initrd_start; - ppd.vaddr_end = initrd_end; - sme_map_range_encrypted(&ppd); - /* - * Add decrypted, write-protected initrd (non-identity) mappings - */ - ppd.paddr = initrd_start; - ppd.vaddr = initrd_start + decrypted_base; - ppd.vaddr_end = initrd_end + decrypted_base; - sme_map_range_decrypted_wp(&ppd); - } - - /* Add decrypted workarea mappings to both kernel mappings */ - ppd.paddr = workarea_start; - ppd.vaddr = workarea_start; - ppd.vaddr_end = workarea_end; - sme_map_range_decrypted(&ppd); - - ppd.paddr = workarea_start; - ppd.vaddr = workarea_start + decrypted_base; - ppd.vaddr_end = workarea_end + decrypted_base; - sme_map_range_decrypted(&ppd); - - /* Perform the encryption */ - sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)ppd.pgd); - - if (initrd_len) - sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, - initrd_len, workarea_start, - (unsigned long)ppd.pgd); - - /* - * At this point we are running encrypted. Remove the mappings for - * the decrypted areas - all that is needed for this is to remove - * the PGD entry/entries. - */ - ppd.vaddr = kernel_start + decrypted_base; - ppd.vaddr_end = kernel_end + decrypted_base; - sme_clear_pgd(&ppd); - - if (initrd_len) { - ppd.vaddr = initrd_start + decrypted_base; - ppd.vaddr_end = initrd_end + decrypted_base; - sme_clear_pgd(&ppd); - } - - ppd.vaddr = workarea_start + decrypted_base; - ppd.vaddr_end = workarea_end + decrypted_base; - sme_clear_pgd(&ppd); - - /* Flush the TLB - no globals so cr3 is enough */ - native_write_cr3(__native_read_cr3()); -} - -void __init __nostackprotector sme_enable(struct boot_params *bp) -{ - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; - unsigned int eax, ebx, ecx, edx; - unsigned long feature_mask; - bool active_by_default; - unsigned long me_mask; - char buffer[16]; - u64 msr; - - /* Check for the SME/SEV support leaf */ - eax = 0x80000000; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (eax < 0x8000001f) - return; - -#define AMD_SME_BIT BIT(0) -#define AMD_SEV_BIT BIT(1) - /* - * Set the feature mask (SME or SEV) based on whether we are - * running under a hypervisor. - */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT; - - /* - * Check for the SME/SEV feature: - * CPUID Fn8000_001F[EAX] - * - Bit 0 - Secure Memory Encryption support - * - Bit 1 - Secure Encrypted Virtualization support - * CPUID Fn8000_001F[EBX] - * - Bits 5:0 - Pagetable bit position used to indicate encryption - */ - eax = 0x8000001f; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (!(eax & feature_mask)) - return; - - me_mask = 1UL << (ebx & 0x3f); - - /* Check if memory encryption is enabled */ - if (feature_mask == AMD_SME_BIT) { - /* For SME, check the SYSCFG MSR */ - msr = __rdmsr(MSR_K8_SYSCFG); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) - return; - } else { - /* For SEV, check the SEV MSR */ - msr = __rdmsr(MSR_AMD64_SEV); - if (!(msr & MSR_AMD64_SEV_ENABLED)) - return; - - /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; - sev_enabled = true; - return; - } - - /* - * Fixups have not been applied to phys_base yet and we're running - * identity mapped, so we must obtain the address to the SME command - * line argument data using rip-relative addressing. - */ - asm ("lea sme_cmdline_arg(%%rip), %0" - : "=r" (cmdline_arg) - : "p" (sme_cmdline_arg)); - asm ("lea sme_cmdline_on(%%rip), %0" - : "=r" (cmdline_on) - : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; - - cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | - ((u64)bp->ext_cmd_line_ptr << 32)); - - cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); - - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; -} diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 01f682cf77a8..40a6085063d6 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -15,6 +15,7 @@ #include <asm/page.h> #include <asm/processor-flags.h> #include <asm/msr-index.h> +#include <asm/nospec-branch.h> .text .code64 @@ -59,6 +60,7 @@ ENTRY(sme_encrypt_execute) movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + ANNOTATE_RETPOLINE_SAFE call *%rax /* Call the encryption routine */ pop %r12 diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c new file mode 100644 index 000000000000..1b2197d13832 --- /dev/null +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -0,0 +1,564 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define DISABLE_BRANCH_PROFILING + +/* + * Since we're dealing with identity mappings, physical and virtual + * addresses are the same, so override these defines which are ultimately + * used by the headers in misc.h. + */ +#define __pa(x) ((unsigned long)(x)) +#define __va(x) ((void *)((unsigned long)(x))) + +/* + * Special hack: we have to be careful, because no indirections are + * allowed here, and paravirt_ops is a kind of one. As it will only run in + * baremetal anyway, we just keep it from happening. (This list needs to + * be extended when new paravirt and debugging variants are added.) + */ +#undef CONFIG_PARAVIRT +#undef CONFIG_PARAVIRT_SPINLOCKS + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/mem_encrypt.h> + +#include <asm/setup.h> +#include <asm/sections.h> +#include <asm/cmdline.h> + +#include "mm_internal.h" + +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) + +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static char sme_cmdline_arg[] __initdata = "mem_encrypt"; +static char sme_cmdline_on[] __initdata = "on"; +static char sme_cmdline_off[] __initdata = "off"; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +{ + unsigned long pgd_start, pgd_end, pgd_size; + pgd_t *pgd_p; + + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; + + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); + + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); + + memset(pgd_p, 0, pgd_size); +} + +static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = ppd->pgd + pgd_index(ppd->vaddr); + if (pgd_none(*pgd)) { + p4d = ppd->pgtable_area; + memset(p4d, 0, sizeof(*p4d) * PTRS_PER_P4D); + ppd->pgtable_area += sizeof(*p4d) * PTRS_PER_P4D; + set_pgd(pgd, __pgd(PGD_FLAGS | __pa(p4d))); + } + + p4d = p4d_offset(pgd, ppd->vaddr); + if (p4d_none(*p4d)) { + pud = ppd->pgtable_area; + memset(pud, 0, sizeof(*pud) * PTRS_PER_PUD); + ppd->pgtable_area += sizeof(*pud) * PTRS_PER_PUD; + set_p4d(p4d, __p4d(P4D_FLAGS | __pa(pud))); + } + + pud = pud_offset(p4d, ppd->vaddr); + if (pud_none(*pud)) { + pmd = ppd->pgtable_area; + memset(pmd, 0, sizeof(*pmd) * PTRS_PER_PMD); + ppd->pgtable_area += sizeof(*pmd) * PTRS_PER_PMD; + set_pud(pud, __pud(PUD_FLAGS | __pa(pmd))); + } + + if (pud_large(*pud)) + return NULL; + + return pud; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pud_t *pud; + pmd_t *pmd; + + pud = sme_prepare_pgd(ppd); + if (!pud) + return; + + pmd = pmd_offset(pud, ppd->vaddr); + if (pmd_large(*pmd)) + return; + + set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); +} + +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pud = sme_prepare_pgd(ppd); + if (!pud) + return; + + pmd = pmd_offset(pud, ppd->vaddr); + if (pmd_none(*pmd)) { + pte = ppd->pgtable_area; + memset(pte, 0, sizeof(pte) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE; + set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte))); + } + + if (pmd_large(*pmd)) + return; + + pte = pte_offset_map(pmd, ppd->vaddr); + if (pte_none(*pte)) + set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); +} + +static unsigned long __init sme_pgtable_calc(unsigned long len) +{ + unsigned long entries = 0, tables = 0; + + /* + * Perform a relatively simplistic calculation of the pagetable + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required + * number of P4D, PUD and PMD structures needed to perform the + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. + */ + + /* PGDIR_SIZE is equal to P4D_SIZE on 4-level machine. */ + if (PTRS_PER_P4D > 1) + entries += (DIV_ROUND_UP(len, PGDIR_SIZE) + 1) * sizeof(p4d_t) * PTRS_PER_P4D; + entries += (DIV_ROUND_UP(len, P4D_SIZE) + 1) * sizeof(pud_t) * PTRS_PER_PUD; + entries += (DIV_ROUND_UP(len, PUD_SIZE) + 1) * sizeof(pmd_t) * PTRS_PER_PMD; + entries += 2 * sizeof(pte_t) * PTRS_PER_PTE; + + /* + * Now calculate the added pagetable structures needed to populate + * the new pagetables. + */ + + if (PTRS_PER_P4D > 1) + tables += DIV_ROUND_UP(entries, PGDIR_SIZE) * sizeof(p4d_t) * PTRS_PER_P4D; + tables += DIV_ROUND_UP(entries, P4D_SIZE) * sizeof(pud_t) * PTRS_PER_PUD; + tables += DIV_ROUND_UP(entries, PUD_SIZE) * sizeof(pmd_t) * PTRS_PER_PMD; + + return entries + tables; +} + +void __init sme_encrypt_kernel(struct boot_params *bp) +{ + unsigned long workarea_start, workarea_end, workarea_len; + unsigned long execute_start, execute_end, execute_len; + unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; + unsigned long pgtable_area_len; + unsigned long decrypted_base; + + if (!sme_active()) + return; + + /* + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. + * + * One range of virtual addresses will map the memory occupied + * by the kernel and initrd as encrypted. + * + * Another range of virtual addresses will map the memory occupied + * by the kernel and initrd as decrypted and write-protected. + * + * The use of write-protect attribute will prevent any of the + * memory from being cached. + */ + + /* Physical addresses gives us the identity mapped virtual addresses */ + kernel_start = __pa_symbol(_text); + kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); + kernel_len = kernel_end - kernel_start; + + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + + /* Set the encryption workarea to be immediately after the kernel */ + workarea_start = kernel_end; + + /* + * Calculate required number of workarea bytes needed: + * executable encryption area size: + * stack page (PAGE_SIZE) + * encryption routine page (PAGE_SIZE) + * intermediate copy buffer (PMD_PAGE_SIZE) + * pagetable structures for the encryption of the kernel + * pagetable structures for workarea (in case not currently mapped) + */ + execute_start = workarea_start; + execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE; + execute_len = execute_end - execute_start; + + /* + * One PGD for both encrypted and decrypted mappings and a set of + * PUDs and PMDs for each of the encrypted and decrypted mappings. + */ + pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; + pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; + + /* PUDs and PMDs needed in the current pagetables for the workarea */ + pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); + + /* + * The total workarea includes the executable encryption area and + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. + */ + workarea_len = execute_len + pgtable_area_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); + + /* + * Set the address to the start of where newly created pagetable + * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable + * structures are created when the workarea is added to the current + * pagetables and when the new encrypted and decrypted kernel + * mappings are populated. + */ + ppd.pgtable_area = (void *)execute_end; + + /* + * Make sure the current pagetable structure has entries for + * addressing the workarea. + */ + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); + + /* + * A new pagetable structure is being built to allow for the kernel + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. + */ + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; + + /* + * A different PGD index/entry must be used to get different + * pagetable entries for the decrypted mapping. Choose the next + * PGD index and convert it to a virtual address to be used as + * the base of the mapping. + */ + decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } + decrypted_base <<= PGDIR_SHIFT; + + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + + /* Add decrypted, write-protected kernel (non-identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + } + + /* Add decrypted workarea mappings to both kernel mappings */ + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); + + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); + + /* Perform the encryption */ + sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); + + /* + * At this point we are running encrypted. Remove the mappings for + * the decrypted areas - all that is needed for this is to remove + * the PGD entry/entries. + */ + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } + + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); + + /* Flush the TLB - no globals so cr3 is enough */ + native_write_cr3(__native_read_cr3()); +} + +void __init sme_enable(struct boot_params *bp) +{ + const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; + unsigned int eax, ebx, ecx, edx; + unsigned long feature_mask; + bool active_by_default; + unsigned long me_mask; + char buffer[16]; + u64 msr; + + /* Check for the SME/SEV support leaf */ + eax = 0x80000000; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax < 0x8000001f) + return; + +#define AMD_SME_BIT BIT(0) +#define AMD_SEV_BIT BIT(1) + /* + * Set the feature mask (SME or SEV) based on whether we are + * running under a hypervisor. + */ + eax = 1; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (!(eax & feature_mask)) + return; + + me_mask = 1UL << (ebx & 0x3f); + + /* Check if memory encryption is enabled */ + if (feature_mask == AMD_SME_BIT) { + /* For SME, check the SYSCFG MSR */ + msr = __rdmsr(MSR_K8_SYSCFG); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + } else { + /* For SEV, check the SEV MSR */ + msr = __rdmsr(MSR_AMD64_SEV); + if (!(msr & MSR_AMD64_SEV_ENABLED)) + return; + + /* SEV state cannot be controlled by a command line option */ + sme_me_mask = me_mask; + sev_enabled = true; + return; + } + + /* + * Fixups have not been applied to phys_base yet and we're running + * identity mapped, so we must obtain the address to the SME command + * line argument data using rip-relative addressing. + */ + asm ("lea sme_cmdline_arg(%%rip), %0" + : "=r" (cmdline_arg) + : "p" (sme_cmdline_arg)); + asm ("lea sme_cmdline_on(%%rip), %0" + : "=r" (cmdline_on) + : "p" (sme_cmdline_on)); + asm ("lea sme_cmdline_off(%%rip), %0" + : "=r" (cmdline_off) + : "p" (sme_cmdline_off)); + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) + active_by_default = true; + else + active_by_default = false; + + cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | + ((u64)bp->ext_cmd_line_ptr << 32)); + + cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)); + + if (!strncmp(buffer, cmdline_on, sizeof(buffer))) + sme_me_mask = me_mask; + else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) + sme_me_mask = 0; + else + sme_me_mask = active_by_default ? me_mask : 0; +} diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index aca6295350f3..e8a4a09e20f1 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -60,17 +60,6 @@ void memory_present(int nid, unsigned long start, unsigned long end) } printk(KERN_CONT "\n"); } - -unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - unsigned long nr_pages = end_pfn - start_pfn; - - if (!nr_pages) - return 0; - - return (nr_pages + 1) * sizeof(struct page); -} #endif extern unsigned long highend_pfn, highstart_pfn; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 004abf9ebf12..34cda7e0551b 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -702,4 +702,52 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } + +/** + * pud_free_pmd_page - Clear pud entry and free pmd page. + * @pud: Pointer to a PUD. + * + * Context: The pud range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pud_free_pmd_page(pud_t *pud) +{ + pmd_t *pmd; + int i; + + if (pud_none(*pud)) + return 1; + + pmd = (pmd_t *)pud_page_vaddr(*pud); + + for (i = 0; i < PTRS_PER_PMD; i++) + if (!pmd_free_pte_page(&pmd[i])) + return 0; + + pud_clear(pud); + free_page((unsigned long)pmd); + + return 1; +} + +/** + * pmd_free_pte_page - Clear pmd entry and free pte page. + * @pmd: Pointer to a PMD. + * + * Context: The pmd range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pmd_free_pte_page(pmd_t *pmd) +{ + pte_t *pte; + + if (pmd_none(*pmd)) + return 1; + + pte = (pte_t *)pmd_page_vaddr(*pmd); + pmd_clear(pmd); + free_page((unsigned long)pte); + + return 1; +} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index c3c5274410a9..9bb7f0ab9fe6 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -63,7 +63,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) * It's enough to flush this one mapping. * (PGE mappings get flushed as well) */ - __flush_tlb_one(vaddr); + __flush_tlb_one_kernel(vaddr); } unsigned long __FIXADDR_TOP = 0xfffff000; diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ce38f165489b..631507f0c198 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void) } /* - * Clone the ESPFIX P4D into the user space visinble page table + * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8dcc0607f805..e055d1a06699 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -157,7 +157,7 @@ static void sync_current_stack_to_mm(struct mm_struct *mm) unsigned long sp = current_stack_pointer; pgd_t *pgd = pgd_offset(mm, sp); - if (CONFIG_PGTABLE_LEVELS > 4) { + if (pgtable_l5_enabled) { if (unlikely(pgd_none(*pgd))) { pgd_t *pgd_ref = pgd_offset_k(sp); @@ -498,7 +498,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * flush that changes context.tlb_gen from 2 to 3. If they get * processed on this CPU in reverse order, we'll see * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. - * If we were to use __flush_tlb_single() and set local_tlb_gen to + * If we were to use __flush_tlb_one_user() and set local_tlb_gen to * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * @@ -519,7 +519,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, addr = f->start; while (addr < f->end) { - __flush_tlb_single(addr); + __flush_tlb_one_user(addr); addr += PAGE_SIZE; } if (local) @@ -613,7 +613,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, { int cpu; - struct flush_tlb_info info = { + struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = { .mm = mm, }; @@ -666,7 +666,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_one(addr); + __flush_tlb_one_kernel(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4923d92f918d..ce5b2ebd5701 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -13,6 +13,7 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> #include <asm/set_memory.h> +#include <asm/nospec-branch.h> #include <linux/bpf.h> /* @@ -290,7 +291,7 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 43 /* number of bytes to jump */ +#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; @@ -299,7 +300,7 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 32 +#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ @@ -313,7 +314,7 @@ static void emit_bpf_tail_call(u8 **pprog) * goto out; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ -#define OFFSET3 10 +#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; @@ -326,7 +327,7 @@ static void emit_bpf_tail_call(u8 **pprog) * rdi == ctx (1st arg) * rax == prog->bpf_func + prologue_size */ - EMIT2(0xFF, 0xE0); /* jmp rax */ + RETPOLINE_RAX_BPF_JIT(); /* out: */ BUILD_BUG_ON(cnt - label1 != OFFSET1); @@ -1187,7 +1188,7 @@ skip_init_addrs: * may converge on the last pass. In such case do one more * pass to emit the final image */ - for (pass = 0; pass < 10 || image; pass++) { + for (pass = 0; pass < 20 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); if (proglen <= 0) { image = NULL; @@ -1214,6 +1215,7 @@ skip_init_addrs: } } oldproglen = proglen; + cond_resched(); } if (bpf_jit_enable > 1) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 174c59774cc9..a7a7677265b6 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -460,7 +460,7 @@ static int nmi_setup(void) goto fail; for_each_possible_cpu(cpu) { - if (!cpu) + if (!IS_ENABLED(CONFIG_SMP) || !cpu) continue; memcpy(per_cpu(cpu_msrs, cpu).counters, diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 7df49c40665e..5559dcaddd5e 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -140,12 +140,10 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = { void __init pci_acpi_crs_quirks(void) { - int year; + int year = dmi_get_bios_year(); - if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) { - if (iomem_resource.end <= 0xffffffff) - pci_use_crs = false; - } + if (year >= 0 && year < 2008 && iomem_resource.end <= 0xffffffff) + pci_use_crs = false; dmi_check_system(pci_crs_quirks); diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 2d9503323d10..a51074c55982 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -195,14 +195,13 @@ static const struct pci_raw_ops pci_direct_conf2 = { static int __init pci_sanity_check(const struct pci_raw_ops *o) { u32 x = 0; - int year, devfn; + int devfn; if (pci_probe & PCI_NO_CHECKS) return 1; /* Assume Type 1 works for newer systems. This handles machines that don't have anything on PCI Bus 0. */ - dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL); - if (year >= 2001) + if (dmi_get_bios_year() >= 2001) return 1; for (devfn = 0; devfn < 0x100; devfn++) { diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index 1cb01abcb1be..dfbe6ac38830 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -4,6 +4,7 @@ #include <linux/init.h> #include <linux/export.h> #include <linux/pci.h> +#include <asm/jailhouse_para.h> #include <asm/pci_x86.h> /* @@ -34,13 +35,14 @@ int __init pci_legacy_init(void) void pcibios_scan_specific_bus(int busn) { + int stride = jailhouse_paravirt() ? 1 : 8; int devfn; u32 l; if (pci_find_bus(0, busn)) return; - for (devfn = 0; devfn < 256; devfn += 8) { + for (devfn = 0; devfn < 256; devfn += stride) { if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) && l != 0x0000 && l != 0xffff) { DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 96684d0adcf9..7389db538c30 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -94,8 +94,8 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start, return new; } -static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, - int end, u64 addr) +struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, + int end, u64 addr) { struct pci_mmcfg_region *new; @@ -547,19 +547,14 @@ static void __init pci_mmcfg_reject_broken(int early) static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, struct acpi_mcfg_allocation *cfg) { - int year; - if (cfg->address < 0xFFFFFFFF) return 0; if (!strncmp(mcfg->header.oem_id, "SGI", 3)) return 0; - if (mcfg->header.revision >= 1) { - if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && - year >= 2010) - return 0; - } + if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010)) + return 0; pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx " "is above 4GB, ignored\n", cfg->pci_segment, diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 75577c1490c4..7a5bafb76d77 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -159,43 +159,6 @@ static dma_addr_t a2p(dma_addr_t a, struct pci_dev *pdev) return p; } -/** - * sta2x11_swiotlb_alloc_coherent - Allocate swiotlb bounce buffers - * returns virtual address. This is the only "special" function here. - * @dev: PCI device - * @size: Size of the buffer - * @dma_handle: DMA address - * @flags: memory flags - */ -static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, - size_t size, - dma_addr_t *dma_handle, - gfp_t flags, - unsigned long attrs) -{ - void *vaddr; - - vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs); - *dma_handle = p2a(*dma_handle, to_pci_dev(dev)); - return vaddr; -} - -/* We have our own dma_ops: the same as swiotlb but from alloc (above) */ -static const struct dma_map_ops sta2x11_dma_ops = { - .alloc = sta2x11_swiotlb_alloc_coherent, - .free = x86_swiotlb_free_coherent, - .map_page = swiotlb_map_page, - .unmap_page = swiotlb_unmap_page, - .map_sg = swiotlb_map_sg_attrs, - .unmap_sg = swiotlb_unmap_sg_attrs, - .sync_single_for_cpu = swiotlb_sync_single_for_cpu, - .sync_single_for_device = swiotlb_sync_single_for_device, - .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = swiotlb_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, - .dma_supported = x86_dma_supported, -}; - /* At setup time, we use our own ops if the device is a ConneXt one */ static void sta2x11_setup_pdev(struct pci_dev *pdev) { @@ -205,7 +168,8 @@ static void sta2x11_setup_pdev(struct pci_dev *pdev) return; pci_set_consistent_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); pci_set_dma_mask(pdev, STA2X11_AMBA_SIZE - 1); - pdev->dev.dma_ops = &sta2x11_dma_ops; + pdev->dev.dma_ops = &swiotlb_dma_ops; + pdev->dev.archdata.is_sta2x11 = true; /* We must enable all devices as master, for audio DMA to work */ pci_set_master(pdev); @@ -225,7 +189,7 @@ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { struct sta2x11_mapping *map; - if (dev->dma_ops != &sta2x11_dma_ops) { + if (!dev->archdata.is_sta2x11) { if (!dev->dma_mask) return false; return addr + size - 1 <= *dev->dma_mask; @@ -243,13 +207,13 @@ bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) } /** - * phys_to_dma - Return the DMA AMBA address used for this STA2x11 device + * __phys_to_dma - Return the DMA AMBA address used for this STA2x11 device * @dev: device for a PCI device * @paddr: Physical address */ -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { - if (dev->dma_ops != &sta2x11_dma_ops) + if (!dev->archdata.is_sta2x11) return paddr; return p2a(paddr, to_pci_dev(dev)); } @@ -259,9 +223,9 @@ dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) * @dev: device for a PCI device * @daddr: STA2x11 AMBA DMA address */ -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) +phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr) { - if (dev->dma_ops != &sta2x11_dma_ops) + if (!dev->archdata.is_sta2x11) return daddr; return a2p(daddr, to_pci_dev(dev)); } diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index d49d3be81953..034813d4ab1e 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -109,18 +109,7 @@ static int punit_dev_state_show(struct seq_file *seq_file, void *unused) return 0; } - -static int punit_dev_state_open(struct inode *inode, struct file *file) -{ - return single_open(file, punit_dev_state_show, inode->i_private); -} - -static const struct file_operations punit_dev_state_ops = { - .open = punit_dev_state_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(punit_dev_state); static struct dentry *punit_dbg_file; @@ -132,9 +121,9 @@ static int punit_dbgfs_register(struct punit_device *punit_device) if (!punit_dbg_file) return -ENXIO; - dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO, + dev_state = debugfs_create_file("dev_power_state", 0444, punit_dbg_file, punit_device, - &punit_dev_state_ops); + &punit_dev_state_fops); if (!dev_state) { pr_err("punit_dev_state register failed\n"); debugfs_remove(punit_dbg_file); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index c310a8284358..bed7e7f4e44c 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -27,12 +27,14 @@ #include <linux/ioport.h> #include <linux/mc146818rtc.h> #include <linux/efi.h> +#include <linux/export.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/reboot.h> #include <linux/slab.h> #include <linux/ucs2_string.h> #include <linux/mem_encrypt.h> +#include <linux/sched/task.h> #include <asm/setup.h> #include <asm/page.h> @@ -81,9 +83,8 @@ pgd_t * __init efi_call_phys_prolog(void) int n_pgds, i, j; if (!efi_enabled(EFI_OLD_MEMMAP)) { - save_pgd = (pgd_t *)__read_cr3(); - write_cr3((unsigned long)efi_scratch.efi_pgt); - goto out; + efi_switch_mm(&efi_mm); + return NULL; } early_code_mapping_set_exec(1); @@ -155,8 +156,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) pud_t *pud; if (!efi_enabled(EFI_OLD_MEMMAP)) { - write_cr3((unsigned long)save_pgd); - __flush_tlb_all(); + efi_switch_mm(efi_scratch.prev_mm); return; } @@ -190,7 +190,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) early_code_mapping_set_exec(0); } -static pgd_t *efi_pgd; +EXPORT_SYMBOL_GPL(efi_mm); /* * We need our own copy of the higher levels of the page tables @@ -203,7 +203,7 @@ static pgd_t *efi_pgd; */ int __init efi_alloc_page_tables(void) { - pgd_t *pgd; + pgd_t *pgd, *efi_pgd; p4d_t *p4d; pud_t *pud; gfp_t gfp_mask; @@ -225,12 +225,16 @@ int __init efi_alloc_page_tables(void) pud = pud_alloc(&init_mm, p4d, EFI_VA_END); if (!pud) { - if (CONFIG_PGTABLE_LEVELS > 4) + if (pgtable_l5_enabled) free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_page((unsigned long)efi_pgd); + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); return -ENOMEM; } + efi_mm.pgd = efi_pgd; + mm_init_cpumask(&efi_mm); + init_new_context(NULL, &efi_mm); + return 0; } @@ -243,6 +247,7 @@ void efi_sync_low_kernel_mappings(void) pgd_t *pgd_k, *pgd_efi; p4d_t *p4d_k, *p4d_efi; pud_t *pud_k, *pud_efi; + pgd_t *efi_pgd = efi_mm.pgd; if (efi_enabled(EFI_OLD_MEMMAP)) return; @@ -255,8 +260,8 @@ void efi_sync_low_kernel_mappings(void) * only span a single PGD entry and that the entry also maps * other important kernel regions. */ - BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END)); - BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) != + MAYBE_BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END)); + MAYBE_BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) != (EFI_VA_END & PGDIR_MASK)); pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET); @@ -336,20 +341,12 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) unsigned long pfn, text, pf; struct page *page; unsigned npages; - pgd_t *pgd; + pgd_t *pgd = efi_mm.pgd; if (efi_enabled(EFI_OLD_MEMMAP)) return 0; /* - * Since the PGD is encrypted, set the encryption mask so that when - * this value is loaded into cr3 the PGD will be decrypted during - * the pagetable walk. - */ - efi_scratch.efi_pgt = (pgd_t *)__sme_pa(efi_pgd); - pgd = efi_pgd; - - /* * It can happen that the physical address of new_memmap lands in memory * which is not mapped in the EFI page table. Therefore we need to go * and ident-map those pages containing the map before calling @@ -362,8 +359,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } - efi_scratch.use_pgd = true; - /* * Certain firmware versions are way too sentimential and still believe * they are exclusive and unquestionable owners of the first physical page, @@ -417,7 +412,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) { unsigned long flags = _PAGE_RW; unsigned long pfn; - pgd_t *pgd = efi_pgd; + pgd_t *pgd = efi_mm.pgd; if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; @@ -521,7 +516,7 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) { unsigned long pfn; - pgd_t *pgd = efi_pgd; + pgd_t *pgd = efi_mm.pgd; int err1, err2; /* Update the 1:1 mapping */ @@ -618,10 +613,26 @@ void __init efi_dump_pagetable(void) if (efi_enabled(EFI_OLD_MEMMAP)) ptdump_walk_pgd_level(NULL, swapper_pg_dir); else - ptdump_walk_pgd_level(NULL, efi_pgd); + ptdump_walk_pgd_level(NULL, efi_mm.pgd); #endif } +/* + * Makes the calling thread switch to/from efi_mm context. Can be used + * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well + * as during efi runtime calls i.e current->active_mm == current_mm. + * We are not mm_dropping()/mm_grabbing() any mm, because we are not + * losing/creating any references. + */ +void efi_switch_mm(struct mm_struct *mm) +{ + task_lock(current); + efi_scratch.prev_mm = current->active_mm; + current->active_mm = mm; + switch_mm(efi_scratch.prev_mm, mm, NULL); + task_unlock(current); +} + #ifdef CONFIG_EFI_MIXED extern efi_status_t efi64_thunk(u32, ...); @@ -675,16 +686,13 @@ efi_status_t efi_thunk_set_virtual_address_map( efi_sync_low_kernel_mappings(); local_irq_save(flags); - efi_scratch.prev_cr3 = __read_cr3(); - write_cr3((unsigned long)efi_scratch.efi_pgt); - __flush_tlb_all(); + efi_switch_mm(&efi_mm); func = (u32)(unsigned long)phys_set_virtual_address_map; status = efi64_thunk(func, memory_map_size, descriptor_size, descriptor_version, virtual_map); - write_cr3(efi_scratch.prev_cr3); - __flush_tlb_all(); + efi_switch_mm(efi_scratch.prev_mm); local_irq_restore(flags); return status; diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 189b218da87c..46c58b08739c 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -33,7 +33,7 @@ ENTRY(efi64_thunk) * Switch to 1:1 mapped 32-bit stack pointer. */ movq %rsp, efi_saved_sp(%rip) - movq efi_scratch+25(%rip), %rsp + movq efi_scratch(%rip), %rsp /* * Calculate the physical address of the kernel text. diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 5b513ccffde4..36c1f8b9f7e0 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -75,7 +75,7 @@ struct quark_security_header { u32 rsvd[2]; }; -static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; +static const efi_char16_t efi_dummy_name[] = L"DUMMY"; static bool efi_no_storage_paranoia; @@ -105,7 +105,8 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia); */ void efi_delete_dummy_variable(void) { - efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + efi.set_variable((efi_char16_t *)efi_dummy_name, + &EFI_DUMMY_GUID, EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS | EFI_VARIABLE_RUNTIME_ACCESS, @@ -177,12 +178,13 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, * that by attempting to use more space than is available. */ unsigned long dummy_size = remaining_size + 1024; - void *dummy = kzalloc(dummy_size, GFP_ATOMIC); + void *dummy = kzalloc(dummy_size, GFP_KERNEL); if (!dummy) return EFI_OUT_OF_RESOURCES; - status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + status = efi.set_variable((efi_char16_t *)efi_dummy_name, + &EFI_DUMMY_GUID, EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS | EFI_VARIABLE_RUNTIME_ACCESS, diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 2c67bae6bb53..2ebdf31d9996 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -79,7 +79,7 @@ static void intel_mid_power_off(void) static void intel_mid_reboot(void) { - intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); } static unsigned long __init intel_mid_calibrate_tsc(void) @@ -199,6 +199,12 @@ void __init x86_intel_mid_early_setup(void) legacy_pic = &null_legacy_pic; + /* + * Do nothing for now as everything needed done in + * x86_intel_mid_early_setup() below. + */ + x86_init.acpi.reduced_hw_early_init = x86_init_noop; + pm_power_off = intel_mid_power_off; machine_ops.emergency_restart = intel_mid_reboot; diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 17d6d2296e4d..49828c2707ac 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -224,25 +224,7 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused) mutex_unlock(&idev->lock); return ret; } - -/** - * imr_state_open - debugfs open callback. - * - * @inode: pointer to struct inode. - * @file: pointer to struct file. - * @return: result of single open. - */ -static int imr_state_open(struct inode *inode, struct file *file) -{ - return single_open(file, imr_dbgfs_state_show, inode->i_private); -} - -static const struct file_operations imr_state_ops = { - .open = imr_state_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(imr_dbgfs_state); /** * imr_debugfs_register - register debugfs hooks. @@ -252,8 +234,8 @@ static const struct file_operations imr_state_ops = { */ static int imr_debugfs_register(struct imr_device *idev) { - idev->file = debugfs_create_file("imr_state", S_IFREG | S_IRUGO, NULL, - idev, &imr_state_ops); + idev->file = debugfs_create_file("imr_state", 0444, NULL, idev, + &imr_dbgfs_state_fops); return PTR_ERR_OR_ZERO(idev->file); } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index c2e9285d1bf1..b36caae0fb2f 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_single(msg->address); + __flush_tlb_one_user(msg->address); stat->d_onetlb++; } stat->d_requestee++; @@ -2255,8 +2255,6 @@ static int __init uv_bau_init(void) init_uvhub(uvhub, vector, uv_base_pnode); } - alloc_intr_gate(vector, uv_bau_message_intr1); - for_each_possible_blade(uvhub) { if (uv_blade_nr_possible_cpus(uvhub)) { unsigned long val; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 0ef5e5204968..74a532989308 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -50,7 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; pud_t *pud; - p4d_t *p4d; + p4d_t *p4d = NULL; /* * The new mapping only has to cover the page containing the image @@ -66,7 +66,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) * tables used by the image kernel. */ - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + if (pgtable_l5_enabled) { p4d = (p4d_t *)get_safe_page(GFP_ATOMIC); if (!p4d) return -ENOMEM; @@ -84,7 +84,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); set_pud(pud + pud_index(restore_jump_address), __pud(__pa(pmd) | _KERNPG_TABLE)); - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + if (p4d) { set_p4d(p4d + p4d_index(restore_jump_address), __p4d(__pa(pud) | _KERNPG_TABLE)); set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(p4d) | _KERNPG_TABLE)); } else { diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 2f15a2ac4209..d70c15de417b 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -16,7 +16,7 @@ KCOV_INSTRUMENT := n # in turn leaves some undefined symbols like __fentry__ in purgatory and not # sure how to relocate those. Like kexec-tools, use custom flags. -KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large +KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -Os -mcmodel=large KBUILD_CFLAGS += -m$(BITS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index de53bd15df5a..24bb7598774e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -102,7 +102,7 @@ ENTRY(startup_32) * don't we'll eventually crash trying to execute encrypted * instructions. */ - bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone movl $MSR_K8_SYSCFG, %ecx rdmsr diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 5d73c443e778..220e97841e49 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -770,9 +770,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym, break; case R_X86_64_PC32: + case R_X86_64_PLT32: /* * PC relative relocations don't need to be adjusted unless * referencing a percpu symbol. + * + * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32. */ if (is_percpu_sym(sym, symname)) add_reloc(&relocs32neg, offset); diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index b7d73400ea29..f31e5d903161 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -30,11 +30,7 @@ #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_PPRO_FENCE -#define dma_rmb() rmb() -#else /* CONFIG_X86_PPRO_FENCE */ #define dma_rmb() barrier() -#endif /* CONFIG_X86_PPRO_FENCE */ #define dma_wmb() barrier() #include <asm-generic/barrier.h> diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index f605825a04ab..c1f98f32c45f 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -18,9 +18,6 @@ config XEN_PV bool "Xen PV guest support" default y depends on XEN - # XEN_PV is not ready to work with 5-level paging. - # Changes to hypervisor are also required. - depends on !X86_5LEVEL select XEN_HAVE_PVMMU select XEN_HAVE_VPMU help @@ -79,6 +76,4 @@ config XEN_DEBUG_FS config XEN_PVH bool "Support for running as a PVH guest" depends on XEN && XEN_PVHVM && ACPI - # Pre-built page tables are not ready to handle 5-level paging. - depends on !X86_5LEVEL def_bool n diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index de58533d3664..2163888497d3 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -215,7 +215,7 @@ static void __init xen_apic_check(void) } void __init xen_init_apic(void) { - x86_io_apic_ops.read = xen_io_apic_read; + x86_apic_ops.io_apic_read = xen_io_apic_read; /* On PV guests the APIC CPUID bit is disabled so none of the * routines end up executing. */ if (!xen_initial_domain()) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c047f42552e1..3c2c2530737e 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1376,8 +1376,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (!xen_initial_domain()) { add_preferred_console("xenboot", 0, NULL); - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; } else { @@ -1410,6 +1408,10 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_boot_params_init_edd(); } + + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ pci_probe &= ~PCI_PROBE_BIOS; diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 436c4f003e17..aa1c6a6831a9 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -6,6 +6,7 @@ #include <asm/io_apic.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> +#include <asm/x86_init.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -16,15 +17,20 @@ /* * PVH variables. * - * xen_pvh and pvh_bootparams need to live in data segment since they - * are used after startup_{32|64}, which clear .bss, are invoked. + * xen_pvh pvh_bootparams and pvh_start_info need to live in data segment + * since they are used after startup_{32|64}, which clear .bss, are invoked. */ bool xen_pvh __attribute__((section(".data"))) = 0; struct boot_params pvh_bootparams __attribute__((section(".data"))); +struct hvm_start_info pvh_start_info __attribute__((section(".data"))); -struct hvm_start_info pvh_start_info; unsigned int pvh_start_info_sz = sizeof(pvh_start_info); +static u64 pvh_get_root_pointer(void) +{ + return pvh_start_info.rsdp_paddr; +} + static void __init init_pvh_bootparams(void) { struct xen_memory_map memmap; @@ -71,6 +77,8 @@ static void __init init_pvh_bootparams(void) */ pvh_bootparams.hdr.version = 0x212; pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ + + x86_init.acpi.get_root_pointer = pvh_get_root_pointer; } /* diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index d85076223a69..d20763472920 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -538,6 +538,22 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val) xen_mc_issue(PARAVIRT_LAZY_MMU); } + +#if CONFIG_PGTABLE_LEVELS >= 5 +__visible p4dval_t xen_p4d_val(p4d_t p4d) +{ + return pte_mfn_to_pfn(p4d.p4d); +} +PV_CALLEE_SAVE_REGS_THUNK(xen_p4d_val); + +__visible p4d_t xen_make_p4d(p4dval_t p4d) +{ + p4d = pte_pfn_to_mfn(p4d); + + return native_make_p4d(p4d); +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d); +#endif /* CONFIG_PGTABLE_LEVELS >= 5 */ #endif /* CONFIG_X86_64 */ static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, @@ -1300,12 +1316,12 @@ static void xen_flush_tlb(void) preempt_enable(); } -static void xen_flush_tlb_single(unsigned long addr) +static void xen_flush_tlb_one_user(unsigned long addr) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_single(addr); + trace_xen_mmu_flush_tlb_one_user(addr); preempt_disable(); @@ -2370,7 +2386,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_user = xen_flush_tlb, .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_single = xen_flush_tlb_single, + .flush_tlb_one_user = xen_flush_tlb_one_user, .flush_tlb_others = xen_flush_tlb_others, .pgd_alloc = xen_pgd_alloc, @@ -2411,6 +2427,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .alloc_pud = xen_alloc_pmd_init, .release_pud = xen_release_pmd_init, + +#if CONFIG_PGTABLE_LEVELS >= 5 + .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), + .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), +#endif #endif /* CONFIG_X86_64 */ .activate_mm = xen_activate_mm, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 77c959cf81e7..7a43b2ae19f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -122,6 +122,8 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); + else + calculate_max_logical_packages(); if (xen_have_vcpu_info_placement) return; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d9f96cc5d743..1d83152c761b 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/tick.h> +#include <linux/percpu-defs.h> #include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> +#include <asm/cpufeatures.h> +#include <asm/msr-index.h> #include <asm/xen/hypercall.h> #include <asm/xen/page.h> #include <asm/fixmap.h> @@ -15,6 +18,8 @@ #include "mmu.h" #include "pmu.h" +static DEFINE_PER_CPU(u64, spec_ctrl); + void xen_arch_pre_suspend(void) { xen_save_time_memory_area(); @@ -35,6 +40,9 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl)); + /* Boot processor notified via generic timekeeping_resume() */ if (smp_processor_id() == 0) return; @@ -44,7 +52,15 @@ static void xen_vcpu_notify_restore(void *data) static void xen_vcpu_notify_suspend(void *data) { + u64 tmp; + tick_suspend_local(); + + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) { + rdmsrl(MSR_IA32_SPEC_CTRL, tmp); + this_cpu_write(spec_ctrl, tmp); + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } } void xen_arch_resume(void) |