diff options
Diffstat (limited to 'arch/x86')
51 files changed, 719 insertions, 410 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 603f374f871d..45b94fa9e98c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2423,7 +2423,7 @@ menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER def_bool y - depends on X86_64 && HIBERNATION + depends on HIBERNATION source "kernel/power/Kconfig" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 28764dacf018..466f66c8a7f8 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -37,6 +37,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) +KBUILD_CFLAGS += -Wno-pointer-sign KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 1458b1700fc7..8b4c5e001157 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -738,6 +738,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) struct desc_struct *desc; void *handle; efi_system_table_t *_table; + unsigned long cmdline_paddr; efi_early = c; @@ -756,6 +757,15 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) setup_boot_services32(efi_early); /* + * make_boot_params() may have been called before efi_main(), in which + * case this is the second time we parse the cmdline. This is ok, + * parsing the cmdline multiple times does not have side-effects. + */ + cmdline_paddr = ((u64)hdr->cmd_line_ptr | + ((u64)boot_params->ext_cmd_line_ptr << 32)); + efi_parse_options((char *)cmdline_paddr); + + /* * If the boot loader gave us a value for secure_boot then we use that, * otherwise we ask the BIOS. */ diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index d4e6cd4577e5..bf0e82400358 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -391,6 +391,13 @@ int main(int argc, char ** argv) die("Unable to mmap '%s': %m", argv[2]); /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ sys_size = (sz + 15 + 4) / 16; +#ifdef CONFIG_EFI_STUB + /* + * COFF requires minimum 32-byte alignment of sections, and + * adding a signature is problematic without that alignment. + */ + sys_size = (sys_size + 1) & ~1; +#endif /* Patch the setup code with the appropriate size parameters */ buf[0x1f1] = setup_sectors-1; diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2767c625a52c..fbbf1ba57ec6 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -389,6 +389,13 @@ * that register for the time this macro runs */ + /* + * The high bits of the CS dword (__csh) are used for + * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case + * hardware didn't do this for us. + */ + andl $(0x0000ffff), PT_CS(%esp) + /* Are we on the entry stack? Bail out if not! */ movl PER_CPU_VAR(cpu_entry_area), %ecx addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx @@ -407,12 +414,6 @@ /* Load top of task-stack into %edi */ movl TSS_entry2task_stack(%edi), %edi - /* - * Clear unused upper bits of the dword containing the word-sized CS - * slot in pt_regs in case hardware didn't clear it for us. - */ - andl $(0x0000ffff), PT_CS(%esp) - /* Special case - entry from kernel mode via entry stack */ #ifdef CONFIG_VM86 movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 957dfb693ecc..f95dcb209fdf 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1187,6 +1187,16 @@ ENTRY(paranoid_entry) xorl %ebx, %ebx 1: + /* + * Always stash CR3 in %r14. This value will be restored, + * verbatim, at exit. Needed if paranoid_entry interrupted + * another entry that already switched to the user CR3 value + * but has not yet returned to userspace. + * + * This is also why CS (stashed in the "iret frame" by the + * hardware at entry) can not be used: this may be a return + * to kernel code, but with a user CR3 value. + */ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 ret @@ -1211,11 +1221,13 @@ ENTRY(paranoid_exit) testl %ebx, %ebx /* swapgs needed? */ jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 SWAPGS_UNSAFE_STACK jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel @@ -1626,6 +1638,7 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 testl %ebx, %ebx /* swapgs needed? */ diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index fa3f439f0a92..141d415a8c80 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS) + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + CFL += $(RETPOLINE_VDSO_CFLAGS) +endif +endif $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) @@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) + +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_VDSO_CFLAGS),) + KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) +endif +endif + $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) $(obj)/vdso32.so.dbg: FORCE \ diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index f19856d95c60..e48ca3afa091 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -43,8 +43,9 @@ extern u8 hvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; } @@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; } @@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 981ba5e8241b..8671de126eac 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -36,6 +36,7 @@ static int num_counters_llc; static int num_counters_nb; +static bool l3_mask; static HLIST_HEAD(uncore_unused_list); @@ -209,6 +210,13 @@ static int amd_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1; + /* + * SliceMask and ThreadMask need to be set for certain L3 events in + * Family 17h. For other events, the two fields do not affect the count. + */ + if (l3_mask) + hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK); + if (event->cpu < 0) return -EINVAL; @@ -525,6 +533,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l3"; format_attr_event_df.show = &event_show_df; format_attr_event_l3.show = &event_show_l3; + l3_mask = true; } else { num_counters_nb = NUM_COUNTERS_NB; num_counters_llc = NUM_COUNTERS_L2; @@ -532,6 +541,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l2"; format_attr_event_df = format_attr_event; format_attr_event_l3 = format_attr_event; + l3_mask = false; } amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 51d7c117e3c7..c07bee31abe8 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3061,7 +3061,7 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id); if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; @@ -3931,16 +3931,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3), }, { /* M3UPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0), }, { /* M3UPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1), }, { /* M3UPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2), }, { /* end: all zeroes */ } }; diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index cec5fae23eb3..eea40d52ca78 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -140,6 +140,7 @@ 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); +extern void efi_recover_from_page_fault(unsigned long phys_addr); struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 068ff7689268..5f7290e6e954 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -528,7 +528,7 @@ static inline void fpregs_activate(struct fpu *fpu) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->initialized) { + if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 6de64840dd22..9a92a3ac2ac5 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -369,18 +369,6 @@ extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); extern bool is_early_ioremap_ptep(pte_t *ptep); -#ifdef CONFIG_XEN -#include <xen/xen.h> -struct bio_vec; - -extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, - const struct bio_vec *vec2); - -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ - (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2))) -#endif /* CONFIG_XEN */ - #define IO_SPACE_LIMIT 0xffff #include <asm-generic/io.h> diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index e9202a0de8f0..1a19d11cfbbd 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -185,22 +185,22 @@ do { \ typeof(var) pfo_ret__; \ switch (sizeof(var)) { \ case 1: \ - asm(op "b "__percpu_arg(1)",%0" \ + asm volatile(op "b "__percpu_arg(1)",%0"\ : "=q" (pfo_ret__) \ : "m" (var)); \ break; \ case 2: \ - asm(op "w "__percpu_arg(1)",%0" \ + asm volatile(op "w "__percpu_arg(1)",%0"\ : "=r" (pfo_ret__) \ : "m" (var)); \ break; \ case 4: \ - asm(op "l "__percpu_arg(1)",%0" \ + asm volatile(op "l "__percpu_arg(1)",%0"\ : "=r" (pfo_ret__) \ : "m" (var)); \ break; \ case 8: \ - asm(op "q "__percpu_arg(1)",%0" \ + asm volatile(op "q "__percpu_arg(1)",%0"\ : "=r" (pfo_ret__) \ : "m" (var)); \ break; \ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 12f54082f4c8..78241b736f2a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -46,6 +46,14 @@ #define INTEL_ARCH_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) +#define AMD64_L3_SLICE_SHIFT 48 +#define AMD64_L3_SLICE_MASK \ + ((0xFULL) << AMD64_L3_SLICE_SHIFT) + +#define AMD64_L3_THREAD_SHIFT 56 +#define AMD64_L3_THREAD_MASK \ + ((0xFFULL) << AMD64_L3_THREAD_SHIFT) + #define X86_RAW_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_EVENT | \ ARCH_PERFMON_EVENTSEL_UMASK | \ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b64acb08a62b..106b7d0e2dae 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -124,7 +124,7 @@ */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) + _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) /* diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h index ecffe81ff65c..a892494ca5e4 100644 --- a/arch/x86/include/asm/suspend.h +++ b/arch/x86/include/asm/suspend.h @@ -4,3 +4,11 @@ #else # include <asm/suspend_64.h> #endif +extern unsigned long restore_jump_address __visible; +extern unsigned long jump_address_phys; +extern unsigned long restore_cr3 __visible; +extern unsigned long temp_pgt __visible; +extern unsigned long relocated_restore_code __visible; +extern int relocate_restore_code(void); +/* Defined in hibernate_asm_32/64.S */ +extern asmlinkage __visible int restore_image(void); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 8be6afb58471..fdbd9d7b7bca 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -32,4 +32,8 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); +/* routines for saving/restoring kernel state */ +extern char core_restore_code[]; +extern char restore_registers[]; + #endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index a80c0673798f..e60c45fd3679 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -10,8 +10,13 @@ struct cpumask; struct mm_struct; #ifdef CONFIG_X86_UV +#include <linux/efi.h> extern enum uv_system_type get_uv_system_type(void); +static inline bool is_early_uv_system(void) +{ + return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab); +} extern int is_uv_system(void); extern int is_uv_hubless(void); extern void uv_cpu_init(void); @@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, #else /* X86_UV */ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } +static inline bool is_early_uv_system(void) { return 0; } static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index d383140e1dc8..068d9b067c83 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_XEN_EVENTS_H #define _ASM_X86_XEN_EVENTS_H +#include <xen/xen.h> + enum ipi_vector { XEN_RESCHEDULE_VECTOR, XEN_CALL_FUNCTION_VECTOR, diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index f299d8a479bb..3f9d1b4019bb 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -482,7 +482,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, { void *vaddr; - vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs); + vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs); if (!vaddr || !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24)) return vaddr; @@ -494,7 +494,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, goto out_free; return vaddr; out_free: - dma_direct_free(dev, size, vaddr, *dma_addr, attrs); + dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs); return NULL; } @@ -504,7 +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_direct_free(dev, size, vaddr, dma_addr, attrs); + dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 22ab408177b2..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 285eb3ec4200..3736f6dc9545 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -529,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive); + unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, - u32 cbm); + unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); int rdt_pseudo_lock_init(void); void rdt_pseudo_lock_release(void); diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index 40f3903ae5d9..f8c260d522ca 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -797,25 +797,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) /** * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked * @d: RDT domain - * @_cbm: CBM to test + * @cbm: CBM to test * - * @d represents a cache instance and @_cbm a capacity bitmask that is - * considered for it. Determine if @_cbm overlaps with any existing + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing * pseudo-locked region on @d. * - * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false * otherwise. */ -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *cbm_b; unsigned int cbm_len; + unsigned long cbm_b; if (d->plr) { cbm_len = d->plr->r->cache.cbm_len; - cbm_b = (unsigned long *)&d->plr->cbm; - if (bitmap_intersects(cbm, cbm_b, cbm_len)) + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) return true; } return false; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 1b8e86a5d5e1..b140c68bc14b 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -975,33 +975,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * is false then overlaps with any resource group or hardware entities * will be considered. * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * * Return: false if CBM does not overlap, true if it does. */ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive) + unsigned long cbm, int closid, bool exclusive) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *ctrl_b; enum rdtgrp_mode mode; + unsigned long ctrl_b; u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ if (!exclusive) { - if (bitmap_intersects(cbm, - (unsigned long *)&r->cache.shareable_bits, - r->cache.cbm_len)) + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) return true; } /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { - ctrl_b = (unsigned long *)ctrl; + ctrl_b = *ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { - if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { if (exclusive) { if (mode == RDT_MODE_EXCLUSIVE) return true; @@ -1138,15 +1139,18 @@ out: * computed by first dividing the total cache size by the CBM length to * determine how many bytes each bit in the bitmask represents. The result * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. */ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, - struct rdt_domain *d, u32 cbm) + struct rdt_domain *d, unsigned long cbm) { struct cpu_cacheinfo *ci; unsigned int size = 0; int num_b, i; - num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + num_b = bitmap_weight(&cbm, r->cache.cbm_len); ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == r->cache_level) { @@ -2353,6 +2357,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 used_b = 0, unused_b = 0; u32 closid = rdtgrp->closid; struct rdt_resource *r; + unsigned long tmp_cbm; enum rdtgrp_mode mode; struct rdt_domain *d; int i, ret; @@ -2390,9 +2395,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) * modify the CBM based on system availability. */ cbm_ensure_valid(&d->new_ctrl, r); - if (bitmap_weight((unsigned long *) &d->new_ctrl, - r->cache.cbm_len) < - r->cache.min_cbm_bits) { + /* + * Assign the u32 CBM to an unsigned long to ensure + * that bitmap_weight() does not access out-of-bound + * memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < + r->cache.min_cbm_bits) { rdt_last_cmd_printf("no space on %s:%d\n", r->name, d->id); return -ENOSPC; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 23f1691670b6..61a949d84dfa 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -314,7 +314,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Validate and sanitize the copied state. */ - struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 661583662430..71c0b01d93b1 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override, int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ -#ifdef CONFIG_X86_64 if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; -#endif /* * If SME is active then swiotlb will be set to 1 so that bounce diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4866badb235..90ecc108bc8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p) x86_init.hyper.guest_late_init(); e820__reserve_resources(); - e820__register_nosave_regions(max_low_pfn); + e820__register_nosave_regions(max_pfn); x86_init.resources.reserve_resources(); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index be01328eb755..fddaefc51fb6 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -25,7 +25,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES; +__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6490f618e096..6d5dc5dabfd7 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -26,6 +26,7 @@ #include <asm/apic.h> #include <asm/intel-family.h> #include <asm/i8259.h> +#include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -57,7 +58,7 @@ struct cyc2ns { static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -void cyc2ns_read_begin(struct cyc2ns_data *data) +void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data) { int seq, idx; @@ -74,7 +75,7 @@ void cyc2ns_read_begin(struct cyc2ns_data *data) } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -void cyc2ns_read_end(void) +void __always_inline cyc2ns_read_end(void) { preempt_enable_notrace(); } @@ -103,7 +104,7 @@ void cyc2ns_read_end(void) * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -static inline unsigned long long cycles_2_ns(unsigned long long cyc) +static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; unsigned long long ns; @@ -1433,6 +1434,9 @@ void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; + /* Don't change UV TSC multi-chassis synchronization */ + if (is_early_uv_system()) + return; if (!determine_cpu_tsc_frequencies(true)) return; loops_per_jiffy = get_loops_per_jiffy(); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d7e9bce6ff61..51b953ad9d4e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask; */ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; +/* + * In some cases, we need to preserve the GFN of a non-present or reserved + * SPTE when we usurp the upper five bits of the physical address space to + * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll + * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask + * left into the reserved bits, i.e. the GFN in the SPTE will be split into + * high and low parts. This mask covers the lower bits of the GFN. + */ +static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; + + static void mmu_spte_set(u64 *sptep, u64 spte); static union kvm_mmu_page_role kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu); @@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte) static gfn_t get_mmio_spte_gfn(u64 spte) { - u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask | - shadow_nonpresent_or_rsvd_mask; - u64 gpa = spte & ~mask; + u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) & shadow_nonpresent_or_rsvd_mask; @@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); static void kvm_mmu_reset_all_pte_masks(void) { + u8 low_phys_bits; + shadow_user_mask = 0; shadow_accessed_mask = 0; shadow_dirty_mask = 0; @@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void) * appropriate mask to guard against L1TF attacks. Otherwise, it is * assumed that the CPU is not vulnerable to L1TF. */ + low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_data.x86_phys_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) + 52 - shadow_nonpresent_or_rsvd_mask_len) { shadow_nonpresent_or_rsvd_mask = rsvd_bits(boot_cpu_data.x86_phys_bits - shadow_nonpresent_or_rsvd_mask_len, boot_cpu_data.x86_phys_bits - 1); + low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; + } + shadow_nonpresent_or_rsvd_lower_gfn_mask = + GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); } static int is_cpuid_PSE36(void) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d96092b35936..61ccfb13899e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -436,14 +436,18 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) static inline bool svm_sev_enabled(void) { - return max_sev_asid; + return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0; } static inline bool sev_guest(struct kvm *kvm) { +#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->active; +#else + return false; +#endif } static inline int sev_get_asid(struct kvm *kvm) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06412ba46aa3..e665aa7167cf 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO); #define MSR_BITMAP_MODE_X2APIC 1 #define MSR_BITMAP_MODE_X2APIC_APICV 2 -#define MSR_BITMAP_MODE_LM 4 #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL @@ -857,6 +856,7 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u64 vmcs01_guest_bndcfgs; u16 vpid02; u16 last_vpid; @@ -1572,8 +1572,12 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm) goto out; } + /* + * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the + * base of EPT PML4 table, strip off EPT configuration information. + */ ret = hyperv_flush_guest_mapping( - to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer); + to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK); out: spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); @@ -2899,8 +2903,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE); } - if (is_long_mode(&vmx->vcpu)) - wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #else savesegment(fs, fs_sel); savesegment(gs, gs_sel); @@ -2951,8 +2954,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) vmx->loaded_cpu_state = NULL; #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); #endif if (host_state->ldt_sel || (host_state->gs_sel & 7)) { kvm_load_ldt(host_state->ldt_sel); @@ -2980,24 +2982,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) #ifdef CONFIG_X86_64 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - rdmsrl(MSR_KERNEL_GS_BASE, - vmx->msr_guest_kernel_gs_base); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + preempt_enable(); return vmx->msr_guest_kernel_gs_base; } static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data) { - if (is_long_mode(&vmx->vcpu)) { - preempt_disable(); - if (vmx->loaded_cpu_state) - wrmsrl(MSR_KERNEL_GS_BASE, data); - preempt_enable(); - } + preempt_disable(); + if (vmx->loaded_cpu_state) + wrmsrl(MSR_KERNEL_GS_BASE, data); + preempt_enable(); vmx->msr_guest_kernel_gs_base = data; } #endif @@ -3533,9 +3530,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; - if (kvm_mpx_supported()) - msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; - /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; @@ -3552,8 +3546,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) VM_ENTRY_LOAD_IA32_PAT; msrs->entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER); - if (kvm_mpx_supported()) - msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; @@ -3601,12 +3593,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high); msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_DESC | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING; + /* * We can emulate "VMCS shadowing," even if the hardware * doesn't support it. @@ -3663,6 +3655,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv) msrs->secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (flexpriority_enabled) + msrs->secondary_ctls_high |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, msrs->misc_low, @@ -5073,19 +5069,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!msr) return; - /* - * MSR_KERNEL_GS_BASE is not intercepted when the guest is in - * 64-bit mode as a 64-bit kernel may frequently access the - * MSR. This means we need to manually save/restore the MSR - * when switching between guest and host state, but only if - * the guest is in 64-bit mode. Sync our cached value if the - * guest is transitioning to 32-bit mode and the CPU contains - * guest state, i.e. the cache is stale. - */ -#ifdef CONFIG_X86_64 - if (!(efer & EFER_LMA)) - (void)vmx_read_guest_kernel_gs_base(vmx); -#endif vcpu->arch.efer = efer; if (efer & EFER_LMA) { vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE); @@ -6078,9 +6061,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu) mode |= MSR_BITMAP_MODE_X2APIC_APICV; } - if (is_long_mode(vcpu)) - mode |= MSR_BITMAP_MODE_LM; - return mode; } @@ -6121,9 +6101,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu) if (!changed) return; - vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW, - !(mode & MSR_BITMAP_MODE_LM)); - if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV)) vmx_update_msr_bitmap_x2apic(msr_bitmap, mode); @@ -6189,6 +6166,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static u8 vmx_get_rvi(void) +{ + return vmcs_read16(GUEST_INTR_STATUS) & 0xff; +} + static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6201,7 +6183,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) return false; - rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff; + rvi = vmx_get_rvi(); vapic_page = kmap(vmx->nested.virtual_apic_page); vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); @@ -10245,15 +10227,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; + if (!flexpriority_enabled && + !cpu_has_vmx_virtualize_x2apic_mode()) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_need_tpr_shadow(vcpu)) - return; - sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); @@ -10375,6 +10358,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) return max_irr; } +static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) +{ + u8 rvi = vmx_get_rvi(); + u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -11264,6 +11255,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) #undef cr4_fixed1_update } +static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (kvm_mpx_supported()) { + bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX); + + if (mpx_enabled) { + vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; + } else { + vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS; + vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS; + } + } +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -11280,8 +11288,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &= ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - if (nested_vmx_allowed(vcpu)) + if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); + nested_vmx_entry_exit_ctls_update(vcpu); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -12049,8 +12059,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - if (vmx_mpx_supported()) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + if (kvm_mpx_supported()) { + if (vmx->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + else + vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs); + } if (enable_vpid) { if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) @@ -12595,15 +12610,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; - u32 vmcs01_cpu_exec_ctrl; + bool evaluate_pending_interrupts; int r = 0; - vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING); + if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) + evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + if (kvm_mpx_supported() && + !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)) + vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02); vmx_segment_cache_clear(vmx); @@ -12643,16 +12664,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) * to L1 or delivered directly to L2 (e.g. In case L1 don't * intercept EXTERNAL_INTERRUPT). * - * Usually this would be handled by L0 requesting a - * IRQ/NMI window by setting VMCS accordingly. However, - * this setting was done on VMCS01 and now VMCS02 is active - * instead. Thus, we force L0 to perform pending event - * evaluation by requesting a KVM_REQ_EVENT. - */ - if (vmcs01_cpu_exec_ctrl & - (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + * Usually this would be handled by the processor noticing an + * IRQ/NMI window request, or checking RVI during evaluation of + * pending virtual interrupts. However, this setting was done + * on VMCS01 and now VMCS02 is active instead. Thus, we force L0 + * to perform pending event evaluation by requesting a KVM_REQ_EVENT. + */ + if (unlikely(evaluate_pending_interrupts)) kvm_make_request(KVM_REQ_EVENT, vcpu); - } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index edbf00ec56b3..ca717737347e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4698,7 +4698,7 @@ static void kvm_init_msr_list(void) */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: - if (!kvm_x86_ops->mpx_supported()) + if (!kvm_mpx_supported()) continue; break; case MSR_TSC_AUX: diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index cf16dfec2734..0d45f6debb3a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -16,6 +16,7 @@ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ +#include <linux/efi.h> /* efi_recover_from_page_fault()*/ #include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ @@ -25,6 +26,7 @@ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ +#include <asm/efi.h> /* efi_recover_from_page_fault()*/ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -791,6 +793,13 @@ no_context(struct pt_regs *regs, unsigned long error_code, return; /* + * Buggy firmware could access regions which might page fault, try to + * recover from such faults. + */ + if (IS_ENABLED(CONFIG_EFI)) + efi_recover_from_page_fault(address); + + /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 089e78c4effd..59274e2c1ac4 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -115,6 +115,8 @@ static inline void pgd_list_del(pgd_t *pgd) #define UNSHARED_PTRS_PER_PGD \ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) +#define MAX_UNSHARED_PTRS_PER_PGD \ + max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD) static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) @@ -181,6 +183,7 @@ static void pgd_dtor(pgd_t *pgd) * and initialize the kernel pmds here. */ #define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD +#define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD /* * We allocate separate PMDs for the kernel part of the user page-table @@ -189,6 +192,7 @@ static void pgd_dtor(pgd_t *pgd) */ #define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) +#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { @@ -210,7 +214,9 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 +#define MAX_PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 +#define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) @@ -428,8 +434,8 @@ static inline void _pgd_free(pgd_t *pgd) pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; - pmd_t *u_pmds[PREALLOCATED_USER_PMDS]; - pmd_t *pmds[PREALLOCATED_PMDS]; + pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; + pmd_t *pmds[MAX_PREALLOCATED_PMDS]; pgd = _pgd_alloc(); diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c index 5fdacb322ceb..7476b3b097e1 100644 --- a/arch/x86/platform/efi/early_printk.c +++ b/arch/x86/platform/efi/early_printk.c @@ -26,12 +26,14 @@ static bool early_efi_keep; */ static __init int early_efi_map_fb(void) { - unsigned long base, size; + u64 base, size; if (!early_efi_keep) return 0; base = boot_params.screen_info.lfb_base; + if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) + base |= (u64)boot_params.screen_info.ext_lfb_base << 32; size = boot_params.screen_info.lfb_size; efi_fb = ioremap(base, size); @@ -46,9 +48,11 @@ early_initcall(early_efi_map_fb); */ static __ref void *early_efi_map(unsigned long start, unsigned long len) { - unsigned long base; + u64 base; base = boot_params.screen_info.lfb_base; + if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) + base |= (u64)boot_params.screen_info.ext_lfb_base << 32; if (efi_fb) return (efi_fb + start); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index ee5d08f25ce4..e8da7f492970 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void) /* * 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. + * in a kernel thread and user context. Preemption needs to remain disabled + * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm + * can not change under us. + * It should be ensured that there are no concurent calls to this function. */ 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 diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 844d31cb8a0c..669babcaf245 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -16,6 +16,7 @@ #include <asm/efi.h> #include <asm/uv/uv.h> #include <asm/cpu_device_id.h> +#include <asm/reboot.h> #define EFI_MIN_RESERVE 5120 @@ -654,3 +655,80 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, } #endif + +/* + * If any access by any efi runtime service causes a page fault, then, + * 1. If it's efi_reset_system(), reboot through BIOS. + * 2. If any other efi runtime service, then + * a. Return error status to the efi caller process. + * b. Disable EFI Runtime Services forever and + * c. Freeze efi_rts_wq and schedule new process. + * + * @return: Returns, if the page fault is not handled. This function + * will never return if the page fault is handled successfully. + */ +void efi_recover_from_page_fault(unsigned long phys_addr) +{ + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* + * Make sure that an efi runtime service caused the page fault. + * "efi_mm" cannot be used to check if the page fault had occurred + * in the firmware context because efi=old_map doesn't use efi_pgd. + */ + if (efi_rts_work.efi_rts_id == NONE) + return; + + /* + * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so + * page faulting on these addresses isn't expected. + */ + if (phys_addr >= 0x0000 && phys_addr <= 0x0fff) + return; + + /* + * Print stack trace as it might be useful to know which EFI Runtime + * Service is buggy. + */ + WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n", + phys_addr); + + /* + * Buggy efi_reset_system() is handled differently from other EFI + * Runtime Services as it doesn't use efi_rts_wq. Although, + * native_machine_emergency_restart() says that machine_real_restart() + * could fail, it's better not to compilcate this fault handler + * because this case occurs *very* rarely and hence could be improved + * on a need by basis. + */ + if (efi_rts_work.efi_rts_id == RESET_SYSTEM) { + pr_info("efi_reset_system() buggy! Reboot through BIOS\n"); + machine_real_restart(MRR_BIOS); + return; + } + + /* + * Before calling EFI Runtime Service, the kernel has switched the + * calling process to efi_mm. Hence, switch back to task_mm. + */ + arch_efi_call_virt_teardown(); + + /* Signal error status to the efi caller process */ + efi_rts_work.status = EFI_ABORTED; + complete(&efi_rts_work.efi_rts_comp); + + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n"); + + /* + * Call schedule() in an infinite loop, so that any spurious wake ups + * will never run efi_rts_wq again. + */ + for (;;) { + set_current_state(TASK_IDLE); + schedule(); + } + + return; +} diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c index 4392c15ed9e0..dbfc5cf2aa93 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c @@ -10,7 +10,7 @@ * of the License. */ -#include <linux/gpio.h> +#include <linux/gpio/machine.h> #include <linux/platform_device.h> #include <linux/regulator/machine.h> #include <linux/regulator/fixed.h> @@ -43,7 +43,6 @@ static struct fixed_voltage_config bcm43xx_vmmc = { * real voltage and signaling are still 1.8V. */ .microvolts = 2000000, /* 1.8V */ - .gpio = -EINVAL, .startup_delay = 250 * 1000, /* 250ms */ .enable_high = 1, /* active high */ .enabled_at_boot = 0, /* disabled at boot */ @@ -58,11 +57,23 @@ static struct platform_device bcm43xx_vmmc_regulator = { }, }; +static struct gpiod_lookup_table bcm43xx_vmmc_gpio_table = { + .dev_id = "reg-fixed-voltage.0", + .table = { + GPIO_LOOKUP("0000:00:0c.0", -1, NULL, GPIO_ACTIVE_LOW), + {} + }, +}; + static int __init bcm43xx_regulator_register(void) { + struct gpiod_lookup_table *table = &bcm43xx_vmmc_gpio_table; + struct gpiod_lookup *lookup = table->table; int ret; - bcm43xx_vmmc.gpio = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME); + lookup[0].chip_hwnum = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME); + gpiod_add_lookup_table(table); + ret = platform_device_register(&bcm43xx_vmmc_regulator); if (ret) { pr_err("%s: vmmc regulator register failed\n", __func__); diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c index fd39301f25ac..7e56fc74093c 100644 --- a/arch/x86/platform/ts5500/ts5500.c +++ b/arch/x86/platform/ts5500/ts5500.c @@ -24,7 +24,6 @@ #include <linux/kernel.h> #include <linux/leds.h> #include <linux/init.h> -#include <linux/platform_data/gpio-ts5500.h> #include <linux/platform_data/max197.h> #include <linux/platform_device.h> #include <linux/slab.h> diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index a4701389562c..37923d715741 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -7,4 +7,4 @@ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_cpu.o := $(nostackp) obj-$(CONFIG_PM_SLEEP) += cpu.o -obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o +obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c new file mode 100644 index 000000000000..bcddf09b5aa3 --- /dev/null +++ b/arch/x86/power/hibernate.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hibernation support for x86 + * + * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl> + * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz> + * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org> + */ +#include <linux/gfp.h> +#include <linux/smp.h> +#include <linux/suspend.h> +#include <linux/scatterlist.h> +#include <linux/kdebug.h> + +#include <crypto/hash.h> + +#include <asm/e820/api.h> +#include <asm/init.h> +#include <asm/proto.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/mtrr.h> +#include <asm/sections.h> +#include <asm/suspend.h> +#include <asm/tlbflush.h> + +/* + * Address to jump to in the last phase of restore in order to get to the image + * kernel's text (this value is passed in the image header). + */ +unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; + +/* + * Value of the cr3 register from before the hibernation (this value is passed + * in the image header). + */ +unsigned long restore_cr3 __visible; +unsigned long temp_pgt __visible; +unsigned long relocated_restore_code __visible; + +/** + * pfn_is_nosave - check if given pfn is in the 'nosave' section + */ +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn; + unsigned long nosave_end_pfn; + + nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; + nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; + + return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn; +} + + +#define MD5_DIGEST_SIZE 16 + +struct restore_data_record { + unsigned long jump_address; + unsigned long jump_address_phys; + unsigned long cr3; + unsigned long magic; + u8 e820_digest[MD5_DIGEST_SIZE]; +}; + +#if IS_BUILTIN(CONFIG_CRYPTO_MD5) +/** + * get_e820_md5 - calculate md5 according to given e820 table + * + * @table: the e820 table to be calculated + * @buf: the md5 result to be stored to + */ +static int get_e820_md5(struct e820_table *table, void *buf) +{ + struct crypto_shash *tfm; + struct shash_desc *desc; + int size; + int ret = 0; + + tfm = crypto_alloc_shash("md5", 0, 0); + if (IS_ERR(tfm)) + return -ENOMEM; + + desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), + GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto free_tfm; + } + + desc->tfm = tfm; + desc->flags = 0; + + size = offsetof(struct e820_table, entries) + + sizeof(struct e820_entry) * table->nr_entries; + + if (crypto_shash_digest(desc, (u8 *)table, size, buf)) + ret = -EINVAL; + + kzfree(desc); + +free_tfm: + crypto_free_shash(tfm); + return ret; +} + +static int hibernation_e820_save(void *buf) +{ + return get_e820_md5(e820_table_firmware, buf); +} + +static bool hibernation_e820_mismatch(void *buf) +{ + int ret; + u8 result[MD5_DIGEST_SIZE]; + + memset(result, 0, MD5_DIGEST_SIZE); + /* If there is no digest in suspend kernel, let it go. */ + if (!memcmp(result, buf, MD5_DIGEST_SIZE)) + return false; + + ret = get_e820_md5(e820_table_firmware, result); + if (ret) + return true; + + return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; +} +#else +static int hibernation_e820_save(void *buf) +{ + return 0; +} + +static bool hibernation_e820_mismatch(void *buf) +{ + /* If md5 is not builtin for restore kernel, let it go. */ + return false; +} +#endif + +#ifdef CONFIG_X86_64 +#define RESTORE_MAGIC 0x23456789ABCDEF01UL +#else +#define RESTORE_MAGIC 0x12345678UL +#endif + +/** + * arch_hibernation_header_save - populate the architecture specific part + * of a hibernation image header + * @addr: address to save the data at + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct restore_data_record *rdr = addr; + + if (max_size < sizeof(struct restore_data_record)) + return -EOVERFLOW; + rdr->magic = RESTORE_MAGIC; + rdr->jump_address = (unsigned long)restore_registers; + rdr->jump_address_phys = __pa_symbol(restore_registers); + + /* + * The restore code fixes up CR3 and CR4 in the following sequence: + * + * [in hibernation asm] + * 1. CR3 <= temporary page tables + * 2. CR4 <= mmu_cr4_features (from the kernel that restores us) + * 3. CR3 <= rdr->cr3 + * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel) + * [in restore_processor_state()] + * 5. CR4 <= saved CR4 + * 6. CR3 <= saved CR3 + * + * Our mmu_cr4_features has CR4.PCIDE=0, and toggling + * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so + * rdr->cr3 needs to point to valid page tables but must not + * have any of the PCID bits set. + */ + rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK; + + return hibernation_e820_save(rdr->e820_digest); +} + +/** + * arch_hibernation_header_restore - read the architecture specific data + * from the hibernation image header + * @addr: address to read the data from + */ +int arch_hibernation_header_restore(void *addr) +{ + struct restore_data_record *rdr = addr; + + if (rdr->magic != RESTORE_MAGIC) { + pr_crit("Unrecognized hibernate image header format!\n"); + return -EINVAL; + } + + restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; + restore_cr3 = rdr->cr3; + + if (hibernation_e820_mismatch(rdr->e820_digest)) { + pr_crit("Hibernate inconsistent memory map detected!\n"); + return -ENODEV; + } + + return 0; +} + +int relocate_restore_code(void) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3_pa()) + + pgd_index(relocated_restore_code); + p4d = p4d_offset(pgd, relocated_restore_code); + if (p4d_large(*p4d)) { + set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); + goto out; + } + pud = pud_offset(p4d, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + goto out; + } + pmd = pmd_offset(pud, relocated_restore_code); + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + goto out; + } + pte = pte_offset_kernel(pmd, relocated_restore_code); + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); +out: + __flush_tlb_all(); + return 0; +} diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index afc4ed7b1578..15695e30f982 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -14,9 +14,7 @@ #include <asm/pgtable.h> #include <asm/mmzone.h> #include <asm/sections.h> - -/* Defined in hibernate_asm_32.S */ -extern int restore_image(void); +#include <asm/suspend.h> /* Pointer to the temporary resume page tables */ pgd_t *resume_pg_dir; @@ -145,6 +143,32 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir) #endif } +static int set_up_temporary_text_mapping(pgd_t *pgd_base) +{ + pgd_t *pgd; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_base + pgd_index(restore_jump_address); + + pmd = resume_one_md_table_init(pgd); + if (!pmd) + return -ENOMEM; + + if (boot_cpu_has(X86_FEATURE_PSE)) { + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | pgprot_val(PAGE_KERNEL_LARGE_EXEC))); + } else { + pte = resume_one_page_table_init(pmd); + if (!pte) + return -ENOMEM; + set_pte(pte + pte_index(restore_jump_address), + __pte((jump_address_phys & PAGE_MASK) | pgprot_val(PAGE_KERNEL_EXEC))); + } + + return 0; +} + asmlinkage int swsusp_arch_resume(void) { int error; @@ -154,22 +178,22 @@ asmlinkage int swsusp_arch_resume(void) return -ENOMEM; resume_init_first_level_page_table(resume_pg_dir); + + error = set_up_temporary_text_mapping(resume_pg_dir); + if (error) + return error; + error = resume_physical_mapping_init(resume_pg_dir); if (error) return error; + temp_pgt = __pa(resume_pg_dir); + + error = relocate_restore_code(); + if (error) + return error; + /* We have got enough memory and from now on we cannot recover */ restore_image(); return 0; } - -/* - * pfn_is_nosave - check if given pfn is in the 'nosave' section - */ - -int pfn_is_nosave(unsigned long pfn) -{ - unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; - unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; - return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); -} diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f8e3b668d20b..239f424ccb29 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -26,26 +26,6 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> -/* Defined in hibernate_asm_64.S */ -extern asmlinkage __visible int restore_image(void); - -/* - * Address to jump to in the last phase of restore in order to get to the image - * kernel's text (this value is passed in the image header). - */ -unsigned long restore_jump_address __visible; -unsigned long jump_address_phys; - -/* - * Value of the cr3 register from before the hibernation (this value is passed - * in the image header). - */ -unsigned long restore_cr3 __visible; - -unsigned long temp_level4_pgt __visible; - -unsigned long relocated_restore_code __visible; - static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; @@ -141,46 +121,7 @@ static int set_up_temporary_mappings(void) return result; } - temp_level4_pgt = __pa(pgd); - return 0; -} - -static int relocate_restore_code(void) -{ - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - relocated_restore_code = get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - - memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); - - /* Make the page containing the relocated code executable */ - pgd = (pgd_t *)__va(read_cr3_pa()) + - pgd_index(relocated_restore_code); - p4d = p4d_offset(pgd, relocated_restore_code); - if (p4d_large(*p4d)) { - set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); - goto out; - } - pud = pud_offset(p4d, relocated_restore_code); - if (pud_large(*pud)) { - set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); - goto out; - } - pmd = pmd_offset(pud, relocated_restore_code); - if (pmd_large(*pmd)) { - set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); - goto out; - } - pte = pte_offset_kernel(pmd, relocated_restore_code); - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); -out: - __flush_tlb_all(); + temp_pgt = __pa(pgd); return 0; } @@ -200,166 +141,3 @@ asmlinkage int swsusp_arch_resume(void) restore_image(); return 0; } - -/* - * pfn_is_nosave - check if given pfn is in the 'nosave' section - */ - -int pfn_is_nosave(unsigned long pfn) -{ - unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT; - unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; - return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); -} - -#define MD5_DIGEST_SIZE 16 - -struct restore_data_record { - unsigned long jump_address; - unsigned long jump_address_phys; - unsigned long cr3; - unsigned long magic; - u8 e820_digest[MD5_DIGEST_SIZE]; -}; - -#define RESTORE_MAGIC 0x23456789ABCDEF01UL - -#if IS_BUILTIN(CONFIG_CRYPTO_MD5) -/** - * get_e820_md5 - calculate md5 according to given e820 table - * - * @table: the e820 table to be calculated - * @buf: the md5 result to be stored to - */ -static int get_e820_md5(struct e820_table *table, void *buf) -{ - struct crypto_shash *tfm; - struct shash_desc *desc; - int size; - int ret = 0; - - tfm = crypto_alloc_shash("md5", 0, 0); - if (IS_ERR(tfm)) - return -ENOMEM; - - desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!desc) { - ret = -ENOMEM; - goto free_tfm; - } - - desc->tfm = tfm; - desc->flags = 0; - - size = offsetof(struct e820_table, entries) + - sizeof(struct e820_entry) * table->nr_entries; - - if (crypto_shash_digest(desc, (u8 *)table, size, buf)) - ret = -EINVAL; - - kzfree(desc); - -free_tfm: - crypto_free_shash(tfm); - return ret; -} - -static void hibernation_e820_save(void *buf) -{ - get_e820_md5(e820_table_firmware, buf); -} - -static bool hibernation_e820_mismatch(void *buf) -{ - int ret; - u8 result[MD5_DIGEST_SIZE]; - - memset(result, 0, MD5_DIGEST_SIZE); - /* If there is no digest in suspend kernel, let it go. */ - if (!memcmp(result, buf, MD5_DIGEST_SIZE)) - return false; - - ret = get_e820_md5(e820_table_firmware, result); - if (ret) - return true; - - return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false; -} -#else -static void hibernation_e820_save(void *buf) -{ -} - -static bool hibernation_e820_mismatch(void *buf) -{ - /* If md5 is not builtin for restore kernel, let it go. */ - return false; -} -#endif - -/** - * arch_hibernation_header_save - populate the architecture specific part - * of a hibernation image header - * @addr: address to save the data at - */ -int arch_hibernation_header_save(void *addr, unsigned int max_size) -{ - struct restore_data_record *rdr = addr; - - if (max_size < sizeof(struct restore_data_record)) - return -EOVERFLOW; - rdr->jump_address = (unsigned long)restore_registers; - rdr->jump_address_phys = __pa_symbol(restore_registers); - - /* - * The restore code fixes up CR3 and CR4 in the following sequence: - * - * [in hibernation asm] - * 1. CR3 <= temporary page tables - * 2. CR4 <= mmu_cr4_features (from the kernel that restores us) - * 3. CR3 <= rdr->cr3 - * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel) - * [in restore_processor_state()] - * 5. CR4 <= saved CR4 - * 6. CR3 <= saved CR3 - * - * Our mmu_cr4_features has CR4.PCIDE=0, and toggling - * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so - * rdr->cr3 needs to point to valid page tables but must not - * have any of the PCID bits set. - */ - rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK; - - rdr->magic = RESTORE_MAGIC; - - hibernation_e820_save(rdr->e820_digest); - - return 0; -} - -/** - * arch_hibernation_header_restore - read the architecture specific data - * from the hibernation image header - * @addr: address to read the data from - */ -int arch_hibernation_header_restore(void *addr) -{ - struct restore_data_record *rdr = addr; - - restore_jump_address = rdr->jump_address; - jump_address_phys = rdr->jump_address_phys; - restore_cr3 = rdr->cr3; - - if (rdr->magic != RESTORE_MAGIC) { - pr_crit("Unrecognized hibernate image header format!\n"); - return -EINVAL; - } - - if (hibernation_e820_mismatch(rdr->e820_digest)) { - pr_crit("Hibernate inconsistent memory map detected!\n"); - return -ENODEV; - } - - return 0; -} diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index 6e56815e13a0..6fe383002125 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -12,6 +12,7 @@ #include <asm/page_types.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/frame.h> .text @@ -24,13 +25,30 @@ ENTRY(swsusp_arch_suspend) pushfl popl saved_context_eflags + /* save cr3 */ + movl %cr3, %eax + movl %eax, restore_cr3 + + FRAME_BEGIN call swsusp_save + FRAME_END ret +ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) + /* prepare to jump to the image kernel */ + movl restore_jump_address, %ebx + movl restore_cr3, %ebp + movl mmu_cr4_features, %ecx - movl resume_pg_dir, %eax - subl $__PAGE_OFFSET, %eax + + /* jump to relocated restore code */ + movl relocated_restore_code, %eax + jmpl *%eax + +/* code below has been relocated to a safe page */ +ENTRY(core_restore_code) + movl temp_pgt, %eax movl %eax, %cr3 jecxz 1f # cr4 Pentium and higher, skip if zero @@ -49,7 +67,7 @@ copy_loop: movl pbe_address(%edx), %esi movl pbe_orig_address(%edx), %edi - movl $1024, %ecx + movl $(PAGE_SIZE >> 2), %ecx rep movsl @@ -58,10 +76,13 @@ copy_loop: .p2align 4,,7 done: + jmpl *%ebx + + /* code below belongs to the image kernel */ + .align PAGE_SIZE +ENTRY(restore_registers) /* go back to the original page tables */ - movl $swapper_pg_dir, %eax - subl $__PAGE_OFFSET, %eax - movl %eax, %cr3 + movl %ebp, %cr3 movl mmu_cr4_features, %ecx jecxz 1f # cr4 Pentium and higher, skip if zero movl %ecx, %cr4; # turn PGE back on @@ -82,4 +103,8 @@ done: xorl %eax, %eax + /* tell the hibernation core that we've just restored the memory */ + movl %eax, in_suspend + ret +ENDPROC(restore_registers) diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index fd369a6e9ff8..3008baa2fa95 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -59,7 +59,7 @@ ENTRY(restore_image) movq restore_cr3(%rip), %r9 /* prepare to switch to temporary page tables */ - movq temp_level4_pgt(%rip), %rax + movq temp_pgt(%rip), %rax movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2eeddd814653..0ca46e03b830 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -5,6 +5,7 @@ #include <linux/kexec.h> #include <linux/slab.h> +#include <xen/xen.h> #include <xen/features.h> #include <xen/page.h> #include <xen/interface/memory.h> diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index c85d1a88f476..2a9025343534 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -11,6 +11,7 @@ #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> +#include <xen/xen.h> #include <xen/interface/memory.h> #include <xen/interface/hvm/start_info.h> diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 33a783c77d96..b99585034dd2 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -23,6 +23,7 @@ #include <linux/io.h> #include <linux/export.h> +#include <xen/xen.h> #include <xen/platform_pci.h> #include "xen-ops.h" diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 95997e6c0696..0972184f3f19 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -3,6 +3,7 @@ #include <linux/interrupt.h> #include <asm/xen/hypercall.h> +#include <xen/xen.h> #include <xen/page.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> |