diff options
Diffstat (limited to 'arch/x86')
141 files changed, 2287 insertions, 1369 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc98d5a..a641b90 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -106,6 +106,7 @@ config X86 select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT + select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE @@ -290,6 +291,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config KASAN_SHADOW_OFFSET hex depends on KASAN + default 0xdff8000000000000 if X86_5LEVEL default 0xdffffc0000000000 config HAVE_INTEL_TXT @@ -2787,6 +2789,9 @@ config X86_DMA_REMAP bool depends on STA2X11 +config HAVE_GENERIC_GUP + def_bool y + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d44933..a94a4d1 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -120,10 +120,6 @@ else # -funit-at-a-time shrinks the kernel .text considerably # unfortunately it makes reading oopses harder. KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time) - - # this works around some issues with generating unwind tables in older gccs - # newer gccs do it by default - KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args) endif ifdef CONFIG_X86_X32 @@ -147,6 +143,37 @@ ifeq ($(CONFIG_KMEMCHECK),y) KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy) endif +# +# If the function graph tracer is used with mcount instead of fentry, +# '-maccumulate-outgoing-args' is needed to prevent a GCC bug +# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109) +# +ifdef CONFIG_FUNCTION_GRAPH_TRACER + ifndef CONFIG_HAVE_FENTRY + ACCUMULATE_OUTGOING_ARGS := 1 + else + ifeq ($(call cc-option-yn, -mfentry), n) + ACCUMULATE_OUTGOING_ARGS := 1 + endif + endif +endif + +# +# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a +# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way +# to test for this bug at compile-time because the test case needs to execute, +# which is a no-go for cross compilers. So check the GCC version instead. +# +ifdef CONFIG_JUMP_LABEL + ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1) + ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1) + endif +endif + +ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) + KBUILD_CFLAGS += -maccumulate-outgoing-args +endif + # Stackpointer is addressed different for 32 bit and 64 bit x86 sp-$(CONFIG_X86_32) := esp sp-$(CONFIG_X86_64) := rsp diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 6647ed4..a45eb15 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx) # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) -# Work around the pentium-mmx code generator madness of gcc4.4.x which -# does stack alignment by generating horrible code _before_ the mcount -# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph -# tracer assumptions. For i686, generic, core2 this is set by the -# compiler anyway -ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y) -ADD_ACCUMULATE_OUTGOING_ARGS := y -endif - -# Work around to a bug with asm goto with first implementations of it -# in gcc causing gcc to mess up the push and pop of the stack in some -# uses of asm goto. -ifeq ($(CONFIG_JUMP_LABEL), y) -ADD_ACCUMULATE_OUTGOING_ARGS := y -endif - -cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args) - # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. ifneq ($(CONFIG_X86_P6_NOP),y) diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index 4ad7d70..8f0c4c9 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -44,6 +44,15 @@ static const u32 req_flags[NCAPINTS] = 0, /* REQUIRED_MASK5 not implemented in this file */ REQUIRED_MASK6, 0, /* REQUIRED_MASK7 not implemented in this file */ + 0, /* REQUIRED_MASK8 not implemented in this file */ + 0, /* REQUIRED_MASK9 not implemented in this file */ + 0, /* REQUIRED_MASK10 not implemented in this file */ + 0, /* REQUIRED_MASK11 not implemented in this file */ + 0, /* REQUIRED_MASK12 not implemented in this file */ + 0, /* REQUIRED_MASK13 not implemented in this file */ + 0, /* REQUIRED_MASK14 not implemented in this file */ + 0, /* REQUIRED_MASK15 not implemented in this file */ + REQUIRED_MASK16, }; #define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a)) diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 6687ab9..9e77c23 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -70,16 +70,19 @@ int has_eflag(unsigned long mask) # define EBX_REG "=b" #endif -static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d) +static inline void cpuid_count(u32 id, u32 count, + u32 *a, u32 *b, u32 *c, u32 *d) { asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" "cpuid \n\t" ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif \n\t" : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b) - : "a" (id) + : "a" (id), "c" (count) ); } +#define cpuid(id, a, b, c, d) cpuid_count(id, 0, a, b, c, d) + void get_cpuflags(void) { u32 max_intel_level, max_amd_level; @@ -108,6 +111,11 @@ void get_cpuflags(void) cpu.model += ((tfms >> 16) & 0xf) << 4; } + if (max_intel_level >= 0x00000007) { + cpuid_count(0x00000007, 0, &ignored, &ignored, + &cpu.flags[16], &ignored); + } + cpuid(0x80000000, &max_amd_level, &ignored, &ignored, &ignored); diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 7ef4a09..6205d3b 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -176,6 +176,7 @@ CONFIG_E1000E=y CONFIG_SKY2=y CONFIG_FORCEDETH=y CONFIG_8139TOO=y +CONFIG_R8169=y CONFIG_FDDI=y CONFIG_INPUT_POLLDEV=y # CONFIG_INPUT_MOUSEDEV_PSAUX is not set diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 044d18e..f07b4ef 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -265,12 +265,9 @@ return_from_SYSCALL_64: * * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. + * + * Change top 16 bits to be the sign-extension of 47th bit */ - .ifne __VIRTUAL_MASK_SHIFT - 47 - .error "virtual address width changed -- SYSRET checks need update" - .endif - - /* Change top 16 bits to be the sign-extension of 47th bit */ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 9ba050f..0af59fa 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -390,3 +390,4 @@ 381 i386 pkey_alloc sys_pkey_alloc 382 i386 pkey_free sys_pkey_free 383 i386 statx sys_statx +384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 226ca70..5c5d4d7 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -354,7 +354,7 @@ static void vgetcpu_cpu_init(void *arg) d.p = 1; /* Present */ d.d = 1; /* 32-bit */ - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); } static int vgetcpu_online(unsigned int cpu) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index afb222b..c84584b 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, return &amd_f15_PMC20; } case AMD_EVENT_NB: - /* moved to perf_event_amd_uncore.c */ + /* moved to uncore.c */ return &emptyconstraint; default: return &emptyconstraint; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 349d4d1..580b60f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->mm) - load_mm_cr4(current->mm); + if (current->active_mm) + load_mm_cr4(current->active_mm); } static void x86_pmu_event_mapped(struct perf_event *event) @@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event) if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; + /* + * This function relies on not being called concurrently in two + * tasks in the same mm. Otherwise one task could observe + * perf_rdpmc_allowed > 1 and return all the way back to + * userspace with CR4.PCE clear while another task is still + * doing on_each_cpu_mask() to propagate CR4.PCE. + * + * For now, this can't happen because all callers hold mmap_sem + * for write. If this changes, we'll need a different solution. + */ + lockdep_assert_held_exclusive(¤t->mm->mmap_sem); + if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); } @@ -2244,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data *data; + u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; @@ -2251,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event, !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); userpg->pmc_width = x86_pmu.cntval_bits; - if (!sched_clock_stable()) + if (!using_native_sched_clock() || !sched_clock_stable()) return; data = cyc2ns_read_begin(); + offset = data->cyc2ns_offset + __sched_clock_offset; + /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. @@ -2263,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time = 1; userpg->time_mult = data->cyc2ns_mul; userpg->time_shift = data->cyc2ns_shift; - userpg->time_offset = data->cyc2ns_offset - now; + userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different @@ -2271,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event, */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; - userpg->time_zero = data->cyc2ns_offset; + userpg->time_zero = offset; } cyc2ns_read_end(data); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index aff4b5b..238ae32 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -1,5 +1,5 @@ /* - * perf_event_intel_cstate.c: support cstate residency counters + * Support cstate residency counters * * Copyright (C) 2015, Intel Corp. * Author: Kan Liang (kan.liang@intel.com) diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 22054ca..9d05c7e 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -1,5 +1,5 @@ /* - * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters + * Support Intel RAPL energy consumption counters * Copyright (C) 2013 Google, Inc., Stephane Eranian * * Intel RAPL interface is specified in the IA-32 Manual Vol3b diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index ad986c1..df5989f 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head; extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; -/* perf_event_intel_uncore_snb.c */ +/* uncore_snb.c */ int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); @@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); -/* perf_event_intel_uncore_snbep.c */ +/* uncore_snbep.c */ int snbep_uncore_pci_init(void); void snbep_uncore_cpu_init(void); int ivbep_uncore_pci_init(void); @@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void); int skx_uncore_pci_init(void); void skx_uncore_cpu_init(void); -/* perf_event_intel_uncore_nhmex.c */ +/* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index db64baf0..8bef70e 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -158,13 +158,13 @@ void hyperv_init(void) clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); return; } +register_msr_cs: #endif /* * For 32 bit guests just use the MSR based mechanism for reading * the partition counter. */ -register_msr_cs: hyperv_cs = &hyperv_cs_msr; if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4e77723..0fe0044 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -187,6 +187,7 @@ * Reuse free bits when adding new feature flags! */ #define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ @@ -289,7 +290,8 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 1548ca9..d0a21b1 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -4,6 +4,7 @@ #include <asm/desc_defs.h> #include <asm/ldt.h> #include <asm/mmu.h> +#include <asm/fixmap.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -45,11 +46,43 @@ struct gdt_page { DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); -static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu) +/* Provide the original GDT */ +static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) { return per_cpu(gdt_page, cpu).gdt; } +/* Provide the current original GDT */ +static inline struct desc_struct *get_current_gdt_rw(void) +{ + return this_cpu_ptr(&gdt_page)->gdt; +} + +/* Get the fixmap index for a specific processor */ +static inline unsigned int get_cpu_gdt_ro_index(int cpu) +{ + return FIX_GDT_REMAP_BEGIN + cpu; +} + +/* Provide the fixmap address of the remapped GDT */ +static inline struct desc_struct *get_cpu_gdt_ro(int cpu) +{ + unsigned int idx = get_cpu_gdt_ro_index(cpu); + return (struct desc_struct *)__fix_to_virt(idx); +} + +/* Provide the current read-only GDT */ +static inline struct desc_struct *get_current_gdt_ro(void) +{ + return get_cpu_gdt_ro(smp_processor_id()); +} + +/* Provide the physical address of the GDT page. */ +static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) +{ + return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); +} + #ifdef CONFIG_X86_64 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, @@ -174,7 +207,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned t static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) { - struct desc_struct *d = get_cpu_gdt_table(cpu); + struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, @@ -194,22 +227,90 @@ static inline void native_set_ldt(const void *addr, unsigned int entries) set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, entries * LDT_ENTRY_SIZE - 1); - write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, &ldt, DESC_LDT); asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); } } +static inline void native_load_gdt(const struct desc_ptr *dtr) +{ + asm volatile("lgdt %0"::"m" (*dtr)); +} + +static inline void native_load_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +static inline void native_store_gdt(struct desc_ptr *dtr) +{ + asm volatile("sgdt %0":"=m" (*dtr)); +} + +static inline void native_store_idt(struct desc_ptr *dtr) +{ + asm volatile("sidt %0":"=m" (*dtr)); +} + +/* + * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is + * a read-only remapping. To prevent a page fault, the GDT is switched to the + * original writeable version when needed. + */ +#ifdef CONFIG_X86_64 +static inline void native_load_tr_desc(void) +{ + struct desc_ptr gdt; + int cpu = raw_smp_processor_id(); + bool restore = 0; + struct desc_struct *fixmap_gdt; + + native_store_gdt(&gdt); + fixmap_gdt = get_cpu_gdt_ro(cpu); + + /* + * If the current GDT is the read-only fixmap, swap to the original + * writeable version. Swap back at the end. + */ + if (gdt.address == (unsigned long)fixmap_gdt) { + load_direct_gdt(cpu); + restore = 1; + } + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); + if (restore) + load_fixmap_gdt(cpu); +} +#else static inline void native_load_tr_desc(void) { asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +#endif + +static inline unsigned long native_store_tr(void) +{ + unsigned long tr; + + asm volatile("str %0":"=r" (tr)); + + return tr; +} + +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) +{ + struct desc_struct *gdt = get_cpu_gdt_rw(cpu); + unsigned int i; + + for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) + gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; +} DECLARE_PER_CPU(bool, __tss_limit_invalid); static inline void force_reload_TR(void) { - struct desc_struct *d = get_cpu_gdt_table(smp_processor_id()); + struct desc_struct *d = get_current_gdt_rw(); tss_desc tss; memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); @@ -257,44 +358,6 @@ static inline void invalidate_tss_limit(void) this_cpu_write(__tss_limit_invalid, true); } -static inline void native_load_gdt(const struct desc_ptr *dtr) -{ - asm volatile("lgdt %0"::"m" (*dtr)); -} - -static inline void native_load_idt(const struct desc_ptr *dtr) -{ - asm volatile("lidt %0"::"m" (*dtr)); -} - -static inline void native_store_gdt(struct desc_ptr *dtr) -{ - asm volatile("sgdt %0":"=m" (*dtr)); -} - -static inline void native_store_idt(struct desc_ptr *dtr) -{ - asm volatile("sidt %0":"=m" (*dtr)); -} - -static inline unsigned long native_store_tr(void) -{ - unsigned long tr; - - asm volatile("str %0":"=r" (tr)); - - return tr; -} - -static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) -{ - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - unsigned int i; - - for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) - gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; -} - /* This intentionally ignores lm, since 32-bit apps don't have that field. */ #define LDT_empty(info) \ ((info)->base_addr == 0 && \ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 85599ad..5dff775 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -36,6 +36,12 @@ # define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31)) #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ +#ifdef CONFIG_X86_5LEVEL +# define DISABLE_LA57 0 +#else +# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -55,7 +61,7 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) #define DISABLED_MASK17 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9d49c18..d4d3ed4 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -293,8 +293,23 @@ do { \ } \ } while (0) +/* + * True on X86_32 or when emulating IA32 on X86_64 + */ +static inline int mmap_is_ia32(void) +{ + return IS_ENABLED(CONFIG_X86_32) || + (IS_ENABLED(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); +} + +extern unsigned long tasksize_32bit(void); +extern unsigned long tasksize_64bit(void); +extern unsigned long get_mmap_base(int is_legacy); + #ifdef CONFIG_X86_32 +#define __STACK_RND_MASK(is32bit) (0x7ff) #define STACK_RND_MASK (0x7ff) #define ARCH_DLINFO ARCH_DLINFO_IA32 @@ -304,7 +319,8 @@ do { \ #else /* CONFIG_X86_32 */ /* 1GB for 64bit, 8MB for 32bit */ -#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff) +#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) +#define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) #define ARCH_DLINFO \ do { \ @@ -348,16 +364,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages -/* - * True on X86_32 or when emulating IA32 on X86_64 - */ -static inline int mmap_is_ia32(void) -{ - return IS_ENABLED(CONFIG_X86_32) || - (IS_ENABLED(CONFIG_COMPAT) && - test_thread_flag(TIF_ADDR32)); -} - /* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 8554f96..b65155c 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -100,6 +100,10 @@ enum fixed_addresses { #ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif + /* Fixmap entries to remap the GDTs, one per processor. */ + FIX_GDT_REMAP_BEGIN, + FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index 1410b56..f527b02 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -11,9 +11,12 @@ * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT */ #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (0xffff800000000000ULL >> 3)) -/* 47 bits for kernel address -> (47 - 3) bits for shadow */ -#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (47 - 3))) + ((-1UL << __VIRTUAL_MASK_SHIFT) >> 3)) +/* + * 47 bits for kernel address -> (47 - 3) bits for shadow + * 56 bits for kernel address -> (56 - 3) bits for shadow + */ +#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3))) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 282630e..70ef205 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -164,6 +164,7 @@ struct kimage_arch { }; #else struct kimage_arch { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index d74747b..c4eda79 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node { }; void kvm_page_track_init(struct kvm *kvm); +void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 306c7e12..6e933d2 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -220,18 +220,6 @@ static inline int vma_pkey(struct vm_area_struct *vma) } #endif -static inline bool __pkru_allows_pkey(u16 pkey, bool write) -{ - u32 pkru = read_pkru(); - - if (!__pkru_allows_read(pkru, pkey)) - return false; - if (write && !__pkru_allows_write(pkru, pkey)) - return false; - - return true; -} - /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other @@ -268,8 +256,4 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } -static inline bool arch_pte_access_permitted(pte_t pte, bool write) -{ - return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write); -} #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d8b5f8a..673f9ac 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -45,6 +45,8 @@ #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd #define MSR_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31 +#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT) #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -127,6 +129,7 @@ /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) @@ -552,10 +555,12 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) -/* MISC_FEATURE_ENABLES non-architectural features */ -#define MSR_MISC_FEATURE_ENABLES 0x00000140 +/* MISC_FEATURES_ENABLES non-architectural features */ +#define MSR_MISC_FEATURES_ENABLES 0x00000140 -#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT) +#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1 #define MSR_IA32_TSC_DEADLINE 0x000006E0 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 9215e05..3f5f08b 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -36,7 +36,12 @@ * 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 + #ifdef CONFIG_RANDOMIZE_MEMORY #define __PAGE_OFFSET page_offset_base #else @@ -46,8 +51,13 @@ #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 +#else #define __PHYSICAL_MASK_SHIFT 46 #define __VIRTUAL_MASK_SHIFT 47 +#endif /* * Kernel image size is limited to 1GiB due to the fixmap living in the diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 0489884..55fa56f 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -357,6 +357,16 @@ static inline void paravirt_release_pud(unsigned long pfn) PVOP_VCALL1(pv_mmu_ops.release_pud, pfn); } +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn); +} + +static inline void paravirt_release_p4d(unsigned long pfn) +{ + PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn); +} + static inline void pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -536,7 +546,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud) PVOP_VCALL2(pv_mmu_ops.set_pud, pudp, val); } -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 static inline pud_t __pud(pudval_t val) { pudval_t ret; @@ -565,26 +575,54 @@ static inline pudval_t pud_val(pud_t pud) return ret; } -static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +static inline void pud_clear(pud_t *pudp) { - pgdval_t val = native_pgd_val(pgd); + set_pud(pudp, __pud(0)); +} - if (sizeof(pgdval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp, +static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + p4dval_t val = native_p4d_val(p4d); + + if (sizeof(p4dval_t) > sizeof(long)) + PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp, val, (u64)val >> 32); else - PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, + PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp, val); } +#if CONFIG_PGTABLE_LEVELS >= 5 + +static inline p4d_t __p4d(p4dval_t val) +{ + p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val); + + return (p4d_t) { ret }; +} + +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) +{ + pgdval_t val = native_pgd_val(pgd); + + PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val); +} + static inline void pgd_clear(pgd_t *pgdp) { set_pgd(pgdp, __pgd(0)); } -static inline void pud_clear(pud_t *pudp) +#endif /* CONFIG_PGTABLE_LEVELS == 5 */ + +static inline void p4d_clear(p4d_t *p4dp) { - set_pud(pudp, __pud(0)); + set_p4d(p4dp, __p4d(0)); } #endif /* CONFIG_PGTABLE_LEVELS == 4 */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b060f96..7465d6f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -238,9 +238,11 @@ struct pv_mmu_ops { void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn); void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn); void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_p4d)(struct mm_struct *mm, unsigned long pfn); void (*release_pte)(unsigned long pfn); void (*release_pmd)(unsigned long pfn); void (*release_pud)(unsigned long pfn); + void (*release_p4d)(unsigned long pfn); /* Pagetable manipulation functions */ void (*set_pte)(pte_t *ptep, pte_t pteval); @@ -279,12 +281,21 @@ struct pv_mmu_ops { struct paravirt_callee_save pmd_val; struct paravirt_callee_save make_pmd; -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 struct paravirt_callee_save pud_val; struct paravirt_callee_save make_pud; - void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); -#endif /* CONFIG_PGTABLE_LEVELS == 4 */ + void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval); + +#if CONFIG_PGTABLE_LEVELS >= 5 + struct paravirt_callee_save p4d_val; + struct paravirt_callee_save make_p4d; + + void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval); +#endif /* CONFIG_PGTABLE_LEVELS >= 5 */ + +#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ + #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ struct pv_lazy_ops lazy_mode; diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b6d4259..b2d0cd8 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -17,9 +17,11 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) { static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} +static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* @@ -121,10 +123,10 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); - set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))); + set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -150,6 +152,37 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, ___pud_free_tlb(tlb, pud); } +#if CONFIG_PGTABLE_LEVELS > 4 +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_KERNEL_ACCOUNT; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + return (p4d_t *)get_zeroed_page(gfp); +} + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + free_page((unsigned long)p4d); +} + +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); +} + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index 3925764..373ab1d 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -7,6 +7,7 @@ typedef unsigned long pteval_t; typedef unsigned long pmdval_t; typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; typedef unsigned long pgdval_t; typedef unsigned long pgprotval_t; diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 72277b1..c8821ba 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd) *(tmp + 1) = 0; } -#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \ - defined(CONFIG_PARAVIRT)) static inline void native_pud_clear(pud_t *pudp) { } -#endif static inline void pud_clear(pud_t *pudp) { @@ -215,4 +212,51 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } }) +#define gup_get_pte gup_get_pte +/* + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atomically, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a PTE will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' iff pte_high + * sees 'h'. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have gotten rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. Because get_user_pages_fast() only operates on present ptes + * we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; + + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index bcc8962..b8a4341 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -7,6 +7,7 @@ typedef u64 pteval_t; typedef u64 pmdval_t; typedef u64 pudval_t; +typedef u64 p4dval_t; typedef u64 pgdval_t; typedef u64 pgprotval_t; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index eef5fbc..942482a 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -51,16 +51,24 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) -#ifndef __PAGETABLE_PUD_FOLDED +#ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) native_pgd_clear(pgd) #endif +#ifndef set_p4d +# define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +#define p4d_clear(p4d) native_p4d_clear(p4d) +#endif + #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif -#ifndef __PAGETABLE_PMD_FOLDED +#ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif @@ -72,6 +80,11 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) +#ifndef __PAGETABLE_P4D_FOLDED +#define p4d_val(x) native_p4d_val(x) +#define __p4d(x) native_make_p4d(x) +#endif + #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) @@ -177,6 +190,17 @@ static inline unsigned long pud_pfn(pud_t pud) return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; } +static inline unsigned long p4d_pfn(p4d_t p4d) +{ + return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; +} + +static inline int p4d_large(p4d_t p4d) +{ + /* No 512 GiB pages yet */ + return 0; +} + #define pte_page(pte) pfn_to_page(pte_pfn(pte)) static inline int pmd_large(pmd_t pte) @@ -220,6 +244,11 @@ static inline int pud_devmap(pud_t pud) return 0; } #endif + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -536,6 +565,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) +#define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) @@ -585,6 +615,7 @@ pte_t *populate_extra_pte(unsigned long vaddr); #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> +#include <asm/fixmap.h> static inline int pte_none(pte_t pte) { @@ -768,7 +799,52 @@ static inline int pud_large(pud_t pud) } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + #if CONFIG_PGTABLE_LEVELS > 3 +static inline int p4d_none(p4d_t p4d) +{ + return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + return p4d_flags(p4d) & _PAGE_PRESENT; +} + +static inline unsigned long p4d_page_vaddr(p4d_t p4d) +{ + return (unsigned long)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); +} + +/* + * Currently stuck as a macro due to indirect forward reference to + * linux/mmzone.h's __section_mem_map_addr() definition: + */ +#define p4d_page(p4d) \ + pfn_to_page((p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT) + +/* Find an entry in the third-level page table.. */ +static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); +} + +static inline int p4d_bad(p4d_t p4d) +{ + return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; +} +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ + +static inline unsigned long p4d_index(unsigned long address) +{ + return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); +} + +#if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { return pgd_flags(pgd) & _PAGE_PRESENT; @@ -786,14 +862,9 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd) #define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT) /* to find an entry in a page-table-directory. */ -static inline unsigned long pud_index(unsigned long address) -{ - return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); -} - -static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { - return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address); + return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) @@ -811,7 +882,7 @@ static inline int pgd_none(pgd_t pgd) */ return !native_pgd_val(pgd); } -#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ @@ -1119,6 +1190,54 @@ static inline u16 pte_flags_pkey(unsigned long pte_flags) #endif } +static inline bool __pkru_allows_pkey(u16 pkey, bool write) +{ + u32 pkru = read_pkru(); + + if (!__pkru_allows_read(pkru, pkey)) + return false; + if (write && !__pkru_allows_write(pkru, pkey)) + return false; + + return true; +} + +/* + * 'pteval' can come from a PTE, PMD or PUD. We only check + * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the + * same value on all 3 types. + */ +static inline bool __pte_access_permitted(unsigned long pteval, bool write) +{ + unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; + + if (write) + need_pte_bits |= _PAGE_RW; + + if ((pteval & need_pte_bits) != need_pte_bits) + return 0; + + return __pkru_allows_pkey(pte_flags_pkey(pteval), write); +} + +#define pte_access_permitted pte_access_permitted +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + return __pte_access_permitted(pte_val(pte), write); +} + +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + return __pte_access_permitted(pmd_val(pmd), write); +} + +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return __pte_access_permitted(pud_val(pud), write); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index fbc7336..bfab5567 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -14,7 +14,6 @@ */ #ifndef __ASSEMBLY__ #include <asm/processor.h> -#include <asm/fixmap.h> #include <linux/threads.h> #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 73c7ccc..12ea312 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -35,15 +35,22 @@ extern void paging_init(void); #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) + +#if CONFIG_PGTABLE_LEVELS >= 5 +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), p4d_val(e)) +#endif + #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; +void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); - static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -121,6 +128,20 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp) #endif } +static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + *p4dp = p4d; +} + +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) { *pgdp = pgd; @@ -206,6 +227,20 @@ extern void cleanup_highmap(void); extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); -#endif /* !__ASSEMBLY__ */ +#define gup_fast_permitted gup_fast_permitted +static inline bool gup_fast_permitted(unsigned long start, int nr_pages, + int write) +{ + unsigned long len, end; + + len = (unsigned long)nr_pages << PAGE_SHIFT; + end = start + len; + if (end < start) + return false; + if (end >> __VIRTUAL_MASK_SHIFT) + return false; + return true; +} +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 3a26420..06470da 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -13,6 +13,7 @@ typedef unsigned long pteval_t; typedef unsigned long pmdval_t; typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; typedef unsigned long pgdval_t; typedef unsigned long pgprotval_t; @@ -22,12 +23,32 @@ typedef struct { pteval_t pte; } pte_t; #define SHARED_KERNEL_PMD 0 +#ifdef CONFIG_X86_5LEVEL + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT 48 +#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)) + +#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 +#endif /* CONFIG_X86_5LEVEL */ + /* * 3rd level page */ @@ -55,9 +76,15 @@ typedef struct { pteval_t pte; } pte_t; /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ #define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#ifdef CONFIG_X86_5LEVEL +#define VMALLOC_SIZE_TB _AC(16384, UL) +#define __VMALLOC_BASE _AC(0xff92000000000000, UL) +#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +#else #define VMALLOC_SIZE_TB _AC(32, UL) #define __VMALLOC_BASE _AC(0xffffc90000000000, UL) #define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +#endif #ifdef CONFIG_RANDOMIZE_MEMORY #define VMALLOC_START vmalloc_base #define VMEMMAP_START vmemmap_base @@ -67,10 +94,11 @@ typedef struct { pteval_t pte; } pte_t; #endif /* CONFIG_RANDOMIZE_MEMORY */ #define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) -#define MODULES_END _AC(0xffffffffff000000, UL) +/* The module sections ends with the start of the fixmap */ +#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) #define MODULES_LEN (MODULES_END - MODULES_VADDR) #define ESPFIX_PGD_ENTRY _AC(-2, UL) -#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) #define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) #define EFI_VA_END (-68 * (_AC(1, UL) << 30)) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 8b4de22..bf9638e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -272,6 +272,27 @@ static inline pgdval_t pgd_flags(pgd_t pgd) return native_pgd_val(pgd) & PTE_FLAGS_MASK; } +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; + +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { val }; +} + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return p4d.p4d; +} +#else +#include <asm-generic/pgtable-nop4d.h> + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return native_pgd_val(p4d.pgd); +} +#endif + #if CONFIG_PGTABLE_LEVELS > 3 typedef struct { pudval_t pud; } pud_t; @@ -289,7 +310,7 @@ static inline pudval_t native_pud_val(pud_t pud) static inline pudval_t native_pud_val(pud_t pud) { - return native_pgd_val(pud.pgd); + return native_pgd_val(pud.p4d.pgd); } #endif @@ -310,10 +331,26 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) static inline pmdval_t native_pmd_val(pmd_t pmd) { - return native_pgd_val(pmd.pud.pgd); + return native_pgd_val(pmd.pud.p4d.pgd); } #endif +static inline p4dval_t p4d_pfn_mask(p4d_t p4d) +{ + /* No 512 GiB huge pages yet */ + return PTE_PFN_MASK; +} + +static inline p4dval_t p4d_flags_mask(p4d_t p4d) +{ + return ~p4d_pfn_mask(p4d); +} + +static inline p4dval_t p4d_flags(p4d_t p4d) +{ + return native_p4d_val(p4d) & p4d_flags_mask(p4d); +} + static inline pudval_t pud_pfn_mask(pud_t pud) { if (native_pud_val(pud) & _PAGE_PSE) @@ -457,6 +494,7 @@ enum pg_level { PG_LEVEL_4K, PG_LEVEL_2M, PG_LEVEL_1G, + PG_LEVEL_512G, PG_LEVEL_NUM }; diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 34684ad..b3b09b9 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { + /* + * "Allocated" pkeys are those that have been returned + * from pkey_alloc(). pkey 0 is special, and never + * returned from pkey_alloc(). + */ + if (pkey <= 0) + return false; + if (pkey >= arch_max_pkey()) + return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } @@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm) static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { - /* - * pkey 0 is special, always allocated and can never - * be freed. - */ - if (!pkey) - return -EINVAL; if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f385eca..3cada99 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -80,7 +80,7 @@ extern u16 __read_mostly tlb_lld_1g[NR_INFO]; /* * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head.S, so think twice + * Members of this structure are referenced in head_32.S, so think twice * before touching them. [mj] */ @@ -89,14 +89,7 @@ struct cpuinfo_x86 { __u8 x86_vendor; /* CPU vendor */ __u8 x86_model; __u8 x86_mask; -#ifdef CONFIG_X86_32 - char wp_works_ok; /* It doesn't on 386's */ - - /* Problems on some 486Dx4's and old 386's: */ - char rfu; - char pad0; - char pad1; -#else +#ifdef CONFIG_X86_64 /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; #endif @@ -716,6 +709,8 @@ extern struct desc_ptr early_gdt_descr; extern void cpu_set_gdt(int); extern void switch_to_new_gdt(int); +extern void load_direct_gdt(int); +extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); @@ -797,6 +792,7 @@ static inline void spin_lock_prefetch(const void *x) /* * User space process size: 3GB (default). */ +#define IA32_PAGE_OFFSET PAGE_OFFSET #define TASK_SIZE PAGE_OFFSET #define TASK_SIZE_MAX TASK_SIZE #define STACK_TOP TASK_SIZE @@ -873,7 +869,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) +#define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) +#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE) #define KSTK_EIP(task) (task_pt_regs(task)->ip) @@ -884,6 +881,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); +DECLARE_PER_CPU(u64, msr_misc_features_shadow); + /* Register/unregister a process' MPX related resource */ #define MPX_ENABLE_MANAGEMENT() mpx_enable_management() #define MPX_DISABLE_MANAGEMENT() mpx_disable_management() diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 9b9b30b1..8d3964f 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -9,6 +9,7 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif #ifdef CONFIG_X86_32 @@ -30,6 +31,7 @@ void x86_report_nx(void); extern int reboot_force; -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr); +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h new file mode 100644 index 0000000..d7da272 --- /dev/null +++ b/arch/x86/include/asm/purgatory.h @@ -0,0 +1,20 @@ +#ifndef _ASM_X86_PURGATORY_H +#define _ASM_X86_PURGATORY_H + +#ifndef __ASSEMBLY__ +#include <linux/purgatory.h> + +extern void purgatory(void); +/* + * These forward declarations serve two purposes: + * + * 1) Make sparse happy when checking arch/purgatory + * 2) Document that these are required to be global so the symbol + * lookup in kexec works + */ +extern unsigned long purgatory_backup_dest; +extern unsigned long purgatory_backup_src; +extern unsigned long purgatory_backup_sz; +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_PURGATORY_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index fac9a5c..d91ba04 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -53,6 +53,12 @@ # 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 */ @@ -98,7 +104,7 @@ #define REQUIRED_MASK13 0 #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 -#define REQUIRED_MASK16 0 +#define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 #define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 4517d6b..1f5bee2c 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -26,8 +26,13 @@ # endif #else /* CONFIG_X86_32 */ # define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */ -# define MAX_PHYSADDR_BITS 44 -# define MAX_PHYSMEM_BITS 46 +# 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 #endif #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 58505f0..dcbd9bc 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -87,7 +87,7 @@ static inline void setup_stack_canary_segment(int cpu) { #ifdef CONFIG_X86_32 unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu); - struct desc_struct *gdt_table = get_cpu_gdt_table(cpu); + struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu); struct desc_struct desc; desc = gdt_table[GDT_ENTRY_STACK_CANARY]; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ad6f5eb0..9fc44b9 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -87,6 +87,7 @@ struct thread_info { #define TIF_SECCOMP 8 /* secure computing */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ +#define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ @@ -110,6 +111,7 @@ struct thread_info { #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) +#define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_NOHZ (1 << TIF_NOHZ) @@ -138,7 +140,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) @@ -239,6 +241,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); +extern void arch_setup_new_exec(void); +#define arch_setup_new_exec arch_setup_new_exec #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_THREAD_INFO_H */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a04eabd..27e9f9d 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void); extern int no_timer_check; +extern bool using_native_sched_clock(void); + /* * We use the full linear equation: f(x) = a + b*x, in order to allow * a continuous function in the face of dynamic freq changes. diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6fa8594..75d002b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask) } } +static inline void cr4_toggle_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + cr4 ^= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Read the CR4 shadow. */ static inline unsigned long cr4_read_shadow(void) { @@ -188,7 +198,7 @@ static inline void __native_flush_tlb_single(unsigned long addr) static inline void __flush_tlb_all(void) { - if (static_cpu_has(X86_FEATURE_PGE)) + if (boot_cpu_has(X86_FEATURE_PGE)) __flush_tlb_global(); else __flush_tlb(); diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 72e8300..9cffb44 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr) if (paddr < uv_hub_info->lowmem_remap_top) paddr |= uv_hub_info->lowmem_remap_base; - paddr |= uv_hub_info->gnode_upper; - if (m_val) + + if (m_val) { + paddr |= uv_hub_info->gnode_upper; paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | ((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift); - else + } else { paddr |= uv_soc_phys_ram_to_nasid(paddr) << uv_hub_info->gpa_shift; + } return paddr; } diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 64c5e74..8a5a02b 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -280,13 +280,17 @@ static inline pte_t __pte_ma(pteval_t x) #define pmd_val_ma(v) ((v).pmd) #ifdef __PAGETABLE_PUD_FOLDED -#define pud_val_ma(v) ((v).pgd.pgd) +#define pud_val_ma(v) ((v).p4d.pgd.pgd) #else #define pud_val_ma(v) ((v).pud) #endif #define __pmd_ma(x) ((pmd_t) { (x) } ) -#define pgd_val_ma(x) ((x).pgd) +#ifdef __PAGETABLE_P4D_FOLDED +#define p4d_val_ma(x) ((x).pgd.pgd) +#else +#define p4d_val_ma(x) ((x).p4d) +#endif void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid); diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 41af92e..ddef37b 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -57,7 +57,7 @@ struct setup_header { __u32 header; __u16 version; __u32 realmode_swtch; - __u16 start_sys; + __u16 start_sys_seg; __u16 kernel_version; __u8 type_of_loader; __u8 loadflags; diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 835aa51..c457655 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -1,10 +1,13 @@ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H -#define ARCH_SET_GS 0x1001 -#define ARCH_SET_FS 0x1002 -#define ARCH_GET_FS 0x1003 -#define ARCH_GET_GS 0x1004 +#define ARCH_SET_GS 0x1001 +#define ARCH_SET_FS 0x1002 +#define ARCH_GET_FS 0x1003 +#define ARCH_GET_GS 0x1004 + +#define ARCH_GET_CPUID 0x1011 +#define ARCH_SET_CPUID 0x1012 #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a468f0f..294eab0 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -180,10 +180,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) return -EINVAL; } + if (!enabled) { + ++disabled_cpus; + return -EINVAL; + } + if (boot_cpu_physical_apicid != -1U) ver = boot_cpu_apic_version; - cpu = __generic_processor_info(id, ver, enabled); + cpu = generic_processor_info(id, ver); if (cpu >= 0) early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; @@ -711,7 +716,7 @@ static void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 4858733..ed01481 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -101,7 +101,7 @@ int x86_acpi_suspend_lowlevel(void) #ifdef CONFIG_SMP initial_stack = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = - (unsigned long)get_cpu_gdt_table(smp_processor_id()); + (unsigned long)get_cpu_gdt_rw(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); #endif initial_code = (unsigned long)wakeup_long64; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4eca103..0b657bf 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } #endif /* !CONFIG_X86_X2APIC */ -static int __init try_to_enable_IR(void) -{ -#ifdef CONFIG_X86_IO_APIC - if (!x2apic_enabled() && skip_ioapic_setup) { - pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); - return -1; - } -#endif - return irq_remapping_enable(); -} - void __init enable_IR_x2apic(void) { unsigned long flags; int ret, ir_stat; - if (skip_ioapic_setup) + if (skip_ioapic_setup) { + pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n"); return; + } ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) @@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void) /* If irq_remapping_prepare() succeeded, try to enable it */ if (ir_stat >= 0) - ir_stat = try_to_enable_IR(); + ir_stat = irq_remapping_enable(); /* ir_stat contains the remap mode or an error code */ try_to_enable_x2apic(ir_stat); @@ -2062,17 +2053,17 @@ static int allocate_logical_cpuid(int apicid) /* Allocate a new cpuid. */ if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "Only %d processors supported." + WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. " "Processor %d/0x%x and the rest are ignored.\n", - nr_cpu_ids - 1, nr_logical_cpuids, apicid); - return -1; + nr_cpu_ids, nr_logical_cpuids, apicid); + return -EINVAL; } cpuid_to_apicid[nr_logical_cpuids] = apicid; return nr_logical_cpuids++; } -int __generic_processor_info(int apicid, int version, bool enabled) +int generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2130,11 +2121,9 @@ int __generic_processor_info(int apicid, int version, bool enabled) if (num_processors >= nr_cpu_ids) { int thiscpu = max + disabled_cpus; - if (enabled) { - pr_warning("APIC: NR_CPUS/possible_cpus limit of %i " - "reached. Processor %d/0x%x ignored.\n", - max, thiscpu, apicid); - } + pr_warning("APIC: NR_CPUS/possible_cpus limit of %i " + "reached. Processor %d/0x%x ignored.\n", + max, thiscpu, apicid); disabled_cpus++; return -EINVAL; @@ -2186,23 +2175,13 @@ int __generic_processor_info(int apicid, int version, bool enabled) apic->x86_32_early_logical_apicid(cpu); #endif set_cpu_possible(cpu, true); - - if (enabled) { - num_processors++; - physid_set(apicid, phys_cpu_present_map); - set_cpu_present(cpu, true); - } else { - disabled_cpus++; - } + physid_set(apicid, phys_cpu_present_map); + set_cpu_present(cpu, true); + num_processors++; return cpu; } -int generic_processor_info(int apicid, int version) -{ - return __generic_processor_info(apicid, version, true); -} - int hard_smp_processor_id(void) { return read_apic_id(); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7f179f1..b487b3a 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1106,7 +1106,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi) node_id.v = uv_read_local_mmr(UVH_NODE_ID); uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val); hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1; - hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val; + if (mn.m_val) + hi->gnode_upper = (u64)hi->gnode_extra << mn.m_val; if (uv_gp_table) { hi->global_mmr_base = uv_gp_table->mmr_base; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5a41454..446b0d3 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -609,7 +609,7 @@ static long __apm_bios_call(void *_call) cpu = get_cpu(); BUG_ON(cpu != 0); - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; @@ -685,7 +685,7 @@ static long __apm_bios_call_simple(void *_call) cpu = get_cpu(); BUG_ON(cpu != 0); - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; @@ -2352,7 +2352,7 @@ static int __init apm_init(void) * Note we only set APM segments on CPU zero, since we pin the APM * code to that CPU. */ - gdt = get_cpu_gdt_table(0); + gdt = get_cpu_gdt_rw(0); set_desc_base(&gdt[APM_CS >> 3], (unsigned long)__va((unsigned long)apm_info.bios.cseg << 4)); set_desc_base(&gdt[APM_CS_16 >> 3], diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 35a5d5d..c36140d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 106bd33..44207b7 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif - - clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b11b38c..8ee3211 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif - clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -449,19 +448,60 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } +/* Setup the fixmap mapping only once per-processor */ +static inline void setup_fixmap_gdt(int cpu) +{ +#ifdef CONFIG_X86_64 + /* On 64-bit systems, we use a read-only fixmap GDT. */ + pgprot_t prot = PAGE_KERNEL_RO; +#else + /* + * On native 32-bit systems, the GDT cannot be read-only because + * our double fault handler uses a task gate, and entering through + * a task gate needs to change an available TSS to busy. If the GDT + * is read-only, that will triple fault. + * + * On Xen PV, the GDT must be read-only because the hypervisor requires + * it. + */ + pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? + PAGE_KERNEL_RO : PAGE_KERNEL; +#endif + + __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); +} + +/* Load the original GDT from the per-cpu structure */ +void load_direct_gdt(int cpu) +{ + struct desc_ptr gdt_descr; + + gdt_descr.address = (long)get_cpu_gdt_rw(cpu); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); +} +EXPORT_SYMBOL_GPL(load_direct_gdt); + +/* Load a fixmap remapping of the per-cpu GDT */ +void load_fixmap_gdt(int cpu) +{ + struct desc_ptr gdt_descr; + + gdt_descr.address = (long)get_cpu_gdt_ro(cpu); + gdt_descr.size = GDT_SIZE - 1; + load_gdt(&gdt_descr); +} +EXPORT_SYMBOL_GPL(load_fixmap_gdt); + /* * Current gdt points %fs at the "master" per-cpu area: after this, * it's on the real one. */ void switch_to_new_gdt(int cpu) { - struct desc_ptr gdt_descr; - - gdt_descr.address = (long)get_cpu_gdt_table(cpu); - gdt_descr.size = GDT_SIZE - 1; - load_gdt(&gdt_descr); + /* Load the original GDT */ + load_direct_gdt(cpu); /* Reload the per-cpu base */ - load_percpu_segment(cpu); } @@ -1077,8 +1117,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); - else - clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); @@ -1529,6 +1567,9 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); + + setup_fixmap_gdt(cpu); + load_fixmap_gdt(cpu); } #else @@ -1584,6 +1625,9 @@ void cpu_init(void) dbg_restore_debug_regs(); fpu__init_cpu(); + + setup_fixmap_gdt(cpu); + load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 0a3bc19..a70fd61 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } - clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fe0a615..dfa90a3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) return; } - if (ring3mwait_disabled) { - msr_clear_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + if (ring3mwait_disabled) return; - } - - msr_set_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + this_cpu_or(msr_misc_features_shadow, + 1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT); if (c == &boot_cpu_data) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; @@ -162,10 +158,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (check_tsc_unstable()) - clear_sched_clock_stable(); - } else { - clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -492,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c) init_intel_energy_perf(c); } +static void init_cpuid_fault(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) { + if (msr & MSR_PLATFORM_INFO_CPUID_FAULT) + set_cpu_cap(c, X86_FEATURE_CPUID_FAULT); + } +} + +static void init_intel_misc_features(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr)) + return; + + /* Clear all MISC features */ + this_cpu_write(msr_misc_features_shadow, 0); + + /* Check features and update capabilities and shadow control bits */ + init_cpuid_fault(c); + probe_xeon_phi_r3mwait(c); + + msr = this_cpu_read(msr_misc_features_shadow); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -606,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); - probe_xeon_phi_r3mwait(c); + init_intel_misc_features(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 0bbe0f3..9ac2a5c 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -28,7 +28,6 @@ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/slab.h> -#include <linux/cpu.h> #include <linux/task_work.h> #include <uapi/linux/magic.h> @@ -728,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { kernfs_unbreak_active_protection(kn); - kernfs_put(kn); + kernfs_put(rdtgrp->kn); kfree(rdtgrp); } else { kernfs_unbreak_active_protection(kn); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 524cc57..6e4a047 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -60,7 +60,7 @@ static const char * const th_names[] = { "load_store", "insn_fetch", "combined_unit", - "", + "decode_unit", "northbridge", "execution_unit", }; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 18ca99f..6df621a 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -31,14 +31,13 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "fpu\t\t: %s\n" "fpu_exception\t: %s\n" "cpuid level\t: %d\n" - "wp\t\t: %s\n", + "wp\t\t: yes\n", static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no", static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no", static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no", static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", - c->cpuid_level, - c->wp_works_ok ? "yes" : "no"); + c->cpuid_level); } #else static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 8457b49..d77d07a 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } - - clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 891f4da..22403a2 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -30,7 +30,6 @@ #include <asm/hypervisor.h> #include <asm/timer.h> #include <asm/apic.h> -#include <asm/timer.h> #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 04f89ca..8e598a1 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -50,11 +50,11 @@ #define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) /* There is address space for how many espfix pages? */ -#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) +#define ESPFIX_PAGE_SPACE (1UL << (P4D_SHIFT-PAGE_SHIFT-16)) #define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) #if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS -# error "Need more than one PGD for the ESPFIX hack" +# error "Need more virtual address space for the ESPFIX hack" #endif #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) @@ -121,11 +121,13 @@ static void init_espfix_random(void) void __init init_espfix_bsp(void) { - pgd_t *pgd_p; + pgd_t *pgd; + p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; - pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); + p4d_populate(&init_mm, p4d, espfix_pud_page); /* Randomize the locations */ init_espfix_random(); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8639bb2..cbd73eb 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -29,6 +29,12 @@ #include <asm/ftrace.h> #include <asm/nops.h> +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \ + !defined(CC_USING_FENTRY) && \ + !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) +# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE +#endif + #ifdef CONFIG_DYNAMIC_FTRACE int ftrace_arch_code_modify_prepare(void) @@ -535,7 +541,7 @@ static void run_sync(void) { int enable_irqs = irqs_disabled(); - /* We may be called with interrupts disbled (on bootup). */ + /* We may be called with interrupts disabled (on bootup). */ if (enable_irqs) local_irq_enable(); on_each_cpu(do_sync_core, NULL, 1); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index baa0e7b..43b7002 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -4,6 +4,7 @@ * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE */ +#define DISABLE_BRANCH_PROFILING #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dc6ba5b..89ff7af 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); - disable_irq(hdev->irq); + disable_hardirq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); } diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index bdb83e4..38b6458 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void) struct dentry *dbp, *version, *data; int error = -ENOMEM; - dbp = debugfs_create_dir("boot_params", NULL); + dbp = debugfs_create_dir("boot_params", arch_debugfs_dir); if (!dbp) return -ENOMEM; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index c6ee63f..d688826 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -67,7 +67,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(kprobe_opcode_t *instruction); +extern int can_boost(kprobe_opcode_t *instruction, void *addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6384eb7..993fa4f 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes); * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(kprobe_opcode_t *opcodes) +int can_boost(kprobe_opcode_t *opcodes, void *addr) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; - if (search_exception_tables((unsigned long)opcodes)) + if (search_exception_tables((unsigned long)addr)) return 0; /* Page fault may occur on this address. */ retry: @@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p) * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - if (can_boost(p->ainsn.insn)) + if (can_boost(p->ainsn.insn, p->addr)) p->ainsn.boostable = 0; else p->ainsn.boostable = -1; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 3d1bee9..3e7c6e5 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src) while (len < RELATIVEJUMP_SIZE) { ret = __copy_instruction(dest + len, src + len); - if (!ret || !can_boost(dest + len)) + if (!ret || !can_boost(dest + len, src + len)) return -EINVAL; len += ret; } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 469b23d..5f43cec 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -103,6 +103,7 @@ static void machine_kexec_page_table_set_one( pgd_t *pgd, pmd_t *pmd, pte_t *pte, unsigned long vaddr, unsigned long paddr) { + p4d_t *p4d; pud_t *pud; pgd += pgd_index(vaddr); @@ -110,7 +111,8 @@ static void machine_kexec_page_table_set_one( if (!(pgd_val(*pgd) & _PAGE_PRESENT)) set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT)); #endif - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); pmd = pmd_offset(pud, vaddr); if (!(pmd_val(*pmd) & _PAGE_PRESENT)) set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 307b1f4..085c3b3 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -36,6 +36,7 @@ static struct kexec_file_ops *kexec_file_loaders[] = { static void free_transition_pgtable(struct kimage *image) { + free_page((unsigned long)image->arch.p4d); free_page((unsigned long)image->arch.pud); free_page((unsigned long)image->arch.pmd); free_page((unsigned long)image->arch.pte); @@ -43,6 +44,7 @@ static void free_transition_pgtable(struct kimage *image) static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -53,13 +55,21 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { + p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); + if (!p4d) + goto err; + image->arch.p4d = p4d; + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + p4d = p4d_offset(pgd, vaddr); + if (!p4d_present(*p4d)) { pud = (pud_t *)get_zeroed_page(GFP_KERNEL); if (!pud) goto err; image->arch.pud = pud; - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); } - pud = pud_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); if (!pud_present(*pud)) { pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); if (!pmd) @@ -194,19 +204,22 @@ static int arch_update_purgatory(struct kimage *image) /* Setup copying of backup region */ if (image->type == KEXEC_TYPE_CRASH) { - ret = kexec_purgatory_get_set_symbol(image, "backup_dest", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_dest", &image->arch.backup_load_addr, sizeof(image->arch.backup_load_addr), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_src", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_src", &image->arch.backup_src_start, sizeof(image->arch.backup_src_start), 0); if (ret) return ret; - ret = kexec_purgatory_get_set_symbol(image, "backup_sz", + ret = kexec_purgatory_get_set_symbol(image, + "purgatory_backup_sz", &image->arch.backup_src_sz, sizeof(image->arch.backup_src_sz), 0); if (ret) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index f088ea4..a723ae94 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) spin_lock_irqsave(&desc->lock, flags); /* - * most handlers of type NMI_UNKNOWN never return because - * they just assume the NMI is theirs. Just a sanity check - * to manage expectations + * Indicate if there are multiple registrations on the + * internal NMI handler call chains (SERR and IO_CHECK). */ - WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head)); WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head)); WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head)); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 4797e87..3586996 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -405,9 +405,11 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .alloc_pte = paravirt_nop, .alloc_pmd = paravirt_nop, .alloc_pud = paravirt_nop, + .alloc_p4d = paravirt_nop, .release_pte = paravirt_nop, .release_pmd = paravirt_nop, .release_pud = paravirt_nop, + .release_p4d = paravirt_nop, .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, @@ -430,12 +432,19 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 .pud_val = PTE_IDENT, .make_pud = PTE_IDENT, + .set_p4d = native_set_p4d, + +#if CONFIG_PGTABLE_LEVELS >= 5 + .p4d_val = PTE_IDENT, + .make_p4d = PTE_IDENT, + .set_pgd = native_set_pgd, -#endif +#endif /* CONFIG_PGTABLE_LEVELS >= 5 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 4 */ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ .pte_val = PTE_IDENT, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f675915..0bb8842 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/vm86.h> #include <asm/switch_to.h> #include <asm/desc.h> +#include <asm/prctl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -124,11 +125,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); } -static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -137,15 +133,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -154,7 +145,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -182,54 +173,129 @@ int set_tsc_mode(unsigned int val) return 0; } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; +DEFINE_PER_CPU(u64, msr_misc_features_shadow); - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); +static void set_cpuid_faulting(bool on) +{ + u64 msrval; - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; + msrval = this_cpu_read(msr_misc_features_shadow); + msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; + msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); + this_cpu_write(msr_misc_features_shadow, msrval); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval); +} - update_debugctlmsr(debugctl); +static void disable_cpuid(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(true); } + preempt_enable(); +} - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); +static void enable_cpuid(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(false); } + preempt_enable(); +} + +static int get_cpuid_mode(void) +{ + return !test_thread_flag(TIF_NOCPUID); +} + +static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +{ + if (!static_cpu_has(X86_FEATURE_CPUID_FAULT)) + return -ENODEV; + + if (cpuid_enabled) + enable_cpuid(); + else + disable_cpuid(); + + return 0; +} + +/* + * Called immediately after a successful exec. + */ +void arch_setup_new_exec(void) +{ + /* If cpuid was previously disabled for this task, re-enable it. */ + if (test_thread_flag(TIF_NOCPUID)) + enable_cpuid(); +} - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) +{ + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. * Normally this is 128 bytes or less: */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); - /* * Make sure that the TSS limit is correct for the CPU * to notice the IO bitmap. */ refresh_tss_limit(); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + } else if (tifp & _TIF_IO_BITMAP) { /* * Clear any possible leftover bits: */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + unsigned long tifp, tifn; + + prev = &prev_p->thread; + next = &next_p->thread; + + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_NOCPUID) + set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); } /* @@ -550,3 +616,16 @@ out: put_task_stack(p); return ret; } + +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled) +{ + switch (option) { + case ARCH_GET_CPUID: + return get_cpuid_mode(); + case ARCH_SET_CPUID: + return set_cpuid_mode(task, cpuid_enabled); + } + + return -EINVAL; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4c818f8..ff40e74 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -56,6 +57,7 @@ #include <asm/switch_to.h> #include <asm/vm86.h> #include <asm/intel_rdt.h> +#include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) { @@ -304,3 +306,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); +} diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d6b784a..825a1e4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -52,6 +53,11 @@ #include <asm/xen/hypervisor.h> #include <asm/vdso.h> #include <asm/intel_rdt.h> +#include <asm/unistd.h> +#ifdef CONFIG_IA32_EMULATION +/* Not included via unistd.h */ +#include <asm/unistd_32_ia32.h> +#endif __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); @@ -204,7 +210,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, tls); + err = do_arch_prctl_64(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -493,6 +499,8 @@ void set_personality_64bit(void) clear_thread_flag(TIF_IA32); clear_thread_flag(TIF_ADDR32); clear_thread_flag(TIF_X32); + /* Pretend that this comes from a 64bit execve */ + task_pt_regs(current)->orig_ax = __NR_execve; /* Ensure the corresponding mm is not marked. */ if (current->mm) @@ -505,32 +513,50 @@ void set_personality_64bit(void) current->personality &= ~READ_IMPLIES_EXEC; } -void set_personality_ia32(bool x32) +static void __set_personality_x32(void) { - /* inherit personality from parent */ +#ifdef CONFIG_X86_X32 + clear_thread_flag(TIF_IA32); + set_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_X32; + current->personality &= ~READ_IMPLIES_EXEC; + /* + * in_compat_syscall() uses the presence of the x32 syscall bit + * flag to determine compat status. The x86 mmap() code relies on + * the syscall bitness so set x32 syscall bit right here to make + * in_compat_syscall() work during exec(). + * + * Pretend to come from a x32 execve. + */ + task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT; + current->thread.status &= ~TS_COMPAT; +#endif +} + +static void __set_personality_ia32(void) +{ +#ifdef CONFIG_IA32_EMULATION + set_thread_flag(TIF_IA32); + clear_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_IA32; + current->personality |= force_personality32; + /* Prepare the first "return" to user space */ + task_pt_regs(current)->orig_ax = __NR_ia32_execve; + current->thread.status |= TS_COMPAT; +#endif +} +void set_personality_ia32(bool x32) +{ /* Make sure to be in 32bit mode */ set_thread_flag(TIF_ADDR32); - /* Mark the associated mm as containing 32-bit tasks. */ - if (x32) { - clear_thread_flag(TIF_IA32); - set_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_X32; - current->personality &= ~READ_IMPLIES_EXEC; - /* in_compat_syscall() uses the presence of the x32 - syscall bit flag to determine compat status */ - current->thread.status &= ~TS_COMPAT; - } else { - set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_IA32; - current->personality |= force_personality32; - /* Prepare the first "return" to user space */ - current->thread.status |= TS_COMPAT; - } + if (x32) + __set_personality_x32(); + else + __set_personality_ia32(); } EXPORT_SYMBOL_GPL(set_personality_ia32); @@ -547,70 +573,72 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) } #endif -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; int doit = task == current; int cpu; - switch (code) { + switch (option) { case ARCH_SET_GS: - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.gsindex = 0; - task->thread.gsbase = addr; + task->thread.gsbase = arg2; if (doit) { load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2); } put_cpu(); break; case ARCH_SET_FS: /* Not strictly needed for fs, but do it for symmetry with gs */ - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.fsindex = 0; - task->thread.fsbase = addr; + task->thread.fsbase = arg2; if (doit) { /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, arg2); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; + if (doit) rdmsrl(MSR_FS_BASE, base); else base = task->thread.fsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { unsigned long base; + if (doit) rdmsrl(MSR_KERNEL_GS_BASE, base); else base = task->thread.gsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } #ifdef CONFIG_CHECKPOINT_RESTORE # ifdef CONFIG_X86_X32_ABI case ARCH_MAP_VDSO_X32: - return prctl_map_vdso(&vdso_image_x32, addr); + return prctl_map_vdso(&vdso_image_x32, arg2); # endif # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION case ARCH_MAP_VDSO_32: - return prctl_map_vdso(&vdso_image_32, addr); + return prctl_map_vdso(&vdso_image_32, arg2); # endif case ARCH_MAP_VDSO_64: - return prctl_map_vdso(&vdso_image_64, addr); + return prctl_map_vdso(&vdso_image_64, arg2); #endif default: @@ -621,10 +649,23 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl(current, code, addr); + long ret; + + ret = do_arch_prctl_64(current, option, arg2); + if (ret == -EINVAL) + ret = do_arch_prctl_common(current, option, arg2); + + return ret; +} + +#ifdef CONFIG_IA32_EMULATION +COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); } +#endif unsigned long KSTK_ESP(struct task_struct *task) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2364b23..f37d181 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -396,12 +396,12 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the segment base, use do_arch_prctl + * When changing the segment base, use do_arch_prctl_64 * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ if (child->thread.fsbase != value) - return do_arch_prctl(child, ARCH_SET_FS, value); + return do_arch_prctl_64(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +410,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return do_arch_prctl(child, ARCH_SET_GS, value); + return do_arch_prctl_64(child, ARCH_SET_GS, value); return 0; #endif } @@ -869,7 +869,7 @@ long arch_ptrace(struct task_struct *child, long request, Works just like arch_prctl, except that the arguments are reversed. */ case PTRACE_ARCH_PRCTL: - ret = do_arch_prctl(child, data, addr); + ret = do_arch_prctl_64(child, data, addr); break; #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e244c19..067f981 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, + { /* Handle problems with rebooting on ASUS EeeBook X205TA */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"), + }, + }, + { /* Handle problems with rebooting on ASUS EeeBook X205TAW */ + .callback = set_acpi_reboot, + .ident = "ASUS EeeBook X205TAW", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"), + }, + }, /* Certec */ { /* Handle problems with rebooting on Certec BPC600 */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cab13f7..21a3db1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -173,14 +173,11 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data = { - .wp_works_ok = -1, -}; +/* cpu data as detected by the assembly code in head_32.S */ +struct cpuinfo_x86 new_cpu_data; + /* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data __read_mostly = { - .wp_works_ok = -1, -}; +struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); unsigned int def_to_bigsmp; @@ -1202,21 +1199,6 @@ 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. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif - tboot_probe(); map_vsyscall(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 9820d6d..bb1e8cc 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -160,7 +160,7 @@ static inline void setup_percpu_segment(int cpu) pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, 0x2 | DESCTYPE_S, 0x8); gdt.s = 1; - write_gdt_entry(get_cpu_gdt_table(cpu), + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); #endif } @@ -288,4 +288,25 @@ 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. We want to make sure that + * all kernel mappings, including percpu mappings, are available + * in the smpboot asm. We can't reliably pick up percpu + * mappings using vmalloc_fault(), because exception dispatch + * needs percpu data. + */ + 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 } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bd1f1ad..f04479a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -983,7 +983,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); - early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); + early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; initial_stack = idle->thread.sp; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 50215a4..207b8f2 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -17,6 +17,8 @@ #include <linux/uaccess.h> #include <linux/elf.h> +#include <asm/elf.h> +#include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> @@ -101,7 +103,7 @@ out: static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { + if (!in_compat_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit it to that. This means we need to move the @@ -114,10 +116,11 @@ static void find_start_end(unsigned long flags, unsigned long *begin, if (current->flags & PF_RANDOMIZE) { *begin = randomize_page(*begin, 0x02000000); } - } else { - *begin = current->mm->mmap_legacy_base; - *end = TASK_SIZE; + return; } + + *begin = get_mmap_base(1); + *end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit(); } unsigned long @@ -176,7 +179,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legacy mmap base */ - if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) + if (!in_compat_syscall() && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ @@ -191,7 +194,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; + info.high_limit = get_mmap_base(0); info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index ccccd33..d4c8011 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -118,12 +118,16 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, pgprot_t prot) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pgd = pgd_offset(&tboot_mm, vaddr); - pud = pud_alloc(&tboot_mm, pgd, vaddr); + p4d = p4d_alloc(&tboot_mm, pgd, vaddr); + if (!p4d) + return -1; + pud = pud_alloc(&tboot_mm, p4d, vaddr); if (!pud) return -1; pmd = pmd_alloc(&tboot_mm, pud, vaddr); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 6c89344..dcd699b 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -92,10 +92,17 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info) || LDT_zero(info)) + if (LDT_empty(info) || LDT_zero(info)) { desc->a = desc->b = 0; - else + } else { fill_ldt(desc, info); + + /* + * Always set the accessed bit so that the CPU + * doesn't try to write to the (read-only) GDT. + */ + desc->type |= 1; + } ++info; ++desc; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 46bcda4..714dfba 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -327,9 +327,16 @@ unsigned long long sched_clock(void) { return paravirt_sched_clock(); } + +bool using_native_sched_clock(void) +{ + return pv_time_ops.sched_clock == native_sched_clock; +} #else unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); + +bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) @@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; + tsc_unstable = 1; - clear_sched_clock_stable(); + if (using_native_sched_clock()) + clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } @@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = { void mark_tsc_unstable(char *reason) { - if (!tsc_unstable) { - tsc_unstable = 1; + if (tsc_unstable) + return; + + tsc_unstable = 1; + if (using_native_sched_clock()) clear_sched_clock_stable(); - disable_sched_clock_irqtime(); - pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) - clocksource_mark_unstable(&clocksource_tsc); - else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to %s\n", reason); + /* Change only the rating, when not registered */ + if (clocksource_tsc.mult) { + clocksource_mark_unstable(&clocksource_tsc); + } else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; + clocksource_tsc.rating = 0; } } @@ -1322,6 +1333,8 @@ static int __init init_tsc_clocksource(void) * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { + if (boot_cpu_has(X86_FEATURE_ART)) + art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); return 0; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 478d15d..0833926 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs) return sizeof(*regs); } +#ifdef CONFIG_X86_32 +#define GCC_REALIGN_WORDS 3 +#else +#define GCC_REALIGN_WORDS 1 +#endif + static bool is_last_task_frame(struct unwind_state *state) { - unsigned long bp = (unsigned long)state->bp; - unsigned long regs = (unsigned long)task_pt_regs(state->task); + unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2; + unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS; /* * We have to check for the last task frame at two different locations * because gcc can occasionally decide to realign the stack pointer and - * change the offset of the stack frame by a word in the prologue of a - * function called by head/entry code. + * change the offset of the stack frame in the prologue of a function + * called by head/entry code. Examples: + * + * <start_secondary>: + * push %edi + * lea 0x8(%esp),%edi + * and $0xfffffff8,%esp + * pushl -0x4(%edi) + * push %ebp + * mov %esp,%ebp + * + * <x86_64_start_kernel>: + * lea 0x8(%rsp),%r10 + * and $0xfffffffffffffff0,%rsp + * pushq -0x8(%r10) + * push %rbp + * mov %rsp,%rbp + * + * Note that after aligning the stack, it pushes a duplicate copy of + * the return address before pushing the frame pointer. */ - return bp == regs - FRAME_HEADER_SIZE || - bp == regs - FRAME_HEADER_SIZE - sizeof(long); + return (state->bp == last_bp || + (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1))); } /* diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 23ee89c..62597c3 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -164,6 +164,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) struct vm_area_struct *vma; spinlock_t *ptl; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -173,7 +174,10 @@ static void mark_screen_rdonly(struct mm_struct *mm) pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; - pud = pud_offset(pgd, 0xA0000); + p4d = p4d_offset(pgd, 0xA0000); + if (p4d_none_or_clear_bad(p4d)) + goto out; + pud = pud_offset(p4d, 0xA0000); if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 73ea24d..047b17a 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm) { struct kvm_pic *vpic = kvm->arch.vpic; + if (!vpic) + return; + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 6e219e5..289270a 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + if (!ioapic) + return; + cancel_delayed_work_sync(&ioapic->eoi_inject); kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); kvm->arch.vioapic = NULL; diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index 37942e4..60168cd 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); } +void kvm_page_track_cleanup(struct kvm *kvm) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + cleanup_srcu_struct(&head->track_srcu); +} + void kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d1efe2c..5f48f62 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -741,7 +741,6 @@ static int svm_hardware_enable(void) struct svm_cpu_data *sd; uint64_t efer; - struct desc_ptr gdt_descr; struct desc_struct *gdt; int me = raw_smp_processor_id(); @@ -763,8 +762,7 @@ static int svm_hardware_enable(void) sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; - native_store_gdt(&gdt_descr); - gdt = (struct desc_struct *)gdt_descr.address; + gdt = get_current_gdt_rw(); sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); wrmsrl(MSR_EFER, efer | EFER_SVME); @@ -1379,6 +1377,9 @@ static void avic_vm_destroy(struct kvm *kvm) unsigned long flags; struct kvm_arch *vm_data = &kvm->arch; + if (!avic) + return; + avic_free_vm_id(vm_data->avic_vm_id); if (vm_data->avic_logical_id_table_page) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 283aa86..535cc06 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -935,7 +935,6 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); * when a CPU is brought down, and we need to VMCLEAR all VMCSs loaded on it. */ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); -static DEFINE_PER_CPU(struct desc_ptr, host_gdt); /* * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we @@ -1239,6 +1238,11 @@ static inline bool cpu_has_vmx_invvpid_global(void) return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; } +static inline bool cpu_has_vmx_invvpid(void) +{ + return vmx_capability.vpid & VMX_VPID_INVVPID_BIT; +} + static inline bool cpu_has_vmx_ept(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -2052,14 +2056,13 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ static unsigned long segment_base(u16 selector) { - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *table; unsigned long v; if (!(selector & ~SEGMENT_RPL_MASK)) return 0; - table = (struct desc_struct *)gdt->address; + table = get_current_gdt_ro(); if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); @@ -2164,7 +2167,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) #endif if (vmx->host_state.msr_host_bndcfgs) wrmsrl(MSR_IA32_BNDCFGS, vmx->host_state.msr_host_bndcfgs); - load_gdt(this_cpu_ptr(&host_gdt)); + load_fixmap_gdt(raw_smp_processor_id()); } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -2266,7 +2269,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } if (!already_loaded) { - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); + void *gdt = get_current_gdt_ro(); unsigned long sysenter_esp; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); @@ -2277,7 +2280,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) */ vmcs_writel(HOST_TR_BASE, (unsigned long)this_cpu_ptr(&cpu_tss)); - vmcs_writel(HOST_GDTR_BASE, gdt->address); + vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* * VM exits change the host TR limit to 0x67 after a VM @@ -2753,7 +2756,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_DESC | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING | @@ -2781,10 +2783,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * though it is treated as global context. The alternative is * not failing the single-context invvpid, and it is worse. */ - if (enable_vpid) + if (enable_vpid) { + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_ENABLE_VPID; vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | VMX_VPID_EXTENT_SUPPORTED_MASK; - else + } else vmx->nested.nested_vmx_vpid_caps = 0; if (enable_unrestricted_guest) @@ -3465,8 +3469,6 @@ static int hardware_enable(void) ept_sync_global(); } - native_store_gdt(this_cpu_ptr(&host_gdt)); - return 0; } @@ -4024,6 +4026,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu) __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); } +static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) +{ + if (enable_ept) + vmx_flush_tlb(vcpu); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -6517,8 +6525,10 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); - if (!cpu_has_vmx_vpid()) + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || + !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; + if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) @@ -7258,9 +7268,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 zero = 0; gpa_t vmptr; - struct vmcs12 *vmcs12; - struct page *page; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -7271,22 +7280,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); - page = nested_get_page(vcpu, vmptr); - if (page == NULL) { - /* - * For accurate processor emulation, VMCLEAR beyond available - * physical memory should do nothing at all. However, it is - * possible that a nested vmx bug, not a guest hypervisor bug, - * resulted in this case, so let's shut down before doing any - * more damage: - */ - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - return 1; - } - vmcs12 = kmap(page); - vmcs12->launch_state = 0; - kunmap(page); - nested_release_page(page); + kvm_vcpu_write_guest(vcpu, + vmptr + offsetof(struct vmcs12, launch_state), + &zero, sizeof(zero)); nested_free_vmcs02(vmx, vmptr); @@ -8515,7 +8511,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", + exit_reason); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -8561,6 +8558,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } else { sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmx_flush_tlb_ept_only(vcpu); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -8586,8 +8584,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) */ if (!is_guest_mode(vcpu) || !nested_cpu_has2(get_vmcs12(&vmx->vcpu), - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); + vmx_flush_tlb_ept_only(vcpu); + } } static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) @@ -9694,10 +9694,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, return false; page = nested_get_page(vcpu, vmcs12->msr_bitmap); - if (!page) { - WARN_ON(1); + if (!page) return false; - } msr_bitmap_l1 = (unsigned long *)kmap(page); memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9990,7 +9988,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; - bool nested_ept_enabled = false; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); @@ -10137,8 +10134,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_intr_status); } - nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0; - /* * Write an illegal value to APIC_ACCESS_ADDR. Later, * nested_get_vmcs12_pages will either fix it up or @@ -10271,6 +10266,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_ept(vmcs12)) { kvm_mmu_unload(vcpu); nested_ept_init_mmu_context(vcpu); + } else if (nested_cpu_has2(vmcs12, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + vmx_flush_tlb_ept_only(vcpu); } /* @@ -10298,12 +10296,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_efer(vcpu, vcpu->arch.efer); /* Shadow page tables on either EPT or shadow page tables. */ - if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled, + if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), entry_failure_code)) return 1; - kvm_mmu_reset_context(vcpu); - if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; @@ -11072,6 +11068,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx->nested.change_vmcs01_virtual_x2apic_mode = false; vmx_set_virtual_x2apic_mode(vcpu, vcpu->arch.apic_base & X2APIC_ENABLE); + } else if (!nested_cpu_has_ept(vmcs12) && + nested_cpu_has2(vmcs12, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + vmx_flush_tlb_ept_only(vcpu); } /* This is needed for same reason as it was needed in prepare_vmcs02 */ @@ -11121,8 +11121,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ static void vmx_leave_nested(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.nested_run_pending = 0; nested_vmx_vmexit(vcpu, -1, 0, 0); + } free_nested(to_vmx(vcpu)); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1faf620..ccbd45e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); kvm_iommu_unmap_guest(kvm); - kfree(kvm->arch.vpic); - kfree(kvm->arch.vioapic); + kvm_pic_destroy(kvm); + kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kvm_mmu_uninit_vm(kvm); + kvm_page_track_cleanup(kvm); } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, @@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_ready(work->arch.token, work->gva); if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + trace_kvm_async_pf_ready(work->arch.token, work->gva); if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 779782f..9a53a06 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -290,7 +290,7 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 96d2b84..0fbdcb6 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -2,7 +2,7 @@ KCOV_INSTRUMENT_tlb.o := n obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 58b5bee..9f305be 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -110,7 +110,8 @@ static struct addr_marker address_markers[] = { #define PTE_LEVEL_MULT (PAGE_SIZE) #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT) #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT) -#define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) +#define P4D_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT) +#define PGD_LEVEL_MULT (PTRS_PER_PUD * P4D_LEVEL_MULT) #define pt_dump_seq_printf(m, to_dmesg, fmt, args...) \ ({ \ @@ -286,14 +287,13 @@ static void note_page(struct seq_file *m, struct pg_state *st, } } -static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, - unsigned long P) +static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P) { int i; pte_t *start; pgprotval_t prot; - start = (pte_t *) pmd_page_vaddr(addr); + start = (pte_t *)pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); @@ -304,14 +304,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, #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, unsigned long P) { int i; pmd_t *start; pgprotval_t prot; - start = (pmd_t *) pud_page_vaddr(addr); + 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)) { @@ -347,15 +346,14 @@ static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx) return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud)); } -static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, - unsigned long P) +static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P) { int i; pud_t *start; pgprotval_t prot; pud_t *prev_pud = NULL; - start = (pud_t *) pgd_page_vaddr(addr); + start = (pud_t *)p4d_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); @@ -377,9 +375,42 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, } #else -#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(pgd_val(a)),p) -#define pgd_large(a) pud_large(__pud(pgd_val(a))) -#define pgd_none(a) pud_none(__pud(pgd_val(a))) +#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),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) +{ + int i; + p4d_t *start; + pgprotval_t prot; + + 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)) { + if (p4d_large(*start) || !p4d_present(*start)) { + prot = p4d_flags(*start); + note_page(m, st, __pgprot(prot), 2); + } else { + walk_pud_level(m, st, *start, + P + i * P4D_LEVEL_MULT); + } + } else + note_page(m, st, __pgprot(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 static inline bool is_hypervisor_range(int idx) @@ -424,7 +455,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, prot = pgd_flags(*start); note_page(m, &st, __pgprot(prot), 1); } else { - walk_pud_level(m, &st, *start, + walk_p4d_level(m, &st, *start, i * PGD_LEVEL_MULT); } } else diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 428e3176..8ad91a0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -253,6 +253,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; + p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; @@ -265,10 +266,15 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would - * set_pud. + * set_p4d/set_pud. */ - pud = pud_offset(pgd, address); - pud_k = pud_offset(pgd_k, address); + p4d = p4d_offset(pgd, address); + p4d_k = p4d_offset(pgd_k, address); + if (!p4d_present(*p4d_k)) + return NULL; + + pud = pud_offset(p4d, address); + pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; @@ -384,6 +390,8 @@ static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3()); pgd_t *pgd = &base[pgd_index(address)]; + p4d_t *p4d; + pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -392,7 +400,9 @@ static void dump_pagetable(unsigned long address) if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #endif - pmd = pmd_offset(pud_offset(pgd, address), address); + p4d = p4d_offset(pgd, address); + pud = pud_offset(p4d, address); + pmd = pmd_offset(pud, address); printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); /* @@ -425,6 +435,7 @@ 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; @@ -448,17 +459,37 @@ static noinline int vmalloc_fault(unsigned long address) if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); arch_flush_lazy_mmu_mode(); - } else { + } else if (CONFIG_PGTABLE_LEVELS > 4) { + /* + * With folded p4d, pgd_none() is always false, so the pgd may + * point to an empty page table entry and pgd_page_vaddr() + * will return garbage. + * + * We will do the correct sanity check on the p4d level. + */ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); } + /* 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)) + return -1; + + if (p4d_none(*p4d)) { + set_p4d(p4d, *p4d_ref); + arch_flush_lazy_mmu_mode(); + } else { + BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_ref)); + } + /* * Below here mismatches are bugs because these lower tables * are shared: */ - pud = pud_offset(pgd, address); - pud_ref = pud_offset(pgd_ref, address); + pud = pud_offset(p4d, address); + pud_ref = pud_offset(p4d_ref, address); if (pud_none(*pud_ref)) return -1; @@ -526,6 +557,7 @@ static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK); pgd_t *pgd = base + pgd_index(address); + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -538,7 +570,15 @@ static void dump_pagetable(unsigned long address) if (!pgd_present(*pgd)) goto out; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (bad_address(p4d)) + goto bad; + + printk("P4D %lx ", p4d_val(*p4d)); + if (!p4d_present(*p4d) || p4d_large(*p4d)) + goto out; + + pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; @@ -1082,6 +1122,7 @@ static noinline int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1104,7 +1145,14 @@ spurious_fault(unsigned long error_code, unsigned long address) if (!pgd_present(*pgd)) return 0; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (!p4d_present(*p4d)) + return 0; + + if (p4d_large(*p4d)) + return spurious_fault_check(error_code, (pte_t *) p4d); + + pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c deleted file mode 100644 index 99c7805..0000000 --- a/arch/x86/mm/gup.c +++ /dev/null @@ -1,470 +0,0 @@ -/* - * Lockless get_user_pages_fast for x86 - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <linux/swap.h> -#include <linux/memremap.h> - -#include <asm/mmu_context.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#ifndef CONFIG_X86_PAE - return READ_ONCE(*ptep); -#else - /* - * With get_user_pages_fast, we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a pte will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees l iff pte_high - * sees h. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have got rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. And get_user_pages_fast only operates on present ptes, so - * we're safe. - * - * gup_get_pte should not be used or copied outside gup.c without being - * very careful -- it does not atomically load the pte or anything that - * is likely to be useful for you. - */ - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#endif -} - -static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) -{ - while ((*nr) - nr_start) { - struct page *page = pages[--(*nr)]; - - ClearPageReferenced(page); - put_page(page); - } -} - -/* - * 'pteval' can come from a pte, pmd or pud. We only check - * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 3 types. - */ -static inline int pte_allows_gup(unsigned long pteval, int write) -{ - unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; - - if (write) - need_pte_bits |= _PAGE_RW; - - if ((pteval & need_pte_bits) != need_pte_bits) - return 0; - - /* Check memory protection keys permissions. */ - if (!__pkru_allows_pkey(pte_flags_pkey(pteval), write)) - return 0; - - return 1; -} - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct dev_pagemap *pgmap = NULL; - int nr_start = *nr; - pte_t *ptep; - - ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - /* Similar to the PMD case, NUMA hinting must take slow path */ - if (pte_protnone(pte)) { - pte_unmap(ptep); - return 0; - } - - if (pte_devmap(pte)) { - pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - pte_unmap(ptep); - return 0; - } - } else if (!pte_allows_gup(pte_val(pte), write) || - pte_special(pte)) { - pte_unmap(ptep); - return 0; - } - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - put_dev_pagemap(pgmap); - SetPageReferenced(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - pte_unmap(ptep - 1); - - return 1; -} - -static inline void get_head_page_multiple(struct page *page, int nr) -{ - VM_BUG_ON_PAGE(page != compound_head(page), page); - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, nr); - SetPageReferenced(page); -} - -static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - int nr_start = *nr; - struct dev_pagemap *pgmap = NULL; - - do { - struct page *page = pfn_to_page(pfn); - - pgmap = get_dev_pagemap(pfn, pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - return 0; - } - SetPageReferenced(page); - pages[*nr] = page; - get_page(page); - put_dev_pagemap(pgmap); - (*nr)++; - pfn++; - } while (addr += PAGE_SIZE, addr != end); - return 1; -} - -static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static int __gup_device_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pmd_val(pmd), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); - if (pmd_devmap(pmd)) - return __gup_device_huge_pmd(pmd, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - - refs = 0; - head = pmd_page(pmd); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { - /* - * NUMA hinting faults need to be handled in the GUP - * slowpath for accounting purposes and so that they - * can be serialised against THP migration. - */ - if (pmd_protnone(pmd)) - return 0; - if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static noinline int gup_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pud_val(pud), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pud_pfn(pud))); - if (pud_devmap(pud)) - return __gup_device_huge_pud(pud, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); - - refs = 0; - head = pud_page(pud); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_large(pud))) { - if (!gup_huge_pud(pud, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } - } while (pudp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - (void __user *)start, len))) - return 0; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start) - goto slow_irqon; - -#ifdef CONFIG_X86_64 - if (end >> __VIRTUAL_MASK_SHIFT) - goto slow_irqon; -#endif - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, - pages, write ? FOLL_WRITE : 0); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index c5066a2..302f43f 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -12,10 +12,12 @@ #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> +#include <linux/compat.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> +#include <asm/elf.h> #if 0 /* This is just for testing */ struct page * @@ -82,8 +84,9 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, info.flags = 0; info.length = len; - info.low_limit = current->mm->mmap_legacy_base; - info.high_limit = TASK_SIZE; + info.low_limit = get_mmap_base(1); + info.high_limit = in_compat_syscall() ? + tasksize_32bit() : tasksize_64bit(); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -100,7 +103,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; - info.high_limit = current->mm->mmap_base; + info.high_limit = get_mmap_base(0); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 4473cb4..04210a2 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -45,6 +45,34 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, return 0; } +static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next) { + p4d_t *p4d = p4d_page + p4d_index(addr); + pud_t *pud; + + next = (addr & P4D_MASK) + P4D_SIZE; + if (next > end) + next = end; + + if (p4d_present(*p4d)) { + pud = pud_offset(p4d, 0); + ident_pud_init(info, pud, addr, next); + continue; + } + pud = (pud_t *)info->alloc_pgt_page(info->context); + if (!pud) + return -ENOMEM; + ident_pud_init(info, pud, addr, next); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + } + + return 0; +} + int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, unsigned long pstart, unsigned long pend) { @@ -55,27 +83,36 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, for (; addr < end; addr = next) { pgd_t *pgd = pgd_page + pgd_index(addr); - pud_t *pud; + p4d_t *p4d; next = (addr & PGDIR_MASK) + PGDIR_SIZE; if (next > end) next = end; if (pgd_present(*pgd)) { - pud = pud_offset(pgd, 0); - result = ident_pud_init(info, pud, addr, next); + p4d = p4d_offset(pgd, 0); + result = ident_p4d_init(info, p4d, addr, next); if (result) return result; continue; } - pud = (pud_t *)info->alloc_pgt_page(info->context); - if (!pud) + p4d = (p4d_t *)info->alloc_pgt_page(info->context); + if (!p4d) return -ENOMEM; - result = ident_pud_init(info, pud, addr, next); + result = ident_p4d_init(info, p4d, addr, next); if (result) return result; - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } else { + /* + * With p4d folded, pgd is equal to p4d. + * The pgd entry has to point to the pud page table in this case. + */ + pud_t *pud = pud_offset(p4d, 0); + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + } } return 0; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 1fa97c9..f34d275 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -56,8 +56,6 @@ unsigned long highstart_pfn, highend_pfn; -static noinline int do_test_wp_bit(void); - bool __read_mostly __vmalloc_start_set = false; /* @@ -67,6 +65,7 @@ bool __read_mostly __vmalloc_start_set = false; */ static pmd_t * __init one_md_table_init(pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd_table; @@ -75,13 +74,15 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) pmd_table = (pmd_t *)alloc_low_page(); paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); return pmd_table; } #endif - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); pmd_table = pmd_offset(pud, 0); return pmd_table; @@ -390,8 +391,11 @@ pte_t *kmap_pte; static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr) { - return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), - vaddr), vaddr), vaddr); + pgd_t *pgd = pgd_offset_k(vaddr); + p4d_t *p4d = p4d_offset(pgd, vaddr); + pud_t *pud = pud_offset(p4d, vaddr); + pmd_t *pmd = pmd_offset(pud, vaddr); + return pte_offset_kernel(pmd, vaddr); } static void __init kmap_init(void) @@ -410,6 +414,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) { unsigned long vaddr; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -418,7 +423,8 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); pgd = swapper_pg_dir + pgd_index(vaddr); - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + pud = pud_offset(p4d, vaddr); pmd = pmd_offset(pud, vaddr); pte = pte_offset_kernel(pmd, vaddr); pkmap_page_table = pte; @@ -450,6 +456,7 @@ void __init native_pagetable_init(void) { unsigned long pfn, va; pgd_t *pgd, *base = swapper_pg_dir; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -469,7 +476,8 @@ void __init native_pagetable_init(void) if (!pgd_present(*pgd)) break; - pud = pud_offset(pgd, va); + p4d = p4d_offset(pgd, va); + pud = pud_offset(p4d, va); pmd = pmd_offset(pud, va); if (!pmd_present(*pmd)) break; @@ -716,20 +724,20 @@ void __init paging_init(void) */ static void __init test_wp_bit(void) { - printk(KERN_INFO - "Checking if this processor honours the WP bit even in supervisor mode..."); + char z = 0; + + printk(KERN_INFO "Checking if this processor honours the WP bit even in supervisor mode..."); - /* Any page-aligned address will do, the test is non-destructive */ - __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO); - boot_cpu_data.wp_works_ok = do_test_wp_bit(); - clear_fixmap(FIX_WP_TEST); + __set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO); - if (!boot_cpu_data.wp_works_ok) { - printk(KERN_CONT "No.\n"); - panic("Linux doesn't support CPUs with broken WP."); - } else { + if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { + clear_fixmap(FIX_WP_TEST); printk(KERN_CONT "Ok.\n"); + return; } + + printk(KERN_CONT "No.\n"); + panic("Linux doesn't support CPUs with broken WP."); } void __init mem_init(void) @@ -811,8 +819,7 @@ void __init mem_init(void) BUG_ON(VMALLOC_START >= VMALLOC_END); BUG_ON((unsigned long)high_memory > VMALLOC_START); - if (boot_cpu_data.wp_works_ok < 0) - test_wp_bit(); + test_wp_bit(); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -840,30 +847,6 @@ int arch_remove_memory(u64 start, u64 size) #endif #endif -/* - * This function cannot be __init, since exceptions don't work in that - * section. Put this after the callers, so that it cannot be inlined. - */ -static noinline int do_test_wp_bit(void) -{ - char tmp_reg; - int flag; - - __asm__ __volatile__( - " movb %0, %1 \n" - "1: movb %1, %0 \n" - " xorl %2, %2 \n" - "2: \n" - _ASM_EXTABLE(1b,2b) - :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)), - "=q" (tmp_reg), - "=r" (flag) - :"2" (1) - :"memory"); - - return flag; -} - int kernel_set_to_readonly __read_mostly; void set_kernel_text_rw(void) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f6da869..a242139 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -97,28 +97,38 @@ void sync_global_pgds(unsigned long start, unsigned long end) unsigned long address; for (address = start; address <= end; address += PGDIR_SIZE) { - const pgd_t *pgd_ref = pgd_offset_k(address); + pgd_t *pgd_ref = pgd_offset_k(address); + const p4d_t *p4d_ref; struct page *page; - if (pgd_none(*pgd_ref)) + /* + * With folded p4d, pgd_none() is always false, we need to + * handle synchonization on p4d level. + */ + BUILD_BUG_ON(pgd_none(*pgd_ref)); + p4d_ref = p4d_offset(pgd_ref, address); + + if (p4d_none(*p4d_ref)) continue; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; + p4d_t *p4d; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(address); + p4d = p4d_offset(pgd, address); /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) - BUG_ON(pgd_page_vaddr(*pgd) - != pgd_page_vaddr(*pgd_ref)); + if (!p4d_none(*p4d_ref) && !p4d_none(*p4d)) + BUG_ON(p4d_page_vaddr(*p4d) + != p4d_page_vaddr(*p4d_ref)); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); + if (p4d_none(*p4d)) + set_p4d(p4d, *p4d_ref); spin_unlock(pgt_lock); } @@ -149,16 +159,28 @@ static __ref void *spp_getpage(void) return ptr; } -static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr) +static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr) { if (pgd_none(*pgd)) { - pud_t *pud = (pud_t *)spp_getpage(); - pgd_populate(&init_mm, pgd, pud); - if (pud != pud_offset(pgd, 0)) + p4d_t *p4d = (p4d_t *)spp_getpage(); + pgd_populate(&init_mm, pgd, p4d); + if (p4d != p4d_offset(pgd, 0)) printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n", - pud, pud_offset(pgd, 0)); + p4d, p4d_offset(pgd, 0)); + } + return p4d_offset(pgd, vaddr); +} + +static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr) +{ + if (p4d_none(*p4d)) { + pud_t *pud = (pud_t *)spp_getpage(); + p4d_populate(&init_mm, p4d, pud); + if (pud != pud_offset(p4d, 0)) + printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", + pud, pud_offset(p4d, 0)); } - return pud_offset(pgd, vaddr); + return pud_offset(p4d, vaddr); } static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) @@ -167,7 +189,7 @@ static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr) pmd_t *pmd = (pmd_t *) spp_getpage(); pud_populate(&init_mm, pud, pmd); if (pmd != pmd_offset(pud, 0)) - printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", + printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n", pmd, pmd_offset(pud, 0)); } return pmd_offset(pud, vaddr); @@ -179,20 +201,15 @@ static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr) pte_t *pte = (pte_t *) spp_getpage(); pmd_populate_kernel(&init_mm, pmd, pte); if (pte != pte_offset_kernel(pmd, 0)) - printk(KERN_ERR "PAGETABLE BUG #02!\n"); + printk(KERN_ERR "PAGETABLE BUG #03!\n"); } return pte_offset_kernel(pmd, vaddr); } -void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte) { - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pud = pud_page + pud_index(vaddr); - pmd = fill_pmd(pud, vaddr); - pte = fill_pte(pmd, vaddr); + pmd_t *pmd = fill_pmd(pud, vaddr); + pte_t *pte = fill_pte(pmd, vaddr); set_pte(pte, new_pte); @@ -203,10 +220,25 @@ void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) __flush_tlb_one(vaddr); } +void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte) +{ + p4d_t *p4d = p4d_page + p4d_index(vaddr); + pud_t *pud = fill_pud(p4d, vaddr); + + __set_pte_vaddr(pud, vaddr, new_pte); +} + +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte) +{ + pud_t *pud = pud_page + pud_index(vaddr); + + __set_pte_vaddr(pud, vaddr, new_pte); +} + void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; - pud_t *pud_page; + p4d_t *p4d_page; pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval)); @@ -216,17 +248,20 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) "PGD FIXMAP MISSING, it should be setup in head.S!\n"); return; } - pud_page = (pud_t*)pgd_page_vaddr(*pgd); - set_pte_vaddr_pud(pud_page, vaddr, pteval); + + p4d_page = p4d_offset(pgd, 0); + set_pte_vaddr_p4d(p4d_page, vaddr, pteval); } pmd_t * __init populate_extra_pmd(unsigned long vaddr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(vaddr); - pud = fill_pud(pgd, vaddr); + p4d = fill_p4d(pgd, vaddr); + pud = fill_pud(p4d, vaddr); return fill_pmd(pud, vaddr); } @@ -245,6 +280,7 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, enum page_cache_mode cache) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgprot_t prot; @@ -255,11 +291,17 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size, for (; size; phys += PMD_SIZE, size -= PMD_SIZE) { pgd = pgd_offset_k((unsigned long)__va(phys)); if (pgd_none(*pgd)) { + p4d = (p4d_t *) spp_getpage(); + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE | + _PAGE_USER)); + } + p4d = p4d_offset(pgd, (unsigned long)__va(phys)); + if (p4d_none(*p4d)) { pud = (pud_t *) spp_getpage(); - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE | + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE | _PAGE_USER)); } - pud = pud_offset(pgd, (unsigned long)__va(phys)); + pud = pud_offset(p4d, (unsigned long)__va(phys)); if (pud_none(*pud)) { pmd = (pmd_t *) spp_getpage(); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | @@ -563,12 +605,15 @@ kernel_physical_mapping_init(unsigned long paddr_start, for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); + p4d_t *p4d; pud_t *pud; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; - if (pgd_val(*pgd)) { - pud = (pud_t *)pgd_page_vaddr(*pgd); + BUILD_BUG_ON(pgd_none(*pgd)); + p4d = p4d_offset(pgd, vaddr); + if (p4d_val(*p4d)) { + pud = (pud_t *)p4d_page_vaddr(*p4d); paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), page_size_mask); @@ -580,7 +625,7 @@ kernel_physical_mapping_init(unsigned long paddr_start, page_size_mask); spin_lock(&init_mm.page_table_lock); - pgd_populate(&init_mm, pgd, pud); + p4d_populate(&init_mm, p4d, pud); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } @@ -726,6 +771,24 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) spin_unlock(&init_mm.page_table_lock); } +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) +{ + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } + + /* free a pud talbe */ + free_pagetable(p4d_page(*p4d), 0); + spin_lock(&init_mm.page_table_lock); + p4d_clear(p4d); + spin_unlock(&init_mm.page_table_lock); +} + static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, bool direct) @@ -908,6 +971,32 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, update_page_count(PG_LEVEL_1G, -pages); } +static void __meminit +remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pud_t *pud_base; + p4d_t *p4d; + + p4d = p4d_start + p4d_index(addr); + for (; addr < end; addr = next, p4d++) { + next = p4d_addr_end(addr, end); + + if (!p4d_present(*p4d)) + continue; + + BUILD_BUG_ON(p4d_large(*p4d)); + + pud_base = (pud_t *)p4d_page_vaddr(*p4d); + remove_pud_table(pud_base, addr, next, direct); + free_pud_table(pud_base, p4d); + } + + if (direct) + update_page_count(PG_LEVEL_512G, -pages); +} + /* start and end are both virtual address. */ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct) @@ -915,7 +1004,7 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) unsigned long next; unsigned long addr; pgd_t *pgd; - pud_t *pud; + p4d_t *p4d; for (addr = start; addr < end; addr = next) { next = pgd_addr_end(addr, end); @@ -924,8 +1013,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) if (!pgd_present(*pgd)) continue; - pud = (pud_t *)pgd_page_vaddr(*pgd); - remove_pud_table(pud, addr, next, direct); + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + remove_p4d_table(p4d, addr, next, direct); } flush_tlb_all(); @@ -1090,6 +1179,7 @@ int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1101,7 +1191,11 @@ int kern_addr_valid(unsigned long addr) if (pgd_none(*pgd)) return 0; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return 0; + + pud = pud_offset(p4d, addr); if (pud_none(*pud)) return 0; @@ -1158,6 +1252,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long addr; unsigned long next; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -1168,7 +1263,11 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, addr, node); + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + + pud = vmemmap_pud_populate(p4d, addr, node); if (!pud) return -ENOMEM; @@ -1236,6 +1335,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, unsigned long end = (unsigned long)(start_page + size); unsigned long next; pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; unsigned int nr_pages; @@ -1251,7 +1351,14 @@ void register_page_bootmem_memmap(unsigned long section_nr, } get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, p4d_page(*p4d), MIX_SECTION_INFO); + + pud = pud_offset(p4d, addr); if (pud_none(*pud)) { next = (addr + PAGE_SIZE) & PAGE_MASK; continue; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index c43b6b3..e4f7b25 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -426,7 +426,8 @@ static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) /* Don't assume we're using swapper_pg_dir at this point */ pgd_t *base = __va(read_cr3()); pgd_t *pgd = &base[pgd_index(addr)]; - pud_t *pud = pud_offset(pgd, addr); + p4d_t *p4d = p4d_offset(pgd, addr); + pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); return pmd; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 66d2017..0c7d812 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> @@ -33,8 +34,19 @@ static int __init map_range(struct range *range) static void __init clear_pgds(unsigned long start, unsigned long end) { - for (; start < end; start += PGDIR_SIZE) - pgd_clear(pgd_offset_k(start)); + pgd_t *pgd; + + for (; start < end; start += PGDIR_SIZE) { + pgd = pgd_offset_k(start); + /* + * With folded p4d, pgd_clear() is nop, use p4d_clear() + * instead. + */ + if (CONFIG_PGTABLE_LEVELS < 5) + p4d_clear(p4d_offset(pgd, start)); + else + pgd_clear(pgd); + } } static void __init kasan_map_early_shadow(pgd_t *pgd) @@ -44,8 +56,18 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) unsigned long end = KASAN_SHADOW_END; for (i = pgd_index(start); start < end; i++) { - pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) - | _KERNPG_TABLE); + switch (CONFIG_PGTABLE_LEVELS) { + case 4: + pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) | + _KERNPG_TABLE); + break; + case 5: + pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) | + _KERNPG_TABLE); + break; + default: + BUILD_BUG(); + } start += PGDIR_SIZE; } } @@ -73,6 +95,7 @@ void __init kasan_early_init(void) pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL; pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE; pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE; + p4dval_t p4d_val = __pa_nodebug(kasan_zero_pud) | _KERNPG_TABLE; for (i = 0; i < PTRS_PER_PTE; i++) kasan_zero_pte[i] = __pte(pte_val); @@ -83,6 +106,9 @@ void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PUD; i++) kasan_zero_pud[i] = __pud(pud_val); + for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++) + kasan_zero_p4d[i] = __p4d(p4d_val); + kasan_map_early_shadow(early_level4_pgt); kasan_map_early_shadow(init_level4_pgt); } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 887e571..aed2064 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; #if defined(CONFIG_X86_ESPFIX64) static const unsigned long vaddr_end = ESPFIX_BASE_ADDR; #elif defined(CONFIG_EFI) -static const unsigned long vaddr_end = EFI_VA_START; +static const unsigned long vaddr_end = EFI_VA_END; #else static const unsigned long vaddr_end = __START_KERNEL_map; #endif @@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void) */ BUILD_BUG_ON(vaddr_start >= vaddr_end); BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) && - vaddr_end >= EFI_VA_START); + vaddr_end >= EFI_VA_END); BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) || IS_ENABLED(CONFIG_EFI)) && vaddr_end >= __START_KERNEL_map); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 7940166..19ad095 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -30,30 +30,44 @@ #include <linux/limits.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> +#include <linux/compat.h> #include <asm/elf.h> struct va_alignment __read_mostly va_align = { .flags = -1, }; -static unsigned long stack_maxrandom_size(void) +unsigned long tasksize_32bit(void) +{ + return IA32_PAGE_OFFSET; +} + +unsigned long tasksize_64bit(void) +{ + return TASK_SIZE_MAX; +} + +static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT; + max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); + max <<= PAGE_SHIFT; } return max; } -/* - * Top of mmap area (just below the process stack). - * - * Leave an at least ~128 MB hole with possible stack randomization. - */ -#define MIN_GAP (128*1024*1024UL + stack_maxrandom_size()) -#define MAX_GAP (TASK_SIZE/6*5) +#ifdef CONFIG_COMPAT +# define mmap32_rnd_bits mmap_rnd_compat_bits +# define mmap64_rnd_bits mmap_rnd_bits +#else +# define mmap32_rnd_bits mmap_rnd_bits +# define mmap64_rnd_bits mmap_rnd_bits +#endif + +#define SIZE_128M (128 * 1024 * 1024UL) static int mmap_is_legacy(void) { @@ -66,54 +80,91 @@ static int mmap_is_legacy(void) return sysctl_legacy_va_layout; } -unsigned long arch_mmap_rnd(void) +static unsigned long arch_rnd(unsigned int rndbits) { - unsigned long rnd; - - if (mmap_is_ia32()) -#ifdef CONFIG_COMPAT - rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); -#else - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); -#endif - else - rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); + return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; +} - return rnd << PAGE_SHIFT; +unsigned long arch_mmap_rnd(void) +{ + if (!(current->flags & PF_RANDOMIZE)) + return 0; + return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } -static unsigned long mmap_base(unsigned long rnd) +static unsigned long mmap_base(unsigned long rnd, unsigned long task_size) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long gap_min, gap_max; + + /* + * Top of mmap area (just below the process stack). + * Leave an at least ~128 MB hole with possible stack randomization. + */ + gap_min = SIZE_128M + stack_maxrandom_size(task_size); + gap_max = (task_size / 6) * 5; - if (gap < MIN_GAP) - gap = MIN_GAP; - else if (gap > MAX_GAP) - gap = MAX_GAP; + if (gap < gap_min) + gap = gap_min; + else if (gap > gap_max) + gap = gap_max; + + return PAGE_ALIGN(task_size - gap - rnd); +} - return PAGE_ALIGN(TASK_SIZE - gap - rnd); +static unsigned long mmap_legacy_base(unsigned long rnd, + unsigned long task_size) +{ + return __TASK_UNMAPPED_BASE(task_size) + rnd; } /* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ +static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, + unsigned long random_factor, unsigned long task_size) +{ + *legacy_base = mmap_legacy_base(random_factor, task_size); + if (mmap_is_legacy()) + *base = *legacy_base; + else + *base = mmap_base(random_factor, task_size); +} + void arch_pick_mmap_layout(struct mm_struct *mm) { - unsigned long random_factor = 0UL; + if (mmap_is_legacy()) + mm->get_unmapped_area = arch_get_unmapped_area; + else + mm->get_unmapped_area = arch_get_unmapped_area_topdown; - if (current->flags & PF_RANDOMIZE) - random_factor = arch_mmap_rnd(); + arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, + arch_rnd(mmap64_rnd_bits), tasksize_64bit()); + +#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES + /* + * The mmap syscall mapping base decision depends solely on the + * syscall type (64-bit or compat). This applies for 64bit + * applications and 32bit applications. The 64bit syscall uses + * mmap_base, the compat syscall uses mmap_compat_base. + */ + arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base, + arch_rnd(mmap32_rnd_bits), tasksize_32bit()); +#endif +} - mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor; +unsigned long get_mmap_base(int is_legacy) +{ + struct mm_struct *mm = current->mm; - if (mmap_is_legacy()) { - mm->mmap_base = mm->mmap_legacy_base; - mm->get_unmapped_area = arch_get_unmapped_area; - } else { - mm->mmap_base = mmap_base(random_factor); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; +#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES + if (in_compat_syscall()) { + return is_legacy ? mm->mmap_compat_legacy_base + : mm->mmap_compat_base; } +#endif + return is_legacy ? mm->mmap_legacy_base : mm->mmap_base; } const char *arch_vma_name(struct vm_area_struct *vma) diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 5126dfd..cd44ae7 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -590,7 +590,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, * we might run off the end of the bounds table if we are on * a 64-bit kernel and try to get 8 bytes. */ -int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, +static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, long __user *bd_entry_ptr) { u32 bd_entry_32; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index f9d9953..25504d5 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -201,7 +201,7 @@ static void __init alloc_node_data(int nid) nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, MEMBLOCK_ALLOC_ACCESSIBLE); if (!nd_pa) { - pr_err("Cannot find %zu bytes in node %d\n", + pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", nd_size, nid); return; } @@ -225,7 +225,7 @@ static void __init alloc_node_data(int nid) * numa_cleanup_meminfo - Cleanup a numa_meminfo * @mi: numa_meminfo to clean up * - * Sanitize @mi by merging and removing unncessary memblks. Also check for + * Sanitize @mi by merging and removing unnecessary memblks. Also check for * conflicts and clear unused memblks. * * RETURNS: diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a57e8e0..56b22fa 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -346,6 +346,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd; @@ -354,7 +355,15 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, if (pgd_none(*pgd)) return NULL; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d)) + return NULL; + + *level = PG_LEVEL_512G; + if (p4d_large(*p4d) || !p4d_present(*p4d)) + return (pte_t *)p4d; + + pud = pud_offset(p4d, address); if (pud_none(*pud)) return NULL; @@ -406,13 +415,18 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, pmd_t *lookup_pmd_address(unsigned long address) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pgd = pgd_offset_k(address); if (pgd_none(*pgd)) return NULL; - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d)) + return NULL; + + pud = pud_offset(p4d, address); if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) return NULL; @@ -477,11 +491,13 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = (pgd_t *)page_address(page) + pgd_index(address); - pud = pud_offset(pgd, address); + p4d = p4d_offset(pgd, address); + pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); set_pte_atomic((pte_t *)pmd, pte); } @@ -836,9 +852,9 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) pud_clear(pud); } -static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) +static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) { - pud_t *pud = pud_offset(pgd, start); + pud_t *pud = pud_offset(p4d, start); /* * Not on a GB page boundary? @@ -1004,8 +1020,8 @@ static long populate_pmd(struct cpa_data *cpa, return num_pages; } -static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, - pgprot_t pgprot) +static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d, + pgprot_t pgprot) { pud_t *pud; unsigned long end; @@ -1026,7 +1042,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, cur_pages = (pre_end - start) >> PAGE_SHIFT; cur_pages = min_t(int, (int)cpa->numpages, cur_pages); - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); /* * Need a PMD page? @@ -1047,7 +1063,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, if (cpa->numpages == cur_pages) return cur_pages; - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); pud_pgprot = pgprot_4k_2_large(pgprot); /* @@ -1067,7 +1083,7 @@ static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd, if (start < end) { long tmp; - pud = pud_offset(pgd, start); + pud = pud_offset(p4d, start); if (pud_none(*pud)) if (alloc_pmd_page(pud)) return -1; @@ -1090,33 +1106,43 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) { pgprot_t pgprot = __pgprot(_KERNPG_TABLE); pud_t *pud = NULL; /* shut up gcc */ + p4d_t *p4d; pgd_t *pgd_entry; long ret; pgd_entry = cpa->pgd + pgd_index(addr); + if (pgd_none(*pgd_entry)) { + p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + if (!p4d) + return -1; + + set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + /* * Allocate a PUD page and hand it down for mapping. */ - if (pgd_none(*pgd_entry)) { + p4d = p4d_offset(pgd_entry, addr); + if (p4d_none(*p4d)) { pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); if (!pud) return -1; - set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE)); + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); } pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(pgprot) |= pgprot_val(cpa->mask_set); - ret = populate_pud(cpa, addr, pgd_entry, pgprot); + ret = populate_pud(cpa, addr, p4d, pgprot); if (ret < 0) { /* * Leave the PUD page in place in case some other CPU or thread * already found it, but remove any useless entries we just * added to it. */ - unmap_pud_range(pgd_entry, addr, + unmap_pud_range(p4d, addr, addr + (cpa->numpages << PAGE_SHIFT)); return ret; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 6cbdff2..508a708 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -81,6 +81,14 @@ void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); tlb_remove_page(tlb, virt_to_page(pud)); } + +#if CONFIG_PGTABLE_LEVELS > 4 +void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) +{ + paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); + tlb_remove_page(tlb, virt_to_page(p4d)); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ @@ -120,7 +128,7 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) references from swapper_pg_dir. */ if (CONFIG_PGTABLE_LEVELS == 2 || (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || - CONFIG_PGTABLE_LEVELS == 4) { + CONFIG_PGTABLE_LEVELS >= 4) { clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); @@ -261,13 +269,15 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { + p4d_t *p4d; pud_t *pud; int i; if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ return; - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; @@ -580,6 +590,28 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +#ifdef CONFIG_X86_5LEVEL +/** + * p4d_set_huge - setup kernel P4D mapping + * + * No 512GB pages yet -- always return 0 + */ +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} + +/** + * p4d_clear_huge - clear kernel P4D mapping when it is set + * + * No 512GB pages yet -- always return 0 + */ +int p4d_clear_huge(p4d_t *p4d) +{ + return 0; +} +#endif + /** * pud_set_huge - setup kernel PUD mapping * diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index de53c525..b9bd5b8 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -26,6 +26,7 @@ unsigned int __VMALLOC_RESERVE = 128 << 20; void set_pte_vaddr(unsigned long vaddr, pte_t pteval) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -35,7 +36,12 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) BUG(); return; } - pud = pud_offset(pgd, vaddr); + p4d = p4d_offset(pgd, vaddr); + if (p4d_none(*p4d)) { + BUG(); + return; + } + pud = pud_offset(p4d, vaddr); if (pud_none(*pud)) { BUG(); return; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 0cb52ae..190e718 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev) pcibios_disable_irq(dev); } +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +void pcibios_release_device(struct pci_dev *dev) +{ + if (atomic_dec_return(&dev->enable_cnt) >= 0) + pcibios_disable_device(dev); + +} +#endif + int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index e1fb269..292ab03 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; for_each_pci_msi_entry(msidesc, dev) { - __pci_read_msi_msg(msidesc, &msg); - pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | - ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); - if (msg.data != XEN_PIRQ_MSI_DATA || - xen_irq_from_pirq(pirq) < 0) { - pirq = xen_allocate_pirq_msi(dev, msidesc); - if (pirq < 0) { - irq = -ENODEV; - goto error; - } - xen_msi_compose_msg(dev, pirq, &msg); - __pci_write_msi_msg(msidesc, &msg); - dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); - } else { - dev_dbg(&dev->dev, - "xen: msi already bound to pirq=%d\n", pirq); + pirq = xen_allocate_pirq_msi(dev, msidesc); + if (pirq < 0) { + irq = -ENODEV; + goto error; } + xen_msi_compose_msg(dev, pirq, &msg); + __pci_write_msi_msg(msidesc, &msg); + dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index cef39b0..3481268 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -68,7 +68,7 @@ pgd_t * __init efi_call_phys_prolog(void) load_cr3(initial_page_table); __flush_tlb_all(); - gdt_descr.address = __pa(get_cpu_gdt_table(0)); + gdt_descr.address = get_cpu_gdt_paddr(0); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); @@ -79,7 +79,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) { struct desc_ptr gdt_descr; - gdt_descr.address = (unsigned long)get_cpu_gdt_table(0); + gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2ee7694..6b6b8e8 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -135,6 +135,7 @@ static pgd_t *efi_pgd; int __init efi_alloc_page_tables(void) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; gfp_t gfp_mask; @@ -147,15 +148,20 @@ int __init efi_alloc_page_tables(void) return -ENOMEM; pgd = efi_pgd + pgd_index(EFI_VA_END); + p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END); + if (!p4d) { + free_page((unsigned long)efi_pgd); + return -ENOMEM; + } - pud = pud_alloc_one(NULL, 0); + pud = pud_alloc(&init_mm, p4d, EFI_VA_END); if (!pud) { + if (CONFIG_PGTABLE_LEVELS > 4) + free_page((unsigned long) pgd_page_vaddr(*pgd)); free_page((unsigned long)efi_pgd); return -ENOMEM; } - pgd_populate(NULL, pgd, pud); - return 0; } @@ -166,6 +172,7 @@ void efi_sync_low_kernel_mappings(void) { unsigned num_entries; pgd_t *pgd_k, *pgd_efi; + p4d_t *p4d_k, *p4d_efi; pud_t *pud_k, *pud_efi; if (efi_enabled(EFI_OLD_MEMMAP)) @@ -190,23 +197,37 @@ void efi_sync_low_kernel_mappings(void) memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries); /* + * As with PGDs, we share all P4D entries apart from the one entry + * that covers the EFI runtime mapping space. + */ + BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END)); + BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK)); + + pgd_efi = efi_pgd + pgd_index(EFI_VA_END); + pgd_k = pgd_offset_k(EFI_VA_END); + p4d_efi = p4d_offset(pgd_efi, 0); + p4d_k = p4d_offset(pgd_k, 0); + + num_entries = p4d_index(EFI_VA_END); + memcpy(p4d_efi, p4d_k, sizeof(p4d_t) * num_entries); + + /* * We share all the PUD entries apart from those that map the * EFI regions. Copy around them. */ BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0); BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0); - pgd_efi = efi_pgd + pgd_index(EFI_VA_END); - pud_efi = pud_offset(pgd_efi, 0); - - pgd_k = pgd_offset_k(EFI_VA_END); - pud_k = pud_offset(pgd_k, 0); + p4d_efi = p4d_offset(pgd_efi, EFI_VA_END); + p4d_k = p4d_offset(pgd_k, EFI_VA_END); + pud_efi = pud_offset(p4d_efi, 0); + pud_k = pud_offset(p4d_k, 0); num_entries = pud_index(EFI_VA_END); memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); - pud_efi = pud_offset(pgd_efi, EFI_VA_START); - pud_k = pud_offset(pgd_k, EFI_VA_START); + pud_efi = pud_offset(p4d_efi, EFI_VA_START); + pud_k = pud_offset(p4d_k, EFI_VA_START); num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START); memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index a7dbec4..3dbde04 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -26,5 +26,6 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o # MISC Devices obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o +obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c new file mode 100644 index 0000000..a6c3705 --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c @@ -0,0 +1,82 @@ +/* + * Intel Merrifield power button support + * + * (C) Copyright 2017 Intel Corporation + * + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/sfi.h> + +#include <asm/intel-mid.h> +#include <asm/intel_scu_ipc.h> + +static struct resource mrfld_power_btn_resources[] = { + { + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device mrfld_power_btn_dev = { + .name = "msic_power_btn", + .id = PLATFORM_DEVID_NONE, + .num_resources = ARRAY_SIZE(mrfld_power_btn_resources), + .resource = mrfld_power_btn_resources, +}; + +static int mrfld_power_btn_scu_status_change(struct notifier_block *nb, + unsigned long code, void *data) +{ + if (code == SCU_DOWN) { + platform_device_unregister(&mrfld_power_btn_dev); + return 0; + } + + return platform_device_register(&mrfld_power_btn_dev); +} + +static struct notifier_block mrfld_power_btn_scu_notifier = { + .notifier_call = mrfld_power_btn_scu_status_change, +}; + +static int __init register_mrfld_power_btn(void) +{ + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return -ENODEV; + + /* + * We need to be sure that the SCU IPC is ready before + * PMIC power button device can be registered: + */ + intel_scu_notifier_add(&mrfld_power_btn_scu_notifier); + + return 0; +} +arch_initcall(register_mrfld_power_btn); + +static void __init *mrfld_power_btn_platform_data(void *info) +{ + struct resource *res = mrfld_power_btn_resources; + struct sfi_device_table_entry *pentry = info; + + res->start = res->end = pentry->irq; + return NULL; +} + +static const struct devs_id mrfld_power_btn_dev_id __initconst = { + .name = "bcove_power_btn", + .type = SFI_DEV_TYPE_IPC, + .delay = 1, + .msic = 1, + .get_platform_data = &mrfld_power_btn_platform_data, +}; + +sfi_device(mrfld_power_btn_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c index 86edd1e9..9e304e2 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c @@ -19,7 +19,7 @@ #include <asm/intel_scu_ipc.h> #include <asm/io_apic.h> -#define TANGIER_EXT_TIMER0_MSI 15 +#define TANGIER_EXT_TIMER0_MSI 12 static struct platform_device wdt_dev = { .name = "intel_mid_wdt", diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c index e793fe5..e42978d 100644 --- a/arch/x86/platform/intel-mid/mfld.c +++ b/arch/x86/platform/intel-mid/mfld.c @@ -17,16 +17,6 @@ #include "intel_mid_weak_decls.h" -static void penwell_arch_setup(void); -/* penwell arch ops */ -static struct intel_mid_ops penwell_ops = { - .arch_setup = penwell_arch_setup, -}; - -static void mfld_power_off(void) -{ -} - static unsigned long __init mfld_calibrate_tsc(void) { unsigned long fast_calibrate; @@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void) static void __init penwell_arch_setup(void) { x86_platform.calibrate_tsc = mfld_calibrate_tsc; - pm_power_off = mfld_power_off; } +static struct intel_mid_ops penwell_ops = { + .arch_setup = penwell_arch_setup, +}; + void *get_penwell_ops(void) { return &penwell_ops; diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 766d4d3..f25982c 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode) ops.write_payload_first(pnode, first); ops.write_payload_last(pnode, last); - ops.write_g_sw_ack(pnode, 0xffffUL); /* in effect, all msg_type's are set to MSG_NOOP */ memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 66ade16..6b05a92 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -95,7 +95,7 @@ static void __save_processor_state(struct saved_context *ctxt) * 'pmode_gdt' in wakeup_start. */ ctxt->gdt_desc.size = GDT_SIZE - 1; - ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); + ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id()); store_tr(ctxt->tr); @@ -162,7 +162,7 @@ static void fix_processor_context(void) int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 - struct desc_struct *desc = get_cpu_gdt_table(cpu); + struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif set_tss_desc(cpu, t); /* @@ -183,6 +183,9 @@ static void fix_processor_context(void) load_mm_ldt(current->active_mm); /* This does lldt */ fpu__resume_cpu(); + + /* The processor is back on the direct GDT, load back the fixmap */ + load_fixmap_gdt(cpu); } /** diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 9f14bd3..c35fdb5 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -32,6 +32,7 @@ pgd_t *resume_pg_dir; */ static pmd_t *resume_one_md_table_init(pgd_t *pgd) { + p4d_t *p4d; pud_t *pud; pmd_t *pmd_table; @@ -41,11 +42,13 @@ static pmd_t *resume_one_md_table_init(pgd_t *pgd) return NULL; set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); BUG_ON(pmd_table != pmd_offset(pud, 0)); #else - pud = pud_offset(pgd, 0); + p4d = p4d_offset(pgd, 0); + pud = pud_offset(p4d, 0); pmd_table = pmd_offset(pud, 0); #endif diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 053801b..6a61194 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -50,6 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) { pmd_t *pmd; pud_t *pud; + p4d_t *p4d; /* * The new mapping only has to cover the page containing the image @@ -64,6 +65,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd) * the virtual address space after switching over to the original page * tables used by the image kernel. */ + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = (p4d_t *)get_safe_page(GFP_ATOMIC); + if (!p4d) + return -ENOMEM; + } + pud = (pud_t *)get_safe_page(GFP_ATOMIC); if (!pud) return -ENOMEM; @@ -76,8 +84,13 @@ 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)); - set_pgd(pgd + pgd_index(restore_jump_address), - __pgd(__pa(pud) | _KERNPG_TABLE)); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + 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 { + /* No p4d for 4-level paging: point the pgd to the pud page table */ + set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(pud) | _KERNPG_TABLE)); + } return 0; } @@ -125,7 +138,10 @@ static int set_up_temporary_mappings(void) 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) @@ -135,22 +151,25 @@ static int relocate_restore_code(void) /* Make the page containing the relocated code executable */ pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); - pud = pud_offset(pgd, 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)); - } else { - pmd_t *pmd = pmd_offset(pud, relocated_restore_code); - - if (pmd_large(*pmd)) { - set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); - } else { - pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); - - set_pte(pte, __pte(pte_val(*pte) & ~_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/purgatory/Makefile b/arch/x86/purgatory/Makefile index 555b9fa..7dbdb78 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -8,6 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro +KASAN_SANITIZE := n KCOV_INSTRUMENT := n # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index 25e068b..470edad 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -10,21 +10,19 @@ * Version 2. See the file COPYING for more details. */ +#include <linux/bug.h> +#include <asm/purgatory.h> + #include "sha256.h" #include "../boot/string.h" -struct sha_region { - unsigned long start; - unsigned long len; -}; - -unsigned long backup_dest = 0; -unsigned long backup_src = 0; -unsigned long backup_sz = 0; +unsigned long purgatory_backup_dest __section(.kexec-purgatory); +unsigned long purgatory_backup_src __section(.kexec-purgatory); +unsigned long purgatory_backup_sz __section(.kexec-purgatory); -u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 }; +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory); -struct sha_region sha_regions[16] = {}; +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory); /* * On x86, second kernel requries first 640K of memory to boot. Copy @@ -33,26 +31,28 @@ struct sha_region sha_regions[16] = {}; */ static int copy_backup_region(void) { - if (backup_dest) - memcpy((void *)backup_dest, (void *)backup_src, backup_sz); - + if (purgatory_backup_dest) { + memcpy((void *)purgatory_backup_dest, + (void *)purgatory_backup_src, purgatory_backup_sz); + } return 0; } -int verify_sha256_digest(void) +static int verify_sha256_digest(void) { - struct sha_region *ptr, *end; + struct kexec_sha_region *ptr, *end; u8 digest[SHA256_DIGEST_SIZE]; struct sha256_state sctx; sha256_init(&sctx); - end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])]; - for (ptr = sha_regions; ptr < end; ptr++) + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + + for (ptr = purgatory_sha_regions; ptr < end; ptr++) sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); sha256_final(&sctx, digest); - if (memcmp(digest, sha256_digest, sizeof(digest))) + if (memcmp(digest, purgatory_sha256_digest, sizeof(digest))) return 1; return 0; diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S index fe3c91b..dfae9b9 100644 --- a/arch/x86/purgatory/setup-x86_64.S +++ b/arch/x86/purgatory/setup-x86_64.S @@ -9,6 +9,7 @@ * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. */ +#include <asm/purgatory.h> .text .globl purgatory_start diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h index bd15a41..2867d98 100644 --- a/arch/x86/purgatory/sha256.h +++ b/arch/x86/purgatory/sha256.h @@ -10,7 +10,6 @@ #ifndef SHA256_H #define SHA256_H - #include <linux/types.h> #include <crypto/sha.h> diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index e7e7055..69f0827 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -16,7 +16,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \ ifeq ($(CONFIG_X86_32),y) -obj-y += checksum_32.o +obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index e59eef2..b291ca5 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -78,7 +78,7 @@ static inline int ptrace_set_thread_area(struct task_struct *child, int idx, return -ENOSYS; } -extern long arch_prctl(struct task_struct *task, int code, +extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c index 96eb2bd..8431e87 100644 --- a/arch/x86/um/os-Linux/prctl.c +++ b/arch/x86/um/os-Linux/prctl.c @@ -6,7 +6,7 @@ #include <sys/ptrace.h> #include <asm/ptrace.h> -int os_arch_prctl(int pid, int code, unsigned long *addr) +int os_arch_prctl(int pid, int option, unsigned long *arg2) { - return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code); + return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option); } diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c new file mode 100644 index 0000000..627d688 --- /dev/null +++ b/arch/x86/um/syscalls_32.c @@ -0,0 +1,7 @@ +#include <linux/syscalls.h> +#include <os.h> + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return -EINVAL; +} diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index 10d9070..58f5166 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -7,13 +7,15 @@ #include <linux/sched.h> #include <linux/sched/mm.h> +#include <linux/syscalls.h> #include <linux/uaccess.h> #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <os.h> -long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) +long arch_prctl(struct task_struct *task, int option, + unsigned long __user *arg2) { - unsigned long *ptr = addr, tmp; + unsigned long *ptr = arg2, tmp; long ret; int pid = task->mm->context.id.u.pid; @@ -30,7 +32,7 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) * arch_prctl is run on the host, then the registers are read * back. */ - switch (code) { + switch (option) { case ARCH_SET_FS: case ARCH_SET_GS: ret = restore_registers(pid, ¤t->thread.regs.regs); @@ -50,11 +52,11 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ptr = &tmp; } - ret = os_arch_prctl(pid, code, ptr); + ret = os_arch_prctl(pid, option, ptr); if (ret) return ret; - switch (code) { + switch (option) { case ARCH_SET_FS: current->thread.arch.fs = (unsigned long) ptr; ret = save_registers(pid, ¤t->thread.regs.regs); @@ -63,19 +65,19 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ret = save_registers(pid, ¤t->thread.regs.regs); break; case ARCH_GET_FS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; case ARCH_GET_GS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; } return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return arch_prctl(current, code, (unsigned long __user *) addr); + return arch_prctl(current, option, (unsigned long __user *) arg2); } void arch_switch_to(struct task_struct *to) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 7824345..30822e8 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -711,7 +711,7 @@ static void load_TLS_descriptor(struct thread_struct *t, *shadow = t->tls_array[i]; - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); mc = __xen_mc_entry(0); @@ -1596,7 +1596,6 @@ asmlinkage __visible void __init xen_start_kernel(void) /* set up basic CPUID stuff */ cpu_detect(&new_cpu_data); set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); - new_cpu_data.wp_works_ok = 1; new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); #endif diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 1d68be6..f226038 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -535,40 +535,41 @@ static pgd_t *xen_get_user_pgd(pgd_t *pgd) return user_ptr; } -static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) +static void __xen_set_p4d_hyper(p4d_t *ptr, p4d_t val) { struct mmu_update u; u.ptr = virt_to_machine(ptr).maddr; - u.val = pgd_val_ma(val); + u.val = p4d_val_ma(val); xen_extend_mmu_update(&u); } /* - * Raw hypercall-based set_pgd, intended for in early boot before + * Raw hypercall-based set_p4d, intended for in early boot before * there's a page structure. This implies: * 1. The only existing pagetable is the kernel's * 2. It is always pinned * 3. It has no user pagetable attached to it */ -static void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val) +static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val) { preempt_disable(); xen_mc_batch(); - __xen_set_pgd_hyper(ptr, val); + __xen_set_p4d_hyper(ptr, val); xen_mc_issue(PARAVIRT_LAZY_MMU); preempt_enable(); } -static void xen_set_pgd(pgd_t *ptr, pgd_t val) +static void xen_set_p4d(p4d_t *ptr, p4d_t val) { - pgd_t *user_ptr = xen_get_user_pgd(ptr); + pgd_t *user_ptr = xen_get_user_pgd((pgd_t *)ptr); + pgd_t pgd_val; - trace_xen_mmu_set_pgd(ptr, user_ptr, val); + trace_xen_mmu_set_p4d(ptr, (p4d_t *)user_ptr, val); /* If page is not pinned, we can just update the entry directly */ @@ -576,7 +577,8 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val) *ptr = val; if (user_ptr) { WARN_ON(xen_page_pinned(user_ptr)); - *user_ptr = val; + pgd_val.pgd = p4d_val_ma(val); + *user_ptr = pgd_val; } return; } @@ -585,14 +587,72 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val) user updates together. */ xen_mc_batch(); - __xen_set_pgd_hyper(ptr, val); + __xen_set_p4d_hyper(ptr, val); if (user_ptr) - __xen_set_pgd_hyper(user_ptr, val); + __xen_set_p4d_hyper((p4d_t *)user_ptr, val); xen_mc_issue(PARAVIRT_LAZY_MMU); } #endif /* CONFIG_PGTABLE_LEVELS == 4 */ +static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD; + for (i = 0; i < nr; i++) { + if (!pmd_none(pmd[i])) + flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE); + } + return flush; +} + +static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD; + for (i = 0; i < nr; i++) { + pmd_t *pmd; + + if (pud_none(pud[i])) + continue; + + pmd = pmd_offset(&pud[i], 0); + if (PTRS_PER_PMD > 1) + flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); + flush |= xen_pmd_walk(mm, pmd, func, + last && i == nr - 1, limit); + } + return flush; +} + +static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, + int (*func)(struct mm_struct *mm, struct page *, enum pt_level), + bool last, unsigned long limit) +{ + int i, nr, flush = 0; + + nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D; + for (i = 0; i < nr; i++) { + pud_t *pud; + + if (p4d_none(p4d[i])) + continue; + + pud = pud_offset(&p4d[i], 0); + if (PTRS_PER_PUD > 1) + flush |= (*func)(mm, virt_to_page(pud), PT_PUD); + flush |= xen_pud_walk(mm, pud, func, + last && i == nr - 1, limit); + } + return flush; +} + /* * (Yet another) pagetable walker. This one is intended for pinning a * pagetable. This means that it walks a pagetable and calls the @@ -613,10 +673,8 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, enum pt_level), unsigned long limit) { - int flush = 0; + int i, nr, flush = 0; unsigned hole_low, hole_high; - unsigned pgdidx_limit, pudidx_limit, pmdidx_limit; - unsigned pgdidx, pudidx, pmdidx; /* The limit is the last byte to be touched */ limit--; @@ -633,65 +691,22 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, hole_low = pgd_index(USER_LIMIT); hole_high = pgd_index(PAGE_OFFSET); - pgdidx_limit = pgd_index(limit); -#if PTRS_PER_PUD > 1 - pudidx_limit = pud_index(limit); -#else - pudidx_limit = 0; -#endif -#if PTRS_PER_PMD > 1 - pmdidx_limit = pmd_index(limit); -#else - pmdidx_limit = 0; -#endif - - for (pgdidx = 0; pgdidx <= pgdidx_limit; pgdidx++) { - pud_t *pud; + nr = pgd_index(limit) + 1; + for (i = 0; i < nr; i++) { + p4d_t *p4d; - if (pgdidx >= hole_low && pgdidx < hole_high) + if (i >= hole_low && i < hole_high) continue; - if (!pgd_val(pgd[pgdidx])) + if (pgd_none(pgd[i])) continue; - pud = pud_offset(&pgd[pgdidx], 0); - - if (PTRS_PER_PUD > 1) /* not folded */ - flush |= (*func)(mm, virt_to_page(pud), PT_PUD); - - for (pudidx = 0; pudidx < PTRS_PER_PUD; pudidx++) { - pmd_t *pmd; - - if (pgdidx == pgdidx_limit && - pudidx > pudidx_limit) - goto out; - - if (pud_none(pud[pudidx])) - continue; - - pmd = pmd_offset(&pud[pudidx], 0); - - if (PTRS_PER_PMD > 1) /* not folded */ - flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); - - for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) { - struct page *pte; - - if (pgdidx == pgdidx_limit && - pudidx == pudidx_limit && - pmdidx > pmdidx_limit) - goto out; - - if (pmd_none(pmd[pmdidx])) - continue; - - pte = pmd_page(pmd[pmdidx]); - flush |= (*func)(mm, pte, PT_PTE); - } - } + p4d = p4d_offset(&pgd[i], 0); + if (PTRS_PER_P4D > 1) + flush |= (*func)(mm, virt_to_page(p4d), PT_P4D); + flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); } -out: /* Do the top level last, so that the callbacks can use it as a cue to do final things like tlb flushes. */ flush |= (*func)(mm, virt_to_page(pgd), PT_PGD); @@ -1150,57 +1165,97 @@ static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) xen_free_ro_pages(pa, PAGE_SIZE); } +static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin) +{ + unsigned long pa; + pte_t *pte_tbl; + int i; + + if (pmd_large(*pmd)) { + pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PMD_SIZE); + return; + } + + pte_tbl = pte_offset_kernel(pmd, 0); + for (i = 0; i < PTRS_PER_PTE; i++) { + if (pte_none(pte_tbl[i])) + continue; + pa = pte_pfn(pte_tbl[i]) << PAGE_SHIFT; + xen_free_ro_pages(pa, PAGE_SIZE); + } + set_pmd(pmd, __pmd(0)); + xen_cleanmfnmap_free_pgtbl(pte_tbl, unpin); +} + +static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin) +{ + unsigned long pa; + pmd_t *pmd_tbl; + int i; + + if (pud_large(*pud)) { + pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PUD_SIZE); + return; + } + + pmd_tbl = pmd_offset(pud, 0); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd_none(pmd_tbl[i])) + continue; + xen_cleanmfnmap_pmd(pmd_tbl + i, unpin); + } + set_pud(pud, __pud(0)); + xen_cleanmfnmap_free_pgtbl(pmd_tbl, unpin); +} + +static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin) +{ + unsigned long pa; + pud_t *pud_tbl; + int i; + + if (p4d_large(*p4d)) { + pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, P4D_SIZE); + return; + } + + pud_tbl = pud_offset(p4d, 0); + for (i = 0; i < PTRS_PER_PUD; i++) { + if (pud_none(pud_tbl[i])) + continue; + xen_cleanmfnmap_pud(pud_tbl + i, unpin); + } + set_p4d(p4d, __p4d(0)); + xen_cleanmfnmap_free_pgtbl(pud_tbl, unpin); +} + /* * Since it is well isolated we can (and since it is perhaps large we should) * also free the page tables mapping the initial P->M table. */ static void __init xen_cleanmfnmap(unsigned long vaddr) { - unsigned long va = vaddr & PMD_MASK; - unsigned long pa; - pgd_t *pgd = pgd_offset_k(va); - pud_t *pud_page = pud_offset(pgd, 0); - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgd; + p4d_t *p4d; unsigned int i; bool unpin; unpin = (vaddr == 2 * PGDIR_SIZE); - set_pgd(pgd, __pgd(0)); - do { - pud = pud_page + pud_index(va); - if (pud_none(*pud)) { - va += PUD_SIZE; - } else if (pud_large(*pud)) { - pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; - xen_free_ro_pages(pa, PUD_SIZE); - va += PUD_SIZE; - } else { - pmd = pmd_offset(pud, va); - if (pmd_large(*pmd)) { - pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; - xen_free_ro_pages(pa, PMD_SIZE); - } else if (!pmd_none(*pmd)) { - pte = pte_offset_kernel(pmd, va); - set_pmd(pmd, __pmd(0)); - for (i = 0; i < PTRS_PER_PTE; ++i) { - if (pte_none(pte[i])) - break; - pa = pte_pfn(pte[i]) << PAGE_SHIFT; - xen_free_ro_pages(pa, PAGE_SIZE); - } - xen_cleanmfnmap_free_pgtbl(pte, unpin); - } - va += PMD_SIZE; - if (pmd_index(va)) - continue; - set_pud(pud, __pud(0)); - xen_cleanmfnmap_free_pgtbl(pmd, unpin); - } - - } while (pud_index(va) || pmd_index(va)); - xen_cleanmfnmap_free_pgtbl(pud_page, unpin); + vaddr &= PMD_MASK; + pgd = pgd_offset_k(vaddr); + p4d = p4d_offset(pgd, 0); + for (i = 0; i < PTRS_PER_P4D; i++) { + if (p4d_none(p4d[i])) + continue; + xen_cleanmfnmap_p4d(p4d + i, unpin); + } + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + set_pgd(pgd, __pgd(0)); + xen_cleanmfnmap_free_pgtbl(p4d, unpin); + } } static void __init xen_pagetable_p2m_free(void) @@ -1538,7 +1593,6 @@ static int xen_pgd_alloc(struct mm_struct *mm) BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); } #endif - return ret; } @@ -1730,7 +1784,7 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -2071,21 +2125,27 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) */ void __init xen_relocate_p2m(void) { - phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; + phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys; unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; - int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud; + int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d; pte_t *pt; pmd_t *pmd; pud_t *pud; + p4d_t *p4d = NULL; pgd_t *pgd; unsigned long *new_p2m; + int save_pud; size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT; n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT; - n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; - n_frames = n_pte + n_pt + n_pmd + n_pud; + n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT; + if (PTRS_PER_P4D > 1) + n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; + else + n_p4d = 0; + n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d; new_area = xen_find_free_area(PFN_PHYS(n_frames)); if (!new_area) { @@ -2101,55 +2161,76 @@ void __init xen_relocate_p2m(void) * To avoid any possible virtual address collision, just use * 2 * PUD_SIZE for the new area. */ - pud_phys = new_area; + p4d_phys = new_area; + pud_phys = p4d_phys + PFN_PHYS(n_p4d); pmd_phys = pud_phys + PFN_PHYS(n_pud); pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; pgd = __va(read_cr3()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); - for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { - pud = early_memremap(pud_phys, PAGE_SIZE); - clear_page(pud); - for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); - idx_pmd++) { - pmd = early_memremap(pmd_phys, PAGE_SIZE); - clear_page(pmd); - for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); - idx_pt++) { - pt = early_memremap(pt_phys, PAGE_SIZE); - clear_page(pt); - for (idx_pte = 0; - idx_pte < min(n_pte, PTRS_PER_PTE); - idx_pte++) { - set_pte(pt + idx_pte, - pfn_pte(p2m_pfn, PAGE_KERNEL)); - p2m_pfn++; + idx_p4d = 0; + save_pud = n_pud; + do { + if (n_p4d > 0) { + p4d = early_memremap(p4d_phys, PAGE_SIZE); + clear_page(p4d); + n_pud = min(save_pud, PTRS_PER_P4D); + } + for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { + pud = early_memremap(pud_phys, PAGE_SIZE); + clear_page(pud); + for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); + idx_pmd++) { + pmd = early_memremap(pmd_phys, PAGE_SIZE); + clear_page(pmd); + for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); + idx_pt++) { + pt = early_memremap(pt_phys, PAGE_SIZE); + clear_page(pt); + for (idx_pte = 0; + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + set_pte(pt + idx_pte, + pfn_pte(p2m_pfn, PAGE_KERNEL)); + p2m_pfn++; + } + n_pte -= PTRS_PER_PTE; + early_memunmap(pt, PAGE_SIZE); + make_lowmem_page_readonly(__va(pt_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, + PFN_DOWN(pt_phys)); + set_pmd(pmd + idx_pt, + __pmd(_PAGE_TABLE | pt_phys)); + pt_phys += PAGE_SIZE; } - n_pte -= PTRS_PER_PTE; - early_memunmap(pt, PAGE_SIZE); - make_lowmem_page_readonly(__va(pt_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, - PFN_DOWN(pt_phys)); - set_pmd(pmd + idx_pt, - __pmd(_PAGE_TABLE | pt_phys)); - pt_phys += PAGE_SIZE; + n_pt -= PTRS_PER_PMD; + early_memunmap(pmd, PAGE_SIZE); + make_lowmem_page_readonly(__va(pmd_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, + PFN_DOWN(pmd_phys)); + set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pmd_phys += PAGE_SIZE; } - n_pt -= PTRS_PER_PMD; - early_memunmap(pmd, PAGE_SIZE); - make_lowmem_page_readonly(__va(pmd_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, - PFN_DOWN(pmd_phys)); - set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); - pmd_phys += PAGE_SIZE; + n_pmd -= PTRS_PER_PUD; + early_memunmap(pud, PAGE_SIZE); + make_lowmem_page_readonly(__va(pud_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); + if (n_p4d > 0) + set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys)); + else + set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); + pud_phys += PAGE_SIZE; } - n_pmd -= PTRS_PER_PUD; - early_memunmap(pud, PAGE_SIZE); - make_lowmem_page_readonly(__va(pud_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); - set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); - pud_phys += PAGE_SIZE; - } + if (n_p4d > 0) { + save_pud -= PTRS_PER_P4D; + early_memunmap(p4d, PAGE_SIZE); + make_lowmem_page_readonly(__va(p4d_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys)); + set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys)); + p4d_phys += PAGE_SIZE; + } + } while (++idx_p4d < n_p4d); /* Now copy the old p2m info to the new area. */ memcpy(new_p2m, xen_p2m_addr, size); @@ -2326,6 +2407,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: + case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END: /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -2378,8 +2460,8 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; -#if CONFIG_PGTABLE_LEVELS == 4 - pv_mmu_ops.set_pgd = xen_set_pgd; +#if CONFIG_PGTABLE_LEVELS >= 4 + pv_mmu_ops.set_p4d = xen_set_p4d; #endif /* This will work as long as patching hasn't happened yet @@ -2388,7 +2470,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pmd = xen_alloc_pmd; pv_mmu_ops.release_pte = xen_release_pte; pv_mmu_ops.release_pmd = xen_release_pmd; -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif @@ -2454,10 +2536,10 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#if CONFIG_PGTABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS >= 4 .pud_val = PV_CALLEE_SAVE(xen_pud_val), .make_pud = PV_CALLEE_SAVE(xen_make_pud), - .set_pgd = xen_set_pgd_hyper, + .set_p4d = xen_set_p4d_hyper, .alloc_pud = xen_alloc_pmd_init, .release_pud = xen_release_pmd_init, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 73809bb..3fe2b32 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -5,6 +5,7 @@ enum pt_level { PT_PGD, + PT_P4D, PT_PUD, PT_PMD, PT_PTE diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 7ff2f1b..eaa3616 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -392,7 +392,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) if (ctxt == NULL) return -ENOMEM; - gdt = get_cpu_gdt_table(cpu); + gdt = get_cpu_gdt_rw(cpu); #ifdef CONFIG_X86_32 ctxt->user_regs.fs = __KERNEL_PERCPU; |
