diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-03 14:45:09 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-03 14:45:09 -0700 |
commit | 7a69f9c60b49699579f5bfb71f928cceba0afe1a (patch) | |
tree | bf3b5640bbd9f23beeb5a55d18348d65bafff8e8 | |
parent | 9bc088ab66be8978fbc981ba9644468fa2c2fd3f (diff) | |
parent | 8781fb7e9749da424e01daacd14834b674658c63 (diff) | |
download | linux-7a69f9c60b49699579f5bfb71f928cceba0afe1a.tar.gz linux-7a69f9c60b49699579f5bfb71f928cceba0afe1a.tar.bz2 linux-7a69f9c60b49699579f5bfb71f928cceba0afe1a.zip |
Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 mm updates from Ingo Molnar:
"The main changes in this cycle were:
- Continued work to add support for 5-level paging provided by future
Intel CPUs. In particular we switch the x86 GUP code to the generic
implementation. (Kirill A. Shutemov)
- Continued work to add PCID CPU support to native kernels as well.
In this round most of the focus is on reworking/refreshing the TLB
flush infrastructure for the upcoming PCID changes. (Andy
Lutomirski)"
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
x86/mm: Delete a big outdated comment about TLB flushing
x86/mm: Don't reenter flush_tlb_func_common()
x86/KASLR: Fix detection 32/64 bit bootloaders for 5-level paging
x86/ftrace: Exclude functions in head64.c from function-tracing
x86/mmap, ASLR: Do not treat unlimited-stack tasks as legacy mmap
x86/mm: Remove reset_lazy_tlbstate()
x86/ldt: Simplify the LDT switching logic
x86/boot/64: Put __startup_64() into .head.text
x86/mm: Add support for 5-level paging for KASLR
x86/mm: Make kernel_physical_mapping_init() support 5-level paging
x86/mm: Add sync_global_pgds() for configuration with 5-level paging
x86/boot/64: Add support of additional page table level during early boot
x86/boot/64: Rename init_level4_pgt and early_level4_pgt
x86/boot/64: Rewrite startup_64() in C
x86/boot/compressed: Enable 5-level paging during decompression stage
x86/boot/efi: Define __KERNEL32_CS GDT on 64-bit configurations
x86/boot/efi: Fix __KERNEL_CS definition of GDT entry on 64-bit configurations
x86/boot/efi: Cleanup initialization of GDT entries
x86/asm: Fix comment in return_from_SYSCALL_64()
x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation
...
62 files changed, 1083 insertions, 1220 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index bf3285b7532a..6491be556ddc 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1638,7 +1638,7 @@ config ARCH_SELECT_MEMORY_MODEL config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP def_bool y depends on ARM_LPAE diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index b2024db225a9..95c7ed392003 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -205,7 +205,7 @@ config GENERIC_CALIBRATE_DELAY config ZONE_DMA def_bool y -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP def_bool y config ARCH_DMA_ADDR_T_64BIT diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bf4391d18923..6189238e69f8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -184,7 +184,7 @@ config PPC select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS - select HAVE_GENERIC_RCU_GUP + select HAVE_GENERIC_GUP select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx) select HAVE_IDE select HAVE_IOREMAP_PROT diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0efb4c9497bc..737212c0333e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,7 +69,7 @@ config X86 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS - select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_FRAME_POINTERS select ARCH_WANTS_DYNAMIC_TASK_STRUCT select BUILDTIME_EXTABLE_SORT @@ -2793,6 +2793,9 @@ 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/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index cbf4b87f55b9..c3e869eaef0c 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1046,9 +1046,31 @@ struct boot_params *efi_main(struct efi_config *c, memset((char *)gdt->address, 0x0, gdt->size); desc = (struct desc_struct *)gdt->address; - /* The first GDT is a dummy and the second is unused. */ - desc += 2; + /* The first GDT is a dummy. */ + desc++; + + if (IS_ENABLED(CONFIG_X86_64)) { + /* __KERNEL32_CS */ + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } else { + /* Second entry is unused on 32-bit */ + desc++; + } + /* __KERNEL_CS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1058,12 +1080,18 @@ struct boot_params *efi_main(struct efi_config *c, desc->p = 1; desc->limit = 0xf; desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; + if (IS_ENABLED(CONFIG_X86_64)) { + desc->l = 1; + desc->d = 0; + } else { + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + } desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - desc++; + + /* __KERNEL_DS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1077,24 +1105,25 @@ struct boot_params *efi_main(struct efi_config *c, desc->d = SEG_OP_SIZE_32BIT; desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - -#ifdef CONFIG_X86_64 - /* Task segment value */ desc++; - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; -#endif /* CONFIG_X86_64 */ + + if (IS_ENABLED(CONFIG_X86_64)) { + /* Task segment value */ + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } asm volatile("cli"); asm volatile ("lgdt %0" : : "m" (*gdt)); diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d2ae1f821e0c..fbf4c32d0b62 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -346,6 +346,48 @@ preferred_addr: /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp +#ifdef CONFIG_X86_5LEVEL + /* Check if 5-level paging has already enabled */ + movq %cr4, %rax + testl $X86_CR4_LA57, %eax + jnz lvl5 + + /* + * At this point we are in long mode with 4-level paging enabled, + * but we want to enable 5-level paging. + * + * The problem is that we cannot do it directly. Setting LA57 in + * long mode would trigger #GP. So we need to switch off long mode + * first. + * + * NOTE: This is not going to work if bootloader put us above 4G + * limit. + * + * The first step is go into compatibility mode. + */ + + /* Clear additional page table */ + leaq lvl5_pgtable(%rbx), %rdi + xorq %rax, %rax + movq $(PAGE_SIZE/8), %rcx + rep stosq + + /* + * Setup current CR3 as the first and only entry in a new top level + * page table. + */ + movq %cr3, %rdi + leaq 0x7 (%rdi), %rax + movq %rax, lvl5_pgtable(%rbx) + + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq compatible_mode(%rip), %rax + pushq %rax + lretq +lvl5: +#endif + /* Zero EFLAGS */ pushq $0 popfq @@ -429,6 +471,44 @@ relocated: jmp *%rax .code32 +#ifdef CONFIG_X86_5LEVEL +compatible_mode: + /* Setup data and stack segments */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %ss + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Point CR3 to 5-level paging */ + leal lvl5_pgtable(%ebx), %eax + movl %eax, %cr3 + + /* Enable PAE and LA57 mode */ + movl %cr4, %eax + orl $(X86_CR4_PAE | X86_CR4_LA57), %eax + movl %eax, %cr4 + + /* Calculate address we are running at */ + call 1f +1: popl %edi + subl $1b, %edi + + /* Prepare stack for far return to Long Mode */ + pushl $__KERNEL_CS + leal lvl5(%edi), %eax + push %eax + + /* Enable paging back */ + movl $(X86_CR0_PG | X86_CR0_PE), %eax + movl %eax, %cr0 + + lret +#endif + no_longmode: /* This isn't an x86-64 CPU so hang */ 1: @@ -442,7 +522,7 @@ gdt: .word gdt_end - gdt .long gdt .word 0 - .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ .quad 0x00af9a000000ffff /* __KERNEL_CS */ .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ @@ -486,3 +566,7 @@ boot_stack_end: .balign 4096 pgtable: .fill BOOT_PGT_SIZE, 1, 0 +#ifdef CONFIG_X86_5LEVEL +lvl5_pgtable: + .fill PAGE_SIZE, 1, 0 +#endif diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 1d78f1739087..28029be47fbb 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -63,7 +63,7 @@ static void *alloc_pgt_page(void *context) static struct alloc_pgt_data pgt_data; /* The top level page table entry pointer. */ -static unsigned long level4p; +static unsigned long top_level_pgt; /* * Mapping information structure passed to kernel_ident_mapping_init(). @@ -91,9 +91,15 @@ void initialize_identity_maps(void) * If we came here via startup_32(), cr3 will be _pgtable already * and we must append to the existing area instead of entirely * overwriting it. + * + * With 5-level paging, we use '_pgtable' to allocate the p4d page table, + * the top-level page table is allocated separately. + * + * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level + * cases. On 4-level paging it's equal to 'top_level_pgt'. */ - level4p = read_cr3(); - if (level4p == (unsigned long)_pgtable) { + top_level_pgt = read_cr3_pa(); + if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; @@ -103,7 +109,7 @@ void initialize_identity_maps(void) pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); - level4p = (unsigned long)alloc_pgt_page(&pgt_data); + top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } } @@ -123,7 +129,7 @@ void add_identity_map(unsigned long start, unsigned long size) return; /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p, + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); } @@ -134,5 +140,5 @@ void add_identity_map(unsigned long start, unsigned long size) */ void finalize_identity_maps(void) { - write_cr3(level4p); + write_cr3(top_level_pgt); } diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4a4c0834f965..a9a8027a6c0e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -265,7 +265,8 @@ 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 + * Change top bits to match most significant bit (47th or 56th bit + * depending on paging mode) in the address. */ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 628b8c556aab..2de0dd73830a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2111,8 +2111,7 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->active_mm) - load_mm_cr4(current->active_mm); + load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } static void x86_pmu_event_mapped(struct perf_event *event) @@ -2344,7 +2343,7 @@ static unsigned long get_segment_base(unsigned int segment) /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->size) + if (!ldt || idx > ldt->nr_entries) return 0; desc = &ldt->entries[idx]; diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2f77bcefe6b4..d2ff779f347e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -74,7 +74,7 @@ struct efi_scratch { __kernel_fpu_begin(); \ \ if (efi_scratch.use_pgd) { \ - efi_scratch.prev_cr3 = read_cr3(); \ + efi_scratch.prev_cr3 = __read_cr3(); \ write_cr3((unsigned long)efi_scratch.efi_pgt); \ __flush_tlb_all(); \ } \ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 59405a248fc2..9b76cd331990 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,8 +22,8 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - unsigned int irq_tlb_count; #endif + unsigned int irq_tlb_count; #ifdef CONFIG_X86_THERMAL_VECTOR unsigned int irq_thermal_count; #endif diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index f9813b6d8b80..79b647a7ebd0 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,12 +37,6 @@ typedef struct { #endif } mm_context_t; -#ifdef CONFIG_SMP void leave_mm(int cpu); -#else -static inline void leave_mm(int cpu) -{ -} -#endif #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 68b329d77b3a..ecfcb6643c9b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -47,7 +47,7 @@ struct ldt_struct { * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; - unsigned int size; + unsigned int nr_entries; }; /* @@ -87,22 +87,46 @@ static inline void load_mm_ldt(struct mm_struct *mm) */ if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->size); + set_ldt(ldt->entries, ldt->nr_entries); else clear_LDT(); #else clear_LDT(); #endif +} + +static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ +#ifdef CONFIG_MODIFY_LDT_SYSCALL + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { -#ifdef CONFIG_SMP if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); -#endif } static inline int init_new_context(struct task_struct *tsk, @@ -220,18 +244,6 @@ 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 @@ -268,4 +280,23 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } + +/* + * This can be used from process context to figure out what the value of + * CR3 is without needing to do a (slow) __read_cr3(). + * + * It's intended to be used for code like KVM that sneakily changes CR3 + * and needs to restore it. It needs to be used very carefully. + */ +static inline unsigned long __get_current_cr3_fast(void) +{ + unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); + + /* For now, be very restrictive about when this can be called. */ + VM_WARN_ON(in_nmi() || !in_atomic()); + + VM_BUG_ON(cr3 != __read_cr3()); + return cr3; +} + #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index a3dcf8944cb9..9ccac1926587 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -61,7 +61,7 @@ static inline void write_cr2(unsigned long x) PVOP_VCALL1(pv_mmu_ops.write_cr2, x); } -static inline unsigned long read_cr3(void) +static inline unsigned long __read_cr3(void) { return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3); } @@ -312,11 +312,9 @@ static inline void __flush_tlb_single(unsigned long addr) } static inline void flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end); + PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7465d6fe336f..cb976bab6299 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -51,6 +51,7 @@ struct mm_struct; struct desc_struct; struct task_struct; struct cpumask; +struct flush_tlb_info; /* * Wrapper type for pointers to code which uses the non-standard @@ -223,9 +224,7 @@ struct pv_mmu_ops { void (*flush_tlb_kernel)(void); void (*flush_tlb_single)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, - struct mm_struct *mm, - unsigned long start, - unsigned long end); + const struct flush_tlb_info *info); /* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm); diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 50d35e3185f5..c8821bab938f 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -212,4 +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.h b/arch/x86/include/asm/pgtable.h index f5af95a0c6b8..77037b6f1caa 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -244,6 +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 */ @@ -917,7 +922,7 @@ extern pgd_t trampoline_pgd_entry; static inline void __meminit init_trampoline_default(void) { /* Default trampoline pgd value */ - trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)]; + trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; } # ifdef CONFIG_RANDOMIZE_MEMORY void __meminit init_trampoline(void); @@ -1185,6 +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_64.h b/arch/x86/include/asm/pgtable_64.h index 9991224f6238..2160c1fee920 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,15 +14,17 @@ #include <linux/bitops.h> #include <linux/threads.h> +extern p4d_t level4_kernel_pgt[512]; +extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512]; -extern pgd_t init_level4_pgt[]; +extern pgd_t init_top_pgt[]; -#define swapper_pg_dir init_level4_pgt +#define swapper_pg_dir init_top_pgt extern void paging_init(void); @@ -227,6 +229,20 @@ 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/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 39fb618e2211..79aa2f98398d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -8,4 +8,40 @@ #else #define X86_VM_MASK 0 /* No VM86 support */ #endif + +/* + * CR3's layout varies depending on several things. + * + * If CR4.PCIDE is set (64-bit only), then CR3[11:0] is the address space ID. + * If PAE is enabled, then CR3[11:5] is part of the PDPT address + * (i.e. it's 32-byte aligned, not page-aligned) and CR3[4:0] is ignored. + * Otherwise (non-PAE, non-PCID), CR3[3] is PWT, CR3[4] is PCD, and + * CR3[2:0] and CR3[11:5] are ignored. + * + * In all cases, Linux puts zeros in the low ignored bits and in PWT and PCD. + * + * CR3[63] is always read as zero. If CR4.PCIDE is set, then CR3[63] may be + * written as 1 to prevent the write to CR3 from flushing the TLB. + * + * On systems with SME, one bit (in a variable position!) is stolen to indicate + * that the top-level paging structure is encrypted. + * + * All of the remaining bits indicate the physical address of the top-level + * paging structure. + * + * CR3_ADDR_MASK is the mask used by read_cr3_pa(). + */ +#ifdef CONFIG_X86_64 +/* Mask off the address space ID bits. */ +#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull +#define CR3_PCID_MASK 0xFFFull +#else +/* + * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save + * a tiny bit of code size by setting all the bits. + */ +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#endif + #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a28b671f1549..2e1696294af5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -231,6 +231,14 @@ native_cpuid_reg(ebx) native_cpuid_reg(ecx) native_cpuid_reg(edx) +/* + * Friendlier CR3 helpers. + */ +static inline unsigned long read_cr3_pa(void) +{ + return __read_cr3() & CR3_ADDR_MASK; +} + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 12af3e35edfa..9efaabf5b54b 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -39,7 +39,7 @@ static inline void native_write_cr2(unsigned long val) asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); } -static inline unsigned long native_read_cr3(void) +static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); @@ -159,9 +159,13 @@ static inline void write_cr2(unsigned long x) native_write_cr2(x); } -static inline unsigned long read_cr3(void) +/* + * Careful! CR3 contains more than just an address. You probably want + * read_cr3_pa() instead. + */ +static inline unsigned long __read_cr3(void) { - return native_read_cr3(); + return __native_read_cr3(); } static inline void write_cr3(unsigned long x) diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 000000000000..f4a6ff352a0e --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,14 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include <linux/cpumask.h> + +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6ed9ea469b48..50ea3482e1d1 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -7,6 +7,7 @@ #include <asm/processor.h> #include <asm/cpufeature.h> #include <asm/special_insns.h> +#include <asm/smp.h> static inline void __invpcid(unsigned long pcid, unsigned long addr, unsigned long type) @@ -65,10 +66,14 @@ static inline void invpcid_flush_all_nonglobals(void) #endif struct tlb_state { -#ifdef CONFIG_SMP - struct mm_struct *active_mm; + /* + * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts + * are on. This means that it may not match current->active_mm, + * which will contain the previous user mm when we're in lazy TLB + * mode even if we've already switched back to swapper_pg_dir. + */ + struct mm_struct *loaded_mm; int state; -#endif /* * Access to this CR4 shadow and to H/W CR4 is protected by @@ -151,7 +156,7 @@ static inline void __native_flush_tlb(void) * back: */ preempt_disable(); - native_write_cr3(native_read_cr3()); + native_write_cr3(__native_read_cr3()); preempt_enable(); } @@ -220,84 +225,16 @@ static inline void __flush_tlb_one(unsigned long addr) * - flush_tlb_page(vma, vmaddr) flushes one page * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus + * - flush_tlb_others(cpumask, info) flushes TLBs on other cpus * * ..but the i386 has somewhat limited tlb flushing capabilities, * and page-granular flushes are available only on i486 and up. */ - -#ifndef CONFIG_SMP - -/* "_up" is for UniProcessor. - * - * This is a helper for other header functions. *Not* intended to be called - * directly. All global TLB flushes need to either call this, or to bump the - * vm statistics themselves. - */ -static inline void __flush_tlb_up(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); -} - -static inline void flush_tlb_all(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb_all(); -} - -static inline void local_flush_tlb(void) -{ - __flush_tlb_up(); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_mm_range(struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned long vmflag) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ -} - -static inline void reset_lazy_tlbstate(void) -{ -} - -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - flush_tlb_all(); -} - -#else /* SMP */ - -#include <asm/smp.h> +struct flush_tlb_info { + struct mm_struct *mm; + unsigned long start; + unsigned long end; +}; #define local_flush_tlb() __flush_tlb() @@ -307,29 +244,32 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); +} + void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, unsigned long end); + const struct flush_tlb_info *info); #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 -static inline void reset_lazy_tlbstate(void) +static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) { - this_cpu_write(cpu_tlbstate.state, 0); - this_cpu_write(cpu_tlbstate.active_mm, &init_mm); + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } -#endif /* SMP */ +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); #ifndef CONFIG_PARAVIRT -#define flush_tlb_others(mask, mm, start, end) \ - native_flush_tlb_others(mask, mm, start, end) +#define flush_tlb_others(mask, info) \ + native_flush_tlb_others(mask, info) #endif #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 6686820feae9..b5a32231abd8 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H +#include <asm/tlbflush.h> + enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; struct cpumask; @@ -15,10 +17,7 @@ extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu); + const struct flush_tlb_info *info); #else /* X86_UV */ @@ -28,8 +27,8 @@ static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned int cpu) +uv_flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) { return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 567de50a4c2a..185f3d10c194 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -104,6 +104,8 @@ #define X86_CR4_OSFXSR _BITUL(X86_CR4_OSFXSR_BIT) #define X86_CR4_OSXMMEXCPT_BIT 10 /* enable unmasked SSE exceptions */ #define X86_CR4_OSXMMEXCPT _BITUL(X86_CR4_OSXMMEXCPT_BIT) +#define X86_CR4_LA57_BIT 12 /* enable 5-level page tables */ +#define X86_CR4_LA57 _BITUL(X86_CR4_LA57_BIT) #define X86_CR4_VMXE_BIT 13 /* enable VMX virtualization */ #define X86_CR4_VMXE _BITUL(X86_CR4_VMXE_BIT) #define X86_CR4_SMXE_BIT 14 /* enable safer mode (TXT) */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 3c7c419c4e3e..a01892bdd61a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -18,6 +18,7 @@ CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg +CFLAGS_REMOVE_head64.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 8e598a1ad986..6b91e2eb8d3f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -125,7 +125,7 @@ void __init init_espfix_bsp(void) p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); p4d_populate(&init_mm, p4d, espfix_pud_page); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 43b7002f44fb..46c3c73e7f43 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -33,17 +33,120 @@ /* * Manage page tables very early on. */ -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; -static unsigned int __initdata next_early_pgt = 2; +static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +#define __head __section(.head.text) + +static void __head *fixup_pointer(void *ptr, unsigned long physaddr) +{ + return ptr - (void *)_text + (void *)physaddr; +} + +void __head __startup_64(unsigned long physaddr) +{ + unsigned long load_delta, *p; + pgdval_t *pgd; + p4dval_t *p4d; + pudval_t *pud; + pmdval_t *pmd, pmd_entry; + int i; + + /* Is the address too large? */ + if (physaddr >> MAX_PHYSMEM_BITS) + for (;;); + + /* + * Compute the delta between the address I am compiled to run at + * and the address I am actually running at. + */ + load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + + /* Is the address not 2M aligned? */ + if (load_delta & ~PMD_PAGE_MASK) + for (;;); + + /* Fixup the physical addresses in the page table */ + + pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd[pgd_index(__START_KERNEL_map)] += load_delta; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d[511] += load_delta; + } + + pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud[510] += load_delta; + pud[511] += load_delta; + + pmd = fixup_pointer(level2_fixmap_pgt, physaddr); + pmd[506] += load_delta; + + /* + * Set up the identity mapping for the switchover. These + * entries should *NOT* have the global bit set! This also + * creates a bunch of nonsense entries but that is fine -- + * it avoids problems around wraparound. + */ + + pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + + i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; + p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } else { + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } + + i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; + pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + + pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += physaddr; + + for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { + int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; + pmd[idx] = pmd_entry + i * PMD_SIZE; + } + + /* + * Fixup the kernel text+data virtual addresses. Note that + * we might write invalid pmds, when the kernel is relocated + * cleanup_highmap() fixes this up along with the mappings + * beyond _end. + */ + + pmd = fixup_pointer(level2_kernel_pgt, physaddr); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd[i] & _PAGE_PRESENT) + pmd[i] += load_delta; + } + + /* Fixup phys_base */ + p = fixup_pointer(&phys_base, physaddr); + *p += load_delta; +} + /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { - memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); + memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_level4_pgt)); + write_cr3(__pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ @@ -51,15 +154,16 @@ int __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; + p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; /* Invalid address or early pgt is done ? */ - if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt)) + if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) return -1; again: - pgd_p = &early_level4_pgt[pgd_index(address)].pgd; + pgd_p = &early_top_pgt[pgd_index(address)].pgd; pgd = *pgd_p; /* @@ -67,8 +171,25 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (pgd) - pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = pgd_p; + else if (pgd) + p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { + reset_early_page_tables(); + goto again; + } + + p4d_p = (p4dval_t *)early_dynamic_pgts[next_early_pgt++]; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + *pgd_p = (pgdval_t)p4d_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + p4d_p += p4d_index(address); + p4d = *p4d_p; + + if (p4d) + pud_p = (pudval_t *)((p4d & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); else { if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { reset_early_page_tables(); @@ -77,7 +198,7 @@ again: pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + *p4d_p = (p4dval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pud_p += pud_index(address); pud = *pud_p; @@ -156,7 +277,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); - clear_page(init_level4_pgt); + clear_page(init_top_pgt); kasan_early_init(); @@ -171,8 +292,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - /* set init_level4_pgt kernel high mapping*/ - init_level4_pgt[511] = early_level4_pgt[511]; + /* set init_top_pgt kernel high mapping*/ + init_top_pgt[511] = early_top_pgt[511]; x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ac9d327d2e42..6225550883df 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -37,10 +37,11 @@ * */ +#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) -L4_START_KERNEL = pgd_index(__START_KERNEL_map) +PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) +PGD_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -72,101 +73,12 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu - /* - * Compute the delta between the address I am compiled to run at and the - * address I am actually running at. - */ - leaq _text(%rip), %rbp - subq $_text - __START_KERNEL_map, %rbp - - /* Is the address not 2M aligned? */ - testl $~PMD_PAGE_MASK, %ebp - jnz bad_address - - /* - * Is the address too large? - */ - leaq _text(%rip), %rax - shrq $MAX_PHYSMEM_BITS, %rax - jnz bad_address - - /* - * Fixup the physical addresses in the page table - */ - addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip) - - addq %rbp, level3_kernel_pgt + (510*8)(%rip) - addq %rbp, level3_kernel_pgt + (511*8)(%rip) - - addq %rbp, level2_fixmap_pgt + (506*8)(%rip) - - /* - * Set up the identity mapping for the switchover. These - * entries should *NOT* have the global bit set! This also - * creates a bunch of nonsense entries but that is fine -- - * it avoids problems around wraparound. - */ leaq _text(%rip), %rdi - leaq early_level4_pgt(%rip), %rbx - - movq %rdi, %rax - shrq $PGDIR_SHIFT, %rax - - leaq (PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx - movq %rdx, 0(%rbx,%rax,8) - movq %rdx, 8(%rbx,%rax,8) - - addq $PAGE_SIZE, %rdx - movq %rdi, %rax - shrq $PUD_SHIFT, %rax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - incl %eax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - - addq $PAGE_SIZE * 2, %rbx - movq %rdi, %rax - shrq $PMD_SHIFT, %rdi - addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax - leaq (_end - 1)(%rip), %rcx - shrq $PMD_SHIFT, %rcx - subq %rdi, %rcx - incl %ecx - -1: - andq $(PTRS_PER_PMD - 1), %rdi - movq %rax, (%rbx,%rdi,8) - incq %rdi - addq $PMD_SIZE, %rax - decl %ecx - jnz 1b - - test %rbp, %rbp - jz .Lskip_fixup + pushq %rsi + call __startup_64 + popq %rsi - /* - * Fixup the kernel text+data virtual addresses. Note that - * we might write invalid pmds, when the kernel is relocated - * cleanup_highmap() fixes this up along with the mappings - * beyond _end. - */ - leaq level2_kernel_pgt(%rip), %rdi - leaq PAGE_SIZE(%rdi), %r8 - /* See if it is a valid page table entry */ -1: testb $_PAGE_PRESENT, 0(%rdi) - jz 2f - addq %rbp, 0(%rdi) - /* Go to the next page */ -2: addq $8, %rdi - cmp %r8, %rdi - jne 1b - - /* Fixup phys_base */ - addq %rbp, phys_base(%rip) - -.Lskip_fixup: - movq $(early_level4_pgt - __START_KERNEL_map), %rax + movq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -186,14 +98,17 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_level4_pgt - __START_KERNEL_map), %rax + movq $(init_top_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ + /* Enable PAE mode, PGE and LA57 */ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx +#ifdef CONFIG_X86_5LEVEL + orl $X86_CR4_LA57, %ecx +#endif movq %rcx, %cr4 - /* Setup early boot stage 4 level pagetables. */ + /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax movq %rax, %cr3 @@ -417,9 +332,13 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PAGE(early_top_pgt) .fill 511,8,0 +#ifdef CONFIG_X86_5LEVEL + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -427,14 +346,14 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 + .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_START_KERNEL*8, 0 + .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -448,6 +367,12 @@ NEXT_PAGE(level2_ident_pgt) PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif +#ifdef CONFIG_X86_5LEVEL +NEXT_PAGE(level4_kernel_pgt) + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif + NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d4a15831ac58..a870910c8565 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -22,24 +22,25 @@ #include <asm/syscalls.h> /* context.lock is held for us, so we don't need any locking. */ -static void flush_ldt(void *current_mm) +static void flush_ldt(void *__mm) { + struct mm_struct *mm = __mm; mm_context_t *pc; - if (current->active_mm != current_mm) + if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = ¤t->active_mm->context; - set_ldt(pc->ldt->entries, pc->ldt->size); + pc = &mm->context; + set_ldt(pc->ldt->entries, pc->ldt->nr_entries); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ -static struct ldt_struct *alloc_ldt_struct(unsigned int size) +static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; - if (size > LDT_ENTRIES) + if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); @@ -47,7 +48,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); - alloc_size = size * LDT_ENTRY_SIZE; + alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no @@ -65,14 +66,14 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; } - new_ldt->size = size; + new_ldt->nr_entries = num_entries; return new_ldt; } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { - paravirt_alloc_ldt(ldt->entries, ldt->size); + paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } /* context.lock is held */ @@ -91,8 +92,8 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; - paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + paravirt_free_ldt(ldt->entries, ldt->nr_entries); + if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); @@ -122,14 +123,14 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) goto out_unlock; } - new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, - new_ldt->size * LDT_ENTRY_SIZE); + new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); mm->context.ldt = new_ldt; @@ -152,9 +153,9 @@ void destroy_context_ldt(struct mm_struct *mm) static int read_ldt(void __user *ptr, unsigned long bytecount) { - int retval; - unsigned long size; struct mm_struct *mm = current->mm; + unsigned long entries_size; + int retval; mutex_lock(&mm->context.lock); @@ -166,18 +167,18 @@ static int read_ldt(void __user *ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - size = mm->context.ldt->size * LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; + entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; + if (entries_size > bytecount) + entries_size = bytecount; - if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } - if (size != bytecount) { + if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ - if (clear_user(ptr + size, bytecount - size)) { + if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } @@ -208,7 +209,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; - unsigned int oldsize, newsize; + unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; @@ -247,17 +248,18 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) mutex_lock(&mm->context.lock); - old_ldt = mm->context.ldt; - oldsize = old_ldt ? old_ldt->size : 0; - newsize = max(ldt_info.entry_number + 1, oldsize); + old_ldt = mm->context.ldt; + old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; + new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; - new_ldt = alloc_ldt_struct(newsize); + new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) - memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6f5ca4ebe6e5..cb0a30473c23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -347,7 +347,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_level4_pgt); + VMCOREINFO_SYMBOL(init_top_pgt); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3586996fc50d..bc0a849589bb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -391,7 +391,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, - .read_cr3 = native_read_cr3, + .read_cr3 = __native_read_cr3, .write_cr3 = native_write_cr3, .flush_tlb_user = native_flush_tlb, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ffeae818aa7a..c6d6dc5f8bb2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -92,7 +92,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b6840bf3940b..c3169be4c596 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -104,7 +104,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", @@ -142,7 +142,7 @@ void release_thread(struct task_struct *dead_task) pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt->entries, - dead_task->mm->context.ldt->size); + dead_task->mm->context.ldt->nr_entries); BUG(); } #endif diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 045e4f993bd2..b474c8de7fba 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1589,7 +1589,6 @@ void native_cpu_die(unsigned int cpu) void play_dead_common(void) { idle_task_exit(); - reset_lazy_tlbstate(); /* Ack it */ (void)cpu_report_death(); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f07f83b3611b..5f25cfbd952e 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -34,7 +34,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re mutex_lock(&child->mm->context.lock); if (unlikely(!child->mm->context.ldt || - seg >= child->mm->context.ldt->size)) + seg >= child->mm->context.ldt->nr_entries)) addr = -1L; /* bogus selector, access would fault */ else { desc = &child->mm->context.ldt->entries[seg]; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1b469b6c762f..6dcc4873e435 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -49,6 +49,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/mmu_context.h> #include "trace.h" #include "pmu.h" @@ -597,6 +598,7 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { @@ -5013,12 +5015,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; - unsigned long cr0, cr4; + unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + + /* + * Save the most likely value for this task's CR3 in the VMCS. + * We can't use __get_current_cr3_fast() because we're not atomic. + */ + cr3 = __read_cr3(); + vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ + vmx->host_state.vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); @@ -8822,7 +8831,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr4; + unsigned long debugctlmsr, cr3, cr4; /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ @@ -8844,6 +8853,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->host_state.vmcs_host_cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 5e044d506b7a..a179254a5122 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -27,7 +27,7 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) #ifdef CONFIG_MODIFY_LDT_SYSCALL seg >>= 3; mutex_lock(¤t->mm->context.lock); - if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + if (current->mm->context.ldt && seg < current->mm->context.ldt->nr_entries) ret = current->mm->context.ldt->entries[seg]; mutex_unlock(¤t->mm->context.lock); #endif diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 96d2b847e09e..0fbdcb64f9f8 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 bce6990b1d81..0470826d2bdc 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -431,7 +431,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, bool checkwx) { #ifdef CONFIG_X86_64 - pgd_t *start = (pgd_t *) &init_level4_pgt; + pgd_t *start = (pgd_t *) &init_top_pgt; #else pgd_t *start = swapper_pg_dir; #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8ad91a01cbc8..2a1fa10c6a98 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -346,7 +346,7 @@ static noinline int vmalloc_fault(unsigned long address) * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ - pgd_paddr = read_cr3(); + pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; @@ -388,7 +388,7 @@ static bool low_pfn(unsigned long pfn) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3()); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; @@ -451,7 +451,7 @@ static noinline int vmalloc_fault(unsigned long address) * happen within a race in page table update. In the later * case just flush: */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address); + pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address); pgd_ref = pgd_offset_k(address); if (pgd_none(*pgd_ref)) return -1; @@ -555,7 +555,7 @@ static int bad_address(void *p) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; @@ -700,7 +700,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, pgd_t *pgd; pte_t *pte; - pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c deleted file mode 100644 index 456dfdfd2249..000000000000 --- a/arch/x86/mm/gup.c +++ /dev/null @@ -1,496 +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, pud or p4d. We only check - * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 4 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, ret = 0; - pte_t *ptep, *ptem; - - /* - * Keep the original mapped PTE value (ptem) around since we - * might increment ptep off the end of the page when finishing - * our loop iteration. - */ - ptem = 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)) - break; - - if (!pte_allows_gup(pte_val(pte), write)) - break; - - if (pte_devmap(pte)) { - pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - break; - } - } else if (pte_special(pte)) - break; - - 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); - if (addr == end) - ret = 1; - pte_unmap(ptem); - - return ret; -} - -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(p4d_t p4d, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&p4d, 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; -} - -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - p4d_t *p4dp; - - p4dp = p4d_offset(&pgd, addr); - do { - p4d_t p4d = *p4dp; - - next = p4d_addr_end(addr, end); - if (p4d_none(p4d)) - return 0; - BUILD_BUG_ON(p4d_large(p4d)); - if (!gup_pud_range(p4d, addr, next, write, pages, nr)) - return 0; - } while (p4dp++, 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_p4d_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_p4d_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/init.c b/arch/x86/mm/init.c index 9b3f9fa5b283..673541eb3b3f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -811,10 +811,8 @@ void __init zone_sizes_init(void) } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { -#ifdef CONFIG_SMP - .active_mm = &init_mm, + .loaded_mm = &init_mm, .state = 0, -#endif .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 0a59daf799f8..dae6a5e5ad4a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -92,6 +92,44 @@ __setup("noexec32=", nonx32_setup); * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ +#ifdef CONFIG_X86_5LEVEL +void sync_global_pgds(unsigned long start, unsigned long end) +{ + unsigned long addr; + + for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + const pgd_t *pgd_ref = pgd_offset_k(addr); + struct page *page; + + /* Check for overflow */ + if (addr < start) + break; + + if (pgd_none(*pgd_ref)) + continue; + + spin_lock(&pgd_lock); + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd; + spinlock_t *pgt_lock; + + pgd = (pgd_t *)page_address(page) + pgd_index(addr); + /* 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 (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + + spin_unlock(pgt_lock); + } + spin_unlock(&pgd_lock); + } +} +#else void sync_global_pgds(unsigned long start, unsigned long end) { unsigned long addr; @@ -135,6 +173,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(&pgd_lock); } } +#endif /* * NOTE: This function is marked __ref because it calls __init function @@ -585,6 +624,57 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, return paddr_last; } +static unsigned long __meminit +phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, + unsigned long page_size_mask) +{ + unsigned long paddr_next, paddr_last = paddr_end; + unsigned long vaddr = (unsigned long)__va(paddr); + int i = p4d_index(vaddr); + + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask); + + for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d; + pud_t *pud; + + vaddr = (unsigned long)__va(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + if (paddr >= paddr_end) { + if (!after_bootmem && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) + set_p4d(p4d, __p4d(0)); + continue; + } + + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, 0); + paddr_last = phys_pud_init(pud, paddr, + paddr_end, + page_size_mask); + __flush_tlb_all(); + continue; + } + + pud = alloc_low_page(); + paddr_last = phys_pud_init(pud, paddr, paddr_end, + page_size_mask); + + spin_lock(&init_mm.page_table_lock); + p4d_populate(&init_mm, p4d, pud); + spin_unlock(&init_mm.page_table_lock); + } + __flush_tlb_all(); + + return paddr_last; +} + /* * Create page table mapping for the physical memory for specific physical * addresses. The virtual and physical addresses have to be aligned on PMD level @@ -606,26 +696,26 @@ 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; - 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), + if (pgd_val(*pgd)) { + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } - pud = alloc_low_page(); - paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), + p4d = alloc_low_page(); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); spin_lock(&init_mm.page_table_lock); - p4d_populate(&init_mm, p4d, pud); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + pgd_populate(&init_mm, pgd, p4d); + else + p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index bbc558b88a88..4c1b5fd0c7ad 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -424,7 +424,7 @@ static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; 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 *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(addr)]; p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0c7d8129bed6..88215ac16b24 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -12,7 +12,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) @@ -109,8 +109,8 @@ void __init kasan_early_init(void) 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); + kasan_map_early_shadow(early_top_pgt); + kasan_map_early_shadow(init_top_pgt); } void __init kasan_init(void) @@ -121,8 +121,8 @@ void __init kasan_init(void) register_die_notifier(&kasan_die_notifier); #endif - memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt)); - load_cr3(early_level4_pgt); + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + load_cr3(early_top_pgt); __flush_tlb_all(); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -148,7 +148,7 @@ void __init kasan_init(void) kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); - load_cr3(init_level4_pgt); + load_cr3(init_top_pgt); __flush_tlb_all(); /* diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index aed206475aa7..af599167fe3c 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -6,12 +6,12 @@ * * Entropy is generated using the KASLR early boot functions now shared in * the lib directory (originally written by Kees Cook). Randomization is - * done on PGD & PUD page table levels to increase possible addresses. The - * physical memory mapping code was adapted to support PUD level virtual - * addresses. This implementation on the best configuration provides 30,000 - * possible virtual addresses in average for each memory region. An additional - * low memory page is used to ensure each CPU can start with a PGD aligned - * virtual address (for realmode). + * done on PGD & P4D/PUD page table levels to increase possible addresses. + * The physical memory mapping code was adapted to support P4D/PUD level + * virtual addresses. This implementation on the best configuration provides + * 30,000 possible virtual addresses in average for each memory region. + * An additional low memory page is used to ensure each CPU can start with + * a PGD aligned virtual address (for realmode). * * The order of each memory region is not changed. The feature looks at * the available space for the regions based on different configuration @@ -70,7 +70,7 @@ static __initdata struct kaslr_memory_region { unsigned long *base; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 64/* Maximum */ }, + { &page_offset_base, 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT) /* Maximum */ }, { &vmalloc_base, VMALLOC_SIZE_TB }, { &vmemmap_base, 1 }, }; @@ -142,7 +142,10 @@ void __init kernel_randomize_memory(void) */ entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); prandom_bytes_state(&rand_state, &rand, sizeof(rand)); - entropy = (rand % (entropy + 1)) & PUD_MASK; + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + entropy = (rand % (entropy + 1)) & P4D_MASK; + else + entropy = (rand % (entropy + 1)) & PUD_MASK; vaddr += entropy; *kaslr_regions[i].base = vaddr; @@ -151,27 +154,21 @@ void __init kernel_randomize_memory(void) * randomization alignment. */ vaddr += get_padding(&kaslr_regions[i]); - vaddr = round_up(vaddr + 1, PUD_SIZE); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + vaddr = round_up(vaddr + 1, P4D_SIZE); + else + vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } } -/* - * Create PGD aligned trampoline table to allow real mode initialization - * of additional CPUs. Consume only 1 low memory page. - */ -void __meminit init_trampoline(void) +static void __meminit init_trampoline_pud(void) { unsigned long paddr, paddr_next; pgd_t *pgd; pud_t *pud_page, *pud_page_tramp; int i; - if (!kaslr_memory_enabled()) { - init_trampoline_default(); - return; - } - pud_page_tramp = alloc_low_page(); paddr = 0; @@ -192,3 +189,49 @@ void __meminit init_trampoline(void) set_pgd(&trampoline_pgd_entry, __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); } + +static void __meminit init_trampoline_p4d(void) +{ + unsigned long paddr, paddr_next; + pgd_t *pgd; + p4d_t *p4d_page, *p4d_page_tramp; + int i; + + p4d_page_tramp = alloc_low_page(); + + paddr = 0; + pgd = pgd_offset_k((unsigned long)__va(paddr)); + p4d_page = (p4d_t *) pgd_page_vaddr(*pgd); + + for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d, *p4d_tramp; + unsigned long vaddr = (unsigned long)__va(paddr); + + p4d_tramp = p4d_page_tramp + p4d_index(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + *p4d_tramp = *p4d; + } + + set_pgd(&trampoline_pgd_entry, + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); +} + +/* + * Create PGD aligned trampoline table to allow real mode initialization + * of additional CPUs. Consume only 1 low memory page. + */ +void __meminit init_trampoline(void) +{ + + if (!kaslr_memory_enabled()) { + init_trampoline_default(); + return; + } + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + init_trampoline_p4d(); + else + init_trampoline_pud(); +} diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 19ad095b41df..797295e792b2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -74,9 +74,6 @@ static int mmap_is_legacy(void) if (current->personality & ADDR_COMPAT_LAYOUT) return 1; - if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) - return 1; - return sysctl_legacy_va_layout; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6e7bedf69af7..014d07a80053 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -15,7 +15,7 @@ #include <linux/debugfs.h> /* - * Smarter SMP flushing macros. + * TLB flushing, formerly SMP-only * c/o Linus Torvalds. * * These mean you can really definitely utterly forget about @@ -28,39 +28,28 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ -#ifdef CONFIG_SMP - -struct flush_tlb_info { - struct mm_struct *flush_mm; - unsigned long flush_start; - unsigned long flush_end; -}; - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - */ void leave_mm(int cpu) { - struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm); + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + + /* + * It's plausible that we're in lazy TLB mode while our mm is init_mm. + * If so, our callers still expect us to flush the TLB, but there + * aren't any user TLB entries in init_mm to worry about. + * + * This needs to happen before any other sanity checks due to + * intel_idle's shenanigans. + */ + if (loaded_mm == &init_mm) + return; + if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) BUG(); - if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { - cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); - load_cr3(swapper_pg_dir); - /* - * This gets called in the idle path where RCU - * functions differently. Tracing normally - * uses RCU, so we have to call the tracepoint - * specially here. - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - } + + switch_mm(NULL, &init_mm, NULL); } EXPORT_SYMBOL_GPL(leave_mm); -#endif /* CONFIG_SMP */ - void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -75,216 +64,167 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { unsigned cpu = smp_processor_id(); + struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); - if (likely(prev != next)) { - if (IS_ENABLED(CONFIG_VMAP_STACK)) { - /* - * If our current stack is in vmalloc space and isn't - * mapped in the new pgd, we'll double-fault. Forcibly - * map it. - */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - - pgd_t *pgd = next->pgd + stack_pgd_index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[stack_pgd_index]); - } + /* + * NB: The scheduler will call us with prev == next when + * switching from lazy TLB mode to normal mode if active_mm + * isn't changing. When this happens, there is no guarantee + * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next. + * + * NB: leave_mm() calls us with prev == NULL and tsk == NULL. + */ -#ifdef CONFIG_SMP - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - this_cpu_write(cpu_tlbstate.active_mm, next); -#endif + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - cpumask_set_cpu(cpu, mm_cpumask(next)); + if (real_prev == next) { + /* + * There's nothing to do: we always keep the per-mm control + * regs in sync with cpu_tlbstate.loaded_mm. Just + * sanity-check mm_cpumask. + */ + if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + return; + } + if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - * + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. */ - load_cr3(next->pgd); + unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + pgd_t *pgd = next->pgd + stack_pgd_index; - /* Stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[stack_pgd_index]); + } - /* Load per-mm CR4 state */ - load_mm_cr4(next); + this_cpu_write(cpu_tlbstate.loaded_mm, next); -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT, if the LDT is different. - * - * It's possible that prev->context.ldt doesn't match - * the LDT register. This can happen if leave_mm(prev) - * was called and then modify_ldt changed - * prev->context.ldt but suppressed an IPI to this CPU. - * In this case, prev->context.ldt != NULL, because we - * never set context.ldt to NULL while the mm still - * exists. That means that next->context.ldt != - * prev->context.ldt, because mms never share an LDT. - */ - if (unlikely(prev->context.ldt != next->context.ldt)) - load_mm_ldt(next); -#endif + WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + cpumask_set_cpu(cpu, mm_cpumask(next)); + + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + */ + load_cr3(next->pgd); + + /* + * This gets called via leave_mm() in the idle path where RCU + * functions differently. Tracing normally uses RCU, so we have to + * call the tracepoint specially here. + */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + + /* Stop flush ipis for the previous mm */ + WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + + /* Load per-mm CR4 and LDTR state */ + load_mm_cr4(next); + switch_ldt(real_prev, next); +} + +static void flush_tlb_func_common(const struct flush_tlb_info *f, + bool local, enum tlb_flush_reason reason) +{ + /* This code cannot presently handle being reentered. */ + VM_WARN_ON(!irqs_disabled()); + + if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { + leave_mm(smp_processor_id()); + return; } -#ifdef CONFIG_SMP - else { - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - - if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * On established mms, the mm_cpumask is only changed - * from irq context, from ptep_clear_flush() while in - * lazy tlb mode, and here. Irqs are blocked during - * schedule, protecting us from simultaneous changes. - */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - /* - * We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - * - * As above, load_cr3() is serializing and orders TLB - * fills with respect to the mm_cpumask write. - */ - load_cr3(next->pgd); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - load_mm_cr4(next); - load_mm_ldt(next); + if (f->end == TLB_FLUSH_ALL) { + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); + } else { + unsigned long addr; + unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; + while (addr < f->end) { + __flush_tlb_single(addr); + addr += PAGE_SIZE; } + if (local) + count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); + trace_tlb_flush(reason, nr_pages); } -#endif } -#ifdef CONFIG_SMP +static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) +{ + const struct flush_tlb_info *f = info; -/* - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) set cpu_tlbstate to TLBSTATE_OK - * Now the tlb flush NMI handler flush_tlb_func won't call leave_mm - * if cpu0 was in lazy tlb mode. - * 1a2) update cpu active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but flush_tlb_func ignore flush ipis for the wrong - * mm, and in the worst case we perform a superfluous tlb flush. - * 1b) thread switch without mm change - * cpu active_mm is correct, cpu0 already handles flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ + flush_tlb_func_common(f, true, reason); +} -/* - * TLB flush funcation: - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ -static void flush_tlb_func(void *info) +static void flush_tlb_func_remote(void *info) { - struct flush_tlb_info *f = info; + const struct flush_tlb_info *f = info; inc_irq_stat(irq_tlb_count); - if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) return; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) { - local_flush_tlb(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); - } else { - unsigned long addr; - unsigned long nr_pages = - (f->flush_end - f->flush_start) / PAGE_SIZE; - addr = f->flush_start; - while (addr < f->flush_end) { - __flush_tlb_single(addr); - addr += PAGE_SIZE; - } - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); - } - } else - leave_mm(smp_processor_id()); - + flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN); } void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - struct flush_tlb_info info; - - info.flush_mm = mm; - info.flush_start = start; - info.flush_end = end; - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - if (end == TLB_FLUSH_ALL) + if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); else trace_tlb_flush(TLB_REMOTE_SEND_IPI, - (end - start) >> PAGE_SHIFT); + (info->end - info->start) >> PAGE_SHIFT); if (is_uv_system()) { unsigned int cpu; cpu = smp_processor_id(); - cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu); + cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) - smp_call_function_many(cpumask, flush_tlb_func, - &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func, &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); } /* @@ -302,85 +242,41 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { - unsigned long addr; - /* do a global flush by default */ - unsigned long base_pages_to_flush = TLB_FLUSH_ALL; - - preempt_disable(); + int cpu; - if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; - if (base_pages_to_flush > tlb_single_page_flush_ceiling) - base_pages_to_flush = TLB_FLUSH_ALL; + struct flush_tlb_info info = { + .mm = mm, + }; - if (current->active_mm != mm) { - /* Synchronize with switch_mm. */ - smp_mb(); + cpu = get_cpu(); - goto out; - } - - if (!current->mm) { - leave_mm(smp_processor_id()); + /* Synchronize with switch_mm. */ + smp_mb(); - /* Synchronize with switch_mm. */ - smp_mb(); - - goto out; - } - - /* - * Both branches below are implicit full barriers (MOV to CR or - * INVLPG) that synchronize with switch_mm. - */ - if (base_pages_to_flush == TLB_FLUSH_ALL) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); + /* Should we flush just the requested range? */ + if ((end != TLB_FLUSH_ALL) && + !(vmflag & VM_HUGETLB) && + ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) { + info.start = start; + info.end = end; } else { - /* flush range by one by one 'invlpg' */ - for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); - } - } - trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); -out: - if (base_pages_to_flush == TLB_FLUSH_ALL) { - start = 0UL; - end = TLB_FLUSH_ALL; + info.start = 0UL; + info.end = TLB_FLUSH_ALL; } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, end); - preempt_enable(); -} -void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) -{ - struct mm_struct *mm = vma->vm_mm; - - preempt_disable(); - - if (current->active_mm == mm) { - if (current->mm) { - /* - * Implicit full barrier (INVLPG) that synchronizes - * with switch_mm. - */ - __flush_tlb_one(start); - } else { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); - } + if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN); + local_irq_enable(); } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); - - preempt_enable(); + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), &info); + put_cpu(); } + static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -401,7 +297,7 @@ static void do_kernel_range_flush(void *info) unsigned long addr; /* flush range by one by one 'invlpg' */ - for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE) + for (addr = f->start; addr < f->end; addr += PAGE_SIZE) __flush_tlb_single(addr); } @@ -410,16 +306,40 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) /* Balance as user space task's flush, a bit conservative */ if (end == TLB_FLUSH_ALL || - (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) { + (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) { on_each_cpu(do_flush_tlb_all, NULL, 1); } else { struct flush_tlb_info info; - info.flush_start = start; - info.flush_end = end; + info.start = start; + info.end = end; on_each_cpu(do_kernel_range_flush, &info, 1); } } +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + struct flush_tlb_info info = { + .mm = NULL, + .start = 0UL, + .end = TLB_FLUSH_ALL, + }; + + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN); + local_irq_enable(); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, &info); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -465,5 +385,3 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); - -#endif /* CONFIG_SMP */ diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 8ff1f95627f9..9bf72f5bfedb 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -80,7 +80,7 @@ pgd_t * __init efi_call_phys_prolog(void) int n_pgds, i, j; if (!efi_enabled(EFI_OLD_MEMMAP)) { - save_pgd = (pgd_t *)read_cr3(); + save_pgd = (pgd_t *)__read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); goto out; } @@ -649,7 +649,7 @@ efi_status_t efi_thunk_set_virtual_address_map( efi_sync_low_kernel_mappings(); local_irq_save(flags); - efi_scratch.prev_cr3 = read_cr3(); + efi_scratch.prev_cr3 = __read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); __flush_tlb_all(); diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index c5350fd27d70..0668aaff8bfe 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -77,7 +77,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state) asmlinkage __visible int xo1_do_sleep(u8 sleep_state) { - void *pgd_addr = __va(read_cr3()); + void *pgd_addr = __va(read_cr3_pa()); /* Program wakeup mask (using dword access to CS5536_PM1_EN) */ outl(wakeup_mask << 16, acpi_base + CS5536_PM1_STS); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 795671593528..2983faab5b18 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1123,11 +1123,9 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, * done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu) + const struct flush_tlb_info *info) { + unsigned int cpu = smp_processor_id(); int locals = 0, remotes = 0, hubs = 0; struct bau_desc *bau_desc; struct cpumask *flush_mask; @@ -1181,8 +1179,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, record_send_statistics(stat, locals, hubs, remotes, bau_desc); - if (!end || (end - start) <= PAGE_SIZE) - address = start; + if (!info->end || (info->end - info->start) <= PAGE_SIZE) + address = info->start; else address = TLB_FLUSH_ALL; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 6b05a9219ea2..78459a6d455a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -129,7 +129,7 @@ static void __save_processor_state(struct saved_context *ctxt) */ ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); - ctxt->cr3 = read_cr3(); + ctxt->cr3 = __read_cr3(); ctxt->cr4 = __read_cr4(); #ifdef CONFIG_X86_64 ctxt->cr8 = read_cr8(); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index a6e21fee22ea..e3e62c8a8e70 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -150,7 +150,8 @@ static int relocate_restore_code(void) memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); /* Make the page containing the relocated code executable */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pgd = (pgd_t *)__va(read_cr3_pa()) + + pgd_index(relocated_restore_code); p4d = p4d_offset(pgd, relocated_restore_code); if (p4d_large(*p4d)) { set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index a163a90af4aa..cd4be19c36dc 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -102,7 +102,7 @@ static void __init setup_real_mode(void) trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_level4_pgt[511].pgd; + trampoline_pgd[511] = init_top_pgt[511].pgd; #endif } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1f386d7fdf70..1d7a7213a310 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -975,37 +975,32 @@ static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } - -#ifdef CONFIG_SMP -/* Another cpu may still have their %cr3 pointing at the pagetable, so - we need to repoint it somewhere else before we can unpin it. */ -static void drop_other_mm_ref(void *info) +static void drop_mm_ref_this_cpu(void *info) { struct mm_struct *mm = info; - struct mm_struct *active_mm; - - active_mm = this_cpu_read(cpu_tlbstate.active_mm); - if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) leave_mm(smp_processor_id()); - /* If this cpu still has a stale cr3 reference, then make sure - it has been flushed. */ + /* + * If this cpu still has a stale cr3 reference, then make sure + * it has been flushed. + */ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd)) - load_cr3(swapper_pg_dir); + xen_mc_flush(); } +#ifdef CONFIG_SMP +/* + * Another cpu may still have their %cr3 pointing at the pagetable, so + * we need to repoint it somewhere else before we can unpin it. + */ static void xen_drop_mm_ref(struct mm_struct *mm) { cpumask_var_t mask; unsigned cpu; - if (current->active_mm == mm) { - if (current->mm == mm) - load_cr3(swapper_pg_dir); - else - leave_mm(smp_processor_id()); - } + drop_mm_ref_this_cpu(mm); /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { @@ -1013,31 +1008,31 @@ static void xen_drop_mm_ref(struct mm_struct *mm) if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; - smp_call_function_single(cpu, drop_other_mm_ref, mm, 1); + smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1); } return; } cpumask_copy(mask, mm_cpumask(mm)); - /* It's possible that a vcpu may have a stale reference to our - cr3, because its in lazy mode, and it hasn't yet flushed - its set of pending hypercalls yet. In this case, we can - look at its actual current cr3 value, and force it to flush - if needed. */ + /* + * It's possible that a vcpu may have a stale reference to our + * cr3, because its in lazy mode, and it hasn't yet flushed + * its set of pending hypercalls yet. In this case, we can + * look at its actual current cr3 value, and force it to flush + * if needed. + */ for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) cpumask_set_cpu(cpu, mask); } - if (!cpumask_empty(mask)) - smp_call_function_many(mask, drop_other_mm_ref, mm, 1); + smp_call_function_many(mask, drop_mm_ref_this_cpu, mm, 1); free_cpumask_var(mask); } #else static void xen_drop_mm_ref(struct mm_struct *mm) { - if (current->active_mm == mm) - load_cr3(swapper_pg_dir); + drop_mm_ref_this_cpu(mm); } #endif @@ -1366,8 +1361,7 @@ static void xen_flush_tlb_single(unsigned long addr) } static void xen_flush_tlb_others(const struct cpumask *cpus, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { struct { struct mmuext_op op; @@ -1379,7 +1373,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_others(cpus, mm, start, end); + trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ @@ -1393,9 +1387,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (info->end != TLB_FLUSH_ALL && + (info->end - info->start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; - args->op.arg1.linear_addr = start; + args->op.arg1.linear_addr = info->start; } MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); @@ -1470,8 +1465,8 @@ static void xen_write_cr3(unsigned long cr3) * At the start of the day - when Xen launches a guest, it has already * built pagetables for the guest. We diligently look over them * in xen_setup_kernel_pagetable and graft as appropriate them in the - * init_level4_pgt and its friends. Then when we are happy we load - * the new init_level4_pgt - and continue on. + * init_top_pgt and its friends. Then when we are happy we load + * the new init_top_pgt - and continue on. * * The generic code starts (start_kernel) and 'init_mem_mapping' sets * up the rest of the pagetables. When it has completed it loads the cr3. @@ -1914,12 +1909,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) pt_end = pt_base + xen_start_info->nr_pt_frames; /* Zap identity mapping */ - init_level4_pgt[0] = __pgd(0); + init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ /* L4[272] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ - convert_pfn_mfn(init_level4_pgt); + convert_pfn_mfn(init_top_pgt); /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); @@ -1950,10 +1945,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Copy the initial P->M table mappings if necessary. */ i = pgd_index(xen_start_info->mfn_list); if (i && i < pgd_index(__START_KERNEL_map)) - init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; + init_top_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); + set_page_prot(init_top_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); @@ -1964,7 +1959,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); + PFN_DOWN(__pa_symbol(init_top_pgt))); /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); @@ -1974,7 +1969,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) * attach it to, so make sure we just set kernel pgd. */ xen_mc_batch(); - __xen_write_cr3(true, __pa(init_level4_pgt)); + __xen_write_cr3(true, __pa(init_top_pgt)); xen_mc_issue(PARAVIRT_LAZY_CPU); /* We can't that easily rip out L3 and L2, as the Xen pagetables are @@ -2022,7 +2017,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) pmd_t pmd; pte_t pte; - pa = read_cr3(); + pa = read_cr3_pa(); pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * sizeof(pgd))); if (!pgd_present(pgd)) @@ -2102,7 +2097,7 @@ void __init xen_relocate_p2m(void) pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; - pgd = __va(read_cr3()); + pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); idx_p4d = 0; save_pud = n_pud; @@ -2209,7 +2204,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) { unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); - BUG_ON(read_cr3() != __pa(initial_page_table)); + BUG_ON(read_cr3_pa() != __pa(initial_page_table)); BUG_ON(cr3 != __pa(swapper_pg_dir)); /* diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S index 5e246716d58f..e1a5fbeae08d 100644 --- a/arch/x86/xen/xen-pvh.S +++ b/arch/x86/xen/xen-pvh.S @@ -87,7 +87,7 @@ ENTRY(pvh_start_xen) wrmsr /* Enable pre-constructed page tables. */ - mov $_pa(init_level4_pgt), %eax + mov $_pa(init_top_pgt), %eax mov %eax, %cr3 mov $(X86_CR0_PG | X86_CR0_PE), %eax mov %eax, %cr0 diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 136dfdf63ba1..fc412fbd80bd 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -14,6 +14,10 @@ #include <asm/page.h> +#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH +#include <asm/tlbbatch.h> +#endif + #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) @@ -67,12 +71,15 @@ struct page_frag { struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* - * Each bit set is a CPU that potentially has a TLB entry for one of - * the PFNs being flushed. See set_tlb_ubc_flush_pending(). + * The arch code makes the following promise: generic code can modify a + * PTE, then call arch_tlbbatch_add_mm() (which internally provides all + * needed barriers), then call arch_tlbbatch_flush(), and the entries + * will be flushed on all CPUs by the time that arch_tlbbatch_flush() + * returns. */ - struct cpumask cpumask; + struct arch_tlbflush_unmap_batch arch; - /* True if any bit in cpumask is set */ + /* True if a flush is needed. */ bool flush_required; /* diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index d84ae90ccd5c..be3ab2d13adf 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -93,10 +93,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif #endif #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/mm/Kconfig b/mm/Kconfig index beb7a455915d..398b46064544 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -137,7 +137,7 @@ config HAVE_MEMBLOCK_NODE_MAP config HAVE_MEMBLOCK_PHYS_MAP bool -config HAVE_GENERIC_RCU_GUP +config HAVE_GENERIC_GUP bool config ARCH_DISCARD_MEMBLOCK @@ -1146,7 +1146,7 @@ struct page *get_dump_page(unsigned long addr) #endif /* CONFIG_ELF_CORE */ /* - * Generic RCU Fast GUP + * Generic Fast GUP * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be @@ -1167,8 +1167,8 @@ struct page *get_dump_page(unsigned long addr) * Before activating this code, please be aware that the following assumptions * are currently made: * - * *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free - * pages containing page tables. + * *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to + * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * @@ -1178,7 +1178,7 @@ struct page *get_dump_page(unsigned long addr) * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ -#ifdef CONFIG_HAVE_GENERIC_RCU_GUP +#ifdef CONFIG_HAVE_GENERIC_GUP #ifndef gup_get_pte /* @@ -1668,4 +1668,4 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, return ret; } -#endif /* CONFIG_HAVE_GENERIC_RCU_GUP */ +#endif /* CONFIG_HAVE_GENERIC_GUP */ diff --git a/mm/rmap.c b/mm/rmap.c index d405f0e0ee96..130c238fe384 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - int cpu; if (!tlb_ubc->flush_required) return; - cpu = get_cpu(); - - if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); - trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); - } - - if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) - flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); - cpumask_clear(&tlb_ubc->cpumask); + arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; - put_cpu(); } /* Flush iff there are potentially writable TLB entries that can race with IO */ @@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); + arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* |