diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/Makefile | 1 | ||||
| -rw-r--r-- | arch/x86/mm/dump_pagetables.c | 16 | ||||
| -rw-r--r-- | arch/x86/mm/extable.c | 15 | ||||
| -rw-r--r-- | arch/x86/mm/fault.c | 6 | ||||
| -rw-r--r-- | arch/x86/mm/init.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 204 | ||||
| -rw-r--r-- | arch/x86/mm/kasan_init_64.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/kaslr.c | 172 | ||||
| -rw-r--r-- | arch/x86/mm/numa.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr.c | 49 | ||||
| -rw-r--r-- | arch/x86/mm/pat.c | 5 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable.c | 10 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable_32.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/srat.c | 116 |
14 files changed, 338 insertions, 268 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 62c0043a5fd5..96d2b847e09e 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -37,4 +37,5 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MPX) += mpx.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o +obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 99bfb192803f..9a17250bcbe0 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -72,9 +72,9 @@ static struct addr_marker address_markers[] = { { 0, "User Space" }, #ifdef CONFIG_X86_64 { 0x8000000000000000UL, "Kernel Space" }, - { PAGE_OFFSET, "Low Kernel Mapping" }, - { VMALLOC_START, "vmalloc() Area" }, - { VMEMMAP_START, "Vmemmap" }, + { 0/* PAGE_OFFSET */, "Low Kernel Mapping" }, + { 0/* VMALLOC_START */, "vmalloc() Area" }, + { 0/* VMEMMAP_START */, "Vmemmap" }, # ifdef CONFIG_X86_ESPFIX64 { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, # endif @@ -434,8 +434,16 @@ void ptdump_walk_pgd_level_checkwx(void) static int __init pt_dump_init(void) { + /* + * Various markers are not compile-time constants, so assign them + * here. + */ +#ifdef CONFIG_X86_64 + address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET; + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START; +#endif #ifdef CONFIG_X86_32 - /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; # ifdef CONFIG_HIGHMEM diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 4bb53b89f3c5..832b98f822be 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,6 +1,7 @@ #include <linux/module.h> #include <asm/uaccess.h> #include <asm/traps.h> +#include <asm/kdebug.h> typedef bool (*ex_handler_t)(const struct exception_table_entry *, struct pt_regs *, int); @@ -37,7 +38,7 @@ bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { /* Special hack for uaccess_err */ - current_thread_info()->uaccess_err = 1; + current->thread.uaccess_err = 1; regs->ip = ex_fixup_addr(fixup); return true; } @@ -46,8 +47,9 @@ EXPORT_SYMBOL(ex_handler_ext); bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { - WARN_ONCE(1, "unchecked MSR access error: RDMSR from 0x%x\n", - (unsigned int)regs->cx); + if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n", + (unsigned int)regs->cx, regs->ip, (void *)regs->ip)) + show_stack_regs(regs); /* Pretend that the read succeeded and returned 0. */ regs->ip = ex_fixup_addr(fixup); @@ -60,9 +62,10 @@ EXPORT_SYMBOL(ex_handler_rdmsr_unsafe); bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { - WARN_ONCE(1, "unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x)\n", - (unsigned int)regs->cx, - (unsigned int)regs->dx, (unsigned int)regs->ax); + if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n", + (unsigned int)regs->cx, (unsigned int)regs->dx, + (unsigned int)regs->ax, regs->ip, (void *)regs->ip)) + show_stack_regs(regs); /* Pretend that the write succeeded. */ regs->ip = ex_fixup_addr(fixup); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7d1fa7cd2374..dc8023060456 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -439,7 +439,7 @@ static noinline int vmalloc_fault(unsigned long address) * happen within a race in page table update. In the later * case just flush: */ - pgd = pgd_offset(current->active_mm, address); + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address); pgd_ref = pgd_offset_k(address); if (pgd_none(*pgd_ref)) return -1; @@ -737,7 +737,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, * In this case we need to make sure we're not recursively * faulting through the emulate_vsyscall() logic. */ - if (current_thread_info()->sig_on_uaccess_error && signal) { + if (current->thread.sig_on_uaccess_err && signal) { tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | PF_USER; tsk->thread.cr2 = address; @@ -1353,7 +1353,7 @@ good_area: * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; /* diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 372aad2b3291..cc82830bc8c4 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -17,6 +17,7 @@ #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> +#include <asm/kaslr.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -590,6 +591,9 @@ void __init init_mem_mapping(void) /* the ISA range is always mapped regardless of memory holes */ init_memory_mapping(0, ISA_END_ADDRESS); + /* Init the trampoline, possibly with KASLR memory offset */ + init_trampoline(); + /* * If the allocation is in bottom-up direction, we setup direct mapping * in bottom-up, otherwise we setup direct mapping in top-down. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bce2e5d9edd4..53cc2256cf23 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -328,22 +328,30 @@ void __init cleanup_highmap(void) } } +/* + * Create PTE level page table mapping for physical addresses. + * It returns the last physical address mapped. + */ static unsigned long __meminit -phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end, +phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, pgprot_t prot) { - unsigned long pages = 0, next; - unsigned long last_map_addr = end; + unsigned long pages = 0, paddr_next; + unsigned long paddr_last = paddr_end; + pte_t *pte; int i; - pte_t *pte = pte_page + pte_index(addr); + pte = pte_page + pte_index(paddr); + i = pte_index(paddr); - for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) { - next = (addr & PAGE_MASK) + PAGE_SIZE; - if (addr >= end) { + for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) { + paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE; + if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) && - !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN)) + !e820_any_mapped(paddr & PAGE_MASK, paddr_next, + E820_RAM) && + !e820_any_mapped(paddr & PAGE_MASK, paddr_next, + E820_RESERVED_KERN)) set_pte(pte, __pte(0)); continue; } @@ -354,54 +362,61 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end, * pagetable pages as RO. So assume someone who pre-setup * these mappings are more intelligent. */ - if (pte_val(*pte)) { + if (!pte_none(*pte)) { if (!after_bootmem) pages++; continue; } if (0) - printk(" pte=%p addr=%lx pte=%016lx\n", - pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte); + pr_info(" pte=%p addr=%lx pte=%016lx\n", pte, paddr, + pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL).pte); pages++; - set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot)); - last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE; + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot)); + paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE; } update_page_count(PG_LEVEL_4K, pages); - return last_map_addr; + return paddr_last; } +/* + * Create PMD level page table mapping for physical addresses. The virtual + * and physical address have to be aligned at this level. + * It returns the last physical address mapped. + */ static unsigned long __meminit -phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, +phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, pgprot_t prot) { - unsigned long pages = 0, next; - unsigned long last_map_addr = end; + unsigned long pages = 0, paddr_next; + unsigned long paddr_last = paddr_end; - int i = pmd_index(address); + int i = pmd_index(paddr); - for (; i < PTRS_PER_PMD; i++, address = next) { - pmd_t *pmd = pmd_page + pmd_index(address); + for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) { + pmd_t *pmd = pmd_page + pmd_index(paddr); pte_t *pte; pgprot_t new_prot = prot; - next = (address & PMD_MASK) + PMD_SIZE; - if (address >= end) { + paddr_next = (paddr & PMD_MASK) + PMD_SIZE; + if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(address & PMD_MASK, next, E820_RAM) && - !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN)) + !e820_any_mapped(paddr & PMD_MASK, paddr_next, + E820_RAM) && + !e820_any_mapped(paddr & PMD_MASK, paddr_next, + E820_RESERVED_KERN)) set_pmd(pmd, __pmd(0)); continue; } - if (pmd_val(*pmd)) { + if (!pmd_none(*pmd)) { if (!pmd_large(*pmd)) { spin_lock(&init_mm.page_table_lock); pte = (pte_t *)pmd_page_vaddr(*pmd); - last_map_addr = phys_pte_init(pte, address, - end, prot); + paddr_last = phys_pte_init(pte, paddr, + paddr_end, prot); spin_unlock(&init_mm.page_table_lock); continue; } @@ -420,7 +435,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, if (page_size_mask & (1 << PG_LEVEL_2M)) { if (!after_bootmem) pages++; - last_map_addr = next; + paddr_last = paddr_next; continue; } new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd)); @@ -430,51 +445,65 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, pages++; spin_lock(&init_mm.page_table_lock); set_pte((pte_t *)pmd, - pfn_pte((address & PMD_MASK) >> PAGE_SHIFT, + pfn_pte((paddr & PMD_MASK) >> PAGE_SHIFT, __pgprot(pgprot_val(prot) | _PAGE_PSE))); spin_unlock(&init_mm.page_table_lock); - last_map_addr = next; + paddr_last = paddr_next; continue; } pte = alloc_low_page(); - last_map_addr = phys_pte_init(pte, address, end, new_prot); + paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot); spin_lock(&init_mm.page_table_lock); pmd_populate_kernel(&init_mm, pmd, pte); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); - return last_map_addr; + return paddr_last; } +/* + * Create PUD level page table mapping for physical addresses. The virtual + * and physical address do not have to be aligned at this level. KASLR can + * randomize virtual addresses up to this level. + * It returns the last physical address mapped. + */ static unsigned long __meminit -phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, - unsigned long page_size_mask) +phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, + unsigned long page_size_mask) { - unsigned long pages = 0, next; - unsigned long last_map_addr = end; - int i = pud_index(addr); + unsigned long pages = 0, paddr_next; + unsigned long paddr_last = paddr_end; + unsigned long vaddr = (unsigned long)__va(paddr); + int i = pud_index(vaddr); - for (; i < PTRS_PER_PUD; i++, addr = next) { - pud_t *pud = pud_page + pud_index(addr); + for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) { + pud_t *pud; pmd_t *pmd; pgprot_t prot = PAGE_KERNEL; - next = (addr & PUD_MASK) + PUD_SIZE; - if (addr >= end) { + vaddr = (unsigned long)__va(paddr); + pud = pud_page + pud_index(vaddr); + paddr_next = (paddr & PUD_MASK) + PUD_SIZE; + + if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) && - !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN)) + !e820_any_mapped(paddr & PUD_MASK, paddr_next, + E820_RAM) && + !e820_any_mapped(paddr & PUD_MASK, paddr_next, + E820_RESERVED_KERN)) set_pud(pud, __pud(0)); continue; } - if (pud_val(*pud)) { + if (!pud_none(*pud)) { if (!pud_large(*pud)) { pmd = pmd_offset(pud, 0); - last_map_addr = phys_pmd_init(pmd, addr, end, - page_size_mask, prot); + paddr_last = phys_pmd_init(pmd, paddr, + paddr_end, + page_size_mask, + prot); __flush_tlb_all(); continue; } @@ -493,7 +522,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, if (page_size_mask & (1 << PG_LEVEL_1G)) { if (!after_bootmem) pages++; - last_map_addr = next; + paddr_last = paddr_next; continue; } prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud)); @@ -503,16 +532,16 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, pages++; spin_lock(&init_mm.page_table_lock); set_pte((pte_t *)pud, - pfn_pte((addr & PUD_MASK) >> PAGE_SHIFT, + pfn_pte((paddr & PUD_MASK) >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); spin_unlock(&init_mm.page_table_lock); - last_map_addr = next; + paddr_last = paddr_next; continue; } pmd = alloc_low_page(); - last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask, - prot); + paddr_last = phys_pmd_init(pmd, paddr, paddr_end, + page_size_mask, prot); spin_lock(&init_mm.page_table_lock); pud_populate(&init_mm, pud, pmd); @@ -522,38 +551,44 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, update_page_count(PG_LEVEL_1G, pages); - return last_map_addr; + 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 + * down. It returns the last physical address mapped. + */ unsigned long __meminit -kernel_physical_mapping_init(unsigned long start, - unsigned long end, +kernel_physical_mapping_init(unsigned long paddr_start, + unsigned long paddr_end, unsigned long page_size_mask) { bool pgd_changed = false; - unsigned long next, last_map_addr = end; - unsigned long addr; + unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last; - start = (unsigned long)__va(start); - end = (unsigned long)__va(end); - addr = start; + paddr_last = paddr_end; + vaddr = (unsigned long)__va(paddr_start); + vaddr_end = (unsigned long)__va(paddr_end); + vaddr_start = vaddr; - for (; start < end; start = next) { - pgd_t *pgd = pgd_offset_k(start); + for (; vaddr < vaddr_end; vaddr = vaddr_next) { + pgd_t *pgd = pgd_offset_k(vaddr); pud_t *pud; - next = (start & PGDIR_MASK) + PGDIR_SIZE; + vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; if (pgd_val(*pgd)) { pud = (pud_t *)pgd_page_vaddr(*pgd); - last_map_addr = phys_pud_init(pud, __pa(start), - __pa(end), page_size_mask); + paddr_last = phys_pud_init(pud, __pa(vaddr), + __pa(vaddr_end), + page_size_mask); continue; } pud = alloc_low_page(); - last_map_addr = phys_pud_init(pud, __pa(start), __pa(end), - page_size_mask); + paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), + page_size_mask); spin_lock(&init_mm.page_table_lock); pgd_populate(&init_mm, pgd, pud); @@ -562,11 +597,11 @@ kernel_physical_mapping_init(unsigned long start, } if (pgd_changed) - sync_global_pgds(addr, end - 1, 0); + sync_global_pgds(vaddr_start, vaddr_end - 1, 0); __flush_tlb_all(); - return last_map_addr; + return paddr_last; } #ifndef CONFIG_NUMA @@ -673,7 +708,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) for (i = 0; i < PTRS_PER_PTE; i++) { pte = pte_start + i; - if (pte_val(*pte)) + if (!pte_none(*pte)) return; } @@ -691,7 +726,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) for (i = 0; i < PTRS_PER_PMD; i++) { pmd = pmd_start + i; - if (pmd_val(*pmd)) + if (!pmd_none(*pmd)) return; } @@ -702,27 +737,6 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) spin_unlock(&init_mm.page_table_lock); } -/* Return true if pgd is changed, otherwise return false. */ -static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd) -{ - pud_t *pud; - int i; - - for (i = 0; i < PTRS_PER_PUD; i++) { - pud = pud_start + i; - if (pud_val(*pud)) - return false; - } - - /* free a pud table */ - free_pagetable(pgd_page(*pgd), 0); - spin_lock(&init_mm.page_table_lock); - pgd_clear(pgd); - spin_unlock(&init_mm.page_table_lock); - - return true; -} - static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, bool direct) @@ -913,7 +927,6 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) unsigned long addr; pgd_t *pgd; pud_t *pud; - bool pgd_changed = false; for (addr = start; addr < end; addr = next) { next = pgd_addr_end(addr, end); @@ -924,13 +937,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct) pud = (pud_t *)pgd_page_vaddr(*pgd); remove_pud_table(pud, addr, next, direct); - if (free_pud_table(pud, pgd)) - pgd_changed = true; } - if (pgd_changed) - sync_global_pgds(start, end - 1, 1); - flush_tlb_all(); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110fa0057..0493c17b8a51 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c new file mode 100644 index 000000000000..26dccd6c0df1 --- /dev/null +++ b/arch/x86/mm/kaslr.c @@ -0,0 +1,172 @@ +/* + * This file implements KASLR memory randomization for x86_64. It randomizes + * the virtual address space of kernel memory regions (physical memory + * mapping, vmalloc & vmemmap) for x86_64. This security feature mitigates + * exploits relying on predictable kernel addresses. + * + * 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). + * + * The order of each memory region is not changed. The feature looks at + * the available space for the regions based on different configuration + * options and randomizes the base and space between each. The size of the + * physical memory mapping is the available physical memory. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/random.h> + +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/setup.h> +#include <asm/kaslr.h> + +#include "mm_internal.h" + +#define TB_SHIFT 40 + +/* + * Virtual address start and end range for randomization. The end changes base + * on configuration to have the highest amount of space for randomization. + * It increases the possible random position for each randomized region. + * + * You need to add an if/def entry if you introduce a new memory region + * compatible with KASLR. Your entry must be in logical order with memory + * layout. For example, ESPFIX is before EFI because its virtual address is + * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to + * ensure that this order is correct and won't be changed. + */ +static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; +static const unsigned long vaddr_end = VMEMMAP_START; + +/* Default values */ +unsigned long page_offset_base = __PAGE_OFFSET_BASE; +EXPORT_SYMBOL(page_offset_base); +unsigned long vmalloc_base = __VMALLOC_BASE; +EXPORT_SYMBOL(vmalloc_base); + +/* + * Memory regions randomized by KASLR (except modules that use a separate logic + * earlier during boot). The list is ordered based on virtual addresses. This + * order is kept after randomization. + */ +static __initdata struct kaslr_memory_region { + unsigned long *base; + unsigned long size_tb; +} kaslr_regions[] = { + { &page_offset_base, 64/* Maximum */ }, + { &vmalloc_base, VMALLOC_SIZE_TB }, +}; + +/* Get size in bytes used by the memory region */ +static inline unsigned long get_padding(struct kaslr_memory_region *region) +{ + return (region->size_tb << TB_SHIFT); +} + +/* + * Apply no randomization if KASLR was disabled at boot or if KASAN + * is enabled. KASAN shadow mappings rely on regions being PGD aligned. + */ +static inline bool kaslr_memory_enabled(void) +{ + return kaslr_enabled() && !config_enabled(CONFIG_KASAN); +} + +/* Initialize base and padding for each memory region randomized with KASLR */ +void __init kernel_randomize_memory(void) +{ + size_t i; + unsigned long vaddr = vaddr_start; + unsigned long rand, memory_tb; + struct rnd_state rand_state; + unsigned long remain_entropy; + + if (!kaslr_memory_enabled()) + return; + + /* + * Update Physical memory mapping to available and + * add padding if needed (especially for memory hotplug support). + */ + BUG_ON(kaslr_regions[0].base != &page_offset_base); + memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) + + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; + + /* Adapt phyiscal memory region size based on available memory */ + if (memory_tb < kaslr_regions[0].size_tb) + kaslr_regions[0].size_tb = memory_tb; + + /* Calculate entropy available between regions */ + remain_entropy = vaddr_end - vaddr_start; + for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) + remain_entropy -= get_padding(&kaslr_regions[i]); + + prandom_seed_state(&rand_state, kaslr_get_random_long("Memory")); + + for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) { + unsigned long entropy; + + /* + * Select a random virtual address using the extra entropy + * available. + */ + entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); + prandom_bytes_state(&rand_state, &rand, sizeof(rand)); + entropy = (rand % (entropy + 1)) & PUD_MASK; + vaddr += entropy; + *kaslr_regions[i].base = vaddr; + + /* + * Jump the region and add a minimum padding based on + * randomization alignment. + */ + vaddr += get_padding(&kaslr_regions[i]); + 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) +{ + 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; + pgd = pgd_offset_k((unsigned long)__va(paddr)); + pud_page = (pud_t *) pgd_page_vaddr(*pgd); + + for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) { + pud_t *pud, *pud_tramp; + unsigned long vaddr = (unsigned long)__va(paddr); + + pud_tramp = pud_page_tramp + pud_index(paddr); + pud = pud_page + pud_index(vaddr); + paddr_next = (paddr & PUD_MASK) + PUD_SIZE; + + *pud_tramp = *pud; + } + + set_pgd(&trampoline_pgd_entry, + __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); +} diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 9c086c57105c..968ac028c34e 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -1,4 +1,5 @@ /* Common code for 32 and 64-bit NUMA */ +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> @@ -15,7 +16,6 @@ #include <asm/e820.h> #include <asm/proto.h> #include <asm/dma.h> -#include <asm/acpi.h> #include <asm/amd_nb.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 7a1f7bbf4105..849dc09fa4f0 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -101,7 +101,8 @@ static inline unsigned long highmap_start_pfn(void) static inline unsigned long highmap_end_pfn(void) { - return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; + /* Do not reference physical address outside the kernel. */ + return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; } #endif @@ -112,6 +113,12 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } +static inline int +within_inclusive(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr <= end; +} + /* * Flushing functions */ @@ -746,18 +753,6 @@ static bool try_to_free_pmd_page(pmd_t *pmd) return true; } -static bool try_to_free_pud_page(pud_t *pud) -{ - int i; - - for (i = 0; i < PTRS_PER_PUD; i++) - if (!pud_none(pud[i])) - return false; - - free_page((unsigned long)pud); - return true; -} - static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end) { pte_t *pte = pte_offset_kernel(pmd, start); @@ -871,16 +866,6 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end) */ } -static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end) -{ - pgd_t *pgd_entry = root + pgd_index(addr); - - unmap_pud_range(pgd_entry, addr, end); - - if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry))) - pgd_clear(pgd_entry); -} - static int alloc_pte_page(pmd_t *pmd) { pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); @@ -1113,7 +1098,12 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) ret = populate_pud(cpa, addr, pgd_entry, pgprot); if (ret < 0) { - unmap_pgd_range(cpa->pgd, addr, + /* + * Leave the PUD page in place in case some other CPU or thread + * already found it, but remove any useless entries we just + * added to it. + */ + unmap_pud_range(pgd_entry, addr, addr + (cpa->numpages << PAGE_SHIFT)); return ret; } @@ -1185,7 +1175,7 @@ repeat: return __cpa_process_fault(cpa, address, primary); old_pte = *kpte; - if (!pte_val(old_pte)) + if (pte_none(old_pte)) return __cpa_process_fault(cpa, address, primary); if (level == PG_LEVEL_4K) { @@ -1316,7 +1306,8 @@ static int cpa_process_alias(struct cpa_data *cpa) * to touch the high mapped kernel as well: */ if (!within(vaddr, (unsigned long)_text, _brk_end) && - within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) { + within_inclusive(cpa->pfn, highmap_start_pfn(), + highmap_end_pfn())) { unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa = *cpa; @@ -1991,12 +1982,6 @@ out: return retval; } -void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, - unsigned numpages) -{ - unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT)); -} - /* * The testcases use internal knowledge of the implementation that shouldn't * be exposed to the rest of the kernel. Include these directly here. diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index fb0604f11eec..db00e3e2f3dc 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -755,11 +755,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) return 1; while (cursor < to) { - if (!devmem_is_allowed(pfn)) { - pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", - current->comm, from, to - 1); + if (!devmem_is_allowed(pfn)) return 0; - } cursor += PAGE_SIZE; pfn++; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 4eb287e25043..3feec5af4e67 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include <asm/fixmap.h> #include <asm/mtrr.h> -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO) #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM @@ -18,7 +18,7 @@ gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(PGALLOC_GFP); + return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) @@ -207,9 +207,13 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; + gfp_t gfp = PGALLOC_GFP; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; for(i = 0; i < PREALLOCATED_PMDS; i++) { - pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); + pmd_t *pmd = (pmd_t *)__get_free_page(gfp); if (!pmd) failed = true; if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 75cc0978d45d..e67ae0e6c59d 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -47,7 +47,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) return; } pte = pte_offset_kernel(pmd, vaddr); - if (pte_val(pteval)) + if (!pte_none(pteval)) set_pte_at(&init_mm, vaddr, pte, pteval); else pte_clear(&init_mm, vaddr, pte); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index b5f821881465..b1ecff460a46 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -15,8 +15,6 @@ #include <linux/bitmap.h> #include <linux/module.h> #include <linux/topology.h> -#include <linux/bootmem.h> -#include <linux/memblock.h> #include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> @@ -24,51 +22,6 @@ #include <asm/apic.h> #include <asm/uv/uv.h> -int acpi_numa __initdata; - -static __init int setup_node(int pxm) -{ - return acpi_map_pxm_to_node(pxm); -} - -static __init void bad_srat(void) -{ - printk(KERN_ERR "SRAT: SRAT not used.\n"); - acpi_numa = -1; -} - -static __init inline int srat_disabled(void) -{ - return acpi_numa < 0; -} - -/* - * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for - * I/O localities since SRAT does not list them. I/O localities are - * not supported at this point. - */ -void __init acpi_numa_slit_init(struct acpi_table_slit *slit) -{ - int i, j; - - for (i = 0; i < slit->locality_count; i++) { - const int from_node = pxm_to_node(i); - - if (from_node == NUMA_NO_NODE) - continue; - - for (j = 0; j < slit->locality_count; j++) { - const int to_node = pxm_to_node(j); - - if (to_node == NUMA_NO_NODE) - continue; - - numa_set_distance(from_node, to_node, - slit->entry[slit->locality_count * i + j]); - } - } -} - /* Callback for Proximity Domain -> x2APIC mapping */ void __init acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) @@ -91,7 +44,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) pxm, apic_id); return; } - node = setup_node(pxm); + node = acpi_map_pxm_to_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); bad_srat(); @@ -104,7 +57,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } @@ -127,7 +79,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pxm = pa->proximity_domain_lo; if (acpi_srat_revision >= 2) pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8; - node = setup_node(pxm); + node = acpi_map_pxm_to_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); bad_srat(); @@ -146,74 +98,10 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - acpi_numa = 1; printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline int save_add_info(void) {return 1;} -#else -static inline int save_add_info(void) {return 0;} -#endif - -/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ -int __init -acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) -{ - u64 start, end; - u32 hotpluggable; - int node, pxm; - - if (srat_disabled()) - goto out_err; - if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) - goto out_err_bad_srat; - if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - goto out_err; - hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; - if (hotpluggable && !save_add_info()) - goto out_err; - - start = ma->base_address; - end = start + ma->length; - pxm = ma->proximity_domain; - if (acpi_srat_revision <= 1) - pxm &= 0xff; - - node = setup_node(pxm); - if (node < 0) { - printk(KERN_ERR "SRAT: Too many proximity domains.\n"); - goto out_err_bad_srat; - } - - if (numa_add_memblk(node, start, end) < 0) - goto out_err_bad_srat; - - node_set(node, numa_nodes_parsed); - - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", - node, pxm, - (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : "", - ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); - - /* Mark hotplug range in memblock. */ - if (hotpluggable && memblock_mark_hotplug(start, ma->length)) - pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", - (unsigned long long)start, (unsigned long long)end - 1); - - max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); - - return 0; -out_err_bad_srat: - bad_srat(); -out_err: - return -1; -} - -void __init acpi_numa_arch_fixup(void) {} - int __init x86_acpi_numa_init(void) { int ret; |