diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/include/asm/e820.h | 2 | ||||
| -rw-r--r-- | arch/x86/include/asm/numa.h | 4 | ||||
| -rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/boot.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/e820.c | 72 | ||||
| -rw-r--r-- | arch/x86/mm/fault.c | 8 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 12 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 397 | ||||
| -rw-r--r-- | arch/x86/mm/numa.c | 12 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr.c | 97 | ||||
| -rw-r--r-- | arch/x86/platform/efi/efi.c | 15 |
11 files changed, 571 insertions, 53 deletions
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index cccd07fa5e3a..b8e9224f0b45 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -17,6 +17,8 @@ extern unsigned long pci_mem_start; extern int e820_any_mapped(u64 start, u64 end, unsigned type); extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); +extern void e820_add_limit_region(u64 start, u64 size, int type); +extern void e820_adjust_region(u64 *start, u64 *size); extern void e820_print_map(char *who); extern int sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 52560a2038e1..1b99ee5c9f00 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -57,8 +57,8 @@ static inline int numa_cpu_node(int cpu) #endif #ifdef CONFIG_NUMA -extern void __cpuinit numa_set_node(int cpu, int node); -extern void __cpuinit numa_clear_node(int cpu); +extern void numa_set_node(int cpu, int node); +extern void numa_clear_node(int cpu); extern void __init init_cpu_to_node(void); extern void __cpuinit numa_add_cpu(int cpu); extern void __cpuinit numa_remove_cpu(int cpu); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index e6423002c10b..13805d7aa790 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -352,6 +352,7 @@ static inline void update_page_count(int level, unsigned long pages) { } */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern phys_addr_t slow_virt_to_phys(void *__address); +extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index cfc755dc1607..230c8ea878e5 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -696,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { +#ifdef CONFIG_ACPI_NUMA + set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); +#endif + per_cpu(x86_cpu_to_apicid, cpu) = -1; set_cpu_present(cpu, false); num_processors--; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..0d5bb689649a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe; #ifdef CONFIG_PCI EXPORT_SYMBOL(pci_mem_start); #endif +static u64 mem_limit = ~0ULL; /* * This function checks if any part of the range <start,end> is mapped @@ -108,7 +109,7 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) * Add a memory region to the kernel e820 map. */ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, - int type) + int type, bool limited) { int x = e820x->nr_map; @@ -119,6 +120,22 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, return; } + if (limited) { + if (start >= mem_limit) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)start, + (unsigned long long)(start + size - 1)); + return; + } + + if (mem_limit - start < size) { + printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n", + (unsigned long long)mem_limit, + (unsigned long long)(start + size - 1)); + size = mem_limit - start; + } + } + e820x->map[x].addr = start; e820x->map[x].size = size; e820x->map[x].type = type; @@ -127,7 +144,37 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, void __init e820_add_region(u64 start, u64 size, int type) { - __e820_add_region(&e820, start, size, type); + __e820_add_region(&e820, start, size, type, false); +} + +/* + * do_add_efi_memmap() calls this function(). + * + * Note: BOOT_SERVICES_{CODE,DATA} regions on some efi machines are marked + * as E820_RAM, and they are needed to be mapped. Please use e820_add_region() + * to add BOOT_SERVICES_{CODE,DATA} regions. + */ +void __init e820_add_limit_region(u64 start, u64 size, int type) +{ + /* + * efi_init() is called after finish_e820_parsing(), so we should + * check whether [start, start + size) contains address above + * mem_limit if the type is E820_RAM. + */ + __e820_add_region(&e820, start, size, type, type == E820_RAM); +} + +void __init e820_adjust_region(u64 *start, u64 *size) +{ + if (*start >= mem_limit) { + *size = 0; + return; + } + + if (mem_limit - *start < *size) + *size = mem_limit - *start; + + return; } static void __init e820_print_type(u32 type) @@ -455,8 +502,9 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, /* new range is totally covered? */ if (ei->addr < start && ei_end > end) { - __e820_add_region(e820x, start, size, new_type); - __e820_add_region(e820x, end, ei_end - end, ei->type); + __e820_add_region(e820x, start, size, new_type, false); + __e820_add_region(e820x, end, ei_end - end, ei->type, + false); ei->size = start - ei->addr; real_updated_size += size; continue; @@ -469,7 +517,7 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, continue; __e820_add_region(e820x, final_start, final_end - final_start, - new_type); + new_type, false); real_updated_size += final_end - final_start; @@ -809,7 +857,7 @@ static int userdef __initdata; /* "mem=nopentium" disables the 4MB page tables. */ static int __init parse_memopt(char *p) { - u64 mem_size; + char *oldp; if (!p) return -EINVAL; @@ -825,11 +873,11 @@ static int __init parse_memopt(char *p) } userdef = 1; - mem_size = memparse(p, &p); + oldp = p; + mem_limit = memparse(p, &p); /* don't remove all of memory when handling "mem={invalid}" param */ - if (mem_size == 0) + if (mem_limit == 0 || p == oldp) return -EINVAL; - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); return 0; } @@ -895,6 +943,12 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { + if (mem_limit != ~0ULL) { + userdef = 1; + e820_remove_range(mem_limit, ULLONG_MAX - mem_limit, + E820_RAM, 1); + } + if (userdef) { u32 nr = e820.nr_map; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 027088f2f7dd..c755cd624bf0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -937,14 +937,8 @@ spurious_fault(unsigned long error_code, unsigned long address) if (pmd_large(*pmd)) return spurious_fault_check(error_code, (pte_t *) pmd); - /* - * Note: don't use pte_present() here, since it returns true - * if the _PAGE_PROTNONE bit is set. However, this aliases the - * _PAGE_GLOBAL bit, which for kernel pages give false positives - * when CONFIG_DEBUG_PAGEALLOC is used. - */ pte = pte_offset_kernel(pmd, address); - if (!(pte_flags(*pte) & _PAGE_PRESENT)) + if (!pte_present(*pte)) return 0; ret = spurious_fault_check(error_code, pte); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index b299724f6e34..2d19001151d5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -862,6 +862,18 @@ int arch_add_memory(int nid, u64 start, u64 size) return __add_pages(nid, zone, start_pfn, nr_pages); } + +#ifdef CONFIG_MEMORY_HOTREMOVE +int arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + + zone = page_zone(pfn_to_page(start_pfn)); + return __remove_pages(zone, start_pfn, nr_pages); +} +#endif #endif /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 90b6a624fa18..67bad4b25681 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -707,6 +707,343 @@ int arch_add_memory(int nid, u64 start, u64 size) } EXPORT_SYMBOL_GPL(arch_add_memory); +#define PAGE_INUSE 0xFD + +static void __meminit free_pagetable(struct page *page, int order) +{ + struct zone *zone; + bool bootmem = false; + unsigned long magic; + unsigned int nr_pages = 1 << order; + + /* bootmem page has reserved flag */ + if (PageReserved(page)) { + __ClearPageReserved(page); + bootmem = true; + + magic = (unsigned long)page->lru.next; + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { + while (nr_pages--) + put_page_bootmem(page++); + } else + __free_pages_bootmem(page, order); + } else + free_pages((unsigned long)page_address(page), order); + + /* + * SECTION_INFO pages and MIX_SECTION_INFO pages + * are all allocated by bootmem. + */ + if (bootmem) { + zone = page_zone(page); + zone_span_writelock(zone); + zone->present_pages += nr_pages; + zone_span_writeunlock(zone); + totalram_pages += nr_pages; + } +} + +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (pte_val(*pte)) + return; + } + + /* free a pte talbe */ + free_pagetable(pmd_page(*pmd), 0); + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); +} + +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (pmd_val(*pmd)) + return; + } + + /* free a pmd talbe */ + free_pagetable(pud_page(*pud), 0); + spin_lock(&init_mm.page_table_lock); + pud_clear(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) +{ + unsigned long next, pages = 0; + pte_t *pte; + void *page_addr; + phys_addr_t phys_addr; + + pte = pte_start + pte_index(addr); + for (; addr < end; addr = next, pte++) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + if (!pte_present(*pte)) + continue; + + /* + * We mapped [0,1G) memory as identity mapping when + * initializing, in arch/x86/kernel/head_64.S. These + * pagetables cannot be removed. + */ + phys_addr = pte_val(*pte) + (addr & PAGE_MASK); + if (phys_addr < (phys_addr_t)0x40000000) + return; + + if (IS_ALIGNED(addr, PAGE_SIZE) && + IS_ALIGNED(next, PAGE_SIZE)) { + /* + * Do not free direct mapping pages since they were + * freed when offlining, or simplely not in use. + */ + if (!direct) + free_pagetable(pte_page(*pte), 0); + + spin_lock(&init_mm.page_table_lock); + pte_clear(&init_mm, addr, pte); + spin_unlock(&init_mm.page_table_lock); + + /* For non-direct mapping, pages means nothing. */ + pages++; + } else { + /* + * If we are here, we are freeing vmemmap pages since + * direct mapped memory ranges to be freed are aligned. + * + * If we are not removing the whole page, it means + * other page structs in this page are being used and + * we canot remove them. So fill the unused page_structs + * with 0xFD, and remove the page when it is wholly + * filled with 0xFD. + */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pte_page(*pte)); + if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { + free_pagetable(pte_page(*pte), 0); + + spin_lock(&init_mm.page_table_lock); + pte_clear(&init_mm, addr, pte); + spin_unlock(&init_mm.page_table_lock); + } + } + } + + /* Call free_pte_table() in remove_pmd_table(). */ + flush_tlb_all(); + if (direct) + update_page_count(PG_LEVEL_4K, -pages); +} + +static void __meminit +remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pte_t *pte_base; + pmd_t *pmd; + void *page_addr; + + pmd = pmd_start + pmd_index(addr); + for (; addr < end; addr = next, pmd++) { + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (pmd_large(*pmd)) { + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + if (!direct) + free_pagetable(pmd_page(*pmd), + get_order(PMD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); + pages++; + } else { + /* If here, we are freeing vmemmap pages. */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pmd_page(*pmd)); + if (!memchr_inv(page_addr, PAGE_INUSE, + PMD_SIZE)) { + free_pagetable(pmd_page(*pmd), + get_order(PMD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pmd_clear(pmd); + spin_unlock(&init_mm.page_table_lock); + } + } + + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmd); + remove_pte_table(pte_base, addr, next, direct); + free_pte_table(pte_base, pmd); + } + + /* Call free_pmd_table() in remove_pud_table(). */ + if (direct) + update_page_count(PG_LEVEL_2M, -pages); +} + +static void __meminit +remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, + bool direct) +{ + unsigned long next, pages = 0; + pmd_t *pmd_base; + pud_t *pud; + void *page_addr; + + pud = pud_start + pud_index(addr); + for (; addr < end; addr = next, pud++) { + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (pud_large(*pud)) { + if (IS_ALIGNED(addr, PUD_SIZE) && + IS_ALIGNED(next, PUD_SIZE)) { + if (!direct) + free_pagetable(pud_page(*pud), + get_order(PUD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); + pages++; + } else { + /* If here, we are freeing vmemmap pages. */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(pud_page(*pud)); + if (!memchr_inv(page_addr, PAGE_INUSE, + PUD_SIZE)) { + free_pagetable(pud_page(*pud), + get_order(PUD_SIZE)); + + spin_lock(&init_mm.page_table_lock); + pud_clear(pud); + spin_unlock(&init_mm.page_table_lock); + } + } + + continue; + } + + pmd_base = (pmd_t *)pud_page_vaddr(*pud); + remove_pmd_table(pmd_base, addr, next, direct); + free_pmd_table(pmd_base, pud); + } + + if (direct) + update_page_count(PG_LEVEL_1G, -pages); +} + +/* start and end are both virtual address. */ +static void __meminit +remove_pagetable(unsigned long start, unsigned long end, bool direct) +{ + unsigned long next; + pgd_t *pgd; + pud_t *pud; + bool pgd_changed = false; + + for (; start < end; start = next) { + pgd = pgd_offset_k(start); + if (!pgd_present(*pgd)) + continue; + + next = pgd_addr_end(start, end); + + pud = (pud_t *)pgd_page_vaddr(*pgd); + remove_pud_table(pud, start, next, direct); + if (free_pud_table(pud, pgd)) + pgd_changed = true; + } + + if (pgd_changed) + sync_global_pgds(start, end - 1); + + flush_tlb_all(); +} + +void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages) +{ + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + remove_pagetable(start, end, false); +} + +static void __meminit +kernel_physical_mapping_remove(unsigned long start, unsigned long end) +{ + start = (unsigned long)__va(start); + end = (unsigned long)__va(end); + + remove_pagetable(start, end, true); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +int __ref arch_remove_memory(u64 start, u64 size) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + struct zone *zone; + int ret; + + zone = page_zone(pfn_to_page(start_pfn)); + kernel_physical_mapping_remove(start, start + size); + ret = __remove_pages(zone, start_pfn, nr_pages); + WARN_ON_ONCE(ret); + + return ret; +} +#endif #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; @@ -1016,6 +1353,66 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) return 0; } +#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) +void register_page_bootmem_memmap(unsigned long section_nr, + struct page *start_page, unsigned long size) +{ + unsigned long addr = (unsigned long)start_page; + unsigned long end = (unsigned long)(start_page + size); + unsigned long next; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + unsigned int nr_pages; + struct page *page; + + for (; addr < end; addr = next) { + pte_t *pte = NULL; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, pgd_page(*pgd), MIX_SECTION_INFO); + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + continue; + } + get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO); + + if (!cpu_has_pse) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + get_page_bootmem(section_nr, pmd_page(*pmd), + MIX_SECTION_INFO); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + continue; + get_page_bootmem(section_nr, pte_page(*pte), + SECTION_INFO); + } else { + next = pmd_addr_end(addr, end); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + + nr_pages = 1 << (get_order(PMD_SIZE)); + page = pmd_page(*pmd); + while (nr_pages--) + get_page_bootmem(section_nr, page++, + SECTION_INFO); + } + } +} +#endif + void __meminit vmemmap_populate_print_last(void) { if (p_start) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 8504f3698753..9df61320e812 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL(node_to_cpumask_map); DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); -void __cpuinit numa_set_node(int cpu, int node) +void numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); @@ -97,11 +97,10 @@ void __cpuinit numa_set_node(int cpu, int node) #endif per_cpu(x86_cpu_to_node_map, cpu) = node; - if (node != NUMA_NO_NODE) - set_cpu_numa_node(cpu, node); + set_cpu_numa_node(cpu, node); } -void __cpuinit numa_clear_node(int cpu) +void numa_clear_node(int cpu) { numa_set_node(cpu, NUMA_NO_NODE); } @@ -213,10 +212,9 @@ static void __init setup_node_data(int nid, u64 start, u64 end) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { - pr_err("Cannot find %zu bytes in node %d\n", - nd_size, nid); + pr_err("Cannot find %zu bytes in any node\n", nd_size); return; } nd = __va(nd_pa); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a1b1c88f9caf..091934e1d0d9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -473,6 +473,19 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); /* + * Set the PSE and GLOBAL flags only if the PRESENT flag is + * set otherwise pmd_present/pmd_huge will return true even on + * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(new_prot) & _PAGE_PRESENT) + pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + else + pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + + new_prot = canon_pgprot(new_prot); + + /* * old_pte points to the large page base address. So we need * to add the offset of the virtual address: */ @@ -517,7 +530,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot)); + new_pte = pfn_pte(pte_pfn(old_pte), new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; do_split = 0; @@ -529,21 +542,13 @@ out_unlock: return do_split; } -static int split_large_page(pte_t *kpte, unsigned long address) +int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase) { unsigned long pfn, pfninc = 1; unsigned int i, level; - pte_t *pbase, *tmp; + pte_t *tmp; pgprot_t ref_prot; - struct page *base; - - if (!debug_pagealloc) - spin_unlock(&cpa_lock); - base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); - if (!debug_pagealloc) - spin_lock(&cpa_lock); - if (!base) - return -ENOMEM; + struct page *base = virt_to_page(pbase); spin_lock(&pgd_lock); /* @@ -551,10 +556,11 @@ static int split_large_page(pte_t *kpte, unsigned long address) * up for us already: */ tmp = lookup_address(address, &level); - if (tmp != kpte) - goto out_unlock; + if (tmp != kpte) { + spin_unlock(&pgd_lock); + return 1; + } - pbase = (pte_t *)page_address(base); paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); /* @@ -568,16 +574,35 @@ static int split_large_page(pte_t *kpte, unsigned long address) #ifdef CONFIG_X86_64 if (level == PG_LEVEL_1G) { pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; - pgprot_val(ref_prot) |= _PAGE_PSE; + /* + * Set the PSE flags only if the PRESENT flag is set + * otherwise pmd_present/pmd_huge will return true + * even on a non present pmd. + */ + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_PSE; + else + pgprot_val(ref_prot) &= ~_PAGE_PSE; } #endif /* + * Set the GLOBAL flags only if the PRESENT flag is set + * otherwise pmd/pte_present will return true even on a non + * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL + * for the ancient hardware that doesn't support it. + */ + if (pgprot_val(ref_prot) & _PAGE_PRESENT) + pgprot_val(ref_prot) |= _PAGE_GLOBAL; + else + pgprot_val(ref_prot) &= ~_PAGE_GLOBAL; + + /* * Get the target pfn from the original entry: */ pfn = pte_pfn(*kpte); for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) - set_pte(&pbase[i], pfn_pte(pfn, ref_prot)); + set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), PFN_DOWN(__pa(address)) + 1)) @@ -601,17 +626,27 @@ static int split_large_page(pte_t *kpte, unsigned long address) * going on. */ __flush_tlb_all(); + spin_unlock(&pgd_lock); - base = NULL; + return 0; +} -out_unlock: - /* - * If we dropped out via the lookup_address check under - * pgd_lock then stick the page back into the pool: - */ - if (base) +static int split_large_page(pte_t *kpte, unsigned long address) +{ + pte_t *pbase; + struct page *base; + + if (!debug_pagealloc) + spin_unlock(&cpa_lock); + base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); + if (!debug_pagealloc) + spin_lock(&cpa_lock); + if (!base) + return -ENOMEM; + + pbase = (pte_t *)page_address(base); + if (__split_large_page(kpte, address, pbase)) __free_page(base); - spin_unlock(&pgd_lock); return 0; } @@ -682,6 +717,18 @@ repeat: new_prot = static_protections(new_prot, address, pfn); /* + * Set the GLOBAL flags only if the PRESENT flag is + * set otherwise pte_present will return true even on + * a non present pte. The canon_pgprot will clear + * _PAGE_GLOBAL for the ancient hardware that doesn't + * support it. + */ + if (pgprot_val(new_prot) & _PAGE_PRESENT) + pgprot_val(new_prot) |= _PAGE_GLOBAL; + else + pgprot_val(new_prot) &= ~_PAGE_GLOBAL; + + /* * We need to keep the pfn from the existing PTE, * after all we're only going to change it's attributes * not the memory it points to diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 9b9054b98187..fe59054afc1d 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -320,10 +320,17 @@ static void __init do_add_efi_memmap(void) int e820_type; switch (md->type) { - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: + /* EFI_BOOT_SERVICES_{CODE,DATA} needs to be mapped */ + if (md->attribute & EFI_MEMORY_WB) + e820_type = E820_RAM; + else + e820_type = E820_RESERVED; + e820_add_region(start, size, e820_type); + continue; + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: case EFI_CONVENTIONAL_MEMORY: if (md->attribute & EFI_MEMORY_WB) e820_type = E820_RAM; @@ -348,7 +355,7 @@ static void __init do_add_efi_memmap(void) e820_type = E820_RESERVED; break; } - e820_add_region(start, size, e820_type); + e820_add_limit_region(start, size, e820_type); } sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } @@ -455,6 +462,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + e820_adjust_region(&start, &size); + /* Could not reserve boot area */ if (!size) continue; |