diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/init.c | 469 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 118 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 652 | ||||
| -rw-r--r-- | arch/x86/mm/mm_internal.h | 19 | ||||
| -rw-r--r-- | arch/x86/mm/numa.c | 43 | ||||
| -rw-r--r-- | arch/x86/mm/numa_32.c | 161 | ||||
| -rw-r--r-- | arch/x86/mm/numa_64.c | 13 | ||||
| -rw-r--r-- | arch/x86/mm/numa_internal.h | 6 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr.c | 113 | ||||
| -rw-r--r-- | arch/x86/mm/pat.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable.c | 7 | ||||
| -rw-r--r-- | arch/x86/mm/physaddr.c | 60 | ||||
| -rw-r--r-- | arch/x86/mm/srat.c | 125 |
13 files changed, 1206 insertions, 584 deletions
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d7aea41563b3..4903a03ae876 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -16,87 +16,134 @@ #include <asm/tlb.h> #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ +#include <asm/microcode.h> -unsigned long __initdata pgt_buf_start; -unsigned long __meminitdata pgt_buf_end; -unsigned long __meminitdata pgt_buf_top; +#include "mm_internal.h" -int after_bootmem; +static unsigned long __initdata pgt_buf_start; +static unsigned long __initdata pgt_buf_end; +static unsigned long __initdata pgt_buf_top; -int direct_gbpages -#ifdef CONFIG_DIRECT_GBPAGES - = 1 -#endif -; +static unsigned long min_pfn_mapped; -struct map_range { - unsigned long start; - unsigned long end; - unsigned page_size_mask; -}; +static bool __initdata can_use_brk_pgt = true; /* - * First calculate space needed for kernel direct mapping page tables to cover - * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB - * pages. Then find enough contiguous space for those page tables. + * Pages returned are already directly mapped. + * + * Changing that is likely to break Xen, see commit: + * + * 279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve + * + * for detailed information. */ -static void __init find_early_table_space(struct map_range *mr, int nr_range) +__ref void *alloc_low_pages(unsigned int num) { + unsigned long pfn; int i; - unsigned long puds = 0, pmds = 0, ptes = 0, tables; - unsigned long start = 0, good_end; - phys_addr_t base; - for (i = 0; i < nr_range; i++) { - unsigned long range, extra; + if (after_bootmem) { + unsigned int order; - range = mr[i].end - mr[i].start; - puds += (range + PUD_SIZE - 1) >> PUD_SHIFT; + order = get_order((unsigned long)num << PAGE_SHIFT); + return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK | + __GFP_ZERO, order); + } - if (mr[i].page_size_mask & (1 << PG_LEVEL_1G)) { - extra = range - ((range >> PUD_SHIFT) << PUD_SHIFT); - pmds += (extra + PMD_SIZE - 1) >> PMD_SHIFT; - } else { - pmds += (range + PMD_SIZE - 1) >> PMD_SHIFT; - } + if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { + unsigned long ret; + if (min_pfn_mapped >= max_pfn_mapped) + panic("alloc_low_page: ran out of memory"); + ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT, + max_pfn_mapped << PAGE_SHIFT, + PAGE_SIZE * num , PAGE_SIZE); + if (!ret) + panic("alloc_low_page: can not alloc memory"); + memblock_reserve(ret, PAGE_SIZE * num); + pfn = ret >> PAGE_SHIFT; + } else { + pfn = pgt_buf_end; + pgt_buf_end += num; + printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n", + pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1); + } - if (mr[i].page_size_mask & (1 << PG_LEVEL_2M)) { - extra = range - ((range >> PMD_SHIFT) << PMD_SHIFT); -#ifdef CONFIG_X86_32 - extra += PMD_SIZE; -#endif - ptes += (extra + PAGE_SIZE - 1) >> PAGE_SHIFT; - } else { - ptes += (range + PAGE_SIZE - 1) >> PAGE_SHIFT; - } + for (i = 0; i < num; i++) { + void *adr; + + adr = __va((pfn + i) << PAGE_SHIFT); + clear_page(adr); } - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); - tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE); - tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE); + return __va(pfn << PAGE_SHIFT); +} -#ifdef CONFIG_X86_32 - /* for fixmap */ - tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); -#endif - good_end = max_pfn_mapped << PAGE_SHIFT; +/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */ +#define INIT_PGT_BUF_SIZE (5 * PAGE_SIZE) +RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); +void __init early_alloc_pgt_buf(void) +{ + unsigned long tables = INIT_PGT_BUF_SIZE; + phys_addr_t base; - base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); - if (!base) - panic("Cannot find space for the kernel page tables"); + base = __pa(extend_brk(tables, PAGE_SIZE)); pgt_buf_start = base >> PAGE_SHIFT; pgt_buf_end = pgt_buf_start; pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); +} - printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n", - mr[nr_range - 1].end - 1, pgt_buf_start << PAGE_SHIFT, - (pgt_buf_top << PAGE_SHIFT) - 1); +int after_bootmem; + +int direct_gbpages +#ifdef CONFIG_DIRECT_GBPAGES + = 1 +#endif +; + +static void __init init_gbpages(void) +{ +#ifdef CONFIG_X86_64 + if (direct_gbpages && cpu_has_gbpages) + printk(KERN_INFO "Using GB pages for direct mapping\n"); + else + direct_gbpages = 0; +#endif } -void __init native_pagetable_reserve(u64 start, u64 end) +struct map_range { + unsigned long start; + unsigned long end; + unsigned page_size_mask; +}; + +static int page_size_mask; + +static void __init probe_page_size_mask(void) { - memblock_reserve(start, end - start); + init_gbpages(); + +#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) + /* + * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. + * This will simplify cpa(), which otherwise needs to support splitting + * large pages into small in interrupt context, etc. + */ + if (direct_gbpages) + page_size_mask |= 1 << PG_LEVEL_1G; + if (cpu_has_pse) + page_size_mask |= 1 << PG_LEVEL_2M; +#endif + + /* Enable PSE if available */ + if (cpu_has_pse) + set_in_cr4(X86_CR4_PSE); + + /* Enable PGE if available */ + if (cpu_has_pge) { + set_in_cr4(X86_CR4_PGE); + __supported_pte_mask |= _PAGE_GLOBAL; + } } #ifdef CONFIG_X86_32 @@ -122,58 +169,51 @@ static int __meminit save_mr(struct map_range *mr, int nr_range, } /* - * Setup the direct mapping of the physical memory at PAGE_OFFSET. - * This runs before bootmem is initialized and gets pages directly from - * the physical memory. To access them they are temporarily mapped. + * adjust the page_size_mask for small range to go with + * big page size instead small one if nearby are ram too. */ -unsigned long __init_refok init_memory_mapping(unsigned long start, - unsigned long end) +static void __init_refok adjust_range_page_size_mask(struct map_range *mr, + int nr_range) { - unsigned long page_size_mask = 0; - unsigned long start_pfn, end_pfn; - unsigned long ret = 0; - unsigned long pos; - - struct map_range mr[NR_RANGE_MR]; - int nr_range, i; - int use_pse, use_gbpages; + int i; - printk(KERN_INFO "init_memory_mapping: [mem %#010lx-%#010lx]\n", - start, end - 1); + for (i = 0; i < nr_range; i++) { + if ((page_size_mask & (1<<PG_LEVEL_2M)) && + !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) { + unsigned long start = round_down(mr[i].start, PMD_SIZE); + unsigned long end = round_up(mr[i].end, PMD_SIZE); -#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK) - /* - * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. - * This will simplify cpa(), which otherwise needs to support splitting - * large pages into small in interrupt context, etc. - */ - use_pse = use_gbpages = 0; -#else - use_pse = cpu_has_pse; - use_gbpages = direct_gbpages; +#ifdef CONFIG_X86_32 + if ((end >> PAGE_SHIFT) > max_low_pfn) + continue; #endif - /* Enable PSE if available */ - if (cpu_has_pse) - set_in_cr4(X86_CR4_PSE); + if (memblock_is_region_memory(start, end - start)) + mr[i].page_size_mask |= 1<<PG_LEVEL_2M; + } + if ((page_size_mask & (1<<PG_LEVEL_1G)) && + !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) { + unsigned long start = round_down(mr[i].start, PUD_SIZE); + unsigned long end = round_up(mr[i].end, PUD_SIZE); - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __supported_pte_mask |= _PAGE_GLOBAL; + if (memblock_is_region_memory(start, end - start)) + mr[i].page_size_mask |= 1<<PG_LEVEL_1G; + } } +} - if (use_gbpages) - page_size_mask |= 1 << PG_LEVEL_1G; - if (use_pse) - page_size_mask |= 1 << PG_LEVEL_2M; +static int __meminit split_mem_range(struct map_range *mr, int nr_range, + unsigned long start, + unsigned long end) +{ + unsigned long start_pfn, end_pfn, limit_pfn; + unsigned long pfn; + int i; - memset(mr, 0, sizeof(mr)); - nr_range = 0; + limit_pfn = PFN_DOWN(end); /* head if not big page alignment ? */ - start_pfn = start >> PAGE_SHIFT; - pos = start_pfn << PAGE_SHIFT; + pfn = start_pfn = PFN_DOWN(start); #ifdef CONFIG_X86_32 /* * Don't use a large page for the first 2/4MB of memory @@ -181,66 +221,60 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * and overlapping MTRRs into large pages can cause * slowdowns. */ - if (pos == 0) - end_pfn = 1<<(PMD_SHIFT - PAGE_SHIFT); + if (pfn == 0) + end_pfn = PFN_DOWN(PMD_SIZE); else - end_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ - end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #endif - if (end_pfn > (end >> PAGE_SHIFT)) - end_pfn = end >> PAGE_SHIFT; + if (end_pfn > limit_pfn) + end_pfn = limit_pfn; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); - pos = end_pfn << PAGE_SHIFT; + pfn = end_pfn; } /* big page (2M) range */ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); + start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #ifdef CONFIG_X86_32 - end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ - end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) - end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); + end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); + if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE))) + end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #endif if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; + pfn = end_pfn; } #ifdef CONFIG_X86_64 /* big page (1G) range */ - start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) - << (PUD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); + start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); + end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); - pos = end_pfn << PAGE_SHIFT; + pfn = end_pfn; } /* tail is not big page (1G) alignment */ - start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) - << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); + end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); - pos = end_pfn << PAGE_SHIFT; + pfn = end_pfn; } #endif /* tail is not big page (2M) alignment */ - start_pfn = pos>>PAGE_SHIFT; - end_pfn = end>>PAGE_SHIFT; + start_pfn = pfn; + end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); /* try to merge same page size and continuous */ @@ -257,59 +291,169 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, nr_range--; } + if (!after_bootmem) + adjust_range_page_size_mask(mr, nr_range); + for (i = 0; i < nr_range; i++) printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":( (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k")); - /* - * Find space for the kernel direct mapping tables. - * - * Later we should allocate these tables in the local node of the - * memory mapped. Unfortunately this is done currently before the - * nodes are discovered. - */ - if (!after_bootmem) - find_early_table_space(mr, nr_range); + return nr_range; +} + +struct range pfn_mapped[E820_X_MAX]; +int nr_pfn_mapped; + +static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) +{ + nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX, + nr_pfn_mapped, start_pfn, end_pfn); + nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX); + + max_pfn_mapped = max(max_pfn_mapped, end_pfn); + + if (start_pfn < (1UL<<(32-PAGE_SHIFT))) + max_low_pfn_mapped = max(max_low_pfn_mapped, + min(end_pfn, 1UL<<(32-PAGE_SHIFT))); +} + +bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) +{ + int i; + + for (i = 0; i < nr_pfn_mapped; i++) + if ((start_pfn >= pfn_mapped[i].start) && + (end_pfn <= pfn_mapped[i].end)) + return true; + + return false; +} + +/* + * Setup the direct mapping of the physical memory at PAGE_OFFSET. + * This runs before bootmem is initialized and gets pages directly from + * the physical memory. To access them they are temporarily mapped. + */ +unsigned long __init_refok init_memory_mapping(unsigned long start, + unsigned long end) +{ + struct map_range mr[NR_RANGE_MR]; + unsigned long ret = 0; + int nr_range, i; + + pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n", + start, end - 1); + + memset(mr, 0, sizeof(mr)); + nr_range = split_mem_range(mr, 0, start, end); for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, mr[i].page_size_mask); -#ifdef CONFIG_X86_32 - early_ioremap_page_table_range_init(); + add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT); - load_cr3(swapper_pg_dir); -#endif + return ret >> PAGE_SHIFT; +} - __flush_tlb_all(); +/* + * would have hole in the middle or ends, and only ram parts will be mapped. + */ +static unsigned long __init init_range_memory_mapping( + unsigned long r_start, + unsigned long r_end) +{ + unsigned long start_pfn, end_pfn; + unsigned long mapped_ram_size = 0; + int i; - /* - * Reserve the kernel pagetable pages we used (pgt_buf_start - - * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top) - * so that they can be reused for other purposes. - * - * On native it just means calling memblock_reserve, on Xen it also - * means marking RW the pagetable pages that we allocated before - * but that haven't been used. - * - * In fact on xen we mark RO the whole range pgt_buf_start - - * pgt_buf_top, because we have to make sure that when - * init_memory_mapping reaches the pagetable pages area, it maps - * RO all the pagetable pages, including the ones that are beyond - * pgt_buf_end at that time. - */ - if (!after_bootmem && pgt_buf_end > pgt_buf_start) - x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start), - PFN_PHYS(pgt_buf_end)); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end); + u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end); + if (start >= end) + continue; - if (!after_bootmem) - early_memtest(start, end); + /* + * if it is overlapping with brk pgt, we need to + * alloc pgt buf from memblock instead. + */ + can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >= + min(end, (u64)pgt_buf_top<<PAGE_SHIFT); + init_memory_mapping(start, end); + mapped_ram_size += end - start; + can_use_brk_pgt = true; + } - return ret >> PAGE_SHIFT; + return mapped_ram_size; } +/* (PUD_SHIFT-PMD_SHIFT)/2 */ +#define STEP_SIZE_SHIFT 5 +void __init init_mem_mapping(void) +{ + unsigned long end, real_end, start, last_start; + unsigned long step_size; + unsigned long addr; + unsigned long mapped_ram_size = 0; + unsigned long new_mapped_ram_size; + + probe_page_size_mask(); + +#ifdef CONFIG_X86_64 + end = max_pfn << PAGE_SHIFT; +#else + end = max_low_pfn << PAGE_SHIFT; +#endif + + /* the ISA range is always mapped regardless of memory holes */ + init_memory_mapping(0, ISA_END_ADDRESS); + + /* xen has big range in reserved near end of ram, skip it at first */ + addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, + PAGE_SIZE); + real_end = addr + PMD_SIZE; + + /* step_size need to be small so pgt_buf from BRK could cover it */ + step_size = PMD_SIZE; + max_pfn_mapped = 0; /* will get exact value next */ + min_pfn_mapped = real_end >> PAGE_SHIFT; + last_start = start = real_end; + while (last_start > ISA_END_ADDRESS) { + if (last_start > step_size) { + start = round_down(last_start - 1, step_size); + if (start < ISA_END_ADDRESS) + start = ISA_END_ADDRESS; + } else + start = ISA_END_ADDRESS; + new_mapped_ram_size = init_range_memory_mapping(start, + last_start); + last_start = start; + min_pfn_mapped = last_start >> PAGE_SHIFT; + /* only increase step_size after big range get mapped */ + if (new_mapped_ram_size > mapped_ram_size) + step_size <<= STEP_SIZE_SHIFT; + mapped_ram_size += new_mapped_ram_size; + } + + if (real_end < end) + init_range_memory_mapping(real_end, end); + +#ifdef CONFIG_X86_64 + if (max_pfn > max_low_pfn) { + /* can we preseve max_low_pfn ?*/ + max_low_pfn = max_pfn; + } +#else + early_ioremap_page_table_range_init(); +#endif + + load_cr3(swapper_pg_dir); + __flush_tlb_all(); + + early_memtest(0, max_pfn_mapped << PAGE_SHIFT); +} /* * devmem_is_allowed() checks to see if /dev/mem access to a certain address @@ -391,6 +535,15 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { +#ifdef CONFIG_MICROCODE_EARLY + /* + * Remember, initrd memory may contain microcode or other useful things. + * Before we lose initrd mem, we need to find a place to hold them + * now that normal virtual memory is enabled. + */ + save_microcode_in_initrd(); +#endif + /* * end could be not aligned, and We can not align that, * decompresser could be confused by aligned initrd_end diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 745d66b843c8..2d19001151d5 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -53,25 +53,14 @@ #include <asm/page_types.h> #include <asm/init.h> +#include "mm_internal.h" + unsigned long highstart_pfn, highend_pfn; static noinline int do_test_wp_bit(void); bool __read_mostly __vmalloc_start_set = false; -static __init void *alloc_low_page(void) -{ - unsigned long pfn = pgt_buf_end++; - void *adr; - - if (pfn >= pgt_buf_top) - panic("alloc_low_page: ran out of memory"); - - adr = __va(pfn * PAGE_SIZE); - clear_page(adr); - return adr; -} - /* * Creates a middle page table and puts a pointer to it in the * given global directory entry. This only returns the gd entry @@ -84,10 +73,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) #ifdef CONFIG_X86_PAE if (!(pgd_val(*pgd) & _PAGE_PRESENT)) { - if (after_bootmem) - pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE); - else - pmd_table = (pmd_t *)alloc_low_page(); + pmd_table = (pmd_t *)alloc_low_page(); paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT); set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); pud = pud_offset(pgd, 0); @@ -109,17 +95,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd) static pte_t * __init one_page_table_init(pmd_t *pmd) { if (!(pmd_val(*pmd) & _PAGE_PRESENT)) { - pte_t *page_table = NULL; - - if (after_bootmem) { -#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK) - page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE); -#endif - if (!page_table) - page_table = - (pte_t *)alloc_bootmem_pages(PAGE_SIZE); - } else - page_table = (pte_t *)alloc_low_page(); + pte_t *page_table = (pte_t *)alloc_low_page(); paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); @@ -146,8 +122,39 @@ pte_t * __init populate_extra_pte(unsigned long vaddr) return one_page_table_init(pmd) + pte_idx; } +static unsigned long __init +page_table_range_init_count(unsigned long start, unsigned long end) +{ + unsigned long count = 0; +#ifdef CONFIG_HIGHMEM + int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT; + int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT; + int pgd_idx, pmd_idx; + unsigned long vaddr; + + if (pmd_idx_kmap_begin == pmd_idx_kmap_end) + return 0; + + vaddr = start; + pgd_idx = pgd_index(vaddr); + + for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) { + for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); + pmd_idx++) { + if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin && + (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) + count++; + vaddr += PMD_SIZE; + } + pmd_idx = 0; + } +#endif + return count; +} + static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, - unsigned long vaddr, pte_t *lastpte) + unsigned long vaddr, pte_t *lastpte, + void **adr) { #ifdef CONFIG_HIGHMEM /* @@ -161,16 +168,15 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, if (pmd_idx_kmap_begin != pmd_idx_kmap_end && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin - && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end - && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start - || (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) { + && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) { pte_t *newpte; int i; BUG_ON(after_bootmem); - newpte = alloc_low_page(); + newpte = *adr; for (i = 0; i < PTRS_PER_PTE; i++) set_pte(newpte + i, pte[i]); + *adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE); paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE)); @@ -204,6 +210,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) pgd_t *pgd; pmd_t *pmd; pte_t *pte = NULL; + unsigned long count = page_table_range_init_count(start, end); + void *adr = NULL; + + if (count) + adr = alloc_low_pages(count); vaddr = start; pgd_idx = pgd_index(vaddr); @@ -216,7 +227,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { pte = page_table_kmap_check(one_page_table_init(pmd), - pmd, vaddr, pte); + pmd, vaddr, pte, &adr); vaddr += PMD_SIZE; } @@ -310,6 +321,7 @@ repeat: __pgprot(PTE_IDENT_ATTR | _PAGE_PSE); + pfn &= PMD_MASK >> PAGE_SHIFT; addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; @@ -455,9 +467,14 @@ void __init native_pagetable_init(void) /* * Remove any mappings which extend past the end of physical - * memory from the boot time page table: + * memory from the boot time page table. + * In virtual address space, we should have at least two pages + * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END + * definition. And max_low_pfn is set to VMALLOC_END physical + * address. If initial memory mapping is doing right job, we + * should have pte used near max_low_pfn or one pmd is not present. */ - for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) { + for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) { va = PAGE_OFFSET + (pfn<<PAGE_SHIFT); pgd = base + pgd_index(va); if (!pgd_present(*pgd)) @@ -468,10 +485,19 @@ void __init native_pagetable_init(void) if (!pmd_present(*pmd)) break; + /* should not be large page here */ + if (pmd_large(*pmd)) { + pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n", + pfn, pmd, __pa(pmd)); + BUG_ON(1); + } + pte = pte_offset_kernel(pmd, va); if (!pte_present(*pte)) break; + printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n", + pfn, pmd, __pa(pmd), pte, __pa(pte)); pte_clear(NULL, va, pte); } paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT); @@ -550,7 +576,7 @@ early_param("highmem", parse_highmem); * artificially via the highmem=x boot parameter then create * it: */ -void __init lowmem_pfn_init(void) +static void __init lowmem_pfn_init(void) { /* max_low_pfn is 0, we already have early_res support */ max_low_pfn = max_pfn; @@ -586,7 +612,7 @@ void __init lowmem_pfn_init(void) * We have more RAM than fits into lowmem - we try to put it into * highmem, also taking the highmem=x boot parameter into account: */ -void __init highmem_pfn_init(void) +static void __init highmem_pfn_init(void) { max_low_pfn = MAXMEM_PFN; @@ -669,8 +695,6 @@ void __init setup_bootmem_allocator(void) printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); - - after_bootmem = 1; } /* @@ -753,6 +777,8 @@ void __init mem_init(void) if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) reservedpages++; + after_bootmem = 1; + codesize = (unsigned long) &_etext - (unsigned long) &_text; datasize = (unsigned long) &_edata - (unsigned long) &_etext; initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; @@ -836,6 +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 d6eeead43758..474e28f10815 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -54,6 +54,82 @@ #include <asm/uv/uv.h> #include <asm/setup.h> +#include "mm_internal.h" + +static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, + unsigned long addr, unsigned long end) +{ + addr &= PMD_MASK; + for (; addr < end; addr += PMD_SIZE) { + pmd_t *pmd = pmd_page + pmd_index(addr); + + if (!pmd_present(*pmd)) + set_pmd(pmd, __pmd(addr | pmd_flag)); + } +} +static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + + for (; addr < end; addr = next) { + pud_t *pud = pud_page + pud_index(addr); + pmd_t *pmd; + + next = (addr & PUD_MASK) + PUD_SIZE; + if (next > end) + next = end; + + if (pud_present(*pud)) { + pmd = pmd_offset(pud, 0); + ident_pmd_init(info->pmd_flag, pmd, addr, next); + continue; + } + pmd = (pmd_t *)info->alloc_pgt_page(info->context); + if (!pmd) + return -ENOMEM; + ident_pmd_init(info->pmd_flag, pmd, addr, next); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + + return 0; +} + +int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, + unsigned long addr, unsigned long end) +{ + unsigned long next; + int result; + int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; + + for (; addr < end; addr = next) { + pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pud_t *pud; + + next = (addr & PGDIR_MASK) + PGDIR_SIZE; + if (next > end) + next = end; + + if (pgd_present(*pgd)) { + pud = pud_offset(pgd, 0); + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + continue; + } + + pud = (pud_t *)info->alloc_pgt_page(info->context); + if (!pud) + return -ENOMEM; + result = ident_pud_init(info, pud, addr, next); + if (result) + return result; + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); + } + + return 0; +} + static int __init parse_direct_gbpages_off(char *arg) { direct_gbpages = 0; @@ -302,10 +378,18 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size) void __init cleanup_highmap(void) { unsigned long vaddr = __START_KERNEL_map; - unsigned long vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT); + unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE; unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1; pmd_t *pmd = level2_kernel_pgt; + /* + * Native path, max_pfn_mapped is not set yet. + * Xen has valid max_pfn_mapped set in + * arch/x86/xen/mmu.c:xen_setup_kernel_pagetable(). + */ + if (max_pfn_mapped) + vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT); + for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; @@ -314,69 +398,24 @@ void __init cleanup_highmap(void) } } -static __ref void *alloc_low_page(unsigned long *phys) -{ - unsigned long pfn = pgt_buf_end++; - void *adr; - - if (after_bootmem) { - adr = (void *)get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK); - *phys = __pa(adr); - - return adr; - } - - if (pfn >= pgt_buf_top) - panic("alloc_low_page: ran out of memory"); - - adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); - clear_page(adr); - *phys = pfn * PAGE_SIZE; - return adr; -} - -static __ref void *map_low_page(void *virt) -{ - void *adr; - unsigned long phys, left; - - if (after_bootmem) - return virt; - - phys = __pa(virt); - left = phys & (PAGE_SIZE - 1); - adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE); - adr = (void *)(((unsigned long)adr) | left); - - return adr; -} - -static __ref void unmap_low_page(void *adr) -{ - if (after_bootmem) - return; - - early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE); -} - static unsigned long __meminit phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end, pgprot_t prot) { - unsigned pages = 0; + unsigned long pages = 0, next; unsigned long last_map_addr = end; int i; pte_t *pte = pte_page + pte_index(addr); - for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) { - + for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) { + next = (addr & PAGE_MASK) + PAGE_SIZE; if (addr >= end) { - if (!after_bootmem) { - for(; i < PTRS_PER_PTE; i++, pte++) - set_pte(pte, __pte(0)); - } - break; + if (!after_bootmem && + !e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) && + !e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN)) + set_pte(pte, __pte(0)); + continue; } /* @@ -414,28 +453,25 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, int i = pmd_index(address); for (; i < PTRS_PER_PMD; i++, address = next) { - unsigned long pte_phys; pmd_t *pmd = pmd_page + pmd_index(address); pte_t *pte; pgprot_t new_prot = prot; + next = (address & PMD_MASK) + PMD_SIZE; if (address >= end) { - if (!after_bootmem) { - for (; i < PTRS_PER_PMD; i++, pmd++) - set_pmd(pmd, __pmd(0)); - } - break; + if (!after_bootmem && + !e820_any_mapped(address & PMD_MASK, next, E820_RAM) && + !e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN)) + set_pmd(pmd, __pmd(0)); + continue; } - next = (address & PMD_MASK) + PMD_SIZE; - if (pmd_val(*pmd)) { if (!pmd_large(*pmd)) { spin_lock(&init_mm.page_table_lock); - pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd)); + pte = (pte_t *)pmd_page_vaddr(*pmd); last_map_addr = phys_pte_init(pte, address, end, prot); - unmap_low_page(pte); spin_unlock(&init_mm.page_table_lock); continue; } @@ -464,19 +500,18 @@ 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 >> PAGE_SHIFT, + pfn_pte((address & PMD_MASK) >> PAGE_SHIFT, __pgprot(pgprot_val(prot) | _PAGE_PSE))); spin_unlock(&init_mm.page_table_lock); last_map_addr = next; continue; } - pte = alloc_low_page(&pte_phys); + pte = alloc_low_page(); last_map_addr = phys_pte_init(pte, address, end, new_prot); - unmap_low_page(pte); spin_lock(&init_mm.page_table_lock); - pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); + pmd_populate_kernel(&init_mm, pmd, pte); spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); @@ -492,27 +527,24 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, int i = pud_index(addr); for (; i < PTRS_PER_PUD; i++, addr = next) { - unsigned long pmd_phys; pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; pgprot_t prot = PAGE_KERNEL; - if (addr >= end) - break; - next = (addr & PUD_MASK) + PUD_SIZE; - - if (!after_bootmem && !e820_any_mapped(addr, next, 0)) { - set_pud(pud, __pud(0)); + if (addr >= end) { + if (!after_bootmem && + !e820_any_mapped(addr & PUD_MASK, next, E820_RAM) && + !e820_any_mapped(addr & PUD_MASK, next, E820_RESERVED_KERN)) + set_pud(pud, __pud(0)); continue; } if (pud_val(*pud)) { if (!pud_large(*pud)) { - pmd = map_low_page(pmd_offset(pud, 0)); + pmd = pmd_offset(pud, 0); last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask, prot); - unmap_low_page(pmd); __flush_tlb_all(); continue; } @@ -541,19 +573,19 @@ 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 >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + pfn_pte((addr & PUD_MASK) >> PAGE_SHIFT, + PAGE_KERNEL_LARGE)); spin_unlock(&init_mm.page_table_lock); last_map_addr = next; continue; } - pmd = alloc_low_page(&pmd_phys); + pmd = alloc_low_page(); last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask, prot); - unmap_low_page(pmd); spin_lock(&init_mm.page_table_lock); - pud_populate(&init_mm, pud, __va(pmd_phys)); + pud_populate(&init_mm, pud, pmd); spin_unlock(&init_mm.page_table_lock); } __flush_tlb_all(); @@ -578,28 +610,23 @@ kernel_physical_mapping_init(unsigned long start, for (; start < end; start = next) { pgd_t *pgd = pgd_offset_k(start); - unsigned long pud_phys; pud_t *pud; - next = (start + PGDIR_SIZE) & PGDIR_MASK; - if (next > end) - next = end; + next = (start & PGDIR_MASK) + PGDIR_SIZE; if (pgd_val(*pgd)) { - pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd)); + pud = (pud_t *)pgd_page_vaddr(*pgd); last_map_addr = phys_pud_init(pud, __pa(start), __pa(end), page_size_mask); - unmap_low_page(pud); continue; } - pud = alloc_low_page(&pud_phys); - last_map_addr = phys_pud_init(pud, __pa(start), __pa(next), + pud = alloc_low_page(); + last_map_addr = phys_pud_init(pud, __pa(start), __pa(end), page_size_mask); - unmap_low_page(pud); spin_lock(&init_mm.page_table_lock); - pgd_populate(&init_mm, pgd, __va(pud_phys)); + pgd_populate(&init_mm, pgd, pud); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } @@ -664,13 +691,11 @@ int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + ZONE_NORMAL; - unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT; + unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - last_mapped_pfn = init_memory_mapping(start, start + size); - if (last_mapped_pfn > max_pfn_mapped) - max_pfn_mapped = last_mapped_pfn; + init_memory_mapping(start, start + size); ret = __add_pages(nid, zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); @@ -682,10 +707,357 @@ 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) { + next = pgd_addr_end(start, end); + + pgd = pgd_offset_k(start); + if (!pgd_present(*pgd)) + continue; + + 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; +static void __init register_page_bootmem_info(void) +{ +#ifdef CONFIG_NUMA + int i; + + for_each_online_node(i) + register_page_bootmem_info_node(NODE_DATA(i)); +#endif +} + void __init mem_init(void) { long codesize, reservedpages, datasize, initsize; @@ -698,11 +1070,8 @@ void __init mem_init(void) reservedpages = 0; /* this will put all low memory onto the freelists */ -#ifdef CONFIG_NUMA - totalram_pages = numa_free_all_bootmem(); -#else + register_page_bootmem_info(); totalram_pages = free_all_bootmem(); -#endif absent_pages = absent_pages_in_range(0, max_pfn); reservedpages = max_pfn - totalram_pages - absent_pages; @@ -772,12 +1141,11 @@ void set_kernel_text_ro(void) void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); - unsigned long rodata_start = - ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; + unsigned long rodata_start = PFN_ALIGN(__start_rodata); unsigned long end = (unsigned long) &__end_rodata_hpage_align; - unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table); - unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata); - unsigned long data_start = (unsigned long) &_sdata; + unsigned long text_end = PFN_ALIGN(&__stop___ex_table); + unsigned long rodata_end = PFN_ALIGN(&__end_rodata); + unsigned long all_end = PFN_ALIGN(&_end); printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -786,10 +1154,10 @@ void mark_rodata_ro(void) kernel_set_to_readonly = 1; /* - * The rodata section (but not the kernel text!) should also be - * not-executable. + * The rodata/data/bss/brk section (but not the kernel text!) + * should also be not-executable. */ - set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); rodata_test(); @@ -802,12 +1170,12 @@ void mark_rodata_ro(void) #endif free_init_pages("unused kernel memory", - (unsigned long) page_address(virt_to_page(text_end)), - (unsigned long) - page_address(virt_to_page(rodata_start))); + (unsigned long) __va(__pa_symbol(text_end)), + (unsigned long) __va(__pa_symbol(rodata_start))); + free_init_pages("unused kernel memory", - (unsigned long) page_address(virt_to_page(rodata_end)), - (unsigned long) page_address(virt_to_page(data_start))); + (unsigned long) __va(__pa_symbol(rodata_end)), + (unsigned long) __va(__pa_symbol(_sdata))); } #endif @@ -988,6 +1356,66 @@ 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/mm_internal.h b/arch/x86/mm/mm_internal.h new file mode 100644 index 000000000000..6b563a118891 --- /dev/null +++ b/arch/x86/mm/mm_internal.h @@ -0,0 +1,19 @@ +#ifndef __X86_MM_INTERNAL_H +#define __X86_MM_INTERNAL_H + +void *alloc_low_pages(unsigned int num); +static inline void *alloc_low_page(void) +{ + return alloc_low_pages(1); +} + +void early_ioremap_page_table_range_init(void); + +unsigned long kernel_physical_mapping_init(unsigned long start, + unsigned long end, + unsigned long page_size_mask); +void zone_sizes_init(void); + +extern int after_bootmem; + +#endif /* __X86_MM_INTERNAL_H */ diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 21d02f0d7a2c..ff3633c794c6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -56,7 +56,7 @@ early_param("numa", numa_setup); /* * apicid, cpu, node mappings */ -s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { +s16 __apicid_to_node[MAX_LOCAL_APIC] = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; @@ -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); @@ -100,7 +100,7 @@ void __cpuinit numa_set_node(int cpu, int 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); } @@ -192,7 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) static void __init setup_node_data(int nid, u64 start, u64 end) { const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - bool remapped = false; u64 nd_pa; void *nd; int tnid; @@ -204,37 +203,27 @@ static void __init setup_node_data(int nid, u64 start, u64 end) if (end && (end - start) < NODE_MIN_SIZE) return; - /* initialize remap allocator before aligning to ZONE_ALIGN */ - init_alloc_remap(nid, start, end); - start = roundup(start, ZONE_ALIGN); printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid, start, end - 1); /* - * Allocate node data. Try remap allocator first, node-local - * memory and then any node. Never allocate in DMA zone. + * Allocate node data. Try node-local memory and then any node. + * Never allocate in DMA zone. */ - nd = alloc_remap(nid, nd_size); - if (nd) { - nd_pa = __pa(nd); - remapped = true; - } else { - nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in node %d\n", - nd_size, nid); - return; - } - nd = __va(nd_pa); + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) { + pr_err("Cannot find %zu bytes in any node\n", nd_size); + return; } + nd = __va(nd_pa); /* report and initialize */ - printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]%s\n", - nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : ""); + printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]\n", + nd_pa, nd_pa + nd_size - 1); tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (!remapped && tnid != nid) + if (tnid != nid) printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); node_data[nid] = nd; @@ -570,10 +559,12 @@ static int __init numa_init(int (*init_func)(void)) for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); - nodes_clear(numa_nodes_parsed); + /* + * Do not clear numa_nodes_parsed or zero numa_meminfo here, because + * SRAT was parsed earlier in early_parse_srat(). + */ nodes_clear(node_possible_map); nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES)); numa_reset_distance(); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 534255a36b6b..73a6d7395bd3 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, extern unsigned long highend_pfn, highstart_pfn; -#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE) - -static void *node_remap_start_vaddr[MAX_NUMNODES]; -void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); - -/* - * Remap memory allocator - */ -static unsigned long node_remap_start_pfn[MAX_NUMNODES]; -static void *node_remap_end_vaddr[MAX_NUMNODES]; -static void *node_remap_alloc_vaddr[MAX_NUMNODES]; - -/** - * alloc_remap - Allocate remapped memory - * @nid: NUMA node to allocate memory from - * @size: The size of allocation - * - * Allocate @size bytes from the remap area of NUMA node @nid. The - * size of the remap area is predetermined by init_alloc_remap() and - * only the callers considered there should call this function. For - * more info, please read the comment on top of init_alloc_remap(). - * - * The caller must be ready to handle allocation failure from this - * function and fall back to regular memory allocator in such cases. - * - * CONTEXT: - * Single CPU early boot context. - * - * RETURNS: - * Pointer to the allocated memory on success, %NULL on failure. - */ -void *alloc_remap(int nid, unsigned long size) -{ - void *allocation = node_remap_alloc_vaddr[nid]; - - size = ALIGN(size, L1_CACHE_BYTES); - - if (!allocation || (allocation + size) > node_remap_end_vaddr[nid]) - return NULL; - - node_remap_alloc_vaddr[nid] += size; - memset(allocation, 0, size); - - return allocation; -} - -#ifdef CONFIG_HIBERNATION -/** - * resume_map_numa_kva - add KVA mapping to the temporary page tables created - * during resume from hibernation - * @pgd_base - temporary resume page directory - */ -void resume_map_numa_kva(pgd_t *pgd_base) -{ - int node; - - for_each_online_node(node) { - unsigned long start_va, start_pfn, nr_pages, pfn; - - start_va = (unsigned long)node_remap_start_vaddr[node]; - start_pfn = node_remap_start_pfn[node]; - nr_pages = (node_remap_end_vaddr[node] - - node_remap_start_vaddr[node]) >> PAGE_SHIFT; - - printk(KERN_DEBUG "%s: node %d\n", __func__, node); - - for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) { - unsigned long vaddr = start_va + (pfn << PAGE_SHIFT); - pgd_t *pgd = pgd_base + pgd_index(vaddr); - pud_t *pud = pud_offset(pgd, vaddr); - pmd_t *pmd = pmd_offset(pud, vaddr); - - set_pmd(pmd, pfn_pmd(start_pfn + pfn, - PAGE_KERNEL_LARGE_EXEC)); - - printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n", - __func__, vaddr, start_pfn + pfn); - } - } -} -#endif - -/** - * init_alloc_remap - Initialize remap allocator for a NUMA node - * @nid: NUMA node to initizlie remap allocator for - * - * NUMA nodes may end up without any lowmem. As allocating pgdat and - * memmap on a different node with lowmem is inefficient, a special - * remap allocator is implemented which can be used by alloc_remap(). - * - * For each node, the amount of memory which will be necessary for - * pgdat and memmap is calculated and two memory areas of the size are - * allocated - one in the node and the other in lowmem; then, the area - * in the node is remapped to the lowmem area. - * - * As pgdat and memmap must be allocated in lowmem anyway, this - * doesn't waste lowmem address space; however, the actual lowmem - * which gets remapped over is wasted. The amount shouldn't be - * problematic on machines this feature will be used. - * - * Initialization failure isn't fatal. alloc_remap() is used - * opportunistically and the callers will fall back to other memory - * allocation mechanisms on failure. - */ -void __init init_alloc_remap(int nid, u64 start, u64 end) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long end_pfn = end >> PAGE_SHIFT; - unsigned long size, pfn; - u64 node_pa, remap_pa; - void *remap_va; - - /* - * The acpi/srat node info can show hot-add memroy zones where - * memory could be added but not currently present. - */ - printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n", - nid, start_pfn, end_pfn); - - /* calculate the necessary space aligned to large page size */ - size = node_memmap_size_bytes(nid, start_pfn, end_pfn); - size += ALIGN(sizeof(pg_data_t), PAGE_SIZE); - size = ALIGN(size, LARGE_PAGE_BYTES); - - /* allocate node memory and the lowmem remap area */ - node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES); - if (!node_pa) { - pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n", - size, nid); - return; - } - memblock_reserve(node_pa, size); - - remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, - max_low_pfn << PAGE_SHIFT, - size, LARGE_PAGE_BYTES); - if (!remap_pa) { - pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", - size, nid); - memblock_free(node_pa, size); - return; - } - memblock_reserve(remap_pa, size); - remap_va = phys_to_virt(remap_pa); - - /* perform actual remap */ - for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE) - set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT), - (node_pa >> PAGE_SHIFT) + pfn, - PAGE_KERNEL_LARGE); - - /* initialize remap allocator parameters */ - node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT; - node_remap_start_vaddr[nid] = remap_va; - node_remap_end_vaddr[nid] = remap_va + size; - node_remap_alloc_vaddr[nid] = remap_va; - - printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n", - nid, node_pa, node_pa + size, remap_va, remap_va + size); -} - void __init initmem_init(void) { x86_numa_init(); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 92e27119ee1a..9405ffc91502 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -10,16 +10,3 @@ void __init initmem_init(void) { x86_numa_init(); } - -unsigned long __init numa_free_all_bootmem(void) -{ - unsigned long pages = 0; - int i; - - for_each_online_node(i) - pages += free_all_bootmem_node(NODE_DATA(i)); - - pages += free_low_memory_core_early(MAX_NUMNODES); - - return pages; -} diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index 7178c3afe05e..ad86ec91e640 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -21,12 +21,6 @@ void __init numa_reset_distance(void); void __init x86_numa_init(void); -#ifdef CONFIG_X86_64 -static inline void init_alloc_remap(int nid, u64 start, u64 end) { } -#else -void __init init_alloc_remap(int nid, u64 start, u64 end); -#endif - #ifdef CONFIG_NUMA_EMU void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 2713be4bca41..091934e1d0d9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -94,12 +94,12 @@ static inline void split_page_count(int level) { } static inline unsigned long highmap_start_pfn(void) { - return __pa(_text) >> PAGE_SHIFT; + return __pa_symbol(_text) >> PAGE_SHIFT; } static inline unsigned long highmap_end_pfn(void) { - return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; + return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT; } #endif @@ -276,8 +276,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, * The .rodata section needs to be read-only. Using the pfn * catches all aliases. */ - if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, - __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) + if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT, + __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) @@ -364,6 +364,37 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) EXPORT_SYMBOL_GPL(lookup_address); /* + * This is necessary because __pa() does not work on some + * kinds of memory, like vmalloc() or the alloc_remap() + * areas on 32-bit NUMA systems. The percpu areas can + * end up in this kind of memory, for instance. + * + * This could be optimized, but it is only intended to be + * used at inititalization time, and keeping it + * unoptimized should increase the testing coverage for + * the more obscure platforms. + */ +phys_addr_t slow_virt_to_phys(void *__virt_addr) +{ + unsigned long virt_addr = (unsigned long)__virt_addr; + phys_addr_t phys_addr; + unsigned long offset; + enum pg_level level; + unsigned long psize; + unsigned long pmask; + pte_t *pte; + + pte = lookup_address(virt_addr, &level); + BUG_ON(!pte); + psize = page_level_size(level); + pmask = page_level_mask(level); + offset = virt_addr & ~pmask; + phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + return (phys_addr | offset); +} +EXPORT_SYMBOL_GPL(slow_virt_to_phys); + +/* * Set the new pmd in all the pgds we know about: */ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte) @@ -396,7 +427,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; - unsigned int level; + enum pg_level level; if (cpa->force_split) return 1; @@ -412,15 +443,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, switch (level) { case PG_LEVEL_2M: - psize = PMD_PAGE_SIZE; - pmask = PMD_PAGE_MASK; - break; #ifdef CONFIG_X86_64 case PG_LEVEL_1G: - psize = PUD_PAGE_SIZE; - pmask = PUD_PAGE_MASK; - break; #endif + psize = page_level_size(level); + pmask = page_level_mask(level); + break; default: do_split = -EINVAL; goto out_unlock; @@ -514,21 +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); /* @@ -536,10 +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)); /* @@ -583,16 +604,10 @@ static int split_large_page(pte_t *kpte, unsigned long address) for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); - if (address >= (unsigned long)__va(0) && - address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT)) + if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), + PFN_DOWN(__pa(address)) + 1)) split_page_count(level); -#ifdef CONFIG_X86_64 - if (address >= (unsigned long)__va(1UL<<32) && - address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT)) - split_page_count(level); -#endif - /* * Install the new, split up pagetable. * @@ -611,17 +626,27 @@ static int split_large_page(pte_t *kpte, unsigned long address) * going on. */ __flush_tlb_all(); + spin_unlock(&pgd_lock); + + return 0; +} - base = NULL; +static int split_large_page(pte_t *kpte, unsigned long address) +{ + pte_t *pbase; + struct page *base; -out_unlock: - /* - * If we dropped out via the lookup_address check under - * pgd_lock then stick the page back into the pool: - */ - if (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; } @@ -773,13 +798,9 @@ static int cpa_process_alias(struct cpa_data *cpa) unsigned long vaddr; int ret; - if (cpa->pfn >= max_pfn_mapped) + if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1)) return 0; -#ifdef CONFIG_X86_64 - if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT))) - return 0; -#endif /* * No need to redo, when the primary call touched the direct * mapping already: diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 0eb572eda406..2610bd93c896 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -560,10 +560,10 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags) { unsigned long id_sz; - if (base >= __pa(high_memory)) + if (base > __pa(high_memory-1)) return 0; - id_sz = (__pa(high_memory) < base + size) ? + id_sz = (__pa(high_memory-1) <= base + size) ? __pa(high_memory) - base : size; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e27fbf887f3b..193350b51f90 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -334,7 +334,12 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *pmdp = entry; pmd_update_defer(vma->vm_mm, address, pmdp); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + /* + * We had a write-protection fault here and changed the pmd + * to to more permissive. No need to flush the TLB for that, + * #PF is architecturally guaranteed to do that and in the + * worst-case we'll generate a spurious fault. + */ } return changed; diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index d2e2735327b4..e666cbbb9261 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,3 +1,4 @@ +#include <linux/bootmem.h> #include <linux/mmdebug.h> #include <linux/module.h> #include <linux/mm.h> @@ -8,33 +9,54 @@ #ifdef CONFIG_X86_64 +#ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { - if (x >= __START_KERNEL_map) { - x -= __START_KERNEL_map; - VIRTUAL_BUG_ON(x >= KERNEL_IMAGE_SIZE); - x += phys_base; + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { - VIRTUAL_BUG_ON(x < PAGE_OFFSET); - x -= PAGE_OFFSET; - VIRTUAL_BUG_ON(!phys_addr_valid(x)); + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } + return x; } EXPORT_SYMBOL(__phys_addr); +unsigned long __phys_addr_symbol(unsigned long x) +{ + unsigned long y = x - __START_KERNEL_map; + + /* only check upper bounds since lower bounds will trigger carry */ + VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); + + return y + phys_base; +} +EXPORT_SYMBOL(__phys_addr_symbol); +#endif + bool __virt_addr_valid(unsigned long x) { - if (x >= __START_KERNEL_map) { - x -= __START_KERNEL_map; - if (x >= KERNEL_IMAGE_SIZE) + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + if (y >= KERNEL_IMAGE_SIZE) return false; - x += phys_base; } else { - if (x < PAGE_OFFSET) - return false; - x -= PAGE_OFFSET; - if (!phys_addr_valid(x)) + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + if ((x > y) || !phys_addr_valid(x)) return false; } @@ -47,10 +69,16 @@ EXPORT_SYMBOL(__virt_addr_valid); #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { + unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); - return x - PAGE_OFFSET; + /* max_low_pfn is set early, but not _that_ early */ + if (max_low_pfn) { + VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); + BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); + } + return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index cdd0da9dd530..79836d01f789 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -141,11 +141,126 @@ static inline int save_add_info(void) {return 1;} static inline int save_add_info(void) {return 0;} #endif +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +static void __init +handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable) +{ + int overlap, i; + unsigned long start_pfn, end_pfn; + + start_pfn = PFN_DOWN(start); + end_pfn = PFN_UP(end); + + /* + * For movablemem_map=acpi: + * + * SRAT: |_____| |_____| |_________| |_________| ...... + * node id: 0 1 1 2 + * hotpluggable: n y y n + * movablemem_map: |_____| |_________| + * + * Using movablemem_map, we can prevent memblock from allocating memory + * on ZONE_MOVABLE at boot time. + * + * Before parsing SRAT, memblock has already reserve some memory ranges + * for other purposes, such as for kernel image. We cannot prevent + * kernel from using these memory, so we need to exclude these memory + * even if it is hotpluggable. + * Furthermore, to ensure the kernel has enough memory to boot, we make + * all the memory on the node which the kernel resides in + * un-hotpluggable. + */ + if (hotpluggable && movablemem_map.acpi) { + /* Exclude ranges reserved by memblock. */ + struct memblock_type *rgn = &memblock.reserved; + + for (i = 0; i < rgn->cnt; i++) { + if (end <= rgn->regions[i].base || + start >= rgn->regions[i].base + + rgn->regions[i].size) + continue; + + /* + * If the memory range overlaps the memory reserved by + * memblock, then the kernel resides in this node. + */ + node_set(node, movablemem_map.numa_nodes_kernel); + + goto out; + } + + /* + * If the kernel resides in this node, then the whole node + * should not be hotpluggable. + */ + if (node_isset(node, movablemem_map.numa_nodes_kernel)) + goto out; + + insert_movablemem_map(start_pfn, end_pfn); + + /* + * numa_nodes_hotplug nodemask represents which nodes are put + * into movablemem_map.map[]. + */ + node_set(node, movablemem_map.numa_nodes_hotplug); + goto out; + } + + /* + * For movablemem_map=nn[KMG]@ss[KMG]: + * + * SRAT: |_____| |_____| |_________| |_________| ...... + * node id: 0 1 1 2 + * user specified: |__| |___| + * movablemem_map: |___| |_________| |______| ...... + * + * Using movablemem_map, we can prevent memblock from allocating memory + * on ZONE_MOVABLE at boot time. + * + * NOTE: In this case, SRAT info will be ingored. + */ + overlap = movablemem_map_overlap(start_pfn, end_pfn); + if (overlap >= 0) { + /* + * If part of this range is in movablemem_map, we need to + * add the range after it to extend the range to the end + * of the node, because from the min address specified to + * the end of the node will be ZONE_MOVABLE. + */ + start_pfn = max(start_pfn, + movablemem_map.map[overlap].start_pfn); + insert_movablemem_map(start_pfn, end_pfn); + + /* + * Set the nodemask, so that if the address range on one node + * is not continuse, we can add the subsequent ranges on the + * same node into movablemem_map. + */ + node_set(node, movablemem_map.numa_nodes_hotplug); + } else { + if (node_isset(node, movablemem_map.numa_nodes_hotplug)) + /* + * Insert the range if we already have movable ranges + * on the same node. + */ + insert_movablemem_map(start_pfn, end_pfn); + } +out: + return; +} +#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +static inline void +handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable) +{ +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + /* 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()) @@ -154,7 +269,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) goto out_err_bad_srat; if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) goto out_err; - if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) + hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; + if (hotpluggable && !save_add_info()) goto out_err; start = ma->base_address; @@ -174,9 +290,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", + printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n", node, pxm, - (unsigned long long) start, (unsigned long long) end - 1); + (unsigned long long) start, (unsigned long long) end - 1, + hotpluggable ? "Hot Pluggable": ""); + + handle_movablemem(node, start, end, hotpluggable); return 0; out_err_bad_srat: |