diff options
Diffstat (limited to 'mm/memory.c')
| -rw-r--r-- | mm/memory.c | 3679 |
1 files changed, 2651 insertions, 1028 deletions
diff --git a/mm/memory.c b/mm/memory.c index 0f60baf6f69..8b44f765b64 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -45,18 +45,35 @@ #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/ksm.h> #include <linux/rmap.h> -#include <linux/module.h> +#include <linux/export.h> +#include <linux/delayacct.h> #include <linux/init.h> +#include <linux/writeback.h> +#include <linux/memcontrol.h> +#include <linux/mmu_notifier.h> +#include <linux/kallsyms.h> +#include <linux/swapops.h> +#include <linux/elf.h> +#include <linux/gfp.h> +#include <linux/migrate.h> +#include <linux/string.h> +#include <linux/dma-debug.h> +#include <linux/debugfs.h> +#include <asm/io.h> #include <asm/pgalloc.h> #include <asm/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/pgtable.h> -#include <linux/swapops.h> -#include <linux/elf.h> +#include "internal.h" + +#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS +#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. +#endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ @@ -67,7 +84,6 @@ EXPORT_SYMBOL(max_mapnr); EXPORT_SYMBOL(mem_map); #endif -unsigned long num_physpages; /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end @@ -76,48 +92,308 @@ unsigned long num_physpages; * and ZONE_HIGHMEM. */ void * high_memory; -unsigned long vmalloc_earlyreserve; -EXPORT_SYMBOL(num_physpages); EXPORT_SYMBOL(high_memory); -EXPORT_SYMBOL(vmalloc_earlyreserve); /* - * If a p?d_bad entry is found while walking page tables, report - * the error, before resetting entry to p?d_none. Usually (but - * very seldom) called out from the p?d_none_or_clear_bad macros. + * Randomize the address space (stacks, mmaps, brk, etc.). + * + * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, + * as ancient (libc5 based) binaries can segfault. ) */ +int randomize_va_space __read_mostly = +#ifdef CONFIG_COMPAT_BRK + 1; +#else + 2; +#endif -void pgd_clear_bad(pgd_t *pgd) +static int __init disable_randmaps(char *s) { - pgd_ERROR(*pgd); - pgd_clear(pgd); + randomize_va_space = 0; + return 1; } +__setup("norandmaps", disable_randmaps); -void pud_clear_bad(pud_t *pud) +unsigned long zero_pfn __read_mostly; +unsigned long highest_memmap_pfn __read_mostly; + +/* + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() + */ +static int __init init_zero_pfn(void) { - pud_ERROR(*pud); - pud_clear(pud); + zero_pfn = page_to_pfn(ZERO_PAGE(0)); + return 0; } +core_initcall(init_zero_pfn); -void pmd_clear_bad(pmd_t *pmd) + +#if defined(SPLIT_RSS_COUNTING) + +void sync_mm_rss(struct mm_struct *mm) { - pmd_ERROR(*pmd); - pmd_clear(pmd); + int i; + + for (i = 0; i < NR_MM_COUNTERS; i++) { + if (current->rss_stat.count[i]) { + add_mm_counter(mm, i, current->rss_stat.count[i]); + current->rss_stat.count[i] = 0; + } + } + current->rss_stat.events = 0; +} + +static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) +{ + struct task_struct *task = current; + + if (likely(task->mm == mm)) + task->rss_stat.count[member] += val; + else + add_mm_counter(mm, member, val); } +#define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) +#define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) + +/* sync counter once per 64 page faults */ +#define TASK_RSS_EVENTS_THRESH (64) +static void check_sync_rss_stat(struct task_struct *task) +{ + if (unlikely(task != current)) + return; + if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) + sync_mm_rss(task->mm); +} +#else /* SPLIT_RSS_COUNTING */ + +#define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) +#define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) + +static void check_sync_rss_stat(struct task_struct *task) +{ +} + +#endif /* SPLIT_RSS_COUNTING */ + +#ifdef HAVE_GENERIC_MMU_GATHER + +static int tlb_next_batch(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + batch = tlb->active; + if (batch->next) { + tlb->active = batch->next; + return 1; + } + + if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) + return 0; + + batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); + if (!batch) + return 0; + + tlb->batch_count++; + batch->next = NULL; + batch->nr = 0; + batch->max = MAX_GATHER_BATCH; + + tlb->active->next = batch; + tlb->active = batch; + + return 1; +} + +/* tlb_gather_mmu + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. The @fullmm argument is used when @mm is without + * users and we're going to destroy the full address space (exit/execve). + */ +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end) +{ + tlb->mm = mm; + + /* Is it from 0 to ~0? */ + tlb->fullmm = !(start | (end+1)); + tlb->need_flush_all = 0; + tlb->start = start; + tlb->end = end; + tlb->need_flush = 0; + tlb->local.next = NULL; + tlb->local.nr = 0; + tlb->local.max = ARRAY_SIZE(tlb->__pages); + tlb->active = &tlb->local; + tlb->batch_count = 0; + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb->batch = NULL; +#endif +} + +static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) +{ + tlb->need_flush = 0; + tlb_flush(tlb); +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb_table_flush(tlb); +#endif +} + +static void tlb_flush_mmu_free(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + for (batch = &tlb->local; batch; batch = batch->next) { + free_pages_and_swap_cache(batch->pages, batch->nr); + batch->nr = 0; + } + tlb->active = &tlb->local; +} + +void tlb_flush_mmu(struct mmu_gather *tlb) +{ + if (!tlb->need_flush) + return; + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + +/* tlb_finish_mmu + * Called at the end of the shootdown operation to free up any resources + * that were required. + */ +void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +{ + struct mmu_gather_batch *batch, *next; + + tlb_flush_mmu(tlb); + + /* keep the page table cache within bounds */ + check_pgt_cache(); + + for (batch = tlb->local.next; batch; batch = next) { + next = batch->next; + free_pages((unsigned long)batch, 0); + } + tlb->local.next = NULL; +} + +/* __tlb_remove_page + * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while + * handling the additional races in SMP caused by other CPUs caching valid + * mappings in their TLBs. Returns the number of free page slots left. + * When out of page slots we must call tlb_flush_mmu(). + */ +int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + struct mmu_gather_batch *batch; + + VM_BUG_ON(!tlb->need_flush); + + batch = tlb->active; + batch->pages[batch->nr++] = page; + if (batch->nr == batch->max) { + if (!tlb_next_batch(tlb)) + return 0; + batch = tlb->active; + } + VM_BUG_ON_PAGE(batch->nr > batch->max, page); + + return batch->max - batch->nr; +} + +#endif /* HAVE_GENERIC_MMU_GATHER */ + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + +/* + * See the comment near struct mmu_table_batch. + */ + +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +static void tlb_remove_table_one(void *table) +{ + /* + * This isn't an RCU grace period and hence the page-tables cannot be + * assumed to be actually RCU-freed. + * + * It is however sufficient for software page-table walkers that rely on + * IRQ disabling. See the comment near struct mmu_table_batch. + */ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); + __tlb_remove_table(table); +} + +static void tlb_remove_table_rcu(struct rcu_head *head) +{ + struct mmu_table_batch *batch; + int i; + + batch = container_of(head, struct mmu_table_batch, rcu); + + for (i = 0; i < batch->nr; i++) + __tlb_remove_table(batch->tables[i]); + + free_page((unsigned long)batch); +} + +void tlb_table_flush(struct mmu_gather *tlb) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch) { + call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); + *batch = NULL; + } +} + +void tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + struct mmu_table_batch **batch = &tlb->batch; + + tlb->need_flush = 1; + + /* + * When there's less then two users of this mm there cannot be a + * concurrent page-table walk. + */ + if (atomic_read(&tlb->mm->mm_users) < 2) { + __tlb_remove_table(table); + return; + } + + if (*batch == NULL) { + *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); + if (*batch == NULL) { + tlb_remove_table_one(table); + return; + } + (*batch)->nr = 0; + } + (*batch)->tables[(*batch)->nr++] = table; + if ((*batch)->nr == MAX_TABLE_BATCH) + tlb_table_flush(tlb); +} + +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ -static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) +static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr) { - struct page *page = pmd_page(*pmd); + pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); - pte_lock_deinit(page); - pte_free_tlb(tlb, page); - dec_page_state(nr_page_table_pages); - tlb->mm->nr_ptes--; + pte_free_tlb(tlb, token, addr); + atomic_long_dec(&tlb->mm->nr_ptes); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, @@ -134,7 +410,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - free_pte_range(tlb, pmd); + free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; @@ -150,7 +426,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); - pmd_free_tlb(tlb, pmd); + pmd_free_tlb(tlb, pmd, start); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -183,21 +459,18 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, pud = pud_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud); + pud_free_tlb(tlb, pud, start); } /* * This function frees user-level page tables of a process. - * - * Must be called with pagetable lock held. */ -void free_pgd_range(struct mmu_gather **tlb, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; - unsigned long start; /* * The next few lines have given us lots of grief... @@ -241,20 +514,16 @@ void free_pgd_range(struct mmu_gather **tlb, if (addr > end - 1) return; - start = addr; - pgd = pgd_offset((*tlb)->mm, addr); + pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - free_pud_range(*tlb, pgd, addr, next, floor, ceiling); + free_pud_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); - - if (!(*tlb)->fullmm) - flush_tlb_pgtables((*tlb)->mm, start, end); } -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { @@ -262,12 +531,13 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, unsigned long addr = vma->vm_start; /* - * Hide vma from rmap and vmtruncate before freeing pgtables + * Hide vma from rmap and truncate_pagecache before freeing + * pgtables */ - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); - if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) { + if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next? next->vm_start: ceiling); } else { @@ -275,11 +545,10 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE - && !is_hugepage_only_range(vma->vm_mm, next->vm_start, - HPAGE_SIZE)) { + && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; - anon_vma_unlink(vma); + unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, @@ -289,23 +558,43 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, } } -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long address) { - struct page *new = pte_alloc_one(mm, address); + spinlock_t *ptl; + pgtable_t new = pte_alloc_one(mm, address); + int wait_split_huge_page; if (!new) return -ENOMEM; - pte_lock_init(new); - spin_lock(&mm->page_table_lock); - if (pmd_present(*pmd)) { /* Another has populated it */ - pte_lock_deinit(new); - pte_free(new); - } else { - mm->nr_ptes++; - inc_page_state(nr_page_table_pages); + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_read_barrier_depends() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + + ptl = pmd_lock(mm, pmd); + wait_split_huge_page = 0; + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + atomic_long_inc(&mm->nr_ptes); pmd_populate(mm, pmd, new); - } - spin_unlock(&mm->page_table_lock); + new = NULL; + } else if (unlikely(pmd_trans_splitting(*pmd))) + wait_split_huge_page = 1; + spin_unlock(ptl); + if (new) + pte_free(mm, new); + if (wait_split_huge_page) + wait_split_huge_page(vma->anon_vma, pmd); return 0; } @@ -315,38 +604,194 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&init_mm.page_table_lock); - if (pmd_present(*pmd)) /* Another has populated it */ - pte_free_kernel(new); - else + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); + new = NULL; + } else + VM_BUG_ON(pmd_trans_splitting(*pmd)); spin_unlock(&init_mm.page_table_lock); + if (new) + pte_free_kernel(&init_mm, new); return 0; } -static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +static inline void init_rss_vec(int *rss) +{ + memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); +} + +static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { - if (file_rss) - add_mm_counter(mm, file_rss, file_rss); - if (anon_rss) - add_mm_counter(mm, anon_rss, anon_rss); + int i; + + if (current->mm == mm) + sync_mm_rss(mm); + for (i = 0; i < NR_MM_COUNTERS; i++) + if (rss[i]) + add_mm_counter(mm, i, rss[i]); } /* - * This function is called to print an error when a pte in a - * !VM_RESERVED region is found pointing to an invalid pfn (which - * is an error. + * This function is called to print an error when a bad pte + * is found. For example, we might have a PFN-mapped pte in + * a region that doesn't allow it. * * The calling function must still handle the error. */ -void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr) +static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, struct page *page) { - printk(KERN_ERR "Bad pte = %08llx, process = %s, " - "vm_flags = %lx, vaddr = %lx\n", - (long long)pte_val(pte), - (vma->vm_mm == current->mm ? current->comm : "???"), - vma->vm_flags, vaddr); + pgd_t *pgd = pgd_offset(vma->vm_mm, addr); + pud_t *pud = pud_offset(pgd, addr); + pmd_t *pmd = pmd_offset(pud, addr); + struct address_space *mapping; + pgoff_t index; + static unsigned long resume; + static unsigned long nr_shown; + static unsigned long nr_unshown; + + /* + * Allow a burst of 60 reports, then keep quiet for that minute; + * or allow a steady drip of one report per second. + */ + if (nr_shown == 60) { + if (time_before(jiffies, resume)) { + nr_unshown++; + return; + } + if (nr_unshown) { + printk(KERN_ALERT + "BUG: Bad page map: %lu messages suppressed\n", + nr_unshown); + nr_unshown = 0; + } + nr_shown = 0; + } + if (nr_shown++ == 0) + resume = jiffies + 60 * HZ; + + mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; + index = linear_page_index(vma, addr); + + printk(KERN_ALERT + "BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", + current->comm, + (long long)pte_val(pte), (long long)pmd_val(*pmd)); + if (page) + dump_page(page, "bad pte"); + printk(KERN_ALERT + "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", + (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); + /* + * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y + */ + if (vma->vm_ops) + printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", + vma->vm_ops->fault); + if (vma->vm_file) + printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", + vma->vm_file->f_op->mmap); dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +} + +/* + * vm_normal_page -- This function gets the "struct page" associated with a pte. + * + * "Special" mappings do not wish to be associated with a "struct page" (either + * it doesn't exist, or it exists but they don't want to touch it). In this + * case, NULL is returned here. "Normal" mappings do have a struct page. + * + * There are 2 broad cases. Firstly, an architecture may define a pte_special() + * pte bit, in which case this function is trivial. Secondly, an architecture + * may not have a spare pte bit, which requires a more complicated scheme, + * described below. + * + * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a + * special mapping (even if there are underlying and valid "struct pages"). + * COWed pages of a VM_PFNMAP are always normal. + * + * The way we recognize COWed pages within VM_PFNMAP mappings is through the + * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit + * set, and the vm_pgoff will point to the first PFN mapped: thus every special + * mapping will always honor the rule + * + * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) + * + * And for normal mappings this is false. + * + * This restricts such mappings to be a linear translation from virtual address + * to pfn. To get around this restriction, we allow arbitrary mappings so long + * as the vma is not a COW mapping; in that case, we know that all ptes are + * special (because none can have been COWed). + * + * + * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. + * + * VM_MIXEDMAP mappings can likewise contain memory with or without "struct + * page" backing, however the difference is that _all_ pages with a struct + * page (that is, those where pfn_valid is true) are refcounted and considered + * normal pages by the VM. The disadvantage is that pages are refcounted + * (which can be slower and simply not an option for some PFNMAP users). The + * advantage is that we don't have to follow the strict linearity rule of + * PFNMAP mappings in order to support COWable mappings. + * + */ +#ifdef __HAVE_ARCH_PTE_SPECIAL +# define HAVE_PTE_SPECIAL 1 +#else +# define HAVE_PTE_SPECIAL 0 +#endif +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + if (HAVE_PTE_SPECIAL) { + if (likely(!pte_special(pte) || pte_numa(pte))) + goto check_pfn; + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return NULL; + if (!is_zero_pfn(pfn)) + print_bad_pte(vma, addr, pte, NULL); + return NULL; + } + + /* !HAVE_PTE_SPECIAL case follows: */ + + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + +check_pfn: + if (unlikely(pfn > highest_memmap_pfn)) { + print_bad_pte(vma, addr, pte, NULL); + return NULL; + } + + if (is_zero_pfn(pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); } /* @@ -355,7 +800,7 @@ void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr) * covered by this vma. */ -static inline void +static inline unsigned long copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr, int *rss) @@ -363,12 +808,15 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; - unsigned long pfn; /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { if (!pte_file(pte)) { - swap_duplicate(pte_to_swp_entry(pte)); + swp_entry_t entry = pte_to_swp_entry(pte); + + if (swap_duplicate(entry) < 0) + return entry.val; + /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); @@ -377,34 +825,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, &src_mm->mmlist); spin_unlock(&mmlist_lock); } - } - goto out_set_pte; - } + if (likely(!non_swap_entry(entry))) + rss[MM_SWAPENTS]++; + else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); - /* If the region is VM_RESERVED, the mapping is not - * mapped via rmap - duplicate the pte as is. - */ - if (vm_flags & VM_RESERVED) + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } + } goto out_set_pte; - - pfn = pte_pfn(pte); - /* If the pte points outside of valid memory but - * the region is not VM_RESERVED, we have a problem. - */ - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, pte, addr); - goto out_set_pte; /* try to do something sane */ } - page = pfn_to_page(pfn); - /* * If it's a COW mapping, write protect it both * in the parent and the child */ - if ((vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) { + if (is_cow_mapping(vm_flags)) { ptep_set_wrprotect(src_mm, addr, src_pte); - pte = *src_pte; + pte = pte_wrprotect(pte); } /* @@ -414,31 +868,45 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); - get_page(page); - page_dup_rmap(page); - rss[!!PageAnon(page)]++; + + page = vm_normal_page(vma, addr, pte); + if (page) { + get_page(page); + page_dup_rmap(page); + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + } out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; } -static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) { + pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress = 0; - int rss[2]; + int rss[NR_MM_COUNTERS]; + swp_entry_t entry = (swp_entry_t){0}; again: - rss[1] = rss[0] = 0; + init_rss_vec(rss); + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; - src_pte = pte_offset_map_nested(src_pmd, addr); + src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); - spin_lock(src_ptl); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + orig_src_pte = src_pte; + orig_dst_pte = dst_pte; + arch_enter_lazy_mmu_mode(); do { /* @@ -448,23 +916,32 @@ again: if (progress >= 32) { progress = 0; if (need_resched() || - need_lockbreak(src_ptl) || - need_lockbreak(dst_ptl)) + spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } - copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss); + entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, + vma, addr, rss); + if (entry.val) + break; progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); - pte_unmap_nested(src_pte - 1); - add_mm_rss(dst_mm, rss[0], rss[1]); - pte_unmap_unlock(dst_pte - 1, dst_ptl); + pte_unmap(orig_src_pte); + add_mm_rss_vec(dst_mm, rss); + pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); + + if (entry.val) { + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) + return -ENOMEM; + progress = 0; + } if (addr != end) goto again; return 0; @@ -483,6 +960,17 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*src_pmd)) { + int err; + VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); + err = copy_huge_pmd(dst_mm, src_mm, + dst_pmd, src_pmd, addr, vma); + if (err == -ENOMEM) + return -ENOMEM; + if (!err) + continue; + /* fall through */ + } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, @@ -521,6 +1009,10 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long next; unsigned long addr = vma->vm_start; unsigned long end = vma->vm_end; + unsigned long mmun_start; /* For mmu_notifiers */ + unsigned long mmun_end; /* For mmu_notifiers */ + bool is_cow; + int ret; /* * Don't copy ptes where a page fault will fill them correctly. @@ -528,7 +1020,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) { + if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | + VM_PFNMAP | VM_MIXEDMAP))) { if (!vma->anon_vma) return 0; } @@ -536,44 +1029,75 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); + if (unlikely(vma->vm_flags & VM_PFNMAP)) { + /* + * We do not free on error cases below as remove_vma + * gets called on error from higher level routine + */ + ret = track_pfn_copy(vma); + if (ret) + return ret; + } + + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + is_cow = is_cow_mapping(vma->vm_flags); + mmun_start = addr; + mmun_end = end; + if (is_cow) + mmu_notifier_invalidate_range_start(src_mm, mmun_start, + mmun_end); + + ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next)) - return -ENOMEM; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - return 0; + + if (is_cow) + mmu_notifier_invalidate_range_end(src_mm, mmun_start, mmun_end); + return ret; } -static void zap_pte_range(struct mmu_gather *tlb, +static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; - pte_t *pte; + int force_flush = 0; + int rss[NR_MM_COUNTERS]; spinlock_t *ptl; - int file_rss = 0; - int anon_rss = 0; + pte_t *start_pte; + pte_t *pte; - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); +again: + init_rss_vec(rss); + start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte = start_pte; + arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; - if (pte_none(ptent)) + if (pte_none(ptent)) { continue; + } + if (pte_present(ptent)) { - struct page *page = NULL; - if (!(vma->vm_flags & VM_RESERVED)) { - unsigned long pfn = pte_pfn(ptent); - if (unlikely(!pfn_valid(pfn))) - print_bad_pte(vma, ptent, addr); - else - page = pfn_to_page(pfn); - } + struct page *page; + + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -599,20 +1123,31 @@ static void zap_pte_range(struct mmu_gather *tlb, continue; if (unlikely(details) && details->nonlinear_vma && linear_page_index(details->nonlinear_vma, - addr) != page->index) - set_pte_at(mm, addr, pte, - pgoff_to_pte(page->index)); + addr) != page->index) { + pte_t ptfile = pgoff_to_pte(page->index); + if (pte_soft_dirty(ptent)) + pte_file_mksoft_dirty(ptfile); + set_pte_at(mm, addr, pte, ptfile); + } if (PageAnon(page)) - anon_rss--; + rss[MM_ANONPAGES]--; else { - if (pte_dirty(ptent)) + if (pte_dirty(ptent)) { + force_flush = 1; set_page_dirty(page); - if (pte_young(ptent)) + } + if (pte_young(ptent) && + likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); - file_rss--; + rss[MM_FILEPAGES]--; } page_remove_rmap(page); - tlb_remove_page(tlb, page); + if (unlikely(page_mapcount(page) < 0)) + print_bad_pte(vma, addr, ptent, page); + if (unlikely(!__tlb_remove_page(tlb, page))) { + force_flush = 1; + break; + } continue; } /* @@ -621,16 +1156,68 @@ static void zap_pte_range(struct mmu_gather *tlb, */ if (unlikely(details)) continue; - if (!pte_file(ptent)) - free_swap_and_cache(pte_to_swp_entry(ptent)); - pte_clear_full(mm, addr, pte, tlb->fullmm); + if (pte_file(ptent)) { + if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) + print_bad_pte(vma, addr, ptent, NULL); + } else { + swp_entry_t entry = pte_to_swp_entry(ptent); + + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; + + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; + } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); + } + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); - add_mm_rss(mm, file_rss, anon_rss); - pte_unmap_unlock(pte - 1, ptl); + add_mm_rss_vec(mm, rss); + arch_leave_lazy_mmu_mode(); + + /* Do the actual TLB flush before dropping ptl */ + if (force_flush) { + unsigned long old_end; + + /* + * Flush the TLB just for the previous segment, + * then update the range to be the remaining + * TLB range. + */ + old_end = tlb->end; + tlb->end = addr; + tlb_flush_mmu_tlbonly(tlb); + tlb->start = addr; + tlb->end = old_end; + } + pte_unmap_unlock(start_pte, ptl); + + /* + * If we forced a TLB flush (either due to running out of + * batch buffers or because we needed to flush dirty TLB + * entries before releasing the ptl), free the batched + * memory too. Restart if we didn't do everything. + */ + if (force_flush) { + force_flush = 0; + tlb_flush_mmu_free(tlb); + + if (addr != end) + goto again; + } + + return addr; } -static inline void zap_pmd_range(struct mmu_gather *tlb, +static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) @@ -641,13 +1228,40 @@ static inline void zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_none_or_clear_bad(pmd)) - continue; - zap_pte_range(tlb, vma, pmd, addr, next, details); + if (pmd_trans_huge(*pmd)) { + if (next - addr != HPAGE_PMD_SIZE) { +#ifdef CONFIG_DEBUG_VM + if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { + pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", + __func__, addr, end, + vma->vm_start, + vma->vm_end); + BUG(); + } +#endif + split_huge_page_pmd(vma, addr, pmd); + } else if (zap_huge_pmd(tlb, vma, pmd, addr)) + goto next; + /* fall through */ + } + /* + * Here there can be other concurrent MADV_DONTNEED or + * trans huge page faults running, and if the pmd is + * none or trans huge it can change under us. This is + * because MADV_DONTNEED holds the mmap_sem in read + * mode. + */ + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + goto next; + next = zap_pte_range(tlb, vma, pmd, addr, next, details); +next: + cond_resched(); } while (pmd++, addr = next, addr != end); + + return addr; } -static inline void zap_pud_range(struct mmu_gather *tlb, +static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) @@ -660,13 +1274,16 @@ static inline void zap_pud_range(struct mmu_gather *tlb, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - zap_pmd_range(tlb, vma, pud, addr, next, details); + next = zap_pmd_range(tlb, vma, pud, addr, next, details); } while (pud++, addr = next, addr != end); + + return addr; } -static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - struct zap_details *details) +static void unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct zap_details *details) { pgd_t *pgd; unsigned long next; @@ -675,41 +1292,72 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, details = NULL; BUG_ON(addr >= end); + mem_cgroup_uncharge_start(); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_pud_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); + mem_cgroup_uncharge_end(); } -#ifdef CONFIG_PREEMPT -# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE) -#else -/* No preempt: go for improved straight-line efficiency */ -# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE) -#endif + +static void unmap_single_vma(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start_addr, + unsigned long end_addr, + struct zap_details *details) +{ + unsigned long start = max(vma->vm_start, start_addr); + unsigned long end; + + if (start >= vma->vm_end) + return; + end = min(vma->vm_end, end_addr); + if (end <= vma->vm_start) + return; + + if (vma->vm_file) + uprobe_munmap(vma, start, end); + + if (unlikely(vma->vm_flags & VM_PFNMAP)) + untrack_pfn(vma, 0, 0); + + if (start != end) { + if (unlikely(is_vm_hugetlb_page(vma))) { + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of mmap_region. When + * hugetlbfs ->mmap method fails, + * mmap_region() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) { + mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); + __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + } + } else + unmap_page_range(tlb, vma, start, end, details); + } +} /** * unmap_vmas - unmap a range of memory covered by a list of vma's - * @tlbp: address of the caller's struct mmu_gather + * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping - * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here - * @details: details of nonlinear truncation or shared cache invalidation - * - * Returns the end address of the unmapping (restart addr if interrupted). * * Unmap all pages in the vma list. * - * We aim to not hold locks for too long (for scheduling latency reasons). - * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to - * return the ending mmu_gather to the caller. - * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. @@ -719,303 +1367,298 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -unsigned long unmap_vmas(struct mmu_gather **tlbp, +void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, - unsigned long end_addr, unsigned long *nr_accounted, - struct zap_details *details) + unsigned long end_addr) { - unsigned long zap_bytes = ZAP_BLOCK_SIZE; - unsigned long tlb_start = 0; /* For tlb_finish_mmu */ - int tlb_start_valid = 0; - unsigned long start = start_addr; - spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; - int fullmm = (*tlbp)->fullmm; - - for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { - unsigned long end; - - start = max(vma->vm_start, start_addr); - if (start >= vma->vm_end) - continue; - end = min(vma->vm_end, end_addr); - if (end <= vma->vm_start) - continue; - - if (vma->vm_flags & VM_ACCOUNT) - *nr_accounted += (end - start) >> PAGE_SHIFT; - - while (start != end) { - unsigned long block; - - if (!tlb_start_valid) { - tlb_start = start; - tlb_start_valid = 1; - } - - if (is_vm_hugetlb_page(vma)) { - block = end - start; - unmap_hugepage_range(vma, start, end); - } else { - block = min(zap_bytes, end - start); - unmap_page_range(*tlbp, vma, start, - start + block, details); - } - - start += block; - zap_bytes -= block; - if ((long)zap_bytes > 0) - continue; + struct mm_struct *mm = vma->vm_mm; - tlb_finish_mmu(*tlbp, tlb_start, start); + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); + for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) + unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); +} - if (need_resched() || - (i_mmap_lock && need_lockbreak(i_mmap_lock))) { - if (i_mmap_lock) { - *tlbp = NULL; - goto out; - } - cond_resched(); - } +/** + * zap_page_range - remove user pages in a given range + * @vma: vm_area_struct holding the applicable pages + * @start: starting address of pages to zap + * @size: number of bytes to zap + * @details: details of nonlinear truncation or shared cache invalidation + * + * Caller must protect the VMA list + */ +void zap_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long size, struct zap_details *details) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + unsigned long end = start + size; - *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); - tlb_start_valid = 0; - zap_bytes = ZAP_BLOCK_SIZE; - } - } -out: - return start; /* which is now the end (or restart) address */ + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start, end); + update_hiwater_rss(mm); + mmu_notifier_invalidate_range_start(mm, start, end); + for ( ; vma && vma->vm_start < end; vma = vma->vm_next) + unmap_single_vma(&tlb, vma, start, end, details); + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_finish_mmu(&tlb, start, end); } /** - * zap_page_range - remove user pages in a given range + * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of nonlinear truncation or shared cache invalidation + * + * The range must fit into one VMA. */ -unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, +static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mm_struct *mm = vma->vm_mm; - struct mmu_gather *tlb; + struct mmu_gather tlb; unsigned long end = address + size; - unsigned long nr_accounted = 0; lru_add_drain(); - tlb = tlb_gather_mmu(mm, 0); + tlb_gather_mmu(&tlb, mm, address, end); update_hiwater_rss(mm); - end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); - if (tlb) - tlb_finish_mmu(tlb, address, end); - return end; + mmu_notifier_invalidate_range_start(mm, address, end); + unmap_single_vma(&tlb, vma, address, end, details); + mmu_notifier_invalidate_range_end(mm, address, end); + tlb_finish_mmu(&tlb, address, end); +} + +/** + * zap_vma_ptes - remove ptes mapping the vma + * @vma: vm_area_struct holding ptes to be zapped + * @address: starting address of pages to zap + * @size: number of bytes to zap + * + * This function only unmaps ptes assigned to VM_PFNMAP vmas. + * + * The entire address range must be fully contained within the vma. + * + * Returns 0 if successful. + */ +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size) +{ + if (address < vma->vm_start || address + size > vma->vm_end || + !(vma->vm_flags & VM_PFNMAP)) + return -1; + zap_page_range_single(vma, address, size, NULL); + return 0; +} +EXPORT_SYMBOL_GPL(zap_vma_ptes); + +pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pgd_t * pgd = pgd_offset(mm, addr); + pud_t * pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd_t * pmd = pmd_alloc(mm, pud, addr); + if (pmd) { + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pte_alloc_map_lock(mm, pmd, addr, ptl); + } + } + return NULL; } /* - * Do a quick page-table lookup for a single page. + * This is the old fallback for page remapping. + * + * For historical reasons, it only allows reserved pages. Only + * old drivers should use this, and they needed to mark their + * pages reserved for the old functions anyway. */ -struct page *follow_page(struct mm_struct *mm, unsigned long address, - unsigned int flags) +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep, pte; + struct mm_struct *mm = vma->vm_mm; + int retval; + pte_t *pte; spinlock_t *ptl; - unsigned long pfn; - struct page *page; - page = follow_huge_addr(mm, address, flags & FOLL_WRITE); - if (!IS_ERR(page)) { - BUG_ON(flags & FOLL_GET); + retval = -EINVAL; + if (PageAnon(page)) goto out; - } + retval = -ENOMEM; + flush_dcache_page(page); + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + goto out; + retval = -EBUSY; + if (!pte_none(*pte)) + goto out_unlock; - page = NULL; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; + /* Ok, finally just insert the thing.. */ + get_page(page); + inc_mm_counter_fast(mm, MM_FILEPAGES); + page_add_file_rmap(page); + set_pte_at(mm, addr, pte, mk_pte(page, prot)); - pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto no_page_table; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - goto no_page_table; + retval = 0; + pte_unmap_unlock(pte, ptl); + return retval; +out_unlock: + pte_unmap_unlock(pte, ptl); +out: + return retval; +} - if (pmd_huge(*pmd)) { - BUG_ON(flags & FOLL_GET); - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - goto out; +/** + * vm_insert_page - insert single page into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @page: source kernel page + * + * This allows drivers to insert individual pages they've allocated + * into a user vma. + * + * The page has to be a nice clean _individual_ kernel allocation. + * If you allocate a compound page, you need to have marked it as + * such (__GFP_COMP), or manually just split the page up yourself + * (see split_page()). + * + * NOTE! Traditionally this was done with "remap_pfn_range()" which + * took an arbitrary page protection parameter. This doesn't allow + * that. Your vma protection will have to be set up correctly, which + * means that if you want a shared writable mapping, you'd better + * ask for a shared writable mapping! + * + * The page does not need to be reserved. + * + * Usually this function is called from f_op->mmap() handler + * under mm->mmap_sem write-lock, so it can change vma->vm_flags. + * Caller must set VM_MIXEDMAP on vma if it wants to call this + * function from other places, for example from page-fault handler. + */ +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page) +{ + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + if (!page_count(page)) + return -EINVAL; + if (!(vma->vm_flags & VM_MIXEDMAP)) { + BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem)); + BUG_ON(vma->vm_flags & VM_PFNMAP); + vma->vm_flags |= VM_MIXEDMAP; } + return insert_page(vma, addr, page, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_page); - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!ptep) +static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) +{ + struct mm_struct *mm = vma->vm_mm; + int retval; + pte_t *pte, entry; + spinlock_t *ptl; + + retval = -ENOMEM; + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) goto out; + retval = -EBUSY; + if (!pte_none(*pte)) + goto out_unlock; - pte = *ptep; - if (!pte_present(pte)) - goto unlock; - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - pfn = pte_pfn(pte); - if (!pfn_valid(pfn)) - goto unlock; + /* Ok, finally just insert the thing.. */ + entry = pte_mkspecial(pfn_pte(pfn, prot)); + set_pte_at(mm, addr, pte, entry); + update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ - page = pfn_to_page(pfn); - if (flags & FOLL_GET) - get_page(page); - if (flags & FOLL_TOUCH) { - if ((flags & FOLL_WRITE) && - !pte_dirty(pte) && !PageDirty(page)) - set_page_dirty(page); - mark_page_accessed(page); - } -unlock: - pte_unmap_unlock(ptep, ptl); + retval = 0; +out_unlock: + pte_unmap_unlock(pte, ptl); out: - return page; - -no_page_table: - /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate page tables. - */ - if (flags & FOLL_ANON) { - page = ZERO_PAGE(address); - if (flags & FOLL_GET) - get_page(page); - BUG_ON(flags & FOLL_WRITE); - } - return page; + return retval; } -int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, int len, int write, int force, - struct page **pages, struct vm_area_struct **vmas) +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return NULL. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + */ +int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) { - int i; - unsigned int vm_flags; - - /* - * Require read or write permissions. - * If 'force' is set, we only require the "MAY" flags. + int ret; + pgprot_t pgprot = vma->vm_page_prot; + /* + * Technically, architectures with pte_special can avoid all these + * restrictions (same for remap_pfn_range). However we would like + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. */ - vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - i = 0; + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); - do { - struct vm_area_struct *vma; - unsigned int foll_flags; - - vma = find_extend_vma(mm, start); - if (!vma && in_gate_area(tsk, start)) { - unsigned long pg = start & PAGE_MASK; - struct vm_area_struct *gate_vma = get_gate_vma(tsk); - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - if (write) /* user gate pages are read-only */ - return i ? : -EFAULT; - if (pg > TASK_SIZE) - pgd = pgd_offset_k(pg); - else - pgd = pgd_offset_gate(mm, pg); - BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, pg); - BUG_ON(pud_none(*pud)); - pmd = pmd_offset(pud, pg); - if (pmd_none(*pmd)) - return i ? : -EFAULT; - pte = pte_offset_map(pmd, pg); - if (pte_none(*pte)) { - pte_unmap(pte); - return i ? : -EFAULT; - } - if (pages) { - pages[i] = pte_page(*pte); - get_page(pages[i]); - } - pte_unmap(pte); - if (vmas) - vmas[i] = gate_vma; - i++; - start += PAGE_SIZE; - len--; - continue; - } + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + if (track_pfn_insert(vma, &pgprot, pfn)) + return -EINVAL; - if (!vma || (vma->vm_flags & (VM_IO | VM_RESERVED)) - || !(vm_flags & vma->vm_flags)) - return i ? : -EFAULT; + ret = insert_pfn(vma, addr, pfn, pgprot); - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &len, i); - continue; - } + return ret; +} +EXPORT_SYMBOL(vm_insert_pfn); - foll_flags = FOLL_TOUCH; - if (pages) - foll_flags |= FOLL_GET; - if (!write && !(vma->vm_flags & VM_LOCKED) && - (!vma->vm_ops || !vma->vm_ops->nopage)) - foll_flags |= FOLL_ANON; +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); - do { - struct page *page; + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; - if (write) - foll_flags |= FOLL_WRITE; + /* + * If we don't have pte special, then we have to use the pfn_valid() + * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* + * refcount the page if pfn_valid is true (hence insert_page rather + * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP + * without pte special, it would there be refcounted as a normal page. + */ + if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + struct page *page; - cond_resched(); - while (!(page = follow_page(mm, start, foll_flags))) { - int ret; - ret = __handle_mm_fault(mm, vma, start, - foll_flags & FOLL_WRITE); - /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has - * broken COW when necessary, even if maybe_mkwrite - * decided not to set pte_write. We can thus safely do - * subsequent page lookups as if they were reads. - */ - if (ret & VM_FAULT_WRITE) - foll_flags &= ~FOLL_WRITE; - - switch (ret & ~VM_FAULT_WRITE) { - case VM_FAULT_MINOR: - tsk->min_flt++; - break; - case VM_FAULT_MAJOR: - tsk->maj_flt++; - break; - case VM_FAULT_SIGBUS: - return i ? i : -EFAULT; - case VM_FAULT_OOM: - return i ? i : -ENOMEM; - default: - BUG(); - } - } - if (pages) { - pages[i] = page; - flush_dcache_page(page); - } - if (vmas) - vmas[i] = vma; - i++; - start += PAGE_SIZE; - len--; - } while (len && start < vma->vm_end); - } while (len); - return i; + page = pfn_to_page(pfn); + return insert_page(vma, addr, page, vma->vm_page_prot); + } + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); } -EXPORT_SYMBOL(get_user_pages); +EXPORT_SYMBOL(vm_insert_mixed); -static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, unsigned long end, pgprot_t prot) +/* + * maps a range of physical memory into the requested pages. the old + * mappings are removed. any references to nonexistent pages results + * in null mappings (currently treated as "copy-on-access") + */ +static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { pte_t *pte; spinlock_t *ptl; @@ -1023,181 +1666,282 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; + arch_enter_lazy_mmu_mode(); do { - struct page *page = ZERO_PAGE(addr); - pte_t zero_pte = pte_wrprotect(mk_pte(page, prot)); - page_cache_get(page); - page_add_file_rmap(page); - inc_mm_counter(mm, file_rss); BUG_ON(!pte_none(*pte)); - set_pte_at(mm, addr, pte, zero_pte); + set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); + pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return 0; } -static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end, pgprot_t prot) +static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; + pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; + VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); - if (zeromap_pte_range(mm, pmd, addr, next, prot)) + if (remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } -static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end, pgprot_t prot) +static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; + pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, pgd, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (zeromap_pmd_range(mm, pud, addr, next, prot)) + if (remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } -int zeromap_page_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgprot_t prot) +/** + * remap_pfn_range - remap kernel memory to userspace + * @vma: user vma to map to + * @addr: target user address to start at + * @pfn: physical address of kernel memory + * @size: size of map area + * @prot: page protection flags for this mapping + * + * Note: this is only safe if the mm semaphore is held when called. + */ +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; - unsigned long end = addr + size; + unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; + /* + * Physically remapped pages are special. Tell the + * rest of the world about it: + * VM_IO tells people not to look at these pages + * (accesses can have side effects). + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. + * VM_DONTEXPAND + * Disable vma merging and expanding with mremap(). + * VM_DONTDUMP + * Omit vma from core dump, even when VM_IO turned off. + * + * There's a horrible special case to handle copy-on-write + * behaviour that some programs depend on. We mark the "original" + * un-COW'ed pages by matching them up with "vma->vm_pgoff". + * See vm_normal_page() for details. + */ + if (is_cow_mapping(vma->vm_flags)) { + if (addr != vma->vm_start || end != vma->vm_end) + return -EINVAL; + vma->vm_pgoff = pfn; + } + + err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); + if (err) + return -EINVAL; + + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + BUG_ON(addr >= end); + pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = zeromap_pud_range(mm, pgd, addr, next, prot); + err = remap_pud_range(mm, pgd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); if (err) break; } while (pgd++, addr = next, addr != end); + + if (err) + untrack_pfn(vma, pfn, PAGE_ALIGN(size)); + return err; } +EXPORT_SYMBOL(remap_pfn_range); -/* - * maps a range of physical memory into the requested pages. the old - * mappings are removed. any references to nonexistent pages results - * in null mappings (currently treated as "copy-on-access") +/** + * vm_iomap_memory - remap memory to userspace + * @vma: user vma to map to + * @start: start of area + * @len: size of area + * + * This is a simplified io_remap_pfn_range() for common driver use. The + * driver just needs to give us the physical memory range to be mapped, + * we'll figure out the rest from the vma information. + * + * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get + * whatever write-combining details or similar. */ -static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned long pfn, pgprot_t prot) +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long vm_len, pfn, pages; + + /* Check that the physical memory area passed in looks valid */ + if (start + len < start) + return -EINVAL; + /* + * You *really* shouldn't map things that aren't page-aligned, + * but we've historically allowed it because IO memory might + * just have smaller alignment. + */ + len += start & ~PAGE_MASK; + pfn = start >> PAGE_SHIFT; + pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; + if (pfn + pages < pfn) + return -EINVAL; + + /* We start the mapping 'vm_pgoff' pages into the area */ + if (vma->vm_pgoff > pages) + return -EINVAL; + pfn += vma->vm_pgoff; + pages -= vma->vm_pgoff; + + /* Can we fit all of the mapping? */ + vm_len = vma->vm_end - vma->vm_start; + if (vm_len >> PAGE_SHIFT > pages) + return -EINVAL; + + /* Ok, let it rip */ + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + +static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) { pte_t *pte; - spinlock_t *ptl; + int err; + pgtable_t token; + spinlock_t *uninitialized_var(ptl); - pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + pte = (mm == &init_mm) ? + pte_alloc_kernel(pmd, addr) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; + + BUG_ON(pmd_huge(*pmd)); + + arch_enter_lazy_mmu_mode(); + + token = pmd_pgtable(*pmd); + do { - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); - pfn++; - } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap_unlock(pte - 1, ptl); - return 0; + err = fn(pte++, token, addr, data); + if (err) + break; + } while (addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); + + if (mm != &init_mm) + pte_unmap_unlock(pte-1, ptl); + return err; } -static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end, - unsigned long pfn, pgprot_t prot) +static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) { pmd_t *pmd; unsigned long next; + int err; + + BUG_ON(pud_huge(*pud)); - pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); - if (remap_pte_range(mm, pmd, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = apply_to_pte_range(mm, pmd, addr, next, fn, data); + if (err) + break; } while (pmd++, addr = next, addr != end); - return 0; + return err; } -static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end, - unsigned long pfn, pgprot_t prot) +static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) { pud_t *pud; unsigned long next; + int err; - pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, pgd, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (remap_pmd_range(mm, pud, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = apply_to_pmd_range(mm, pud, addr, next, fn, data); + if (err) + break; } while (pud++, addr = next, addr != end); - return 0; + return err; } -/* Note: this is only safe if the mm semaphore is held when called. */ -int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t prot) +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) { pgd_t *pgd; unsigned long next; - unsigned long end = addr + PAGE_ALIGN(size); - struct mm_struct *mm = vma->vm_mm; + unsigned long end = addr + size; int err; - /* - * Physically remapped pages are special. Tell the - * rest of the world about it: - * VM_IO tells people not to look at these pages - * (accesses can have side effects). - * VM_RESERVED tells the core MM not to "manage" these pages - * (e.g. refcount, mapcount, try to swap them out). - */ - vma->vm_flags |= VM_IO | VM_RESERVED; - BUG_ON(addr >= end); - pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); - flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, - pfn + (addr >> PAGE_SHIFT), prot); + err = apply_to_pud_range(mm, pgd, addr, next, fn, data); if (err) break; } while (pgd++, addr = next, addr != end); + return err; } -EXPORT_SYMBOL(remap_pfn_range); +EXPORT_SYMBOL_GPL(apply_to_page_range); /* * handle_pte_fault chooses page fault handler according to an entry * which was read non-atomically. Before making any commitment, on * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_file_page + * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault * must check under lock before unmapping the pte and proceeding * (but do_wp_page is only called after already making such a check; - * and do_anonymous_page and do_no_page can safely check later on). + * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) @@ -1215,17 +1959,64 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; } +static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +{ + debug_dma_assert_idle(src); + + /* + * If the source page was a PFN mapping, we don't have + * a "struct page" for it. We do a best-effort copy by + * just copying from the original user address. If that + * fails, we just zero-fill it. Live with it. + */ + if (unlikely(!src)) { + void *kaddr = kmap_atomic(dst); + void __user *uaddr = (void __user *)(va & PAGE_MASK); + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + clear_page(kaddr); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + } else + copy_user_highpage(dst, src, va, vma); +} + /* - * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when - * servicing faults for write access. In the normal case, do always want - * pte_mkwrite. But get_user_pages can cause write faults for mappings - * that do not have writing enabled, when used by access_process_vm. + * Notify the address space that the page is about to become writable so that + * it can prohibit this or wait for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can sleep if it needs to. */ -static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, + unsigned long address) { - if (likely(vma->vm_flags & VM_WRITE)) - pte = pte_mkwrite(pte); - return pte; + struct vm_fault vmf; + int ret; + + vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.pgoff = page->index; + vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.page = page; + + ret = vma->vm_ops->page_mkwrite(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; + if (unlikely(!(ret & VM_FAULT_LOCKED))) { + lock_page(page); + if (!page->mapping) { + unlock_page(page); + return 0; /* retry */ + } + ret |= VM_FAULT_LOCKED; + } else + VM_BUG_ON_PAGE(!PageLocked(page), page); + return ret; } /* @@ -1249,193 +2040,284 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, spinlock_t *ptl, pte_t orig_pte) + __releases(ptl) { - struct page *old_page, *new_page; - unsigned long pfn = pte_pfn(orig_pte); + struct page *old_page, *new_page = NULL; pte_t entry; - int ret = VM_FAULT_MINOR; - - BUG_ON(vma->vm_flags & VM_RESERVED); - - if (unlikely(!pfn_valid(pfn))) { + int ret = 0; + int page_mkwrite = 0; + struct page *dirty_page = NULL; + unsigned long mmun_start = 0; /* For mmu_notifiers */ + unsigned long mmun_end = 0; /* For mmu_notifiers */ + + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) { /* - * Page table corrupted: show pte and kill process. + * VM_MIXEDMAP !pfn_valid() case + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable as we can't do any dirty + * accounting on raw pfn maps. */ - print_bad_pte(vma, orig_pte, address); - ret = VM_FAULT_OOM; - goto unlock; + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + goto reuse; + goto gotten; } - old_page = pfn_to_page(pfn); - if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { - int reuse = can_share_swap_page(old_page); + /* + * Take out anonymous pages first, anonymous shared vmas are + * not dirty accountable. + */ + if (PageAnon(old_page) && !PageKsm(old_page)) { + if (!trylock_page(old_page)) { + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + lock_page(old_page); + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + goto unlock; + } + page_cache_release(old_page); + } + if (reuse_swap_page(old_page)) { + /* + * The page is all ours. Move it to our anon_vma so + * the rmap code will not search our parent or siblings. + * Protected against the rmap code by the page lock. + */ + page_move_anon_rmap(old_page, vma, address); + unlock_page(old_page); + goto reuse; + } unlock_page(old_page); - if (reuse) { - flush_cache_page(vma, address, pfn); - entry = pte_mkyoung(orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - ptep_set_access_flags(vma, address, page_table, entry, 1); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - ret |= VM_FAULT_WRITE; - goto unlock; + } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED))) { + /* + * Only catch write-faults on shared writable pages, + * read-only shared pages can get COWed by + * get_user_pages(.write=1, .force=1). + */ + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + int tmp; + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + tmp = do_page_mkwrite(vma, old_page, address); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(old_page); + return tmp; + } + /* + * Since we dropped the lock we need to revalidate + * the PTE as someone else may have changed it. If + * they did, we just return, as we can count on the + * MMU to tell us if they didn't also make it writable. + */ + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) { + unlock_page(old_page); + goto unlock; + } + + page_mkwrite = 1; } + dirty_page = old_page; + get_page(dirty_page); + +reuse: + /* + * Clear the pages cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. + */ + if (old_page) + page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1); + + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, address, page_table, entry,1)) + update_mmu_cache(vma, address, page_table); + pte_unmap_unlock(page_table, ptl); + ret |= VM_FAULT_WRITE; + + if (!dirty_page) + return ret; + + /* + * Yes, Virginia, this is actually required to prevent a race + * with clear_page_dirty_for_io() from clearing the page dirty + * bit after it clear all dirty ptes, but before a racing + * do_wp_page installs a dirty pte. + * + * do_shared_fault is protected similarly. + */ + if (!page_mkwrite) { + wait_on_page_locked(dirty_page); + set_page_dirty_balance(dirty_page); + /* file_update_time outside page_lock */ + if (vma->vm_file) + file_update_time(vma->vm_file); + } + put_page(dirty_page); + if (page_mkwrite) { + struct address_space *mapping = dirty_page->mapping; + + set_page_dirty(dirty_page); + unlock_page(dirty_page); + page_cache_release(dirty_page); + if (mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + } + + return ret; } /* * Ok, we need to copy. Oh, well.. */ page_cache_get(old_page); +gotten: pte_unmap_unlock(page_table, ptl); if (unlikely(anon_vma_prepare(vma))) goto oom; - if (old_page == ZERO_PAGE(address)) { - new_page = alloc_zeroed_user_highpage(vma, address); + + if (is_zero_pfn(pte_pfn(orig_pte))) { + new_page = alloc_zeroed_user_highpage_movable(vma, address); if (!new_page) goto oom; } else { - new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (!new_page) goto oom; - copy_user_highpage(new_page, old_page, address); + cow_user_page(new_page, old_page, address, vma); } + __SetPageUptodate(new_page); + + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) + goto oom_free_new; + + mmun_start = address & PAGE_MASK; + mmun_end = mmun_start + PAGE_SIZE; + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); /* * Re-check the pte - we dropped the lock */ page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) { - page_remove_rmap(old_page); - if (!PageAnon(old_page)) { - inc_mm_counter(mm, anon_rss); - dec_mm_counter(mm, file_rss); - } - flush_cache_page(vma, address, pfn); + if (old_page) { + if (!PageAnon(old_page)) { + dec_mm_counter_fast(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, MM_ANONPAGES); + } + } else + inc_mm_counter_fast(mm, MM_ANONPAGES); + flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); - ptep_establish(vma, address, page_table, entry); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); + /* + * Clear the pte entry and flush it first, before updating the + * pte with the new entry. This will avoid a race condition + * seen in the presence of one thread doing SMC and another + * thread doing COW. + */ + ptep_clear_flush(vma, address, page_table); + page_add_new_anon_rmap(new_page, vma, address); + /* + * We call the notify macro here because, when using secondary + * mmu page tables (such as kvm shadow page tables), we want the + * new page to be mapped directly into the secondary page table. + */ + set_pte_at_notify(mm, address, page_table, entry); + update_mmu_cache(vma, address, page_table); + if (old_page) { + /* + * Only after switching the pte to the new page may + * we remove the mapcount here. Otherwise another + * process may come and find the rmap count decremented + * before the pte is switched to the new page, and + * "reuse" the old page writing into it while our pte + * here still points into it and can be read by other + * threads. + * + * The critical issue is to order this + * page_remove_rmap with the ptp_clear_flush above. + * Those stores are ordered by (if nothing else,) + * the barrier present in the atomic_add_negative + * in page_remove_rmap. + * + * Then the TLB flush in ptep_clear_flush ensures that + * no process can access the old page before the + * decremented mapcount is visible. And the old page + * cannot be reused until after the decremented + * mapcount is visible. So transitively, TLBs to + * old page will be flushed before it can be reused. + */ + page_remove_rmap(old_page); + } /* Free the old page.. */ new_page = old_page; ret |= VM_FAULT_WRITE; - } - page_cache_release(new_page); - page_cache_release(old_page); + } else + mem_cgroup_uncharge_page(new_page); + + if (new_page) + page_cache_release(new_page); unlock: pte_unmap_unlock(page_table, ptl); + if (mmun_end > mmun_start) + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + if (old_page) { + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { + lock_page(old_page); /* LRU manipulation */ + munlock_vma_page(old_page); + unlock_page(old_page); + } + page_cache_release(old_page); + } return ret; +oom_free_new: + page_cache_release(new_page); oom: - page_cache_release(old_page); + if (old_page) + page_cache_release(old_page); return VM_FAULT_OOM; } -/* - * Helper functions for unmap_mapping_range(). - * - * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __ - * - * We have to restart searching the prio_tree whenever we drop the lock, - * since the iterator is only valid while the lock is held, and anyway - * a later vma might be split and reinserted earlier while lock dropped. - * - * The list of nonlinear vmas could be handled more efficiently, using - * a placeholder, but handle it in the same way until a need is shown. - * It is important to search the prio_tree before nonlinear list: a vma - * may become nonlinear and be shifted from prio_tree to nonlinear list - * while the lock is dropped; but never shifted from list to prio_tree. - * - * In order to make forward progress despite restarting the search, - * vm_truncate_count is used to mark a vma as now dealt with, so we can - * quickly skip it next time around. Since the prio_tree search only - * shows us those vmas affected by unmapping the range in question, we - * can't efficiently keep all vmas in step with mapping->truncate_count: - * so instead reset them all whenever it wraps back to 0 (then go to 1). - * mapping->truncate_count and vma->vm_truncate_count are protected by - * i_mmap_lock. - * - * In order to make forward progress despite repeatedly restarting some - * large vma, note the restart_addr from unmap_vmas when it breaks out: - * and restart from that address when we reach that vma again. It might - * have been split or merged, shrunk or extended, but never shifted: so - * restart_addr remains valid so long as it remains in the vma's range. - * unmap_mapping_range forces truncate_count to leap over page-aligned - * values so we can save vma's restart_addr in its truncate_count field. - */ -#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK)) - -static void reset_vma_truncate_counts(struct address_space *mapping) -{ - struct vm_area_struct *vma; - struct prio_tree_iter iter; - - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX) - vma->vm_truncate_count = 0; - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) - vma->vm_truncate_count = 0; -} - -static int unmap_mapping_range_vma(struct vm_area_struct *vma, +static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { - unsigned long restart_addr; - int need_break; - -again: - restart_addr = vma->vm_truncate_count; - if (is_restart_addr(restart_addr) && start_addr < restart_addr) { - start_addr = restart_addr; - if (start_addr >= end_addr) { - /* Top of vma has been split off since last time */ - vma->vm_truncate_count = details->truncate_count; - return 0; - } - } - - restart_addr = zap_page_range(vma, start_addr, - end_addr - start_addr, details); - need_break = need_resched() || - need_lockbreak(details->i_mmap_lock); - - if (restart_addr >= end_addr) { - /* We have now completed this vma: mark it so */ - vma->vm_truncate_count = details->truncate_count; - if (!need_break) - return 0; - } else { - /* Note restart_addr in vma's truncate_count field */ - vma->vm_truncate_count = restart_addr; - if (!need_break) - goto again; - } - - spin_unlock(details->i_mmap_lock); - cond_resched(); - spin_lock(details->i_mmap_lock); - return -EINTR; + zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } -static inline void unmap_mapping_range_tree(struct prio_tree_root *root, +static inline void unmap_mapping_range_tree(struct rb_root *root, struct zap_details *details) { struct vm_area_struct *vma; - struct prio_tree_iter iter; pgoff_t vba, vea, zba, zea; -restart: - vma_prio_tree_foreach(vma, &iter, root, + vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { - /* Skip quickly over those we have already dealt with */ - if (vma->vm_truncate_count == details->truncate_count) - continue; vba = vma->vm_pgoff; - vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1; + vea = vba + vma_pages(vma) - 1; /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ zba = details->first_index; if (zba < vba) @@ -1444,11 +2326,10 @@ restart: if (zea > vea) zea = vea; - if (unmap_mapping_range_vma(vma, + unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, - details) < 0) - goto restart; + details); } } @@ -1463,26 +2344,18 @@ static inline void unmap_mapping_range_list(struct list_head *head, * across *all* the pages in each nonlinear VMA, not just the pages * whose virtual address lies outside the file truncation point. */ -restart: - list_for_each_entry(vma, head, shared.vm_set.list) { - /* Skip quickly over those we have already dealt with */ - if (vma->vm_truncate_count == details->truncate_count) - continue; + list_for_each_entry(vma, head, shared.nonlinear) { details->nonlinear_vma = vma; - if (unmap_mapping_range_vma(vma, vma->vm_start, - vma->vm_end, details) < 0) - goto restart; + unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); } } /** - * unmap_mapping_range - unmap the portion of all mmaps - * in the specified address_space corresponding to the specified - * page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE - * boundary. Note that this is different from vmtruncate(), which + * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded @@ -1512,163 +2385,55 @@ void unmap_mapping_range(struct address_space *mapping, details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; - details.i_mmap_lock = &mapping->i_mmap_lock; - - spin_lock(&mapping->i_mmap_lock); - /* serialize i_size write against truncate_count write */ - smp_wmb(); - /* Protect against page faults, and endless unmapping loops */ - mapping->truncate_count++; - /* - * For archs where spin_lock has inclusive semantics like ia64 - * this smp_mb() will prevent to read pagetable contents - * before the truncate_count increment is visible to - * other cpus. - */ - smp_mb(); - if (unlikely(is_restart_addr(mapping->truncate_count))) { - if (mapping->truncate_count == 0) - reset_vma_truncate_counts(mapping); - mapping->truncate_count++; - } - details.truncate_count = mapping->truncate_count; - if (unlikely(!prio_tree_empty(&mapping->i_mmap))) + mutex_lock(&mapping->i_mmap_mutex); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); - spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->i_mmap_mutex); } EXPORT_SYMBOL(unmap_mapping_range); /* - * Handle all mappings that got truncated by a "truncate()" - * system call. - * - * NOTE! We have to be ready to update the memory sharing - * between the file and the memory map for a potential last - * incomplete page. Ugly, but necessary. - */ -int vmtruncate(struct inode * inode, loff_t offset) -{ - struct address_space *mapping = inode->i_mapping; - unsigned long limit; - - if (inode->i_size < offset) - goto do_expand; - /* - * truncation of in-use swapfiles is disallowed - it would cause - * subsequent swapout to scribble on the now-freed blocks. - */ - if (IS_SWAPFILE(inode)) - goto out_busy; - i_size_write(inode, offset); - unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(mapping, offset); - goto out_truncate; - -do_expand: - limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; - if (limit != RLIM_INFINITY && offset > limit) - goto out_sig; - if (offset > inode->i_sb->s_maxbytes) - goto out_big; - i_size_write(inode, offset); - -out_truncate: - if (inode->i_op && inode->i_op->truncate) - inode->i_op->truncate(inode); - return 0; -out_sig: - send_sig(SIGXFSZ, current, 0); -out_big: - return -EFBIG; -out_busy: - return -ETXTBSY; -} - -EXPORT_SYMBOL(vmtruncate); - -/* - * Primitive swap readahead code. We simply read an aligned block of - * (1 << page_cluster) entries in the swap area. This method is chosen - * because it doesn't cost us any seek time. We also make sure to queue - * the 'original' request together with the readahead ones... - * - * This has been extended to use the NUMA policies from the mm triggering - * the readahead. - * - * Caller must hold down_read on the vma->vm_mm if vma is not NULL. - */ -void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma) -{ -#ifdef CONFIG_NUMA - struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL; -#endif - int i, num; - struct page *new_page; - unsigned long offset; - - /* - * Get the number of handles we should do readahead io to. - */ - num = valid_swaphandles(entry, &offset); - for (i = 0; i < num; offset++, i++) { - /* Ok, do the async read-ahead now */ - new_page = read_swap_cache_async(swp_entry(swp_type(entry), - offset), vma, addr); - if (!new_page) - break; - page_cache_release(new_page); -#ifdef CONFIG_NUMA - /* - * Find the next applicable VMA for the NUMA policy. - */ - addr += PAGE_SIZE; - if (addr == 0) - vma = NULL; - if (vma) { - if (addr >= vma->vm_end) { - vma = next_vma; - next_vma = vma ? vma->vm_next : NULL; - } - if (vma && addr < vma->vm_start) - vma = NULL; - } else { - if (next_vma && addr >= next_vma->vm_start) { - vma = next_vma; - next_vma = vma->vm_next; - } - } -#endif - } - lru_add_drain(); /* Push any new pages onto the LRU now */ -} - -/* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access, pte_t orig_pte) + unsigned int flags, pte_t orig_pte) { spinlock_t *ptl; - struct page *page; + struct page *page, *swapcache; swp_entry_t entry; pte_t pte; - int ret = VM_FAULT_MINOR; + int locked; + struct mem_cgroup *ptr; + int exclusive = 0; + int ret = 0; if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) goto out; entry = pte_to_swp_entry(orig_pte); + if (unlikely(non_swap_entry(entry))) { + if (is_migration_entry(entry)) { + migration_entry_wait(mm, pmd, address); + } else if (is_hwpoison_entry(entry)) { + ret = VM_FAULT_HWPOISON; + } else { + print_bad_pte(vma, address, orig_pte, NULL); + ret = VM_FAULT_SIGBUS; + } + goto out; + } + delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { - swapin_readahead(entry, address, vma); - page = read_swap_cache_async(entry, vma, address); + page = swapin_readahead(entry, + GFP_HIGHUSER_MOVABLE, vma, address); if (!page) { /* * Back out if somebody else faulted in this pte @@ -1677,17 +2442,54 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) ret = VM_FAULT_OOM; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; - inc_page_state(pgmajfault); - grab_swap_token(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(mm, PGMAJFAULT); + } else if (PageHWPoison(page)) { + /* + * hwpoisoned dirty swapcache pages are kept for killing + * owner processes (which may be unknown at hwpoison time) + */ + ret = VM_FAULT_HWPOISON; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + swapcache = page; + goto out_release; + } + + swapcache = page; + locked = lock_page_or_retry(page, mm, flags); + + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + if (!locked) { + ret |= VM_FAULT_RETRY; + goto out_release; + } + + /* + * Make sure try_to_free_swap or reuse_swap_page or swapoff did not + * release the swapcache from under us. The page pin, and pte_same + * test below, are not enough to exclude that. Even if it is still + * swapcache, we need to check that the page's swap has not changed. + */ + if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) + goto out_page; + + page = ksm_might_need_to_copy(page, vma, address); + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + goto out_page; } - mark_page_accessed(page); - lock_page(page); + if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { + ret = VM_FAULT_OOM; + goto out_page; + } /* * Back out if somebody else already faulted in this pte. @@ -1701,227 +2503,534 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_nomap; } - /* The page isn't present yet, go ahead with the fault. */ + /* + * The page isn't present yet, go ahead with the fault. + * + * Be careful about the sequence of operations here. + * To get its accounting right, reuse_swap_page() must be called + * while the page is counted on swap but not yet in mapcount i.e. + * before page_add_anon_rmap() and swap_free(); try_to_free_swap() + * must be called after the swap_free(), or it will never succeed. + * Because delete_from_swap_page() may be called by reuse_swap_page(), + * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry + * in page->private. In this case, a record in swap_cgroup is silently + * discarded at swap_free(). + */ - inc_mm_counter(mm, anon_rss); + inc_mm_counter_fast(mm, MM_ANONPAGES); + dec_mm_counter_fast(mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if (write_access && can_share_swap_page(page)) { + if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); - write_access = 0; + flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + exclusive = 1; } - flush_icache_page(vma, page); + if (pte_swp_soft_dirty(orig_pte)) + pte = pte_mksoft_dirty(pte); set_pte_at(mm, address, page_table, pte); - page_add_anon_rmap(page, vma, address); + if (page == swapcache) + do_page_add_anon_rmap(page, vma, address, exclusive); + else /* ksm created a completely new copy */ + page_add_new_anon_rmap(page, vma, address); + /* It's better to call commit-charge after rmap is established */ + mem_cgroup_commit_charge_swapin(page, ptr); swap_free(entry); - if (vm_swap_full()) - remove_exclusive_swap_page(page); + if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) + try_to_free_swap(page); unlock_page(page); + if (page != swapcache) { + /* + * Hold the lock to avoid the swap entry to be reused + * until we take the PT lock for the pte_same() check + * (to avoid false positives from pte_same). For + * further safety release the lock after the swap_free + * so that the swap count won't change under a + * parallel locked swapcache. + */ + unlock_page(swapcache); + page_cache_release(swapcache); + } - if (write_access) { - if (do_wp_page(mm, vma, address, - page_table, pmd, ptl, pte) == VM_FAULT_OOM) - ret = VM_FAULT_OOM; + if (flags & FAULT_FLAG_WRITE) { + ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + if (ret & VM_FAULT_ERROR) + ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, pte); - lazy_mmu_prot_update(pte); + update_mmu_cache(vma, address, page_table); unlock: pte_unmap_unlock(page_table, ptl); out: return ret; out_nomap: + mem_cgroup_cancel_charge_swapin(ptr); pte_unmap_unlock(page_table, ptl); +out_page: unlock_page(page); +out_release: page_cache_release(page); + if (page != swapcache) { + unlock_page(swapcache); + page_cache_release(swapcache); + } return ret; } /* + * This is like a special single-page "expand_{down|up}wards()", + * except we must first make sure that 'address{-|+}PAGE_SIZE' + * doesn't hit another vma. + */ +static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) +{ + address &= PAGE_MASK; + if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) { + struct vm_area_struct *prev = vma->vm_prev; + + /* + * Is there a mapping abutting this one below? + * + * That's only ok if it's the same stack mapping + * that has gotten split.. + */ + if (prev && prev->vm_end == address) + return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; + + expand_downwards(vma, address - PAGE_SIZE); + } + if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { + struct vm_area_struct *next = vma->vm_next; + + /* As VM_GROWSDOWN but s/below/above/ */ + if (next && next->vm_start == address + PAGE_SIZE) + return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; + + expand_upwards(vma, address + PAGE_SIZE); + } + return 0; +} + +/* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access) + unsigned int flags) { struct page *page; spinlock_t *ptl; pte_t entry; - if (write_access) { - /* Allocate our own private page. */ - pte_unmap(page_table); - - if (unlikely(anon_vma_prepare(vma))) - goto oom; - page = alloc_zeroed_user_highpage(vma, address); - if (!page) - goto oom; + pte_unmap(page_table); - entry = mk_pte(page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + /* Check if we need to add a guard page to the stack */ + if (check_stack_guard_page(vma, address) < 0) + return VM_FAULT_SIGBUS; + /* Use the zero-page for reads */ + if (!(flags & FAULT_FLAG_WRITE)) { + entry = pte_mkspecial(pfn_pte(my_zero_pfn(address), + vma->vm_page_prot)); page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte_none(*page_table)) - goto release; - inc_mm_counter(mm, anon_rss); - lru_cache_add_active(page); - SetPageReferenced(page); - page_add_anon_rmap(page, vma, address); - } else { - /* Map the ZERO_PAGE - vm_page_prot is readonly */ - page = ZERO_PAGE(address); - page_cache_get(page); - entry = mk_pte(page, vma->vm_page_prot); - - ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - if (!pte_none(*page_table)) - goto release; - inc_mm_counter(mm, file_rss); - page_add_file_rmap(page); + goto unlock; + goto setpte; } + /* Allocate our own private page. */ + if (unlikely(anon_vma_prepare(vma))) + goto oom; + page = alloc_zeroed_user_highpage_movable(vma, address); + if (!page) + goto oom; + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceeding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL)) + goto oom_free_page; + + entry = mk_pte(page, vma->vm_page_prot); + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry)); + + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!pte_none(*page_table)) + goto release; + + inc_mm_counter_fast(mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, address); +setpte: set_pte_at(mm, address, page_table, entry); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); + update_mmu_cache(vma, address, page_table); unlock: pte_unmap_unlock(page_table, ptl); - return VM_FAULT_MINOR; + return 0; release: + mem_cgroup_uncharge_page(page); page_cache_release(page); goto unlock; +oom_free_page: + page_cache_release(page); oom: return VM_FAULT_OOM; } -/* - * do_no_page() tries to create a new page mapping. It aggressively - * tries to share with existing pages, but makes a separate copy if - * the "write_access" parameter is true in order to avoid the next - * page fault. +static int __do_fault(struct vm_area_struct *vma, unsigned long address, + pgoff_t pgoff, unsigned int flags, struct page **page) +{ + struct vm_fault vmf; + int ret; + + vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.pgoff = pgoff; + vmf.flags = flags; + vmf.page = NULL; + + ret = vma->vm_ops->fault(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + if (unlikely(PageHWPoison(vmf.page))) { + if (ret & VM_FAULT_LOCKED) + unlock_page(vmf.page); + page_cache_release(vmf.page); + return VM_FAULT_HWPOISON; + } + + if (unlikely(!(ret & VM_FAULT_LOCKED))) + lock_page(vmf.page); + else + VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); + + *page = vmf.page; + return ret; +} + +/** + * do_set_pte - setup new PTE entry for given page and add reverse page mapping. * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. + * @vma: virtual memory area + * @address: user virtual address + * @page: page to map + * @pte: pointer to target page table entry + * @write: true, if new entry is writable + * @anon: true, if it's anonymous page * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. + * Caller must hold page table lock relevant for @pte. + * + * Target users are page handler itself and implementations of + * vm_ops->map_pages. */ -static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access) +void do_set_pte(struct vm_area_struct *vma, unsigned long address, + struct page *page, pte_t *pte, bool write, bool anon) { - spinlock_t *ptl; - struct page *new_page; - struct address_space *mapping = NULL; pte_t entry; - unsigned int sequence = 0; - int ret = VM_FAULT_MINOR; - int anon = 0; - - pte_unmap(page_table); - if (vma->vm_file) { - mapping = vma->vm_file->f_mapping; - sequence = mapping->truncate_count; - smp_rmb(); /* serializes i_size against truncate_count */ + flush_icache_page(vma, page); + entry = mk_pte(page, vma->vm_page_prot); + if (write) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) + pte_mksoft_dirty(entry); + if (anon) { + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, address); + } else { + inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES); + page_add_file_rmap(page); } -retry: - new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret); + set_pte_at(vma->vm_mm, address, pte, entry); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, address, pte); +} + +static unsigned long fault_around_bytes = rounddown_pow_of_two(65536); + +static inline unsigned long fault_around_pages(void) +{ + return fault_around_bytes >> PAGE_SHIFT; +} + +static inline unsigned long fault_around_mask(void) +{ + return ~(fault_around_bytes - 1) & PAGE_MASK; +} + +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) +{ + *val = fault_around_bytes; + return 0; +} + +/* + * fault_around_pages() and fault_around_mask() expects fault_around_bytes + * rounded down to nearest page order. It's what do_fault_around() expects to + * see. + */ +static int fault_around_bytes_set(void *data, u64 val) +{ + if (val / PAGE_SIZE > PTRS_PER_PTE) + return -EINVAL; + if (val > PAGE_SIZE) + fault_around_bytes = rounddown_pow_of_two(val); + else + fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); + +static int __init fault_around_debugfs(void) +{ + void *ret; + + ret = debugfs_create_file("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); + if (!ret) + pr_warn("Failed to create fault_around_bytes in debugfs"); + return 0; +} +late_initcall(fault_around_debugfs); +#endif + +/* + * do_fault_around() tries to map few pages around the fault address. The hope + * is that the pages will be needed soon and this will lower the number of + * faults to handle. + * + * It uses vm_ops->map_pages() to map the pages, which skips the page if it's + * not ready to be mapped: not up-to-date, locked, etc. + * + * This function is called with the page table lock taken. In the split ptlock + * case the page table lock only protects only those entries which belong to + * the page table corresponding to the fault address. + * + * This function doesn't cross the VMA boundaries, in order to call map_pages() + * only once. + * + * fault_around_pages() defines how many pages we'll try to map. + * do_fault_around() expects it to return a power of two less than or equal to + * PTRS_PER_PTE. + * + * The virtual address of the area that we map is naturally aligned to the + * fault_around_pages() value (and therefore to page order). This way it's + * easier to guarantee that we don't cross page table boundaries. + */ +static void do_fault_around(struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pgoff_t pgoff, unsigned int flags) +{ + unsigned long start_addr; + pgoff_t max_pgoff; + struct vm_fault vmf; + int off; + + start_addr = max(address & fault_around_mask(), vma->vm_start); + off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + pte -= off; + pgoff -= off; + /* - * No smp_rmb is needed here as long as there's a full - * spin_lock/unlock sequence inside the ->nopage callback - * (for the pagecache lookup) that acts as an implicit - * smp_mb() and prevents the i_size read to happen - * after the next truncate_count read. + * max_pgoff is either end of page table or end of vma + * or fault_around_pages() from pgoff, depending what is nearest. */ + max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + PTRS_PER_PTE - 1; + max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1, + pgoff + fault_around_pages() - 1); + + /* Check if it makes any sense to call ->map_pages */ + while (!pte_none(*pte)) { + if (++pgoff > max_pgoff) + return; + start_addr += PAGE_SIZE; + if (start_addr >= vma->vm_end) + return; + pte++; + } - /* no page was available -- either SIGBUS or OOM */ - if (new_page == NOPAGE_SIGBUS) - return VM_FAULT_SIGBUS; - if (new_page == NOPAGE_OOM) - return VM_FAULT_OOM; + vmf.virtual_address = (void __user *) start_addr; + vmf.pte = pte; + vmf.pgoff = pgoff; + vmf.max_pgoff = max_pgoff; + vmf.flags = flags; + vma->vm_ops->map_pages(vma, &vmf); +} + +static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + spinlock_t *ptl; + pte_t *pte; + int ret = 0; /* - * Should we do an early C-O-W break? + * Let's call ->map_pages() first and use ->fault() as fallback + * if page by the offset is not ready to be mapped (cold cache or + * something). */ - if (write_access && !(vma->vm_flags & VM_SHARED)) { - struct page *page; + if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && + fault_around_pages() > 1) { + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + do_fault_around(vma, address, pte, pgoff, flags); + if (!pte_same(*pte, orig_pte)) + goto unlock_out; + pte_unmap_unlock(pte, ptl); + } - if (unlikely(anon_vma_prepare(vma))) - goto oom; - page = alloc_page_vma(GFP_HIGHUSER, vma, address); - if (!page) - goto oom; - copy_user_highpage(page, new_page, address); - page_cache_release(new_page); - new_page = page; - anon = 1; + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; } + do_set_pte(vma, address, fault_page, pte, false, false); + unlock_page(fault_page); +unlock_out: + pte_unmap_unlock(pte, ptl); + return ret; +} - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - /* - * For a file-backed vma, someone could have truncated or otherwise - * invalidated this page. If unmap_mapping_range got called, - * retry getting the page. - */ - if (mapping && unlikely(sequence != mapping->truncate_count)) { - pte_unmap_unlock(page_table, ptl); +static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page, *new_page; + spinlock_t *ptl; + pte_t *pte; + int ret; + + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!new_page) + return VM_FAULT_OOM; + + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) { page_cache_release(new_page); - cond_resched(); - sequence = mapping->truncate_count; - smp_rmb(); - goto retry; + return VM_FAULT_OOM; } + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; + + copy_user_highpage(new_page, fault_page, address, vma); + __SetPageUptodate(new_page); + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + goto uncharge_out; + } + do_set_pte(vma, address, new_page, pte, true, true); + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; +uncharge_out: + mem_cgroup_uncharge_page(new_page); + page_cache_release(new_page); + return ret; +} + +static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + struct page *fault_page; + struct address_space *mapping; + spinlock_t *ptl; + pte_t *pte; + int dirtied = 0; + int ret, tmp; + + ret = __do_fault(vma, address, pgoff, flags, &fault_page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + /* - * This silly early PAGE_DIRTY setting removes a race - * due to the bad i386 page protection. But it's valid - * for other architectures too. - * - * Note that if write_access is true, we either now have - * an exclusive copy of the page, or this is a shared mapping, - * so we can make it writable and dirty to avoid having to - * handle that later. + * Check if the backing address space wants to know that the page is + * about to become writable */ - /* Only go through if we didn't race with anybody else... */ - if (pte_none(*page_table)) { - flush_icache_page(vma, new_page); - entry = mk_pte(new_page, vma->vm_page_prot); - if (write_access) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - set_pte_at(mm, address, page_table, entry); - if (anon) { - inc_mm_counter(mm, anon_rss); - lru_cache_add_active(new_page); - page_add_anon_rmap(new_page, vma, address); - } else if (!(vma->vm_flags & VM_RESERVED)) { - inc_mm_counter(mm, file_rss); - page_add_file_rmap(new_page); + if (vma->vm_ops->page_mkwrite) { + unlock_page(fault_page); + tmp = do_page_mkwrite(vma, fault_page, address); + if (unlikely(!tmp || + (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + page_cache_release(fault_page); + return tmp; } - } else { - /* One of our sibling threads was faster, back out. */ - page_cache_release(new_page); - goto unlock; } - /* no need to invalidate: a not-present page shouldn't be cached */ - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); -unlock: - pte_unmap_unlock(page_table, ptl); + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*pte, orig_pte))) { + pte_unmap_unlock(pte, ptl); + unlock_page(fault_page); + page_cache_release(fault_page); + return ret; + } + do_set_pte(vma, address, fault_page, pte, true, false); + pte_unmap_unlock(pte, ptl); + + if (set_page_dirty(fault_page)) + dirtied = 1; + mapping = fault_page->mapping; + unlock_page(fault_page); + if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) { + /* + * Some device drivers do not set page.mapping but still + * dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + + /* file_update_time outside page_lock */ + if (vma->vm_file && !vma->vm_ops->page_mkwrite) + file_update_time(vma->vm_file); + return ret; -oom: - page_cache_release(new_page); - return VM_FAULT_OOM; +} + +static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + unsigned int flags, pte_t orig_pte) +{ + pgoff_t pgoff = (((address & PAGE_MASK) + - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + + pte_unmap(page_table); + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } /* @@ -1933,33 +3042,123 @@ oom: * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, - int write_access, pte_t orig_pte) + unsigned int flags, pte_t orig_pte) { pgoff_t pgoff; - int err; + + flags |= FAULT_FLAG_NONLINEAR; if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return VM_FAULT_MINOR; + return 0; if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { /* * Page table corrupted: show pte and kill process. */ - print_bad_pte(vma, orig_pte, address); - return VM_FAULT_OOM; + print_bad_pte(vma, address, orig_pte, NULL); + return VM_FAULT_SIGBUS; } - /* We can then assume vm->vm_ops && vma->vm_ops->populate */ pgoff = pte_to_pgoff(orig_pte); - err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, - vma->vm_page_prot, pgoff, 0); - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err) - return VM_FAULT_SIGBUS; - return VM_FAULT_MAJOR; + if (!(flags & FAULT_FLAG_WRITE)) + return do_read_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + if (!(vma->vm_flags & VM_SHARED)) + return do_cow_fault(mm, vma, address, pmd, pgoff, flags, + orig_pte); + return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); +} + +static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, + int *flags) +{ + get_page(page); + + count_vm_numa_event(NUMA_HINT_FAULTS); + if (page_nid == numa_node_id()) { + count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + *flags |= TNF_FAULT_LOCAL; + } + + return mpol_misplaced(page, vma, addr); +} + +static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) +{ + struct page *page = NULL; + spinlock_t *ptl; + int page_nid = -1; + int last_cpupid; + int target_nid; + bool migrated = false; + int flags = 0; + + /* + * The "pte" at this point cannot be used safely without + * validation through pte_unmap_same(). It's of NUMA type but + * the pfn may be screwed if the read is non atomic. + * + * ptep_modify_prot_start is not called as this is clearing + * the _PAGE_NUMA bit and it is not really expected that there + * would be concurrent hardware modifications to the PTE. + */ + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (unlikely(!pte_same(*ptep, pte))) { + pte_unmap_unlock(ptep, ptl); + goto out; + } + + pte = pte_mknonnuma(pte); + set_pte_at(mm, addr, ptep, pte); + update_mmu_cache(vma, addr, ptep); + + page = vm_normal_page(vma, addr, pte); + if (!page) { + pte_unmap_unlock(ptep, ptl); + return 0; + } + BUG_ON(is_zero_pfn(page_to_pfn(page))); + + /* + * Avoid grouping on DSO/COW pages in specific and RO pages + * in general, RO pages shouldn't hurt as much anyway since + * they can be in shared cache state. + */ + if (!pte_write(pte)) + flags |= TNF_NO_GROUP; + + /* + * Flag if the page is shared between multiple address spaces. This + * is later used when determining whether to group tasks together + */ + if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) + flags |= TNF_SHARED; + + last_cpupid = page_cpupid_last(page); + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags); + pte_unmap_unlock(ptep, ptl); + if (target_nid == -1) { + put_page(page); + goto out; + } + + /* Migrate to the requested node */ + migrated = migrate_misplaced_page(page, vma, target_nid); + if (migrated) { + page_nid = target_nid; + flags |= TNF_MIGRATED; + } + +out: + if (page_nid != -1) + task_numa_fault(last_cpupid, page_nid, 1, flags); + return 0; } /* @@ -1975,45 +3174,47 @@ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static inline int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, int write_access) +static int handle_pte_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pmd_t *pmd, unsigned int flags) { pte_t entry; - pte_t old_entry; spinlock_t *ptl; - old_entry = entry = *pte; + entry = *pte; if (!pte_present(entry)) { if (pte_none(entry)) { - if (!vma->vm_ops || !vma->vm_ops->nopage) - return do_anonymous_page(mm, vma, address, - pte, pmd, write_access); - return do_no_page(mm, vma, address, - pte, pmd, write_access); + if (vma->vm_ops) { + if (likely(vma->vm_ops->fault)) + return do_linear_fault(mm, vma, address, + pte, pmd, flags, entry); + } + return do_anonymous_page(mm, vma, address, + pte, pmd, flags); } if (pte_file(entry)) - return do_file_page(mm, vma, address, - pte, pmd, write_access, entry); + return do_nonlinear_fault(mm, vma, address, + pte, pmd, flags, entry); return do_swap_page(mm, vma, address, - pte, pmd, write_access, entry); + pte, pmd, flags, entry); } + if (pte_numa(entry)) + return do_numa_page(mm, vma, address, entry, pte, pmd); + ptl = pte_lockptr(mm, pmd); spin_lock(ptl); if (unlikely(!pte_same(*pte, entry))) goto unlock; - if (write_access) { + if (flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(mm, vma, address, pte, pmd, ptl, entry); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - if (!pte_same(old_entry, entry)) { - ptep_set_access_flags(vma, address, pte, entry, write_access); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); + if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) { + update_mmu_cache(vma, address, pte); } else { /* * This is needed only for protection faults but the arch code @@ -2021,31 +3222,27 @@ static inline int handle_pte_fault(struct mm_struct *mm, * This still avoids useless tlb flushes for .text page faults * with threads. */ - if (write_access) - flush_tlb_page(vma, address); + if (flags & FAULT_FLAG_WRITE) + flush_tlb_fix_spurious_fault(vma, address); } unlock: pte_unmap_unlock(pte, ptl); - return VM_FAULT_MINOR; + return 0; } /* * By the time we get here, we already hold the mm semaphore */ -int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access) +static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - __set_current_state(TASK_RUNNING); - - inc_page_state(pgfault); - if (unlikely(is_vm_hugetlb_page(vma))) - return hugetlb_fault(mm, vma, address, write_access); + return hugetlb_fault(mm, vma, address, flags); pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); @@ -2054,11 +3251,103 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, pmd = pmd_alloc(mm, pud, address); if (!pmd) return VM_FAULT_OOM; - pte = pte_alloc_map(mm, pmd, address); - if (!pte) + if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { + int ret = VM_FAULT_FALLBACK; + if (!vma->vm_ops) + ret = do_huge_pmd_anonymous_page(mm, vma, address, + pmd, flags); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + pmd_t orig_pmd = *pmd; + int ret; + + barrier(); + if (pmd_trans_huge(orig_pmd)) { + unsigned int dirty = flags & FAULT_FLAG_WRITE; + + /* + * If the pmd is splitting, return and retry the + * the fault. Alternative: wait until the split + * is done, and goto retry. + */ + if (pmd_trans_splitting(orig_pmd)) + return 0; + + if (pmd_numa(orig_pmd)) + return do_huge_pmd_numa_page(mm, vma, address, + orig_pmd, pmd); + + if (dirty && !pmd_write(orig_pmd)) { + ret = do_huge_pmd_wp_page(mm, vma, address, pmd, + orig_pmd); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pmd_set_accessed(mm, vma, address, pmd, + orig_pmd, dirty); + return 0; + } + } + } + + /* + * Use __pte_alloc instead of pte_alloc_map, because we can't + * run pte_offset_map on the pmd, if an huge pmd could + * materialize from under us from a different thread. + */ + if (unlikely(pmd_none(*pmd)) && + unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; + /* if an huge pmd materialized from under us just retry later */ + if (unlikely(pmd_trans_huge(*pmd))) + return 0; + /* + * A regular pmd is established and it can't morph into a huge pmd + * from under us anymore at this point because we hold the mmap_sem + * read mode and khugepaged takes it in write mode. So now it's + * safe to run pte_offset_map(). + */ + pte = pte_offset_map(pmd, address); - return handle_pte_fault(mm, vma, address, pte, pmd, write_access); + return handle_pte_fault(mm, vma, address, pte, pmd, flags); +} + +int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, unsigned int flags) +{ + int ret; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + mem_cgroup_count_vm_event(mm, PGFAULT); + + /* do counter updates before entering really critical section. */ + check_sync_rss_stat(current); + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_oom_enable(); + + ret = __handle_mm_fault(mm, vma, address, flags); + + if (flags & FAULT_FLAG_USER) { + mem_cgroup_oom_disable(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } + + return ret; } #ifndef __PAGETABLE_PUD_FOLDED @@ -2072,9 +3361,11 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ - pud_free(new); + pud_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); @@ -2093,15 +3384,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) if (!new) return -ENOMEM; + smp_wmb(); /* See comment in __pte_alloc */ + spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK if (pud_present(*pud)) /* Another has populated it */ - pmd_free(new); + pmd_free(mm, new); else pud_populate(mm, pud, new); #else if (pgd_present(*pud)) /* Another has populated it */ - pmd_free(new); + pmd_free(mm, new); else pgd_populate(mm, pud, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ @@ -2110,67 +3403,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -int make_pages_present(unsigned long addr, unsigned long end) -{ - int ret, len, write; - struct vm_area_struct * vma; - - vma = find_vma(current->mm, addr); - if (!vma) - return -1; - write = (vma->vm_flags & VM_WRITE) != 0; - if (addr >= end) - BUG(); - if (end > vma->vm_end) - BUG(); - len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE; - ret = get_user_pages(current, current->mm, addr, - len, write, 0, NULL, NULL); - if (ret < 0) - return ret; - return ret == len ? 0 : -1; -} - -/* - * Map a vmalloc()-space virtual address to the physical page. - */ -struct page * vmalloc_to_page(void * vmalloc_addr) -{ - unsigned long addr = (unsigned long) vmalloc_addr; - struct page *page = NULL; - pgd_t *pgd = pgd_offset_k(addr); - pud_t *pud; - pmd_t *pmd; - pte_t *ptep, pte; - - if (!pgd_none(*pgd)) { - pud = pud_offset(pgd, addr); - if (!pud_none(*pud)) { - pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - ptep = pte_offset_map(pmd, addr); - pte = *ptep; - if (pte_present(pte)) - page = pte_page(pte); - pte_unmap(ptep); - } - } - } - return page; -} - -EXPORT_SYMBOL(vmalloc_to_page); - -/* - * Map a vmalloc()-space virtual address to the physical page frame number. - */ -unsigned long vmalloc_to_pfn(void * vmalloc_addr) -{ - return page_to_pfn(vmalloc_to_page(vmalloc_addr)); -} - -EXPORT_SYMBOL(vmalloc_to_pfn); - #if !defined(__HAVE_ARCH_GATE_AREA) #if defined(AT_SYSINFO_EHDR) @@ -2181,14 +3413,15 @@ static int __init gate_vma_init(void) gate_vma.vm_mm = NULL; gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_page_prot = PAGE_READONLY; - gate_vma.vm_flags = VM_RESERVED; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + return 0; } __initcall(gate_vma_init); #endif -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef AT_SYSINFO_EHDR return &gate_vma; @@ -2197,7 +3430,7 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk) #endif } -int in_gate_area_no_task(unsigned long addr) +int in_gate_area_no_mm(unsigned long addr) { #ifdef AT_SYSINFO_EHDR if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) @@ -2207,3 +3440,393 @@ int in_gate_area_no_task(unsigned long addr) } #endif /* __HAVE_ARCH_GATE_AREA */ + +static int __follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep; + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto out; + + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto out; + + pmd = pmd_offset(pud, address); + VM_BUG_ON(pmd_trans_huge(*pmd)); + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto out; + + /* We cannot handle huge page PFN maps. Luckily they don't exist. */ + if (pmd_huge(*pmd)) + goto out; + + ptep = pte_offset_map_lock(mm, pmd, address, ptlp); + if (!ptep) + goto out; + if (!pte_present(*ptep)) + goto unlock; + *ptepp = ptep; + return 0; +unlock: + pte_unmap_unlock(ptep, *ptlp); +out: + return -EINVAL; +} + +static inline int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) +{ + int res; + + /* (void) is needed to make gcc happy */ + (void) __cond_lock(*ptlp, + !(res = __follow_pte(mm, address, ptepp, ptlp))); + return res; +} + +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * Returns zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + int ret = -EINVAL; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return ret; + + ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); + if (ret) + return ret; + *pfn = pte_pfn(*ptep); + pte_unmap_unlock(ptep, ptl); + return 0; +} +EXPORT_SYMBOL(follow_pfn); + +#ifdef CONFIG_HAVE_IOREMAP_PROT +int follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot, resource_size_t *phys) +{ + int ret = -EINVAL; + pte_t *ptep, pte; + spinlock_t *ptl; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + goto out; + pte = *ptep; + + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + + ret = 0; +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return ret; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void __iomem *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (follow_phys(vma, addr, write, &prot, &phys_addr)) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +EXPORT_SYMBOL_GPL(generic_access_phys); +#endif + +/* + * Access another process' address space as given in mm. If non-NULL, use the + * given task for page fault accounting. + */ +static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, + unsigned long addr, void *buf, int len, int write) +{ + struct vm_area_struct *vma; + void *old_buf = buf; + + down_read(&mm->mmap_sem); + /* ignore errors, just check how much was successfully transferred */ + while (len) { + int bytes, ret, offset; + void *maddr; + struct page *page = NULL; + + ret = get_user_pages(tsk, mm, addr, 1, + write, 1, &page, &vma); + if (ret <= 0) { + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ +#ifdef CONFIG_HAVE_IOREMAP_PROT + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) +#endif + break; + bytes = ret; + } else { + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); + } + len -= bytes; + buf += bytes; + addr += bytes; + } + up_read(&mm->mmap_sem); + + return buf - old_buf; +} + +/** + * access_remote_vm - access another process' address space + * @mm: the mm_struct of the target address space + * @addr: start address to access + * @buf: source or destination buffer + * @len: number of bytes to transfer + * @write: whether the access is a write + * + * The caller must hold a reference on @mm. + */ +int access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, int write) +{ + return __access_remote_vm(NULL, mm, addr, buf, len, write); +} + +/* + * Access another process' address space. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, + void *buf, int len, int write) +{ + struct mm_struct *mm; + int ret; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + ret = __access_remote_vm(tsk, mm, addr, buf, len, write); + mmput(mm); + + return ret; +} + +/* + * Print the name of a VMA. + */ +void print_vma_addr(char *prefix, unsigned long ip) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + + /* + * Do not print if we are in atomic + * contexts (in exception stacks, etc.): + */ + if (preempt_count()) + return; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma && vma->vm_file) { + struct file *f = vma->vm_file; + char *buf = (char *)__get_free_page(GFP_KERNEL); + if (buf) { + char *p; + + p = d_path(&f->f_path, buf, PAGE_SIZE); + if (IS_ERR(p)) + p = "?"; + printk("%s%s[%lx+%lx]", prefix, kbasename(p), + vma->vm_start, + vma->vm_end - vma->vm_start); + free_page((unsigned long)buf); + } + } + up_read(&mm->mmap_sem); +} + +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +void might_fault(void) +{ + /* + * Some code (nfs/sunrpc) uses socket ops on kernel memory while + * holding the mmap_sem, this is safe because kernel memory doesn't + * get paged out, therefore we'll never actually fault, and the + * below annotations will generate false positives. + */ + if (segment_eq(get_fs(), KERNEL_DS)) + return; + + /* + * it would be nicer only to annotate paths which are not under + * pagefault_disable, however that requires a larger audit and + * providing helpers like get_user_atomic. + */ + if (in_atomic()) + return; + + __might_sleep(__FILE__, __LINE__, 0); + + if (current->mm) + might_lock_read(¤t->mm->mmap_sem); +} +EXPORT_SYMBOL(might_fault); +#endif + +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +static void clear_gigantic_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_page) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < pages_per_huge_page; + i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} +void clear_huge_page(struct page *page, + unsigned long addr, unsigned int pages_per_huge_page) +{ + int i; + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + clear_gigantic_page(page, addr, pages_per_huge_page); + return; + } + + might_sleep(); + for (i = 0; i < pages_per_huge_page; i++) { + cond_resched(); + clear_user_highpage(page + i, addr + i * PAGE_SIZE); + } +} + +static void copy_user_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, + struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < pages_per_huge_page; ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +void copy_user_huge_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma, + unsigned int pages_per_huge_page) +{ + int i; + + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { + copy_user_gigantic_page(dst, src, addr, vma, + pages_per_huge_page); + return; + } + + might_sleep(); + for (i = 0; i < pages_per_huge_page; i++) { + cond_resched(); + copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); + } +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS + +static struct kmem_cache *page_ptl_cachep; + +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + +bool ptlock_alloc(struct page *page) +{ + spinlock_t *ptl; + + ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); + if (!ptl) + return false; + page->ptl = ptl; + return true; +} + +void ptlock_free(struct page *page) +{ + kmem_cache_free(page_ptl_cachep, page->ptl); +} +#endif |