| /* |
| * linux/mm/memory.c |
| * |
| * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds |
| */ |
| |
| /* |
| * demand-loading started 01.12.91 - seems it is high on the list of |
| * things wanted, and it should be easy to implement. - Linus |
| */ |
| |
| /* |
| * Ok, demand-loading was easy, shared pages a little bit tricker. Shared |
| * pages started 02.12.91, seems to work. - Linus. |
| * |
| * Tested sharing by executing about 30 /bin/sh: under the old kernel it |
| * would have taken more than the 6M I have free, but it worked well as |
| * far as I could see. |
| * |
| * Also corrected some "invalidate()"s - I wasn't doing enough of them. |
| */ |
| |
| /* |
| * Real VM (paging to/from disk) started 18.12.91. Much more work and |
| * thought has to go into this. Oh, well.. |
| * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. |
| * Found it. Everything seems to work now. |
| * 20.12.91 - Ok, making the swap-device changeable like the root. |
| */ |
| |
| /* |
| * 05.04.94 - Multi-page memory management added for v1.1. |
| * Idea by Alex Bligh (alex@cconcepts.co.uk) |
| * |
| * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG |
| * (Gerhard.Wichert@pdb.siemens.de) |
| * |
| * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) |
| */ |
| |
| #include <linux/kernel_stat.h> |
| #include <linux/mm.h> |
| #include <linux/sched/mm.h> |
| #include <linux/sched/coredump.h> |
| #include <linux/sched/numa_balancing.h> |
| #include <linux/sched/task.h> |
| #include <linux/hugetlb.h> |
| #include <linux/mman.h> |
| #include <linux/swap.h> |
| #include <linux/highmem.h> |
| #include <linux/pagemap.h> |
| #include <linux/memremap.h> |
| #include <linux/ksm.h> |
| #include <linux/rmap.h> |
| #include <linux/export.h> |
| #include <linux/delayacct.h> |
| #include <linux/init.h> |
| #include <linux/pfn_t.h> |
| #include <linux/writeback.h> |
| #include <linux/memcontrol.h> |
| #include <linux/mmu_notifier.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 <linux/userfaultfd_k.h> |
| #include <linux/dax.h> |
| #include <linux/oom.h> |
| #include <linux/numa.h> |
| |
| #include <asm/io.h> |
| #include <asm/mmu_context.h> |
| #include <asm/pgalloc.h> |
| #include <linux/uaccess.h> |
| #include <asm/tlb.h> |
| #include <asm/tlbflush.h> |
| #include <asm/pgtable.h> |
| |
| #include "internal.h" |
| |
| #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) |
| #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 */ |
| unsigned long max_mapnr; |
| EXPORT_SYMBOL(max_mapnr); |
| |
| struct page *mem_map; |
| EXPORT_SYMBOL(mem_map); |
| #endif |
| |
| /* |
| * 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 |
| * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and |
| * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL |
| * and ZONE_HIGHMEM. |
| */ |
| void *high_memory; |
| EXPORT_SYMBOL(high_memory); |
| |
| /* |
| * 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 |
| |
| static int __init disable_randmaps(char *s) |
| { |
| randomize_va_space = 0; |
| return 1; |
| } |
| __setup("norandmaps", disable_randmaps); |
| |
| unsigned long zero_pfn __read_mostly; |
| EXPORT_SYMBOL(zero_pfn); |
| |
| 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) |
| { |
| zero_pfn = page_to_pfn(ZERO_PAGE(0)); |
| return 0; |
| } |
| core_initcall(init_zero_pfn); |
| |
| |
| #if defined(SPLIT_RSS_COUNTING) |
| |
| void sync_mm_rss(struct mm_struct *mm) |
| { |
| 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 */ |
| |
| /* |
| * 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, |
| unsigned long addr) |
| { |
| pgtable_t token = pmd_pgtable(*pmd); |
| pmd_clear(pmd); |
| pte_free_tlb(tlb, token, addr); |
| mm_dec_nr_ptes(tlb->mm); |
| } |
| |
| static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, |
| unsigned long addr, unsigned long end, |
| unsigned long floor, unsigned long ceiling) |
| { |
| pmd_t *pmd; |
| unsigned long next; |
| unsigned long start; |
| |
| start = addr; |
| pmd = pmd_offset(pud, addr); |
| do { |
| next = pmd_addr_end(addr, end); |
| if (pmd_none_or_clear_bad(pmd)) |
| continue; |
| free_pte_range(tlb, pmd, addr); |
| } while (pmd++, addr = next, addr != end); |
| |
| start &= PUD_MASK; |
| if (start < floor) |
| return; |
| if (ceiling) { |
| ceiling &= PUD_MASK; |
| if (!ceiling) |
| return; |
| } |
| if (end - 1 > ceiling - 1) |
| return; |
| |
| pmd = pmd_offset(pud, start); |
| pud_clear(pud); |
| pmd_free_tlb(tlb, pmd, start); |
| mm_dec_nr_pmds(tlb->mm); |
| } |
| |
| static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, |
| unsigned long addr, unsigned long end, |
| unsigned long floor, unsigned long ceiling) |
| { |
| pud_t *pud; |
| unsigned long next; |
| unsigned long start; |
| |
| start = addr; |
| pud = pud_offset(p4d, addr); |
| do { |
| next = pud_addr_end(addr, end); |
| if (pud_none_or_clear_bad(pud)) |
| continue; |
| free_pmd_range(tlb, pud, addr, next, floor, ceiling); |
| } while (pud++, addr = next, addr != end); |
| |
| start &= P4D_MASK; |
| if (start < floor) |
| return; |
| if (ceiling) { |
| ceiling &= P4D_MASK; |
| if (!ceiling) |
| return; |
| } |
| if (end - 1 > ceiling - 1) |
| return; |
| |
| pud = pud_offset(p4d, start); |
| p4d_clear(p4d); |
| pud_free_tlb(tlb, pud, start); |
| mm_dec_nr_puds(tlb->mm); |
| } |
| |
| static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, |
| unsigned long addr, unsigned long end, |
| unsigned long floor, unsigned long ceiling) |
| { |
| p4d_t *p4d; |
| unsigned long next; |
| unsigned long start; |
| |
| start = addr; |
| p4d = p4d_offset(pgd, addr); |
| do { |
| next = p4d_addr_end(addr, end); |
| if (p4d_none_or_clear_bad(p4d)) |
| continue; |
| free_pud_range(tlb, p4d, addr, next, floor, ceiling); |
| } while (p4d++, addr = next, addr != end); |
| |
| start &= PGDIR_MASK; |
| if (start < floor) |
| return; |
| if (ceiling) { |
| ceiling &= PGDIR_MASK; |
| if (!ceiling) |
| return; |
| } |
| if (end - 1 > ceiling - 1) |
| return; |
| |
| p4d = p4d_offset(pgd, start); |
| pgd_clear(pgd); |
| p4d_free_tlb(tlb, p4d, start); |
| } |
| |
| /* |
| * This function frees user-level page tables of a process. |
| */ |
| 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; |
| |
| /* |
| * The next few lines have given us lots of grief... |
| * |
| * Why are we testing PMD* at this top level? Because often |
| * there will be no work to do at all, and we'd prefer not to |
| * go all the way down to the bottom just to discover that. |
| * |
| * Why all these "- 1"s? Because 0 represents both the bottom |
| * of the address space and the top of it (using -1 for the |
| * top wouldn't help much: the masks would do the wrong thing). |
| * The rule is that addr 0 and floor 0 refer to the bottom of |
| * the address space, but end 0 and ceiling 0 refer to the top |
| * Comparisons need to use "end - 1" and "ceiling - 1" (though |
| * that end 0 case should be mythical). |
| * |
| * Wherever addr is brought up or ceiling brought down, we must |
| * be careful to reject "the opposite 0" before it confuses the |
| * subsequent tests. But what about where end is brought down |
| * by PMD_SIZE below? no, end can't go down to 0 there. |
| * |
| * Whereas we round start (addr) and ceiling down, by different |
| * masks at different levels, in order to test whether a table |
| * now has no other vmas using it, so can be freed, we don't |
| * bother to round floor or end up - the tests don't need that. |
| */ |
| |
| addr &= PMD_MASK; |
| if (addr < floor) { |
| addr += PMD_SIZE; |
| if (!addr) |
| return; |
| } |
| if (ceiling) { |
| ceiling &= PMD_MASK; |
| if (!ceiling) |
| return; |
| } |
| if (end - 1 > ceiling - 1) |
| end -= PMD_SIZE; |
| if (addr > end - 1) |
| return; |
| /* |
| * We add page table cache pages with PAGE_SIZE, |
| * (see pte_free_tlb()), flush the tlb if we need |
| */ |
| tlb_remove_check_page_size_change(tlb, PAGE_SIZE); |
| pgd = pgd_offset(tlb->mm, addr); |
| do { |
| next = pgd_addr_end(addr, end); |
| if (pgd_none_or_clear_bad(pgd)) |
| continue; |
| free_p4d_range(tlb, pgd, addr, next, floor, ceiling); |
| } while (pgd++, addr = next, addr != end); |
| } |
| |
| void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, |
| unsigned long floor, unsigned long ceiling) |
| { |
| while (vma) { |
| struct vm_area_struct *next = vma->vm_next; |
| unsigned long addr = vma->vm_start; |
| |
| /* |
| * Hide vma from rmap and truncate_pagecache before freeing |
| * pgtables |
| */ |
| unlink_anon_vmas(vma); |
| unlink_file_vma(vma); |
| |
| if (is_vm_hugetlb_page(vma)) { |
| hugetlb_free_pgd_range(tlb, addr, vma->vm_end, |
| floor, next ? next->vm_start : ceiling); |
| } else { |
| /* |
| * Optimization: gather nearby vmas into one call down |
| */ |
| while (next && next->vm_start <= vma->vm_end + PMD_SIZE |
| && !is_vm_hugetlb_page(next)) { |
| vma = next; |
| next = vma->vm_next; |
| unlink_anon_vmas(vma); |
| unlink_file_vma(vma); |
| } |
| free_pgd_range(tlb, addr, vma->vm_end, |
| floor, next ? next->vm_start : ceiling); |
| } |
| vma = next; |
| } |
| } |
| |
| int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) |
| { |
| spinlock_t *ptl; |
| pgtable_t new = pte_alloc_one(mm); |
| if (!new) |
| return -ENOMEM; |
| |
| /* |
| * 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); |
| if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ |
| mm_inc_nr_ptes(mm); |
| pmd_populate(mm, pmd, new); |
| new = NULL; |
| } |
| spin_unlock(ptl); |
| if (new) |
| pte_free(mm, new); |
| return 0; |
| } |
| |
| int __pte_alloc_kernel(pmd_t *pmd) |
| { |
| pte_t *new = pte_alloc_one_kernel(&init_mm); |
| if (!new) |
| return -ENOMEM; |
| |
| smp_wmb(); /* See comment in __pte_alloc */ |
| |
| spin_lock(&init_mm.page_table_lock); |
| if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ |
| pmd_populate_kernel(&init_mm, pmd, new); |
| new = NULL; |
| } |
| spin_unlock(&init_mm.page_table_lock); |
| if (new) |
| pte_free_kernel(&init_mm, new); |
| return 0; |
| } |
| |
| 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) |
| { |
| 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 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. |
| */ |
| static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, |
| pte_t pte, struct page *page) |
| { |
| pgd_t *pgd = pgd_offset(vma->vm_mm, addr); |
| p4d_t *p4d = p4d_offset(pgd, addr); |
| pud_t *pud = pud_offset(p4d, 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) { |
| pr_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); |
| |
| pr_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"); |
| pr_alert("addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", |
| (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); |
| pr_alert("file:%pD fault:%pf mmap:%pf readpage:%pf\n", |
| vma->vm_file, |
| vma->vm_ops ? vma->vm_ops->fault : NULL, |
| vma->vm_file ? vma->vm_file->f_op->mmap : NULL, |
| mapping ? mapping->a_ops->readpage : NULL); |
| 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. |
| * |
| */ |
| struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, |
| pte_t pte, bool with_public_device) |
| { |
| unsigned long pfn = pte_pfn(pte); |
| |
| if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { |
| if (likely(!pte_special(pte))) |
| goto check_pfn; |
| if (vma->vm_ops && vma->vm_ops->find_special_page) |
| return vma->vm_ops->find_special_page(vma, addr); |
| if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) |
| return NULL; |
| if (is_zero_pfn(pfn)) |
| return NULL; |
| |
| /* |
| * Device public pages are special pages (they are ZONE_DEVICE |
| * pages but different from persistent memory). They behave |
| * allmost like normal pages. The difference is that they are |
| * not on the lru and thus should never be involve with any- |
| * thing that involve lru manipulation (mlock, numa balancing, |
| * ...). |
| * |
| * This is why we still want to return NULL for such page from |
| * vm_normal_page() so that we do not have to special case all |
| * call site of vm_normal_page(). |
| */ |
| if (likely(pfn <= highest_memmap_pfn)) { |
| struct page *page = pfn_to_page(pfn); |
| |
| if (is_device_public_page(page)) { |
| if (with_public_device) |
| return page; |
| return NULL; |
| } |
| } |
| |
| if (pte_devmap(pte)) |
| return NULL; |
| |
| print_bad_pte(vma, addr, pte, NULL); |
| return NULL; |
| } |
| |
| /* !CONFIG_ARCH_HAS_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; |
| } |
| } |
| |
| if (is_zero_pfn(pfn)) |
| return NULL; |
| |
| check_pfn: |
| if (unlikely(pfn > highest_memmap_pfn)) { |
| print_bad_pte(vma, addr, pte, NULL); |
| 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); |
| } |
| |
| #ifdef CONFIG_TRANSPARENT_HUGEPAGE |
| struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, |
| pmd_t pmd) |
| { |
| unsigned long pfn = pmd_pfn(pmd); |
| |
| /* |
| * There is no pmd_special() but there may be special pmds, e.g. |
| * in a direct-access (dax) mapping, so let's just replicate the |
| * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. |
| */ |
| 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; |
| } |
| } |
| |
| if (pmd_devmap(pmd)) |
| return NULL; |
| if (is_zero_pfn(pfn)) |
| return NULL; |
| if (unlikely(pfn > highest_memmap_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); |
| } |
| #endif |
| |
| /* |
| * copy one vm_area from one task to the other. Assumes the page tables |
| * already present in the new task to be cleared in the whole range |
| * covered by this vma. |
| */ |
| |
| 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) |
| { |
| unsigned long vm_flags = vma->vm_flags; |
| pte_t pte = *src_pte; |
| struct page *page; |
| |
| /* pte contains position in swap or file, so copy. */ |
| if (unlikely(!pte_present(pte))) { |
| swp_entry_t entry = pte_to_swp_entry(pte); |
| |
| if (likely(!non_swap_entry(entry))) { |
| 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); |
| if (list_empty(&dst_mm->mmlist)) |
| list_add(&dst_mm->mmlist, |
| &src_mm->mmlist); |
| spin_unlock(&mmlist_lock); |
| } |
| rss[MM_SWAPENTS]++; |
| } else if (is_migration_entry(entry)) { |
| page = migration_entry_to_page(entry); |
| |
| rss[mm_counter(page)]++; |
| |
| 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); |
| } |
| } else if (is_device_private_entry(entry)) { |
| page = device_private_entry_to_page(entry); |
| |
| /* |
| * Update rss count even for unaddressable pages, as |
| * they should treated just like normal pages in this |
| * respect. |
| * |
| * We will likely want to have some new rss counters |
| * for unaddressable pages, at some point. But for now |
| * keep things as they are. |
| */ |
| get_page(page); |
| rss[mm_counter(page)]++; |
| page_dup_rmap(page, false); |
| |
| /* |
| * We do not preserve soft-dirty information, because so |
| * far, checkpoint/restore is the only feature that |
| * requires that. And checkpoint/restore does not work |
| * when a device driver is involved (you cannot easily |
| * save and restore device driver state). |
| */ |
| if (is_write_device_private_entry(entry) && |
| is_cow_mapping(vm_flags)) { |
| make_device_private_entry_read(&entry); |
| pte = swp_entry_to_pte(entry); |
| set_pte_at(src_mm, addr, src_pte, pte); |
| } |
| } |
| goto out_set_pte; |
| } |
| |
| /* |
| * If it's a COW mapping, write protect it both |
| * in the parent and the child |
| */ |
| if (is_cow_mapping(vm_flags) && pte_write(pte)) { |
| ptep_set_wrprotect(src_mm, addr, src_pte); |
| pte = pte_wrprotect(pte); |
| } |
| |
| /* |
| * If it's a shared mapping, mark it clean in |
| * the child |
| */ |
| if (vm_flags & VM_SHARED) |
| pte = pte_mkclean(pte); |
| pte = pte_mkold(pte); |
| |
| page = vm_normal_page(vma, addr, pte); |
| if (page) { |
| get_page(page); |
| page_dup_rmap(page, false); |
| rss[mm_counter(page)]++; |
| } else if (pte_devmap(pte)) { |
| page = pte_page(pte); |
| |
| /* |
| * Cache coherent device memory behave like regular page and |
| * not like persistent memory page. For more informations see |
| * MEMORY_DEVICE_CACHE_COHERENT in memory_hotplug.h |
| */ |
| if (is_device_public_page(page)) { |
| get_page(page); |
| page_dup_rmap(page, false); |
| rss[mm_counter(page)]++; |
| } |
| } |
| |
| 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) |
| { |
| 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[NR_MM_COUNTERS]; |
| swp_entry_t entry = (swp_entry_t){0}; |
| |
| again: |
| 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(src_pmd, addr); |
| src_ptl = pte_lockptr(src_mm, src_pmd); |
| spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); |
| orig_src_pte = src_pte; |
| orig_dst_pte = dst_pte; |
| arch_enter_lazy_mmu_mode(); |
| |
| do { |
| /* |
| * We are holding two locks at this point - either of them |
| * could generate latencies in another task on another CPU. |
| */ |
| if (progress >= 32) { |
| progress = 0; |
| if (need_resched() || |
| spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) |
| break; |
| } |
| if (pte_none(*src_pte)) { |
| progress++; |
| continue; |
| } |
| 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(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; |
| } |
| |
| static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, |
| pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, |
| unsigned long addr, unsigned long end) |
| { |
| pmd_t *src_pmd, *dst_pmd; |
| unsigned long next; |
| |
| dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); |
| if (!dst_pmd) |
| return -ENOMEM; |
| src_pmd = pmd_offset(src_pud, addr); |
| do { |
| next = pmd_addr_end(addr, end); |
| if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) |
| || pmd_devmap(*src_pmd)) { |
| int err; |
| VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma); |
| 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, |
| vma, addr, next)) |
| return -ENOMEM; |
| } while (dst_pmd++, src_pmd++, addr = next, addr != end); |
| return 0; |
| } |
| |
| static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, |
| p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, |
| unsigned long addr, unsigned long end) |
| { |
| pud_t *src_pud, *dst_pud; |
| unsigned long next; |
| |
| dst_pud = pud_alloc(dst_mm, dst_p4d, addr); |
| if (!dst_pud) |
| return -ENOMEM; |
| src_pud = pud_offset(src_p4d, addr); |
| do { |
| next = pud_addr_end(addr, end); |
| if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { |
| int err; |
| |
| VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma); |
| err = copy_huge_pud(dst_mm, src_mm, |
| dst_pud, src_pud, addr, vma); |
| if (err == -ENOMEM) |
| return -ENOMEM; |
| if (!err) |
| continue; |
| /* fall through */ |
| } |
| if (pud_none_or_clear_bad(src_pud)) |
| continue; |
| if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, |
| vma, addr, next)) |
| return -ENOMEM; |
| } while (dst_pud++, src_pud++, addr = next, addr != end); |
| return 0; |
| } |
| |
| static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, |
| pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, |
| unsigned long addr, unsigned long end) |
| { |
| p4d_t *src_p4d, *dst_p4d; |
| unsigned long next; |
| |
| dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); |
| if (!dst_p4d) |
| return -ENOMEM; |
| src_p4d = p4d_offset(src_pgd, addr); |
| do { |
| next = p4d_addr_end(addr, end); |
| if (p4d_none_or_clear_bad(src_p4d)) |
| continue; |
| if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, |
| vma, addr, next)) |
| return -ENOMEM; |
| } while (dst_p4d++, src_p4d++, addr = next, addr != end); |
| return 0; |
| } |
| |
| int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, |
| struct vm_area_struct *vma) |
| { |
| pgd_t *src_pgd, *dst_pgd; |
| unsigned long next; |
| unsigned long addr = vma->vm_start; |
| unsigned long end = vma->vm_end; |
| struct mmu_notifier_range range; |
| bool is_cow; |
| int ret; |
| |
| /* |
| * Don't copy ptes where a page fault will fill them correctly. |
| * Fork becomes much lighter when there are big shared or private |
| * readonly mappings. The tradeoff is that copy_page_range is more |
| * efficient than faulting. |
| */ |
| if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && |
| !vma->anon_vma) |
| return 0; |
| |
| 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); |
| |
| if (is_cow) { |
| mmu_notifier_range_init(&range, src_mm, addr, end); |
| mmu_notifier_invalidate_range_start(&range); |
| } |
| |
| 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 (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, |
| vma, addr, next))) { |
| ret = -ENOMEM; |
| break; |
| } |
| } while (dst_pgd++, src_pgd++, addr = next, addr != end); |
| |
| if (is_cow) |
| mmu_notifier_invalidate_range_end(&range); |
| return ret; |
| } |
| |
| 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; |
| int force_flush = 0; |
| int rss[NR_MM_COUNTERS]; |
| spinlock_t *ptl; |
| pte_t *start_pte; |
| pte_t *pte; |
| swp_entry_t entry; |
| |
| tlb_remove_check_page_size_change(tlb, PAGE_SIZE); |
| again: |
| init_rss_vec(rss); |
| start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); |
| pte = start_pte; |
| flush_tlb_batched_pending(mm); |
| arch_enter_lazy_mmu_mode(); |
| do { |
| pte_t ptent = *pte; |
| if (pte_none(ptent)) |
| continue; |
| |
| if (pte_present(ptent)) { |
| struct page *page; |
| |
| page = _vm_normal_page(vma, addr, ptent, true); |
| if (unlikely(details) && page) { |
| /* |
| * unmap_shared_mapping_pages() wants to |
| * invalidate cache without truncating: |
| * unmap shared but keep private pages. |
| */ |
| if (details->check_mapping && |
| details->check_mapping != page_rmapping(page)) |
| continue; |
| } |
| ptent = ptep_get_and_clear_full(mm, addr, pte, |
| tlb->fullmm); |
| tlb_remove_tlb_entry(tlb, pte, addr); |
| if (unlikely(!page)) |
| continue; |
| |
| if (!PageAnon(page)) { |
| if (pte_dirty(ptent)) { |
| force_flush = 1; |
| set_page_dirty(page); |
| } |
| if (pte_young(ptent) && |
| likely(!(vma->vm_flags & VM_SEQ_READ))) |
| mark_page_accessed(page); |
| } |
| rss[mm_counter(page)]--; |
| page_remove_rmap(page, false); |
| if (unlikely(page_mapcount(page) < 0)) |
| print_bad_pte(vma, addr, ptent, page); |
| if (unlikely(__tlb_remove_page(tlb, page))) { |
| force_flush = 1; |
| addr += PAGE_SIZE; |
| break; |
| } |
| continue; |
| } |
| |
| entry = pte_to_swp_entry(ptent); |
| if (non_swap_entry(entry) && is_device_private_entry(entry)) { |
| struct page *page = device_private_entry_to_page(entry); |
| |
| if (unlikely(details && details->check_mapping)) { |
| /* |
| * unmap_shared_mapping_pages() wants to |
| * invalidate cache without truncating: |
| * unmap shared but keep private pages. |
| */ |
| if (details->check_mapping != |
| page_rmapping(page)) |
| continue; |
| } |
| |
| pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); |
| rss[mm_counter(page)]--; |
| page_remove_rmap(page, false); |
| put_page(page); |
| continue; |
| } |
| |
| /* If details->check_mapping, we leave swap entries. */ |
| if (unlikely(details)) |
| continue; |
| |
| 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); |
| rss[mm_counter(page)]--; |
| } |
| 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_vec(mm, rss); |
| arch_leave_lazy_mmu_mode(); |
| |
| /* Do the actual TLB flush before dropping ptl */ |
| if (force_flush) |
| tlb_flush_mmu_tlbonly(tlb); |
| 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 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) |
| { |
| pmd_t *pmd; |
| unsigned long next; |
| |
| pmd = pmd_offset(pud, addr); |
| do { |
| next = pmd_addr_end(addr, end); |
| if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { |
| if (next - addr != HPAGE_PMD_SIZE) |
| __split_huge_pmd(vma, pmd, addr, false, NULL); |
| 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 unsigned long zap_pud_range(struct mmu_gather *tlb, |
| struct vm_area_struct *vma, p4d_t *p4d, |
| unsigned long addr, unsigned long end, |
| struct zap_details *details) |
| { |
| pud_t *pud; |
| unsigned long next; |
| |
| pud = pud_offset(p4d, addr); |
| do { |
| next = pud_addr_end(addr, end); |
| if (pud_trans_huge(*pud) || pud_devmap(*pud)) { |
| if (next - addr != HPAGE_PUD_SIZE) { |
| VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma); |
| split_huge_pud(vma, pud, addr); |
| } else if (zap_huge_pud(tlb, vma, pud, addr)) |
| goto next; |
| /* fall through */ |
| } |
| if (pud_none_or_clear_bad(pud)) |
| continue; |
| next = zap_pmd_range(tlb, vma, pud, addr, next, details); |
| next: |
| cond_resched(); |
| } while (pud++, addr = next, addr != end); |
| |
| return addr; |
| } |
| |
| static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, |
| struct vm_area_struct *vma, pgd_t *pgd, |
| unsigned long addr, unsigned long end, |
| struct zap_details *details) |
| { |
| p4d_t *p4d; |
| unsigned long next; |
| |
| p4d = p4d_offset(pgd, addr); |
| do { |
| next = p4d_addr_end(addr, end); |
| if (p4d_none_or_clear_bad(p4d)) |
| continue; |
| next = zap_pud_range(tlb, vma, p4d, addr, next, details); |
| } while (p4d++, addr = next, addr != end); |
| |
| return addr; |
| } |
| |
| 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; |
| |
| BUG_ON(addr >= end); |
| 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; |
| next = zap_p4d_range(tlb, vma, pgd, addr, next, details); |
| } while (pgd++, addr = next, addr != end); |
| tlb_end_vma(tlb, vma); |
| } |
| |
| |
| 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) { |
| i_mmap_lock_write(vma->vm_file->f_mapping); |
| __unmap_hugepage_range_final(tlb, vma, start, end, NULL); |
| i_mmap_unlock_write(vma->vm_file->f_mapping); |
| } |
| } else |
| unmap_page_range(tlb, vma, start, end, details); |
| } |
| } |
| |
| /** |
| * unmap_vmas - unmap a range of memory covered by a list of vma's |
| * @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 |
| * |
| * Unmap all pages in the vma list. |
| * |
| * Only addresses between `start' and `end' will be unmapped. |
| * |
| * The VMA list must be sorted in ascending virtual address order. |
| * |
| * unmap_vmas() assumes that the caller will flush the whole unmapped address |
| * range after unmap_vmas() returns. So the only responsibility here is to |
| * ensure that any thus-far unmapped pages are flushed before unmap_vmas() |
| * drops the lock and schedules. |
| */ |
| void unmap_vmas(struct mmu_gather *tlb, |
| struct vm_area_struct *vma, unsigned long start_addr, |
| unsigned long end_addr) |
| { |
| struct mmu_notifier_range range; |
| |
| mmu_notifier_range_init(&range, vma->vm_mm, start_addr, end_addr); |
| mmu_notifier_invalidate_range_start(&range); |
| 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(&range); |
| } |
| |
| /** |
| * 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 |
| * |
| * Caller must protect the VMA list |
| */ |
| void zap_page_range(struct vm_area_struct *vma, unsigned long start, |
| unsigned long size) |
| { |
| struct mmu_notifier_range range; |
| struct mmu_gather tlb; |
| |
| lru_add_drain(); |
| mmu_notifier_range_init(&range, vma->vm_mm, start, start + size); |
| tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); |
| update_hiwater_rss(vma->vm_mm); |
| mmu_notifier_invalidate_range_start(&range); |
| for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) |
| unmap_single_vma(&tlb, vma, start, range.end, NULL); |
| mmu_notifier_invalidate_range_end(&range); |
| tlb_finish_mmu(&tlb, start, range.end); |
| } |
| |
| /** |
| * 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 shared cache invalidation |
| * |
| * The range must fit into one VMA. |
| */ |
| static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, |
| unsigned long size, struct zap_details *details) |
| { |
| struct mmu_notifier_range range; |
| struct mmu_gather tlb; |
| |
| lru_add_drain(); |
| mmu_notifier_range_init(&range, vma->vm_mm, address, address + size); |
| tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); |
| update_hiwater_rss(vma->vm_mm); |
| mmu_notifier_invalidate_range_start(&range); |
| unmap_single_vma(&tlb, vma, address, range.end, details); |
| mmu_notifier_invalidate_range_end(&range); |
| tlb_finish_mmu(&tlb, address, range.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. |
| * |
| */ |
| void 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; |
| |
| zap_page_range_single(vma, address, size, NULL); |
| } |
| EXPORT_SYMBOL_GPL(zap_vma_ptes); |
| |
| pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, |
| spinlock_t **ptl) |
| { |
| pgd_t *pgd; |
| p4d_t *p4d; |
| pud_t *pud; |
| pmd_t *pmd; |
| |
| pgd = pgd_offset(mm, addr); |
| p4d = p4d_alloc(mm, pgd, addr); |
| if (!p4d) |
| return NULL; |
| pud = pud_alloc(mm, p4d, addr); |
| if (!pud) |
| return NULL; |
| pmd = pmd_alloc(mm, pud, addr); |
| if (!pmd) |
| return NULL; |
| |
| VM_BUG_ON(pmd_trans_huge(*pmd)); |
| return pte_alloc_map_lock(mm, pmd, addr, ptl); |
| } |
| |
| /* |
| * 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. |
| */ |
| static int insert_page(struct vm_area_struct *vma, unsigned long addr, |
| struct page *page, pgprot_t prot) |
| { |
| struct mm_struct *mm = vma->vm_mm; |
| int retval; |
| pte_t *pte; |
| spinlock_t *ptl; |
| |
| retval = -EINVAL; |
| if (PageAnon(page) || PageSlab(page) || page_has_type(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; |
| |
| /* Ok, finally just insert the thing.. */ |
| get_page(page); |
| inc_mm_counter_fast(mm, mm_counter_file(page)); |
| page_add_file_rmap(page, false); |
| set_pte_at(mm, addr, pte, mk_pte(page, prot)); |
| |
| retval = 0; |
| pte_unmap_unlock(pte, ptl); |
| return retval; |
| out_unlock: |
| pte_unmap_unlock(pte, ptl); |
| out: |
| return retval; |
| } |
| |
| /** |
| * 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. |
| * |
| * Return: %0 on success, negative error code otherwise. |
| */ |
| 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); |
| |
| static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, |
| pfn_t pfn, pgprot_t prot, bool mkwrite) |
| { |
| struct mm_struct *mm = vma->vm_mm; |
| pte_t *pte, entry; |
| spinlock_t *ptl; |
| |
| pte = get_locked_pte(mm, addr, &ptl); |
| if (!pte) |
| return VM_FAULT_OOM; |
| if (!pte_none(*pte)) { |
| if (mkwrite) { |
| /* |
| * For read faults on private mappings the PFN passed |
| * in may not match the PFN we have mapped if the |
| * mapped PFN is a writeable COW page. In the mkwrite |
| * case we are creating a writable PTE for a shared |
| * mapping and we expect the PFNs to match. If they |
| * don't match, we are likely racing with block |
| * allocation and mapping invalidation so just skip the |
| * update. |
| */ |
| if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { |
| WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); |
| goto out_unlock; |
| } |
| entry = pte_mkyoung(*pte); |
| entry = maybe_mkwrite(pte_mkdirty(entry), vma); |
| if (ptep_set_access_flags(vma, addr, pte, entry, 1)) |
| update_mmu_cache(vma, addr, pte); |
| } |
| goto out_unlock; |
| } |
| |
| /* Ok, finally just insert the thing.. */ |
| if (pfn_t_devmap(pfn)) |
| entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); |
| else |
| entry = pte_mkspecial(pfn_t_pte(pfn, prot)); |
| |
| if (mkwrite) { |
| entry = pte_mkyoung(entry); |
| entry = maybe_mkwrite(pte_mkdirty(entry), vma); |
| } |
| |
| set_pte_at(mm, addr, pte, entry); |
| update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ |
| |
| out_unlock: |
| pte_unmap_unlock(pte, ptl); |
| return VM_FAULT_NOPAGE; |
| } |
| |
| /** |
| * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot |
| * @vma: user vma to map to |
| * @addr: target user address of this page |
| * @pfn: source kernel pfn |
| * @pgprot: pgprot flags for the inserted page |
| * |
| * This is exactly like vmf_insert_pfn(), except that it allows drivers to |
| * to override pgprot on a per-page basis. |
| * |
| * This only makes sense for IO mappings, and it makes no sense for |
| * COW mappings. In general, using multiple vmas is preferable; |
| * vmf_insert_pfn_prot should only be used if using multiple VMAs is |
| * impractical. |
| * |
| * Context: Process context. May allocate using %GFP_KERNEL. |
| * Return: vm_fault_t value. |
| */ |
| vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, |
| unsigned long pfn, pgprot_t pgprot) |
| { |
| /* |
| * 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. |
| */ |
| 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)); |
| |
| if (addr < vma->vm_start || addr >= vma->vm_end) |
| return VM_FAULT_SIGBUS; |
| |
| if (!pfn_modify_allowed(pfn, pgprot)) |
| return VM_FAULT_SIGBUS; |
| |
| track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); |
| |
| return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, |
| false); |
| } |
| EXPORT_SYMBOL(vmf_insert_pfn_prot); |
| |
| /** |
| * vmf_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 the result of this function. |
| * |
| * 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. |
| * |
| * Context: Process context. May allocate using %GFP_KERNEL. |
| * Return: vm_fault_t value. |
| */ |
| vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, |
| unsigned long pfn) |
| { |
| return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); |
| } |
| EXPORT_SYMBOL(vmf_insert_pfn); |
| |
| static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) |
| { |
| /* these checks mirror the abort conditions in vm_normal_page */ |
| if (vma->vm_flags & VM_MIXEDMAP) |
| return true; |
| if (pfn_t_devmap(pfn)) |
| return true; |
| if (pfn_t_special(pfn)) |
| return true; |
| if (is_zero_pfn(pfn_t_to_pfn(pfn))) |
| return true; |
| return false; |
| } |
| |
| static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, |
| unsigned long addr, pfn_t pfn, bool mkwrite) |
| { |
| pgprot_t pgprot = vma->vm_page_prot; |
| int err; |
| |
| BUG_ON(!vm_mixed_ok(vma, pfn)); |
| |
| if (addr < vma->vm_start || addr >= vma->vm_end) |
| return VM_FAULT_SIGBUS; |
| |
| track_pfn_insert(vma, &pgprot, pfn); |
| |
| if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) |
| return VM_FAULT_SIGBUS; |
| |
| /* |
| * 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 (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && |
| !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { |
| struct page *page; |
| |
| /* |
| * At this point we are committed to insert_page() |
| * regardless of whether the caller specified flags that |
| * result in pfn_t_has_page() == false. |
| */ |
| page = pfn_to_page(pfn_t_to_pfn(pfn)); |
| err = insert_page(vma, addr, page, pgprot); |
| } else { |
| return insert_pfn(vma, addr, pfn, pgprot, mkwrite); |
| } |
| |
| if (err == -ENOMEM) |
| return VM_FAULT_OOM; |
| if (err < 0 && err != -EBUSY) |
| return VM_FAULT_SIGBUS; |
| |
| return VM_FAULT_NOPAGE; |
| } |
| |
| vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, |
| pfn_t pfn) |
| { |
| return __vm_insert_mixed(vma, addr, pfn, false); |
| } |
| EXPORT_SYMBOL(vmf_insert_mixed); |
| |
| /* |
| * If the insertion of PTE failed because someone else already added a |
| * different entry in the mean time, we treat that as success as we assume |
| * the same entry was actually inserted. |
| */ |
| vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, |
| unsigned long addr, pfn_t pfn) |
| { |
| return __vm_insert_mixed(vma, addr, pfn, true); |
| } |
| EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); |
| |
| /* |
| * 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; |
| int err = 0; |
| |
| pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); |
| if (!pte) |
| return -ENOMEM; |
| arch_enter_lazy_mmu_mode(); |
| do { |
| BUG_ON(!pte_none(*pte)); |
| if (!pfn_modify_allowed(pfn, prot)) { |
| err = -EACCES; |
| break; |
| } |
| 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 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) |
| { |
| pmd_t *pmd; |
| unsigned long next; |
| int err; |
| |
| 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); |
| err = remap_pte_range(mm, pmd, addr, next, |
| pfn + (addr >> PAGE_SHIFT), prot); |
| if (err) |
| return err; |
| } while (pmd++, addr = next, addr != end); |
| return 0; |
| } |
| |
| static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, |
| unsigned long addr, unsigned long end, |
| unsigned long pfn, pgprot_t prot) |
| { |
| pud_t *pud; |
| unsigned long next; |
| int err; |
| |
| pfn -= addr >> PAGE_SHIFT; |
| pud = pud_alloc(mm, p4d, addr); |
| if (!pud) |
| return -ENOMEM; |
| do { |
| next = pud_addr_end(addr, end); |
| err = remap_pmd_range(mm, pud, addr, next, |
| pfn + (addr >> PAGE_SHIFT), prot); |
| if (err) |
| return err; |
| } while (pud++, addr = next, addr != end); |
| return 0; |
| } |
| |
| static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, |
| unsigned long addr, unsigned long end, |
| unsigned long pfn, pgprot_t prot) |
| { |
| p4d_t *p4d; |
| unsigned long next; |
| int err; |
| |
| pfn -= addr >> PAGE_SHIFT; |
| p4d = p4d_alloc(mm, pgd, addr); |
| if (!p4d) |
| return -ENOMEM; |
| do { |
| next = p4d_addr_end(addr, end); |
| err = remap_pud_range(mm, p4d, addr, next, |
| pfn + (addr >> PAGE_SHIFT), prot); |
| if (err) |
| return err; |
| } while (p4d++, addr = next, addr != end); |
| return 0; |
| } |
| |
| /** |
| * 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. |
| * |
| * Return: %0 on success, negative error code otherwise. |
| */ |
| 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 + PAGE_ALIGN(size); |
| struct mm_struct *mm = vma->vm_mm; |
| unsigned long remap_pfn = pfn; |
| 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, remap_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 = remap_p4d_range(mm, pgd, addr, next, |
| pfn + (addr >> PAGE_SHIFT), prot); |
| if (err) |
| break; |
| } while (pgd++, addr = next, addr != end); |
| |
| if (err) |
| untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); |
| |
| return err; |
| } |
| EXPORT_SYMBOL(remap_pfn_range); |
| |
| /** |
| * 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. |
| * |
| * Return: %0 on success, negative error code otherwise. |
| */ |
| 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; |
| int err; |
| pgtable_t token; |
| spinlock_t *uninitialized_var(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 { |
| 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 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)); |
| |
| pmd = pmd_alloc(mm, pud, addr); |
| if (!pmd) |
| return -ENOMEM; |
| do { |
| next = pmd_addr_end(addr, end); |
| err = apply_to_pte_range(mm, pmd, addr, next, fn, data); |
| if (err) |
| break; |
| } while (pmd++, addr = next, addr != end); |
| return err; |
| } |
| |
| static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, |
| unsigned long addr, unsigned long end, |
| pte_fn_t fn, void *data) |
| { |
| pud_t *pud; |
| unsigned long next; |
| int err; |
| |
| pud = pud_alloc(mm, p4d, addr); |
| if (!pud) |
| return -ENOMEM; |
| do { |
| next = pud_addr_end(addr, end); |
| err = apply_to_pmd_range(mm, pud, addr, next, fn, data); |
| if (err) |
| break; |
| } while (pud++, addr = next, addr != end); |
| return err; |
| } |
| |
| static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, |
| unsigned long addr, unsigned long end, |
| pte_fn_t fn, void *data) |
| { |
| p4d_t *p4d; |
| unsigned long next; |
| int err; |
| |
| p4d = p4d_alloc(mm, pgd, addr); |
| if (!p4d) |
| return -ENOMEM; |
| do { |
| next = p4d_addr_end(addr, end); |
| err = apply_to_pud_range(mm, p4d, addr, next, fn, data); |
| if (err) |
| break; |
| } while (p4d++, addr = next, addr != end); |
| return err; |
| } |
| |
| /* |
| * 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 + size; |
| int err; |
| |
| if (WARN_ON(addr >= end)) |
| return -EINVAL; |
| |
| pgd = pgd_offset(mm, addr); |
| do { |
| next = pgd_addr_end(addr, end); |
| err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); |
| if (err) |
| break; |
| } while (pgd++, addr = next, addr != end); |
| |
| return err; |
| } |
| 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 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 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) |
| { |
| int same = 1; |
| #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) |
| if (sizeof(pte_t) > sizeof(unsigned long)) { |
| spinlock_t *ptl = pte_lockptr(mm, pmd); |
| spin_lock(ptl); |
| same = pte_same(*page_table, orig_pte); |
| spin_unlock(ptl); |
| } |
| #endif |
| pte_unmap(page_table); |
| 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); |
| } |
| |
| static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) |
| { |
| struct file *vm_file = vma->vm_file; |
| |
| if (vm_file) |
| return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; |
| |
| /* |
| * Special mappings (e.g. VDSO) do not have any file so fake |
| * a default GFP_KERNEL for them. |
| */ |
| return GFP_KERNEL; |
| } |
| |
| /* |
| * 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 vm_fault_t do_page_mkwrite(struct vm_fault *vmf) |
| { |
| vm_fault_t ret; |
| struct page *page = vmf->page; |
| unsigned int old_flags = vmf->flags; |
| |
| vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; |
| |
| ret = vmf->vma->vm_ops->page_mkwrite(vmf); |
| /* Restore original flags so that caller is not surprised */ |
| vmf->flags = old_flags; |
| 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; |
| } |
| |
| /* |
| * Handle dirtying of a page in shared file mapping on a write fault. |
| * |
| * The function expects the page to be locked and unlocks it. |
| */ |
| static void fault_dirty_shared_page(struct vm_area_struct *vma, |
| struct page *page) |
| { |
| struct address_space *mapping; |
| bool dirtied; |
| bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; |
| |
| dirtied = set_page_dirty(page); |
| VM_BUG_ON_PAGE(PageAnon(page), page); |
| /* |
| * Take a local copy of the address_space - page.mapping may be zeroed |
| * by truncate after unlock_page(). The address_space itself remains |
| * pinned by vma->vm_file's reference. We rely on unlock_page()'s |
| * release semantics to prevent the compiler from undoing this copying. |
| */ |
| mapping = page_rmapping(page); |
| unlock_page(page); |
| |
| if ((dirtied || page_mkwrite) && mapping) { |
| /* |
| * Some device drivers do not set page.mapping |
| * but still dirty their pages |
| */ |
| balance_dirty_pages_ratelimited(mapping); |
| } |
| |
| if (!page_mkwrite) |
| file_update_time(vma->vm_file); |
| } |
| |
| /* |
| * Handle write page faults for pages that can be reused in the current vma |
| * |
| * This can happen either due to the mapping being with the VM_SHARED flag, |
| * or due to us being the last reference standing to the page. In either |
| * case, all we need to do here is to mark the page as writable and update |
| * any related book-keeping. |
| */ |
| static inline void wp_page_reuse(struct vm_fault *vmf) |
| __releases(vmf->ptl) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| struct page *page = vmf->page; |
| pte_t entry; |
| /* |
| * Clear the pages cpupid information as the existing |
| * information potentially belongs to a now completely |
| * unrelated process. |
| */ |
| if (page) |
| page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); |
| |
| flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); |
| entry = pte_mkyoung(vmf->orig_pte); |
| entry = maybe_mkwrite(pte_mkdirty(entry), vma); |
| if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) |
| update_mmu_cache(vma, vmf->address, vmf->pte); |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| } |
| |
| /* |
| * Handle the case of a page which we actually need to copy to a new page. |
| * |
| * Called with mmap_sem locked and the old page referenced, but |
| * without the ptl held. |
| * |
| * High level logic flow: |
| * |
| * - Allocate a page, copy the content of the old page to the new one. |
| * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. |
| * - Take the PTL. If the pte changed, bail out and release the allocated page |
| * - If the pte is still the way we remember it, update the page table and all |
| * relevant references. This includes dropping the reference the page-table |
| * held to the old page, as well as updating the rmap. |
| * - In any case, unlock the PTL and drop the reference we took to the old page. |
| */ |
| static vm_fault_t wp_page_copy(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| struct mm_struct *mm = vma->vm_mm; |
| struct page *old_page = vmf->page; |
| struct page *new_page = NULL; |
| pte_t entry; |
| int page_copied = 0; |
| struct mem_cgroup *memcg; |
| struct mmu_notifier_range range; |
| |
| if (unlikely(anon_vma_prepare(vma))) |
| goto oom; |
| |
| if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { |
| new_page = alloc_zeroed_user_highpage_movable(vma, |
| vmf->address); |
| if (!new_page) |
| goto oom; |
| } else { |
| new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, |
| vmf->address); |
| if (!new_page) |
| goto oom; |
| cow_user_page(new_page, old_page, vmf->address, vma); |
| } |
| |
| if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) |
| goto oom_free_new; |
| |
| __SetPageUptodate(new_page); |
| |
| mmu_notifier_range_init(&range, mm, vmf->address & PAGE_MASK, |
| (vmf->address & PAGE_MASK) + PAGE_SIZE); |
| mmu_notifier_invalidate_range_start(&range); |
| |
| /* |
| * Re-check the pte - we dropped the lock |
| */ |
| vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); |
| if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { |
| if (old_page) { |
| if (!PageAnon(old_page)) { |
| dec_mm_counter_fast(mm, |
| mm_counter_file(old_page)); |
| inc_mm_counter_fast(mm, MM_ANONPAGES); |
| } |
| } else { |
| inc_mm_counter_fast(mm, MM_ANONPAGES); |
| } |
| flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); |
| entry = mk_pte(new_page, vma->vm_page_prot); |
| entry = maybe_mkwrite(pte_mkdirty(entry), vma); |
| /* |
| * 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_notify(vma, vmf->address, vmf->pte); |
| page_add_new_anon_rmap(new_page, vma, vmf->address, false); |
| mem_cgroup_commit_charge(new_page, memcg, false, false); |
| lru_cache_add_active_or_unevictable(new_page, vma); |
| /* |
| * 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, vmf->address, vmf->pte, entry); |
| update_mmu_cache(vma, vmf->address, vmf->pte); |
| 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, false); |
| } |
| |
| /* Free the old page.. */ |
| new_page = old_page; |
| page_copied = 1; |
| } else { |
| mem_cgroup_cancel_charge(new_page, memcg, false); |
| } |
| |
| if (new_page) |
| put_page(new_page); |
| |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| /* |
| * No need to double call mmu_notifier->invalidate_range() callback as |
| * the above ptep_clear_flush_notify() did already call it. |
| */ |
| mmu_notifier_invalidate_range_only_end(&range); |
| if (old_page) { |
| /* |
| * Don't let another task, with possibly unlocked vma, |
| * keep the mlocked page. |
| */ |
| if (page_copied && (vma->vm_flags & VM_LOCKED)) { |
| lock_page(old_page); /* LRU manipulation */ |
| if (PageMlocked(old_page)) |
| munlock_vma_page(old_page); |
| unlock_page(old_page); |
| } |
| put_page(old_page); |
| } |
| return page_copied ? VM_FAULT_WRITE : 0; |
| oom_free_new: |
| put_page(new_page); |
| oom: |
| if (old_page) |
| put_page(old_page); |
| return VM_FAULT_OOM; |
| } |
| |
| /** |
| * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE |
| * writeable once the page is prepared |
| * |
| * @vmf: structure describing the fault |
| * |
| * This function handles all that is needed to finish a write page fault in a |
| * shared mapping due to PTE being read-only once the mapped page is prepared. |
| * It handles locking of PTE and modifying it. |
| * |
| * The function expects the page to be locked or other protection against |
| * concurrent faults / writeback (such as DAX radix tree locks). |
| * |
| * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before |
| * we acquired PTE lock. |
| */ |
| vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) |
| { |
| WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); |
| vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, |
| &vmf->ptl); |
| /* |
| * We might have raced with another page fault while we released the |
| * pte_offset_map_lock. |
| */ |
| if (!pte_same(*vmf->pte, vmf->orig_pte)) { |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| return VM_FAULT_NOPAGE; |
| } |
| wp_page_reuse(vmf); |
| return 0; |
| } |
| |
| /* |
| * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED |
| * mapping |
| */ |
| static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| |
| if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { |
| vm_fault_t ret; |
| |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| vmf->flags |= FAULT_FLAG_MKWRITE; |
| ret = vma->vm_ops->pfn_mkwrite(vmf); |
| if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) |
| return ret; |
| return finish_mkwrite_fault(vmf); |
| } |
| wp_page_reuse(vmf); |
| return VM_FAULT_WRITE; |
| } |
| |
| static vm_fault_t wp_page_shared(struct vm_fault *vmf) |
| __releases(vmf->ptl) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| |
| get_page(vmf->page); |
| |
| if (vma->vm_ops && vma->vm_ops->page_mkwrite) { |
| vm_fault_t tmp; |
| |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| tmp = do_page_mkwrite(vmf); |
| if (unlikely(!tmp || (tmp & |
| (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { |
| put_page(vmf->page); |
| return tmp; |
| } |
| tmp = finish_mkwrite_fault(vmf); |
| if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { |
| unlock_page(vmf->page); |
| put_page(vmf->page); |
| return tmp; |
| } |
| } else { |
| wp_page_reuse(vmf); |
| lock_page(vmf->page); |
| } |
| fault_dirty_shared_page(vma, vmf->page); |
| put_page(vmf->page); |
| |
| return VM_FAULT_WRITE; |
| } |
| |
| /* |
| * This routine handles present pages, when users try to write |
| * to a shared page. It is done by copying the page to a new address |
| * and decrementing the shared-page counter for the old page. |
| * |
| * Note that this routine assumes that the protection checks have been |
| * done by the caller (the low-level page fault routine in most cases). |
| * Thus we can safely just mark it writable once we've done any necessary |
| * COW. |
| * |
| * We also mark the page dirty at this point even though the page will |
| * change only once the write actually happens. This avoids a few races, |
| * and potentially makes it more efficient. |
| * |
| * We enter with non-exclusive mmap_sem (to exclude vma changes, |
| * but allow concurrent faults), with pte both mapped and locked. |
| * We return with mmap_sem still held, but pte unmapped and unlocked. |
| */ |
| static vm_fault_t do_wp_page(struct vm_fault *vmf) |
| __releases(vmf->ptl) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| |
| vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); |
| if (!vmf->page) { |
| /* |
| * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a |
| * VM_PFNMAP VMA. |
| * |
| * We should not cow pages in a shared writeable mapping. |
| * Just mark the pages writable and/or call ops->pfn_mkwrite. |
| */ |
| if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == |
| (VM_WRITE|VM_SHARED)) |
| return wp_pfn_shared(vmf); |
| |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| return wp_page_copy(vmf); |
| } |
| |
| /* |
| * Take out anonymous pages first, anonymous shared vmas are |
| * not dirty accountable. |
| */ |
| if (PageAnon(vmf->page)) { |
| int total_map_swapcount; |
| if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) || |
| page_count(vmf->page) != 1)) |
| goto copy; |
| if (!trylock_page(vmf->page)) { |
| get_page(vmf->page); |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| lock_page(vmf->page); |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, |
| vmf->address, &vmf->ptl); |
| if (!pte_same(*vmf->pte, vmf->orig_pte)) { |
| unlock_page(vmf->page); |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| put_page(vmf->page); |
| return 0; |
| } |
| put_page(vmf->page); |
| } |
| if (PageKsm(vmf->page)) { |
| bool reused = reuse_ksm_page(vmf->page, vmf->vma, |
| vmf->address); |
| unlock_page(vmf->page); |
| if (!reused) |
| goto copy; |
| wp_page_reuse(vmf); |
| return VM_FAULT_WRITE; |
| } |
| if (reuse_swap_page(vmf->page, &total_map_swapcount)) { |
| if (total_map_swapcount == 1) { |
| /* |
| * 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(vmf->page, vma); |
| } |
| unlock_page(vmf->page); |
| wp_page_reuse(vmf); |
| return VM_FAULT_WRITE; |
| } |
| unlock_page(vmf->page); |
| } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == |
| (VM_WRITE|VM_SHARED))) { |
| return wp_page_shared(vmf); |
| } |
| copy: |
| /* |
| * Ok, we need to copy. Oh, well.. |
| */ |
| get_page(vmf->page); |
| |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| return wp_page_copy(vmf); |
| } |
| |
| static void unmap_mapping_range_vma(struct vm_area_struct *vma, |
| unsigned long start_addr, unsigned long end_addr, |
| struct zap_details *details) |
| { |
| zap_page_range_single(vma, start_addr, end_addr - start_addr, details); |
| } |
| |
| static inline void unmap_mapping_range_tree(struct rb_root_cached *root, |
| struct zap_details *details) |
| { |
| struct vm_area_struct *vma; |
| pgoff_t vba, vea, zba, zea; |
| |
| vma_interval_tree_foreach(vma, root, |
| details->first_index, details->last_index) { |
| |
| vba = vma->vm_pgoff; |
| vea = vba + vma_pages(vma) - 1; |
| zba = details->first_index; |
| if (zba < vba) |
| zba = vba; |
| zea = details->last_index; |
| if (zea > vea) |
| zea = vea; |
| |
| unmap_mapping_range_vma(vma, |
| ((zba - vba) << PAGE_SHIFT) + vma->vm_start, |
| ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, |
| details); |
| } |
| } |
| |
| /** |
| * unmap_mapping_pages() - Unmap pages from processes. |
| * @mapping: The address space containing pages to be unmapped. |
| * @start: Index of first page to be unmapped. |
| * @nr: Number of pages to be unmapped. 0 to unmap to end of file. |
| * @even_cows: Whether to unmap even private COWed pages. |
| * |
| * Unmap the pages in this address space from any userspace process which |
| * has them mmaped. Generally, you want to remove COWed pages as well when |
| * a file is being truncated, but not when invalidating pages from the page |
| * cache. |
| */ |
| void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, |
| pgoff_t nr, bool even_cows) |
| { |
| struct zap_details details = { }; |
| |
| details.check_mapping = even_cows ? NULL : mapping; |
| details.first_index = start; |
| details.last_index = start + nr - 1; |
| if (details.last_index < details.first_index) |
| details.last_index = ULONG_MAX; |
| |
| i_mmap_lock_write(mapping); |
| if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) |
| unmap_mapping_range_tree(&mapping->i_mmap, &details); |
| i_mmap_unlock_write(mapping); |
| } |
| |
| /** |
| * unmap_mapping_range - unmap the portion of all mmaps in the specified |
| * address_space corresponding to the specified byte 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 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 |
| * up to a PAGE_SIZE boundary. A holelen of zero truncates to the |
| * end of the file. |
| * @even_cows: 1 when truncating a file, unmap even private COWed pages; |
| * but 0 when invalidating pagecache, don't throw away private data. |
| */ |
| void unmap_mapping_range(struct address_space *mapping, |
| loff_t const holebegin, loff_t const holelen, int even_cows) |
| { |
| pgoff_t hba = holebegin >> PAGE_SHIFT; |
| pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; |
| |
| /* Check for overflow. */ |
| if (sizeof(holelen) > sizeof(hlen)) { |
| long long holeend = |
| (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; |
| if (holeend & ~(long long)ULONG_MAX) |
| hlen = ULONG_MAX - hba + 1; |
| } |
| |
| unmap_mapping_pages(mapping, hba, hlen, even_cows); |
| } |
| EXPORT_SYMBOL(unmap_mapping_range); |
| |
| /* |
| * 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 pte unmapped and unlocked. |
| * |
| * We return with the mmap_sem locked or unlocked in the same cases |
| * as does filemap_fault(). |
| */ |
| vm_fault_t do_swap_page(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| struct page *page = NULL, *swapcache; |
| struct mem_cgroup *memcg; |
| swp_entry_t entry; |
| pte_t pte; |
| int locked; |
| int exclusive = 0; |
| vm_fault_t ret = 0; |
| |
| if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) |
| goto out; |
| |
| entry = pte_to_swp_entry(vmf->orig_pte); |
| if (unlikely(non_swap_entry(entry))) { |
| if (is_migration_entry(entry)) { |
| migration_entry_wait(vma->vm_mm, vmf->pmd, |
| vmf->address); |
| } else if (is_device_private_entry(entry)) { |
| /* |
| * For un-addressable device memory we call the pgmap |
| * fault handler callback. The callback must migrate |
| * the page back to some CPU accessible page. |
| */ |
| ret = device_private_entry_fault(vma, vmf->address, entry, |
| vmf->flags, vmf->pmd); |
| } else if (is_hwpoison_entry(entry)) { |
| ret = VM_FAULT_HWPOISON; |
| } else { |
| print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); |
| ret = VM_FAULT_SIGBUS; |
| } |
| goto out; |
| } |
| |
| |
| delayacct_set_flag(DELAYACCT_PF_SWAPIN); |
| page = lookup_swap_cache(entry, vma, vmf->address); |
| swapcache = page; |
| |
| if (!page) { |
| struct swap_info_struct *si = swp_swap_info(entry); |
| |
| if (si->flags & SWP_SYNCHRONOUS_IO && |
| __swap_count(si, entry) == 1) { |
| /* skip swapcache */ |
| page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, |
| vmf->address); |
| if (page) { |
| __SetPageLocked(page); |
| __SetPageSwapBacked(page); |
| set_page_private(page, entry.val); |
| lru_cache_add_anon(page); |
| swap_readpage(page, true); |
| } |
| } else { |
| page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, |
| vmf); |
| swapcache = page; |
| } |
| |
| if (!page) { |
| /* |
| * Back out if somebody else faulted in this pte |
| * while we released the pte lock. |
| */ |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, |
| vmf->address, &vmf->ptl); |
| if (likely(pte_same(*vmf->pte, vmf->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; |
| count_vm_event(PGMAJFAULT); |
| count_memcg_event_mm(vma->vm_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); |
| goto out_release; |
| } |
| |
| locked = lock_page_or_retry(page, vma->vm_mm, vmf->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)) && swapcache) |
| goto out_page; |
| |
| page = ksm_might_need_to_copy(page, vma, vmf->address); |
| if (unlikely(!page)) { |
| ret = VM_FAULT_OOM; |
| page = swapcache; |
| goto out_page; |
| } |
| |
| if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, |
| &memcg, false)) { |
| ret = VM_FAULT_OOM; |
| goto out_page; |
| } |
| |
| /* |
| * Back out if somebody else already faulted in this pte. |
| */ |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, |
| &vmf->ptl); |
| if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) |
| goto out_nomap; |
| |
| if (unlikely(!PageUptodate(page))) { |
| ret = VM_FAULT_SIGBUS; |
| goto out_nomap; |
| } |
| |
| /* |
| * 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. |
| */ |
| |
| inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); |
| dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); |
| pte = mk_pte(page, vma->vm_page_prot); |
| if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { |
| pte = maybe_mkwrite(pte_mkdirty(pte), vma); |
| vmf->flags &= ~FAULT_FLAG_WRITE; |
| ret |= VM_FAULT_WRITE; |
| exclusive = RMAP_EXCLUSIVE; |
| } |
| flush_icache_page(vma, page); |
| if (pte_swp_soft_dirty(vmf->orig_pte)) |
| pte = pte_mksoft_dirty(pte); |
| set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); |
| arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); |
| vmf->orig_pte = pte; |
| |
| /* ksm created a completely new copy */ |
| if (unlikely(page != swapcache && swapcache)) { |
| page_add_new_anon_rmap(page, vma, vmf->address, false); |
| mem_cgroup_commit_charge(page, memcg, false, false); |
| lru_cache_add_active_or_unevictable(page, vma); |
| } else { |
| do_page_add_anon_rmap(page, vma, vmf->address, exclusive); |
| mem_cgroup_commit_charge(page, memcg, true, false); |
| activate_page(page); |
| } |
| |
| swap_free(entry); |
| if (mem_cgroup_swap_full(page) || |
| (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) |
| try_to_free_swap(page); |
| unlock_page(page); |
| if (page != swapcache && 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); |
| put_page(swapcache); |
| } |
| |
| if (vmf->flags & FAULT_FLAG_WRITE) { |
| ret |= do_wp_page(vmf); |
| if (ret & VM_FAULT_ERROR) |
| ret &= VM_FAULT_ERROR; |
| goto out; |
| } |
| |
| /* No need to invalidate - it was non-present before */ |
| update_mmu_cache(vma, vmf->address, vmf->pte); |
| unlock: |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| out: |
| return ret; |
| out_nomap: |
| mem_cgroup_cancel_charge(page, memcg, false); |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| out_page: |
| unlock_page(page); |
| out_release: |
| put_page(page); |
| if (page != swapcache && swapcache) { |
| unlock_page(swapcache); |
| put_page(swapcache); |
| } |
| return ret; |
| } |
| |
| /* |
| * 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 vm_fault_t do_anonymous_page(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| struct mem_cgroup *memcg; |
| struct page *page; |
| vm_fault_t ret = 0; |
| pte_t entry; |
| |
| /* File mapping without ->vm_ops ? */ |
| if (vma->vm_flags & VM_SHARED) |
| return VM_FAULT_SIGBUS; |
| |
| /* |
| * Use pte_alloc() instead of pte_alloc_map(). We can't run |
| * pte_offset_map() on pmds where a huge pmd might be created |
| * from a different thread. |
| * |
| * pte_alloc_map() is safe to use under down_write(mmap_sem) or when |
| * parallel threads are excluded by other means. |
| * |
| * Here we only have down_read(mmap_sem). |
| */ |
| if (pte_alloc(vma->vm_mm, vmf->pmd)) |
| return VM_FAULT_OOM; |
| |
| /* See the comment in pte_alloc_one_map() */ |
| if (unlikely(pmd_trans_unstable(vmf->pmd))) |
| return 0; |
| |
| /* Use the zero-page for reads */ |
| if (!(vmf->flags & FAULT_FLAG_WRITE) && |
| !mm_forbids_zeropage(vma->vm_mm)) { |
| entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), |
| vma->vm_page_prot)); |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, |
| vmf->address, &vmf->ptl); |
| if (!pte_none(*vmf->pte)) |
| goto unlock; |
| ret = check_stable_address_space(vma->vm_mm); |
| if (ret) |
| goto unlock; |
| /* Deliver the page fault to userland, check inside PT lock */ |
| if (userfaultfd_missing(vma)) { |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| return handle_userfault(vmf, VM_UFFD_MISSING); |
| } |
| goto setpte; |
| } |
| |
| /* Allocate our own private page. */ |
| if (unlikely(anon_vma_prepare(vma))) |
| goto oom; |
| page = alloc_zeroed_user_highpage_movable(vma, vmf->address); |
| if (!page) |
| goto oom; |
| |
| if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, |
| false)) |
| goto oom_free_page; |
| |
| /* |
| * The memory barrier inside __SetPageUptodate makes sure that |
| * preceeding stores to the page contents become visible before |
| * the set_pte_at() write. |
| */ |
| __SetPageUptodate(page); |
| |
| entry = mk_pte(page, vma->vm_page_prot); |
| if (vma->vm_flags & VM_WRITE) |
| entry = pte_mkwrite(pte_mkdirty(entry)); |
| |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, |
| &vmf->ptl); |
| if (!pte_none(*vmf->pte)) |
| goto release; |
| |
| ret = check_stable_address_space(vma->vm_mm); |
| if (ret) |
| goto release; |
| |
| /* Deliver the page fault to userland, check inside PT lock */ |
| if (userfaultfd_missing(vma)) { |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| mem_cgroup_cancel_charge(page, memcg, false); |
| put_page(page); |
| return handle_userfault(vmf, VM_UFFD_MISSING); |
| } |
| |
| inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); |
| page_add_new_anon_rmap(page, vma, vmf->address, false); |
| mem_cgroup_commit_charge(page, memcg, false, false); |
| lru_cache_add_active_or_unevictable(page, vma); |
| setpte: |
| set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); |
| |
| /* No need to invalidate - it was non-present before */ |
| update_mmu_cache(vma, vmf->address, vmf->pte); |
| unlock: |
| pte_unmap_unlock(vmf->pte, vmf->ptl); |
| return ret; |
| release: |
| mem_cgroup_cancel_charge(page, memcg, false); |
| put_page(page); |
| goto unlock; |
| oom_free_page: |
| put_page(page); |
| oom: |
| return VM_FAULT_OOM; |
| } |
| |
| /* |
| * The mmap_sem must have been held on entry, and may have been |
| * released depending on flags and vma->vm_ops->fault() return value. |
| * See filemap_fault() and __lock_page_retry(). |
| */ |
| static vm_fault_t __do_fault(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| vm_fault_t ret; |
| |
| /* |
| * Preallocate pte before we take page_lock because this might lead to |
| * deadlocks for memcg reclaim which waits for pages under writeback: |
| * lock_page(A) |
| * SetPageWriteback(A) |
| * unlock_page(A) |
| * lock_page(B) |
| * lock_page(B) |
| * pte_alloc_pne |
| * shrink_page_list |
| * wait_on_page_writeback(A) |
| * SetPageWriteback(B) |
| * unlock_page(B) |
| * # flush A, B to clear the writeback |
| */ |
| if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { |
| vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); |
| if (!vmf->prealloc_pte) |
| return VM_FAULT_OOM; |
| smp_wmb(); /* See comment in __pte_alloc() */ |
| } |
| |
| ret = vma->vm_ops->fault(vmf); |
| if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | |
| VM_FAULT_DONE_COW))) |
| return ret; |
| |
| if (unlikely(PageHWPoison(vmf->page))) { |
| if (ret & VM_FAULT_LOCKED) |
| unlock_page(vmf->page); |
| put_page(vmf->page); |
| vmf->page = NULL; |
| return VM_FAULT_HWPOISON; |
| } |
| |
| if (unlikely(!(ret & VM_FAULT_LOCKED))) |
| lock_page(vmf->page); |
| else |
| VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); |
| |
| return ret; |
| } |
| |
| /* |
| * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. |
| * If we check pmd_trans_unstable() first we will trip the bad_pmd() check |
| * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly |
| * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. |
| */ |
| static int pmd_devmap_trans_unstable(pmd_t *pmd) |
| { |
| return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); |
| } |
| |
| static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) |
| { |
| struct vm_area_struct *vma = vmf->vma; |
| |
| if (!pmd_none(*vmf->pmd)) |
| goto map_pte; |
| if (vmf->prealloc_pte) { |
| vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); |
| if (unlikely(!pmd_none(*vmf->pmd))) { |
| spin_unlock(vmf->ptl); |
| goto map_pte; |
| } |
| |
| mm_inc_nr_ptes(vma->vm_mm); |
| pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); |
| spin_unlock(vmf->ptl); |
| vmf->prealloc_pte = NULL; |
| } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { |
| return VM_FAULT_OOM; |
| } |
| map_pte: |
| /* |
| * If a huge pmd materialized under us just retry later. Use |
| * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of |
| * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge |
| * under us and then back to pmd_none, as a result of MADV_DONTNEED |
| * running immediately after a huge pmd fault in a different thread of |
| * this mm, in turn leading to a misleading pmd_trans_huge() retval. |
| * All we have to ensure is that it is a regular pmd that we can walk |
| * with pte_offset_map() and we can do that through an atomic read in |
| * C, which is what pmd_trans_unstable() provides. |
| */ |
| if (pmd_devmap_trans_unstable(vmf->pmd)) |
| return VM_FAULT_NOPAGE; |
| |
| /* |
| * At this point we know that our vmf->pmd points to a page of ptes |
| * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() |
| * for the duration of the fault. If a racing MADV_DONTNEED runs and |
| * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still |
| * be valid and we will re-check to make sure the vmf->pte isn't |
| * pte_none() under vmf->ptl protection when we return to |
| * alloc_set_pte(). |
| */ |
| vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, |
| &vmf->ptl); |
| return 0; |
| } |
| |
| #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE |
| |
| #define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - |