diff options
Diffstat (limited to 'mm/memory.c')
| -rw-r--r-- | mm/memory.c | 8445 |
1 files changed, 5772 insertions, 2673 deletions
diff --git a/mm/memory.c b/mm/memory.c index 1ce2e2a734fc..2a55edc48a65 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * @@ -30,7 +31,7 @@ /* * 05.04.94 - Multi-page memory management added for v1.1. - * Idea by Alex Bligh (alex@cconcepts.co.uk) + * 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) @@ -40,11 +41,17 @@ #include <linux/kernel_stat.h> #include <linux/mm.h> +#include <linux/mm_inline.h> +#include <linux/sched/mm.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/kmsan.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> @@ -53,45 +60,57 @@ #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> -#include <linux/kallsyms.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> +#include <linux/shmem_fs.h> +#include <linux/memory-tiers.h> +#include <linux/debugfs.h> +#include <linux/userfaultfd_k.h> +#include <linux/dax.h> +#include <linux/oom.h> +#include <linux/numa.h> +#include <linux/perf_event.h> +#include <linux/ptrace.h> +#include <linux/vmalloc.h> +#include <linux/sched/sysctl.h> +#include <linux/pgalloc.h> +#include <linux/uaccess.h> + +#include <trace/events/kmem.h> #include <asm/io.h> -#include <asm/pgalloc.h> -#include <asm/uaccess.h> +#include <asm/mmu_context.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -#include <asm/pgtable.h> +#include "pgalloc-track.h" #include "internal.h" +#include "swap.h" -#ifdef LAST_NID_NOT_IN_PAGE_FLAGS -#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid. +#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; -struct page *mem_map; - -EXPORT_SYMBOL(max_mapnr); -EXPORT_SYMBOL(mem_map); -#endif +static vm_fault_t do_fault(struct vm_fault *vmf); +static vm_fault_t do_anonymous_page(struct vm_fault *vmf); +static bool vmf_pte_changed(struct vm_fault *vmf); /* - * 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. + * Return true if the original pte was a uffd-wp pte marker (so the pte was + * wr-protected). */ -void * high_memory; +static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) +{ + if (!userfaultfd_wp(vmf->vma)) + return false; + if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) + return false; -EXPORT_SYMBOL(high_memory); + return pte_is_uffd_wp_marker(vmf->orig_pte); +} /* * Randomize the address space (stacks, mmaps, brk, etc.). @@ -106,295 +125,61 @@ int randomize_va_space __read_mostly = 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; -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) +static const struct ctl_table mmu_sysctl_table[] = { + { + .procname = "randomize_va_space", + .data = &randomize_va_space, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +}; + +static int __init init_mm_sysctl(void) { - zero_pfn = page_to_pfn(ZERO_PAGE(0)); + register_sysctl_init("kernel", mmu_sysctl_table); 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 */ - -#ifdef HAVE_GENERIC_MMU_GATHER - -static int tlb_next_batch(struct mmu_gather *tlb) -{ - struct mmu_gather_batch *batch; - - batch = tlb->active; - if (batch->next) { - tlb->active = batch->next; - return 1; - } - - if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) - return 0; - - batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); - if (!batch) - return 0; - - tlb->batch_count++; - batch->next = NULL; - batch->nr = 0; - batch->max = MAX_GATHER_BATCH; - - tlb->active->next = batch; - tlb->active = batch; - - return 1; -} - -/* tlb_gather_mmu - * Called to initialize an (on-stack) mmu_gather structure for page-table - * tear-down from @mm. The @fullmm argument is used when @mm is without - * users and we're going to destroy the full address space (exit/execve). - */ -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) -{ - tlb->mm = mm; - - tlb->fullmm = fullmm; - tlb->need_flush_all = 0; - tlb->start = -1UL; - tlb->end = 0; - tlb->need_flush = 0; - tlb->local.next = NULL; - tlb->local.nr = 0; - tlb->local.max = ARRAY_SIZE(tlb->__pages); - tlb->active = &tlb->local; - tlb->batch_count = 0; - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb->batch = NULL; -#endif -} - -void tlb_flush_mmu(struct mmu_gather *tlb) -{ - struct mmu_gather_batch *batch; - - if (!tlb->need_flush) - return; - tlb->need_flush = 0; - tlb_flush(tlb); -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb_table_flush(tlb); -#endif - - for (batch = &tlb->local; batch; batch = batch->next) { - free_pages_and_swap_cache(batch->pages, batch->nr); - batch->nr = 0; - } - tlb->active = &tlb->local; -} - -/* tlb_finish_mmu - * Called at the end of the shootdown operation to free up any resources - * that were required. - */ -void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) -{ - struct mmu_gather_batch *batch, *next; - - tlb->start = start; - tlb->end = end; - tlb_flush_mmu(tlb); - - /* keep the page table cache within bounds */ - check_pgt_cache(); - - for (batch = tlb->local.next; batch; batch = next) { - next = batch->next; - free_pages((unsigned long)batch, 0); - } - tlb->local.next = NULL; -} - -/* __tlb_remove_page - * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while - * handling the additional races in SMP caused by other CPUs caching valid - * mappings in their TLBs. Returns the number of free page slots left. - * When out of page slots we must call tlb_flush_mmu(). - */ -int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - struct mmu_gather_batch *batch; - - VM_BUG_ON(!tlb->need_flush); - - batch = tlb->active; - batch->pages[batch->nr++] = page; - if (batch->nr == batch->max) { - if (!tlb_next_batch(tlb)) - return 0; - batch = tlb->active; - } - VM_BUG_ON(batch->nr > batch->max); - - return batch->max - batch->nr; -} - -#endif /* HAVE_GENERIC_MMU_GATHER */ - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - -/* - * See the comment near struct mmu_table_batch. - */ -static void tlb_remove_table_smp_sync(void *arg) -{ - /* Simply deliver the interrupt */ -} +subsys_initcall(init_mm_sysctl); -static void tlb_remove_table_one(void *table) +#ifndef arch_wants_old_prefaulted_pte +static inline bool arch_wants_old_prefaulted_pte(void) { /* - * This isn't an RCU grace period and hence the page-tables cannot be - * assumed to be actually RCU-freed. - * - * It is however sufficient for software page-table walkers that rely on - * IRQ disabling. See the comment near struct mmu_table_batch. + * Transitioning a PTE from 'old' to 'young' can be expensive on + * some architectures, even if it's performed in hardware. By + * default, "false" means prefaulted entries will be 'young'. */ - smp_call_function(tlb_remove_table_smp_sync, NULL, 1); - __tlb_remove_table(table); -} - -static void tlb_remove_table_rcu(struct rcu_head *head) -{ - struct mmu_table_batch *batch; - int i; - - batch = container_of(head, struct mmu_table_batch, rcu); - - for (i = 0; i < batch->nr; i++) - __tlb_remove_table(batch->tables[i]); - - free_page((unsigned long)batch); + return false; } +#endif -void tlb_table_flush(struct mmu_gather *tlb) +static int __init disable_randmaps(char *s) { - struct mmu_table_batch **batch = &tlb->batch; - - if (*batch) { - call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); - *batch = NULL; - } + randomize_va_space = 0; + return 1; } +__setup("norandmaps", disable_randmaps); -void tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - struct mmu_table_batch **batch = &tlb->batch; - - tlb->need_flush = 1; - - /* - * When there's less then two users of this mm there cannot be a - * concurrent page-table walk. - */ - if (atomic_read(&tlb->mm->mm_users) < 2) { - __tlb_remove_table(table); - return; - } - - if (*batch == NULL) { - *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); - if (*batch == NULL) { - tlb_remove_table_one(table); - return; - } - (*batch)->nr = 0; - } - (*batch)->tables[(*batch)->nr++] = table; - if ((*batch)->nr == MAX_TABLE_BATCH) - tlb_table_flush(tlb); -} +unsigned long zero_pfn __read_mostly; +EXPORT_SYMBOL(zero_pfn); -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ +unsigned long highest_memmap_pfn __read_mostly; /* - * If a p?d_bad entry is found while walking page tables, report - * the error, before resetting entry to p?d_none. Usually (but - * very seldom) called out from the p?d_none_or_clear_bad macros. + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ - -void pgd_clear_bad(pgd_t *pgd) -{ - pgd_ERROR(*pgd); - pgd_clear(pgd); -} - -void pud_clear_bad(pud_t *pud) +static int __init init_zero_pfn(void) { - pud_ERROR(*pud); - pud_clear(pud); + zero_pfn = page_to_pfn(ZERO_PAGE(0)); + return 0; } +early_initcall(init_zero_pfn); -void pmd_clear_bad(pmd_t *pmd) +void mm_trace_rss_stat(struct mm_struct *mm, int member) { - pmd_ERROR(*pmd); - pmd_clear(pmd); + trace_rss_stat(mm, member); } /* @@ -407,7 +192,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); - tlb->mm->nr_ptes--; + mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, @@ -441,9 +226,10 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } -static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +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) { @@ -452,7 +238,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long start; start = addr; - pud = pud_offset(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) @@ -460,6 +246,40 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, 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; @@ -471,15 +291,22 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, if (end - 1 > ceiling - 1) return; - pud = pud_offset(pgd, start); + p4d = p4d_offset(pgd, start); pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); + p4d_free_tlb(tlb, p4d, start); } -/* - * This function frees user-level page tables of a process. +/** + * free_pgd_range - Unmap and free page tables in the range + * @tlb: the mmu_gather containing pending TLB flush info + * @addr: virtual address start + * @end: virtual address end + * @floor: lowest address boundary + * @ceiling: highest address boundary * - * Must be called with pagetable lock held. + * This function tears down all user-level page tables in the + * specified virtual address range [@addr..@end). It is part of + * the memory unmap flow. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -529,104 +356,122 @@ void free_pgd_range(struct mmu_gather *tlb, 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_change_page_size(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_pud_range(tlb, pgd, addr, next, floor, ceiling); + 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) +void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, + struct vm_area_struct *vma, unsigned long floor, + unsigned long ceiling, bool mm_wr_locked) { - while (vma) { - struct vm_area_struct *next = vma->vm_next; + struct unlink_vma_file_batch vb; + + tlb_free_vmas(tlb); + + do { unsigned long addr = vma->vm_start; + struct vm_area_struct *next; + + /* + * Note: USER_PGTABLES_CEILING may be passed as ceiling and may + * be 0. This will underflow and is okay. + */ + next = mas_find(mas, ceiling - 1); + if (unlikely(xa_is_zero(next))) + next = NULL; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ + if (mm_wr_locked) + vma_start_write(vma); 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); + unlink_file_vma_batch_init(&vb); + unlink_file_vma_batch_add(&vb, vma); + + /* + * Optimization: gather nearby vmas into one call down + */ + while (next && next->vm_start <= vma->vm_end + PMD_SIZE) { + vma = next; + next = mas_find(mas, ceiling - 1); + if (unlikely(xa_is_zero(next))) + next = NULL; + if (mm_wr_locked) + vma_start_write(vma); + unlink_anon_vmas(vma); + unlink_file_vma_batch_add(&vb, vma); } + unlink_file_vma_batch_final(&vb); + + free_pgd_range(tlb, addr, vma->vm_end, + floor, next ? next->vm_start : ceiling); vma = next; + } while (vma); +} + +void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) +{ + spinlock_t *ptl = pmd_lock(mm, pmd); + + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + mm_inc_nr_ptes(mm); + /* + * 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_rmb() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + pmd_populate(mm, pmd, *pte); + *pte = NULL; } + spin_unlock(ptl); } -int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, - pmd_t *pmd, unsigned long address) +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { - pgtable_t new = pte_alloc_one(mm, address); - int wait_split_huge_page; + 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 */ - - spin_lock(&mm->page_table_lock); - wait_split_huge_page = 0; - if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ - mm->nr_ptes++; - pmd_populate(mm, pmd, new); - new = NULL; - } else if (unlikely(pmd_trans_splitting(*pmd))) - wait_split_huge_page = 1; - spin_unlock(&mm->page_table_lock); + pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); - if (wait_split_huge_page) - wait_split_huge_page(vma->anon_vma, pmd); return 0; } -int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) +int __pte_alloc_kernel(pmd_t *pmd) { - pte_t *new = pte_alloc_one_kernel(&init_mm, address); + 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 ? */ + smp_wmb(); /* See comment in pmd_install() */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; - } else - VM_BUG_ON(pmd_trans_splitting(*pmd)); + } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); @@ -642,28 +487,13 @@ 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) +static bool is_bad_page_map_ratelimited(void) { - pgd_t *pgd = pgd_offset(vma->vm_mm, addr); - pud_t *pud = pud_offset(pgd, addr); - pmd_t *pmd = pmd_offset(pud, addr); - struct address_space *mapping; - pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; @@ -675,60 +505,146 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; - return; + return true; } if (nr_unshown) { - printk(KERN_ALERT - "BUG: Bad page map: %lu messages suppressed\n", - 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; + return false; +} - mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; - index = linear_page_index(vma, addr); +static void __print_bad_page_map_pgtable(struct mm_struct *mm, unsigned long addr) +{ + unsigned long long pgdv, p4dv, pudv, pmdv; + p4d_t p4d, *p4dp; + pud_t pud, *pudp; + pmd_t pmd, *pmdp; + pgd_t *pgdp; - printk(KERN_ALERT - "BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", - current->comm, - (long long)pte_val(pte), (long long)pmd_val(*pmd)); - if (page) - dump_page(page); - printk(KERN_ALERT - "addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", - (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); /* - * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y + * Although this looks like a fully lockless pgtable walk, it is not: + * see locking requirements for print_bad_page_map(). */ - if (vma->vm_ops) - printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n", - vma->vm_ops->fault); - if (vma->vm_file && vma->vm_file->f_op) - printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n", - vma->vm_file->f_op->mmap); - dump_stack(); - add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); + pgdp = pgd_offset(mm, addr); + pgdv = pgd_val(*pgdp); + + if (!pgd_present(*pgdp) || pgd_leaf(*pgdp)) { + pr_alert("pgd:%08llx\n", pgdv); + return; + } + + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + p4dv = p4d_val(p4d); + + if (!p4d_present(p4d) || p4d_leaf(p4d)) { + pr_alert("pgd:%08llx p4d:%08llx\n", pgdv, p4dv); + return; + } + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + pudv = pud_val(pud); + + if (!pud_present(pud) || pud_leaf(pud)) { + pr_alert("pgd:%08llx p4d:%08llx pud:%08llx\n", pgdv, p4dv, pudv); + return; + } + + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + pmdv = pmd_val(pmd); + + /* + * Dumping the PTE would be nice, but it's tricky with CONFIG_HIGHPTE, + * because the table should already be mapped by the caller and + * doing another map would be bad. print_bad_page_map() should + * already take care of printing the PTE. + */ + pr_alert("pgd:%08llx p4d:%08llx pud:%08llx pmd:%08llx\n", pgdv, + p4dv, pudv, pmdv); } -static inline bool is_cow_mapping(vm_flags_t flags) +/* + * This function is called to print an error when a bad page table entry (e.g., + * corrupted page table entry) 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. + * + * This function must be called during a proper page table walk, as it will + * re-walk the page table to dump information: the caller MUST prevent page + * table teardown (by holding mmap, vma or rmap lock) and MUST hold the leaf + * page table lock. + */ +static void print_bad_page_map(struct vm_area_struct *vma, + unsigned long addr, unsigned long long entry, struct page *page, + enum pgtable_level level) { - return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; + struct address_space *mapping; + pgoff_t index; + + if (is_bad_page_map_ratelimited()) + return; + + 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 %s:%08llx", current->comm, + pgtable_level_to_str(level), entry); + __print_bad_page_map_pgtable(vma->vm_mm, addr); + if (page) + dump_page(page, "bad page map"); + pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", + (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); + pr_alert("file:%pD fault:%ps mmap:%ps mmap_prepare: %ps read_folio:%ps\n", + vma->vm_file, + vma->vm_ops ? vma->vm_ops->fault : NULL, + vma->vm_file ? vma->vm_file->f_op->mmap : NULL, + vma->vm_file ? vma->vm_file->f_op->mmap_prepare : NULL, + mapping ? mapping->a_ops->read_folio : NULL); + dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +#define print_bad_pte(vma, addr, pte, page) \ + print_bad_page_map(vma, addr, pte_val(pte), page, PGTABLE_LEVEL_PTE) -/* - * vm_normal_page -- This function gets the "struct page" associated with a pte. +/** + * __vm_normal_page() - Get the "struct page" associated with a page table entry. + * @vma: The VMA mapping the page table entry. + * @addr: The address where the page table entry is mapped. + * @pfn: The PFN stored in the page table entry. + * @special: Whether the page table entry is marked "special". + * @level: The page table level for error reporting purposes only. + * @entry: The page table entry value for error reporting purposes only. * * "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. + * case, NULL is returned here. "Normal" mappings do have a struct page and + * are ordinarily refcounted. + * + * Page mappings of the shared zero folios are always considered "special", as + * they are not ordinarily refcounted: neither the refcount nor the mapcount + * of these folios is adjusted when mapping them into user page tables. + * Selected page table walkers (such as GUP) can still identify mappings of the + * shared zero folios and work with the underlying "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. + * There are 2 broad cases. Firstly, an architecture may define a "special" + * page table entry bit, such as pte_special(), in which case this function is + * trivial. Secondly, an architecture may not have a spare page table + * entry bit, which requires a more complicated scheme, described below. + * + * With CONFIG_FIND_NORMAL_PAGE, we might have the "special" bit set on + * page table entries that actually map "normal" pages: however, that page + * cannot be looked up through the PFN stored in the page table entry, but + * instead will be looked up through vm_ops->find_normal_page(). So far, this + * only applies to PTEs. * * 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"). @@ -753,179 +669,598 @@ static inline bool is_cow_mapping(vm_flags_t flags) * * 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. + * page (that is, those where pfn_valid is true, except the shared zero + * folios) 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. * + * Return: Returns the "struct page" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. */ -#ifdef __HAVE_ARCH_PTE_SPECIAL -# define HAVE_PTE_SPECIAL 1 -#else -# define HAVE_PTE_SPECIAL 0 -#endif -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte) +static inline struct page *__vm_normal_page(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, bool special, + unsigned long long entry, enum pgtable_level level) { - unsigned long pfn = pte_pfn(pte); + if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { + if (unlikely(special)) { +#ifdef CONFIG_FIND_NORMAL_PAGE + if (vma->vm_ops && vma->vm_ops->find_normal_page) + return vma->vm_ops->find_normal_page(vma, addr); +#endif /* CONFIG_FIND_NORMAL_PAGE */ + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return NULL; + if (is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)) + return NULL; - if (HAVE_PTE_SPECIAL) { - if (likely(!pte_special(pte))) - goto check_pfn; - if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + print_bad_page_map(vma, addr, entry, NULL, level); return NULL; - if (!is_zero_pfn(pfn)) - print_bad_pte(vma, addr, pte, NULL); - return NULL; - } - - /* !HAVE_PTE_SPECIAL case follows: */ + } + /* + * With CONFIG_ARCH_HAS_PTE_SPECIAL, any special page table + * mappings (incl. shared zero folios) are marked accordingly. + */ + } else { + if (unlikely(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + /* If it has a "struct page", it's "normal". */ + if (!pfn_valid(pfn)) + return NULL; + } else { + unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT; - 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; + /* Only CoW'ed anon folios are "normal". */ + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } } + + if (is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)) + return NULL; } - if (is_zero_pfn(pfn)) - return NULL; -check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { - print_bad_pte(vma, addr, pte, NULL); + /* Corrupted page table entry. */ + print_bad_page_map(vma, addr, entry, NULL, level); return NULL; } - /* * NOTE! We still have PageReserved() pages in the page tables. - * eg. VDSO mappings can cause them to exist. + * For example, VDSO mappings can cause them to exist. */ -out: + VM_WARN_ON_ONCE(is_zero_pfn(pfn) || is_huge_zero_pfn(pfn)); return pfn_to_page(pfn); } +/** + * vm_normal_page() - Get the "struct page" associated with a PTE + * @vma: The VMA mapping the @pte. + * @addr: The address where the @pte is mapped. + * @pte: The PTE. + * + * Get the "struct page" associated with a PTE. See __vm_normal_page() + * for details on "normal" and "special" mappings. + * + * Return: Returns the "struct page" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. + */ +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + return __vm_normal_page(vma, addr, pte_pfn(pte), pte_special(pte), + pte_val(pte), PGTABLE_LEVEL_PTE); +} + +/** + * vm_normal_folio() - Get the "struct folio" associated with a PTE + * @vma: The VMA mapping the @pte. + * @addr: The address where the @pte is mapped. + * @pte: The PTE. + * + * Get the "struct folio" associated with a PTE. See __vm_normal_page() + * for details on "normal" and "special" mappings. + * + * Return: Returns the "struct folio" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. + */ +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + struct page *page = vm_normal_page(vma, addr, pte); + + if (page) + return page_folio(page); + return NULL; +} + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES +/** + * vm_normal_page_pmd() - Get the "struct page" associated with a PMD + * @vma: The VMA mapping the @pmd. + * @addr: The address where the @pmd is mapped. + * @pmd: The PMD. + * + * Get the "struct page" associated with a PTE. See __vm_normal_page() + * for details on "normal" and "special" mappings. + * + * Return: Returns the "struct page" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. + */ +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + return __vm_normal_page(vma, addr, pmd_pfn(pmd), pmd_special(pmd), + pmd_val(pmd), PGTABLE_LEVEL_PMD); +} + +/** + * vm_normal_folio_pmd() - Get the "struct folio" associated with a PMD + * @vma: The VMA mapping the @pmd. + * @addr: The address where the @pmd is mapped. + * @pmd: The PMD. + * + * Get the "struct folio" associated with a PTE. See __vm_normal_page() + * for details on "normal" and "special" mappings. + * + * Return: Returns the "struct folio" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. + */ +struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd) +{ + struct page *page = vm_normal_page_pmd(vma, addr, pmd); + + if (page) + return page_folio(page); + return NULL; +} + +/** + * vm_normal_page_pud() - Get the "struct page" associated with a PUD + * @vma: The VMA mapping the @pud. + * @addr: The address where the @pud is mapped. + * @pud: The PUD. + * + * Get the "struct page" associated with a PUD. See __vm_normal_page() + * for details on "normal" and "special" mappings. + * + * Return: Returns the "struct page" if this is a "normal" mapping. Returns + * NULL if this is a "special" mapping. + */ +struct page *vm_normal_page_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t pud) +{ + return __vm_normal_page(vma, addr, pud_pfn(pud), pud_special(pud), + pud_val(pud), PGTABLE_LEVEL_PUD); +} +#endif + +/** + * restore_exclusive_pte - Restore a device-exclusive entry + * @vma: VMA covering @address + * @folio: the mapped folio + * @page: the mapped folio page + * @address: the virtual address + * @ptep: pte pointer into the locked page table mapping the folio page + * @orig_pte: pte value at @ptep + * + * Restore a device-exclusive non-swap entry to an ordinary present pte. + * + * The folio and the page table must be locked, and MMU notifiers must have + * been called to invalidate any (exclusive) device mappings. + * + * Locking the folio makes sure that anybody who just converted the pte to + * a device-exclusive entry can map it into the device to make forward + * progress without others converting it back until the folio was unlocked. + * + * If the folio lock ever becomes an issue, we can stop relying on the folio + * lock; it might make some scenarios with heavy thrashing less likely to + * make forward progress, but these scenarios might not be valid use cases. + * + * Note that the folio lock does not protect against all cases of concurrent + * page table modifications (e.g., MADV_DONTNEED, mprotect), so device drivers + * must use MMU notifiers to sync against any concurrent changes. + */ +static void restore_exclusive_pte(struct vm_area_struct *vma, + struct folio *folio, struct page *page, unsigned long address, + pte_t *ptep, pte_t orig_pte) +{ + pte_t pte; + + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + + pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(orig_pte)) + pte = pte_mksoft_dirty(pte); + + if (pte_swp_uffd_wp(orig_pte)) + pte = pte_mkuffd_wp(pte); + + if ((vma->vm_flags & VM_WRITE) && + can_change_pte_writable(vma, address, pte)) { + if (folio_test_dirty(folio)) + pte = pte_mkdirty(pte); + pte = pte_mkwrite(pte, vma); + } + set_pte_at(vma->vm_mm, address, ptep, pte); + + /* + * No need to invalidate - it was non-present before. However + * secondary CPUs may have mappings that need invalidating. + */ + update_mmu_cache(vma, address, ptep); +} + +/* + * Tries to restore an exclusive pte if the page lock can be acquired without + * sleeping. + */ +static int try_restore_exclusive_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, pte_t orig_pte) +{ + const softleaf_t entry = softleaf_from_pte(orig_pte); + struct page *page = softleaf_to_page(entry); + struct folio *folio = page_folio(page); + + if (folio_trylock(folio)) { + restore_exclusive_pte(vma, folio, page, addr, ptep, orig_pte); + folio_unlock(folio); + return 0; + } + + return -EBUSY; +} + /* * 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) +static unsigned long +copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, unsigned long addr, int *rss) { - unsigned long vm_flags = vma->vm_flags; - pte_t pte = *src_pte; + vm_flags_t vm_flags = dst_vma->vm_flags; + pte_t orig_pte = ptep_get(src_pte); + softleaf_t entry = softleaf_from_pte(orig_pte); + pte_t pte = orig_pte; + struct folio *folio; struct page *page; - /* pte contains position in swap or file, so copy. */ - if (unlikely(!pte_present(pte))) { - if (!pte_file(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - if (likely(!non_swap_entry(entry))) - rss[MM_SWAPENTS]++; - else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - set_pte_at(src_mm, addr, src_pte, pte); - } - } + if (likely(softleaf_is_swap(entry))) { + if (swap_duplicate(entry) < 0) + return -EIO; + + /* 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); + } + /* Mark the swap entry as shared. */ + if (pte_swp_exclusive(orig_pte)) { + pte = pte_swp_clear_exclusive(orig_pte); + set_pte_at(src_mm, addr, src_pte, pte); } - goto out_set_pte; + rss[MM_SWAPENTS]++; + } else if (softleaf_is_migration(entry)) { + folio = softleaf_to_folio(entry); + + rss[mm_counter(folio)]++; + + if (!softleaf_is_migration_read(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both parent and child + * to be set to read. A previously exclusive entry is + * now shared. + */ + entry = make_readable_migration_entry( + swp_offset(entry)); + pte = softleaf_to_pte(entry); + if (pte_swp_soft_dirty(orig_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(orig_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (softleaf_is_device_private(entry)) { + page = softleaf_to_page(entry); + folio = page_folio(page); + + /* + * 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. + */ + folio_get(folio); + rss[mm_counter(folio)]++; + /* Cannot fail as these pages cannot get pinned. */ + folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma); + + /* + * 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 (softleaf_is_device_private_write(entry) && + is_cow_mapping(vm_flags)) { + entry = make_readable_device_private_entry( + swp_offset(entry)); + pte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(orig_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (softleaf_is_device_exclusive(entry)) { + /* + * Make device exclusive entries present by restoring the + * original entry then copying as for a present pte. Device + * exclusive entries currently only support private writable + * (ie. COW) mappings. + */ + VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); + if (try_restore_exclusive_pte(src_vma, addr, src_pte, orig_pte)) + return -EBUSY; + return -ENOENT; + } else if (softleaf_is_marker(entry)) { + pte_marker marker = copy_pte_marker(entry, dst_vma); + + if (marker) + set_pte_at(dst_mm, addr, dst_pte, + make_pte_marker(marker)); + return 0; } + if (!userfaultfd_wp(dst_vma)) + pte = pte_swp_clear_uffd_wp(pte); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy a present and normal page. + * + * NOTE! The usual case is that this isn't required; + * instead, the caller can just increase the page refcount + * and re-use the pte the traditional way. + * + * And if we need a pre-allocated page but don't yet have + * one, return a negative error to let the preallocation + * code know so that it can do so outside the page table + * lock. + */ +static inline int +copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, + struct folio **prealloc, struct page *page) +{ + struct folio *new_folio; + pte_t pte; + + new_folio = *prealloc; + if (!new_folio) + return -EAGAIN; /* - * If it's a COW mapping, write protect it both - * in the parent and the child + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. */ - if (is_cow_mapping(vm_flags)) { - ptep_set_wrprotect(src_mm, addr, src_pte); + + if (copy_mc_user_highpage(&new_folio->page, page, addr, src_vma)) + return -EHWPOISON; + + *prealloc = NULL; + __folio_mark_uptodate(new_folio); + folio_add_new_anon_rmap(new_folio, dst_vma, addr, RMAP_EXCLUSIVE); + folio_add_lru_vma(new_folio, dst_vma); + rss[MM_ANONPAGES]++; + + /* All done, just insert the new page copy in the child */ + pte = folio_mk_pte(new_folio, dst_vma->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + if (userfaultfd_pte_wp(dst_vma, ptep_get(src_pte))) + /* Uffd-wp needs to be delivered to dest pte as well */ + pte = pte_mkuffd_wp(pte); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, + pte_t pte, unsigned long addr, int nr) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + + /* If it's a COW mapping, write protect it both processes. */ + if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) { + wrprotect_ptes(src_mm, addr, src_pte, nr); pte = pte_wrprotect(pte); } - /* - * If it's a shared mapping, mark it clean in - * the child - */ - if (vm_flags & VM_SHARED) + /* If it's a shared mapping, mark it clean in the child. */ + if (src_vma->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); - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; + if (!userfaultfd_wp(dst_vma)) + pte = pte_clear_uffd_wp(pte); + + set_ptes(dst_vma->vm_mm, addr, dst_pte, pte, nr); +} + +/* + * Copy one present PTE, trying to batch-process subsequent PTEs that map + * consecutive pages of the same folio by copying them as well. + * + * Returns -EAGAIN if one preallocated page is required to copy the next PTE. + * Otherwise, returns the number of copied PTEs (at least 1). + */ +static inline int +copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pte_t *dst_pte, pte_t *src_pte, pte_t pte, unsigned long addr, + int max_nr, int *rss, struct folio **prealloc) +{ + fpb_t flags = FPB_MERGE_WRITE; + struct page *page; + struct folio *folio; + int err, nr; + + page = vm_normal_page(src_vma, addr, pte); + if (unlikely(!page)) + goto copy_pte; + + folio = page_folio(page); + + /* + * If we likely have to copy, just don't bother with batching. Make + * sure that the common "small folio" case is as fast as possible + * by keeping the batching logic separate. + */ + if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) { + if (!(src_vma->vm_flags & VM_SHARED)) + flags |= FPB_RESPECT_DIRTY; + if (vma_soft_dirty_enabled(src_vma)) + flags |= FPB_RESPECT_SOFT_DIRTY; + + nr = folio_pte_batch_flags(folio, src_vma, src_pte, &pte, max_nr, flags); + folio_ref_add(folio, nr); + if (folio_test_anon(folio)) { + if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, + nr, dst_vma, src_vma))) { + folio_ref_sub(folio, nr); + return -EAGAIN; + } + rss[MM_ANONPAGES] += nr; + VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); + } else { + folio_dup_file_rmap_ptes(folio, page, nr, dst_vma); + rss[mm_counter_file(folio)] += nr; + } + __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, + addr, nr); + return nr; } -out_set_pte: - set_pte_at(dst_mm, addr, dst_pte, pte); - return 0; + folio_get(folio); + if (folio_test_anon(folio)) { + /* + * If this page may have been pinned by the parent process, + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future. + */ + if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, dst_vma, src_vma))) { + /* Page may be pinned, we have to copy. */ + folio_put(folio); + err = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, page); + return err ? err : 1; + } + rss[MM_ANONPAGES]++; + VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio); + } else { + folio_dup_file_rmap_pte(folio, page, dst_vma); + rss[mm_counter_file(folio)]++; + } + +copy_pte: + __copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte, addr, 1); + return 1; +} + +static inline struct folio *folio_prealloc(struct mm_struct *src_mm, + struct vm_area_struct *vma, unsigned long addr, bool need_zero) +{ + struct folio *new_folio; + + if (need_zero) + new_folio = vma_alloc_zeroed_movable_folio(vma, addr); + else + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); + + if (!new_folio) + return NULL; + + if (mem_cgroup_charge(new_folio, src_mm, GFP_KERNEL)) { + folio_put(new_folio); + return NULL; + } + folio_throttle_swaprate(new_folio, GFP_KERNEL); + + return new_folio; } -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) +static int +copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; + pmd_t dummy_pmdval; + pte_t ptent; spinlock_t *src_ptl, *dst_ptl; - int progress = 0; + int progress, max_nr, ret = 0; int rss[NR_MM_COUNTERS]; - swp_entry_t entry = (swp_entry_t){0}; + softleaf_t entry = softleaf_mk_none(); + struct folio *prealloc = NULL; + int nr; again: + progress = 0; init_rss_vec(rss); + /* + * copy_pmd_range()'s prior pmd_none_or_clear_bad(src_pmd), and the + * error handling here, assume that exclusive mmap_lock on dst and src + * protects anon from unexpected THP transitions; with shmem and file + * protected by mmap_lock-less collapse skipping areas with anon_vma + * (whereas vma_needs_copy() skips areas without anon_vma). A rework + * can remove such assumptions later, but this is good enough for now. + */ 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); + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } + + /* + * We already hold the exclusive mmap_lock, the copy_pte_range() and + * retract_page_tables() are using vma->anon_vma to be exclusive, so + * the PTE page is stable, and there is no need to get pmdval and do + * pmd_same() check. + */ + src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval, + &src_ptl); + if (!src_pte) { + pte_unmap_unlock(dst_pte, dst_ptl); + /* ret == 0 */ + goto out; + } spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { + nr = 1; + /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. @@ -936,38 +1271,101 @@ again: spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } - if (pte_none(*src_pte)) { + ptent = ptep_get(src_pte); + if (pte_none(ptent)) { progress++; continue; } - entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, - vma, addr, rss); - if (entry.val) + if (unlikely(!pte_present(ptent))) { + ret = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + dst_vma, src_vma, + addr, rss); + if (ret == -EIO) { + entry = softleaf_from_pte(ptep_get(src_pte)); + break; + } else if (ret == -EBUSY) { + break; + } else if (!ret) { + progress += 8; + continue; + } + ptent = ptep_get(src_pte); + VM_WARN_ON_ONCE(!pte_present(ptent)); + + /* + * Device exclusive entry restored, continue by copying + * the now present pte. + */ + WARN_ON_ONCE(ret != -ENOENT); + } + /* copy_present_ptes() will clear `*prealloc' if consumed */ + max_nr = (end - addr) / PAGE_SIZE; + ret = copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, + ptent, addr, max_nr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + * If copy failed due to hwpoison in source page, break out. + */ + if (unlikely(ret == -EAGAIN || ret == -EHWPOISON)) break; - progress += 8; - } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + if (unlikely(prealloc)) { + /* + * pre-alloc page cannot be reused by next time so as + * to strictly follow mempolicy (e.g., alloc_page_vma() + * will allocate page according to address). This + * could only happen if one pinned pte changed. + */ + folio_put(prealloc); + prealloc = NULL; + } + nr = ret; + progress += 8 * nr; + } while (dst_pte += nr, src_pte += nr, addr += PAGE_SIZE * nr, + addr != end); arch_leave_lazy_mmu_mode(); - spin_unlock(src_ptl); - pte_unmap(orig_src_pte); + pte_unmap_unlock(orig_src_pte, src_ptl); 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) + if (ret == -EIO) { + VM_WARN_ON_ONCE(!entry.val); + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { + ret = -ENOMEM; + goto out; + } + entry.val = 0; + } else if (ret == -EBUSY || unlikely(ret == -EHWPOISON)) { + goto out; + } else if (ret == -EAGAIN) { + prealloc = folio_prealloc(src_mm, src_vma, addr, false); + if (!prealloc) return -ENOMEM; - progress = 0; + } else if (ret < 0) { + VM_WARN_ON_ONCE(1); } + + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; + if (addr != end) goto again; - return 0; +out: + if (unlikely(prealloc)) + folio_put(prealloc); + return ret; } -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) +static inline int +copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pud_t *dst_pud, pud_t *src_pud, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; @@ -977,11 +1375,12 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*src_pmd)) { + if (pmd_is_huge(*src_pmd)) { int err; - VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); - err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, vma); + + VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); + err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -990,71 +1389,118 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src } if (pmd_none_or_clear_bad(src_pmd)) continue; - if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, addr, next)) + if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, + 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, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline int +copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, + unsigned long end) { + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; - dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; - src_pud = pud_offset(src_pgd, addr); + src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); + if (pud_trans_huge(*src_pud)) { + int err; + + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); + err = copy_huge_pud(dst_mm, src_mm, + dst_pud, src_pud, addr, src_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)) + if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, + addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, 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) +static inline int +copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, + pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, + unsigned long end) { - pgd_t *src_pgd, *dst_pgd; + struct mm_struct *dst_mm = dst_vma->vm_mm; + p4d_t *src_p4d, *dst_p4d; unsigned long next; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - bool is_cow; - int ret; + 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_vma, src_vma, dst_p4d, src_p4d, + addr, next)) + return -ENOMEM; + } while (dst_p4d++, src_p4d++, addr = next, addr != end); + return 0; +} + +/* + * Return true if the vma needs to copy the pgtable during this fork(). Return + * false when we can speed up fork() by allowing lazy page faults later until + * when the child accesses the memory range. + */ +static bool +vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + if (src_vma->vm_flags & VM_COPY_ON_FORK) + return true; /* - * 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. + * The presence of an anon_vma indicates an anonymous VMA has page + * tables which naturally cannot be reconstituted on page fault. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | - VM_PFNMAP | VM_MIXEDMAP))) { - if (!vma->anon_vma) - return 0; - } + if (src_vma->anon_vma) + return true; - if (is_vm_hugetlb_page(vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, vma); + /* + * 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. + */ + return false; +} - 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; - } +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + pgd_t *src_pgd, *dst_pgd; + unsigned long addr = src_vma->vm_start; + unsigned long end = src_vma->vm_end; + struct mm_struct *dst_mm = dst_vma->vm_mm; + struct mm_struct *src_mm = src_vma->vm_mm; + struct mmu_notifier_range range; + unsigned long next; + bool is_cow; + int ret; + + if (!vma_needs_copy(dst_vma, src_vma)) + return 0; + + if (is_vm_hugetlb_page(src_vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); /* * We need to invalidate the secondary MMU mappings only when @@ -1062,12 +1508,22 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ - is_cow = is_cow_mapping(vma->vm_flags); - mmun_start = addr; - mmun_end = end; - if (is_cow) - mmu_notifier_invalidate_range_start(src_mm, mmun_start, - mmun_end); + is_cow = is_cow_mapping(src_vma->vm_flags); + + if (is_cow) { + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, + 0, src_mm, addr, end); + mmu_notifier_invalidate_range_start(&range); + /* + * Disabling preemption is not needed for the write side, as + * the read side doesn't spin, but goes to the mmap_lock. + * + * Use the raw variant of the seqcount_t write API to avoid + * lockdep complaining about preemptibility. + */ + vma_assert_write_locked(src_vma); + raw_write_seqcount_begin(&src_mm->write_protect_seq); + } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); @@ -1076,143 +1532,378 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; - if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next))) { + if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, + addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); - if (is_cow) - mmu_notifier_invalidate_range_end(src_mm, mmun_start, mmun_end); + if (is_cow) { + raw_write_seqcount_end(&src_mm->write_protect_seq); + mmu_notifier_invalidate_range_end(&range); + } return ret; } +/* Whether we should zap all COWed (private) pages too */ +static inline bool should_zap_cows(struct zap_details *details) +{ + /* By default, zap all pages */ + if (!details || details->reclaim_pt) + return true; + + /* Or, we zap COWed pages only if the caller wants to */ + return details->even_cows; +} + +/* Decides whether we should zap this folio with the folio pointer specified */ +static inline bool should_zap_folio(struct zap_details *details, + struct folio *folio) +{ + /* If we can make a decision without *folio.. */ + if (should_zap_cows(details)) + return true; + + /* Otherwise we should only zap non-anon folios */ + return !folio_test_anon(folio); +} + +static inline bool zap_drop_markers(struct zap_details *details) +{ + if (!details) + return false; + + return details->zap_flags & ZAP_FLAG_DROP_MARKER; +} + +/* + * This function makes sure that we'll replace the none pte with an uffd-wp + * swap special pte marker when necessary. Must be with the pgtable lock held. + * + * Returns true if uffd-wp ptes was installed, false otherwise. + */ +static inline bool +zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte, int nr, + struct zap_details *details, pte_t pteval) +{ + bool was_installed = false; + + if (!uffd_supports_wp_marker()) + return false; + + /* Zap on anonymous always means dropping everything */ + if (vma_is_anonymous(vma)) + return false; + + if (zap_drop_markers(details)) + return false; + + for (;;) { + /* the PFN in the PTE is irrelevant. */ + if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval)) + was_installed = true; + if (--nr == 0) + break; + pte++; + addr += PAGE_SIZE; + } + + return was_installed; +} + +static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, + struct vm_area_struct *vma, struct folio *folio, + struct page *page, pte_t *pte, pte_t ptent, unsigned int nr, + unsigned long addr, struct zap_details *details, int *rss, + bool *force_flush, bool *force_break, bool *any_skipped) +{ + struct mm_struct *mm = tlb->mm; + bool delay_rmap = false; + + if (!folio_test_anon(folio)) { + ptent = get_and_clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); + if (pte_dirty(ptent)) { + folio_mark_dirty(folio); + if (tlb_delay_rmap(tlb)) { + delay_rmap = true; + *force_flush = true; + } + } + if (pte_young(ptent) && likely(vma_has_recency(vma))) + folio_mark_accessed(folio); + rss[mm_counter(folio)] -= nr; + } else { + /* We don't need up-to-date accessed/dirty bits. */ + clear_full_ptes(mm, addr, pte, nr, tlb->fullmm); + rss[MM_ANONPAGES] -= nr; + } + /* Checking a single PTE in a batch is sufficient. */ + arch_check_zapped_pte(vma, ptent); + tlb_remove_tlb_entries(tlb, pte, nr, addr); + if (unlikely(userfaultfd_pte_wp(vma, ptent))) + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, + nr, details, ptent); + + if (!delay_rmap) { + folio_remove_rmap_ptes(folio, page, nr, vma); + + if (unlikely(folio_mapcount(folio) < 0)) + print_bad_pte(vma, addr, ptent, page); + } + if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { + *force_flush = true; + *force_break = true; + } +} + +/* + * Zap or skip at least one present PTE, trying to batch-process subsequent + * PTEs that map consecutive pages of the same folio. + * + * Returns the number of processed (skipped or zapped) PTEs (at least 1). + */ +static inline int zap_present_ptes(struct mmu_gather *tlb, + struct vm_area_struct *vma, pte_t *pte, pte_t ptent, + unsigned int max_nr, unsigned long addr, + struct zap_details *details, int *rss, bool *force_flush, + bool *force_break, bool *any_skipped) +{ + struct mm_struct *mm = tlb->mm; + struct folio *folio; + struct page *page; + int nr; + + page = vm_normal_page(vma, addr, ptent); + if (!page) { + /* We don't need up-to-date accessed/dirty bits. */ + ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); + arch_check_zapped_pte(vma, ptent); + tlb_remove_tlb_entry(tlb, pte, addr); + if (userfaultfd_pte_wp(vma, ptent)) + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, + pte, 1, details, ptent); + ksm_might_unmap_zero_page(mm, ptent); + return 1; + } + + folio = page_folio(page); + if (unlikely(!should_zap_folio(details, folio))) { + *any_skipped = true; + return 1; + } + + /* + * Make sure that the common "small folio" case is as fast as possible + * by keeping the batching logic separate. + */ + if (unlikely(folio_test_large(folio) && max_nr != 1)) { + nr = folio_pte_batch(folio, pte, ptent, max_nr); + zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, + addr, details, rss, force_flush, + force_break, any_skipped); + return nr; + } + zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr, + details, rss, force_flush, force_break, any_skipped); + return 1; +} + +static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, + struct vm_area_struct *vma, pte_t *pte, pte_t ptent, + unsigned int max_nr, unsigned long addr, + struct zap_details *details, int *rss, bool *any_skipped) +{ + softleaf_t entry; + int nr = 1; + + *any_skipped = true; + entry = softleaf_from_pte(ptent); + if (softleaf_is_device_private(entry) || + softleaf_is_device_exclusive(entry)) { + struct page *page = softleaf_to_page(entry); + struct folio *folio = page_folio(page); + + if (unlikely(!should_zap_folio(details, folio))) + return 1; + /* + * Both device private/exclusive mappings should only + * work with anonymous page so far, so we don't need to + * consider uffd-wp bit when zap. For more information, + * see zap_install_uffd_wp_if_needed(). + */ + WARN_ON_ONCE(!vma_is_anonymous(vma)); + rss[mm_counter(folio)]--; + folio_remove_rmap_pte(folio, page, vma); + folio_put(folio); + } else if (softleaf_is_swap(entry)) { + /* Genuine swap entries, hence a private anon pages */ + if (!should_zap_cows(details)) + return 1; + + nr = swap_pte_batch(pte, max_nr, ptent); + rss[MM_SWAPENTS] -= nr; + free_swap_and_cache_nr(entry, nr); + } else if (softleaf_is_migration(entry)) { + struct folio *folio = softleaf_to_folio(entry); + + if (!should_zap_folio(details, folio)) + return 1; + rss[mm_counter(folio)]--; + } else if (softleaf_is_uffd_wp_marker(entry)) { + /* + * For anon: always drop the marker; for file: only + * drop the marker if explicitly requested. + */ + if (!vma_is_anonymous(vma) && !zap_drop_markers(details)) + return 1; + } else if (softleaf_is_guard_marker(entry)) { + /* + * Ordinary zapping should not remove guard PTE + * markers. Only do so if we should remove PTE markers + * in general. + */ + if (!zap_drop_markers(details)) + return 1; + } else if (softleaf_is_hwpoison(entry) || + softleaf_is_poison_marker(entry)) { + if (!should_zap_cows(details)) + return 1; + } else { + /* We should have covered all the swap entry types */ + pr_alert("unrecognized swap entry 0x%lx\n", entry.val); + WARN_ON_ONCE(1); + } + clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm); + *any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); + + return nr; +} + +static inline int do_zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, unsigned long end, + struct zap_details *details, int *rss, + bool *force_flush, bool *force_break, + bool *any_skipped) +{ + pte_t ptent = ptep_get(pte); + int max_nr = (end - addr) / PAGE_SIZE; + int nr = 0; + + /* Skip all consecutive none ptes */ + if (pte_none(ptent)) { + for (nr = 1; nr < max_nr; nr++) { + ptent = ptep_get(pte + nr); + if (!pte_none(ptent)) + break; + } + max_nr -= nr; + if (!max_nr) + return nr; + pte += nr; + addr += nr * PAGE_SIZE; + } + + if (pte_present(ptent)) + nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr, + details, rss, force_flush, force_break, + any_skipped); + else + nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr, + details, rss, any_skipped); + + return nr; +} + 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) { + bool force_flush = false, force_break = false; 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; - unsigned long range_start = addr; + pmd_t pmdval; + unsigned long start = addr; + bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); + bool direct_reclaim = true; + int nr; -again: +retry: + tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); - start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); - pte = start_pte; + start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return addr; + + 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; + bool any_skipped = false; - page = vm_normal_page(vma, addr, ptent); - 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->mapping) - continue; - /* - * Each page->index must be checked when - * invalidating or truncating nonlinear. - */ - if (details->nonlinear_vma && - (page->index < details->first_index || - page->index > details->last_index)) - continue; - } - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - tlb_remove_tlb_entry(tlb, pte, addr); - if (unlikely(!page)) - continue; - if (unlikely(details) && details->nonlinear_vma - && linear_page_index(details->nonlinear_vma, - addr) != page->index) - set_pte_at(mm, addr, pte, - pgoff_to_pte(page->index)); - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else { - if (pte_dirty(ptent)) - set_page_dirty(page); - if (pte_young(ptent) && - likely(!(vma->vm_flags & VM_SEQ_READ))) - mark_page_accessed(page); - rss[MM_FILEPAGES]--; - } - page_remove_rmap(page); - if (unlikely(page_mapcount(page) < 0)) - print_bad_pte(vma, addr, ptent, page); - force_flush = !__tlb_remove_page(tlb, page); - if (force_flush) - break; - continue; + if (need_resched()) { + direct_reclaim = false; + break; } - /* - * If details->check_mapping, we leave swap entries; - * if details->nonlinear_vma, we leave file entries. - */ - if (unlikely(details)) - continue; - if (pte_file(ptent)) { - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) - print_bad_pte(vma, addr, ptent, NULL); - } else { - swp_entry_t entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) - rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; - - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; - } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, + &force_flush, &force_break, &any_skipped); + if (any_skipped) + can_reclaim_pt = false; + if (unlikely(force_break)) { + addr += nr * PAGE_SIZE; + direct_reclaim = false; + break; } - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); + + /* + * Fast path: try to hold the pmd lock and unmap the PTE page. + * + * If the pte lock was released midway (retry case), or if the attempt + * to hold the pmd lock failed, then we need to recheck all pte entries + * to ensure they are still none, thereby preventing the pte entries + * from being repopulated by another thread. + */ + if (can_reclaim_pt && direct_reclaim && addr == end) + direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); 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); + tlb_flush_rmaps(tlb, vma); + } pte_unmap_unlock(start_pte, ptl); /* - * mmu_gather ran out of room to batch pages, we break out of - * the PTE lock to avoid doing the potential expensive TLB invalidate - * and page-free while holding it. + * 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. Come back again if we didn't do everything. */ - if (force_flush) { - force_flush = 0; - -#ifdef HAVE_GENERIC_MMU_GATHER - tlb->start = range_start; - tlb->end = addr; -#endif + if (force_flush) tlb_flush_mmu(tlb); - if (addr != end) { - range_start = addr; - goto again; - } + + if (addr != end) { + cond_resched(); + force_flush = false; + force_break = false; + goto retry; + } + + if (can_reclaim_pt) { + if (direct_reclaim) + free_pte(mm, start, tlb, pmdval); + else + try_to_free_pte(mm, pmd, start, tlb); } return addr; @@ -1229,59 +1920,86 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) { -#ifdef CONFIG_DEBUG_VM - if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { - pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", - __func__, addr, end, - vma->vm_start, - vma->vm_end); - BUG(); - } -#endif - split_huge_page_pmd(vma, addr, pmd); - } else if (zap_huge_pmd(tlb, vma, pmd, addr)) - goto next; + if (pmd_is_huge(*pmd)) { + if (next - addr != HPAGE_PMD_SIZE) + __split_huge_pmd(vma, pmd, addr, false); + else if (zap_huge_pmd(tlb, vma, pmd, addr)) { + addr = next; + continue; + } /* fall through */ + } else if (details && details->single_folio && + folio_test_pmd_mappable(details->single_folio) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } - /* - * 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); + if (pmd_none(*pmd)) { + addr = next; + continue; + } + addr = zap_pte_range(tlb, vma, pmd, addr, next, details); + if (addr != next) + pmd--; + } while (pmd++, cond_resched(), addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, pgd_t *pgd, + 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(pgd, addr); + pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); + if (pud_trans_huge(*pud)) { + if (next - addr != HPAGE_PUD_SIZE) { + mmap_assert_locked(tlb->mm); + 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 void unmap_page_range(struct mmu_gather *tlb, +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) @@ -1289,28 +2007,22 @@ static void unmap_page_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; - if (details && !details->check_mapping && !details->nonlinear_vma) - details = NULL; - BUG_ON(addr >= end); - mem_cgroup_uncharge_start(); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - next = zap_pud_range(tlb, vma, pgd, addr, next, details); + next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); - mem_cgroup_uncharge_end(); } 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 end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; @@ -1324,26 +2036,24 @@ static void unmap_single_vma(struct mmu_gather *tlb, 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 do_mmap_pgoff. When + * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file + * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { - mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); - __unmap_hugepage_range_final(tlb, vma, start, end, NULL); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + zap_flags_t zap_flags = details ? + details->zap_flags : 0; + __unmap_hugepage_range(tlb, vma, start, end, + NULL, zap_flags); } } else unmap_page_range(tlb, vma, start, end, details); @@ -1353,9 +2063,11 @@ static void unmap_single_vma(struct mmu_gather *tlb, /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather + * @mas: the maple state * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping + * @tree_end: The maximum index to check * * Unmap all pages in the vma list. * @@ -1368,42 +2080,71 @@ static void unmap_single_vma(struct mmu_gather *tlb, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -void unmap_vmas(struct mmu_gather *tlb, +void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *vma, unsigned long start_addr, - unsigned long end_addr) + unsigned long end_addr, unsigned long tree_end) { - struct mm_struct *mm = vma->vm_mm; - - mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); - for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) - unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); - mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); + struct mmu_notifier_range range; + struct zap_details details = { + .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, + /* Careful - we need to zap private pages too! */ + .even_cows = true, + }; + + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma->vm_mm, + start_addr, end_addr); + mmu_notifier_invalidate_range_start(&range); + do { + unsigned long start = start_addr; + unsigned long end = end_addr; + hugetlb_zap_begin(vma, &start, &end); + unmap_single_vma(tlb, vma, start, end, &details); + hugetlb_zap_end(vma, &details); + vma = mas_find(mas, tree_end - 1); + } while (vma && likely(!xa_is_zero(vma))); + mmu_notifier_invalidate_range_end(&range); } /** - * zap_page_range - remove user pages in a given range + * zap_page_range_single_batched - remove user pages in a given range + * @tlb: pointer to the caller's struct mmu_gather * @vma: vm_area_struct holding the applicable pages - * @start: starting address of pages to zap - * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @address: starting address of pages to remove + * @size: number of bytes to remove + * @details: details of shared cache invalidation * - * Caller must protect the VMA list + * @tlb shouldn't be NULL. The range must fit into one VMA. If @vma is for + * hugetlb, @tlb is flushed and re-initialized by this function. */ -void zap_page_range(struct vm_area_struct *vma, unsigned long start, +void zap_page_range_single_batched(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { - struct mm_struct *mm = vma->vm_mm; - struct mmu_gather tlb; - unsigned long end = start + size; + const unsigned long end = address + size; + struct mmu_notifier_range range; - lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); - update_hiwater_rss(mm); - mmu_notifier_invalidate_range_start(mm, start, end); - for ( ; vma && vma->vm_start < end; vma = vma->vm_next) - unmap_single_vma(&tlb, vma, start, end, details); - mmu_notifier_invalidate_range_end(mm, start, end); - tlb_finish_mmu(&tlb, start, end); + VM_WARN_ON_ONCE(!tlb || tlb->mm != vma->vm_mm); + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, + address, end); + hugetlb_zap_begin(vma, &range.start, &range.end); + update_hiwater_rss(vma->vm_mm); + mmu_notifier_invalidate_range_start(&range); + /* + * unmap 'address-end' not 'range.start-range.end' as range + * could have been expanded for hugetlb pmd sharing. + */ + unmap_single_vma(tlb, vma, address, end, details); + mmu_notifier_invalidate_range_end(&range); + if (is_vm_hugetlb_page(vma)) { + /* + * flush tlb and free resources before hugetlb_zap_end(), to + * avoid concurrent page faults' allocation failure. + */ + tlb_finish_mmu(tlb); + hugetlb_zap_end(vma, details); + tlb_gather_mmu(tlb, vma->vm_mm); + } } /** @@ -1411,24 +2152,18 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @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, +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { - struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; - unsigned long end = address + size; - lru_add_drain(); - tlb_gather_mmu(&tlb, mm, 0); - update_hiwater_rss(mm); - mmu_notifier_invalidate_range_start(mm, address, end); - unmap_single_vma(&tlb, vma, address, end, details); - mmu_notifier_invalidate_range_end(mm, address, end); - tlb_finish_mmu(&tlb, address, end); + tlb_gather_mmu(&tlb, vma->vm_mm); + zap_page_range_single_batched(&tlb, vma, address, size, details); + tlb_finish_mmu(&tlb); } /** @@ -1441,673 +2176,263 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr * * The entire address range must be fully contained within the vma. * - * Returns 0 if successful. */ -int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, +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 || + if (!range_in_vma(vma, address, address + size) || !(vma->vm_flags & VM_PFNMAP)) - return -1; + return; + zap_page_range_single(vma, address, size, NULL); - return 0; } EXPORT_SYMBOL_GPL(zap_vma_ptes); -/** - * follow_page_mask - look up a page descriptor from a user-virtual address - * @vma: vm_area_struct mapping @address - * @address: virtual address to look up - * @flags: flags modifying lookup behaviour - * @page_mask: on output, *page_mask is set according to the size of the page - * - * @flags can have FOLL_ flags set, defined in <linux/mm.h> - * - * Returns the mapped (struct page *), %NULL if no mapping exists, or - * an error pointer if there is a mapping to something not represented - * by a page descriptor (see also vm_normal_page()). - */ -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) +static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - struct page *page; - struct mm_struct *mm = vma->vm_mm; - - *page_mask = 0; - - page = follow_huge_addr(mm, address, flags & FOLL_WRITE); - if (!IS_ERR(page)) { - BUG_ON(flags & FOLL_GET); - goto out; - } - - page = NULL; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto no_page_table; - - pud = pud_offset(pgd, address); - if (pud_none(*pud)) - goto no_page_table; - if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - goto out; - } - if (unlikely(pud_bad(*pud))) - goto no_page_table; - - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd)) - goto no_page_table; - if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - BUG_ON(flags & FOLL_GET); - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - goto out; - } - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) - goto no_page_table; - if (pmd_trans_huge(*pmd)) { - if (flags & FOLL_SPLIT) { - split_huge_page_pmd(vma, address, pmd); - goto split_fallthrough; - } - spin_lock(&mm->page_table_lock); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&mm->page_table_lock); - wait_split_huge_page(vma->anon_vma, pmd); - } else { - page = follow_trans_huge_pmd(vma, address, - pmd, flags); - spin_unlock(&mm->page_table_lock); - *page_mask = HPAGE_PMD_NR - 1; - goto out; - } - } else - spin_unlock(&mm->page_table_lock); - /* fall through */ - } -split_fallthrough: - if (unlikely(pmd_bad(*pmd))) - goto no_page_table; - - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - - pte = *ptep; - if (!pte_present(pte)) { - swp_entry_t entry; - /* - * KSM's break_ksm() relies upon recognizing a ksm page - * even while it is being migrated, so for that case we - * need migration_entry_wait(). - */ - if (likely(!(flags & FOLL_MIGRATION))) - goto no_page; - if (pte_none(pte) || pte_file(pte)) - goto no_page; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) - goto no_page; - pte_unmap_unlock(ptep, ptl); - migration_entry_wait(mm, pmd, address); - goto split_fallthrough; - } - if ((flags & FOLL_NUMA) && pte_numa(pte)) - goto no_page; - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - - page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) { - if ((flags & FOLL_DUMP) || - !is_zero_pfn(pte_pfn(pte))) - goto bad_page; - page = pte_page(pte); - } - - if (flags & FOLL_GET) - get_page_foll(page); - if (flags & FOLL_TOUCH) { - if ((flags & FOLL_WRITE) && - !pte_dirty(pte) && !PageDirty(page)) - set_page_dirty(page); - /* - * pte_mkyoung() would be more correct here, but atomic care - * is needed to avoid losing the dirty bit: it is easier to use - * mark_page_accessed(). - */ - mark_page_accessed(page); - } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - /* - * The preliminary mapping check is mainly to avoid the - * pointless overhead of lock_page on the ZERO_PAGE - * which might bounce very badly if there is contention. - * - * If the page is already locked, we don't need to - * handle it now - vmscan will handle it later if and - * when it attempts to reclaim the page. - */ - if (page->mapping && trylock_page(page)) { - lru_add_drain(); /* push cached pages to LRU */ - /* - * Because we lock page here, and migration is - * blocked by the pte's page reference, and we - * know the page is still mapped, we don't even - * need to check for file-cache page truncation. - */ - mlock_vma_page(page); - unlock_page(page); - } - } -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return page; - -bad_page: - pte_unmap_unlock(ptep, ptl); - return ERR_PTR(-EFAULT); -no_page: - pte_unmap_unlock(ptep, ptl); - if (!pte_none(pte)) - return page; + 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; -no_page_table: - /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or - * page tables. Return error instead of NULL to skip handle_mm_fault, - * then get_dump_page() will return NULL to leave a hole in the dump. - * But we can only make this optimization where a hole would surely - * be zero-filled if handle_mm_fault() actually did handle it. - */ - if ((flags & FOLL_DUMP) && - (!vma->vm_ops || !vma->vm_ops->fault)) - return ERR_PTR(-EFAULT); - return page; + VM_BUG_ON(pmd_trans_huge(*pmd)); + return pmd; } -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) +pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) { - return stack_guard_page_start(vma, addr) || - stack_guard_page_end(vma, addr+PAGE_SIZE); + pmd_t *pmd = walk_to_pmd(mm, addr); + + if (!pmd) + return NULL; + return pte_alloc_map_lock(mm, pmd, addr, ptl); } -/** - * __get_user_pages() - pin user pages in memory - * @tsk: task_struct of target task - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @gup_flags: flags modifying pin behaviour - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * @nonblocking: whether waiting for disk IO or mmap_sem contention - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * __get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * __get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If - * the page is written to, set_page_dirty (or set_page_dirty_lock, as - * appropriate) must be called after the page is finished with, and - * before put_page is called. - * - * If @nonblocking != NULL, __get_user_pages will not wait for disk IO - * or mmap_sem contention, and if waiting is needed to pin all pages, - * *@nonblocking will be set to 0. - * - * In most cases, get_user_pages or get_user_pages_fast should be used - * instead of __get_user_pages. __get_user_pages should be used only if - * you need some special @gup_flags. - */ -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas, int *nonblocking) +static bool vm_mixed_zeropage_allowed(struct vm_area_struct *vma) { - long i; - unsigned long vm_flags; - unsigned int page_mask; - - if (!nr_pages) - return 0; - - VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET)); - - /* - * Require read or write permissions. - * If FOLL_FORCE is set, we only require the "MAY" flags. + VM_WARN_ON_ONCE(vma->vm_flags & VM_PFNMAP); + /* + * Whoever wants to forbid the zeropage after some zeropages + * might already have been mapped has to scan the page tables and + * bail out on any zeropages. Zeropages in COW mappings can + * be unshared using FAULT_FLAG_UNSHARE faults. */ - vm_flags = (gup_flags & FOLL_WRITE) ? - (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - vm_flags &= (gup_flags & FOLL_FORCE) ? - (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); - + if (mm_forbids_zeropage(vma->vm_mm)) + return false; + /* zeropages in COW mappings are common and unproblematic. */ + if (is_cow_mapping(vma->vm_flags)) + return true; + /* Mappings that do not allow for writable PTEs are unproblematic. */ + if (!(vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) + return true; /* - * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault - * would be called on PROT_NONE ranges. We must never invoke - * handle_mm_fault on PROT_NONE ranges or the NUMA hinting - * page faults would unprotect the PROT_NONE ranges if - * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd - * bitflag. So to avoid that, don't set FOLL_NUMA if - * FOLL_FORCE is set. + * Why not allow any VMA that has vm_ops->pfn_mkwrite? GUP could + * find the shared zeropage and longterm-pin it, which would + * be problematic as soon as the zeropage gets replaced by a different + * page due to vma->vm_ops->pfn_mkwrite, because what's mapped would + * now differ to what GUP looked up. FSDAX is incompatible to + * FOLL_LONGTERM and VM_IO is incompatible to GUP completely (see + * check_vma_flags). */ - if (!(gup_flags & FOLL_FORCE)) - gup_flags |= FOLL_NUMA; - - i = 0; - - do { - struct vm_area_struct *vma; - - vma = find_extend_vma(mm, start); - if (!vma && in_gate_area(mm, start)) { - unsigned long pg = start & PAGE_MASK; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - /* user gate pages are read-only */ - if (gup_flags & FOLL_WRITE) - return i ? : -EFAULT; - if (pg > TASK_SIZE) - pgd = pgd_offset_k(pg); - else - pgd = pgd_offset_gate(mm, pg); - BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd, pg); - BUG_ON(pud_none(*pud)); - pmd = pmd_offset(pud, pg); - if (pmd_none(*pmd)) - return i ? : -EFAULT; - VM_BUG_ON(pmd_trans_huge(*pmd)); - pte = pte_offset_map(pmd, pg); - if (pte_none(*pte)) { - pte_unmap(pte); - return i ? : -EFAULT; - } - vma = get_gate_vma(mm); - if (pages) { - struct page *page; - - page = vm_normal_page(vma, start, *pte); - if (!page) { - if (!(gup_flags & FOLL_DUMP) && - is_zero_pfn(pte_pfn(*pte))) - page = pte_page(*pte); - else { - pte_unmap(pte); - return i ? : -EFAULT; - } - } - pages[i] = page; - get_page(page); - } - pte_unmap(pte); - page_mask = 0; - goto next_page; - } - - if (!vma || - (vma->vm_flags & (VM_IO | VM_PFNMAP)) || - !(vm_flags & vma->vm_flags)) - return i ? : -EFAULT; - - if (is_vm_hugetlb_page(vma)) { - i = follow_hugetlb_page(mm, vma, pages, vmas, - &start, &nr_pages, i, gup_flags); - continue; - } - - do { - struct page *page; - unsigned int foll_flags = gup_flags; - unsigned int page_increm; - - /* - * If we have a pending SIGKILL, don't keep faulting - * pages and potentially allocating memory. - */ - if (unlikely(fatal_signal_pending(current))) - return i ? i : -ERESTARTSYS; - - cond_resched(); - while (!(page = follow_page_mask(vma, start, - foll_flags, &page_mask))) { - int ret; - unsigned int fault_flags = 0; - - /* For mlock, just skip the stack guard page. */ - if (foll_flags & FOLL_MLOCK) { - if (stack_guard_page(vma, start)) - goto next_page; - } - if (foll_flags & FOLL_WRITE) - fault_flags |= FAULT_FLAG_WRITE; - if (nonblocking) - fault_flags |= FAULT_FLAG_ALLOW_RETRY; - if (foll_flags & FOLL_NOWAIT) - fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT); - - ret = handle_mm_fault(mm, vma, start, - fault_flags); - - if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return i ? i : -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | - VM_FAULT_HWPOISON_LARGE)) { - if (i) - return i; - else if (gup_flags & FOLL_HWPOISON) - return -EHWPOISON; - else - return -EFAULT; - } - if (ret & VM_FAULT_SIGBUS) - return i ? i : -EFAULT; - BUG(); - } - - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; - } - - if (ret & VM_FAULT_RETRY) { - if (nonblocking) - *nonblocking = 0; - return i; - } + return vma->vm_ops && vma->vm_ops->pfn_mkwrite && + (vma_is_fsdax(vma) || vma->vm_flags & VM_IO); +} - /* - * The VM_FAULT_WRITE bit tells us that - * do_wp_page has broken COW when necessary, - * even if maybe_mkwrite decided not to set - * pte_write. We can thus safely do subsequent - * page lookups as if they were reads. But only - * do so when looping for pte_write is futile: - * in some cases userspace may also be wanting - * to write to the gotten user page, which a - * read fault here might prevent (a readonly - * page might get reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && - !(vma->vm_flags & VM_WRITE)) - foll_flags &= ~FOLL_WRITE; +static int validate_page_before_insert(struct vm_area_struct *vma, + struct page *page) +{ + struct folio *folio = page_folio(page); - cond_resched(); - } - if (IS_ERR(page)) - return i ? i : PTR_ERR(page); - if (pages) { - pages[i] = page; - - flush_anon_page(vma, page, start); - flush_dcache_page(page); - page_mask = 0; - } -next_page: - if (vmas) { - vmas[i] = vma; - page_mask = 0; - } - page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); - if (page_increm > nr_pages) - page_increm = nr_pages; - i += page_increm; - start += page_increm * PAGE_SIZE; - nr_pages -= page_increm; - } while (nr_pages && start < vma->vm_end); - } while (nr_pages); - return i; -} -EXPORT_SYMBOL(__get_user_pages); + if (!folio_ref_count(folio)) + return -EINVAL; + if (unlikely(is_zero_folio(folio))) { + if (!vm_mixed_zeropage_allowed(vma)) + return -EINVAL; + return 0; + } + if (folio_test_anon(folio) || page_has_type(page)) + return -EINVAL; + flush_dcache_folio(folio); + return 0; +} -/* - * fixup_user_fault() - manually resolve a user page fault - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @address: user address - * @fault_flags:flags to pass down to handle_mm_fault() - * - * This is meant to be called in the specific scenario where for locking reasons - * we try to access user memory in atomic context (within a pagefault_disable() - * section), this returns -EFAULT, and we want to resolve the user fault before - * trying again. - * - * Typically this is meant to be used by the futex code. - * - * The main difference with get_user_pages() is that this function will - * unconditionally call handle_mm_fault() which will in turn perform all the - * necessary SW fixup of the dirty and young bits in the PTE, while - * handle_mm_fault() only guarantees to update these in the struct page. - * - * This is important for some architectures where those bits also gate the - * access permission to the page because they are maintained in software. On - * such architectures, gup() will not be enough to make a subsequent access - * succeed. - * - * This should be called with the mm_sem held for read. - */ -int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags) +static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, struct page *page, + pgprot_t prot, bool mkwrite) { - struct vm_area_struct *vma; - int ret; + struct folio *folio = page_folio(page); + pte_t pteval = ptep_get(pte); - vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) - return -EFAULT; + if (!pte_none(pteval)) { + if (!mkwrite) + return -EBUSY; - ret = handle_mm_fault(mm, vma, address, fault_flags); - if (ret & VM_FAULT_ERROR) { - if (ret & VM_FAULT_OOM) - return -ENOMEM; - if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) - return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + /* see insert_pfn(). */ + if (pte_pfn(pteval) != page_to_pfn(page)) { + WARN_ON_ONCE(!is_zero_pfn(pte_pfn(pteval))); return -EFAULT; - BUG(); + } + pteval = maybe_mkwrite(pteval, vma); + pteval = pte_mkyoung(pteval); + if (ptep_set_access_flags(vma, addr, pte, pteval, 1)) + update_mmu_cache(vma, addr, pte); + return 0; } - if (tsk) { - if (ret & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; + + /* Ok, finally just insert the thing.. */ + pteval = mk_pte(page, prot); + if (unlikely(is_zero_folio(folio))) { + pteval = pte_mkspecial(pteval); + } else { + folio_get(folio); + pteval = mk_pte(page, prot); + if (mkwrite) { + pteval = pte_mkyoung(pteval); + pteval = maybe_mkwrite(pte_mkdirty(pteval), vma); + } + inc_mm_counter(vma->vm_mm, mm_counter_file(folio)); + folio_add_file_rmap_pte(folio, page, vma); } + set_pte_at(vma->vm_mm, addr, pte, pteval); return 0; } -/* - * get_user_pages() - pin user pages in memory - * @tsk: the task_struct to use for page fault accounting, or - * NULL if faults are not to be recorded. - * @mm: mm_struct of target mm - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to by the caller - * @force: whether to force write access even if user mapping is - * readonly. This will result in the page being COWed even - * in MAP_SHARED mappings. You do not want this. - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. - * @vmas: array of pointers to vmas corresponding to each page. - * Or NULL if the caller does not require them. - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. vmas will only - * remain valid while mmap_sem is held. - * - * Must be called with mmap_sem held for read or write. - * - * get_user_pages walks a process's page tables and takes a reference to - * each struct page that each user address corresponds to at a given - * instant. That is, it takes the page that would be accessed if a user - * thread accesses the given user virtual address at that instant. - * - * This does not guarantee that the page exists in the user mappings when - * get_user_pages returns, and there may even be a completely different - * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page - * won't be freed completely. And mostly callers simply care that the page - * contains data that was valid *at some point in time*. Typically, an IO - * or similar operation cannot guarantee anything stronger anyway because - * locks can't be held over the syscall boundary. - * - * If write=0, the page must not be written to. If the page is written to, - * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called - * after the page is finished with, and before put_page is called. - * - * get_user_pages is typically used for fewer-copy IO operations, to get a - * handle on the memory by some means other than accesses via the user virtual - * addresses. The pages may be submitted for DMA to devices or accessed via - * their kernel linear mapping (via the kmap APIs). Care should be taken to - * use the correct cache flushing APIs. - * - * See also get_user_pages_fast, for performance critical applications. - */ -long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, int write, - int force, struct page **pages, struct vm_area_struct **vmas) +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot, bool mkwrite) { - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; + int retval; + pte_t *pte; + spinlock_t *ptl; - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); + retval = validate_page_before_insert(vma, page); + if (retval) + goto out; + retval = -ENOMEM; + pte = get_locked_pte(vma->vm_mm, addr, &ptl); + if (!pte) + goto out; + retval = insert_page_into_pte_locked(vma, pte, addr, page, prot, + mkwrite); + pte_unmap_unlock(pte, ptl); +out: + return retval; } -EXPORT_SYMBOL(get_user_pages); -/** - * get_dump_page() - pin user page in memory while writing it to core dump - * @addr: user address - * - * Returns struct page pointer of user page pinned for dump, - * to be freed afterwards by page_cache_release() or put_page(). - * - * Returns NULL on any kind of failure - a hole must then be inserted into - * the corefile, to preserve alignment with its headers; and also returns - * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - - * allowing a hole to be left in the corefile to save diskspace. - * - * Called without mmap_sem, but after all other threads have been killed. - */ -#ifdef CONFIG_ELF_CORE -struct page *get_dump_page(unsigned long addr) +static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, struct page *page, pgprot_t prot) { - struct vm_area_struct *vma; - struct page *page; + int err; - if (__get_user_pages(current, current->mm, addr, 1, - FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma, - NULL) < 1) - return NULL; - flush_cache_page(vma, addr, page_to_pfn(page)); - return page; + err = validate_page_before_insert(vma, page); + if (err) + return err; + return insert_page_into_pte_locked(vma, pte, addr, page, prot, false); } -#endif /* CONFIG_ELF_CORE */ -pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, - spinlock_t **ptl) +/* insert_pages() amortizes the cost of spinlock operations + * when inserting pages in a loop. + */ +static int insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num, pgprot_t prot) { - pgd_t * pgd = pgd_offset(mm, addr); - pud_t * pud = pud_alloc(mm, pgd, addr); - if (pud) { - pmd_t * pmd = pmd_alloc(mm, pud, addr); - if (pmd) { - VM_BUG_ON(pmd_trans_huge(*pmd)); - return pte_alloc_map_lock(mm, pmd, addr, ptl); + pmd_t *pmd = NULL; + pte_t *start_pte, *pte; + spinlock_t *pte_lock; + struct mm_struct *const mm = vma->vm_mm; + unsigned long curr_page_idx = 0; + unsigned long remaining_pages_total = *num; + unsigned long pages_to_write_in_pmd; + int ret; +more: + ret = -EFAULT; + pmd = walk_to_pmd(mm, addr); + if (!pmd) + goto out; + + pages_to_write_in_pmd = min_t(unsigned long, + remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); + + /* Allocate the PTE if necessary; takes PMD lock once only. */ + ret = -ENOMEM; + if (pte_alloc(mm, pmd)) + goto out; + + while (pages_to_write_in_pmd) { + int pte_idx = 0; + const int batch_size = min_t(int, pages_to_write_in_pmd, 8); + + start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); + if (!start_pte) { + ret = -EFAULT; + goto out; + } + for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { + int err = insert_page_in_batch_locked(vma, pte, + addr, pages[curr_page_idx], prot); + if (unlikely(err)) { + pte_unmap_unlock(start_pte, pte_lock); + ret = err; + remaining_pages_total -= pte_idx; + goto out; + } + addr += PAGE_SIZE; + ++curr_page_idx; } + pte_unmap_unlock(start_pte, pte_lock); + pages_to_write_in_pmd -= batch_size; + remaining_pages_total -= batch_size; } - return NULL; + if (remaining_pages_total) + goto more; + ret = 0; +out: + *num = remaining_pages_total; + return ret; } -/* - * This is the old fallback for page remapping. +/** + * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. + * @vma: user vma to map to + * @addr: target start user address of these pages + * @pages: source kernel pages + * @num: in: number of pages to map. out: number of pages that were *not* + * mapped. (0 means all pages were successfully mapped). + * + * Preferred over vm_insert_page() when inserting multiple pages. * - * 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. + * In case of error, we may have mapped a subset of the provided + * pages. It is the caller's responsibility to account for this case. + * + * The same restrictions apply as in vm_insert_page(). */ -static int insert_page(struct vm_area_struct *vma, unsigned long addr, - struct page *page, pgprot_t prot) +int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num) { - struct mm_struct *mm = vma->vm_mm; - int retval; - pte_t *pte; - spinlock_t *ptl; - - retval = -EINVAL; - if (PageAnon(page)) - goto out; - retval = -ENOMEM; - flush_dcache_page(page); - pte = get_locked_pte(mm, addr, &ptl); - if (!pte) - goto out; - retval = -EBUSY; - if (!pte_none(*pte)) - goto out_unlock; - - /* Ok, finally just insert the thing.. */ - get_page(page); - inc_mm_counter_fast(mm, MM_FILEPAGES); - page_add_file_rmap(page); - set_pte_at(mm, addr, pte, mk_pte(page, prot)); + const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; - retval = 0; - pte_unmap_unlock(pte, ptl); - return retval; -out_unlock: - pte_unmap_unlock(pte, ptl); -out: - return retval; + if (addr < vma->vm_start || end_addr >= vma->vm_end) + return -EFAULT; + if (!(vma->vm_flags & VM_MIXEDMAP)) { + BUG_ON(mmap_read_trylock(vma->vm_mm)); + BUG_ON(vma->vm_flags & VM_PFNMAP); + vm_flags_set(vma, VM_MIXEDMAP); + } + /* Defer page refcount checking till we're about to map that page. */ + return insert_pages(vma, addr, pages, num, vma->vm_page_prot); } +EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma @@ -2116,7 +2441,8 @@ out: * @page: source kernel page * * This allows drivers to insert individual pages they've allocated - * into a user vma. + * into a user vma. The zeropage is supported in some VMAs, + * see vm_mixed_zeropage_allowed(). * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as @@ -2132,76 +2458,196 @@ out: * 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. + * under mm->mmap_lock 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(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); - vma->vm_flags |= VM_MIXEDMAP; + vm_flags_set(vma, VM_MIXEDMAP); } - return insert_page(vma, addr, page, vma->vm_page_prot); + return insert_page(vma, addr, page, vma->vm_page_prot, false); } EXPORT_SYMBOL(vm_insert_page); -static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t prot) +/* + * __vm_map_pages - maps range of kernel pages into user vma + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * @offset: user's requested vm_pgoff + * + * This allows drivers to map range of kernel pages into a user vma. + * The zeropage is supported in some VMAs, see + * vm_mixed_zeropage_allowed(). + * + * Return: 0 on success and error code otherwise. + */ +static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num, unsigned long offset) +{ + unsigned long count = vma_pages(vma); + unsigned long uaddr = vma->vm_start; + int ret, i; + + /* Fail if the user requested offset is beyond the end of the object */ + if (offset >= num) + return -ENXIO; + + /* Fail if the user requested size exceeds available object size */ + if (count > num - offset) + return -ENXIO; + + for (i = 0; i < count; i++) { + ret = vm_insert_page(vma, uaddr, pages[offset + i]); + if (ret < 0) + return ret; + uaddr += PAGE_SIZE; + } + + return 0; +} + +/** + * vm_map_pages - maps range of kernel pages starts with non zero offset + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * + * Maps an object consisting of @num pages, catering for the user's + * requested vm_pgoff + * + * If we fail to insert any page into the vma, the function will return + * immediately leaving any previously inserted pages present. Callers + * from the mmap handler may immediately return the error as their caller + * will destroy the vma, removing any successfully inserted pages. Other + * callers should make their own arrangements for calling unmap_region(). + * + * Context: Process context. Called by mmap handlers. + * Return: 0 on success and error code otherwise. + */ +int vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return __vm_map_pages(vma, pages, num, vma->vm_pgoff); +} +EXPORT_SYMBOL(vm_map_pages); + +/** + * vm_map_pages_zero - map range of kernel pages starts with zero offset + * @vma: user vma to map to + * @pages: pointer to array of source kernel pages + * @num: number of pages in page array + * + * Similar to vm_map_pages(), except that it explicitly sets the offset + * to 0. This function is intended for the drivers that did not consider + * vm_pgoff. + * + * Context: Process context. Called by mmap handlers. + * Return: 0 on success and error code otherwise. + */ +int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, + unsigned long num) +{ + return __vm_map_pages(vma, pages, num, 0); +} +EXPORT_SYMBOL(vm_map_pages_zero); + +static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; - int retval; pte_t *pte, entry; spinlock_t *ptl; - retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto out; - retval = -EBUSY; - if (!pte_none(*pte)) + return VM_FAULT_OOM; + entry = ptep_get(pte); + if (!pte_none(entry)) { + 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(entry) != pfn) { + WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry))); + goto out_unlock; + } + entry = pte_mkyoung(entry); + 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.. */ entry = pte_mkspecial(pfn_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? */ - retval = 0; out_unlock: pte_unmap_unlock(pte, ptl); -out: - return retval; + return VM_FAULT_NOPAGE; } /** - * vm_insert_pfn - insert single pfn into user vma + * 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 * - * Similar to vm_insert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. + * This is exactly like vmf_insert_pfn(), except that it allows drivers + * to override pgprot on a per-page basis. * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. + * 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. * - * vma cannot be a COW mapping. + * pgprot typically only differs from @vma->vm_page_prot when drivers set + * caching- and encryption bits different than those of @vma->vm_page_prot, + * because the caching- or encryption mode may not be known at mmap() time. * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. + * This is ok as long as @vma->vm_page_prot is not used by the core vm + * to set caching and encryption bits for those vmas (except for COW pages). + * This is ensured by core vm only modifying these page table entries using + * functions that don't touch caching- or encryption bits, using pte_modify() + * if needed. (See for example mprotect()). + * + * Also when new page-table entries are created, this is only done using the + * fault() callback, and never using the value of vma->vm_page_prot, + * except for page-table entries that point to anonymous pages as the result + * of COW. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) { - int ret; - pgprot_t pgprot = vma->vm_page_prot; /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -2215,23 +2661,74 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) - return -EFAULT; - if (track_pfn_insert(vma, &pgprot, pfn)) - return -EINVAL; + return VM_FAULT_SIGBUS; - ret = insert_pfn(vma, addr, pfn, pgprot); + if (!pfn_modify_allowed(pfn, pgprot)) + return VM_FAULT_SIGBUS; - return ret; + pfnmap_setup_cachemode_pfn(pfn, &pgprot); + + return insert_pfn(vma, addr, pfn, pgprot, false); } -EXPORT_SYMBOL(vm_insert_pfn); +EXPORT_SYMBOL(vmf_insert_pfn_prot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +/** + * 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) { - BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); + 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, unsigned long pfn, + bool mkwrite) +{ + if (unlikely(is_zero_pfn(pfn)) && + (mkwrite || !vm_mixed_zeropage_allowed(vma))) + return false; + /* these checks mirror the abort conditions in vm_normal_page */ + if (vma->vm_flags & VM_MIXEDMAP) + return true; + if (is_zero_pfn(pfn)) + return true; + return false; +} + +static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn, bool mkwrite) +{ + pgprot_t pgprot = vma->vm_page_prot; + int err; + + if (!vm_mixed_ok(vma, pfn, mkwrite)) + return VM_FAULT_SIGBUS; if (addr < vma->vm_start || addr >= vma->vm_end) - return -EFAULT; + return VM_FAULT_SIGBUS; + + pfnmap_setup_cachemode_pfn(pfn, &pgprot); + + if (!pfn_modify_allowed(pfn, pgprot)) + return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() @@ -2240,15 +2737,65 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_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); - return insert_page(vma, addr, page, vma->vm_page_prot); + err = insert_page(vma, addr, page, pgprot, mkwrite); + } else { + return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } - return insert_pfn(vma, addr, pfn, vma->vm_page_prot); + + 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_page_mkwrite(struct vm_fault *vmf, struct page *page, + bool write) +{ + pgprot_t pgprot = vmf->vma->vm_page_prot; + unsigned long addr = vmf->address; + int err; + + if (addr < vmf->vma->vm_start || addr >= vmf->vma->vm_end) + return VM_FAULT_SIGBUS; + + err = insert_page(vmf->vma, addr, page, pgprot, write); + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(vmf_insert_page_mkwrite); + +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long 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, unsigned long pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, true); } -EXPORT_SYMBOL(vm_insert_mixed); /* * maps a range of physical memory into the requested pages. the old @@ -2259,21 +2806,26 @@ 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; + pte_t *pte, *mapped_pte; spinlock_t *ptl; + int err = 0; - pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { - BUG_ON(!pte_none(*pte)); + BUG_ON(!pte_none(ptep_get(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 0; + pte_unmap_unlock(mapped_pte, ptl); + return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, @@ -2282,6 +2834,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, { pmd_t *pmd; unsigned long next; + int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); @@ -2290,81 +2843,90 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); - if (remap_pte_range(mm, pmd, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + 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, pgd_t *pgd, +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, pgd, addr); + pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (remap_pmd_range(mm, pud, addr, next, - pfn + (addr >> PAGE_SHIFT), prot)) - return -ENOMEM; + err = remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + return err; } while (pud++, 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. - */ -int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t prot) +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) { - pgd_t *pgd; + p4d_t *p4d; unsigned long next; - unsigned long end = addr + PAGE_ALIGN(size); - struct mm_struct *mm = vma->vm_mm; 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; +} + +static int get_remap_pgoff(vm_flags_t vm_flags, unsigned long addr, + unsigned long end, unsigned long vm_start, unsigned long vm_end, + unsigned long pfn, pgoff_t *vm_pgoff_p) +{ /* - * 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) + if (is_cow_mapping(vm_flags)) { + if (addr != vm_start || end != vm_end) return -EINVAL; - vma->vm_pgoff = pfn; + *vm_pgoff_p = pfn; } - err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); - if (err) + return 0; +} + +static int remap_pfn_range_internal(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; + int err; + + if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + VM_WARN_ON_ONCE((vma->vm_flags & VM_REMAP_FLAGS) != VM_REMAP_FLAGS); BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; @@ -2372,23 +2934,178 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); - err = remap_pud_range(mm, pgd, addr, next, + err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) - break; + return err; } while (pgd++, addr = next, addr != end); - if (err) - untrack_pfn(vma, pfn, PAGE_ALIGN(size)); + return 0; +} +/* + * Variant of remap_pfn_range that does not call track_pfn_remap. The caller + * must have pre-validated the caching bits of the pgprot_t. + */ +static int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); + + if (!error) + return 0; + + /* + * A partial pfn range mapping is dangerous: it does not + * maintain page reference counts, and callers may free + * pages due to the error. So zap it early. + */ + zap_page_range_single(vma, addr, size, NULL); + return error; +} + +#ifdef __HAVE_PFNMAP_TRACKING +static inline struct pfnmap_track_ctx *pfnmap_track_ctx_alloc(unsigned long pfn, + unsigned long size, pgprot_t *prot) +{ + struct pfnmap_track_ctx *ctx; + + if (pfnmap_track(pfn, size, prot)) + return ERR_PTR(-EINVAL); + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (unlikely(!ctx)) { + pfnmap_untrack(pfn, size); + return ERR_PTR(-ENOMEM); + } + + ctx->pfn = pfn; + ctx->size = size; + kref_init(&ctx->kref); + return ctx; +} + +void pfnmap_track_ctx_release(struct kref *ref) +{ + struct pfnmap_track_ctx *ctx = container_of(ref, struct pfnmap_track_ctx, kref); + + pfnmap_untrack(ctx->pfn, ctx->size); + kfree(ctx); +} + +static int remap_pfn_range_track(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + struct pfnmap_track_ctx *ctx = NULL; + int err; + + size = PAGE_ALIGN(size); + + /* + * If we cover the full VMA, we'll perform actual tracking, and + * remember to untrack when the last reference to our tracking + * context from a VMA goes away. We'll keep tracking the whole pfn + * range even during VMA splits and partial unmapping. + * + * If we only cover parts of the VMA, we'll only setup the cachemode + * in the pgprot for the pfn range. + */ + if (addr == vma->vm_start && addr + size == vma->vm_end) { + if (vma->pfnmap_track_ctx) + return -EINVAL; + ctx = pfnmap_track_ctx_alloc(pfn, size, &prot); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + } else if (pfnmap_setup_cachemode(pfn, size, &prot)) { + return -EINVAL; + } + + err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); + if (ctx) { + if (err) + kref_put(&ctx->kref, pfnmap_track_ctx_release); + else + vma->pfnmap_track_ctx = ctx; + } return err; } + +static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + return remap_pfn_range_track(vma, addr, pfn, size, prot); +} +#else +static int do_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + return remap_pfn_range_notrack(vma, addr, pfn, size, prot); +} +#endif + +void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn) +{ + /* + * We set addr=VMA start, end=VMA end here, so this won't fail, but we + * check it again on complete and will fail there if specified addr is + * invalid. + */ + get_remap_pgoff(desc->vm_flags, desc->start, desc->end, + desc->start, desc->end, pfn, &desc->pgoff); + desc->vm_flags |= VM_REMAP_FLAGS; +} + +static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size) +{ + unsigned long end = addr + PAGE_ALIGN(size); + int err; + + err = get_remap_pgoff(vma->vm_flags, addr, end, + vma->vm_start, vma->vm_end, + pfn, &vma->vm_pgoff); + if (err) + return err; + + vm_flags_set(vma, VM_REMAP_FLAGS); + return 0; +} + +/** + * remap_pfn_range - remap kernel memory to userspace + * @vma: user vma to map to + * @addr: target page aligned user address to start at + * @pfn: page frame number of kernel physical memory address + * @size: size of mapping 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) +{ + int err; + + err = remap_pfn_range_prepare_vma(vma, addr, pfn, size); + if (err) + return err; + + return do_remap_pfn_range(vma, addr, pfn, size, prot); +} EXPORT_SYMBOL(remap_pfn_range); +int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + return do_remap_pfn_range(vma, addr, pfn, size, prot); +} + /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to - * @start: start of area + * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The @@ -2397,6 +3114,8 @@ EXPORT_SYMBOL(remap_pfn_range); * * 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) { @@ -2434,398 +3153,642 @@ 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_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { - 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; + pte_t *pte, *mapped_pte; + int err = 0; + spinlock_t *ptl; - BUG_ON(pmd_huge(*pmd)); + if (create) { + mapped_pte = pte = (mm == &init_mm) ? + pte_alloc_kernel_track(pmd, addr, mask) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + } else { + mapped_pte = pte = (mm == &init_mm) ? + pte_offset_kernel(pmd, addr) : + pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -EINVAL; + } 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); + if (fn) { + do { + if (create || !pte_none(ptep_get(pte))) { + err = fn(pte, addr, data); + if (err) + break; + } + } while (pte++, addr += PAGE_SIZE, addr != end); + } + *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) - pte_unmap_unlock(pte-1, ptl); + pte_unmap_unlock(mapped_pte, 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) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; - int err; + int err = 0; - BUG_ON(pud_huge(*pud)); + BUG_ON(pud_leaf(*pud)); - pmd = pmd_alloc(mm, pud, addr); - if (!pmd) - return -ENOMEM; + if (create) { + pmd = pmd_alloc_track(mm, pud, addr, mask); + if (!pmd) + return -ENOMEM; + } else { + pmd = pmd_offset(pud, addr); + } do { next = pmd_addr_end(addr, end); - err = apply_to_pte_range(mm, pmd, addr, next, fn, data); + if (pmd_none(*pmd) && !create) + continue; + if (WARN_ON_ONCE(pmd_leaf(*pmd))) + return -EINVAL; + if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) { + if (!create) + continue; + pmd_clear_bad(pmd); + } + err = apply_to_pte_range(mm, pmd, addr, next, + fn, data, create, mask); if (err) break; } while (pmd++, addr = next, addr != end); + return err; } -static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, +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) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; - int err; + int err = 0; - pud = pud_alloc(mm, pgd, addr); - if (!pud) - return -ENOMEM; + if (create) { + pud = pud_alloc_track(mm, p4d, addr, mask); + if (!pud) + return -ENOMEM; + } else { + pud = pud_offset(p4d, addr); + } do { next = pud_addr_end(addr, end); - err = apply_to_pmd_range(mm, pud, addr, next, fn, data); + if (pud_none(*pud) && !create) + continue; + if (WARN_ON_ONCE(pud_leaf(*pud))) + return -EINVAL; + if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { + if (!create) + continue; + pud_clear_bad(pud); + } + err = apply_to_pmd_range(mm, pud, addr, next, + fn, data, create, mask); if (err) break; } while (pud++, 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) +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, bool create, + pgtbl_mod_mask *mask) { - pgd_t *pgd; + p4d_t *p4d; unsigned long next; + int err = 0; + + if (create) { + p4d = p4d_alloc_track(mm, pgd, addr, mask); + if (!p4d) + return -ENOMEM; + } else { + p4d = p4d_offset(pgd, addr); + } + do { + next = p4d_addr_end(addr, end); + if (p4d_none(*p4d) && !create) + continue; + if (WARN_ON_ONCE(p4d_leaf(*p4d))) + return -EINVAL; + if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) { + if (!create) + continue; + p4d_clear_bad(p4d); + } + err = apply_to_pud_range(mm, p4d, addr, next, + fn, data, create, mask); + if (err) + break; + } while (p4d++, addr = next, addr != end); + + return err; +} + +static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, + void *data, bool create) +{ + pgd_t *pgd; + unsigned long start = addr, next; unsigned long end = addr + size; - int err; + pgtbl_mod_mask mask = 0; + int err = 0; + + if (WARN_ON(addr >= end)) + return -EINVAL; - BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + if (pgd_none(*pgd) && !create) + continue; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) { + err = -EINVAL; + break; + } + if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { + if (!create) + continue; + pgd_clear_bad(pgd); + } + err = apply_to_p4d_range(mm, pgd, addr, next, + fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, start + size); + 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) +{ + return __apply_to_page_range(mm, addr, size, fn, data, true); +} EXPORT_SYMBOL_GPL(apply_to_page_range); /* - * handle_pte_fault chooses page fault handler according to an entry - * which was read non-atomically. Before making any commitment, on - * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault - * must check under lock before unmapping the pte and proceeding - * (but do_wp_page is only called after already making such a check; + * Scan a region of virtual memory, calling a provided function on + * each leaf page table where it exists. + * + * Unlike apply_to_page_range, this does _not_ fill in page tables + * where they are absent. + */ +int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, false); +} + +/* + * 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) +static inline int pte_unmap_same(struct vm_fault *vmf) { int same = 1; -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) 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); + spin_lock(vmf->ptl); + same = pte_same(ptep_get(vmf->pte), vmf->orig_pte); + spin_unlock(vmf->ptl); } #endif - pte_unmap(page_table); + pte_unmap(vmf->pte); + vmf->pte = NULL; return same; } -static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +/* + * Return: + * 0: copied succeeded + * -EHWPOISON: copy failed due to hwpoison in source page + * -EAGAIN: copied failed (some other reason) + */ +static inline int __wp_page_copy_user(struct page *dst, struct page *src, + struct vm_fault *vmf) { + int ret; + void *kaddr; + void __user *uaddr; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + + if (likely(src)) { + if (copy_mc_user_highpage(dst, src, addr, vma)) + return -EHWPOISON; + return 0; + } + /* * 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); + kaddr = kmap_local_page(dst); + pagefault_disable(); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + vmf->pte = NULL; + if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and update local tlb only + */ + if (vmf->pte) + update_mmu_tlb(vma, addr, vmf->pte); + ret = -EAGAIN; + goto pte_unlock; + } + + entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache_range(vmf, vma, addr, vmf->pte, 1); + } + + /* + * 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)) { + if (vmf->pte) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + /* The PTE changed under us, update local tlb */ + if (vmf->pte) + update_mmu_tlb(vma, addr, vmf->pte); + ret = -EAGAIN; + goto pte_unlock; + } /* - * 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. + * The same page can be mapped back since last copy attempt. + * Try to copy again under PTL. */ - if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); clear_page(kaddr); - kunmap_atomic(kaddr); - flush_dcache_page(dst); - } else - copy_user_highpage(dst, src, va, vma); + } + } + + ret = 0; + +pte_unlock: + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); + pagefault_enable(); + kunmap_local(kaddr); + flush_dcache_page(dst); + + return ret; +} + +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; } /* - * 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. + * 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. * - * 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. + * We do this without the lock held, so that it can sleep if it needs to. */ -static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - spinlock_t *ptl, pte_t orig_pte) - __releases(ptl) +static vm_fault_t do_page_mkwrite(struct vm_fault *vmf, struct folio *folio) { - struct page *old_page, *new_page = NULL; - pte_t entry; - int ret = 0; - int page_mkwrite = 0; - struct page *dirty_page = NULL; - unsigned long mmun_start = 0; /* For mmu_notifiers */ - unsigned long mmun_end = 0; /* For mmu_notifiers */ - - old_page = vm_normal_page(vma, address, orig_pte); - if (!old_page) { - /* - * VM_MIXEDMAP !pfn_valid() case - * - * We should not cow pages in a shared writeable mapping. - * Just mark the pages writable as we can't do any dirty - * accounting on raw pfn maps. - */ - if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == - (VM_WRITE|VM_SHARED)) - goto reuse; - goto gotten; - } + vm_fault_t ret; + unsigned int old_flags = vmf->flags; - /* - * Take out anonymous pages first, anonymous shared vmas are - * not dirty accountable. - */ - if (PageAnon(old_page) && !PageKsm(old_page)) { - if (!trylock_page(old_page)) { - page_cache_get(old_page); - pte_unmap_unlock(page_table, ptl); - lock_page(old_page); - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { - unlock_page(old_page); - goto unlock; - } - page_cache_release(old_page); - } - if (reuse_swap_page(old_page)) { - /* - * The page is all ours. Move it to our anon_vma so - * the rmap code will not search our parent or siblings. - * Protected against the rmap code by the page lock. - */ - page_move_anon_rmap(old_page, vma, address); - unlock_page(old_page); - goto reuse; + vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + + if (vmf->vma->vm_file && + IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) + return VM_FAULT_SIGBUS; + + 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))) { + folio_lock(folio); + if (!folio->mapping) { + folio_unlock(folio); + return 0; /* retry */ } - unlock_page(old_page); - } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == - (VM_WRITE|VM_SHARED))) { - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ - if (vma->vm_ops && vma->vm_ops->page_mkwrite) { - struct vm_fault vmf; - int tmp; + ret |= VM_FAULT_LOCKED; + } else + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + return ret; +} - vmf.virtual_address = (void __user *)(address & - PAGE_MASK); - vmf.pgoff = old_page->index; - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - vmf.page = old_page; +/* + * 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 vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct address_space *mapping; + struct folio *folio = page_folio(vmf->page); + bool dirtied; + bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; - /* - * 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. - */ - page_cache_get(old_page); - pte_unmap_unlock(page_table, ptl); - - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; - } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(old_page); - if (!old_page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(old_page); - goto unwritable_page; - } - } else - VM_BUG_ON(!PageLocked(old_page)); + dirtied = folio_mark_dirty(folio); + VM_BUG_ON_FOLIO(folio_test_anon(folio), folio); + /* + * Take a local copy of the address_space - folio.mapping may be zeroed + * by truncate after folio_unlock(). The address_space itself remains + * pinned by vma->vm_file's reference. We rely on folio_unlock()'s + * release semantics to prevent the compiler from undoing this copying. + */ + mapping = folio_raw_mapping(folio); + folio_unlock(folio); - /* - * Since we dropped the lock we need to revalidate - * the PTE as someone else may have changed it. If - * they did, we just return, as we can count on the - * MMU to tell us if they didn't also make it writable. - */ - page_table = pte_offset_map_lock(mm, pmd, address, - &ptl); - if (!pte_same(*page_table, orig_pte)) { - unlock_page(old_page); - goto unlock; - } + if (!page_mkwrite) + file_update_time(vma->vm_file); - page_mkwrite = 1; + /* + * Throttle page dirtying rate down to writeback speed. + * + * mapping may be NULL here because some device drivers do not + * set page.mapping but still dirty their pages + * + * Drop the mmap_lock before waiting on IO, if we can. The file + * is pinning the mapping, as per above. + */ + if ((dirtied || page_mkwrite) && mapping) { + struct file *fpin; + + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + balance_dirty_pages_ratelimited(mapping); + if (fpin) { + fput(fpin); + return VM_FAULT_COMPLETED; } - dirty_page = old_page; - get_page(dirty_page); + } -reuse: - flush_cache_page(vma, address, pte_pfn(orig_pte)); - entry = pte_mkyoung(orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (ptep_set_access_flags(vma, address, page_table, entry,1)) - update_mmu_cache(vma, address, page_table); - pte_unmap_unlock(page_table, ptl); - ret |= VM_FAULT_WRITE; + return 0; +} - if (!dirty_page) - return ret; +/* + * 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, struct folio *folio) + __releases(vmf->ptl) +{ + struct vm_area_struct *vma = vmf->vma; + pte_t entry; + + VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); + VM_WARN_ON(is_zero_pfn(pte_pfn(vmf->orig_pte))); + if (folio) { + VM_BUG_ON(folio_test_anon(folio) && + !PageAnonExclusive(vmf->page)); /* - * Yes, Virginia, this is actually required to prevent a race - * with clear_page_dirty_for_io() from clearing the page dirty - * bit after it clear all dirty ptes, but before a racing - * do_wp_page installs a dirty pte. - * - * __do_fault is protected similarly. + * Clear the folio's cpupid information as the existing + * information potentially belongs to a now completely + * unrelated process. */ - if (!page_mkwrite) { - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page, page_mkwrite); - /* file_update_time outside page_lock */ - if (vma->vm_file) - file_update_time(vma->vm_file); - } - put_page(dirty_page); - if (page_mkwrite) { - struct address_space *mapping = dirty_page->mapping; - - set_page_dirty(dirty_page); - unlock_page(dirty_page); - page_cache_release(dirty_page); - if (mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } - } + folio_xchg_last_cpupid(folio, (1 << LAST_CPUPID_SHIFT) - 1); + } - return ret; + 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_range(vmf, vma, vmf->address, vmf->pte, 1); + pte_unmap_unlock(vmf->pte, vmf->ptl); + count_vm_event(PGREUSE); +} + +/* + * We could add a bitflag somewhere, but for now, we know that all + * vm_ops that have a ->map_pages have been audited and don't need + * the mmap_lock to be held. + */ +static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + if (vma->vm_ops->map_pages || !(vmf->flags & FAULT_FLAG_VMA_LOCK)) + return 0; + vma_end_read(vma); + return VM_FAULT_RETRY; +} + +/** + * __vmf_anon_prepare - Prepare to handle an anonymous fault. + * @vmf: The vm_fault descriptor passed from the fault handler. + * + * When preparing to insert an anonymous page into a VMA from a + * fault handler, call this function rather than anon_vma_prepare(). + * If this vma does not already have an associated anon_vma and we are + * only protected by the per-VMA lock, the caller must retry with the + * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to + * determine if this VMA can share its anon_vma, and that's not safe to + * do with only the per-VMA lock held for this VMA. + * + * Return: 0 if fault handling can proceed. Any other value should be + * returned to the caller. + */ +vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = 0; + + if (likely(vma->anon_vma)) + return 0; + if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + if (!mmap_read_trylock(vma->vm_mm)) + return VM_FAULT_RETRY; } + if (__anon_vma_prepare(vma)) + ret = VM_FAULT_OOM; + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + mmap_read_unlock(vma->vm_mm); + return ret; +} - /* - * Ok, we need to copy. Oh, well.. - */ - page_cache_get(old_page); -gotten: - pte_unmap_unlock(page_table, ptl); +/* + * Handle the case of a page which we actually need to copy to a new page, + * either due to COW or unsharing. + * + * Called with mmap_lock 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) +{ + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + struct folio *old_folio = NULL; + struct folio *new_folio = NULL; + pte_t entry; + int page_copied = 0; + struct mmu_notifier_range range; + vm_fault_t ret; + bool pfn_is_zero; + + delayacct_wpcopy_start(); - if (unlikely(anon_vma_prepare(vma))) + if (vmf->page) + old_folio = page_folio(vmf->page); + ret = vmf_anon_prepare(vmf); + if (unlikely(ret)) + goto out; + + pfn_is_zero = is_zero_pfn(pte_pfn(vmf->orig_pte)); + new_folio = folio_prealloc(mm, vma, vmf->address, pfn_is_zero); + if (!new_folio) goto oom; - if (is_zero_pfn(pte_pfn(orig_pte))) { - new_page = alloc_zeroed_user_highpage_movable(vma, address); - if (!new_page) - goto oom; - } else { - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!new_page) - goto oom; - cow_user_page(new_page, old_page, address, vma); + if (!pfn_is_zero) { + int err; + + err = __wp_page_copy_user(&new_folio->page, vmf->page, vmf); + if (err) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + * The -EHWPOISON case will not be retried. + */ + folio_put(new_folio); + if (old_folio) + folio_put(old_folio); + + delayacct_wpcopy_end(); + return err == -EHWPOISON ? VM_FAULT_HWPOISON : 0; + } + kmsan_copy_page_meta(&new_folio->page, vmf->page); } - __SetPageUptodate(new_page); - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) - goto oom_free_new; + __folio_mark_uptodate(new_folio); - mmun_start = address & PAGE_MASK; - mmun_end = mmun_start + PAGE_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, 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 */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (likely(pte_same(*page_table, orig_pte))) { - if (old_page) { - if (!PageAnon(old_page)) { - dec_mm_counter_fast(mm, MM_FILEPAGES); - inc_mm_counter_fast(mm, MM_ANONPAGES); + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); + if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + if (old_folio) { + if (!folio_test_anon(old_folio)) { + dec_mm_counter(mm, mm_counter_file(old_folio)); + inc_mm_counter(mm, MM_ANONPAGES); } - } else - inc_mm_counter_fast(mm, MM_ANONPAGES); - flush_cache_page(vma, address, pte_pfn(orig_pte)); - entry = mk_pte(new_page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } else { + ksm_might_unmap_zero_page(mm, vmf->orig_pte); + inc_mm_counter(mm, MM_ANONPAGES); + } + flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); + entry = folio_mk_pte(new_folio, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); + if (unlikely(unshare)) { + if (pte_soft_dirty(vmf->orig_pte)) + entry = pte_mksoft_dirty(entry); + if (pte_uffd_wp(vmf->orig_pte)) + entry = pte_mkuffd_wp(entry); + } else { + 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(vma, address, page_table); - page_add_new_anon_rmap(new_page, vma, address); - /* - * We call the notify macro here because, when using secondary - * mmu page tables (such as kvm shadow page tables), we want the - * new page to be mapped directly into the secondary page table. + * pte with the new entry, to keep TLBs on different CPUs in + * sync. This code used to set the new PTE then flush TLBs, but + * that left a window where the new PTE could be loaded into + * some TLBs while the old PTE remains in others. */ - set_pte_at_notify(mm, address, page_table, entry); - update_mmu_cache(vma, address, page_table); - if (old_page) { + ptep_clear_flush(vma, vmf->address, vmf->pte); + folio_add_new_anon_rmap(new_folio, vma, vmf->address, RMAP_EXCLUSIVE); + folio_add_lru_vma(new_folio, vma); + BUG_ON(unshare && pte_write(entry)); + set_pte_at(mm, vmf->address, vmf->pte, entry); + update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); + if (old_folio) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another @@ -2836,10 +3799,10 @@ gotten: * 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,) + * folio_remove_rmap_pte() 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. + * in folio_remove_rmap_pte(); * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the @@ -2848,44 +3811,373 @@ gotten: * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(old_page); + folio_remove_rmap_pte(old_folio, vmf->page, vma); } /* Free the old page.. */ - new_page = old_page; - ret |= VM_FAULT_WRITE; - } else - mem_cgroup_uncharge_page(new_page); + new_folio = old_folio; + page_copied = 1; + pte_unmap_unlock(vmf->pte, vmf->ptl); + } else if (vmf->pte) { + update_mmu_tlb(vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + } + + mmu_notifier_invalidate_range_end(&range); + + if (new_folio) + folio_put(new_folio); + if (old_folio) { + if (page_copied) + free_swap_cache(old_folio); + folio_put(old_folio); + } + + delayacct_wpcopy_end(); + return 0; +oom: + ret = VM_FAULT_OOM; +out: + if (old_folio) + folio_put(old_folio); + + delayacct_wpcopy_end(); + return ret; +} + +/** + * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE + * writeable once the page is prepared + * + * @vmf: structure describing the fault + * @folio: the folio of vmf->page + * + * 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: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before + * we acquired PTE lock. + */ +static vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf, struct folio *folio) +{ + 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); + if (!vmf->pte) + return VM_FAULT_NOPAGE; + /* + * We might have raced with another page fault while we released the + * pte_offset_map_lock. + */ + if (!pte_same(ptep_get(vmf->pte), vmf->orig_pte)) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return VM_FAULT_NOPAGE; + } + wp_page_reuse(vmf, folio); + 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); + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; + + 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, NULL); + } + wp_page_reuse(vmf, NULL); + return 0; +} + +static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) + __releases(vmf->ptl) +{ + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = 0; + + folio_get(folio); + + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + vm_fault_t tmp; + + pte_unmap_unlock(vmf->pte, vmf->ptl); + tmp = vmf_can_call_fault(vmf); + if (tmp) { + folio_put(folio); + return tmp; + } + + tmp = do_page_mkwrite(vmf, folio); + if (unlikely(!tmp || (tmp & + (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + folio_put(folio); + return tmp; + } + tmp = finish_mkwrite_fault(vmf, folio); + if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { + folio_unlock(folio); + folio_put(folio); + return tmp; + } + } else { + wp_page_reuse(vmf, folio); + folio_lock(folio); + } + ret |= fault_dirty_shared_page(vmf); + folio_put(folio); + + return ret; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static bool __wp_can_reuse_large_anon_folio(struct folio *folio, + struct vm_area_struct *vma) +{ + bool exclusive = false; + + /* Let's just free up a large folio if only a single page is mapped. */ + if (folio_large_mapcount(folio) <= 1) + return false; + + /* + * The assumption for anonymous folios is that each page can only get + * mapped once into each MM. The only exception are KSM folios, which + * are always small. + * + * Each taken mapcount must be paired with exactly one taken reference, + * whereby the refcount must be incremented before the mapcount when + * mapping a page, and the refcount must be decremented after the + * mapcount when unmapping a page. + * + * If all folio references are from mappings, and all mappings are in + * the page tables of this MM, then this folio is exclusive to this MM. + */ + if (test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids)) + return false; + + VM_WARN_ON_ONCE(folio_test_ksm(folio)); + + if (unlikely(folio_test_swapcache(folio))) { + /* + * Note: freeing up the swapcache will fail if some PTEs are + * still swap entries. + */ + if (!folio_trylock(folio)) + return false; + folio_free_swap(folio); + folio_unlock(folio); + } + + if (folio_large_mapcount(folio) != folio_ref_count(folio)) + return false; + + /* Stabilize the mapcount vs. refcount and recheck. */ + folio_lock_large_mapcount(folio); + VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio); + + if (test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids)) + goto unlock; + if (folio_large_mapcount(folio) != folio_ref_count(folio)) + goto unlock; + + VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_nr_pages(folio), folio); + VM_WARN_ON_ONCE_FOLIO(folio_entire_mapcount(folio), folio); + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != vma->vm_mm->mm_id && + folio_mm_id(folio, 1) != vma->vm_mm->mm_id); - if (new_page) - page_cache_release(new_page); + /* + * Do we need the folio lock? Likely not. If there would have been + * references from page migration/swapout, we would have detected + * an additional folio reference and never ended up here. + */ + exclusive = true; unlock: - pte_unmap_unlock(page_table, ptl); - if (mmun_end > mmun_start) - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (old_page) { + folio_unlock_large_mapcount(folio); + return exclusive; +} +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static bool __wp_can_reuse_large_anon_folio(struct folio *folio, + struct vm_area_struct *vma) +{ + BUILD_BUG(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static bool wp_can_reuse_anon_folio(struct folio *folio, + struct vm_area_struct *vma) +{ + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && folio_test_large(folio)) + return __wp_can_reuse_large_anon_folio(folio, vma); + + /* + * We have to verify under folio lock: these early checks are + * just an optimization to avoid locking the folio and freeing + * the swapcache if there is little hope that we can reuse. + * + * KSM doesn't necessarily raise the folio refcount. + */ + if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) + return false; + if (!folio_test_lru(folio)) /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. + * We cannot easily detect+handle references from + * remote LRU caches or references to LRU folios. */ - if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { - lock_page(old_page); /* LRU manipulation */ - munlock_vma_page(old_page); - unlock_page(old_page); + lru_add_drain(); + if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) + return false; + if (!folio_trylock(folio)) + return false; + if (folio_test_swapcache(folio)) + folio_free_swap(folio); + if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { + folio_unlock(folio); + return false; + } + /* + * Ok, we've got the only folio reference from our mapping + * and the folio is locked, it's dark out, and we're wearing + * sunglasses. Hit it. + */ + folio_move_anon_rmap(folio, vma); + folio_unlock(folio); + return true; +} + +/* + * This routine handles present pages, when + * * users try to write to a shared page (FAULT_FLAG_WRITE) + * * GUP wants to take a R/O pin on a possibly shared anonymous page + * (FAULT_FLAG_UNSHARE) + * + * 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, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've + * done any necessary COW. + * + * In case of FAULT_FLAG_WRITE, 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_lock (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_lock still held, but pte unmapped and unlocked. + */ +static vm_fault_t do_wp_page(struct vm_fault *vmf) + __releases(vmf->ptl) +{ + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio = NULL; + pte_t pte; + + if (likely(!unshare)) { + if (userfaultfd_pte_wp(vma, ptep_get(vmf->pte))) { + if (!userfaultfd_wp_async(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Nothing needed (cache flush, TLB invalidations, + * etc.) because we're only removing the uffd-wp bit, + * which is completely invisible to the user. + */ + pte = pte_clear_uffd_wp(ptep_get(vmf->pte)); + + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + /* + * Update this to be prepared for following up CoW + * handling + */ + vmf->orig_pte = pte; } - page_cache_release(old_page); + + /* + * Userfaultfd write-protect can defer flushes. Ensure the TLB + * is flushed in this case before copying. + */ + if (unlikely(userfaultfd_wp(vmf->vma) && + mm_tlb_flush_pending(vmf->vma->vm_mm))) + flush_tlb_page(vmf->vma, vmf->address); } - return ret; -oom_free_new: - page_cache_release(new_page); -oom: - if (old_page) - page_cache_release(old_page); - return VM_FAULT_OOM; -unwritable_page: - page_cache_release(old_page); - return ret; + vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); + + if (vmf->page) + folio = page_folio(vmf->page); + + /* + * Shared mapping: we are guaranteed to have VM_WRITE and + * FAULT_FLAG_WRITE set at this point. + */ + if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + /* + * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a + * VM_PFNMAP VMA. FS DAX also wants ops->pfn_mkwrite called. + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable and/or call ops->pfn_mkwrite. + */ + if (!vmf->page || is_fsdax_page(vmf->page)) { + vmf->page = NULL; + return wp_pfn_shared(vmf); + } + return wp_page_shared(vmf, folio); + } + + /* + * Private mapping: create an exclusive anonymous page copy if reuse + * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. + * + * If we encounter a page that is marked exclusive, we must reuse + * the page without further checks. + */ + if (folio && folio_test_anon(folio) && + (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { + if (!PageAnonExclusive(vmf->page)) + SetPageAnonExclusive(vmf->page); + if (unlikely(unshare)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + wp_page_reuse(vmf, folio); + return 0; + } + /* + * Ok, we need to copy. Oh, well.. + */ + if (folio) + folio_get(folio); + + pte_unmap_unlock(vmf->pte, vmf->ptl); +#ifdef CONFIG_KSM + if (folio && folio_test_ksm(folio)) + count_vm_event(COW_KSM); +#endif + return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, @@ -2895,24 +4187,19 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } -static inline void unmap_mapping_range_tree(struct rb_root *root, +static inline void unmap_mapping_range_tree(struct rb_root_cached *root, + pgoff_t first_index, + pgoff_t last_index, 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) { - + vma_interval_tree_foreach(vma, root, first_index, last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; - /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ - zba = details->first_index; - if (zba < vba) - zba = vba; - zea = details->last_index; - if (zea > vea) - zea = vea; + zba = max(first_index, vba); + zea = min(last_index, vea); unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, @@ -2921,25 +4208,76 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, } } -static inline void unmap_mapping_range_list(struct list_head *head, - struct zap_details *details) +/** + * unmap_mapping_folio() - Unmap single folio from processes. + * @folio: The locked folio to be unmapped. + * + * Unmap this folio from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a folio, it may find that + * the page has been remapped again: and then uses unmap_mapping_folio() + * to unmap it finally. + */ +void unmap_mapping_folio(struct folio *folio) { - struct vm_area_struct *vma; + struct address_space *mapping = folio->mapping; + struct zap_details details = { }; + pgoff_t first_index; + pgoff_t last_index; - /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. - */ - list_for_each_entry(vma, head, shared.nonlinear) { - details->nonlinear_vma = vma; - unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); - } + VM_BUG_ON(!folio_test_locked(folio)); + + first_index = folio->index; + last_index = folio_next_index(folio) - 1; + + details.even_cows = false; + details.single_folio = folio; + details.zap_flags = ZAP_FLAG_DROP_MARKER; + + i_mmap_lock_read(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); + i_mmap_unlock_read(mapping); +} + +/** + * 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 = { }; + pgoff_t first_index = start; + pgoff_t last_index = start + nr - 1; + + details.even_cows = even_cows; + if (last_index < first_index) + last_index = ULONG_MAX; + + i_mmap_lock_read(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); + i_mmap_unlock_read(mapping); } +EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** - * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified 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 @@ -2955,9 +4293,8 @@ static inline void unmap_mapping_range_list(struct list_head *head, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - struct zap_details details; - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { @@ -2967,167 +4304,715 @@ void unmap_mapping_range(struct address_space *mapping, hlen = ULONG_MAX - hba + 1; } - details.check_mapping = even_cows? NULL: mapping; - details.nonlinear_vma = NULL; - details.first_index = hba; - details.last_index = hba + hlen - 1; - if (details.last_index < details.first_index) - details.last_index = ULONG_MAX; + unmap_mapping_pages(mapping, hba, hlen, even_cows); +} +EXPORT_SYMBOL(unmap_mapping_range); + +/* + * Restore a potential device exclusive pte to a working pte entry + */ +static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) +{ + struct folio *folio = page_folio(vmf->page); + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + vm_fault_t ret; + /* + * We need a reference to lock the folio because we don't hold + * the PTL so a racing thread can remove the device-exclusive + * entry and unmap it. If the folio is free the entry must + * have been removed already. If it happens to have already + * been re-allocated after being freed all we do is lock and + * unlock it. + */ + if (!folio_try_get(folio)) + return 0; - mutex_lock(&mapping->i_mmap_mutex); - if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) - unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); - mutex_unlock(&mapping->i_mmap_mutex); + ret = folio_lock_or_retry(folio, vmf); + if (ret) { + folio_put(folio); + return ret; + } + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_CLEAR, 0, + vma->vm_mm, vmf->address & PAGE_MASK, + (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); + mmu_notifier_invalidate_range_start(&range); + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (likely(vmf->pte && pte_same(ptep_get(vmf->pte), vmf->orig_pte))) + restore_exclusive_pte(vma, folio, vmf->page, vmf->address, + vmf->pte, vmf->orig_pte); + + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); + folio_unlock(folio); + folio_put(folio); + + mmu_notifier_invalidate_range_end(&range); + return 0; +} + +static inline bool should_try_to_free_swap(struct folio *folio, + struct vm_area_struct *vma, + unsigned int fault_flags) +{ + if (!folio_test_swapcache(folio)) + return false; + if (mem_cgroup_swap_full(folio) || (vma->vm_flags & VM_LOCKED) || + folio_test_mlocked(folio)) + return true; + /* + * If we want to map a page that's in the swapcache writable, we + * have to detect via the refcount if we're really the exclusive + * user. Try freeing the swapcache to get rid of the swapcache + * reference only in case it's likely that we'll be the exclusive user. + */ + return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && + folio_ref_count(folio) == (1 + folio_nr_pages(folio)); +} + +static vm_fault_t pte_marker_clear(struct vm_fault *vmf) +{ + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (!vmf->pte) + return 0; + /* + * Be careful so that we will only recover a special uffd-wp pte into a + * none pte. Otherwise it means the pte could have changed, so retry. + * + * This should also cover the case where e.g. the pte changed + * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_POISONED. + * So pte_is_marker() check is not enough to safely drop the pte. + */ + if (pte_same(vmf->orig_pte, ptep_get(vmf->pte))) + pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; +} + +static vm_fault_t do_pte_missing(struct vm_fault *vmf) +{ + if (vma_is_anonymous(vmf->vma)) + return do_anonymous_page(vmf); + else + return do_fault(vmf); } -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 mmap_sem still held, but pte unmapped and unlocked. + * This is actually a page-missing access, but with uffd-wp special pte + * installed. It means this pte was wr-protected before being unmapped. */ -static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) +static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) { + /* + * Just in case there're leftover special ptes even after the region + * got unregistered - we can simply clear them. + */ + if (unlikely(!userfaultfd_wp(vmf->vma))) + return pte_marker_clear(vmf); + + return do_pte_missing(vmf); +} + +static vm_fault_t handle_pte_marker(struct vm_fault *vmf) +{ + const softleaf_t entry = softleaf_from_pte(vmf->orig_pte); + const pte_marker marker = softleaf_to_marker(entry); + + /* + * PTE markers should never be empty. If anything weird happened, + * the best thing to do is to kill the process along with its mm. + */ + if (WARN_ON_ONCE(!marker)) + return VM_FAULT_SIGBUS; + + /* Higher priority than uffd-wp when data corrupted */ + if (marker & PTE_MARKER_POISONED) + return VM_FAULT_HWPOISON; + + /* Hitting a guard page is always a fatal condition. */ + if (marker & PTE_MARKER_GUARD) + return VM_FAULT_SIGSEGV; + + if (softleaf_is_uffd_wp_marker(entry)) + return pte_marker_handle_uffd_wp(vmf); + + /* This is an unknown pte marker */ + return VM_FAULT_SIGBUS; +} + +static struct folio *__alloc_swap_folio(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + softleaf_t entry; + + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address); + if (!folio) + return NULL; + + entry = softleaf_from_pte(vmf->orig_pte); + if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, + GFP_KERNEL, entry)) { + folio_put(folio); + return NULL; + } + + return folio; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * Check if the PTEs within a range are contiguous swap entries + * and have consistent swapcache, zeromap. + */ +static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) +{ + unsigned long addr; + softleaf_t entry; + int idx; + pte_t pte; + + addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); + idx = (vmf->address - addr) / PAGE_SIZE; + pte = ptep_get(ptep); + + if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx))) + return false; + entry = softleaf_from_pte(pte); + if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages) + return false; + + /* + * swap_read_folio() can't handle the case a large folio is hybridly + * from different backends. And they are likely corner cases. Similar + * things might be added once zswap support large folios. + */ + if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages)) + return false; + if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages)) + return false; + + return true; +} + +static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset, + unsigned long addr, + unsigned long orders) +{ + int order, nr; + + order = highest_order(orders); + + /* + * To swap in a THP with nr pages, we require that its first swap_offset + * is aligned with that number, as it was when the THP was swapped out. + * This helps filter out most invalid entries. + */ + while (orders) { + nr = 1 << order; + if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr) + break; + order = next_order(&orders, order); + } + + return orders; +} + +static struct folio *alloc_swap_folio(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long orders; + struct folio *folio; + unsigned long addr; + softleaf_t entry; spinlock_t *ptl; - struct page *page, *swapcache; - swp_entry_t entry; + pte_t *pte; + gfp_t gfp; + int order; + + /* + * If uffd is active for the vma we need per-page fault fidelity to + * maintain the uffd semantics. + */ + if (unlikely(userfaultfd_armed(vma))) + goto fallback; + + /* + * A large swapped out folio could be partially or fully in zswap. We + * lack handling for such cases, so fallback to swapping in order-0 + * folio. + */ + if (!zswap_never_enabled()) + goto fallback; + + entry = softleaf_from_pte(vmf->orig_pte); + /* + * Get a list of all the (large) orders below PMD_ORDER that are enabled + * and suitable for swapping THP. + */ + orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_PAGEFAULT, + BIT(PMD_ORDER) - 1); + orders = thp_vma_suitable_orders(vma, vmf->address, orders); + orders = thp_swap_suitable_orders(swp_offset(entry), + vmf->address, orders); + + if (!orders) + goto fallback; + + pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address & PMD_MASK, &ptl); + if (unlikely(!pte)) + goto fallback; + + /* + * For do_swap_page, find the highest order where the aligned range is + * completely swap entries with contiguous swap offsets. + */ + order = highest_order(orders); + while (orders) { + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order)) + break; + order = next_order(&orders, order); + } + + pte_unmap_unlock(pte, ptl); + + /* Try allocating the highest of the remaining orders. */ + gfp = vma_thp_gfp_mask(vma); + while (orders) { + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + folio = vma_alloc_folio(gfp, order, vma, addr); + if (folio) { + if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, + gfp, entry)) + return folio; + count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE); + folio_put(folio); + } + count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK); + order = next_order(&orders, order); + } + +fallback: + return __alloc_swap_folio(vmf); +} +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static struct folio *alloc_swap_folio(struct vm_fault *vmf) +{ + return __alloc_swap_folio(vmf); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq); + +/* + * We enter with non-exclusive mmap_lock (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_lock 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 folio *swapcache, *folio = NULL; + DECLARE_WAITQUEUE(wait, current); + struct page *page; + struct swap_info_struct *si = NULL; + rmap_t rmap_flags = RMAP_NONE; + bool need_clear_cache = false; + bool exclusive = false; + softleaf_t entry; pte_t pte; - int locked; - struct mem_cgroup *ptr; - int exclusive = 0; - int ret = 0; + vm_fault_t ret = 0; + void *shadow = NULL; + int nr_pages; + unsigned long page_idx; + unsigned long address; + pte_t *ptep; - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + if (!pte_unmap_same(vmf)) goto out; - entry = pte_to_swp_entry(orig_pte); - if (unlikely(non_swap_entry(entry))) { - if (is_migration_entry(entry)) { - migration_entry_wait(mm, pmd, address); - } else if (is_hwpoison_entry(entry)) { + entry = softleaf_from_pte(vmf->orig_pte); + if (unlikely(!softleaf_is_swap(entry))) { + if (softleaf_is_migration(entry)) { + migration_entry_wait(vma->vm_mm, vmf->pmd, + vmf->address); + } else if (softleaf_is_device_exclusive(entry)) { + vmf->page = softleaf_to_page(entry); + ret = remove_device_exclusive_entry(vmf); + } else if (softleaf_is_device_private(entry)) { + if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + /* + * migrate_to_ram is not yet ready to operate + * under VMA lock. + */ + vma_end_read(vma); + ret = VM_FAULT_RETRY; + goto out; + } + + vmf->page = softleaf_to_page(entry); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte || + !pte_same(ptep_get(vmf->pte), + vmf->orig_pte))) + goto unlock; + + /* + * Get a page reference while we know the page can't be + * freed. + */ + if (trylock_page(vmf->page)) { + struct dev_pagemap *pgmap; + + get_page(vmf->page); + pte_unmap_unlock(vmf->pte, vmf->ptl); + pgmap = page_pgmap(vmf->page); + ret = pgmap->ops->migrate_to_ram(vmf); + unlock_page(vmf->page); + put_page(vmf->page); + } else { + pte_unmap_unlock(vmf->pte, vmf->ptl); + } + } else if (softleaf_is_hwpoison(entry)) { ret = VM_FAULT_HWPOISON; + } else if (softleaf_is_marker(entry)) { + ret = handle_pte_marker(vmf); } else { - print_bad_pte(vma, address, orig_pte, NULL); + 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); - if (!page) { - page = swapin_readahead(entry, - GFP_HIGHUSER_MOVABLE, vma, address); - if (!page) { + + /* Prevent swapoff from happening to us. */ + si = get_swap_device(entry); + if (unlikely(!si)) + goto out; + + folio = swap_cache_get_folio(entry); + if (folio) + swap_update_readahead(folio, vma, vmf->address); + swapcache = folio; + + if (!folio) { + if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + __swap_count(entry) == 1) { + /* skip swapcache */ + folio = alloc_swap_folio(vmf); + if (folio) { + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + + nr_pages = folio_nr_pages(folio); + if (folio_test_large(folio)) + entry.val = ALIGN_DOWN(entry.val, nr_pages); + /* + * Prevent parallel swapin from proceeding with + * the cache flag. Otherwise, another thread + * may finish swapin first, free the entry, and + * swapout reusing the same entry. It's + * undetectable as pte_same() returns true due + * to entry reuse. + */ + if (swapcache_prepare(entry, nr_pages)) { + /* + * Relax a bit to prevent rapid + * repeated page faults. + */ + add_wait_queue(&swapcache_wq, &wait); + schedule_timeout_uninterruptible(1); + remove_wait_queue(&swapcache_wq, &wait); + goto out_page; + } + need_clear_cache = true; + + memcg1_swapin(entry, nr_pages); + + shadow = swap_cache_get_shadow(entry); + if (shadow) + workingset_refault(folio, shadow); + + folio_add_lru(folio); + + /* To provide entry to swap_read_folio() */ + folio->swap = entry; + swap_read_folio(folio, NULL); + folio->private = NULL; + } + } else { + folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, + vmf); + swapcache = folio; + } + + if (!folio) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (likely(pte_same(*page_table, orig_pte))) + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (likely(vmf->pte && + pte_same(ptep_get(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); - mem_cgroup_count_vm_event(mm, PGMAJFAULT); - } else if (PageHWPoison(page)) { + count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); + } + + ret |= folio_lock_or_retry(folio, vmf); + if (ret & VM_FAULT_RETRY) + goto out_release; + + page = folio_file_page(folio, swp_offset(entry)); + if (swapcache) { /* - * hwpoisoned dirty swapcache pages are kept for killing - * owner processes (which may be unknown at hwpoison time) + * Make sure folio_free_swap() 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. */ - ret = VM_FAULT_HWPOISON; - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - swapcache = page; - goto out_release; - } + if (unlikely(!folio_matches_swap_entry(folio, entry))) + goto out_page; - swapcache = page; - locked = lock_page_or_retry(page, mm, flags); + if (unlikely(PageHWPoison(page))) { + /* + * hwpoisoned dirty swapcache pages are kept for killing + * owner processes (which may be unknown at hwpoison time) + */ + ret = VM_FAULT_HWPOISON; + goto out_page; + } - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - if (!locked) { - ret |= VM_FAULT_RETRY; - goto out_release; + /* + * KSM sometimes has to copy on read faults, for example, if + * folio->index of non-ksm folios would be nonlinear inside the + * anon VMA -- the ksm flag is lost on actual swapout. + */ + folio = ksm_might_need_to_copy(folio, vma, vmf->address); + if (unlikely(!folio)) { + ret = VM_FAULT_OOM; + folio = swapcache; + goto out_page; + } else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { + ret = VM_FAULT_HWPOISON; + folio = swapcache; + goto out_page; + } + if (folio != swapcache) + page = folio_page(folio, 0); + + /* + * If we want to map a page that's in the swapcache writable, we + * have to detect via the refcount if we're really the exclusive + * owner. Try removing the extra reference from the local LRU + * caches if required. + */ + if ((vmf->flags & FAULT_FLAG_WRITE) && folio == swapcache && + !folio_test_ksm(folio) && !folio_test_lru(folio)) + lru_add_drain(); } + folio_throttle_swaprate(folio, GFP_KERNEL); + /* - * 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. + * Back out if somebody else already faulted in this pte. */ - if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) - goto out_page; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (unlikely(!vmf->pte || !pte_same(ptep_get(vmf->pte), vmf->orig_pte))) + goto out_nomap; - page = ksm_might_need_to_copy(page, vma, address); - if (unlikely(!page)) { - ret = VM_FAULT_OOM; - page = swapcache; - goto out_page; + if (unlikely(!folio_test_uptodate(folio))) { + ret = VM_FAULT_SIGBUS; + goto out_nomap; } - if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { - ret = VM_FAULT_OOM; - goto out_page; + /* allocated large folios for SWP_SYNCHRONOUS_IO */ + if (folio_test_large(folio) && !folio_test_swapcache(folio)) { + unsigned long nr = folio_nr_pages(folio); + unsigned long folio_start = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE); + unsigned long idx = (vmf->address - folio_start) / PAGE_SIZE; + pte_t *folio_ptep = vmf->pte - idx; + pte_t folio_pte = ptep_get(folio_ptep); + + if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || + swap_pte_batch(folio_ptep, nr, folio_pte) != nr) + goto out_nomap; + + page_idx = idx; + address = folio_start; + ptep = folio_ptep; + goto check_folio; + } + + nr_pages = 1; + page_idx = 0; + address = vmf->address; + ptep = vmf->pte; + if (folio_test_large(folio) && folio_test_swapcache(folio)) { + int nr = folio_nr_pages(folio); + unsigned long idx = folio_page_idx(folio, page); + unsigned long folio_start = address - idx * PAGE_SIZE; + unsigned long folio_end = folio_start + nr * PAGE_SIZE; + pte_t *folio_ptep; + pte_t folio_pte; + + if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start))) + goto check_folio; + if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end))) + goto check_folio; + + folio_ptep = vmf->pte - idx; + folio_pte = ptep_get(folio_ptep); + if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) || + swap_pte_batch(folio_ptep, nr, folio_pte) != nr) + goto check_folio; + + page_idx = idx; + address = folio_start; + ptep = folio_ptep; + nr_pages = nr; + entry = folio->swap; + page = &folio->page; } +check_folio: /* - * Back out if somebody else already faulted in this pte. + * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte + * must never point at an anonymous page in the swapcache that is + * PG_anon_exclusive. Sanity check that this holds and especially, that + * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity + * check after taking the PT lock and making sure that nobody + * concurrently faulted in this page and set PG_anon_exclusive. */ - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (unlikely(!pte_same(*page_table, orig_pte))) - goto out_nomap; + BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio)); + BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page)); - if (unlikely(!PageUptodate(page))) { - ret = VM_FAULT_SIGBUS; - goto out_nomap; + /* + * Check under PT lock (to protect against concurrent fork() sharing + * the swap entry concurrently) for certainly exclusive pages. + */ + if (!folio_test_ksm(folio)) { + exclusive = pte_swp_exclusive(vmf->orig_pte); + if (folio != swapcache) { + /* + * We have a fresh page that is not exposed to the + * swapcache -> certainly exclusive. + */ + exclusive = true; + } else if (exclusive && folio_test_writeback(folio) && + data_race(si->flags & SWP_STABLE_WRITES)) { + /* + * This is tricky: not all swap backends support + * concurrent page modifications while under writeback. + * + * So if we stumble over such a page in the swapcache + * we must not set the page exclusive, otherwise we can + * map it writable without further checks and modify it + * while still under writeback. + * + * For these problematic swap backends, simply drop the + * exclusive marker: this is perfectly fine as we start + * writeback only if we fully unmapped the page and + * there are no unexpected references on the page after + * unmapping succeeded. After fully unmapped, no + * further GUP references (FOLL_GET and FOLL_PIN) can + * appear, so dropping the exclusive marker and mapping + * it only R/O is fine. + */ + exclusive = false; + } } /* - * The page isn't present yet, go ahead with the fault. - * - * Be careful about the sequence of operations here. - * To get its accounting right, reuse_swap_page() must be called - * while the page is counted on swap but not yet in mapcount i.e. - * before page_add_anon_rmap() and swap_free(); try_to_free_swap() - * must be called after the swap_free(), or it will never succeed. - * Because delete_from_swap_page() may be called by reuse_swap_page(), - * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry - * in page->private. In this case, a record in swap_cgroup is silently - * discarded at swap_free(). + * Some architectures may have to restore extra metadata to the page + * when reading from swap. This metadata may be indexed by swap entry + * so this must be called before swap_free(). */ + arch_swap_restore(folio_swap(entry, folio), folio); - inc_mm_counter_fast(mm, MM_ANONPAGES); - dec_mm_counter_fast(mm, MM_SWAPENTS); + /* + * Remove the swap entry and conditionally try to free up the swapcache. + * We're already holding a reference on the page but haven't mapped it + * yet. + */ + swap_free_nr(entry, nr_pages); + if (should_try_to_free_swap(folio, vma, vmf->flags)) + folio_free_swap(folio); + + add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); + add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages); pte = mk_pte(page, vma->vm_page_prot); - if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); - flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; - exclusive = 1; - } - flush_icache_page(vma, page); - set_pte_at(mm, address, page_table, pte); - if (page == swapcache) - do_page_add_anon_rmap(page, vma, address, exclusive); - else /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, address); - /* It's better to call commit-charge after rmap is established */ - mem_cgroup_commit_charge_swapin(page, ptr); - - swap_free(entry); - if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) - try_to_free_swap(page); - unlock_page(page); - if (page != swapcache) { + if (pte_swp_soft_dirty(vmf->orig_pte)) + pte = pte_mksoft_dirty(pte); + if (pte_swp_uffd_wp(vmf->orig_pte)) + pte = pte_mkuffd_wp(pte); + + /* + * Same logic as in do_wp_page(); however, optimize for pages that are + * certainly not shared either because we just allocated them without + * exposing them to the swapcache or because the swap entry indicates + * exclusivity. + */ + if (!folio_test_ksm(folio) && + (exclusive || folio_ref_count(folio) == 1)) { + if ((vma->vm_flags & VM_WRITE) && !userfaultfd_pte_wp(vma, pte) && + !pte_needs_soft_dirty_wp(vma, pte)) { + pte = pte_mkwrite(pte, vma); + if (vmf->flags & FAULT_FLAG_WRITE) { + pte = pte_mkdirty(pte); + vmf->flags &= ~FAULT_FLAG_WRITE; + } + } + rmap_flags |= RMAP_EXCLUSIVE; + } + folio_ref_add(folio, nr_pages - 1); + flush_icache_pages(vma, page, nr_pages); + vmf->orig_pte = pte_advance_pfn(pte, page_idx); + + /* ksm created a completely new copy */ + if (unlikely(folio != swapcache && swapcache)) { + folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + } else if (!folio_test_anon(folio)) { + /* + * We currently only expect small !anon folios which are either + * fully exclusive or fully shared, or new allocated large + * folios which are fully exclusive. If we ever get large + * folios within swapcache here, we have to be careful. + */ + VM_WARN_ON_ONCE(folio_test_large(folio) && folio_test_swapcache(folio)); + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + folio_add_new_anon_rmap(folio, vma, address, rmap_flags); + } else { + folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address, + rmap_flags); + } + + VM_BUG_ON(!folio_test_anon(folio) || + (pte_write(pte) && !PageAnonExclusive(page))); + set_ptes(vma->vm_mm, address, ptep, pte, nr_pages); + arch_do_swap_page_nr(vma->vm_mm, vma, address, + pte, pte, nr_pages); + + folio_unlock(folio); + if (folio != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check @@ -3136,551 +5021,1197 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * so that the swap count won't change under a * parallel locked swapcache. */ - unlock_page(swapcache); - page_cache_release(swapcache); + folio_unlock(swapcache); + folio_put(swapcache); } - if (flags & FAULT_FLAG_WRITE) { - ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + 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, address, page_table); + update_mmu_cache_range(vmf, vma, address, ptep, nr_pages); unlock: - pte_unmap_unlock(page_table, ptl); + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); out: + /* Clear the swap cache pin for direct swapin after PTL unlock */ + if (need_clear_cache) { + swapcache_clear(si, entry, nr_pages); + if (waitqueue_active(&swapcache_wq)) + wake_up(&swapcache_wq); + } + if (si) + put_swap_device(si); return ret; out_nomap: - mem_cgroup_cancel_charge_swapin(ptr); - pte_unmap_unlock(page_table, ptl); + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: - unlock_page(page); + folio_unlock(folio); out_release: - page_cache_release(page); - if (page != swapcache) { - unlock_page(swapcache); - page_cache_release(swapcache); + folio_put(folio); + if (folio != swapcache && swapcache) { + folio_unlock(swapcache); + folio_put(swapcache); + } + if (need_clear_cache) { + swapcache_clear(si, entry, nr_pages); + if (waitqueue_active(&swapcache_wq)) + wake_up(&swapcache_wq); } + if (si) + put_swap_device(si); return ret; } -/* - * This is like a special single-page "expand_{down|up}wards()", - * except we must first make sure that 'address{-|+}PAGE_SIZE' - * doesn't hit another vma. - */ -static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) +static bool pte_range_none(pte_t *pte, int nr_pages) { - address &= PAGE_MASK; - if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) { - struct vm_area_struct *prev = vma->vm_prev; + int i; - /* - * Is there a mapping abutting this one below? - * - * That's only ok if it's the same stack mapping - * that has gotten split.. - */ - if (prev && prev->vm_end == address) - return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; + for (i = 0; i < nr_pages; i++) { + if (!pte_none(ptep_get_lockless(pte + i))) + return false; + } + + return true; +} + +static struct folio *alloc_anon_folio(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + unsigned long orders; + struct folio *folio; + unsigned long addr; + pte_t *pte; + gfp_t gfp; + int order; - expand_downwards(vma, address - PAGE_SIZE); + /* + * If uffd is active for the vma we need per-page fault fidelity to + * maintain the uffd semantics. + */ + if (unlikely(userfaultfd_armed(vma))) + goto fallback; + + /* + * Get a list of all the (large) orders below PMD_ORDER that are enabled + * for this vma. Then filter out the orders that can't be allocated over + * the faulting address and still be fully contained in the vma. + */ + orders = thp_vma_allowable_orders(vma, vma->vm_flags, TVA_PAGEFAULT, + BIT(PMD_ORDER) - 1); + orders = thp_vma_suitable_orders(vma, vmf->address, orders); + + if (!orders) + goto fallback; + + pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK); + if (!pte) + return ERR_PTR(-EAGAIN); + + /* + * Find the highest order where the aligned range is completely + * pte_none(). Note that all remaining orders will be completely + * pte_none(). + */ + order = highest_order(orders); + while (orders) { + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + if (pte_range_none(pte + pte_index(addr), 1 << order)) + break; + order = next_order(&orders, order); } - if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { - struct vm_area_struct *next = vma->vm_next; - /* As VM_GROWSDOWN but s/below/above/ */ - if (next && next->vm_start == address + PAGE_SIZE) - return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; + pte_unmap(pte); + + if (!orders) + goto fallback; - expand_upwards(vma, address + PAGE_SIZE); + /* Try allocating the highest of the remaining orders. */ + gfp = vma_thp_gfp_mask(vma); + while (orders) { + addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); + folio = vma_alloc_folio(gfp, order, vma, addr); + if (folio) { + if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + folio_put(folio); + goto next; + } + folio_throttle_swaprate(folio, gfp); + /* + * When a folio is not zeroed during allocation + * (__GFP_ZERO not used) or user folios require special + * handling, folio_zero_user() is used to make sure + * that the page corresponding to the faulting address + * will be hot in the cache after zeroing. + */ + if (user_alloc_needs_zeroing()) + folio_zero_user(folio, vmf->address); + return folio; + } +next: + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + order = next_order(&orders, order); } - return 0; + +fallback: +#endif + return folio_prealloc(vma->vm_mm, vma, vmf->address, true); } /* - * We enter with non-exclusive mmap_sem (to exclude vma changes, + * We enter with non-exclusive mmap_lock (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. + * We return with mmap_lock still held, but pte unmapped and unlocked. */ -static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags) +static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { - struct page *page; - spinlock_t *ptl; + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address; + struct folio *folio; + vm_fault_t ret = 0; + int nr_pages = 1; pte_t entry; - pte_unmap(page_table); - - /* Check if we need to add a guard page to the stack */ - if (check_stack_guard_page(vma, address) < 0) + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; + /* + * Use pte_alloc() instead of pte_alloc_map(), so that OOM can + * be distinguished from a transient failure of pte_offset_map(). + */ + if (pte_alloc(vma->vm_mm, vmf->pmd)) + return VM_FAULT_OOM; + /* Use the zero-page for reads */ - if (!(flags & FAULT_FLAG_WRITE)) { - entry = pte_mkspecial(pfn_pte(my_zero_pfn(address), + 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)); - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!pte_none(*page_table)) + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (!vmf->pte) + goto unlock; + if (vmf_pte_changed(vmf)) { + update_mmu_tlb(vma, vmf->address, 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, address); - if (!page) + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; + /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ + folio = alloc_anon_folio(vmf); + if (IS_ERR(folio)) + return 0; + if (!folio) goto oom; + + nr_pages = folio_nr_pages(folio); + addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE); + /* - * The memory barrier inside __SetPageUptodate makes sure that - * preceeding stores to the page contents become visible before + * The memory barrier inside __folio_mark_uptodate makes sure that + * preceding stores to the page contents become visible before * the set_pte_at() write. */ - __SetPageUptodate(page); + __folio_mark_uptodate(folio); - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) - goto oom_free_page; - - entry = mk_pte(page, vma->vm_page_prot); + entry = folio_mk_pte(folio, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) - entry = pte_mkwrite(pte_mkdirty(entry)); + entry = pte_mkwrite(pte_mkdirty(entry), vma); + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); + if (!vmf->pte) + goto release; + if (nr_pages == 1 && vmf_pte_changed(vmf)) { + update_mmu_tlb(vma, addr, vmf->pte); + goto release; + } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { + update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); + goto release; + } - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!pte_none(*page_table)) + ret = check_stable_address_space(vma->vm_mm); + if (ret) goto release; - inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); + /* Deliver the page fault to userland, check inside PT lock */ + if (userfaultfd_missing(vma)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + folio_put(folio); + return handle_userfault(vmf, VM_UFFD_MISSING); + } + + folio_ref_add(folio, nr_pages - 1); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); + count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); + folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); setpte: - set_pte_at(mm, address, page_table, entry); + if (vmf_orig_pte_uffd_wp(vmf)) + entry = pte_mkuffd_wp(entry); + set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, address, page_table); + update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages); unlock: - pte_unmap_unlock(page_table, ptl); - return 0; + if (vmf->pte) + pte_unmap_unlock(vmf->pte, vmf->ptl); + return ret; release: - mem_cgroup_uncharge_page(page); - page_cache_release(page); + folio_put(folio); goto unlock; -oom_free_page: - page_cache_release(page); oom: return VM_FAULT_OOM; } /* - * __do_fault() tries to create a new page mapping. It aggressively - * tries to share with existing pages, but makes a separate copy if - * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid - * the next page fault. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte neither mapped nor locked. - * We return with mmap_sem still held, but pte unmapped and unlocked. + * The mmap_lock 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 int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +static vm_fault_t __do_fault(struct vm_fault *vmf) { - pte_t *page_table; - spinlock_t *ptl; - struct page *page; - struct page *cow_page; - pte_t entry; - int anon = 0; - struct page *dirty_page = NULL; - struct vm_fault vmf; - int ret; - int page_mkwrite = 0; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + vm_fault_t ret; /* - * If we do COW later, allocate page befor taking lock_page() - * on the file cache page. This will reduce lock holding time. + * 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_one + * shrink_folio_list + * wait_on_page_writeback(A) + * SetPageWriteback(B) + * unlock_page(B) + * # flush A, B to clear the writeback */ - if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { - - if (unlikely(anon_vma_prepare(vma))) + if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); + if (!vmf->prealloc_pte) return VM_FAULT_OOM; + } - cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (!cow_page) - return VM_FAULT_OOM; + 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 (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) { - page_cache_release(cow_page); - return VM_FAULT_OOM; + folio = page_folio(vmf->page); + if (unlikely(PageHWPoison(vmf->page))) { + vm_fault_t poisonret = VM_FAULT_HWPOISON; + if (ret & VM_FAULT_LOCKED) { + if (page_mapped(vmf->page)) + unmap_mapping_folio(folio); + /* Retry if a clean folio was removed from the cache. */ + if (mapping_evict_folio(folio->mapping, folio)) + poisonret = VM_FAULT_NOPAGE; + folio_unlock(folio); } - } else - cow_page = NULL; + folio_put(folio); + vmf->page = NULL; + return poisonret; + } - vmf.virtual_address = (void __user *)(address & PAGE_MASK); - vmf.pgoff = pgoff; - vmf.flags = flags; - vmf.page = NULL; + if (unlikely(!(ret & VM_FAULT_LOCKED))) + folio_lock(folio); + else + VM_BUG_ON_PAGE(!folio_test_locked(folio), vmf->page); - ret = vma->vm_ops->fault(vma, &vmf); - if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | - VM_FAULT_RETRY))) - goto uncharge_out; + return ret; +} - if (unlikely(PageHWPoison(vmf.page))) { - if (ret & VM_FAULT_LOCKED) - unlock_page(vmf.page); - ret = VM_FAULT_HWPOISON; - goto uncharge_out; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void deposit_prealloc_pte(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); + /* + * We are going to consume the prealloc table, + * count that as nr_ptes. + */ + mm_inc_nr_ptes(vma->vm_mm); + vmf->prealloc_pte = NULL; +} + +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page) +{ + struct vm_area_struct *vma = vmf->vma; + bool write = vmf->flags & FAULT_FLAG_WRITE; + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + pmd_t entry; + vm_fault_t ret = VM_FAULT_FALLBACK; + + /* + * It is too late to allocate a small folio, we already have a large + * folio in the pagecache: especially s390 KVM cannot tolerate any + * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any + * PMD mappings if THPs are disabled. As we already have a THP, + * behave as if we are forcing a collapse. + */ + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags, + /* forced_collapse=*/ true)) + return ret; + + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) + return ret; + + if (folio_order(folio) != HPAGE_PMD_ORDER) + return ret; + page = &folio->page; + + /* + * Just backoff if any subpage of a THP is corrupted otherwise + * the corrupted page may mapped by PMD silently to escape the + * check. This kind of THP just can be PTE mapped. Access to + * the corrupted subpage should trigger SIGBUS as expected. + */ + if (unlikely(folio_test_has_hwpoisoned(folio))) + return ret; + + /* + * Archs like ppc64 need additional space to store information + * related to pte entry. Use the preallocated table for that. + */ + if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); + if (!vmf->prealloc_pte) + return VM_FAULT_OOM; } + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_none(*vmf->pmd))) + goto out; + + flush_icache_pages(vma, page, HPAGE_PMD_NR); + + entry = folio_mk_pmd(folio, vma->vm_page_prot); + if (write) + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + + add_mm_counter(vma->vm_mm, mm_counter_file(folio), HPAGE_PMD_NR); + folio_add_file_rmap_pmd(folio, page, vma); + /* - * For consistency in subsequent calls, make the faulted page always - * locked. + * deposit and withdraw with pmd lock held */ - if (unlikely(!(ret & VM_FAULT_LOCKED))) - lock_page(vmf.page); + if (arch_needs_pgtable_deposit()) + deposit_prealloc_pte(vmf); + + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); + + update_mmu_cache_pmd(vma, haddr, vmf->pmd); + + /* fault is handled */ + ret = 0; + count_vm_event(THP_FILE_MAPPED); +out: + spin_unlock(vmf->ptl); + return ret; +} +#else +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page) +{ + return VM_FAULT_FALLBACK; +} +#endif + +/** + * set_pte_range - Set a range of PTEs to point to pages in a folio. + * @vmf: Fault description. + * @folio: The folio that contains @page. + * @page: The first page to create a PTE for. + * @nr: The number of PTEs to create. + * @addr: The first address to create a PTE for. + */ +void set_pte_range(struct vm_fault *vmf, struct folio *folio, + struct page *page, unsigned int nr, unsigned long addr) +{ + struct vm_area_struct *vma = vmf->vma; + bool write = vmf->flags & FAULT_FLAG_WRITE; + bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); + pte_t entry; + + flush_icache_pages(vma, page, nr); + entry = mk_pte(page, vma->vm_page_prot); + + if (prefault && arch_wants_old_prefaulted_pte()) + entry = pte_mkold(entry); else - VM_BUG_ON(!PageLocked(vmf.page)); + entry = pte_sw_mkyoung(entry); + + if (write) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + else if (pte_write(entry) && folio_test_dirty(folio)) + entry = pte_mkdirty(entry); + if (unlikely(vmf_orig_pte_uffd_wp(vmf))) + entry = pte_mkuffd_wp(entry); + /* copy-on-write page */ + if (write && !(vma->vm_flags & VM_SHARED)) { + VM_BUG_ON_FOLIO(nr != 1, folio); + folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + } else { + folio_add_file_rmap_ptes(folio, page, nr, vma); + } + set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr); +} + +static bool vmf_pte_changed(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) + return !pte_same(ptep_get(vmf->pte), vmf->orig_pte); + + return !pte_none(ptep_get(vmf->pte)); +} +/** + * finish_fault - finish page fault once we have prepared the page to fault + * + * @vmf: structure describing the fault + * + * This function handles all that is needed to finish a page fault once the + * page to fault in is prepared. It handles locking of PTEs, inserts PTE for + * given page, adds reverse page mapping, handles memcg charges and LRU + * addition. + * + * The function expects the page to be locked and on success it consumes a + * reference of a page being mapped (for the PTE which maps it). + * + * Return: %0 on success, %VM_FAULT_ code in case of error. + */ +vm_fault_t finish_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct page *page; + struct folio *folio; + vm_fault_t ret; + bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && + !(vma->vm_flags & VM_SHARED); + int type, nr_pages; + unsigned long addr; + bool needs_fallback = false; + +fallback: + addr = vmf->address; + + /* Did we COW the page? */ + if (is_cow) + page = vmf->cow_page; + else + page = vmf->page; + + folio = page_folio(page); /* - * Should we do an early C-O-W break? + * check even for read faults because we might have lost our CoWed + * page */ - page = vmf.page; - if (flags & FAULT_FLAG_WRITE) { - if (!(vma->vm_flags & VM_SHARED)) { - page = cow_page; - anon = 1; - copy_user_highpage(page, vmf.page, address, vma); - __SetPageUptodate(page); + if (!(vma->vm_flags & VM_SHARED)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) + return ret; + } + + if (!needs_fallback && vma->vm_file) { + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t file_end; + + file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); + + /* + * Do not allow to map with PTEs beyond i_size and with PMD + * across i_size to preserve SIGBUS semantics. + * + * Make an exception for shmem/tmpfs that for long time + * intentionally mapped with PMDs across i_size. + */ + needs_fallback = !shmem_mapping(mapping) && + file_end < folio_next_index(folio); + } + + if (pmd_none(*vmf->pmd)) { + if (!needs_fallback && folio_test_pmd_mappable(folio)) { + ret = do_set_pmd(vmf, folio, page); + if (ret != VM_FAULT_FALLBACK) + return ret; + } + + if (vmf->prealloc_pte) + pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); + else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) + return VM_FAULT_OOM; + } + + nr_pages = folio_nr_pages(folio); + + /* Using per-page fault to maintain the uffd semantics */ + if (unlikely(userfaultfd_armed(vma)) || unlikely(needs_fallback)) { + nr_pages = 1; + } else if (nr_pages > 1) { + pgoff_t idx = folio_page_idx(folio, page); + /* The page offset of vmf->address within the VMA. */ + pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; + /* The index of the entry in the pagetable for fault page. */ + pgoff_t pte_off = pte_index(vmf->address); + + /* + * Fallback to per-page fault in case the folio size in page + * cache beyond the VMA limits and PMD pagetable limits. + */ + if (unlikely(vma_off < idx || + vma_off + (nr_pages - idx) > vma_pages(vma) || + pte_off < idx || + pte_off + (nr_pages - idx) > PTRS_PER_PTE)) { + nr_pages = 1; } else { - /* - * If the page will be shareable, see if the backing - * address space wants to know that the page is about - * to become writable - */ - if (vma->vm_ops->page_mkwrite) { - int tmp; - - unlock_page(page); - vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; - tmp = vma->vm_ops->page_mkwrite(vma, &vmf); - if (unlikely(tmp & - (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { - ret = tmp; - goto unwritable_page; - } - if (unlikely(!(tmp & VM_FAULT_LOCKED))) { - lock_page(page); - if (!page->mapping) { - ret = 0; /* retry the fault */ - unlock_page(page); - goto unwritable_page; - } - } else - VM_BUG_ON(!PageLocked(page)); - page_mkwrite = 1; - } + /* Now we can set mappings for the whole large folio. */ + addr = vmf->address - idx * PAGE_SIZE; + page = &folio->page; } + } + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + addr, &vmf->ptl); + if (!vmf->pte) + return VM_FAULT_NOPAGE; + /* Re-check under ptl */ + if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) { + update_mmu_tlb(vma, addr, vmf->pte); + ret = VM_FAULT_NOPAGE; + goto unlock; + } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { + needs_fallback = true; + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto fallback; } - page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + folio_ref_add(folio, nr_pages - 1); + set_pte_range(vmf, folio, page, nr_pages, addr); + type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); + add_mm_counter(vma->vm_mm, type, nr_pages); + ret = 0; + +unlock: + pte_unmap_unlock(vmf->pte, vmf->ptl); + return ret; +} + +static unsigned long fault_around_pages __read_mostly = + 65536 >> PAGE_SHIFT; + +#ifdef CONFIG_DEBUG_FS +static int fault_around_bytes_get(void *data, u64 *val) +{ + *val = fault_around_pages << PAGE_SHIFT; + return 0; +} + +/* + * fault_around_bytes must be rounded down to the nearest page order as it's + * what do_fault_around() expects to see. + */ +static int fault_around_bytes_set(void *data, u64 val) +{ + if (val / PAGE_SIZE > PTRS_PER_PTE) + return -EINVAL; /* - * This silly early PAGE_DIRTY setting removes a race - * due to the bad i386 page protection. But it's valid - * for other architectures too. - * - * Note that if FAULT_FLAG_WRITE is set, we either now have - * an exclusive copy of the page, or this is a shared mapping, - * so we can make it writable and dirty to avoid having to - * handle that later. + * The minimum value is 1 page, however this results in no fault-around + * at all. See should_fault_around(). */ - /* Only go through if we didn't race with anybody else... */ - if (likely(pte_same(*page_table, orig_pte))) { - flush_icache_page(vma, page); - entry = mk_pte(page, vma->vm_page_prot); - if (flags & FAULT_FLAG_WRITE) - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (anon) { - inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); - } else { - inc_mm_counter_fast(mm, MM_FILEPAGES); - page_add_file_rmap(page); - if (flags & FAULT_FLAG_WRITE) { - dirty_page = page; - get_page(dirty_page); - } - } - set_pte_at(mm, address, page_table, entry); + val = max(val, PAGE_SIZE); + fault_around_pages = rounddown_pow_of_two(val) >> PAGE_SHIFT; - /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, address, page_table); - } else { - if (cow_page) - mem_cgroup_uncharge_page(cow_page); - if (anon) - page_cache_release(page); - else - anon = 1; /* no anon but release faulted_page */ + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, + fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); + +static int __init fault_around_debugfs(void) +{ + debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, + &fault_around_bytes_fops); + return 0; +} +late_initcall(fault_around_debugfs); +#endif + +/* + * do_fault_around() tries to map few pages around the fault address. The hope + * is that the pages will be needed soon and this will lower the number of + * faults to handle. + * + * It uses vm_ops->map_pages() to map the pages, which skips the page if it's + * not ready to be mapped: not up-to-date, locked, etc. + * + * This function doesn't cross VMA or page table boundaries, in order to call + * map_pages() and acquire a PTE lock only once. + * + * fault_around_pages defines how many pages we'll try to map. + * do_fault_around() expects it to be set to a power of two less than or equal + * to PTRS_PER_PTE. + * + * The virtual address of the area that we map is naturally aligned to + * fault_around_pages * PAGE_SIZE rounded down to the machine page size + * (and therefore to page order). This way it's easier to guarantee + * that we don't cross page table boundaries. + */ +static vm_fault_t do_fault_around(struct vm_fault *vmf) +{ + pgoff_t nr_pages = READ_ONCE(fault_around_pages); + pgoff_t pte_off = pte_index(vmf->address); + /* The page offset of vmf->address within the VMA. */ + pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; + pgoff_t from_pte, to_pte; + vm_fault_t ret; + + /* The PTE offset of the start address, clamped to the VMA. */ + from_pte = max(ALIGN_DOWN(pte_off, nr_pages), + pte_off - min(pte_off, vma_off)); + + /* The PTE offset of the end address, clamped to the VMA and PTE. */ + to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE, + pte_off + vma_pages(vmf->vma) - vma_off) - 1; + + if (pmd_none(*vmf->pmd)) { + vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); + if (!vmf->prealloc_pte) + return VM_FAULT_OOM; } - pte_unmap_unlock(page_table, ptl); + rcu_read_lock(); + ret = vmf->vma->vm_ops->map_pages(vmf, + vmf->pgoff + from_pte - pte_off, + vmf->pgoff + to_pte - pte_off); + rcu_read_unlock(); - if (dirty_page) { - struct address_space *mapping = page->mapping; - int dirtied = 0; + return ret; +} - if (set_page_dirty(dirty_page)) - dirtied = 1; - unlock_page(dirty_page); - put_page(dirty_page); - if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping but still - * dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } +/* Return true if we should do read fault-around, false otherwise */ +static inline bool should_fault_around(struct vm_fault *vmf) +{ + /* No ->map_pages? No way to fault around... */ + if (!vmf->vma->vm_ops->map_pages) + return false; - /* file_update_time outside page_lock */ - if (vma->vm_file && !page_mkwrite) - file_update_time(vma->vm_file); - } else { - unlock_page(vmf.page); - if (anon) - page_cache_release(vmf.page); + if (uffd_disable_fault_around(vmf->vma)) + return false; + + /* A single page implies no faulting 'around' at all. */ + return fault_around_pages > 1; +} + +static vm_fault_t do_read_fault(struct vm_fault *vmf) +{ + vm_fault_t ret = 0; + struct folio *folio; + + /* + * Let's call ->map_pages() first and use ->fault() as fallback + * if page by the offset is not ready to be mapped (cold cache or + * something). + */ + if (should_fault_around(vmf)) { + ret = do_fault_around(vmf); + if (ret) + return ret; } + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; + + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + ret |= finish_fault(vmf); + folio = page_folio(vmf->page); + folio_unlock(folio); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + folio_put(folio); return ret; +} + +static vm_fault_t do_cow_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + vm_fault_t ret; + + ret = vmf_can_call_fault(vmf); + if (!ret) + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; + + folio = folio_prealloc(vma->vm_mm, vma, vmf->address, false); + if (!folio) + return VM_FAULT_OOM; + + vmf->cow_page = &folio->page; + + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; + if (ret & VM_FAULT_DONE_COW) + return ret; -unwritable_page: - page_cache_release(page); + if (copy_mc_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma)) { + ret = VM_FAULT_HWPOISON; + goto unlock; + } + __folio_mark_uptodate(folio); + + ret |= finish_fault(vmf); +unlock: + unlock_page(vmf->page); + put_page(vmf->page); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + goto uncharge_out; return ret; uncharge_out: - /* fs's fault handler get error */ - if (cow_page) { - mem_cgroup_uncharge_page(cow_page); - page_cache_release(cow_page); - } + folio_put(folio); return ret; } -static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) +static vm_fault_t do_shared_fault(struct vm_fault *vmf) { - pgoff_t pgoff = (((address & PAGE_MASK) - - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret, tmp; + struct folio *folio; + + ret = vmf_can_call_fault(vmf); + if (ret) + return ret; - pte_unmap(page_table); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + ret = __do_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) + return ret; + + folio = page_folio(vmf->page); + + /* + * Check if the backing address space wants to know that the page is + * about to become writable + */ + if (vma->vm_ops->page_mkwrite) { + folio_unlock(folio); + tmp = do_page_mkwrite(vmf, folio); + if (unlikely(!tmp || + (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { + folio_put(folio); + return tmp; + } + } + + ret |= finish_fault(vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | + VM_FAULT_RETRY))) { + folio_unlock(folio); + folio_put(folio); + return ret; + } + + ret |= fault_dirty_shared_page(vmf); + return ret; } /* - * Fault of a previously existing named mapping. Repopulate the pte - * from the encoded file_pte if possible. This enables swappable - * nonlinear vmas. - * - * 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. + * We enter with non-exclusive mmap_lock (to exclude vma changes, + * but allow concurrent faults). + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __folio_lock_or_retry(). + * If mmap_lock is released, vma may become invalid (for example + * by other thread calling munmap()). */ -static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) +static vm_fault_t do_fault(struct vm_fault *vmf) { - pgoff_t pgoff; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *vm_mm = vma->vm_mm; + vm_fault_t ret; - flags |= FAULT_FLAG_NONLINEAR; + /* + * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND + */ + if (!vma->vm_ops->fault) { + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + ret = VM_FAULT_SIGBUS; + else { + /* + * Make sure this is not a temporary clearing of pte + * by holding ptl and checking again. A R/M/W update + * of pte involves: take ptl, clearing the pte so that + * we don't have concurrent modification by hardware + * followed by an update. + */ + if (unlikely(pte_none(ptep_get(vmf->pte)))) + ret = VM_FAULT_SIGBUS; + else + ret = VM_FAULT_NOPAGE; - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return 0; + pte_unmap_unlock(vmf->pte, vmf->ptl); + } + } else if (!(vmf->flags & FAULT_FLAG_WRITE)) + ret = do_read_fault(vmf); + else if (!(vma->vm_flags & VM_SHARED)) + ret = do_cow_fault(vmf); + else + ret = do_shared_fault(vmf); - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_SIGBUS; + /* preallocated pagetable is unused: free it */ + if (vmf->prealloc_pte) { + pte_free(vm_mm, vmf->prealloc_pte); + vmf->prealloc_pte = NULL; } - - pgoff = pte_to_pgoff(orig_pte); - return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); + return ret; } -int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int current_nid) +int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, + unsigned long addr, int *flags, + bool writable, int *last_cpupid) { - get_page(page); + struct vm_area_struct *vma = vmf->vma; + + /* + * Avoid grouping on RO pages in general. RO pages shouldn't hurt as + * much anyway since they can be in shared cache state. This misses + * the case where a mapping is writable but the process never writes + * to it but pte_write gets cleared during protection updates and + * pte_dirty has unpredictable behaviour between PTE scan updates, + * background writeback, dirty balancing and application behaviour. + */ + if (!writable) + *flags |= TNF_NO_GROUP; + + /* + * Flag if the folio is shared between multiple address spaces. This + * is later used when determining whether to group tasks together + */ + if (folio_maybe_mapped_shared(folio) && (vma->vm_flags & VM_SHARED)) + *flags |= TNF_SHARED; + /* + * For memory tiering mode, cpupid of slow memory page is used + * to record page access time. So use default value. + */ + if (folio_use_access_time(folio)) + *last_cpupid = (-1 & LAST_CPUPID_MASK); + else + *last_cpupid = folio_last_cpupid(folio); + + /* Record the current PID acceesing VMA */ + vma_set_access_pid_bit(vma); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) +#ifdef CONFIG_NUMA_BALANCING + count_memcg_folio_events(folio, NUMA_HINT_FAULTS, 1); +#endif + if (folio_nid(folio) == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + *flags |= TNF_FAULT_LOCAL; + } - return mpol_misplaced(page, vma, addr); + return mpol_misplaced(folio, vmf, addr); } -int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd) +static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long fault_addr, pte_t *fault_pte, + bool writable) { - struct page *page = NULL; - spinlock_t *ptl; - int current_nid = -1; - int target_nid; - bool migrated = false; + pte_t pte, old_pte; + + old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte); + pte = pte_modify(old_pte, vma->vm_page_prot); + pte = pte_mkyoung(pte); + if (writable) + pte = pte_mkwrite(pte, vma); + ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte); + update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1); +} - /* - * The "pte" at this point cannot be used safely without - * validation through pte_unmap_same(). It's of NUMA type but - * the pfn may be screwed if the read is non atomic. - * - * ptep_modify_prot_start is not called as this is clearing - * the _PAGE_NUMA bit and it is not really expected that there - * would be concurrent hardware modifications to the PTE. - */ - ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - if (unlikely(!pte_same(*ptep, pte))) { - pte_unmap_unlock(ptep, ptl); - goto out; +static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, + struct folio *folio, pte_t fault_pte, + bool ignore_writable, bool pte_write_upgrade) +{ + int nr = pte_pfn(fault_pte) - folio_pfn(folio); + unsigned long start, end, addr = vmf->address; + unsigned long addr_start = addr - (nr << PAGE_SHIFT); + unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); + pte_t *start_ptep; + + /* Stay within the VMA and within the page table. */ + start = max3(addr_start, pt_start, vma->vm_start); + end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, + vma->vm_end); + start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); + + /* Restore all PTEs' mapping of the large folio */ + for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { + pte_t ptent = ptep_get(start_ptep); + bool writable = false; + + if (!pte_present(ptent) || !pte_protnone(ptent)) + continue; + + if (pfn_folio(pte_pfn(ptent)) != folio) + continue; + + if (!ignore_writable) { + ptent = pte_modify(ptent, vma->vm_page_prot); + writable = pte_write(ptent); + if (!writable && pte_write_upgrade && + can_change_pte_writable(vma, addr, ptent)) + writable = true; + } + + numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable); } +} - pte = pte_mknonnuma(pte); - set_pte_at(mm, addr, ptep, pte); - update_mmu_cache(vma, addr, ptep); +static vm_fault_t do_numa_page(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct folio *folio = NULL; + int nid = NUMA_NO_NODE; + bool writable = false, ignore_writable = false; + bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma); + int last_cpupid; + int target_nid; + pte_t pte, old_pte; + int flags = 0, nr_pages; - page = vm_normal_page(vma, addr, pte); - if (!page) { - pte_unmap_unlock(ptep, ptl); + /* + * The pte cannot be used safely until we verify, while holding the page + * table lock, that its contents have not changed during fault handling. + */ + spin_lock(vmf->ptl); + /* Read the live PTE from the page tables: */ + old_pte = ptep_get(vmf->pte); + + if (unlikely(!pte_same(old_pte, vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } - current_nid = page_to_nid(page); - target_nid = numa_migrate_prep(page, vma, addr, current_nid); - pte_unmap_unlock(ptep, ptl); - if (target_nid == -1) { - /* - * Account for the fault against the current node if it not - * being replaced regardless of where the page is located. - */ - current_nid = numa_node_id(); - put_page(page); - goto out; + pte = pte_modify(old_pte, vma->vm_page_prot); + + /* + * Detect now whether the PTE could be writable; this information + * is only valid while holding the PT lock. + */ + writable = pte_write(pte); + if (!writable && pte_write_upgrade && + can_change_pte_writable(vma, vmf->address, pte)) + writable = true; + + folio = vm_normal_folio(vma, vmf->address, pte); + if (!folio || folio_is_zone_device(folio)) + goto out_map; + + nid = folio_nid(folio); + nr_pages = folio_nr_pages(folio); + + target_nid = numa_migrate_check(folio, vmf, vmf->address, &flags, + writable, &last_cpupid); + if (target_nid == NUMA_NO_NODE) + goto out_map; + if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) { + flags |= TNF_MIGRATE_FAIL; + goto out_map; } + /* The folio is isolated and isolation code holds a folio reference. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + writable = false; + ignore_writable = true; /* Migrate to the requested node */ - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - current_nid = target_nid; + if (!migrate_misplaced_folio(folio, target_nid)) { + nid = target_nid; + flags |= TNF_MIGRATED; + task_numa_fault(last_cpupid, nid, nr_pages, flags); + return 0; + } -out: - if (current_nid != -1) - task_numa_fault(current_nid, 1, migrated); + flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } +out_map: + /* + * Make it present again, depending on how arch implements + * non-accessible ptes, some can allow access by kernel mode. + */ + if (folio && folio_test_large(folio)) + numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable, + pte_write_upgrade); + else + numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, + writable); + pte_unmap_unlock(vmf->pte, vmf->ptl); + + if (nid != NUMA_NO_NODE) + task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; } -/* NUMA hinting page fault entry point for regular pmds */ -#ifdef CONFIG_NUMA_BALANCING -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) +static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { - pmd_t pmd; - pte_t *pte, *orig_pte; - unsigned long _addr = addr & PMD_MASK; - unsigned long offset; - spinlock_t *ptl; - bool numa = false; - int local_nid = numa_node_id(); - - spin_lock(&mm->page_table_lock); - pmd = *pmdp; - if (pmd_numa(pmd)) { - set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd)); - numa = true; - } - spin_unlock(&mm->page_table_lock); - - if (!numa) - return 0; + struct vm_area_struct *vma = vmf->vma; + if (vma_is_anonymous(vma)) + return do_huge_pmd_anonymous_page(vmf); + if (vma->vm_ops->huge_fault) + return vma->vm_ops->huge_fault(vmf, PMD_ORDER); + return VM_FAULT_FALLBACK; +} - /* we're in a page fault so some vma must be in the range */ - BUG_ON(!vma); - BUG_ON(vma->vm_start >= _addr + PMD_SIZE); - offset = max(_addr, vma->vm_start) & ~PMD_MASK; - VM_BUG_ON(offset >= PMD_SIZE); - orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl); - pte += offset >> PAGE_SHIFT; - for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { - pte_t pteval = *pte; - struct page *page; - int curr_nid = local_nid; - int target_nid; - bool migrated; - if (!pte_present(pteval)) - continue; - if (!pte_numa(pteval)) - continue; - if (addr >= vma->vm_end) { - vma = find_vma(mm, addr); - /* there's a pte present so there must be a vma */ - BUG_ON(!vma); - BUG_ON(addr < vma->vm_start); - } - if (pte_numa(pteval)) { - pteval = pte_mknonnuma(pteval); - set_pte_at(mm, addr, pte, pteval); +/* `inline' is required to avoid gcc 4.1.2 build error */ +static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + vm_fault_t ret; + + if (vma_is_anonymous(vma)) { + if (likely(!unshare) && + userfaultfd_huge_pmd_wp(vma, vmf->orig_pmd)) { + if (userfaultfd_wp_async(vmf->vma)) + goto split; + return handle_userfault(vmf, VM_UFFD_WP); } - page = vm_normal_page(vma, addr, pteval); - if (unlikely(!page)) - continue; - /* only check non-shared pages */ - if (unlikely(page_mapcount(page) != 1)) - continue; + return do_huge_pmd_wp_page(vmf); + } - /* - * Note that the NUMA fault is later accounted to either - * the node that is currently running or where the page is - * migrated to. - */ - curr_nid = local_nid; - target_nid = numa_migrate_prep(page, vma, addr, - page_to_nid(page)); - if (target_nid == -1) { - put_page(page); - continue; + if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + if (vma->vm_ops->huge_fault) { + ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } + } - /* Migrate to the requested node */ - pte_unmap_unlock(pte, ptl); - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - curr_nid = target_nid; - task_numa_fault(curr_nid, 1, migrated); +split: + /* COW or write-notify handled on pte level: split pmd. */ + __split_huge_pmd(vma, vmf->pmd, vmf->address, false); - pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); - } - pte_unmap_unlock(orig_pte, ptl); + return VM_FAULT_FALLBACK; +} - return 0; +static vm_fault_t create_huge_pud(struct vm_fault *vmf) +{ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + struct vm_area_struct *vma = vmf->vma; + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vma)) + return VM_FAULT_FALLBACK; + if (vma->vm_ops->huge_fault) + return vma->vm_ops->huge_fault(vmf, PUD_ORDER); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + return VM_FAULT_FALLBACK; } -#else -static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp) + +static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { - BUG(); - return 0; +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret; + + /* No support for anonymous transparent PUD pages yet */ + if (vma_is_anonymous(vma)) + goto split; + if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { + if (vma->vm_ops->huge_fault) { + ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } + } +split: + /* COW or write-notify not handled on PUD level: split pud.*/ + __split_huge_pud(vma, vmf->pud, vmf->address); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + return VM_FAULT_FALLBACK; } -#endif /* CONFIG_NUMA_BALANCING */ /* + * The page faults may be spurious because of the racy access to the + * page table. For example, a non-populated virtual page is accessed + * on 2 CPUs simultaneously, thus the page faults are triggered on + * both CPUs. However, it's possible that one CPU (say CPU A) cannot + * find the reason for the page fault if the other CPU (say CPU B) has + * changed the page table before the PTE is checked on CPU A. Most of + * the time, the spurious page faults can be ignored safely. However, + * if the page fault is for the write access, it's possible that a + * stale read-only TLB entry exists in the local CPU and needs to be + * flushed on some architectures. This is called the spurious page + * fault fixing. + * + * Note: flush_tlb_fix_spurious_fault() is defined as flush_tlb_page() + * by default and used as such on most architectures, while + * flush_tlb_fix_spurious_fault_pmd() is defined as NOP by default and + * used as such on most architectures. + */ +static void fix_spurious_fault(struct vm_fault *vmf, + enum pgtable_level ptlevel) +{ + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + return; + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (vmf->flags & FAULT_FLAG_WRITE) { + if (ptlevel == PGTABLE_LEVEL_PTE) + flush_tlb_fix_spurious_fault(vmf->vma, vmf->address, + vmf->pte); + else + flush_tlb_fix_spurious_fault_pmd(vmf->vma, vmf->address, + vmf->pmd); + } +} +/* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. @@ -3689,183 +6220,436 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * - * 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. + * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow + * concurrent faults). + * + * The mmap_lock may have been released depending on flags and our return value. + * See filemap_fault() and __folio_lock_or_retry(). */ -int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - pte_t *pte, pmd_t *pmd, unsigned int flags) +static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; - spinlock_t *ptl; - entry = *pte; - if (!pte_present(entry)) { - if (pte_none(entry)) { - if (vma->vm_ops) { - if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, - pte, pmd, flags, entry); - } - return do_anonymous_page(mm, vma, address, - pte, pmd, flags); + if (unlikely(pmd_none(*vmf->pmd))) { + /* + * Leave __pte_alloc() until later: because vm_ops->fault may + * want to allocate huge page, and if we expose page table + * for an instant, it will be difficult to retract from + * concurrent faults and from rmap lookups. + */ + vmf->pte = NULL; + vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; + } else { + pmd_t dummy_pmdval; + + /* + * A regular pmd is established and it can't morph into a huge + * pmd by anon khugepaged, since that takes mmap_lock in write + * mode; but shmem or file collapse to THP could still morph + * it into a huge pmd: just retry later if so. + * + * Use the maywrite version to indicate that vmf->pte may be + * modified, but since we will use pte_same() to detect the + * change of the !pte_none() entry, there is no need to recheck + * the pmdval. Here we chooes to pass a dummy variable instead + * of NULL, which helps new user think about why this place is + * special. + */ + vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &dummy_pmdval, + &vmf->ptl); + if (unlikely(!vmf->pte)) + return 0; + vmf->orig_pte = ptep_get_lockless(vmf->pte); + vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; + + if (pte_none(vmf->orig_pte)) { + pte_unmap(vmf->pte); + vmf->pte = NULL; } - if (pte_file(entry)) - return do_nonlinear_fault(mm, vma, address, - pte, pmd, flags, entry); - return do_swap_page(mm, vma, address, - pte, pmd, flags, entry); } - if (pte_numa(entry)) - return do_numa_page(mm, vma, address, entry, pte, pmd); + if (!vmf->pte) + return do_pte_missing(vmf); + + if (!pte_present(vmf->orig_pte)) + return do_swap_page(vmf); + + if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) + return do_numa_page(vmf); - ptl = pte_lockptr(mm, pmd); - spin_lock(ptl); - if (unlikely(!pte_same(*pte, entry))) + spin_lock(vmf->ptl); + entry = vmf->orig_pte; + if (unlikely(!pte_same(ptep_get(vmf->pte), entry))) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; - if (flags & FAULT_FLAG_WRITE) { + } + if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) - return do_wp_page(mm, vma, address, - pte, pmd, ptl, entry); - entry = pte_mkdirty(entry); + return do_wp_page(vmf); + else if (likely(vmf->flags & FAULT_FLAG_WRITE)) + entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) { - update_mmu_cache(vma, address, pte); - } else { - /* - * This is needed only for protection faults but the arch code - * is not yet telling us if this is a protection fault or not. - * This still avoids useless tlb flushes for .text page faults - * with threads. - */ - if (flags & FAULT_FLAG_WRITE) - flush_tlb_fix_spurious_fault(vma, address); - } + if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, + vmf->flags & FAULT_FLAG_WRITE)) + update_mmu_cache_range(vmf, vmf->vma, vmf->address, + vmf->pte, 1); + else + fix_spurious_fault(vmf, PGTABLE_LEVEL_PTE); unlock: - pte_unmap_unlock(pte, ptl); + pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* - * By the time we get here, we already hold the mm semaphore + * On entry, we hold either the VMA lock or the mmap_lock + * (FAULT_FLAG_VMA_LOCK tells you which). If VM_FAULT_RETRY is set in + * the result, the mmap_lock is not held on exit. See filemap_fault() + * and __folio_lock_or_retry(). */ -int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, +static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { + struct vm_fault vmf = { + .vma = vma, + .address = address & PAGE_MASK, + .real_address = address, + .flags = flags, + .pgoff = linear_page_index(vma, address), + .gfp_mask = __get_fault_gfp_mask(vma), + }; + struct mm_struct *mm = vma->vm_mm; + vm_flags_t vm_flags = vma->vm_flags; pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - __set_current_state(TASK_RUNNING); + p4d_t *p4d; + vm_fault_t ret; - count_vm_event(PGFAULT); - mem_cgroup_count_vm_event(mm, PGFAULT); - - /* do counter updates before entering really critical section. */ - check_sync_rss_stat(current); - - if (unlikely(is_vm_hugetlb_page(vma))) - return hugetlb_fault(mm, vma, address, flags); - -retry: pgd = pgd_offset(mm, address); - pud = pud_alloc(mm, pgd, address); - if (!pud) + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) return VM_FAULT_OOM; - pmd = pmd_alloc(mm, pud, address); - if (!pmd) + + vmf.pud = pud_alloc(mm, p4d, address); + if (!vmf.pud) return VM_FAULT_OOM; - if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) { - if (!vma->vm_ops) - return do_huge_pmd_anonymous_page(mm, vma, address, - pmd, flags); +retry_pud: + if (pud_none(*vmf.pud) && + thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PUD_ORDER)) { + ret = create_huge_pud(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { - pmd_t orig_pmd = *pmd; - int ret; + pud_t orig_pud = *vmf.pud; barrier(); - if (pmd_trans_huge(orig_pmd)) { - unsigned int dirty = flags & FAULT_FLAG_WRITE; + if (pud_trans_huge(orig_pud)) { /* - * If the pmd is splitting, return and retry the - * the fault. Alternative: wait until the split - * is done, and goto retry. + * TODO once we support anonymous PUDs: NUMA case and + * FAULT_FLAG_UNSHARE handling. */ - if (pmd_trans_splitting(orig_pmd)) + if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { + ret = wp_huge_pud(&vmf, orig_pud); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + huge_pud_set_accessed(&vmf, orig_pud); return 0; + } + } + } - if (pmd_numa(orig_pmd)) - return do_huge_pmd_numa_page(mm, vma, address, - orig_pmd, pmd); + vmf.pmd = pmd_alloc(mm, vmf.pud, address); + if (!vmf.pmd) + return VM_FAULT_OOM; - if (dirty && !pmd_write(orig_pmd)) { - ret = do_huge_pmd_wp_page(mm, vma, address, pmd, - orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; - } else { - huge_pmd_set_accessed(mm, vma, address, pmd, - orig_pmd, dirty); - } + /* Huge pud page fault raced with pmd_alloc? */ + if (pud_trans_unstable(vmf.pud)) + goto retry_pud; + if (pmd_none(*vmf.pmd) && + thp_vma_allowable_order(vma, vm_flags, TVA_PAGEFAULT, PMD_ORDER)) { + ret = create_huge_pmd(&vmf); + if (ret & VM_FAULT_FALLBACK) + goto fallback; + else + return ret; + } + + vmf.orig_pmd = pmdp_get_lockless(vmf.pmd); + if (pmd_none(vmf.orig_pmd)) + goto fallback; + + if (unlikely(!pmd_present(vmf.orig_pmd))) { + if (pmd_is_device_private_entry(vmf.orig_pmd)) + return do_huge_pmd_device_private(&vmf); + + if (pmd_is_migration_entry(vmf.orig_pmd)) + pmd_migration_entry_wait(mm, vmf.pmd); + return 0; + } + if (pmd_trans_huge(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); + + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !pmd_write(vmf.orig_pmd)) { + ret = wp_huge_pmd(&vmf); + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } else { + vmf.ptl = pmd_lock(mm, vmf.pmd); + if (!huge_pmd_set_accessed(&vmf)) + fix_spurious_fault(&vmf, PGTABLE_LEVEL_PMD); + spin_unlock(vmf.ptl); return 0; } } - if (pmd_numa(*pmd)) - return do_pmd_numa_page(mm, vma, address, pmd); +fallback: + return handle_pte_fault(&vmf); +} + +/** + * mm_account_fault - Do page fault accounting + * @mm: mm from which memcg should be extracted. It can be NULL. + * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting + * of perf event counters, but we'll still do the per-task accounting to + * the task who triggered this page fault. + * @address: the faulted address. + * @flags: the fault flags. + * @ret: the fault retcode. + * + * This will take care of most of the page fault accounting. Meanwhile, it + * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter + * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should + * still be in per-arch page fault handlers at the entry of page fault. + */ +static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs, + unsigned long address, unsigned int flags, + vm_fault_t ret) +{ + bool major; + + /* Incomplete faults will be accounted upon completion. */ + if (ret & VM_FAULT_RETRY) + return; /* - * Use __pte_alloc instead of pte_alloc_map, because we can't - * run pte_offset_map on the pmd, if an huge pmd could - * materialize from under us from a different thread. + * To preserve the behavior of older kernels, PGFAULT counters record + * both successful and failed faults, as opposed to perf counters, + * which ignore failed cases. */ - if (unlikely(pmd_none(*pmd)) && - unlikely(__pte_alloc(mm, vma, pmd, address))) - return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) - return 0; + count_vm_event(PGFAULT); + count_memcg_event_mm(mm, PGFAULT); + + /* + * Do not account for unsuccessful faults (e.g. when the address wasn't + * valid). That includes arch_vma_access_permitted() failing before + * reaching here. So this is not a "this many hardware page faults" + * counter. We should use the hw profiling for that. + */ + if (ret & VM_FAULT_ERROR) + return; + + /* + * We define the fault as a major fault when the final successful fault + * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't + * handle it immediately previously). + */ + major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); + + if (major) + current->maj_flt++; + else + current->min_flt++; + + /* + * If the fault is done for GUP, regs will be NULL. We only do the + * accounting for the per thread fault counters who triggered the + * fault, and we skip the perf event updates. + */ + if (!regs) + return; + + if (major) + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); +} + +#ifdef CONFIG_LRU_GEN +static void lru_gen_enter_fault(struct vm_area_struct *vma) +{ + /* the LRU algorithm only applies to accesses with recency */ + current->in_lru_fault = vma_has_recency(vma); +} + +static void lru_gen_exit_fault(void) +{ + current->in_lru_fault = false; +} +#else +static void lru_gen_enter_fault(struct vm_area_struct *vma) +{ +} + +static void lru_gen_exit_fault(void) +{ +} +#endif /* CONFIG_LRU_GEN */ + +static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, + unsigned int *flags) +{ + if (unlikely(*flags & FAULT_FLAG_UNSHARE)) { + if (WARN_ON_ONCE(*flags & FAULT_FLAG_WRITE)) + return VM_FAULT_SIGSEGV; + /* + * FAULT_FLAG_UNSHARE only applies to COW mappings. Let's + * just treat it like an ordinary read-fault otherwise. + */ + if (!is_cow_mapping(vma->vm_flags)) + *flags &= ~FAULT_FLAG_UNSHARE; + } else if (*flags & FAULT_FLAG_WRITE) { + /* Write faults on read-only mappings are impossible ... */ + if (WARN_ON_ONCE(!(vma->vm_flags & VM_MAYWRITE))) + return VM_FAULT_SIGSEGV; + /* ... and FOLL_FORCE only applies to COW mappings. */ + if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE) && + !is_cow_mapping(vma->vm_flags))) + return VM_FAULT_SIGSEGV; + } +#ifdef CONFIG_PER_VMA_LOCK /* - * A regular pmd is established and it can't morph into a huge pmd - * from under us anymore at this point because we hold the mmap_sem - * read mode and khugepaged takes it in write mode. So now it's - * safe to run pte_offset_map(). + * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of + * the assumption that lock is dropped on VM_FAULT_RETRY. */ - pte = pte_offset_map(pmd, address); + if (WARN_ON_ONCE((*flags & + (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) == + (FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT))) + return VM_FAULT_SIGSEGV; +#endif - return handle_pte_fault(mm, vma, address, pte, pmd, flags); + return 0; } +/* + * By the time we get here, we already hold either the VMA lock or the + * mmap_lock (FAULT_FLAG_VMA_LOCK tells you which). + * + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __folio_lock_or_retry(). + */ +vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs) +{ + /* If the fault handler drops the mmap_lock, vma may be freed */ + struct mm_struct *mm = vma->vm_mm; + vm_fault_t ret; + bool is_droppable; + + __set_current_state(TASK_RUNNING); + + ret = sanitize_fault_flags(vma, &flags); + if (ret) + goto out; + + if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, + flags & FAULT_FLAG_INSTRUCTION, + flags & FAULT_FLAG_REMOTE)) { + ret = VM_FAULT_SIGSEGV; + goto out; + } + + is_droppable = !!(vma->vm_flags & VM_DROPPABLE); + + /* + * Enable the memcg OOM handling for faults triggered in user + * space. Kernel faults are handled more gracefully. + */ + if (flags & FAULT_FLAG_USER) + mem_cgroup_enter_user_fault(); + + lru_gen_enter_fault(vma); + + if (unlikely(is_vm_hugetlb_page(vma))) + ret = hugetlb_fault(vma->vm_mm, vma, address, flags); + else + ret = __handle_mm_fault(vma, address, flags); + + /* + * Warning: It is no longer safe to dereference vma-> after this point, + * because mmap_lock might have been dropped by __handle_mm_fault(), so + * vma might be destroyed from underneath us. + */ + + lru_gen_exit_fault(); + + /* If the mapping is droppable, then errors due to OOM aren't fatal. */ + if (is_droppable) + ret &= ~VM_FAULT_OOM; + + if (flags & FAULT_FLAG_USER) { + mem_cgroup_exit_user_fault(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } +out: + mm_account_fault(mm, regs, address, flags, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(handle_mm_fault); + +#ifndef __PAGETABLE_P4D_FOLDED +/* + * Allocate p4d page table. + * We've already handled the fast-path in-line. + */ +int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + p4d_t *new = p4d_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) { /* Another has populated it */ + p4d_free(mm, new); + } else { + smp_wmb(); /* See comment in pmd_install() */ + pgd_populate(mm, pgd, new); + } + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_P4D_FOLDED */ + #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ -int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ + if (!p4d_present(*p4d)) { + mm_inc_nr_puds(mm); + smp_wmb(); /* See comment in pmd_install() */ + p4d_populate(mm, p4d, new); + } else /* Another has populated it */ pud_free(mm, new); - else - pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } @@ -3878,254 +6662,317 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { + spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - - spin_lock(&mm->page_table_lock); -#ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) /* Another has populated it */ - pmd_free(mm, new); - else + ptl = pud_lock(mm, pud); + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); + smp_wmb(); /* See comment in pmd_install() */ pud_populate(mm, pud, new); -#else - if (pgd_present(*pud)) /* Another has populated it */ + } else { /* Another has populated it */ pmd_free(mm, new); - else - pgd_populate(mm, pud, new); -#endif /* __ARCH_HAS_4LEVEL_HACK */ - spin_unlock(&mm->page_table_lock); + } + spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ -#if !defined(__HAVE_ARCH_GATE_AREA) - -#if defined(AT_SYSINFO_EHDR) -static struct vm_area_struct gate_vma; - -static int __init gate_vma_init(void) +static inline void pfnmap_args_setup(struct follow_pfnmap_args *args, + spinlock_t *lock, pte_t *ptep, + pgprot_t pgprot, unsigned long pfn_base, + unsigned long addr_mask, bool writable, + bool special) { - gate_vma.vm_mm = NULL; - gate_vma.vm_start = FIXADDR_USER_START; - gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; - gate_vma.vm_page_prot = __P101; - - return 0; + args->lock = lock; + args->ptep = ptep; + args->pfn = pfn_base + ((args->address & ~addr_mask) >> PAGE_SHIFT); + args->addr_mask = addr_mask; + args->pgprot = pgprot; + args->writable = writable; + args->special = special; } -__initcall(gate_vma_init); -#endif -struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) { -#ifdef AT_SYSINFO_EHDR - return &gate_vma; -#else - return NULL; -#endif -} +#ifdef CONFIG_LOCKDEP + struct file *file = vma->vm_file; + struct address_space *mapping = file ? file->f_mapping : NULL; -int in_gate_area_no_mm(unsigned long addr) -{ -#ifdef AT_SYSINFO_EHDR - if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) - return 1; + if (mapping) + lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) || + lockdep_is_held(&vma->vm_mm->mmap_lock)); + else + lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); #endif - return 0; } -#endif /* __HAVE_ARCH_GATE_AREA */ - -static int __follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) +/** + * follow_pfnmap_start() - Look up a pfn mapping at a user virtual address + * @args: Pointer to struct @follow_pfnmap_args + * + * The caller needs to setup args->vma and args->address to point to the + * virtual address as the target of such lookup. On a successful return, + * the results will be put into other output fields. + * + * After the caller finished using the fields, the caller must invoke + * another follow_pfnmap_end() to proper releases the locks and resources + * of such look up request. + * + * During the start() and end() calls, the results in @args will be valid + * as proper locks will be held. After the end() is called, all the fields + * in @follow_pfnmap_args will be invalid to be further accessed. Further + * use of such information after end() may require proper synchronizations + * by the caller with page table updates, otherwise it can create a + * security bug. + * + * If the PTE maps a refcounted page, callers are responsible to protect + * against invalidation with MMU notifiers; otherwise access to the PFN at + * a later point in time can trigger use-after-free. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read, and the mmap semaphore cannot be released + * before the end() is invoked. + * + * This function must not be used to modify PTE content. + * + * Return: zero on success, negative otherwise. + */ +int follow_pfnmap_start(struct follow_pfnmap_args *args) { - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; + struct vm_area_struct *vma = args->vma; + unsigned long address = args->address; + struct mm_struct *mm = vma->vm_mm; + spinlock_t *lock; + pgd_t *pgdp; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + pfnmap_lockdep_assert(vma); + + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto out; - pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; +retry: + pgdp = pgd_offset(mm, address); + if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) goto out; - pmd = pmd_offset(pud, address); - VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + p4dp = p4d_offset(pgdp, address); + p4d = p4dp_get(p4dp); + if (p4d_none(p4d) || unlikely(p4d_bad(p4d))) goto out; - /* We cannot handle huge page PFN maps. Luckily they don't exist. */ - if (pmd_huge(*pmd)) + pudp = pud_offset(p4dp, address); + pud = pudp_get(pudp); + if (pud_none(pud)) goto out; + if (pud_leaf(pud)) { + lock = pud_lock(mm, pudp); + if (!unlikely(pud_leaf(pud))) { + spin_unlock(lock); + goto retry; + } + pfnmap_args_setup(args, lock, NULL, pud_pgprot(pud), + pud_pfn(pud), PUD_MASK, pud_write(pud), + pud_special(pud)); + return 0; + } + + pmdp = pmd_offset(pudp, address); + pmd = pmdp_get_lockless(pmdp); + if (pmd_leaf(pmd)) { + lock = pmd_lock(mm, pmdp); + if (!unlikely(pmd_leaf(pmd))) { + spin_unlock(lock); + goto retry; + } + pfnmap_args_setup(args, lock, NULL, pmd_pgprot(pmd), + pmd_pfn(pmd), PMD_MASK, pmd_write(pmd), + pmd_special(pmd)); + return 0; + } - ptep = pte_offset_map_lock(mm, pmd, address, ptlp); + ptep = pte_offset_map_lock(mm, pmdp, address, &lock); if (!ptep) goto out; - if (!pte_present(*ptep)) + pte = ptep_get(ptep); + if (!pte_present(pte)) goto unlock; - *ptepp = ptep; + pfnmap_args_setup(args, lock, ptep, pte_pgprot(pte), + pte_pfn(pte), PAGE_MASK, pte_write(pte), + pte_special(pte)); return 0; unlock: - pte_unmap_unlock(ptep, *ptlp); + pte_unmap_unlock(ptep, lock); out: return -EINVAL; } - -static inline int follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) -{ - int res; - - /* (void) is needed to make gcc happy */ - (void) __cond_lock(*ptlp, - !(res = __follow_pte(mm, address, ptepp, ptlp))); - return res; -} +EXPORT_SYMBOL_GPL(follow_pfnmap_start); /** - * follow_pfn - look up PFN at a user virtual address - * @vma: memory mapping - * @address: user virtual address - * @pfn: location to store found PFN - * - * Only IO mappings and raw PFN mappings are allowed. + * follow_pfnmap_end(): End a follow_pfnmap_start() process + * @args: Pointer to struct @follow_pfnmap_args * - * Returns zero and the pfn at @pfn on success, -ve otherwise. + * Must be used in pair of follow_pfnmap_start(). See the start() function + * above for more information. */ -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn) +void follow_pfnmap_end(struct follow_pfnmap_args *args) { - int ret = -EINVAL; - spinlock_t *ptl; - pte_t *ptep; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return ret; - - ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); - if (ret) - return ret; - *pfn = pte_pfn(*ptep); - pte_unmap_unlock(ptep, ptl); - return 0; + if (args->lock) + spin_unlock(args->lock); + if (args->ptep) + pte_unmap(args->ptep); } -EXPORT_SYMBOL(follow_pfn); +EXPORT_SYMBOL_GPL(follow_pfnmap_end); #ifdef CONFIG_HAVE_IOREMAP_PROT -int follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot, resource_size_t *phys) -{ - int ret = -EINVAL; - pte_t *ptep, pte; - spinlock_t *ptl; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - goto out; - - if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) - goto out; - pte = *ptep; - - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - - *prot = pgprot_val(pte_pgprot(pte)); - *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; - - ret = 0; -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return ret; -} - +/** + * generic_access_phys - generic implementation for iomem mmap access + * @vma: the vma to access + * @addr: userspace address, not relative offset within @vma + * @buf: buffer to read/write + * @len: length of transfer + * @write: set to FOLL_WRITE when writing, otherwise reading + * + * This is a generic implementation for &vm_operations_struct.access for an + * iomem mapping. This callback is used by access_process_vm() when the @vma is + * not page based. + */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; - unsigned long prot = 0; + pgprot_t prot = __pgprot(0); void __iomem *maddr; - int offset = addr & (PAGE_SIZE-1); + int offset = offset_in_page(addr); + int ret = -EINVAL; + bool writable; + struct follow_pfnmap_args args = { .vma = vma, .address = addr }; - if (follow_phys(vma, addr, write, &prot, &phys_addr)) +retry: + if (follow_pfnmap_start(&args)) return -EINVAL; + prot = args.pgprot; + phys_addr = (resource_size_t)args.pfn << PAGE_SHIFT; + writable = args.writable; + follow_pfnmap_end(&args); + + if ((write & FOLL_WRITE) && !writable) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); + if (!maddr) + return -ENOMEM; + + if (follow_pfnmap_start(&args)) + goto out_unmap; + + if ((pgprot_val(prot) != pgprot_val(args.pgprot)) || + (phys_addr != (args.pfn << PAGE_SHIFT)) || + (writable != args.writable)) { + follow_pfnmap_end(&args); + iounmap(maddr); + goto retry; + } - maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); + ret = len; + follow_pfnmap_end(&args); +out_unmap: iounmap(maddr); - return len; + return ret; } +EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* - * Access another process' address space as given in mm. If non-NULL, use the - * given task for page fault accounting. + * Access another process' address space as given in mm. */ -static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, void *buf, int len, int write) +static int __access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) { - struct vm_area_struct *vma; void *old_buf = buf; + int write = gup_flags & FOLL_WRITE; + + if (mmap_read_lock_killable(mm)) + return 0; + + /* Untag the address before looking up the VMA */ + addr = untagged_addr_remote(mm, addr); + + /* Avoid triggering the temporary warning in __get_user_pages */ + if (!vma_lookup(mm, addr) && !expand_stack(mm, addr)) + return 0; - down_read(&mm->mmap_sem); /* ignore errors, just check how much was successfully transferred */ while (len) { - int bytes, ret, offset; + int bytes, offset; void *maddr; - struct page *page = NULL; + struct folio *folio; + struct vm_area_struct *vma = NULL; + struct page *page = get_user_page_vma_remote(mm, addr, + gup_flags, &vma); + + if (IS_ERR(page)) { + /* We might need to expand the stack to access it */ + vma = vma_lookup(mm, addr); + if (!vma) { + vma = expand_stack(mm, addr); + + /* mmap_lock was dropped on failure */ + if (!vma) + return buf - old_buf; + + /* Try again if stack expansion worked */ + continue; + } - ret = get_user_pages(tsk, mm, addr, 1, - write, 1, &page, &vma); - if (ret <= 0) { /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ + bytes = 0; #ifdef CONFIG_HAVE_IOREMAP_PROT - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - break; if (vma->vm_ops && vma->vm_ops->access) - ret = vma->vm_ops->access(vma, addr, buf, - len, write); - if (ret <= 0) + bytes = vma->vm_ops->access(vma, addr, buf, + len, write); #endif + if (bytes <= 0) break; - bytes = ret; } else { + folio = page_folio(page); bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; - maddr = kmap(page); + maddr = kmap_local_folio(folio, folio_page_idx(folio, page) * PAGE_SIZE); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); - set_page_dirty_lock(page); + folio_mark_dirty_lock(folio); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } - kunmap(page); - page_cache_release(page); + folio_release_kmap(folio, maddr); } len -= bytes; buf += bytes; addr += bytes; } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); return buf - old_buf; } @@ -4136,14 +6983,16 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer - * @write: whether the access is a write + * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. + * + * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, - void *buf, int len, int write) + void *buf, int len, unsigned int gup_flags) { - return __access_remote_vm(NULL, mm, addr, buf, len, write); + return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* @@ -4152,7 +7001,7 @@ int access_remote_vm(struct mm_struct *mm, unsigned long addr, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, - void *buf, int len, int write) + void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; @@ -4161,11 +7010,133 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, if (!mm) return 0; - ret = __access_remote_vm(tsk, mm, addr, buf, len, write); + ret = __access_remote_vm(mm, addr, buf, len, gup_flags); + mmput(mm); return ret; } +EXPORT_SYMBOL_GPL(access_process_vm); + +#ifdef CONFIG_BPF_SYSCALL +/* + * Copy a string from another process's address space as given in mm. + * If there is any error return -EFAULT. + */ +static int __copy_remote_vm_str(struct mm_struct *mm, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + void *old_buf = buf; + int err = 0; + + *(char *)buf = '\0'; + + if (mmap_read_lock_killable(mm)) + return -EFAULT; + + addr = untagged_addr_remote(mm, addr); + + /* Avoid triggering the temporary warning in __get_user_pages */ + if (!vma_lookup(mm, addr)) { + err = -EFAULT; + goto out; + } + + while (len) { + int bytes, offset, retval; + void *maddr; + struct folio *folio; + struct page *page; + struct vm_area_struct *vma = NULL; + + page = get_user_page_vma_remote(mm, addr, gup_flags, &vma); + if (IS_ERR(page)) { + /* + * Treat as a total failure for now until we decide how + * to handle the CONFIG_HAVE_IOREMAP_PROT case and + * stack expansion. + */ + *(char *)buf = '\0'; + err = -EFAULT; + goto out; + } + + folio = page_folio(page); + bytes = len; + offset = addr & (PAGE_SIZE - 1); + if (bytes > PAGE_SIZE - offset) + bytes = PAGE_SIZE - offset; + + maddr = kmap_local_folio(folio, folio_page_idx(folio, page) * PAGE_SIZE); + retval = strscpy(buf, maddr + offset, bytes); + if (retval >= 0) { + /* Found the end of the string */ + buf += retval; + folio_release_kmap(folio, maddr); + break; + } + + buf += bytes - 1; + /* + * Because strscpy always NUL terminates we need to + * copy the last byte in the page if we are going to + * load more pages + */ + if (bytes != len) { + addr += bytes - 1; + copy_from_user_page(vma, page, addr, buf, maddr + (PAGE_SIZE - 1), 1); + buf += 1; + addr += 1; + } + len -= bytes; + + folio_release_kmap(folio, maddr); + } + +out: + mmap_read_unlock(mm); + if (err) + return err; + return buf - old_buf; +} + +/** + * copy_remote_vm_str - copy a string from another process's address space. + * @tsk: the task of the target address space + * @addr: start address to read from + * @buf: destination buffer + * @len: number of bytes to copy + * @gup_flags: flags modifying lookup behaviour + * + * The caller must hold a reference on @mm. + * + * Return: number of bytes copied from @addr (source) to @buf (destination); + * not including the trailing NUL. Always guaranteed to leave NUL-terminated + * buffer. On any error, return -EFAULT. + */ +int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + struct mm_struct *mm; + int ret; + + if (unlikely(len == 0)) + return 0; + + mm = get_task_mm(tsk); + if (!mm) { + *(char *)buf = '\0'; + return -EFAULT; + } + + ret = __copy_remote_vm_str(mm, addr, buf, len, gup_flags); + + mmput(mm); + + return ret; +} +EXPORT_SYMBOL_GPL(copy_remote_vm_str); +#endif /* CONFIG_BPF_SYSCALL */ /* * Print the name of a VMA. @@ -4176,127 +7147,255 @@ void print_vma_addr(char *prefix, unsigned long ip) struct vm_area_struct *vma; /* - * Do not print if we are in atomic - * contexts (in exception stacks, etc.): + * we might be running from an atomic context so we cannot sleep */ - if (preempt_count()) + if (!mmap_read_trylock(mm)) return; - down_read(&mm->mmap_sem); - vma = find_vma(mm, ip); + vma = vma_lookup(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; - char *buf = (char *)__get_free_page(GFP_KERNEL); - if (buf) { - char *p; - - p = d_path(&f->f_path, buf, PAGE_SIZE); - if (IS_ERR(p)) - p = "?"; - printk("%s%s[%lx+%lx]", prefix, kbasename(p), - vma->vm_start, - vma->vm_end - vma->vm_start); - free_page((unsigned long)buf); - } + ip -= vma->vm_start; + ip += vma->vm_pgoff << PAGE_SHIFT; + printk("%s%pD[%lx,%lx+%lx]", prefix, f, ip, + vma->vm_start, + vma->vm_end - vma->vm_start); } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) -void might_fault(void) +void __might_fault(const char *file, int line) { - /* - * Some code (nfs/sunrpc) uses socket ops on kernel memory while - * holding the mmap_sem, this is safe because kernel memory doesn't - * get paged out, therefore we'll never actually fault, and the - * below annotations will generate false positives. - */ - if (segment_eq(get_fs(), KERNEL_DS)) + if (pagefault_disabled()) return; - - /* - * it would be nicer only to annotate paths which are not under - * pagefault_disable, however that requires a larger audit and - * providing helpers like get_user_atomic. - */ - if (in_atomic()) - return; - - __might_sleep(__FILE__, __LINE__, 0); - + __might_sleep(file, line); if (current->mm) - might_lock_read(¤t->mm->mmap_sem); + might_lock_read(¤t->mm->mmap_lock); } -EXPORT_SYMBOL(might_fault); +EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -static void clear_gigantic_page(struct page *page, - unsigned long addr, - unsigned int pages_per_huge_page) +/* + * Process all subpages of the specified huge page with the specified + * operation. The target subpage will be processed last to keep its + * cache lines hot. + */ +static inline int process_huge_page( + unsigned long addr_hint, unsigned int nr_pages, + int (*process_subpage)(unsigned long addr, int idx, void *arg), + void *arg) { - int i; - struct page *p = page; + int i, n, base, l, ret; + unsigned long addr = addr_hint & + ~(((unsigned long)nr_pages << PAGE_SHIFT) - 1); + /* Process target subpage last to keep its cache lines hot */ might_sleep(); - for (i = 0; i < pages_per_huge_page; - i++, p = mem_map_next(p, page, i)) { + n = (addr_hint - addr) / PAGE_SIZE; + if (2 * n <= nr_pages) { + /* If target subpage in first half of huge page */ + base = 0; + l = n; + /* Process subpages at the end of huge page */ + for (i = nr_pages - 1; i >= 2 * n; i--) { + cond_resched(); + ret = process_subpage(addr + i * PAGE_SIZE, i, arg); + if (ret) + return ret; + } + } else { + /* If target subpage in second half of huge page */ + base = nr_pages - 2 * (nr_pages - n); + l = nr_pages - n; + /* Process subpages at the begin of huge page */ + for (i = 0; i < base; i++) { + cond_resched(); + ret = process_subpage(addr + i * PAGE_SIZE, i, arg); + if (ret) + return ret; + } + } + /* + * Process remaining subpages in left-right-left-right pattern + * towards the target subpage + */ + for (i = 0; i < l; i++) { + int left_idx = base + i; + int right_idx = base + 2 * l - 1 - i; + + cond_resched(); + ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); + if (ret) + return ret; cond_resched(); - clear_user_highpage(p, addr + i * PAGE_SIZE); + ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); + if (ret) + return ret; } + return 0; } -void clear_huge_page(struct page *page, - unsigned long addr, unsigned int pages_per_huge_page) + +static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint, + unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio)); int i; - if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { - clear_gigantic_page(page, addr, pages_per_huge_page); - return; - } - might_sleep(); - for (i = 0; i < pages_per_huge_page; i++) { + for (i = 0; i < nr_pages; i++) { cond_resched(); - clear_user_highpage(page + i, addr + i * PAGE_SIZE); + clear_user_highpage(folio_page(folio, i), addr + i * PAGE_SIZE); } } -static void copy_user_gigantic_page(struct page *dst, struct page *src, - unsigned long addr, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page) +static int clear_subpage(unsigned long addr, int idx, void *arg) { - int i; - struct page *dst_base = dst; - struct page *src_base = src; + struct folio *folio = arg; - for (i = 0; i < pages_per_huge_page; ) { - cond_resched(); - copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + clear_user_highpage(folio_page(folio, idx), addr); + return 0; +} - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); - } +/** + * folio_zero_user - Zero a folio which will be mapped to userspace. + * @folio: The folio to zero. + * @addr_hint: The address will be accessed or the base address if uncelar. + */ +void folio_zero_user(struct folio *folio, unsigned long addr_hint) +{ + unsigned int nr_pages = folio_nr_pages(folio); + + if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) + clear_gigantic_page(folio, addr_hint, nr_pages); + else + process_huge_page(addr_hint, nr_pages, clear_subpage, folio); } -void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr, struct vm_area_struct *vma, - unsigned int pages_per_huge_page) +static int copy_user_gigantic_page(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma, + unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); + struct page *dst_page; + struct page *src_page; int i; - if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { - copy_user_gigantic_page(dst, src, addr, vma, - pages_per_huge_page); - return; + for (i = 0; i < nr_pages; i++) { + dst_page = folio_page(dst, i); + src_page = folio_page(src, i); + + cond_resched(); + if (copy_mc_user_highpage(dst_page, src_page, + addr + i*PAGE_SIZE, vma)) + return -EHWPOISON; } + return 0; +} + +struct copy_subpage_arg { + struct folio *dst; + struct folio *src; + struct vm_area_struct *vma; +}; + +static int copy_subpage(unsigned long addr, int idx, void *arg) +{ + struct copy_subpage_arg *copy_arg = arg; + struct page *dst = folio_page(copy_arg->dst, idx); + struct page *src = folio_page(copy_arg->src, idx); + + if (copy_mc_user_highpage(dst, src, addr, copy_arg->vma)) + return -EHWPOISON; + return 0; +} + +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, struct vm_area_struct *vma) +{ + unsigned int nr_pages = folio_nr_pages(dst); + struct copy_subpage_arg arg = { + .dst = dst, + .src = src, + .vma = vma, + }; + + if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) + return copy_user_gigantic_page(dst, src, addr_hint, vma, nr_pages); + + return process_huge_page(addr_hint, nr_pages, copy_subpage, &arg); +} + +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault) +{ + void *kaddr; + unsigned long i, rc = 0; + unsigned int nr_pages = folio_nr_pages(dst_folio); + unsigned long ret_val = nr_pages * PAGE_SIZE; + struct page *subpage; + + for (i = 0; i < nr_pages; i++) { + subpage = folio_page(dst_folio, i); + kaddr = kmap_local_page(subpage); + if (!allow_pagefault) + pagefault_disable(); + rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); + if (!allow_pagefault) + pagefault_enable(); + kunmap_local(kaddr); + + ret_val -= (PAGE_SIZE - rc); + if (rc) + break; + + flush_dcache_page(subpage); - might_sleep(); - for (i = 0; i < pages_per_huge_page; i++) { cond_resched(); - copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } + return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) && ALLOC_SPLIT_PTLOCKS + +static struct kmem_cache *page_ptl_cachep; + +void __init ptlock_cache_init(void) +{ + page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, + SLAB_PANIC, NULL); +} + +bool ptlock_alloc(struct ptdesc *ptdesc) +{ + spinlock_t *ptl; + + ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); + if (!ptl) + return false; + ptdesc->ptl = ptl; + return true; +} + +void ptlock_free(struct ptdesc *ptdesc) +{ + if (ptdesc->ptl) + kmem_cache_free(page_ptl_cachep, ptdesc->ptl); +} +#endif + +void vma_pgtable_walk_begin(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_lock_read(vma); +} + +void vma_pgtable_walk_end(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_unlock_read(vma); +} |