diff options
Diffstat (limited to '')
-rw-r--r-- | mm/memory.c | 2774 |
1 files changed, 1885 insertions, 889 deletions
diff --git a/mm/memory.c b/mm/memory.c index e8bfdf0d9d1d..f88c351aecd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -41,6 +41,7 @@ #include <linux/kernel_stat.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> @@ -51,6 +52,7 @@ #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> @@ -65,12 +67,16 @@ #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> -#include <linux/dma-debug.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 <trace/events/kmem.h> @@ -80,16 +86,16 @@ #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -#include <asm/pgtable.h> +#include "pgalloc-track.h" #include "internal.h" +#include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif -#ifndef CONFIG_NEED_MULTIPLE_NODES -/* use the per-pgdat data instead for discontigmem - mbligh */ +#ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); @@ -97,6 +103,8 @@ struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif +static vm_fault_t do_fault(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 @@ -120,15 +128,15 @@ int randomize_va_space __read_mostly = 2; #endif -#ifndef arch_faults_on_old_pte -static inline bool arch_faults_on_old_pte(void) +#ifndef arch_wants_old_prefaulted_pte +static inline bool arch_wants_old_prefaulted_pte(void) { /* - * Those arches which don't have hw access flag feature need to - * implement their own helper. By default, "true" means pagefault - * will be hit on old pte. + * 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'. */ - return true; + return false; } #endif @@ -152,7 +160,7 @@ static int __init init_zero_pfn(void) zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } -core_initcall(init_zero_pfn); +early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { @@ -385,12 +393,21 @@ void free_pgd_range(struct mmu_gather *tlb, } 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 maple_tree *mt, + struct vm_area_struct *vma, unsigned long floor, + unsigned long ceiling) { - while (vma) { - struct vm_area_struct *next = vma->vm_next; + MA_STATE(mas, mt, vma->vm_end, vma->vm_end); + + 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); /* * Hide vma from rmap and truncate_pagecache before freeing @@ -409,7 +426,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; - next = vma->vm_next; + next = mas_find(&mas, ceiling - 1); unlink_anon_vmas(vma); unlink_file_vma(vma); } @@ -417,38 +434,42 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, 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, pmd_t *pmd) { - spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; - /* - * Ensure all pte setup (eg. pte page lock and page clearing) are - * visible before the pte is made visible to other CPUs by being - * put into page tables. - * - * The other side of the story is the pointer chasing in the page - * table walking code (when walking the page table without locking; - * ie. most of the time). Fortunately, these data accesses consist - * of a chain of data-dependent loads, meaning most CPUs (alpha - * being the notable exception) will already guarantee loads are - * seen in-order. See the alpha page table accessors for the - * smp_read_barrier_depends() barriers in page table walking code. - */ - smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ - - ptl = pmd_lock(mm, pmd); - if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ - mm_inc_nr_ptes(mm); - pmd_populate(mm, pmd, new); - new = NULL; - } - spin_unlock(ptl); + pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; @@ -460,10 +481,9 @@ int __pte_alloc_kernel(pmd_t *pmd) 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; } @@ -538,11 +558,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, dump_page(page, "bad pte"); 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 readpage:%ps\n", + pr_alert("file:%pD fault:%ps mmap:%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, - mapping ? mapping->a_ops->readpage : NULL); + mapping ? mapping->a_ops->read_folio : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } @@ -604,6 +624,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) + /* + * NOTE: New users of ZONE_DEVICE will not set pte_devmap() + * and will have refcounts incremented on their struct pages + * when they are inserted into PTEs, thus they are safe to + * return here. Legacy ZONE_DEVICE pages that set pte_devmap() + * do not have refcounts. Example of legacy ZONE_DEVICE is + * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers. + */ return NULL; print_bad_pte(vma, addr, pte, NULL); @@ -686,86 +714,260 @@ out: } #endif +static void restore_exclusive_pte(struct vm_area_struct *vma, + struct page *page, unsigned long address, + pte_t *ptep) +{ + pte_t pte; + swp_entry_t entry; + + pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); + + entry = pte_to_swp_entry(*ptep); + if (pte_swp_uffd_wp(*ptep)) + pte = pte_mkuffd_wp(pte); + else if (is_writable_device_exclusive_entry(entry)) + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + + VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page))); + + /* + * No need to take a page reference as one was already + * created when the swap entry was made. + */ + if (PageAnon(page)) + page_add_anon_rmap(page, vma, address, RMAP_NONE); + else + /* + * Currently device exclusive access only supports anonymous + * memory so the entry shouldn't point to a filebacked page. + */ + WARN_ON_ONCE(1); + + 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(pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr) +{ + swp_entry_t entry = pte_to_swp_entry(*src_pte); + struct page *page = pfn_swap_entry_to_page(entry); + + if (trylock_page(page)) { + restore_exclusive_pte(vma, page, addr, src_pte); + unlock_page(page); + 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; + unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(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(*src_pte)) { + pte = pte_swp_clear_exclusive(*src_pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = pfn_swap_entry_to_page(entry); - /* pte contains position in swap or file, so copy. */ - if (unlikely(!pte_present(pte))) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - rss[mm_counter(page)]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } - } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + rss[mm_counter(page)]++; + if (!is_readable_migration_entry(entry) && + is_cow_mapping(vm_flags)) { /* - * 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. + * COW mappings require pages in both parent and child + * to be set to read. A previously exclusive entry is + * now shared. */ - get_page(page); - rss[mm_counter(page)]++; - page_dup_rmap(page, false); + entry = make_readable_migration_entry( + swp_offset(entry)); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_private_entry(entry)) { + page = pfn_swap_entry_to_page(entry); - /* - * We do not preserve soft-dirty information, because so - * far, checkpoint/restore is the only feature that - * requires that. And checkpoint/restore does not work - * when a device driver is involved (you cannot easily - * save and restore device driver state). - */ - if (is_write_device_private_entry(entry) && - is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); - pte = swp_entry_to_pte(entry); - set_pte_at(src_mm, addr, src_pte, pte); - } + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + /* Cannot fail as these pages cannot get pinned. */ + BUG_ON(page_try_dup_anon_rmap(page, false, 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 (is_writable_device_private_entry(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(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_exclusive_entry(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_pte, src_vma, addr)) + return -EBUSY; + return -ENOENT; + } else if (is_pte_marker_entry(entry)) { + /* + * We're copying the pgtable should only because dst_vma has + * uffd-wp enabled, do sanity check. + */ + WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); + set_pte_at(dst_mm, addr, dst_pte, pte); + 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 page **prealloc, struct page *page) +{ + struct page *new_page; + pte_t pte; + + new_page = *prealloc; + if (!new_page) + return -EAGAIN; + + /* + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. + */ + *prealloc = NULL; + copy_user_highpage(new_page, page, addr, src_vma); + __SetPageUptodate(new_page); + page_add_new_anon_rmap(new_page, dst_vma, addr); + lru_cache_add_inactive_or_unevictable(new_page, dst_vma); + rss[mm_counter(new_page)]++; + + /* All done, just insert the new page copy in the child */ + pte = mk_pte(new_page, dst_vma->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + if (userfaultfd_pte_wp(dst_vma, *src_pte)) + /* Uffd-wp needs to be delivered to dest pte as well */ + pte = pte_wrprotect(pte_mkuffd_wp(pte)); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page + * is required to copy this pte. + */ +static inline int +copy_present_pte(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 page **prealloc) +{ + struct mm_struct *src_mm = src_vma->vm_mm; + unsigned long vm_flags = src_vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + page = vm_normal_page(src_vma, addr, pte); + if (page && PageAnon(page)) { + /* + * 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. + */ + get_page(page); + if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) { + /* Page maybe pinned, we have to copy. */ + put_page(page); + return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, page); } - goto out_set_pte; + rss[mm_counter(page)]++; + } else if (page) { + get_page(page); + page_dup_file_rmap(page, false); + rss[mm_counter(page)]++; } /* @@ -776,6 +978,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } + VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page)); /* * If it's a shared mapping, mark it clean in @@ -785,37 +988,56 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte = pte_mkclean(pte); pte = pte_mkold(pte); - page = vm_normal_page(vma, addr, pte); - if (page) { - get_page(page); - page_dup_rmap(page, false); - rss[mm_counter(page)]++; - } else if (pte_devmap(pte)) { - page = pte_page(pte); - } + if (!userfaultfd_wp(dst_vma)) + pte = pte_clear_uffd_wp(pte); -out_set_pte: - set_pte_at(dst_mm, addr, dst_pte, pte); + set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } -static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +static inline struct page * +page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, + unsigned long addr) { + struct page *new_page; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); + if (!new_page) + return NULL; + + if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) { + put_page(new_page); + return NULL; + } + cgroup_throttle_swaprate(new_page, GFP_KERNEL); + + return new_page; +} + +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; spinlock_t *src_ptl, *dst_ptl; - int progress = 0; + int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; + struct page *prealloc = NULL; again: + progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); - if (!dst_pte) - return -ENOMEM; + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -838,10 +1060,46 @@ again: 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(*src_pte))) { + ret = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + dst_vma, src_vma, + addr, rss); + if (ret == -EIO) { + entry = pte_to_swp_entry(*src_pte); + break; + } else if (ret == -EBUSY) { + break; + } else if (!ret) { + progress += 8; + continue; + } + + /* + * Device exclusive entry restored, continue by copying + * the now present pte. + */ + WARN_ON_ONCE(ret != -ENOENT); + } + /* copy_present_pte() will clear `*prealloc' if consumed */ + ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + */ + if (unlikely(ret == -EAGAIN)) break; + 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. + */ + put_page(prealloc); + prealloc = NULL; + } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); @@ -852,20 +1110,41 @@ again: 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) { + goto out; + } else if (ret == -EAGAIN) { + prealloc = page_copy_prealloc(src_mm, src_vma, addr); + if (!prealloc) return -ENOMEM; - progress = 0; + } else if (ret) { + 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)) + put_page(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; @@ -878,9 +1157,9 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma); - err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, vma); + 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) @@ -889,17 +1168,20 @@ 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, - p4d_t *dst_p4d, p4d_t *src_p4d, 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; @@ -912,9 +1194,9 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; - VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma); + VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, - dst_pud, src_pud, addr, vma); + dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -923,17 +1205,19 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src } 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; } -static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) +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) { + struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; @@ -945,43 +1229,70 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; - if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, - vma, addr, next)) + 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; } -int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma) +/* + * 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) +{ + /* + * Always copy pgtables when dst_vma has uffd-wp enabled even if it's + * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable + * contains uffd-wp protection information, that's something we can't + * retrieve from page cache, and skip copying will lose those info. + */ + if (userfaultfd_wp(dst_vma)) + return true; + + if (src_vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return true; + + if (src_vma->anon_vma) + 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. + */ + return false; +} + +int +copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; + 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; bool is_cow; int ret; - /* - * Don't copy ptes where a page fault will fill them correctly. - * Fork becomes much lighter when there are big shared or private - * readonly mappings. The tradeoff is that copy_page_range is more - * efficient than faulting. - */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && - !vma->anon_vma) + if (!vma_needs_copy(dst_vma, src_vma)) return 0; - if (is_vm_hugetlb_page(vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, vma); + if (is_vm_hugetlb_page(src_vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); - if (unlikely(vma->vm_flags & VM_PFNMAP)) { + if (unlikely(src_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); + ret = track_pfn_copy(src_vma); if (ret) return ret; } @@ -992,12 +1303,21 @@ 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); + is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, - 0, vma, src_mm, addr, end); + 0, src_vma, 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. + */ + mmap_assert_write_locked(src_mm); + raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; @@ -1007,18 +1327,80 @@ 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_p4d_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) + if (is_cow) { + raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); + } return ret; } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct folio *single_folio; /* Locked folio to be unmapped */ + bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ +}; + +/* 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) + return true; + + /* Or, we zap COWed pages only if the caller wants to */ + return details->even_cows; +} + +/* Decides whether we should zap this page with the page pointer specified */ +static inline bool should_zap_page(struct zap_details *details, struct page *page) +{ + /* If we can make a decision without *page.. */ + if (should_zap_cows(details)) + return true; + + /* E.g. the caller passes NULL for the case of a zero page */ + if (!page) + return true; + + /* Otherwise we should only zap non-anon pages */ + return !PageAnon(page); +} + +static inline bool zap_drop_file_uffd_wp(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. + */ +static inline void +zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte, + struct zap_details *details, pte_t pteval) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (zap_drop_file_uffd_wp(details)) + return; + + pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +#endif +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1041,6 +1423,8 @@ again: arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; + struct page *page; + if (pte_none(ptent)) continue; @@ -1048,22 +1432,14 @@ again: break; if (pte_present(ptent)) { - struct page *page; - 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_rmapping(page)) - continue; - } + if (unlikely(!should_zap_page(details, page))) + continue; ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, + ptent); if (unlikely(!page)) continue; @@ -1077,7 +1453,7 @@ again: mark_page_accessed(page); } rss[mm_counter(page)]--; - page_remove_rmap(page, false); + page_remove_rmap(page, vma, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { @@ -1089,42 +1465,48 @@ again: } entry = pte_to_swp_entry(ptent); - if (non_swap_entry(entry) && is_device_private_entry(entry)) { - struct page *page = device_private_entry_to_page(entry); - - if (unlikely(details && details->check_mapping)) { - /* - * unmap_shared_mapping_pages() wants to - * invalidate cache without truncating: - * unmap shared but keep private pages. - */ - if (details->check_mapping != - page_rmapping(page)) - continue; - } - - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + if (is_device_private_entry(entry) || + is_device_exclusive_entry(entry)) { + page = pfn_swap_entry_to_page(entry); + if (unlikely(!should_zap_page(details, page))) + continue; + /* + * 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(page)]--; - page_remove_rmap(page, false); + if (is_device_private_entry(entry)) + page_remove_rmap(page, vma, false); put_page(page); - continue; - } - - /* If details->check_mapping, we leave swap entries. */ - if (unlikely(details)) - continue; - - if (!non_swap_entry(entry)) + } else if (!non_swap_entry(entry)) { + /* Genuine swap entry, hence a private anon page */ + if (!should_zap_cows(details)) + continue; rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; - - page = migration_entry_to_page(entry); + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); + } else if (is_migration_entry(entry)) { + page = pfn_swap_entry_to_page(entry); + if (!should_zap_page(details, page)) + continue; rss[mm_counter(page)]--; + } else if (pte_marker_entry_uffd_wp(entry)) { + /* Only drop the uffd-wp marker if explicitly requested */ + if (!zap_drop_file_uffd_wp(details)) + continue; + } else if (is_hwpoison_entry(entry) || + is_swapin_error_entry(entry)) { + if (!should_zap_cows(details)) + continue; + } else { + /* We should have covered all the swap entry types */ + WARN_ON_ONCE(1); } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); @@ -1171,12 +1553,23 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* 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 + * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) @@ -1202,7 +1595,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb, next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { - VM_BUG_ON_VMA(!rwsem_is_locked(&tlb->mm->mmap_sem), vma); + mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; @@ -1292,9 +1685,10 @@ static void unmap_single_vma(struct mmu_gather *tlb, * safe to do nothing in this case. */ if (vma->vm_file) { - i_mmap_lock_write(vma->vm_file->f_mapping); - __unmap_hugepage_range_final(tlb, vma, start, end, NULL); - i_mmap_unlock_write(vma->vm_file->f_mapping); + zap_flags_t zap_flags = details ? + details->zap_flags : 0; + __unmap_hugepage_range_final(tlb, vma, start, end, + NULL, zap_flags); } } else unmap_page_range(tlb, vma, start, end, details); @@ -1304,6 +1698,7 @@ 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 + * @mt: the maple tree * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping @@ -1319,17 +1714,24 @@ 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 maple_tree *mt, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; + struct zap_details details = { + .zap_flags = ZAP_FLAG_DROP_MARKER, + /* Careful - we need to zap private pages too! */ + .even_cows = true, + }; + MA_STATE(mas, mt, vma->vm_end, vma->vm_end); mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); - for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) - unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); + do { + unmap_single_vma(tlb, vma, start_addr, end_addr, &details); + } while ((vma = mas_find(&mas, end_addr - 1)) != NULL); mmu_notifier_invalidate_range_end(&range); } @@ -1344,19 +1746,23 @@ void unmap_vmas(struct mmu_gather *tlb, void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { + struct maple_tree *mt = &vma->vm_mm->mm_mt; + unsigned long end = start + size; struct mmu_notifier_range range; struct mmu_gather tlb; + MA_STATE(mas, mt, vma->vm_end, vma->vm_end); lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); - tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); + tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); - for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) + do { unmap_single_vma(&tlb, vma, start, range.end, NULL); + } while ((vma = mas_find(&mas, end - 1)) != NULL); mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb, start, range.end); + tlb_finish_mmu(&tlb); } /** @@ -1377,12 +1783,12 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); - tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); + tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); - tlb_finish_mmu(&tlb, address, range.end); + tlb_finish_mmu(&tlb); } /** @@ -1399,7 +1805,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr 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; @@ -1407,8 +1813,7 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(zap_vma_ptes); -pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, - spinlock_t **ptl) +static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; @@ -1427,9 +1832,40 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); + return pmd; +} + +pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pmd_t *pmd = walk_to_pmd(mm, addr); + + if (!pmd) + return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } +static int validate_page_before_insert(struct page *page) +{ + if (PageAnon(page) || PageSlab(page) || page_has_type(page)) + return -EINVAL; + flush_dcache_page(page); + return 0; +} + +static int insert_page_into_pte_locked(struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, struct page *page, pgprot_t prot) +{ + if (!pte_none(*pte)) + return -EBUSY; + /* Ok, finally just insert the thing.. */ + get_page(page); + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); + page_add_file_rmap(page, vma, false); + set_pte_at(vma->vm_mm, addr, pte, mk_pte(page, prot)); + return 0; +} + /* * This is the old fallback for page remapping. * @@ -1440,36 +1876,140 @@ pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { - struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; - retval = -EINVAL; - if (PageAnon(page) || PageSlab(page) || page_has_type(page)) + retval = validate_page_before_insert(page); + if (retval) goto out; retval = -ENOMEM; - flush_dcache_page(page); - pte = get_locked_pte(mm, addr, &ptl); + pte = get_locked_pte(vma->vm_mm, addr, &ptl); if (!pte) goto out; - retval = -EBUSY; - if (!pte_none(*pte)) - goto out_unlock; - - /* Ok, finally just insert the thing.. */ - get_page(page); - inc_mm_counter_fast(mm, mm_counter_file(page)); - page_add_file_rmap(page, false); - set_pte_at(mm, addr, pte, mk_pte(page, prot)); - - retval = 0; -out_unlock: + retval = insert_page_into_pte_locked(vma, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } +#ifdef pte_index +static int insert_page_in_batch_locked(struct vm_area_struct *vma, pte_t *pte, + unsigned long addr, struct page *page, pgprot_t prot) +{ + int err; + + if (!page_count(page)) + return -EINVAL; + err = validate_page_before_insert(page); + if (err) + return err; + return insert_page_into_pte_locked(vma, pte, addr, page, prot); +} + +/* insert_pages() amortizes the cost of spinlock operations + * when inserting pages in a loop. Arch *must* define pte_index. + */ +static int insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num, pgprot_t prot) +{ + 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); + 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; + } + if (remaining_pages_total) + goto more; + ret = 0; +out: + *num = remaining_pages_total; + return ret; +} +#endif /* ifdef pte_index */ + +/** + * 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. + * + * 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(). + */ +int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, + struct page **pages, unsigned long *num) +{ +#ifdef pte_index + const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; + + 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); + vma->vm_flags |= 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); +#else + unsigned long idx = 0, pgcount = *num; + int err = -EINVAL; + + for (; idx < pgcount; ++idx) { + err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); + if (err) + break; + } + *num = pgcount - idx; + return err; +#endif /* ifdef pte_index */ +} +EXPORT_SYMBOL(vm_insert_pages); + /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to @@ -1493,7 +2033,7 @@ 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. * @@ -1507,7 +2047,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, 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; } @@ -1656,7 +2196,7 @@ out_unlock: * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * - * This is exactly like vmf_insert_pfn(), except that it allows drivers to + * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for @@ -1792,7 +2332,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * - * This is exactly like vmf_insert_mixed(), except that it allows drivers to + * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and @@ -1846,11 +2386,11 @@ 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(); @@ -1864,7 +2404,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); return err; } @@ -1935,28 +2475,22 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, return 0; } -/** - * remap_pfn_range - remap kernel memory to userspace - * @vma: user vma to map to - * @addr: target user address to start at - * @pfn: physical address of kernel memory - * @size: size of map area - * @prot: page protection flags for this mapping - * - * Note: this is only safe if the mm semaphore is held when called. - * - * Return: %0 on success, negative error code otherwise. +/* + * 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. */ -int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, unsigned long size, pgprot_t prot) +int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; - unsigned long remap_pfn = pfn; int err; + if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) + return -EINVAL; + /* * Physically remapped pages are special. Tell the * rest of the world about it: @@ -1981,10 +2515,6 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, vma->vm_pgoff = pfn; } - err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); - if (err) - return -EINVAL; - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); @@ -1996,12 +2526,36 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) - break; + return err; } while (pgd++, addr = next, addr != end); + 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 = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) - untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); + return -EINVAL; + err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); + if (err) + untrack_pfn(vma, pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); @@ -2009,7 +2563,7 @@ EXPORT_SYMBOL(remap_pfn_range); /** * 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 @@ -2057,20 +2611,21 @@ 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, bool create) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { - pte_t *pte; + pte_t *pte, *mapped_pte; int err = 0; - spinlock_t *uninitialized_var(ptl); + spinlock_t *ptl; if (create) { - pte = (mm == &init_mm) ? - pte_alloc_kernel(pmd, addr) : + 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 { - pte = (mm == &init_mm) ? + mapped_pte = pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } @@ -2079,24 +2634,28 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, arch_enter_lazy_mmu_mode(); - do { - if (create || !pte_none(*pte)) { - err = fn(pte++, addr, data); - if (err) - break; - } - } while (addr += PAGE_SIZE, addr != end); + if (fn) { + do { + if (create || !pte_none(*pte)) { + err = fn(pte++, addr, data); + if (err) + break; + } + } while (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, bool create) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; @@ -2105,7 +2664,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, BUG_ON(pud_huge(*pud)); if (create) { - pmd = pmd_alloc(mm, pud, addr); + pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { @@ -2113,26 +2672,35 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, } do { next = pmd_addr_end(addr, end); - if (create || !pmd_none_or_clear_bad(pmd)) { - err = apply_to_pte_range(mm, pmd, addr, next, fn, data, - create); - if (err) - break; + 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, p4d_t *p4d, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data, bool create) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { - pud = pud_alloc(mm, p4d, addr); + pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { @@ -2140,26 +2708,35 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, } do { next = pud_addr_end(addr, end); - if (create || !pud_none_or_clear_bad(pud)) { - err = apply_to_pmd_range(mm, pud, addr, next, fn, data, - create); - if (err) - break; + 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; } 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) + pte_fn_t fn, void *data, bool create, + pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { - p4d = p4d_alloc(mm, pgd, addr); + p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { @@ -2167,13 +2744,21 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, } do { next = p4d_addr_end(addr, end); - if (create || !p4d_none_or_clear_bad(p4d)) { - err = apply_to_pud_range(mm, p4d, addr, next, fn, data, - create); - if (err) - break; + 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; } @@ -2182,8 +2767,9 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, void *data, bool create) { pgd_t *pgd; - unsigned long next; + unsigned long start = addr, next; unsigned long end = addr + size; + pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) @@ -2192,13 +2778,24 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - if (!create && pgd_none_or_clear_bad(pgd)) + if (pgd_none(*pgd) && !create) continue; - err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create); + if (WARN_ON_ONCE(pgd_leaf(*pgd))) + return -EINVAL; + 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; } @@ -2235,24 +2832,24 @@ EXPORT_SYMBOL_GPL(apply_to_existing_page_range); * 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_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { - spinlock_t *ptl = pte_lockptr(mm, pmd); + spinlock_t *ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(ptl); - same = pte_same(*page_table, orig_pte); + same = pte_same(*vmf->pte, vmf->orig_pte); spin_unlock(ptl); } #endif - pte_unmap(page_table); + pte_unmap(vmf->pte); + vmf->pte = NULL; return same; } -static inline bool cow_user_page(struct page *dst, struct page *src, - struct vm_fault *vmf) +static inline bool __wp_page_copy_user(struct page *dst, struct page *src, + struct vm_fault *vmf) { bool ret; void *kaddr; @@ -2262,8 +2859,6 @@ static inline bool cow_user_page(struct page *dst, struct page *src, struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; - debug_dma_assert_idle(src); - if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; @@ -2282,7 +2877,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src, * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ - if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { + 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); @@ -2290,10 +2885,9 @@ static inline bool cow_user_page(struct page *dst, struct page *src, if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault - * and we don't need to do anything. If it's - * not the case, the fault will be triggered - * again on the same address. + * and update local tlb only */ + update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } @@ -2317,13 +2911,14 @@ static inline bool cow_user_page(struct page *dst, struct page *src, vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { - /* The PTE changed under us. Retry page fault. */ + /* The PTE changed under us, update local tlb */ + update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* - * The same page can be mapped back since last copy attampt. + * 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)) { @@ -2430,7 +3025,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * - * Drop the mmap_sem before waiting on IO, if we can. The file + * 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) { @@ -2440,7 +3035,7 @@ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); - return VM_FAULT_RETRY; + return VM_FAULT_COMPLETED; } } @@ -2461,6 +3056,10 @@ static inline void wp_page_reuse(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; + + VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page)); + /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely @@ -2475,12 +3074,14 @@ static inline void wp_page_reuse(struct vm_fault *vmf) if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); + count_vm_event(PGREUSE); } /* - * Handle the case of a page which we actually need to copy to a new page. + * 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_sem locked and the old page referenced, but + * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: @@ -2495,15 +3096,17 @@ static inline void wp_page_reuse(struct vm_fault *vmf) */ 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 page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; - struct mem_cgroup *memcg; struct mmu_notifier_range range; + delayacct_wpcopy_start(); + if (unlikely(anon_vma_prepare(vma))) goto oom; @@ -2518,7 +3121,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) if (!new_page) goto oom; - if (!cow_user_page(new_page, old_page, vmf)) { + if (!__wp_page_copy_user(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on @@ -2528,12 +3131,16 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) put_page(new_page); if (old_page) put_page(old_page); + + delayacct_wpcopy_end(); return 0; } + kmsan_copy_page_meta(new_page, old_page); } - if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) + if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL)) goto oom_free_new; + cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); @@ -2558,22 +3165,32 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + 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. + * 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. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); - mem_cgroup_commit_charge(new_page, memcg, false, false); - lru_cache_add_active_or_unevictable(new_page, vma); + page_add_new_anon_rmap(new_page, vma, vmf->address); + lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ + BUG_ON(unshare && pte_write(entry)); set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { @@ -2599,14 +3216,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(old_page, false); + page_remove_rmap(old_page, vma, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg, false); + update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) @@ -2619,24 +3236,20 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if (page_copied && (vma->vm_flags & VM_LOCKED)) { - lock_page(old_page); /* LRU manipulation */ - if (PageMlocked(old_page)) - munlock_vma_page(old_page); - unlock_page(old_page); - } + if (page_copied) + free_swap_cache(old_page); put_page(old_page); } - return page_copied ? VM_FAULT_WRITE : 0; + + delayacct_wpcopy_end(); + return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); + + delayacct_wpcopy_end(); return VM_FAULT_OOM; } @@ -2653,7 +3266,7 @@ oom: * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * - * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before + * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) @@ -2666,6 +3279,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) * pte_offset_map_lock. */ if (!pte_same(*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; } @@ -2730,30 +3344,60 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) } /* - * 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. + * 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 we can safely just mark it writable once we've done any necessary - * COW. + * Thus, with FAULT_FLAG_WRITE, 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. + * 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_sem (to exclude vma changes, + * 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_sem still held, but pte unmapped and unlocked. + * 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; + + VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); + + if (likely(!unshare)) { + if (userfaultfd_pte_wp(vma, *vmf->pte)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * 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); + } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { + if (unlikely(unshare)) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. @@ -2773,50 +3417,58 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ - if (PageAnon(vmf->page)) { - int total_map_swapcount; - if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) || - page_count(vmf->page) != 1)) + folio = page_folio(vmf->page); + if (folio_test_anon(folio)) { + /* + * If the page is exclusive to this process we must reuse the + * page without further checks. + */ + if (PageAnonExclusive(vmf->page)) + goto reuse; + + /* + * 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) + goto copy; + if (!folio_test_lru(folio)) + /* + * Note: We cannot easily detect+handle references from + * remote LRU pagevecs or references to LRU folios. + */ + lru_add_drain(); + if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) + goto copy; + if (!folio_trylock(folio)) + goto copy; + if (folio_test_swapcache(folio)) + folio_free_swap(folio); + if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { + folio_unlock(folio); goto copy; - if (!trylock_page(vmf->page)) { - get_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - lock_page(vmf->page); - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); - if (!pte_same(*vmf->pte, vmf->orig_pte)) { - unlock_page(vmf->page); - pte_unmap_unlock(vmf->pte, vmf->ptl); - put_page(vmf->page); - return 0; - } - put_page(vmf->page); - } - if (PageKsm(vmf->page)) { - bool reused = reuse_ksm_page(vmf->page, vmf->vma, - vmf->address); - unlock_page(vmf->page); - if (!reused) - goto copy; - wp_page_reuse(vmf); - return VM_FAULT_WRITE; } - if (reuse_swap_page(vmf->page, &total_map_swapcount)) { - if (total_map_swapcount == 1) { - /* - * The page is all ours. Move it to - * our anon_vma so the rmap code will - * not search our parent or siblings. - * Protected against the rmap code by - * the page lock. - */ - page_move_anon_rmap(vmf->page, vma); - } - unlock_page(vmf->page); - wp_page_reuse(vmf); - return VM_FAULT_WRITE; + /* + * 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. + */ + page_move_anon_rmap(vmf->page, vma); + folio_unlock(folio); +reuse: + if (unlikely(unshare)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; } - unlock_page(vmf->page); + wp_page_reuse(vmf); + return VM_FAULT_WRITE; + } else if (unshare) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); @@ -2828,6 +3480,10 @@ copy: get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); +#ifdef CONFIG_KSM + if (PageKsm(vmf->page)) + count_vm_event(COW_KSM); +#endif return wp_page_copy(vmf); } @@ -2839,22 +3495,18 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, } 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; - 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, @@ -2864,6 +3516,40 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** + * 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 address_space *mapping = folio->mapping; + struct zap_details details = { }; + pgoff_t first_index; + pgoff_t last_index; + + VM_BUG_ON(!folio_test_locked(folio)); + + first_index = folio->index; + last_index = folio->index + folio_nr_pages(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. @@ -2879,18 +3565,20 @@ 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.check_mapping = even_cows ? NULL : mapping; - details.first_index = start; - details.last_index = start + nr - 1; - if (details.last_index < details.first_index) - details.last_index = ULONG_MAX; + details.even_cows = even_cows; + if (last_index < first_index) + last_index = ULONG_MAX; - i_mmap_lock_write(mapping); + i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); - i_mmap_unlock_write(mapping); + unmap_mapping_range_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 @@ -2928,25 +3616,128 @@ void unmap_mapping_range(struct address_space *mapping, EXPORT_SYMBOL(unmap_mapping_range); /* - * We enter with non-exclusive mmap_sem (to exclude vma changes, + * 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; + + if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) + return VM_FAULT_RETRY; + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + 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(pte_same(*vmf->pte, vmf->orig_pte))) + restore_exclusive_pte(vma, vmf->page, vmf->address, vmf->pte); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + folio_unlock(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 exlusive user. + */ + return (fault_flags & FAULT_FLAG_WRITE) && !folio_test_ksm(folio) && + folio_ref_count(folio) == 2; +} + +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); + /* + * 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. + */ + if (is_pte_marker(*vmf->pte)) + pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; +} + +/* + * 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 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. We can also do that + * proactively when e.g. when we do UFFDIO_UNREGISTER upon some uffd-wp + * ranges, but it should be more efficient to be done lazily here. + */ + if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma))) + return pte_marker_clear(vmf); + + /* do_fault() can handle pte markers too like none pte */ + return do_fault(vmf); +} + +static vm_fault_t handle_pte_marker(struct vm_fault *vmf) +{ + swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte); + unsigned long marker = pte_marker_get(entry); + + /* + * PTE markers should always be with file-backed memories, and the + * marker 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(vma_is_anonymous(vmf->vma) || !marker)) + return VM_FAULT_SIGBUS; + + if (pte_marker_entry_uffd_wp(entry)) + return pte_marker_handle_uffd_wp(vmf); + + /* This is an unknown pte marker */ + return VM_FAULT_SIGBUS; +} + +/* + * 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_sem locked or unlocked in the same cases + * 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 page *page = NULL, *swapcache; - struct mem_cgroup *memcg; + struct folio *swapcache, *folio = NULL; + struct page *page; + struct swap_info_struct *si = NULL; + rmap_t rmap_flags = RMAP_NONE; + bool exclusive = false; swp_entry_t entry; pte_t pte; int locked; - int exclusive = 0; vm_fault_t ret = 0; + void *shadow = NULL; - if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) + if (!pte_unmap_same(vmf)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); @@ -2954,11 +3745,32 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); + } else if (is_device_exclusive_entry(entry)) { + vmf->page = pfn_swap_entry_to_page(entry); + ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { - vmf->page = device_private_entry_to_page(entry); - ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); + vmf->page = pfn_swap_entry_to_page(entry); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + spin_unlock(vmf->ptl); + goto out; + } + + /* + * Get a page reference while we know the page can't be + * freed. + */ + get_page(vmf->page); + pte_unmap_unlock(vmf->pte, vmf->ptl); + vmf->page->pgmap->ops->migrate_to_ram(vmf); + put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; + } else if (is_swapin_error_entry(entry)) { + ret = VM_FAULT_SIGBUS; + } else if (is_pte_marker_entry(entry)) { + ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; @@ -2966,33 +3778,55 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out; } + /* Prevent swapoff from happening to us. */ + si = get_swap_device(entry); + if (unlikely(!si)) + goto out; - delayacct_set_flag(DELAYACCT_PF_SWAPIN); - page = lookup_swap_cache(entry, vma, vmf->address); - swapcache = page; - - if (!page) { - struct swap_info_struct *si = swp_swap_info(entry); + folio = swap_cache_get_folio(entry, vma, vmf->address); + if (folio) + page = folio_file_page(folio, swp_offset(entry)); + swapcache = folio; - if (si->flags & SWP_SYNCHRONOUS_IO && - __swap_count(entry) == 1) { + if (!folio) { + if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && + __swap_count(entry) == 1) { /* skip swapcache */ - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, - vmf->address); - if (page) { - __SetPageLocked(page); - __SetPageSwapBacked(page); - set_page_private(page, entry.val); - lru_cache_add_anon(page); - swap_readpage(page, true); + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, + vma, vmf->address, false); + page = &folio->page; + if (folio) { + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + + if (mem_cgroup_swapin_charge_folio(folio, + vma->vm_mm, GFP_KERNEL, + entry)) { + ret = VM_FAULT_OOM; + goto out_page; + } + mem_cgroup_swapin_uncharge_swap(entry); + + shadow = get_shadow_from_swap_cache(entry); + if (shadow) + workingset_refault(folio, shadow); + + folio_add_lru(folio); + + /* To provide entry to swap_readpage() */ + folio_set_swap_entry(folio, entry); + swap_readpage(page, true, NULL); + folio->private = NULL; } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); - swapcache = page; + if (page) + folio = page_folio(page); + swapcache = folio; } - if (!page) { + if (!folio) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. @@ -3001,7 +3835,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } @@ -3015,41 +3848,53 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } - locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); + locked = folio_lock_or_retry(folio, vma->vm_mm, vmf->flags); - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } - /* - * Make sure try_to_free_swap or reuse_swap_page or swapoff did not - * release the swapcache from under us. The page pin, and pte_same - * test below, are not enough to exclude that. Even if it is still - * swapcache, we need to check that the page's swap has not changed. - */ - if (unlikely((!PageSwapCache(page) || - page_private(page) != entry.val)) && swapcache) - goto out_page; - - page = ksm_might_need_to_copy(page, vma, vmf->address); - if (unlikely(!page)) { - ret = VM_FAULT_OOM; - page = swapcache; - goto out_page; - } + if (swapcache) { + /* + * 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. + */ + if (unlikely(!folio_test_swapcache(folio) || + page_private(page) != entry.val)) + goto out_page; + + /* + * KSM sometimes has to copy on read faults, for example, if + * page->index of !PageKSM() pages would be nonlinear inside the + * anon VMA -- PageKSM() is lost on actual swapout. + */ + page = ksm_might_need_to_copy(page, vma, vmf->address); + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + goto out_page; + } + folio = page_folio(page); - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, - &memcg, false)) { - ret = VM_FAULT_OOM; - goto out_page; + /* + * 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 + * pagevecs if required. + */ + if ((vmf->flags & FAULT_FLAG_WRITE) && folio == swapcache && + !folio_test_ksm(folio) && !folio_test_lru(folio)) + lru_add_drain(); } + cgroup_throttle_swaprate(page, GFP_KERNEL); + /* * Back out if somebody else already faulted in this pte. */ @@ -3058,54 +3903,114 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; - if (unlikely(!PageUptodate(page))) { + if (unlikely(!folio_test_uptodate(folio))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* - * The page isn't present yet, go ahead with the fault. - * - * Be careful about the sequence of operations here. - * To get its accounting right, reuse_swap_page() must be called - * while the page is counted on swap but not yet in mapcount i.e. - * before page_add_anon_rmap() and swap_free(); try_to_free_swap() - * must be called after the swap_free(), or it will never succeed. + * 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. + */ + BUG_ON(!folio_test_anon(folio) && folio_test_mappedtodisk(folio)); + BUG_ON(folio_test_anon(folio) && PageAnonExclusive(page)); + + /* + * Check under PT lock (to protect against concurrent fork() sharing + * the swap entry concurrently) for certainly exclusive pages. + */ + if (!folio_test_ksm(folio)) { + /* + * Note that pte_swp_exclusive() == false for architectures + * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE. + */ + 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; + } + } + + /* + * 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(entry); + if (should_try_to_free_swap(folio, vma, vmf->flags)) + folio_free_swap(folio); inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); - vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; - exclusive = RMAP_EXCLUSIVE; + + /* + * 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 (vmf->flags & FAULT_FLAG_WRITE) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + vmf->flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + } + rmap_flags |= RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); - set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); - arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); + if (pte_swp_uffd_wp(vmf->orig_pte)) { + pte = pte_mkuffd_wp(pte); + pte = pte_wrprotect(pte); + } vmf->orig_pte = pte; /* ksm created a completely new copy */ - if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + if (unlikely(folio != swapcache && swapcache)) { + page_add_new_anon_rmap(page, vma, vmf->address); + folio_add_lru_vma(folio, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); - mem_cgroup_commit_charge(page, memcg, true, false); - activate_page(page); + page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } - swap_free(entry); - if (mem_cgroup_swap_full(page) || - (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) - try_to_free_swap(page); - unlock_page(page); - if (page != swapcache && swapcache) { + VM_BUG_ON(!folio_test_anon(folio) || + (pte_write(pte) && !PageAnonExclusive(page))); + set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); + arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); + + 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 @@ -3114,8 +4019,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * so that the swap count won't change under a * parallel locked swapcache. */ - unlock_page(swapcache); - put_page(swapcache); + folio_unlock(swapcache); + folio_put(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { @@ -3130,30 +4035,32 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: + if (si) + put_swap_device(si); return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg, false); pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: - unlock_page(page); + folio_unlock(folio); out_release: - put_page(page); - if (page != swapcache && swapcache) { - unlock_page(swapcache); - put_page(swapcache); + folio_put(folio); + if (folio != swapcache && swapcache) { + folio_unlock(swapcache); + folio_put(swapcache); } + if (si) + put_swap_device(si); return ret; } /* - * 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 vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct mem_cgroup *memcg; struct page *page; vm_fault_t ret = 0; pte_t entry; @@ -3167,15 +4074,15 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * - * pte_alloc_map() is safe to use under down_write(mmap_sem) or when + * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * - * Here we only have down_read(mmap_sem). + * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; - /* See the comment in pte_alloc_one_map() */ + /* See comment in handle_pte_fault() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; @@ -3186,8 +4093,10 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) + if (!pte_none(*vmf->pte)) { + update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; + } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; @@ -3206,9 +4115,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, - false)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto oom_free_page; + cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that @@ -3218,13 +4127,16 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) + if (!pte_none(*vmf->pte)) { + update_mmu_tlb(vma, vmf->address, vmf->pte); goto release; + } ret = check_stable_address_space(vma->vm_mm); if (ret) @@ -3233,15 +4145,13 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, false); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + page_add_new_anon_rmap(page, vma, vmf->address); + lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -3251,7 +4161,6 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: - mem_cgroup_cancel_charge(page, memcg, false); put_page(page); goto unlock; oom_free_page: @@ -3261,7 +4170,7 @@ oom: } /* - * The mmap_sem must have been held on entry, and may have been + * 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(). */ @@ -3278,7 +4187,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) * unlock_page(A) * lock_page(B) * lock_page(B) - * pte_alloc_pne + * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) @@ -3286,10 +4195,9 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { - vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); + vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; - smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); @@ -3298,11 +4206,20 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; if (unlikely(PageHWPoison(vmf->page))) { - if (ret & VM_FAULT_LOCKED) - unlock_page(vmf->page); - put_page(vmf->page); + struct page *page = vmf->page; + vm_fault_t poisonret = VM_FAULT_HWPOISON; + if (ret & VM_FAULT_LOCKED) { + if (page_mapped(page)) + unmap_mapping_pages(page_mapping(page), + page->index, 1, false); + /* Retry if a clean page was removed from the cache. */ + if (invalidate_inode_page(page)) + poisonret = VM_FAULT_NOPAGE; + unlock_page(page); + } + put_page(page); vmf->page = NULL; - return VM_FAULT_HWPOISON; + return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) @@ -3313,67 +4230,7 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; } -/* - * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. - * If we check pmd_trans_unstable() first we will trip the bad_pmd() check - * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly - * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. - */ -static int pmd_devmap_trans_unstable(pmd_t *pmd) -{ - return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); -} - -static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) -{ - struct vm_area_struct *vma = vmf->vma; - - if (!pmd_none(*vmf->pmd)) - goto map_pte; - if (vmf->prealloc_pte) { - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_none(*vmf->pmd))) { - spin_unlock(vmf->ptl); - goto map_pte; - } - - mm_inc_nr_ptes(vma->vm_mm); - pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); - spin_unlock(vmf->ptl); - vmf->prealloc_pte = NULL; - } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { - return VM_FAULT_OOM; - } -map_pte: - /* - * If a huge pmd materialized under us just retry later. Use - * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of - * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge - * under us and then back to pmd_none, as a result of MADV_DONTNEED - * running immediately after a huge pmd fault in a different thread of - * this mm, in turn leading to a misleading pmd_trans_huge() retval. - * All we have to ensure is that it is a regular pmd that we can walk - * with pte_offset_map() and we can do that through an atomic read in - * C, which is what pmd_trans_unstable() provides. - */ - if (pmd_devmap_trans_unstable(vmf->pmd)) - return VM_FAULT_NOPAGE; - - /* - * At this point we know that our vmf->pmd points to a page of ptes - * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() - * for the duration of the fault. If a racing MADV_DONTNEED runs and - * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still - * be valid and we will re-check to make sure the vmf->pte isn't - * pte_none() under vmf->ptl protection when we return to - * alloc_set_pte(). - */ - vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); - return 0; -} - -#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; @@ -3387,30 +4244,39 @@ static void deposit_prealloc_pte(struct vm_fault *vmf) vmf->prealloc_pte = NULL; } -static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +vm_fault_t do_set_pmd(struct vm_fault *vmf, 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; int i; - vm_fault_t ret; + vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) - return VM_FAULT_FALLBACK; + return ret; - ret = VM_FAULT_FALLBACK; page = compound_head(page); + if (compound_order(page) != HPAGE_PMD_ORDER) + return ret; /* - * Archs like ppc64 need additonal space to store information + * 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(PageHasHWPoisoned(page))) + 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; - smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); @@ -3425,7 +4291,8 @@ static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); - page_add_file_rmap(page, true); + page_add_file_rmap(page, vma, true); + /* * deposit and withdraw with pmd lock held */ @@ -3444,80 +4311,52 @@ out: return ret; } #else -static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { - BUILD_BUG(); - return 0; + return VM_FAULT_FALLBACK; } #endif -/** - * alloc_set_pte - setup new PTE entry for given page and add reverse page - * mapping. If needed, the fucntion allocates page table or use pre-allocated. - * - * @vmf: fault environment - * @memcg: memcg to charge page (only for private mappings) - * @page: page to map - * - * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on - * return. - * - * Target users are page handler itself and implementations of - * vm_ops->map_pages. - * - * Return: %0 on success, %VM_FAULT_ code in case of error. - */ -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, - struct page *page) +void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; + bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte); bool write = vmf->flags & FAULT_FLAG_WRITE; + bool prefault = vmf->address != addr; pte_t entry; - vm_fault_t ret; - - if (pmd_none(*vmf->pmd) && PageTransCompound(page) && - IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) { - /* THP on COW? */ - VM_BUG_ON_PAGE(memcg, page); - - ret = do_set_pmd(vmf, page); - if (ret != VM_FAULT_FALLBACK) - return ret; - } - - if (!vmf->pte) { - ret = pte_alloc_one_map(vmf); - if (ret) - return ret; - } - - /* Re-check under ptl */ - if (unlikely(!pte_none(*vmf->pte))) - return VM_FAULT_NOPAGE; flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); + + if (prefault && arch_wants_old_prefaulted_pte()) + entry = pte_mkold(entry); + else + entry = pte_sw_mkyoung(entry); + if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (unlikely(uffd_wp)) + entry = pte_mkuffd_wp(pte_wrprotect(entry)); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); - mem_cgroup_commit_charge(page, memcg, false, false); - lru_cache_add_active_or_unevictable(page, vma); + page_add_new_anon_rmap(page, vma, addr); + lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); - page_add_file_rmap(page, false); + page_add_file_rmap(page, vma, false); } - set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); + set_pte_at(vma->vm_mm, addr, vmf->pte, entry); +} - /* no need to invalidate: a not-present page won't be cached */ - update_mmu_cache(vma, vmf->address, vmf->pte); +static bool vmf_pte_changed(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) + return !pte_same(*vmf->pte, vmf->orig_pte); - return 0; + return !pte_none(*vmf->pte); } - /** * finish_fault - finish page fault once we have prepared the page to fault * @@ -3535,12 +4374,12 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, */ vm_fault_t finish_fault(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct page *page; - vm_fault_t ret = 0; + vm_fault_t ret; /* Did we COW the page? */ - if ((vmf->flags & FAULT_FLAG_WRITE) && - !(vmf->vma->vm_flags & VM_SHARED)) + if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; @@ -3549,12 +4388,49 @@ vm_fault_t finish_fault(struct vm_fault *vmf) * check even for read faults because we might have lost our CoWed * page */ - if (!(vmf->vma->vm_flags & VM_SHARED)) - ret = check_stable_address_space(vmf->vma->vm_mm); - if (!ret) - ret = alloc_set_pte(vmf, vmf->memcg, page); - if (vmf->pte) - pte_unmap_unlock(vmf->pte, vmf->ptl); + if (!(vma->vm_flags & VM_SHARED)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) + return ret; + } + + if (pmd_none(*vmf->pmd)) { + if (PageTransCompound(page)) { + ret = do_set_pmd(vmf, 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; + } + + /* + * See comment in handle_pte_fault() for how this scenario happens, we + * need to return NOPAGE so that we drop this page. + */ + if (pmd_devmap_trans_unstable(vmf->pmd)) + return VM_FAULT_NOPAGE; + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + + /* Re-check under ptl */ + if (likely(!vmf_pte_changed(vmf))) { + do_set_pte(vmf, page, vmf->address); + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, vmf->address, vmf->pte); + + ret = 0; + } else { + update_mmu_tlb(vma, vmf->address, vmf->pte); + ret = VM_FAULT_NOPAGE; + } + + pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } @@ -3602,10 +4478,6 @@ late_initcall(fault_around_debugfs); * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * - * This function is called with the page table lock taken. In the split ptlock - * case the page table lock only protects only those entries which belong to - * the page table corresponding to the fault address. - * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * @@ -3624,13 +4496,12 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; - vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; - vmf->address = max(address & mask, vmf->vma->vm_start); - off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); + address = max(address & mask, vmf->vma->vm_start); + off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* @@ -3638,7 +4509,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + + ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); @@ -3646,36 +4517,27 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) - goto out; - smp_wmb(); /* See comment in __pte_alloc() */ + return VM_FAULT_OOM; } - vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); + return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); +} - /* Huge page is mapped? Page fault is solved */ - if (pmd_trans_huge(*vmf->pmd)) { - ret = VM_FAULT_NOPAGE; - goto out; - } +/* 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; - /* ->map_pages() haven't done anything useful. Cold page cache? */ - if (!vmf->pte) - goto out; + if (uffd_disable_fault_around(vmf->vma)) + return false; - /* check if the page fault is solved */ - vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); - if (!pte_none(*vmf->pte)) - ret = VM_FAULT_NOPAGE; - pte_unmap_unlock(vmf->pte, vmf->ptl); -out: - vmf->address = address; - vmf->pte = NULL; - return ret; + return fault_around_bytes >> PAGE_SHIFT > 1; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* @@ -3683,7 +4545,7 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { + if (should_fault_around(vmf)) { ret = do_fault_around(vmf); if (ret) return ret; @@ -3712,11 +4574,12 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL, - &vmf->memcg, false)) { + if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm, + GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } + cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) @@ -3734,7 +4597,6 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) goto uncharge_out; return ret; uncharge_out: - mem_cgroup_cancel_charge(vmf->cow_page, vmf->memcg, false); put_page(vmf->cow_page); return ret; } @@ -3775,11 +4637,11 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) } /* - * 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). - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). - * If mmap_sem is released, vma may become invalid (for example + * 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 vm_fault_t do_fault(struct vm_fault *vmf) @@ -3832,9 +4694,8 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int page_nid, - int *flags) +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, int *flags) { get_page(page); @@ -3854,7 +4715,6 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; - bool migrated = false; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; @@ -3871,29 +4731,17 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) goto out; } - /* - * Make it present again, Depending on how arch implementes non - * accessible ptes, some can allow access by kernel mode. - */ - old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); + /* Get the normal PTE */ + old_pte = ptep_get(vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); - pte = pte_mkyoung(pte); - if (was_writable) - pte = pte_mkwrite(pte); - ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); - update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); - if (!page) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return 0; - } + if (!page || is_zone_device_page(page)) + goto out_map; /* TODO: handle PTE-mapped THP */ - if (PageCompound(page)) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return 0; - } + if (PageCompound(page)) + goto out_map; /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as @@ -3903,7 +4751,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ - if (!pte_write(pte)) + if (!was_writable) flags |= TNF_NO_GROUP; /* @@ -3913,28 +4761,57 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; - last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); + /* + * For memory tiering mode, cpupid of slow memory page is used + * to record page access time. So use default value. + */ + if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && + !node_is_toptier(page_nid)) + last_cpupid = (-1 & LAST_CPUPID_MASK); + else + last_cpupid = page_cpupid_last(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); - pte_unmap_unlock(vmf->pte, vmf->ptl); if (target_nid == NUMA_NO_NODE) { put_page(page); - goto out; + goto out_map; } + pte_unmap_unlock(vmf->pte, vmf->ptl); /* Migrate to the requested node */ - migrated = migrate_misplaced_page(page, vma, target_nid); - if (migrated) { + if (migrate_misplaced_page(page, vma, target_nid)) { page_nid = target_nid; flags |= TNF_MIGRATED; - } else + } else { flags |= TNF_MIGRATE_FAIL; + vmf->pte = pte_offset_map(vmf->pmd, vmf->address); + spin_lock(vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto out; + } + goto out_map; + } out: if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; +out_map: + /* + * Make it present again, depending on how arch implements + * non-accessible ptes, some can allow access by kernel mode. + */ + old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); + pte = pte_modify(old_pte, vma->vm_page_prot); + pte = pte_mkyoung(pte); + if (was_writable) + pte = pte_mkwrite(pte); + ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); + update_mmu_cache(vma, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto out; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) @@ -3947,28 +4824,33 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) } /* `inline' is required to avoid gcc 4.1.2 build error */ -static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { - if (vma_is_anonymous(vmf->vma)) - return do_huge_pmd_wp_page(vmf, orig_pmd); - if (vmf->vma->vm_ops->huge_fault) - return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + + if (vma_is_anonymous(vmf->vma)) { + if (likely(!unshare) && + userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) + return handle_userfault(vmf, VM_UFFD_WP); + return do_huge_pmd_wp_page(vmf); + } + if (vmf->vma->vm_ops->huge_fault) { + vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } - /* COW handled on pte level: split pmd */ - VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma); + /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } -static inline bool vma_is_accessible(struct vm_area_struct *vma) -{ - return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE); -} - static vm_fault_t create_huge_pud(struct vm_fault *vmf) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; @@ -3980,13 +4862,21 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) - return VM_FAULT_FALLBACK; - if (vmf->vma->vm_ops->huge_fault) - return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + goto split; + if (vmf->vma->vm_ops->huge_fault) { + vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + } +split: + /* COW or write-notify not handled on PUD level: split pud.*/ + __split_huge_pud(vmf->vma, vmf->pud, vmf->address); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } @@ -3999,11 +4889,11 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) * 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 + * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * - * The mmap_sem may have been released depending on flags and our return value. - * See filemap_fault() and __lock_page_or_retry(). + * The mmap_lock may have been released depending on flags and our return value. + * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { @@ -4017,18 +4907,31 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * concurrent faults and from rmap lookups. */ vmf->pte = NULL; + vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { - /* See comment in pte_alloc_one_map() */ + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead + * of pmd_trans_huge() to ensure the pmd didn't become + * pmd_trans_huge under us and then back to pmd_none, as a + * result of MADV_DONTNEED running immediately after a huge pmd + * fault in a different thread of this mm, in turn leading to a + * misleading pmd_trans_huge() retval. All we have to ensure is + * that it is a regular pmd that we can walk with + * pte_offset_map() and we can do that through an atomic read + * in C, which is what pmd_trans_unstable() provides. + */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the - * mmap_sem read mode and khugepaged takes it in write mode. + * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; + vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; /* * some architectures can have larger ptes than wordsize, @@ -4061,18 +4964,24 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; - if (unlikely(!pte_same(*vmf->pte, entry))) + if (unlikely(!pte_same(*vmf->pte, entry))) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; - if (vmf->flags & FAULT_FLAG_WRITE) { + } + if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); - entry = pte_mkdirty(entry); + else if (likely(vmf->flags & FAULT_FLAG_WRITE)) + entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. @@ -4090,8 +4999,8 @@ unlock: /* * By the time we get here, we already hold the mm semaphore * - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * The mmap_lock may have been released depending on flags and our + * return value. See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) @@ -4099,12 +5008,13 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, 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), }; - unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; + unsigned long vm_flags = vma->vm_flags; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; @@ -4118,7 +5028,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, if (!vmf.pud) return VM_FAULT_OOM; retry_pud: - if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { + if (pud_none(*vmf.pud) && + hugepage_vma_check(vma, vm_flags, false, true, true)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4128,9 +5039,11 @@ retry_pud: barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { - /* NUMA case for anonymous PUDs would go here */ - - if (dirty && !pud_write(orig_pud)) { + /* + * TODO once we support anonymous PUDs: NUMA case and + * FAULT_FLAG_UNSHARE handling. + */ + if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4149,31 +5062,33 @@ retry_pud: if (pud_trans_unstable(vmf.pud)) goto retry_pud; - if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { + if (pmd_none(*vmf.pmd) && + hugepage_vma_check(vma, vm_flags, false, true, true)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - pmd_t orig_pmd = *vmf.pmd; + vmf.orig_pmd = *vmf.pmd; barrier(); - if (unlikely(is_swap_pmd(orig_pmd))) { + if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(orig_pmd)); - if (is_pmd_migration_entry(orig_pmd)) + !is_pmd_migration_entry(vmf.orig_pmd)); + if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } - if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { - if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) - return do_huge_pmd_numa_page(&vmf, orig_pmd); + if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); - if (dirty && !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); + 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 { - huge_pmd_set_accessed(&vmf, orig_pmd); + huge_pmd_set_accessed(&vmf); return 0; } } @@ -4182,14 +5097,96 @@ retry_pud: return handle_pte_fault(&vmf); } +/** + * mm_account_fault - Do page fault accounting + * + * @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 pt_regs *regs, + unsigned long address, unsigned int flags, + vm_fault_t ret) +{ + bool major; + + /* + * We don't do accounting for some specific faults: + * + * - 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. + * + * - Incomplete faults (VM_FAULT_RETRY). They will only be counted + * once they're completed. + */ + if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) + 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 doesn't apply to sequential or random reads */ + current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)); +} + +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 */ + /* * By the time we get here, we already hold the mm semaphore * - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * 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) + unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; @@ -4213,11 +5210,15 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, 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); + lru_gen_exit_fault(); + if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* @@ -4230,6 +5231,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } + mm_account_fault(regs, address, flags, ret); + return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); @@ -4245,13 +5248,13 @@ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); - if (pgd_present(*pgd)) /* Another has populated it */ + if (pgd_present(*pgd)) { /* Another has populated it */ p4d_free(mm, new); - else + } else { + smp_wmb(); /* See comment in pmd_install() */ pgd_populate(mm, pgd, new); + } spin_unlock(&mm->page_table_lock); return 0; } @@ -4268,22 +5271,13 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - spin_lock(&mm->page_table_lock); -#ifndef __ARCH_HAS_5LEVEL_HACK 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 - if (!pgd_present(*p4d)) { - mm_inc_nr_puds(mm); - pgd_populate(mm, p4d, new); - } else /* Another has populated it */ - pud_free(mm, new); -#endif /* __ARCH_HAS_5LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; } @@ -4301,22 +5295,42 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) if (!new) return -ENOMEM; - smp_wmb(); /* See comment in __pte_alloc */ - 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 /* Another has populated it */ + } else { /* Another has populated it */ pmd_free(mm, new); + } spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ -static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, - pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) +/** + * follow_pte - look up PTE at a user virtual address + * @mm: the mm_struct of the target address space + * @address: user virtual address + * @ptepp: location to store found PTE + * @ptlp: location to store the lock for the PTE + * + * On a successful return, the pointer to the PTE is stored in @ptepp; + * the corresponding lock is taken and its location is stored in @ptlp. + * The contents of the PTE are only stable until @ptlp is released; + * any further use, if any, must be protected against invalidation + * with MMU notifiers. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read. + * + * KVM uses this function. While it is arguably less bad than ``follow_pfn``, + * it is not a good general-purpose API. + * + * Return: zero on success, -ve otherwise. + */ +int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; @@ -4339,35 +5353,9 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_huge(*pmd)) { - if (!pmdpp) - goto out; - - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, - NULL, mm, address & PMD_MASK, - (address & PMD_MASK) + PMD_SIZE); - mmu_notifier_invalidate_range_start(range); - } - *ptlp = pmd_lock(mm, pmd); - if (pmd_huge(*pmd)) { - *pmdpp = pmd; - return 0; - } - spin_unlock(*ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); - } - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, - address & PAGE_MASK, - (address & PAGE_MASK) + PAGE_SIZE); - mmu_notifier_invalidate_range_start(range); - } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; @@ -4375,37 +5363,10 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, return 0; unlock: pte_unmap_unlock(ptep, *ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); 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_pmd(mm, address, NULL, - ptepp, NULL, ptlp))); - return res; -} - -int follow_pte_pmd(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, - pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) -{ - int res; - - /* (void) is needed to make gcc happy */ - (void) __cond_lock(*ptlp, - !(res = __follow_pte_pmd(mm, address, range, - ptepp, pmdpp, ptlp))); - return res; -} -EXPORT_SYMBOL(follow_pte_pmd); +EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address @@ -4415,6 +5376,9 @@ EXPORT_SYMBOL(follow_pte_pmd); * * Only IO mappings and raw PFN mappings are allowed. * + * This function does not allow the caller to read the permissions + * of the PTE. Do not use it. + * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, @@ -4465,44 +5429,83 @@ 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; void __iomem *maddr; - int offset = addr & (PAGE_SIZE-1); + pte_t *ptep, pte; + spinlock_t *ptl; + int offset = offset_in_page(addr); + int ret = -EINVAL; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; - if (follow_phys(vma, addr, write, &prot, &phys_addr)) +retry: + if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) + return -EINVAL; + pte = *ptep; + pte_unmap_unlock(ptep, ptl); + + prot = pgprot_val(pte_pgprot(pte)); + phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + + if ((write & FOLL_WRITE) && !pte_write(pte)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; + if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) + goto out_unmap; + + if (!pte_same(pte, *ptep)) { + pte_unmap_unlock(ptep, ptl); + iounmap(maddr); + + goto retry; + } + if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); + ret = len; + pte_unmap_unlock(ptep, ptl); +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. */ -int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, void *buf, int len, unsigned int gup_flags) +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 (down_read_killable(&mm->mmap_sem)) + if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ @@ -4511,7 +5514,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, void *maddr; struct page *page = NULL; - ret = get_user_pages_remote(tsk, mm, addr, 1, + ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT @@ -4521,8 +5524,8 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) + vma = vma_lookup(mm, addr); + if (!vma) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, @@ -4553,7 +5556,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, buf += bytes; addr += bytes; } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); return buf - old_buf; } @@ -4573,7 +5576,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { - return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); + return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* @@ -4591,7 +5594,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, if (!mm) return 0; - ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); + ret = __access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); @@ -4610,7 +5613,7 @@ void print_vma_addr(char *prefix, unsigned long ip) /* * we might be running from an atomic context so we cannot sleep */ - if (!down_read_trylock(&mm->mmap_sem)) + if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); @@ -4629,26 +5632,18 @@ void print_vma_addr(char *prefix, unsigned long ip) free_page((unsigned long)buf); } } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) 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 (uaccess_kernel()) - return; if (pagefault_disabled()) return; - __might_sleep(file, line, 0); + __might_sleep(file, line); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) - might_lock_read(¤t->mm->mmap_sem); + might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); @@ -4711,11 +5706,11 @@ static void clear_gigantic_page(struct page *page, unsigned int pages_per_huge_page) { int i; - struct page *p = page; + struct page *p; might_sleep(); - for (i = 0; i < pages_per_huge_page; - i++, p = mem_map_next(p, page, i)) { + for (i = 0; i < pages_per_huge_page; i++) { + p = nth_page(page, i); cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } @@ -4751,13 +5746,12 @@ static void copy_user_gigantic_page(struct page *dst, struct page *src, struct page *dst_base = dst; struct page *src_base = src; - for (i = 0; i < pages_per_huge_page; ) { + for (i = 0; i < pages_per_huge_page; i++) { + dst = nth_page(dst_base, i); + src = nth_page(src_base, i); + cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); - - i++; - dst = mem_map_next(dst, dst_base, i); - src = mem_map_next(src, src_base, i); } } @@ -4801,21 +5795,21 @@ long copy_huge_page_from_user(struct page *dst_page, unsigned int pages_per_huge_page, bool allow_pagefault) { - void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; + struct page *subpage; for (i = 0; i < pages_per_huge_page; i++) { + subpage = nth_page(dst_page, i); if (allow_pagefault) - page_kaddr = kmap(dst_page + i); + page_kaddr = kmap(subpage); else - page_kaddr = kmap_atomic(dst_page + i); + page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, - (const void __user *)(src + i * PAGE_SIZE), - PAGE_SIZE); + usr_src + i * PAGE_SIZE, PAGE_SIZE); if (allow_pagefault) - kunmap(dst_page + i); + kunmap(subpage); else kunmap_atomic(page_kaddr); @@ -4823,6 +5817,8 @@ long copy_huge_page_from_user(struct page *dst_page, if (rc) break; + flush_dcache_page(subpage); + cond_resched(); } return ret_val; |