diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/gup.c | 68 | ||||
-rw-r--r-- | mm/huge_memory.c | 64 | ||||
-rw-r--r-- | mm/hugetlb.c | 26 | ||||
-rw-r--r-- | mm/mmap.c | 7 | ||||
-rw-r--r-- | mm/shmem.c | 59 | ||||
-rw-r--r-- | mm/userfaultfd.c | 29 | ||||
-rw-r--r-- | mm/vmstat.c | 9 |
7 files changed, 174 insertions, 88 deletions
@@ -478,14 +478,42 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, return -EEXIST; } -/* - * FOLL_FORCE can write to even unwritable pte's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ +static inline bool can_follow_write_pte(pte_t pte, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pte_write(pte) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte)); + /* If the pte is writable, we can write to the page. */ + if (pte_write(pte)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) + return false; + return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, @@ -528,12 +556,19 @@ retry: } if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; - if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) { - pte_unmap_unlock(ptep, ptl); - return NULL; - } page = vm_normal_page(vma, address, pte); + + /* + * We only care about anon pages in can_follow_write_pte() and don't + * have to worry about pte_devmap() because they are never anon. + */ + if ((flags & FOLL_WRITE) && + !can_follow_write_pte(pte, page, vma, flags)) { + page = NULL; + goto out; + } + if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN @@ -986,17 +1021,6 @@ static int faultin_page(struct vm_area_struct *vma, return -EBUSY; } - /* - * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when - * necessary, even if maybe_mkwrite decided not to set pte_write. We - * can thus safely do subsequent page lookups as if they were reads. - * But only do so when looping for pte_write is futile: in some cases - * userspace may also be wanting to write to the gotten user page, - * which a read fault here might prevent (a readonly page might get - * reCOWed by userspace write). - */ - if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE)) - *flags |= FOLL_COW; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8a7c1b344abe..e9414ee57c5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1040,12 +1040,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, assert_spin_locked(pmd_lockptr(mm, pmd)); - /* - * When we COW a devmap PMD entry, we split it into PTEs, so we should - * not be in this function with `flags & FOLL_COW` set. - */ - WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set"); - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) @@ -1395,14 +1389,42 @@ fallback: return VM_FAULT_FALLBACK; } -/* - * FOLL_FORCE can write to even unwritable pmd's, but only - * after we've gone through a COW cycle and they are dirty. - */ -static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags) +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) { - return pmd_write(pmd) || - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd)); + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, @@ -1411,12 +1433,16 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; - struct page *page = NULL; + struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); - if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags)) - goto out; + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(*pmd, page, vma, flags)) + return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) @@ -1424,10 +1450,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, /* Full NUMA hinting faults to serialise migration in fault paths */ if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) - goto out; - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + return NULL; if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) return ERR_PTR(-EMLINK); @@ -1444,7 +1467,6 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); -out: return page; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0aee2f3ae15c..2480ba627aa5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5241,6 +5241,21 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, VM_BUG_ON(unshare && (flags & FOLL_WRITE)); VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + /* + * hugetlb does not support FOLL_FORCE-style write faults that keep the + * PTE mapped R/O such as maybe_mkwrite() would do. + */ + if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) + return VM_FAULT_SIGSEGV; + + /* Let's take out MAP_SHARED mappings first. */ + if (vma->vm_flags & VM_MAYSHARE) { + if (unlikely(unshare)) + return 0; + set_huge_ptep_writable(vma, haddr, ptep); + return 0; + } + pte = huge_ptep_get(ptep); old_page = pte_page(pte); @@ -5781,12 +5796,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the - * spinlock. For private mappings, we also lookup the pagecache - * page now as it is used to determine if a reservation has been - * consumed. + * spinlock. Also lookup the pagecache page now as it is used to + * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !huge_pte_write(entry)) { + !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -5794,9 +5808,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); - if (!(vma->vm_flags & VM_MAYSHARE)) - pagecache_page = hugetlbfs_pagecache_page(h, - vma, haddr); + pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); diff --git a/mm/mmap.c b/mm/mmap.c index c035020d0c89..9d780f415be3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1646,8 +1646,11 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; - /* Do we need to track softdirty? */ - if (vma_soft_dirty_enabled(vma)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ diff --git a/mm/shmem.c b/mm/shmem.c index 5783f11351bb..d075dd2dcc48 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1659,7 +1659,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, new = page_folio(newpage); mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); + __inc_lruvec_page_state(newpage, NR_SHMEM); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); + __dec_lruvec_page_state(oldpage, NR_SHMEM); } xa_unlock_irq(&swap_mapping->i_pages); @@ -2281,16 +2283,34 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -/* Mask out flags that are inappropriate for the given type of inode. */ -static unsigned shmem_mask_flags(umode_t mode, __u32 flags) +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); + +/* + * chattr's fsflags are unrelated to extended attributes, + * but tmpfs has chosen to enable them under the same config option. + */ +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) +{ + unsigned int i_flags = 0; + + if (fsflags & FS_NOATIME_FL) + i_flags |= S_NOATIME; + if (fsflags & FS_APPEND_FL) + i_flags |= S_APPEND; + if (fsflags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + /* + * But FS_NODUMP_FL does not require any action in i_flags. + */ + inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE); +} +#else +static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags) { - if (S_ISDIR(mode)) - return flags; - else if (S_ISREG(mode)) - return flags & SHMEM_REG_FLMASK; - else - return flags & SHMEM_OTHER_FLMASK; } +#define shmem_initxattrs NULL +#endif static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) @@ -2319,7 +2339,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, info->i_crtime = inode->i_mtime; info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; - info->fsflags = shmem_mask_flags(mode, info->fsflags); + if (info->fsflags) + shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); @@ -2468,12 +2489,6 @@ out_unacct_blocks: static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; -#ifdef CONFIG_TMPFS_XATTR -static int shmem_initxattrs(struct inode *, const struct xattr *, void *); -#else -#define shmem_initxattrs NULL -#endif - static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, @@ -2826,12 +2841,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); - inode->i_ctime = current_time(inode); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: + if (!error) + file_modified(file); inode_unlock(inode); return error; } @@ -3179,18 +3195,13 @@ static int shmem_fileattr_set(struct user_namespace *mnt_userns, if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; + if (fa->flags & ~SHMEM_FL_USER_MODIFIABLE) + return -EOPNOTSUPP; info->fsflags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) | (fa->flags & SHMEM_FL_USER_MODIFIABLE); - inode->i_flags &= ~(S_APPEND | S_IMMUTABLE | S_NOATIME); - if (info->fsflags & FS_APPEND_FL) - inode->i_flags |= S_APPEND; - if (info->fsflags & FS_IMMUTABLE_FL) - inode->i_flags |= S_IMMUTABLE; - if (info->fsflags & FS_NOATIME_FL) - inode->i_flags |= S_NOATIME; - + shmem_set_inode_flags(inode, info->fsflags); inode->i_ctime = current_time(inode); return 0; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 07d3befc80e4..7327b2573f7c 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -703,14 +703,29 @@ ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, mmap_changing, 0); } +void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, + unsigned long start, unsigned long len, bool enable_wp) +{ + struct mmu_gather tlb; + pgprot_t newprot; + + if (enable_wp) + newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); + else + newprot = vm_get_page_prot(dst_vma->vm_flags); + + tlb_gather_mmu(&tlb, dst_mm); + change_protection(&tlb, dst_vma, start, start + len, newprot, + enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); + tlb_finish_mmu(&tlb); +} + int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; unsigned long page_mask; - struct mmu_gather tlb; - pgprot_t newprot; int err; /* @@ -750,15 +765,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, goto out_unlock; } - if (enable_wp) - newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); - else - newprot = vm_get_page_prot(dst_vma->vm_flags); - - tlb_gather_mmu(&tlb, dst_mm); - change_protection(&tlb, dst_vma, start, start + len, newprot, - enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); - tlb_finish_mmu(&tlb); + uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); err = 0; out_unlock: diff --git a/mm/vmstat.c b/mm/vmstat.c index 373d2730fcf2..90af9a8572f5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1168,8 +1168,15 @@ int fragmentation_index(struct zone *zone, unsigned int order) #define TEXT_FOR_HIGHMEM(xx) #endif +#ifdef CONFIG_ZONE_DEVICE +#define TEXT_FOR_DEVICE(xx) xx "_device", +#else +#define TEXT_FOR_DEVICE(xx) +#endif + #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ - TEXT_FOR_HIGHMEM(xx) xx "_movable", + TEXT_FOR_HIGHMEM(xx) xx "_movable", \ + TEXT_FOR_DEVICE(xx) const char * const vmstat_text[] = { /* enum zone_stat_item counters */ |