diff options
Diffstat (limited to 'fs/proc/task_mmu.c')
-rw-r--r-- | fs/proc/task_mmu.c | 114 |
1 files changed, 76 insertions, 38 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ef2eb12906da..102f48668c35 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) const char *name = NULL; if (file) { - struct inode *inode = file_inode(vma->vm_file); + const struct inode *inode = file_user_inode(vma->vm_file); + dev = inode->i_sb->s_dev; ino = inode->i_ino; pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; @@ -865,7 +866,8 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %8u\n", - hugepage_vma_check(vma, vma->vm_flags, true, false, true)); + !!thp_vma_allowable_orders(vma, vma->vm_flags, true, false, + true, THP_ORDERS_ALL)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -1350,8 +1352,7 @@ static inline pagemap_entry_t make_pme(u64 frame, u64 flags) return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags }; } -static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, - struct pagemapread *pm) +static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm) { pm->buffer[pm->pos++] = *pme; if (pm->pos >= pm->len) @@ -1378,7 +1379,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, hole_end = end; for (; addr < hole_end; addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) goto out; } @@ -1390,7 +1391,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, if (vma->vm_flags & VM_SOFTDIRTY) pme = make_pme(0, PM_SOFT_DIRTY); for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) goto out; } @@ -1517,7 +1518,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, for (; addr != end; addr += PAGE_SIZE) { pagemap_entry_t pme = make_pme(frame, flags); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) break; if (pm->show_pfn) { @@ -1545,7 +1546,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, pagemap_entry_t pme; pme = pte_to_pagemap_entry(pm, vma, addr, ptep_get(pte)); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) break; } @@ -1595,7 +1596,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, for (; addr != end; addr += PAGE_SIZE) { pagemap_entry_t pme = make_pme(frame, flags); - err = add_to_pagemap(addr, &pme, pm); + err = add_to_pagemap(&pme, pm); if (err) return err; if (pm->show_pfn && (flags & PM_PRESENT)) @@ -1761,7 +1762,7 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -1793,6 +1794,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { swp_entry_t swp; @@ -1803,24 +1806,24 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, if (p->masks_of_interest & PAGE_IS_FILE) { swp = pte_to_swp_entry(pte); if (is_pfn_swap_entry(swp) && - !PageAnon(pfn_swap_entry_to_page(swp))) + !folio_test_anon(pfn_swap_entry_folio(swp))) categories |= PAGE_IS_FILE; } + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; } static void make_uffd_wp_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t *pte) + unsigned long addr, pte_t *pte, pte_t ptent) { - pte_t ptent = ptep_get(pte); - if (pte_present(ptent)) { pte_t old_pte; old_pte = ptep_modify_prot_start(vma, addr, pte); - ptent = pte_mkuffd_wp(ptent); + ptent = pte_mkuffd_wp(old_pte); ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_mkuffd_wp(ptent); @@ -1853,17 +1856,21 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, if (is_zero_pfn(pmd_pfn(pmd))) categories |= PAGE_IS_PFNZERO; + if (pmd_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pmd(pmd)) { swp_entry_t swp; categories |= PAGE_IS_SWAPPED; if (!pmd_swp_uffd_wp(pmd)) categories |= PAGE_IS_WRITTEN; + if (pmd_swp_soft_dirty(pmd)) + categories |= PAGE_IS_SOFT_DIRTY; if (p->masks_of_interest & PAGE_IS_FILE) { swp = pmd_to_swp_entry(pmd); if (is_pfn_swap_entry(swp) && - !PageAnon(pfn_swap_entry_to_page(swp))) + !folio_test_anon(pfn_swap_entry_folio(swp))) categories |= PAGE_IS_FILE; } } @@ -1905,10 +1912,14 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) categories |= PAGE_IS_FILE; if (is_zero_pfn(pte_pfn(pte))) categories |= PAGE_IS_PFNZERO; + if (pte_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } else if (is_swap_pte(pte)) { categories |= PAGE_IS_SWAPPED; if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; + if (pte_swp_soft_dirty(pte)) + categories |= PAGE_IS_SOFT_DIRTY; } return categories; @@ -1982,15 +1993,34 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end, struct pagemap_scan_private *p = walk->private; struct vm_area_struct *vma = walk->vma; unsigned long vma_category = 0; + bool wp_allowed = userfaultfd_wp_async(vma) && + userfaultfd_wp_use_markers(vma); - if (userfaultfd_wp_async(vma) && userfaultfd_wp_use_markers(vma)) - vma_category |= PAGE_IS_WPALLOWED; - else if (p->arg.flags & PM_SCAN_CHECK_WPASYNC) - return -EPERM; + if (!wp_allowed) { + /* User requested explicit failure over wp-async capability */ + if (p->arg.flags & PM_SCAN_CHECK_WPASYNC) + return -EPERM; + /* + * User requires wr-protect, and allows silently skipping + * unsupported vmas. + */ + if (p->arg.flags & PM_SCAN_WP_MATCHING) + return 1; + /* + * Then the request doesn't involve wr-protects at all, + * fall through to the rest checks, and allow vma walk. + */ + } if (vma->vm_flags & VM_PFNMAP) return 1; + if (wp_allowed) + vma_category |= PAGE_IS_WPALLOWED; + + if (vma->vm_flags & VM_SOFTDIRTY) + vma_category |= PAGE_IS_SOFT_DIRTY; + if (!pagemap_scan_is_interesting_vma(vma_category, p)) return 1; @@ -2140,12 +2170,15 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, return 0; } - if (!p->vec_out) { + if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) { /* Fast path for performing exclusive WP */ for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { - if (pte_uffd_wp(ptep_get(pte))) + pte_t ptent = ptep_get(pte); + + if ((pte_present(ptent) && pte_uffd_wp(ptent)) || + pte_swp_uffd_wp_any(ptent)) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = addr + PAGE_SIZE; @@ -2158,8 +2191,10 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, p->arg.return_mask == PAGE_IS_WRITTEN) { for (addr = start; addr < end; pte++, addr += PAGE_SIZE) { unsigned long next = addr + PAGE_SIZE; + pte_t ptent = ptep_get(pte); - if (pte_uffd_wp(ptep_get(pte))) + if ((pte_present(ptent) && pte_uffd_wp(ptent)) || + pte_swp_uffd_wp_any(ptent)) continue; ret = pagemap_scan_output(p->cur_vma_category | PAGE_IS_WRITTEN, p, addr, &next); @@ -2167,7 +2202,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, break; if (~p->arg.flags & PM_SCAN_WP_MATCHING) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = next; @@ -2176,8 +2211,9 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, } for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { + pte_t ptent = ptep_get(pte); unsigned long categories = p->cur_vma_category | - pagemap_page_category(p, vma, addr, ptep_get(pte)); + pagemap_page_category(p, vma, addr, ptent); unsigned long next = addr + PAGE_SIZE; if (!pagemap_scan_is_interesting_page(categories, p)) @@ -2192,7 +2228,7 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, if (~categories & PAGE_IS_WRITTEN) continue; - make_uffd_wp_pte(vma, addr, pte); + make_uffd_wp_pte(vma, addr, pte, ptent); if (!flush_end) start = addr; flush_end = next; @@ -2399,7 +2435,6 @@ static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p) static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) { - struct mmu_notifier_range range; struct pagemap_scan_private p = {0}; unsigned long walk_start; size_t n_ranges_out = 0; @@ -2415,15 +2450,9 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) if (ret) return ret; - /* Protection change for the range is going to happen. */ - if (p.arg.flags & PM_SCAN_WP_MATCHING) { - mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, - mm, p.arg.start, p.arg.end); - mmu_notifier_invalidate_range_start(&range); - } - for (walk_start = p.arg.start; walk_start < p.arg.end; walk_start = p.arg.walk_end) { + struct mmu_notifier_range range; long n_out; if (fatal_signal_pending(current)) { @@ -2434,8 +2463,20 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) ret = mmap_read_lock_killable(mm); if (ret) break; + + /* Protection change for the range is going to happen. */ + if (p.arg.flags & PM_SCAN_WP_MATCHING) { + mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, + mm, walk_start, p.arg.end); + mmu_notifier_invalidate_range_start(&range); + } + ret = walk_page_range(mm, walk_start, p.arg.end, &pagemap_scan_ops, &p); + + if (p.arg.flags & PM_SCAN_WP_MATCHING) + mmu_notifier_invalidate_range_end(&range); + mmap_read_unlock(mm); n_out = pagemap_scan_flush_buffer(&p); @@ -2461,9 +2502,6 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg) if (pagemap_scan_writeback_args(&p.arg, uarg)) ret = -EFAULT; - if (p.arg.flags & PM_SCAN_WP_MATCHING) - mmu_notifier_invalidate_range_end(&range); - kfree(p.vec_buf); return ret; } |