diff options
Diffstat (limited to 'fs/proc')
| -rw-r--r-- | fs/proc/generic.c | 9 | ||||
| -rw-r--r-- | fs/proc/page.c | 2 | ||||
| -rw-r--r-- | fs/proc/task_mmu.c | 74 |
3 files changed, 72 insertions, 13 deletions
diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8bb81e58c9d8..32b6b0f97967 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -112,6 +112,8 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); rb_insert_color(&de->subdir_node, root); + if (S_ISDIR(de->mode)) + dir->nlink++; return true; } @@ -404,7 +406,6 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, write_unlock(&proc_subdir_lock); goto out_free_inum; } - dir->nlink++; write_unlock(&proc_subdir_lock); return dp; @@ -702,6 +703,8 @@ static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) { rb_erase(&pde->subdir_node, &parent->subdir); RB_CLEAR_NODE(&pde->subdir_node); + if (S_ISDIR(pde->mode)) + parent->nlink--; } /* @@ -727,8 +730,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = NULL; } else { pde_erase(de, parent); - if (S_ISDIR(de->mode)) - parent->nlink--; } } write_unlock(&proc_subdir_lock); @@ -787,8 +788,6 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) continue; } next = de->parent; - if (S_ISDIR(de->mode)) - next->nlink--; write_unlock(&proc_subdir_lock); proc_entry_rundown(de); diff --git a/fs/proc/page.c b/fs/proc/page.c index f9b2c2c906cd..7d9387143435 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -173,7 +173,7 @@ u64 stable_page_flags(const struct page *page) u |= 1 << KPF_MMAP; if (is_anon) { u |= 1 << KPF_ANON; - if (mapping & FOLIO_MAPPING_KSM) + if ((mapping & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_KSM) u |= 1 << KPF_KSM; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 751b9ba160fb..29f4bdf6e4ab 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2042,7 +2042,6 @@ static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr, flags |= PM_SOFT_DIRTY; if (pmd_swp_uffd_wp(pmd)) flags |= PM_UFFD_WP; - VM_WARN_ON_ONCE(!pmd_is_migration_entry(pmd)); page = softleaf_to_page(entry); } @@ -2523,12 +2522,16 @@ static void make_uffd_wp_huge_pte(struct vm_area_struct *vma, if (softleaf_is_hwpoison(entry) || softleaf_is_marker(entry)) return; - if (softleaf_is_migration(entry)) + if (softleaf_is_migration(entry)) { set_huge_pte_at(vma->vm_mm, addr, ptep, pte_swp_mkuffd_wp(ptent), psize); - else - huge_ptep_modify_prot_commit(vma, addr, ptep, ptent, - huge_pte_mkuffd_wp(ptent)); + } else { + pte_t old_pte, new_pte; + + old_pte = huge_ptep_modify_prot_start(vma, addr, ptep); + new_pte = huge_pte_mkuffd_wp(old_pte); + huge_ptep_modify_prot_commit(vma, addr, ptep, old_pte, new_pte); + } } #endif /* CONFIG_HUGETLB_PAGE */ @@ -2869,7 +2872,7 @@ static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask, if (~categories & PAGE_IS_WRITTEN) goto out_unlock; - if (end != start + HPAGE_SIZE) { + if (end != start + huge_page_size(hstate_vma(vma))) { /* Partial HugeTLB page WP isn't possible. */ pagemap_scan_backout_range(p, start, end); p->arg.walk_end = start; @@ -2886,8 +2889,62 @@ out_unlock: return ret; } + +/* + * Write-protect the unpopulated hugetlb entries covering [addr, end) by + * installing uffd-wp markers inline, exactly as pagemap_scan_hugetlb_entry() + * does for populated entries. + * + * walk_hugetlb_range() currently calls ->pte_hole() once per huge page, so the + * loop normally runs a single iteration; it is written to cover the full range + * in case the walker ever coalesces adjacent holes. + * + * The obvious route -- uffd_wp_range() -> hugetlb_change_protection() -- + * cannot be used here: it takes hugetlb_vma_lock_write(), but the page-table + * walker (walk_hugetlb_range()) already holds hugetlb_vma_lock_read() on the + * same VMA, so the scanning thread would deadlock against itself. PMD sharing + * is disabled on uffd-wp VMAs (hugetlb_unshare_all_pmds() at registration), so + * the vma lock guards nothing that matters for these entries anyway. + */ +static int pagemap_scan_hugetlb_hole_wp(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct hstate *h = hstate_vma(vma); + unsigned long psize = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pte_t *ptep; + pte_t pte; + + for (addr = ALIGN_DOWN(addr, psize); addr < end; addr += psize) { + ptep = huge_pte_alloc(mm, vma, addr, psize); + if (!ptep) + return -ENOMEM; + + i_mmap_lock_write(vma->vm_file->f_mapping); + ptl = huge_pte_lock(h, mm, ptep); + pte = huge_ptep_get(mm, addr, ptep); + make_uffd_wp_huge_pte(vma, addr, ptep, pte); + /* + * A none entry has no cached translation, so installing the + * marker needs no TLB flush. Flush only if a fault populated + * the entry between huge_pte_alloc() and the page table lock. + */ + if (!huge_pte_none(pte)) + flush_hugetlb_tlb_range(vma, addr, addr + psize); + spin_unlock(ptl); + i_mmap_unlock_write(vma->vm_file->f_mapping); + } + + return 0; +} #else #define pagemap_scan_hugetlb_entry NULL +static int pagemap_scan_hugetlb_hole_wp(struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + return 0; +} #endif static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end, @@ -2907,7 +2964,10 @@ static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end, if (~p->arg.flags & PM_SCAN_WP_MATCHING) return ret; - err = uffd_wp_range(vma, addr, end - addr, true); + if (is_vm_hugetlb_page(vma)) + err = pagemap_scan_hugetlb_hole_wp(vma, addr, end); + else + err = uffd_wp_range(vma, addr, end - addr, true); if (err < 0) ret = err; |