diff options
Diffstat (limited to 'fs')
45 files changed, 422 insertions, 303 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3abc447783aa..f23fd86697ea 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -161,7 +161,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if ((fl->fl_flags & FL_POSIX) != FL_POSIX) BUG(); - res = posix_lock_file_wait(filp, fl); + res = locks_lock_file_wait(filp, fl); if (res < 0) goto out; @@ -231,7 +231,7 @@ out_unlock: if (res < 0 && fl->fl_type != F_UNLCK) { fl_type = fl->fl_type; fl->fl_type = F_UNLCK; - res = posix_lock_file_wait(filp, fl); + res = locks_lock_file_wait(filp, fl); fl->fl_type = fl_type; } out: diff --git a/fs/block_dev.c b/fs/block_dev.c index 073bb57adab1..0a793c7930eb 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1075,7 +1075,7 @@ int revalidate_disk(struct gendisk *disk) if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - + blk_integrity_revalidate(disk); bdev = bdget_disk(disk, 0); if (!bdev) return ret; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index ecbc63d3143e..9a2ec79e8cfb 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1828,7 +1828,6 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, int found = 0; struct extent_buffer *eb; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; u32 item_size; u32 cur_offset; unsigned long ptr; @@ -1856,9 +1855,8 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, slot); - ptr = btrfs_item_ptr_offset(leaf, slot); + item_size = btrfs_item_size_nr(eb, slot); + ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { @@ -1872,7 +1870,7 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root, if (ret) break; - cur_offset += btrfs_inode_extref_name_len(leaf, extref); + cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } btrfs_tree_read_unlock_blocking(eb); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 295795aebe0b..1e60d00d4ea7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2847,6 +2847,8 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + if (!IS_ERR(chunk_root->node)) + free_extent_buffer(chunk_root->node); chunk_root->node = NULL; goto fail_tree_roots; } @@ -2885,6 +2887,8 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); + if (!IS_ERR(tree_root->node)) + free_extent_buffer(tree_root->node); tree_root->node = NULL; goto recovery_tree_root; } diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 8d052209f473..2513a7f53334 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -112,11 +112,11 @@ static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { - if (fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) + if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else @@ -136,11 +136,11 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || - fh_len != BTRFS_FID_SIZE_CONNECTABLE_ROOT) && + fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || - fh_len != BTRFS_FID_SIZE_NON_CONNECTABLE)) + fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 9f9604201333..601d7d45d164 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2828,6 +2828,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head; int ret; int run_all = count == (unsigned long)-1; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2844,6 +2845,7 @@ again: #ifdef SCRAMBLE_DELAYED_REFS delayed_refs->run_delayed_start = find_middle(&delayed_refs->root); #endif + trans->can_flush_pending_bgs = false; ret = __btrfs_run_delayed_refs(trans, root, count); if (ret < 0) { btrfs_abort_transaction(trans, root, ret); @@ -2893,6 +2895,7 @@ again: } out: assert_qgroups_uptodate(trans); + trans->can_flush_pending_bgs = can_flush_pending_bgs; return 0; } @@ -4306,7 +4309,8 @@ out: * the block groups that were made dirty during the lifetime of the * transaction. */ - if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + if (trans->can_flush_pending_bgs && + trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { btrfs_create_pending_block_groups(trans, trans->root); btrfs_trans_release_chunk_metadata(trans); } @@ -9560,7 +9564,9 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_block_group_item item; struct btrfs_key key; int ret = 0; + bool can_flush_pending_bgs = trans->can_flush_pending_bgs; + trans->can_flush_pending_bgs = false; list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { if (ret) goto next; @@ -9581,6 +9587,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, next: list_del_init(&block_group->bg_list); } + trans->can_flush_pending_bgs = can_flush_pending_bgs; } int btrfs_make_block_group(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index e2357e31609a..3915c9473e94 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3132,12 +3132,12 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { struct inode *inode; struct btrfs_ordered_extent *ordered; int index; - u64 prev_em_start = (u64)-1; inode = pages[0]->mapping->host; while (1) { @@ -3153,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree, for (index = 0; index < nr_pages; index++) { __do_readpage(tree, pages[index], get_extent, em_cached, bio, - mirror_num, bio_flags, rw, &prev_em_start); + mirror_num, bio_flags, rw, prev_em_start); page_cache_release(pages[index]); } } @@ -3163,7 +3163,8 @@ static void __extent_readpages(struct extent_io_tree *tree, int nr_pages, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int rw) + unsigned long *bio_flags, int rw, + u64 *prev_em_start) { u64 start = 0; u64 end = 0; @@ -3184,7 +3185,7 @@ static void __extent_readpages(struct extent_io_tree *tree, index - first_index, start, end, get_extent, em_cached, bio, mirror_num, bio_flags, - rw); + rw, prev_em_start); start = page_start; end = start + PAGE_CACHE_SIZE - 1; first_index = index; @@ -3195,7 +3196,8 @@ static void __extent_readpages(struct extent_io_tree *tree, __do_contiguous_readpages(tree, &pages[first_index], index - first_index, start, end, get_extent, em_cached, bio, - mirror_num, bio_flags, rw); + mirror_num, bio_flags, rw, + prev_em_start); } static int __extent_read_full_page(struct extent_io_tree *tree, @@ -4207,6 +4209,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *page; struct extent_map *em_cached = NULL; int nr = 0; + u64 prev_em_start = (u64)-1; for (page_idx = 0; page_idx < nr_pages; page_idx++) { page = list_entry(pages->prev, struct page, lru); @@ -4223,12 +4226,12 @@ int extent_readpages(struct extent_io_tree *tree, if (nr < ARRAY_SIZE(pagepool)) continue; __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); nr = 0; } if (nr) __extent_readpages(tree, pagepool, nr, get_extent, &em_cached, - &bio, 0, &bio_flags, READ); + &bio, 0, &bio_flags, READ, &prev_em_start); if (em_cached) free_extent_map(em_cached); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b823fac91c92..8c6f247ba81d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2584,7 +2584,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start); if (ret) goto out; - } else { + } else if (offset + len > inode->i_size) { /* * If we are fallocating from the end of the file onward we * need to zero out the end of the page if i_size lands in the diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0adf5422fce9..8d20f3b1cab0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4639,6 +4639,11 @@ locked: bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } + if (bctl->flags & ~(BTRFS_BALANCE_ARGS_MASK | BTRFS_BALANCE_TYPE_MASK)) { + ret = -EINVAL; + goto out_bctl; + } + do_balance: /* * Ownership of bctl and mutually_exclusive_operation_running @@ -4650,12 +4655,15 @@ do_balance: need_unlock = false; ret = btrfs_balance(bctl, bargs); + bctl = NULL; if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) ret = -EFAULT; } +out_bctl: + kfree(bctl); out_bargs: kfree(bargs); out_unlock: diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index aa72bfd28f7d..a739b825bdd3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1920,10 +1920,12 @@ static int did_overwrite_ref(struct send_ctx *sctx, /* * We know that it is or will be overwritten. Check this now. * The current inode being processed might have been the one that caused - * inode 'ino' to be orphanized, therefore ow_inode can actually be the - * same as sctx->send_progress. + * inode 'ino' to be orphanized, therefore check if ow_inode matches + * the current inode being processed. */ - if (ow_inode <= sctx->send_progress) + if ((ow_inode < sctx->send_progress) || + (ino != sctx->cur_ino && ow_inode == sctx->cur_ino && + gen == sctx->cur_inode_gen)) ret = 1; else ret = 0; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 74bc3338418b..a5b06442f0bf 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -557,6 +557,7 @@ again: h->delayed_ref_elem.seq = 0; h->type = type; h->allocating_chunk = false; + h->can_flush_pending_bgs = true; h->reloc_reserved = false; h->sync = false; INIT_LIST_HEAD(&h->qgroup_ref_list); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 87964bf8892d..a994bb097ee5 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -118,6 +118,7 @@ struct btrfs_trans_handle { short aborted; short adding_csums; bool allocating_chunk; + bool can_flush_pending_bgs; bool reloc_reserved; bool sync; unsigned int type; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2ca784a14e84..595279a8b99f 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -376,6 +376,14 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT) + /* * Profile changing flags. When SOFT is set we won't relocate chunk if * it already has the target profile (even though it may be diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 6706bde9ad1b..a2cb0c254060 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -228,12 +228,12 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, file, lock_cmd, wait, fl); if (!err) { - err = flock_lock_file_wait(file, fl); + err = locks_lock_file_wait(file, fl); if (err) { ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, file, CEPH_LOCK_UNLOCK, 0, fl); - dout("got %d on flock_lock_file_wait, undid lock", err); + dout("got %d on locks_lock_file_wait, undid lock", err); } } return err; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e2a6af1508af..47c5c97e2dd3 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1553,7 +1553,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, out: if (flock->fl_flags & FL_POSIX && !rc) - rc = posix_lock_file_wait(file, flock); + rc = locks_lock_file_wait(file, flock); return rc; } @@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, struct page *page, *tpage; unsigned int expected_index; int rc; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); INIT_LIST_HEAD(tmplist); @@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, */ __set_page_locked(page); rc = add_to_page_cache_locked(page, mapping, - page->index, GFP_KERNEL); + page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { @@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, break; __set_page_locked(page); - if (add_to_page_cache_locked(page, mapping, page->index, - GFP_KERNEL)) { + if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { __clear_page_locked(page); break; } @@ -285,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh, static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { + struct address_space *mapping = inode->i_mapping; sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; void __pmem *addr; @@ -292,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, pgoff_t size; int error; + i_mmap_lock_read(mapping); + /* * Check truncate didn't happen while we were allocating a block. * If it did, this block may or may not be still allocated to the @@ -321,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, error = vm_insert_mixed(vma, vaddr, pfn); out: + i_mmap_unlock_read(mapping); + return error; } @@ -382,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * from a read fault and we've raced with a truncate */ error = -EIO; - goto unlock; + goto unlock_page; } - } else { - i_mmap_lock_write(mapping); } error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) - goto unlock; + goto unlock_page; if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) { if (vmf->flags & FAULT_FLAG_WRITE) { @@ -403,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) - goto unlock; + goto unlock_page; } else { - i_mmap_unlock_write(mapping); return dax_load_hole(mapping, page, vmf); } } @@ -417,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, else clear_user_highpage(new_page, vaddr); if (error) - goto unlock; + goto unlock_page; vmf->page = page; if (!page) { + i_mmap_lock_read(mapping); /* Check we didn't race with truncate */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) { + i_mmap_unlock_read(mapping); error = -EIO; - goto unlock; + goto out; } } return VM_FAULT_LOCKED; @@ -461,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); } - if (!page) - i_mmap_unlock_write(mapping); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; @@ -471,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; - unlock: + unlock_page: if (page) { unlock_page(page); page_cache_release(page); - } else { - i_mmap_unlock_write(mapping); } - goto out; } EXPORT_SYMBOL(__dax_fault); @@ -556,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - i_mmap_lock_write(mapping); length = get_block(inode, block, &bh, write); if (length) return VM_FAULT_SIGBUS; + i_mmap_lock_read(mapping); /* * If the filesystem isn't willing to tell us the length of a hole, @@ -569,36 +568,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) goto fallback; - sector = bh.b_blocknr << (blkbits - 9); - - if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - - length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, - bh.b_size); - if (length < 0) { - result = VM_FAULT_SIGBUS; - goto out; - } - if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) - goto fallback; - - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); - wmb_pmem(); - count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); - result |= VM_FAULT_MAJOR; - } - /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (buffer_new(&bh)) { - i_mmap_unlock_write(mapping); + i_mmap_unlock_read(mapping); unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0); - i_mmap_lock_write(mapping); + i_mmap_lock_read(mapping); } /* @@ -635,6 +612,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, result = VM_FAULT_NOPAGE; spin_unlock(ptl); } else { + sector = bh.b_blocknr << (blkbits - 9); length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, bh.b_size); if (length < 0) { @@ -644,15 +622,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) goto fallback; + if (buffer_unwritten(&bh) || buffer_new(&bh)) { + int i; + for (i = 0; i < PTRS_PER_PMD; i++) + clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + wmb_pmem(); + count_vm_event(PGMAJFAULT); + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); + result |= VM_FAULT_MAJOR; + } + result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); } out: + i_mmap_unlock_read(mapping); + if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); - i_mmap_unlock_write(mapping); - return result; fallback: diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 6c55ade071c3..d2ba12e23ed9 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -42,6 +42,22 @@ const struct file_operations debugfs_file_operations = { .llseek = noop_llseek, }; +static struct dentry *debugfs_create_mode(const char *name, umode_t mode, + struct dentry *parent, void *value, + const struct file_operations *fops, + const struct file_operations *fops_ro, + const struct file_operations *fops_wo) +{ + /* if there are no write bits set, make read only */ + if (!(mode & S_IWUGO)) + return debugfs_create_file(name, mode, parent, value, fops_ro); + /* if there are no read bits set, make write only */ + if (!(mode & S_IRUGO)) + return debugfs_create_file(name, mode, parent, value, fops_wo); + + return debugfs_create_file(name, mode, parent, value, fops); +} + static int debugfs_u8_set(void *data, u64 val) { *(u8 *)data = val; @@ -83,14 +99,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); struct dentry *debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u8_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u8_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u8); + return debugfs_create_mode(name, mode, parent, value, &fops_u8, + &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); @@ -135,14 +145,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u16_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u16_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u16); + return debugfs_create_mode(name, mode, parent, value, &fops_u16, + &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); @@ -187,14 +191,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u32_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u32_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u32); + return debugfs_create_mode(name, mode, parent, value, &fops_u32, + &fops_u32_ro, &fops_u32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u32); @@ -240,17 +238,59 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); struct dentry *debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u64_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_u64_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_u64); + return debugfs_create_mode(name, mode, parent, value, &fops_u64, + &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); +static int debugfs_ulong_set(void *data, u64 val) +{ + *(unsigned long *)data = val; + return 0; +} + +static int debugfs_ulong_get(void *data, u64 *val) +{ + *val = *(unsigned long *)data; + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); + +/** + * debugfs_create_ulong - create a debugfs file that is used to read and write + * an unsigned long value. + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is %NULL, then the + * file will be created in the root of the debugfs filesystem. + * @value: a pointer to the variable that the file should read to and write + * from. + * + * This function creates a file in debugfs with the given name that + * contains the value of the variable @value. If the @mode variable is so + * set, it can be read from, and written to. + * + * This function will return a pointer to a dentry if it succeeds. This + * pointer must be passed to the debugfs_remove() function when the file is + * to be removed (no automatic cleanup happens if your module is unloaded, + * you are responsible here.) If an error occurs, %NULL will be returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. It is not wise to check for this value, but rather, check for + * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling + * code. + */ +struct dentry *debugfs_create_ulong(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value) +{ + return debugfs_create_mode(name, mode, parent, value, &fops_ulong, + &fops_ulong_ro, &fops_ulong_wo); +} +EXPORT_SYMBOL_GPL(debugfs_create_ulong); + DEFINE_SIMPLE_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n"); @@ -264,6 +304,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n"); DEFINE_SIMPLE_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); /* * debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value @@ -286,14 +328,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x8_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x8_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x8); + return debugfs_create_mode(name, mode, parent, value, &fops_x8, + &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); @@ -310,14 +346,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x8); struct dentry *debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x16_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x16_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x16); + return debugfs_create_mode(name, mode, parent, value, &fops_x16, + &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); @@ -334,14 +364,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x16); struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x32_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, &fops_x32_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_x32); + return debugfs_create_mode(name, mode, parent, value, &fops_x32, + &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); @@ -358,7 +382,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_x32); struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { - return debugfs_create_file(name, mode, parent, value, &fops_x64); + return debugfs_create_mode(name, mode, parent, value, &fops_x64, + &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); @@ -375,6 +400,8 @@ static int debugfs_size_t_get(void *data, u64 *val) } DEFINE_SIMPLE_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, "%llu\n"); /* %llu and %zu are more or less the same */ +DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n"); +DEFINE_SIMPLE_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); /** * debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value @@ -389,7 +416,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { - return debugfs_create_file(name, mode, parent, value, &fops_size_t); + return debugfs_create_mode(name, mode, parent, value, &fops_size_t, + &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); @@ -422,16 +450,8 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) { - /* if there are no write bits set, make read only */ - if (!(mode & S_IWUGO)) - return debugfs_create_file(name, mode, parent, value, - &fops_atomic_t_ro); - /* if there are no read bits set, make write only */ - if (!(mode & S_IRUGO)) - return debugfs_create_file(name, mode, parent, value, - &fops_atomic_t_wo); - - return debugfs_create_file(name, mode, parent, value, &fops_atomic_t); + return debugfs_create_mode(name, mode, parent, value, &fops_atomic_t, + &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); @@ -439,7 +459,7 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[3]; - u32 *val = file->private_data; + bool *val = file->private_data; if (*val) buf[0] = 'Y'; @@ -457,7 +477,7 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, char buf[32]; size_t buf_size; bool bv; - u32 *val = file->private_data; + bool *val = file->private_data; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) @@ -478,6 +498,18 @@ static const struct file_operations fops_bool = { .llseek = default_llseek, }; +static const struct file_operations fops_bool_ro = { + .read = debugfs_read_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + +static const struct file_operations fops_bool_wo = { + .write = debugfs_write_file_bool, + .open = simple_open, + .llseek = default_llseek, +}; + /** * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. @@ -503,9 +535,10 @@ static const struct file_operations fops_bool = { * code. */ struct dentry *debugfs_create_bool(const char *name, umode_t mode, - struct dentry *parent, u32 *value) + struct dentry *parent, bool *value) { - return debugfs_create_file(name, mode, parent, value, &fops_bool); + return debugfs_create_mode(name, mode, parent, value, &fops_bool, + &fops_bool_ro, &fops_bool_wo); } EXPORT_SYMBOL_GPL(debugfs_create_bool); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index c711be8d6a3c..5d8f35f1382a 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -533,7 +533,8 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) /** * debugfs_remove - removes a file or directory from the debugfs filesystem * @dentry: a pointer to a the dentry of the file or directory to be - * removed. + * removed. If this parameter is NULL or an error value, nothing + * will be done. * * This function removes a file or directory in debugfs that was previously * created with a call to another debugfs function (like @@ -565,7 +566,8 @@ EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_remove_recursive - recursively removes a directory - * @dentry: a pointer to a the dentry of the directory to be removed. + * @dentry: a pointer to a the dentry of the directory to be removed. If this + * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function diff --git a/fs/direct-io.c b/fs/direct-io.c index 11256291642e..3ae0e0427191 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -120,6 +120,7 @@ struct dio { int page_errors; /* errno from get_user_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ + bool should_dirty; /* if pages should be dirtied */ int io_error; /* IO error in completion path */ unsigned long refcount; /* direct_io_worker() and bios */ struct bio *bio_list; /* singly linked via bi_private */ @@ -393,7 +394,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) dio->refcount++; spin_unlock_irqrestore(&dio->bio_lock, flags); - if (dio->is_async && dio->rw == READ) + if (dio->is_async && dio->rw == READ && dio->should_dirty) bio_set_pages_dirty(bio); if (sdio->submit_io) @@ -464,14 +465,15 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) if (bio->bi_error) dio->io_error = -EIO; - if (dio->is_async && dio->rw == READ) { + if (dio->is_async && dio->rw == READ && dio->should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (dio->rw == READ && !PageCompound(page)) + if (dio->rw == READ && !PageCompound(page) && + dio->should_dirty) set_page_dirty_lock(page); page_cache_release(page); } @@ -1219,6 +1221,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; + dio->should_dirty = (iter->type == ITER_IOVEC); sdio.iter = iter; sdio.final_block_in_request = (offset + iov_iter_count(iter)) >> blkbits; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 5532f097f6da..d401425f602a 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -145,7 +145,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, send_op(op); if (xop->callback == NULL) { - rv = wait_event_killable(recv_wq, (op->done != 0)); + rv = wait_event_interruptible(recv_wq, (op->done != 0)); if (rv == -ERESTARTSYS) { log_debug(ls, "dlm_posix_lock: wait killed %llx", (unsigned long long)number); @@ -172,7 +172,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = op->info.rv; if (!rv) { - if (posix_lock_file_wait(file, fl) < 0) + if (locks_lock_file_wait(file, fl) < 0) log_error(ls, "dlm_posix_lock: vfs lock error %llx", (unsigned long long)number); } @@ -262,7 +262,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, /* cause the vfs unlock to return ENOENT if lock is not found */ fl->fl_flags |= FL_EXISTS; - rv = posix_lock_file_wait(file, fl); + rv = locks_lock_file_wait(file, fl); if (rv == -ENOENT) { rv = 0; goto out_free; diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 47728da7702c..b46e9fc64196 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -63,7 +63,7 @@ config EXT4_FS If unsure, say N. config EXT4_USE_FOR_EXT2 - bool "Use ext4 for ext2/ext3 file systems" + bool "Use ext4 for ext2 file systems" depends on EXT4_FS depends on EXT2_FS=n default y diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index e26803fb210d..560af0437704 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping, if (pages) { page = list_entry(pages->prev, struct page, lru); list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) + if (add_to_page_cache_lru(page, mapping, page->index, + GFP_KERNEL & mapping_gfp_mask(mapping))) goto next_page; } diff --git a/fs/file.c b/fs/file.c index 6c672ad329e9..c6986dce0334 100644 --- a/fs/file.c +++ b/fs/file.c @@ -56,6 +56,9 @@ static void free_fdtable_rcu(struct rcu_head *rcu) __free_fdtable(container_of(rcu, struct fdtable, rcu)); } +#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) +#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) + /* * Expand the fdset in the files_struct. Called with the files spinlock * held for write. @@ -77,6 +80,11 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memset((char *)(nfdt->open_fds) + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)(nfdt->close_on_exec) + cpy, 0, set); + + cpy = BITBIT_SIZE(ofdt->max_fds); + set = BITBIT_SIZE(nfdt->max_fds) - cpy; + memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); + memset(cpy+(char *)nfdt->full_fds_bits, 0, set); } static struct fdtable * alloc_fdtable(unsigned int nr) @@ -115,12 +123,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr) fdt->fd = data; data = alloc_fdmem(max_t(size_t, - 2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES)); + 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES)); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; + data += nr / BITS_PER_BYTE; + fdt->full_fds_bits = data; return fdt; @@ -226,17 +236,22 @@ static inline void __set_close_on_exec(int fd, struct fdtable *fdt) static inline void __clear_close_on_exec(int fd, struct fdtable *fdt) { - __clear_bit(fd, fdt->close_on_exec); + if (test_bit(fd, fdt->close_on_exec)) + __clear_bit(fd, fdt->close_on_exec); } -static inline void __set_open_fd(int fd, struct fdtable *fdt) +static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); + fd /= BITS_PER_LONG; + if (!~fdt->open_fds[fd]) + __set_bit(fd, fdt->full_fds_bits); } -static inline void __clear_open_fd(int fd, struct fdtable *fdt) +static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); + __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static int count_open_files(struct fdtable *fdt) @@ -280,6 +295,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; + new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); @@ -323,6 +339,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8); memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8); + memcpy(new_fdt->full_fds_bits, old_fdt->full_fds_bits, BITBIT_SIZE(open_files)); for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; @@ -454,10 +471,25 @@ struct files_struct init_files = { .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, + .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), }; +static unsigned long find_next_fd(struct fdtable *fdt, unsigned long start) +{ + unsigned long maxfd = fdt->max_fds; + unsigned long maxbit = maxfd / BITS_PER_LONG; + unsigned long bitbit = start / BITS_PER_LONG; + + bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; + if (bitbit > maxfd) + return maxfd; + if (bitbit > start) + start = bitbit; + return find_next_zero_bit(fdt->open_fds, maxfd, start); +} + /* * allocate a file descriptor, mark it busy. */ @@ -476,7 +508,7 @@ repeat: fd = files->next_fd; if (fd < fdt->max_fds) - fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd); + fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 091a36444972..7378169e90be 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -778,19 +778,24 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { - int next_memcg_id = 0; - struct bdi_writeback *wb; - struct wb_iter iter; + struct bdi_writeback *last_wb = NULL; + struct bdi_writeback *wb = list_entry(&bdi->wb_list, + struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); - bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) { + list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; + if (last_wb) { + wb_put(last_wb); + last_wb = NULL; + } + /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || @@ -819,12 +824,22 @@ restart: wb_queue_work(wb, work); - next_memcg_id = wb->memcg_css->id + 1; + /* + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + wb_get(wb); + last_wb = wb; + rcu_read_unlock(); wb_wait_for_completion(bdi, &fallback_work_done); goto restart; } rcu_read_unlock(); + + if (last_wb) + wb_put(last_wb); } #else /* CONFIG_CGROUP_WRITEBACK */ @@ -1857,12 +1872,11 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; if (!bdi_has_dirty_io(bdi)) continue; - bdi_for_each_wb(wb, bdi, &iter, 0) + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages), false, reason); } @@ -1894,11 +1908,10 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; - struct wb_iter iter; - bdi_for_each_wb(wb, bdi, &iter, 0) - if (!list_empty(&bdi->wb.b_dirty_time)) - wb_wakeup(&bdi->wb); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + if (!list_empty(&wb->b_dirty_time)) + wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f523f2f04c19..e0faf8f2c868 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2189,7 +2189,7 @@ static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl) int err; if (fc->no_flock) { - err = flock_lock_file_wait(file, fl); + err = locks_lock_file_wait(file, fl); } else { struct fuse_file *ff = file->private_data; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index cf4ab89159f4..9287a2d17b8c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1000,7 +1000,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) } if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { if (fl->fl_type == F_UNLCK) - posix_lock_file_wait(file, fl); + locks_lock_file_wait(file, fl); return -EIO; } if (IS_GETLK(cmd)) @@ -1031,7 +1031,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (gl) { if (fl_gh->gh_state == state) goto out; - flock_lock_file_wait(file, + locks_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); @@ -1056,7 +1056,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (error == GLR_TRYFAILED) error = -EAGAIN; } else { - error = flock_lock_file_wait(file, fl); + error = locks_lock_file_wait(file, fl); gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error); } @@ -1071,7 +1071,7 @@ static void do_unflock(struct file *file, struct file_lock *fl) struct gfs2_holder *fl_gh = &fp->f_fl_gh; mutex_lock(&fp->f_fl_mutex); - flock_lock_file_wait(file, fl); + locks_lock_file_wait(file, fl); if (fl_gh->gh_gl) { gfs2_glock_dq(fl_gh); gfs2_holder_uninit(fl_gh); diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index acd394716349..112952037933 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -474,18 +474,7 @@ static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *ho static int do_vfs_lock(struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_file_wait(fl->fl_file, fl); - break; - case FL_FLOCK: - res = flock_lock_file_wait(fl->fl_file, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_file_wait(fl->fl_file, fl); } /* diff --git a/fs/locks.c b/fs/locks.c index 2a54c800a223..0d2b3267e2a3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -205,28 +205,32 @@ static struct kmem_cache *filelock_cache __read_mostly; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { - struct file_lock_context *new; + struct file_lock_context *ctx; - if (likely(inode->i_flctx) || type == F_UNLCK) + /* paired with cmpxchg() below */ + ctx = smp_load_acquire(&inode->i_flctx); + if (likely(ctx) || type == F_UNLCK) goto out; - new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); - if (!new) + ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!ctx) goto out; - spin_lock_init(&new->flc_lock); - INIT_LIST_HEAD(&new->flc_flock); - INIT_LIST_HEAD(&new->flc_posix); - INIT_LIST_HEAD(&new->flc_lease); + spin_lock_init(&ctx->flc_lock); + INIT_LIST_HEAD(&ctx->flc_flock); + INIT_LIST_HEAD(&ctx->flc_posix); + INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ - if (cmpxchg(&inode->i_flctx, NULL, new)) - kmem_cache_free(flctx_cache, new); + if (cmpxchg(&inode->i_flctx, NULL, ctx)) { + kmem_cache_free(flctx_cache, ctx); + ctx = smp_load_acquire(&inode->i_flctx); + } out: - return inode->i_flctx; + return ctx; } void @@ -762,7 +766,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) struct file_lock_context *ctx; struct inode *inode = file_inode(filp); - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; @@ -1167,10 +1171,9 @@ EXPORT_SYMBOL(posix_lock_file); * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * - * Variant of posix_lock_file_wait that does not take a filp, and so can be - * used after the filp has already been torn down. + * Apply a POSIX style lock request to an inode. */ -int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) +static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); @@ -1187,7 +1190,6 @@ int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) } return error; } -EXPORT_SYMBOL(posix_lock_inode_wait); /** * locks_mandatory_locked - Check for an active lock @@ -1203,7 +1205,7 @@ int locks_mandatory_locked(struct file *file) struct file_lock_context *ctx; struct file_lock *fl; - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) return 0; @@ -1388,7 +1390,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; @@ -1400,6 +1402,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) { WARN_ON_ONCE(1); return error; @@ -1494,9 +1497,10 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; struct file_lock *fl; + ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); if (!list_empty(&ctx->flc_lease)) { @@ -1543,10 +1547,11 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); + ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); time_out_leases(file_inode(filp), &dispose); @@ -1711,11 +1716,11 @@ static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; - struct file_lock_context *ctx = inode->i_flctx; + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx; LIST_HEAD(dispose); + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -1751,8 +1756,7 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) @@ -1856,7 +1860,7 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) * * Apply a FLOCK style lock request to an inode. */ -int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) +static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); @@ -1873,7 +1877,30 @@ int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) } return error; } -EXPORT_SYMBOL(flock_lock_inode_wait); + +/** + * locks_lock_inode_wait - Apply a lock to an inode + * @inode: inode of the file to apply to + * @fl: The lock to be applied + * + * Apply a POSIX or FLOCK style lock request to an inode. + */ +int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) +{ + int res = 0; + switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { + case FL_POSIX: + res = posix_lock_inode_wait(inode, fl); + break; + case FL_FLOCK: + res = flock_lock_inode_wait(inode, fl); + break; + default: + BUG(); + } + return res; +} +EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. @@ -1931,7 +1958,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) (can_sleep) ? F_SETLKW : F_SETLK, lock); else - error = flock_lock_file_wait(f.file, lock); + error = locks_lock_file_wait(f.file, lock); out_free: locks_free_lock(lock); @@ -2107,7 +2134,7 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, return error; } -/* Ensure that fl->fl_filp has compatible f_mode for F_SETLK calls */ +/* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { @@ -2359,13 +2386,14 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { struct file_lock lock; - struct file_lock_context *ctx = file_inode(filp)->i_flctx; + struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ + ctx = smp_load_acquire(&file_inode(filp)->i_flctx); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2389,7 +2417,7 @@ EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void -locks_remove_flock(struct file *filp) +locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl = { .fl_owner = filp, @@ -2400,7 +2428,6 @@ locks_remove_flock(struct file *filp) .fl_end = OFFSET_MAX, }; struct inode *inode = file_inode(filp); - struct file_lock_context *flctx = inode->i_flctx; if (list_empty(&flctx->flc_flock)) return; @@ -2416,10 +2443,8 @@ locks_remove_flock(struct file *filp) /* The i_flctx must be valid when calling into here */ static void -locks_remove_lease(struct file *filp) +locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { - struct inode *inode = file_inode(filp); - struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; LIST_HEAD(dispose); @@ -2439,17 +2464,20 @@ locks_remove_lease(struct file *filp) */ void locks_remove_file(struct file *filp) { - if (!file_inode(filp)->i_flctx) + struct file_lock_context *ctx; + + ctx = smp_load_acquire(&file_inode(filp)->i_flctx); + if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ - locks_remove_flock(filp); + locks_remove_flock(filp, ctx); /* remove any leases */ - locks_remove_lease(filp); + locks_remove_lease(filp, ctx); } /** @@ -2616,7 +2644,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0; - ctx = inode->i_flctx; + ctx = smp_load_acquire(&inode->i_flctx); if (!ctx) return; diff --git a/fs/mpage.c b/fs/mpage.c index 778a4ddef77a..09abba7653aa 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) static struct bio * do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, sector_t *last_block_in_bio, struct buffer_head *map_bh, - unsigned long *first_logical_block, get_block_t get_block) + unsigned long *first_logical_block, get_block_t get_block, + gfp_t gfp) { struct inode *inode = page->mapping->host; const unsigned blkbits = inode->i_blkbits; @@ -277,8 +278,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, nr_pages, BIO_MAX_PAGES), - GFP_KERNEL); + min_t(int, nr_pages, BIO_MAX_PAGES), gfp); if (bio == NULL) goto confused; } @@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping); map_bh.b_state = 0; map_bh.b_size = 0; @@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages, prefetchw(&page->flags); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, - page->index, GFP_KERNEL)) { + page->index, + gfp)) { bio = do_mpage_readpage(bio, page, nr_pages - page_idx, &last_block_in_bio, &map_bh, &first_logical_block, - get_block); + get_block, gfp); } page_cache_release(page); } @@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block) sector_t last_block_in_bio = 0; struct buffer_head map_bh; unsigned long first_logical_block = 0; + gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping); map_bh.b_state = 0; map_bh.b_size = 0; bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio, - &map_bh, &first_logical_block, get_block); + &map_bh, &first_logical_block, get_block, gfp); if (bio) mpage_bio_submit(READ, bio); return 0; @@ -482,6 +485,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc, struct buffer_head map_bh; loff_t i_size = i_size_read(inode); int ret = 0; + int wr = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); @@ -590,7 +594,7 @@ page_is_mapped: * This page will go to BIO. Do we need to send this BIO off first? */ if (bio && mpd->last_block_in_bio != blocks[0] - 1) - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); alloc_new: if (bio == NULL) { @@ -617,7 +621,7 @@ alloc_new: wbc_account_io(wbc, page, PAGE_SIZE); length = first_unmapped << blkbits; if (bio_add_page(bio, page, length, 0) < length) { - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); goto alloc_new; } @@ -627,7 +631,7 @@ alloc_new: set_page_writeback(page); unlock_page(page); if (boundary || (first_unmapped != blocks_per_page)) { - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); if (boundary_block) { write_boundary_block(boundary_bdev, boundary_block, 1 << blkbits); @@ -639,7 +643,7 @@ alloc_new: confused: if (bio) - bio = mpage_bio_submit(WRITE, bio); + bio = mpage_bio_submit(wr, bio); if (mpd->use_writepage) { ret = mapping->a_ops->writepage(page, wbc); @@ -695,8 +699,11 @@ mpage_writepages(struct address_space *mapping, }; ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd); - if (mpd.bio) - mpage_bio_submit(WRITE, mpd.bio); + if (mpd.bio) { + int wr = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC : WRITE); + mpage_bio_submit(wr, mpd.bio); + } } blk_finish_plug(&plug); return ret; @@ -713,8 +720,11 @@ int mpage_writepage(struct page *page, get_block_t get_block, .use_writepage = 0, }; int ret = __mpage_writepage(page, wbc, &mpd); - if (mpd.bio) - mpage_bio_submit(WRITE, mpd.bio); + if (mpd.bio) { + int wr = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC : WRITE); + mpage_bio_submit(wr, mpd.bio); + } return ret; } EXPORT_SYMBOL(mpage_writepage); diff --git a/fs/namei.c b/fs/namei.c index 726d211db484..33e9495a3129 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1558,8 +1558,6 @@ static int lookup_fast(struct nameidata *nd, negative = d_is_negative(dentry); if (read_seqcount_retry(&dentry->d_seq, seq)) return -ECHILD; - if (negative) - return -ENOENT; /* * This sequence count validates that the parent had no @@ -1580,6 +1578,12 @@ static int lookup_fast(struct nameidata *nd, goto unlazy; } } + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (negative) + return -ENOENT; path->mnt = mnt; path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index c0f9b1ed12b9..37f639d50af5 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -738,18 +738,7 @@ out_noconflict: static int do_vfs_lock(struct file *file, struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_file_wait(file, fl); - break; - case FL_FLOCK: - res = flock_lock_file_wait(file, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_file_wait(file, fl); } static int diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5133bb18830e..0e5ff69455c7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5513,18 +5513,7 @@ static int nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock * static int do_vfs_lock(struct inode *inode, struct file_lock *fl) { - int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { - case FL_POSIX: - res = posix_lock_inode_wait(inode, fl); - break; - case FL_FLOCK: - res = flock_lock_inode_wait(inode, fl); - break; - default: - BUG(); - } - return res; + return locks_lock_inode_wait(inode, fl); } struct nfs4_unlockdata { diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index cdefaa331a07..c29d9421bd5e 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -56,14 +56,6 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; - /* - * We do not attempt to support I/O smaller than the fs block size, - * or not aligned to it. - */ - if (args->lg_minlength < block_size) { - dprintk("pnfsd: I/O too small\n"); - goto out_layoutunavailable; - } if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ee5aa4daaea0..ce38b4ccc9ab 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1658,12 +1658,13 @@ send_response: if (ret < 0) { mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; + spin_unlock(&res->spinlock); dlm_lockres_put(res); } else { dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); } - spin_unlock(&res->spinlock); } else { if (res) dlm_lockres_put(res); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 3d90ad7ff91f..58eaa5c0d387 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1723,8 +1723,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, } else { dispatched = 1; __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); } - spin_unlock(&res->spinlock); } else { /* put.. incase we are not the master */ spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 6b6d092b0998..652ece4a9d9e 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -66,7 +66,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, * level. */ - flock_lock_file_wait(file, + locks_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); ocfs2_file_unlock(file); @@ -81,7 +81,7 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, goto out; } - ret = flock_lock_file_wait(file, fl); + ret = locks_lock_file_wait(file, fl); if (ret) ocfs2_file_unlock(file); @@ -98,7 +98,7 @@ static int ocfs2_do_funlock(struct file *file, int cmd, struct file_lock *fl) mutex_lock(&fp->fp_mutex); ocfs2_file_unlock(file); - ret = flock_lock_file_wait(file, fl); + ret = locks_lock_file_wait(file, fl); mutex_unlock(&fp->fp_mutex); return ret; @@ -119,7 +119,7 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl) if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) || ocfs2_mount_local(osb)) - return flock_lock_file_wait(file, fl); + return locks_lock_file_wait(file, fl); if (fl->fl_type == F_UNLCK) return ocfs2_do_funlock(file, cmd, fl); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 84d693d37428..871fcb67be97 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -81,11 +81,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) if (len == 0) return 0; - old_file = ovl_path_open(old, O_RDONLY); + old_file = ovl_path_open(old, O_LARGEFILE | O_RDONLY); if (IS_ERR(old_file)) return PTR_ERR(old_file); - new_file = ovl_path_open(new, O_WRONLY); + new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY); if (IS_ERR(new_file)) { error = PTR_ERR(new_file); goto out_fput; @@ -267,7 +267,7 @@ out: out_cleanup: ovl_cleanup(wdir, newdentry); - goto out; + goto out2; } /* diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d9da5a4e9382..ec0c2a050043 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -363,6 +363,9 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags) ovl_path_upper(dentry, &realpath); } + if (realpath.dentry->d_flags & DCACHE_OP_SELECT_INODE) + return realpath.dentry->d_op->d_select_inode(realpath.dentry, file_flags); + return d_backing_inode(realpath.dentry); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 79073d68b475..e38ee0fed24a 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -544,6 +544,7 @@ static void ovl_put_super(struct super_block *sb) mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir); @@ -1048,6 +1049,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) oe->lowerstack[i].dentry = stack[i].dentry; oe->lowerstack[i].mnt = ufs->lower_mnt[i]; } + kfree(stack); root_dentry->d_fsdata = oe; diff --git a/fs/proc/array.c b/fs/proc/array.c index f60f0121e331..eed2050db9be 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -375,7 +375,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task, int whole) { - unsigned long vsize, eip, esp, wchan = ~0UL; + unsigned long vsize, eip, esp, wchan = 0; int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; @@ -507,7 +507,19 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL); seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL); - seq_put_decimal_ull(m, ' ', wchan); + + /* + * We used to output the absolute kernel address, but that's an + * information leak - so instead we show a 0/1 flag here, to signal + * to user-space whether there's a wchan field in /proc/PID/wchan. + * + * This works with older implementations of procps as well. + */ + if (wchan) + seq_puts(m, " 1"); + else + seq_puts(m, " 0"); + seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ll(m, ' ', task->exit_signal); diff --git a/fs/proc/base.c b/fs/proc/base.c index b25eee4cead5..29595af32866 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -430,13 +430,10 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, wchan = get_wchan(task); - if (lookup_symbol_name(wchan, symname) < 0) { - if (!ptrace_may_access(task, PTRACE_MODE_READ)) - return 0; - seq_printf(m, "%lu", wchan); - } else { + if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); - } + else + seq_putc(m, '0'); return 0; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index d3ebf2e61853..9155a5a0d3b9 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -27,7 +27,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; unsigned long committed; - struct vmalloc_info vmi; long cached; long available; unsigned long pagecache; @@ -49,8 +48,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) if (cached < 0) cached = 0; - get_vmalloc_info(&vmi); - for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) pages[lru] = global_page_state(NR_LRU_BASE + lru); @@ -191,8 +188,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(vm_commit_limit()), K(committed), (unsigned long)VMALLOC_TOTAL >> 10, - vmi.used >> 10, - vmi.largest_chunk >> 10 + 0ul, // used to be vmalloc 'used' + 0ul // used to be vmalloc 'largest_chunk' #ifdef CONFIG_MEMORY_FAILURE , atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10) #endif diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e2d46adb54b4..b029d426c558 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -754,7 +754,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, if (pte_present(ptent)) { ptent = pte_wrprotect(ptent); - ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); + ptent = pte_clear_soft_dirty(ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); } @@ -768,7 +768,7 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, pmd_t pmd = *pmdp; pmd = pmd_wrprotect(pmd); - pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); + pmd = pmd_clear_soft_dirty(pmd); if (vma->vm_flags & VM_SOFTDIRTY) vma->vm_flags &= ~VM_SOFTDIRTY; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a94924..a586467f6ff6 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) unsigned order; void *data; int ret; + gfp_t gfp = mapping_gfp_mask(inode->i_mapping); /* make various checks */ order = get_order(newsize); @@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* allocate enough contiguous pages to be able to satisfy the * request */ - pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order); + pages = alloc_pages(gfp, order); if (!pages) return -ENOMEM; @@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) struct page *page = pages + loop; ret = add_to_page_cache_lru(page, inode->i_mapping, loop, - GFP_KERNEL); + gfp); if (ret < 0) goto add_error; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 6c95628ea377..f35523d4fa3a 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,6 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; + size_t len; /* * If buf != of->prealloc_buf, we don't know how @@ -115,7 +116,8 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, */ if (pos || WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; - return ops->show(kobj, of->kn->priv, buf); + len = ops->show(kobj, of->kn->priv, buf); + return min(count, len); } /* kernfs write callback for regular sysfs files */ |