diff options
Diffstat (limited to 'fs')
44 files changed, 391 insertions, 129 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 77e9c4387c1d..a59c26cc3c7d 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -561,7 +561,7 @@ static ssize_t caches_show(struct kobject *kobj, spin_lock(&v9fs_sessionlist_lock); list_for_each_entry(v9ses, &v9fs_sessionlist, slist) { if (v9ses->cachetag) { - n = snprintf(buf, limit, "%s\n", v9ses->cachetag); + n = snprintf(buf + count, limit, "%s\n", v9ses->cachetag); if (n < 0) { count = n; break; @@ -597,13 +597,16 @@ static const struct attribute_group v9fs_attr_group = { static int __init v9fs_sysfs_init(void) { + int ret; + v9fs_kobj = kobject_create_and_add("9p", fs_kobj); if (!v9fs_kobj) return -ENOMEM; - if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) { + ret = sysfs_create_group(v9fs_kobj, &v9fs_attr_group); + if (ret) { kobject_put(v9fs_kobj); - return -ENOMEM; + return ret; } return 0; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a1566df45be9..144e44199930 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2167,6 +2167,14 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, wbc_account_cgroup_owner(wbc, folio, range_len); folio_unlock(folio); } + /* + * If the fs is already in error status, do not submit any writeback + * but immediately finish it. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) { + btrfs_bio_end_io(bbio, errno_to_blk_status(BTRFS_FS_ERROR(fs_info))); + return; + } btrfs_submit_bbio(bbio, 0); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 204674934795..9f6dcae25218 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2855,12 +2855,22 @@ static int btrfs_fallocate_update_isize(struct inode *inode, { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; + u64 range_start; + u64 range_end; int ret; int ret2; if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode)) return 0; + range_start = round_down(i_size_read(inode), root->fs_info->sectorsize); + range_end = round_up(end, root->fs_info->sectorsize); + + ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), range_start, + range_end - range_start); + if (ret) + return ret; + trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index da102da169fd..4958c6b32429 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1539,8 +1539,10 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst ASSERT(prealloc); /* Check the level of src and dst first */ - if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) + if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) { + kfree(prealloc); return -EINVAL; + } mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 32973c62c1a2..d18c0eaef9b7 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1260,8 +1260,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, spin_unlock(&fsc->async_unlink_conflict_lock); spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags); spin_unlock(&dentry->d_lock); synchronize_rcu(); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 978acd3d4b32..d7b943feb932 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -579,8 +579,7 @@ static void wake_async_create_waiters(struct inode *inode, spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { - ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE; - wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags); if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) { ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS; @@ -762,8 +761,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode, } spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_CREATE; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_CREATE_BIT, &di->flags); spin_unlock(&dentry->d_lock); return ret; diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index e861de3c79b9..15cde055f3da 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -246,21 +246,28 @@ static long ceph_ioctl_lazyio(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc; struct ceph_client *cl = mdsc->fsc->client; + bool is_file_already_lazy = false; + spin_lock(&ci->i_ceph_lock); if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) { - spin_lock(&ci->i_ceph_lock); fi->fmode |= CEPH_FILE_MODE_LAZY; ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++; __ceph_touch_fmode(ci, mdsc, fi->fmode); - spin_unlock(&ci->i_ceph_lock); + } else { + is_file_already_lazy = true; + } + spin_unlock(&ci->i_ceph_lock); + + if (is_file_already_lazy) { + doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, + ceph_vinop(inode)); + } else { doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode, ceph_vinop(inode)); ceph_check_caps(ci, 0); - } else { - doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, - ceph_vinop(inode)); } + return 0; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index ebf4ac0055dd..dd764f9c64b9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -221,7 +221,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, if (err && err != -ERESTARTSYS) return err; - wait_for_completion_killable(&req->r_safe_completion); + err = wait_for_completion_killable(&req->r_safe_completion); + if (err) + return err; + return 0; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3bc72b47fe4d..3efbc11596e0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5649,11 +5649,19 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); struct ceph_client *cl = mdsc->fsc->client; + const char *fs_name = mdsc->fsc->mount_options->mds_namespace; const char *spath = mdsc->fsc->mount_options->server_path; bool gid_matched = false; u32 gid, tlen, len; int i, j; + doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n", + fs_name, auth->match.fs_name ? auth->match.fs_name : ""); + if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { + /* fsname mismatch, try next one */ + return 0; + } + doutc(cl, "match.uid %lld\n", auth->match.uid); if (auth->match.uid != MDS_AUTH_UID_ANY) { if (auth->match.uid != caller_uid) diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 8109aba66e02..2c7b151a7c95 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -353,10 +353,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { + u32 fsname_len; /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); /* fs_name */ - ceph_decode_skip_string(p, end, bad_ext); + ceph_decode_32_safe(p, end, fsname_len, bad_ext); + + /* validate fsname against mds_namespace */ + if (!namespace_equals(mdsc->fsc->mount_options, *p, + fsname_len)) { + pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n", + (int)fsname_len, (char *)*p, + mdsc->fsc->mount_options->mds_namespace); + goto bad; + } + /* skip fsname after validation */ + ceph_decode_skip_n(p, end, fsname_len, bad); } /* damaged */ if (mdsmap_ev >= 9) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index c3eb651862c5..ebef5244ae25 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -246,20 +246,6 @@ static void canonicalize_path(char *path) path[j] = '\0'; } -/* - * Check if the mds namespace in ceph_mount_options matches - * the passed in namespace string. First time match (when - * ->mds_namespace is NULL) is treated specially, since - * ->mds_namespace needs to be initialized by the caller. - */ -static int namespace_equals(struct ceph_mount_options *fsopt, - const char *namespace, size_t len) -{ - return !(fsopt->mds_namespace && - (strlen(fsopt->mds_namespace) != len || - strncmp(fsopt->mds_namespace, namespace, len))); -} - static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index cf176aab0f82..4ac6561285b1 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -104,6 +104,20 @@ struct ceph_mount_options { struct fscrypt_dummy_policy dummy_enc_policy; }; +/* + * Check if the mds namespace in ceph_mount_options matches + * the passed in namespace string. First time match (when + * ->mds_namespace is NULL) is treated specially, since + * ->mds_namespace needs to be initialized by the caller. + */ +static inline int namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) +{ + return !(fsopt->mds_namespace && + (strlen(fsopt->mds_namespace) != len || + strncmp(fsopt->mds_namespace, namespace, len))); +} + /* mount state */ enum { CEPH_MOUNT_MOUNTING, diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index caaff809765b..45dea07f37a2 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -333,8 +333,7 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, inode = mapping->host; *inode_ret = inode; - *lblk_num_ret = ((u64)folio->index << (PAGE_SHIFT - inode->i_blkbits)) + - (bh_offset(bh) >> inode->i_blkbits); + *lblk_num_ret = (folio_pos(folio) + bh_offset(bh)) >> inode->i_blkbits; return true; } diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index cc01556c9d9b..071448adbd5d 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -26,12 +26,55 @@ /* * Allocation Bitmap Management Functions */ +static bool exfat_test_bitmap_range(struct super_block *sb, unsigned int clu, + unsigned int count) +{ + struct exfat_sb_info *sbi = EXFAT_SB(sb); + unsigned int start = clu; + unsigned int end = clu + count; + unsigned int ent_idx, i, b; + unsigned int bit_offset, bits_to_check; + __le_long *bitmap_le; + unsigned long mask, word; + + if (!is_valid_cluster(sbi, start) || !is_valid_cluster(sbi, end - 1)) + return false; + + while (start < end) { + ent_idx = CLUSTER_TO_BITMAP_ENT(start); + i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); + b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); + + bitmap_le = (__le_long *)sbi->vol_amap[i]->b_data; + + /* Calculate how many bits we can check in the current word */ + bit_offset = b % BITS_PER_LONG; + bits_to_check = min(end - start, + (unsigned int)(BITS_PER_LONG - bit_offset)); + + /* Create a bitmask for the range of bits to check */ + if (bits_to_check >= BITS_PER_LONG) + mask = ~0UL; + else + mask = ((1UL << bits_to_check) - 1) << bit_offset; + word = lel_to_cpu(bitmap_le[b / BITS_PER_LONG]); + + /* Check if all bits in the mask are set */ + if ((word & mask) != mask) + return false; + + start += bits_to_check; + } + + return true; +} + static int exfat_allocate_bitmap(struct super_block *sb, struct exfat_dentry *ep) { struct exfat_sb_info *sbi = EXFAT_SB(sb); long long map_size; - unsigned int i, need_map_size; + unsigned int i, j, need_map_size; sector_t sector; sbi->map_clu = le32_to_cpu(ep->dentry.bitmap.start_clu); @@ -58,20 +101,25 @@ static int exfat_allocate_bitmap(struct super_block *sb, sector = exfat_cluster_to_sector(sbi, sbi->map_clu); for (i = 0; i < sbi->map_sectors; i++) { sbi->vol_amap[i] = sb_bread(sb, sector + i); - if (!sbi->vol_amap[i]) { - /* release all buffers and free vol_amap */ - int j = 0; - - while (j < i) - brelse(sbi->vol_amap[j++]); - - kvfree(sbi->vol_amap); - sbi->vol_amap = NULL; - return -EIO; - } + if (!sbi->vol_amap[i]) + goto err_out; } + if (exfat_test_bitmap_range(sb, sbi->map_clu, + EXFAT_B_TO_CLU_ROUND_UP(map_size, sbi)) == false) + goto err_out; + return 0; + +err_out: + j = 0; + /* release all buffers and free vol_amap */ + while (j < i) + brelse(sbi->vol_amap[j++]); + + kvfree(sbi->vol_amap); + sbi->vol_amap = NULL; + return -EIO; } int exfat_load_bitmap(struct super_block *sb) diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 232cc7f8ab92..825083634ba2 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -89,35 +89,36 @@ int exfat_ent_get(struct super_block *sb, unsigned int loc, int err; if (!is_valid_cluster(sbi, loc)) { - exfat_fs_error(sb, "invalid access to FAT (entry 0x%08x)", + exfat_fs_error_ratelimit(sb, + "invalid access to FAT (entry 0x%08x)", loc); return -EIO; } err = __exfat_ent_get(sb, loc, content); if (err) { - exfat_fs_error(sb, + exfat_fs_error_ratelimit(sb, "failed to access to FAT (entry 0x%08x, err:%d)", loc, err); return err; } if (*content == EXFAT_FREE_CLUSTER) { - exfat_fs_error(sb, + exfat_fs_error_ratelimit(sb, "invalid access to FAT free cluster (entry 0x%08x)", loc); return -EIO; } if (*content == EXFAT_BAD_CLUSTER) { - exfat_fs_error(sb, + exfat_fs_error_ratelimit(sb, "invalid access to FAT bad cluster (entry 0x%08x)", loc); return -EIO; } if (*content != EXFAT_EOF_CLUSTER && !is_valid_cluster(sbi, *content)) { - exfat_fs_error(sb, + exfat_fs_error_ratelimit(sb, "invalid access to FAT (entry 0x%08x) bogus content (0x%08x)", loc, *content); return -EIO; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 42bee1d4f9f9..fa66b08de999 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -663,7 +663,7 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { - blk_opf_t write_flags = REQ_SYNC; + blk_opf_t write_flags = JBD2_JOURNAL_REQ_FLAGS; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; /* Add REQ_FUA | REQ_PREFLUSH only its tail */ diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b0e60a44dae9..ce7253b3f549 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1535,7 +1535,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && !(current->flags & PF_MEMALLOC_NOFS)); - ea_data = kvmalloc(value_len, GFP_KERNEL); + ea_data = kvmalloc(value_len, GFP_NOFS); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); return NULL; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 199c1e7a83ef..ba0a07bfd346 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -604,7 +604,13 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, p = &(*p)->rb_right; leftmost = false; } else { + f2fs_err_ratelimited(sbi, "%s: corrupted extent, type: %d, " + "extent node in rb tree [%u, %u, %u], age [%llu, %llu], " + "extent node to insert [%u, %u, %u], age [%llu, %llu]", + __func__, et->type, en->ei.fofs, en->ei.blk, en->ei.len, en->ei.age, + en->ei.last_blocks, ei->fofs, ei->blk, ei->len, ei->age, ei->last_blocks); f2fs_bug_on(sbi, 1); + return NULL; } } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 92054dcbe20d..4254db453b2d 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -27,12 +27,17 @@ static struct kmem_cache *free_nid_slab; static struct kmem_cache *nat_entry_set_slab; static struct kmem_cache *fsync_node_entry_slab; +static inline bool is_invalid_nid(struct f2fs_sb_info *sbi, nid_t nid) +{ + return nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid; +} + /* * Check whether the given nid is within node id range. */ int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { - if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { + if (unlikely(is_invalid_nid(sbi, nid))) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.", __func__, nid); @@ -2654,6 +2659,16 @@ retry: f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); i = list_first_entry(&nm_i->free_nid_list, struct free_nid, list); + + if (unlikely(is_invalid_nid(sbi, i->nid))) { + spin_unlock(&nm_i->nid_list_lock); + f2fs_err(sbi, "Corrupted nid %u in free_nid_list", + i->nid); + f2fs_stop_checkpoint(sbi, false, + STOP_CP_REASON_CORRUPTED_NID); + return false; + } + *nid = i->nid; __move_free_nid(sbi, i, FREE_NID, PREALLOC_NID); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index f736052dea50..902ffb3faa1f 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1723,12 +1723,15 @@ static int __maybe_unused disk_map_seq_show(struct seq_file *seq, seq_printf(seq, " Main : 0x%010x (%10d)\n", SM_I(sbi)->main_blkaddr, le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_main)); - seq_printf(seq, " # of Sections : %12d\n", - le32_to_cpu(F2FS_RAW_SUPER(sbi)->section_count)); + seq_printf(seq, " Block size : %12lu KB\n", F2FS_BLKSIZE >> 10); + seq_printf(seq, " Segment size : %12d MB\n", + (BLKS_PER_SEG(sbi) << (F2FS_BLKSIZE_BITS - 10)) >> 10); seq_printf(seq, " Segs/Sections : %12d\n", SEGS_PER_SEC(sbi)); seq_printf(seq, " Section size : %12d MB\n", - SEGS_PER_SEC(sbi) << 1); + (BLKS_PER_SEC(sbi) << (F2FS_BLKSIZE_BITS - 10)) >> 10); + seq_printf(seq, " # of Sections : %12d\n", + le32_to_cpu(F2FS_RAW_SUPER(sbi)->section_count)); if (!f2fs_is_multi_device(sbi)) return 0; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index dbf53c7bc853..612d4da6d7d9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -322,6 +322,7 @@ unsigned int fuse_req_hash(u64 unique) { return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS); } +EXPORT_SYMBOL_GPL(fuse_req_hash); /* * A new request is available, wake fiq->waitq diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 7ddfd2b3cc9c..7c0403a002e7 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -101,14 +101,11 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) if (!fi) return NULL; - fi->i_time = 0; + /* Initialize private data (i.e. everything except fi->inode) */ + BUILD_BUG_ON(offsetof(struct fuse_inode, inode) != 0); + memset((void *) fi + sizeof(fi->inode), 0, sizeof(*fi) - sizeof(fi->inode)); + fi->inval_mask = ~0; - fi->nodeid = 0; - fi->nlookup = 0; - fi->attr_version = 0; - fi->orig_ino = 0; - fi->state = 0; - fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 76c8fd0bfc75..1751cd6e3d42 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -20,6 +20,7 @@ #include <linux/cleanup.h> #include <linux/uio.h> #include "fuse_i.h" +#include "fuse_dev_i.h" /* Used to help calculate the FUSE connection's max_pages limit for a request's * size. Parts of the struct fuse_req are sliced into scattergather lists in @@ -1384,7 +1385,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, unsigned int out_sgs = 0; unsigned int in_sgs = 0; unsigned int total_sgs; - unsigned int i; + unsigned int i, hash; int ret; bool notify; struct fuse_pqueue *fpq; @@ -1444,8 +1445,9 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, /* Request successfully sent. */ fpq = &fsvq->fud->pq; + hash = fuse_req_hash(req->in.h.unique); spin_lock(&fpq->lock); - list_add_tail(&req->list, fpq->processing); + list_add_tail(&req->list, &fpq->processing[hash]); spin_unlock(&fpq->lock); set_bit(FR_SENT, &req->flags); /* matches barrier in request_wait_answer() */ diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index e3cdc421dfba..353e13a615f5 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -52,8 +52,10 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, dee.fnode = cpu_to_le32(fno); dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail2; + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -153,9 +155,10 @@ static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; result->i_mode |= S_IFREG; @@ -239,9 +242,10 @@ static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -314,8 +318,10 @@ static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; + } result->i_ino = fno; hpfs_init_inode(result); hpfs_i(result)->i_parent_dir = dir->i_ino; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index fcedeb514e14..21f3d029da7d 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -59,9 +59,15 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino) */ inode->i_link[inode->i_size] = '\0'; } - } else { + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &jfs_file_inode_operations; init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + printk(KERN_DEBUG "JFS: Invalid file type 0%04o for inode %lu.\n", + inode->i_mode, inode->i_ino); + iget_failed(inode); + return ERR_PTR(-EIO); } unlock_new_inode(inode); return inode; diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index be17e3c43582..7840a03e5bcb 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -272,14 +272,15 @@ int txInit(void) if (TxBlock == NULL) return -ENOMEM; - for (k = 1; k < nTxBlock - 1; k++) { - TxBlock[k].next = k + 1; + for (k = 0; k < nTxBlock; k++) { init_waitqueue_head(&TxBlock[k].gcwait); init_waitqueue_head(&TxBlock[k].waitor); } + + for (k = 1; k < nTxBlock - 1; k++) { + TxBlock[k].next = k + 1; + } TxBlock[k].next = 0; - init_waitqueue_head(&TxBlock[k].gcwait); - init_waitqueue_head(&TxBlock[k].waitor); TxAnchor.freetid = 1; init_waitqueue_head(&TxAnchor.freewait); diff --git a/fs/namespace.c b/fs/namespace.c index c8c2376bb242..fa7c034ac4a6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2785,12 +2785,19 @@ static int do_lock_mount(struct path *path, struct pinned_mountpoint *pinned, bo struct path under = {}; int err = -ENOENT; + if (unlikely(beneath) && !path_mounted(path)) + return -EINVAL; + for (;;) { struct mount *m = real_mount(mnt); if (beneath) { path_put(&under); read_seqlock_excl(&mount_lock); + if (unlikely(!mnt_has_parent(m))) { + read_sequnlock_excl(&mount_lock); + return -EINVAL; + } under.mnt = mntget(&m->mnt_parent->mnt); under.dentry = dget(m->mnt_mountpoint); read_sequnlock_excl(&mount_lock); @@ -3462,8 +3469,6 @@ static bool mount_is_ancestor(const struct mount *p1, const struct mount *p2) * @to: mount under which to mount * @mp: mountpoint of @to * - * - Make sure that @to->dentry is actually the root of a mount under - * which we can mount another mount. * - Make sure that nothing can be mounted beneath the caller's current * root or the rootfs of the namespace. * - Make sure that the caller can unmount the topmost mount ensuring @@ -3485,12 +3490,6 @@ static int can_move_mount_beneath(const struct path *from, *mnt_to = real_mount(to->mnt), *parent_mnt_to = mnt_to->mnt_parent; - if (!mnt_has_parent(mnt_to)) - return -EINVAL; - - if (!path_mounted(to)) - return -EINVAL; - if (IS_MNT_LOCKED(mnt_to)) return -EINVAL; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 611e6283c194..b76da06864e5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -391,7 +391,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent *p++ = htonl(attrs); /* bitmap */ *p++ = htonl(12); /* attribute buffer length */ *p++ = htonl(NF4DIR); + spin_lock(&dentry->d_lock); p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry->d_parent))); + spin_unlock(&dentry->d_lock); readdir->pgbase = (char *)p - (char *)start; readdir->count -= readdir->pgbase; @@ -7872,10 +7874,10 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, return err; do { err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); - if (err != -NFS4ERR_DELAY) + if (err != -NFS4ERR_DELAY && err != -NFS4ERR_GRACE) break; ssleep(1); - } while (err == -NFS4ERR_DELAY); + } while (err == -NFS4ERR_DELAY || err == -NFSERR_GRACE); return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err); } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 7612e977e80b..01179f7de322 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2744,6 +2744,9 @@ out_error: case -ENETUNREACH: nfs_mark_client_ready(clp, -EIO); break; + case -EINVAL: + nfs_mark_client_ready(clp, status); + break; default: ssleep(1); break; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7ae8e885d753..ebc8689e7781 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -988,10 +988,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static void nfsd4_read_release(union nfsd4_op_u *u) { - if (u->read.rd_nf) + if (u->read.rd_nf) { + trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, + u->read.rd_offset, u->read.rd_length); nfsd_file_put(u->read.rd_nf); - trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, - u->read.rd_offset, u->read.rd_length); + } } static __be32 @@ -2858,10 +2859,20 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) rqstp->rq_lease_breaker = (void **)&cstate->clp; - trace_nfsd_compound(rqstp, args->tag, args->taglen, args->opcnt); + trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; + if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) { + /* If there are still more operations to process, + * stop here and report NFS4ERR_RESOURCE. */ + if (cstate->minorversion == 0 && + args->client_opcnt > resp->opcnt) { + op->status = nfserr_resource; + goto encode_op; + } + } + /* * The XDR decode routines may have pre-set op->status; * for example, if there is a miscellaneous XDR error @@ -2938,7 +2949,7 @@ encode_op: status = op->status; } - trace_nfsd_compound_status(args->opcnt, resp->opcnt, + trace_nfsd_compound_status(args->client_opcnt, resp->opcnt, status, nfsd4_op_name(op->opnum)); nfsd4_cstate_clear_replay(cstate); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 205ee8cc6fa2..a3fb6caa95f9 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3865,6 +3865,7 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->headerpadsz = 0; ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc); ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc); + ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND); ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 89cc970effbc..1f6c3db3bc6e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2488,8 +2488,10 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) return false; - if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) + if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0) return false; + argp->opcnt = min_t(u32, argp->client_opcnt, + NFSD_MAX_OPS_PER_COMPOUND); if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops)); @@ -2939,6 +2941,12 @@ struct nfsd4_fattr_args { typedef __be32(*nfsd4_enc_attr)(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args); +static __be32 nfsd4_encode_fattr4__inval(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfserr_inval; +} + static __be32 nfsd4_encode_fattr4__noop(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { @@ -3560,6 +3568,8 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { [FATTR4_MODE_UMASK] = nfsd4_encode_fattr4__noop, [FATTR4_XATTR_SUPPORT] = nfsd4_encode_fattr4_xattr_support, + [FATTR4_TIME_DELEG_ACCESS] = nfsd4_encode_fattr4__inval, + [FATTR4_TIME_DELEG_MODIFY] = nfsd4_encode_fattr4__inval, [FATTR4_OPEN_ARGUMENTS] = nfsd4_encode_fattr4_open_arguments, }; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 1cd0bed57bc2..ab22a4cef621 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -57,6 +57,9 @@ struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 200 + struct nfsd_genl_rqstp { struct sockaddr rq_daddr; struct sockaddr rq_saddr; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index d4b48602b2b0..ee0570cbdd9e 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -903,6 +903,7 @@ struct nfsd4_compoundargs { char * tag; u32 taglen; u32 minorversion; + u32 client_opcnt; u32 opcnt; bool splice_ok; struct nfsd4_op *ops; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 37cbbee7fa58..b08b00912165 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -471,6 +471,7 @@ end_enum: fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) { /* Records in $Extend are not a files or general directories. */ inode->i_op = &ntfs_file_inode_operations; + mode = S_IFREG; } else { err = -EINVAL; goto out; diff --git a/fs/open.c b/fs/open.c index 9655158c3885..4890b13461c7 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1059,18 +1059,20 @@ EXPORT_SYMBOL(finish_open); * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer - * @dentry: dentry or NULL (as returned from ->lookup()) + * @dentry: dentry, ERR_PTR(-E...) or NULL (as returned from ->lookup()) * - * This can be used to set the result of a successful lookup in ->atomic_open(). + * This can be used to set the result of a lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * - * Returns "0" which must be the return value of ->atomic_open() after having - * called this function. + * Returns 0 or -E..., which must be the return value of ->atomic_open() after + * having called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { + if (IS_ERR(dentry)) + return PTR_ERR(dentry); file->f_path.dentry = dentry; return 0; } diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 74ef75586f38..eee3c5ed1bbb 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -54,7 +54,9 @@ static inline int convert_to_internal_xattr_flags(int setxattr_flags) static unsigned int xattr_key(const char *key) { unsigned int i = 0; - while (key) + if (!key) + return 0; + while (*key) i += *key++; return i % 16; } @@ -175,8 +177,8 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, cx->length = -1; cx->timeout = jiffies + orangefs_getattr_timeout_msecs*HZ/1000; - hash_add(orangefs_inode->xattr_cache, &cx->node, - xattr_key(cx->key)); + hlist_add_head( &cx->node, + &orangefs_inode->xattr_cache[xattr_key(cx->key)]); } } goto out_release_op; @@ -229,8 +231,8 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, memcpy(cx->val, buffer, length); cx->length = length; cx->timeout = jiffies + HZ; - hash_add(orangefs_inode->xattr_cache, &cx->node, - xattr_key(cx->key)); + hlist_add_head(&cx->node, + &orangefs_inode->xattr_cache[xattr_key(cx->key)]); } } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index dbd63a74df4b..039e829aa7de 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -205,12 +205,32 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, err = -EPERM; } } - if (!err && WARN_ON(!newdentry->d_inode)) { + if (err) + goto out; + + if (WARN_ON(!newdentry->d_inode)) { /* * Not quite sure if non-instantiated dentry is legal or not. * VFS doesn't seem to care so check and warn here. */ err = -EIO; + } else if (d_unhashed(newdentry)) { + struct dentry *d; + /* + * Some filesystems (i.e. casefolded) may return an unhashed + * negative dentry from the ovl_lookup_upper() call before + * ovl_create_real(). + * In that case, lookup again after making the newdentry + * positive, so ovl_create_upper() always returns a hashed + * positive dentry. + */ + d = ovl_lookup_upper(ofs, newdentry->d_name.name, parent, + newdentry->d_name.len); + dput(newdentry); + if (IS_ERR_OR_NULL(d)) + err = d ? PTR_ERR(d) : -ENOENT; + else + return d; } out: if (err) { diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b69daeb1301b..1ab737ffedfe 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -389,11 +389,11 @@ out: * lease. Release one here, and the second below. */ cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } spin_unlock(&cfids->cfid_list_lock); - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } else { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); @@ -423,6 +423,7 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon, cifs_dbg(FYI, "found a cached file handle by dentry\n"); kref_get(&cfid->refcount); *ret_cfid = cfid; + cfid->last_access_time = jiffies; spin_unlock(&cfids->cfid_list_lock); return 0; } @@ -433,12 +434,14 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon, static void smb2_close_cached_fid(struct kref *ref) +__releases(&cfid->cfids->cfid_list_lock) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); int rc; - spin_lock(&cfid->cfids->cfid_list_lock); + lockdep_assert_held(&cfid->cfids->cfid_list_lock); + if (cfid->on_list) { list_del(&cfid->entry); cfid->on_list = false; @@ -473,7 +476,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->has_lease) { cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } spin_unlock(&cfid->cfids->cfid_list_lock); close_cached_dir(cfid); @@ -482,7 +485,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, void close_cached_dir(struct cached_fid *cfid) { - kref_put(&cfid->refcount, smb2_close_cached_fid); + kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock); } /* @@ -593,7 +596,7 @@ cached_dir_offload_close(struct work_struct *work) WARN_ON(cfid->on_list); - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cached_close); } @@ -770,7 +773,7 @@ static void cfids_laundromat_worker(struct work_struct *work) * Drop the ref-count from above, either the lease-ref (if there * was one) or the extra one acquired. */ - kref_put(&cfid->refcount, smb2_close_cached_fid); + close_cached_dir(cfid); } queue_delayed_work(cfid_put_wq, &cfids->laundromat_work, dir_cache_timeout * HZ); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 7e86d0ef4b35..a4c283348c7b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2716,11 +2716,12 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; int rc; __le16 *utf16_path; - struct cached_fid *cfid = NULL; + struct cached_fid *cfid; int retries = 0, cur_sleep = 1; replay_again: /* reinitialize for possible replay */ + cfid = NULL; flags = CIFS_CP_CREATE_CLOSE_OP; oplock = SMB2_OPLOCK_LEVEL_NONE; server = cifs_pick_channel(ses); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c3b9d3f6210f..f925b2da76c1 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4054,9 +4054,12 @@ replay_again: smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; - smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), - le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov, + rc = smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), + &rsp_iov, sizeof(struct file_notify_information)); + if (rc) + goto cnotify_exit; *out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset), le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index a61ba7f3fb86..940e90107134 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -22,6 +22,7 @@ #include <linux/mempool.h> #include <linux/sched/signal.h> #include <linux/task_io_accounting_ops.h> +#include <linux/task_work.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" @@ -173,9 +174,16 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, * send a packet. In most cases if we fail to send * after the retries we will kill the socket and * reconnect which may clear the network problem. + * + * Even if regular signals are masked, EINTR might be + * propagated from sk_stream_wait_memory() to here when + * TIF_NOTIFY_SIGNAL is used for task work. For example, + * certain io_uring completions will use that. Treat + * having EINTR with pending task work the same as EAGAIN + * to avoid unnecessary reconnects. */ rc = sock_sendmsg(ssocket, smb_msg); - if (rc == -EAGAIN) { + if (rc == -EAGAIN || unlikely(rc == -EINTR && task_work_pending(current))) { retries++; if (retries >= 14 || (!server->noblocksnd && (retries > 2))) { diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index 1009cb324fd5..43401d09c9db 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -473,12 +473,13 @@ static int create_socket(struct interface *iface) struct socket *ksmbd_socket; bool ipv4 = false; - ret = sock_create(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &ksmbd_socket); + ret = sock_create_kern(current->nsproxy->net_ns, PF_INET6, SOCK_STREAM, + IPPROTO_TCP, &ksmbd_socket); if (ret) { if (ret != -EAFNOSUPPORT) pr_err("Can't create socket for ipv6, fallback to ipv4: %d\n", ret); - ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, - &ksmbd_socket); + ret = sock_create_kern(current->nsproxy->net_ns, PF_INET, + SOCK_STREAM, IPPROTO_TCP, &ksmbd_socket); if (ret) { pr_err("Can't create socket for ipv4: %d\n", ret); goto out_clear; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2a74f2957341..0cf84b25d656 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1082,6 +1082,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = { }; #endif /* CONFIG_XFS_RT */ +#ifdef DEBUG +static void +xfs_check_atomic_cow_conversion( + struct xfs_inode *ip, + xfs_fileoff_t offset_fsb, + xfs_filblks_t count_fsb, + const struct xfs_bmbt_irec *cmap) +{ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec cmap2 = { }; + + if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2)) + xfs_trim_extent(&cmap2, offset_fsb, count_fsb); + + ASSERT(cmap2.br_startoff == cmap->br_startoff); + ASSERT(cmap2.br_blockcount == cmap->br_blockcount); + ASSERT(cmap2.br_startblock == cmap->br_startblock); + ASSERT(cmap2.br_state == cmap->br_state); +} +#else +# define xfs_check_atomic_cow_conversion(...) ((void)0) +#endif + static int xfs_atomic_write_cow_iomap_begin( struct inode *inode, @@ -1093,9 +1116,10 @@ xfs_atomic_write_cow_iomap_begin( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); - xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length); - xfs_filblks_t count_fsb = end_fsb - offset_fsb; + const xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + const xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); + const xfs_filblks_t count_fsb = end_fsb - offset_fsb; + xfs_filblks_t hole_count_fsb; int nmaps = 1; xfs_filblks_t resaligned; struct xfs_bmbt_irec cmap; @@ -1121,7 +1145,7 @@ xfs_atomic_write_cow_iomap_begin( return -EAGAIN; trace_xfs_iomap_atomic_write_cow(ip, offset, length); - +retry: xfs_ilock(ip, XFS_ILOCK_EXCL); if (!ip->i_cowfp) { @@ -1132,14 +1156,22 @@ xfs_atomic_write_cow_iomap_begin( if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap)) cmap.br_startoff = end_fsb; if (cmap.br_startoff <= offset_fsb) { + if (isnullstartblock(cmap.br_startblock)) + goto convert_delay; + + /* + * cmap could extend outside the write range due to previous + * speculative preallocations. We must trim cmap to the write + * range because the cow fork treats written mappings to mean + * "write in progress". + */ xfs_trim_extent(&cmap, offset_fsb, count_fsb); goto found; } - end_fsb = cmap.br_startoff; - count_fsb = end_fsb - offset_fsb; + hole_count_fsb = cmap.br_startoff - offset_fsb; - resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, + resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb, xfs_get_cowextsz_hint(ip)); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -1160,8 +1192,10 @@ xfs_atomic_write_cow_iomap_begin( if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap)) cmap.br_startoff = end_fsb; if (cmap.br_startoff <= offset_fsb) { - xfs_trim_extent(&cmap, offset_fsb, count_fsb); xfs_trans_cancel(tp); + if (isnullstartblock(cmap.br_startblock)) + goto convert_delay; + xfs_trim_extent(&cmap, offset_fsb, count_fsb); goto found; } @@ -1173,7 +1207,7 @@ xfs_atomic_write_cow_iomap_begin( * atomic writes to that same range will be aligned (and don't require * this COW-based method). */ - error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, + error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb, XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC | XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps); if (error) { @@ -1186,21 +1220,43 @@ xfs_atomic_write_cow_iomap_begin( if (error) goto out_unlock; + /* + * cmap could map more blocks than the range we passed into bmapi_write + * because of EXTSZALIGN or adjacent pre-existing unwritten mappings + * that were merged. Trim cmap to the original write range so that we + * don't convert more than we were asked to do for this write. + */ + xfs_trim_extent(&cmap, offset_fsb, count_fsb); + found: if (cmap.br_state != XFS_EXT_NORM) { - error = xfs_reflink_convert_cow_locked(ip, offset_fsb, - count_fsb); + error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff, + cmap.br_blockcount); if (error) goto out_unlock; cmap.br_state = XFS_EXT_NORM; + xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb, + &cmap); } - length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount); - trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap); + trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap); seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED); xfs_iunlock(ip, XFS_ILOCK_EXCL); return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq); +convert_delay: + xfs_iunlock(ip, XFS_ILOCK_EXCL); + error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap, + NULL); + if (error) + return error; + + /* + * Try the lookup again, because the delalloc conversion might have + * turned the COW mapping into unwritten, but we need it to be in + * written state. + */ + goto retry; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; |