diff options
Diffstat (limited to 'fs')
85 files changed, 1551 insertions, 1106 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 664991afe0c0..a6bb530b1ec5 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -165,6 +165,7 @@ config HUGETLB_PAGE def_bool HUGETLBFS source "fs/configfs/Kconfig" +source "fs/efivarfs/Kconfig" endmenu @@ -209,7 +210,6 @@ source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" source "fs/f2fs/Kconfig" -source "fs/efivarfs/Kconfig" endif # MISC_FILESYSTEMS @@ -1140,6 +1140,13 @@ static long aio_read_events_ring(struct kioctx *ctx, long ret = 0; int copy_ret; + /* + * The mutex can block and wake us up and that will cause + * wait_event_interruptible_hrtimeout() to schedule without sleeping + * and repeat. This should be rare enough that it doesn't cause + * peformance issues. See the comment in read_events() for more detail. + */ + sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_pages here is protected by ctx->ring_lock. */ diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index a66768ebc8d1..80e9c18ea64f 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -8,6 +8,7 @@ config BTRFS_FS select LZO_DECOMPRESS select RAID6_PQ select XOR_BLOCKS + select SRCU help Btrfs is a general purpose copy-on-write filesystem with extents, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2d3e32ebfd15..8729cf68d2fe 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1552,7 +1552,6 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, { int ret; int type; - struct btrfs_tree_block_info *info; struct btrfs_extent_inline_ref *eiref; if (*ptr == (unsigned long)-1) @@ -1573,9 +1572,17 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, } /* we can treat both ref types equally here */ - info = (struct btrfs_tree_block_info *)(ei + 1); *out_root = btrfs_extent_inline_ref_offset(eb, eiref); - *out_level = btrfs_tree_block_level(eb, info); + + if (key->type == BTRFS_EXTENT_ITEM_KEY) { + struct btrfs_tree_block_info *info; + + info = (struct btrfs_tree_block_info *)(ei + 1); + *out_level = btrfs_tree_block_level(eb, info); + } else { + ASSERT(key->type == BTRFS_METADATA_ITEM_KEY); + *out_level = (u8)key->offset; + } if (ret == 1) *ptr = (unsigned long)-1; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7e607416755a..0b180708bf79 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1171,6 +1171,7 @@ struct btrfs_space_info { struct percpu_counter total_bytes_pinned; struct list_head list; + /* Protected by the spinlock 'lock'. */ struct list_head ro_bgs; struct rw_semaphore groups_sem; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 054577bddaf2..de4e70fb3cbb 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode) { struct btrfs_delayed_node *delayed_node; + /* + * we don't do delayed inode updates during log recovery because it + * leads to enospc problems. This means we also can't do + * delayed inode refs + */ + if (BTRFS_I(inode)->root->fs_info->log_root_recovering) + return -EAGAIN; + delayed_node = btrfs_get_or_create_delayed_node(inode); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a80b97100d90..a684086c3c81 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3139,9 +3139,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1); - if (ret < 0) + if (ret) { + if (ret > 0) + ret = -ENOENT; goto fail; - BUG_ON(ret); /* Corruption */ + } leaf = path->nodes[0]; bi = btrfs_item_ptr_offset(leaf, path->slots[0]); @@ -3149,11 +3151,9 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); fail: - if (ret) { + if (ret) btrfs_abort_transaction(trans, root, ret); - return ret; - } - return 0; + return ret; } @@ -9422,7 +9422,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * are still on the list after taking the semaphore */ list_del_init(&block_group->list); - list_del_init(&block_group->ro_list); if (list_empty(&block_group->space_info->block_groups[index])) { kobj = block_group->space_info->block_group_kobjs[index]; block_group->space_info->block_group_kobjs[index] = NULL; @@ -9464,6 +9463,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_remove_free_space_cache(block_group); spin_lock(&block_group->space_info->lock); + list_del_init(&block_group->ro_list); block_group->space_info->total_bytes -= block_group->key.offset; block_group->space_info->bytes_readonly -= block_group->key.offset; block_group->space_info->disk_total -= block_group->key.offset * factor; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4ebabd237153..790dbae3343c 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2190,7 +2190,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end) next = next_state(state); - failrec = (struct io_failure_record *)state->private; + failrec = (struct io_failure_record *)(unsigned long)state->private; free_extent_state(state); kfree(failrec); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e687bb0dc73a..8bf326affb94 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6255,8 +6255,10 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) out_fail: btrfs_end_transaction(trans, root); - if (drop_on_err) + if (drop_on_err) { + inode_dec_link_count(inode); iput(inode); + } btrfs_balance_delayed_items(root); btrfs_btree_balance_dirty(root); return err; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f2bb13a23f86..e427cb7ee12c 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2607,9 +2607,9 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, ret = scrub_pages_for_parity(sparity, logical, l, physical, dev, flags, gen, mirror_num, have_csum ? csum : NULL); -skip: if (ret) return ret; +skip: len -= l; logical += l; physical += l; @@ -3053,7 +3053,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, ppath = btrfs_alloc_path(); if (!ppath) { - btrfs_free_path(ppath); + btrfs_free_path(path); return -ENOMEM; } @@ -3065,6 +3065,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, path->search_commit_root = 1; path->skip_locking = 1; + ppath->search_commit_root = 1; + ppath->skip_locking = 1; /* * trigger the readahead for extent tree csum tree and wait for * completion. During readahead, the scrub is officially paused diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 60f7cbe815e9..6f49b2872a64 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1000,10 +1000,20 @@ int btrfs_sync_fs(struct super_block *sb, int wait) */ if (fs_info->pending_changes == 0) return 0; + /* + * A non-blocking test if the fs is frozen. We must not + * start a new transaction here otherwise a deadlock + * happens. The pending operations are delayed to the + * next commit after thawing. + */ + if (__sb_start_write(sb, SB_FREEZE_WRITE, false)) + __sb_end_write(sb, SB_FREEZE_WRITE); + else + return 0; trans = btrfs_start_transaction(root, 0); - } else { - return PTR_ERR(trans); } + if (IS_ERR(trans)) + return PTR_ERR(trans); } return btrfs_commit_transaction(trans, root); } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index a605d4e2f2bc..e88b59d13439 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2118,7 +2118,7 @@ void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info) unsigned long prev; unsigned long bit; - prev = cmpxchg(&fs_info->pending_changes, 0, 0); + prev = xchg(&fs_info->pending_changes, 0); if (!prev) return; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9a02da16f2be..1a9585d4380a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2591,6 +2591,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { + blk_finish_plug(&plug); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index f5013d92a7e6..c81c0e004588 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1416,7 +1416,7 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page, } } - dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n", + dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n", inode, ceph_vinop(inode), len, locked_page); if (len > 0) { diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index c35c5c614e38..06ea5cd05cd9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -239,23 +239,21 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) return err; } -/** - * Must be called with lock_flocks() already held. Fills in the passed - * counter variables, so you can prepare pagelist metadata before calling - * ceph_encode_locks. +/* + * Fills in the passed counter variables, so you can prepare pagelist metadata + * before calling ceph_encode_locks. */ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) { - struct file_lock *lock; + struct file_lock_context *ctx; *fcntl_count = 0; *flock_count = 0; - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) - ++(*fcntl_count); - else if (lock->fl_flags & FL_FLOCK) - ++(*flock_count); + ctx = inode->i_flctx; + if (ctx) { + *fcntl_count = ctx->flc_posix_cnt; + *flock_count = ctx->flc_flock_cnt; } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); @@ -271,6 +269,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; + struct file_lock_context *ctx = inode->i_flctx; int err = 0; int seen_fcntl = 0; int seen_flock = 0; @@ -279,33 +278,34 @@ int ceph_encode_locks_to_buffer(struct inode *inode, dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) { - ++seen_fcntl; - if (seen_fcntl > num_fcntl_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + if (!ctx) + return 0; + + spin_lock(&ctx->flc_lock); + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_fcntl; + if (seen_fcntl > num_fcntl_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_FLOCK) { - ++seen_flock; - if (seen_flock > num_flock_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_flock; + if (seen_flock > num_flock_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } fail: + spin_unlock(&ctx->flc_lock); return err; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d2171f4a6980..5f62fb7a5d0a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2700,20 +2700,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_filelock *flocks; encode_again: - spin_lock(&inode->i_lock); ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks); - spin_unlock(&inode->i_lock); flocks = kmalloc((num_fcntl_locks+num_flock_locks) * sizeof(struct ceph_filelock), GFP_NOFS); if (!flocks) { err = -ENOMEM; goto out_free; } - spin_lock(&inode->i_lock); err = ceph_encode_locks_to_buffer(inode, flocks, num_fcntl_locks, num_flock_locks); - spin_unlock(&inode->i_lock); if (err) { kfree(flocks); if (err == -ENOSPC) diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 9c56ef776407..7febcf2475c5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -606,9 +606,11 @@ cifs_security_flags_handle_must_flags(unsigned int *flags) *flags = CIFSSEC_MUST_NTLMV2; else if ((*flags & CIFSSEC_MUST_NTLM) == CIFSSEC_MUST_NTLM) *flags = CIFSSEC_MUST_NTLM; - else if ((*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) + else if (CIFSSEC_MUST_LANMAN && + (*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) *flags = CIFSSEC_MUST_LANMAN; - else if ((*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) + else if (CIFSSEC_MUST_PLNTXT && + (*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) *flags = CIFSSEC_MUST_PLNTXT; *flags |= signflags; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 6e139111fdb2..22b289a3b1c4 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -661,16 +661,16 @@ set_credits(struct TCP_Server_Info *server, const int val) server->ops->set_credits(server, val); } -static inline __u64 +static inline __le64 get_next_mid64(struct TCP_Server_Info *server) { - return server->ops->get_next_mid(server); + return cpu_to_le64(server->ops->get_next_mid(server)); } static inline __le16 get_next_mid(struct TCP_Server_Info *server) { - __u16 mid = get_next_mid64(server); + __u16 mid = server->ops->get_next_mid(server); /* * The value in the SMB header should be little endian for easy * on-the-wire decoding. diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 96b7e9b7706d..c1a86764bbf7 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* @@ -1109,11 +1113,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } -/* copied from fs/locks.c with a name change */ -#define cifs_for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; \ - lockp = &(*lockp)->fl_next) - struct lock_to_push { struct list_head llist; __u64 offset; @@ -1128,8 +1127,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) { struct inode *inode = cfile->dentry->d_inode; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct file_lock *flock, **before; - unsigned int count = 0, i = 0; + struct file_lock *flock; + struct file_lock_context *flctx = inode->i_flctx; + unsigned int i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1137,21 +1137,17 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) xid = get_xid(); - spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - if ((*before)->fl_flags & FL_POSIX) - count++; - } - spin_unlock(&inode->i_lock); + if (!flctx) + goto out; INIT_LIST_HEAD(&locks_to_send); /* - * Allocating count locks is enough because no FL_POSIX locks can be - * added to the list while we are holding cinode->lock_sem that + * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks + * can be added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (; i < count; i++) { + for (i = 0; i < flctx->flc_posix_cnt; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; @@ -1161,11 +1157,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) } el = locks_to_send.next; - spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - flock = *before; - if ((flock->fl_flags & FL_POSIX) == 0) - continue; + spin_lock(&flctx->flc_lock); + list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* * The list ended. We don't have enough allocated @@ -1185,9 +1178,8 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->length = length; lck->type = type; lck->offset = flock->fl_start; - el = el->next; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { int stored_rc; diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 45cb59bcc791..8b7898b7670f 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, } src_inode = file_inode(src_file.file); + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants * server could even support copy of range where source = target */ - - /* so we do not deadlock racing two ioctls on same files */ - if (target_inode < src_inode) { - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD); - } + lock_two_nondirectories(target_inode, src_inode); /* determine range to clone */ rc = -EINVAL; @@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ - if (target_inode < src_inode) { - mutex_unlock(&src_inode->i_mutex); - mutex_unlock(&target_inode->i_mutex); - } else { - mutex_unlock(&target_inode->i_mutex); - mutex_unlock(&src_inode->i_mutex); - } + unlock_two_nondirectories(src_inode, target_inode); out_fput: fdput(src_file); out_drop_write: diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index b333ff60781d..abae6dd2c6b9 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -926,6 +926,7 @@ cifs_NTtimeToUnix(__le64 ntutc) /* Subtract the NTFS time offset, then convert to 1s intervals. */ s64 t = le64_to_cpu(ntutc) - NTFS_TIME_OFFSET; + u64 abs_t; /* * Unfortunately can not use normal 64 bit division on 32 bit arch, but @@ -933,13 +934,14 @@ cifs_NTtimeToUnix(__le64 ntutc) * to special case them */ if (t < 0) { - t = -t; - ts.tv_nsec = (long)(do_div(t, 10000000) * 100); + abs_t = -t; + ts.tv_nsec = (long)(do_div(abs_t, 10000000) * 100); ts.tv_nsec = -ts.tv_nsec; - ts.tv_sec = -t; + ts.tv_sec = -abs_t; } else { - ts.tv_nsec = (long)do_div(t, 10000000) * 100; - ts.tv_sec = t; + abs_t = t; + ts.tv_nsec = (long)do_div(abs_t, 10000000) * 100; + ts.tv_sec = abs_t; } return ts; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 8eaf20a80649..c295338e0a98 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -69,7 +69,8 @@ static inline void dump_cifs_file_struct(struct file *file, char *label) * Attempt to preload the dcache with the results from the FIND_FIRST/NEXT * * Find the dentry that matches "name". If there isn't one, create one. If it's - * a negative dentry or the uniqueid changed, then drop it and recreate it. + * a negative dentry or the uniqueid or filetype(mode) changed, + * then drop it and recreate it. */ static void cifs_prime_dcache(struct dentry *parent, struct qstr *name, @@ -97,8 +98,11 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) fattr->cf_uniqueid = CIFS_I(inode)->uniqueid; - /* update inode in place if i_ino didn't change */ - if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + /* update inode in place + * if both i_ino and i_mode didn't change */ + if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid && + (inode->i_mode & S_IFMT) == + (fattr->cf_mode & S_IFMT)) { cifs_fattr_to_inode(inode, fattr); goto out; } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index f1cefc9763ed..689f035915cf 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -32,12 +32,14 @@ static int check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid) { + __u64 wire_mid = le64_to_cpu(hdr->MessageId); + /* * Make sure that this really is an SMB, that it is a response, * and that the message ids match. */ if ((*(__le32 *)hdr->ProtocolId == SMB2_PROTO_NUMBER) && - (mid == hdr->MessageId)) { + (mid == wire_mid)) { if (hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR) return 0; else { @@ -51,11 +53,11 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid) if (*(__le32 *)hdr->ProtocolId != SMB2_PROTO_NUMBER) cifs_dbg(VFS, "Bad protocol string signature header %x\n", *(unsigned int *) hdr->ProtocolId); - if (mid != hdr->MessageId) + if (mid != wire_mid) cifs_dbg(VFS, "Mids do not match: %llu and %llu\n", - mid, hdr->MessageId); + mid, wire_mid); } - cifs_dbg(VFS, "Bad SMB detected. The Mid=%llu\n", hdr->MessageId); + cifs_dbg(VFS, "Bad SMB detected. The Mid=%llu\n", wire_mid); return 1; } @@ -95,7 +97,7 @@ smb2_check_message(char *buf, unsigned int length) { struct smb2_hdr *hdr = (struct smb2_hdr *)buf; struct smb2_pdu *pdu = (struct smb2_pdu *)hdr; - __u64 mid = hdr->MessageId; + __u64 mid = le64_to_cpu(hdr->MessageId); __u32 len = get_rfc1002_length(buf); __u32 clc_len; /* calculated length */ int command; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 93fd0586f9ec..96b5d40a2ece 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -176,10 +176,11 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) { struct mid_q_entry *mid; struct smb2_hdr *hdr = (struct smb2_hdr *)buf; + __u64 wire_mid = le64_to_cpu(hdr->MessageId); spin_lock(&GlobalMid_Lock); list_for_each_entry(mid, &server->pending_mid_q, qhead) { - if ((mid->mid == hdr->MessageId) && + if ((mid->mid == wire_mid) && (mid->mid_state == MID_REQUEST_SUBMITTED) && (mid->command == hdr->Command)) { spin_unlock(&GlobalMid_Lock); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index ce858477002a..70867d54fb8b 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -110,7 +110,7 @@ struct smb2_hdr { __le16 CreditRequest; /* CreditResponse */ __le32 Flags; __le32 NextCommand; - __u64 MessageId; /* opaque - so can stay little endian */ + __le64 MessageId; __le32 ProcessId; __u32 TreeId; /* opaque - so do not make little endian */ __u64 SessionId; /* opaque - so do not make little endian */ diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 5111e7272db6..d4c5b6f109a7 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -490,7 +490,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer, return temp; else { memset(temp, 0, sizeof(struct mid_q_entry)); - temp->mid = smb_buffer->MessageId; /* always LE */ + temp->mid = le64_to_cpu(smb_buffer->MessageId); temp->pid = current->pid; temp->command = smb_buffer->Command; /* Always LE */ temp->when_alloc = jiffies; diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 6c1566366a66..a4232ec4f2ba 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -221,7 +221,7 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16, } rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16)); - memset(wpwd, 0, 129 * sizeof(__le16)); + memzero_explicit(wpwd, sizeof(wpwd)); return rc; } diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig index 367bbb10c543..c2499ef174a2 100644 --- a/fs/efivarfs/Kconfig +++ b/fs/efivarfs/Kconfig @@ -1,6 +1,7 @@ config EFIVAR_FS tristate "EFI Variable filesystem" depends on EFI + default m help efivarfs is a replacement filesystem for the old EFI variable support via sysfs, as it doesn't suffer from the diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6dad1176ec52..ddbce42548c9 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -140,7 +140,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len] = '-'; - efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 9b4e7d750d4f..d4dbf3c259b3 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -466,6 +466,8 @@ static void ext3_put_super (struct super_block * sb) } sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); + mutex_destroy(&sbi->s_orphan_lock); + mutex_destroy(&sbi->s_resize_lock); kfree(sbi); } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e5d3eadf47b1..bed43081720f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5166,8 +5166,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, /* fallback to generic here if not in extents fmt */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - return __generic_block_fiemap(inode, fieinfo, start, len, - ext4_get_block); + return generic_block_fiemap(inode, fieinfo, start, len, + ext4_get_block); if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS)) return -EBADR; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 513c12cf444c..8131be8c0af3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -273,19 +273,24 @@ static int ext4_file_open(struct inode * inode, struct file * filp) * we determine this extent as a data or a hole according to whether the * page cache has data or not. */ -static int ext4_find_unwritten_pgoff(struct inode *inode, int whence, - loff_t endoff, loff_t *offset) +static int ext4_find_unwritten_pgoff(struct inode *inode, + int whence, + struct ext4_map_blocks *map, + loff_t *offset) { struct pagevec pvec; + unsigned int blkbits; pgoff_t index; pgoff_t end; + loff_t endoff; loff_t startoff; loff_t lastoff; int found = 0; + blkbits = inode->i_sb->s_blocksize_bits; startoff = *offset; lastoff = startoff; - + endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits; index = startoff >> PAGE_CACHE_SHIFT; end = endoff >> PAGE_CACHE_SHIFT; @@ -403,144 +408,147 @@ out: static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize) { struct inode *inode = file->f_mapping->host; - struct fiemap_extent_info fie; - struct fiemap_extent ext[2]; - loff_t next; - int i, ret = 0; + struct ext4_map_blocks map; + struct extent_status es; + ext4_lblk_t start, last, end; + loff_t dataoff, isize; + int blkbits; + int ret = 0; mutex_lock(&inode->i_mutex); - if (offset >= inode->i_size) { + + isize = i_size_read(inode); + if (offset >= isize) { mutex_unlock(&inode->i_mutex); return -ENXIO; } - fie.fi_flags = 0; - fie.fi_extents_max = 2; - fie.fi_extents_start = (struct fiemap_extent __user *) &ext; - while (1) { - mm_segment_t old_fs = get_fs(); - - fie.fi_extents_mapped = 0; - memset(ext, 0, sizeof(*ext) * fie.fi_extents_max); - - set_fs(get_ds()); - ret = ext4_fiemap(inode, &fie, offset, maxsize - offset); - set_fs(old_fs); - if (ret) + + blkbits = inode->i_sb->s_blocksize_bits; + start = offset >> blkbits; + last = start; + end = isize >> blkbits; + dataoff = offset; + + do { + map.m_lblk = last; + map.m_len = end - last + 1; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) { + if (last != start) + dataoff = (loff_t)last << blkbits; break; + } - /* No extents found, EOF */ - if (!fie.fi_extents_mapped) { - ret = -ENXIO; + /* + * If there is a delay extent at this offset, + * it will be as a data. + */ + ext4_es_find_delayed_extent_range(inode, last, last, &es); + if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) { + if (last != start) + dataoff = (loff_t)last << blkbits; break; } - for (i = 0; i < fie.fi_extents_mapped; i++) { - next = (loff_t)(ext[i].fe_length + ext[i].fe_logical); - if (offset < (loff_t)ext[i].fe_logical) - offset = (loff_t)ext[i].fe_logical; - /* - * If extent is not unwritten, then it contains valid - * data, mapped or delayed. - */ - if (!(ext[i].fe_flags & FIEMAP_EXTENT_UNWRITTEN)) - goto out; + /* + * If there is a unwritten extent at this offset, + * it will be as a data or a hole according to page + * cache that has data or not. + */ + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int unwritten; + unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA, + &map, &dataoff); + if (unwritten) + break; + } - /* - * If there is a unwritten extent at this offset, - * it will be as a data or a hole according to page - * cache that has data or not. - */ - if (ext4_find_unwritten_pgoff(inode, SEEK_DATA, - next, &offset)) - goto out; + last++; + dataoff = (loff_t)last << blkbits; + } while (last <= end); - if (ext[i].fe_flags & FIEMAP_EXTENT_LAST) { - ret = -ENXIO; - goto out; - } - offset = next; - } - } - if (offset > inode->i_size) - offset = inode->i_size; -out: mutex_unlock(&inode->i_mutex); - if (ret) - return ret; - return vfs_setpos(file, offset, maxsize); + if (dataoff > isize) + return -ENXIO; + + return vfs_setpos(file, dataoff, maxsize); } /* - * ext4_seek_hole() retrieves the offset for SEEK_HOLE + * ext4_seek_hole() retrieves the offset for SEEK_HOLE. */ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize) { struct inode *inode = file->f_mapping->host; - struct fiemap_extent_info fie; - struct fiemap_extent ext[2]; - loff_t next; - int i, ret = 0; + struct ext4_map_blocks map; + struct extent_status es; + ext4_lblk_t start, last, end; + loff_t holeoff, isize; + int blkbits; + int ret = 0; mutex_lock(&inode->i_mutex); - if (offset >= inode->i_size) { + + isize = i_size_read(inode); + if (offset >= isize) { mutex_unlock(&inode->i_mutex); return -ENXIO; } - fie.fi_flags = 0; - fie.fi_extents_max = 2; - fie.fi_extents_start = (struct fiemap_extent __user *)&ext; - while (1) { - mm_segment_t old_fs = get_fs(); - - fie.fi_extents_mapped = 0; - memset(ext, 0, sizeof(*ext)); + blkbits = inode->i_sb->s_blocksize_bits; + start = offset >> blkbits; + last = start; + end = isize >> blkbits; + holeoff = offset; - set_fs(get_ds()); - ret = ext4_fiemap(inode, &fie, offset, maxsize - offset); - set_fs(old_fs); - if (ret) - break; + do { + map.m_lblk = last; + map.m_len = end - last + 1; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) { + last += ret; + holeoff = (loff_t)last << blkbits; + continue; + } - /* No extents found */ - if (!fie.fi_extents_mapped) - break; + /* + * If there is a delay extent at this offset, + * we will skip this extent. + */ + ext4_es_find_delayed_extent_range(inode, last, last, &es); + if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) { + last = es.es_lblk + es.es_len; + holeoff = (loff_t)last << blkbits; + continue; + } - for (i = 0; i < fie.fi_extents_mapped; i++) { - next = (loff_t)(ext[i].fe_logical + ext[i].fe_length); - /* - * If extent is not unwritten, then it contains valid - * data, mapped or delayed. - */ - if (!(ext[i].fe_flags & FIEMAP_EXTENT_UNWRITTEN)) { - if (offset < (loff_t)ext[i].fe_logical) - goto out; - offset = next; + /* + * If there is a unwritten extent at this offset, + * it will be as a data or a hole according to page + * cache that has data or not. + */ + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int unwritten; + unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE, + &map, &holeoff); + if (!unwritten) { + last += ret; + holeoff = (loff_t)last << blkbits; continue; } - /* - * If there is a unwritten extent at this offset, - * it will be as a data or a hole according to page - * cache that has data or not. - */ - if (ext4_find_unwritten_pgoff(inode, SEEK_HOLE, - next, &offset)) - goto out; - - offset = next; - if (ext[i].fe_flags & FIEMAP_EXTENT_LAST) - goto out; } - } - if (offset > inode->i_size) - offset = inode->i_size; -out: + + /* find a hole */ + break; + } while (last <= end); + mutex_unlock(&inode->i_mutex); - if (ret) - return ret; - return vfs_setpos(file, offset, maxsize); + if (holeoff > isize) + holeoff = isize; + + return vfs_setpos(file, holeoff, maxsize); } /* diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index bf76f405a5f9..8a8ec6293b19 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -24,6 +24,18 @@ int ext4_resize_begin(struct super_block *sb) return -EPERM; /* + * If we are not using the primary superblock/GDT copy don't resize, + * because the user tools have no way of handling this. Probably a + * bad time to do it anyways. + */ + if (EXT4_SB(sb)->s_sbh->b_blocknr != + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + ext4_warning(sb, "won't resize using backup superblock at %llu", + (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); + return -EPERM; + } + + /* * We are not allowed to do online-resizing on a filesystem mounted * with error, because it can destroy the filesystem easily. */ @@ -758,18 +770,6 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n", gdb_num); - /* - * If we are not using the primary superblock/GDT copy don't resize, - * because the user tools have no way of handling this. Probably a - * bad time to do it anyways. - */ - if (EXT4_SB(sb)->s_sbh->b_blocknr != - le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { - ext4_warning(sb, "won't resize using backup superblock at %llu", - (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); - return -EPERM; - } - gdb_bh = sb_bread(sb, gdblock); if (!gdb_bh) return -EIO; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 43c92b1685cb..ac64edbe501d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1046,10 +1046,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id); static int ext4_quota_off(struct super_block *sb, int type); -static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); @@ -1084,16 +1081,6 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; - -static const struct quotactl_ops ext4_qctl_sysfile_operations = { - .quota_on_meta = ext4_quota_on_sysfile, - .quota_off = ext4_quota_off_sysfile, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk -}; #endif static const struct super_operations ext4_sops = { @@ -3482,7 +3469,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) - ext4_warning(sb, KERN_INFO "metadata_csum and uninit_bg are " + ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); /* Check for a known checksum algorithm */ @@ -3935,7 +3922,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - sb->s_qcop = &ext4_qctl_sysfile_operations; + sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; @@ -5288,21 +5275,6 @@ static int ext4_enable_quotas(struct super_block *sb) return 0; } -/* - * quota_on function that is used when QUOTA feature is set. - */ -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* - * USAGE was enabled at mount time. Only need to enable LIMITS now. - */ - return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); -} - static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -5329,18 +5301,6 @@ out: return dquot_quota_off(sb, type); } -/* - * quota_off function that is used when QUOTA feature is set. - */ -static int ext4_quota_off_sysfile(struct super_block *sb, int type) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* Disable only the limits. */ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) diff --git a/fs/fcntl.c b/fs/fcntl.c index 99d440a4a6ba..ee85cd4e136a 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -740,14 +740,15 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( + BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | O_APPEND | /* O_NONBLOCK | */ __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH | __O_TMPFILE + __FMODE_EXEC | O_PATH | __O_TMPFILE | + __FMODE_NONOTIFY )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ba1107977f2e..ed19a7d622fa 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -131,6 +131,13 @@ static void fuse_req_init_context(struct fuse_req *req) req->in.h.pid = current->pid; } +void fuse_set_initialized(struct fuse_conn *fc) +{ + /* Make sure stores before this are seen on another CPU */ + smp_wmb(); + fc->initialized = 1; +} + static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) { return !fc->initialized || (for_background && fc->blocked); @@ -155,6 +162,8 @@ static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages, if (intr) goto out; } + /* Matches smp_wmb() in fuse_set_initialized() */ + smp_rmb(); err = -ENOTCONN; if (!fc->connected) @@ -253,6 +262,8 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc, atomic_inc(&fc->num_waiting); wait_event(fc->blocked_waitq, fc->initialized); + /* Matches smp_wmb() in fuse_set_initialized() */ + smp_rmb(); req = fuse_request_alloc(0); if (!req) req = get_reserved_req(fc, file); @@ -511,6 +522,39 @@ void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req) } EXPORT_SYMBOL_GPL(fuse_request_send); +static void fuse_adjust_compat(struct fuse_conn *fc, struct fuse_args *args) +{ + if (fc->minor < 4 && args->in.h.opcode == FUSE_STATFS) + args->out.args[0].size = FUSE_COMPAT_STATFS_SIZE; + + if (fc->minor < 9) { + switch (args->in.h.opcode) { + case FUSE_LOOKUP: + case FUSE_CREATE: + case FUSE_MKNOD: + case FUSE_MKDIR: + case FUSE_SYMLINK: + case FUSE_LINK: + args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; + break; + case FUSE_GETATTR: + case FUSE_SETATTR: + args->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; + break; + } + } + if (fc->minor < 12) { + switch (args->in.h.opcode) { + case FUSE_CREATE: + args->in.args[0].size = sizeof(struct fuse_open_in); + break; + case FUSE_MKNOD: + args->in.args[0].size = FUSE_COMPAT_MKNOD_IN_SIZE; + break; + } + } +} + ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args) { struct fuse_req *req; @@ -520,6 +564,9 @@ ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args) if (IS_ERR(req)) return PTR_ERR(req); + /* Needs to be done after fuse_get_req() so that fc->minor is valid */ + fuse_adjust_compat(fc, args); + req->in.h.opcode = args->in.h.opcode; req->in.h.nodeid = args->in.h.nodeid; req->in.numargs = args->in.numargs; @@ -2127,7 +2174,7 @@ void fuse_abort_conn(struct fuse_conn *fc) if (fc->connected) { fc->connected = 0; fc->blocked = 0; - fc->initialized = 1; + fuse_set_initialized(fc); end_io_requests(fc); end_queued_requests(fc); end_polls(fc); @@ -2146,7 +2193,7 @@ int fuse_dev_release(struct inode *inode, struct file *file) spin_lock(&fc->lock); fc->connected = 0; fc->blocked = 0; - fc->initialized = 1; + fuse_set_initialized(fc); end_queued_requests(fc); end_polls(fc); wake_up_all(&fc->blocked_waitq); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 252b8a5de8b5..08e7b1a9d5d0 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -156,10 +156,7 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, args->in.args[0].size = name->len + 1; args->in.args[0].value = name->name; args->out.numargs = 1; - if (fc->minor < 9) - args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; - else - args->out.args[0].size = sizeof(struct fuse_entry_out); + args->out.args[0].size = sizeof(struct fuse_entry_out); args->out.args[0].value = outarg; } @@ -422,16 +419,12 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, args.in.h.opcode = FUSE_CREATE; args.in.h.nodeid = get_node_id(dir); args.in.numargs = 2; - args.in.args[0].size = fc->minor < 12 ? sizeof(struct fuse_open_in) : - sizeof(inarg); + args.in.args[0].size = sizeof(inarg); args.in.args[0].value = &inarg; args.in.args[1].size = entry->d_name.len + 1; args.in.args[1].value = entry->d_name.name; args.out.numargs = 2; - if (fc->minor < 9) - args.out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; - else - args.out.args[0].size = sizeof(outentry); + args.out.args[0].size = sizeof(outentry); args.out.args[0].value = &outentry; args.out.args[1].size = sizeof(outopen); args.out.args[1].value = &outopen; @@ -539,10 +532,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, memset(&outarg, 0, sizeof(outarg)); args->in.h.nodeid = get_node_id(dir); args->out.numargs = 1; - if (fc->minor < 9) - args->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE; - else - args->out.args[0].size = sizeof(outarg); + args->out.args[0].size = sizeof(outarg); args->out.args[0].value = &outarg; err = fuse_simple_request(fc, args); if (err) @@ -592,8 +582,7 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode, inarg.umask = current_umask(); args.in.h.opcode = FUSE_MKNOD; args.in.numargs = 2; - args.in.args[0].size = fc->minor < 12 ? FUSE_COMPAT_MKNOD_IN_SIZE : - sizeof(inarg); + args.in.args[0].size = sizeof(inarg); args.in.args[0].value = &inarg; args.in.args[1].size = entry->d_name.len + 1; args.in.args[1].value = entry->d_name.name; @@ -899,10 +888,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, args.in.args[0].size = sizeof(inarg); args.in.args[0].value = &inarg; args.out.numargs = 1; - if (fc->minor < 9) - args.out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; - else - args.out.args[0].size = sizeof(outarg); + args.out.args[0].size = sizeof(outarg); args.out.args[0].value = &outarg; err = fuse_simple_request(fc, &args); if (!err) { @@ -1574,10 +1560,7 @@ static void fuse_setattr_fill(struct fuse_conn *fc, struct fuse_args *args, args->in.args[0].size = sizeof(*inarg_p); args->in.args[0].value = inarg_p; args->out.numargs = 1; - if (fc->minor < 9) - args->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE; - else - args->out.args[0].size = sizeof(*outarg_p); + args->out.args[0].size = sizeof(*outarg_p); args->out.args[0].value = outarg_p; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e0fc6725d1d0..1cdfb07c1376 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -906,4 +906,6 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc); int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct file *file); +void fuse_set_initialized(struct fuse_conn *fc); + #endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6749109f255d..f38256e4476e 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -424,8 +424,7 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf) args.in.h.opcode = FUSE_STATFS; args.in.h.nodeid = get_node_id(dentry->d_inode); args.out.numargs = 1; - args.out.args[0].size = - fc->minor < 4 ? FUSE_COMPAT_STATFS_SIZE : sizeof(outarg); + args.out.args[0].size = sizeof(outarg); args.out.args[0].value = &outarg; err = fuse_simple_request(fc, &args); if (!err) @@ -898,7 +897,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->max_write = max_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } - fc->initialized = 1; + fuse_set_initialized(fc); wake_up_all(&fc->blocked_waitq); } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c8b148bbdc8b..3e193cb36996 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -667,7 +667,7 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, s64 change, struct gfs2_quota_data *qd, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct inode *inode = &ip->i_inode; struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -697,16 +697,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, be64_add_cpu(&q.qu_value, change); qd->qd_qb.qb_value = q.qu_value; if (fdq) { - if (fdq->d_fieldmask & FS_DQ_BSOFT) { - q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_SOFT) { + q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_warn = q.qu_warn; } - if (fdq->d_fieldmask & FS_DQ_BHARD) { - q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_HARD) { + q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_limit = q.qu_limit; } - if (fdq->d_fieldmask & FS_DQ_BCOUNT) { - q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPACE) { + q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_value = q.qu_value; } } @@ -1497,7 +1497,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb, } static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_lvb *qlvb; @@ -1505,7 +1505,7 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, struct gfs2_holder q_gh; int error; - memset(fdq, 0, sizeof(struct fs_disk_quota)); + memset(fdq, 0, sizeof(*fdq)); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ @@ -1522,12 +1522,9 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, goto out; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; - fdq->d_version = FS_DQUOT_VERSION; - fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA; - fdq->d_id = from_kqid_munged(current_user_ns(), qid); - fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift; - fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift; - fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift; + fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift; + fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift; + fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift; gfs2_glock_dq_uninit(&q_gh); out: @@ -1536,10 +1533,10 @@ out: } /* GFS2 only supports a subset of the XFS fields */ -#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT) +#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE) static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); @@ -1583,17 +1580,17 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, goto out_i; /* If nothing has changed, this is a no-op */ - if ((fdq->d_fieldmask & FS_DQ_BSOFT) && - ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) - fdq->d_fieldmask ^= FS_DQ_BSOFT; + if ((fdq->d_fieldmask & QC_SPC_SOFT) && + ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) + fdq->d_fieldmask ^= QC_SPC_SOFT; - if ((fdq->d_fieldmask & FS_DQ_BHARD) && - ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) - fdq->d_fieldmask ^= FS_DQ_BHARD; + if ((fdq->d_fieldmask & QC_SPC_HARD) && + ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) + fdq->d_fieldmask ^= QC_SPC_HARD; - if ((fdq->d_fieldmask & FS_DQ_BCOUNT) && - ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value))) - fdq->d_fieldmask ^= FS_DQ_BCOUNT; + if ((fdq->d_fieldmask & QC_SPACE) && + ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value))) + fdq->d_fieldmask ^= QC_SPACE; if (fdq->d_fieldmask == 0) goto out_i; diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..f30872ade6d7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif - + inode->i_flctx = NULL; this_cpu_inc(nr_inodes); return 0; @@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode) BUG_ON(inode_has_buffers(inode)); security_inode_free(inode); fsnotify_inode_delete(inode); + locks_free_lock_context(inode->i_flctx); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index bb63254ed848..735d7522a3a9 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -362,6 +362,9 @@ repeat: rs.cont_size = isonum_733(rr->u.CE.size); break; case SIG('E', 'R'): + /* Invalid length of ER tag id? */ + if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len) + goto out; ISOFS_SB(inode->i_sb)->s_rock = 1; printk(KERN_DEBUG "ISO 9660 Extensions: "); { diff --git a/fs/isofs/util.c b/fs/isofs/util.c index 01e1ee7a998b..005a15cfd30a 100644 --- a/fs/isofs/util.c +++ b/fs/isofs/util.c @@ -2,6 +2,7 @@ * linux/fs/isofs/util.c */ +#include <linux/time.h> #include "isofs.h" /* @@ -17,9 +18,9 @@ int iso_date(char * p, int flag) { int year, month, day, hour, minute, second, tz; - int crtime, days, i; + int crtime; - year = p[0] - 70; + year = p[0]; month = p[1]; day = p[2]; hour = p[3]; @@ -31,18 +32,7 @@ int iso_date(char * p, int flag) if (year < 0) { crtime = 0; } else { - int monlen[12] = {31,28,31,30,31,30,31,31,30,31,30,31}; - - days = year * 365; - if (year > 2) - days += (year+1) / 4; - for (i = 1; i < month; i++) - days += monlen[i-1]; - if (((year+2) % 4) == 0 && month > 2) - days++; - days += day - 1; - crtime = ((((days * 24) + hour) * 60 + minute) * 60) - + second; + crtime = mktime64(year+1900, month, day, hour, minute, second); /* sign extend */ if (tz & 0x80) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 37989f02a226..2d881b381d2b 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -201,10 +201,14 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns) static int kernfs_name_compare(unsigned int hash, const char *name, const void *ns, const struct kernfs_node *kn) { - if (hash != kn->hash) - return hash - kn->hash; - if (ns != kn->ns) - return ns - kn->ns; + if (hash < kn->hash) + return -1; + if (hash > kn->hash) + return 1; + if (ns < kn->ns) + return -1; + if (ns > kn->ns) + return 1; return strcmp(name, kn->name); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index e94c887da2d7..55505cbe11af 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -138,10 +138,6 @@ lockd(void *vrqstp) dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); - if (!nlm_timeout) - nlm_timeout = LOCKD_DFLT_TIMEO; - nlmsvc_timeout = nlm_timeout * HZ; - /* * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. @@ -350,6 +346,10 @@ static struct svc_serv *lockd_create_svc(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); + if (!nlm_timeout) + nlm_timeout = LOCKD_DFLT_TIMEO; + nlmsvc_timeout = nlm_timeout * HZ; + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, svc_rpcb_cleanup); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d12ff4e2dbe7..665ef5a05183 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; struct nlm_host *lockhost; + if (!flctx || list_empty_careful(&flctx->flc_posix)) + return 0; again: file->f_locks = 0; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -180,7 +183,7 @@ again: if (match(lockhost, host)) { struct file_lock lock = *fl; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; @@ -192,7 +195,7 @@ again: goto again; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 0; } @@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { - if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); - return 1; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_lmops == &nlmsvc_lock_operations) { + spin_unlock(&flctx->flc_lock); + return 1; + } } + spin_unlock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); file->f_locks = 0; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 735b8d3fa78c..4d0d41163a50 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -157,14 +157,11 @@ static int target_leasetype(struct file_lock *fl) int leases_enable = 1; int lease_break_time = 45; -#define for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next) - /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via * the file_lock_lglock. Note that alterations to the list also require that - * the relevant i_lock is held. + * the relevant flc_lock is held. */ DEFINE_STATIC_LGLOCK(file_lock_lglock); static DEFINE_PER_CPU(struct hlist_head, file_lock_list); @@ -192,21 +189,68 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); * contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, - * we often hold the i_lock as well. In certain cases, when reading the fields + * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the - * i_lock. + * flc_lock. * * In particular, adding an entry to the fl_block list requires that you hold - * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting - * an entry from the list however only requires the file_lock_lock. + * both the flc_lock and the blocked_lock_lock (acquired in that order). + * Deleting an entry from the list however only requires the file_lock_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); +static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; +static struct file_lock_context * +locks_get_lock_context(struct inode *inode) +{ + struct file_lock_context *new; + + if (likely(inode->i_flctx)) + goto out; + + new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!new) + 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); + + /* + * Assign the pointer if it's not already assigned. If it is, then + * free the context we just allocated. + */ + spin_lock(&inode->i_lock); + if (likely(!inode->i_flctx)) { + inode->i_flctx = new; + new = NULL; + } + spin_unlock(&inode->i_lock); + + if (new) + kmem_cache_free(flctx_cache, new); +out: + return inode->i_flctx; +} + +void +locks_free_lock_context(struct file_lock_context *ctx) +{ + if (ctx) { + WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); + WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); + kmem_cache_free(flctx_cache, ctx); + } +} + static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); + INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_block); init_waitqueue_head(&fl->fl_wait); } @@ -243,6 +287,7 @@ EXPORT_SYMBOL_GPL(locks_release_private); void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_block)); BUG_ON(!hlist_unhashed(&fl->fl_link)); @@ -257,8 +302,8 @@ locks_dispose_list(struct list_head *dispose) struct file_lock *fl; while (!list_empty(dispose)) { - fl = list_first_entry(dispose, struct file_lock, fl_block); - list_del_init(&fl->fl_block); + fl = list_first_entry(dispose, struct file_lock, fl_list); + list_del_init(&fl->fl_list); locks_free_lock(fl); } } @@ -513,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) return fl1->fl_owner == fl2->fl_owner; } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { lg_local_lock(&file_lock_lglock); @@ -522,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl) lg_local_unlock(&file_lock_lglock); } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { /* * Avoid taking lock if already unhashed. This is safe since this check - * is done while holding the i_lock, and new insertions into the list + * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) @@ -579,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter) * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * - * Must be called with both the i_lock and blocked_lock_lock held. The fl_block - * list itself is protected by the blocked_lock_lock, but by ensuring that the - * i_lock is also held on insertions we can avoid taking the blocked_lock_lock - * in some cases when we see that the fl_block list is empty. + * Must be called with both the flc_lock and blocked_lock_lock held. The + * fl_block list itself is protected by the blocked_lock_lock, but by ensuring + * that the flc_lock is also held on insertions we can avoid taking the + * blocked_lock_lock in some cases when we see that the fl_block list is empty. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) @@ -594,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker, locks_insert_global_blocked(waiter); } -/* Must be called with i_lock held. */ +/* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) { @@ -606,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker, /* * Wake up processes blocked waiting for blocker. * - * Must be called with the inode->i_lock held! + * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new - * blocked requests are only added to the list under the i_lock, and - * the i_lock is always held here. Note that removal from the fl_block - * list does not require the i_lock, so we must recheck list_empty() + * blocked requests are only added to the list under the flc_lock, and + * the flc_lock is always held here. Note that removal from the fl_block + * list does not require the flc_lock, so we must recheck list_empty() * after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_block)) @@ -635,63 +680,36 @@ static void locks_wake_up_blocks(struct file_lock *blocker) spin_unlock(&blocked_lock_lock); } -/* Insert file lock fl into an inode's lock list at the position indicated - * by pos. At the same time add the lock to the global file lock list. - * - * Must be called with the i_lock held! - */ -static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) +static void +locks_insert_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *before) { fl->fl_nspid = get_pid(task_tgid(current)); - - /* insert into file's list */ - fl->fl_next = *pos; - *pos = fl; - + list_add_tail(&fl->fl_list, before); + ++*counter; locks_insert_global_locks(fl); } -/** - * locks_delete_lock - Delete a lock and then free it. - * @thisfl_p: pointer that points to the fl_next field of the previous - * inode->i_flock list entry - * - * Unlink a lock from all lists and free the namespace reference, but don't - * free it yet. Wake up processes that are blocked waiting for this lock and - * notify the FS that the lock has been cleared. - * - * Must be called with the i_lock held! - */ -static void locks_unlink_lock(struct file_lock **thisfl_p) +static void +locks_unlink_lock_ctx(struct file_lock *fl, int *counter) { - struct file_lock *fl = *thisfl_p; - locks_delete_global_locks(fl); - - *thisfl_p = fl->fl_next; - fl->fl_next = NULL; - + list_del_init(&fl->fl_list); + --*counter; if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; } - locks_wake_up_blocks(fl); } -/* - * Unlink a lock from all lists and free it. - * - * Must be called with i_lock held! - */ -static void locks_delete_lock(struct file_lock **thisfl_p, - struct list_head *dispose) +static void +locks_delete_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *dispose) { - struct file_lock *fl = *thisfl_p; - - locks_unlink_lock(thisfl_p); + locks_unlink_lock_ctx(fl, counter); if (dispose) - list_add(&fl->fl_block, dispose); + list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } @@ -746,22 +764,27 @@ void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + struct file_lock_context *ctx; struct inode *inode = file_inode(filp); - spin_lock(&inode->i_lock); - for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) { - if (!IS_POSIX(cfl)) - continue; - if (posix_locks_conflict(fl, cfl)) - break; - } - if (cfl) { - locks_copy_conflock(fl, cfl); - if (cfl->fl_nspid) - fl->fl_pid = pid_vnr(cfl->fl_nspid); - } else + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; - spin_unlock(&inode->i_lock); + return; + } + + spin_lock(&ctx->flc_lock); + list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { + if (posix_locks_conflict(fl, cfl)) { + locks_copy_conflock(fl, cfl); + if (cfl->fl_nspid) + fl->fl_pid = pid_vnr(cfl->fl_nspid); + goto out; + } + } + fl->fl_type = F_UNLCK; +out: + spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); @@ -845,34 +868,34 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, static int flock_lock_file(struct file *filp, struct file_lock *request) { struct file_lock *new_fl = NULL; - struct file_lock **before; - struct inode * inode = file_inode(filp); + struct file_lock *fl; + struct file_lock_context *ctx; + struct inode *inode = file_inode(filp); int error = 0; - int found = 0; + bool found = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (filp != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; - found = 1; - locks_delete_lock(before, &dispose); + found = true; + locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose); break; } @@ -887,18 +910,13 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) { - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); cond_resched(); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); } find_conflict: - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; @@ -911,12 +929,12 @@ find_conflict: if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock); new_fl = NULL; error = 0; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -925,16 +943,20 @@ out: static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { - struct file_lock *fl; + struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; - struct file_lock **before; + struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. @@ -948,15 +970,14 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { - for_each_lock(inode, before) { - fl = *before; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!IS_POSIX(fl)) continue; if (!posix_locks_conflict(request, fl)) @@ -986,29 +1007,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (request->fl_flags & FL_ACCESS) goto out; - /* - * Find the first old lock with the same owner as the new lock. - */ - - before = &inode->i_flock; - - /* First skip locks owned by other processes. */ - while ((fl = *before) && (!IS_POSIX(fl) || - !posix_same_owner(request, fl))) { - before = &fl->fl_next; + /* Find the first old lock with the same owner as the new lock */ + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { + if (posix_same_owner(request, fl)) + break; } /* Process locks with this owner. */ - while ((fl = *before) && posix_same_owner(request, fl)) { - /* Detect adjacent or overlapping regions (if same lock type) - */ + list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { + if (!posix_same_owner(request, fl)) + break; + + /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) - goto next_lock; + continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ @@ -1029,18 +1046,18 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt, + &dispose); continue; } request = fl; added = true; - } - else { + } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) - goto next_lock; + continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) @@ -1059,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); continue; } /* @@ -1075,15 +1093,13 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_delete_lock(before, &dispose); - locks_insert_lock(before, request); + locks_insert_lock_ctx(request, + &ctx->flc_posix_cnt, &fl->fl_list); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); added = true; } } - /* Go on to next lock. - */ - next_lock: - before = &fl->fl_next; } /* @@ -1108,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt, + &fl->fl_list); new_fl = NULL; } if (right) { @@ -1119,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock(before, left); + locks_insert_lock_ctx(left, &ctx->flc_posix_cnt, + &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1129,7 +1147,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); /* * Free any unused locks. */ @@ -1199,22 +1217,29 @@ EXPORT_SYMBOL(posix_lock_file_wait); */ int locks_mandatory_locked(struct file *file) { + int ret; struct inode *inode = file_inode(file); + struct file_lock_context *ctx; struct file_lock *fl; + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) + return 0; + /* * Search the lock list for this inode for any POSIX locks. */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!IS_POSIX(fl)) - continue; + spin_lock(&ctx->flc_lock); + ret = 0; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && - fl->fl_owner != file) + fl->fl_owner != file) { + ret = -EAGAIN; break; + } } - spin_unlock(&inode->i_lock); - return fl ? -EAGAIN : 0; + spin_unlock(&ctx->flc_lock); + return ret; } /** @@ -1294,9 +1319,9 @@ static void lease_clear_pending(struct file_lock *fl, int arg) } /* We already had a lease on this file; just change its type */ -int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) +int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { - struct file_lock *fl = *before; + struct file_lock_context *flctx; int error = assign_type(fl, arg); if (error) @@ -1306,6 +1331,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) if (arg == F_UNLCK) { struct file *filp = fl->fl_file; + flctx = file_inode(filp)->i_flctx; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); @@ -1313,7 +1339,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock(before, dispose); + locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose); } return 0; } @@ -1329,20 +1355,17 @@ static bool past_time(unsigned long then) static void time_out_leases(struct inode *inode, struct list_head *dispose) { - struct file_lock **before; - struct file_lock *fl; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); - before = &inode->i_flock; - while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(before, F_RDLCK, dispose); + lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(before, F_UNLCK, dispose); - if (fl == *before) /* lease_modify may have freed fl */ - before = &fl->fl_next; + lease_modify(fl, F_UNLCK, dispose); } } @@ -1356,11 +1379,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { + struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); - for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } @@ -1384,7 +1408,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock *new_fl; - struct file_lock *fl, **before; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1394,7 +1419,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return PTR_ERR(new_fl); new_fl->fl_flags = type; - spin_lock(&inode->i_lock); + /* typically we will check that ctx is non-NULL before calling */ + if (!ctx) { + WARN_ON_ONCE(1); + return error; + } + + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1408,9 +1439,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { @@ -1419,17 +1448,17 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { - if (lease_breaking(inode->i_flock)) + if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt, + &dispose); } - fl = inode->i_flock; - if (!fl || !IS_LEASE(fl)) + if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { @@ -1439,18 +1468,19 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) } restart: - break_time = inode->i_flock->fl_break_time; + fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); + break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; - locks_insert_block(inode->i_flock, new_fl); + locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { @@ -1462,12 +1492,10 @@ restart: time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; - error = 0; } - out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1487,14 +1515,18 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock *flock; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; - if (inode->i_flock) { - spin_lock(&inode->i_lock); - flock = inode->i_flock; - if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK)) - has_lease = true; - spin_unlock(&inode->i_lock); + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&ctx->flc_lock); + if (!list_empty(&ctx->flc_lease)) { + fl = list_first_entry(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl->fl_type == F_WRLCK) + has_lease = true; + } + spin_unlock(&ctx->flc_lock); } if (has_lease) @@ -1532,20 +1564,22 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; int type = F_UNLCK; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(file_inode(filp), &dispose); - for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl); - fl = fl->fl_next) { - if (fl->fl_file == filp) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&ctx->flc_lock); + time_out_leases(file_inode(filp), &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file != filp) + continue; type = target_leasetype(fl); break; } + spin_unlock(&ctx->flc_lock); + locks_dispose_list(&dispose); } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); return type; } @@ -1578,9 +1612,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg) static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct file_lock *fl, **before, **my_before = NULL, *lease; + struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); @@ -1588,6 +1623,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock @@ -1606,7 +1645,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg); if (error) @@ -1621,13 +1660,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * except for this filp. */ error = -EAGAIN; - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { - my_before = before; + my_fl = fl; continue; } + /* * No exclusive leases if someone else has a lease on * this file: @@ -1642,9 +1680,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr goto out; } - if (my_before != NULL) { - lease = *my_before; - error = lease->fl_lmops->lm_change(my_before, arg, &dispose); + if (my_fl != NULL) { + error = lease->fl_lmops->lm_change(my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1654,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock(before, lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1666,45 +1703,49 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr */ smp_mb(); error = check_conflicting_open(dentry, arg); - if (error) - goto out_unlink; + if (error) { + locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt); + goto out; + } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); - if (!error && !my_before) + if (!error && !my_fl) *flp = NULL; return error; -out_unlink: - locks_unlink_lock(before); - goto out; } static int generic_delete_lease(struct file *filp) { int error = -EAGAIN; - struct file_lock *fl, **before; + 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; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(inode, &dispose); - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { - if (fl->fl_file == filp) + if (!ctx) { + trace_generic_delete_lease(inode, NULL); + return error; + } + + spin_lock(&ctx->flc_lock); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp) { + victim = fl; break; + } } trace_generic_delete_lease(inode, fl); - if (fl) - error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + if (victim) + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; } @@ -2171,7 +2212,7 @@ again: */ /* * we need that spin_lock here - it prevents reordering between - * update of inode->i_flock and check for it done in close(). + * update of i_flctx->flc_posix and check for it done in close(). * rcu_read_lock() wouldn't do. */ spin_lock(¤t->files->file_lock); @@ -2331,13 +2372,14 @@ 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; /* * 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. */ - if (!file_inode(filp)->i_flock) + if (!ctx || list_empty(&ctx->flc_posix)) return; lock.fl_type = F_UNLCK; @@ -2358,67 +2400,67 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) EXPORT_SYMBOL(locks_remove_posix); +/* The i_flctx must be valid when calling into here */ +static void +locks_remove_flock(struct file *filp) +{ + struct file_lock fl = { + .fl_owner = filp, + .fl_pid = current->tgid, + .fl_file = filp, + .fl_flags = FL_FLOCK, + .fl_type = F_UNLCK, + .fl_end = OFFSET_MAX, + }; + struct file_lock_context *flctx = file_inode(filp)->i_flctx; + + if (list_empty(&flctx->flc_flock)) + return; + + if (filp->f_op->flock) + filp->f_op->flock(filp, F_SETLKW, &fl); + else + flock_lock_file(filp, &fl); + + if (fl.fl_ops && fl.fl_ops->fl_release_private) + fl.fl_ops->fl_release_private(&fl); +} + +/* The i_flctx must be valid when calling into here */ +static void +locks_remove_lease(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; + LIST_HEAD(dispose); + + if (list_empty(&ctx->flc_lease)) + return; + + spin_lock(&ctx->flc_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + lease_modify(fl, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); + locks_dispose_list(&dispose); +} + /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { - struct inode * inode = file_inode(filp); - struct file_lock *fl; - struct file_lock **before; - LIST_HEAD(dispose); - - if (!inode->i_flock) + if (!file_inode(filp)->i_flctx) return; + /* remove any OFD locks */ locks_remove_posix(filp, filp); - if (filp->f_op->flock) { - struct file_lock fl = { - .fl_owner = filp, - .fl_pid = current->tgid, - .fl_file = filp, - .fl_flags = FL_FLOCK, - .fl_type = F_UNLCK, - .fl_end = OFFSET_MAX, - }; - filp->f_op->flock(filp, F_SETLKW, &fl); - if (fl.fl_ops && fl.fl_ops->fl_release_private) - fl.fl_ops->fl_release_private(&fl); - } - - spin_lock(&inode->i_lock); - before = &inode->i_flock; - - while ((fl = *before) != NULL) { - if (fl->fl_file == filp) { - if (IS_LEASE(fl)) { - lease_modify(before, F_UNLCK, &dispose); - continue; - } - - /* - * There's a leftover lock on the list of a type that - * we didn't expect to see. Most likely a classic - * POSIX lock that ended up not getting released - * properly, or that raced onto the list somehow. Log - * some info about it and then just remove it from - * the list. - */ - WARN(!IS_FLOCK(fl), - "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), inode->i_ino, - fl->fl_type, fl->fl_flags, - fl->fl_start, fl->fl_end); + /* remove flock locks */ + locks_remove_flock(filp); - locks_delete_lock(before, &dispose); - continue; - } - before = &fl->fl_next; - } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); + /* remove any leases */ + locks_remove_lease(filp); } /** @@ -2621,6 +2663,9 @@ static int __init filelock_init(void) { int i; + flctx_cache = kmem_cache_create("file_lock_ctx", + sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); + filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7f3f60641344..8cdb2b28a104 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,25 +85,30 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ { struct inode *inode = state->inode; struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; int status = 0; - if (inode->i_flock == NULL) + if (flctx == NULL) goto out; - /* Protect inode->i_flock using the i_lock */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) - continue; + list = &flctx->flc_posix; + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = nfs4_lock_delegation_recall(fl, state, stateid); if (status < 0) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); out: return status; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 10bf07280f4a..294692ff83b1 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -212,6 +212,12 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { + struct inode *inode = iocb->ki_filp->f_mapping->host; + + /* we only support swap file calling nfs_direct_IO */ + if (!IS_SWAPFILE(inode)) + return 0; + #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp, (long long) pos, iter->nr_segs); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 4bffe637ea32..2211f6ba8736 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -352,8 +352,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_attr_check_mountpoint(sb, fattr); - if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) && - !nfs_attr_use_mounted_on_fileid(fattr)) + if (nfs_attr_use_mounted_on_fileid(fattr)) + fattr->fileid = fattr->mounted_on_fileid; + else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index efaa31c70fbe..b6f34bfa6fe8 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -31,8 +31,6 @@ static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; - - fattr->fileid = fattr->mounted_on_fileid; return 1; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 03311259b0c4..706ad10b8186 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -228,6 +228,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp) kfree(clp->cl_serverowner); kfree(clp->cl_serverscope); kfree(clp->cl_implid); + kfree(clp->cl_owner_id); } void nfs4_free_client(struct nfs_client *clp) @@ -452,6 +453,14 @@ static void nfs4_swap_callback_idents(struct nfs_client *keep, spin_unlock(&nn->nfs_client_lock); } +static bool nfs4_match_client_owner_id(const struct nfs_client *clp1, + const struct nfs_client *clp2) +{ + if (clp1->cl_owner_id == NULL || clp2->cl_owner_id == NULL) + return true; + return strcmp(clp1->cl_owner_id, clp2->cl_owner_id) == 0; +} + /** * nfs40_walk_client_list - Find server that recognizes a client ID * @@ -483,9 +492,6 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->rpc_ops != new->rpc_ops) continue; - if (pos->cl_proto != new->cl_proto) - continue; - if (pos->cl_minorversion != new->cl_minorversion) continue; @@ -510,6 +516,9 @@ int nfs40_walk_client_list(struct nfs_client *new, if (pos->cl_clientid != new->cl_clientid) continue; + if (!nfs4_match_client_owner_id(pos, new)) + continue; + atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -566,20 +575,14 @@ static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b) } /* - * Returns true if the server owners match + * Returns true if the server major ids match */ static bool -nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b) +nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b) { struct nfs41_server_owner *o1 = a->cl_serverowner; struct nfs41_server_owner *o2 = b->cl_serverowner; - if (o1->minor_id != o2->minor_id) { - dprintk("NFS: --> %s server owner minor IDs do not match\n", - __func__); - return false; - } - if (o1->major_id_sz != o2->major_id_sz) goto out_major_mismatch; if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0) @@ -621,9 +624,6 @@ int nfs41_walk_client_list(struct nfs_client *new, if (pos->rpc_ops != new->rpc_ops) continue; - if (pos->cl_proto != new->cl_proto) - continue; - if (pos->cl_minorversion != new->cl_minorversion) continue; @@ -639,7 +639,7 @@ int nfs41_walk_client_list(struct nfs_client *new, prev = pos; status = nfs_wait_client_init_complete(pos); - if (status == 0) { + if (pos->cl_cons_state == NFS_CS_SESSION_INITING) { nfs4_schedule_lease_recovery(pos); status = nfs4_wait_clnt_recover(pos); } @@ -654,7 +654,19 @@ int nfs41_walk_client_list(struct nfs_client *new, if (!nfs4_match_clientids(pos, new)) continue; - if (!nfs4_match_serverowners(pos, new)) + /* + * Note that session trunking is just a special subcase of + * client id trunking. In either case, we want to fall back + * to using the existing nfs_client. + */ + if (!nfs4_check_clientid_trunking(pos, new)) + continue; + + /* Unlike NFSv4.0, we know that NFSv4.1 always uses the + * uniform string, however someone might switch the + * uniquifier string on us. + */ + if (!nfs4_match_client_owner_id(pos, new)) continue; atomic_inc(&pos->cl_count); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e7f8d5ff2581..c347705b0161 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1117,8 +1117,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode) return 0; if ((delegation->type & fmode) != fmode) return 0; - if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags)) - return 0; if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) return 0; nfs_mark_delegation_referenced(delegation); @@ -4917,11 +4915,14 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, } static unsigned int -nfs4_init_nonuniform_client_string(const struct nfs_client *clp, +nfs4_init_nonuniform_client_string(struct nfs_client *clp, char *buf, size_t len) { unsigned int result; + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); + rcu_read_lock(); result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s", clp->cl_ipaddr, @@ -4930,24 +4931,32 @@ nfs4_init_nonuniform_client_string(const struct nfs_client *clp, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_PROTO)); rcu_read_unlock(); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); return result; } static unsigned int -nfs4_init_uniform_client_string(const struct nfs_client *clp, +nfs4_init_uniform_client_string(struct nfs_client *clp, char *buf, size_t len) { const char *nodename = clp->cl_rpcclient->cl_nodename; + unsigned int result; + + if (clp->cl_owner_id != NULL) + return strlcpy(buf, clp->cl_owner_id, len); if (nfs4_client_id_uniquifier[0] != '\0') - return scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", + result = scnprintf(buf, len, "Linux NFSv%u.%u %s/%s", clp->rpc_ops->version, clp->cl_minorversion, nfs4_client_id_uniquifier, nodename); - return scnprintf(buf, len, "Linux NFSv%u.%u %s", + else + result = scnprintf(buf, len, "Linux NFSv%u.%u %s", clp->rpc_ops->version, clp->cl_minorversion, nodename); + clp->cl_owner_id = kstrdup(buf, GFP_KERNEL); + return result; } /* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5194933ed419..a3bb22ab68c5 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1366,49 +1366,55 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct nfs_inode *nfsi = NFS_I(inode); struct file_lock *fl; int status = 0; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; - if (inode->i_flock == NULL) + if (flctx == NULL) return 0; + list = &flctx->flc_posix; + /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - /* Protect inode->i_flock using the BKL */ - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) - continue; + spin_lock(&flctx->flc_lock); +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = ops->recover_lock(state, fl); switch (status) { - case 0: - break; - case -ESTALE: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_NO_GRACE: - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - goto out; - default: - printk(KERN_ERR "NFS: %s: unhandled error %d\n", - __func__, status); - case -ENOMEM: - case -NFS4ERR_DENIED: - case -NFS4ERR_RECLAIM_BAD: - case -NFS4ERR_RECLAIM_CONFLICT: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ - status = 0; + case 0: + break; + case -ESTALE: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_NO_GRACE: + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto out; + default: + pr_err("NFS: %s: unhandled error %d\n", + __func__, status); + case -ENOMEM: + case -NFS4ERR_DENIED: + case -NFS4ERR_RECLAIM_BAD: + case -NFS4ERR_RECLAIM_CONFLICT: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + status = 0; } - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } + spin_unlock(&flctx->flc_lock); out: up_write(&nfsi->rwsem); return status; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2b5e769beb16..29c7f33c9cf1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -826,11 +826,15 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct nfs_pageio_descriptor *pgio) { size_t size; + struct file_lock_context *flctx; if (prev) { if (!nfs_match_open_context(req->wb_context, prev->wb_context)) return false; - if (req->wb_context->dentry->d_inode->i_flock != NULL && + flctx = req->wb_context->dentry->d_inode->i_flctx; + if (flctx != NULL && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock)) && !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e3..4ae66f416eb9 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct nfs_lock_context *l_ctx; + struct file_lock_context *flctx = file_inode(file)->i_flctx; struct nfs_page *req; int do_flush, status; /* @@ -1109,7 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page) do_flush = req->wb_page != page || req->wb_context != ctx; /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; - if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { + if (l_ctx && flctx && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock))) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } @@ -1170,6 +1173,13 @@ out: return PageUptodate(page) != 0; } +static bool +is_whole_file_wrlock(struct file_lock *fl) +{ + return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX && + fl->fl_type == F_WRLCK; +} + /* If we know the page is up to date, and we're not using byte range locks (or * if we have the whole file locked for writing), it may be more efficient to * extend the write to cover the entire page in order to avoid fragmentation @@ -1180,17 +1190,36 @@ out: */ static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) { + int ret; + struct file_lock_context *flctx = inode->i_flctx; + struct file_lock *fl; + if (file->f_flags & O_DSYNC) return 0; if (!nfs_write_pageuptodate(page, inode)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 && - inode->i_flock->fl_end == OFFSET_MAX && - inode->i_flock->fl_type != F_RDLCK)) - return 1; - return 0; + if (!flctx || (list_empty_careful(&flctx->flc_flock) && + list_empty_careful(&flctx->flc_posix))) + return 0; + + /* Check to see if there are whole file write locks */ + ret = 0; + spin_lock(&flctx->flc_lock); + if (!list_empty(&flctx->flc_posix)) { + fl = list_first_entry(&flctx->flc_posix, struct file_lock, + fl_list); + if (is_whole_file_wrlock(fl)) + ret = 1; + } else if (!list_empty(&flctx->flc_flock)) { + fl = list_first_entry(&flctx->flc_flock, struct file_lock, + fl_list); + if (fl->fl_type == F_WRLCK) + ret = 1; + } + spin_unlock(&flctx->flc_lock); + return ret; } /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 3550a9c87616..532a60cca2fb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) } static int -nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose) +nfsd_change_deleg_cb(struct file_lock *onlist, int arg, + struct list_head *dispose) { if (arg & F_UNLCK) return lease_modify(onlist, arg, dispose); @@ -3897,11 +3898,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = nfs4_setlease(dp); goto out; } - atomic_inc(&fp->fi_delegees); if (fp->fi_had_conflict) { status = -EAGAIN; goto out_unlock; } + atomic_inc(&fp->fi_delegees); hash_delegation_locked(dp, fp); status = 0; out_unlock: @@ -5556,10 +5557,11 @@ out_nfserr: static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { - struct file_lock **flpp; + struct file_lock *fl; int status = false; struct file *filp = find_any_file(fp); struct inode *inode; + struct file_lock_context *flctx; if (!filp) { /* Any valid lock stateid should have some sort of access */ @@ -5568,15 +5570,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } inode = file_inode(filp); + flctx = inode->i_flctx; - spin_lock(&inode->i_lock); - for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { - if ((*flpp)->fl_owner == (fl_owner_t)lowner) { - status = true; - break; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&flctx->flc_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_owner == (fl_owner_t)lowner) { + status = true; + break; + } } + spin_unlock(&flctx->flc_lock); } - spin_unlock(&inode->i_lock); fput(filp); return status; } diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 91093cd74f0d..385704027575 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 7ef18fc656c2..469086b9f99b 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1900,8 +1906,8 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1912,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink) { + /* + * Defer calling iput() to avoid a deadlock + * over I_SYNC flag for inodes with i_nlink == 0 + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2583,6 +2604,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2609,6 +2632,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2633,6 +2658,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2642,6 +2670,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d0013314..a48d6de1e02c 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/workqueue.h> #include <linux/nilfs2_fs.h> #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index 22c629eedd82..2a24249b30af 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -1,5 +1,6 @@ config FSNOTIFY def_bool n + select SRCU source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index c991616acca9..bff8567aa42d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -259,16 +259,15 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, struct fsnotify_event *kevent; char __user *start; int ret; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); start = buf; group = file->private_data; pr_debug("%s: group=%p\n", __func__, group); + add_wait_queue(&group->notification_waitq, &wait); while (1) { - prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE); - mutex_lock(&group->notification_mutex); kevent = get_one_event(group, count); mutex_unlock(&group->notification_mutex); @@ -289,7 +288,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, if (start != buf) break; - schedule(); + + wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); continue; } @@ -318,8 +318,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, buf += ret; count -= ret; } + remove_wait_queue(&group->notification_waitq, &wait); - finish_wait(&group->notification_waitq, &wait); if (start != buf && ret != -EFAULT) ret = buf - start; return ret; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 79b5af5e6a7b..cecd875653e4 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2023,11 +2023,8 @@ leave: dlm_lockres_drop_inflight_ref(dlm, res); spin_unlock(&res->spinlock); - if (ret < 0) { + if (ret < 0) mlog_errno(ret); - if (newlock) - dlm_lock_put(newlock); - } return ret; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b931e04e3388..914c121ec890 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, struct inode *inode, const char *symname); +static int ocfs2_double_lock(struct ocfs2_super *osb, + struct buffer_head **bh1, + struct inode *inode1, + struct buffer_head **bh2, + struct inode *inode2, + int rename); + +static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2); /* An orphan dir name is an 8 byte value, printed as a hex string */ #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) @@ -678,8 +686,10 @@ static int ocfs2_link(struct dentry *old_dentry, { handle_t *handle; struct inode *inode = old_dentry->d_inode; + struct inode *old_dir = old_dentry->d_parent->d_inode; int err; struct buffer_head *fe_bh = NULL; + struct buffer_head *old_dir_bh = NULL; struct buffer_head *parent_fe_bh = NULL; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); @@ -696,19 +706,33 @@ static int ocfs2_link(struct dentry *old_dentry, dquot_initialize(dir); - err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT); + err = ocfs2_double_lock(osb, &old_dir_bh, old_dir, + &parent_fe_bh, dir, 0); if (err < 0) { if (err != -ENOENT) mlog_errno(err); return err; } + /* make sure both dirs have bhs + * get an extra ref on old_dir_bh if old==new */ + if (!parent_fe_bh) { + if (old_dir_bh) { + parent_fe_bh = old_dir_bh; + get_bh(parent_fe_bh); + } else { + mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str); + err = -EIO; + goto out; + } + } + if (!dir->i_nlink) { err = -ENOENT; goto out; } - err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name, old_dentry->d_name.len, &old_de_ino); if (err) { err = -ENOENT; @@ -801,10 +825,11 @@ out_unlock_inode: ocfs2_inode_unlock(inode, 1); out: - ocfs2_inode_unlock(dir, 1); + ocfs2_double_unlock(old_dir, dir); brelse(fe_bh); brelse(parent_fe_bh); + brelse(old_dir_bh); ocfs2_free_dir_lookup_result(&lookup); @@ -1072,14 +1097,15 @@ static int ocfs2_check_if_ancestor(struct ocfs2_super *osb, } /* - * The only place this should be used is rename! + * The only place this should be used is rename and link! * if they have the same id, then the 1st one is the only one locked. */ static int ocfs2_double_lock(struct ocfs2_super *osb, struct buffer_head **bh1, struct inode *inode1, struct buffer_head **bh2, - struct inode *inode2) + struct inode *inode2, + int rename) { int status; int inode1_is_ancestor, inode2_is_ancestor; @@ -1127,7 +1153,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id2 */ status = ocfs2_inode_lock_nested(inode2, bh2, 1, - OI_LS_RENAME1); + rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -1136,7 +1162,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, } /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2); + status = ocfs2_inode_lock_nested(inode1, bh1, 1, + rename == 1 ? OI_LS_RENAME2 : OI_LS_PARENT); if (status < 0) { /* * An error return must mean that no cluster locks @@ -1252,7 +1279,7 @@ static int ocfs2_rename(struct inode *old_dir, /* if old and new are the same, this'll just do one lock. */ status = ocfs2_double_lock(osb, &old_dir_bh, old_dir, - &new_dir_bh, new_dir); + &new_dir_bh, new_dir, 1); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index 1eae330193a6..b6d51333ad02 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -48,6 +48,7 @@ struct ocfs2_quota_recovery { /* In-memory structure with quota header information */ struct ocfs2_mem_dqinfo { unsigned int dqi_type; /* Quota type this structure describes */ + unsigned int dqi_flags; /* Flags OLQF_* */ unsigned int dqi_chunks; /* Number of chunks in local quota file */ unsigned int dqi_blocks; /* Number of blocks allocated for local quota file */ unsigned int dqi_syncms; /* How often should we sync with other nodes */ diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 10b653930ee2..89c0b2620814 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -292,7 +292,7 @@ static void olq_update_info(struct buffer_head *bh, void *private) ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); spin_lock(&dq_data_lock); - ldinfo->dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + ldinfo->dqi_flags = cpu_to_le32(oinfo->dqi_flags); ldinfo->dqi_chunks = cpu_to_le32(oinfo->dqi_chunks); ldinfo->dqi_blocks = cpu_to_le32(oinfo->dqi_blocks); spin_unlock(&dq_data_lock); @@ -701,8 +701,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) /* We don't need the lock and we have to acquire quota file locks * which will later depend on this lock */ mutex_unlock(&sb_dqopt(sb)->dqio_mutex); - info->dqi_maxblimit = 0x7fffffffffffffffLL; - info->dqi_maxilimit = 0x7fffffffffffffffLL; + info->dqi_max_spc_limit = 0x7fffffffffffffffLL; + info->dqi_max_ino_limit = 0x7fffffffffffffffLL; oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS); if (!oinfo) { mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota" @@ -737,13 +737,13 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); - info->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); + oinfo->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); oinfo->dqi_chunks = le32_to_cpu(ldinfo->dqi_chunks); oinfo->dqi_blocks = le32_to_cpu(ldinfo->dqi_blocks); oinfo->dqi_libh = bh; /* We crashed when using local quota file? */ - if (!(info->dqi_flags & OLQF_CLEAN)) { + if (!(oinfo->dqi_flags & OLQF_CLEAN)) { rec = OCFS2_SB(sb)->quota_rec; if (!rec) { rec = ocfs2_alloc_quota_recovery(); @@ -772,7 +772,7 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } /* Now mark quota file as used */ - info->dqi_flags &= ~OLQF_CLEAN; + oinfo->dqi_flags &= ~OLQF_CLEAN; status = ocfs2_modify_bh(lqinode, bh, olq_update_info, info); if (status < 0) { mlog_errno(status); @@ -857,7 +857,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) goto out; /* Mark local file as clean */ - info->dqi_flags |= OLQF_CLEAN; + oinfo->dqi_flags |= OLQF_CLEAN; status = ocfs2_modify_bh(sb_dqopt(sb)->files[type], oinfo->dqi_libh, olq_update_info, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 83723179e1ec..706c71c2955d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1000,36 +1000,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) } } -/* Handle quota on quotactl */ -static int ocfs2_quota_on(struct super_block *sb, int type, int format_id) -{ - unsigned int feature[OCFS2_MAXQUOTAS] = { - OCFS2_FEATURE_RO_COMPAT_USRQUOTA, - OCFS2_FEATURE_RO_COMPAT_GRPQUOTA}; - - if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type])) - return -EINVAL; - - return dquot_enable(sb_dqopt(sb)->files[type], type, - format_id, DQUOT_LIMITS_ENABLED); -} - -/* Handle quota off quotactl */ -static int ocfs2_quota_off(struct super_block *sb, int type) -{ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - -static const struct quotactl_ops ocfs2_quotactl_ops = { - .quota_on_meta = ocfs2_quota_on, - .quota_off = ocfs2_quota_off, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk, -}; - static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) { struct dentry *root; @@ -2079,7 +2049,7 @@ static int ocfs2_initialize_super(struct super_block *sb, sb->s_op = &ocfs2_sops; sb->s_d_op = &ocfs2_dentry_ops; sb->s_export_op = &ocfs2_export_ops; - sb->s_qcop = &ocfs2_quotactl_ops; + sb->s_qcop = &dquot_quotactl_sysfile_ops; sb->dq_op = &ocfs2_quota_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb->s_xattr = ocfs2_xattr_handlers; diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index c51df1dd237e..4a09975aac90 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -5,6 +5,7 @@ config QUOTA bool "Quota support" select QUOTACTL + select SRCU help If you say Y here, you will be able to set per user limits for disk usage (also called disk quotas). Currently, it works for the diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8f0acef3d184..0ccd4ba3a246 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot) return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || - !(info->dqi_flags & V1_DQF_RSQUASH)); + !(info->dqi_flags & DQF_ROOT_SQUASH)); } /* needs dq_data_lock */ @@ -2385,41 +2385,106 @@ out: } EXPORT_SYMBOL(dquot_quota_on_mount); -static inline qsize_t qbtos(qsize_t blocks) +static int dquot_quota_enable(struct super_block *sb, unsigned int flags) { - return blocks << QIF_DQBLKSIZE_BITS; + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* Accounting cannot be turned on while fs is mounted */ + flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); + if (!flags) + return -EINVAL; + for (type = 0; type < MAXQUOTAS; type++) { + if (!(flags & qtype_enforce_flag(type))) + continue; + /* Can't enforce without accounting */ + if (!sb_has_quota_usage_enabled(sb, type)) + return -EINVAL; + ret = dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + return 0; +out_err: + /* Backout enforcement enablement we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + } + /* Error code translation for better compatibility with XFS */ + if (ret == -EBUSY) + ret = -EEXIST; + return ret; } -static inline qsize_t stoqb(qsize_t space) +static int dquot_quota_disable(struct super_block *sb, unsigned int flags) { - return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* + * We don't support turning off accounting via quotactl. In principle + * quota infrastructure can do this but filesystems don't expect + * userspace to be able to do it. + */ + if (flags & + (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) + return -EOPNOTSUPP; + + /* Filter out limits not enabled */ + for (type = 0; type < MAXQUOTAS; type++) + if (!sb_has_quota_limits_enabled(sb, type)) + flags &= ~qtype_enforce_flag(type); + /* Nothing left? */ + if (!flags) + return -EEXIST; + for (type = 0; type < MAXQUOTAS; type++) { + if (flags & qtype_enforce_flag(type)) { + ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + } + return 0; +out_err: + /* Backout enforcement disabling we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + } + return ret; } /* Generic routine for getting common part of quota structure */ -static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); - di->d_version = FS_DQUOT_VERSION; - di->d_flags = dquot->dq_id.type == USRQUOTA ? - FS_USER_QUOTA : FS_GROUP_QUOTA; - di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id); - spin_lock(&dq_data_lock); - di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit); - di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit); + di->d_spc_hardlimit = dm->dqb_bhardlimit; + di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; di->d_ino_softlimit = dm->dqb_isoftlimit; - di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace; - di->d_icount = dm->dqb_curinodes; - di->d_btimer = dm->dqb_btime; - di->d_itimer = dm->dqb_itime; + di->d_space = dm->dqb_curspace + dm->dqb_rsvspace; + di->d_ino_count = dm->dqb_curinodes; + di->d_spc_timer = dm->dqb_btime; + di->d_ino_timer = dm->dqb_itime; spin_unlock(&dq_data_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; @@ -2433,70 +2498,70 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid, } EXPORT_SYMBOL(dquot_get_dqblk); -#define VFS_FS_DQ_MASK \ - (FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \ - FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \ - FS_DQ_BTIMER | FS_DQ_ITIMER) +#define VFS_QC_MASK \ + (QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \ + QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \ + QC_SPC_TIMER | QC_INO_TIMER) /* Generic routine for setting common part of quota structure */ -static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; int check_blim = 0, check_ilim = 0; struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - if (di->d_fieldmask & ~VFS_FS_DQ_MASK) + if (di->d_fieldmask & ~VFS_QC_MASK) return -EINVAL; - if (((di->d_fieldmask & FS_DQ_BSOFT) && - (di->d_blk_softlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_BHARD) && - (di->d_blk_hardlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_ISOFT) && - (di->d_ino_softlimit > dqi->dqi_maxilimit)) || - ((di->d_fieldmask & FS_DQ_IHARD) && - (di->d_ino_hardlimit > dqi->dqi_maxilimit))) + if (((di->d_fieldmask & QC_SPC_SOFT) && + di->d_spc_softlimit > dqi->dqi_max_spc_limit) || + ((di->d_fieldmask & QC_SPC_HARD) && + di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || + ((di->d_fieldmask & QC_INO_SOFT) && + (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || + ((di->d_fieldmask & QC_INO_HARD) && + (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dq_data_lock); - if (di->d_fieldmask & FS_DQ_BCOUNT) { - dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace; + if (di->d_fieldmask & QC_SPACE) { + dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BSOFT) - dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit); - if (di->d_fieldmask & FS_DQ_BHARD) - dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit); - if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) { + if (di->d_fieldmask & QC_SPC_SOFT) + dm->dqb_bsoftlimit = di->d_spc_softlimit; + if (di->d_fieldmask & QC_SPC_HARD) + dm->dqb_bhardlimit = di->d_spc_hardlimit; + if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) { check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ICOUNT) { - dm->dqb_curinodes = di->d_icount; + if (di->d_fieldmask & QC_INO_COUNT) { + dm->dqb_curinodes = di->d_ino_count; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ISOFT) + if (di->d_fieldmask & QC_INO_SOFT) dm->dqb_isoftlimit = di->d_ino_softlimit; - if (di->d_fieldmask & FS_DQ_IHARD) + if (di->d_fieldmask & QC_INO_HARD) dm->dqb_ihardlimit = di->d_ino_hardlimit; - if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) { + if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) { check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BTIMER) { - dm->dqb_btime = di->d_btimer; + if (di->d_fieldmask & QC_SPC_TIMER) { + dm->dqb_btime = di->d_spc_timer; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ITIMER) { - dm->dqb_itime = di->d_itimer; + if (di->d_fieldmask & QC_INO_TIMER) { + dm->dqb_itime = di->d_ino_timer; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); } @@ -2506,7 +2571,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curspace < dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_BTIMER)) + } else if (!(di->d_fieldmask & QC_SPC_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_btime = get_seconds() + dqi->dqi_bgrace; } @@ -2515,7 +2580,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curinodes < dm->dqb_isoftlimit) { dm->dqb_itime = 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_ITIMER)) + } else if (!(di->d_fieldmask & QC_INO_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_itime = get_seconds() + dqi->dqi_igrace; } @@ -2531,7 +2596,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) } int dquot_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; int rc; @@ -2582,6 +2647,14 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii) goto out; } mi = sb_dqopt(sb)->info + type; + if (ii->dqi_valid & IIF_FLAGS) { + if (ii->dqi_flags & ~DQF_SETINFO_MASK || + (ii->dqi_flags & DQF_ROOT_SQUASH && + mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) { + err = -EINVAL; + goto out; + } + } spin_lock(&dq_data_lock); if (ii->dqi_valid & IIF_BGRACE) mi->dqi_bgrace = ii->dqi_bgrace; @@ -2611,6 +2684,17 @@ const struct quotactl_ops dquot_quotactl_ops = { }; EXPORT_SYMBOL(dquot_quotactl_ops); +const struct quotactl_ops dquot_quotactl_sysfile_ops = { + .quota_enable = dquot_quota_enable, + .quota_disable = dquot_quota_disable, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; +EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); + static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 2aa4151f99d2..d14a799c7785 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -66,18 +66,40 @@ static int quota_sync_all(int type) return ret; } +unsigned int qtype_enforce_flag(int type) +{ + switch (type) { + case USRQUOTA: + return FS_QUOTA_UDQ_ENFD; + case GRPQUOTA: + return FS_QUOTA_GDQ_ENFD; + case PRJQUOTA: + return FS_QUOTA_PDQ_ENFD; + } + return 0; +} + static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; - if (sb->s_qcop->quota_on_meta) - return sb->s_qcop->quota_on_meta(sb, type, id); + if (sb->s_qcop->quota_enable) + return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } +static int quota_quotaoff(struct super_block *sb, int type) +{ + if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) + return -ENOSYS; + if (sb->s_qcop->quota_disable) + return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); + return sb->s_qcop->quota_off(sb, type); +} + static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; @@ -118,17 +140,27 @@ static int quota_setinfo(struct super_block *sb, int type, void __user *addr) return sb->s_qcop->set_info(sb, type, &info); } -static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src) +static inline qsize_t qbtos(qsize_t blocks) +{ + return blocks << QIF_DQBLKSIZE_BITS; +} + +static inline qsize_t stoqb(qsize_t space) +{ + return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; +} + +static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src) { memset(dst, 0, sizeof(*dst)); - dst->dqb_bhardlimit = src->d_blk_hardlimit; - dst->dqb_bsoftlimit = src->d_blk_softlimit; - dst->dqb_curspace = src->d_bcount; + dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit); + dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit); + dst->dqb_curspace = src->d_space; dst->dqb_ihardlimit = src->d_ino_hardlimit; dst->dqb_isoftlimit = src->d_ino_softlimit; - dst->dqb_curinodes = src->d_icount; - dst->dqb_btime = src->d_btimer; - dst->dqb_itime = src->d_itimer; + dst->dqb_curinodes = src->d_ino_count; + dst->dqb_btime = src->d_spc_timer; + dst->dqb_itime = src->d_ino_timer; dst->dqb_valid = QIF_ALL; } @@ -136,7 +168,7 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; int ret; @@ -154,36 +186,36 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, return 0; } -static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src) +static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { - dst->d_blk_hardlimit = src->dqb_bhardlimit; - dst->d_blk_softlimit = src->dqb_bsoftlimit; - dst->d_bcount = src->dqb_curspace; + dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); + dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit); + dst->d_space = src->dqb_curspace; dst->d_ino_hardlimit = src->dqb_ihardlimit; dst->d_ino_softlimit = src->dqb_isoftlimit; - dst->d_icount = src->dqb_curinodes; - dst->d_btimer = src->dqb_btime; - dst->d_itimer = src->dqb_itime; + dst->d_ino_count = src->dqb_curinodes; + dst->d_spc_timer = src->dqb_btime; + dst->d_ino_timer = src->dqb_itime; dst->d_fieldmask = 0; if (src->dqb_valid & QIF_BLIMITS) - dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD; + dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD; if (src->dqb_valid & QIF_SPACE) - dst->d_fieldmask |= FS_DQ_BCOUNT; + dst->d_fieldmask |= QC_SPACE; if (src->dqb_valid & QIF_ILIMITS) - dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD; + dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD; if (src->dqb_valid & QIF_INODES) - dst->d_fieldmask |= FS_DQ_ICOUNT; + dst->d_fieldmask |= QC_INO_COUNT; if (src->dqb_valid & QIF_BTIME) - dst->d_fieldmask |= FS_DQ_BTIMER; + dst->d_fieldmask |= QC_SPC_TIMER; if (src->dqb_valid & QIF_ITIME) - dst->d_fieldmask |= FS_DQ_ITIMER; + dst->d_fieldmask |= QC_INO_TIMER; } static int quota_setquota(struct super_block *sb, int type, qid_t id, void __user *addr) { - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; struct kqid qid; @@ -198,15 +230,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id, return sb->s_qcop->set_dqblk(sb, qid, &fdq); } -static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr) +static int quota_enable(struct super_block *sb, void __user *addr) +{ + __u32 flags; + + if (copy_from_user(&flags, addr, sizeof(flags))) + return -EFAULT; + if (!sb->s_qcop->quota_enable) + return -ENOSYS; + return sb->s_qcop->quota_enable(sb, flags); +} + +static int quota_disable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; - if (!sb->s_qcop->set_xstate) + if (!sb->s_qcop->quota_disable) return -ENOSYS; - return sb->s_qcop->set_xstate(sb, flags, cmd); + return sb->s_qcop->quota_disable(sb, flags); } static int quota_getxstate(struct super_block *sb, void __user *addr) @@ -247,10 +290,78 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr) return ret; } +/* + * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them + * out of there as xfsprogs rely on definitions being in that header file. So + * just define same functions here for quota purposes. + */ +#define XFS_BB_SHIFT 9 + +static inline u64 quota_bbtob(u64 blocks) +{ + return blocks << XFS_BB_SHIFT; +} + +static inline u64 quota_btobb(u64 bytes) +{ + return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT; +} + +static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) +{ + dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit); + dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_space = quota_bbtob(src->d_bcount); + dst->d_ino_count = src->d_icount; + dst->d_ino_timer = src->d_itimer; + dst->d_spc_timer = src->d_btimer; + dst->d_ino_warns = src->d_iwarns; + dst->d_spc_warns = src->d_bwarns; + dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit); + dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit); + dst->d_rt_space = quota_bbtob(src->d_rtbcount); + dst->d_rt_spc_timer = src->d_rtbtimer; + dst->d_rt_spc_warns = src->d_rtbwarns; + dst->d_fieldmask = 0; + if (src->d_fieldmask & FS_DQ_ISOFT) + dst->d_fieldmask |= QC_INO_SOFT; + if (src->d_fieldmask & FS_DQ_IHARD) + dst->d_fieldmask |= QC_INO_HARD; + if (src->d_fieldmask & FS_DQ_BSOFT) + dst->d_fieldmask |= QC_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_BHARD) + dst->d_fieldmask |= QC_SPC_HARD; + if (src->d_fieldmask & FS_DQ_RTBSOFT) + dst->d_fieldmask |= QC_RT_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_RTBHARD) + dst->d_fieldmask |= QC_RT_SPC_HARD; + if (src->d_fieldmask & FS_DQ_BTIMER) + dst->d_fieldmask |= QC_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_ITIMER) + dst->d_fieldmask |= QC_INO_TIMER; + if (src->d_fieldmask & FS_DQ_RTBTIMER) + dst->d_fieldmask |= QC_RT_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_BWARNS) + dst->d_fieldmask |= QC_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_IWARNS) + dst->d_fieldmask |= QC_INO_WARNS; + if (src->d_fieldmask & FS_DQ_RTBWARNS) + dst->d_fieldmask |= QC_RT_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_BCOUNT) + dst->d_fieldmask |= QC_SPACE; + if (src->d_fieldmask & FS_DQ_ICOUNT) + dst->d_fieldmask |= QC_INO_COUNT; + if (src->d_fieldmask & FS_DQ_RTBCOUNT) + dst->d_fieldmask |= QC_RT_SPACE; +} + static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; if (copy_from_user(&fdq, addr, sizeof(fdq))) @@ -260,13 +371,44 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - return sb->s_qcop->set_dqblk(sb, qid, &fdq); + copy_from_xfs_dqblk(&qdq, &fdq); + return sb->s_qcop->set_dqblk(sb, qid, &qdq); +} + +static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src, + int type, qid_t id) +{ + memset(dst, 0, sizeof(*dst)); + dst->d_version = FS_DQUOT_VERSION; + dst->d_id = id; + if (type == USRQUOTA) + dst->d_flags = FS_USER_QUOTA; + else if (type == PRJQUOTA) + dst->d_flags = FS_PROJ_QUOTA; + else + dst->d_flags = FS_GROUP_QUOTA; + dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit); + dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_bcount = quota_btobb(src->d_space); + dst->d_icount = src->d_ino_count; + dst->d_itimer = src->d_ino_timer; + dst->d_btimer = src->d_spc_timer; + dst->d_iwarns = src->d_ino_warns; + dst->d_bwarns = src->d_spc_warns; + dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit); + dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit); + dst->d_rtbcount = quota_btobb(src->d_rt_space); + dst->d_rtbtimer = src->d_rt_spc_timer; + dst->d_rtbwarns = src->d_rt_spc_warns; } static int quota_getxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; int ret; @@ -275,8 +417,11 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - ret = sb->s_qcop->get_dqblk(sb, qid, &fdq); - if (!ret && copy_to_user(addr, &fdq, sizeof(fdq))) + ret = sb->s_qcop->get_dqblk(sb, qid, &qdq); + if (ret) + return ret; + copy_to_xfs_dqblk(&fdq, &qdq, type, id); + if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } @@ -317,9 +462,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_QUOTAON: return quota_quotaon(sb, type, cmd, id, path); case Q_QUOTAOFF: - if (!sb->s_qcop->quota_off) - return -ENOSYS; - return sb->s_qcop->quota_off(sb, type); + return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: @@ -335,8 +478,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: + return quota_enable(sb, addr); case Q_XQUOTAOFF: - return quota_setxstate(sb, cmd, addr); + return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 469c6848b322..8fe79beced5c 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type) } ret = 0; /* limits are stored as unsigned 32-bit data */ - dqopt->info[type].dqi_maxblimit = 0xffffffff; - dqopt->info[type].dqi_maxilimit = 0xffffffff; + dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + dqopt->info[type].dqi_max_ino_limit = 0xffffffff; dqopt->info[type].dqi_igrace = dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME; dqopt->info[type].dqi_bgrace = diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 02751ec695c5..9cb10d7197f7 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -117,16 +117,17 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ - info->dqi_maxblimit = 0xffffffff; - info->dqi_maxilimit = 0xffffffff; + info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + info->dqi_max_ino_limit = 0xffffffff; } else { - /* used space is stored as unsigned 64-bit value */ - info->dqi_maxblimit = 0xffffffffffffffffULL; /* 2^64-1 */ - info->dqi_maxilimit = 0xffffffffffffffffULL; + /* used space is stored as unsigned 64-bit value in bytes */ + info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */ + info->dqi_max_ino_limit = 0xffffffffffffffffULL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); - info->dqi_flags = le32_to_cpu(dinfo.dqi_flags); + /* No flags currently supported */ + info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); @@ -157,7 +158,8 @@ static int v2_write_file_info(struct super_block *sb, int type) info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); - dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + /* No flags currently supported */ + dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); diff --git a/fs/read_write.c b/fs/read_write.c index c0805c93b6fa..4060691e78f7 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t return retval; } - if (unlikely(inode->i_flock && mandatory_lock(inode))) { + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { retval = locks_mandatory_area( read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig index 0e0e99bd6bce..c6e17a744c3b 100644 --- a/fs/udf/Kconfig +++ b/fs/udf/Kconfig @@ -2,10 +2,12 @@ config UDF_FS tristate "UDF file system support" select CRC_ITU_T help - This is the new file system used on some CD-ROMs and DVDs. Say Y if - you intend to mount DVD discs or CDRW's written in packet mode, or - if written to by other UDF utilities, such as DirectCD. - Please read <file:Documentation/filesystems/udf.txt>. + This is a file system used on some CD-ROMs and DVDs. Since the + file system is supported by multiple operating systems and is more + compatible with standard unix file systems, it is also suitable for + removable USB disks. Say Y if you intend to mount DVD discs or CDRW's + written in packet mode, or if you want to use UDF for removable USB + disks. Please read <file:Documentation/filesystems/udf.txt>. To compile this file system support as a module, choose M here: the module will be called udf. diff --git a/fs/udf/dir.c b/fs/udf/dir.c index a012c51caffd..05e90edd1992 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -57,6 +57,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) sector_t offset; int i, num, ret = 0; struct extent_position epos = { NULL, 0, {0, 0} }; + struct super_block *sb = dir->i_sb; if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) @@ -76,16 +77,16 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) if (nf_pos == 0) nf_pos = udf_ext0_offset(dir); - fibh.soffset = fibh.eoffset = nf_pos & (dir->i_sb->s_blocksize - 1); + fibh.soffset = fibh.eoffset = nf_pos & (sb->s_blocksize - 1); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - if (inode_bmap(dir, nf_pos >> dir->i_sb->s_blocksize_bits, + if (inode_bmap(dir, nf_pos >> sb->s_blocksize_bits, &epos, &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30)) { ret = -ENOENT; goto out; } - block = udf_get_lb_pblock(dir->i_sb, &eloc, offset); - if ((++offset << dir->i_sb->s_blocksize_bits) < elen) { + block = udf_get_lb_pblock(sb, &eloc, offset); + if ((++offset << sb->s_blocksize_bits) < elen) { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) epos.offset -= sizeof(struct short_ad); else if (iinfo->i_alloc_type == @@ -95,18 +96,18 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) offset = 0; } - if (!(fibh.sbh = fibh.ebh = udf_tread(dir->i_sb, block))) { + if (!(fibh.sbh = fibh.ebh = udf_tread(sb, block))) { ret = -EIO; goto out; } - if (!(offset & ((16 >> (dir->i_sb->s_blocksize_bits - 9)) - 1))) { - i = 16 >> (dir->i_sb->s_blocksize_bits - 9); - if (i + offset > (elen >> dir->i_sb->s_blocksize_bits)) - i = (elen >> dir->i_sb->s_blocksize_bits) - offset; + if (!(offset & ((16 >> (sb->s_blocksize_bits - 9)) - 1))) { + i = 16 >> (sb->s_blocksize_bits - 9); + if (i + offset > (elen >> sb->s_blocksize_bits)) + i = (elen >> sb->s_blocksize_bits) - offset; for (num = 0; i > 0; i--) { - block = udf_get_lb_pblock(dir->i_sb, &eloc, offset + i); - tmp = udf_tgetblk(dir->i_sb, block); + block = udf_get_lb_pblock(sb, &eloc, offset + i); + tmp = udf_tgetblk(sb, block); if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp)) bha[num++] = tmp; else @@ -152,12 +153,12 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) } if ((cfi.fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { - if (!UDF_QUERY_FLAG(dir->i_sb, UDF_FLAG_UNDELETE)) + if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } if ((cfi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) != 0) { - if (!UDF_QUERY_FLAG(dir->i_sb, UDF_FLAG_UNHIDE)) + if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } @@ -167,12 +168,12 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) continue; } - flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi); + flen = udf_get_filename(sb, nameptr, lfi, fname, UDF_NAME_LEN); if (!flen) continue; tloc = lelb_to_cpu(cfi.icb.extLocation); - iblock = udf_get_lb_pblock(dir->i_sb, &tloc, 0); + iblock = udf_get_lb_pblock(sb, &tloc, 0); if (!dir_emit(ctx, fname, flen, iblock, DT_UNKNOWN)) goto out; } /* end while */ diff --git a/fs/udf/file.c b/fs/udf/file.c index bb15771b92ae..08f3555fbeac 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -224,7 +224,7 @@ out: static int udf_release_file(struct inode *inode, struct file *filp) { if (filp->f_mode & FMODE_WRITE && - atomic_read(&inode->i_writecount) > 1) { + atomic_read(&inode->i_writecount) == 1) { /* * Grab i_mutex to avoid races with writes changing i_size * while we are running. diff --git a/fs/udf/inode.c b/fs/udf/inode.c index c9b4df5810d5..a445d599098d 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -750,7 +750,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Are we beyond EOF? */ if (etype == -1) { int ret; - isBeyondEOF = 1; + isBeyondEOF = true; if (count) { if (c) laarr[0] = laarr[1]; @@ -792,7 +792,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, endnum = c + 1; lastblock = 1; } else { - isBeyondEOF = 0; + isBeyondEOF = false; endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, @@ -1288,6 +1288,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) struct kernel_lb_addr *iloc = &iinfo->i_location; unsigned int link_count; unsigned int indirections = 0; + int bs = inode->i_sb->s_blocksize; int ret = -EIO; reread: @@ -1374,38 +1375,35 @@ reread: if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) { iinfo->i_efe = 1; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct extendedFileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct extendedFileEntry), - inode->i_sb->s_blocksize - - sizeof(struct extendedFileEntry)); + bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { iinfo->i_efe = 0; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - - sizeof(struct fileEntry)); + ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct fileEntry), - inode->i_sb->s_blocksize - sizeof(struct fileEntry)); + bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { iinfo->i_efe = 0; iinfo->i_use = 1; iinfo->i_lenAlloc = le32_to_cpu( ((struct unallocSpaceEntry *)bh->b_data)-> lengthAllocDescs); - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct unallocSpaceEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct unallocSpaceEntry), - inode->i_sb->s_blocksize - - sizeof(struct unallocSpaceEntry)); + bs - sizeof(struct unallocSpaceEntry)); return 0; } @@ -1489,6 +1487,28 @@ reread: } inode->i_generation = iinfo->i_unique; + /* + * Sanity check length of allocation descriptors and extended attrs to + * avoid integer overflows + */ + if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs) + goto out; + /* Now do exact checks */ + if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs) + goto out; + /* Sanity checks for files in ICB so that we don't get confused later */ + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { + /* + * For file in ICB data is stored in allocation descriptor + * so sizes should match + */ + if (iinfo->i_lenAlloc != inode->i_size) + goto out; + /* File in ICB has to fit in there... */ + if (inode->i_size > bs - udf_file_entry_alloc_offset(inode)) + goto out; + } + switch (fe->icbTag.fileType) { case ICBTAG_FILE_TYPE_DIRECTORY: inode->i_op = &udf_dir_inode_operations; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index c12e260fd6c4..33b246b82c98 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -159,18 +159,19 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, struct udf_inode_info *dinfo = UDF_I(dir); int isdotdot = child->len == 2 && child->name[0] == '.' && child->name[1] == '.'; + struct super_block *sb = dir->i_sb; size = udf_ext0_offset(dir) + dir->i_size; f_pos = udf_ext0_offset(dir); fibh->sbh = fibh->ebh = NULL; - fibh->soffset = fibh->eoffset = f_pos & (dir->i_sb->s_blocksize - 1); + fibh->soffset = fibh->eoffset = f_pos & (sb->s_blocksize - 1); if (dinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { - if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits, &epos, + if (inode_bmap(dir, f_pos >> sb->s_blocksize_bits, &epos, &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30)) goto out_err; - block = udf_get_lb_pblock(dir->i_sb, &eloc, offset); - if ((++offset << dir->i_sb->s_blocksize_bits) < elen) { + block = udf_get_lb_pblock(sb, &eloc, offset); + if ((++offset << sb->s_blocksize_bits) < elen) { if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) epos.offset -= sizeof(struct short_ad); else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) @@ -178,7 +179,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, } else offset = 0; - fibh->sbh = fibh->ebh = udf_tread(dir->i_sb, block); + fibh->sbh = fibh->ebh = udf_tread(sb, block); if (!fibh->sbh) goto out_err; } @@ -217,12 +218,12 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, } if ((cfi->fileCharacteristics & FID_FILE_CHAR_DELETED) != 0) { - if (!UDF_QUERY_FLAG(dir->i_sb, UDF_FLAG_UNDELETE)) + if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } if ((cfi->fileCharacteristics & FID_FILE_CHAR_HIDDEN) != 0) { - if (!UDF_QUERY_FLAG(dir->i_sb, UDF_FLAG_UNHIDE)) + if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } @@ -233,7 +234,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, if (!lfi) continue; - flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi); + flen = udf_get_filename(sb, nameptr, lfi, fname, UDF_NAME_LEN); if (flen && udf_match(flen, fname, child->len, child->name)) goto out_ok; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 3ccb2f11fc76..f169411c4ea0 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1599,7 +1599,7 @@ static noinline int udf_process_sequence( struct udf_vds_record *curr; struct generic_desc *gd; struct volDescPtr *vdp; - int done = 0; + bool done = false; uint32_t vdsn; uint16_t ident; long next_s = 0, next_e = 0; @@ -1680,7 +1680,7 @@ static noinline int udf_process_sequence( lastblock = next_e; next_s = next_e = 0; } else - done = 1; + done = true; break; } brelse(bh); @@ -2300,6 +2300,7 @@ static void udf_put_super(struct super_block *sb) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); + mutex_destroy(&sbi->s_alloc_mutex); kfree(sb->s_fs_info); sb->s_fs_info = NULL; } diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 6fb7945c1e6e..ac10ca939f26 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -30,49 +30,73 @@ #include <linux/buffer_head.h> #include "udf_i.h" -static void udf_pc_to_char(struct super_block *sb, unsigned char *from, - int fromlen, unsigned char *to) +static int udf_pc_to_char(struct super_block *sb, unsigned char *from, + int fromlen, unsigned char *to, int tolen) { struct pathComponent *pc; int elen = 0; + int comp_len; unsigned char *p = to; + /* Reserve one byte for terminating \0 */ + tolen--; while (elen < fromlen) { pc = (struct pathComponent *)(from + elen); + elen += sizeof(struct pathComponent); switch (pc->componentType) { case 1: /* * Symlink points to some place which should be agreed * upon between originator and receiver of the media. Ignore. */ - if (pc->lengthComponentIdent > 0) + if (pc->lengthComponentIdent > 0) { + elen += pc->lengthComponentIdent; break; + } /* Fall through */ case 2: + if (tolen == 0) + return -ENAMETOOLONG; p = to; *p++ = '/'; + tolen--; break; case 3: + if (tolen < 3) + return -ENAMETOOLONG; memcpy(p, "../", 3); p += 3; + tolen -= 3; break; case 4: + if (tolen < 2) + return -ENAMETOOLONG; memcpy(p, "./", 2); p += 2; + tolen -= 2; /* that would be . - just ignore */ break; case 5: - p += udf_get_filename(sb, pc->componentIdent, p, - pc->lengthComponentIdent); + elen += pc->lengthComponentIdent; + if (elen > fromlen) + return -EIO; + comp_len = udf_get_filename(sb, pc->componentIdent, + pc->lengthComponentIdent, + p, tolen); + p += comp_len; + tolen -= comp_len; + if (tolen == 0) + return -ENAMETOOLONG; *p++ = '/'; + tolen--; break; } - elen += sizeof(struct pathComponent) + pc->lengthComponentIdent; } if (p > to + 1) p[-1] = '\0'; else p[0] = '\0'; + return 0; } static int udf_symlink_filler(struct file *file, struct page *page) @@ -80,11 +104,17 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct buffer_head *bh = NULL; unsigned char *symlink; - int err = -EIO; + int err; unsigned char *p = kmap(page); struct udf_inode_info *iinfo; uint32_t pos; + /* We don't support symlinks longer than one block */ + if (inode->i_size > inode->i_sb->s_blocksize) { + err = -ENAMETOOLONG; + goto out_unmap; + } + iinfo = UDF_I(inode); pos = udf_block_map(inode, 0); @@ -94,14 +124,18 @@ static int udf_symlink_filler(struct file *file, struct page *page) } else { bh = sb_bread(inode->i_sb, pos); - if (!bh) - goto out; + if (!bh) { + err = -EIO; + goto out_unlock_inode; + } symlink = bh->b_data; } - udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p); + err = udf_pc_to_char(inode->i_sb, symlink, inode->i_size, p, PAGE_SIZE); brelse(bh); + if (err) + goto out_unlock_inode; up_read(&iinfo->i_data_sem); SetPageUptodate(page); @@ -109,9 +143,10 @@ static int udf_symlink_filler(struct file *file, struct page *page) unlock_page(page); return 0; -out: +out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); +out_unmap: kunmap(page); unlock_page(page); return err; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 1cc3c993ebd0..47bb3f5ca360 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -211,7 +211,8 @@ udf_get_lb_pblock(struct super_block *sb, struct kernel_lb_addr *loc, } /* unicode.c */ -extern int udf_get_filename(struct super_block *, uint8_t *, uint8_t *, int); +extern int udf_get_filename(struct super_block *, uint8_t *, int, uint8_t *, + int); extern int udf_put_filename(struct super_block *, const uint8_t *, uint8_t *, int); extern int udf_build_ustr(struct ustr *, dstring *, int); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index afd470e588ff..b84fee372734 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -28,7 +28,8 @@ #include "udf_sb.h" -static int udf_translate_to_linux(uint8_t *, uint8_t *, int, uint8_t *, int); +static int udf_translate_to_linux(uint8_t *, int, uint8_t *, int, uint8_t *, + int); static int udf_char_to_ustr(struct ustr *dest, const uint8_t *src, int strlen) { @@ -333,8 +334,8 @@ try_again: return u_len + 1; } -int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname, - int flen) +int udf_get_filename(struct super_block *sb, uint8_t *sname, int slen, + uint8_t *dname, int dlen) { struct ustr *filename, *unifilename; int len = 0; @@ -347,7 +348,7 @@ int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname, if (!unifilename) goto out1; - if (udf_build_ustr_exact(unifilename, sname, flen)) + if (udf_build_ustr_exact(unifilename, sname, slen)) goto out2; if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) { @@ -366,7 +367,8 @@ int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname, } else goto out2; - len = udf_translate_to_linux(dname, filename->u_name, filename->u_len, + len = udf_translate_to_linux(dname, dlen, + filename->u_name, filename->u_len, unifilename->u_name, unifilename->u_len); out2: kfree(unifilename); @@ -403,10 +405,12 @@ int udf_put_filename(struct super_block *sb, const uint8_t *sname, #define EXT_MARK '.' #define CRC_MARK '#' #define EXT_SIZE 5 +/* Number of chars we need to store generated CRC to make filename unique */ +#define CRC_LEN 5 -static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, - int udfLen, uint8_t *fidName, - int fidNameLen) +static int udf_translate_to_linux(uint8_t *newName, int newLen, + uint8_t *udfName, int udfLen, + uint8_t *fidName, int fidNameLen) { int index, newIndex = 0, needsCRC = 0; int extIndex = 0, newExtIndex = 0, hasExt = 0; @@ -439,7 +443,7 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, newExtIndex = newIndex; } } - if (newIndex < 256) + if (newIndex < newLen) newName[newIndex++] = curr; else needsCRC = 1; @@ -467,13 +471,13 @@ static int udf_translate_to_linux(uint8_t *newName, uint8_t *udfName, } ext[localExtIndex++] = curr; } - maxFilenameLen = 250 - localExtIndex; + maxFilenameLen = newLen - CRC_LEN - localExtIndex; if (newIndex > maxFilenameLen) newIndex = maxFilenameLen; else newIndex = newExtIndex; - } else if (newIndex > 250) - newIndex = 250; + } else if (newIndex > newLen - CRC_LEN) + newIndex = newLen - CRC_LEN; newName[newIndex++] = CRC_MARK; valueCRC = crc_itu_t(0, fidName, fidNameLen); newName[newIndex++] = hex_asc_upper_hi(valueCRC >> 8); diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index d6e4d88094ab..0d4d3590cf85 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -165,9 +165,9 @@ extern void xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint); /* quota ops */ extern int xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint); extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t, - uint, struct fs_disk_quota *); + uint, struct qc_dqblk *); extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint, - struct fs_disk_quota *); + struct qc_dqblk *); extern int xfs_qm_scall_getqstat(struct xfs_mount *, struct fs_quota_stat *); extern int xfs_qm_scall_getqstatv(struct xfs_mount *, diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index b8a565edb4ae..9b965db45800 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -39,7 +39,6 @@ STATIC int xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint); STATIC int xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *, uint); STATIC uint xfs_qm_export_flags(uint); -STATIC uint xfs_qm_export_qtype_flags(uint); /* * Turn off quota accounting and/or enforcement for all udquots and/or @@ -326,22 +325,16 @@ xfs_qm_scall_quotaon( return -EINVAL; } - /* No fs can turn on quotas with a delayed effect */ - ASSERT((flags & XFS_ALL_QUOTA_ACCT) == 0); - /* * Can't enforce without accounting. We check the superblock * qflags here instead of m_qflags because rootfs can have * quota acct on ondisk without m_qflags' knowing. */ - if (((flags & XFS_UQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && + if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && (flags & XFS_UQUOTA_ENFD)) || - ((flags & XFS_GQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && (flags & XFS_GQUOTA_ENFD)) || - ((flags & XFS_PQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && (flags & XFS_PQUOTA_ENFD))) { xfs_debug(mp, "%s: Can't enforce without acct, flags=%x sbflags=%x", @@ -380,8 +373,7 @@ xfs_qm_scall_quotaon( ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) != (mp->m_qflags & XFS_PQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) != - (mp->m_qflags & XFS_GQUOTA_ACCT)) || - (flags & XFS_ALL_QUOTA_ENFD) == 0) + (mp->m_qflags & XFS_GQUOTA_ACCT))) return 0; if (! XFS_IS_QUOTA_RUNNING(mp)) @@ -418,20 +410,12 @@ xfs_qm_scall_getqstat( memset(out, 0, sizeof(fs_quota_stat_t)); out->qs_version = FS_QSTAT_VERSION; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -477,14 +461,13 @@ xfs_qm_scall_getqstat( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } @@ -505,13 +488,6 @@ xfs_qm_scall_getqstatv( bool tempgqip = false; bool temppqip = false; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - out->qs_pquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); @@ -519,11 +495,9 @@ xfs_qm_scall_getqstatv( out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; out->qs_pquota.qfs_ino = mp->m_sb.sb_pquotino; - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -558,19 +532,18 @@ xfs_qm_scall_getqstatv( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } -#define XFS_DQ_MASK \ - (FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK) +#define XFS_QC_MASK \ + (QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK) /* * Adjust quota limits, and start/stop timers accordingly. @@ -580,7 +553,7 @@ xfs_qm_scall_setqlim( struct xfs_mount *mp, xfs_dqid_t id, uint type, - fs_disk_quota_t *newlim) + struct qc_dqblk *newlim) { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_disk_dquot *ddq; @@ -589,9 +562,9 @@ xfs_qm_scall_setqlim( int error; xfs_qcnt_t hard, soft; - if (newlim->d_fieldmask & ~XFS_DQ_MASK) + if (newlim->d_fieldmask & ~XFS_QC_MASK) return -EINVAL; - if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0) + if ((newlim->d_fieldmask & XFS_QC_MASK) == 0) return 0; /* @@ -629,11 +602,11 @@ xfs_qm_scall_setqlim( /* * Make sure that hardlimits are >= soft limits before changing. */ - hard = (newlim->d_fieldmask & FS_DQ_BHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) : + hard = (newlim->d_fieldmask & QC_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) : be64_to_cpu(ddq->d_blk_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) : + soft = (newlim->d_fieldmask & QC_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) : be64_to_cpu(ddq->d_blk_softlimit); if (hard == 0 || hard >= soft) { ddq->d_blk_hardlimit = cpu_to_be64(hard); @@ -646,11 +619,11 @@ xfs_qm_scall_setqlim( } else { xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) : + hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) : be64_to_cpu(ddq->d_rtb_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) : + soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) : be64_to_cpu(ddq->d_rtb_softlimit); if (hard == 0 || hard >= soft) { ddq->d_rtb_hardlimit = cpu_to_be64(hard); @@ -663,10 +636,10 @@ xfs_qm_scall_setqlim( xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_IHARD) ? + hard = (newlim->d_fieldmask & QC_INO_HARD) ? (xfs_qcnt_t) newlim->d_ino_hardlimit : be64_to_cpu(ddq->d_ino_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ? + soft = (newlim->d_fieldmask & QC_INO_SOFT) ? (xfs_qcnt_t) newlim->d_ino_softlimit : be64_to_cpu(ddq->d_ino_softlimit); if (hard == 0 || hard >= soft) { @@ -683,12 +656,12 @@ xfs_qm_scall_setqlim( /* * Update warnings counter(s) if requested */ - if (newlim->d_fieldmask & FS_DQ_BWARNS) - ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns); - if (newlim->d_fieldmask & FS_DQ_IWARNS) - ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns); - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns); + if (newlim->d_fieldmask & QC_SPC_WARNS) + ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns); + if (newlim->d_fieldmask & QC_INO_WARNS) + ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns); + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns); if (id == 0) { /* @@ -698,24 +671,24 @@ xfs_qm_scall_setqlim( * soft and hard limit values (already done, above), and * for warnings. */ - if (newlim->d_fieldmask & FS_DQ_BTIMER) { - q->qi_btimelimit = newlim->d_btimer; - ddq->d_btimer = cpu_to_be32(newlim->d_btimer); + if (newlim->d_fieldmask & QC_SPC_TIMER) { + q->qi_btimelimit = newlim->d_spc_timer; + ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_ITIMER) { - q->qi_itimelimit = newlim->d_itimer; - ddq->d_itimer = cpu_to_be32(newlim->d_itimer); + if (newlim->d_fieldmask & QC_INO_TIMER) { + q->qi_itimelimit = newlim->d_ino_timer; + ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer); } - if (newlim->d_fieldmask & FS_DQ_RTBTIMER) { - q->qi_rtbtimelimit = newlim->d_rtbtimer; - ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer); + if (newlim->d_fieldmask & QC_RT_SPC_TIMER) { + q->qi_rtbtimelimit = newlim->d_rt_spc_timer; + ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_BWARNS) - q->qi_bwarnlimit = newlim->d_bwarns; - if (newlim->d_fieldmask & FS_DQ_IWARNS) - q->qi_iwarnlimit = newlim->d_iwarns; - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - q->qi_rtbwarnlimit = newlim->d_rtbwarns; + if (newlim->d_fieldmask & QC_SPC_WARNS) + q->qi_bwarnlimit = newlim->d_spc_warns; + if (newlim->d_fieldmask & QC_INO_WARNS) + q->qi_iwarnlimit = newlim->d_ino_warns; + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + q->qi_rtbwarnlimit = newlim->d_rt_spc_warns; } else { /* * If the user is now over quota, start the timelimit. @@ -820,7 +793,7 @@ xfs_qm_scall_getquota( struct xfs_mount *mp, xfs_dqid_t id, uint type, - struct fs_disk_quota *dst) + struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; @@ -844,28 +817,25 @@ xfs_qm_scall_getquota( } memset(dst, 0, sizeof(*dst)); - dst->d_version = FS_DQUOT_VERSION; - dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags); - dst->d_id = be32_to_cpu(dqp->q_core.d_id); - dst->d_blk_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); - dst->d_blk_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); + dst->d_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); + dst->d_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit); dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit); - dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount); - dst->d_icount = dqp->q_res_icount; - dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer); - dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer); - dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns); - dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns); - dst->d_rtb_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); - dst->d_rtb_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); - dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount); - dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer); - dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns); + dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount); + dst->d_ino_count = dqp->q_res_icount; + dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer); + dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer); + dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns); + dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns); + dst->d_rt_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); + dst->d_rt_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); + dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount); + dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer); + dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns); /* * Internally, we don't reset all the timers when quota enforcement @@ -878,23 +848,23 @@ xfs_qm_scall_getquota( dqp->q_core.d_flags == XFS_DQ_GROUP) || (!XFS_IS_PQUOTA_ENFORCED(mp) && dqp->q_core.d_flags == XFS_DQ_PROJ)) { - dst->d_btimer = 0; - dst->d_itimer = 0; - dst->d_rtbtimer = 0; + dst->d_spc_timer = 0; + dst->d_ino_timer = 0; + dst->d_rt_spc_timer = 0; } #ifdef DEBUG - if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) || - (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) || - (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) && - dst->d_id != 0) { - if ((dst->d_bcount > dst->d_blk_softlimit) && - (dst->d_blk_softlimit > 0)) { - ASSERT(dst->d_btimer != 0); + if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) || + (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) || + (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) && + id != 0) { + if ((dst->d_space > dst->d_spc_softlimit) && + (dst->d_spc_softlimit > 0)) { + ASSERT(dst->d_spc_timer != 0); } - if ((dst->d_icount > dst->d_ino_softlimit) && + if ((dst->d_ino_count > dst->d_ino_softlimit) && (dst->d_ino_softlimit > 0)) { - ASSERT(dst->d_itimer != 0); + ASSERT(dst->d_ino_timer != 0); } } #endif @@ -904,26 +874,6 @@ out_put: } STATIC uint -xfs_qm_export_qtype_flags( - uint flags) -{ - /* - * Can't be more than one, or none. - */ - ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) != - (FS_PROJ_QUOTA | FS_USER_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) != - (FS_PROJ_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) != - (FS_USER_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0); - - return (flags & XFS_DQ_USER) ? - FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ? - FS_PROJ_QUOTA : FS_GROUP_QUOTA; -} - -STATIC uint xfs_qm_export_flags( uint flags) { diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7542bbeca6a1..6923905ab33d 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -64,19 +64,10 @@ xfs_fs_get_xstatev( return xfs_qm_scall_getqstatv(mp, fqs); } -STATIC int -xfs_fs_set_xstate( - struct super_block *sb, - unsigned int uflags, - int op) +static unsigned int +xfs_quota_flags(unsigned int uflags) { - struct xfs_mount *mp = XFS_M(sb); - unsigned int flags = 0; - - if (sb->s_flags & MS_RDONLY) - return -EROFS; - if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp)) - return -ENOSYS; + unsigned int flags = 0; if (uflags & FS_QUOTA_UDQ_ACCT) flags |= XFS_UQUOTA_ACCT; @@ -91,16 +82,39 @@ xfs_fs_set_xstate( if (uflags & FS_QUOTA_PDQ_ENFD) flags |= XFS_PQUOTA_ENFD; - switch (op) { - case Q_XQUOTAON: - return xfs_qm_scall_quotaon(mp, flags); - case Q_XQUOTAOFF: - if (!XFS_IS_QUOTA_ON(mp)) - return -EINVAL; - return xfs_qm_scall_quotaoff(mp, flags); - } + return flags; +} + +STATIC int +xfs_quota_enable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + + return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags)); +} + +STATIC int +xfs_quota_disable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + if (!XFS_IS_QUOTA_ON(mp)) + return -EINVAL; - return -EINVAL; + return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags)); } STATIC int @@ -131,7 +145,7 @@ STATIC int xfs_fs_get_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -141,14 +155,14 @@ xfs_fs_get_dqblk( return -ESRCH; return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } STATIC int xfs_fs_set_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -160,13 +174,14 @@ xfs_fs_set_dqblk( return -ESRCH; return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } const struct quotactl_ops xfs_quotactl_operations = { .get_xstatev = xfs_fs_get_xstatev, .get_xstate = xfs_fs_get_xstate, - .set_xstate = xfs_fs_set_xstate, + .quota_enable = xfs_quota_enable, + .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, .set_dqblk = xfs_fs_set_dqblk, |