diff options
| author | Marcel Ziswiler <marcel.ziswiler@toradex.com> | 2020-05-19 23:01:26 +0200 |
|---|---|---|
| committer | Marcel Ziswiler <marcel.ziswiler@toradex.com> | 2020-05-19 23:37:01 +0200 |
| commit | 2ae782ca839e0ee07de37122ddea362adff2e975 (patch) | |
| tree | df6b1a190760f51465122ca4c13492d5ac5984c6 /fs | |
| parent | 0a8ab17689e628c84a666195bfc6ab85d11cf057 (diff) | |
| parent | 0661b3d6cfd774e28a2e2ba90a3d87479e5c399b (diff) | |
Merge tag 'v4.9.220' into 4.9-2.3.x-imx
This is the 4.9.220 stable release
Conflicts:
arch/arm/Kconfig.debug
arch/arm/boot/dts/imx7s.dtsi
arch/arm/mach-imx/common.h
arch/arm/mach-imx/cpuidle-imx6q.c
arch/arm/mach-imx/cpuidle-imx6sx.c
arch/arm/mach-imx/suspend-imx6.S
block/blk-core.c
drivers/crypto/caam/caamalg.c
drivers/crypto/mxs-dcp.c
drivers/dma/imx-sdma.c
drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
drivers/input/keyboard/imx_keypad.c
drivers/input/keyboard/snvs_pwrkey.c
drivers/mmc/host/sdhci.c
drivers/net/can/flexcan.c
drivers/net/ethernet/freescale/fec_main.c
drivers/net/phy/phy_device.c
drivers/net/wireless/ath/ath10k/pci.c
drivers/tty/serial/imx.c
drivers/usb/dwc3/gadget.c
drivers/usb/host/xhci.c
include/linux/blkdev.h
include/linux/cpu.h
include/linux/platform_data/dma-imx-sdma.h
kernel/cpu.c
net/wireless/util.c
sound/soc/fsl/Kconfig
sound/soc/fsl/fsl_esai.c
sound/soc/fsl/fsl_sai.c
sound/soc/fsl/imx-sgtl5000.c
Diffstat (limited to 'fs')
244 files changed, 3347 insertions, 1471 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 082d227fa56b..6261719f6f2a 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -276,7 +276,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, switch (handler->flags) { case ACL_TYPE_ACCESS: if (acl) { - struct iattr iattr; + struct iattr iattr = { 0 }; struct posix_acl *old_acl = acl; retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 072e7599583a..a8ff43068619 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -59,6 +59,8 @@ enum { Opt_cache_loose, Opt_fscache, Opt_mmap, /* Access options */ Opt_access, Opt_posixacl, + /* Lock timeout option */ + Opt_locktimeout, /* Error token */ Opt_err }; @@ -78,6 +80,7 @@ static const match_table_t tokens = { {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, + {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} }; @@ -126,6 +129,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif + v9ses->session_lock_timeout = P9_LOCK_TIMEOUT; if (!opts) return 0; @@ -298,6 +302,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #endif break; + case Opt_locktimeout: + r = match_int(&args[0], &option); + if (r < 0) { + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } + if (option < 1) { + p9_debug(P9_DEBUG_ERROR, + "locktimeout must be a greater than zero integer.\n"); + ret = -EINVAL; + continue; + } + v9ses->session_lock_timeout = (long)option * HZ; + break; + default: continue; } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 443d12e02043..ce6ca9f4f683 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -116,6 +116,7 @@ struct v9fs_session_info { struct list_head slist; /* list of sessions registered with v9fs */ struct backing_dev_info bdi; struct rw_semaphore rename_sem; + long session_lock_timeout; /* retry interval for blocking locks */ }; /* cache_validity flags */ diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 6181ad79e1a5..e45b1a0dd513 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -49,8 +49,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) +static int v9fs_fid_readpage(void *data, struct page *page) { + struct p9_fid *fid = data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -121,7 +122,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) return ret; - ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp); + ret = read_cache_pages(mapping, pages, v9fs_fid_readpage, + filp->private_data); p9_debug(P9_DEBUG_VFS, " = %d\n", ret); return ret; } diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 48db9a9f13f9..cb6c4031af55 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -105,7 +105,6 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) int err = 0; struct p9_fid *fid; int buflen; - int reclen = 0; struct p9_rdir *rdir; struct kvec kvec; @@ -138,11 +137,10 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) while (rdir->head < rdir->tail) { err = p9stat_read(fid->clnt, rdir->buf + rdir->head, rdir->tail - rdir->head, &st); - if (err) { + if (err <= 0) { p9_debug(P9_DEBUG_VFS, "returned %d\n", err); return -EIO; } - reclen = st.size+2; over = !dir_emit(ctx, st.name, strlen(st.name), v9fs_qid2ino(&st.qid), dt_type(&st)); @@ -150,8 +148,8 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) if (over) return 0; - rdir->head += reclen; - ctx->pos += reclen; + rdir->head += err; + ctx->pos += err; } } } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 2f035b15180e..e963b83afc71 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) uint8_t status = P9_LOCK_ERROR; int res = 0; unsigned char fl_type; + struct v9fs_session_info *v9ses; fid = filp->private_data; BUG_ON(fid == NULL); @@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if (IS_SETLKW(cmd)) flock.flags = P9_LOCK_FLAGS_BLOCK; + v9ses = v9fs_inode2v9ses(file_inode(filp)); + /* * if its a blocked request and we get P9_LOCK_BLOCKED as the status * for lock request, keep on trying @@ -202,7 +205,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) break; - if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) + if (schedule_timeout_interruptible(v9ses->session_lock_timeout) + != 0) break; /* * p9_client_lock_dotl overwrites flock.client_id with the @@ -524,6 +528,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) v9inode = V9FS_I(inode); mutex_lock(&v9inode->v_mutex); if (!v9inode->writeback_fid && + (vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) { /* * clone a fid and add it to writeback_fid @@ -625,6 +630,8 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) (vma->vm_end - vma->vm_start - 1), }; + if (!(vma->vm_flags & VM_SHARED)) + return; p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma); diff --git a/fs/adfs/super.c b/fs/adfs/super.c index c9fdfb112933..e42c30001509 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -368,6 +368,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) struct buffer_head *bh; struct object_info root_obj; unsigned char *b_data; + unsigned int blocksize; struct adfs_sb_info *asb; struct inode *root; int ret = -EINVAL; @@ -419,8 +420,10 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent) goto error_free_bh; } + blocksize = 1 << dr->log2secsize; brelse(bh); - if (sb_set_blocksize(sb, 1 << dr->log2secsize)) { + + if (sb_set_blocksize(sb, blocksize)) { bh = sb_bread(sb, ADFS_DISCRECORD / sb->s_blocksize); if (!bh) { adfs_error(sb, "couldn't read superblock on " diff --git a/fs/afs/super.c b/fs/afs/super.c index fbdb022b75a2..65389394e202 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -317,6 +317,7 @@ static int afs_fill_super(struct super_block *sb, /* fill in the superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; sb->s_bdi = &as->volume->bdi; diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 2e1f50e467f1..02f0d373adbf 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -469,9 +469,10 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, */ flags &= ~AUTOFS_EXP_LEAVES; found = should_expire(expired, mnt, timeout, how); - if (!found || found != expired) - /* Something has changed, continue */ + if (found != expired) { // something has changed, continue + dput(found); goto next; + } if (expired != dentry) dput(dentry); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 9b2917a30294..b18543b36ae1 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -859,9 +859,14 @@ err: static int load_flat_shared_library(int id, struct lib_info *libs) { + /* + * This is a fake bprm struct; only the members "buf", "file" and + * "filename" are actually used. + */ struct linux_binprm bprm; int res; char buf[16]; + loff_t pos = 0; memset(&bprm, 0, sizeof(bprm)); @@ -875,25 +880,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; - bprm.cred = prepare_exec_creds(); - res = -ENOMEM; - if (!bprm.cred) - goto out; - - /* We don't really care about recalculating credentials at this point - * as we're past the point of no return and are dealing with shared - * libraries. - */ - bprm.cred_prepared = 1; + res = kernel_read(bprm.file, pos, bprm.buf, BINPRM_BUF_SIZE); - res = prepare_binprm(&bprm); - - if (!res) + if (res >= 0) res = load_flat_file(&bprm, libs, id, NULL); - abort_creds(bprm.cred); - -out: allow_write_access(bprm.file); fput(bprm.file); diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index afdf4e3cafc2..37c2093a24d3 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -14,14 +14,31 @@ #include <linux/err.h> #include <linux/fs.h> +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline char *next_non_spacetab(char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline char *next_terminator(char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + static int load_script(struct linux_binprm *bprm) { const char *i_arg, *i_name; - char *cp; + char *cp, *buf_end; struct file *file; char interp[BINPRM_BUF_SIZE]; int retval; + /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; @@ -34,18 +51,40 @@ static int load_script(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - /* - * This section does the #! interpretation. - * Sorta complicated, but hopefully it will work. -TYT - */ - + /* Release since we are not mapping a binary into memory. */ allow_write_access(bprm->file); fput(bprm->file); bprm->file = NULL; - bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; - if ((cp = strchr(bprm->buf, '\n')) == NULL) - cp = bprm->buf+BINPRM_BUF_SIZE-1; + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!cp) { + cp = next_non_spacetab(bprm->buf + 2, buf_end); + if (!cp) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(cp, buf_end)) + return -ENOEXEC; + cp = buf_end; + } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; while (cp > bprm->buf) { cp--; diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index ff0b0be92d61..5456937836b8 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -265,16 +265,17 @@ out: } } -static void run_ordered_work(struct __btrfs_workqueue *wq) +static void run_ordered_work(struct __btrfs_workqueue *wq, + struct btrfs_work *self) { struct list_head *list = &wq->ordered_list; struct btrfs_work *work; spinlock_t *lock = &wq->list_lock; unsigned long flags; + void *wtag; + bool free_self = false; while (1) { - void *wtag; - spin_lock_irqsave(lock, flags); if (list_empty(list)) break; @@ -300,16 +301,47 @@ static void run_ordered_work(struct __btrfs_workqueue *wq) list_del(&work->ordered_list); spin_unlock_irqrestore(lock, flags); - /* - * We don't want to call the ordered free functions with the - * lock held though. Save the work as tag for the trace event, - * because the callback could free the structure. - */ - wtag = work; - work->ordered_free(work); - trace_btrfs_all_work_done(wq->fs_info, wtag); + if (work == self) { + /* + * This is the work item that the worker is currently + * executing. + * + * The kernel workqueue code guarantees non-reentrancy + * of work items. I.e., if a work item with the same + * address and work function is queued twice, the second + * execution is blocked until the first one finishes. A + * work item may be freed and recycled with the same + * work function; the workqueue code assumes that the + * original work item cannot depend on the recycled work + * item in that case (see find_worker_executing_work()). + * + * Note that the work of one Btrfs filesystem may depend + * on the work of another Btrfs filesystem via, e.g., a + * loop device. Therefore, we must not allow the current + * work item to be recycled until we are really done, + * otherwise we break the above assumption and can + * deadlock. + */ + free_self = true; + } else { + /* + * We don't want to call the ordered free functions with + * the lock held though. Save the work as tag for the + * trace event, because the callback could free the + * structure. + */ + wtag = work; + work->ordered_free(work); + trace_btrfs_all_work_done(wq->fs_info, wtag); + } } spin_unlock_irqrestore(lock, flags); + + if (free_self) { + wtag = self; + self->ordered_free(self); + trace_btrfs_all_work_done(wq->fs_info, wtag); + } } static void normal_work_helper(struct btrfs_work *work) @@ -337,7 +369,7 @@ static void normal_work_helper(struct btrfs_work *work) work->func(work); if (need_order) { set_bit(WORK_DONE_BIT, &work->flags); - run_ordered_work(wq); + run_ordered_work(wq, work); } if (!need_order) trace_btrfs_all_work_done(wq->fs_info, wtag); @@ -415,3 +447,11 @@ void btrfs_set_work_high_priority(struct btrfs_work *work) { set_bit(WORK_HIGH_PRIO_BIT, &work->flags); } + +void btrfs_flush_workqueue(struct btrfs_workqueue *wq) +{ + if (wq->high) + flush_workqueue(wq->high->normal_wq); + + flush_workqueue(wq->normal->normal_wq); +} diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 1f9597355c9d..a0f6986806a4 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -85,4 +85,6 @@ void btrfs_set_work_high_priority(struct btrfs_work *work); struct btrfs_fs_info *btrfs_work_owner(struct btrfs_work *work); struct btrfs_fs_info *btrfs_workqueue_owner(struct __btrfs_workqueue *wq); bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq); +void btrfs_flush_workqueue(struct btrfs_workqueue *wq); + #endif diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 85dc7ab8f89e..2973d256bb44 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2018,13 +2018,19 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, extent_item_objectid); if (!search_commit_root) { - trans = btrfs_join_transaction(fs_info->extent_root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + trans = btrfs_attach_transaction(fs_info->extent_root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && + PTR_ERR(trans) != -EROFS) + return PTR_ERR(trans); + trans = NULL; + } + } + + if (trans) btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); - } else { + else down_read(&fs_info->commit_root_sem); - } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, tree_mod_seq_elem.seq, &refs, @@ -2056,7 +2062,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, free_leaf_list(refs); out: - if (!search_commit_root) { + if (trans) { btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_end_transaction(trans, fs_info->extent_root); } else { diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c94d3390cbfc..b5ebb43b1824 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -331,26 +331,6 @@ struct tree_mod_elem { struct tree_mod_root old_root; }; -static inline void tree_mod_log_read_lock(struct btrfs_fs_info *fs_info) -{ - read_lock(&fs_info->tree_mod_log_lock); -} - -static inline void tree_mod_log_read_unlock(struct btrfs_fs_info *fs_info) -{ - read_unlock(&fs_info->tree_mod_log_lock); -} - -static inline void tree_mod_log_write_lock(struct btrfs_fs_info *fs_info) -{ - write_lock(&fs_info->tree_mod_log_lock); -} - -static inline void tree_mod_log_write_unlock(struct btrfs_fs_info *fs_info) -{ - write_unlock(&fs_info->tree_mod_log_lock); -} - /* * Pull a new tree mod seq number for our operation. */ @@ -370,14 +350,12 @@ static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info) u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info, struct seq_list *elem) { - tree_mod_log_write_lock(fs_info); - spin_lock(&fs_info->tree_mod_seq_lock); + write_lock(&fs_info->tree_mod_log_lock); if (!elem->seq) { elem->seq = btrfs_inc_tree_mod_seq(fs_info); list_add_tail(&elem->list, &fs_info->tree_mod_seq_list); } - spin_unlock(&fs_info->tree_mod_seq_lock); - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); return elem->seq; } @@ -396,7 +374,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, if (!seq_putting) return; - spin_lock(&fs_info->tree_mod_seq_lock); + write_lock(&fs_info->tree_mod_log_lock); list_del(&elem->list); elem->seq = 0; @@ -407,29 +385,27 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, * blocker with lower sequence number exists, we * cannot remove anything from the log */ - spin_unlock(&fs_info->tree_mod_seq_lock); + write_unlock(&fs_info->tree_mod_log_lock); return; } min_seq = cur_elem->seq; } } - spin_unlock(&fs_info->tree_mod_seq_lock); /* * anything that's lower than the lowest existing (read: blocked) * sequence number can be removed from the tree. */ - tree_mod_log_write_lock(fs_info); tm_root = &fs_info->tree_mod_log; for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); tm = container_of(node, struct tree_mod_elem, node); - if (tm->seq > min_seq) + if (tm->seq >= min_seq) continue; rb_erase(node, tm_root); kfree(tm); } - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); } /* @@ -440,7 +416,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, * for root replace operations, or the logical address of the affected * block for all other operations. * - * Note: must be called with write lock (tree_mod_log_write_lock). + * Note: must be called with write lock for fs_info::tree_mod_log_lock. */ static noinline int __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) @@ -480,7 +456,7 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) * Determines if logging can be omitted. Returns 1 if it can. Otherwise, it * returns zero with the tree_mod_log_lock acquired. The caller must hold * this until all tree mod log insertions are recorded in the rb tree and then - * call tree_mod_log_write_unlock() to release. + * write unlock fs_info::tree_mod_log_lock. */ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { @@ -490,9 +466,9 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, if (eb && btrfs_header_level(eb) == 0) return 1; - tree_mod_log_write_lock(fs_info); + write_lock(&fs_info->tree_mod_log_lock); if (list_empty(&(fs_info)->tree_mod_seq_list)) { - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); return 1; } @@ -556,7 +532,7 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, } ret = __tree_mod_log_insert(fs_info, tm); - tree_mod_log_write_unlock(fs_info); + write_unlock(&eb->fs_info->tree_mod_log_lock); if (ret) kfree(tm); @@ -620,7 +596,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, ret = __tree_mod_log_insert(fs_info, tm); if (ret) goto free_tms; - tree_mod_log_write_unlock(fs_info); + write_unlock(&eb->fs_info->tree_mod_log_lock); kfree(tm_list); return 0; @@ -631,7 +607,7 @@ free_tms: kfree(tm_list[i]); } if (locked) - tree_mod_log_write_unlock(fs_info); + write_unlock(&eb->fs_info->tree_mod_log_lock); kfree(tm_list); kfree(tm); @@ -712,7 +688,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, if (!ret) ret = __tree_mod_log_insert(fs_info, tm); - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); if (ret) goto free_tms; kfree(tm_list); @@ -739,7 +715,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq, struct tree_mod_elem *cur = NULL; struct tree_mod_elem *found = NULL; - tree_mod_log_read_lock(fs_info); + read_lock(&fs_info->tree_mod_log_lock); tm_root = &fs_info->tree_mod_log; node = tm_root->rb_node; while (node) { @@ -767,7 +743,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq, break; } } - tree_mod_log_read_unlock(fs_info); + read_unlock(&fs_info->tree_mod_log_lock); return found; } @@ -848,7 +824,7 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, goto free_tms; } - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); kfree(tm_list); return 0; @@ -860,7 +836,7 @@ free_tms: kfree(tm_list[i]); } if (locked) - tree_mod_log_write_unlock(fs_info); + write_unlock(&fs_info->tree_mod_log_lock); kfree(tm_list); return ret; @@ -920,7 +896,7 @@ tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) goto free_tms; ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems); - tree_mod_log_write_unlock(fs_info); + write_unlock(&eb->fs_info->tree_mod_log_lock); if (ret) goto free_tms; kfree(tm_list); @@ -1271,7 +1247,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, unsigned long p_size = sizeof(struct btrfs_key_ptr); n = btrfs_header_nritems(eb); - tree_mod_log_read_lock(fs_info); + read_lock(&fs_info->tree_mod_log_lock); while (tm && tm->seq >= time_seq) { /* * all the operations are recorded with the operator used for @@ -1326,7 +1302,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, if (tm->logical != first_tm->logical) break; } - tree_mod_log_read_unlock(fs_info); + read_unlock(&fs_info->tree_mod_log_lock); btrfs_set_header_nritems(eb, n); } @@ -1406,6 +1382,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq) struct tree_mod_elem *tm; struct extent_buffer *eb = NULL; struct extent_buffer *eb_root; + u64 eb_root_owner = 0; struct extent_buffer *old; struct tree_mod_root *old_root = NULL; u64 old_generation = 0; @@ -1439,6 +1416,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq) free_extent_buffer(old); } } else if (old_root) { + eb_root_owner = btrfs_header_owner(eb_root); btrfs_tree_read_unlock(eb_root); free_extent_buffer(eb_root); eb = alloc_dummy_extent_buffer(root->fs_info, logical, @@ -1457,7 +1435,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (old_root) { btrfs_set_header_bytenr(eb, eb->start); btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); - btrfs_set_header_owner(eb, btrfs_header_owner(eb_root)); + btrfs_set_header_owner(eb, eb_root_owner); btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } @@ -2971,6 +2949,10 @@ int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, again: b = get_old_root(root, time_seq); + if (!b) { + ret = -EIO; + goto done; + } level = btrfs_header_level(b); p->locks[level] = BTRFS_READ_LOCK; @@ -5465,6 +5447,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, advance_left = advance_right = 0; while (1) { + cond_resched(); if (advance_left && !left_end_reached) { ret = tree_advance(left_root, left_path, &left_level, left_root_level, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a423c36bcd72..2bc37d03d407 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -851,14 +851,12 @@ struct btrfs_fs_info { struct list_head delayed_iputs; struct mutex cleaner_delayed_iput_mutex; - /* this protects tree_mod_seq_list */ - spinlock_t tree_mod_seq_lock; atomic64_t tree_mod_seq; - struct list_head tree_mod_seq_list; - /* this protects tree_mod_log */ + /* this protects tree_mod_log and tree_mod_seq_list */ rwlock_t tree_mod_log_lock; struct rb_root tree_mod_log; + struct list_head tree_mod_seq_list; atomic_t nr_async_submits; atomic_t async_submit_draining; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 8d93854a4b4f..c1ca4ce11e69 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -193,8 +193,6 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans, ref->in_tree = 0; btrfs_put_delayed_ref(ref); atomic_dec(&delayed_refs->num_entries); - if (trans->delayed_ref_updates) - trans->delayed_ref_updates--; } static bool merge_ref(struct btrfs_trans_handle *trans, @@ -281,7 +279,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, if (head->is_data) return; - spin_lock(&fs_info->tree_mod_seq_lock); + read_lock(&fs_info->tree_mod_log_lock); if (!list_empty(&fs_info->tree_mod_seq_list)) { struct seq_list *elem; @@ -289,7 +287,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, struct seq_list, list); seq = elem->seq; } - spin_unlock(&fs_info->tree_mod_seq_lock); + read_unlock(&fs_info->tree_mod_log_lock); ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node, list); @@ -317,7 +315,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, struct seq_list *elem; int ret = 0; - spin_lock(&fs_info->tree_mod_seq_lock); + read_lock(&fs_info->tree_mod_log_lock); if (!list_empty(&fs_info->tree_mod_seq_list)) { elem = list_first_entry(&fs_info->tree_mod_seq_list, struct seq_list, list); @@ -331,7 +329,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, } } - spin_unlock(&fs_info->tree_mod_seq_lock); + read_unlock(&fs_info->tree_mod_log_lock); return ret; } @@ -445,7 +443,6 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans, add_tail: list_add_tail(&ref->list, &href->ref_list); atomic_inc(&root->num_entries); - trans->delayed_ref_updates++; spin_unlock(&href->lock); return ret; } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index fb973cc0af66..395b07764269 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -511,18 +511,27 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, } btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1); - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); - return PTR_ERR(trans); + while (1) { + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); + return PTR_ERR(trans); + } + ret = btrfs_commit_transaction(trans, root); + WARN_ON(ret); + mutex_lock(&uuid_mutex); + /* keep away write_all_supers() during the finishing procedure */ + mutex_lock(&root->fs_info->fs_devices->device_list_mutex); + mutex_lock(&root->fs_info->chunk_mutex); + if (src_device->has_pending_chunks) { + mutex_unlock(&root->fs_info->chunk_mutex); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); + mutex_unlock(&uuid_mutex); + } else { + break; + } } - ret = btrfs_commit_transaction(trans, root); - WARN_ON(ret); - mutex_lock(&uuid_mutex); - /* keep away write_all_supers() during the finishing procedure */ - mutex_lock(&root->fs_info->fs_devices->device_list_mutex); - mutex_lock(&root->fs_info->chunk_mutex); btrfs_dev_replace_lock(dev_replace, 1); dev_replace->replace_state = scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9d3352fe8dc9..1de017051928 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1712,8 +1712,8 @@ static void end_workqueue_fn(struct btrfs_work *work) bio->bi_error = end_io_wq->error; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; - kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); bio_endio(bio); + kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); } static int cleaner_kthread(void *arg) @@ -2104,7 +2104,7 @@ static void free_root_extent_buffers(struct btrfs_root *root) } /* helper to cleanup tree roots */ -static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root) { free_root_extent_buffers(info->tree_root); @@ -2113,7 +2113,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) free_root_extent_buffers(info->csum_root); free_root_extent_buffers(info->quota_root); free_root_extent_buffers(info->uuid_root); - if (chunk_root) + if (free_chunk_root) free_root_extent_buffers(info->chunk_root); free_root_extent_buffers(info->free_space_root); } @@ -2519,7 +2519,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->free_chunk_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->buffer_lock); @@ -2980,6 +2979,7 @@ retry_root_backup: /* do not make disk changes in broken FS or nologreplay is given */ if (btrfs_super_log_root(disk_super) != 0 && !btrfs_test_opt(tree_root->fs_info, NOLOGREPLAY)) { + btrfs_info(fs_info, "start tree-log replay"); ret = btrfs_replay_log(fs_info, fs_devices); if (ret) { err = ret; @@ -3136,7 +3136,7 @@ fail_block_groups: btrfs_free_block_groups(fs_info); fail_tree_roots: - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); fail_sb_buffer: @@ -3165,7 +3165,7 @@ recovery_tree_root: if (!btrfs_test_opt(tree_root->fs_info, USEBACKUPROOT)) goto fail_tree_roots; - free_root_pointers(fs_info, 0); + free_root_pointers(fs_info, false); /* don't use the log in recovery mode, it won't be valid */ btrfs_set_super_log_root(disk_super, 0); @@ -3825,6 +3825,19 @@ void close_ctree(struct btrfs_root *root) */ btrfs_delete_unused_bgs(root->fs_info); + /* + * There might be existing delayed inode workers still running + * and holding an empty delayed inode item. We must wait for + * them to complete first because they can create a transaction. + * This happens when someone calls btrfs_balance_delayed_items() + * and then a transaction commit runs the same delayed nodes + * before any delayed worker has done something with the nodes. + * We must wait for any worker here and not at transaction + * commit time since that could cause a deadlock. + * This is a very rare case. + */ + btrfs_flush_workqueue(fs_info->delayed_workers); + ret = btrfs_commit_super(root); if (ret) btrfs_err(fs_info, "commit super ret %d", ret); @@ -3862,7 +3875,7 @@ void close_ctree(struct btrfs_root *root) btrfs_stop_all_workers(fs_info); clear_bit(BTRFS_FS_OPEN, &fs_info->flags); - free_root_pointers(fs_info, 1); + free_root_pointers(fs_info, true); iput(fs_info->btree_inode); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7938c48c72ff..538f378eea52 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7571,6 +7571,14 @@ search: */ if ((flags & extra) && !(block_group->flags & extra)) goto loop; + + /* + * This block group has different flags than we want. + * It's possible that we have MIXED_GROUP flag but no + * block group is mixed. Just skip such block group. + */ + btrfs_release_block_group(block_group, delalloc); + continue; } have_block_group: @@ -10317,6 +10325,7 @@ int btrfs_read_block_groups(struct btrfs_root *root) btrfs_err(info, "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups", cache->key.objectid); + btrfs_put_block_group(cache); ret = -EINVAL; goto error; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4d901200be13..1372d3e5d90b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4060,6 +4060,14 @@ retry: */ scanned = 1; index = 0; + + /* + * If we're looping we could run into a page that is locked by a + * writer and that writer could be waiting on writeback for a + * page in our current bio, and thus deadlock, so flush the + * write bio here. + */ + flush_write_bio(data); goto retry; } @@ -4994,12 +5002,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return eb; eb = alloc_dummy_extent_buffer(fs_info, start, nodesize); if (!eb) - return NULL; + return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: ret = radix_tree_preload(GFP_NOFS); - if (ret) + if (ret) { + exists = ERR_PTR(ret); goto free_eb; + } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, start >> PAGE_SHIFT, eb); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 26f9ac719d20..4f59b4089eb0 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -227,6 +227,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) struct extent_map *merge = NULL; struct rb_node *rb; + /* + * We can't modify an extent map that is in the tree and that is being + * used by another task, as it can cause that other task to see it in + * inconsistent state during the merging. We always have 1 reference for + * the tree and 1 for this task (which is unpinning the extent map or + * clearing the logging flag), so anything > 2 means it's being used by + * other tasks too. + */ + if (atomic_read(&em->refs) > 2) + return; + if (em->start != 0) { rb = rb_prev(&em->rb_node); if (rb) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 437544846e4e..03661b744eaf 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1555,6 +1555,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, break; } + only_release_metadata = false; sector_offset = pos & (root->sectorsize - 1); reserve_bytes = round_up(write_bytes + sector_offset, root->sectorsize); @@ -1704,7 +1705,6 @@ again: set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, EXTENT_NORESERVE, NULL, NULL, GFP_NOFS); - only_release_metadata = false; } btrfs_drop_pages(pages, num_pages); @@ -1952,6 +1952,18 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) u64 len; /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * The range length can be represented by u64, we have to do the typecasts * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() */ @@ -2634,6 +2646,11 @@ out_only_mutex: * for detecting, at fsync time, if the inode isn't yet in the * log tree or it's there but not up to date. */ + struct timespec now = current_time(inode); + + inode_inc_iversion(inode); + inode->i_mtime = now; + inode->i_ctime = now; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { err = PTR_ERR(trans); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 69a3c11af9d4..a84a1ceb260a 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -391,6 +391,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); lock_page(page); + if (page->mapping != inode->i_mapping) { + btrfs_err(BTRFS_I(inode)->root->fs_info, + "free space cache page truncated"); + io_ctl_drop_pages(io_ctl); + return -EIO; + } if (!PageUptodate(page)) { btrfs_err(BTRFS_I(inode)->root->fs_info, "error reading free space cache"); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index d27014b8bf72..075b59516c8c 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -159,6 +159,7 @@ static void start_caching(struct btrfs_root *root) spin_lock(&root->ino_cache_lock); root->ino_cache_state = BTRFS_CACHE_FINISHED; spin_unlock(&root->ino_cache_lock); + wake_up(&root->ino_cache_wait); return; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a609d2017a63..f56610ad64bd 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5576,7 +5576,6 @@ static void inode_tree_del(struct inode *inode) spin_unlock(&root->inode_lock); if (empty && btrfs_root_refs(&root->root_item) == 0) { - synchronize_srcu(&root->fs_info->subvol_srcu); spin_lock(&root->inode_lock); empty = RB_EMPTY_ROOT(&root->inode_tree); spin_unlock(&root->inode_lock); @@ -9596,9 +9595,8 @@ static int btrfs_rename_exchange(struct inode *old_dir, return -EXDEV; /* close the race window with snapshot create/destroy ioctl */ - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) - down_read(&root->fs_info->subvol_sem); - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + if (old_ino == BTRFS_FIRST_FREE_OBJECTID || + new_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&dest->fs_info->subvol_sem); /* @@ -9615,6 +9613,9 @@ static int btrfs_rename_exchange(struct inode *old_dir, goto out_notrans; } + if (dest != root) + btrfs_record_root_in_trans(trans, dest); + /* * We need to find a free sequence number both in the source and * in the destination directory for the exchange. @@ -9781,9 +9782,8 @@ out_fail: ret2 = btrfs_end_transaction(trans, root); ret = ret ? ret : ret2; out_notrans: - if (new_ino == BTRFS_FIRST_FREE_OBJECTID) - up_read(&dest->fs_info->subvol_sem); - if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + if (new_ino == BTRFS_FIRST_FREE_OBJECTID || + old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&root->fs_info->subvol_sem); return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 242584a0d3b5..eefe103c65da 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -385,6 +385,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * If the fs is mounted with nologreplay, which requires it to be + * mounted in RO mode as well, we can not allow discard on free space + * inside block groups, because log trees refer to extents that are not + * pinned in a block group's free space cache (pinning the extents is + * precisely the first phase of replaying a log tree). + */ + if (btrfs_test_opt(fs_info, NOLOGREPLAY)) + return -EROFS; + rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { @@ -600,12 +610,18 @@ static noinline int create_subvol(struct inode *dir, btrfs_i_size_write(dir, dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_add_root_ref(trans, root->fs_info->tree_root, objectid, root->root_key.objectid, btrfs_ino(dir), index, name, namelen); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root, root_item->uuid, BTRFS_UUID_KEY_SUBVOL, diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index b2d1e95de7be..7dc2284017fa 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -837,10 +837,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) } btrfs_start_ordered_extent(inode, ordered, 1); end = ordered->file_offset; + /* + * If the ordered extent had an error save the error but don't + * exit without waiting first for all other ordered extents in + * the range to complete. + */ if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) ret = -EIO; btrfs_put_ordered_extent(ordered); - if (ret || end == 0 || end == start) + if (end == 0 || end == start) break; end--; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index f25233093d68..0355e6d9e21c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -759,10 +759,10 @@ out: return ret; } -static int update_qgroup_status_item(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, - struct btrfs_root *root) +static int update_qgroup_status_item(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *quota_root = fs_info->quota_root; struct btrfs_path *path; struct btrfs_key key; struct extent_buffer *l; @@ -778,7 +778,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - ret = btrfs_search_slot(trans, root, &key, path, 0, 1); + ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1); if (ret > 0) ret = -ENOENT; @@ -1863,7 +1863,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON; spin_unlock(&fs_info->qgroup_lock); - ret = update_qgroup_status_item(trans, fs_info, quota_root); + ret = update_qgroup_status_item(trans); if (ret) fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -2380,9 +2380,6 @@ out: btrfs_free_path(path); mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) - fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; - if (err > 0 && fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) { fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -2398,16 +2395,30 @@ out: trans = btrfs_start_transaction(fs_info->quota_root, 1); if (IS_ERR(trans)) { err = PTR_ERR(trans); + trans = NULL; btrfs_err(fs_info, "fail to start transaction for status update: %d\n", err); - goto done; } - ret = update_qgroup_status_item(trans, fs_info, fs_info->quota_root); - if (ret < 0) { - err = ret; - btrfs_err(fs_info, "fail to update qgroup status: %d", err); + + mutex_lock(&fs_info->qgroup_rescan_lock); + if (!btrfs_fs_closing(fs_info)) + fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; + if (trans) { + ret = update_qgroup_status_item(trans); + if (ret < 0) { + err = ret; + btrfs_err(fs_info, "fail to update qgroup status: %d", + err); + } } + fs_info->qgroup_rescan_running = false; + complete_all(&fs_info->qgroup_rescan_completion); + mutex_unlock(&fs_info->qgroup_rescan_lock); + + if (!trans) + return; + btrfs_end_transaction(trans, fs_info->quota_root); if (btrfs_fs_closing(fs_info)) { @@ -2418,12 +2429,6 @@ out: } else { btrfs_err(fs_info, "qgroup scan failed with %d", err); } - -done: - mutex_lock(&fs_info->qgroup_rescan_lock); - fs_info->qgroup_rescan_running = false; - mutex_unlock(&fs_info->qgroup_rescan_lock); - complete_all(&fs_info->qgroup_rescan_completion); } /* diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index af6a776fa18c..5aa07de5750e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2395,8 +2395,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bitmap_clear(rbio->dbitmap, pagenr, 1); kunmap(p); - for (stripe = 0; stripe < rbio->real_stripes; stripe++) + for (stripe = 0; stripe < nr_data; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); + kunmap(p_page); } __free_page(p_page); diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 75bab76739be..0d1565d71231 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -734,21 +734,19 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info, static void reada_start_machine_worker(struct btrfs_work *work) { struct reada_machine_work *rmw; - struct btrfs_fs_info *fs_info; int old_ioprio; rmw = container_of(work, struct reada_machine_work, work); - fs_info = rmw->fs_info; - - kfree(rmw); old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current), task_nice_ioprio(current)); set_task_ioprio(current, BTRFS_IOPRIO_READA); - __reada_start_machine(fs_info); + __reada_start_machine(rmw->fs_info); set_task_ioprio(current, old_ioprio); - atomic_dec(&fs_info->reada_works_cnt); + atomic_dec(&rmw->fs_info->reada_works_cnt); + + kfree(rmw); } static void __reada_start_machine(struct btrfs_fs_info *fs_info) @@ -759,6 +757,7 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info) u64 total = 0; int i; +again: do { enqueued = 0; mutex_lock(&fs_devices->device_list_mutex); @@ -771,6 +770,10 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info) mutex_unlock(&fs_devices->device_list_mutex); total += enqueued; } while (enqueued && total < 10000); + if (fs_devices->seed) { + fs_devices = fs_devices->seed; + goto again; + } if (enqueued == 0) return; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b0c3a6afe664..1003b983a8d7 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -537,8 +537,8 @@ static int should_ignore_root(struct btrfs_root *root) if (!reloc_root) return 0; - if (btrfs_root_last_snapshot(&reloc_root->root_item) == - root->fs_info->running_transaction->transid - 1) + if (btrfs_header_generation(reloc_root->commit_root) == + root->fs_info->running_transaction->transid) return 0; /* * if there is reloc tree and it was created in previous @@ -1185,7 +1185,7 @@ out: free_backref_node(cache, lower); } - free_backref_node(cache, node); + remove_backref_node(cache, node); return ERR_PTR(err); } ASSERT(!node || !node->detached); @@ -1296,7 +1296,7 @@ static int __must_check __add_reloc_root(struct btrfs_root *root) if (!node) return -ENOMEM; - node->bytenr = root->node->start; + node->bytenr = root->commit_root->start; node->data = root; spin_lock(&rc->reloc_root_tree.lock); @@ -1328,10 +1328,11 @@ static void __del_reloc_root(struct btrfs_root *root) if (rc && root->node) { spin_lock(&rc->reloc_root_tree.lock); rb_node = tree_search(&rc->reloc_root_tree.rb_root, - root->node->start); + root->commit_root->start); if (rb_node) { node = rb_entry(rb_node, struct mapping_node, rb_node); rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root); + RB_CLEAR_NODE(&node->rb_node); } spin_unlock(&rc->reloc_root_tree.lock); if (!node) @@ -1349,7 +1350,7 @@ static void __del_reloc_root(struct btrfs_root *root) * helper to update the 'address of tree root -> reloc tree' * mapping */ -static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr) +static int __update_reloc_root(struct btrfs_root *root) { struct rb_node *rb_node; struct mapping_node *node = NULL; @@ -1357,7 +1358,7 @@ static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr) spin_lock(&rc->reloc_root_tree.lock); rb_node = tree_search(&rc->reloc_root_tree.rb_root, - root->node->start); + root->commit_root->start); if (rb_node) { node = rb_entry(rb_node, struct mapping_node, rb_node); rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root); @@ -1369,7 +1370,7 @@ static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr) BUG_ON((struct btrfs_root *)node->data != root); spin_lock(&rc->reloc_root_tree.lock); - node->bytenr = new_bytenr; + node->bytenr = root->node->start; rb_node = tree_insert(&rc->reloc_root_tree.rb_root, node->bytenr, &node->rb_node); spin_unlock(&rc->reloc_root_tree.lock); @@ -1519,6 +1520,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, } if (reloc_root->commit_root != reloc_root->node) { + __update_reloc_root(reloc_root); btrfs_set_root_node(root_item, reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->commit_root = btrfs_root_node(reloc_root); @@ -2457,7 +2459,21 @@ out: free_reloc_roots(&reloc_roots); } - BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root)); + /* + * We used to have + * + * BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root)); + * + * here, but it's wrong. If we fail to start the transaction in + * prepare_to_merge() we will have only 0 ref reloc roots, none of which + * have actually been removed from the reloc_root_tree rb tree. This is + * fine because we're bailing here, and we hold a reference on the root + * for the list that holds it, so these roots will be cleaned up when we + * do the reloc_dirty_list afterwards. Meanwhile the root->reloc_root + * will be cleaned up on unmount. + * + * The remaining nodes will be cleaned up by free_reloc_control. + */ } static void free_block_list(struct rb_root *blocks) @@ -4587,6 +4603,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) reloc_root->root_key.offset); if (IS_ERR(fs_root)) { err = PTR_ERR(fs_root); + list_add_tail(&reloc_root->root_list, &reloc_roots); goto out_free; } @@ -4702,11 +4719,6 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, BUG_ON(rc->stage == UPDATE_DATA_PTRS && root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); - if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { - if (buf == root->node) - __update_reloc_root(root, cow->start); - } - level = btrfs_header_level(buf); if (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item)) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index edae751e870c..307b8baaf0e9 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -144,10 +144,8 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, 0, 1); - if (ret < 0) { - btrfs_abort_transaction(trans, ret); + if (ret < 0) goto out; - } if (ret != 0) { btrfs_print_leaf(root, path->nodes[0]); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index a45f26ac5da7..edfc7ba38b33 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -37,6 +37,14 @@ #include "compression.h" /* + * Maximum number of references an extent can have in order for us to attempt to + * issue clone operations instead of write operations. This currently exists to + * avoid hitting limitations of the backreference walking code (taking a lot of + * time and using too much memory for extents with large number of references). + */ +#define SEND_MAX_EXTENT_REFS 64 + +/* * A fs_path is a helper to dynamically build path names with unknown size. * It reallocates the internal buffer on demand. * It allows fast adding of path elements on the right side (normal path) and @@ -1327,6 +1335,7 @@ static int find_extent_clone(struct send_ctx *sctx, struct clone_root *cur_clone_root; struct btrfs_key found_key; struct btrfs_path *tmp_path; + struct btrfs_extent_item *ei; int compressed; u32 i; @@ -1376,7 +1385,6 @@ static int find_extent_clone(struct send_ctx *sctx, ret = extent_from_logical(fs_info, disk_byte, tmp_path, &found_key, &flags); up_read(&fs_info->commit_root_sem); - btrfs_release_path(tmp_path); if (ret < 0) goto out; @@ -1385,6 +1393,21 @@ static int find_extent_clone(struct send_ctx *sctx, goto out; } + ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0], + struct btrfs_extent_item); + /* + * Backreference walking (iterate_extent_inodes() below) is currently + * too expensive when an extent has a large number of references, both + * in time spent and used memory. So for now just fallback to write + * operations instead of clone operations when an extent has more than + * a certain amount of references. + */ + if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) { + ret = -ENOENT; + goto out; + } + btrfs_release_path(tmp_path); + /* * Setup the clone roots. */ @@ -5835,68 +5858,21 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - if (sctx->cur_ino != sctx->cmp_key->objectid) { - - if (result == BTRFS_COMPARE_TREE_CHANGED) { - struct extent_buffer *leaf_l; - struct extent_buffer *leaf_r; - struct btrfs_file_extent_item *ei_l; - struct btrfs_file_extent_item *ei_r; - - leaf_l = sctx->left_path->nodes[0]; - leaf_r = sctx->right_path->nodes[0]; - ei_l = btrfs_item_ptr(leaf_l, - sctx->left_path->slots[0], - struct btrfs_file_extent_item); - ei_r = btrfs_item_ptr(leaf_r, - sctx->right_path->slots[0], - struct btrfs_file_extent_item); - - /* - * We may have found an extent item that has changed - * only its disk_bytenr field and the corresponding - * inode item was not updated. This case happens due to - * very specific timings during relocation when a leaf - * that contains file extent items is COWed while - * relocation is ongoing and its in the stage where it - * updates data pointers. So when this happens we can - * safely ignore it since we know it's the same extent, - * but just at different logical and physical locations - * (when an extent is fully replaced with a new one, we - * know the generation number must have changed too, - * since snapshot creation implies committing the current - * transaction, and the inode item must have been updated - * as well). - * This replacement of the disk_bytenr happens at - * relocation.c:replace_file_extents() through - * relocation.c:btrfs_reloc_cow_block(). - */ - if (btrfs_file_extent_generation(leaf_l, ei_l) == - btrfs_file_extent_generation(leaf_r, ei_r) && - btrfs_file_extent_ram_bytes(leaf_l, ei_l) == - btrfs_file_extent_ram_bytes(leaf_r, ei_r) && - btrfs_file_extent_compression(leaf_l, ei_l) == - btrfs_file_extent_compression(leaf_r, ei_r) && - btrfs_file_extent_encryption(leaf_l, ei_l) == - btrfs_file_extent_encryption(leaf_r, ei_r) && - btrfs_file_extent_other_encoding(leaf_l, ei_l) == - btrfs_file_extent_other_encoding(leaf_r, ei_r) && - btrfs_file_extent_type(leaf_l, ei_l) == - btrfs_file_extent_type(leaf_r, ei_r) && - btrfs_file_extent_disk_bytenr(leaf_l, ei_l) != - btrfs_file_extent_disk_bytenr(leaf_r, ei_r) && - btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) && - btrfs_file_extent_offset(leaf_l, ei_l) == - btrfs_file_extent_offset(leaf_r, ei_r) && - btrfs_file_extent_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_num_bytes(leaf_r, ei_r)) - return 0; - } - - inconsistent_snapshot_error(sctx, result, "extent"); - return -EIO; - } + /* + * We have found an extent item that changed without the inode item + * having changed. This can happen either after relocation (where the + * disk_bytenr of an extent item is replaced at + * relocation.c:replace_file_extents()) or after deduplication into a + * file in both the parent and send snapshots (where an extent item can + * get modified or replaced with a new one). Note that deduplication + * updates the inode item, but it only changes the iversion (sequence + * field in the inode item) of the inode, so if a file is deduplicated + * the same amount of times in both the parent and send snapshots, its + * iversion becames the same in both snapshots, whence the inode item is + * the same on both snapshots. + */ + if (sctx->cur_ino != sctx->cmp_key->objectid) + return 0; if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a7b69deb6d70..9286603a6a98 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1809,6 +1809,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) } if (btrfs_super_log_root(fs_info->super_copy) != 0) { + btrfs_warn(fs_info, + "mount required to replay tree-log, cannot remount read-write"); ret = -EINVAL; goto restore; } @@ -2164,7 +2166,15 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ thresh = 4 * 1024 * 1024; - if (!mixed && total_free_meta - thresh < block_rsv->size) + /* + * We only want to claim there's no available space if we can no longer + * allocate chunks for our metadata profile and our global reserve will + * not fit in the free metadata space. If we aren't ->full then we + * still can allocate chunks and thus are fine using the currently + * calculated f_bavail. + */ + if (!mixed && block_rsv->space_info->full && + total_free_meta - thresh < block_rsv->size) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f157fba8940..510cad48e519 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -751,7 +751,12 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, fs_devs->fsid_kobj.kset = btrfs_kset; error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, parent, "%pU", fs_devs->fsid); - return error; + if (error) { + kobject_put(&fs_devs->fsid_kobj); + return error; + } + + return 0; } int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index bf62ad919a95..9edc2674b8a7 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -112,7 +112,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void) spin_lock_init(&fs_info->qgroup_op_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->fs_roots_radix_lock); - spin_lock_init(&fs_info->tree_mod_seq_lock); mutex_init(&fs_info->qgroup_ioctl_lock); mutex_init(&fs_info->qgroup_rescan_lock); rwlock_init(&fs_info->tree_mod_log_lock); diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index a724d9a79bd2..5e3b875d87e2 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -476,9 +476,9 @@ static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize, root->node = alloc_test_extent_buffer(root->fs_info, nodesize, nodesize); - if (!root->node) { - test_msg("Couldn't allocate dummy buffer\n"); - ret = -ENOMEM; + if (IS_ERR(root->node)) { + test_msg("couldn't allocate dummy buffer\n"); + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index 9c6666692341..e0aa6b9786fa 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -488,9 +488,9 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) */ root->node = alloc_test_extent_buffer(root->fs_info, nodesize, nodesize); - if (!root->node) { + if (IS_ERR(root->node)) { test_msg("Couldn't allocate dummy buffer\n"); - ret = -ENOMEM; + ret = PTR_ERR(root->node); goto out; } btrfs_set_header_level(root->node, 0); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index fd6c74662e9a..31df020634cd 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1917,6 +1917,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_transaction *prev_trans = NULL; int ret; + /* + * Some places just start a transaction to commit it. We need to make + * sure that if this commit fails that the abort code actually marks the + * transaction as failed, so set trans->dirty to make the abort code do + * the right thing. + */ + trans->dirty = true; + /* Stop the commit early if ->aborted is set */ if (unlikely(ACCESS_ONCE(cur_trans->aborted))) { ret = cur_trans->aborted; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 47d11a30bee7..f79682937faf 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2827,6 +2827,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, log->log_transid = root->log_transid; root->log_start_pid = 0; /* + * Update or create log root item under the root's log_mutex to prevent + * races with concurrent log syncs that can lead to failure to update + * log root item because it was not created yet. + */ + ret = update_log_root(trans, log); + /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -2845,8 +2851,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); - ret = update_log_root(trans, log); - mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { /* @@ -3343,9 +3347,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done; /* @@ -4432,13 +4443,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, extent) == - BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_inline_len(leaf, - path->slots[0], - extent); - ASSERT(len == i_size); + BTRFS_FILE_EXTENT_INLINE) return 0; - } len = btrfs_file_extent_num_bytes(leaf, extent); /* Last extent goes beyond i_size, no need to log a hole. */ @@ -4835,7 +4841,7 @@ again: err = btrfs_log_inode(trans, root, other_inode, LOG_OTHER_INODE, 0, LLONG_MAX, ctx); - iput(other_inode); + btrfs_add_delayed_iput(other_inode); if (err) goto out_unlock; else @@ -5253,7 +5259,7 @@ process_leaf: } if (btrfs_inode_in_log(di_inode, trans->transid)) { - iput(di_inode); + btrfs_add_delayed_iput(di_inode); break; } @@ -5265,7 +5271,7 @@ process_leaf: if (!ret && btrfs_must_commit_transaction(trans, di_inode)) ret = 1; - iput(di_inode); + btrfs_add_delayed_iput(di_inode); if (ret) goto next_dir_inode; if (ctx->log_new_dentries) { @@ -5411,7 +5417,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, if (!ret && ctx && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, root, dir_inode, ctx); - iput(dir_inode); + btrfs_add_delayed_iput(dir_inode); if (ret) goto out; } @@ -5691,9 +5697,28 @@ again: wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); + + /* + * We didn't find the subvol, likely because it was + * deleted. This is ok, simply skip this log and go to + * the next one. + * + * We need to exclude the root because we can't have + * other log replays overwriting this log as we'll read + * it back in a few more times. This will keep our + * block from being modified, and we'll just bail for + * each subsequent pass. + */ + if (ret == -ENOENT) + ret = btrfs_pin_extent_for_log_replay(fs_info->extent_root, + log->node->start, + log->node->len); free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); + + if (!ret) + goto next; btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root for tree log recovery."); goto error; @@ -5725,7 +5750,6 @@ again: &root->highest_objectid); } - key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); free_extent_buffer(log->commit_root); @@ -5733,9 +5757,10 @@ again: if (ret) goto error; - +next: if (found_key.offset == 0) break; + key.offset = found_key.offset - 1; } btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 83bb2f2aa83c..ee1c76cf8886 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -335,6 +335,8 @@ again_search_slot: } if (ret < 0 && ret != -ENOENT) goto out; + key.offset++; + goto again_search_slot; } item_size -= sizeof(subid_le); offset += sizeof(subid_le); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c063ac57c30e..70aa22a8a9cc 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4876,6 +4876,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, for (i = 0; i < map->num_stripes; i++) { num_bytes = map->stripes[i].dev->bytes_used + stripe_size; btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes); + map->stripes[i].dev->has_pending_chunks = true; } spin_lock(&extent_root->fs_info->free_chunk_lock); @@ -5071,8 +5072,7 @@ static inline int btrfs_chunk_max_errors(struct map_lookup *map) if (map->type & (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_DUP)) { + BTRFS_BLOCK_GROUP_RAID5)) { max_errors = 1; } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) { max_errors = 2; @@ -7250,6 +7250,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root, for (i = 0; i < map->num_stripes; i++) { dev = map->stripes[i].dev; dev->commit_bytes_used = dev->bytes_used; + dev->has_pending_chunks = false; } } unlock_chunks(root); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 9c09aa29d6bd..96c1b847def6 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -62,6 +62,11 @@ struct btrfs_device { spinlock_t io_lock ____cacheline_aligned; int running_pending; + /* When true means this device has pending chunk alloc in + * current transaction. Protected by chunk_mutex. + */ + bool has_pending_chunks; + /* regular prio bios */ struct btrfs_pending_bios pending_bios; /* WRITE_SYNC bios */ @@ -307,7 +312,6 @@ struct btrfs_bio { u64 map_type; /* get from map_lookup->type */ bio_end_io_t *end_io; struct bio *orig_bio; - unsigned long flags; void *private; atomic_t error; int max_errors; diff --git a/fs/buffer.c b/fs/buffer.c index e2d4a45ae135..90d1fb5ed73d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3041,6 +3041,13 @@ void guard_bio_eod(int op, struct bio *bio) /* Uhhuh. We've got a bio that straddles the device size! */ truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9); + /* + * The bio contains more than one segment which spans EOD, just return + * and let IO layer turn it into an EIO + */ + if (truncated_bytes > bvec->bv_len) + return; + /* Truncate the bio.. */ bio->bi_iter.bi_size -= truncated_bytes; bvec->bv_len -= truncated_bytes; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f916cd7b1918..f5d9835264aa 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -933,6 +933,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode); + /* remove from inode's cap rbtree, and clear auth cap */ + rb_erase(&cap->ci_node, &ci->i_caps); + if (ci->i_auth_cap == cap) + ci->i_auth_cap = NULL; + /* remove from session list */ spin_lock(&session->s_cap_lock); if (session->s_cap_iterator == cap) { @@ -968,11 +973,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release) spin_unlock(&session->s_cap_lock); - /* remove from inode list */ - rb_erase(&cap->ci_node, &ci->i_caps); - if (ci->i_auth_cap == cap) - ci->i_auth_cap = NULL; - if (removed) ceph_put_cap(mdsc, cap); @@ -1081,20 +1081,23 @@ static int send_cap_msg(struct ceph_mds_session *session, } /* - * Queue cap releases when an inode is dropped from our cache. Since - * inode is about to be destroyed, there is no need for i_ceph_lock. + * Queue cap releases when an inode is dropped from our cache. */ void ceph_queue_caps_release(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct rb_node *p; + /* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU) + * may call __ceph_caps_issued_mask() on a freeing inode. */ + spin_lock(&ci->i_ceph_lock); p = rb_first(&ci->i_caps); while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); p = rb_next(p); __ceph_remove_cap(cap, true); } + spin_unlock(&ci->i_ceph_lock); } /* diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index cec25691cbae..2ffc7fe8da52 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1471,6 +1471,7 @@ void ceph_dentry_lru_del(struct dentry *dn) unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1478,8 +1479,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 30d9d9e7057d..049cff197d2a 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -523,6 +523,7 @@ static void ceph_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); + kfree(ci->i_symlink); kmem_cache_free(ceph_inode_cachep, ci); } @@ -554,7 +555,6 @@ void ceph_destroy_inode(struct inode *inode) ceph_put_snap_realm(mdsc, realm); } - kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); @@ -741,6 +741,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, int issued = 0, implemented, new_issued; struct timespec mtime, atime, ctime; struct ceph_buffer *xattr_blob = NULL; + struct ceph_buffer *old_blob = NULL; struct ceph_string *pool_ns = NULL; struct ceph_cap *new_cap = NULL; int err = 0; @@ -799,7 +800,12 @@ static int fill_inode(struct inode *inode, struct page *locked_page, ci->i_version = le64_to_cpu(info->version); inode->i_version++; inode->i_rdev = le32_to_cpu(info->rdev); - inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; + /* directories have fl_stripe_unit set to zero */ + if (le32_to_cpu(info->layout.fl_stripe_unit)) + inode->i_blkbits = + fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; + else + inode->i_blkbits = CEPH_BLOCK_SHIFT; if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) && (issued & CEPH_CAP_AUTH_EXCL) == 0) { @@ -858,7 +864,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) && le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) { if (ci->i_xattrs.blob) - ceph_buffer_put(ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = xattr_blob; if (xattr_blob) memcpy(ci->i_xattrs.blob->vec.iov_base, @@ -1004,8 +1010,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page, out: if (new_cap) ceph_put_cap(mdsc, new_cap); - if (xattr_blob) - ceph_buffer_put(xattr_blob); + ceph_buffer_put(old_blob); + ceph_buffer_put(xattr_blob); ceph_put_string(pool_ns); return err; } @@ -1624,7 +1630,6 @@ retry_lookup: if (IS_ERR(realdn)) { err = PTR_ERR(realdn); d_drop(dn); - dn = NULL; goto next_item; } dn = realdn; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6cbd0d805c9d..3139fbd4c34e 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1187,6 +1187,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -3401,7 +3410,9 @@ static void delayed_work(struct work_struct *work) pr_info("mds%d hung\n", s->s_mds); } } - if (s->s_state < CEPH_MDS_SESSION_OPEN) { + if (s->s_state == CEPH_MDS_SESSION_NEW || + s->s_state == CEPH_MDS_SESSION_RESTARTING || + s->s_state == CEPH_MDS_SESSION_REJECTED) { /* this mds is failed or recovering, just wait */ ceph_put_mds_session(s); continue; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 411e9df0d40e..3a76ae001360 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -563,7 +563,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 2a8903025853..ec1640f3167b 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -85,7 +85,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } - static int ceph_sync_fs(struct super_block *sb, int wait) { struct ceph_fs_client *fsc = ceph_sb_to_client(sb); @@ -178,6 +177,26 @@ static match_table_t fsopt_tokens = { {-1, NULL} }; +/* + * Remove adjacent slashes and then the trailing slash, unless it is + * the only remaining character. + * + * E.g. "//dir1////dir2///" --> "/dir1/dir2", "///" --> "/". + */ +static void canonicalize_path(char *path) +{ + int i, j = 0; + + for (i = 0; path[i] != '\0'; i++) { + if (path[i] != '/' || j < 1 || path[j - 1] != '/') + path[j++] = path[i]; + } + + if (j > 1 && path[j - 1] == '/') + j--; + path[j] = '\0'; +} + static int parse_fsopt_token(char *c, void *private) { struct ceph_mount_options *fsopt = private; @@ -337,6 +356,7 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name); if (ret) return ret; + ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; @@ -396,13 +416,17 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, */ dev_name_end = strchr(dev_name, '/'); if (dev_name_end) { - if (strlen(dev_name_end) > 1) { - fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); - if (!fsopt->server_path) { - err = -ENOMEM; - goto out; - } + /* + * The server_path will include the whole chars from userland + * including the leading '/'. + */ + fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); + if (!fsopt->server_path) { + err = -ENOMEM; + goto out; } + + canonicalize_path(fsopt->server_path); } else { dev_name_end = dev_name + strlen(dev_name); } @@ -725,7 +749,6 @@ static void destroy_caches(void) ceph_fscache_unregister(); } - /* * ceph_umount_begin - initiate forced umount. Tear down down the * mount, skipping steps that may hang while waiting for server(s). @@ -742,6 +765,12 @@ static void ceph_umount_begin(struct super_block *sb) return; } +static int ceph_remount(struct super_block *sb, int *flags, char *data) +{ + sync_filesystem(sb); + return 0; +} + static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .destroy_inode = ceph_destroy_inode, @@ -750,6 +779,7 @@ static const struct super_operations ceph_super_ops = { .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, + .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, @@ -805,9 +835,6 @@ out: return root; } - - - /* * mount: join the ceph cluster, and open root directory. */ @@ -821,18 +848,14 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) mutex_lock(&fsc->client->mount_mutex); if (!fsc->sb->s_root) { - const char *path; + const char *path = fsc->mount_options->server_path ? + fsc->mount_options->server_path + 1 : ""; + err = __ceph_open_session(fsc->client, started); if (err < 0) goto out; - if (!fsc->mount_options->server_path) { - path = ""; - dout("mount opening path \\t\n"); - } else { - path = fsc->mount_options->server_path + 1; - dout("mount opening path %s\n", path); - } + dout("mount opening path '%s'\n", path); err = ceph_fs_debugfs_init(fsc); if (err < 0) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 622d5dd9f616..9f18635f78c7 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -70,7 +70,7 @@ struct ceph_mount_options { char *snapdir_name; /* default ".snap" */ char *mds_namespace; /* default NULL */ - char *server_path; /* default "/" */ + char *server_path; /* default NULL (means "/") */ }; struct ceph_fs_client { @@ -476,7 +476,12 @@ static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci, long long release_count, long long ordered_count) { - smp_mb__before_atomic(); + /* + * Makes sure operations that setup readdir cache (update page + * cache and i_size) are strongly ordered w.r.t. the following + * atomic64_set() operations. + */ + smp_mb(); atomic64_set(&ci->i_complete_seq[0], release_count); atomic64_set(&ci->i_complete_seq[1], ordered_count); } diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 75267cdd5dfd..18b999deed03 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -74,7 +74,7 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, const char *ns_field = " pool_namespace="; char buf[128]; size_t len, total_len = 0; - int ret; + ssize_t ret; pool_ns = ceph_try_get_string(ci->i_layout.pool_ns); @@ -98,11 +98,8 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, if (pool_ns) total_len += strlen(ns_field) + pool_ns->len; - if (!size) { - ret = total_len; - } else if (total_len > size) { - ret = -ERANGE; - } else { + ret = total_len; + if (size >= total_len) { memcpy(val, buf, len); ret = len; if (pool_name) { @@ -757,8 +754,11 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, vxattr = ceph_match_vxattr(inode, name); if (vxattr) { err = -ENODATA; - if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) + if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) { err = vxattr->getxattr_cb(ci, value, size); + if (size && size < err) + err = -ERANGE; + } return err; } @@ -951,6 +951,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf = NULL; + struct ceph_buffer *old_blob = NULL; int issued; int err; int dirty = 0; @@ -1019,13 +1020,15 @@ retry: struct ceph_buffer *blob; spin_unlock(&ci->i_ceph_lock); - dout(" preaallocating new blob size=%d\n", required_blob_size); + ceph_buffer_put(old_blob); /* Shouldn't be required */ + dout(" pre-allocating new blob size=%d\n", required_blob_size); blob = ceph_buffer_new(required_blob_size, GFP_NOFS); if (!blob) goto do_sync_unlocked; spin_lock(&ci->i_ceph_lock); + /* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) - ceph_buffer_put(ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; } @@ -1041,6 +1044,7 @@ retry: } spin_unlock(&ci->i_ceph_lock); + ceph_buffer_put(old_blob); if (lock_snap_rwsem) up_read(&mdsc->snap_rwsem); if (dirty) diff --git a/fs/char_dev.c b/fs/char_dev.c index 44a240c4bb65..23e0477edf7d 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -134,6 +134,12 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, ret = -EBUSY; goto out; } + + if (new_min < old_min && new_max > old_max) { + ret = -EBUSY; + goto out; + } + } cd->next = *cp; @@ -330,7 +336,7 @@ static struct kobject *cdev_get(struct cdev *p) if (owner && !try_module_get(owner)) return NULL; - kobj = kobject_get(&p->kobj); + kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) module_put(owner); return kobj; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 9156be545b0f..4660208132a2 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -271,9 +271,9 @@ static void dump_referral(const struct dfs_info3_param *ref) { cifs_dbg(FYI, "DFS: ref path: %s\n", ref->path_name); cifs_dbg(FYI, "DFS: node path: %s\n", ref->node_name); - cifs_dbg(FYI, "DFS: fl: %hd, srv_type: %hd\n", + cifs_dbg(FYI, "DFS: fl: %d, srv_type: %d\n", ref->flags, ref->server_type); - cifs_dbg(FYI, "DFS: ref_flags: %hd, path_consumed: %hd\n", + cifs_dbg(FYI, "DFS: ref_flags: %d, path_consumed: %d\n", ref->ref_flag, ref->path_consumed); } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 15bac390dff9..10aedc2a4c2d 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -603,7 +603,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); - cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode); + cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode); return; } @@ -632,7 +632,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use, if (mode & S_IXUGO) *pace_flags |= SET_FILE_EXEC_RIGHTS; - cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n", + cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n", mode, *pace_flags); return; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 4ed4736b5bc6..7ae21ad420fb 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1157,6 +1157,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1177,6 +1178,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); struct cifsInodeInfo { bool can_cache_brlcks; struct list_head llist; /* locks helb by this inode */ + /* + * NOTE: Some code paths call down_read(lock_sem) twice, so + * we must always use use cifs_down_write() instead of down_write() + * for this semaphore to avoid deadlocks. + */ struct rw_semaphore lock_sem; /* protect the fields above */ /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; @@ -1651,6 +1657,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index cd8025a249bb..cdf244df91c2 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -138,6 +138,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); +extern void cifs_down_write(struct rw_semaphore *sem); extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 33e65b71c49a..f2707ff795d4 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -885,6 +885,7 @@ cifs_demultiplex_thread(void *p) mempool_resize(cifs_req_poolp, length + cifs_min_rcv); set_freezable(); + allow_kernel_signal(SIGKILL); while (server->tcpStatus != CifsExiting) { if (try_to_freeze()) continue; @@ -1201,6 +1202,11 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) const char *delims = "/\\"; size_t len; + if (unlikely(!devname || !*devname)) { + cifs_dbg(VFS, "Device name not specified.\n"); + return -EINVAL; + } + /* make sure we have a valid UNC double delimiter prefix */ len = strspn(devname, delims); if (len != 2) @@ -2216,7 +2222,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) task = xchg(&server->tsk, NULL); if (task) - force_sig(SIGKILL, task); + send_sig(SIGKILL, task, 1); } static struct TCP_Server_Info * @@ -2442,6 +2448,7 @@ static int cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) { int rc = 0; + int is_domain = 0; const char *delim, *payload; char *desc; ssize_t len; @@ -2489,6 +2496,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) rc = PTR_ERR(key); goto out_err; } + is_domain = 1; } down_read(&key->sem); @@ -2546,6 +2554,26 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses) goto out_key_put; } + /* + * If we have a domain key then we must set the domainName in the + * for the request. + */ + if (is_domain && ses->domainName) { + vol->domainname = kstrndup(ses->domainName, + strlen(ses->domainName), + GFP_KERNEL); + if (!vol->domainname) { + cifs_dbg(FYI, "Unable to allocate %zd bytes for " + "domain\n", len); + rc = -ENOMEM; + kfree(vol->username); + vol->username = NULL; + kzfree(vol->password); + vol->password = NULL; + goto out_key_put; + } + } + out_key_put: up_read(&key->sem); key_put(key); @@ -2899,8 +2927,10 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data) { struct cifs_sb_info *old = CIFS_SB(sb); struct cifs_sb_info *new = mnt_data->cifs_sb; - bool old_set = old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH; - bool new_set = new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH; + bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + old->prepath; + bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + new->prepath; if (old_set && new_set && !strcmp(new->prepath, old->prepath)) return 1; @@ -3371,7 +3401,7 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_gid = pvolume_info->linux_gid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; - cifs_dbg(FYI, "file mode: 0x%hx dir mode: 0x%hx\n", + cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); cifs_sb->actimeo = pvolume_info->actimeo; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index e98e24eaa6a8..0262c8f7e7c7 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -551,7 +551,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, if (server->ops->close) server->ops->close(xid, tcon, &fid); cifs_del_pending_open(&open); - fput(file); rc = -ENOMEM; } @@ -830,10 +829,16 @@ lookup_out: static int cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { + struct inode *inode; + if (flags & LOOKUP_RCU) return -ECHILD; if (d_really_is_positive(direntry)) { + inode = d_inode(direntry); + if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) + CIFS_I(inode)->time = 0; /* force reval */ + if (cifs_revalidate_dentry(direntry)) return 0; else { @@ -844,7 +849,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags) * attributes will have been updated by * cifs_revalidate_dentry(). */ - if (IS_AUTOMOUNT(d_inode(direntry)) && + if (IS_AUTOMOUNT(inode) && !(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) { spin_lock(&direntry->d_lock); direntry->d_flags |= DCACHE_NEED_AUTOMOUNT; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 1c5099fffaec..09d83275c20b 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -252,6 +252,12 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, xid, fid); + if (rc) { + server->ops->close(xid, tcon, fid); + if (rc == -ESTALE) + rc = -EOPENSTALE; + } + out: kfree(buf); return rc; @@ -274,6 +280,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode) return has_locks; } +void +cifs_down_write(struct rw_semaphore *sem) +{ + while (!down_write_trylock(sem)) + msleep(10); +} + struct cifsFileInfo * cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock) @@ -299,9 +312,6 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; - down_write(&cinode->lock_sem); - list_add(&fdlocks->llist, &cinode->llist); - up_write(&cinode->lock_sem); cfile->count = 1; cfile->pid = current->tgid; @@ -325,6 +335,10 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, oplock = 0; } + cifs_down_write(&cinode->lock_sem); + list_add(&fdlocks->llist, &cinode->llist); + up_write(&cinode->lock_sem); + spin_lock(&tcon->open_file_lock); if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock) oplock = fid->pending_open->oplock; @@ -358,13 +372,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -411,7 +443,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -432,7 +465,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) * Delete any outstanding lock records. We'll lose them when the file * is closed anyway. */ - down_write(&cifsi->lock_sem); + cifs_down_write(&cifsi->lock_sem); list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) { list_del(&li->llist); cifs_del_lock_waiters(li); @@ -689,6 +722,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush) if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (cfile->f_flags & O_SYNC) + create_options |= CREATE_WRITE_THROUGH; + + if (cfile->f_flags & O_DIRECT) + create_options |= CREATE_NO_BUFFER; + if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &cfile->fid); @@ -986,7 +1026,7 @@ static void cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock) { struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry)); - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_add_tail(&lock->llist, &cfile->llist->locks); up_write(&cinode->lock_sem); } @@ -1008,7 +1048,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock, try_again: exist = false; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length, lock->type, &conf_lock, CIFS_LOCK_OP); @@ -1030,7 +1070,7 @@ try_again: (lock->blist.next == &lock->blist)); if (!rc) goto try_again; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_del_init(&lock->blist); } @@ -1083,7 +1123,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock) return rc; try_again: - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1287,7 +1327,7 @@ cifs_push_locks(struct cifsFileInfo *cfile) int rc = 0; /* we are going to update can_cache_brlcks here - need a write access */ - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); if (!cinode->can_cache_brlcks) { up_write(&cinode->lock_sem); return rc; @@ -1476,7 +1516,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, if (!buf) return -ENOMEM; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); for (i = 0; i < 2; i++) { cur = buf; num = 0; @@ -1627,8 +1667,20 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, rc = server->ops->mand_unlock_range(cfile, flock, xid); out: - if (flock->fl_flags & FL_POSIX && !rc) + if (flock->fl_flags & FL_POSIX) { + /* + * If this is a request to remove all locks because we + * are closing the file, it doesn't matter if the + * unlocking failed as both cifs.ko and the SMB server + * remove the lock on file close + */ + if (rc) { + cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc); + if (!(flock->fl_flags & FL_CLOSE)) + return rc; + } rc = locks_lock_file_wait(file, flock); + } return rc; } @@ -2861,7 +2913,9 @@ cifs_read_allocate_pages(struct cifs_readdata *rdata, unsigned int nr_pages) } if (rc) { - for (i = 0; i < nr_pages; i++) { + unsigned int nr_page_failed = i; + + for (i = 0; i < nr_page_failed; i++) { put_page(rdata->pages[i]); rdata->pages[i] = NULL; } @@ -3901,6 +3955,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 57c938ffeb6e..dfa85ad5b481 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -405,6 +405,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* if uniqueid is different, return error */ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM && CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) { + CIFS_I(*pinode)->time = 0; /* force reval */ rc = -ESTALE; goto cgiiu_exit; } @@ -412,6 +413,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, /* if filetype is different, return error */ if (unlikely(((*pinode)->i_mode & S_IFMT) != (fattr.cf_mode & S_IFMT))) { + CIFS_I(*pinode)->time = 0; /* force reval */ rc = -ESTALE; goto cgiiu_exit; } @@ -771,43 +773,50 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, } else if ((rc == -EACCES) && backup_cred(cifs_sb) && (strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0)) { - /* - * For SMB2 and later the backup intent flag is already - * sent if needed on open and there is no path based - * FindFirst operation to use to retry with - */ + /* + * For SMB2 and later the backup intent flag is already + * sent if needed on open and there is no path based + * FindFirst operation to use to retry with + */ - srchinf = kzalloc(sizeof(struct cifs_search_info), - GFP_KERNEL); - if (srchinf == NULL) { - rc = -ENOMEM; - goto cgii_exit; - } + srchinf = kzalloc(sizeof(struct cifs_search_info), + GFP_KERNEL); + if (srchinf == NULL) { + rc = -ENOMEM; + goto cgii_exit; + } - srchinf->endOfSearch = false; + srchinf->endOfSearch = false; + if (tcon->unix_ext) + srchinf->info_level = SMB_FIND_FILE_UNIX; + else if ((tcon->ses->capabilities & + tcon->ses->server->vals->cap_nt_find) == 0) + srchinf->info_level = SMB_FIND_FILE_INFO_STANDARD; + else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) srchinf->info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; + else /* no srvino useful for fallback to some netapp */ + srchinf->info_level = SMB_FIND_FILE_DIRECTORY_INFO; - srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | - CIFS_SEARCH_CLOSE_AT_END | - CIFS_SEARCH_BACKUP_SEARCH; + srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | + CIFS_SEARCH_CLOSE_AT_END | + CIFS_SEARCH_BACKUP_SEARCH; - rc = CIFSFindFirst(xid, tcon, full_path, - cifs_sb, NULL, srchflgs, srchinf, false); - if (!rc) { - data = - (FILE_ALL_INFO *)srchinf->srch_entries_start; + rc = CIFSFindFirst(xid, tcon, full_path, + cifs_sb, NULL, srchflgs, srchinf, false); + if (!rc) { + data = (FILE_ALL_INFO *)srchinf->srch_entries_start; - cifs_dir_info_to_fattr(&fattr, - (FILE_DIRECTORY_INFO *)data, cifs_sb); - fattr.cf_uniqueid = le64_to_cpu( - ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); - validinum = true; + cifs_dir_info_to_fattr(&fattr, + (FILE_DIRECTORY_INFO *)data, cifs_sb); + fattr.cf_uniqueid = le64_to_cpu( + ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); + validinum = true; - cifs_buf_release(srchinf->ntwrk_buf_start); - } - kfree(srchinf); - if (rc) - goto cgii_exit; + cifs_buf_release(srchinf->ntwrk_buf_start); + } + kfree(srchinf); + if (rc) + goto cgii_exit; } else goto cgii_exit; @@ -910,6 +919,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* if uniqueid is different, return error */ if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM && CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) { + CIFS_I(*inode)->time = 0; /* force reval */ rc = -ESTALE; goto cgii_exit; } @@ -917,6 +927,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, /* if filetype is different, return error */ if (unlikely(((*inode)->i_mode & S_IFMT) != (fattr.cf_mode & S_IFMT))) { + CIFS_I(*inode)->time = 0; /* force reval */ rc = -ESTALE; goto cgii_exit; } @@ -1562,7 +1573,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) struct TCP_Server_Info *server; char *full_path; - cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n", + cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n", mode, inode); cifs_sb = CIFS_SB(inode->i_sb); @@ -1715,6 +1726,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; @@ -1975,6 +1990,7 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) struct inode *inode = d_inode(dentry); struct super_block *sb = dentry->d_sb; char *full_path = NULL; + int count = 0; if (inode == NULL) return -ENOENT; @@ -1996,15 +2012,18 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry) full_path, inode, inode->i_count.counter, dentry, cifs_get_time(dentry), jiffies); +again: if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid); else rc = cifs_get_inode_info(&inode, full_path, NULL, sb, xid, NULL); - + if (rc == -EAGAIN && count++ < 10) + goto again; out: kfree(full_path); free_xid(xid); + return rc; } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 50559a80acf8..5e75df69062d 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -494,8 +494,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -592,6 +591,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index cc88f4f0325e..bed973330227 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -130,10 +130,6 @@ static const struct smb_to_posix_error mapping_table_ERRSRV[] = { {0, 0} }; -static const struct smb_to_posix_error mapping_table_ERRHRD[] = { - {0, 0} -}; - /* * Convert a string containing text IPv4 or IPv6 address to binary form. * diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index efd72e1fae74..6f5d78b172ba 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -180,6 +180,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server) /* we do not want to loop forever */ last_mid = cur_mid; cur_mid++; + /* avoid 0xFFFF MID */ + if (cur_mid == 0xffff) + cur_mid++; /* * This nested loop looks more expensive than it is. @@ -305,7 +308,7 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) remaining = tgt_total_cnt - total_in_tgt; if (remaining < 0) { - cifs_dbg(FYI, "Server sent too much data. tgt_total_cnt=%hu total_in_tgt=%hu\n", + cifs_dbg(FYI, "Server sent too much data. tgt_total_cnt=%hu total_in_tgt=%u\n", tgt_total_cnt, total_in_tgt); return -EPROTO; } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index dee5250701de..4dcce3f034f4 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -69,7 +69,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, goto out; - if (oparms->tcon->use_resilient) { + if (oparms->tcon->use_resilient) { nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, @@ -138,7 +138,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, cur = buf; - down_write(&cinode->lock_sem); + cifs_down_write(&cinode->lock_sem); list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) { if (flock->fl_start > li->offset || (flock->fl_start + length) < diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 98c25b969ab8..7e93d5706bf6 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1034,7 +1034,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO, "STATUS_UNFINISHED_CONTEXT_DELETED"}, {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"}, - {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"}, + /* Note that ENOATTTR and ENODATA are the same errno */ + {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"}, {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"}, {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO, "STATUS_WRONG_CREDENTIAL_HANDLE"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 244d27bb8fba..7b7b47e26dbd 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -512,7 +512,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -617,10 +617,10 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &server->smb_ses_list) { ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each(tmp1, &ses->tcon_list) { tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); - cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks); spin_lock(&tcon->open_file_lock); list_for_each(tmp2, &tcon->openFileList) { cfile = list_entry(tmp2, struct cifsFileInfo, @@ -632,6 +632,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) continue; cifs_dbg(FYI, "file id match, oplock break\n"); + cifs_stats_inc( + &tcon->stats.cifs_stats.num_oplock_brks); cinode = CIFS_I(d_inode(cfile->dentry)); spin_lock(&cfile->file_info_lock); if (!CIFS_CACHE_WRITE(cinode) && @@ -656,17 +658,14 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - cifs_dbg(FYI, "No matching file for oplock break\n"); - return true; } } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 97d8e2a3df9b..67d9b7a277a3 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1413,26 +1413,33 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { char message[5] = {0}; + unsigned int new_oplock = 0; oplock &= 0xFF; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; - cinode->oplock = 0; + /* Check if the server granted an oplock rather than a lease */ + if (oplock & SMB2_OPLOCK_LEVEL_EXCLUSIVE) + return smb2_set_oplock_level(cinode, oplock, epoch, + purge_cache); + if (oplock & SMB2_LEASE_READ_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_READ_FLG; + new_oplock |= CIFS_CACHE_READ_FLG; strcat(message, "R"); } if (oplock & SMB2_LEASE_HANDLE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_HANDLE_FLG; + new_oplock |= CIFS_CACHE_HANDLE_FLG; strcat(message, "H"); } if (oplock & SMB2_LEASE_WRITE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_WRITE_FLG; + new_oplock |= CIFS_CACHE_WRITE_FLG; strcat(message, "W"); } - if (!cinode->oplock) - strcat(message, "None"); + if (!new_oplock) + strncpy(message, "None", sizeof(message)); + + cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, &cinode->vfs_inode); } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 52b6e4a40748..e8dc28dbe563 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -168,7 +168,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) if (tcon == NULL) return 0; - if (smb2_command == SMB2_TREE_CONNECT) + if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL) return 0; if (tcon->tidStatus == CifsExiting) { @@ -247,9 +247,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) */ mutex_lock(&tcon->ses->session_mutex); rc = cifs_negotiate_protocol(0, tcon->ses); - if (!rc && tcon->ses->need_reconnect) + if (!rc && tcon->ses->need_reconnect) { rc = cifs_setup_session(0, tcon->ses, nls_codepage); - + if ((rc == -EACCES) && !tcon->retry) { + rc = -EHOSTDOWN; + mutex_unlock(&tcon->ses->session_mutex); + goto failed; + } + } if (rc || !tcon->need_reconnect) { mutex_unlock(&tcon->ses->session_mutex); goto out; @@ -291,6 +296,7 @@ out: case SMB2_SET_INFO: rc = -EAGAIN; } +failed: unload_nls(nls_codepage); return rc; } @@ -660,7 +666,12 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data) else req->SecurityMode = 0; +#ifdef CONFIG_CIFS_DFS_UPCALL + req->Capabilities = cpu_to_le32(SMB2_GLOBAL_CAP_DFS); +#else req->Capabilities = 0; +#endif /* DFS_UPCALL */ + req->Channel = 0; /* MBZ */ sess_data->iov[0].iov_base = (char *)req; diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 20af5187ba63..6634ad3567e0 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -31,7 +31,7 @@ #include "cifs_fs_sb.h" #include "cifs_unicode.h" -#define MAX_EA_VALUE_SIZE 65535 +#define MAX_EA_VALUE_SIZE CIFSMaxBufSize #define CIFS_XATTR_CIFS_ACL "system.cifs_acl" #define CIFS_XATTR_ATTRIB "cifs.dosattrib" /* full name: user.cifs.dosattrib */ #define CIFS_XATTR_CREATETIME "cifs.creationtime" /* user.cifs.creationtime */ diff --git a/fs/coda/file.c b/fs/coda/file.c index 6e0154eb6fcc..649d17edc071 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -60,6 +60,41 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +struct coda_vm_ops { + atomic_t refcnt; + struct file *coda_file; + const struct vm_operations_struct *host_vm_ops; + struct vm_operations_struct vm_ops; +}; + +static void +coda_vm_open(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + atomic_inc(&cvm_ops->refcnt); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open) + cvm_ops->host_vm_ops->open(vma); +} + +static void +coda_vm_close(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close) + cvm_ops->host_vm_ops->close(vma); + + if (atomic_dec_and_test(&cvm_ops->refcnt)) { + vma->vm_ops = cvm_ops->host_vm_ops; + fput(cvm_ops->coda_file); + kfree(cvm_ops); + } +} + static int coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) { @@ -67,6 +102,8 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) struct coda_inode_info *cii; struct file *host_file; struct inode *coda_inode, *host_inode; + struct coda_vm_ops *cvm_ops; + int ret; cfi = CODA_FTOC(coda_file); BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); @@ -75,6 +112,13 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) if (!host_file->f_op->mmap) return -ENODEV; + if (WARN_ON(coda_file != vma->vm_file)) + return -EIO; + + cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL); + if (!cvm_ops) + return -ENOMEM; + coda_inode = file_inode(coda_file); host_inode = file_inode(host_file); @@ -88,6 +132,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) * the container file on us! */ else if (coda_inode->i_mapping != host_inode->i_mapping) { spin_unlock(&cii->c_lock); + kfree(cvm_ops); return -EBUSY; } @@ -96,7 +141,29 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) cfi->cfi_mapcount++; spin_unlock(&cii->c_lock); - return host_file->f_op->mmap(host_file, vma); + vma->vm_file = get_file(host_file); + ret = host_file->f_op->mmap(host_file, vma); + + if (ret) { + /* if call_mmap fails, our caller will put coda_file so we + * should drop the reference to the host_file that we got. + */ + fput(host_file); + kfree(cvm_ops); + } else { + /* here we add redirects for the open/close vm_operations */ + cvm_ops->host_vm_ops = vma->vm_ops; + if (vma->vm_ops) + cvm_ops->vm_ops = *vma->vm_ops; + + cvm_ops->vm_ops.open = coda_vm_open; + cvm_ops->vm_ops.close = coda_vm_close; + cvm_ops->coda_file = coda_file; + atomic_set(&cvm_ops->refcnt, 1); + + vma->vm_ops = &cvm_ops->vm_ops; + } + return ret; } int coda_open(struct inode *coda_inode, struct file *coda_file) diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 822629126e89..ff9b5cf8ff01 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -187,8 +187,11 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf, if (req->uc_opcode == CODA_OPEN_BY_FD) { struct coda_open_by_fd_out *outp = (struct coda_open_by_fd_out *)req->uc_data; - if (!outp->oh.result) + if (!outp->oh.result) { outp->fh = fget(outp->fd); + if (!outp->fh) + return -EBADF; + } } wake_up(&req->uc_sleep); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 93c8e4a4bbd3..02ac9067a354 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -160,6 +160,7 @@ struct compat_video_event { unsigned int frame_rate; } u; }; +#define VIDEO_GET_EVENT32 _IOR('o', 28, struct compat_video_event) static int do_video_get_event(struct file *file, unsigned int cmd, struct compat_video_event __user *up) @@ -171,7 +172,7 @@ static int do_video_get_event(struct file *file, if (kevent == NULL) return -EFAULT; - err = do_ioctl(file, cmd, (unsigned long)kevent); + err = do_ioctl(file, VIDEO_GET_EVENT, (unsigned long)kevent); if (!err) { err = convert_in_user(&kevent->type, &up->type); err |= convert_in_user(&kevent->timestamp, &up->timestamp); @@ -190,6 +191,7 @@ struct compat_video_still_picture { compat_uptr_t iFrame; int32_t size; }; +#define VIDEO_STILLPICTURE32 _IOW('o', 30, struct compat_video_still_picture) static int do_video_stillpicture(struct file *file, unsigned int cmd, struct compat_video_still_picture __user *up) @@ -212,7 +214,7 @@ static int do_video_stillpicture(struct file *file, if (err) return -EFAULT; - err = do_ioctl(file, cmd, (unsigned long) up_native); + err = do_ioctl(file, VIDEO_STILLPICTURE, (unsigned long) up_native); return err; } @@ -1038,9 +1040,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ @@ -1487,9 +1486,9 @@ static long do_ioctl_trans(unsigned int cmd, return rtc_ioctl(file, cmd, argp); /* dvb */ - case VIDEO_GET_EVENT: + case VIDEO_GET_EVENT32: return do_video_get_event(file, cmd, argp); - case VIDEO_STILLPICTURE: + case VIDEO_STILLPICTURE32: return do_video_stillpicture(file, cmd, argp); case VIDEO_SET_SPU_PALETTE: return do_video_set_spu_palette(file, cmd, argp); @@ -1586,9 +1585,10 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, #endif case FICLONE: + goto do_ioctl; case FICLONERANGE: case FIDEDUPERANGE: - goto do_ioctl; + goto found_handler; case FIBMAP: case FIGETBSZ: diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index ccc31fa6f1a7..16eb59adf5aa 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -34,6 +34,15 @@ #include <linux/list.h> #include <linux/spinlock.h> +struct configfs_fragment { + atomic_t frag_count; + struct rw_semaphore frag_sem; + bool frag_dead; +}; + +void put_fragment(struct configfs_fragment *); +struct configfs_fragment *get_fragment(struct configfs_fragment *); + struct configfs_dirent { atomic_t s_count; int s_dependent_count; @@ -48,6 +57,7 @@ struct configfs_dirent { #ifdef CONFIG_LOCKDEP int s_depth; #endif + struct configfs_fragment *s_frag; }; #define CONFIGFS_ROOT 0x0001 @@ -75,8 +85,8 @@ extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct in extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); extern int configfs_create_bin_file(struct config_item *, const struct configfs_bin_attribute *); -extern int configfs_make_dirent(struct configfs_dirent *, - struct dentry *, void *, umode_t, int); +extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, + void *, umode_t, int, struct configfs_fragment *); extern int configfs_dirent_is_ready(struct configfs_dirent *); extern void configfs_hash_and_remove(struct dentry * dir, const char * name); @@ -151,6 +161,7 @@ static inline void release_configfs_dirent(struct configfs_dirent * sd) { if (!(sd->s_type & CONFIGFS_ROOT)) { kfree(sd->s_iattr); + put_fragment(sd->s_frag); kmem_cache_free(configfs_dir_cachep, sd); } } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index d2a1a79fa324..c2ef617d2f97 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -58,15 +58,13 @@ static void configfs_d_iput(struct dentry * dentry, if (sd) { /* Coordinate with configfs_readdir */ spin_lock(&configfs_dirent_lock); - /* Coordinate with configfs_attach_attr where will increase - * sd->s_count and update sd->s_dentry to new allocated one. - * Only set sd->dentry to null when this dentry is the only - * sd owner. - * If not do so, configfs_d_iput may run just after - * configfs_attach_attr and set sd->s_dentry to null - * even it's still in use. + /* + * Set sd->s_dentry to null only when this dentry is the one + * that is going to be killed. Otherwise configfs_d_iput may + * run just after configfs_attach_attr and set sd->s_dentry to + * NULL even it's still in use. */ - if (atomic_read(&sd->s_count) <= 2) + if (sd->s_dentry == dentry) sd->s_dentry = NULL; spin_unlock(&configfs_dirent_lock); @@ -166,11 +164,38 @@ configfs_adjust_dir_dirent_depth_after_populate(struct configfs_dirent *sd) #endif /* CONFIG_LOCKDEP */ +static struct configfs_fragment *new_fragment(void) +{ + struct configfs_fragment *p; + + p = kmalloc(sizeof(struct configfs_fragment), GFP_KERNEL); + if (p) { + atomic_set(&p->frag_count, 1); + init_rwsem(&p->frag_sem); + p->frag_dead = false; + } + return p; +} + +void put_fragment(struct configfs_fragment *frag) +{ + if (frag && atomic_dec_and_test(&frag->frag_count)) + kfree(frag); +} + +struct configfs_fragment *get_fragment(struct configfs_fragment *frag) +{ + if (likely(frag)) + atomic_inc(&frag->frag_count); + return frag; +} + /* * Allocates a new configfs_dirent and links it to the parent configfs_dirent */ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *parent_sd, - void *element, int type) + void *element, int type, + struct configfs_fragment *frag) { struct configfs_dirent * sd; @@ -190,6 +215,7 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *paren kmem_cache_free(configfs_dir_cachep, sd); return ERR_PTR(-ENOENT); } + sd->s_frag = get_fragment(frag); list_add(&sd->s_sibling, &parent_sd->s_children); spin_unlock(&configfs_dirent_lock); @@ -224,11 +250,11 @@ static int configfs_dirent_exists(struct configfs_dirent *parent_sd, int configfs_make_dirent(struct configfs_dirent * parent_sd, struct dentry * dentry, void * element, - umode_t mode, int type) + umode_t mode, int type, struct configfs_fragment *frag) { struct configfs_dirent * sd; - sd = configfs_new_dirent(parent_sd, element, type); + sd = configfs_new_dirent(parent_sd, element, type, frag); if (IS_ERR(sd)) return PTR_ERR(sd); @@ -275,7 +301,8 @@ static void init_symlink(struct inode * inode) * until it is validated by configfs_dir_set_ready() */ -static int configfs_create_dir(struct config_item *item, struct dentry *dentry) +static int configfs_create_dir(struct config_item *item, struct dentry *dentry, + struct configfs_fragment *frag) { int error; umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; @@ -288,7 +315,8 @@ static int configfs_create_dir(struct config_item *item, struct dentry *dentry) return error; error = configfs_make_dirent(p->d_fsdata, dentry, item, mode, - CONFIGFS_DIR | CONFIGFS_USET_CREATING); + CONFIGFS_DIR | CONFIGFS_USET_CREATING, + frag); if (unlikely(error)) return error; @@ -353,9 +381,10 @@ int configfs_create_link(struct configfs_symlink *sl, { int err = 0; umode_t mode = S_IFLNK | S_IRWXUGO; + struct configfs_dirent *p = parent->d_fsdata; - err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode, - CONFIGFS_ITEM_LINK); + err = configfs_make_dirent(p, dentry, sl, mode, + CONFIGFS_ITEM_LINK, p->s_frag); if (!err) { err = configfs_create(dentry, mode, init_symlink); if (err) { @@ -614,7 +643,8 @@ static int populate_attrs(struct config_item *item) static int configfs_attach_group(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry); + struct dentry *dentry, + struct configfs_fragment *frag); static void configfs_detach_group(struct config_item *item); static void detach_groups(struct config_group *group) @@ -662,7 +692,8 @@ static void detach_groups(struct config_group *group) * try using vfs_mkdir. Just a thought. */ static int create_default_group(struct config_group *parent_group, - struct config_group *group) + struct config_group *group, + struct configfs_fragment *frag) { int ret; struct configfs_dirent *sd; @@ -678,7 +709,7 @@ static int create_default_group(struct config_group *parent_group, d_add(child, NULL); ret = configfs_attach_group(&parent_group->cg_item, - &group->cg_item, child); + &group->cg_item, child, frag); if (!ret) { sd = child->d_fsdata; sd->s_type |= CONFIGFS_USET_DEFAULT; @@ -692,13 +723,14 @@ static int create_default_group(struct config_group *parent_group, return ret; } -static int populate_groups(struct config_group *group) +static int populate_groups(struct config_group *group, + struct configfs_fragment *frag) { struct config_group *new_group; int ret = 0; list_for_each_entry(new_group, &group->default_groups, group_entry) { - ret = create_default_group(group, new_group); + ret = create_default_group(group, new_group, frag); if (ret) { detach_groups(group); break; @@ -812,11 +844,12 @@ static void link_group(struct config_group *parent_group, struct config_group *g */ static int configfs_attach_item(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry) + struct dentry *dentry, + struct configfs_fragment *frag) { int ret; - ret = configfs_create_dir(item, dentry); + ret = configfs_create_dir(item, dentry, frag); if (!ret) { ret = populate_attrs(item); if (ret) { @@ -846,12 +879,13 @@ static void configfs_detach_item(struct config_item *item) static int configfs_attach_group(struct config_item *parent_item, struct config_item *item, - struct dentry *dentry) + struct dentry *dentry, + struct configfs_fragment *frag) { int ret; struct configfs_dirent *sd; - ret = configfs_attach_item(parent_item, item, dentry); + ret = configfs_attach_item(parent_item, item, dentry, frag); if (!ret) { sd = dentry->d_fsdata; sd->s_type |= CONFIGFS_USET_DIR; @@ -867,7 +901,7 @@ static int configfs_attach_group(struct config_item *parent_item, */ inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); configfs_adjust_dir_dirent_depth_before_populate(sd); - ret = populate_groups(to_config_group(item)); + ret = populate_groups(to_config_group(item), frag); if (ret) { configfs_detach_item(item); d_inode(dentry)->i_flags |= S_DEAD; @@ -1262,6 +1296,7 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode struct configfs_dirent *sd; struct config_item_type *type; struct module *subsys_owner = NULL, *new_item_owner = NULL; + struct configfs_fragment *frag; char *name; sd = dentry->d_parent->d_fsdata; @@ -1280,6 +1315,12 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode goto out; } + frag = new_fragment(); + if (!frag) { + ret = -ENOMEM; + goto out; + } + /* Get a working ref for the duration of this function */ parent_item = configfs_get_config_item(dentry->d_parent); type = parent_item->ci_type; @@ -1382,9 +1423,9 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode spin_unlock(&configfs_dirent_lock); if (group) - ret = configfs_attach_group(parent_item, item, dentry); + ret = configfs_attach_group(parent_item, item, dentry, frag); else - ret = configfs_attach_item(parent_item, item, dentry); + ret = configfs_attach_item(parent_item, item, dentry, frag); spin_lock(&configfs_dirent_lock); sd->s_type &= ~CONFIGFS_USET_IN_MKDIR; @@ -1421,6 +1462,7 @@ out_put: * reference. */ config_item_put(parent_item); + put_fragment(frag); out: return ret; @@ -1432,6 +1474,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) struct config_item *item; struct configfs_subsystem *subsys; struct configfs_dirent *sd; + struct configfs_fragment *frag; struct module *subsys_owner = NULL, *dead_item_owner = NULL; int ret; @@ -1489,6 +1532,16 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) } } while (ret == -EAGAIN); + frag = sd->s_frag; + if (down_write_killable(&frag->frag_sem)) { + spin_lock(&configfs_dirent_lock); + configfs_detach_rollback(dentry); + spin_unlock(&configfs_dirent_lock); + return -EINTR; + } + frag->frag_dead = true; + up_write(&frag->frag_sem); + /* Get a working ref for the duration of this function */ item = configfs_get_config_item(dentry); @@ -1589,7 +1642,7 @@ static int configfs_dir_open(struct inode *inode, struct file *file) */ err = -ENOENT; if (configfs_dirent_is_ready(parent_sd)) { - file->private_data = configfs_new_dirent(parent_sd, NULL, 0); + file->private_data = configfs_new_dirent(parent_sd, NULL, 0, NULL); if (IS_ERR(file->private_data)) err = PTR_ERR(file->private_data); else @@ -1745,8 +1798,13 @@ int configfs_register_group(struct config_group *parent_group, { struct configfs_subsystem *subsys = parent_group->cg_subsys; struct dentry *parent; + struct configfs_fragment *frag; int ret; + frag = new_fragment(); + if (!frag) + return -ENOMEM; + mutex_lock(&subsys->su_mutex); link_group(parent_group, group); mutex_unlock(&subsys->su_mutex); @@ -1754,13 +1812,22 @@ int configfs_register_group(struct config_group *parent_group, parent = parent_group->cg_item.ci_dentry; inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - ret = create_default_group(parent_group, group); - if (!ret) { - spin_lock(&configfs_dirent_lock); - configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); - spin_unlock(&configfs_dirent_lock); - } + ret = create_default_group(parent_group, group, frag); + if (ret) + goto err_out; + + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); inode_unlock(d_inode(parent)); + put_fragment(frag); + return 0; +err_out: + inode_unlock(d_inode(parent)); + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); + put_fragment(frag); return ret; } EXPORT_SYMBOL(configfs_register_group); @@ -1776,16 +1843,12 @@ void configfs_unregister_group(struct config_group *group) struct configfs_subsystem *subsys = group->cg_subsys; struct dentry *dentry = group->cg_item.ci_dentry; struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; - mutex_lock(&subsys->su_mutex); - if (!group->cg_item.ci_parent->ci_group) { - /* - * The parent has already been unlinked and detached - * due to a rmdir. - */ - goto unlink_group; - } - mutex_unlock(&subsys->su_mutex); + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); spin_lock(&configfs_dirent_lock); @@ -1801,7 +1864,6 @@ void configfs_unregister_group(struct config_group *group) dput(dentry); mutex_lock(&subsys->su_mutex); -unlink_group: unlink_group(group); mutex_unlock(&subsys->su_mutex); } @@ -1858,10 +1920,17 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) struct dentry *dentry; struct dentry *root; struct configfs_dirent *sd; + struct configfs_fragment *frag; + + frag = new_fragment(); + if (!frag) + return -ENOMEM; root = configfs_pin_fs(); - if (IS_ERR(root)) + if (IS_ERR(root)) { + put_fragment(frag); return PTR_ERR(root); + } if (!group->cg_item.ci_name) group->cg_item.ci_name = group->cg_item.ci_namebuf; @@ -1877,7 +1946,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) d_add(dentry, NULL); err = configfs_attach_group(sd->s_element, &group->cg_item, - dentry); + dentry, frag); if (err) { BUG_ON(d_inode(dentry)); d_drop(dentry); @@ -1895,6 +1964,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) unlink_group(group); configfs_release_fs(); } + put_fragment(frag); return err; } @@ -1904,12 +1974,18 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) struct config_group *group = &subsys->su_group; struct dentry *dentry = group->cg_item.ci_dentry; struct dentry *root = dentry->d_sb->s_root; + struct configfs_dirent *sd = dentry->d_fsdata; + struct configfs_fragment *frag = sd->s_frag; if (dentry->d_parent != root) { pr_err("Tried to unregister non-subsystem!\n"); return; } + down_write(&frag->frag_sem); + frag->frag_dead = true; + up_write(&frag->frag_sem); + inode_lock_nested(d_inode(root), I_MUTEX_PARENT); inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 2c6312db8516..7285440bc62e 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -53,40 +53,44 @@ struct configfs_buffer { bool write_in_progress; char *bin_buffer; int bin_buffer_size; + int cb_max_size; + struct config_item *item; + struct module *owner; + union { + struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; + }; }; +static inline struct configfs_fragment *to_frag(struct file *file) +{ + struct configfs_dirent *sd = file->f_path.dentry->d_fsdata; -/** - * fill_read_buffer - allocate and fill buffer from item. - * @dentry: dentry pointer. - * @buffer: data buffer for file. - * - * Allocate @buffer->page, if it hasn't been already, then call the - * config_item's show() method to fill the buffer with this attribute's - * data. - * This is called only once, on the file's first read. - */ -static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buffer) + return sd->s_frag; +} + +static int fill_read_buffer(struct file *file, struct configfs_buffer *buffer) { - struct configfs_attribute * attr = to_attr(dentry); - struct config_item * item = to_item(dentry->d_parent); - int ret = 0; - ssize_t count; + struct configfs_fragment *frag = to_frag(file); + ssize_t count = -ENOENT; if (!buffer->page) buffer->page = (char *) get_zeroed_page(GFP_KERNEL); if (!buffer->page) return -ENOMEM; - count = attr->show(item, buffer->page); - - BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE); - if (count >= 0) { - buffer->needs_read_fill = 0; - buffer->count = count; - } else - ret = count; - return ret; + down_read(&frag->frag_sem); + if (!frag->frag_dead) + count = buffer->attr->show(buffer->item, buffer->page); + up_read(&frag->frag_sem); + + if (count < 0) + return count; + if (WARN_ON_ONCE(count > (ssize_t)SIMPLE_ATTR_SIZE)) + return -EIO; + buffer->needs_read_fill = 0; + buffer->count = count; + return 0; } /** @@ -111,12 +115,13 @@ static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buf static ssize_t configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct configfs_buffer * buffer = file->private_data; + struct configfs_buffer *buffer = file->private_data; ssize_t retval = 0; mutex_lock(&buffer->mutex); if (buffer->needs_read_fill) { - if ((retval = fill_read_buffer(file->f_path.dentry,buffer))) + retval = fill_read_buffer(file, buffer); + if (retval) goto out; } pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n", @@ -152,10 +157,8 @@ static ssize_t configfs_read_bin_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { + struct configfs_fragment *frag = to_frag(file); struct configfs_buffer *buffer = file->private_data; - struct dentry *dentry = file->f_path.dentry; - struct config_item *item = to_item(dentry->d_parent); - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); ssize_t retval = 0; ssize_t len = min_t(size_t, count, PAGE_SIZE); @@ -166,18 +169,23 @@ configfs_read_bin_file(struct file *file, char __user *buf, retval = -ETXTBSY; goto out; } - buffer->read_in_progress = 1; + buffer->read_in_progress = true; if (buffer->needs_read_fill) { /* perform first read with buf == NULL to get extent */ - len = bin_attr->read(item, NULL, 0); + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, NULL, 0); + else + len = -ENOENT; + up_read(&frag->frag_sem); if (len <= 0) { retval = len; goto out; } /* do not exceed the maximum value */ - if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) { + if (buffer->cb_max_size && len > buffer->cb_max_size) { retval = -EFBIG; goto out; } @@ -190,7 +198,13 @@ configfs_read_bin_file(struct file *file, char __user *buf, buffer->bin_buffer_size = len; /* perform second read to fill buffer */ - len = bin_attr->read(item, buffer->bin_buffer, len); + down_read(&frag->frag_sem); + if (!frag->frag_dead) + len = buffer->bin_attr->read(buffer->item, + buffer->bin_buffer, len); + else + len = -ENOENT; + up_read(&frag->frag_sem); if (len < 0) { retval = len; vfree(buffer->bin_buffer); @@ -240,25 +254,17 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size return error ? -EFAULT : count; } - -/** - * flush_write_buffer - push buffer to config_item. - * @dentry: dentry to the attribute - * @buffer: data buffer for file. - * @count: number of bytes - * - * Get the correct pointers for the config_item and the attribute we're - * dealing with, then call the store() method for the attribute, - * passing the buffer that we acquired in fill_write_buffer(). - */ - static int -flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size_t count) +flush_write_buffer(struct file *file, struct configfs_buffer *buffer, size_t count) { - struct configfs_attribute * attr = to_attr(dentry); - struct config_item * item = to_item(dentry->d_parent); - - return attr->store(item, buffer->page, count); + struct configfs_fragment *frag = to_frag(file); + int res = -ENOENT; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) + res = buffer->attr->store(buffer->item, buffer->page, count); + up_read(&frag->frag_sem); + return res; } @@ -282,13 +288,13 @@ flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size static ssize_t configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct configfs_buffer * buffer = file->private_data; + struct configfs_buffer *buffer = file->private_data; ssize_t len; mutex_lock(&buffer->mutex); len = fill_write_buffer(buffer, buf, count); if (len > 0) - len = flush_write_buffer(file->f_path.dentry, buffer, len); + len = flush_write_buffer(file, buffer, len); if (len > 0) *ppos += len; mutex_unlock(&buffer->mutex); @@ -313,8 +319,6 @@ configfs_write_bin_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct configfs_buffer *buffer = file->private_data; - struct dentry *dentry = file->f_path.dentry; - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); void *tbuf = NULL; ssize_t len; @@ -325,13 +329,13 @@ configfs_write_bin_file(struct file *file, const char __user *buf, len = -ETXTBSY; goto out; } - buffer->write_in_progress = 1; + buffer->write_in_progress = true; /* buffer grows? */ if (*ppos + count > buffer->bin_buffer_size) { - if (bin_attr->cb_max_size && - *ppos + count > bin_attr->cb_max_size) { + if (buffer->cb_max_size && + *ppos + count > buffer->cb_max_size) { len = -EFBIG; goto out; } @@ -363,31 +367,51 @@ out: return len; } -static int check_perm(struct inode * inode, struct file * file, int type) +static int __configfs_open_file(struct inode *inode, struct file *file, int type) { - struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent); - struct configfs_attribute * attr = to_attr(file->f_path.dentry); - struct configfs_bin_attribute *bin_attr = NULL; - struct configfs_buffer * buffer; - struct configfs_item_operations * ops = NULL; - int error = 0; + struct dentry *dentry = file->f_path.dentry; + struct configfs_fragment *frag = to_frag(file); + struct configfs_attribute *attr; + struct configfs_buffer *buffer; + int error; - if (!item || !attr) - goto Einval; + error = -ENOMEM; + buffer = kzalloc(sizeof(struct configfs_buffer), GFP_KERNEL); + if (!buffer) + goto out; - if (type & CONFIGFS_ITEM_BIN_ATTR) - bin_attr = to_bin_attr(file->f_path.dentry); + error = -ENOENT; + down_read(&frag->frag_sem); + if (unlikely(frag->frag_dead)) + goto out_free_buffer; - /* Grab the module reference for this attribute if we have one */ - if (!try_module_get(attr->ca_owner)) { - error = -ENODEV; - goto Done; + error = -EINVAL; + buffer->item = to_item(dentry->d_parent); + if (!buffer->item) + goto out_free_buffer; + + attr = to_attr(dentry); + if (!attr) + goto out_put_item; + + if (type & CONFIGFS_ITEM_BIN_ATTR) { + buffer->bin_attr = to_bin_attr(dentry); + buffer->cb_max_size = buffer->bin_attr->cb_max_size; + } else { + buffer->attr = attr; } - if (item->ci_type) - ops = item->ci_type->ct_item_ops; - else - goto Eaccess; + buffer->owner = attr->ca_owner; + /* Grab the module reference for this attribute if we have one */ + error = -ENODEV; + if (!try_module_get(buffer->owner)) + goto out_put_item; + + error = -EACCES; + if (!buffer->item->ci_type) + goto out_put_module; + + buffer->ops = buffer->item->ci_type->ct_item_ops; /* File needs write support. * The inode's perms must say it's ok, @@ -395,13 +419,11 @@ static int check_perm(struct inode * inode, struct file * file, int type) */ if (file->f_mode & FMODE_WRITE) { if (!(inode->i_mode & S_IWUGO)) - goto Eaccess; - + goto out_put_module; if ((type & CONFIGFS_ITEM_ATTR) && !attr->store) - goto Eaccess; - - if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write) - goto Eaccess; + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->write) + goto out_put_module; } /* File needs read support. @@ -410,92 +432,72 @@ static int check_perm(struct inode * inode, struct file * file, int type) */ if (file->f_mode & FMODE_READ) { if (!(inode->i_mode & S_IRUGO)) - goto Eaccess; - + goto out_put_module; if ((type & CONFIGFS_ITEM_ATTR) && !attr->show) - goto Eaccess; - - if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read) - goto Eaccess; + goto out_put_module; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->read) + goto out_put_module; } - /* No error? Great, allocate a buffer for the file, and store it - * it in file->private_data for easy access. - */ - buffer = kzalloc(sizeof(struct configfs_buffer),GFP_KERNEL); - if (!buffer) { - error = -ENOMEM; - goto Enomem; - } mutex_init(&buffer->mutex); buffer->needs_read_fill = 1; - buffer->read_in_progress = 0; - buffer->write_in_progress = 0; - buffer->ops = ops; + buffer->read_in_progress = false; + buffer->write_in_progress = false; file->private_data = buffer; - goto Done; + up_read(&frag->frag_sem); + return 0; - Einval: - error = -EINVAL; - goto Done; - Eaccess: - error = -EACCES; - Enomem: - module_put(attr->ca_owner); - Done: - if (error && item) - config_item_put(item); +out_put_module: + module_put(buffer->owner); +out_put_item: + config_item_put(buffer->item); +out_free_buffer: + up_read(&frag->frag_sem); + kfree(buffer); +out: return error; } static int configfs_release(struct inode *inode, struct file *filp) { - struct config_item * item = to_item(filp->f_path.dentry->d_parent); - struct configfs_attribute * attr = to_attr(filp->f_path.dentry); - struct module * owner = attr->ca_owner; - struct configfs_buffer * buffer = filp->private_data; - - if (item) - config_item_put(item); - /* After this point, attr should not be accessed. */ - module_put(owner); - - if (buffer) { - if (buffer->page) - free_page((unsigned long)buffer->page); - mutex_destroy(&buffer->mutex); - kfree(buffer); - } + struct configfs_buffer *buffer = filp->private_data; + + module_put(buffer->owner); + if (buffer->page) + free_page((unsigned long)buffer->page); + mutex_destroy(&buffer->mutex); + kfree(buffer); return 0; } static int configfs_open_file(struct inode *inode, struct file *filp) { - return check_perm(inode, filp, CONFIGFS_ITEM_ATTR); + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_ATTR); } static int configfs_open_bin_file(struct inode *inode, struct file *filp) { - return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR); + return __configfs_open_file(inode, filp, CONFIGFS_ITEM_BIN_ATTR); } -static int configfs_release_bin_file(struct inode *inode, struct file *filp) +static int configfs_release_bin_file(struct inode *inode, struct file *file) { - struct configfs_buffer *buffer = filp->private_data; - struct dentry *dentry = filp->f_path.dentry; - struct config_item *item = to_item(dentry->d_parent); - struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); - ssize_t len = 0; - int ret; + struct configfs_buffer *buffer = file->private_data; - buffer->read_in_progress = 0; + buffer->read_in_progress = false; if (buffer->write_in_progress) { - buffer->write_in_progress = 0; - - len = bin_attr->write(item, buffer->bin_buffer, - buffer->bin_buffer_size); - + struct configfs_fragment *frag = to_frag(file); + buffer->write_in_progress = false; + + down_read(&frag->frag_sem); + if (!frag->frag_dead) { + /* result of ->release() is ignored */ + buffer->bin_attr->write(buffer->item, + buffer->bin_buffer, + buffer->bin_buffer_size); + } + up_read(&frag->frag_sem); /* vfree on NULL is safe */ vfree(buffer->bin_buffer); buffer->bin_buffer = NULL; @@ -503,10 +505,8 @@ static int configfs_release_bin_file(struct inode *inode, struct file *filp) buffer->needs_read_fill = 1; } - ret = configfs_release(inode, filp); - if (len < 0) - return len; - return ret; + configfs_release(inode, file); + return 0; } @@ -541,7 +541,7 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib inode_lock_nested(d_inode(dir), I_MUTEX_NORMAL); error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode, - CONFIGFS_ITEM_ATTR); + CONFIGFS_ITEM_ATTR, parent_sd->s_frag); inode_unlock(d_inode(dir)); return error; @@ -563,7 +563,7 @@ int configfs_create_bin_file(struct config_item *item, inode_lock_nested(dir->d_inode, I_MUTEX_NORMAL); error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode, - CONFIGFS_ITEM_BIN_ATTR); + CONFIGFS_ITEM_BIN_ATTR, parent_sd->s_frag); inode_unlock(dir->d_inode); return error; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index fea6db1ee065..afd79a1a34b3 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -157,11 +157,42 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna !type->ct_item_ops->allow_link) goto out_put; + /* + * This is really sick. What they wanted was a hybrid of + * link(2) and symlink(2) - they wanted the target resolved + * at syscall time (as link(2) would've done), be a directory + * (which link(2) would've refused to do) *AND* be a deep + * fucking magic, making the target busy from rmdir POV. + * symlink(2) is nothing of that sort, and the locking it + * gets matches the normal symlink(2) semantics. Without + * attempts to resolve the target (which might very well + * not even exist yet) done prior to locking the parent + * directory. This perversion, OTOH, needs to resolve + * the target, which would lead to obvious deadlocks if + * attempted with any directories locked. + * + * Unfortunately, that garbage is userland ABI and we should've + * said "no" back in 2005. Too late now, so we get to + * play very ugly games with locking. + * + * Try *ANYTHING* of that sort in new code, and you will + * really regret it. Just ask yourself - what could a BOFH + * do to me and do I want to find it out first-hand? + * + * AV, a thoroughly annoyed bastard. + */ + inode_unlock(dir); ret = get_target(symname, &path, &target_item, dentry->d_sb); + inode_lock(dir); if (ret) goto out_put; - ret = type->ct_item_ops->allow_link(parent_item, target_item); + if (dentry->d_inode || d_unhashed(dentry)) + ret = -EEXIST; + else + ret = inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (!ret) + ret = type->ct_item_ops->allow_link(parent_item, target_item); if (!ret) { mutex_lock(&configfs_symlink_mutex); ret = create_link(parent_item, target_item, dentry); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index c160d2d0e18d..57a97b38a2fa 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -114,6 +114,8 @@ int fscrypt_process_policy(struct file *filp, if (!inode_has_encryption_context(inode)) { if (!S_ISDIR(inode->i_mode)) ret = -ENOTDIR; + else if (IS_DEADDIR(inode)) + ret = -ENOENT; else if (!inode->i_sb->s_cop->empty_dir) ret = -EOPNOTSUPP; else if (!inode->i_sb->s_cop->empty_dir(inode)) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 77e9cd7a0137..20ee612017bf 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -170,19 +170,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void debugfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, debugfs_i_callback); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .destroy_inode = debugfs_destroy_inode, }; static struct vfsmount *debugfs_automount(struct path *path) diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 30e4e01db35a..b14bb2c46042 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -800,6 +800,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_delete_debug_file(ls); + idr_destroy(&ls->ls_recover_idr); kfree(ls->ls_recover_buf); /* diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 9c47f1c14a8b..a47ae99f7bcb 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -683,7 +683,7 @@ int dlm_ls_start(struct dlm_ls *ls) error = dlm_config_nodes(ls->ls_name, &nodes, &count); if (error < 0) - goto fail; + goto fail_rv; spin_lock(&ls->ls_recover_lock); @@ -715,8 +715,9 @@ int dlm_ls_start(struct dlm_ls *ls) return 0; fail: - kfree(rv); kfree(nodes); + fail_rv: + kfree(rv); return error; } diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c index 7cd24bccd4fe..37be29f21d04 100644 --- a/fs/dlm/memory.c +++ b/fs/dlm/memory.c @@ -38,10 +38,8 @@ int __init dlm_memory_init(void) void dlm_memory_exit(void) { - if (lkb_cache) - kmem_cache_destroy(lkb_cache); - if (rsb_cache) - kmem_cache_destroy(rsb_cache); + kmem_cache_destroy(lkb_cache); + kmem_cache_destroy(rsb_cache); } char *dlm_allocate_lvb(struct dlm_ls *ls) @@ -86,8 +84,7 @@ void dlm_free_lkb(struct dlm_lkb *lkb) struct dlm_user_args *ua; ua = lkb->lkb_ua; if (ua) { - if (ua->lksb.sb_lvbptr) - kfree(ua->lksb.sb_lvbptr); + kfree(ua->lksb.sb_lvbptr); kfree(ua); } } diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 9ac65914ab5b..bb0d307deadd 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -25,6 +25,7 @@ #include "lvb_table.h" #include "user.h" #include "ast.h" +#include "config.h" static const char name_prefix[] = "dlm"; static const struct file_operations device_fops; @@ -402,7 +403,7 @@ static int device_create_lockspace(struct dlm_lspace_params *params) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - error = dlm_new_lockspace(params->name, NULL, params->flags, + error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags, DLM_USER_LVB_LEN, NULL, NULL, NULL, &lockspace); if (error) @@ -700,7 +701,7 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, result.version[0] = DLM_DEVICE_VERSION_MAJOR; result.version[1] = DLM_DEVICE_VERSION_MINOR; result.version[2] = DLM_DEVICE_VERSION_PATCH; - memcpy(&result.lksb, &ua->lksb, sizeof(struct dlm_lksb)); + memcpy(&result.lksb, &ua->lksb, offsetof(struct dlm_lksb, sb_lvbptr)); result.user_lksb = ua->user_lksb; /* FIXME: dlm1 provides for the user's bastparam/addr to not be updated diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index e5e29f8c920b..ff6cf23be8a2 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -339,8 +339,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, struct extent_crypt_result ecr; int rc = 0; - BUG_ON(!crypt_stat || !crypt_stat->tfm - || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)); + if (!crypt_stat || !crypt_stat->tfm + || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) + return -EINVAL; + if (unlikely(ecryptfs_verbosity > 0)) { ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n", crypt_stat->key_size); @@ -1034,8 +1036,10 @@ int ecryptfs_read_and_validate_header_region(struct inode *inode) rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES, inode); - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); @@ -1397,8 +1401,10 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, ecryptfs_inode_to_lower(inode), ECRYPTFS_XATTR_NAME, file_size, ECRYPTFS_SIZE_AND_MARKER_BYTES); - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5c5ff9f6fe07..2a5e436ff8dd 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -326,9 +326,9 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode) static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, struct dentry *lower_dentry) { - struct inode *inode, *lower_inode = d_inode(lower_dentry); + struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent); + struct inode *inode, *lower_inode; struct ecryptfs_dentry_info *dentry_info; - struct vfsmount *lower_mnt; int rc = 0; dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL); @@ -340,16 +340,23 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, return ERR_PTR(-ENOMEM); } - lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); fsstack_copy_attr_atime(d_inode(dentry->d_parent), - d_inode(lower_dentry->d_parent)); + d_inode(path->dentry)); BUG_ON(!d_count(lower_dentry)); ecryptfs_set_dentry_private(dentry, dentry_info); - dentry_info->lower_path.mnt = lower_mnt; + dentry_info->lower_path.mnt = mntget(path->mnt); dentry_info->lower_path.dentry = lower_dentry; - if (d_really_is_negative(lower_dentry)) { + /* + * negative dentry can go positive under us here - its parent is not + * locked. That's OK and that could happen just as we return from + * ecryptfs_lookup() anyway. Just need to be careful and fetch + * ->d_inode only once - it's not stable here. + */ + lower_inode = READ_ONCE(lower_dentry->d_inode); + + if (!lower_inode) { /* We want to add because we couldn't find in lower */ d_add(dentry, NULL); return NULL; diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index fa218cd64f74..b134315fb69d 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1335,7 +1335,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat, printk(KERN_WARNING "Tag 1 packet contains key larger " "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES"); rc = -EINVAL; - goto out; + goto out_free; } memcpy((*new_auth_tok)->session_key.encrypted_key, &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2))); diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 4f457d5c4933..26464f9d9b76 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -397,6 +397,7 @@ int __init ecryptfs_init_messaging(void) * ecryptfs_message_buf_len), GFP_KERNEL); if (!ecryptfs_msg_ctx_arr) { + kfree(ecryptfs_daemon_hash); rc = -ENOMEM; printk(KERN_ERR "%s: Failed to allocate memory\n", __func__); goto out; diff --git a/fs/exec.c b/fs/exec.c index 81477116035d..bb03b98fd03b 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1353,7 +1353,7 @@ void setup_new_exec(struct linux_binprm * bprm) /* An exec changes our domain. We are no longer part of the thread group */ - current->self_exec_id++; + WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1); flush_signal_handlers(current, 0); } EXPORT_SYMBOL(setup_new_exec); @@ -1790,7 +1790,7 @@ static int do_execveat_common(int fd, struct filename *filename, current->fs->in_exec = 0; current->in_execve = 0; acct_update_integrals(current); - task_numa_free(current); + task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); putname(filename); diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 7a7bba7c2328..1730122b10e0 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -146,6 +146,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + err = PTR_ERR(tmp); goto out_err; } if (tmp != dentry) { @@ -506,26 +507,33 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * inode is actually connected to the parent. */ err = exportfs_get_name(mnt, target_dir, nbuf, result); - if (!err) { - inode_lock(target_dir->d_inode); - nresult = lookup_one_len(nbuf, target_dir, - strlen(nbuf)); - inode_unlock(target_dir->d_inode); - if (!IS_ERR(nresult)) { - if (nresult->d_inode) { - dput(result); - result = nresult; - } else - dput(nresult); - } + if (err) { + dput(target_dir); + goto err_result; } + inode_lock(target_dir->d_inode); + nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf)); + if (!IS_ERR(nresult)) { + if (unlikely(nresult->d_inode != result->d_inode)) { + dput(nresult); + nresult = ERR_PTR(-ESTALE); + } + } + inode_unlock(target_dir->d_inode); /* * At this point we are done with the parent, but it's pinned * by the child dentry anyway. */ dput(target_dir); + if (IS_ERR(nresult)) { + err = PTR_ERR(nresult); + goto err_result; + } + dput(result); + result = nresult; + /* * And finally make sure the dentry is actually acceptable * to NFSD. diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 85449a6ddc56..fe664949d442 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -697,10 +697,13 @@ static int ext2_get_blocks(struct inode *inode, if (!partial) { count++; mutex_unlock(&ei->truncate_mutex); - if (err) - goto cleanup; goto got_it; } + + if (err) { + mutex_unlock(&ei->truncate_mutex); + goto cleanup; + } } /* diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 6fcb29b393d3..186912c9bf56 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1047,9 +1047,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (EXT2_BLOCKS_PER_GROUP(sb) == 0) goto cantfind_ext2; - sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - - le32_to_cpu(es->s_first_data_block) - 1) - / EXT2_BLOCKS_PER_GROUP(sb)) + 1; + sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - + le32_to_cpu(es->s_first_data_block) - 1) + / EXT2_BLOCKS_PER_GROUP(sb)) + 1; db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) / EXT2_DESC_PER_BLOCK(sb); sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL); diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index babef30d440b..c8679b583561 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -55,6 +55,7 @@ #include <linux/buffer_head.h> #include <linux/init.h> +#include <linux/printk.h> #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> @@ -83,8 +84,8 @@ printk("\n"); \ } while (0) #else -# define ea_idebug(f...) -# define ea_bdebug(f...) +# define ea_idebug(inode, f...) no_printk(f) +# define ea_bdebug(bh, f...) no_printk(f) #endif static int ext2_xattr_set2(struct inode *, struct buffer_head *, @@ -835,8 +836,7 @@ ext2_xattr_cache_insert(struct mb_cache *cache, struct buffer_head *bh) error = mb_cache_entry_create(cache, GFP_NOFS, hash, bh->b_blocknr, 1); if (error) { if (error == -EBUSY) { - ea_bdebug(bh, "already in cache (%d cache entries)", - atomic_read(&ext2_xattr_cache->c_entry_count)); + ea_bdebug(bh, "already in cache"); error = 0; } } else diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 2455fe1446d6..de601f3c023d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -279,6 +279,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bh_p; if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," @@ -289,7 +290,14 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1); - if (!sbi->s_group_desc[group_desc]) { + bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc); + /* + * sbi_array_rcu_deref returns with rcu unlocked, this is ok since + * the pointer being dereferenced won't be dereferenced again. By + * looking at the usage in add_new_gdb() the value isn't modified, + * just the pointer, and so it remains valid. + */ + if (!bh_p) { ext4_error(sb, "Group descriptor not loaded - " "block_group = %u, group_desc = %u, desc = %u", block_group, group_desc, offset); @@ -297,10 +305,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } desc = (struct ext4_group_desc *)( - (__u8 *)sbi->s_group_desc[group_desc]->b_data + + (__u8 *)bh_p->b_data + offset * EXT4_DESC_SIZE(sb)); if (bh) - *bh = sbi->s_group_desc[group_desc]; + *bh = bh_p; return desc; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index e16bc4cec62e..6b3a32f75dad 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -75,6 +75,11 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) error_msg = "directory entry overrun"; + else if (unlikely(((char *) de - buf) + rlen > + size - EXT4_DIR_REC_LEN(1) && + ((char *) de - buf) + rlen != size)) { + error_msg = "directory entry too close to block end"; + } else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -106,7 +111,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; - int dir_has_error = 0; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); if (ext4_encrypted_inode(inode)) { @@ -120,12 +124,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } if (ext4_has_inline_data(inode)) { @@ -142,8 +148,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) return err; } - offset = ctx->pos & (sb->s_blocksize - 1); - while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; @@ -152,9 +156,18 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) goto errout; } cond_resched(); + offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); + if (err == 0) { + /* m_len should never be zero but let's avoid + * an infinite loop if it somehow is */ + if (map.m_len == 0) + map.m_len = 1; + ctx->pos += map.m_len * sb->s_blocksize; + continue; + } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); @@ -173,13 +186,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) } if (!bh) { - if (!dir_has_error) { - EXT4_ERROR_FILE(file, 0, - "directory contains a " - "hole at offset %llu", - (unsigned long long) ctx->pos); - dir_has_error = 1; - } /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 567a6c7af677..eb0ec5068423 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1367,7 +1367,7 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; + struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; unsigned int s_mount_flags; @@ -1427,7 +1427,7 @@ struct ext4_sb_info { #endif /* for buddy allocator */ - struct ext4_group_info ***s_group_info; + struct ext4_group_info ** __rcu *s_group_info; struct inode *s_buddy_cache; spinlock_t s_md_lock; unsigned short *s_mb_offsets; @@ -1475,7 +1475,7 @@ struct ext4_sb_info { unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; + struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; /* workqueue for reserved extent conversions (buffered io) */ @@ -1514,8 +1514,11 @@ struct ext4_sb_info { struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; - /* Barrier between changing inodes' journal flags and writepages ops. */ - struct percpu_rw_semaphore s_journal_flag_rwsem; + /* + * Barrier between writepages ops and changing any inode's JOURNAL_DATA + * or EXTENTS flag. + */ + struct percpu_rw_semaphore s_writepages_rwsem; /* Encryption support */ #ifdef CONFIG_EXT4_FS_ENCRYPTION @@ -1547,6 +1550,23 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) } /* + * Returns: sbi->field[index] + * Used to access an array element from the following sbi fields which require + * rcu protection to avoid dereferencing an invalid pointer due to reassignment + * - s_group_desc + * - s_group_info + * - s_flex_group + */ +#define sbi_array_rcu_deref(sbi, field, index) \ +({ \ + typeof(*((sbi)->field)) _v; \ + rcu_read_lock(); \ + _v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \ + rcu_read_unlock(); \ + _v; \ +}) + +/* * Inode dynamic state flags */ enum { @@ -2375,8 +2395,11 @@ int ext4_insert_dentry(struct inode *dir, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK @@ -2552,6 +2575,7 @@ extern int ext4_generic_delete_entry(handle_t *handle, extern bool ext4_empty_dir(struct inode *inode); /* resize.c */ +extern void ext4_kvfree_array_rcu(void *to_free); extern int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input); extern int ext4_group_extend(struct super_block *sb, @@ -2792,13 +2816,13 @@ static inline struct ext4_group_info *ext4_get_group_info(struct super_block *sb, ext4_group_t group) { - struct ext4_group_info ***grp_info; + struct ext4_group_info **grp_info; long indexv, indexh; BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - grp_info = EXT4_SB(sb)->s_group_info; indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - return grp_info[indexv][indexh]; + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; } /* @@ -2848,7 +2872,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) !inode_is_locked(inode)); down_write(&EXT4_I(inode)->i_data_sem); if (newsize > EXT4_I(inode)->i_disksize) - EXT4_I(inode)->i_disksize = newsize; + WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 106a5bb3ae68..999d2a54297d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1047,6 +1047,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ int err = 0; + size_t ext_size = 0; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ @@ -1138,6 +1139,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1217,6 +1222,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); + memset(bh->b_data + ext_size, 0, + inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1282,6 +1292,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; + size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) @@ -1307,9 +1318,11 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, goto out; } + ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ - memmove(bh->b_data, EXT4_I(inode)->i_data, - sizeof(EXT4_I(inode)->i_data)); + memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); + /* zero out unused area in the extent block */ + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); @@ -3432,8 +3445,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; @@ -3688,8 +3701,8 @@ static int ext4_split_convert_extents(handle_t *handle, __func__, inode->i_ino, (unsigned long long)map->m_lblk, map->m_len); - eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> - inode->i_sb->s_blocksize_bits; + eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) + >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; /* @@ -3742,8 +3755,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { -#ifdef EXT4_DEBUG - ext4_warning("Inode (%ld) finished: extent logical block %llu," +#ifdef CONFIG_EXT4_DEBUG + ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index fe76d0957a1f..59d3ea7094a0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -163,6 +163,13 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) } ret = __generic_file_write_iter(iocb, from); + /* + * Unaligned direct AIO must be the only IO in flight. Otherwise + * overlapping aligned IO after unaligned might result in data + * corruption. + */ + if (ret == -EIOCBQUEUED && unaligned_aio) + ext4_unwritten_wait(inode); inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 4f78e099de1d..c5af7bbf906f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -331,11 +331,13 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { - ext4_group_t f = ext4_flex_group(sbi, block_group); + struct flex_groups *fg; - atomic_inc(&sbi->s_flex_groups[f].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, + ext4_flex_group(sbi, block_group)); + atomic_inc(&fg->free_inodes); if (is_directory) - atomic_dec(&sbi->s_flex_groups[f].used_dirs); + atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2); @@ -376,12 +378,13 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; - struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; if (flex_size > 1) { - stats->free_inodes = atomic_read(&flex_group[g].free_inodes); - stats->free_clusters = atomic64_read(&flex_group[g].free_clusters); - stats->used_dirs = atomic_read(&flex_group[g].used_dirs); + struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), + s_flex_groups, g); + stats->free_inodes = atomic_read(&fg->free_inodes); + stats->free_clusters = atomic64_read(&fg->free_clusters); + stats->used_dirs = atomic_read(&fg->used_dirs); return; } @@ -988,7 +991,8 @@ got: if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group); - atomic_inc(&sbi->s_flex_groups[f].used_dirs); + atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, + f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { @@ -1011,7 +1015,8 @@ got: if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); - atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes); + atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_inodes); } inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 14007e621d2a..d2844fe9040d 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1217,6 +1217,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t offsets[4], offsets2[4]; Indirect chain[4], chain2[4]; Indirect *partial, *partial2; + Indirect *p = NULL, *p2 = NULL; ext4_lblk_t max_block; __le32 nr = 0, nr2 = 0; int n = 0, n2 = 0; @@ -1258,7 +1259,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, } - partial = ext4_find_shared(inode, n, offsets, chain, &nr); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); if (nr) { if (partial == chain) { /* Shared branch grows from the inode */ @@ -1283,13 +1284,11 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } end_range: - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); if (nr2) { if (partial2 == chain2) { /* @@ -1319,16 +1318,14 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } goto do_indirects; } /* Punch happened within the same level (n == n2) */ - partial = ext4_find_shared(inode, n, offsets, chain, &nr); - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); /* Free top, but only if partial2 isn't its subtree. */ if (nr) { @@ -1385,15 +1382,7 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - while (partial > chain) { - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - } - while (partial2 > chain2) { - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); - } - return 0; + goto cleanup; } /* @@ -1408,8 +1397,6 @@ end_range: partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } if (partial2 > chain2 && depth2 <= depth) { @@ -1417,11 +1404,21 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } } + +cleanup: + while (p && p > chain) { + BUFFER_TRACE(p->bh, "call brelse"); + brelse(p->bh); + p--; + } + while (p2 && p2 > chain2) { + BUFFER_TRACE(p2->bh, "call brelse"); + brelse(p2->bh); + p2--; + } return 0; do_indirects: @@ -1429,7 +1426,7 @@ do_indirects: switch (offsets[0]) { default: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_IND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); @@ -1437,7 +1434,7 @@ do_indirects: } case EXT4_IND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); @@ -1445,7 +1442,7 @@ do_indirects: } case EXT4_DIND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); @@ -1454,5 +1451,5 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - return 0; + goto cleanup; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 9a13f86fed62..4df4d31057b3 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1417,7 +1417,7 @@ int htree_inlinedir_to_tree(struct file *dir_file, err = ext4_htree_store_dirent(dir_file, hinfo->hash, hinfo->minor_hash, de, &tmp_str); if (err) { - count = err; + ret = err; goto out; } count++; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4815be26b15f..45bcde1969e3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2475,7 +2475,7 @@ update_disksize: * truncate are avoided by checking i_size under i_data_sem. */ disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT; - if (disksize > EXT4_I(inode)->i_disksize) { + if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; loff_t i_size; @@ -2652,7 +2652,7 @@ static int ext4_writepages(struct address_space *mapping, struct blk_plug plug; bool give_up_on_write = false; - percpu_down_read(&sbi->s_journal_flag_rwsem); + percpu_down_read(&sbi->s_writepages_rwsem); trace_ext4_writepages(inode, wbc); if (dax_mapping(mapping)) { @@ -2853,7 +2853,7 @@ retry: out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_journal_flag_rwsem); + percpu_up_read(&sbi->s_writepages_rwsem); return ret; } @@ -3957,6 +3957,15 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) trace_ext4_punch_hole(inode, offset, length, 0); + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + if (ext4_has_inline_data(inode)) { + down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_convert_inline_data(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); + if (ret) + return ret; + } + /* * Write out all dirty pages to avoid race conditions * Then release them. @@ -4585,6 +4594,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + EXT4_ERROR_INODE(inode, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -4733,7 +4754,7 @@ static int ext4_inode_blocks_set(handle_t *handle, struct ext4_inode_info *ei) { struct inode *inode = &(ei->vfs_inode); - u64 i_blocks = inode->i_blocks; + u64 i_blocks = READ_ONCE(inode->i_blocks); struct super_block *sb = inode->i_sb; if (i_blocks <= ~0U) { @@ -5071,11 +5092,15 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) offset = inode->i_size & (PAGE_SIZE - 1); /* - * All buffers in the last page remain valid? Then there's nothing to - * do. We do the check mainly to optimize the common PAGE_SIZE == - * blocksize case + * If the page is fully truncated, we don't need to wait for any commit + * (and we even should not as __ext4_journalled_invalidatepage() may + * strip all buffers from the page but keep the page dirty which can then + * confuse e.g. concurrent ext4_writepage() seeing dirty page without + * buffers). Also we don't need to wait for any commit if all buffers in + * the page remain valid. This is most beneficial for the common case of + * blocksize == PAGESIZE. */ - if (offset > PAGE_SIZE - i_blocksize(inode)) + if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { page = find_lock_page(inode->i_mapping, @@ -5223,7 +5248,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) { - if (orphan) + if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); goto err_out; } @@ -5459,10 +5484,25 @@ static int ext4_expand_extra_isize(struct inode *inode, { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; + unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) return 0; + /* this was checked at iget time, but double check for good measure */ + if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) || + (ei->i_extra_isize & 3)) { + EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + return -EFSCORRUPTED; + } + if ((new_extra_isize < ei->i_extra_isize) || + (new_extra_isize < 4) || + (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE)) + return -EINVAL; /* Should never happen */ + raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); @@ -5648,7 +5688,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_journal_flag_rwsem); + percpu_down_write(&sbi->s_writepages_rwsem); jbd2_journal_lock_updates(journal); /* @@ -5665,7 +5705,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); ext4_inode_resume_unlocked_dio(inode); return err; } @@ -5674,7 +5714,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_journal_flag_rwsem); + percpu_up_write(&sbi->s_writepages_rwsem); if (val) up_write(&EXT4_I(inode)->i_mmap_sem); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2880e017cd0a..baa2f6375226 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -727,7 +727,7 @@ group_add_out: if (err == 0) err = err2; mnt_drop_write_file(filp); - if (!err && (o_group > EXT4_SB(sb)->s_groups_count) && + if (!err && (o_group < EXT4_SB(sb)->s_groups_count) && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, o_group); @@ -749,6 +749,13 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* + * We haven't replayed the journal, so we cannot use our + * block-bitmap-guided storage zapping commands. + */ + if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) + return -EROFS; + if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a49d0e5d7baf..c18668e3135e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2377,7 +2377,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; - struct ext4_group_info ***new_groupinfo; + struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); @@ -2390,13 +2390,16 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } - if (sbi->s_group_info) { - memcpy(new_groupinfo, sbi->s_group_info, + rcu_read_lock(); + old_groupinfo = rcu_dereference(sbi->s_group_info); + if (old_groupinfo) + memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); - kvfree(sbi->s_group_info); - } - sbi->s_group_info = new_groupinfo; + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + if (old_groupinfo) + ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; @@ -2408,6 +2411,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, { int i; int metalen = 0; + int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2426,12 +2430,12 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, "for a buddy group"); goto exit_meta_group_info; } - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = - meta_group_info; + rcu_read_lock(); + rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; + rcu_read_unlock(); } - meta_group_info = - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; + meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); @@ -2479,8 +2483,13 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { - kfree(sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]); - sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)] = NULL; + struct ext4_group_info ***group_info; + + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); + kfree(group_info[idx]); + group_info[idx] = NULL; + rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; @@ -2493,6 +2502,7 @@ static int ext4_mb_init_backend(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; + struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); @@ -2527,11 +2537,16 @@ err_freebuddy: while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) - kfree(sbi->s_group_info[i]); + kfree(group_info[i]); + rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - kvfree(sbi->s_group_info); + rcu_read_lock(); + kvfree(rcu_dereference(sbi->s_group_info)); + rcu_read_unlock(); return -ENOMEM; } @@ -2720,7 +2735,7 @@ int ext4_mb_release(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; - struct ext4_group_info *grinfo; + struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); @@ -2738,9 +2753,12 @@ int ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); + rcu_read_lock(); + group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) - kfree(sbi->s_group_info[i]); - kvfree(sbi->s_group_info); + kfree(group_info[i]); + kvfree(group_info); + rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); @@ -2998,7 +3016,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4888,7 +4907,8 @@ do_more: if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) @@ -5033,7 +5053,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed), - &sbi->s_flex_groups[flex_group].free_clusters); + &sbi_array_rcu_deref(sbi, s_flex_groups, + flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 364ea4d4a943..bce2d696d6b9 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -434,6 +434,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -458,6 +459,8 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; + percpu_down_write(&sbi->s_writepages_rwsem); + /* * Worst case we can touch the allocation bitmaps, a bgd * block, and a block to link in the orphan list. We do need @@ -468,7 +471,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(handle)) { retval = PTR_ERR(handle); - return retval; + goto out_unlock; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; @@ -479,7 +482,7 @@ int ext4_ext_migrate(struct inode *inode) if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); - return retval; + goto out_unlock; } i_size_write(tmp_inode, i_size_read(inode)); /* @@ -521,7 +524,7 @@ int ext4_ext_migrate(struct inode *inode) */ ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); - goto out; + goto out_tmp_inode; } ei = EXT4_I(inode); @@ -602,10 +605,11 @@ err_out: /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); ext4_journal_stop(handle); -out: +out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); - +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return retval; } @@ -615,7 +619,8 @@ out: int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; - struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; @@ -639,9 +644,13 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); + percpu_down_write(&sbi->s_writepages_rwsem); + handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_unlock; + } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); @@ -676,5 +685,7 @@ int ext4_ind_migrate(struct inode *inode) errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); +out_unlock: + percpu_up_write(&sbi->s_writepages_rwsem); return ret; } diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index c2e830a6206d..fb1ad9510c5f 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -119,10 +119,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, { __ext4_warning(sb, function, line, "%s", msg); __ext4_warning(sb, function, line, - "MMP failure info: last update time: %llu, last update " - "node: %s, last update device: %s", - (long long unsigned int) le64_to_cpu(mmp->mmp_time), - mmp->mmp_nodename, mmp->mmp_bdevname); + "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", + (unsigned long long)le64_to_cpu(mmp->mmp_time), + (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, + (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); } /* @@ -153,6 +153,7 @@ static int kmmpd(void *data) mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); + BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); bdevname(bh->b_bdev, mmp->mmp_bdevname); memcpy(mmp->mmp_nodename, init_utsname()->nodename, @@ -377,7 +378,8 @@ skip: /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 3c3757ee11f0..339ede11896a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -79,8 +79,18 @@ static struct buffer_head *ext4_append(handle_t *handle, static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent); +/* + * Hints to ext4_read_dirblock regarding whether we expect a directory + * block being read to be an index block, or a block containing + * directory entries (and if the latter, whether it was found via a + * logical block in an htree index block). This is used to control + * what sort of sanity checkinig ext4_read_dirblock() will do on the + * directory block read from the storage device. EITHER will means + * the caller doesn't know what kind of directory block will be read, + * so no specific verification will be done. + */ typedef enum { - EITHER, INDEX, DIRENT + EITHER, INDEX, DIRENT, DIRENT_HTREE } dirblock_type_t; #define ext4_read_dirblock(inode, block, type) \ @@ -106,11 +116,14 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, return bh; } - if (!bh) { + if (!bh && (type == INDEX || type == DIRENT_HTREE)) { ext4_error_inode(inode, func, line, block, - "Directory hole found"); + "Directory hole found for htree %s block", + (type == INDEX) ? "index" : "leaf"); return ERR_PTR(-EFSCORRUPTED); } + if (!bh) + return NULL; dirent = (struct ext4_dir_entry *) bh->b_data; /* Determine whether or not we have an index block */ if (is_dx(inode)) { @@ -960,7 +973,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) return PTR_ERR(bh); @@ -1432,6 +1445,7 @@ restart: /* * We deal with the read-ahead logic here. */ + cond_resched(); if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; @@ -1537,7 +1551,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, return (struct buffer_head *) frame; do { block = dx_get_block(frame->at); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) goto errout; @@ -2135,6 +2149,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); @@ -2142,6 +2163,11 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { bh = ext4_read_dirblock(dir, block, DIRENT); + if (bh == NULL) { + bh = ext4_bread(handle, dir, block, + EXT4_GET_BLOCKS_CREATE); + goto add_to_new_block; + } if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2162,6 +2188,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, brelse(bh); } bh = ext4_append(handle, dir, &block); +add_to_new_block: if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2203,7 +2230,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, return PTR_ERR(frame); entries = frame->entries; at = frame->at; - bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT); + bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; @@ -2702,7 +2729,7 @@ bool ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; - struct ext4_dir_entry_2 *de, *de1; + struct ext4_dir_entry_2 *de; struct super_block *sb; if (ext4_has_inline_data(inode)) { @@ -2719,36 +2746,48 @@ bool ext4_empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "invalid size"); return true; } - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, + * so treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; - de1 = ext4_next_entry(de, sb->s_blocksize); - if (le32_to_cpu(de->inode) != inode->i_ino || - le32_to_cpu(de1->inode) == 0 || - strcmp(".", de->name) || strcmp("..", de1->name)) { - ext4_warning_inode(inode, "directory missing '.' and/or '..'"); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + 0) || + le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) { + ext4_warning_inode(inode, "directory missing '.'"); brelse(bh); return true; } - offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) + - ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize); - de = ext4_next_entry(de1, sb->s_blocksize); + offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); + de = ext4_next_entry(de, sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, + offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + ext4_warning_inode(inode, "directory missing '..'"); + brelse(bh); + return true; + } + offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); while (offset < inode->i_size) { - if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { + if (!(offset & (sb->s_blocksize - 1))) { unsigned int lblock; brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); bh = ext4_read_dirblock(inode, lblock, EITHER); + if (bh == NULL) { + offset += sb->s_blocksize; + continue; + } if (IS_ERR(bh)) return true; - de = (struct ext4_dir_entry_2 *) bh->b_data; } + de = (struct ext4_dir_entry_2 *) (bh->b_data + + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, offset)) { - de = (struct ext4_dir_entry_2 *)(bh->b_data + - sb->s_blocksize); offset = (offset | (sb->s_blocksize - 1)) + 1; continue; } @@ -2757,7 +2796,6 @@ bool ext4_empty_dir(struct inode *inode) return false; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); - de = ext4_next_entry(de, sb->s_blocksize); } brelse(bh); return true; @@ -3052,18 +3090,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - if (inode->i_nlink == 0) { - ext4_warning_inode(inode, "Deleting file '%.*s' with no links", - dentry->d_name.len, dentry->d_name.name); - set_nlink(inode, 1); - } retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto end_unlink; dir->i_ctime = dir->i_mtime = ext4_current_time(dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); - drop_nlink(inode); + if (inode->i_nlink == 0) + ext4_warning_inode(inode, "Deleting file '%.*s' with no links", + dentry->d_name.len, dentry->d_name.name); + else + drop_nlink(inode); if (!inode->i_nlink) ext4_orphan_add(handle, inode); inode->i_ctime = ext4_current_time(inode); @@ -3302,7 +3339,10 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, so + * treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) { *retval = PTR_ERR(bh); return NULL; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 0094923e5ebf..94f60f9d57fd 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -469,16 +469,25 @@ int ext4_bio_write_page(struct ext4_io_submit *io, nr_to_submit) { gfp_t gfp_flags = GFP_NOFS; + /* + * Since bounce page allocation uses a mempool, we can only use + * a waiting mask (i.e. request guaranteed allocation) on the + * first page of the bio. Otherwise it can deadlock. + */ + if (io->io_bio) + gfp_flags = GFP_NOWAIT | __GFP_NOWARN; retry_encrypt: data_page = fscrypt_encrypt_page(inode, page, gfp_flags); if (IS_ERR(data_page)) { ret = PTR_ERR(data_page); - if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) { - if (io->io_bio) { + if (ret == -ENOMEM && + (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { + gfp_flags = GFP_NOFS; + if (io->io_bio) ext4_io_submit(io); - congestion_wait(BLK_RW_ASYNC, HZ/50); - } - gfp_flags |= __GFP_NOFAIL; + else + gfp_flags |= __GFP_NOFAIL; + congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry_encrypt; } data_page = NULL; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 67b359629a66..845d9841c91c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -16,6 +16,33 @@ #include "ext4_jbd2.h" +struct ext4_rcu_ptr { + struct rcu_head rcu; + void *ptr; +}; + +static void ext4_rcu_ptr_callback(struct rcu_head *head) +{ + struct ext4_rcu_ptr *ptr; + + ptr = container_of(head, struct ext4_rcu_ptr, rcu); + kvfree(ptr->ptr); + kfree(ptr); +} + +void ext4_kvfree_array_rcu(void *to_free) +{ + struct ext4_rcu_ptr *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); + + if (ptr) { + ptr->ptr = to_free; + call_rcu(&ptr->rcu, ext4_rcu_ptr_callback); + return; + } + synchronize_rcu(); + kvfree(to_free); +} + int ext4_resize_begin(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -541,8 +568,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, brelse(gdb); goto out; } - memcpy(gdb->b_data, sbi->s_group_desc[j]->b_data, - gdb->b_size); + memcpy(gdb->b_data, sbi_array_rcu_deref(sbi, + s_group_desc, j)->b_data, gdb->b_size); set_buffer_uptodate(gdb); err = ext4_handle_dirty_metadata(handle, NULL, gdb); @@ -849,13 +876,15 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, } brelse(dind); - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; - EXT4_SB(sb)->s_group_desc = n_group_desc; + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + ext4_kvfree_array_rcu(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); err = ext4_handle_dirty_super(handle, sb); @@ -903,15 +932,24 @@ static int add_new_gdb_meta_bg(struct super_block *sb, return err; } - o_group_desc = EXT4_SB(sb)->s_group_desc; + rcu_read_lock(); + o_group_desc = rcu_dereference(EXT4_SB(sb)->s_group_desc); memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + rcu_read_unlock(); n_group_desc[gdb_num] = gdb_bh; - EXT4_SB(sb)->s_group_desc = n_group_desc; - EXT4_SB(sb)->s_gdb_count++; - kvfree(o_group_desc); + BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); + if (err) { + kvfree(n_group_desc); + brelse(gdb_bh); + return err; + } + + rcu_assign_pointer(EXT4_SB(sb)->s_group_desc, n_group_desc); + EXT4_SB(sb)->s_gdb_count++; + ext4_kvfree_array_rcu(o_group_desc); return err; } @@ -1173,7 +1211,8 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, * use non-sparse filesystems anymore. This is already checked above. */ if (gdb_off) { - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); @@ -1255,7 +1294,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, /* * get_write_access() has been called on gdb_bh by ext4_add_new_desc(). */ - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); /* Update group descriptor block for new group */ gdp = (struct ext4_group_desc *)(gdb_bh->b_data + gdb_off * EXT4_DESC_SIZE(sb)); @@ -1383,11 +1422,14 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_read(&sbi->s_freeclusters_counter)); if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) { ext4_group_t flex_group; + struct flex_groups *fg; + flex_group = ext4_flex_group(sbi, group_data[0].group); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic64_add(EXT4_NUM_B2C(sbi, free_blocks), - &sbi->s_flex_groups[flex_group].free_clusters); + &fg->free_clusters); atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count, - &sbi->s_flex_groups[flex_group].free_inodes); + &fg->free_inodes); } /* @@ -1482,7 +1524,8 @@ exit_journal: for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - gdb_bh = sbi->s_group_desc[gdb_num]; + gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, + gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, @@ -2040,6 +2083,10 @@ out: free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); - ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); return err; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a6c7ace9cfd1..ed0520fe4dad 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -344,7 +344,8 @@ static void save_error_info(struct super_block *sb, const char *func, unsigned int line) { __save_error_info(sb, func, line); - ext4_commit_super(sb, 1); + if (!bdev_read_only(sb->s_bdev)) + ext4_commit_super(sb, 1); } /* @@ -826,6 +827,8 @@ static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; + struct buffer_head **group_desc; + struct flex_groups **flex_groups; int aborted = 0; int i, err; @@ -857,15 +860,23 @@ static void ext4_put_super(struct super_block *sb) if (!(sb->s_flags & MS_RDONLY)) ext4_commit_super(sb, 1); + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); - kvfree(sbi->s_flex_groups); + brelse(group_desc[i]); + kvfree(group_desc); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) @@ -2109,8 +2120,8 @@ done: int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct flex_groups *new_groups; - int size; + struct flex_groups **old_groups, **new_groups; + int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; @@ -2119,22 +2130,37 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) if (size <= sbi->s_flex_groups_allocated) return 0; - size = roundup_pow_of_two(size * sizeof(struct flex_groups)); - new_groups = ext4_kvzalloc(size, GFP_KERNEL); + new_groups = ext4_kvzalloc(roundup_pow_of_two(size * + sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { - ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", - size / (int) sizeof(struct flex_groups)); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex group pointers", size); return -ENOMEM; } - - if (sbi->s_flex_groups) { - memcpy(new_groups, sbi->s_flex_groups, - (sbi->s_flex_groups_allocated * - sizeof(struct flex_groups))); - kvfree(sbi->s_flex_groups); + for (i = sbi->s_flex_groups_allocated; i < size; i++) { + new_groups[i] = ext4_kvzalloc(roundup_pow_of_two( + sizeof(struct flex_groups)), + GFP_KERNEL); + if (!new_groups[i]) { + for (j = sbi->s_flex_groups_allocated; j < i; j++) + kvfree(new_groups[j]); + kvfree(new_groups); + ext4_msg(sb, KERN_ERR, + "not enough memory for %d flex groups", size); + return -ENOMEM; + } } - sbi->s_flex_groups = new_groups; - sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + rcu_read_lock(); + old_groups = rcu_dereference(sbi->s_flex_groups); + if (old_groups) + memcpy(new_groups, old_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups *))); + rcu_read_unlock(); + rcu_assign_pointer(sbi->s_flex_groups, new_groups); + sbi->s_flex_groups_allocated = size; + if (old_groups) + ext4_kvfree_array_rcu(old_groups); return 0; } @@ -2142,6 +2168,7 @@ static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; + struct flex_groups *fg; ext4_group_t flex_group; int i, err; @@ -2159,12 +2186,11 @@ static int ext4_fill_flex_info(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); - atomic_add(ext4_free_inodes_count(sb, gdp), - &sbi->s_flex_groups[flex_group].free_inodes); + fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); + atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), - &sbi->s_flex_groups[flex_group].free_clusters); - atomic_add(ext4_used_dirs_count(sb, gdp), - &sbi->s_flex_groups[flex_group].used_dirs); + &fg->free_clusters); + atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; @@ -2743,17 +2769,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_QUOTA - if (ext4_has_feature_quota(sb) && !readonly) { - ext4_msg(sb, KERN_ERR, - "Filesystem with quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); - return 0; - } - if (ext4_has_feature_project(sb) && !readonly) { +#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) + if (!readonly && (ext4_has_feature_quota(sb) || + ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, - "Filesystem with project quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); + "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ @@ -3342,6 +3362,40 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } +static void ext4_clamp_want_extra_isize(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + unsigned def_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + + if (sbi->s_inode_size == EXT4_GOOD_OLD_INODE_SIZE) { + sbi->s_want_extra_isize = 0; + return; + } + if (sbi->s_want_extra_isize < 4) { + sbi->s_want_extra_isize = def_extra_isize; + if (ext4_has_feature_extra_isize(sb)) { + if (sbi->s_want_extra_isize < + le16_to_cpu(es->s_want_extra_isize)) + sbi->s_want_extra_isize = + le16_to_cpu(es->s_want_extra_isize); + if (sbi->s_want_extra_isize < + le16_to_cpu(es->s_min_extra_isize)) + sbi->s_want_extra_isize = + le16_to_cpu(es->s_min_extra_isize); + } + } + /* Check if enough inode space is available */ + if ((sbi->s_want_extra_isize > sbi->s_inode_size) || + (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > + sbi->s_inode_size)) { + sbi->s_want_extra_isize = def_extra_isize; + ext4_msg(sb, KERN_INFO, + "required extra inode space not available"); + } +} + static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; @@ -3375,9 +3429,10 @@ static void ext4_set_resv_clusters(struct super_block *sb) static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); - struct buffer_head *bh; + struct buffer_head *bh, **group_desc; struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct flex_groups **flex_groups; ext4_fsblk_t block; ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; @@ -3766,7 +3821,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", - sbi->s_blocks_per_group); + sbi->s_inodes_per_group); goto failed_mount; } sbi->s_itb_per_group = sbi->s_inodes_per_group / @@ -3897,9 +3952,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { - ext4_msg(sb, KERN_WARNING, "groups count too large: %u " + ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " - "blocks per group %lu)", sbi->s_groups_count, + "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); @@ -3927,9 +3982,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } } - sbi->s_group_desc = ext4_kvmalloc(db_count * + rcu_assign_pointer(sbi->s_group_desc, + ext4_kvmalloc(db_count * sizeof(struct buffer_head *), - GFP_KERNEL); + GFP_KERNEL)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); ret = -ENOMEM; @@ -3939,14 +3995,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) bgl_lock_init(sbi->s_blockgroup_lock); for (i = 0; i < db_count; i++) { + struct buffer_head *bh; + block = descriptor_loc(sb, logical_sb_block, i); - sbi->s_group_desc[i] = sb_bread_unmovable(sb, block); - if (!sbi->s_group_desc[i]) { + bh = sb_bread_unmovable(sb, block); + if (!bh) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); db_count = i; goto failed_mount2; } + rcu_read_lock(); + rcu_dereference(sbi->s_group_desc)[i] = bh; + rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { @@ -4034,7 +4095,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "data=, fs mounted w/o journal"); goto failed_mount_wq; } - sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM; + sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); sbi->s_journal = NULL; @@ -4156,29 +4217,7 @@ no_journal: if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY)) sb->s_flags |= MS_RDONLY; - /* determine the minimum size of new large inodes, if present */ - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - if (ext4_has_feature_extra_isize(sb)) { - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_want_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_want_extra_isize); - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_min_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_min_extra_isize); - } - } - /* Check if enough inode space is available */ - if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > - sbi->s_inode_size) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - ext4_msg(sb, KERN_INFO, "required extra inode space not" - "available"); - } + ext4_clamp_want_extra_isize(sb); ext4_set_resv_clusters(sb); @@ -4217,7 +4256,7 @@ no_journal: err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) - err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem); + err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); @@ -4310,13 +4349,19 @@ failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); - if (sbi->s_flex_groups) - kvfree(sbi->s_flex_groups); + rcu_read_lock(); + flex_groups = rcu_dereference(sbi->s_flex_groups); + if (flex_groups) { + for (i = 0; i < sbi->s_flex_groups_allocated; i++) + kvfree(flex_groups[i]); + kvfree(flex_groups); + } + rcu_read_unlock(); percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); - percpu_free_rwsem(&sbi->s_journal_flag_rwsem); + percpu_free_rwsem(&sbi->s_writepages_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); @@ -4343,9 +4388,12 @@ failed_mount3: if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); for (i = 0; i < db_count; i++) - brelse(sbi->s_group_desc[i]); - kvfree(sbi->s_group_desc); + brelse(group_desc[i]); + kvfree(group_desc); + rcu_read_unlock(); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); @@ -4959,6 +5007,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + ext4_clamp_want_extra_isize(sb); + if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9041805096e0..b2cccd4083b8 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1201,6 +1201,7 @@ int do_write_data_page(struct f2fs_io_info *fio) /* This page is already truncated */ if (fio->old_blkaddr == NULL_ADDR) { ClearPageUptodate(page); + clear_cold_data(page); goto out_writepage; } @@ -1266,7 +1267,7 @@ static int f2fs_write_data_page(struct page *page, loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long) i_size) >> PAGE_SHIFT; - loff_t psize = (page->index + 1) << PAGE_SHIFT; + loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; int err = 0; @@ -1337,8 +1338,10 @@ done: clear_cold_data(page); out: inode_dec_dirty_pages(inode); - if (err) + if (err) { ClearPageUptodate(page); + clear_cold_data(page); + } if (wbc->for_reclaim) { f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE); @@ -1821,6 +1824,8 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, inode_dec_dirty_pages(inode); } + clear_cold_data(page); + /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return; @@ -1839,6 +1844,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (IS_ATOMIC_WRITTEN_PAGE(page)) return 0; + clear_cold_data(page); set_page_private(page, 0); ClearPagePrivate(page); return 1; diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index af719d93507e..b414892be08b 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -772,6 +772,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); + clear_cold_data(page); inode_dec_dirty_pages(dir); } f2fs_put_page(page, 1); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f46ac1651bd5..e3c438c8b8ce 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -980,7 +980,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } dn.ofs_in_node++; i++; - new_size = (dst + i) << PAGE_SHIFT; + new_size = (loff_t)(dst + i) << PAGE_SHIFT; if (dst_inode->i_size < new_size) f2fs_i_size_write(dst_inode, new_size); } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR)); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 759056e776e5..b1d62003cda6 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -985,7 +985,7 @@ stop: put_gc_inode(&gc_list); - if (sync) + if (sync && !ret) ret = sec_freed ? 0 : -EAGAIN; return ret; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 1de02c31756b..c56d04ec45dc 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -288,6 +288,7 @@ make_now: return inode; bad_inode: + f2fs_inode_synced(inode); iget_failed(inode); trace_f2fs_iget_exit(inode, ret); return ERR_PTR(ret); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index e59eeaf02eaa..e87b7d7e80fc 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -179,6 +179,8 @@ static void recover_inode(struct inode *inode, struct page *page) char *name; inode->i_mode = le16_to_cpu(raw->i_mode); + i_uid_write(inode, le32_to_cpu(raw->i_uid)); + i_gid_write(inode, le32_to_cpu(raw->i_gid)); f2fs_i_size_write(inode, le64_to_cpu(raw->i_size)); inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime); inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime); @@ -407,7 +409,15 @@ retry_dn: get_node_info(sbi, dn.nid, &ni); f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); - f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); + + if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", + inode->i_ino, ofs_of_node(dn.node_page), + ofs_of_node(page)); + err = -EFAULT; + goto err; + } for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 2fb99a081de8..c4c84af1ec17 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -227,8 +227,10 @@ static int __revoke_inmem_pages(struct inode *inode, } next: /* we don't need to invalidate this in the sccessful status */ - if (drop || recover) + if (drop || recover) { ClearPageUptodate(page); + clear_cold_data(page); + } set_page_private(page, 0); ClearPagePrivate(page); f2fs_put_page(page, 1); @@ -2490,6 +2492,41 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) return init_victim_secmap(sbi); } +static int sanity_check_curseg(struct f2fs_sb_info *sbi) +{ + int i; + + /* + * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr; + * In LFS curseg, all blkaddr after .next_blkoff should be unused. + */ + for (i = 0; i < NO_CHECK_TYPE; i++) { + struct curseg_info *curseg = CURSEG_I(sbi, i); + struct seg_entry *se = get_seg_entry(sbi, curseg->segno); + unsigned int blkofs = curseg->next_blkoff; + + if (f2fs_test_bit(blkofs, se->cur_valid_map)) + goto out; + + if (curseg->alloc_type == SSR) + continue; + + for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) { + if (!f2fs_test_bit(blkofs, se->cur_valid_map)) + continue; +out: + f2fs_msg(sbi->sb, KERN_ERR, + "Current segment's next free block offset is " + "inconsistent with bitmap, logtype:%u, " + "segno:%u, type:%u, next_blkoff:%u, blkofs:%u", + i, curseg->segno, curseg->alloc_type, + curseg->next_blkoff, blkofs); + return -EINVAL; + } + } + return 0; +} + /* * Update min, max modified time for cost-benefit GC algorithm */ @@ -2583,6 +2620,10 @@ int build_segment_manager(struct f2fs_sb_info *sbi) if (err) return err; + err = sanity_check_curseg(sbi); + if (err) + return err; + init_min_max_mtime(sbi); return 0; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 893723978f5e..faca7fdb54b0 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -613,7 +613,6 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) static inline int check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { -#ifdef CONFIG_F2FS_CHECK_FS bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; @@ -640,7 +639,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, set_sbi_flag(sbi, SBI_NEED_FSCK); return -EINVAL; } -#endif + /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg || segno > TOTAL_SEGS(sbi) - 1)) { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 83a96334dc07..e0ac676e0a35 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1489,7 +1489,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; - int i; + int i, j; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -1530,11 +1530,43 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_node_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); + return 1; + } + } + } + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + for (j = 0; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u) and Data segment (%u)" + " has the same segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); @@ -1618,8 +1650,12 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) if (err) return err; - return percpu_counter_init(&sbi->total_valid_inode_count, 0, + err = percpu_counter_init(&sbi->total_valid_inode_count, 0, GFP_KERNEL); + if (err) + percpu_counter_destroy(&sbi->alloc_valid_block_count); + + return err; } /* diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index 73b4e1d1912a..501c283761d2 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -61,6 +61,7 @@ void f2fs_trace_pid(struct page *page) page->private = pid; +retry: if (radix_tree_preload(GFP_NOFS)) return; @@ -71,7 +72,12 @@ void f2fs_trace_pid(struct page *page) if (p) radix_tree_delete(&pids, pid); - f2fs_radix_tree_insert(&pids, pid, current); + if (radix_tree_insert(&pids, pid, current)) { + spin_unlock(&pids_lock); + radix_tree_preload_end(); + cond_resched(); + goto retry; + } trace_printk("%3x:%3x %4x %-16s\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 81cecbe6d7cf..971e369517a7 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1097,8 +1097,11 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, err = -ENOMEM; goto error; } + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); memset(bhs[n]->b_data, 0, sb->s_blocksize); set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); mark_buffer_dirty_inode(bhs[n], dir); n++; @@ -1155,6 +1158,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) fat_time_unix2fat(sbi, ts, &time, &date, &time_cs); de = (struct msdos_dir_entry *)bhs[0]->b_data; + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[0]); /* filling the new directory slots ("." and ".." entries) */ memcpy(de[0].name, MSDOS_DOT, MSDOS_NAME); memcpy(de[1].name, MSDOS_DOTDOT, MSDOS_NAME); @@ -1177,6 +1182,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) de[0].size = de[1].size = 0; memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de)); set_buffer_uptodate(bhs[0]); + unlock_buffer(bhs[0]); mark_buffer_dirty_inode(bhs[0], dir); err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE); @@ -1234,11 +1240,14 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, /* fill the directory entry */ copy = min(size, sb->s_blocksize); + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); memcpy(bhs[n]->b_data, slots, copy); - slots += copy; - size -= copy; set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); mark_buffer_dirty_inode(bhs[n], dir); + slots += copy; + size -= copy; if (!size) break; n++; diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index a9cad9b60790..0129d4d07a54 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -389,8 +389,11 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, err = -ENOMEM; goto error; } + /* Avoid race with userspace read via bdev */ + lock_buffer(c_bh); memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize); set_buffer_uptodate(c_bh); + unlock_buffer(c_bh); mark_buffer_dirty_inode(c_bh, sbi->fat_inode); if (sb->s_flags & MS_SYNCHRONOUS) err = sync_dirty_buffer(c_bh); diff --git a/fs/fat/file.c b/fs/fat/file.c index 3d04b124bce0..392ec5641f38 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -160,12 +160,17 @@ static int fat_file_release(struct inode *inode, struct file *filp) int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; - int res, err; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; - res = generic_file_fsync(filp, start, end, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; - return res ? res : err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 88720011a6eb..f0387d040331 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -736,6 +736,13 @@ static struct inode *fat_alloc_inode(struct super_block *sb) return NULL; init_rwsem(&ei->truncate_lock); + /* Zeroing to allow iput() even if partial initialized inode. */ + ei->mmu_private = 0; + ei->i_start = 0; + ei->i_logstart = 0; + ei->i_attrs = 0; + ei->i_pos = 0; + return &ei->vfs_inode; } @@ -1366,16 +1373,6 @@ out: return 0; } -static void fat_dummy_inode_init(struct inode *inode) -{ - /* Initialize this dummy inode to work as no-op. */ - MSDOS_I(inode)->mmu_private = 0; - MSDOS_I(inode)->i_start = 0; - MSDOS_I(inode)->i_logstart = 0; - MSDOS_I(inode)->i_attrs = 0; - MSDOS_I(inode)->i_pos = 0; -} - static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); @@ -1820,13 +1817,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - fat_dummy_inode_init(fat_inode); sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; - fat_dummy_inode_init(fsinfo_inode); fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); diff --git a/fs/file.c b/fs/file.c index 69d6990e3021..09aac4d4729b 100644 --- a/fs/file.c +++ b/fs/file.c @@ -475,6 +475,7 @@ struct files_struct init_files = { .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), + .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index f3aea1b8702c..882e9d6830df 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -331,11 +331,22 @@ struct inode_switch_wbs_context { struct work_struct work; }; +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + down_write(&bdi->wb_switch_rwsem); +} + +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + up_write(&bdi->wb_switch_rwsem); +} + static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) void **slot; /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be @@ -435,6 +452,8 @@ skip_switch: spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); + up_read(&bdi->wb_switch_rwsem); + if (switched) { wb_wakeup(new_wb); wb_put(old_wb); @@ -475,9 +494,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (inode->i_state & I_WB_SWITCH) return; + /* + * Avoid starting new switches while sync_inodes_sb() is in + * progress. Otherwise, if the down_write protected issue path + * blocks heavily, we might end up starting a large number of + * switches which will block on the rwsem. + */ + if (!down_read_trylock(&bdi->wb_switch_rwsem)) + return; + isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) - return; + goto out_unlock; /* find and pin the new wb */ rcu_read_lock(); @@ -502,8 +530,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) isw->inode = inode; - atomic_inc(&isw_nr_in_flight); - /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -511,12 +537,17 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); - return; + + atomic_inc(&isw_nr_in_flight); + + goto out_unlock; out_free: if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); +out_unlock: + up_read(&bdi->wb_switch_rwsem); } /** @@ -551,10 +582,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, spin_unlock(&inode->i_lock); /* - * A dying wb indicates that the memcg-blkcg mapping has changed - * and a new wb is already serving the memcg. Switch immediately. + * A dying wb indicates that either the blkcg associated with the + * memcg changed or the associated memcg is dying. In the first + * case, a replacement wb should already be available and we should + * refresh the wb immediately. In the second case, trying to + * refresh will keep failing. */ - if (unlikely(wb_dying(wbc->wb))) + if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } @@ -690,6 +724,7 @@ void wbc_detach_inode(struct writeback_control *wbc) void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes) { + struct cgroup_subsys_state *css; int id; /* @@ -701,7 +736,12 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, if (!wbc->wb) return; - id = mem_cgroup_css_from_page(page)->id; + css = mem_cgroup_css_from_page(page); + /* dead cgroups shouldn't contribute to inode ownership arbitration */ + if (!(css->flags & CSS_ONLINE)) + return; + + id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; @@ -878,7 +918,11 @@ restart: void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { - synchronize_rcu(); + /* + * Use rcu_barrier() to wait for all pending callbacks to + * ensure that all in-flight wb switches are in the workqueue. + */ + rcu_barrier(); flush_workqueue(isw_wq); } } @@ -894,6 +938,9 @@ fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } + static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) @@ -2408,8 +2455,11 @@ void sync_inodes_sb(struct super_block *sb) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); + /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ + bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(bdi, &done); + bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index e25c40c10f4f..97ac2f5843fc 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -107,7 +107,7 @@ static ssize_t fuse_conn_max_background_read(struct file *file, if (!fc) return 0; - val = fc->max_background; + val = READ_ONCE(fc->max_background); fuse_conn_put(fc); return fuse_conn_limit_read(file, buf, len, ppos, val); @@ -144,7 +144,7 @@ static ssize_t fuse_conn_congestion_threshold_read(struct file *file, if (!fc) return 0; - val = fc->congestion_threshold; + val = READ_ONCE(fc->congestion_threshold); fuse_conn_put(fc); return fuse_conn_limit_read(file, buf, len, ppos, val); diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index c5b6b7165489..d9aba9700726 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -513,6 +513,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file) rc = cuse_send_init(cc); if (rc) { fuse_dev_free(fud); + fuse_conn_put(&cc->fc); return rc; } file->private_data = fud; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 411f16101d1a..8016cd059db1 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1668,7 +1668,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, offset = outarg->offset & ~PAGE_MASK; file_size = i_size_read(inode); - num = outarg->size; + num = min(outarg->size, fc->max_write); if (outarg->offset > file_size) num = 0; else if (outarg->offset + num > file_size) @@ -1975,10 +1975,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -1996,7 +1994,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2019,11 +2019,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kfree(bufs); return ret; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 60dd2bc10776..9af23f436558 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -234,7 +234,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) kfree(forget); if (ret == -ENOMEM) goto out; - if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) + if (ret || fuse_invalid_attr(&outarg.attr) || + (outarg.attr.mode ^ inode->i_mode) & S_IFMT) goto invalid; forget_all_cached_acls(inode); @@ -297,6 +298,12 @@ int fuse_valid_type(int m) S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); } +bool fuse_invalid_attr(struct fuse_attr *attr) +{ + return !fuse_valid_type(attr->mode) || + attr->size > LLONG_MAX; +} + int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name, struct fuse_entry_out *outarg, struct inode **inode) { @@ -328,7 +335,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name err = -EIO; if (!outarg->nodeid) goto out_put_forget; - if (!fuse_valid_type(outarg->attr.mode)) + if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, @@ -451,7 +458,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, goto out_free_ff; err = -EIO; - if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid)) + if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) || + fuse_invalid_attr(&outentry.attr)) goto out_free_ff; ff->fh = outopen.fh; @@ -557,7 +565,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args, goto out_put_forget_req; err = -EIO; - if (invalid_nodeid(outarg.nodeid)) + if (invalid_nodeid(outarg.nodeid) || fuse_invalid_attr(&outarg.attr)) goto out_put_forget_req; if ((outarg.attr.mode ^ mode) & S_IFMT) @@ -830,7 +838,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, spin_lock(&fc->lock); fi->attr_version = ++fc->attr_version; - inc_nlink(inode); + if (likely(inode->i_nlink < UINT_MAX)) + inc_nlink(inode); spin_unlock(&fc->lock); fuse_invalidate_attr(inode); fuse_update_ctime(inode); @@ -910,7 +919,8 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, args.out.args[0].value = &outarg; err = fuse_simple_request(fc, &args); if (!err) { - if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + if (fuse_invalid_attr(&outarg.attr) || + (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); err = -EIO; } else { @@ -1218,7 +1228,7 @@ static int fuse_direntplus_link(struct file *file, if (invalid_nodeid(o->nodeid)) return -EIO; - if (!fuse_valid_type(o->attr.mode)) + if (fuse_invalid_attr(&o->attr)) return -EIO; fc = get_fuse_conn(dir); @@ -1654,6 +1664,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, if (attr->ia_valid & ATTR_SIZE) is_truncate = true; + /* Flush dirty data/metadata before non-truncate SETATTR */ + if (is_wb && S_ISREG(inode->i_mode) && + attr->ia_valid & + (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET | + ATTR_TIMES_SET)) { + err = write_inode_now(inode, true); + if (err) + return err; + + fuse_set_nowrite(inode); + fuse_release_nowrite(inode); + } + if (is_truncate) { fuse_set_nowrite(inode); set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); @@ -1682,7 +1705,8 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, goto error; } - if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + if (fuse_invalid_attr(&outarg.attr) || + (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { make_bad_inode(inode); err = -EIO; goto error; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 30a607473621..92f905ea20b0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -178,7 +178,9 @@ void fuse_finish_open(struct inode *inode, struct file *file) file->f_op = &fuse_direct_io_file_operations; if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); - if (ff->open_flags & FOPEN_NONSEEKABLE) + if (ff->open_flags & FOPEN_STREAM) + stream_open(inode, file); + else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -199,7 +201,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) { struct fuse_conn *fc = get_fuse_conn(inode); int err; - bool lock_inode = (file->f_flags & O_TRUNC) && + bool is_wb_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc && fc->writeback_cache; @@ -207,16 +209,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) if (err) return err; - if (lock_inode) + if (is_wb_truncate) { inode_lock(inode); + fuse_set_nowrite(inode); + } err = fuse_do_open(fc, get_node_id(inode), file, isdir); if (!err) fuse_finish_open(inode, file); - if (lock_inode) + if (is_wb_truncate) { + fuse_release_nowrite(inode); inode_unlock(inode); + } return err; } @@ -1521,7 +1527,7 @@ __acquires(fc->lock) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); - size_t crop = i_size_read(inode); + loff_t crop = i_size_read(inode); struct fuse_req *req; while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) { @@ -1692,6 +1698,7 @@ static int fuse_writepage(struct page *page, struct writeback_control *wbc) WARN_ON(wbc->sync_mode == WB_SYNC_ALL); redirty_page_for_writepage(wbc, page); + unlock_page(page); return 0; } @@ -2961,6 +2968,13 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, } } + if (!(mode & FALLOC_FL_KEEP_SIZE) && + offset + length > i_size_read(inode)) { + err = inode_newsize_ok(inode, offset + length); + if (err) + goto out; + } + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1c905c7666de..f84dd6d87d90 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -898,6 +898,8 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc); */ int fuse_valid_type(int m); +bool fuse_invalid_attr(struct fuse_attr *attr); + /** * Is current process allowed to perform filesystem operation? */ diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 39af17b407f0..d83e99fa98b3 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1236,6 +1236,8 @@ static int do_grow(struct inode *inode, u64 size) } error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT + + (unstuff && + gfs2_is_jdata(ip) ? RES_JDATA : 0) + (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF ? 0 : RES_QUOTA), 0); if (error) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 7a8b1d72e3d9..adc1a97cfe96 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -136,22 +136,26 @@ static int demote_ok(const struct gfs2_glock *gl) void gfs2_glock_add_to_lru(struct gfs2_glock *gl) { + if (!(gl->gl_ops->go_flags & GLOF_LRU)) + return; + spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) - list_del_init(&gl->gl_lru); - else + list_del(&gl->gl_lru); + list_add_tail(&gl->gl_lru, &lru_list); + + if (!test_bit(GLF_LRU, &gl->gl_flags)) { + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); + } - list_add_tail(&gl->gl_lru, &lru_list); - set_bit(GLF_LRU, &gl->gl_flags); spin_unlock(&lru_lock); } static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) { spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) { + if (test_bit(GLF_LRU, &gl->gl_flags)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); @@ -544,6 +548,9 @@ __acquires(&gl->gl_lockref.lock) goto out_unlock; if (nonblock) goto out_sched; + smp_mb(); + if (atomic_read(&gl->gl_revokes) != 0) + goto out_sched; set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; @@ -1048,8 +1055,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } - if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl) && - (glops->go_flags & GLOF_LRU)) + if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl)) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); @@ -1349,6 +1355,7 @@ __acquires(&lru_lock) if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); continue; } @@ -1356,7 +1363,6 @@ add_back_to_lru: spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } - clear_bit(GLF_LRU, &gl->gl_flags); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1392,6 +1398,7 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); + clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index bd6202b70447..daad7b04f88c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1248,7 +1248,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry, if (!(*opened & FILE_OPENED)) return finish_no_open(file, d); dput(d); - return 0; + return excl && (flags & O_CREAT) ? -EEXIST : 0; } BUG_ON(d != NULL); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 8b907c5cc913..3c3d037df824 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -32,9 +32,10 @@ extern struct workqueue_struct *gfs2_control_wq; * @delta is the difference between the current rtt sample and the * running average srtt. We add 1/8 of that to the srtt in order to * update the current srtt estimate. The variance estimate is a bit - * more complicated. We subtract the abs value of the @delta from - * the current variance estimate and add 1/4 of that to the running - * total. + * more complicated. We subtract the current variance estimate from + * the abs value of the @delta and add 1/4 of that to the running + * total. That's equivalent to 3/4 of the current variance + * estimate plus 1/4 of the abs of @delta. * * Note that the index points at the array entry containing the smoothed * mean value, and the variance is always in the following entry @@ -50,7 +51,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); + s->stats[index] += (s64)(abs(delta) - s->stats[index]) >> 2; } /** diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 073126707270..0a80f6636549 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -630,7 +630,10 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) RB_CLEAR_NODE(&rs->rs_node); if (rs->rs_free) { - struct gfs2_bitmap *bi = rbm_bi(&rs->rs_rbm); + u64 last_block = gfs2_rbm_to_block(&rs->rs_rbm) + + rs->rs_free - 1; + struct gfs2_rbm last_rbm = { .rgd = rs->rs_rbm.rgd, }; + struct gfs2_bitmap *start, *last; /* return reserved blocks to the rgrp */ BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free); @@ -641,7 +644,13 @@ static void __rs_deltree(struct gfs2_blkreserv *rs) it will force the number to be recalculated later. */ rgd->rd_extfail_pt += rs->rs_free; rs->rs_free = 0; - clear_bit(GBF_FULL, &bi->bi_flags); + if (gfs2_rbm_from_block(&last_rbm, last_block)) + return; + start = rbm_bi(&rs->rs_rbm); + last = rbm_bi(&last_rbm); + do + clear_bit(GBF_FULL, &start->bi_flags); + while (start++ != last); } } @@ -1211,7 +1220,7 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd) rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags); rl_flags &= ~GFS2_RDF_MASK; rgd->rd_flags &= GFS2_RDF_MASK; - rgd->rd_flags |= (rl_flags | GFS2_RDF_UPTODATE | GFS2_RDF_CHECK); + rgd->rd_flags |= (rl_flags | GFS2_RDF_CHECK); if (rgd->rd_rgl->rl_unlinked == 0) rgd->rd_flags &= ~GFS2_RDF_CHECK; rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index e3ee387a6dfe..37496d83661a 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -844,10 +844,10 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) return error; + flush_workqueue(gfs2_delete_workqueue); kthread_stop(sdp->sd_quotad_process); kthread_stop(sdp->sd_logd_process); - flush_workqueue(gfs2_delete_workqueue); gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 2e713673df42..85dab71bee74 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -444,6 +444,7 @@ skip: /* restore search_key */ hfs_bnode_read_key(node, fd->search_key, 14); } + new_node = NULL; } if (!rec && node->parent) diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 320f4372f172..77eff447d301 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -219,25 +219,17 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) return node; } -struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) +/* Make sure @tree has enough space for the @rsvd_nodes */ +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) { - struct hfs_bnode *node, *next_node; - struct page **pagep; - u32 nidx, idx; - unsigned off; - u16 off16; - u16 len; - u8 *data, byte, m; - int i; - - while (!tree->free_nodes) { - struct inode *inode = tree->inode; - u32 count; - int res; + struct inode *inode = tree->inode; + u32 count; + int res; + while (tree->free_nodes < rsvd_nodes) { res = hfs_extend_file(inode); if (res) - return ERR_PTR(res); + return res; HFS_I(inode)->phys_size = inode->i_size = (loff_t)HFS_I(inode)->alloc_blocks * HFS_SB(tree->sb)->alloc_blksz; @@ -245,9 +237,26 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) tree->sb->s_blocksize_bits; inode_set_bytes(inode, inode->i_size); count = inode->i_size >> tree->node_size_shift; - tree->free_nodes = count - tree->node_count; + tree->free_nodes += count - tree->node_count; tree->node_count = count; } + return 0; +} + +struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) +{ + struct hfs_bnode *node, *next_node; + struct page **pagep; + u32 nidx, idx; + unsigned off; + u16 off16; + u16 len; + u8 *data, byte, m; + int i, res; + + res = hfs_bmap_reserve(tree, 1); + if (res) + return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index f6bd266d70b5..2715f416b5a8 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -81,6 +81,7 @@ struct hfs_find_data { extern struct hfs_btree *hfs_btree_open(struct super_block *, u32, btree_keycmp); extern void hfs_btree_close(struct hfs_btree *); extern void hfs_btree_write(struct hfs_btree *); +extern int hfs_bmap_reserve(struct hfs_btree *, int); extern struct hfs_bnode * hfs_bmap_alloc(struct hfs_btree *); extern void hfs_bmap_free(struct hfs_bnode *node); diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 8a66405b0f8b..d365bf0b8c77 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -97,6 +97,14 @@ int hfs_cat_create(u32 cnid, struct inode *dir, const struct qstr *str, struct i if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth); + if (err) + goto err2; + hfs_cat_build_key(sb, fd.search_key, cnid, NULL); entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ? HFS_CDR_THD : HFS_CDR_FTH, @@ -295,6 +303,14 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, const struct qstr *src_name, return err; dst_fd = src_fd; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(src_fd.tree, 2 * src_fd.tree->depth); + if (err) + goto out; + /* find the old dir entry and read the data */ hfs_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); err = hfs_brec_find(&src_fd); diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index e33a0d36a93e..cbe4fca96378 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -117,6 +117,10 @@ static int __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) if (HFS_I(inode)->flags & HFS_FLG_EXT_NEW) { if (res != -ENOENT) return res; + /* Fail early and avoid ENOSPC during the btree operation */ + res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); + if (res) + return res; hfs_brec_insert(fd, HFS_I(inode)->cached_extents, sizeof(hfs_extent_rec)); HFS_I(inode)->flags &= ~(HFS_FLG_EXT_DIRTY|HFS_FLG_EXT_NEW); } else { @@ -300,7 +304,7 @@ int hfs_free_fork(struct super_block *sb, struct hfs_cat_file *file, int type) return 0; blocks = 0; - for (i = 0; i < 3; extent++, i++) + for (i = 0; i < 3; i++) blocks += be16_to_cpu(extent[i].count); res = hfs_free_extents(sb, extent, blocks, blocks); @@ -341,7 +345,9 @@ int hfs_get_block(struct inode *inode, sector_t block, ablock = (u32)block / HFS_SB(sb)->fs_div; if (block >= HFS_I(inode)->fs_blocks) { - if (block > HFS_I(inode)->fs_blocks || !create) + if (!create) + return 0; + if (block > HFS_I(inode)->fs_blocks) return -EIO; if (ablock >= HFS_I(inode)->alloc_blocks) { res = hfs_extend_file(inode); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index f776acf2378a..de0d6d4c46b6 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -641,6 +641,8 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) truncate_setsize(inode, attr->ia_size); hfs_file_truncate(inode); + inode->i_atime = inode->i_mtime = inode->i_ctime = + current_time(inode); } setattr_copy(inode, attr); diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index e5b221de7de6..0c4548d8cd0b 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -216,6 +216,11 @@ int hfsplus_create_attr(struct inode *inode, if (err) goto failed_init_create_attr; + /* Fail early and avoid ENOSPC during the btree operation */ + err = hfs_bmap_reserve(fd.tree, fd.tree->depth + 1); + if (err) + goto failed_create_attr; + if (name) { err = hfsplus_attr_build_key(sb, fd.search_key, inode->i_ino, name); @@ -286,6 +291,10 @@ static int __hfsplus_delete_attr(struct inode *inode, u32 cnid, return -ENOENT; } + /* Avoid btree corruption */ + hfs_bnode_read(fd->bnode, fd->search_key, + fd->keyoffset, fd->keylength); + err = hfs_brec_remove(fd); if (err) return err; @@ -312,6 +321,11 @@ int hfsplus_delete_attr(struct inode *inode, const char *name) if (err) return err; + /* Fail early and avoid ENOSPC during the btree operation */ + err = hfs_bmap_reserve(fd.tree, fd.tree->depth); + if (err) + goto out; + if (name) { err = hfsplus_attr_build_key(sb, fd.search_key, inode->i_ino, name); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 1002a0c08319..20ce698251ad 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -447,6 +447,7 @@ skip: /* restore search_key */ hfs_bnode_read_key(node, fd->search_key, 14); } + new_node = NULL; } if (!rec && node->parent) diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 8d2256454efe..7e96b4c294f7 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -341,26 +341,21 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) return node; } -struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) +/* Make sure @tree has enough space for the @rsvd_nodes */ +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) { - struct hfs_bnode *node, *next_node; - struct page **pagep; - u32 nidx, idx; - unsigned off; - u16 off16; - u16 len; - u8 *data, byte, m; - int i; + struct inode *inode = tree->inode; + struct hfsplus_inode_info *hip = HFSPLUS_I(inode); + u32 count; + int res; - while (!tree->free_nodes) { - struct inode *inode = tree->inode; - struct hfsplus_inode_info *hip = HFSPLUS_I(inode); - u32 count; - int res; + if (rsvd_nodes <= 0) + return 0; + while (tree->free_nodes < rsvd_nodes) { res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree)); if (res) - return ERR_PTR(res); + return res; hip->phys_size = inode->i_size = (loff_t)hip->alloc_blocks << HFSPLUS_SB(tree->sb)->alloc_blksz_shift; @@ -368,9 +363,26 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift; inode_set_bytes(inode, inode->i_size); count = inode->i_size >> tree->node_size_shift; - tree->free_nodes = count - tree->node_count; + tree->free_nodes += count - tree->node_count; tree->node_count = count; } + return 0; +} + +struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) +{ + struct hfs_bnode *node, *next_node; + struct page **pagep; + u32 nidx, idx; + unsigned off; + u16 off16; + u16 len; + u8 *data, byte, m; + int i, res; + + res = hfs_bmap_reserve(tree, 1); + if (res) + return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index a5e00f7a4c14..947da72e72a3 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -264,6 +264,14 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth); + if (err) + goto err2; + hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid); entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ? @@ -332,6 +340,14 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, const struct qstr *str) if (err) return err; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most once. + */ + err = hfs_bmap_reserve(fd.tree, 2 * (int)fd.tree->depth - 2); + if (err) + goto out; + if (!str) { int len; @@ -432,6 +448,14 @@ int hfsplus_rename_cat(u32 cnid, return err; dst_fd = src_fd; + /* + * Fail early and avoid ENOSPC during the btree operations. We may + * have to split the root node at most twice. + */ + err = hfs_bmap_reserve(src_fd.tree, 4 * (int)src_fd.tree->depth - 1); + if (err) + goto out; + /* find the old dir entry and read the data */ err = hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index feca524ce2a5..d93c051559cb 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -99,6 +99,10 @@ static int __hfsplus_ext_write_extent(struct inode *inode, if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return res; + /* Fail early and avoid ENOSPC during the btree operation */ + res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); + if (res) + return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); @@ -232,7 +236,9 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, ablock = iblock >> sbi->fs_shift; if (iblock >= hip->fs_blocks) { - if (iblock > hip->fs_blocks || !create) + if (!create) + return 0; + if (iblock > hip->fs_blocks) return -EIO; if (ablock >= hip->alloc_blocks) { res = hfsplus_file_extend(inode, false); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a3f03b247463..35cd703c6604 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -311,6 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb) #define hfs_btree_open hfsplus_btree_open #define hfs_btree_close hfsplus_btree_close #define hfs_btree_write hfsplus_btree_write +#define hfs_bmap_reserve hfsplus_bmap_reserve #define hfs_bmap_alloc hfsplus_bmap_alloc #define hfs_bmap_free hfsplus_bmap_free #define hfs_bnode_read hfsplus_bnode_read @@ -395,6 +396,7 @@ u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, u64 sectors, struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id); void hfs_btree_close(struct hfs_btree *tree); int hfs_btree_write(struct hfs_btree *tree); +int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes); struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree); void hfs_bmap_free(struct hfs_bnode *node); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 2e796f8302ff..cfd380e2743d 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -260,6 +260,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) } truncate_setsize(inode, attr->ia_size); hfsplus_file_truncate(inode); + inode->i_mtime = inode->i_ctime = current_time(inode); } setattr_copy(inode, attr); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 001487b230b5..253b03451b72 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -451,9 +451,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, if (next >= end) break; - hash = hugetlb_fault_mutex_hash(h, current->mm, - &pseudo_vma, - mapping, next, 0); + hash = hugetlb_fault_mutex_hash(h, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -573,7 +571,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); struct vm_area_struct pseudo_vma; - struct mm_struct *mm = current->mm; loff_t hpage_size = huge_page_size(h); unsigned long hpage_shift = huge_page_shift(h); pgoff_t start, index, end; @@ -637,8 +634,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, - index, addr); + hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ @@ -746,11 +742,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -782,8 +784,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } else - kref_put(&resv_map->refs, resv_map_release); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } diff --git a/fs/inode.c b/fs/inode.c index 2071ff5343c5..0d993ce7a940 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -135,6 +135,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; + atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; @@ -1804,8 +1805,13 @@ int file_remove_privs(struct file *file) int kill; int error = 0; - /* Fast path for nothing security related */ - if (IS_NOSEC(inode)) + /* + * Fast path for nothing security related. + * As well for non-regular files, e.g. blkdev inodes. + * For example, blkdev_write_iter() might get here + * trying to remove privs which it is not allowed to. + */ + if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 4d5a5a4cc017..addb0784dd1c 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -168,7 +168,7 @@ void __jbd2_log_wait_for_space(journal_t *journal) "journal space in %s\n", __func__, journal->j_devname); WARN_ON(1); - jbd2_journal_abort(journal, 0); + jbd2_journal_abort(journal, -EIO); } write_lock(&journal->j_state_lock); } else { diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 31f8ca046639..f65ad50d5f7b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -700,9 +700,11 @@ void jbd2_journal_commit_transaction(journal_t *journal) the last tag we set up. */ tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG); - - jbd2_descriptor_block_csum_set(journal, descriptor); start_journal_io: + if (descriptor) + jbd2_descriptor_block_csum_set(journal, + descriptor); + for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; /* @@ -720,7 +722,6 @@ start_journal_io: submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh); } cond_resched(); - stats.run.rs_blocks_logged += bufs; /* Force a new descriptor to be generated next time round the loop. */ @@ -778,7 +779,7 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); } blk_finish_plug(&plug); @@ -807,6 +808,7 @@ start_journal_io: if (unlikely(!buffer_uptodate(bh))) err = -EIO; jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; /* * The list contains temporary buffer heads created by @@ -852,6 +854,7 @@ start_journal_io: BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile"); clear_buffer_jwrite(bh); jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; __brelse(bh); /* One for getblk */ /* AKPM: bforget here */ } @@ -869,10 +872,11 @@ start_journal_io: err = journal_submit_commit_record(journal, commit_transaction, &cbh, crc32_sum); if (err) - __jbd2_journal_abort_hard(journal); + jbd2_journal_abort(journal, err); } if (cbh) err = journal_wait_on_commit_record(journal, cbh); + stats.run.rs_blocks_logged++; if (jbd2_has_feature_async_commit(journal) && journal->j_flags & JBD2_BARRIER) { blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); @@ -965,29 +969,34 @@ restart_loop: * it. */ /* - * A buffer which has been freed while still being journaled by - * a previous transaction. - */ - if (buffer_freed(bh)) { + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + struct address_space *mapping; + + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + /* - * If the running transaction is the one containing - * "add to orphan" operation (b_next_transaction != - * NULL), we have to wait for that transaction to - * commit before we can really get rid of the buffer. - * So just clear b_modified to not confuse transaction - * credit accounting and refile the buffer to - * BJ_Forget of the running transaction. If the just - * committed transaction contains "add to orphan" - * operation, we can completely invalidate the buffer - * now. We are rather through in that since the - * buffer may be still accessible when blocksize < - * pagesize and it is attached to the last partial - * page. + * Block device buffers need to stay mapped all the + * time, so it is enough to clear buffer_jbddirty and + * buffer_freed bits. For the file mapping buffers (i.e. + * journalled data) we need to unmap buffer and clear + * more bits. We also need to be careful about the check + * because the data page mapping can get cleared under + * our hands. Note that if mapping == NULL, we don't + * need to make buffer unmapped because the page is + * already detached from the mapping and buffers cannot + * get reused. */ - jh->b_modified = 0; - if (!jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); + mapping = READ_ONCE(bh->b_page->mapping); + if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { clear_buffer_mapped(bh); clear_buffer_new(bh); clear_buffer_req(bh); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index d10bb2c30bf8..efc8cfd06073 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1339,6 +1339,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) journal_superblock_t *sb = journal->j_superblock; int ret; + /* Buffer got discarded which means block device got invalidated */ + if (!buffer_mapped(bh)) + return -EIO; + trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); @@ -1666,6 +1670,11 @@ int jbd2_journal_load(journal_t *journal) journal->j_devname); return -EFSCORRUPTED; } + /* + * clear JBD2_ABORT flag initialized in journal_init_common + * here to update log tail information with the newest seq. + */ + journal->j_flags &= ~JBD2_ABORT; /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory @@ -1673,7 +1682,6 @@ int jbd2_journal_load(journal_t *journal) if (journal_reset(journal)) goto recovery_error; - journal->j_flags &= ~JBD2_ABORT; journal->j_flags |= JBD2_LOADED; return 0; @@ -2092,12 +2100,10 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); - if (errno) { - jbd2_journal_update_sb_errno(journal); - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); - } + jbd2_journal_update_sb_errno(journal); + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); } /** @@ -2139,11 +2145,6 @@ static void __journal_abort_soft (journal_t *journal, int errno) * failure to disk. ext3_error, for example, now uses this * functionality. * - * Errors which originate from within the journaling layer will NOT - * supply an errno; a null errno implies that absolutely no further - * writes are done to the journal (unless there are any already in - * progress). - * */ void jbd2_journal_abort(journal_t *journal, int errno) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 799f96c67211..8de458d64134 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1037,8 +1037,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -2213,14 +2213,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, return -EBUSY; } /* - * OK, buffer won't be reachable after truncate. We just set - * j_next_transaction to the running transaction (if there is - * one) and mark buffer as freed so that commit code knows it - * should clear dirty bits when it is done with the buffer. + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); @@ -2446,8 +2448,8 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 06a71dbd4833..2f236cca6095 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 226640563df3..76aedbc97773 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) static void jffs2_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_destroy_inode(struct inode *inode) diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 4d973524c887..224ef034004b 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1928,8 +1928,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * header ? */ if (tlck->type & tlckTRUNCATE) { - /* This odd declaration suppresses a bogus gcc warning */ - pxd_t pxd = pxd; /* truncated extent of xad */ + pxd_t pxd; /* truncated extent of xad */ int twm; /* diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 80317b04c84a..e431a850f2f2 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -63,6 +63,9 @@ static int kernfs_get_target_path(struct kernfs_node *parent, if (base == kn) break; + if ((s - path) + 3 >= PATH_MAX) + return -ENAMETOOLONG; + strcpy(s, "../"); s += 3; base = base->parent; @@ -79,7 +82,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, if (len < 2) return -EINVAL; len--; - if ((s - path) + len > PATH_MAX) + if ((s - path) + len >= PATH_MAX) return -ENAMETOOLONG; /* reverse fillup of target string from target to base */ diff --git a/fs/libfs.c b/fs/libfs.c index 9588780ad43e..278457f22148 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -85,58 +85,47 @@ int dcache_dir_close(struct inode *inode, struct file *file) EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ -static struct dentry *next_positive(struct dentry *parent, - struct list_head *from, - int count) +/* + * Returns an element of siblings' list. + * We are looking for <count>th positive after <p>; if + * found, dentry is grabbed and passed to caller via *<res>. + * If no such element exists, the anchor of list is returned + * and *<res> is set to NULL. + */ +static struct list_head *scan_positives(struct dentry *cursor, + struct list_head *p, + loff_t count, + struct dentry **res) { - unsigned *seq = &parent->d_inode->i_dir_seq, n; - struct dentry *res; - struct list_head *p; - bool skipped; - int i; + struct dentry *dentry = cursor->d_parent, *found = NULL; -retry: - i = count; - skipped = false; - n = smp_load_acquire(seq) & ~1; - res = NULL; - rcu_read_lock(); - for (p = from->next; p != &parent->d_subdirs; p = p->next) { + spin_lock(&dentry->d_lock); + while ((p = p->next) != &dentry->d_subdirs) { struct dentry *d = list_entry(p, struct dentry, d_child); - if (!simple_positive(d)) { - skipped = true; - } else if (!--i) { - res = d; - break; + // we must at least skip cursors, to avoid livelocks + if (d->d_flags & DCACHE_DENTRY_CURSOR) + continue; + if (simple_positive(d) && !--count) { + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + if (simple_positive(d)) + found = dget_dlock(d); + spin_unlock(&d->d_lock); + if (likely(found)) + break; + count = 1; + } + if (need_resched()) { + list_move(&cursor->d_child, p); + p = &cursor->d_child; + spin_unlock(&dentry->d_lock); + cond_resched(); + spin_lock(&dentry->d_lock); } } - rcu_read_unlock(); - if (skipped) { - smp_rmb(); - if (unlikely(*seq != n)) - goto retry; - } - return res; -} - -static void move_cursor(struct dentry *cursor, struct list_head *after) -{ - struct dentry *parent = cursor->d_parent; - unsigned n, *seq = &parent->d_inode->i_dir_seq; - spin_lock(&parent->d_lock); - for (;;) { - n = *seq; - if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) - break; - cpu_relax(); - } - __list_del(cursor->d_child.prev, cursor->d_child.next); - if (after) - list_add(&cursor->d_child, after); - else - list_add_tail(&cursor->d_child, &parent->d_subdirs); - smp_store_release(seq, n + 2); - spin_unlock(&parent->d_lock); + spin_unlock(&dentry->d_lock); + dput(*res); + *res = found; + return p; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) @@ -152,17 +141,28 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) return -EINVAL; } if (offset != file->f_pos) { + struct dentry *cursor = file->private_data; + struct dentry *to = NULL; + struct list_head *p; + file->f_pos = offset; - if (file->f_pos >= 2) { - struct dentry *cursor = file->private_data; - struct dentry *to; - loff_t n = file->f_pos - 2; - - inode_lock_shared(dentry->d_inode); - to = next_positive(dentry, &dentry->d_subdirs, n); - move_cursor(cursor, to ? &to->d_child : NULL); - inode_unlock_shared(dentry->d_inode); + inode_lock_shared(dentry->d_inode); + + if (file->f_pos > 2) { + p = scan_positives(cursor, &dentry->d_subdirs, + file->f_pos - 2, &to); + spin_lock(&dentry->d_lock); + list_move(&cursor->d_child, p); + spin_unlock(&dentry->d_lock); + } else { + spin_lock(&dentry->d_lock); + list_del_init(&cursor->d_child); + spin_unlock(&dentry->d_lock); } + + dput(to); + + inode_unlock_shared(dentry->d_inode); } return offset; } @@ -184,25 +184,29 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *p = &cursor->d_child; - struct dentry *next; - bool moved = false; + struct list_head *anchor = &dentry->d_subdirs; + struct dentry *next = NULL; + struct list_head *p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) - p = &dentry->d_subdirs; - while ((next = next_positive(dentry, p, 1)) != NULL) { + p = anchor; + else + p = &cursor->d_child; + + while ((p = scan_positives(cursor, p, 1, &next)) != anchor) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) break; - moved = true; - p = &next->d_child; ctx->pos++; } - if (moved) - move_cursor(cursor, p); + spin_lock(&dentry->d_lock); + list_move_tail(&cursor->d_child, p); + spin_unlock(&dentry->d_lock); + dput(next); + return 0; } EXPORT_SYMBOL(dcache_readdir); @@ -795,7 +799,7 @@ int simple_attr_open(struct inode *inode, struct file *file, { struct simple_attr *attr; - attr = kmalloc(sizeof(*attr), GFP_KERNEL); + attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) return -ENOMEM; @@ -835,9 +839,11 @@ ssize_t simple_attr_read(struct file *file, char __user *buf, if (ret) return ret; - if (*ppos) { /* continued read */ + if (*ppos && attr->get_buf[0]) { + /* continued read */ size = strlen(attr->get_buf); - } else { /* first read */ + } else { + /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) diff --git a/fs/locks.c b/fs/locks.c index 22c5b4aa4961..8252647c6084 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2681,7 +2681,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } if (inode) { /* userspace relies on this representation of dev_t */ - seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, + seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { diff --git a/fs/namei.c b/fs/namei.c index eb4626bad88a..0953281430b1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1011,7 +1011,8 @@ static int may_linkat(struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. - * @dir: the sticky parent directory + * @dir_mode: mode bits of directory + * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: @@ -1027,18 +1028,18 @@ static int may_linkat(struct path *link) * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(struct dentry * const dir, +static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || - likely(!(dir->d_inode->i_mode & S_ISVTX)) || - uid_eq(inode->i_uid, dir->d_inode->i_uid) || + likely(!(dir_mode & S_ISVTX)) || + uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; - if (likely(dir->d_inode->i_mode & 0002) || - (dir->d_inode->i_mode & 0020 && + if (likely(dir_mode & 0002) || + (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { return -EACCES; @@ -1369,7 +1370,7 @@ static int follow_dotdot_rcu(struct nameidata *nd) nd->path.dentry = parent; nd->seq = seq; if (unlikely(!path_connected(&nd->path))) - return -ENOENT; + return -ECHILD; break; } else { struct mount *mnt = real_mount(nd->path.mnt); @@ -3259,6 +3260,8 @@ static int do_last(struct nameidata *nd, int *opened) { struct dentry *dir = nd->path.dentry; + kuid_t dir_uid = nd->inode->i_uid; + umode_t dir_mode = nd->inode->i_mode; int open_flag = op->open_flag; bool will_truncate = (open_flag & O_TRUNC) != 0; bool got_write = false; @@ -3401,7 +3404,7 @@ finish_open: error = -EISDIR; if (d_is_dir(nd->path.dentry)) goto out; - error = may_create_in_sticky(dir, + error = may_create_in_sticky(dir_mode, dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) goto out; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index b1daeafbea92..c3428767332c 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -89,7 +89,7 @@ config NFS_V4 config NFS_SWAP bool "Provide swap over NFS support" default n - depends on NFS_FS + depends on NFS_FS && SWAP select SUNRPC_SWAP help This option enables swapon to work on files located on NFS mounts. diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 9d7537446260..0d4a56c77a1a 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -419,7 +419,7 @@ static bool referring_call_exists(struct nfs_client *clp, uint32_t nrclists, struct referring_call_list *rclists) { - bool status = 0; + bool status = false; int i, j; struct nfs4_session *session; struct nfs4_slot_table *tbl; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ebecfb8fba06..28d8a57a9908 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -440,7 +440,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, case XPRT_TRANSPORT_RDMA: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index dff600ae0d74..014039618cff 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -52,6 +52,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation, return false; } +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode) +{ + struct nfs_delegation *delegation; + + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (nfs4_is_valid_delegation(delegation, 0)) + return delegation; + return NULL; +} + static int nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark) { @@ -91,7 +101,7 @@ int nfs4_check_delegation(struct inode *inode, fmode_t flags) return nfs4_do_check_delegation(inode, flags, false); } -static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid) +static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_stateid *stateid) { struct inode *inode = state->inode; struct file_lock *fl; @@ -106,7 +116,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ spin_lock(&flctx->flc_lock); restart: list_for_each_entry(fl, list, fl_list) { - if (nfs_file_open_context(fl->fl_file) != ctx) + if (nfs_file_open_context(fl->fl_file)->state != state) continue; spin_unlock(&flctx->flc_lock); status = nfs4_lock_delegation_recall(fl, state, stateid); @@ -153,7 +163,7 @@ again: seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); err = nfs4_open_delegation_recall(ctx, state, stateid, type); if (!err) - err = nfs_delegation_claim_locks(ctx, state, stateid); + err = nfs_delegation_claim_locks(state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) err = -EAGAIN; mutex_unlock(&sp->so_delegreturn_mutex); @@ -224,6 +234,8 @@ static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation spin_lock(&delegation->lock); if (delegation->inode != NULL) inode = igrab(delegation->inode); + if (!inode) + set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags); spin_unlock(&delegation->lock); return inode; } @@ -857,10 +869,11 @@ restart: list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - if (test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags)) - continue; - if (test_bit(NFS_DELEGATION_NEED_RECLAIM, + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) continue; if (!nfs_sb_active(server->super)) @@ -965,10 +978,11 @@ restart: list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - if (test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags)) - continue; - if (test_bit(NFS_DELEGATION_TEST_EXPIRED, + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags) == 0) continue; if (!nfs_sb_active(server->super)) diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index e9d555796873..f72095bf9e10 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -33,6 +33,7 @@ enum { NFS_DELEGATION_RETURNING, NFS_DELEGATION_REVOKED, NFS_DELEGATION_TEST_EXPIRED, + NFS_DELEGATION_INODE_FREEING, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); @@ -62,6 +63,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred); +struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); int nfs4_have_delegation(struct inode *inode, fmode_t flags); int nfs4_check_delegation(struct inode *inode, fmode_t flags); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 1e5321d1ed22..2517fcd423b6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -57,7 +57,7 @@ static void nfs_readdir_clear_array(struct page*); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, .read = generic_read_dir, - .iterate_shared = nfs_readdir, + .iterate = nfs_readdir, .open = nfs_opendir, .release = nfs_closedir, .fsync = nfs_fsync_dir, @@ -145,7 +145,6 @@ struct nfs_cache_array_entry { }; struct nfs_cache_array { - atomic_t refcount; int size; int eof_index; u64 last_cookie; @@ -170,6 +169,17 @@ typedef struct { unsigned int eof:1; } nfs_readdir_descriptor_t; +static +void nfs_readdir_init_array(struct page *page) +{ + struct nfs_cache_array *array; + + array = kmap_atomic(page); + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; + kunmap_atomic(array); +} + /* * The caller is responsible for calling nfs_readdir_release_array(page) */ @@ -201,18 +211,10 @@ void nfs_readdir_clear_array(struct page *page) int i; array = kmap_atomic(page); - if (atomic_dec_and_test(&array->refcount)) - for (i = 0; i < array->size; i++) - kfree(array->array[i].string.name); - kunmap_atomic(array); -} - -static bool grab_page(struct page *page) -{ - struct nfs_cache_array *array = kmap_atomic(page); - bool res = atomic_inc_not_zero(&array->refcount); + for (i = 0; i < array->size; i++) + kfree(array->array[i].string.name); + array->size = 0; kunmap_atomic(array); - return res; } /* @@ -287,7 +289,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri desc->cache_entry_index = index; return 0; out_eof: - desc->eof = 1; + desc->eof = true; return -EBADCOOKIE; } @@ -341,7 +343,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des if (array->eof_index >= 0) { status = -EBADCOOKIE; if (*desc->dir_cookie == array->last_cookie) - desc->eof = 1; + desc->eof = true; } out: return status; @@ -653,6 +655,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, int status = -ENOMEM; unsigned int array_size = ARRAY_SIZE(pages); + nfs_readdir_init_array(page); + entry.prev_cookie = 0; entry.cookie = desc->last_cookie; entry.eof = 0; @@ -673,9 +677,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, status = PTR_ERR(array); goto out_label_free; } - memset(array, 0, sizeof(struct nfs_cache_array)); - atomic_set(&array->refcount, 1); - array->eof_index = -1; status = nfs_readdir_alloc_pages(pages, array_size); if (status < 0) @@ -730,6 +731,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) unlock_page(page); return 0; error: + nfs_readdir_clear_array(page); unlock_page(page); return ret; } @@ -737,7 +739,6 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) static void cache_page_release(nfs_readdir_descriptor_t *desc) { - nfs_readdir_clear_array(desc->page); put_page(desc->page); desc->page = NULL; } @@ -745,33 +746,34 @@ void cache_page_release(nfs_readdir_descriptor_t *desc) static struct page *get_cache_page(nfs_readdir_descriptor_t *desc) { - struct page *page; - - for (;;) { - page = read_cache_page(desc->file->f_mapping, + return read_cache_page(desc->file->f_mapping, desc->page_index, (filler_t *)nfs_readdir_filler, desc); - if (IS_ERR(page) || grab_page(page)) - break; - put_page(page); - } - return page; } /* * Returns 0 if desc->dir_cookie was found on page desc->page_index + * and locks the page to prevent removal from the page cache. */ static -int find_cache_page(nfs_readdir_descriptor_t *desc) +int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc) { int res; desc->page = get_cache_page(desc); if (IS_ERR(desc->page)) return PTR_ERR(desc->page); - - res = nfs_readdir_search_array(desc); + res = lock_page_killable(desc->page); if (res != 0) - cache_page_release(desc); + goto error; + res = -EAGAIN; + if (desc->page->mapping != NULL) { + res = nfs_readdir_search_array(desc); + if (res == 0) + return 0; + } + unlock_page(desc->page); +error: + cache_page_release(desc); return res; } @@ -786,7 +788,7 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) desc->last_cookie = 0; } do { - res = find_cache_page(desc); + res = find_and_lock_cache_page(desc); } while (res == -EAGAIN); return res; } @@ -815,7 +817,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc) ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->string.name, ent->string.len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { - desc->eof = 1; + desc->eof = true; break; } desc->ctx->pos++; @@ -827,11 +829,10 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc) ctx->duped = 1; } if (array->eof_index >= 0) - desc->eof = 1; + desc->eof = true; nfs_readdir_release_array(desc->page); out: - cache_page_release(desc); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", (unsigned long long)*desc->dir_cookie, res); return res; @@ -877,13 +878,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc) status = nfs_do_filldir(desc); + out_release: + nfs_readdir_clear_array(desc->page); + cache_page_release(desc); out: dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; - out_release: - cache_page_release(desc); - goto out; } /* The file offset position represents the dirent entry number. A @@ -928,7 +929,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) if (res == -EBADCOOKIE) { res = 0; /* This means either end of directory */ - if (*desc->dir_cookie && desc->eof == 0) { + if (*desc->dir_cookie && !desc->eof) { /* Or that the server has 'lost' a cookie */ res = uncached_readdir(desc); if (res == 0) @@ -948,6 +949,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; res = nfs_do_filldir(desc); + unlock_page(desc->page); + cache_page_release(desc); if (res < 0) break; } while (!desc->eof); @@ -960,11 +963,13 @@ out: static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { + struct inode *inode = file_inode(filp); struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", filp, offset, whence); + inode_lock(inode); switch (whence) { case 1: offset += filp->f_pos; @@ -972,13 +977,16 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) if (offset >= 0) break; default: - return -EINVAL; + offset = -EINVAL; + goto out; } if (offset != filp->f_pos) { filp->f_pos = offset; dir_ctx->dir_cookie = 0; dir_ctx->duped = 0; } +out: + inode_unlock(inode); return offset; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 53f0012ace42..de135d2591ff 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -595,6 +595,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { result = PTR_ERR(l_ctx); + nfs_direct_req_release(dreq); goto out_release; } dreq->l_ctx = l_ctx; @@ -1019,6 +1020,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { result = PTR_ERR(l_ctx); + nfs_direct_req_release(dreq); goto out_release; } dreq->l_ctx = l_ctx; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 90099896b838..c8863563c635 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -17,7 +17,7 @@ #define NFSDBG_FACILITY NFSDBG_PNFS_LD -static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS; +static unsigned int dataserver_timeo = NFS_DEF_TCP_TIMEO; static unsigned int dataserver_retrans; void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 76ae25661d3f..851274b25d39 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -950,6 +950,7 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } +EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 1452177c822d..c719389381dc 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -434,7 +434,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); -extern void nfs4_purge_state_owners(struct nfs_server *); +extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *); +extern void nfs4_free_state_owners(struct list_head *head); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, fmode_t); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 43f42cc30a60..3ee60c533217 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -781,9 +781,12 @@ found: static void nfs4_destroy_server(struct nfs_server *server) { + LIST_HEAD(freeme); + nfs_server_return_all_delegations(server); unset_pnfs_layoutdriver(server); - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); + nfs4_free_state_owners(&freeme); } /* @@ -844,7 +847,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, spin_lock(&nn->nfs_client_lock); list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { - if (nfs4_cb_match_client(addr, clp, minorversion) == false) + if (!nfs4_cb_match_client(addr, clp, minorversion)) continue; if (!nfs4_has_session(clp)) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 89a77950e0b0..7138383382ff 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) return err; if ((openflags & O_ACCMODE) == 3) - openflags--; + return nfs_open(inode, filp); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -73,13 +73,13 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (IS_ERR(inode)) { err = PTR_ERR(inode); switch (err) { - case -EPERM: - case -EACCES: - case -EDQUOT: - case -ENOSPC: - case -EROFS: - goto out_put_ctx; default: + goto out_put_ctx; + case -ENOENT: + case -ESTALE: + case -EISDIR: + case -ENOTDIR: + case -ELOOP: goto out_drop; } } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index eb55ab6930b5..632d3c3f8dfb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1121,6 +1121,12 @@ struct nfs4_opendata { int cancelled; }; +struct nfs4_open_createattrs { + struct nfs4_label *label; + struct iattr *sattr; + const __u32 verf[2]; +}; + static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, int err, struct nfs4_exception *exception) { @@ -1190,8 +1196,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p) static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct nfs4_state_owner *sp, fmode_t fmode, int flags, - const struct iattr *attrs, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, enum open_claim_type4 claim, gfp_t gfp_mask) { @@ -1199,6 +1204,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct inode *dir = d_inode(parent); struct nfs_server *server = NFS_SERVER(dir); struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + struct nfs4_label *label = (c != NULL) ? c->label : NULL; struct nfs4_opendata *p; p = kzalloc(sizeof(*p), gfp_mask); @@ -1255,15 +1261,11 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_DELEG_PREV_FH: p->o_arg.fh = NFS_FH(d_inode(dentry)); } - if (attrs != NULL && attrs->ia_valid != 0) { - __u32 verf[2]; - + if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) { p->o_arg.u.attrs = &p->attrs; - memcpy(&p->attrs, attrs, sizeof(p->attrs)); + memcpy(&p->attrs, c->sattr, sizeof(p->attrs)); - verf[0] = jiffies; - verf[1] = current->pid; - memcpy(p->o_arg.u.verifier.data, verf, + memcpy(p->o_arg.u.verifier.data, c->verf, sizeof(p->o_arg.u.verifier.data)); } p->c_arg.fh = &p->o_res.fh; @@ -1366,8 +1368,6 @@ 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_RETURNING, &delegation->flags)) - return 0; switch (claim) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_FH: @@ -1626,7 +1626,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) { struct nfs4_state *state = opendata->state; - struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_delegation *delegation; int open_mode = opendata->o_arg.open_flags; fmode_t fmode = opendata->o_arg.fmode; @@ -1643,7 +1642,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) } spin_unlock(&state->owner->so_lock); rcu_read_lock(); - delegation = rcu_dereference(nfsi->delegation); + delegation = nfs4_get_valid_delegation(state->inode); if (!can_open_delegated(delegation, fmode, claim)) { rcu_read_unlock(); break; @@ -1814,7 +1813,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context struct nfs4_opendata *opendata; opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, - NULL, NULL, claim, GFP_NOFS); + NULL, claim, GFP_NOFS); if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; @@ -2140,7 +2139,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags)) goto out_no_action; rcu_read_lock(); - delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); + delegation = nfs4_get_valid_delegation(data->state->inode); if (can_open_delegated(delegation, data->o_arg.fmode, claim)) goto unlock_no_action; rcu_read_unlock(); @@ -2748,7 +2747,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, nfs4_schedule_stateid_recovery(server, state); } out: - nfs4_sequence_free_slot(&opendata->o_res.seq_res); + if (!opendata->cancelled) + nfs4_sequence_free_slot(&opendata->o_res.seq_res); return ret; } @@ -2758,8 +2758,7 @@ out: static int _nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, - struct iattr *sattr, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, int *opened) { struct nfs4_state_owner *sp; @@ -2771,6 +2770,8 @@ static int _nfs4_do_open(struct inode *dir, struct nfs4_threshold **ctx_th = &ctx->mdsthreshold; fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC); enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; + struct iattr *sattr = c->sattr; + struct nfs4_label *label = c->label; struct nfs4_label *olabel = NULL; int status; @@ -2789,8 +2790,8 @@ static int _nfs4_do_open(struct inode *dir, status = -ENOMEM; if (d_really_is_positive(dentry)) claim = NFS4_OPEN_CLAIM_FH; - opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, - label, claim, GFP_KERNEL); + opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, + c, claim, GFP_KERNEL); if (opendata == NULL) goto err_put_state_owner; @@ -2871,10 +2872,18 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; struct nfs4_state *res; + struct nfs4_open_createattrs c = { + .label = label, + .sattr = sattr, + .verf = { + [0] = (__u32)jiffies, + [1] = (__u32)current->pid, + }, + }; int status; do { - status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); + status = _nfs4_do_open(dir, ctx, flags, &c, opened); res = ctx->state; trace_nfs4_open_file(ctx, flags, status); if (status == 0) @@ -2907,6 +2916,11 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, exception.retry = 1; continue; } + if (status == -NFS4ERR_EXPIRED) { + nfs4_schedule_lease_recovery(server->nfs_client); + exception.retry = 1; + continue; + } if (status == -EAGAIN) { /* We must have found a delegation */ exception.retry = 1; @@ -5532,6 +5546,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, } status = task->tk_status; if (setclientid.sc_cred) { + kfree(clp->cl_acceptor); clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred); put_rpccred(setclientid.sc_cred); } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 857af951831f..4e63daeef633 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -143,6 +143,10 @@ int nfs40_discover_server_trunking(struct nfs_client *clp, /* Sustain the lease, even if it's empty. If the clientid4 * goes stale it's of no use for trunking discovery. */ nfs4_schedule_state_renewal(*result); + + /* If the client state need to recover, do it. */ + if (clp->cl_state) + nfs4_schedule_state_manager(clp); } out: return status; @@ -607,24 +611,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) /** * nfs4_purge_state_owners - Release all cached state owners * @server: nfs_server with cached state owners to release + * @head: resulting list of state owners * * Called at umount time. Remaining state owners will be on * the LRU with ref count of zero. + * Note that the state owners are not freed, but are added + * to the list @head, which can later be used as an argument + * to nfs4_free_state_owners. */ -void nfs4_purge_state_owners(struct nfs_server *server) +void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head) { struct nfs_client *clp = server->nfs_client; struct nfs4_state_owner *sp, *tmp; - LIST_HEAD(doomed); spin_lock(&clp->cl_lock); list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { - list_move(&sp->so_lru, &doomed); + list_move(&sp->so_lru, head); nfs4_remove_state_owner_locked(sp); } spin_unlock(&clp->cl_lock); +} - list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { +/** + * nfs4_purge_state_owners - Release all cached state owners + * @head: resulting list of state owners + * + * Frees a list of state owners that was generated by + * nfs4_purge_state_owners + */ +void nfs4_free_state_owners(struct list_head *head) +{ + struct nfs4_state_owner *sp, *tmp; + + list_for_each_entry_safe(sp, tmp, head, so_lru) { list_del(&sp->so_lru); nfs4_free_state_owner(sp); } @@ -1760,12 +1779,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct nfs4_state_owner *sp; struct nfs_server *server; struct rb_node *pos; + LIST_HEAD(freeme); int status = 0; restart: rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); spin_lock(&clp->cl_lock); for (pos = rb_first(&server->state_owners); pos != NULL; @@ -1794,6 +1814,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); + nfs4_free_state_owners(&freeme); return 0; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 5e2724a928ed..d7f8d5ce30e3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1123,7 +1123,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, } else *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } - if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (label && (bmval[2] & FATTR4_WORD2_SECURITY_LABEL)) { *p++ = cpu_to_be32(label->lfs); *p++ = cpu_to_be32(label->pi); *p++ = cpu_to_be32(label->len); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index fad4d5188aaf..529f3a576263 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -562,7 +562,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr, } hdr->res.fattr = &hdr->fattr; - hdr->res.count = count; + hdr->res.count = 0; hdr->res.eof = 0; hdr->res.verf = &hdr->verf; nfs_fattr_init(&hdr->fattr); @@ -851,15 +851,6 @@ static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, return 0; } -/* - * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1) - */ -void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio) -{ - pgio->pg_mirror_count = 1; - pgio->pg_mirror_idx = 0; -} - static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) { pgio->pg_mirror_count = 1; @@ -1285,6 +1276,14 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) } } +/* + * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1) + */ +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio) +{ + nfs_pageio_complete(pgio); +} + int __init nfs_init_nfspagecache(void) { nfs_page_cachep = kmem_cache_create("nfs_page", diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0e008db16b16..c3abf92adfb7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1436,7 +1436,7 @@ pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range, if ((range->iomode == IOMODE_RW && ls_range->iomode != IOMODE_RW) || (range->iomode != ls_range->iomode && - strict_iomode == true) || + strict_iomode) || !pnfs_lseg_range_intersecting(ls_range, range)) return 0; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index b7bca8303989..06e72229be12 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -588,7 +588,8 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) /* Emulate the eof flag, which isn't normally needed in NFSv2 * as it is guaranteed to always return the file attributes */ - if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size) + if ((hdr->res.count == 0 && hdr->args.count > 0) || + hdr->args.offset + hdr->res.count >= hdr->res.fattr->size) hdr->res.eof = 1; } return 0; @@ -609,8 +610,10 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { - if (task->tk_status >= 0) + if (task->tk_status >= 0) { + hdr->res.count = hdr->args.count; nfs_writeback_update_inode(hdr); + } return 0; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 659ad12e33ba..4c21e572f2d9 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1928,7 +1928,7 @@ static int nfs_parse_devname(const char *dev_name, /* kill possible hostname list: not supported */ comma = strchr(dev_name, ','); if (comma != NULL && comma < end) - *comma = 0; + len = comma - dev_name; } if (len > maxnamlen) @@ -2047,7 +2047,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3069cd46ea66..8d842282111b 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -934,8 +934,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -962,6 +963,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -999,6 +1003,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1206,6 +1211,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 64813697f4c4..f6cc2fddb78b 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -680,7 +680,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) /* Client gets 2 lease periods to return it */ cutoff = ktime_add_ns(task->tk_start, - nn->nfsd4_lease * NSEC_PER_SEC * 2); + (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2); if (ktime_before(now, cutoff)) { rpc_delay(task, HZ/100); /* 10 mili-seconds */ diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 66eaeb1e8c2c..dc9586feab31 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -661,7 +661,7 @@ struct cld_net { struct cld_upcall { struct list_head cu_list; struct cld_net *cu_net; - struct task_struct *cu_task; + struct completion cu_done; struct cld_msg cu_msg; }; @@ -670,23 +670,18 @@ __cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg) { int ret; struct rpc_pipe_msg msg; + struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_msg); memset(&msg, 0, sizeof(msg)); msg.data = cmsg; msg.len = sizeof(*cmsg); - /* - * Set task state before we queue the upcall. That prevents - * wake_up_process in the downcall from racing with schedule. - */ - set_current_state(TASK_UNINTERRUPTIBLE); ret = rpc_queue_upcall(pipe, &msg); if (ret < 0) { - set_current_state(TASK_RUNNING); goto out; } - schedule(); + wait_for_completion(&cup->cu_done); if (msg.errno < 0) ret = msg.errno; @@ -753,7 +748,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (copy_from_user(&cup->cu_msg, src, mlen) != 0) return -EFAULT; - wake_up_process(cup->cu_task); + complete(&cup->cu_done); return mlen; } @@ -768,7 +763,7 @@ cld_pipe_destroy_msg(struct rpc_pipe_msg *msg) if (msg->errno >= 0) return; - wake_up_process(cup->cu_task); + complete(&cup->cu_done); } static const struct rpc_pipe_ops cld_upcall_ops = { @@ -899,7 +894,7 @@ restart_search: goto restart_search; } } - new->cu_task = current; + init_completion(&new->cu_done); new->cu_msg.cm_vers = CLD_UPCALL_VERSION; put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid); new->cu_net = cn; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 3656f87d11e3..4509c76716e3 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1502,11 +1502,16 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) { u32 slotsize = slot_bytes(ca); u32 num = ca->maxreqs; - int avail; + unsigned long avail, total_avail; spin_lock(&nfsd_drc_lock); - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); + total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; + avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); + /* + * Never use more than a third of the remaining memory, + * unless it's the only way to give this client a slot: + */ + avail = clamp_t(unsigned long, avail, slotsize, total_avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); @@ -3062,12 +3067,17 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, (bool)seq->cachethis) return false; /* - * If there's an error than the reply can have fewer ops than - * the call. But if we cached a reply with *more* ops than the - * call you're sending us now, then this new call is clearly not - * really a replay of the old one: + * If there's an error then the reply can have fewer ops than + * the call. + */ + if (slot->sl_opcnt < argp->opcnt && !slot->sl_status) + return false; + /* + * But if we cached a reply with *more* ops than the call you're + * sending us now, then this new call is clearly not really a + * replay of the old one: */ - if (slot->sl_opcnt < argp->opcnt) + if (slot->sl_opcnt > argp->opcnt) return false; /* This is the only check explicitly called by spec: */ if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) @@ -6024,7 +6034,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } if (fl_flags & FL_SLEEP) { - nbl->nbl_time = jiffies; + nbl->nbl_time = get_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 5c4800626f13..60291d10f8e4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -430,7 +430,7 @@ void nfsd_reset_versions(void) */ static void set_max_drc(void) { - #define NFSD_DRC_SIZE_SHIFT 10 + #define NFSD_DRC_SIZE_SHIFT 7 nfsd_drc_max_mem = (nr_free_buffer_pages() >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE; nfsd_drc_mem_used = 0; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 86aa92d200e1..7872b1ead885 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -69,6 +69,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { @@ -590,7 +591,7 @@ static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b) struct nfsd4_blocked_lock { struct list_head nbl_list; struct list_head nbl_lru; - unsigned long nbl_time; + time_t nbl_time; struct file_lock nbl_lock; struct knfsd_fh nbl_fh; struct nfsd4_callback nbl_cb; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8f0b19a3ca81..b8cd100cfcd6 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -395,10 +395,23 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); - if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) + if (iap->ia_valid & ATTR_SIZE) { accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; - if (iap->ia_valid & ATTR_SIZE) ftype = S_IFREG; + } + + /* + * If utimes(2) and friends are called with times not NULL, we should + * not set NFSD_MAY_WRITE bit. Otherwise fh_verify->nfsd_permission + * will return EACCESS, when the caller's effective UID does not match + * the owner of the file, and the caller is not privileged. In this + * situation, we should return EPERM(notify_change will return this). + */ + if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME)) { + accmode |= NFSD_MAY_OWNER_OVERRIDE; + if (!(iap->ia_valid & (ATTR_ATIME_SET | ATTR_MTIME_SET))) + accmode |= NFSD_MAY_WRITE; + } /* Callers that do fh_verify should do the fh_want_write: */ get_write_count = !fhp->fh_dentry; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 0bf9e7bf5800..9140b9cf3870 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -116,8 +116,11 @@ void nfsd_put_raparams(struct file *file, struct raparms *ra); static inline int fh_want_write(struct svc_fh *fh) { - int ret = mnt_want_write(fh->fh_export->ex_path.mnt); + int ret; + if (fh->fh_want_write) + return 0; + ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) fh->fh_want_write = true; return ret; diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index ee8dbbae78b6..6dc714a56c37 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -338,8 +338,8 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) down_read(&OCFS2_I(inode)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); up_read(&OCFS2_I(inode)->ip_xattr_sem); - if (IS_ERR(acl) || !acl) - return PTR_ERR(acl); + if (IS_ERR_OR_NULL(acl)) + return PTR_ERR_OR_ZERO(acl); ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); if (ret) return ret; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 06089becca60..dfb8a923921e 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7246,6 +7246,10 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inline_data *idata = &di->id2.i_data; + /* No need to punch hole beyond i_size. */ + if (start >= i_size_read(inode)) + return 0; + if (end > i_size_read(inode)) end = i_size_read(inode); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index c26d046adaaa..6ad76397b31d 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2046,7 +2046,8 @@ out_write_size: inode->i_mtime = inode->i_ctime = current_time(inode); di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ocfs2_update_inode_fsync_trans(handle, inode, 1); + if (handle) + ocfs2_update_inode_fsync_trans(handle, inode, 1); } if (handle) ocfs2_journal_dirty(handle, wc->w_di_bh); @@ -2143,13 +2144,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; - loff_t pos = iblock << inode->i_sb->s_blocksize_bits; + unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; + loff_t pos = iblock << i_blkbits; + sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); + /* + * bh_result->b_size is count in get_more_blocks according to write + * "pos" and "end", we need map twice to return different buffer state: + * 1. area in file size, not set NEW; + * 2. area out file size, set NEW. + * + * iblock endblk + * |--------|---------|---------|--------- + * |<-------area in file------->| + */ + + if ((iblock <= endblk) && + ((iblock + ((len - 1) >> i_blkbits)) > endblk)) + len = (endblk - iblock + 1) << i_blkbits; + mlog(0, "get block of %lu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); @@ -2233,6 +2251,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, if (desc->c_needs_zero) set_buffer_new(bh_result); + if (iblock > endblk) + set_buffer_new(bh_result); + /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 935bac253991..1403c88f2b05 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -98,25 +98,34 @@ out: return ret; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, unsigned int nr, struct buffer_head *bhs[]) { int status = 0; unsigned int i; struct buffer_head *bh; + int new_bh = 0; trace_ocfs2_read_blocks_sync((unsigned long long)block, nr); if (!nr) goto bail; + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(osb->sb, block++); if (bhs[i] == NULL) { status = -ENOMEM; mlog_errno(status); - goto bail; + break; } } bh = bhs[i]; @@ -156,9 +165,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, submit_bh(REQ_OP_READ, 0, bh); } +read_failure: for (i = nr; i > 0; i--) { bh = bhs[i - 1]; + if (unlikely(status)) { + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i - 1] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } + continue; + } + /* No need to wait on the buffer if it's managed by JBD. */ if (!buffer_jbd(bh)) wait_on_buffer(bh); @@ -168,8 +194,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, * so we can safely record this and loop back * to cleanup the other buffers. */ status = -EIO; - put_bh(bh); - bhs[i - 1] = NULL; + goto read_failure; } } @@ -177,6 +202,9 @@ bail: return status; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, struct buffer_head *bhs[], int flags, int (*validate)(struct super_block *sb, @@ -186,6 +214,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, int i, ignore_cache = 0; struct buffer_head *bh; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); + int new_bh = 0; trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags); @@ -211,6 +240,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, goto bail; } + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + ocfs2_metadata_cache_io_lock(ci); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { @@ -219,7 +253,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, ocfs2_metadata_cache_io_unlock(ci); status = -ENOMEM; mlog_errno(status); - goto bail; + /* Don't forget to put previous bh! */ + break; } } bh = bhs[i]; @@ -313,16 +348,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, } } - status = 0; - +read_failure: for (i = (nr - 1); i >= 0; i--) { bh = bhs[i]; if (!(flags & OCFS2_BH_READAHEAD)) { - if (status) { - /* Clear the rest of the buffers on error */ - put_bh(bh); - bhs[i] = NULL; + if (unlikely(status)) { + /* Clear the buffers on error including those + * ever succeeded in reading + */ + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } continue; } /* We know this can't have changed as we hold the @@ -340,9 +386,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * uptodate. */ status = -EIO; clear_buffer_needs_validate(bh); - put_bh(bh); - bhs[i] = NULL; - continue; + goto read_failure; } if (buffer_needs_validate(bh)) { @@ -352,11 +396,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, BUG_ON(buffer_jbd(bh)); clear_buffer_needs_validate(bh); status = validate(sb, bh); - if (status) { - put_bh(bh); - bhs[i] = NULL; - continue; - } + if (status) + goto read_failure; } } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index c204ac9b49e5..81a0d5d82757 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group, struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent); - o2net_disconnect_node(node); + if (cluster->cl_nodes[node->nd_num] == node) { + o2net_disconnect_node(node); - if (cluster->cl_has_local && - (cluster->cl_local_node == node->nd_num)) { - cluster->cl_has_local = 0; - cluster->cl_local_node = O2NM_INVALID_NODE_NUM; - o2net_stop_listening(node); + if (cluster->cl_has_local && + (cluster->cl_local_node == node->nd_num)) { + cluster->cl_has_local = 0; + cluster->cl_local_node = O2NM_INVALID_NODE_NUM; + o2net_stop_listening(node); + } } /* XXX call into net to stop this node from trading messages */ diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 290373024d9d..e8ace3b54e9c 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -310,6 +310,18 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry, out_attach: spin_lock(&dentry_attach_lock); + if (unlikely(dentry->d_fsdata && !alias)) { + /* d_fsdata is set by a racing thread which is doing + * the same thing as this thread is doing. Leave the racing + * thread going ahead and we return here. + */ + spin_unlock(&dentry_attach_lock); + iput(dl->dl_inode); + ocfs2_lock_res_free(&dl->dl_lockres); + kfree(dl); + return 0; + } + dentry->d_fsdata = dl; dl->dl_count++; spin_unlock(&dentry_attach_lock); diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index e7b760deefae..32d60f69db24 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -329,7 +329,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle) { char *buf; - buf = (char *) get_zeroed_page(GFP_NOFS); + buf = (char *) get_zeroed_page(GFP_ATOMIC); if (buf) { dump_mle(mle, buf, PAGE_SIZE - 1); free_page((unsigned long)buf); diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 1082b2c3014b..5f2a120240e5 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -105,7 +105,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, enum dlm_status status; int actions = 0; int in_use; - u8 owner; + u8 owner; + int recovery_wait = 0; mlog(0, "master_node = %d, valblk = %d\n", master_node, flags & LKM_VALBLK); @@ -208,9 +209,12 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, } if (flags & LKM_CANCEL) lock->cancel_pending = 0; - else - lock->unlock_pending = 0; - + else { + if (!lock->unlock_pending) + recovery_wait = 1; + else + lock->unlock_pending = 0; + } } /* get an extra ref on lock. if we are just switching @@ -244,6 +248,17 @@ leave: spin_unlock(&res->spinlock); wake_up(&res->wq); + if (recovery_wait) { + spin_lock(&res->spinlock); + /* Unlock request will directly succeed after owner dies, + * and the lock is already removed from grant list. We have to + * wait for RECOVERING done or we miss the chance to purge it + * since the removement is much faster than RECOVERING proc. + */ + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_RECOVERING); + spin_unlock(&res->spinlock); + } + /* let the caller's final dlm_lock_put handle the actual kfree */ if (actions & DLM_UNLOCK_FREE_LOCK) { /* this should always be coupled with list removal */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 5729d55da67d..2c3e975126b3 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3421,7 +3421,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, * we can recover correctly from node failure. Otherwise, we may get * invalid LVB in LKB, but without DLM_SBF_VALNOTVALIDÂ being set. */ - if (!ocfs2_is_o2cb_active() && + if (ocfs2_userspace_stack(osb) && lockres->l_ops->flags & LOCK_TYPE_USES_LVB) lvb = 1; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 3494e220b510..bed15dec3c16 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -148,16 +148,24 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) u64 blkno; struct dentry *parent; struct inode *dir = d_inode(child); + int set; trace_ocfs2_get_parent(child, child->d_name.len, child->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno); + status = ocfs2_nfs_sync_lock(OCFS2_SB(dir->i_sb), 1); + if (status < 0) { + mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status); + parent = ERR_PTR(status); + goto bail; + } + status = ocfs2_inode_lock(dir, NULL, 0); if (status < 0) { if (status != -ENOENT) mlog_errno(status); parent = ERR_PTR(status); - goto bail; + goto unlock_nfs_sync; } status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno); @@ -166,11 +174,31 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) goto bail_unlock; } + status = ocfs2_test_inode_bit(OCFS2_SB(dir->i_sb), blkno, &set); + if (status < 0) { + if (status == -EINVAL) { + status = -ESTALE; + } else + mlog(ML_ERROR, "test inode bit failed %d\n", status); + parent = ERR_PTR(status); + goto bail_unlock; + } + + trace_ocfs2_get_dentry_test_bit(status, set); + if (!set) { + status = -ESTALE; + parent = ERR_PTR(status); + goto bail_unlock; + } + parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0)); bail_unlock: ocfs2_inode_unlock(dir, 0); +unlock_nfs_sync: + ocfs2_nfs_sync_unlock(OCFS2_SB(dir->i_sb), 1); + bail: trace_ocfs2_get_parent_end(parent); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 4506ec5ec2ea..bfc44644301c 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -289,7 +289,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, if (inode_alloc) inode_lock(inode_alloc); - if (o2info_coherent(&fi->ifi_req)) { + if (inode_alloc && o2info_coherent(&fi->ifi_req)) { status = ocfs2_inode_lock(inode_alloc, &bh, 0); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index fa947d36ae1d..733c05135305 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -231,7 +231,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb) /* At this point, we know that no more recovery threads can be * launched, so wait for any recovery completion work to * complete. */ - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); /* * Now that recovery is shut down, and the osb is about to be @@ -1017,7 +1018,8 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb) mlog_errno(status); } - if (status == 0) { + /* Shutdown the kernel journal system */ + if (!jbd2_journal_destroy(journal->j_journal) && !status) { /* * Do not toggle if flush was unsuccessful otherwise * will leave dirty metadata in a "clean" journal @@ -1026,9 +1028,6 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb) if (status < 0) mlog_errno(status); } - - /* Shutdown the kernel journal system */ - jbd2_journal_destroy(journal->j_journal); journal->j_journal = NULL; OCFS2_I(inode)->ip_open_count--; @@ -1081,6 +1080,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num); + if (replayed) { + jbd2_journal_lock_updates(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal); + jbd2_journal_unlock_updates(journal->j_journal); + if (status < 0) + mlog_errno(status); + } + status = ocfs2_journal_toggle_dirty(osb, 1, replayed); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 497a4171ef61..bfb50fc51528 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -637,9 +637,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle, { struct ocfs2_inode_info *oi = OCFS2_I(inode); - oi->i_sync_tid = handle->h_transaction->t_tid; - if (datasync) - oi->i_datasync_tid = handle->h_transaction->t_tid; + if (!is_handle_aborted(handle)) { + oi->i_sync_tid = handle->h_transaction->t_tid; + if (datasync) + oi->i_datasync_tid = handle->h_transaction->t_tid; + } } #endif /* OCFS2_JOURNAL_H */ diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 5d53d0d63d19..ea38677daa06 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -391,7 +391,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index c179afd0051a..afaa044f5f6b 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -25,6 +25,7 @@ #include "ocfs2_ioctl.h" #include "alloc.h" +#include "localalloc.h" #include "aops.h" #include "dlmglue.h" #include "extent_map.h" @@ -222,6 +223,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, struct ocfs2_refcount_tree *ref_tree = NULL; u32 new_phys_cpos, new_len; u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); + int need_free = 0; if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) { @@ -315,6 +317,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, if (!partial) { context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE; ret = -ENOSPC; + need_free = 1; goto out_commit; } } @@ -339,6 +342,20 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, mlog_errno(ret); out_commit: + if (need_free && context->data_ac) { + struct ocfs2_alloc_context *data_ac = context->data_ac; + + if (context->data_ac->ac_which == OCFS2_AC_USE_LOCAL) + ocfs2_free_local_alloc_bits(osb, handle, data_ac, + new_phys_cpos, new_len); + else + ocfs2_free_clusters(handle, + data_ac->ac_inode, + data_ac->ac_bh, + ocfs2_clusters_to_blocks(osb->sb, new_phys_cpos), + new_len); + } + ocfs2_commit_trans(osb, handle); out_unlock_mutex: diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 87e577a49b0d..542fa21aeaa9 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -714,7 +714,7 @@ static int ocfs2_release_dquot(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out; /* Running from downconvert thread? Postpone quota processing to wq */ if (current == osb->dc_task) { diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 820359096c7a..52c07346bea3 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; -inline int ocfs2_is_o2cb_active(void) -{ - return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); -} -EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); - static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index e3036e1790e8..f2dce10fae54 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); -/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ -int ocfs2_is_o2cb_active(void); - extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 01932763b4d1..e108c945ac1f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3832,7 +3832,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb); int low_bucket = 0, bucket, high_bucket; struct ocfs2_xattr_bucket *search; - u32 last_hash; u64 blkno, lower_blkno = 0; search = ocfs2_xattr_bucket_new(inode); @@ -3876,8 +3875,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, if (xh->xh_count) xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1]; - last_hash = le32_to_cpu(xe->xe_name_hash); - /* record lower_blkno which may be the insert place. */ lower_blkno = blkno; diff --git a/fs/open.c b/fs/open.c index a6c6244f4993..e17cc79bd88a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -380,6 +380,25 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); @@ -717,6 +736,12 @@ static int do_dentry_open(struct file *f, return 0; } + /* Any file opened for execve()/uselib() has to be a regular file. */ + if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { + error = -EACCES; + goto cleanup_file; + } + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) @@ -799,9 +824,6 @@ cleanup_file: * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * - * On successful return @file is a fully instantiated open file. After this, if - * an error occurs in ->atomic_open(), it needs to clean up with fput(). - * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, @@ -1186,3 +1208,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 0748a26598fc..7d7df003f9d8 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -304,6 +304,7 @@ static void *help_start(struct seq_file *m, loff_t *pos) static void *help_next(struct seq_file *m, void *v, loff_t *pos) { + (*pos)++; gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_next: start\n"); return NULL; diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c index a799546a67f7..f6172c3f83ba 100644 --- a/fs/orangefs/orangefs-sysfs.c +++ b/fs/orangefs/orangefs-sysfs.c @@ -315,7 +315,7 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj, /* Can't do a service_operation if the client is not running... */ rc = is_daemon_in_service(); if (rc) { - pr_info("%s: Client not running :%d:\n", + pr_info_ratelimited("%s: Client not running :%d:\n", __func__, is_daemon_in_service()); goto out; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 16f6db88c8e5..804b3469669f 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -234,7 +234,8 @@ static bool ovl_can_list(const char *s) return true; /* Never list trusted.overlay, list other trusted for superuser only */ - return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN); + return !ovl_is_private_xattr(s) && + ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); } ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) diff --git a/fs/pipe.c b/fs/pipe.c index 388e09a689de..347c6dc888c8 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -193,9 +193,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/proc/array.c b/fs/proc/array.c index 712b44c63701..9682bbf325d6 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -448,7 +448,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & PF_DUMPCORE)) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1999e85840d5..191573a625f2 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -500,6 +500,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (root->set_ownership) root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); + else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } return inode; } @@ -1604,8 +1608,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); - start_unregistering(header); + if (parent) { + put_links(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5138e781737a..4b207b10db03 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1057,6 +1057,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 8ab782d8b33d..93d13f4010c1 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -165,6 +165,16 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, } /* + * Architectures which support memory encryption override this. + */ +ssize_t __weak +copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) +{ + return copy_oldmem_page(pfn, buf, csize, offset, userbuf); +} + +/* * Copy to either kernel or user space */ static int copy_to(void *target, void *src, size_t size, int userbuf) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 8b09271e5d66..a73959e6ae32 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -321,6 +321,17 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, prz = cxt->przs[cxt->dump_write_cnt]; + /* + * Since this is a new crash dump, we need to reset the buffer in + * case it still has an old dump present. Without this, the new dump + * will get appended, which would seriously confuse anything trying + * to check dump file contents. Specifically, ramoops_read_kmsg_hdr() + * expects to find a dump header in the beginning of buffer data, so + * we must to reset the buffer values, in order to ensure that the + * header will be written to the beginning of the buffer. + */ + persistent_ram_zap(prz); + hlen = ramoops_write_kmsg_hdr(prz, compressed); if (size + hlen > prz->buffer_size) size = prz->buffer_size - hlen; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f9246ac4eef8..82a5ecbe2da9 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -479,7 +479,7 @@ int dquot_release(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out_dqlock; mutex_lock(&dqopt->dqio_mutex); if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { @@ -611,7 +611,7 @@ EXPORT_SYMBOL(dquot_scan_active); /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { - struct list_head *dirty; + struct list_head dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; @@ -624,9 +624,10 @@ int dquot_writeback_dquots(struct super_block *sb, int type) if (!sb_has_quota_active(sb, cnt)) continue; spin_lock(&dq_list_lock); - dirty = &dqopt->info[cnt].dqi_dirty_list; - while (!list_empty(dirty)) { - dquot = list_first_entry(dirty, struct dquot, + /* Move list away to avoid livelock. */ + list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty); + while (!list_empty(&dirty)) { + dquot = list_first_entry(&dirty, struct dquot, dq_dirty); /* Dirty and inactive can be only bad dquot... */ if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { @@ -2848,68 +2849,73 @@ 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) { - unsigned int type = (int *)table->data - dqstats.stat; + unsigned int type = (unsigned long *)table->data - dqstats.stat; + s64 value = percpu_counter_sum(&dqstats.counter[type]); + + /* Filter negative values for non-monotonic counters */ + if (value < 0 && (type == DQST_ALLOC_DQUOTS || + type == DQST_FREE_DQUOTS)) + value = 0; /* Update global table */ - dqstats.stat[type] = - percpu_counter_sum_positive(&dqstats.counter[type]); - return proc_dointvec(table, write, buffer, lenp, ppos); + dqstats.stat[type] = value; + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "drops", .data = &dqstats.stat[DQST_DROPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "reads", .data = &dqstats.stat[DQST_READS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "writes", .data = &dqstats.stat[DQST_WRITES], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "cache_hits", .data = &dqstats.stat[DQST_CACHE_HITS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "allocated_dquots", .data = &dqstats.stat[DQST_ALLOC_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "free_dquots", .data = &dqstats.stat[DQST_FREE_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "syncs", .data = &dqstats.stat[DQST_SYNCS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, diff --git a/fs/read_write.c b/fs/read_write.c index 9819f7c6c8c5..9e1fd4c20e89 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -575,12 +575,13 @@ EXPORT_SYMBOL(vfs_write); static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) @@ -1204,6 +1205,9 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos, int, flags) { + if (pos == -1) + return do_compat_readv(fd, vec, vlen, flags); + return do_compat_preadv64(fd, vec, vlen, pos, flags); } #endif @@ -1310,6 +1314,9 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos, int, flags) { + if (pos == -1) + return do_compat_writev(fd, vec, vlen, flags); + return do_compat_pwritev64(fd, vec, vlen, pos, flags); } #endif diff --git a/fs/readdir.c b/fs/readdir.c index 9d0212c374d6..1059f2a9be0b 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -64,6 +64,40 @@ out: EXPORT_SYMBOL(iterate_dir); /* + * POSIX says that a dirent name cannot contain NULL or a '/'. + * + * It's not 100% clear what we should really do in this case. + * The filesystem is clearly corrupted, but returning a hard + * error means that you now don't see any of the other names + * either, so that isn't a perfect alternative. + * + * And if you return an error, what error do you use? Several + * filesystems seem to have decided on EUCLEAN being the error + * code for EFSCORRUPTED, and that may be the error to use. Or + * just EIO, which is perhaps more obvious to users. + * + * In order to see the other file names in the directory, the + * caller might want to make this a "soft" error: skip the + * entry, and return the error at the end instead. + * + * Note that this should likely do a "memchr(name, 0, len)" + * check too, since that would be filesystem corruption as + * well. However, that case can't actually confuse user space, + * which has to do a strlen() on the name anyway to find the + * filename length, and the above "soft error" worry means + * that it's probably better left alone until we have that + * issue clarified. + */ +static int verify_dirent_name(const char *name, int len) +{ + if (!len) + return -EIO; + if (memchr(name, '/', len)) + return -EIO; + return 0; +} + +/* * Traditional linux readdir() handling.. * * "count=1" is a special case, meaning that the buffer is one @@ -172,6 +206,9 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; @@ -258,6 +295,9 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return buf->error; buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index bd4c727f4610..9531b6c18ac7 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2102,6 +2102,15 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, goto out_inserted_sd; } + /* + * Mark it private if we're creating the privroot + * or something under it. + */ + if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) { + inode->i_flags |= S_PRIVATE; + inode->i_opflags &= ~IOP_XATTR; + } + if (reiserfs_posixacl(inode->i_sb)) { reiserfs_write_unlock(inode->i_sb); retval = reiserfs_inherit_default_acl(th, dir, dentry, inode); @@ -2116,8 +2125,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, reiserfs_warning(inode->i_sb, "jdm-13090", "ACLs aren't enabled in the fs, " "but vfs thinks they are!"); - } else if (IS_PRIVATE(dir)) - inode->i_flags |= S_PRIVATE; + } if (security->name) { reiserfs_write_unlock(inode->i_sb); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 1ec728cf82d1..1c900f322089 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -377,10 +377,13 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, /* * Propagate the private flag so we know we're - * in the priv tree + * in the priv tree. Also clear IOP_XATTR + * since we don't have xattrs on xattr files. */ - if (IS_PRIVATE(dir)) + if (IS_PRIVATE(dir)) { inode->i_flags |= S_PRIVATE; + inode->i_opflags &= ~IOP_XATTR; + } } reiserfs_write_unlock(dir->i_sb); if (retval == IO_ERROR) { diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index d920a646b578..3e78a394fdb8 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -1167,6 +1167,8 @@ static inline int bmap_would_wrap(unsigned bmap_nr) return bmap_nr > ((1LL << 16) - 1); } +extern const struct xattr_handler *reiserfs_xattr_handlers[]; + /* * this says about version of key of all items (but stat data) the * object consists of diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index a97e352d05d3..5f5fff068877 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -2249,7 +2249,8 @@ error_out: /* also releases the path */ unfix_nodes(&s_ins_balance); #ifdef REISERQUOTA_DEBUG - reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE, + if (inode) + reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE, "reiserquota insert_item(): freeing %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index dec6c93044fa..677608a89b08 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -599,6 +599,7 @@ static void reiserfs_put_super(struct super_block *s) reiserfs_write_unlock(s); mutex_destroy(&REISERFS_SB(s)->lock); destroy_workqueue(REISERFS_SB(s)->commit_wq); + kfree(REISERFS_SB(s)->s_jdev); kfree(s->s_fs_info); s->s_fs_info = NULL; } @@ -1927,7 +1928,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (!sbi->s_jdev) { SWARN(silent, s, "", "Cannot allocate memory for " "journal device name"); - goto error; + goto error_unlocked; } } #ifdef CONFIG_QUOTA @@ -2026,6 +2027,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (replay_only(s)) goto error_unlocked; + s->s_xattr = reiserfs_xattr_handlers; + if (bdev_read_only(s->s_bdev) && !(s->s_flags & MS_RDONLY)) { SWARN(silent, s, "clm-7000", "Detected readonly device, marking FS readonly"); @@ -2215,6 +2218,7 @@ error_unlocked: kfree(qf_names[j]); } #endif + kfree(sbi->s_jdev); kfree(sbi); s->s_fs_info = NULL; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 9e313fc7fdc7..07900105523f 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -121,13 +121,13 @@ static struct dentry *open_xa_root(struct super_block *sb, int flags) struct dentry *xaroot; if (d_really_is_negative(privroot)) - return ERR_PTR(-ENODATA); + return ERR_PTR(-EOPNOTSUPP); inode_lock_nested(d_inode(privroot), I_MUTEX_XATTR); xaroot = dget(REISERFS_SB(sb)->xattr_root); if (!xaroot) - xaroot = ERR_PTR(-ENODATA); + xaroot = ERR_PTR(-EOPNOTSUPP); else if (d_really_is_negative(xaroot)) { int err = -ENODATA; @@ -318,8 +318,12 @@ static int reiserfs_for_each_xattr(struct inode *inode, out_dir: dput(dir); out: - /* -ENODATA isn't an error */ - if (err == -ENODATA) + /* + * -ENODATA: this object doesn't have any xattrs + * -EOPNOTSUPP: this file system doesn't have xattrs enabled on disk. + * Neither are errors + */ + if (err == -ENODATA || err == -EOPNOTSUPP) err = 0; return err; } @@ -609,6 +613,10 @@ int reiserfs_xattr_set(struct inode *inode, const char *name, int error, error2; size_t jbegin_count = reiserfs_xattr_nblocks(inode, buffer_size); + /* Check before we start a transaction and then do nothing. */ + if (!d_really_is_positive(REISERFS_SB(inode->i_sb)->priv_root)) + return -EOPNOTSUPP; + if (!(flags & XATTR_REPLACE)) jbegin_count += reiserfs_xattr_jcreate_nblocks(inode); @@ -831,8 +839,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size) if (d_really_is_negative(dentry)) return -EINVAL; - if (!dentry->d_sb->s_xattr || - get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) + if (get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) return -EOPNOTSUPP; dir = open_xa_dir(d_inode(dentry), XATTR_REPLACE); @@ -872,6 +879,7 @@ static int create_privroot(struct dentry *dentry) } d_inode(dentry)->i_flags |= S_PRIVATE; + d_inode(dentry)->i_opflags &= ~IOP_XATTR; reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr " "storage.\n", PRIVROOT_NAME); @@ -885,7 +893,7 @@ static int create_privroot(struct dentry *dentry) { return 0; } #endif /* Actual operations that are exported to VFS-land */ -static const struct xattr_handler *reiserfs_xattr_handlers[] = { +const struct xattr_handler *reiserfs_xattr_handlers[] = { #ifdef CONFIG_REISERFS_FS_XATTR &reiserfs_xattr_user_handler, &reiserfs_xattr_trusted_handler, @@ -956,8 +964,10 @@ int reiserfs_lookup_privroot(struct super_block *s) if (!IS_ERR(dentry)) { REISERFS_SB(s)->priv_root = dentry; d_set_d_op(dentry, &xattr_lookup_poison_ops); - if (d_really_is_positive(dentry)) + if (d_really_is_positive(dentry)) { d_inode(dentry)->i_flags |= S_PRIVATE; + d_inode(dentry)->i_opflags &= ~IOP_XATTR; + } } else err = PTR_ERR(dentry); inode_unlock(d_inode(s->s_root)); @@ -986,7 +996,6 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) } if (d_really_is_positive(privroot)) { - s->s_xattr = reiserfs_xattr_handlers; inode_lock(d_inode(privroot)); if (!REISERFS_SB(s)->xattr_root) { struct dentry *dentry; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index d92a1dc6ee70..1f1fdfd3bc5c 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -316,10 +316,8 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th, * would be useless since permissions are ignored, and a pain because * it introduces locking cycles */ - if (IS_PRIVATE(dir)) { - inode->i_flags |= S_PRIVATE; + if (IS_PRIVATE(inode)) goto apply_umask; - } err = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (err) diff --git a/fs/splice.c b/fs/splice.c index 01983bea760c..8bfbc8a50164 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1585,7 +1585,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1659,7 +1663,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index b4fbeefba246..5ef0d1d60743 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -721,6 +721,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, int err, page_idx, page_cnt, ret = 0, n = 0; int allocate = bu->buf ? 0 : 1; loff_t isize; + gfp_t ra_gfp_mask = readahead_gfp_mask(mapping) & ~__GFP_FS; err = ubifs_tnc_get_bu_keys(c, bu); if (err) @@ -782,8 +783,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, if (page_offset > end_index) break; - page = find_or_create_page(mapping, page_offset, - GFP_NOFS | __GFP_COLD); + page = pagecache_get_page(mapping, page_offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT, + ra_gfp_mask); if (!page) break; if (!PageUptodate(page)) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index fd817022cb9b..9e66d85021fc 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -478,13 +478,15 @@ static struct buffer_head *udf_getblk(struct inode *inode, long block, return NULL; } -/* Extend the file by 'blocks' blocks, return the number of extents added */ +/* Extend the file with new blocks totaling 'new_block_bytes', + * return the number of extents added + */ static int udf_do_extend_file(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, - sector_t blocks) + loff_t new_block_bytes) { - sector_t add; + uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; struct kernel_lb_addr prealloc_loc = {}; @@ -494,7 +496,7 @@ static int udf_do_extend_file(struct inode *inode, /* The previous extent is fake and we should not extend by anything * - there's nothing to do... */ - if (!blocks && fake) + if (!new_block_bytes && fake) return 0; iinfo = UDF_I(inode); @@ -525,13 +527,12 @@ static int udf_do_extend_file(struct inode *inode, /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { - add = ((1 << 30) - sb->s_blocksize - - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) >> - sb->s_blocksize_bits; - if (add > blocks) - add = blocks; - blocks -= add; - last_ext->extLength += add << sb->s_blocksize_bits; + add = (1 << 30) - sb->s_blocksize - + (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); + if (add > new_block_bytes) + add = new_block_bytes; + new_block_bytes -= add; + last_ext->extLength += add; } if (fake) { @@ -552,28 +553,27 @@ static int udf_do_extend_file(struct inode *inode, } /* Managed to do everything necessary? */ - if (!blocks) + if (!new_block_bytes) goto out; /* All further extents will be NOT_RECORDED_NOT_ALLOCATED */ last_ext->extLocation.logicalBlockNum = 0; last_ext->extLocation.partitionReferenceNum = 0; - add = (1 << (30-sb->s_blocksize_bits)) - 1; - last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (add << sb->s_blocksize_bits); + add = (1 << 30) - sb->s_blocksize; + last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | add; /* Create enough extents to cover the whole hole */ - while (blocks > add) { - blocks -= add; + while (new_block_bytes > add) { + new_block_bytes -= add; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) return err; count++; } - if (blocks) { + if (new_block_bytes) { last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (blocks << sb->s_blocksize_bits); + new_block_bytes; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) @@ -604,6 +604,24 @@ out: return count; } +/* Extend the final block of the file to final_block_len bytes */ +static void udf_do_extend_final_block(struct inode *inode, + struct extent_position *last_pos, + struct kernel_long_ad *last_ext, + uint32_t final_block_len) +{ + struct super_block *sb = inode->i_sb; + uint32_t added_bytes; + + added_bytes = final_block_len - + (last_ext->extLength & (sb->s_blocksize - 1)); + last_ext->extLength += added_bytes; + UDF_I(inode)->i_lenExtents += added_bytes; + + udf_write_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); +} + static int udf_extend_file(struct inode *inode, loff_t newsize) { @@ -613,10 +631,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; + unsigned long partial_final_block; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; - int err; + int err = 0; + int within_final_block; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -626,18 +646,8 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) BUG(); etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); + within_final_block = (etype != -1); - /* File has extent covering the new size (could happen when extending - * inside a block)? */ - if (etype != -1) - return 0; - if (newsize & (sb->s_blocksize - 1)) - offset++; - /* Extended file just to the boundary of the last file block? */ - if (offset == 0) - return 0; - - /* Truncate is extending the file by 'offset' blocks */ if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { /* File has no extents at all or has empty last @@ -651,7 +661,22 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) &extent.extLength, 0); extent.extLength |= etype << 30; } - err = udf_do_extend_file(inode, &epos, &extent, offset); + + partial_final_block = newsize & (sb->s_blocksize - 1); + + /* File has extent covering the new size (could happen when extending + * inside a block)? + */ + if (within_final_block) { + /* Extending file within the last file block */ + udf_do_extend_final_block(inode, &epos, &extent, + partial_final_block); + } else { + loff_t add = ((loff_t)offset << sb->s_blocksize_bits) | + partial_final_block; + err = udf_do_extend_file(inode, &epos, &extent, add); + } + if (err < 0) goto out; err = 0; @@ -756,6 +781,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Are we beyond EOF? */ if (etype == -1) { int ret; + loff_t hole_len; isBeyondEOF = true; if (count) { if (c) @@ -771,7 +797,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, startnum = (offset > 0); } /* Create extents for the hole between EOF and offset */ - ret = udf_do_extend_file(inode, &prev_epos, laarr, offset); + hole_len = (loff_t)offset << inode->i_blkbits; + ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { brelse(prev_epos.bh); brelse(cur_epos.bh); diff --git a/fs/udf/super.c b/fs/udf/super.c index 03369a89600e..4abdba453885 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2460,17 +2460,29 @@ static unsigned int udf_count_free_table(struct super_block *sb, static unsigned int udf_count_free(struct super_block *sb) { unsigned int accum = 0; - struct udf_sb_info *sbi; + struct udf_sb_info *sbi = UDF_SB(sb); struct udf_part_map *map; + unsigned int part = sbi->s_partition; + int ptype = sbi->s_partmaps[part].s_partition_type; + + if (ptype == UDF_METADATA_MAP25) { + part = sbi->s_partmaps[part].s_type_specific.s_metadata. + s_phys_partition_ref; + } else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) { + /* + * Filesystems with VAT are append-only and we cannot write to + * them. Let's just report 0 here. + */ + return 0; + } - sbi = UDF_SB(sb); if (sbi->s_lvid_bh) { struct logicalVolIntegrityDesc *lvid = (struct logicalVolIntegrityDesc *) sbi->s_lvid_bh->b_data; - if (le32_to_cpu(lvid->numOfPartitions) > sbi->s_partition) { + if (le32_to_cpu(lvid->numOfPartitions) > part) { accum = le32_to_cpu( - lvid->freeSpaceTable[sbi->s_partition]); + lvid->freeSpaceTable[part]); if (accum == 0xFFFFFFFF) accum = 0; } @@ -2479,7 +2491,7 @@ static unsigned int udf_count_free(struct super_block *sb) if (accum) return accum; - map = &sbi->s_partmaps[sbi->s_partition]; + map = &sbi->s_partmaps[part]; if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) { accum += udf_count_free_bitmap(sb, map->s_uspace.s_bitmap); diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 398019fb1448..9c4fb1fc0822 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -228,7 +228,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_44BSD: return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid); case UFS_UID_EFT: - if (inode->ui_u1.oldids.ui_suid == 0xFFFF) + if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); /* Fall through */ default: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 784d667475ae..de63d4e2dfba 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -464,6 +464,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; + bool still_valid; ACCESS_ONCE(ctx->released) = true; @@ -479,6 +480,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + still_valid = mmget_still_valid(mm); prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -489,15 +491,17 @@ static int userfaultfd_release(struct inode *inode, struct file *file) continue; } new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); - prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, - new_flags, vma->anon_vma, - vma->vm_file, vma->vm_pgoff, - vma_policy(vma), - NULL_VM_UFFD_CTX); - if (prev) - vma = prev; - else - prev = vma; + if (still_valid) { + prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, + new_flags, vma->anon_vma, + vma->vm_file, vma->vm_pgoff, + vma_policy(vma), + NULL_VM_UFFD_CTX); + if (prev) + vma = prev; + else + prev = vma; + } vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } @@ -802,6 +806,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; + vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -947,6 +954,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; + vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 8ad65d43b65d..9ca8809ee3d0 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -4212,15 +4212,28 @@ xfs_bmapi_read( XFS_STATS_INC(mp, xs_blk_mapr); ifp = XFS_IFORK_PTR(ip, whichfork); + if (!ifp) { + /* No CoW fork? Return a hole. */ + if (whichfork == XFS_COW_FORK) { + mval->br_startoff = bno; + mval->br_startblock = HOLESTARTBLOCK; + mval->br_blockcount = len; + mval->br_state = XFS_EXT_NORM; + *nmap = 1; + return 0; + } - /* No CoW fork? Return a hole. */ - if (whichfork == XFS_COW_FORK && !ifp) { - mval->br_startoff = bno; - mval->br_startblock = HOLESTARTBLOCK; - mval->br_blockcount = len; - mval->br_state = XFS_EXT_NORM; - *nmap = 1; - return 0; + /* + * A missing attr ifork implies that the inode says we're in + * extents or btree format but failed to pass the inode fork + * verifier while trying to load it. Treat that as a file + * corruption too. + */ +#ifdef DEBUG + xfs_alert(mp, "%s: inode %llu missing fork %d", + __func__, ip->i_ino, whichfork); +#endif /* DEBUG */ + return -EFSCORRUPTED; } if (!(ifp->if_flags & XFS_IFEXTENTS)) { @@ -5675,7 +5688,7 @@ __xfs_bunmapi( * Make sure we don't touch multiple AGF headers out of order * in a single transaction, as that could cause AB-BA deadlocks. */ - if (!wasdel) { + if (!wasdel && !isrt) { agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); if (prev_agno != NULLAGNUMBER && prev_agno > agno) break; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 3f45d9867e10..0b58b9d419e8 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -57,6 +57,32 @@ static kmem_zone_t *xfs_buf_zone; #define xb_to_gfp(flags) \ ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) +/* + * Locking orders + * + * xfs_buf_ioacct_inc: + * xfs_buf_ioacct_dec: + * b_sema (caller holds) + * b_lock + * + * xfs_buf_stale: + * b_sema (caller holds) + * b_lock + * lru_lock + * + * xfs_buf_rele: + * b_lock + * pag_buf_lock + * lru_lock + * + * xfs_buftarg_wait_rele + * lru_lock + * b_lock (trylock due to inversion) + * + * xfs_buftarg_isolate + * lru_lock + * b_lock (trylock due to inversion) + */ static inline int xfs_buf_is_vmapped( @@ -957,8 +983,18 @@ xfs_buf_rele( ASSERT(atomic_read(&bp->b_hold) > 0); - release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); + /* + * We grab the b_lock here first to serialise racing xfs_buf_rele() + * calls. The pag_buf_lock being taken on the last reference only + * serialises against racing lookups in xfs_buf_find(). IOWs, the second + * to last reference we drop here is not serialised against the last + * reference until we take bp->b_lock. Hence if we don't grab b_lock + * first, the last "release" reference can win the race to the lock and + * free the buffer before the second-to-last reference is processed, + * leading to a use-after-free scenario. + */ spin_lock(&bp->b_lock); + release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock); if (!release) { /* * Drop the in-flight state if the buffer is already on the LRU @@ -1674,7 +1710,7 @@ xfs_buftarg_isolate( * zero. If the value is already zero, we need to reclaim the * buffer, otherwise it gets another trip through the LRU. */ - if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) { + if (atomic_add_unless(&bp->b_lru_ref, -1, 0)) { spin_unlock(&bp->b_lock); return LRU_ROTATE; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 321f57721b92..6b7ed221726d 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -251,6 +251,32 @@ xfs_compat_ioc_bulkstat( int done; int error; + /* + * Output structure handling functions. Depending on the command, + * either the xfs_bstat and xfs_inogrp structures are written out + * to userpace memory via bulkreq.ubuffer. Normally the compat + * functions and structure size are the correct ones to use ... + */ + inumbers_fmt_pf inumbers_func = xfs_inumbers_fmt_compat; + bulkstat_one_pf bs_one_func = xfs_bulkstat_one_compat; + size_t bs_one_size = sizeof(struct compat_xfs_bstat); + +#ifdef CONFIG_X86_X32 + if (in_x32_syscall()) { + /* + * ... but on x32 the input xfs_fsop_bulkreq has pointers + * which must be handled in the "compat" (32-bit) way, while + * the xfs_bstat and xfs_inogrp structures follow native 64- + * bit layout convention. So adjust accordingly, otherwise + * the data written out in compat layout will not match what + * x32 userspace expects. + */ + inumbers_func = xfs_inumbers_fmt; + bs_one_func = xfs_bulkstat_one; + bs_one_size = sizeof(struct xfs_bstat); + } +#endif + /* done = 1 if there are more stats to get and if bulkstat */ /* should be called again (unused here, but used in dmapi) */ @@ -282,15 +308,15 @@ xfs_compat_ioc_bulkstat( if (cmd == XFS_IOC_FSINUMBERS_32) { error = xfs_inumbers(mp, &inlast, &count, - bulkreq.ubuffer, xfs_inumbers_fmt_compat); + bulkreq.ubuffer, inumbers_func); } else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE_32) { int res; - error = xfs_bulkstat_one_compat(mp, inlast, bulkreq.ubuffer, - sizeof(compat_xfs_bstat_t), NULL, &res); + error = bs_one_func(mp, inlast, bulkreq.ubuffer, + bs_one_size, NULL, &res); } else if (cmd == XFS_IOC_FSBULKSTAT_32) { error = xfs_bulkstat(mp, &inlast, &count, - xfs_bulkstat_one_compat, sizeof(compat_xfs_bstat_t), + bs_one_func, bs_one_size, bulkreq.ubuffer, &done); } else error = -EINVAL; @@ -346,6 +372,7 @@ xfs_compat_attrlist_by_handle( { int error; attrlist_cursor_kern_t *cursor; + compat_xfs_fsop_attrlist_handlereq_t __user *p = arg; compat_xfs_fsop_attrlist_handlereq_t al_hreq; struct dentry *dentry; char *kbuf; @@ -380,6 +407,11 @@ xfs_compat_attrlist_by_handle( if (error) goto out_kfree; + if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) { + error = -EFAULT; + goto out_kfree; + } + if (copy_to_user(compat_ptr(al_hreq.buffer), kbuf, al_hreq.buflen)) error = -EFAULT; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 33c389934238..7bfddcd32d73 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -774,6 +774,7 @@ xfs_setattr_nonsize( out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(ip, XFS_ILOCK_EXCL); out_dqrele: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 33c9a3aae948..7bfcd09d446b 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1540,6 +1540,8 @@ out_free_iclog: if (iclog->ic_bp) xfs_buf_free(iclog->ic_bp); kmem_free(iclog); + if (prev_iclog == log->l_iclog) + break; } spinlock_destroy(&log->l_icloglock); xfs_buf_free(log->l_xbuf); diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index f82d79a8c694..a7c3da09b72f 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -214,6 +214,9 @@ xfs_fs_rm_xquota( if (XFS_IS_QUOTA_ON(mp)) return -EINVAL; + if (uflags & ~(FS_USER_QUOTA | FS_GROUP_QUOTA | FS_PROJ_QUOTA)) + return -EINVAL; + if (uflags & FS_USER_QUOTA) flags |= XFS_DQ_USER; if (uflags & FS_GROUP_QUOTA) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 802bcc326d9f..0d93d3c10fcc 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1222,13 +1222,11 @@ xfs_rtmount_inodes( xfs_sb_t *sbp; sbp = &mp->m_sb; - if (sbp->sb_rbmino == NULLFSINO) - return 0; error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip); if (error) return error; ASSERT(mp->m_rbmip != NULL); - ASSERT(sbp->sb_rsumino != NULLFSINO); + error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip); if (error) { IRELE(mp->m_rbmip); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 67d589e0a49f..b16ca13c11d5 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1674,6 +1674,7 @@ xfs_fs_fill_super( out_close_devices: xfs_close_devices(mp); out_free_fsname: + sb->s_fs_info = NULL; xfs_free_fsname(mp); kfree(mp); out: @@ -1691,6 +1692,10 @@ xfs_fs_put_super( { struct xfs_mount *mp = XFS_M(sb); + /* if ->fill_super failed, we have no mount to tear down */ + if (!sb->s_fs_info) + return; + xfs_notice(mp, "Unmounting Filesystem"); xfs_filestream_unmount(mp); xfs_unmountfs(mp); @@ -1700,6 +1705,8 @@ xfs_fs_put_super( xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); xfs_close_devices(mp); + + sb->s_fs_info = NULL; xfs_free_fsname(mp); kfree(mp); } @@ -1719,6 +1726,9 @@ xfs_fs_nr_cached_objects( struct super_block *sb, struct shrink_control *sc) { + /* Paranoia: catch incorrect calls during mount setup or teardown */ + if (WARN_ON_ONCE(!sb->s_fs_info)) + return 0; return xfs_reclaim_inodes_count(XFS_M(sb)); } |