From 4a7795d35e252f38298980530e01e21867f8f856 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Wed, 19 Nov 2014 15:50:34 +0800 Subject: vfs: fix reference leak in d_prune_aliases() In "d_prune_alias(): just lock the parent and call __dentry_kill()" the old dget + d_drop + dput has been replaced with lock_parent + __dentry_kill; unfortunately, dput() does more than just killing dentry - it also drops the reference to parent. New variant leaks that reference and needs dput(parent) after killing the child off. Signed-off-by: Yan, Zheng Signed-off-by: Al Viro --- fs/dcache.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/dcache.c b/fs/dcache.c index 3ffef7f4e5cd..5bc72b07fde2 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -778,6 +778,7 @@ restart: struct dentry *parent = lock_parent(dentry); if (likely(!dentry->d_lockref.count)) { __dentry_kill(dentry); + dput(parent); goto restart; } if (parent) -- cgit v1.2.3 From 7ca2f234404e738cc807ed87c43f9932513bc8c6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 19 Nov 2014 15:11:24 +0100 Subject: isofs: avoid unused function warning With the isofs_hash() function removed, isofs_hash_ms() is the only user of isofs_hash_common(), but it's defined inside of an #ifdef, which triggers this gcc warning in ARM axm55xx_defconfig starting with v3.18-rc3: fs/isofs/inode.c:177:1: warning: 'isofs_hash_common' defined but not used [-Wunused-function] This patch moves the function inside of the same #ifdef section to avoid that warning, which seems the best compromise of a relatively harmless patch for a late -rc. Signed-off-by: Arnd Bergmann Fixes: b0afd8e5db7b ("isofs: don't bother with ->d_op for normal case") Signed-off-by: Al Viro --- fs/isofs/inode.c | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'fs') diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index fe839b915116..d67a16f2a45d 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -170,27 +170,6 @@ struct iso9660_options{ s32 sbsector; }; -/* - * Compute the hash for the isofs name corresponding to the dentry. - */ -static int -isofs_hash_common(struct qstr *qstr, int ms) -{ - const char *name; - int len; - - len = qstr->len; - name = qstr->name; - if (ms) { - while (len && name[len-1] == '.') - len--; - } - - qstr->hash = full_name_hash(name, len); - - return 0; -} - /* * Compute the hash for the isofs name corresponding to the dentry. */ @@ -263,6 +242,27 @@ isofs_dentry_cmpi(const struct dentry *parent, const struct dentry *dentry, } #ifdef CONFIG_JOLIET +/* + * Compute the hash for the isofs name corresponding to the dentry. + */ +static int +isofs_hash_common(struct qstr *qstr, int ms) +{ + const char *name; + int len; + + len = qstr->len; + name = qstr->name; + if (ms) { + while (len && name[len-1] == '.') + len--; + } + + qstr->hash = full_name_hash(name, len); + + return 0; +} + static int isofs_hash_ms(const struct dentry *dentry, struct qstr *qstr) { -- cgit v1.2.3 From f82c458a2c3ffb94b431fc6ad791a79df1b3713e Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Wed, 19 Nov 2014 10:25:09 -0800 Subject: btrfs: fix lockups from btrfs_clear_path_blocking The fair reader/writer locks mean that btrfs_clear_path_blocking needs to strictly follow lock ordering rules even when we already have blocking locks on a given path. Before we can clear a blocking lock on the path, we need to make sure all of the locks have been converted to blocking. This will remove lock inversions against anyone spinning in write_lock() against the buffers we're trying to get read locks on. These inversions didn't exist before the fair read/writer locks, but now we need to be more careful. We papered over this deadlock in the past by changing btrfs_try_read_lock() to be a true trylock against both the spinlock and the blocking lock. This was slower, and not sufficient to fix all the deadlocks. This patch adds a btrfs_tree_read_lock_atomic(), which basically means get the spinlock but trylock on the blocking lock. Signed-off-by: Chris Mason Signed-off-by: Josef Bacik Reported-by: Patrick Schmid cc: stable@vger.kernel.org #v3.15+ --- fs/btrfs/ctree.c | 14 ++------------ fs/btrfs/locking.c | 24 +++++++++++++++++++++--- fs/btrfs/locking.h | 2 ++ 3 files changed, 25 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 19bc6162fb8e..150822ee0a0b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -80,13 +80,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, { int i; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - /* lockdep really cares that we take all of these spinlocks - * in the right order. If any of the locks in the path are not - * currently blocking, it is going to complain. So, make really - * really sure by forcing the path to blocking before we clear - * the path blocking. - */ if (held) { btrfs_set_lock_blocking_rw(held, held_rw); if (held_rw == BTRFS_WRITE_LOCK) @@ -95,7 +88,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, held_rw = BTRFS_READ_LOCK_BLOCKING; } btrfs_set_path_blocking(p); -#endif for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) { if (p->nodes[i] && p->locks[i]) { @@ -107,10 +99,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p, } } -#ifdef CONFIG_DEBUG_LOCK_ALLOC if (held) btrfs_clear_lock_blocking_rw(held, held_rw); -#endif } /* this also releases the path */ @@ -2893,7 +2883,7 @@ cow_done: } p->locks[level] = BTRFS_WRITE_LOCK; } else { - err = btrfs_try_tree_read_lock(b); + err = btrfs_tree_read_lock_atomic(b); if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); @@ -3025,7 +3015,7 @@ again: } level = btrfs_header_level(b); - err = btrfs_try_tree_read_lock(b); + err = btrfs_tree_read_lock_atomic(b); if (!err) { btrfs_set_path_blocking(p); btrfs_tree_read_lock(b); diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 5665d2149249..f8229ef1b46d 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -127,6 +127,26 @@ again: atomic_inc(&eb->spinning_readers); } +/* + * take a spinning read lock. + * returns 1 if we get the read lock and 0 if we don't + * this won't wait for blocking writers + */ +int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) +{ + if (atomic_read(&eb->blocking_writers)) + return 0; + + read_lock(&eb->lock); + if (atomic_read(&eb->blocking_writers)) { + read_unlock(&eb->lock); + return 0; + } + atomic_inc(&eb->read_locks); + atomic_inc(&eb->spinning_readers); + return 1; +} + /* * returns 1 if we get the read lock and 0 if we don't * this won't wait for blocking writers @@ -158,9 +178,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) atomic_read(&eb->blocking_readers)) return 0; - if (!write_trylock(&eb->lock)) - return 0; - + write_lock(&eb->lock); if (atomic_read(&eb->blocking_writers) || atomic_read(&eb->blocking_readers)) { write_unlock(&eb->lock); diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index b81e0e9a4894..c44a9d5f5362 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -35,6 +35,8 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw); void btrfs_assert_tree_locked(struct extent_buffer *eb); int btrfs_try_tree_read_lock(struct extent_buffer *eb); int btrfs_try_tree_write_lock(struct extent_buffer *eb); +int btrfs_tree_read_lock_atomic(struct extent_buffer *eb); + static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw) { -- cgit v1.2.3 From ef94b1864d1ed5be54376404bb23d22ed0481feb Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:39:59 +0100 Subject: ovl: rename filesystem type to "overlay" Some distributions carry an "old" format of overlayfs while mainline has a "new" format. The distros will possibly want to keep the old overlayfs alongside the new for compatibility reasons. To make it possible to differentiate the two versions change the name of the new one from "overlayfs" to "overlay". Signed-off-by: Miklos Szeredi Reported-by: Serge Hallyn Cc: Andy Whitcroft --- Documentation/filesystems/overlayfs.txt | 2 +- MAINTAINERS | 2 +- fs/Makefile | 2 +- fs/overlayfs/Kconfig | 2 +- fs/overlayfs/Makefile | 4 ++-- fs/overlayfs/super.c | 6 +++--- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 530850a72735..a27c950ece61 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -64,7 +64,7 @@ is formed. At mount time, the two directories given as mount options "lowerdir" and "upperdir" are combined into a merged directory: - mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper,\ + mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,\ workdir=/work /merged The "workdir" needs to be an empty directory on the same filesystem diff --git a/MAINTAINERS b/MAINTAINERS index c444907ccd69..af1e738e8772 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6888,7 +6888,7 @@ F: drivers/scsi/osd/ F: include/scsi/osd_* F: fs/exofs/ -OVERLAYFS FILESYSTEM +OVERLAY FILESYSTEM M: Miklos Szeredi L: linux-fsdevel@vger.kernel.org S: Supported diff --git a/fs/Makefile b/fs/Makefile index 34a1b9dea6dd..da0bbb456d3f 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -104,7 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ -obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/ +obj-$(CONFIG_OVERLAY_FS) += overlayfs/ obj-$(CONFIG_UDF_FS) += udf/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_OMFS_FS) += omfs/ diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index e60125976873..34355818a2e0 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -1,4 +1,4 @@ -config OVERLAYFS_FS +config OVERLAY_FS tristate "Overlay filesystem support" help An overlay filesystem combines two filesystems - an 'upper' filesystem diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile index 8f91889480d0..900daed3e91d 100644 --- a/fs/overlayfs/Makefile +++ b/fs/overlayfs/Makefile @@ -2,6 +2,6 @@ # Makefile for the overlay filesystem. # -obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o +obj-$(CONFIG_OVERLAY_FS) += overlay.o -overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o +overlay-objs := super.o inode.o dir.o readdir.o copy_up.o diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 08b704cebfc4..b92bd1829cf7 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -24,7 +24,7 @@ MODULE_AUTHOR("Miklos Szeredi "); MODULE_DESCRIPTION("Overlay filesystem"); MODULE_LICENSE("GPL"); -#define OVERLAYFS_SUPER_MAGIC 0x794c764f +#define OVERLAYFS_SUPER_MAGIC 0x794c7630 struct ovl_config { char *lowerdir; @@ -776,11 +776,11 @@ static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags, static struct file_system_type ovl_fs_type = { .owner = THIS_MODULE, - .name = "overlayfs", + .name = "overlay", .mount = ovl_mount, .kill_sb = kill_anon_super, }; -MODULE_ALIAS_FS("overlayfs"); +MODULE_ALIAS_FS("overlay"); static int __init ovl_init(void) { -- cgit v1.2.3 From a105d685a8483985a01776411de191a726b48132 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:39:59 +0100 Subject: ovl: fix remove/copy-up race ovl_remove_and_whiteout() needs to check if upper dentry exists or not after having locked upper parent directory. Previously we used a "type" value computed before locking the upper parent directory, which is susceptible to racing with copy-up. There's a similar check in ovl_check_empty_and_clear(). This one is not actually racy, since copy-up doesn't change the "emptyness" property of a directory. Add a comment to this effect, and check the existence of upper dentry locally to make the code cleaner. Signed-off-by: Miklos Szeredi --- fs/overlayfs/dir.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 15cd91ad9940..8ffc4b980f1b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -284,8 +284,7 @@ out: return ERR_PTR(err); } -static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry, - enum ovl_path_type type) +static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry) { int err; struct dentry *ret = NULL; @@ -294,8 +293,17 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry, err = ovl_check_empty_dir(dentry, &list); if (err) ret = ERR_PTR(err); - else if (type == OVL_PATH_MERGE) - ret = ovl_clear_empty(dentry, &list); + else { + /* + * If no upperdentry then skip clearing whiteouts. + * + * Can race with copy-up, since we don't hold the upperdir + * mutex. Doesn't matter, since copy-up can't create a + * non-empty directory from an empty one. + */ + if (ovl_dentry_upper(dentry)) + ret = ovl_clear_empty(dentry, &list); + } ovl_cache_free(&list); @@ -487,8 +495,7 @@ out: return err; } -static int ovl_remove_and_whiteout(struct dentry *dentry, - enum ovl_path_type type, bool is_dir) +static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) { struct dentry *workdir = ovl_workdir(dentry); struct inode *wdir = workdir->d_inode; @@ -500,7 +507,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, int err; if (is_dir) { - opaquedir = ovl_check_empty_and_clear(dentry, type); + opaquedir = ovl_check_empty_and_clear(dentry); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) goto out; @@ -515,9 +522,10 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, if (IS_ERR(whiteout)) goto out_unlock; - if (type == OVL_PATH_LOWER) { + upper = ovl_dentry_upper(dentry); + if (!upper) { upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); + dentry->d_name.len); err = PTR_ERR(upper); if (IS_ERR(upper)) goto kill_whiteout; @@ -529,7 +537,6 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, } else { int flags = 0; - upper = ovl_dentry_upper(dentry); if (opaquedir) upper = opaquedir; err = -ESTALE; @@ -648,7 +655,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) cap_raise(override_cred->cap_effective, CAP_CHOWN); old_cred = override_creds(override_cred); - err = ovl_remove_and_whiteout(dentry, type, is_dir); + err = ovl_remove_and_whiteout(dentry, is_dir); revert_creds(old_cred); put_cred(override_cred); @@ -781,7 +788,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, } if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) { - opaquedir = ovl_check_empty_and_clear(new, new_type); + opaquedir = ovl_check_empty_and_clear(new); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) { opaquedir = NULL; -- cgit v1.2.3 From 521484639ec19a6f1ed56de6993feb255f5f676c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:40:00 +0100 Subject: ovl: fix race in private xattr checks Xattr operations can race with copy up. This does not matter as long as we consistently fiter out "trunsted.overlay.opaque" attribute on upper directories. Previously we checked parent against OVL_PATH_MERGE. This is too general, and prone to race with copy-up. I.e. we found the parent to be on the lower layer but ovl_dentry_real() would return the copied-up dentry, possibly with the "opaque" attribute. So instead use ovl_path_real() and decide to filter the attributes based on the actual type of the dentry we'll use. Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index af2d18c9fcee..07d74b24913b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -235,26 +235,36 @@ out: return err; } +static bool ovl_need_xattr_filter(struct dentry *dentry, + enum ovl_path_type type) +{ + return type == OVL_PATH_UPPER && S_ISDIR(dentry->d_inode->i_mode); +} + ssize_t ovl_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { - if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && - ovl_is_private_xattr(name)) + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); + + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) return -ENODATA; - return vfs_getxattr(ovl_dentry_real(dentry), name, value, size); + return vfs_getxattr(realpath.dentry, name, value, size); } ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) { + struct path realpath; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); ssize_t res; int off; - res = vfs_listxattr(ovl_dentry_real(dentry), list, size); + res = vfs_listxattr(realpath.dentry, list, size); if (res <= 0 || size == 0) return res; - if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE) + if (!ovl_need_xattr_filter(dentry, type)) return res; /* filter out private xattrs */ @@ -279,17 +289,16 @@ int ovl_removexattr(struct dentry *dentry, const char *name) { int err; struct path realpath; - enum ovl_path_type type; + enum ovl_path_type type = ovl_path_real(dentry, &realpath); err = ovl_want_write(dentry); if (err) goto out; - if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && - ovl_is_private_xattr(name)) + err = -ENODATA; + if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) goto out_drop_write; - type = ovl_path_real(dentry, &realpath); if (type == OVL_PATH_LOWER) { err = vfs_getxattr(realpath.dentry, name, NULL, 0); if (err < 0) -- cgit v1.2.3 From 91c77947133f7aef851b625701e182d3f99d14a9 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:40:00 +0100 Subject: ovl: allow filenames with comma Allow option separator (comma) to be escaped with backslash. Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 48 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 45 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index b92bd1829cf7..eee7a62e1c0e 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -462,11 +462,34 @@ static const match_table_t ovl_tokens = { {OPT_ERR, NULL} }; +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; - while ((p = strsep(&opt, ",")) != NULL) { + while ((p = ovl_next_opt(&opt)) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -554,15 +577,34 @@ out_dput: goto out_unlock; } +static void ovl_unescape(char *s) +{ + char *d = s; + + for (;; s++, d++) { + if (*s == '\\') + s++; + *d = *s; + if (!*s) + break; + } +} + static int ovl_mount_dir(const char *name, struct path *path) { int err; + char *tmp = kstrdup(name, GFP_KERNEL); + + if (!tmp) + return -ENOMEM; - err = kern_path(name, LOOKUP_FOLLOW, path); + ovl_unescape(tmp); + err = kern_path(tmp, LOOKUP_FOLLOW, path); if (err) { - pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + pr_err("overlayfs: failed to resolve '%s': %i\n", tmp, err); err = -EINVAL; } + kfree(tmp); return err; } -- cgit v1.2.3 From 71d509280f7e92eb60ae6b7c78c20afafff060c7 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:40:01 +0100 Subject: ovl: use lockless_dereference() for upperdentry Don't open code lockless_dereference() in ovl_upperdentry_dereference(). Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index eee7a62e1c0e..f16d318b71f8 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -84,12 +84,7 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) { - struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry); - /* - * Make sure to order reads to upperdentry wrt ovl_dentry_update() - */ - smp_read_barrier_depends(); - return upperdentry; + return lockless_dereference(oe->__upperdentry); } void ovl_path_upper(struct dentry *dentry, struct path *path) -- cgit v1.2.3 From c9f00fdb9ab3999cb2fb582ad82a5db9e70c82f5 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:40:01 +0100 Subject: ovl: pass dentry into ovl_dir_read_merged() Pass dentry into ovl_dir_read_merged() insted of upperpath and lowerpath. This cleans up callers and paves the way for multi-layer directory reads. Signed-off-by: Miklos Szeredi --- fs/overlayfs/readdir.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 2a7ef4f8e2a6..7299e962f334 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -274,11 +274,11 @@ static int ovl_dir_mark_whiteouts(struct dentry *dir, return 0; } -static inline int ovl_dir_read_merged(struct path *upperpath, - struct path *lowerpath, - struct list_head *list) +static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) { int err; + struct path lowerpath; + struct path upperpath; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_merge, .list = list, @@ -286,25 +286,28 @@ static inline int ovl_dir_read_merged(struct path *upperpath, .is_merge = false, }; - if (upperpath->dentry) { - err = ovl_dir_read(upperpath, &rdd); + ovl_path_lower(dentry, &lowerpath); + ovl_path_upper(dentry, &upperpath); + + if (upperpath.dentry) { + err = ovl_dir_read(&upperpath, &rdd); if (err) goto out; - if (lowerpath->dentry) { - err = ovl_dir_mark_whiteouts(upperpath->dentry, &rdd); + if (lowerpath.dentry) { + err = ovl_dir_mark_whiteouts(upperpath.dentry, &rdd); if (err) goto out; } } - if (lowerpath->dentry) { + if (lowerpath.dentry) { /* * Insert lowerpath entries before upperpath ones, this allows * offsets to be reasonably constant */ list_add(&rdd.middle, rdd.list); rdd.is_merge = true; - err = ovl_dir_read(lowerpath, &rdd); + err = ovl_dir_read(&lowerpath, &rdd); list_del(&rdd.middle); } out: @@ -329,8 +332,6 @@ static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) { int res; - struct path lowerpath; - struct path upperpath; struct ovl_dir_cache *cache; cache = ovl_dir_cache(dentry); @@ -347,10 +348,7 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) cache->refcount = 1; INIT_LIST_HEAD(&cache->entries); - ovl_path_lower(dentry, &lowerpath); - ovl_path_upper(dentry, &upperpath); - - res = ovl_dir_read_merged(&upperpath, &lowerpath, &cache->entries); + res = ovl_dir_read_merged(dentry, &cache->entries); if (res) { ovl_cache_free(&cache->entries); kfree(cache); @@ -538,14 +536,9 @@ const struct file_operations ovl_dir_operations = { int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) { int err; - struct path lowerpath; - struct path upperpath; struct ovl_cache_entry *p; - ovl_path_upper(dentry, &upperpath); - ovl_path_lower(dentry, &lowerpath); - - err = ovl_dir_read_merged(&upperpath, &lowerpath, list); + err = ovl_dir_read_merged(dentry, list); if (err) return err; -- cgit v1.2.3 From 7676895f4736421ebafc48de5078e25ea69e88ee Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Nov 2014 16:40:02 +0100 Subject: ovl: ovl_dir_fsync() cleanup Check against !OVL_PATH_LOWER instead of OVL_PATH_MERGE. For a copied up directory the two are currently equivalent. Signed-off-by: Miklos Szeredi --- fs/overlayfs/readdir.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 7299e962f334..ab1e3dcbed95 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -450,10 +450,10 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, /* * Need to check if we started out being a lower dir, but got copied up */ - if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) { + if (!od->is_upper && ovl_path_type(dentry) != OVL_PATH_LOWER) { struct inode *inode = file_inode(file); - realfile =lockless_dereference(od->upperfile); + realfile = lockless_dereference(od->upperfile); if (!realfile) { struct path upperpath; -- cgit v1.2.3 From c1b69b1ca1f5a8669034348cee9e495fde99bf69 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 23 Oct 2014 17:56:11 +0200 Subject: nfs: Remove dead case from nfs4_map_errors() NFS4ERR_ACCESS has number 13 and thus is matched and returned immediately at the beginning of nfs4_map_errors() and there's no point in checking it later. Coverity-id: 733891 Signed-off-by: Jan Kara Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 69dc20a743f9..15d5eb52cde8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -158,8 +158,6 @@ static int nfs4_map_errors(int err) return -EACCES; case -NFS4ERR_MINOR_VERS_MISMATCH: return -EPROTONOSUPPORT; - case -NFS4ERR_ACCESS: - return -EACCES; case -NFS4ERR_FILE_OPEN: return -EBUSY; default: -- cgit v1.2.3 From 878ffa9f855e84d35d950f1abeb5a37b8435baea Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 23 Oct 2014 14:00:54 -0400 Subject: NFS: Use nfs_server_capable() for checknig NFS_CAP_SEEK This should make the code easier to maintain in the future. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 0886f1db5917..056f5aafecc1 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -50,7 +50,7 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) struct nfs_server *server = NFS_SERVER(inode); int status; - if (!(server->caps & NFS_CAP_SEEK)) + if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); -- cgit v1.2.3 From 6a74c0c9402b85647793da70edc9d6b097d54472 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Nov 2014 16:47:02 -0500 Subject: pnfs/blocklayout: fix end calculation in pnfs_num_cont_bytes Use the number of pages in the pagecache mapping instead of the number of pnfs requests which is only slightly related. Reported-by: Weston Andros Adamson Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 4f46f7a05289..77fec6a55f57 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -812,7 +812,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) /* Optimize common case that writes from 0 to end of file */ end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); - if (end != NFS_I(inode)->npages) { + if (end != inode->i_mapping->nrpages) { rcu_read_lock(); end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); -- cgit v1.2.3 From cb1410c71e0b6b2eba8c1890645a76ff86169d24 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 12 Nov 2014 12:08:00 -0500 Subject: NFS: fix subtle change in COMMIT behavior Recent work in the pgio layer made it possible for there to be more than one request per page. This caused a subtle change in commit behavior, because write.c:nfs_commit_unstable_pages compares the number of *pages* waiting for writeback against the number of requests on a commit list to choose when to send a COMMIT in a non-blocking flush. This is probably hard to hit in normal operation - you have to be using rsize/wsize < PAGE_SIZE, or pnfs with lots of boundaries that are not page aligned to have a noticeable change in behavior. Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 2 +- fs/nfs/inode.c | 8 ++++---- fs/nfs/pagelist.c | 11 ++++++++--- fs/nfs/write.c | 17 ++++++++++++----- include/linux/nfs_fs.h | 4 ++-- 5 files changed, 27 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 73466b934090..e36a9d78ea49 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -49,7 +49,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, goto out_iput; res->size = i_size_read(inode); res->change_attr = delegation->change_attr; - if (nfsi->npages != 0) + if (nfsi->nrequests != 0) res->change_attr++; res->ctime = inode->i_ctime; res->mtime = inode->i_mtime; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 00689a8a85e4..2b48ce58a584 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1149,7 +1149,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) - && nfsi->npages == 0) { + && nfsi->nrequests == 0) { i_size_write(inode, nfs_size_to_loff_t(fattr->size)); ret |= NFS_INO_INVALID_ATTR; } @@ -1192,7 +1192,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); - if (cur_size != new_isize && nfsi->npages == 0) + if (cur_size != new_isize && nfsi->nrequests == 0) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; } @@ -1619,7 +1619,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if ((nfsi->npages == 0) || new_isize > cur_isize) { + if ((nfsi->nrequests == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; invalid &= ~NFS_INO_REVAL_PAGECACHE; @@ -1784,7 +1784,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); INIT_LIST_HEAD(&nfsi->commit_info.list); - nfsi->npages = 0; + nfsi->nrequests = 0; nfsi->commit_info.ncommit = 0; atomic_set(&nfsi->commit_info.rpcs_out, 0); atomic_set(&nfsi->silly_count, 1); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ed0db61f8543..2b5e769beb16 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -258,6 +258,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit) static inline void nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) { + struct inode *inode; WARN_ON_ONCE(prev == req); if (!prev) { @@ -276,12 +277,16 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) * nfs_page_group_destroy is called */ kref_get(&req->wb_head->wb_kref); - /* grab extra ref if head request has extra ref from - * the write/commit path to handle handoff between write - * and commit lists */ + /* grab extra ref and bump the request count if head request + * has extra ref from the write/commit path to handle handoff + * between write and commit lists. */ if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { + inode = page_file_mapping(req->wb_page)->host; set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); + spin_lock(&inode->i_lock); + NFS_I(inode)->nrequests++; + spin_unlock(&inode->i_lock); } } } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f83b02dc9166..d489ff3f438f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -670,7 +670,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) nfs_lock_request(req); spin_lock(&inode->i_lock); - if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) + if (!nfsi->nrequests && + NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) inode->i_version++; /* * Swap-space should not get truncated. Hence no need to plug the race @@ -681,9 +682,11 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) SetPagePrivate(req->wb_page); set_page_private(req->wb_page, (unsigned long)req); } - nfsi->npages++; + nfsi->nrequests++; /* this a head request for a page group - mark it as having an - * extra reference so sub groups can follow suit */ + * extra reference so sub groups can follow suit. + * This flag also informs pgio layer when to bump nrequests when + * adding subrequests. */ WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); @@ -709,7 +712,11 @@ static void nfs_inode_remove_request(struct nfs_page *req) wake_up_page(head->wb_page, PG_private); clear_bit(PG_MAPPED, &head->wb_flags); } - nfsi->npages--; + nfsi->nrequests--; + spin_unlock(&inode->i_lock); + } else { + spin_lock(&inode->i_lock); + nfsi->nrequests--; spin_unlock(&inode->i_lock); } @@ -1735,7 +1742,7 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1)) + if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1)) goto out_mark_dirty; /* don't wait for the COMMIT response */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c72d1ad41ad4..6d627b92df53 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -163,7 +163,7 @@ struct nfs_inode { */ __be32 cookieverf[2]; - unsigned long npages; + unsigned long nrequests; struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ @@ -520,7 +520,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data); static inline int nfs_have_writebacks(struct inode *inode) { - return NFS_I(inode)->npages != 0; + return NFS_I(inode)->nrequests != 0; } /* -- cgit v1.2.3 From 4bd5a980de87d2b5af417485bde97b8eb3d6cf6a Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 11:05:17 +0800 Subject: nfs41: fix nfs4_proc_layoutget error handling nfs4_layoutget_release() drops layout hdr refcnt. Grab the refcnt early so that it is safe to call .release in case nfs4_alloc_pages fails. Signed-off-by: Peng Tao Fixes: a47970ff78147 ("NFSv4.1: Hold reference to layout hdr in layoutget") Cc: stable@vger.kernel.org # 3.9+ Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 15d5eb52cde8..3138913d1cdf 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7702,6 +7702,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) dprintk("--> %s\n", __func__); + /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ + pnfs_get_layout_hdr(NFS_I(inode)->layout); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); @@ -7714,9 +7717,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->res.seq_res.sr_slot = NULL; nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); - /* nfs4_layoutget_release calls pnfs_put_layout_hdr */ - pnfs_get_layout_hdr(NFS_I(inode)->layout); - task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return ERR_CAST(task); -- cgit v1.2.3 From 10b89567db51e143c2f0828839332502916d012d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 17 Nov 2014 16:58:03 -0500 Subject: lockd: eliminate LOCKD_DEBUG LOCKD_DEBUG is always the same value as CONFIG_SUNRPC_DEBUG, so we can just use it instead. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- fs/lockd/svclock.c | 2 +- include/linux/lockd/debug.h | 6 +----- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 13db95f54176..56598742dde4 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -53,7 +53,7 @@ static const struct rpc_call_ops nlmsvc_grant_ops; static LIST_HEAD(nlm_blocked); static DEFINE_SPINLOCK(nlm_blocked_lock); -#ifdef LOCKD_DEBUG +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie) { /* diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h index 257d3779f2ab..0ca8109934e4 100644 --- a/include/linux/lockd/debug.h +++ b/include/linux/lockd/debug.h @@ -17,12 +17,8 @@ * Enable lockd debugging. * Requires RPC_DEBUG. */ -#ifdef RPC_DEBUG -# define LOCKD_DEBUG 1 -#endif - #undef ifdebug -#if defined(RPC_DEBUG) && defined(LOCKD_DEBUG) +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define ifdebug(flag) if (unlikely(nlm_debug & NLMDBG_##flag)) #else # define ifdebug(flag) if (0) -- cgit v1.2.3 From fe0bf1185ddf7e9d193cfe397ed1414d91526e19 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Tue, 18 Nov 2014 13:23:43 +0100 Subject: NFS: Deletion of unnecessary checks before the function call "nfs_put_client" The nfs_put_client() function tests whether its argument is NULL and then returns immediately. Thus the test around the call is not needed. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Signed-off-by: Trond Myklebust --- fs/nfs/filelayout/filelayoutdev.c | 3 +-- fs/nfs/nfs4client.c | 15 +++++---------- 2 files changed, 6 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 9bb806a76d99..bfecac781f19 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -204,8 +204,7 @@ destroy_ds(struct nfs4_pnfs_ds *ds) ifdebug(FACILITY) print_ds(ds); - if (ds->ds_clp) - nfs_put_client(ds->ds_clp); + nfs_put_client(ds->ds_clp); while (!list_empty(&ds->ds_addrs)) { da = list_first_entry(&ds->ds_addrs, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ffdb28d86cf8..5f07a0ed9188 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -498,8 +498,7 @@ int nfs40_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs_wait_client_init_complete(pos); @@ -517,8 +516,7 @@ int nfs40_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs4_proc_setclientid_confirm(pos, &clid, cred); @@ -549,8 +547,7 @@ int nfs40_walk_client_list(struct nfs_client *new, /* No match found. The server lost our clientid */ out: - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); dprintk("NFS: <-- %s status = %d\n", __func__, status); return status; } @@ -641,8 +638,7 @@ int nfs41_walk_client_list(struct nfs_client *new, atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); prev = pos; status = nfs_wait_client_init_complete(pos); @@ -675,8 +671,7 @@ int nfs41_walk_client_list(struct nfs_client *new, /* No matching nfs_client found. */ spin_unlock(&nn->nfs_client_lock); dprintk("NFS: <-- %s status = %d\n", __func__, status); - if (prev) - nfs_put_client(prev); + nfs_put_client(prev); return status; } #endif /* CONFIG_NFS_V4_1 */ -- cgit v1.2.3 From 5a254d08b086d80cbead2ebcee6d2a4b3a15587a Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Sun, 23 Nov 2014 12:47:17 +0800 Subject: nfs: replace nfs_add_stats with nfs_inc_stats when add one Signed-off-by: Li RongQing Signed-off-by: Trond Myklebust --- fs/nfs/read.c | 2 +- fs/nfs/write.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/nfs/read.c b/fs/nfs/read.c index beff2769c5c5..c91a4799c562 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -269,7 +269,7 @@ int nfs_readpage(struct file *file, struct page *page) dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", page, PAGE_CACHE_SIZE, page_file_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); - nfs_add_stats(inode, NFSIOS_READPAGES, 1); + nfs_inc_stats(inode, NFSIOS_READPAGES); /* * Try to flush any pending writes to the file.. diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d489ff3f438f..af3af685a9e3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -575,7 +575,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st int ret; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); + nfs_inc_stats(inode, NFSIOS_WRITEPAGES); nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); -- cgit v1.2.3 From e9f456ca50e579dfacd996f50637f0bb0a585dfc Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Sun, 23 Nov 2014 12:47:41 +0800 Subject: nfs: define nfs_inc_fscache_stats and using it as possible Define and use nfs_inc_fscache_stats when plus one, which can save to pass one parameter. Signed-off-by: Li RongQing Signed-off-by: Trond Myklebust --- fs/nfs/fscache.c | 24 ++++++++++++------------ fs/nfs/iostat.h | 5 +++++ 2 files changed, 17 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 3ef01f0ba0bc..d63bea8bbfbb 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -269,8 +269,8 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp) if (!fscache_maybe_release_page(cookie, page, gfp)) return 0; - nfs_add_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); } return 1; @@ -293,8 +293,8 @@ void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) BUG_ON(!PageLocked(page)); fscache_uncache_page(cookie, page); - nfs_add_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); } /* @@ -343,19 +343,19 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, case 0: /* read BIO submitted (page in fscache) */ dfprintk(FSCACHE, "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); return ret; case -ENOBUFS: /* inode not in cache */ case -ENODATA: /* page not in cache */ - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); return 1; default: dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); } return ret; } @@ -429,11 +429,11 @@ void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) if (ret != 0) { fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_add_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1); - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1); + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); } else { - nfs_add_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1); + nfs_inc_fscache_stats(inode, + NFSIOS_FSCACHE_PAGES_WRITTEN_OK); } } diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h index c5832487c456..0cb806fbd4c4 100644 --- a/fs/nfs/iostat.h +++ b/fs/nfs/iostat.h @@ -55,6 +55,11 @@ static inline void nfs_add_fscache_stats(struct inode *inode, { this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend); } +static inline void nfs_inc_fscache_stats(struct inode *inode, + enum nfs_stat_fscachecounters stat) +{ + this_cpu_inc(NFS_SERVER(inode)->io_stats->fscache[stat]); +} #endif static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void) -- cgit v1.2.3 From 6dd3436b9dc0df4b9ae7bb4e0076996a5ffda219 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 8 Nov 2014 20:15:18 -0500 Subject: NFS: SETCLIENTID XDR buffer sizes are incorrect Use the correct calculation of the maximum size of a clientaddr4 when encoding and decoding SETCLIENTID operations. clientaddr4 is defined in section 2.2.10 of RFC3530bis-31. The usage in encode_setclientid_maxsz is missing the 4-byte length in both strings, but is otherwise correct. decode_setclientid_maxsz simply asks for a page of receive buffer space, which is unnecessarily large (more than 4KB). Note that a SETCLIENTID reply is either clientid+verifier, or clientaddr4, depending on the returned NFS status. It doesn't hurt to allocate enough space for both. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- fs/nfs/nfs4xdr.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 206c08a60c7f..f8afa6783fb8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -141,13 +141,15 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ XDR_QUADLEN(NFS4_SETCLIENTID_NAMELEN) + \ 1 /* sc_prog */ + \ - XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ - XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN) + \ 1) /* sc_cb_ident */ #define decode_setclientid_maxsz \ (op_decode_hdr_maxsz + \ - 2 + \ - 1024) /* large value for CLID_INUSE */ + 2 /* clientid */ + \ + XDR_QUADLEN(NFS4_VERIFIER_SIZE) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN) + \ + 1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) #define encode_setclientid_confirm_maxsz \ (op_encode_hdr_maxsz + \ 3 + (NFS4_VERIFIER_SIZE >> 2)) -- cgit v1.2.3 From c2ef47b7f518f5eae5ffed11b8ac754fb263d398 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 8 Nov 2014 20:15:26 -0500 Subject: NFS: Clean up nfs4_init_callback() nfs4_init_callback() is never invoked for NFS versions other than 4. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- fs/nfs/nfs4client.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ffdb28d86cf8..5f4b818182f9 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -241,28 +241,25 @@ void nfs4_free_client(struct nfs_client *clp) */ static int nfs4_init_callback(struct nfs_client *clp) { + struct rpc_xprt *xprt; int error; - if (clp->rpc_ops->version == 4) { - struct rpc_xprt *xprt; + xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); - xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); - - if (nfs4_has_session(clp)) { - error = xprt_setup_backchannel(xprt, - NFS41_BC_MIN_CALLBACKS); - if (error < 0) - return error; - } - - error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); - if (error < 0) { - dprintk("%s: failed to start callback. Error = %d\n", - __func__, error); + if (nfs4_has_session(clp)) { + error = xprt_setup_backchannel(xprt, NFS41_BC_MIN_CALLBACKS); + if (error < 0) return error; - } - __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); } + + error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); + if (error < 0) { + dprintk("%s: failed to start callback. Error = %d\n", + __func__, error); + return error; + } + __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); + return 0; } -- cgit v1.2.3 From f4ac1674f5da420ef17896f0f222c5215ebcde80 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 25 Nov 2014 13:18:15 -0500 Subject: nfs: Add ALLOCATE support This patch adds support for using the NFS v4.2 operation ALLOCATE to preallocate data in a file. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 1 + fs/nfs/nfs42.h | 1 + fs/nfs/nfs42proc.c | 58 ++++++++++++++++++++++++++++++++++++ fs/nfs/nfs42xdr.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4file.c | 28 ++++++++++++++++++ fs/nfs/nfs4proc.c | 3 +- fs/nfs/nfs4xdr.c | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 14 +++++++++ 11 files changed, 183 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 2b48ce58a584..4bffe637ea32 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -192,6 +192,7 @@ void nfs_zap_caches(struct inode *inode) nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } +EXPORT_SYMBOL_GPL(nfs_zap_caches); void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index d10333a197bf..42656a9cf485 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -6,6 +6,7 @@ #define __LINUX_FS_NFS_NFS4_2_H /* nfs4.2proc.c */ +int nfs42_proc_allocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); /* nfs4.2xdr.h */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 056f5aafecc1..581f34e9d8a0 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -32,6 +32,64 @@ static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, return ret; } +static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + struct nfs42_falloc_args args = { + .falloc_fh = NFS_FH(inode), + .falloc_offset = offset, + .falloc_length = len, + }; + struct nfs42_falloc_res res; + struct nfs_server *server = NFS_SERVER(inode); + int status; + + msg->rpc_argp = &args; + msg->rpc_resp = &res; + + status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + if (status) + return status; + + return nfs4_call_sync(server->client, server, msg, + &args.seq_args, &res.seq_res, 0); +} + +static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, + loff_t offset, loff_t len) +{ + struct nfs_server *server = NFS_SERVER(file_inode(filep)); + struct nfs4_exception exception = { }; + int err; + + do { + err = _nfs42_proc_fallocate(msg, filep, offset, len); + if (err == -ENOTSUPP) + return -EOPNOTSUPP; + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; +} + +int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) + return -EOPNOTSUPP; + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE; + return err; +} + loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct inode *inode = file_inode(filep); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index c90469b604b8..4248d034479c 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -4,6 +4,12 @@ #ifndef __LINUX_FS_NFS_NFS4_2XDR_H #define __LINUX_FS_NFS_NFS4_2XDR_H +#define encode_fallocate_maxsz (encode_stateid_maxsz + \ + 2 /* offset */ + \ + 2 /* length */) +#define encode_allocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_allocate_maxsz (op_decode_hdr_maxsz) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ @@ -14,6 +20,12 @@ 2 /* offset */ + \ 2 /* length */) +#define NFS4_enc_allocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_allocate_maxsz) +#define NFS4_dec_allocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_allocate_maxsz) #define NFS4_enc_seek_sz (compound_encode_hdr_maxsz + \ encode_putfh_maxsz + \ encode_seek_maxsz) @@ -22,6 +34,22 @@ decode_seek_maxsz) +static void encode_fallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + encode_nfs4_stateid(xdr, &args->falloc_stateid); + encode_uint64(xdr, args->falloc_offset); + encode_uint64(xdr, args->falloc_length); +} + +static void encode_allocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + static void encode_seek(struct xdr_stream *xdr, struct nfs42_seek_args *args, struct compound_hdr *hdr) @@ -32,6 +60,24 @@ static void encode_seek(struct xdr_stream *xdr, encode_uint32(xdr, args->sa_what); } +/* + * Encode ALLOCATE request + */ +static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_allocate(xdr, args, &hdr); + encode_nops(&hdr); +} + /* * Encode SEEK request */ @@ -50,6 +96,11 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, encode_nops(&hdr); } +static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_ALLOCATE); +} + static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) { int status; @@ -72,6 +123,30 @@ out_overflow: return -EIO; } +/* + * Decode ALLOCATE request + */ +static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_allocate(xdr, res); +out: + return status; +} + /* * Decode SEEK request */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index be6cac37ea10..a08178764cf9 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -226,6 +226,7 @@ int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); /* nfs4proc.c */ +extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *, struct rpc_message *, struct nfs4_sequence_args *, struct nfs4_sequence_res *, int); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index c51fb4db9bfe..f78e9fd0735a 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -3,6 +3,8 @@ * * Copyright (C) 1992 Rick Sladkey */ +#include +#include #include #include "internal.h" #include "fscache.h" @@ -134,6 +136,29 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) return nfs_file_llseek(filep, offset, whence); } } + +static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + long ret; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + if (mode != 0) + return -EOPNOTSUPP; + + ret = inode_newsize_ok(inode, offset + len); + if (ret < 0) + return ret; + + mutex_lock(&inode->i_mutex); + ret = nfs42_proc_allocate(filep, offset, len); + mutex_unlock(&inode->i_mutex); + + nfs_zap_caches(inode); + return ret; +} #endif /* CONFIG_NFS_V4_2 */ const struct file_operations nfs4_file_operations = { @@ -155,6 +180,9 @@ const struct file_operations nfs4_file_operations = { .flock = nfs_flock, .splice_read = nfs_file_splice_read, .splice_write = iter_file_splice_write, +#ifdef CONFIG_NFS_V4_2 + .fallocate = nfs42_fallocate, +#endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, }; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3138913d1cdf..b1b403b0ca0d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -342,7 +342,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) /* This is the error handling routine for processes that are allowed * to sleep. */ -static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) { struct nfs_client *clp = server->nfs_client; struct nfs4_state *state = exception->state; @@ -8424,6 +8424,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 + | NFS_CAP_ALLOCATE | NFS_CAP_SEEK, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 206c08a60c7f..0a1484561e4b 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7394,6 +7394,7 @@ struct rpc_procinfo nfs4_procedures[] = { #endif /* CONFIG_NFS_V4_1 */ #ifdef CONFIG_NFS_V4_2 PROC(SEEK, enc_seek, dec_seek), + PROC(ALLOCATE, enc_allocate, dec_allocate), #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 356acc2846fd..2b28a21edcd0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -490,6 +490,7 @@ enum { /* nfs42 */ NFSPROC4_CLNT_SEEK, + NFSPROC4_CLNT_ALLOCATE, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a32ba0d7a98f..df6ed429b406 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -231,5 +231,6 @@ struct nfs_server { #define NFS_CAP_ATOMIC_OPEN_V1 (1U << 17) #define NFS_CAP_SECURITY_LABEL (1U << 18) #define NFS_CAP_SEEK (1U << 19) +#define NFS_CAP_ALLOCATE (1U << 20) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 47ebb4fafd87..467c84efb596 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1243,6 +1243,20 @@ nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo) #endif /* CONFIG_NFS_V4_1 */ #ifdef CONFIG_NFS_V4_2 +struct nfs42_falloc_args { + struct nfs4_sequence_args seq_args; + + struct nfs_fh *falloc_fh; + nfs4_stateid falloc_stateid; + u64 falloc_offset; + u64 falloc_length; +}; + +struct nfs42_falloc_res { + struct nfs4_sequence_res seq_res; + unsigned int status; +}; + struct nfs42_seek_args { struct nfs4_sequence_args seq_args; -- cgit v1.2.3 From 624bd5b7b683c978c6d5f4e9f6142cfb3470983d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 25 Nov 2014 13:18:16 -0500 Subject: nfs: Add DEALLOCATE support This patch adds support for using the NFS v4.2 operation DEALLOCATE to punch holes in a file. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs42.h | 1 + fs/nfs/nfs42proc.c | 17 +++++++++++++ fs/nfs/nfs42xdr.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4file.c | 7 ++++-- fs/nfs/nfs4proc.c | 1 + fs/nfs/nfs4xdr.c | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_fs_sb.h | 1 + 8 files changed, 91 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 42656a9cf485..7afb8947dfdf 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -7,6 +7,7 @@ /* nfs4.2proc.c */ int nfs42_proc_allocate(struct file *, loff_t, loff_t); +int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); /* nfs4.2xdr.h */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 581f34e9d8a0..cb170722769c 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -90,6 +90,23 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) return err; } +int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DEALLOCATE], + }; + struct inode *inode = file_inode(filep); + int err; + + if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) + return -EOPNOTSUPP; + + err = nfs42_proc_fallocate(&msg, filep, offset, len); + if (err == -EOPNOTSUPP) + NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE; + return err; +} + loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct inode *inode = file_inode(filep); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 4248d034479c..038a7e1521fa 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -10,6 +10,9 @@ #define encode_allocate_maxsz (op_encode_hdr_maxsz + \ encode_fallocate_maxsz) #define decode_allocate_maxsz (op_decode_hdr_maxsz) +#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \ + encode_fallocate_maxsz) +#define decode_deallocate_maxsz (op_decode_hdr_maxsz) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ @@ -26,6 +29,12 @@ #define NFS4_dec_allocate_sz (compound_decode_hdr_maxsz + \ decode_putfh_maxsz + \ decode_allocate_maxsz) +#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_deallocate_maxsz) +#define NFS4_dec_deallocate_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_deallocate_maxsz) #define NFS4_enc_seek_sz (compound_encode_hdr_maxsz + \ encode_putfh_maxsz + \ encode_seek_maxsz) @@ -50,6 +59,14 @@ static void encode_allocate(struct xdr_stream *xdr, encode_fallocate(xdr, args); } +static void encode_deallocate(struct xdr_stream *xdr, + struct nfs42_falloc_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); + encode_fallocate(xdr, args); +} + static void encode_seek(struct xdr_stream *xdr, struct nfs42_seek_args *args, struct compound_hdr *hdr) @@ -78,6 +95,24 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode DEALLOCATE request + */ +static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs42_falloc_args *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->falloc_fh, &hdr); + encode_deallocate(xdr, args, &hdr); + encode_nops(&hdr); +} + /* * Encode SEEK request */ @@ -101,6 +136,11 @@ static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) return decode_op_hdr(xdr, OP_ALLOCATE); } +static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) +{ + return decode_op_hdr(xdr, OP_DEALLOCATE); +} + static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res) { int status; @@ -147,6 +187,30 @@ out: return status; } +/* + * Decode DEALLOCATE request + */ +static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs42_falloc_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_deallocate(xdr, res); +out: + return status; +} + /* * Decode SEEK request */ diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index f78e9fd0735a..8b46389c4c5b 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -145,7 +145,7 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - if (mode != 0) + if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE))) return -EOPNOTSUPP; ret = inode_newsize_ok(inode, offset + len); @@ -153,7 +153,10 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return ret; mutex_lock(&inode->i_mutex); - ret = nfs42_proc_allocate(filep, offset, len); + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = nfs42_proc_deallocate(filep, offset, len); + else + ret = nfs42_proc_allocate(filep, offset, len); mutex_unlock(&inode->i_mutex); nfs_zap_caches(inode); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b1b403b0ca0d..e7f8d5ff2581 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8425,6 +8425,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 | NFS_CAP_ALLOCATE + | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0a1484561e4b..03d0fa62a06e 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7395,6 +7395,7 @@ struct rpc_procinfo nfs4_procedures[] = { #ifdef CONFIG_NFS_V4_2 PROC(SEEK, enc_seek, dec_seek), PROC(ALLOCATE, enc_allocate, dec_allocate), + PROC(DEALLOCATE, enc_deallocate, dec_deallocate), #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 2b28a21edcd0..022b761dbf0a 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -491,6 +491,7 @@ enum { /* nfs42 */ NFSPROC4_CLNT_SEEK, NFSPROC4_CLNT_ALLOCATE, + NFSPROC4_CLNT_DEALLOCATE, }; /* nfs41 types */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index df6ed429b406..1e37fbb78f7a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -232,5 +232,6 @@ struct nfs_server { #define NFS_CAP_SECURITY_LABEL (1U << 18) #define NFS_CAP_SEEK (1U << 19) #define NFS_CAP_ALLOCATE (1U << 20) +#define NFS_CAP_DEALLOCATE (1U << 21) #endif -- cgit v1.2.3