From 36dfd116edd48fa6174d5694c143f1d4bd81aba8 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:38 -0700 Subject: fs/fscache: convert printk to pr_foo() All printk converted to pr_foo() except internal.h: printk(KERN_DEBUG Coalesce formats. Add pr_fmt Signed-off-by: Fabian Frederick Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fscache/cache.c | 13 ++++++------- fs/fscache/cookie.c | 2 +- fs/fscache/internal.h | 26 ++++++++++++++++---------- fs/fscache/main.c | 7 +++---- fs/fscache/netfs.c | 7 +++---- fs/fscache/operation.c | 3 +-- fs/fscache/page.c | 6 ++---- 7 files changed, 32 insertions(+), 32 deletions(-) (limited to 'fs') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index f7cff36..56cce7f 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -280,15 +280,15 @@ int fscache_add_cache(struct fscache_cache *cache, spin_unlock(&fscache_fsdef_index.lock); up_write(&fscache_addremove_sem); - printk(KERN_NOTICE "FS-Cache: Cache \"%s\" added (type %s)\n", - cache->tag->name, cache->ops->name); + pr_notice("Cache \"%s\" added (type %s)\n", + cache->tag->name, cache->ops->name); kobject_uevent(cache->kobj, KOBJ_ADD); _leave(" = 0 [%s]", cache->identifier); return 0; tag_in_use: - printk(KERN_ERR "FS-Cache: Cache tag '%s' already in use\n", tagname); + pr_err("Cache tag '%s' already in use\n", tagname); __fscache_release_cache_tag(tag); _leave(" = -EXIST"); return -EEXIST; @@ -317,8 +317,7 @@ EXPORT_SYMBOL(fscache_add_cache); void fscache_io_error(struct fscache_cache *cache) { if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags)) - printk(KERN_ERR "FS-Cache:" - " Cache '%s' stopped due to I/O error\n", + pr_err("Cache '%s' stopped due to I/O error\n", cache->ops->name); } EXPORT_SYMBOL(fscache_io_error); @@ -369,8 +368,8 @@ void fscache_withdraw_cache(struct fscache_cache *cache) _enter(""); - printk(KERN_NOTICE "FS-Cache: Withdrawing cache \"%s\"\n", - cache->tag->name); + pr_notice("Withdrawing cache \"%s\"\n", + cache->tag->name); /* make the cache unavailable for cookie acquisition */ if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags)) diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 29d7feb..aec01be 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -519,7 +519,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate) ASSERTCMP(atomic_read(&cookie->n_active), >, 0); if (atomic_read(&cookie->n_children) != 0) { - printk(KERN_ERR "FS-Cache: Cookie '%s' still has children\n", + pr_err("Cookie '%s' still has children\n", cookie->def->name); BUG(); } diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 4226f66..bc6c08f 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -22,6 +22,12 @@ * */ +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "FS-Cache: " fmt + #include #include @@ -413,8 +419,8 @@ do { \ #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "FS-Cache: Assertion failed\n"); \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) @@ -422,9 +428,9 @@ do { \ #define ASSERTCMP(X, OP, Y) \ do { \ if (unlikely(!((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "FS-Cache: Assertion failed\n"); \ - printk(KERN_ERR "%lx " #OP " %lx is false\n", \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ (unsigned long)(X), (unsigned long)(Y)); \ BUG(); \ } \ @@ -433,8 +439,8 @@ do { \ #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "FS-Cache: Assertion failed\n"); \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) @@ -442,9 +448,9 @@ do { \ #define ASSERTIFCMP(C, X, OP, Y) \ do { \ if (unlikely((C) && !((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "FS-Cache: Assertion failed\n"); \ - printk(KERN_ERR "%lx " #OP " %lx is false\n", \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ (unsigned long)(X), (unsigned long)(Y)); \ BUG(); \ } \ diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 7c27907..acd4bf1 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -146,8 +146,7 @@ static int __init fscache_init(void) 0, fscache_cookie_init_once); if (!fscache_cookie_jar) { - printk(KERN_NOTICE - "FS-Cache: Failed to allocate a cookie jar\n"); + pr_notice("Failed to allocate a cookie jar\n"); ret = -ENOMEM; goto error_cookie_jar; } @@ -156,7 +155,7 @@ static int __init fscache_init(void) if (!fscache_root) goto error_kobj; - printk(KERN_NOTICE "FS-Cache: Loaded\n"); + pr_notice("Loaded\n"); return 0; error_kobj: @@ -192,7 +191,7 @@ static void __exit fscache_exit(void) fscache_proc_cleanup(); destroy_workqueue(fscache_op_wq); destroy_workqueue(fscache_object_wq); - printk(KERN_NOTICE "FS-Cache: Unloaded\n"); + pr_notice("Unloaded\n"); } module_exit(fscache_exit); diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c index 989f394..6d941f5 100644 --- a/fs/fscache/netfs.c +++ b/fs/fscache/netfs.c @@ -65,8 +65,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs) list_add(&netfs->link, &fscache_netfs_list); ret = 0; - printk(KERN_NOTICE "FS-Cache: Netfs '%s' registered for caching\n", - netfs->name); + pr_notice("Netfs '%s' registered for caching\n", netfs->name); already_registered: up_write(&fscache_addremove_sem); @@ -97,8 +96,8 @@ void __fscache_unregister_netfs(struct fscache_netfs *netfs) up_write(&fscache_addremove_sem); - printk(KERN_NOTICE "FS-Cache: Netfs '%s' unregistered from caching\n", - netfs->name); + pr_notice("Netfs '%s' unregistered from caching\n", + netfs->name); _leave(""); } diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 318071a..e7b87a0 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -51,8 +51,7 @@ void fscache_enqueue_operation(struct fscache_operation *op) _debug("queue for caller's attention"); break; default: - printk(KERN_ERR "FS-Cache: Unexpected op type %lx", - op->flags); + pr_err("Unexpected op type %lx", op->flags); BUG(); break; } diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 7f5c658..ed70714 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -1108,10 +1108,8 @@ void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page) static bool once_only; if (!once_only) { once_only = true; - printk(KERN_WARNING "FS-Cache:" - " Cookie type %s marked page %lx" - " multiple times\n", - cookie->def->name, page->index); + pr_warn("Cookie type %s marked page %lx multiple times\n", + cookie->def->name, page->index); } } -- cgit v1.1 From 3185a88ce37490938d56119c474aa48616d386e8 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:39 -0700 Subject: fs/fscache: replace seq_printf by seq_puts Replace seq_printf where possible + coalesce formats from 2 existing seq_puts Signed-off-by: Fabian Frederick Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fscache/histogram.c | 6 ++---- fs/fscache/object-list.c | 8 ++++---- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c index bad4967..7d637e2 100644 --- a/fs/fscache/histogram.c +++ b/fs/fscache/histogram.c @@ -31,12 +31,10 @@ static int fscache_histogram_show(struct seq_file *m, void *v) switch ((unsigned long) v) { case 1: - seq_puts(m, "JIFS SECS OBJ INST OP RUNS OBJ RUNS " - " RETRV DLY RETRIEVLS\n"); + seq_puts(m, "JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS\n"); return 0; case 2: - seq_puts(m, "===== ===== ========= ========= =========" - " ========= =========\n"); + seq_puts(m, "===== ===== ========= ========= ========= ========= =========\n"); return 0; default: index = (unsigned long) v - 3; diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index b5ebc2d..b8179ca 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -285,20 +285,20 @@ static int fscache_objlist_show(struct seq_file *m, void *v) fscache_unuse_cookie(obj); if (keylen > 0 || auxlen > 0) { - seq_printf(m, " "); + seq_puts(m, " "); for (p = buf; keylen > 0; keylen--) seq_printf(m, "%02x", *p++); if (auxlen > 0) { if (config & FSCACHE_OBJLIST_CONFIG_KEY) - seq_printf(m, ", "); + seq_puts(m, ", "); for (; auxlen > 0; auxlen--) seq_printf(m, "%02x", *p++); } } - seq_printf(m, "\n"); + seq_puts(m, "\n"); } else { - seq_printf(m, "\n"); + seq_puts(m, "\n"); } return 0; } -- cgit v1.1 From 0a8dd2db579f7a0ac7033d6b857c3d5dbaa77563 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Wed, 4 Jun 2014 16:05:40 -0700 Subject: fanotify: FAN_MARK_FLUSH: avoid having to provide a fake/invalid fd and path Originally from Tvrtko Ursulin (https://lkml.org/lkml/2011/1/12/112) Avoid having to provide a fake/invalid fd and path when flushing marks Currently for a group to flush marks it has set it needs to provide a fake or invalid (but resolvable) file descriptor and path when calling fanotify_mark. This patch pulls the flush handling a bit up so file descriptor and path are completely ignored when flushing. I reworked the patch to be applicable again (the signature of fanotify_mark has changed since Tvrtko's work). Signed-off-by: Heinrich Schuchardt Cc: Tvrtko Ursulin Reviewed-by: Jan Kara Acked-by: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 732648b..f6ac6a2 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -813,6 +813,15 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, group->priority == FS_PRIO_0) goto fput_and_out; + if (flags & FAN_MARK_FLUSH) { + ret = 0; + if (flags & FAN_MARK_MOUNT) + fsnotify_clear_vfsmount_marks_by_group(group); + else + fsnotify_clear_inode_marks_by_group(group); + goto fput_and_out; + } + ret = fanotify_find_path(dfd, pathname, &path, flags); if (ret) goto fput_and_out; @@ -824,7 +833,7 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, mnt = path.mnt; /* create/update an inode mark */ - switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) { + switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) { case FAN_MARK_ADD: if (flags & FAN_MARK_MOUNT) ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags); @@ -837,12 +846,6 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, else ret = fanotify_remove_inode_mark(group, inode, mask, flags); break; - case FAN_MARK_FLUSH: - if (flags & FAN_MARK_MOUNT) - fsnotify_clear_vfsmount_marks_by_group(group); - else - fsnotify_clear_inode_marks_by_group(group); - break; default: ret = -EINVAL; } -- cgit v1.1 From d4c7cf6cffb1bc711a833b5e304ba5bcfe76398b Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Wed, 4 Jun 2014 16:05:41 -0700 Subject: fanotify: create FAN_ACCESS event for readdir Before the patch, read creates FAN_ACCESS_PERM and FAN_ACCESS events, readdir creates only FAN_ACCESS_PERM events. This is inconsistent. After the patch, readdir creates FAN_ACCESS_PERM and FAN_ACCESS events. Signed-off-by: Heinrich Schuchardt Reviewed-by: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/readdir.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/readdir.c b/fs/readdir.c index 5b53d99..33fd922 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,7 @@ int iterate_dir(struct file *file, struct dir_context *ctx) ctx->pos = file->f_pos; res = file->f_op->iterate(file, ctx); file->f_pos = ctx->pos; + fsnotify_access(file); file_accessed(file); } mutex_unlock(&inode->i_mutex); -- cgit v1.1 From efa8f7e5d7bc2a6f1d1f9b43f9514d02f00b9cb1 Mon Sep 17 00:00:00 2001 From: David Cohen Date: Wed, 4 Jun 2014 16:05:42 -0700 Subject: fs/notify/mark.c: trivial cleanup Do not initialize private_destroy_list twice. list_replace_init() already takes care of initializing private_destroy_list. We don't need to initialize it with LIST_HEAD() beforehand. Signed-off-by: David Cohen Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 923fe4a..d90deaa 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -340,7 +340,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, static int fsnotify_mark_destroy(void *ignored) { struct fsnotify_mark *mark, *next; - LIST_HEAD(private_destroy_list); + struct list_head private_destroy_list; for (;;) { spin_lock(&destroy_lock); -- cgit v1.1 From cc299a98eb13a9853675a9cbb90b30b4011e1406 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Wed, 4 Jun 2014 16:05:43 -0700 Subject: fs/notify/fanotify/fanotify_user.c: fix FAN_MARK_FLUSH flag checking If fanotify_mark is called with illegal value of arguments flags and marks it usually returns EINVAL. When fanotify_mark is called with FAN_MARK_FLUSH the argument flags is not checked for irrelevant flags like FAN_MARK_IGNORED_MASK. The patch removes this inconsistency. If an irrelevant flag is set error EINVAL is returned. Signed-off-by: Heinrich Schuchardt Acked-by: Michael Kerrisk Acked-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index f6ac6a2..9163a6e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -776,7 +776,10 @@ SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags, case FAN_MARK_REMOVE: if (!mask) return -EINVAL; + break; case FAN_MARK_FLUSH: + if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH)) + return -EINVAL; break; default: return -EINVAL; -- cgit v1.1 From 48149e9d3a7e924010a0daab30a6197b7d7b6580 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Wed, 4 Jun 2014 16:05:44 -0700 Subject: fanotify: check file flags passed in fanotify_init Without this patch fanotify_init does not validate the value passed in event_f_flags. When a fanotify event is read from the fanotify file descriptor a new file descriptor is created where file.f_flags = event_f_flags. Internal and external open flags are stored together in field f_flags of struct file. Hence, an application might create file descriptors with internal flags like FMODE_EXEC, FMODE_NOCMTIME set. Jan Kara and Eric Paris both aggreed that this is a bug and the value of event_f_flags should be checked: https://lkml.org/lkml/2014/4/29/522 https://lkml.org/lkml/2014/4/29/539 This updated patch version considers the comments by Michael Kerrisk in https://lkml.org/lkml/2014/5/4/10 With the patch the value of event_f_flags is checked. When specifying an invalid value error EINVAL is returned. Internal flags are disallowed. File creation flags are disallowed: O_CREAT, O_DIRECTORY, O_EXCL, O_NOCTTY, O_NOFOLLOW, O_TRUNC, and O_TTY_INIT. Flags which do not make sense with fanotify are disallowed: __O_TMPFILE, O_PATH, FASYNC, and O_DIRECT. This leaves us with the following allowed values: O_RDONLY, O_WRONLY, O_RDWR are basic functionality. The are stored in the bits given by O_ACCMODE. O_APPEND is working as expected. The value might be useful in a logging application which appends the current status each time the log is opened. O_LARGEFILE is needed for files exceeding 4GB on 32bit systems. O_NONBLOCK may be useful when monitoring slow devices like tapes. O_NDELAY is equal to O_NONBLOCK except for platform parisc. To avoid code breaking on parisc either both flags should be allowed or none. The patch allows both. __O_SYNC and O_DSYNC may be used to avoid data loss on power disruption. O_NOATIME may be useful to reduce disk activity. O_CLOEXEC may be useful, if separate processes shall be used to scan files. Once this patch is accepted, the fanotify_init.2 manpage has to be updated. Signed-off-by: Heinrich Schuchardt Reviewed-by: Jan Kara Cc: Michael Kerrisk Cc: Valdis Kletnieks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9163a6e..3fdc8a3 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -25,6 +25,19 @@ #define FANOTIFY_DEFAULT_MAX_MARKS 8192 #define FANOTIFY_DEFAULT_MAX_LISTENERS 128 +/* + * All flags that may be specified in parameter event_f_flags of fanotify_init. + * + * Internal and external open flags are stored together in field f_flags of + * struct file. Only external open flags shall be allowed in event_f_flags. + * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be + * excluded. + */ +#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \ + O_ACCMODE | O_APPEND | O_NONBLOCK | \ + __O_SYNC | O_DSYNC | O_CLOEXEC | \ + O_LARGEFILE | O_NOATIME ) + extern const struct fsnotify_ops fanotify_fsnotify_ops; static struct kmem_cache *fanotify_mark_cache __read_mostly; @@ -669,6 +682,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if (flags & ~FAN_ALL_INIT_FLAGS) return -EINVAL; + if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) + return -EINVAL; + + switch (event_f_flags & O_ACCMODE) { + case O_RDONLY: + case O_RDWR: + case O_WRONLY: + break; + default: + return -EINVAL; + } + user = get_current_user(); if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) { free_uid(user); -- cgit v1.1 From 504e0e2f3dcac242eb529a01a4b0ea45e4a34eb7 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:50 -0700 Subject: ntfs: remove NULL value assignments Static values are automatically initialized to NULL. Signed-off-by: Fabian Frederick Acked-by: Anton Altaparmakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ntfs/compress.c | 2 +- fs/ntfs/super.c | 4 ++-- fs/ntfs/sysctl.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index ee4144c..f82498c 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -58,7 +58,7 @@ typedef enum { /** * ntfs_compression_buffer - one buffer for the decompression engine */ -static u8 *ntfs_compression_buffer = NULL; +static u8 *ntfs_compression_buffer; /** * ntfs_cb_lock - spinlock which protects ntfs_compression_buffer diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 9de2491..6c3296e 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -50,8 +50,8 @@ static unsigned long ntfs_nr_compression_users; /* A global default upcase table and a corresponding reference count. */ -static ntfschar *default_upcase = NULL; -static unsigned long ntfs_nr_upcase_users = 0; +static ntfschar *default_upcase; +static unsigned long ntfs_nr_upcase_users; /* Error constants/strings used in inode.c::ntfs_show_options(). */ typedef enum { diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c index 79a8918..1927170 100644 --- a/fs/ntfs/sysctl.c +++ b/fs/ntfs/sysctl.c @@ -56,7 +56,7 @@ static ctl_table sysctls_root[] = { }; /* Storage for the sysctls header. */ -static struct ctl_table_header *sysctls_root_table = NULL; +static struct ctl_table_header *sysctls_root_table; /** * ntfs_sysctl - add or remove the debug sysctl -- cgit v1.1 From 220108361f7cef9bc3ac0b4c84cb556d36ec2a6f Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:52 -0700 Subject: fs/squashfs/squashfs.h: replace pr_warning by pr_warn Update the last pr_warning callsite in fs branch Signed-off-by: Fabian Frederick Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/squashfs/squashfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 9e1bb79..887d6d2 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -25,7 +25,7 @@ #define ERROR(s, args...) pr_err("SQUASHFS error: "s, ## args) -#define WARNING(s, args...) pr_warning("SQUASHFS: "s, ## args) +#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args) /* block.c */ extern int squashfs_read_data(struct super_block *, u64, int, u64 *, -- cgit v1.1 From f6b1fe7c27800adba0ccf6063ee97478046eeafe Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:57 -0700 Subject: fs/configs/item.c: kernel-doc fixes + clean-up Fix function parameter documentation EXPORT_SYMBOLS moved after corresponding functions Small coding style and checkpatch warning fixes Signed-off-by: Fabian Frederick Acked-by: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/configfs/item.c | 58 ++++++++++++++++++++++++++---------------------------- 1 file changed, 28 insertions(+), 30 deletions(-) (limited to 'fs') diff --git a/fs/configfs/item.c b/fs/configfs/item.c index 50cee7f..e65f9ff 100644 --- a/fs/configfs/item.c +++ b/fs/configfs/item.c @@ -19,7 +19,7 @@ * Boston, MA 021110-1307, USA. * * Based on kobject: - * kobject is Copyright (c) 2002-2003 Patrick Mochel + * kobject is Copyright (c) 2002-2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. * @@ -35,9 +35,9 @@ #include -static inline struct config_item * to_item(struct list_head * entry) +static inline struct config_item *to_item(struct list_head *entry) { - return container_of(entry,struct config_item,ci_entry); + return container_of(entry, struct config_item, ci_entry); } /* Evil kernel */ @@ -47,34 +47,35 @@ static void config_item_release(struct kref *kref); * config_item_init - initialize item. * @item: item in question. */ -void config_item_init(struct config_item * item) +void config_item_init(struct config_item *item) { kref_init(&item->ci_kref); INIT_LIST_HEAD(&item->ci_entry); } +EXPORT_SYMBOL(config_item_init); /** * config_item_set_name - Set the name of an item * @item: item. - * @name: name. + * @fmt: The vsnprintf()'s format string. * * If strlen(name) >= CONFIGFS_ITEM_NAME_LEN, then use a * dynamically allocated string that @item->ci_name points to. * Otherwise, use the static @item->ci_namebuf array. */ -int config_item_set_name(struct config_item * item, const char * fmt, ...) +int config_item_set_name(struct config_item *item, const char *fmt, ...) { int error = 0; int limit = CONFIGFS_ITEM_NAME_LEN; int need; va_list args; - char * name; + char *name; /* * First, try the static array */ - va_start(args,fmt); - need = vsnprintf(item->ci_namebuf,limit,fmt,args); + va_start(args, fmt); + need = vsnprintf(item->ci_namebuf, limit, fmt, args); va_end(args); if (need < limit) name = item->ci_namebuf; @@ -83,13 +84,13 @@ int config_item_set_name(struct config_item * item, const char * fmt, ...) * Need more space? Allocate it and try again */ limit = need + 1; - name = kmalloc(limit,GFP_KERNEL); + name = kmalloc(limit, GFP_KERNEL); if (!name) { error = -ENOMEM; goto Done; } - va_start(args,fmt); - need = vsnprintf(name,limit,fmt,args); + va_start(args, fmt); + need = vsnprintf(name, limit, fmt, args); va_end(args); /* Still? Give up. */ @@ -109,7 +110,6 @@ int config_item_set_name(struct config_item * item, const char * fmt, ...) Done: return error; } - EXPORT_SYMBOL(config_item_set_name); void config_item_init_type_name(struct config_item *item, @@ -131,20 +131,21 @@ void config_group_init_type_name(struct config_group *group, const char *name, } EXPORT_SYMBOL(config_group_init_type_name); -struct config_item * config_item_get(struct config_item * item) +struct config_item *config_item_get(struct config_item *item) { if (item) kref_get(&item->ci_kref); return item; } +EXPORT_SYMBOL(config_item_get); -static void config_item_cleanup(struct config_item * item) +static void config_item_cleanup(struct config_item *item) { - struct config_item_type * t = item->ci_type; - struct config_group * s = item->ci_group; - struct config_item * parent = item->ci_parent; + struct config_item_type *t = item->ci_type; + struct config_group *s = item->ci_group; + struct config_item *parent = item->ci_parent; - pr_debug("config_item %s: cleaning up\n",config_item_name(item)); + pr_debug("config_item %s: cleaning up\n", config_item_name(item)); if (item->ci_name != item->ci_namebuf) kfree(item->ci_name); item->ci_name = NULL; @@ -167,21 +168,23 @@ static void config_item_release(struct kref *kref) * * Decrement the refcount, and if 0, call config_item_cleanup(). */ -void config_item_put(struct config_item * item) +void config_item_put(struct config_item *item) { if (item) kref_put(&item->ci_kref, config_item_release); } +EXPORT_SYMBOL(config_item_put); /** * config_group_init - initialize a group for use - * @k: group + * @group: config_group */ void config_group_init(struct config_group *group) { config_item_init(&group->cg_item); INIT_LIST_HEAD(&group->cg_children); } +EXPORT_SYMBOL(config_group_init); /** * config_group_find_item - search for item in group. @@ -195,11 +198,11 @@ void config_group_init(struct config_group *group) struct config_item *config_group_find_item(struct config_group *group, const char *name) { - struct list_head * entry; - struct config_item * ret = NULL; + struct list_head *entry; + struct config_item *ret = NULL; - list_for_each(entry,&group->cg_children) { - struct config_item * item = to_item(entry); + list_for_each(entry, &group->cg_children) { + struct config_item *item = to_item(entry); if (config_item_name(item) && !strcmp(config_item_name(item), name)) { ret = config_item_get(item); @@ -208,9 +211,4 @@ struct config_item *config_group_find_item(struct config_group *group, } return ret; } - -EXPORT_SYMBOL(config_item_init); -EXPORT_SYMBOL(config_group_init); -EXPORT_SYMBOL(config_item_get); -EXPORT_SYMBOL(config_item_put); EXPORT_SYMBOL(config_group_find_item); -- cgit v1.1 From c6686931335757c2b348fc9a74ff564d8bd10f0a Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:58 -0700 Subject: fs/configfs: convert printk to pr_foo() Signed-off-by: Fabian Frederick Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/configfs/dir.c | 8 ++++---- fs/configfs/inode.c | 5 ++--- fs/configfs/mount.c | 2 +- 3 files changed, 7 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index e081acb..727d06e 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -940,9 +940,9 @@ static void client_drop_item(struct config_item *parent_item, #ifdef DEBUG static void configfs_dump_one(struct configfs_dirent *sd, int level) { - printk(KERN_INFO "%*s\"%s\":\n", level, " ", configfs_get_name(sd)); + pr_info("%*s\"%s\":\n", level, " ", configfs_get_name(sd)); -#define type_print(_type) if (sd->s_type & _type) printk(KERN_INFO "%*s %s\n", level, " ", #_type); +#define type_print(_type) if (sd->s_type & _type) pr_info("%*s %s\n", level, " ", #_type); type_print(CONFIGFS_ROOT); type_print(CONFIGFS_DIR); type_print(CONFIGFS_ITEM_ATTR); @@ -1699,7 +1699,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) struct dentry *root = dentry->d_sb->s_root; if (dentry->d_parent != root) { - printk(KERN_ERR "configfs: Tried to unregister non-subsystem!\n"); + pr_err("configfs: Tried to unregister non-subsystem!\n"); return; } @@ -1709,7 +1709,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) mutex_lock(&configfs_symlink_mutex); spin_lock(&configfs_dirent_lock); if (configfs_detach_prep(dentry, NULL)) { - printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n"); + pr_err("configfs: Tried to unregister non-empty subsystem!\n"); } spin_unlock(&configfs_dirent_lock); mutex_unlock(&configfs_symlink_mutex); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index a9d35b0..fbb30db 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -168,9 +168,8 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd, * In practice the maximum level of locking depth is * already reached. Just inform about possible reasons. */ - printk(KERN_INFO "configfs: Too many levels of inodes" - " for the locking correctness validator.\n"); - printk(KERN_INFO "Spurious warnings may appear.\n"); + pr_info("configfs: Too many levels of inodes for the locking correctness validator.\n"); + pr_info("Spurious warnings may appear.\n"); } } } diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 7f26c3c..af08de0 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -155,7 +155,7 @@ static int __init configfs_init(void) return 0; out4: - printk(KERN_ERR "configfs: Unable to register filesystem!\n"); + pr_err("configfs: Unable to register filesystem!\n"); configfs_inode_exit(); out3: kobject_put(config_kobj); -- cgit v1.1 From 1d88aa441f25811a55c0ed688add108c0a45613e Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:05:59 -0700 Subject: fs/configfs: use pr_fmt Add pr_fmt based on module name. Signed-off-by: Fabian Frederick Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/configfs/configfs_internal.h | 6 ++++++ fs/configfs/dir.c | 4 ++-- fs/configfs/inode.c | 2 +- fs/configfs/mount.c | 4 ++-- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index b5f0a3b..bd4a3c1 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -24,6 +24,12 @@ * configfs Copyright (C) 2005 Oracle. All rights reserved. */ +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 727d06e..668dcab 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1699,7 +1699,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) struct dentry *root = dentry->d_sb->s_root; if (dentry->d_parent != root) { - pr_err("configfs: Tried to unregister non-subsystem!\n"); + pr_err("Tried to unregister non-subsystem!\n"); return; } @@ -1709,7 +1709,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) mutex_lock(&configfs_symlink_mutex); spin_lock(&configfs_dirent_lock); if (configfs_detach_prep(dentry, NULL)) { - pr_err("configfs: Tried to unregister non-empty subsystem!\n"); + pr_err("Tried to unregister non-empty subsystem!\n"); } spin_unlock(&configfs_dirent_lock); mutex_unlock(&configfs_symlink_mutex); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index fbb30db..5946ad9 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -168,7 +168,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd, * In practice the maximum level of locking depth is * already reached. Just inform about possible reasons. */ - pr_info("configfs: Too many levels of inodes for the locking correctness validator.\n"); + pr_info("Too many levels of inodes for the locking correctness validator.\n"); pr_info("Spurious warnings may appear.\n"); } } diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index af08de0..f6c2858 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -85,7 +85,7 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); } else { - pr_debug("configfs: could not get root inode\n"); + pr_debug("could not get root inode\n"); return -ENOMEM; } @@ -155,7 +155,7 @@ static int __init configfs_init(void) return 0; out4: - pr_err("configfs: Unable to register filesystem!\n"); + pr_err("Unable to register filesystem!\n"); configfs_inode_exit(); out3: kobject_put(config_kobj); -- cgit v1.1 From 1a5c4e2a0e339a01fdfbd519ba664d8efdc8d702 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:06 -0700 Subject: ocfs2: remove NULL assignments on static Static values are automatically initialized to NULL. Signed-off-by: Fabian Frederick Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 2 +- fs/ocfs2/dlm/dlmdebug.c | 2 +- fs/ocfs2/dlm/dlmlock.c | 2 +- fs/ocfs2/dlm/dlmmaster.c | 6 +++--- fs/ocfs2/stackglue.c | 2 +- fs/ocfs2/super.c | 4 ++-- fs/ocfs2/uptodate.c | 2 +- 7 files changed, 10 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index c6b90e6..a68e07a 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -108,7 +108,7 @@ static struct rb_root o2net_handler_tree = RB_ROOT; static struct o2net_node o2net_nodes[O2NM_MAX_NODES]; /* XXX someday we'll need better accounting */ -static struct socket *o2net_listen_sock = NULL; +static struct socket *o2net_listen_sock; /* * listen work is only queued by the listening socket callbacks on the diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index e33cd7a..18f13c2 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -338,7 +338,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle) #ifdef CONFIG_DEBUG_FS -static struct dentry *dlm_debugfs_root = NULL; +static struct dentry *dlm_debugfs_root; #define DLM_DEBUGFS_DIR "o2dlm" #define DLM_DEBUGFS_DLM_STATE "dlm_state" diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 5d32f75..66c2a49 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -52,7 +52,7 @@ #define MLOG_MASK_PREFIX ML_DLM #include "cluster/masklog.h" -static struct kmem_cache *dlm_lock_cache = NULL; +static struct kmem_cache *dlm_lock_cache; static DEFINE_SPINLOCK(dlm_cookie_lock); static u64 dlm_next_cookie = 1; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ee1f884..3087a21 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -82,9 +82,9 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm, return 1; } -static struct kmem_cache *dlm_lockres_cache = NULL; -static struct kmem_cache *dlm_lockname_cache = NULL; -static struct kmem_cache *dlm_mle_cache = NULL; +static struct kmem_cache *dlm_lockres_cache; +static struct kmem_cache *dlm_lockname_cache; +static struct kmem_cache *dlm_mle_cache; static void dlm_mle_release(struct kref *kref); static void dlm_init_mle(struct dlm_master_list_entry *mle, diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 83f1a66..5d965e8 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -709,7 +709,7 @@ static struct ctl_table ocfs2_root_table[] = { { } }; -static struct ctl_table_header *ocfs2_table_header = NULL; +static struct ctl_table_header *ocfs2_table_header; /* diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index a7cdd56..9027729 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -75,7 +75,7 @@ #include "buffer_head_io.h" -static struct kmem_cache *ocfs2_inode_cachep = NULL; +static struct kmem_cache *ocfs2_inode_cachep; struct kmem_cache *ocfs2_dquot_cachep; struct kmem_cache *ocfs2_qf_chunk_cachep; @@ -85,7 +85,7 @@ struct kmem_cache *ocfs2_qf_chunk_cachep; * workqueue and schedule on our own. */ struct workqueue_struct *ocfs2_wq = NULL; -static struct dentry *ocfs2_debugfs_root = NULL; +static struct dentry *ocfs2_debugfs_root; MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index 52eaf33..82e17b0 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -67,7 +67,7 @@ struct ocfs2_meta_cache_item { sector_t c_block; }; -static struct kmem_cache *ocfs2_uptodate_cachep = NULL; +static struct kmem_cache *ocfs2_uptodate_cachep; u64 ocfs2_metadata_cache_owner(struct ocfs2_caching_info *ci) { -- cgit v1.1 From 69201bb1132718f45078ba6454093f5e220c0350 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:07 -0700 Subject: fs/ocfs2/super.c: use OCFS2_MAX_VOL_LABEL_LEN and strlcpy Replace strncpy(size 63) by defined value. Signed-off-by: Fabian Frederick Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 9027729..c7a89cea 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2292,8 +2292,8 @@ static int ocfs2_initialize_super(struct super_block *sb, goto bail; } - strncpy(osb->vol_label, di->id2.i_super.s_label, 63); - osb->vol_label[63] = '\0'; + strlcpy(osb->vol_label, di->id2.i_super.s_label, + OCFS2_MAX_VOL_LABEL_LEN); osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno); osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno); osb->first_cluster_group_blkno = -- cgit v1.1 From b3821c3f866a1c02d1537ab67abe9a824d1353ae Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Wed, 4 Jun 2014 16:06:08 -0700 Subject: ocfs2: remove some redundant casting There are two standard techniques for dereferencing structures pointed to by void *: cast to the right type each time they're used, or assign to local variables of the right type. But there's no need to do *both*. Signed-off-by: George Spelvin Cc: Mark Fasheh Acked-by: Joel Becker Reviewed-by: Jie Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/refcounttree.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 6ba4bcb..714e53b 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -1408,10 +1408,9 @@ static void swap_refcount_rec(void *a, void *b, int size) { struct ocfs2_refcount_rec *l = a, *r = b, tmp; - tmp = *(struct ocfs2_refcount_rec *)l; - *(struct ocfs2_refcount_rec *)l = - *(struct ocfs2_refcount_rec *)r; - *(struct ocfs2_refcount_rec *)r = tmp; + tmp = *l; + *l = *r; + *r = tmp; } /* -- cgit v1.1 From 55b465b66809368b459674b9d205010730953c2e Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Wed, 4 Jun 2014 16:06:09 -0700 Subject: ocfs2: limit printk when journal is aborted Once JBD2_ABORT is set, ocfs2_commit_cache will fail in ocfs2_commit_thread. Then it will get into a loop with mass logs. This will meaninglessly consume a larger number of resource and may lead to the system hanging. So limit printk in this case. [akpm@linux-foundation.org: document the msleep] Signed-off-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/journal.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 03ea931..4b0c688 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -30,6 +30,7 @@ #include #include #include +#include #include @@ -2185,8 +2186,20 @@ static int ocfs2_commit_thread(void *arg) || kthread_should_stop()); status = ocfs2_commit_cache(osb); - if (status < 0) - mlog_errno(status); + if (status < 0) { + static unsigned long abort_warn_time; + + /* Warn about this once per minute */ + if (printk_timed_ratelimit(&abort_warn_time, 60*HZ)) + mlog(ML_ERROR, "status = %d, journal is " + "already aborted.\n", status); + /* + * After ocfs2_commit_cache() fails, j_num_trans has a + * non-zero value. Sleep here to avoid a busy-wait + * loop. + */ + msleep_interruptible(1000); + } if (kthread_should_stop() && atomic_read(&journal->j_num_trans)){ mlog(ML_KTHREAD, -- cgit v1.1 From 6718cb5e0e75faa2b938dc1ee247fbd70136ccd7 Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Wed, 4 Jun 2014 16:06:10 -0700 Subject: ocfs2/dlm: fix possible convert=sion deadlock We found there is a conversion deadlock when the owner of lockres happened to crash before send DLM_PROXY_AST_MSG for a downconverting lock. The situation is as follows: Node1 Node2 Node3 the owner of lockresA lock_1 granted at EX mode and call ocfs2_cluster_unlock to decrease ex_holders. converting lock_3 from NL to EX send DLM_PROXY_AST_MSG to Node1, asking Node 1 to downconvert. receiving DLM_PROXY_AST_MSG, thread ocfs2dc send DLM_CONVERT_LOCK_MSG to Node2 to downconvert lock_1(EX->NL). lock_1 can be granted and put it into pending_asts list, return DLM_NORMAL. then something happened and Node2 crashed. received DLM_NORMAL, waiting for DLM_PROXY_AST_MSG. selected as the recovery master, receving migrate lock from Node1, queue lock_1 to the tail of converting list. After dlm recovery, converting list in the master of lockresA(Node3) will be: converting list head <-> lock_3(NL->EX) <->lock_1(EX<->NL). Requested mode of lock_3 is not compatible with the granted mode of lock_1, so it can not be granted. and lock_1 can not downconvert because covnerting queue is strictly FIFO. So a deadlock is created. We think function dlm_process_recovery_data() should queue_ast for lock_1 or alter the order of lock_1 and lock_3, so dlm_thread can process lock_1 first. And if there are multiple downconverting locks, they must convert form PR to NL, so no need to sort them. Signed-off-by: joyce.xue Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmrecovery.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index fe29f79..5de0194 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1986,7 +1986,15 @@ skip_lvb: } if (!bad) { dlm_lock_get(newlock); - list_add_tail(&newlock->list, queue); + if (mres->flags & DLM_MRES_RECOVERY && + ml->list == DLM_CONVERTING_LIST && + newlock->ml.type > + newlock->ml.convert_type) { + /* newlock is doing downconvert, add it to the + * head of converting list */ + list_add(&newlock->list, queue); + } else + list_add_tail(&newlock->list, queue); mlog(0, "%s:%.*s: added lock for node %u, " "setting refmap bit\n", dlm->name, res->lockname.len, res->lockname.name, ml->node); -- cgit v1.1 From c253ed1f6fd68df8542efed2d6b7656c3324f3e4 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:12 -0700 Subject: fs/ocfs2/ioctl.c: add static to local functions ocfs_info_foo() and ocfs2_get_request_ptr functions are only used in ioctl.c Signed-off-by: Fabian Frederick Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/ioctl.c | 81 ++++++++++++++++++++++++++++---------------------------- 1 file changed, 41 insertions(+), 40 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 490229f..6f66b37 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -143,8 +143,8 @@ bail: return status; } -int ocfs2_info_handle_blocksize(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_blocksize(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_blocksize oib; @@ -167,8 +167,8 @@ bail: return status; } -int ocfs2_info_handle_clustersize(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_clustersize(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_clustersize oic; @@ -192,8 +192,8 @@ bail: return status; } -int ocfs2_info_handle_maxslots(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_maxslots(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_maxslots oim; @@ -217,8 +217,8 @@ bail: return status; } -int ocfs2_info_handle_label(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_label(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_label oil; @@ -242,8 +242,8 @@ bail: return status; } -int ocfs2_info_handle_uuid(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_uuid(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_uuid oiu; @@ -267,8 +267,8 @@ bail: return status; } -int ocfs2_info_handle_fs_features(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_fs_features(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_fs_features oif; @@ -294,8 +294,8 @@ bail: return status; } -int ocfs2_info_handle_journal_size(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_journal_size(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_journal_size oij; @@ -319,9 +319,10 @@ bail: return status; } -int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, - struct inode *inode_alloc, u64 blkno, - struct ocfs2_info_freeinode *fi, u32 slot) +static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb, + struct inode *inode_alloc, u64 blkno, + struct ocfs2_info_freeinode *fi, + u32 slot) { int status = 0, unlock = 0; @@ -366,8 +367,8 @@ bail: return status; } -int ocfs2_info_handle_freeinode(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_freeinode(struct inode *inode, + struct ocfs2_info_request __user *req) { u32 i; u64 blkno = -1; @@ -462,19 +463,19 @@ static void o2ffg_update_stats(struct ocfs2_info_freefrag_stats *stats, stats->ffs_free_chunks_real++; } -void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg, - unsigned int chunksize) +static void ocfs2_info_update_ffg(struct ocfs2_info_freefrag *ffg, + unsigned int chunksize) { o2ffg_update_histogram(&(ffg->iff_ffs.ffs_fc_hist), chunksize); o2ffg_update_stats(&(ffg->iff_ffs), chunksize); } -int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb, - struct inode *gb_inode, - struct ocfs2_dinode *gb_dinode, - struct ocfs2_chain_rec *rec, - struct ocfs2_info_freefrag *ffg, - u32 chunks_in_group) +static int ocfs2_info_freefrag_scan_chain(struct ocfs2_super *osb, + struct inode *gb_inode, + struct ocfs2_dinode *gb_dinode, + struct ocfs2_chain_rec *rec, + struct ocfs2_info_freefrag *ffg, + u32 chunks_in_group) { int status = 0, used; u64 blkno; @@ -572,9 +573,9 @@ bail: return status; } -int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb, - struct inode *gb_inode, u64 blkno, - struct ocfs2_info_freefrag *ffg) +static int ocfs2_info_freefrag_scan_bitmap(struct ocfs2_super *osb, + struct inode *gb_inode, u64 blkno, + struct ocfs2_info_freefrag *ffg) { u32 chunks_in_group; int status = 0, unlock = 0, i; @@ -652,8 +653,8 @@ bail: return status; } -int ocfs2_info_handle_freefrag(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_freefrag(struct inode *inode, + struct ocfs2_info_request __user *req) { u64 blkno = -1; char namebuf[40]; @@ -723,8 +724,8 @@ out_err: return status; } -int ocfs2_info_handle_unknown(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_unknown(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_request oir; @@ -752,8 +753,8 @@ bail: * - distinguish different requests. * - validate size of different requests. */ -int ocfs2_info_handle_request(struct inode *inode, - struct ocfs2_info_request __user *req) +static int ocfs2_info_handle_request(struct inode *inode, + struct ocfs2_info_request __user *req) { int status = -EFAULT; struct ocfs2_info_request oir; @@ -811,8 +812,8 @@ bail: return status; } -int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx, - u64 *req_addr, int compat_flag) +static int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx, + u64 *req_addr, int compat_flag) { int status = -EFAULT; u64 __user *bp = NULL; @@ -849,8 +850,8 @@ bail: * a better backward&forward compatibility, since a small piece of * request will be less likely to be broken if disk layout get changed. */ -int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, - int compat_flag) +static int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, + int compat_flag) { int i, status = 0; u64 req_addr; -- cgit v1.1 From a9e9acaeb0a981a6dfa54b32dd756103aeefa6a7 Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Wed, 4 Jun 2014 16:06:13 -0700 Subject: ocfs2: fix umount hang while shutting down truncate log Revert commit 75f82eaa502c ("ocfs2: fix NULL pointer dereference when dismount and ocfs2rec simultaneously") because it may cause a umount hang while shutting down the truncate log. fix NULL pointer dereference when dismount and ocfs2rec simultaneously The situation is as followes: ocfs2_dismout_volume -> ocfs2_recovery_exit -> free osb->recovery_map -> ocfs2_truncate_shutdown -> lock global bitmap inode -> ocfs2_wait_for_recovery -> check whether osb->recovery_map->rm_used is zero Because osb->recovery_map is already freed, rm_used can be any other values, so it may yield umount hang. To prevent NULL pointer dereference while getting sys_root_inode, we use a osb_tl_disable flag to disable schedule osb_truncate_log_wq after truncate log shutdown. Signed-off-by: joyce.xue Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/alloc.c | 6 +++++- fs/ocfs2/ocfs2.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index b4deb5f..9d8fcf2 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6046,7 +6046,8 @@ static void ocfs2_truncate_log_worker(struct work_struct *work) void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb, int cancel) { - if (osb->osb_tl_inode) { + if (osb->osb_tl_inode && + atomic_read(&osb->osb_tl_disable) == 0) { /* We want to push off log flushes while truncates are * still running. */ if (cancel) @@ -6223,6 +6224,8 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb) int status; struct inode *tl_inode = osb->osb_tl_inode; + atomic_set(&osb->osb_tl_disable, 1); + if (tl_inode) { cancel_delayed_work(&osb->osb_truncate_log_wq); flush_workqueue(ocfs2_wq); @@ -6254,6 +6257,7 @@ int ocfs2_truncate_log_init(struct ocfs2_super *osb) * until we're sure all is well. */ INIT_DELAYED_WORK(&osb->osb_truncate_log_wq, ocfs2_truncate_log_worker); + atomic_set(&osb->osb_tl_disable, 0); osb->osb_tl_bh = tl_bh; osb->osb_tl_inode = tl_inode; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 8d64a97..bbec539 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -422,6 +422,7 @@ struct ocfs2_super struct inode *osb_tl_inode; struct buffer_head *osb_tl_bh; struct delayed_work osb_truncate_log_wq; + atomic_t osb_tl_disable; /* * How many clusters in our truncate log. * It must be protected by osb_tl_inode->i_mutex. -- cgit v1.1 From 01c6222f876062355599e5a63560c514b6de25d2 Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Wed, 4 Jun 2014 16:06:14 -0700 Subject: ocfs2/dlm: disallow node joining when recovery is on going We found a race situation when dlm recovery and node joining occurs simultaneously if the network state is bad. N1 N4 start joining dlm and send query join to all live nodes set joining node to N1, return OK send query join to other live nodes and it may take a while call dlm_send_join_assert() to send assert join message when N2 is down, so keep trying to send message to N2 until find N2 is down send assert join message to N3, but connection is down with N3, so it may take a while become the recovery master for N2 and send begin reco message to other nodes in domain map but no N1 connection with N3 is rebuild, then send assert join to N4 call dlm_assert_joined_handler(), add N1 to domain_map dlm recovery done, send finalize message to nodes in domain map, including N1 receiving finalize message, trigger the BUG() because recovery master mismatch. Signed-off-by: joyce.xue Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmdomain.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index c973690..8d46907 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -959,6 +959,14 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data, * domain. Set him in the map and clean up our * leftover join state. */ BUG_ON(dlm->joining_node != assert->node_idx); + + if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(0, "dlm recovery is ongoing, disallow join\n"); + spin_unlock(&dlm->spinlock); + spin_unlock(&dlm_domain_lock); + return -EAGAIN; + } + set_bit(assert->node_idx, dlm->domain_map); clear_bit(assert->node_idx, dlm->exit_domain_map); __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN); @@ -1517,6 +1525,7 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm, unsigned int node) { int status; + int ret; struct dlm_assert_joined assert_msg; mlog(0, "Sending join assert to node %u\n", node); @@ -1528,11 +1537,13 @@ static int dlm_send_one_join_assert(struct dlm_ctxt *dlm, status = o2net_send_message(DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY, &assert_msg, sizeof(assert_msg), node, - NULL); + &ret); if (status < 0) mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to " "node %u\n", status, DLM_ASSERT_JOINED_MSG, DLM_MOD_KEY, node); + else + status = ret; return status; } -- cgit v1.1 From b7ac233515c6263d6cb471d9e0f57bdd7ea36894 Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Wed, 4 Jun 2014 16:06:15 -0700 Subject: ocfs2: cleanup unused paramters in ocfs2_calc_new_backup_super Parameters new_clusters and first_new_cluster are not used in ocfs2_update_last_group_and_inode, so remove them. Signed-off-by: Joseph Qi Reviewed-by: joyce.xue Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/resize.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 822ebc1..168739c 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -53,8 +53,6 @@ */ static u16 ocfs2_calc_new_backup_super(struct inode *inode, struct ocfs2_group_desc *gd, - int new_clusters, - u32 first_new_cluster, u16 cl_cpg, int set) { @@ -127,8 +125,6 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, OCFS2_FEATURE_COMPAT_BACKUP_SB)) { backups = ocfs2_calc_new_backup_super(bm_inode, group, - new_clusters, - first_new_cluster, cl_cpg, 1); le16_add_cpu(&group->bg_free_bits_count, -1 * backups); } @@ -167,8 +163,6 @@ out_rollback: if (ret < 0) { ocfs2_calc_new_backup_super(bm_inode, group, - new_clusters, - first_new_cluster, cl_cpg, 0); le16_add_cpu(&group->bg_free_bits_count, backups); le16_add_cpu(&group->bg_bits, -1 * num_bits); -- cgit v1.1 From 17bf1418b78d9c51370f29c2b840f7d0a1bf311a Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Wed, 4 Jun 2014 16:06:17 -0700 Subject: ocfs2: fix incorrect i_size of global bitmap inode after resize Ocfs2 cluster size may be 1MB, which has 20 bits. When resize, the input new clusters is mostly the number of clusters in a group descriptor(32256). Since the input clusters is defined as type int, so it will overflow when shift left 20 bits and then lead to incorrect global bitmap i_size. Signed-off-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/resize.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 168739c..d5da6f62 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -153,7 +153,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, spin_lock(&OCFS2_I(bm_inode)->ip_lock); OCFS2_I(bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters); - le64_add_cpu(&fe->i_size, new_clusters << osb->s_clustersize_bits); + le64_add_cpu(&fe->i_size, (u64)new_clusters << osb->s_clustersize_bits); spin_unlock(&OCFS2_I(bm_inode)->ip_lock); i_size_write(bm_inode, le64_to_cpu(fe->i_size)); @@ -563,7 +563,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) spin_lock(&OCFS2_I(main_bm_inode)->ip_lock); OCFS2_I(main_bm_inode)->ip_clusters = le32_to_cpu(fe->i_clusters); - le64_add_cpu(&fe->i_size, input->clusters << osb->s_clustersize_bits); + le64_add_cpu(&fe->i_size, (u64)input->clusters << osb->s_clustersize_bits); spin_unlock(&OCFS2_I(main_bm_inode)->ip_lock); i_size_write(main_bm_inode, le64_to_cpu(fe->i_size)); -- cgit v1.1 From e72db989e1c01fde28aabf7fd29faeaa08538e24 Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Wed, 4 Jun 2014 16:06:24 -0700 Subject: ocfs2: remove some unused code dlm_recovery_ctxt.received is unused. ocfs2_should_refresh_lock_res() can only return 0 or 1, so the error handling code in ocfs2_super_lock() is unneeded. Signed-off-by: joyce.xue Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmcommon.h | 1 - fs/ocfs2/dlm/dlmdomain.c | 1 - fs/ocfs2/dlmglue.c | 5 ----- 3 files changed, 7 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index e051776..a106b3f 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -108,7 +108,6 @@ static inline int dlm_is_recovery_lock(const char *lock_name, int name_len) struct dlm_recovery_ctxt { struct list_head resources; - struct list_head received; struct list_head node_data; u8 new_master; u8 dead_node; diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 8d46907..39efc505 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -2034,7 +2034,6 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, INIT_LIST_HEAD(&dlm->list); INIT_LIST_HEAD(&dlm->dirty_list); INIT_LIST_HEAD(&dlm->reco.resources); - INIT_LIST_HEAD(&dlm->reco.received); INIT_LIST_HEAD(&dlm->reco.node_data); INIT_LIST_HEAD(&dlm->purge_list); INIT_LIST_HEAD(&dlm->dlm_domain_handlers); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 6bd690b..52cfe99 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2544,11 +2544,6 @@ int ocfs2_super_lock(struct ocfs2_super *osb, * refreshed, so we do it here. Of course, making sense of * everything is up to the caller :) */ status = ocfs2_should_refresh_lock_res(lockres); - if (status < 0) { - ocfs2_cluster_unlock(osb, lockres, level); - mlog_errno(status); - goto bail; - } if (status) { status = ocfs2_refresh_slot_info(osb); -- cgit v1.1 From bdbeacdea24bad95bb72b6712fd9f716206c3142 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:25 -0700 Subject: fs/9p/v9fs.c: add __init to v9fs_sysfs_init v9fs_sysfs_init is only called by __init init_v9fs Signed-off-by: Fabian Frederick Cc: Eric Van Hensbergen Cc: Ron Minnich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/v9fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 14da825..6894b08 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -537,7 +537,7 @@ static struct attribute_group v9fs_attr_group = { * */ -static int v9fs_sysfs_init(void) +static int __init v9fs_sysfs_init(void) { v9fs_kobj = kobject_create_and_add("9p", fs_kobj); if (!v9fs_kobj) -- cgit v1.1 From fd2916bd77109b69891573fd1e1205ecc619893e Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:26 -0700 Subject: fs/9p: kerneldoc fixes Function parameters comment fixing. Signed-off-by: Fabian Frederick Cc: Eric Van Hensbergen Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_dir.c | 1 - fs/9p/vfs_file.c | 4 ++-- fs/9p/vfs_inode.c | 6 +++--- fs/9p/vfs_inode_dotl.c | 7 +++---- 4 files changed, 8 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 4d0c2e0..0b3bfa3 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -42,7 +42,6 @@ /** * struct p9_rdir - readdir accounting - * @mutex: mutex protecting readdir * @head: start offset of current dirread buffer * @tail: end offset of current dirread buffer * @buf: dirread buffer diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 59e3fe3..96e5507 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -681,7 +681,7 @@ v9fs_direct_read(struct file *filp, char __user *udata, size_t count, /** * v9fs_cached_file_read - read from a file * @filp: file pointer to read - * @udata: user data buffer to read data into + * @data: user data buffer to read data into * @count: size of buffer * @offset: offset at which to read data * @@ -698,7 +698,7 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count, /** * v9fs_mmap_file_read - read from a file * @filp: file pointer to read - * @udata: user data buffer to read data into + * @data: user data buffer to read data into * @count: size of buffer * @offset: offset at which to read data * diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 53161ec..00d140f 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -580,7 +580,7 @@ static int v9fs_at_to_dotl_flags(int flags) * v9fs_remove - helper function to remove files and directories * @dir: directory inode that is being deleted * @dentry: dentry that is being deleted - * @rmdir: removing a directory + * @flags: removing a directory * */ @@ -778,7 +778,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode * v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode * @dir: inode that is being walked from * @dentry: dentry that is being walked to? - * @nameidata: path data + * @flags: lookup flags (unused) * */ @@ -1324,7 +1324,7 @@ v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p) * v9fs_vfs_mkspecial - create a special file * @dir: inode to create special file in * @dentry: dentry to create - * @mode: mode to create special file + * @perm: mode to create special file * @extension: 9p2000.u format extension string representing special file * */ diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 59dc8e8..1fa85aa 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -226,7 +226,7 @@ int v9fs_open_to_dotl_flags(int flags) * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol. * @dir: directory inode that is being created * @dentry: dentry that is being deleted - * @mode: create permissions + * @omode: create permissions * */ @@ -375,7 +375,7 @@ err_clunk_old_fid: * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked - * @mode: mode for new directory + * @omode: mode for new directory * */ @@ -607,7 +607,6 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) * v9fs_stat2inode_dotl - populate an inode structure with stat info * @stat: stat structure * @inode: inode to populate - * @sb: superblock of filesystem * */ @@ -808,7 +807,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, * v9fs_vfs_mknod_dotl - create a special file * @dir: inode destination for new link * @dentry: dentry for file - * @mode: mode for creation + * @omode: mode for creation * @rdev: device associated with special file * */ -- cgit v1.1 From ac13a829f6adb674015ab399594c089990104af7 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:06:27 -0700 Subject: fs/libfs.c: add generic data flush to fsync Description by Jan Kara: "A lot of older filesystems don't properly flush volatile disk caches on fsync(2) which can lead to loss of fsynced data after power failure. This patch makes generic_file_fsync() issue proper cache flush to fix the problem. Sysadmin can use /sys/devices/.../cache_type to tell the system it should not send the cache flush." [akpm@linux-foundation.org: nuke ifdef] [akpm@linux-foundation.org: fix warning] Signed-off-by: Fabian Frederick Suggested-by: Jan Kara Suggested-by: Christoph Hellwig Cc: Jan Kara Cc: Christoph Hellwig Cc: Alexander Viro Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/libfs.c | 34 +++++++++++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/libfs.c b/fs/libfs.c index a184424..88e3e00 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -3,6 +3,7 @@ * Library for filesystems writers. */ +#include #include #include #include @@ -923,16 +924,19 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** - * generic_file_fsync - generic fsync implementation for simple filesystems + * __generic_file_fsync - generic fsync implementation for simple filesystems + * * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ -int generic_file_fsync(struct file *file, loff_t start, loff_t end, - int datasync) +int __generic_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync) { struct inode *inode = file->f_mapping->host; int err; @@ -952,10 +956,34 @@ int generic_file_fsync(struct file *file, loff_t start, loff_t end, err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; + out: mutex_unlock(&inode->i_mutex); return ret; } +EXPORT_SYMBOL(__generic_file_fsync); + +/** + * generic_file_fsync - generic fsync implementation for simple filesystems + * with flush + * @file: file to synchronize + * @start: start offset in bytes + * @end: end offset in bytes (inclusive) + * @datasync: only synchronize essential metadata if true + * + */ + +int generic_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file->f_mapping->host; + int err; + + err = __generic_file_fsync(file, start, end, datasync); + if (err) + return err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); +} EXPORT_SYMBOL(generic_file_fsync); /** -- cgit v1.1 From c86c97ff42cd6c6d1bd29eca4dfabeaf2b7f1020 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 4 Jun 2014 16:06:43 -0700 Subject: mm: softdirty: clear VM_SOFTDIRTY flag inside clear_refs_write() instead of clear_soft_dirty() clear_refs_write() is called earlier than clear_soft_dirty() and it is more natural to clear VM_SOFTDIRTY (which belongs to VMA entry but not PTEs) that early instead of clearing it a way deeper inside call chain. Signed-off-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: Hugh Dickins Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 442177b..2101ce4 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -737,9 +737,6 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, ptent = pte_file_clear_soft_dirty(ptent); } - if (vma->vm_flags & VM_SOFTDIRTY) - vma->vm_flags &= ~VM_SOFTDIRTY; - set_pte_at(vma->vm_mm, addr, pte, ptent); #endif } @@ -807,8 +804,9 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, if (type == CLEAR_REFS_SOFT_DIRTY) { soft_dirty_cleared = true; - pr_warn_once("The pagemap bits 55-60 has changed their meaning! " - "See the linux/Documentation/vm/pagemap.txt for details.\n"); + pr_warn_once("The pagemap bits 55-60 has changed their meaning!" + " See the linux/Documentation/vm/pagemap.txt for " + "details.\n"); } task = get_proc_task(file_inode(file)); @@ -839,11 +837,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, * * Writing 3 to /proc/pid/clear_refs only affects file * mapped pages. + * + * Writing 4 to /proc/pid/clear_refs affects all pages. */ if (type == CLEAR_REFS_ANON && vma->vm_file) continue; if (type == CLEAR_REFS_MAPPED && !vma->vm_file) continue; + if (type == CLEAR_REFS_SOFT_DIRTY) { + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + } walk_page_range(vma->vm_start, vma->vm_end, &clear_refs_walk); } -- cgit v1.1 From 9b857d26d08f00971997cd21aa491e27e0c84ce3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 4 Jun 2014 16:07:21 -0700 Subject: fs/hugetlbfs/inode.c: complete conversion to pr_foo() Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index e19d4c0..2611824 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -6,6 +6,8 @@ * Copyright (C) 2002 Linus Torvalds. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -823,8 +825,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) ps = memparse(args[0].from, &rest); pconfig->hstate = size_to_hstate(ps); if (!pconfig->hstate) { - printk(KERN_ERR - "hugetlbfs: Unsupported page size %lu MB\n", + pr_err("Unsupported page size %lu MB\n", ps >> 20); return -EINVAL; } @@ -832,8 +833,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) } default: - printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n", - p); + pr_err("Bad mount option: \"%s\"\n", p); return -EINVAL; break; } @@ -853,8 +853,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) return 0; bad_val: - printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n", - args[0].from, p); + pr_err("Bad value '%s' for mount option '%s'\n", args[0].from, p); return -EINVAL; } @@ -970,8 +969,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, *user = current_user(); if (user_shm_lock(size, *user)) { task_lock(current); - printk_once(KERN_WARNING - "%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n", + pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n", current->comm, current->pid); task_unlock(current); } else { @@ -1031,7 +1029,7 @@ static int __init init_hugetlbfs_fs(void) int i; if (!hugepages_supported()) { - pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + pr_info("disabling because there are no supported hugepage sizes\n"); return -ENOTSUPP; } @@ -1060,7 +1058,7 @@ static int __init init_hugetlbfs_fs(void) buf); if (IS_ERR(hugetlbfs_vfsmount[i])) { - pr_err("hugetlb: Cannot mount internal hugetlbfs for " + pr_err("Cannot mount internal hugetlbfs for " "page size %uK", ps_kb); error = PTR_ERR(hugetlbfs_vfsmount[i]); hugetlbfs_vfsmount[i] = NULL; -- cgit v1.1 From 1b938c0827478df268d2336469ec48d400a2eb3e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:43 -0700 Subject: fs/buffer.c: remove block_write_full_page_endio() The last in-tree caller of block_write_full_page_endio() was removed in January 2013. It's time to remove the EXPORT_SYMBOL, which leaves block_write_full_page() as the only caller of block_write_full_page_endio(), so inline block_write_full_page_endio() into block_write_full_page(). Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Cc: Dave Chinner Cc: Dheeraj Reddy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 21 +++++---------------- fs/ext4/page-io.c | 2 +- fs/ocfs2/file.c | 2 +- 3 files changed, 7 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index 6a8110c..e33f8d5 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2879,10 +2879,9 @@ EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces - * this form passes in the end_io handler used to finish the IO. */ -int block_write_full_page_endio(struct page *page, get_block_t *get_block, - struct writeback_control *wbc, bh_end_io_t *handler) +int block_write_full_page(struct page *page, get_block_t *get_block, + struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); @@ -2892,7 +2891,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, - handler); + end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_CACHE_SIZE-1); @@ -2915,18 +2914,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_CACHE_SIZE); - return __block_write_full_page(inode, page, get_block, wbc, handler); -} -EXPORT_SYMBOL(block_write_full_page_endio); - -/* - * The generic ->writepage function for buffer-backed address_spaces - */ -int block_write_full_page(struct page *page, get_block_t *get_block, - struct writeback_control *wbc) -{ - return block_write_full_page_endio(page, get_block, wbc, - end_buffer_async_write); + return __block_write_full_page(inode, page, get_block, wbc, + end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index c18d95b..1a64e7a 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -429,7 +429,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, block_start = bh_offset(bh); if (block_start >= len) { /* - * Comments copied from block_write_full_page_endio: + * Comments copied from block_write_full_page: * * The page straddles i_size. It must be zeroed out on * each and every writepage invocation because it may diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8970dcf..8eb6e57 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -828,7 +828,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* * fs-writeback will release the dirty pages without page lock * whose offset are over inode size, the release happens at - * block_write_full_page_endio(). + * block_write_full_page(). */ i_size_write(inode, abs_to); inode->i_blocks = ocfs2_inode_sector_count(inode); -- cgit v1.1 From 90768eee4565adb28ea28b4ac5081c676a8fe1f2 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:44 -0700 Subject: fs/mpage.c: factor clean_buffers() out of __mpage_writepage() __mpage_writepage() is over 200 lines long, has 20 local variables, four goto labels and could desperately use simplification. Splitting clean_buffers() into a helper function improves matters a little, removing 20+ lines from it. Signed-off-by: Matthew Wilcox Cc: Dave Chinner Cc: Dheeraj Reddy Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mpage.c | 54 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 30 insertions(+), 24 deletions(-) (limited to 'fs') diff --git a/fs/mpage.c b/fs/mpage.c index 4979ffa..4cc9c5d 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -439,6 +439,35 @@ struct mpage_data { unsigned use_writepage; }; +/* + * We have our BIO, so we can now mark the buffers clean. Make + * sure to only clean buffers which we know we'll be writing. + */ +static void clean_buffers(struct page *page, unsigned first_unmapped) +{ + unsigned buffer_counter = 0; + struct buffer_head *bh, *head; + if (!page_has_buffers(page)) + return; + head = page_buffers(page); + bh = head; + + do { + if (buffer_counter++ == first_unmapped) + break; + clear_buffer_dirty(bh); + bh = bh->b_this_page; + } while (bh != head); + + /* + * we cannot drop the bh if the page is not uptodate or a concurrent + * readpage would fail to serialize with the bh and it would read from + * disk before we reach the platter. + */ + if (buffer_heads_over_limit && PageUptodate(page)) + try_to_free_buffers(page); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -591,30 +620,7 @@ alloc_new: goto alloc_new; } - /* - * OK, we have our BIO, so we can now mark the buffers clean. Make - * sure to only clean buffers which we know we'll be writing. - */ - if (page_has_buffers(page)) { - struct buffer_head *head = page_buffers(page); - struct buffer_head *bh = head; - unsigned buffer_counter = 0; - - do { - if (buffer_counter++ == first_unmapped) - break; - clear_buffer_dirty(bh); - bh = bh->b_this_page; - } while (bh != head); - - /* - * we cannot drop the bh if the page is not uptodate - * or a concurrent readpage would fail to serialize with the bh - * and it would read from disk before we reach the platter. - */ - if (buffer_heads_over_limit && PageUptodate(page)) - try_to_free_buffers(page); - } + clean_buffers(page, first_unmapped); BUG_ON(PageWriteback(page)); set_page_writeback(page); -- cgit v1.1 From 57d998456ae8680ed446aa1993f45f4d8a9a5973 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:45 -0700 Subject: fs/mpage.c: factor page_endio() out of mpage_end_io() page_endio() takes care of updating all the appropriate page flags once I/O has finished to a page. Switch to using mapping_set_error() instead of setting AS_EIO directly; this will handle thin-provisioned devices correctly. Signed-off-by: Matthew Wilcox Cc: Dave Chinner Cc: Dheeraj Reddy Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/mpage.c | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/mpage.c b/fs/mpage.c index 4cc9c5d..10da0da 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -48,23 +48,7 @@ static void mpage_end_io(struct bio *bio, int err) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - - if (bio_data_dir(bio) == READ) { - if (!err) { - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); - } else { /* bio_data_dir(bio) == WRITE */ - if (err) { - SetPageError(page); - if (page->mapping) - set_bit(AS_EIO, &page->mapping->flags); - } - end_page_writeback(page); - } + page_endio(page, bio_data_dir(bio), err); } bio_put(bio); -- cgit v1.1 From 47a191fd38ebddb1bd1510ec2bc1085c578c8868 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jun 2014 16:07:46 -0700 Subject: fs/block_dev.c: add bdev_read_page() and bdev_write_page() A block device driver may choose to provide a rw_page operation. These will be called when the filesystem is attempting to do page sized I/O to page cache pages (ie not for direct I/O). This does preclude I/Os that are larger than page size, so this may only be a performance gain for some devices. Signed-off-by: Matthew Wilcox Tested-by: Dheeraj Reddy Cc: Dave Chinner Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/mpage.c | 12 +++++++++++ 2 files changed, 75 insertions(+) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 552a8d1..83fba15 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -363,6 +363,69 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(blkdev_fsync); +/** + * bdev_read_page() - Start reading a page from a block device + * @bdev: The device to read the page from + * @sector: The offset on the device to read the page to (need not be aligned) + * @page: The page to read + * + * On entry, the page should be locked. It will be unlocked when the page + * has been read. If the block driver implements rw_page synchronously, + * that will be true on exit from this function, but it need not be. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to read this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_read_page(struct block_device *bdev, sector_t sector, + struct page *page) +{ + const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page) + return -EOPNOTSUPP; + return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ); +} +EXPORT_SYMBOL_GPL(bdev_read_page); + +/** + * bdev_write_page() - Start writing a page to a block device + * @bdev: The device to write the page to + * @sector: The offset on the device to write the page to (need not be aligned) + * @page: The page to write + * @wbc: The writeback_control for the write + * + * On entry, the page should be locked and not currently under writeback. + * On exit, if the write started successfully, the page will be unlocked and + * under writeback. If the write failed already (eg the driver failed to + * queue the page to the device), the page will still be locked. If the + * caller is a ->writepage implementation, it will need to unlock the page. + * + * Errors returned by this function are usually "soft", eg out of memory, or + * queue full; callers should try a different route to write this page rather + * than propagate an error back up the stack. + * + * Return: negative errno if an error occurs, 0 if submission was successful. + */ +int bdev_write_page(struct block_device *bdev, sector_t sector, + struct page *page, struct writeback_control *wbc) +{ + int result; + int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE; + const struct block_device_operations *ops = bdev->bd_disk->fops; + if (!ops->rw_page) + return -EOPNOTSUPP; + set_page_writeback(page); + result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw); + if (result) + end_page_writeback(page); + else + unlock_page(page); + return result; +} +EXPORT_SYMBOL_GPL(bdev_write_page); + /* * pseudo-fs */ diff --git a/fs/mpage.c b/fs/mpage.c index 10da0da..5f9ed62 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -269,6 +269,11 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages, alloc_new: if (bio == NULL) { + if (first_hole == blocks_per_page) { + if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9), + page)) + goto out; + } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), min_t(int, nr_pages, bio_get_nr_vecs(bdev)), GFP_KERNEL); @@ -587,6 +592,13 @@ page_is_mapped: alloc_new: if (bio == NULL) { + if (first_unmapped == blocks_per_page) { + if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), + page, wbc)) { + clean_buffers(page, first_unmapped); + goto out; + } + } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH); if (bio == NULL) -- cgit v1.1 From b745bc85f21ea707e4ea1a91948055fa3e72c77b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:22 -0700 Subject: mm: page_alloc: convert hot/cold parameter and immediate callers to bool cold is a bool, make it one. Make the likely case the "if" part of the block instead of the else as according to the optimisation manual this is preferred. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index aac71ce..098f97b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1614,7 +1614,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - release_pages(req->pages, req->num_pages, 0); + release_pages(req->pages, req->num_pages, false); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, -- cgit v1.1 From e7470ee89f003634a88e7b5e5a7b65b3025987de Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:29 -0700 Subject: fs: buffer: do not use unnecessary atomic operations when discarding buffers Discarding buffers uses a bunch of atomic operations when discarding buffers because ...... I can't think of a reason. Use a cmpxchg loop to clear all the necessary flags. In most (all?) cases this will be a single atomic operations. [akpm@linux-foundation.org: move BUFFER_FLAGS_DISCARD into the .c file] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index e33f8d5..0d3e8d5 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1483,16 +1483,27 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ + +/* Bits that are cleared during an invalidate */ +#define BUFFER_FLAGS_DISCARD \ + (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ + 1 << BH_Delay | 1 << BH_Unwritten) + static void discard_buffer(struct buffer_head * bh) { + unsigned long b_state, b_state_old; + lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; - clear_buffer_mapped(bh); - clear_buffer_req(bh); - clear_buffer_new(bh); - clear_buffer_delay(bh); - clear_buffer_unwritten(bh); + b_state = bh->b_state; + for (;;) { + b_state_old = cmpxchg(&bh->b_state, b_state, + (b_state & ~BUFFER_FLAGS_DISCARD)); + if (b_state_old == b_state) + break; + b_state = b_state_old; + } unlock_buffer(bh); } -- cgit v1.1 From 2457aec63745e235bcafb7ef312b182d8682f0fc Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:31 -0700 Subject: mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Tested-by: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/extent_io.c | 11 ++++++----- fs/btrfs/file.c | 5 +++-- fs/buffer.c | 7 ++++--- fs/ext4/mballoc.c | 14 ++++++++------ fs/f2fs/checkpoint.c | 3 --- fs/f2fs/node.c | 2 -- fs/fuse/file.c | 2 -- fs/gfs2/aops.c | 1 - fs/gfs2/meta_io.c | 4 ++-- fs/ntfs/attrib.c | 1 - fs/ntfs/file.c | 1 - 11 files changed, 23 insertions(+), 28 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f29a54e..4cd0ac9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4510,7 +4510,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4519,7 +4520,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4533,7 +4535,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4581,7 +4583,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4596,7 +4598,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ae6af07..74272a3 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -470,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } diff --git a/fs/buffer.c b/fs/buffer.c index 0d3e8d5..eba6e4f 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c8238a2..afe8a13 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 4aa521a..c405b8f 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -69,7 +69,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } @@ -137,13 +136,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type) if (!page) continue; if (PageUptodate(page)) { - mark_page_accessed(page); f2fs_put_page(page, 1); continue; } f2fs_submit_page_mbio(sbi, page, blk_addr, &fio); - mark_page_accessed(page); f2fs_put_page(page, 0); } out: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a161e95..57caa6e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -967,7 +967,6 @@ repeat: goto repeat; } got_it: - mark_page_accessed(page); return page; } @@ -1022,7 +1021,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f680d2c..903cbc9 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1089,8 +1089,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 5a49b03..492123c 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -577,7 +577,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 2cf09b6..b984a6e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -136,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -153,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fe..250ed5b 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a..86ddab9 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) -- cgit v1.1 From 422b2448fc86bf678f5d398389e41e0f169541d5 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:10:39 -0700 Subject: fs/hugetlbfs/inode.c: add static to hugetlbfs_i_mmap_mutex_key hugetlbfs_i_mmap_mutex_key is only used in inode.c Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 2611824..b242759 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -477,7 +477,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, * annotation because huge_pmd_share() does an allocation under * i_mmap_mutex. */ -struct lock_class_key hugetlbfs_i_mmap_mutex_key; +static struct lock_class_key hugetlbfs_i_mmap_mutex_key; static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct inode *dir, -- cgit v1.1 From be1d2cf5e36b1de3c8e17428885dcad4ca929886 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:10:39 -0700 Subject: fs/hugetlbfs/inode.c: use static const for dentry_operations ...like other filesystems. Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index b242759..cc81d25 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -938,7 +938,7 @@ static int get_hstate_idx(int page_size_log) return h - hstates; } -static struct dentry_operations anon_ops = { +static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; -- cgit v1.1 From 6e6870d4fd19e25332e7d975604497c8568949d9 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:10:40 -0700 Subject: fs/hugetlbfs/inode.c: remove null test before kfree Fix checkpatch warning: WARNING: kfree(NULL) is safe this check is probably not required Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index cc81d25..1e2872b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -901,8 +901,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) goto out_free; return 0; out_free: - if (sbinfo->spool) - kfree(sbinfo->spool); + kfree(sbinfo->spool); kfree(sbinfo); return -ENOMEM; } -- cgit v1.1 From 28f2cd4f6da24a1aa06c226618ed5ad69e13df64 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 4 Jun 2014 16:10:46 -0700 Subject: fs/superblock: unregister sb shrinker before ->kill_sb() This series is aimed at regressions noticed during reclaim activity. The first two patches are shrinker patches that were posted ages ago but never merged for reasons that are unclear to me. I'm posting them again to see if there was a reason they were dropped or if they just got lost. Dave? Time? The last patch adjusts proportional reclaim. Yuanhan Liu, can you retest the vm scalability test cases on a larger machine? Hugh, does this work for you on the memcg test cases? Based on ext4, I get the following results but unfortunately my larger test machines are all unavailable so this is based on a relatively small machine. postmark 3.15.0-rc5 3.15.0-rc5 vanilla proportion-v1r4 Ops/sec Transactions 21.00 ( 0.00%) 25.00 ( 19.05%) Ops/sec FilesCreate 39.00 ( 0.00%) 45.00 ( 15.38%) Ops/sec CreateTransact 10.00 ( 0.00%) 12.00 ( 20.00%) Ops/sec FilesDeleted 6202.00 ( 0.00%) 6202.00 ( 0.00%) Ops/sec DeleteTransact 11.00 ( 0.00%) 12.00 ( 9.09%) Ops/sec DataRead/MB 25.97 ( 0.00%) 30.02 ( 15.59%) Ops/sec DataWrite/MB 49.99 ( 0.00%) 57.78 ( 15.58%) ffsb (mail server simulator) 3.15.0-rc5 3.15.0-rc5 vanilla proportion-v1r4 Ops/sec readall 9402.63 ( 0.00%) 9805.74 ( 4.29%) Ops/sec create 4695.45 ( 0.00%) 4781.39 ( 1.83%) Ops/sec delete 173.72 ( 0.00%) 177.23 ( 2.02%) Ops/sec Transactions 14271.80 ( 0.00%) 14764.37 ( 3.45%) Ops/sec Read 37.00 ( 0.00%) 38.50 ( 4.05%) Ops/sec Write 18.20 ( 0.00%) 18.50 ( 1.65%) dd of a large file 3.15.0-rc5 3.15.0-rc5 vanilla proportion-v1r4 WallTime DownloadTar 75.00 ( 0.00%) 61.00 ( 18.67%) WallTime DD 423.00 ( 0.00%) 401.00 ( 5.20%) WallTime Delete 2.00 ( 0.00%) 5.00 (-150.00%) stutter (times mmap latency during large amounts of IO) 3.15.0-rc5 3.15.0-rc5 vanilla proportion-v1r4 Unit >5ms Delays 80252.0000 ( 0.00%) 81523.0000 ( -1.58%) Unit Mmap min 8.2118 ( 0.00%) 8.3206 ( -1.33%) Unit Mmap mean 17.4614 ( 0.00%) 17.2868 ( 1.00%) Unit Mmap stddev 24.9059 ( 0.00%) 34.6771 (-39.23%) Unit Mmap max 2811.6433 ( 0.00%) 2645.1398 ( 5.92%) Unit Mmap 90% 20.5098 ( 0.00%) 18.3105 ( 10.72%) Unit Mmap 93% 22.9180 ( 0.00%) 20.1751 ( 11.97%) Unit Mmap 95% 25.2114 ( 0.00%) 22.4988 ( 10.76%) Unit Mmap 99% 46.1430 ( 0.00%) 43.5952 ( 5.52%) Unit Ideal Tput 85.2623 ( 0.00%) 78.8906 ( 7.47%) Unit Tput min 44.0666 ( 0.00%) 43.9609 ( 0.24%) Unit Tput mean 45.5646 ( 0.00%) 45.2009 ( 0.80%) Unit Tput stddev 0.9318 ( 0.00%) 1.1084 (-18.95%) Unit Tput max 46.7375 ( 0.00%) 46.7539 ( -0.04%) This patch (of 3): We will like to unregister the sb shrinker before ->kill_sb(). This will allow cached objects to be counted without call to grab_super_passive() to update ref count on sb. We want to avoid locking during memory reclamation especially when we are skipping the memory reclaim when we are out of cached objects. This is safe because grab_super_passive does a try-lock on the sb->s_umount now, and so if we are in the unmount process, it won't ever block. That means what used to be a deadlock and races we were avoiding by using grab_super_passive() is now: shrinker umount down_read(shrinker_rwsem) down_write(sb->s_umount) shrinker_unregister down_write(shrinker_rwsem) grab_super_passive(sb) down_read_trylock(sb->s_umount) .... up_read(shrinker_rwsem) up_write(shrinker_rwsem) ->kill_sb() .... So it is safe to deregister the shrinker before ->kill_sb(). Signed-off-by: Tim Chen Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Hugh Dickins Cc: Dave Chinner Tested-by: Yuanhan Liu Cc: Bob Liu Cc: Jan Kara Acked-by: Rik van Riel Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/super.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/super.c b/fs/super.c index 48377f7..a852b1a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -276,10 +276,8 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { cleancache_invalidate_fs(s); - fs->kill_sb(s); - - /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); + fs->kill_sb(s); put_filesystem(fs); put_super(s); -- cgit v1.1 From d23da150a37c9fe3cc83dbaf71b3e37fd434ed52 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Wed, 4 Jun 2014 16:10:47 -0700 Subject: fs/superblock: avoid locking counting inodes and dentries before reclaiming them We remove the call to grab_super_passive in call to super_cache_count. This becomes a scalability bottleneck as multiple threads are trying to do memory reclamation, e.g. when we are doing large amount of file read and page cache is under pressure. The cached objects quickly got reclaimed down to 0 and we are aborting the cache_scan() reclaim. But counting creates a log jam acquiring the sb_lock. We are holding the shrinker_rwsem which ensures the safety of call to list_lru_count_node() and s_op->nr_cached_objects. The shrinker is unregistered now before ->kill_sb() so the operation is safe when we are doing unmount. The impact will depend heavily on the machine and the workload but for a small machine using postmark tuned to use 4xRAM size the results were 3.15.0-rc5 3.15.0-rc5 vanilla shrinker-v1r1 Ops/sec Transactions 21.00 ( 0.00%) 24.00 ( 14.29%) Ops/sec FilesCreate 39.00 ( 0.00%) 44.00 ( 12.82%) Ops/sec CreateTransact 10.00 ( 0.00%) 12.00 ( 20.00%) Ops/sec FilesDeleted 6202.00 ( 0.00%) 6202.00 ( 0.00%) Ops/sec DeleteTransact 11.00 ( 0.00%) 12.00 ( 9.09%) Ops/sec DataRead/MB 25.97 ( 0.00%) 29.10 ( 12.05%) Ops/sec DataWrite/MB 49.99 ( 0.00%) 56.02 ( 12.06%) ffsb running in a configuration that is meant to simulate a mail server showed 3.15.0-rc5 3.15.0-rc5 vanilla shrinker-v1r1 Ops/sec readall 9402.63 ( 0.00%) 9567.97 ( 1.76%) Ops/sec create 4695.45 ( 0.00%) 4735.00 ( 0.84%) Ops/sec delete 173.72 ( 0.00%) 179.83 ( 3.52%) Ops/sec Transactions 14271.80 ( 0.00%) 14482.81 ( 1.48%) Ops/sec Read 37.00 ( 0.00%) 37.60 ( 1.62%) Ops/sec Write 18.20 ( 0.00%) 18.30 ( 0.55%) Signed-off-by: Tim Chen Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Hugh Dickins Cc: Dave Chinner Tested-by: Yuanhan Liu Cc: Bob Liu Cc: Jan Kara Acked-by: Rik van Riel Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/super.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/super.c b/fs/super.c index a852b1a..d20d5b1 100644 --- a/fs/super.c +++ b/fs/super.c @@ -112,9 +112,14 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); - if (!grab_super_passive(sb)) - return 0; - + /* + * Don't call grab_super_passive as it is a potential + * scalability bottleneck. The counts could get updated + * between super_cache_count and super_cache_scan anyway. + * Call to super_cache_count with shrinker_rwsem held + * ensures the safety of call to list_lru_count_node() and + * s_op->nr_cached_objects(). + */ if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc->nid); @@ -125,7 +130,6 @@ static unsigned long super_cache_count(struct shrinker *shrink, sc->nid); total_objects = vfs_pressure_ratio(total_objects); - drop_super(sb); return total_objects; } -- cgit v1.1 From e37dcbfbb2b2365870cbdd12f9d505c52941f300 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:11:14 -0700 Subject: fs/efivarfs/super.c: use static const for dentry_operations ...like other filesystems. Signed-off-by: Fabian Frederick Cc: Matthew Garrett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/efivarfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index becc725..0a48886 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -83,7 +83,7 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) return 0; } -static struct dentry_operations efivarfs_d_ops = { +static const struct dentry_operations efivarfs_d_ops = { .d_compare = efivarfs_d_compare, .d_hash = efivarfs_d_hash, .d_delete = always_delete_dentry, -- cgit v1.1 From 00f01791e159ba7fb9d397c27d34377206157c6a Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:11:15 -0700 Subject: fs/exportfs/expfs.c: kernel-doc warning fixes Fixing 2 typo in function comments. Signed-off-by: Fabian Frederick Cc: Al Viro Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exportfs/expfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 48a359d..b01fbfb 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -259,7 +259,7 @@ static int filldir_one(void * __buf, const char * name, int len, /** * get_name - default export_operations->get_name function - * @dentry: the directory in which to find a name + * @path: the directory in which to find a name * @name: a pointer to a %NAME_MAX+1 char buffer to store the name * @child: the dentry for the child directory. * @@ -337,7 +337,7 @@ out: /** * export_encode_fh - default export_operations->encode_fh function * @inode: the object to encode - * @fh: where to store the file handle fragment + * @fid: where to store the file handle fragment * @max_len: maximum length to store there * @parent: parent directory inode, if wanted * -- cgit v1.1 From 179b87fb186b524ec75a5d54c0d7f25e8d559415 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:11 -0700 Subject: fs/efs: convert printk to pr_foo() Convert all except KERN_DEBUG (pr_debug doesn't work the same as printk(KERN_DEBUG and requires special check) Signed-off-by: Fabian Frederick Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/efs/dir.c | 8 ++++---- fs/efs/file.c | 10 ++++------ fs/efs/inode.c | 20 ++++++++++---------- fs/efs/namei.c | 6 +++--- fs/efs/super.c | 23 +++++++++++------------ 5 files changed, 32 insertions(+), 35 deletions(-) (limited to 'fs') diff --git a/fs/efs/dir.c b/fs/efs/dir.c index b72307c..46a9a60 100644 --- a/fs/efs/dir.c +++ b/fs/efs/dir.c @@ -26,7 +26,7 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) int slot; if (inode->i_size & (EFS_DIRBSIZE-1)) - printk(KERN_WARNING "EFS: WARNING: readdir(): directory size not a multiple of EFS_DIRBSIZE\n"); + pr_warn("EFS: WARNING: readdir(): directory size not a multiple of EFS_DIRBSIZE\n"); /* work out where this entry can be found */ block = ctx->pos >> EFS_DIRBSIZE_BITS; @@ -43,14 +43,14 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) bh = sb_bread(inode->i_sb, efs_bmap(inode, block)); if (!bh) { - printk(KERN_ERR "EFS: readdir(): failed to read dir block %d\n", block); + pr_err("EFS: readdir(): failed to read dir block %d\n", block); break; } dirblock = (struct efs_dir *) bh->b_data; if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) { - printk(KERN_ERR "EFS: readdir(): invalid directory block\n"); + pr_err("EFS: readdir(): invalid directory block\n"); brelse(bh); break; } @@ -80,7 +80,7 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) /* sanity check */ if (nameptr - (char *) dirblock + namelen > EFS_DIRBSIZE) { - printk(KERN_WARNING "EFS: directory entry %d exceeds directory block\n", slot); + pr_warn("EFS: directory entry %d exceeds directory block\n", slot); continue; } diff --git a/fs/efs/file.c b/fs/efs/file.c index 1ccb364..a75c710 100644 --- a/fs/efs/file.c +++ b/fs/efs/file.c @@ -22,7 +22,7 @@ int efs_get_block(struct inode *inode, sector_t iblock, /* * i have no idea why this happens as often as it does */ - printk(KERN_WARNING "EFS: bmap(): block %d >= %ld (filesize %ld)\n", + pr_warn("EFS: bmap(): block %d >= %ld (filesize %ld)\n", block, inode->i_blocks, inode->i_size); @@ -38,7 +38,7 @@ int efs_get_block(struct inode *inode, sector_t iblock, int efs_bmap(struct inode *inode, efs_block_t block) { if (block < 0) { - printk(KERN_WARNING "EFS: bmap(): block < 0\n"); + pr_warn("EFS: bmap(): block < 0\n"); return 0; } @@ -48,10 +48,8 @@ int efs_bmap(struct inode *inode, efs_block_t block) { /* * i have no idea why this happens as often as it does */ - printk(KERN_WARNING "EFS: bmap(): block %d >= %ld (filesize %ld)\n", - block, - inode->i_blocks, - inode->i_size); + pr_warn("EFS: bmap(): block %d >= %ld (filesize %ld)\n", + block, inode->i_blocks, inode->i_size); #endif return 0; } diff --git a/fs/efs/inode.c b/fs/efs/inode.c index d15ccf2..54f1cbb 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -89,7 +89,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) bh = sb_bread(inode->i_sb, block); if (!bh) { - printk(KERN_WARNING "EFS: bread() failed at block %d\n", block); + pr_warn("EFS: bread() failed at block %d\n", block); goto read_inode_error; } @@ -130,7 +130,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) for(i = 0; i < EFS_DIRECTEXTENTS; i++) { extent_copy(&(efs_inode->di_u.di_extents[i]), &(in->extents[i])); if (i < in->numextents && in->extents[i].cooked.ex_magic != 0) { - printk(KERN_WARNING "EFS: extent %d has bad magic number in inode %lu\n", i, inode->i_ino); + pr_warn("EFS: extent %d has bad magic number in inode %lu\n", i, inode->i_ino); brelse(bh); goto read_inode_error; } @@ -162,7 +162,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) init_special_inode(inode, inode->i_mode, device); break; default: - printk(KERN_WARNING "EFS: unsupported inode mode %o\n", inode->i_mode); + pr_warn("EFS: unsupported inode mode %o\n", inode->i_mode); goto read_inode_error; break; } @@ -171,7 +171,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) return inode; read_inode_error: - printk(KERN_WARNING "EFS: failed to read inode %lu\n", inode->i_ino); + pr_warn("EFS: failed to read inode %lu\n", inode->i_ino); iget_failed(inode); return ERR_PTR(-EIO); } @@ -216,7 +216,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { /* if we only have one extent then nothing can be found */ if (in->numextents == 1) { - printk(KERN_ERR "EFS: map_block() failed to map (1 extent)\n"); + pr_err("EFS: map_block() failed to map (1 extent)\n"); return 0; } @@ -234,7 +234,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { } } - printk(KERN_ERR "EFS: map_block() failed to map block %u (dir)\n", block); + pr_err("EFS: map_block() failed to map block %u (dir)\n", block); return 0; } @@ -262,7 +262,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { if (dirext == direxts) { /* should never happen */ - printk(KERN_ERR "EFS: couldn't find direct extent for indirect extent %d (block %u)\n", cur, block); + pr_err("EFS: couldn't find direct extent for indirect extent %d (block %u)\n", cur, block); if (bh) brelse(bh); return 0; } @@ -279,7 +279,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { bh = sb_bread(inode->i_sb, iblock); if (!bh) { - printk(KERN_ERR "EFS: bread() failed at block %d\n", iblock); + pr_err("EFS: bread() failed at block %d\n", iblock); return 0; } #ifdef DEBUG @@ -294,7 +294,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { extent_copy(&(exts[ioffset]), &ext); if (ext.cooked.ex_magic != 0) { - printk(KERN_ERR "EFS: extent %d has bad magic number in block %d\n", cur, iblock); + pr_err("EFS: extent %d has bad magic number in block %d\n", cur, iblock); if (bh) brelse(bh); return 0; } @@ -306,7 +306,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { } } if (bh) brelse(bh); - printk(KERN_ERR "EFS: map_block() failed to map block %u (indir)\n", block); + pr_err("EFS: map_block() failed to map block %u (indir)\n", block); return 0; } diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 96f66d2..527d0b9 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -23,20 +23,20 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) efs_block_t block; if (inode->i_size & (EFS_DIRBSIZE-1)) - printk(KERN_WARNING "EFS: WARNING: find_entry(): directory size not a multiple of EFS_DIRBSIZE\n"); + pr_warn("EFS: WARNING: find_entry(): directory size not a multiple of EFS_DIRBSIZE\n"); for(block = 0; block < inode->i_blocks; block++) { bh = sb_bread(inode->i_sb, efs_bmap(inode, block)); if (!bh) { - printk(KERN_ERR "EFS: find_entry(): failed to read dir block %d\n", block); + pr_err("EFS: find_entry(): failed to read dir block %d\n", block); return 0; } dirblock = (struct efs_dir *) bh->b_data; if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) { - printk(KERN_ERR "EFS: find_entry(): invalid directory block\n"); + pr_err("EFS: find_entry(): invalid directory block\n"); brelse(bh); return(0); } diff --git a/fs/efs/super.c b/fs/efs/super.c index 3befcc9..0590232 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -134,7 +134,7 @@ static const struct export_operations efs_export_ops = { static int __init init_efs_fs(void) { int err; - printk("EFS: "EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); + pr_info("EFS: "EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); err = init_inodecache(); if (err) goto out1; @@ -179,7 +179,7 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { csum += be32_to_cpu(cs); } if (csum) { - printk(KERN_INFO "EFS: SGI disklabel: checksum bad, label corrupted\n"); + pr_warn("EFS: SGI disklabel: checksum bad, label corrupted\n"); return 0; } @@ -226,11 +226,10 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { } if (slice == -1) { - printk(KERN_NOTICE "EFS: partition table contained no EFS partitions\n"); + pr_notice("EFS: partition table contained no EFS partitions\n"); #ifdef DEBUG } else { - printk(KERN_INFO "EFS: using slice %d (type %s, offset 0x%x)\n", - slice, + pr_info("EFS: using slice %d (type %s, offset 0x%x)\n", slice, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown", sblock); #endif @@ -268,7 +267,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { - printk(KERN_ERR "EFS: device does not support %d byte blocks\n", + pr_err("EFS: device does not support %d byte blocks\n", EFS_BLOCKSIZE); return -EINVAL; } @@ -277,7 +276,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) bh = sb_bread(s, 0); if (!bh) { - printk(KERN_ERR "EFS: cannot read volume header\n"); + pr_err("EFS: cannot read volume header\n"); return -EINVAL; } @@ -295,13 +294,13 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) bh = sb_bread(s, sb->fs_start + EFS_SUPER); if (!bh) { - printk(KERN_ERR "EFS: cannot read superblock\n"); + pr_err("EFS: cannot read superblock\n"); return -EINVAL; } if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG - printk(KERN_WARNING "EFS: invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); + pr_warn("EFS: invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); #endif brelse(bh); return -EINVAL; @@ -310,7 +309,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) if (!(s->s_flags & MS_RDONLY)) { #ifdef DEBUG - printk(KERN_INFO "EFS: forcing read-only mode\n"); + pr_info("EFS: forcing read-only mode\n"); #endif s->s_flags |= MS_RDONLY; } @@ -318,13 +317,13 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) s->s_export_op = &efs_export_ops; root = efs_iget(s, EFS_ROOTINODE); if (IS_ERR(root)) { - printk(KERN_ERR "EFS: get root inode failed\n"); + pr_err("EFS: get root inode failed\n"); return PTR_ERR(root); } s->s_root = d_make_root(root); if (!(s->s_root)) { - printk(KERN_ERR "EFS: get root dentry failed\n"); + pr_err("EFS: get root dentry failed\n"); return -ENOMEM; } -- cgit v1.1 From f403d1dbac6d1ef28f553f3996d5bb5cea90ce15 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:12 -0700 Subject: fs/efs: add pr_fmt / use __func__ Also uniformize function arguments. Signed-off-by: Fabian Frederick Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/efs/dir.c | 11 +++++++---- fs/efs/efs.h | 6 ++++++ fs/efs/file.c | 12 +++++------- fs/efs/inode.c | 24 ++++++++++++++---------- fs/efs/namei.c | 8 +++++--- fs/efs/super.c | 23 ++++++++++++----------- 6 files changed, 49 insertions(+), 35 deletions(-) (limited to 'fs') diff --git a/fs/efs/dir.c b/fs/efs/dir.c index 46a9a60..7f97031 100644 --- a/fs/efs/dir.c +++ b/fs/efs/dir.c @@ -26,7 +26,8 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) int slot; if (inode->i_size & (EFS_DIRBSIZE-1)) - pr_warn("EFS: WARNING: readdir(): directory size not a multiple of EFS_DIRBSIZE\n"); + pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n", + __func__); /* work out where this entry can be found */ block = ctx->pos >> EFS_DIRBSIZE_BITS; @@ -43,14 +44,15 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) bh = sb_bread(inode->i_sb, efs_bmap(inode, block)); if (!bh) { - pr_err("EFS: readdir(): failed to read dir block %d\n", block); + pr_err("%s(): failed to read dir block %d\n", + __func__, block); break; } dirblock = (struct efs_dir *) bh->b_data; if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) { - pr_err("EFS: readdir(): invalid directory block\n"); + pr_err("%s(): invalid directory block\n", __func__); brelse(bh); break; } @@ -80,7 +82,8 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) /* sanity check */ if (nameptr - (char *) dirblock + namelen > EFS_DIRBSIZE) { - pr_warn("EFS: directory entry %d exceeds directory block\n", slot); + pr_warn("directory entry %d exceeds directory block\n", + slot); continue; } diff --git a/fs/efs/efs.h b/fs/efs/efs.h index 5528926..5bbf961 100644 --- a/fs/efs/efs.h +++ b/fs/efs/efs.h @@ -7,6 +7,12 @@ #ifndef _EFS_EFS_H_ #define _EFS_EFS_H_ +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include diff --git a/fs/efs/file.c b/fs/efs/file.c index a75c710..a37dcee 100644 --- a/fs/efs/file.c +++ b/fs/efs/file.c @@ -22,10 +22,8 @@ int efs_get_block(struct inode *inode, sector_t iblock, /* * i have no idea why this happens as often as it does */ - pr_warn("EFS: bmap(): block %d >= %ld (filesize %ld)\n", - block, - inode->i_blocks, - inode->i_size); + pr_warn("%s(): block %d >= %ld (filesize %ld)\n", + __func__, block, inode->i_blocks, inode->i_size); #endif return 0; } @@ -38,7 +36,7 @@ int efs_get_block(struct inode *inode, sector_t iblock, int efs_bmap(struct inode *inode, efs_block_t block) { if (block < 0) { - pr_warn("EFS: bmap(): block < 0\n"); + pr_warn("%s(): block < 0\n", __func__); return 0; } @@ -48,8 +46,8 @@ int efs_bmap(struct inode *inode, efs_block_t block) { /* * i have no idea why this happens as often as it does */ - pr_warn("EFS: bmap(): block %d >= %ld (filesize %ld)\n", - block, inode->i_blocks, inode->i_size); + pr_warn("%s(): block %d >= %ld (filesize %ld)\n", + __func__, block, inode->i_blocks, inode->i_size); #endif return 0; } diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 54f1cbb..6c9684a 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -89,7 +89,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) bh = sb_bread(inode->i_sb, block); if (!bh) { - pr_warn("EFS: bread() failed at block %d\n", block); + pr_warn("%s() failed at block %d\n", __func__, block); goto read_inode_error; } @@ -130,7 +130,8 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) for(i = 0; i < EFS_DIRECTEXTENTS; i++) { extent_copy(&(efs_inode->di_u.di_extents[i]), &(in->extents[i])); if (i < in->numextents && in->extents[i].cooked.ex_magic != 0) { - pr_warn("EFS: extent %d has bad magic number in inode %lu\n", i, inode->i_ino); + pr_warn("extent %d has bad magic number in inode %lu\n", + i, inode->i_ino); brelse(bh); goto read_inode_error; } @@ -162,7 +163,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) init_special_inode(inode, inode->i_mode, device); break; default: - pr_warn("EFS: unsupported inode mode %o\n", inode->i_mode); + pr_warn("unsupported inode mode %o\n", inode->i_mode); goto read_inode_error; break; } @@ -171,7 +172,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) return inode; read_inode_error: - pr_warn("EFS: failed to read inode %lu\n", inode->i_ino); + pr_warn("failed to read inode %lu\n", inode->i_ino); iget_failed(inode); return ERR_PTR(-EIO); } @@ -216,7 +217,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { /* if we only have one extent then nothing can be found */ if (in->numextents == 1) { - pr_err("EFS: map_block() failed to map (1 extent)\n"); + pr_err("%s() failed to map (1 extent)\n", __func__); return 0; } @@ -234,7 +235,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { } } - pr_err("EFS: map_block() failed to map block %u (dir)\n", block); + pr_err("%s() failed to map block %u (dir)\n", __func__, block); return 0; } @@ -262,7 +263,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { if (dirext == direxts) { /* should never happen */ - pr_err("EFS: couldn't find direct extent for indirect extent %d (block %u)\n", cur, block); + pr_err("couldn't find direct extent for indirect extent %d (block %u)\n", + cur, block); if (bh) brelse(bh); return 0; } @@ -279,7 +281,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { bh = sb_bread(inode->i_sb, iblock); if (!bh) { - pr_err("EFS: bread() failed at block %d\n", iblock); + pr_err("%s() failed at block %d\n", + __func__, iblock); return 0; } #ifdef DEBUG @@ -294,7 +297,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { extent_copy(&(exts[ioffset]), &ext); if (ext.cooked.ex_magic != 0) { - pr_err("EFS: extent %d has bad magic number in block %d\n", cur, iblock); + pr_err("extent %d has bad magic number in block %d\n", + cur, iblock); if (bh) brelse(bh); return 0; } @@ -306,7 +310,7 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { } } if (bh) brelse(bh); - pr_err("EFS: map_block() failed to map block %u (indir)\n", block); + pr_err("%s() failed to map block %u (indir)\n", __func__, block); return 0; } diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 527d0b9..356c044 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -23,20 +23,22 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) efs_block_t block; if (inode->i_size & (EFS_DIRBSIZE-1)) - pr_warn("EFS: WARNING: find_entry(): directory size not a multiple of EFS_DIRBSIZE\n"); + pr_warn("%s(): directory size not a multiple of EFS_DIRBSIZE\n", + __func__); for(block = 0; block < inode->i_blocks; block++) { bh = sb_bread(inode->i_sb, efs_bmap(inode, block)); if (!bh) { - pr_err("EFS: find_entry(): failed to read dir block %d\n", block); + pr_err("%s(): failed to read dir block %d\n", + __func__, block); return 0; } dirblock = (struct efs_dir *) bh->b_data; if (be16_to_cpu(dirblock->magic) != EFS_DIRBLK_MAGIC) { - pr_err("EFS: find_entry(): invalid directory block\n"); + pr_err("%s(): invalid directory block\n", __func__); brelse(bh); return(0); } diff --git a/fs/efs/super.c b/fs/efs/super.c index 0590232..cd1399e 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -134,7 +134,7 @@ static const struct export_operations efs_export_ops = { static int __init init_efs_fs(void) { int err; - pr_info("EFS: "EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); + pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); err = init_inodecache(); if (err) goto out1; @@ -179,7 +179,7 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { csum += be32_to_cpu(cs); } if (csum) { - pr_warn("EFS: SGI disklabel: checksum bad, label corrupted\n"); + pr_warn("SGI disklabel: checksum bad, label corrupted\n"); return 0; } @@ -226,10 +226,10 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { } if (slice == -1) { - pr_notice("EFS: partition table contained no EFS partitions\n"); + pr_notice("partition table contained no EFS partitions\n"); #ifdef DEBUG } else { - pr_info("EFS: using slice %d (type %s, offset 0x%x)\n", slice, + pr_info("using slice %d (type %s, offset 0x%x)\n", slice, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown", sblock); #endif @@ -267,7 +267,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { - pr_err("EFS: device does not support %d byte blocks\n", + pr_err("device does not support %d byte blocks\n", EFS_BLOCKSIZE); return -EINVAL; } @@ -276,7 +276,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) bh = sb_bread(s, 0); if (!bh) { - pr_err("EFS: cannot read volume header\n"); + pr_err("cannot read volume header\n"); return -EINVAL; } @@ -294,13 +294,14 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) bh = sb_bread(s, sb->fs_start + EFS_SUPER); if (!bh) { - pr_err("EFS: cannot read superblock\n"); + pr_err("cannot read superblock\n"); return -EINVAL; } if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG - pr_warn("EFS: invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); + pr_warn("invalid superblock at block %u\n", + sb->fs_start + EFS_SUPER); #endif brelse(bh); return -EINVAL; @@ -309,7 +310,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) if (!(s->s_flags & MS_RDONLY)) { #ifdef DEBUG - pr_info("EFS: forcing read-only mode\n"); + pr_info("forcing read-only mode\n"); #endif s->s_flags |= MS_RDONLY; } @@ -317,13 +318,13 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) s->s_export_op = &efs_export_ops; root = efs_iget(s, EFS_ROOTINODE); if (IS_ERR(root)) { - pr_err("EFS: get root inode failed\n"); + pr_err("get root inode failed\n"); return PTR_ERR(root); } s->s_root = d_make_root(root); if (!(s->s_root)) { - pr_err("EFS: get root dentry failed\n"); + pr_err("get root dentry failed\n"); return -ENOMEM; } -- cgit v1.1 From d1826f2a3d64f76b18e9ac4a6874c5db5be24750 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:13 -0700 Subject: fs/efs: convert printk(KERN_DEBUG to pr_debug All KERN_DEBUG callsites being under #ifdef DEBUG we can safely convert everything to pr_debug without changing current behaviour. Remove #ifdef DEBUG around pr_debugs only (suggested by Joe Perches) Signed-off-by: Fabian Frederick Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/efs/dir.c | 7 +++---- fs/efs/inode.c | 18 ++++++------------ fs/efs/super.c | 18 ++++++++---------- 3 files changed, 17 insertions(+), 26 deletions(-) (limited to 'fs') diff --git a/fs/efs/dir.c b/fs/efs/dir.c index 7f97031..ce63b24 100644 --- a/fs/efs/dir.c +++ b/fs/efs/dir.c @@ -71,10 +71,9 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) inodenum = be32_to_cpu(dirslot->inode); namelen = dirslot->namelen; nameptr = dirslot->name; - -#ifdef DEBUG - printk(KERN_DEBUG "EFS: readdir(): block %d slot %d/%d: inode %u, name \"%s\", namelen %u\n", block, slot, dirblock->slots-1, inodenum, nameptr, namelen); -#endif + pr_debug("%s(): block %d slot %d/%d: inode %u, name \"%s\", namelen %u\n", + __func__, block, slot, dirblock->slots-1, + inodenum, nameptr, namelen); if (!namelen) continue; /* found the next entry */ diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 6c9684a..079d203 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -138,12 +138,8 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) } brelse(bh); - -#ifdef DEBUG - printk(KERN_DEBUG "EFS: efs_iget(): inode %lu, extents %d, mode %o\n", - inode->i_ino, in->numextents, inode->i_mode); -#endif - + pr_debug("efs_iget(): inode %lu, extents %d, mode %o\n", + inode->i_ino, in->numextents, inode->i_mode); switch (inode->i_mode & S_IFMT) { case S_IFDIR: inode->i_op = &efs_dir_inode_operations; @@ -239,9 +235,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { return 0; } -#ifdef DEBUG - printk(KERN_DEBUG "EFS: map_block(): indirect search for logical block %u\n", block); -#endif + pr_debug("%s(): indirect search for logical block %u\n", + __func__, block); direxts = in->extents[0].cooked.ex_offset; indexts = in->numextents; @@ -285,9 +280,8 @@ efs_block_t efs_map_block(struct inode *inode, efs_block_t block) { __func__, iblock); return 0; } -#ifdef DEBUG - printk(KERN_DEBUG "EFS: map_block(): read indirect extent block %d\n", iblock); -#endif + pr_debug("%s(): read indirect extent block %d\n", + __func__, iblock); first = 0; lastblock = iblock; } diff --git a/fs/efs/super.c b/fs/efs/super.c index cd1399e..7fca462 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -184,7 +184,7 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { } #ifdef DEBUG - printk(KERN_DEBUG "EFS: bf: \"%16s\"\n", vh->vh_bootfile); + pr_debug("bf: \"%16s\"\n", vh->vh_bootfile); for(i = 0; i < NVDIR; i++) { int j; @@ -196,9 +196,8 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { name[j] = (char) 0; if (name[0]) { - printk(KERN_DEBUG "EFS: vh: %8s block: 0x%08x size: 0x%08x\n", - name, - (int) be32_to_cpu(vh->vh_vd[i].vd_lbn), + pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n", + name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn), (int) be32_to_cpu(vh->vh_vd[i].vd_nbytes)); } } @@ -211,12 +210,11 @@ static efs_block_t efs_validate_vh(struct volume_header *vh) { } #ifdef DEBUG if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) { - printk(KERN_DEBUG "EFS: pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n", - i, - (int) be32_to_cpu(vh->vh_pt[i].pt_firstlbn), - (int) be32_to_cpu(vh->vh_pt[i].pt_nblks), - pt_type, - (pt_entry->pt_name) ? pt_entry->pt_name : "unknown"); + pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n", + i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn), + (int)be32_to_cpu(vh->vh_pt[i].pt_nblks), + pt_type, (pt_entry->pt_name) ? + pt_entry->pt_name : "unknown"); } #endif if (IS_EFS(pt_type)) { -- cgit v1.1 From b219e25f8dd9793904ca87c55c76ab8c8931abb9 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:14 -0700 Subject: fs/binfmt_elf.c: fix bool assignements Fix coccinelle warnings. Signed-off-by: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index aa3cb62..dabc73a 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1686,7 +1686,7 @@ static size_t get_note_info_size(struct elf_note_info *info) static int write_note_info(struct elf_note_info *info, struct coredump_params *cprm) { - bool first = 1; + bool first = true; struct elf_thread_core_info *t = info->thread; do { @@ -1710,7 +1710,7 @@ static int write_note_info(struct elf_note_info *info, !writenote(&t->notes[i], cprm)) return 0; - first = 0; + first = false; t = t->next; } while (t); -- cgit v1.1 From 343034357202be37be335a08ef4a0f0708b6ba3d Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 4 Jun 2014 16:12:15 -0700 Subject: fs/binfmt_flat.c: make old_reloc() static old_reloc() is only used in this file, make it static. Signed-off-by: Axel Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_flat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index d50bbe5..f723cd3 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -380,7 +380,7 @@ failed: /****************************************************************************/ -void old_reloc(unsigned long rl) +static void old_reloc(unsigned long rl) { #ifdef DEBUG char *segment[] = { "TEXT", "DATA", "BSS", "*UNKNOWN*" }; -- cgit v1.1 From 8091b895b76f690aa2f6689b6ed602f07525a938 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:21 -0700 Subject: fs/ncpfs/getopt.c: replace simple_strtoul by kstrtoul Remove obsolete simple_strtoul in ncp_getopt Signed-off-by: Fabian Frederick Cc: Petr Vandrovec Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ncpfs/getopt.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/ncpfs/getopt.c b/fs/ncpfs/getopt.c index 03ffde1..344889c 100644 --- a/fs/ncpfs/getopt.c +++ b/fs/ncpfs/getopt.c @@ -53,15 +53,14 @@ int ncp_getopt(const char *caller, char **options, const struct ncp_option *opts return -EINVAL; } if (opts->has_arg & OPT_INT) { - char* v; + int rc = kstrtoul(val, 0, value); - *value = simple_strtoul(val, &v, 0); - if (!*v) { - return opts->val; + if (rc) { + pr_info("%s: invalid numeric value in %s=%s\n", + caller, token, val); + return rc; } - pr_info("%s: invalid numeric value in %s=%s\n", - caller, token, val); - return -EDOM; + return opts->val; } if (opts->has_arg & OPT_STRING) { return opts->val; -- cgit v1.1 From 3ff6db3287e8a5e8f5bb9529b8e1259ca6b10def Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Jun 2014 16:12:21 -0700 Subject: fs/autofs4/dev-ioctl.c: add __init to autofs_dev_ioctl_init autofs_dev_ioctl_init is only called by __init init_autofs4_fs Signed-off-by: Fabian Frederick Acked-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/dev-ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 232e03d..5b570b6 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -737,7 +737,7 @@ MODULE_ALIAS_MISCDEV(AUTOFS_MINOR); MODULE_ALIAS("devname:autofs"); /* Register/deregister misc character device */ -int autofs_dev_ioctl_init(void) +int __init autofs_dev_ioctl_init(void) { int r; -- cgit v1.1