From afc1246f917c664b0df98b3c22fa62db74d2ca33 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 11 Jul 2008 17:20:49 -0700 Subject: file lock: reorder struct file_lock to save space on 64 bit builds Reduce sizeof struct file_lock by 8 on 64 bit builds allowing +1 objects per slab in the file_lock_cache Signed-off-by: Richard Kennedy Signed-off-by: Andrew Morton Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7c1080826832..87f89bd0f6ee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -917,12 +917,12 @@ struct file_lock { struct list_head fl_link; /* doubly linked list of all locks */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; + unsigned char fl_flags; + unsigned char fl_type; unsigned int fl_pid; struct pid *fl_nspid; wait_queue_head_t fl_wait; struct file *fl_file; - unsigned char fl_flags; - unsigned char fl_type; loff_t fl_start; loff_t fl_end; -- cgit From e108526e77aa41c89b3be96f75d97615db2b751c Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 23 Jul 2008 21:26:44 -0700 Subject: move memory_read_from_buffer() from fs.h to string.h James Bottomley warns that inclusion of linux/fs.h in a low level driver was always a danger signal. This patch moves memory_read_from_buffer() from fs.h to string.h and fixes includes in existing memory_read_from_buffer() users. Signed-off-by: Akinobu Mita Cc: James Bottomley Cc: Geert Uytterhoeven Cc: Zhang Rui Cc: Bob Moore Cc: Thomas Renninger Cc: Len Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/acpi/system.c | 1 + drivers/zorro/zorro-sysfs.c | 1 - include/linux/fs.h | 2 -- include/linux/string.h | 3 +++ 4 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c index d8e3f153b295..91dec448b3ed 100644 --- a/drivers/acpi/system.c +++ b/drivers/acpi/system.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c index 3da712cc7708..5290552d2ef7 100644 --- a/drivers/zorro/zorro-sysfs.c +++ b/drivers/zorro/zorro-sysfs.c @@ -15,7 +15,6 @@ #include #include #include -#include #include "zorro.h" diff --git a/include/linux/fs.h b/include/linux/fs.h index 9c2ac5c0ef5c..ff54ae4933f3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2006,8 +2006,6 @@ extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); -extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, - const void *from, size_t available); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, diff --git a/include/linux/string.h b/include/linux/string.h index efdc44593b52..810d80df0a1d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,5 +111,8 @@ extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); +extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, + const void *from, size_t available); + #endif #endif /* _LINUX_STRING_H_ */ -- cgit From da3bbdd4632c0171406b2677e31494afa5bde2f8 Mon Sep 17 00:00:00 2001 From: Kentaro Makita Date: Wed, 23 Jul 2008 21:27:13 -0700 Subject: fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita Cc: Neil Brown Cc: Trond Myklebust Cc: David Chinner Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dcache.c | 335 ++++++++++++++++++++++++++++------------------------- fs/super.c | 1 + include/linux/fs.h | 4 + 3 files changed, 185 insertions(+), 155 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/dcache.c b/fs/dcache.c index 6068c25b393c..3818d6ab76ca 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -61,7 +61,6 @@ static struct kmem_cache *dentry_cache __read_mostly; static unsigned int d_hash_mask __read_mostly; static unsigned int d_hash_shift __read_mostly; static struct hlist_head *dentry_hashtable __read_mostly; -static LIST_HEAD(dentry_unused); /* Statistics gathering. */ struct dentry_stat_t dentry_stat = { @@ -96,14 +95,6 @@ static void d_free(struct dentry *dentry) call_rcu(&dentry->d_u.d_rcu, d_callback); } -static void dentry_lru_remove(struct dentry *dentry) -{ - if (!list_empty(&dentry->d_lru)) { - list_del_init(&dentry->d_lru); - dentry_stat.nr_unused--; - } -} - /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. @@ -130,6 +121,41 @@ static void dentry_iput(struct dentry * dentry) } } +/* + * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held. + */ +static void dentry_lru_add(struct dentry *dentry) +{ + list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); + dentry->d_sb->s_nr_dentry_unused++; + dentry_stat.nr_unused++; +} + +static void dentry_lru_add_tail(struct dentry *dentry) +{ + list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); + dentry->d_sb->s_nr_dentry_unused++; + dentry_stat.nr_unused++; +} + +static void dentry_lru_del(struct dentry *dentry) +{ + if (!list_empty(&dentry->d_lru)) { + list_del(&dentry->d_lru); + dentry->d_sb->s_nr_dentry_unused--; + dentry_stat.nr_unused--; + } +} + +static void dentry_lru_del_init(struct dentry *dentry) +{ + if (likely(!list_empty(&dentry->d_lru))) { + list_del_init(&dentry->d_lru); + dentry->d_sb->s_nr_dentry_unused--; + dentry_stat.nr_unused--; + } +} + /** * d_kill - kill dentry and return parent * @dentry: dentry to kill @@ -212,8 +238,7 @@ repeat: goto kill_it; if (list_empty(&dentry->d_lru)) { dentry->d_flags |= DCACHE_REFERENCED; - list_add(&dentry->d_lru, &dentry_unused); - dentry_stat.nr_unused++; + dentry_lru_add(dentry); } spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); @@ -222,7 +247,8 @@ repeat: unhash_it: __d_drop(dentry); kill_it: - dentry_lru_remove(dentry); + /* if dentry was on the d_lru list delete it from there */ + dentry_lru_del(dentry); dentry = d_kill(dentry); if (dentry) goto repeat; @@ -290,7 +316,7 @@ int d_invalidate(struct dentry * dentry) static inline struct dentry * __dget_locked(struct dentry *dentry) { atomic_inc(&dentry->d_count); - dentry_lru_remove(dentry); + dentry_lru_del_init(dentry); return dentry; } @@ -406,133 +432,167 @@ static void prune_one_dentry(struct dentry * dentry) if (dentry->d_op && dentry->d_op->d_delete) dentry->d_op->d_delete(dentry); - dentry_lru_remove(dentry); + dentry_lru_del_init(dentry); __d_drop(dentry); dentry = d_kill(dentry); spin_lock(&dcache_lock); } } -/** - * prune_dcache - shrink the dcache - * @count: number of entries to try and free - * @sb: if given, ignore dentries for other superblocks - * which are being unmounted. - * - * Shrink the dcache. This is done when we need - * more memory, or simply when we need to unmount - * something (at which point we need to unuse - * all dentries). - * - * This function may fail to free any resources if - * all the dentries are in use. +/* + * Shrink the dentry LRU on a given superblock. + * @sb : superblock to shrink dentry LRU. + * @count: If count is NULL, we prune all dentries on superblock. + * @flags: If flags is non-zero, we need to do special processing based on + * which flags are set. This means we don't need to maintain multiple + * similar copies of this loop. */ - -static void prune_dcache(int count, struct super_block *sb) +static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags) { - spin_lock(&dcache_lock); - for (; count ; count--) { - struct dentry *dentry; - struct list_head *tmp; - struct rw_semaphore *s_umount; - - cond_resched_lock(&dcache_lock); + LIST_HEAD(referenced); + LIST_HEAD(tmp); + struct dentry *dentry; + int cnt = 0; - tmp = dentry_unused.prev; - if (sb) { - /* Try to find a dentry for this sb, but don't try - * too hard, if they aren't near the tail they will - * be moved down again soon + BUG_ON(!sb); + BUG_ON((flags & DCACHE_REFERENCED) && count == NULL); + spin_lock(&dcache_lock); + if (count != NULL) + /* called from prune_dcache() and shrink_dcache_parent() */ + cnt = *count; +restart: + if (count == NULL) + list_splice_init(&sb->s_dentry_lru, &tmp); + else { + while (!list_empty(&sb->s_dentry_lru)) { + dentry = list_entry(sb->s_dentry_lru.prev, + struct dentry, d_lru); + BUG_ON(dentry->d_sb != sb); + + spin_lock(&dentry->d_lock); + /* + * If we are honouring the DCACHE_REFERENCED flag and + * the dentry has this flag set, don't free it. Clear + * the flag and put it back on the LRU. */ - int skip = count; - while (skip && tmp != &dentry_unused && - list_entry(tmp, struct dentry, d_lru)->d_sb != sb) { - skip--; - tmp = tmp->prev; + if ((flags & DCACHE_REFERENCED) + && (dentry->d_flags & DCACHE_REFERENCED)) { + dentry->d_flags &= ~DCACHE_REFERENCED; + list_move_tail(&dentry->d_lru, &referenced); + spin_unlock(&dentry->d_lock); + } else { + list_move_tail(&dentry->d_lru, &tmp); + spin_unlock(&dentry->d_lock); + cnt--; + if (!cnt) + break; } } - if (tmp == &dentry_unused) - break; - list_del_init(tmp); - prefetch(dentry_unused.prev); - dentry_stat.nr_unused--; - dentry = list_entry(tmp, struct dentry, d_lru); - - spin_lock(&dentry->d_lock); + } + while (!list_empty(&tmp)) { + dentry = list_entry(tmp.prev, struct dentry, d_lru); + dentry_lru_del_init(dentry); + spin_lock(&dentry->d_lock); /* * We found an inuse dentry which was not removed from - * dentry_unused because of laziness during lookup. Do not free - * it - just keep it off the dentry_unused list. + * the LRU because of laziness during lookup. Do not free + * it - just keep it off the LRU list. */ - if (atomic_read(&dentry->d_count)) { - spin_unlock(&dentry->d_lock); + if (atomic_read(&dentry->d_count)) { + spin_unlock(&dentry->d_lock); continue; } - /* If the dentry was recently referenced, don't free it. */ - if (dentry->d_flags & DCACHE_REFERENCED) { - dentry->d_flags &= ~DCACHE_REFERENCED; - list_add(&dentry->d_lru, &dentry_unused); - dentry_stat.nr_unused++; - spin_unlock(&dentry->d_lock); + prune_one_dentry(dentry); + /* dentry->d_lock was dropped in prune_one_dentry() */ + cond_resched_lock(&dcache_lock); + } + if (count == NULL && !list_empty(&sb->s_dentry_lru)) + goto restart; + if (count != NULL) + *count = cnt; + if (!list_empty(&referenced)) + list_splice(&referenced, &sb->s_dentry_lru); + spin_unlock(&dcache_lock); +} + +/** + * prune_dcache - shrink the dcache + * @count: number of entries to try to free + * + * Shrink the dcache. This is done when we need more memory, or simply when we + * need to unmount something (at which point we need to unuse all dentries). + * + * This function may fail to free any resources if all the dentries are in use. + */ +static void prune_dcache(int count) +{ + struct super_block *sb; + int w_count; + int unused = dentry_stat.nr_unused; + int prune_ratio; + int pruned; + + if (unused == 0 || count == 0) + return; + spin_lock(&dcache_lock); +restart: + if (count >= unused) + prune_ratio = 1; + else + prune_ratio = unused / count; + spin_lock(&sb_lock); + list_for_each_entry(sb, &super_blocks, s_list) { + if (sb->s_nr_dentry_unused == 0) continue; - } - /* - * If the dentry is not DCACHED_REFERENCED, it is time - * to remove it from the dcache, provided the super block is - * NULL (which means we are trying to reclaim memory) - * or this dentry belongs to the same super block that - * we want to shrink. - */ - /* - * If this dentry is for "my" filesystem, then I can prune it - * without taking the s_umount lock (I already hold it). + sb->s_count++; + /* Now, we reclaim unused dentrins with fairness. + * We reclaim them same percentage from each superblock. + * We calculate number of dentries to scan on this sb + * as follows, but the implementation is arranged to avoid + * overflows: + * number of dentries to scan on this sb = + * count * (number of dentries on this sb / + * number of dentries in the machine) */ - if (sb && dentry->d_sb == sb) { - prune_one_dentry(dentry); - continue; - } + spin_unlock(&sb_lock); + if (prune_ratio != 1) + w_count = (sb->s_nr_dentry_unused / prune_ratio) + 1; + else + w_count = sb->s_nr_dentry_unused; + pruned = w_count; /* - * ...otherwise we need to be sure this filesystem isn't being - * unmounted, otherwise we could race with - * generic_shutdown_super(), and end up holding a reference to - * an inode while the filesystem is unmounted. - * So we try to get s_umount, and make sure s_root isn't NULL. - * (Take a local copy of s_umount to avoid a use-after-free of - * `dentry'). + * We need to be sure this filesystem isn't being unmounted, + * otherwise we could race with generic_shutdown_super(), and + * end up holding a reference to an inode while the filesystem + * is unmounted. So we try to get s_umount, and make sure + * s_root isn't NULL. */ - s_umount = &dentry->d_sb->s_umount; - if (down_read_trylock(s_umount)) { - if (dentry->d_sb->s_root != NULL) { - prune_one_dentry(dentry); - up_read(s_umount); - continue; + if (down_read_trylock(&sb->s_umount)) { + if ((sb->s_root != NULL) && + (!list_empty(&sb->s_dentry_lru))) { + spin_unlock(&dcache_lock); + __shrink_dcache_sb(sb, &w_count, + DCACHE_REFERENCED); + pruned -= w_count; + spin_lock(&dcache_lock); } - up_read(s_umount); + up_read(&sb->s_umount); } - spin_unlock(&dentry->d_lock); + spin_lock(&sb_lock); + count -= pruned; /* - * Insert dentry at the head of the list as inserting at the - * tail leads to a cycle. + * restart only when sb is no longer on the list and + * we have more work to do. */ - list_add(&dentry->d_lru, &dentry_unused); - dentry_stat.nr_unused++; + if (__put_super_and_need_restart(sb) && count > 0) { + spin_unlock(&sb_lock); + goto restart; + } } + spin_unlock(&sb_lock); spin_unlock(&dcache_lock); } -/* - * Shrink the dcache for the specified super block. - * This allows us to unmount a device without disturbing - * the dcache for the other devices. - * - * This implementation makes just two traversals of the - * unused list. On the first pass we move the selected - * dentries to the most recent end, and on the second - * pass we free them. The second pass must restart after - * each dput(), but since the target dentries are all at - * the end, it's really just a single traversal. - */ - /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock @@ -541,44 +601,9 @@ static void prune_dcache(int count, struct super_block *sb) * is used to free the dcache before unmounting a file * system */ - void shrink_dcache_sb(struct super_block * sb) { - struct list_head *tmp, *next; - struct dentry *dentry; - - /* - * Pass one ... move the dentries for the specified - * superblock to the most recent end of the unused list. - */ - spin_lock(&dcache_lock); - list_for_each_prev_safe(tmp, next, &dentry_unused) { - dentry = list_entry(tmp, struct dentry, d_lru); - if (dentry->d_sb != sb) - continue; - list_move_tail(tmp, &dentry_unused); - } - - /* - * Pass two ... free the dentries for this superblock. - */ -repeat: - list_for_each_prev_safe(tmp, next, &dentry_unused) { - dentry = list_entry(tmp, struct dentry, d_lru); - if (dentry->d_sb != sb) - continue; - dentry_stat.nr_unused--; - list_del_init(tmp); - spin_lock(&dentry->d_lock); - if (atomic_read(&dentry->d_count)) { - spin_unlock(&dentry->d_lock); - continue; - } - prune_one_dentry(dentry); - cond_resched_lock(&dcache_lock); - goto repeat; - } - spin_unlock(&dcache_lock); + __shrink_dcache_sb(sb, NULL, 0); } /* @@ -595,7 +620,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) /* detach this root from the system */ spin_lock(&dcache_lock); - dentry_lru_remove(dentry); + dentry_lru_del_init(dentry); __d_drop(dentry); spin_unlock(&dcache_lock); @@ -609,7 +634,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) spin_lock(&dcache_lock); list_for_each_entry(loop, &dentry->d_subdirs, d_u.d_child) { - dentry_lru_remove(loop); + dentry_lru_del_init(loop); __d_drop(loop); cond_resched_lock(&dcache_lock); } @@ -791,14 +816,13 @@ resume: struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); next = tmp->next; - dentry_lru_remove(dentry); + dentry_lru_del_init(dentry); /* * move only zero ref count dentries to the end * of the unused list for prune_dcache */ if (!atomic_read(&dentry->d_count)) { - list_add_tail(&dentry->d_lru, &dentry_unused); - dentry_stat.nr_unused++; + dentry_lru_add_tail(dentry); found++; } @@ -840,10 +864,11 @@ out: void shrink_dcache_parent(struct dentry * parent) { + struct super_block *sb = parent->d_sb; int found; while ((found = select_parent(parent)) != 0) - prune_dcache(found, parent->d_sb); + __shrink_dcache_sb(sb, &found, 0); } /* @@ -863,7 +888,7 @@ static int shrink_dcache_memory(int nr, gfp_t gfp_mask) if (nr) { if (!(gfp_mask & __GFP_FS)) return -1; - prune_dcache(nr, NULL); + prune_dcache(nr); } return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; } @@ -1215,7 +1240,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) * rcu_read_lock() and rcu_read_unlock() are used to disable preemption while * lookup is going on. * - * dentry_unused list is not updated even if lookup finds the required dentry + * The dentry unused LRU is not updated even if lookup finds the required dentry * in there. It is updated in places such as prune_dcache, shrink_dcache_sb, * select_parent and __dget_locked. This laziness saves lookup from dcache_lock * acquisition. diff --git a/fs/super.c b/fs/super.c index 453877c5697b..e931ae9511fe 100644 --- a/fs/super.c +++ b/fs/super.c @@ -70,6 +70,7 @@ static struct super_block *alloc_super(struct file_system_type *type) INIT_LIST_HEAD(&s->s_instances); INIT_HLIST_HEAD(&s->s_anon); INIT_LIST_HEAD(&s->s_inodes); + INIT_LIST_HEAD(&s->s_dentry_lru); init_rwsem(&s->s_umount); mutex_init(&s->s_lock); lockdep_set_class(&s->s_umount, &type->s_umount_key); diff --git a/include/linux/fs.h b/include/linux/fs.h index ff54ae4933f3..e5e6a244096c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1025,6 +1025,7 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; +#define sb_entry(list) list_entry((list), struct super_block, s_list) #define S_BIAS (1<<30) struct super_block { struct list_head s_list; /* Keep this first */ @@ -1058,6 +1059,9 @@ struct super_block { struct list_head s_more_io; /* parked for more writeback */ struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ struct list_head s_files; + /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ + struct list_head s_dentry_lru; /* unused dentry lru */ + int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; struct mtd_info *s_mtd; -- cgit From ed8cae8ba01348bfd83333f4648dd807b04d7f08 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:30 -0700 Subject: flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/ia32/sys_ia32.c | 2 +- arch/ia64/kernel/sys_ia64.c | 2 +- arch/mips/kernel/syscall.c | 2 +- arch/parisc/hpux/sys_hpux.c | 2 +- arch/sh/kernel/sys_sh32.c | 2 +- arch/sparc/kernel/sys_sparc.c | 2 +- arch/sparc64/kernel/sys_sparc.c | 2 +- arch/x86/ia32/ia32entry.S | 1 + arch/x86/ia32/sys_ia32.c | 2 +- arch/x86/kernel/syscall_table_32.S | 1 + arch/xtensa/kernel/syscall.c | 2 +- fs/pipe.c | 23 ++++++++++++++++++----- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/fs.h | 1 + 15 files changed, 33 insertions(+), 14 deletions(-) (limited to 'include/linux/fs.h') diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 7e028ceb93ba..465116aecb85 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1139,7 +1139,7 @@ sys32_pipe (int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index 1eda194b9559..bcbb6d8792d3 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -160,7 +160,7 @@ sys_pipe (void) int fd[2]; int retval; - retval = do_pipe(fd); + retval = do_pipe_flags(fd, 0); if (retval) goto out; retval = fd[0]; diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3523c8d12eda..343015a2f418 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -52,7 +52,7 @@ asmlinkage int sysm_pipe(nabi_no_regargs volatile struct pt_regs regs) int fd[2]; int error, res; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) { res = error; goto out; diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c index 0c5b9dabb475..be255ebb609c 100644 --- a/arch/parisc/hpux/sys_hpux.c +++ b/arch/parisc/hpux/sys_hpux.c @@ -448,7 +448,7 @@ int hpux_pipe(int *kstack_fildes) int error; lock_kernel(); - error = do_pipe(kstack_fildes); + error = do_pipe_flags(kstack_fildes, 0); unlock_kernel(); return error; } diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index 125e493ead82..f0aa5c398656 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -29,7 +29,7 @@ asmlinkage int sys_pipe(unsigned long r4, unsigned long r5, int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (!error) { regs->regs[1] = fd[1]; return fd[0]; diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c index 3c6b49a53ae8..4d73421559c3 100644 --- a/arch/sparc/kernel/sys_sparc.c +++ b/arch/sparc/kernel/sys_sparc.c @@ -97,7 +97,7 @@ asmlinkage int sparc_pipe(struct pt_regs *regs) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) goto out; regs->u_regs[UREG_I1] = fd[1]; diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c index e1f4eba2e576..39749e32dc7e 100644 --- a/arch/sparc64/kernel/sys_sparc.c +++ b/arch/sparc64/kernel/sys_sparc.c @@ -418,7 +418,7 @@ asmlinkage long sparc_pipe(struct pt_regs *regs) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (error) goto out; regs->u_regs[UREG_I1] = fd[1]; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 5614a8f7bed4..18808b164570 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -830,4 +830,5 @@ ia32_sys_call_table: .quad sys_eventfd2 .quad sys_epoll_create2 .quad sys_dup3 /* 330 */ + .quad sys_pipe2 ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f00afdf61e67..d3c64088b981 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -238,7 +238,7 @@ asmlinkage long sys32_pipe(int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 24a3f1ea6a0e..66154769d52f 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -330,3 +330,4 @@ ENTRY(sys_call_table) .long sys_eventfd2 .long sys_epoll_create2 .long sys_dup3 /* 330 */ + .long sys_pipe2 diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index f3e16efcd47a..ac15ecbdf919 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -49,7 +49,7 @@ asmlinkage long xtensa_pipe(int __user *userfds) int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, 0); if (!error) { if (copy_to_user(userfds, fd, 2 * sizeof(int))) error = -EFAULT; diff --git a/fs/pipe.c b/fs/pipe.c index 700f4e0d9572..68e82061070c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1027,12 +1027,15 @@ struct file *create_read_pipe(struct file *wrf) return f; } -int do_pipe(int *fd) +int do_pipe_flags(int *fd, int flags) { struct file *fw, *fr; int error; int fdw, fdr; + if (flags & ~O_CLOEXEC) + return -EINVAL; + fw = create_write_pipe(); if (IS_ERR(fw)) return PTR_ERR(fw); @@ -1041,12 +1044,12 @@ int do_pipe(int *fd) if (IS_ERR(fr)) goto err_write_pipe; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; - error = get_unused_fd(); + error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; @@ -1074,16 +1077,21 @@ int do_pipe(int *fd) return error; } +int do_pipe(int *fd) +{ + return do_pipe_flags(fd, 0); +} + /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ -asmlinkage long __weak sys_pipe(int __user *fildes) +asmlinkage long __weak sys_pipe2(int __user *fildes, int flags) { int fd[2]; int error; - error = do_pipe(fd); + error = do_pipe_flags(fd, flags); if (!error) { if (copy_to_user(fildes, fd, sizeof(fd))) { sys_close(fd[0]); @@ -1094,6 +1102,11 @@ asmlinkage long __weak sys_pipe(int __user *fildes) return error; } +asmlinkage long __weak sys_pipe(int __user *fildes) +{ + return sys_pipe2(fildes, 0); +} + /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index a1f6383bf695..748a05c77da4 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -336,6 +336,7 @@ #define __NR_eventfd2 328 #define __NR_epoll_create2 329 #define __NR_dup3 330 +#define __NR_pipe2 331 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index f0fb2bd40cdb..d2284b43ad58 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -649,6 +649,8 @@ __SYSCALL(__NR_eventfd2, sys_eventfd2) __SYSCALL(__NR_epoll_create2, sys_epoll_create2) #define __NR_dup3 292 __SYSCALL(__NR_dup3, sys_dup3) +#define __NR_pipe2 293 +__SYSCALL(__NR_pipe2, sys_pipe2) #ifndef __NO_STUBS diff --git a/include/linux/fs.h b/include/linux/fs.h index e5e6a244096c..0e80cd717d32 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,6 +1777,7 @@ static inline void allow_write_access(struct file *file) atomic_inc(&file->f_path.dentry->d_inode->i_writecount); } extern int do_pipe(int *); +extern int do_pipe_flags(int *, int); extern struct file *create_read_pipe(struct file *f); extern struct file *create_write_pipe(void); extern void free_write_pipe(struct file *); -- cgit From be61a86d7237dd80510615f38ae21d6e1e98660c Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:40 -0700 Subject: flag parameters: NONBLOCK in pipe This patch adds O_NONBLOCK support to pipe2. It is minimally more involved than the patches for eventfd et.al but still trivial. The interfaces of the create_write_pipe and create_read_pipe helper functions were changed and the one other caller as well. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fds[2]; if (syscall (__NR_pipe2, fds, 0) == -1) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { printf ("pipe2(0) set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } if (syscall (__NR_pipe2, fds, O_NONBLOCK) == -1) { puts ("pipe2(O_NONBLOCK) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { printf ("pipe2(O_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 14 +++++++------- include/linux/fs.h | 4 ++-- kernel/kmod.c | 4 ++-- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/pipe.c b/fs/pipe.c index 68e82061070c..10c4e9aa5c49 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -950,7 +950,7 @@ fail_inode: return NULL; } -struct file *create_write_pipe(void) +struct file *create_write_pipe(int flags) { int err; struct inode *inode; @@ -983,7 +983,7 @@ struct file *create_write_pipe(void) goto err_dentry; f->f_mapping = inode->i_mapping; - f->f_flags = O_WRONLY; + f->f_flags = O_WRONLY | (flags & O_NONBLOCK); f->f_version = 0; return f; @@ -1007,7 +1007,7 @@ void free_write_pipe(struct file *f) put_filp(f); } -struct file *create_read_pipe(struct file *wrf) +struct file *create_read_pipe(struct file *wrf, int flags) { struct file *f = get_empty_filp(); if (!f) @@ -1019,7 +1019,7 @@ struct file *create_read_pipe(struct file *wrf) f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping; f->f_pos = 0; - f->f_flags = O_RDONLY; + f->f_flags = O_RDONLY | (flags & O_NONBLOCK); f->f_op = &read_pipe_fops; f->f_mode = FMODE_READ; f->f_version = 0; @@ -1033,13 +1033,13 @@ int do_pipe_flags(int *fd, int flags) int error; int fdw, fdr; - if (flags & ~O_CLOEXEC) + if (flags & ~(O_CLOEXEC | O_NONBLOCK)) return -EINVAL; - fw = create_write_pipe(); + fw = create_write_pipe(flags); if (IS_ERR(fw)) return PTR_ERR(fw); - fr = create_read_pipe(fw); + fr = create_read_pipe(fw, flags); error = PTR_ERR(fr); if (IS_ERR(fr)) goto err_write_pipe; diff --git a/include/linux/fs.h b/include/linux/fs.h index 0e80cd717d32..4b86f806014c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1778,8 +1778,8 @@ static inline void allow_write_access(struct file *file) } extern int do_pipe(int *); extern int do_pipe_flags(int *, int); -extern struct file *create_read_pipe(struct file *f); -extern struct file *create_write_pipe(void); +extern struct file *create_read_pipe(struct file *f, int flags); +extern struct file *create_write_pipe(int flags); extern void free_write_pipe(struct file *); extern struct file *do_filp_open(int dfd, const char *pathname, diff --git a/kernel/kmod.c b/kernel/kmod.c index 90d7af1c1655..2989f67c4446 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -417,12 +417,12 @@ int call_usermodehelper_stdinpipe(struct subprocess_info *sub_info, { struct file *f; - f = create_write_pipe(); + f = create_write_pipe(0); if (IS_ERR(f)) return PTR_ERR(f); *filp = f; - f = create_read_pipe(f); + f = create_read_pipe(f, 0); if (IS_ERR(f)) { free_write_pipe(*filp); return PTR_ERR(f); -- cgit From bde74e4bc64415b142e556a34d295a52a1b7da9d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 25 Jul 2008 01:48:57 -0700 Subject: locks: add special return value for asynchronous locks Use a special error value FILE_LOCK_DEFERRED to mean that a locking operation returned asynchronously. This is returned by posix_lock_file() for sleeping locks to mean that the lock has been queued on the block list, and will be woken up when it might become available and needs to be retried (either fl_lmops->fl_notify() is called or fl_wait is woken up). f_op->lock() to mean either the above, or that the filesystem will call back with fl_lmops->fl_grant() when the result of the locking operation is known. The filesystem can do this for sleeping as well as non-sleeping locks. This is to make sure, that return values of -EAGAIN and -EINPROGRESS by filesystems are not mistaken to mean an asynchronous locking. This also makes error handling in fs/locks.c and lockd/svclock.c slightly cleaner. Signed-off-by: Miklos Szeredi Cc: Trond Myklebust Cc: "J. Bruce Fields" Cc: Matthew Wilcox Cc: David Teigland Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dlm/plock.c | 2 +- fs/lockd/svclock.c | 13 ++++--------- fs/locks.c | 28 ++++++++++++++-------------- include/linux/fs.h | 6 ++++++ 4 files changed, 25 insertions(+), 24 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index 78878c5781ca..eba87ff3177b 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -116,7 +116,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, if (xop->callback == NULL) wait_event(recv_wq, (op->done != 0)); else { - rv = -EINPROGRESS; + rv = FILE_LOCK_DEFERRED; goto out; } diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 821b9acdfb66..cf0d5c2c318d 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -418,8 +418,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; case -EAGAIN: ret = nlm_lck_denied; - break; - case -EINPROGRESS: + goto out; + case FILE_LOCK_DEFERRED: if (wait) break; /* Filesystem lock operation is in progress @@ -434,10 +434,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - ret = nlm_lck_denied; - if (!wait) - goto out; - ret = nlm_lck_blocked; /* Append to list of blocked */ @@ -507,7 +503,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, } error = vfs_test_lock(file->f_file, &lock->fl); - if (error == -EINPROGRESS) { + if (error == FILE_LOCK_DEFERRED) { ret = nlmsvc_defer_lock_rqst(rqstp, block); goto out; } @@ -731,8 +727,7 @@ nlmsvc_grant_blocked(struct nlm_block *block) switch (error) { case 0: break; - case -EAGAIN: - case -EINPROGRESS: + case FILE_LOCK_DEFERRED: dprintk("lockd: lock still blocked error %d\n", error); nlmsvc_insert_block(block, NLM_NEVER); nlmsvc_release_block(block); diff --git a/fs/locks.c b/fs/locks.c index dce8c747371c..1ce57b4b362c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -779,8 +779,10 @@ find_conflict: if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; - if (request->fl_flags & FL_SLEEP) - locks_insert_block(fl, request); + if (!(request->fl_flags & FL_SLEEP)) + goto out; + error = FILE_LOCK_DEFERRED; + locks_insert_block(fl, request); goto out; } if (request->fl_flags & FL_ACCESS) @@ -836,7 +838,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str error = -EDEADLK; if (posix_locks_deadlock(request, fl)) goto out; - error = -EAGAIN; + error = FILE_LOCK_DEFERRED; locks_insert_block(fl, request); goto out; } @@ -1035,7 +1037,7 @@ int posix_lock_file_wait(struct file *filp, struct file_lock *fl) might_sleep (); for (;;) { error = posix_lock_file(filp, fl, NULL); - if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP)) + if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); if (!error) @@ -1107,9 +1109,7 @@ int locks_mandatory_area(int read_write, struct inode *inode, for (;;) { error = __posix_lock_file(inode, &fl, NULL); - if (error != -EAGAIN) - break; - if (!(fl.fl_flags & FL_SLEEP)) + if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl.fl_wait, !fl.fl_next); if (!error) { @@ -1531,7 +1531,7 @@ int flock_lock_file_wait(struct file *filp, struct file_lock *fl) might_sleep(); for (;;) { error = flock_lock_file(filp, fl); - if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP)) + if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); if (!error) @@ -1716,17 +1716,17 @@ out: * fl_grant is set. Callers expecting ->lock() to return asynchronously * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if) * the request is for a blocking lock. When ->lock() does return asynchronously, - * it must return -EINPROGRESS, and call ->fl_grant() when the lock + * it must return FILE_LOCK_DEFERRED, and call ->fl_grant() when the lock * request completes. * If the request is for non-blocking lock the file system should return - * -EINPROGRESS then try to get the lock and call the callback routine with - * the result. If the request timed out the callback routine will return a + * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine + * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call - * ->fl_grant() before returning to the caller with a -EINPROGRESS + * ->fl_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) @@ -1804,7 +1804,7 @@ again: else { for (;;) { error = posix_lock_file(filp, file_lock, NULL); - if (error != -EAGAIN || cmd == F_SETLK) + if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(file_lock->fl_wait, !file_lock->fl_next); @@ -1941,7 +1941,7 @@ again: else { for (;;) { error = posix_lock_file(filp, file_lock, NULL); - if (error != -EAGAIN || cmd == F_SETLK64) + if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(file_lock->fl_wait, !file_lock->fl_next); diff --git a/include/linux/fs.h b/include/linux/fs.h index 4b86f806014c..49d8eb7a71be 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -885,6 +885,12 @@ static inline int file_check_writeable(struct file *filp) #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ +/* + * Special return value from posix_lock_file() and vfs_lock_file() for + * asynchronous locking. + */ +#define FILE_LOCK_DEFERRED 1 + /* * The POSIX file lock owner is determined by * the "struct files_struct" in the thread group -- cgit From 19fd6231279be3c3bdd02ed99f9b0eb195978064 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:32 -0700 Subject: mm: spinlock tree_lock mapping->tree_lock has no read lockers. convert the lock from an rwlock to a spinlock. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 4 ++-- fs/inode.c | 2 +- include/asm-arm/cacheflush.h | 4 ++-- include/asm-parisc/cacheflush.h | 4 ++-- include/linux/fs.h | 2 +- mm/filemap.c | 10 +++++----- mm/migrate.c | 11 +++++------ mm/page-writeback.c | 12 ++++++------ mm/swap_state.c | 10 +++++----- mm/swapfile.c | 4 ++-- mm/truncate.c | 6 +++--- mm/vmscan.c | 8 ++++---- 12 files changed, 38 insertions(+), 39 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/buffer.c b/fs/buffer.c index d48caee12e2a..109b261192d9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -706,7 +706,7 @@ static int __set_page_dirty(struct page *page, if (TestSetPageDirty(page)) return 0; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); @@ -719,7 +719,7 @@ static int __set_page_dirty(struct page *page, radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return 1; diff --git a/fs/inode.c b/fs/inode.c index c36d9480335c..35b6414522ea 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -209,7 +209,7 @@ void inode_init_once(struct inode *inode) INIT_LIST_HEAD(&inode->i_dentry); INIT_LIST_HEAD(&inode->i_devices); INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); - rwlock_init(&inode->i_data.tree_lock); + spin_lock_init(&inode->i_data.tree_lock); spin_lock_init(&inode->i_data.i_mmap_lock); INIT_LIST_HEAD(&inode->i_data.private_list); spin_lock_init(&inode->i_data.private_lock); diff --git a/include/asm-arm/cacheflush.h b/include/asm-arm/cacheflush.h index 70b0fe724b62..03cf1ee977b7 100644 --- a/include/asm-arm/cacheflush.h +++ b/include/asm-arm/cacheflush.h @@ -424,9 +424,9 @@ static inline void flush_anon_page(struct vm_area_struct *vma, } #define flush_dcache_mmap_lock(mapping) \ - write_lock_irq(&(mapping)->tree_lock) + spin_lock_irq(&(mapping)->tree_lock) #define flush_dcache_mmap_unlock(mapping) \ - write_unlock_irq(&(mapping)->tree_lock) + spin_unlock_irq(&(mapping)->tree_lock) #define flush_icache_user_range(vma,page,addr,len) \ flush_dcache_page(page) diff --git a/include/asm-parisc/cacheflush.h b/include/asm-parisc/cacheflush.h index 2f1e1b05440a..b7ca6dc7fddc 100644 --- a/include/asm-parisc/cacheflush.h +++ b/include/asm-parisc/cacheflush.h @@ -45,9 +45,9 @@ void flush_cache_mm(struct mm_struct *mm); extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) \ - write_lock_irq(&(mapping)->tree_lock) + spin_lock_irq(&(mapping)->tree_lock) #define flush_dcache_mmap_unlock(mapping) \ - write_unlock_irq(&(mapping)->tree_lock) + spin_unlock_irq(&(mapping)->tree_lock) #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page(page); \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 49d8eb7a71be..53d2edb709b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -499,7 +499,7 @@ struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ - rwlock_t tree_lock; /* and rwlock protecting it */ + spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ diff --git a/mm/filemap.c b/mm/filemap.c index feb8448d8618..2ed8b0389c51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -109,7 +109,7 @@ /* * Remove a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold a write_lock on the mapping's tree_lock. + * is safe. The caller must hold the mapping's tree_lock. */ void __remove_from_page_cache(struct page *page) { @@ -141,9 +141,9 @@ void remove_from_page_cache(struct page *page) BUG_ON(!PageLocked(page)); - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); } static int sync_page(void *word) @@ -469,7 +469,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->mapping = mapping; page->index = offset; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); error = radix_tree_insert(&mapping->page_tree, offset, page); if (likely(!error)) { mapping->nrpages++; @@ -480,7 +480,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page_cache_release(page); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); } else mem_cgroup_uncharge_cache_page(page); diff --git a/mm/migrate.c b/mm/migrate.c index 3ca6392e82cc..153572fb60b8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -323,7 +323,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, return 0; } - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); @@ -331,12 +331,12 @@ static int migrate_page_move_mapping(struct address_space *mapping, expected_count = 2 + !!PagePrivate(page); if (page_count(page) != expected_count || (struct page *)radix_tree_deref_slot(pslot) != page) { - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } if (!page_freeze_refs(page, expected_count)) { - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -373,10 +373,9 @@ static int migrate_page_move_mapping(struct address_space *mapping, __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); - write_unlock_irq(&mapping->tree_lock); - if (!PageSwapCache(newpage)) { + spin_unlock_irq(&mapping->tree_lock); + if (!PageSwapCache(newpage)) mem_cgroup_uncharge_cache_page(page); - } return 0; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 94c6d8988ab3..24de8b65fdbd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1088,7 +1088,7 @@ int __set_page_dirty_nobuffers(struct page *page) if (!mapping) return 1; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); @@ -1102,7 +1102,7 @@ int __set_page_dirty_nobuffers(struct page *page) radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); @@ -1258,7 +1258,7 @@ int test_clear_page_writeback(struct page *page) struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestClearPageWriteback(page); if (ret) { radix_tree_tag_clear(&mapping->page_tree, @@ -1269,7 +1269,7 @@ int test_clear_page_writeback(struct page *page) __bdi_writeout_inc(bdi); } } - write_unlock_irqrestore(&mapping->tree_lock, flags); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestClearPageWriteback(page); } @@ -1287,7 +1287,7 @@ int test_set_page_writeback(struct page *page) struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestSetPageWriteback(page); if (!ret) { radix_tree_tag_set(&mapping->page_tree, @@ -1300,7 +1300,7 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - write_unlock_irqrestore(&mapping->tree_lock, flags); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); } diff --git a/mm/swap_state.c b/mm/swap_state.c index 3e3381d6c7ee..2c217e33d497 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -39,7 +39,7 @@ static struct backing_dev_info swap_backing_dev_info = { struct address_space swapper_space = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .tree_lock = __RW_LOCK_UNLOCKED(swapper_space.tree_lock), + .tree_lock = __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock), .a_ops = &swap_aops, .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear), .backing_dev_info = &swap_backing_dev_info, @@ -80,7 +80,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) SetPageSwapCache(page); set_page_private(page, entry.val); - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); error = radix_tree_insert(&swapper_space.page_tree, entry.val, page); if (likely(!error)) { @@ -88,7 +88,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) __inc_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(add_total); } - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); radix_tree_preload_end(); if (unlikely(error)) { @@ -182,9 +182,9 @@ void delete_from_swap_cache(struct page *page) entry.val = page_private(page); - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); __delete_from_swap_cache(page); - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); swap_free(entry); page_cache_release(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2f33edb8bee9..af283933c14e 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -369,13 +369,13 @@ int remove_exclusive_swap_page(struct page *page) retval = 0; if (p->swap_map[swp_offset(entry)] == 1) { /* Recheck the page count with the swapcache lock held.. */ - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); if ((page_count(page) == 2) && !PageWriteback(page)) { __delete_from_swap_cache(page); SetPageDirty(page); retval = 1; } - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); } spin_unlock(&swap_lock); diff --git a/mm/truncate.c b/mm/truncate.c index b8961cb63414..e68443d74567 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -349,18 +349,18 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); if (PageDirty(page)) goto failed; BUG_ON(PagePrivate(page)); __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); ClearPageUptodate(page); page_cache_release(page); /* pagecache ref */ return 1; failed: - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 0075eac1cd04..8f71761bc4b7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -399,7 +399,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); /* * The non racy check for a busy page. * @@ -436,17 +436,17 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; __delete_from_swap_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); swap_free(swap); } else { __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); } return 1; cannot_free: - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return 0; } -- cgit From d2d9648ec6858e19d16a0b16da62534e85888653 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Tue, 1 Jul 2008 14:16:09 +0200 Subject: [PATCH] reuse xxx_fifo_fops for xxx_pipe_fops Merge fifo and pipe file_operations. Signed-off-by: Denys Vlasenko Signed-off-by: Al Viro --- fs/fifo.c | 8 ++++---- fs/pipe.c | 51 ++++++++------------------------------------------- include/linux/fs.h | 6 +++--- 3 files changed, 15 insertions(+), 50 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/fifo.c b/fs/fifo.c index 9785e36f81e7..987bf9411495 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -57,7 +57,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ - filp->f_op = &read_fifo_fops; + filp->f_op = &read_pipefifo_fops; pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(inode); @@ -86,7 +86,7 @@ static int fifo_open(struct inode *inode, struct file *filp) if ((filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; - filp->f_op = &write_fifo_fops; + filp->f_op = &write_pipefifo_fops; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(inode); @@ -105,7 +105,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ - filp->f_op = &rdwr_fifo_fops; + filp->f_op = &rdwr_pipefifo_fops; pipe->readers++; pipe->writers++; @@ -151,5 +151,5 @@ err_nocleanup: * depending on the access mode of the file... */ const struct file_operations def_fifo_fops = { - .open = fifo_open, /* will set read or write pipe_fops */ + .open = fifo_open, /* will set read_ or write_pipefifo_fops */ }; diff --git a/fs/pipe.c b/fs/pipe.c index 10c4e9aa5c49..fcba6542b8d0 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -777,45 +777,10 @@ pipe_rdwr_open(struct inode *inode, struct file *filp) /* * The file_operations structs are not static because they * are also used in linux/fs/fifo.c to do operations on FIFOs. + * + * Pipes reuse fifos' file_operations structs. */ -const struct file_operations read_fifo_fops = { - .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = bad_pipe_w, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_read_open, - .release = pipe_read_release, - .fasync = pipe_read_fasync, -}; - -const struct file_operations write_fifo_fops = { - .llseek = no_llseek, - .read = bad_pipe_r, - .write = do_sync_write, - .aio_write = pipe_write, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_write_open, - .release = pipe_write_release, - .fasync = pipe_write_fasync, -}; - -const struct file_operations rdwr_fifo_fops = { - .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = do_sync_write, - .aio_write = pipe_write, - .poll = pipe_poll, - .unlocked_ioctl = pipe_ioctl, - .open = pipe_rdwr_open, - .release = pipe_rdwr_release, - .fasync = pipe_rdwr_fasync, -}; - -static const struct file_operations read_pipe_fops = { +const struct file_operations read_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, @@ -827,7 +792,7 @@ static const struct file_operations read_pipe_fops = { .fasync = pipe_read_fasync, }; -static const struct file_operations write_pipe_fops = { +const struct file_operations write_pipefifo_fops = { .llseek = no_llseek, .read = bad_pipe_r, .write = do_sync_write, @@ -839,7 +804,7 @@ static const struct file_operations write_pipe_fops = { .fasync = pipe_write_fasync, }; -static const struct file_operations rdwr_pipe_fops = { +const struct file_operations rdwr_pipefifo_fops = { .llseek = no_llseek, .read = do_sync_read, .aio_read = pipe_read, @@ -927,7 +892,7 @@ static struct inode * get_pipe_inode(void) inode->i_pipe = pipe; pipe->readers = pipe->writers = 1; - inode->i_fop = &rdwr_pipe_fops; + inode->i_fop = &rdwr_pipefifo_fops; /* * Mark the inode dirty from the very beginning, @@ -978,7 +943,7 @@ struct file *create_write_pipe(int flags) d_instantiate(dentry, inode); err = -ENFILE; - f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipe_fops); + f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipefifo_fops); if (!f) goto err_dentry; f->f_mapping = inode->i_mapping; @@ -1020,7 +985,7 @@ struct file *create_read_pipe(struct file *wrf, int flags) f->f_pos = 0; f->f_flags = O_RDONLY | (flags & O_NONBLOCK); - f->f_op = &read_pipe_fops; + f->f_op = &read_pipefifo_fops; f->f_mode = FMODE_READ; f->f_version = 0; diff --git a/include/linux/fs.h b/include/linux/fs.h index 53d2edb709b3..7721a2ac9c0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1696,9 +1696,9 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern const struct file_operations read_fifo_fops; -extern const struct file_operations write_fifo_fops; -extern const struct file_operations rdwr_fifo_fops; +extern const struct file_operations read_pipefifo_fops; +extern const struct file_operations write_pipefifo_fops; +extern const struct file_operations rdwr_pipefifo_fops; extern int fs_may_remount_ro(struct super_block *); -- cgit From e6305c43eda10ebfd2ad9e35d6e172ccc7bb3695 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 15 Jul 2008 21:03:57 -0400 Subject: [PATCH] sanitize ->permission() prototype * kill nameidata * argument; map the 3 bits in ->flags anybody cares about to new MAY_... ones and pass with the mask. * kill redundant gfs2_iop_permission() * sanitize ecryptfs_permission() * fix remaining places where ->permission() instances might barf on new MAY_... found in mask. The obvious next target in that direction is permission(9) folded fix for nfs_permission() breakage from Miklos Szeredi Signed-off-by: Al Viro --- fs/afs/internal.h | 4 +--- fs/afs/security.c | 2 +- fs/bad_inode.c | 3 +-- fs/cifs/cifsfs.c | 2 +- fs/coda/dir.c | 4 +++- fs/coda/pioctl.c | 6 ++---- fs/ecryptfs/inode.c | 17 ++--------------- fs/ext2/acl.c | 2 +- fs/ext2/acl.h | 2 +- fs/ext3/acl.c | 2 +- fs/ext3/acl.h | 2 +- fs/ext4/acl.c | 2 +- fs/ext4/acl.h | 2 +- fs/fuse/dir.c | 6 +++--- fs/gfs2/ops_inode.c | 12 +++--------- fs/hfs/inode.c | 3 +-- fs/hfsplus/inode.c | 2 +- fs/hostfs/hostfs_kern.c | 2 +- fs/jffs2/acl.c | 2 +- fs/jffs2/acl.h | 2 +- fs/jfs/acl.c | 2 +- fs/jfs/jfs_acl.h | 2 +- fs/namei.c | 23 +++++++++++++++++------ fs/nfs/dir.c | 11 +++++------ fs/ocfs2/file.c | 2 +- fs/ocfs2/file.h | 3 +-- fs/proc/base.c | 3 +-- fs/proc/proc_sysctl.c | 2 +- fs/reiserfs/xattr.c | 2 +- fs/smbfs/file.c | 4 ++-- fs/xfs/linux-2.6/xfs_iops.c | 3 +-- include/linux/coda_linux.h | 2 +- include/linux/fs.h | 5 ++++- include/linux/nfs_fs.h | 2 +- include/linux/reiserfs_xattr.h | 2 +- include/linux/shmem_fs.h | 2 +- kernel/sysctl.c | 10 +++++----- mm/shmem_acl.c | 2 +- 38 files changed, 74 insertions(+), 87 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 7102824ba847..3cb6920ff30b 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -469,8 +469,6 @@ extern bool afs_cm_incoming_call(struct afs_call *); extern const struct inode_operations afs_dir_inode_operations; extern const struct file_operations afs_dir_file_operations; -extern int afs_permission(struct inode *, int, struct nameidata *); - /* * file.c */ @@ -605,7 +603,7 @@ extern void afs_clear_permits(struct afs_vnode *); extern void afs_cache_permit(struct afs_vnode *, struct key *, long); extern void afs_zap_permits(struct rcu_head *); extern struct key *afs_request_key(struct afs_cell *); -extern int afs_permission(struct inode *, int, struct nameidata *); +extern int afs_permission(struct inode *, int); /* * server.c diff --git a/fs/afs/security.c b/fs/afs/security.c index 3bcbeceba1bb..3ef504370034 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -284,7 +284,7 @@ static int afs_check_permit(struct afs_vnode *vnode, struct key *key, * - AFS ACLs are attached to directories only, and a file is controlled by its * parent directory's ACL */ -int afs_permission(struct inode *inode, int mask, struct nameidata *nd) +int afs_permission(struct inode *inode, int mask) { struct afs_vnode *vnode = AFS_FS_I(inode); afs_access_t uninitialized_var(access); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index f1c2ea8342f5..5f1538c03b1b 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -243,8 +243,7 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, return -EIO; } -static int bad_inode_permission(struct inode *inode, int mask, - struct nameidata *nd) +static int bad_inode_permission(struct inode *inode, int mask) { return -EIO; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index fe5f6809cba6..1ec7076f7b24 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -267,7 +267,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -static int cifs_permission(struct inode *inode, int mask, struct nameidata *nd) +static int cifs_permission(struct inode *inode, int mask) { struct cifs_sb_info *cifs_sb; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 3d2580e00a3e..c5916228243c 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -137,9 +137,11 @@ exit: } -int coda_permission(struct inode *inode, int mask, struct nameidata *nd) +int coda_permission(struct inode *inode, int mask) { int error = 0; + + mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (!mask) return 0; diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index c21a1f552a63..c38a98974fb0 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -24,8 +24,7 @@ #include /* pioctl ops */ -static int coda_ioctl_permission(struct inode *inode, int mask, - struct nameidata *nd); +static int coda_ioctl_permission(struct inode *inode, int mask); static int coda_pioctl(struct inode * inode, struct file * filp, unsigned int cmd, unsigned long user_data); @@ -42,8 +41,7 @@ const struct file_operations coda_ioctl_operations = { }; /* the coda pioctl inode ops */ -static int coda_ioctl_permission(struct inode *inode, int mask, - struct nameidata *nd) +static int coda_ioctl_permission(struct inode *inode, int mask) { return 0; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index d755455e3bff..32f4228efcd5 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -830,22 +830,9 @@ out: } static int -ecryptfs_permission(struct inode *inode, int mask, struct nameidata *nd) +ecryptfs_permission(struct inode *inode, int mask) { - int rc; - - if (nd) { - struct vfsmount *vfsmnt_save = nd->path.mnt; - struct dentry *dentry_save = nd->path.dentry; - - nd->path.mnt = ecryptfs_dentry_to_lower_mnt(nd->path.dentry); - nd->path.dentry = ecryptfs_dentry_to_lower(nd->path.dentry); - rc = permission(ecryptfs_inode_to_lower(inode), mask, nd); - nd->path.mnt = vfsmnt_save; - nd->path.dentry = dentry_save; - } else - rc = permission(ecryptfs_inode_to_lower(inode), mask, NULL); - return rc; + return permission(ecryptfs_inode_to_lower(inode), mask, NULL); } /** diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index e58669e1b87c..ae8c4f850b27 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -294,7 +294,7 @@ ext2_check_acl(struct inode *inode, int mask) } int -ext2_permission(struct inode *inode, int mask, struct nameidata *nd) +ext2_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, ext2_check_acl); } diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h index 0bde85bafe38..b42cf578554b 100644 --- a/fs/ext2/acl.h +++ b/fs/ext2/acl.h @@ -58,7 +58,7 @@ static inline int ext2_acl_count(size_t size) #define EXT2_ACL_NOT_CACHED ((void *)-1) /* acl.c */ -extern int ext2_permission (struct inode *, int, struct nameidata *); +extern int ext2_permission (struct inode *, int); extern int ext2_acl_chmod (struct inode *); extern int ext2_init_acl (struct inode *, struct inode *); diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index a754d1848173..b60bb241880c 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -299,7 +299,7 @@ ext3_check_acl(struct inode *inode, int mask) } int -ext3_permission(struct inode *inode, int mask, struct nameidata *nd) +ext3_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, ext3_check_acl); } diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h index 0d1e6279cbfd..42da16b8cac0 100644 --- a/fs/ext3/acl.h +++ b/fs/ext3/acl.h @@ -58,7 +58,7 @@ static inline int ext3_acl_count(size_t size) #define EXT3_ACL_NOT_CACHED ((void *)-1) /* acl.c */ -extern int ext3_permission (struct inode *, int, struct nameidata *); +extern int ext3_permission (struct inode *, int); extern int ext3_acl_chmod (struct inode *); extern int ext3_init_acl (handle_t *, struct inode *, struct inode *); diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 3c8dab880d91..c7d04e165446 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -299,7 +299,7 @@ ext4_check_acl(struct inode *inode, int mask) } int -ext4_permission(struct inode *inode, int mask, struct nameidata *nd) +ext4_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, ext4_check_acl); } diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 26a5c1abf147..cd2b855a07d6 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -58,7 +58,7 @@ static inline int ext4_acl_count(size_t size) #define EXT4_ACL_NOT_CACHED ((void *)-1) /* acl.c */ -extern int ext4_permission (struct inode *, int, struct nameidata *); +extern int ext4_permission (struct inode *, int); extern int ext4_acl_chmod (struct inode *); extern int ext4_init_acl (handle_t *, struct inode *, struct inode *); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 51d0035ff07e..48a7934cb950 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -898,7 +898,7 @@ static int fuse_access(struct inode *inode, int mask) return PTR_ERR(req); memset(&inarg, 0, sizeof(inarg)); - inarg.mask = mask; + inarg.mask = mask & (MAY_READ | MAY_WRITE | MAY_EXEC); req->in.h.opcode = FUSE_ACCESS; req->in.h.nodeid = get_node_id(inode); req->in.numargs = 1; @@ -927,7 +927,7 @@ static int fuse_access(struct inode *inode, int mask) * access request is sent. Execute permission is still checked * locally based on file mode. */ -static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) +static int fuse_permission(struct inode *inode, int mask) { struct fuse_conn *fc = get_fuse_conn(inode); bool refreshed = false; @@ -962,7 +962,7 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd) exist. So if permissions are revoked this won't be noticed immediately, only after the attribute timeout has expired */ - } else if (nd && (nd->flags & (LOOKUP_ACCESS | LOOKUP_CHDIR))) { + } else if (mask & (MAY_ACCESS | MAY_CHDIR)) { err = fuse_access(inode, mask); } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) { if (!(inode->i_mode & S_IXUGO)) { diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 1e252dfc5294..4e982532f085 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -915,12 +915,6 @@ int gfs2_permission(struct inode *inode, int mask) return error; } -static int gfs2_iop_permission(struct inode *inode, int mask, - struct nameidata *nd) -{ - return gfs2_permission(inode, mask); -} - static int setattr_size(struct inode *inode, struct iattr *attr) { struct gfs2_inode *ip = GFS2_I(inode); @@ -1150,7 +1144,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name) } const struct inode_operations gfs2_file_iops = { - .permission = gfs2_iop_permission, + .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, .setxattr = gfs2_setxattr, @@ -1169,7 +1163,7 @@ const struct inode_operations gfs2_dir_iops = { .rmdir = gfs2_rmdir, .mknod = gfs2_mknod, .rename = gfs2_rename, - .permission = gfs2_iop_permission, + .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, .setxattr = gfs2_setxattr, @@ -1181,7 +1175,7 @@ const struct inode_operations gfs2_dir_iops = { const struct inode_operations gfs2_symlink_iops = { .readlink = gfs2_readlink, .follow_link = gfs2_follow_link, - .permission = gfs2_iop_permission, + .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, .setxattr = gfs2_setxattr, diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index dc4ec640e875..aa73f3fd5dd9 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -511,8 +511,7 @@ void hfs_clear_inode(struct inode *inode) } } -static int hfs_permission(struct inode *inode, int mask, - struct nameidata *nd) +static int hfs_permission(struct inode *inode, int mask) { if (S_ISREG(inode->i_mode) && mask & MAY_EXEC) return 0; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index cc3b5e24339b..d4014e3044d2 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -238,7 +238,7 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms) perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev); } -static int hfsplus_permission(struct inode *inode, int mask, struct nameidata *nd) +static int hfsplus_permission(struct inode *inode, int mask) { /* MAY_EXEC is also used for lookup, if no x bit is set allow lookup, * open_exec has the same test, so it's still not executable, if a x bit diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 5222345ddccf..d6ecabf4d231 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -822,7 +822,7 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from, return err; } -int hostfs_permission(struct inode *ino, int desired, struct nameidata *nd) +int hostfs_permission(struct inode *ino, int desired) { char *name; int r = 0, w = 0, x = 0, err; diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 4c80404a9aba..d98713777a1b 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -314,7 +314,7 @@ static int jffs2_check_acl(struct inode *inode, int mask) return -EAGAIN; } -int jffs2_permission(struct inode *inode, int mask, struct nameidata *nd) +int jffs2_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, jffs2_check_acl); } diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h index 0bb7f003fd80..8ca058aed384 100644 --- a/fs/jffs2/acl.h +++ b/fs/jffs2/acl.h @@ -28,7 +28,7 @@ struct jffs2_acl_header { #define JFFS2_ACL_NOT_CACHED ((void *)-1) -extern int jffs2_permission(struct inode *, int, struct nameidata *); +extern int jffs2_permission(struct inode *, int); extern int jffs2_acl_chmod(struct inode *); extern int jffs2_init_acl_pre(struct inode *, struct inode *, int *); extern int jffs2_init_acl_post(struct inode *); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 4d84bdc88299..d3e5c33665de 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -140,7 +140,7 @@ static int jfs_check_acl(struct inode *inode, int mask) return -EAGAIN; } -int jfs_permission(struct inode *inode, int mask, struct nameidata *nd) +int jfs_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, jfs_check_acl); } diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index 455fa4292045..88475f10a389 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -20,7 +20,7 @@ #ifdef CONFIG_JFS_POSIX_ACL -int jfs_permission(struct inode *, int, struct nameidata *); +int jfs_permission(struct inode *, int); int jfs_init_acl(tid_t, struct inode *, struct inode *); int jfs_setattr(struct dentry *, struct iattr *); diff --git a/fs/namei.c b/fs/namei.c index 3b26a240ade9..46af98ed136b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -185,6 +185,8 @@ int generic_permission(struct inode *inode, int mask, { umode_t mode = inode->i_mode; + mask &= MAY_READ | MAY_WRITE | MAY_EXEC; + if (current->fsuid == inode->i_uid) mode >>= 6; else { @@ -203,7 +205,7 @@ int generic_permission(struct inode *inode, int mask, /* * If the DACs are ok we don't need any capability check. */ - if (((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)) + if ((mask & ~mode) == 0) return 0; check_capabilities: @@ -228,7 +230,7 @@ int generic_permission(struct inode *inode, int mask, int permission(struct inode *inode, int mask, struct nameidata *nd) { - int retval, submask; + int retval; struct vfsmount *mnt = NULL; if (nd) @@ -261,9 +263,17 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) } /* Ordinary permission routines do not understand MAY_APPEND. */ - submask = mask & ~MAY_APPEND; if (inode->i_op && inode->i_op->permission) { - retval = inode->i_op->permission(inode, submask, nd); + int extra = 0; + if (nd) { + if (nd->flags & LOOKUP_ACCESS) + extra |= MAY_ACCESS; + if (nd->flags & LOOKUP_CHDIR) + extra |= MAY_CHDIR; + if (nd->flags & LOOKUP_OPEN) + extra |= MAY_OPEN; + } + retval = inode->i_op->permission(inode, mask | extra); if (!retval) { /* * Exec permission on a regular file is denied if none @@ -277,7 +287,7 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) return -EACCES; } } else { - retval = generic_permission(inode, submask, NULL); + retval = generic_permission(inode, mask, NULL); } if (retval) return retval; @@ -286,7 +296,8 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) if (retval) return retval; - return security_inode_permission(inode, mask, nd); + return security_inode_permission(inode, + mask & (MAY_READ|MAY_WRITE|MAY_EXEC), nd); } /** diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 28a238dab23a..74f92b717f78 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1884,7 +1884,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) return status; nfs_access_add_cache(inode, &cache); out: - if ((cache.mask & mask) == mask) + if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) return 0; return -EACCES; } @@ -1907,17 +1907,17 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); } -int nfs_permission(struct inode *inode, int mask, struct nameidata *nd) +int nfs_permission(struct inode *inode, int mask) { struct rpc_cred *cred; int res = 0; nfs_inc_stats(inode, NFSIOS_VFSACCESS); - if (mask == 0) + if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) goto out; /* Is this sys_access() ? */ - if (nd != NULL && (nd->flags & LOOKUP_ACCESS)) + if (mask & MAY_ACCESS) goto force_lookup; switch (inode->i_mode & S_IFMT) { @@ -1926,8 +1926,7 @@ int nfs_permission(struct inode *inode, int mask, struct nameidata *nd) case S_IFREG: /* NFSv4 has atomic_open... */ if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN) - && nd != NULL - && (nd->flags & LOOKUP_OPEN)) + && (mask & MAY_OPEN)) goto out; break; case S_IFDIR: diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index e8514e8b6ce8..be2dd95d3a1d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1176,7 +1176,7 @@ bail: return err; } -int ocfs2_permission(struct inode *inode, int mask, struct nameidata *nd) +int ocfs2_permission(struct inode *inode, int mask) { int ret; diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 048ddcaf5c80..1e27b4d017ea 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -62,8 +62,7 @@ int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di, int ocfs2_setattr(struct dentry *dentry, struct iattr *attr); int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); -int ocfs2_permission(struct inode *inode, int mask, - struct nameidata *nd); +int ocfs2_permission(struct inode *inode, int mask); int ocfs2_should_update_atime(struct inode *inode, struct vfsmount *vfsmnt); diff --git a/fs/proc/base.c b/fs/proc/base.c index 81bce6791bfc..d82d800389f6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1859,8 +1859,7 @@ static const struct file_operations proc_fd_operations = { * /proc/pid/fd needs a special permission handler so that a process can still * access /proc/self/fd after it has executed a setuid(). */ -static int proc_fd_permission(struct inode *inode, int mask, - struct nameidata *nd) +static int proc_fd_permission(struct inode *inode, int mask) { int rv; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fa1ec2433e44..f9a8b892718f 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -292,7 +292,7 @@ out: return ret; } -static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *nd) +static int proc_sys_permission(struct inode *inode, int mask) { /* * sysctl entries that are not writeable, diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index d7c4935c1034..bb3cb5b7cdb2 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -1250,7 +1250,7 @@ static int reiserfs_check_acl(struct inode *inode, int mask) return error; } -int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd) +int reiserfs_permission(struct inode *inode, int mask) { /* * We don't do permission checks on the internal objects. diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index 2294783320cb..e4f8d51a5553 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -408,7 +408,7 @@ smb_file_release(struct inode *inode, struct file * file) * privileges, so we need our own check for this. */ static int -smb_file_permission(struct inode *inode, int mask, struct nameidata *nd) +smb_file_permission(struct inode *inode, int mask) { int mode = inode->i_mode; int error = 0; @@ -417,7 +417,7 @@ smb_file_permission(struct inode *inode, int mask, struct nameidata *nd) /* Look at user permissions */ mode >>= 6; - if ((mode & 7 & mask) != mask) + if (mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) error = -EACCES; return error; } diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index 2bf287ef5489..5fc61c824bb9 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -589,8 +589,7 @@ xfs_check_acl( STATIC int xfs_vn_permission( struct inode *inode, - int mask, - struct nameidata *nd) + int mask) { return generic_permission(inode, mask, xfs_check_acl); } diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index 31b75311e2ca..dcc228aa335a 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -37,7 +37,7 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); int coda_release(struct inode *i, struct file *f); -int coda_permission(struct inode *inode, int mask, struct nameidata *nd); +int coda_permission(struct inode *inode, int mask); int coda_revalidate_inode(struct dentry *); int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *); int coda_setattr(struct dentry *, struct iattr *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7721a2ac9c0e..6c923c9b79bc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -60,6 +60,9 @@ extern int dir_notify_enable; #define MAY_WRITE 2 #define MAY_READ 4 #define MAY_APPEND 8 +#define MAY_ACCESS 16 +#define MAY_CHDIR 32 +#define MAY_OPEN 64 #define FMODE_READ 1 #define FMODE_WRITE 2 @@ -1272,7 +1275,7 @@ struct inode_operations { void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, struct nameidata *); + int (*permission) (struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 29d261918734..f08f9ca602af 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -332,7 +332,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int nfs_permission(struct inode *, int, struct nameidata *); +extern int nfs_permission(struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 66a96814d614..af135ae895db 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -55,7 +55,7 @@ int reiserfs_removexattr(struct dentry *dentry, const char *name); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); int reiserfs_xattr_init(struct super_block *sb, int mount_flags); -int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd); +int reiserfs_permission(struct inode *inode, int mask); int reiserfs_xattr_del(struct inode *, const char *); int reiserfs_xattr_get(const struct inode *, const char *, void *, size_t); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f2d12d5a21b8..fd83f2584b15 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -43,7 +43,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) } #ifdef CONFIG_TMPFS_POSIX_ACL -int shmem_permission(struct inode *, int, struct nameidata *); +int shmem_permission(struct inode *, int); int shmem_acl_init(struct inode *, struct inode *); void shmem_acl_destroy_inode(struct inode *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ff5abcca5ddf..911d846f0503 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1516,9 +1516,9 @@ static int do_sysctl_strategy(struct ctl_table_root *root, int op = 0, rc; if (oldval) - op |= 004; + op |= MAY_READ; if (newval) - op |= 002; + op |= MAY_WRITE; if (sysctl_perm(root, table, op)) return -EPERM; @@ -1560,7 +1560,7 @@ repeat: if (n == table->ctl_name) { int error; if (table->child) { - if (sysctl_perm(root, table, 001)) + if (sysctl_perm(root, table, MAY_EXEC)) return -EPERM; name++; nlen--; @@ -1635,7 +1635,7 @@ static int test_perm(int mode, int op) mode >>= 6; else if (in_egroup_p(0)) mode >>= 3; - if ((mode & op & 0007) == op) + if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) return 0; return -EACCES; } @@ -1645,7 +1645,7 @@ int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op) int error; int mode; - error = security_sysctl(table, op); + error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC)); if (error) return error; diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index f5664c5b9eb1..8e5aadd7dcd6 100644 --- a/mm/shmem_acl.c +++ b/mm/shmem_acl.c @@ -191,7 +191,7 @@ shmem_check_acl(struct inode *inode, int mask) * shmem_permission - permission() inode operation */ int -shmem_permission(struct inode *inode, int mask, struct nameidata *nd) +shmem_permission(struct inode *inode, int mask) { return generic_permission(inode, mask, shmem_check_acl); } -- cgit From 2f1936b87783a3a56c9441b27b9ba7a747f11e8e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 24 Jun 2008 16:50:14 +0200 Subject: [patch 3/5] vfs: change remove_suid() to file_remove_suid() All calls to remove_suid() are made with a file pointer, because (similarly to file_update_time) it is called when the file is written. Clean up callers by passing in a file instead of a dentry. Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 2 +- fs/ntfs/file.c | 2 +- fs/splice.c | 4 ++-- fs/xfs/linux-2.6/xfs_lrw.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 7 ++++--- mm/filemap_xip.c | 2 +- 7 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 67ff2c6a8f63..2bada6bbc317 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -893,7 +893,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 3c5550cd11d6..d020866d4232 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2118,7 +2118,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, goto out; if (!count) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; file_update_time(file); diff --git a/fs/splice.c b/fs/splice.c index 47dc1a445d1f..b30311ba8af6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -772,7 +772,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, ssize_t ret; int err; - err = remove_suid(out->f_path.dentry); + err = file_remove_suid(out); if (unlikely(err)) return err; @@ -830,7 +830,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, ssize_t ret; inode_double_lock(inode, pipe->inode); - ret = remove_suid(out->f_path.dentry); + ret = file_remove_suid(out); if (likely(!ret)) ret = __splice_from_pipe(pipe, &sd, pipe_to_file); inode_double_unlock(inode, pipe->inode); diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 5e3b57516ec7..82333b3e118e 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -711,7 +711,7 @@ start: !capable(CAP_FSETID)) { error = xfs_write_clear_setuid(xip); if (likely(!error)) - error = -remove_suid(file->f_path.dentry); + error = -file_remove_suid(file); if (unlikely(error)) { goto out_unlock_internal; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c923c9b79bc..1a3546e69f9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1834,7 +1834,7 @@ extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int should_remove_suid(struct dentry *); -extern int remove_suid(struct dentry *); +extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); diff --git a/mm/filemap.c b/mm/filemap.c index 2ed8b0389c51..5de7633e1dbe 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1758,8 +1758,9 @@ static int __remove_suid(struct dentry *dentry, int kill) return notify_change(dentry, &newattrs); } -int remove_suid(struct dentry *dentry) +int file_remove_suid(struct file *file) { + struct dentry *dentry = file->f_path.dentry; int killsuid = should_remove_suid(dentry); int killpriv = security_inode_need_killpriv(dentry); int error = 0; @@ -1773,7 +1774,7 @@ int remove_suid(struct dentry *dentry) return error; } -EXPORT_SYMBOL(remove_suid); +EXPORT_SYMBOL(file_remove_suid); static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) @@ -2529,7 +2530,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 3e744abcce9d..98a3f31ccd6a 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -380,7 +380,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, if (count == 0) goto out_backing; - ret = remove_suid(filp->f_path.dentry); + ret = file_remove_suid(filp); if (ret) goto out_backing; -- cgit From db2e747b14991a4c6a5c98b0e5f552a193237c03 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 24 Jun 2008 16:50:16 +0200 Subject: [patch 5/5] vfs: remove mode parameter from vfs_symlink() Remove the unused mode parameter from vfs_symlink and callers. Thanks to Tetsuo Handa for noticing. CC: Tetsuo Handa Signed-off-by: Miklos Szeredi --- fs/ecryptfs/inode.c | 4 +--- fs/namei.c | 4 ++-- fs/nfsd/vfs.c | 10 ++-------- include/linux/fs.h | 2 +- 4 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 32f4228efcd5..f25caf2b0887 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -465,7 +465,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, int rc; struct dentry *lower_dentry; struct dentry *lower_dir_dentry; - umode_t mode; char *encoded_symname; int encoded_symlen; struct ecryptfs_crypt_stat *crypt_stat = NULL; @@ -473,7 +472,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, lower_dentry = ecryptfs_dentry_to_lower(dentry); dget(lower_dentry); lower_dir_dentry = lock_parent(lower_dentry); - mode = S_IALLUGO; encoded_symlen = ecryptfs_encode_filename(crypt_stat, symname, strlen(symname), &encoded_symname); @@ -482,7 +480,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, goto out_lock; } rc = vfs_symlink(lower_dir_dentry->d_inode, lower_dentry, - encoded_symname, mode); + encoded_symname); kfree(encoded_symname); if (rc || !lower_dentry->d_inode) goto out_lock; diff --git a/fs/namei.c b/fs/namei.c index 3b67be7631dc..ae0e56fdb742 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2434,7 +2434,7 @@ asmlinkage long sys_unlink(const char __user *pathname) return do_unlinkat(AT_FDCWD, pathname); } -int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode) +int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { int error = may_create(dir, dentry, NULL); @@ -2483,7 +2483,7 @@ asmlinkage long sys_symlinkat(const char __user *oldname, error = mnt_want_write(nd.path.mnt); if (error) goto out_dput; - error = vfs_symlink(nd.path.dentry->d_inode, dentry, from, S_IALLUGO); + error = vfs_symlink(nd.path.dentry->d_inode, dentry, from); mnt_drop_write(nd.path.mnt); out_dput: dput(dentry); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 0f4481e0502d..ad1ad59e3742 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1516,7 +1516,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, struct dentry *dentry, *dnew; __be32 err, cerr; int host_err; - umode_t mode; err = nfserr_noent; if (!flen || !plen) @@ -1535,11 +1534,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dnew)) goto out_nfserr; - mode = S_IALLUGO; - /* Only the MODE ATTRibute is even vaguely meaningful */ - if (iap && (iap->ia_valid & ATTR_MODE)) - mode = iap->ia_mode & S_IALLUGO; - host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); if (host_err) goto out_nfserr; @@ -1551,11 +1545,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, else { strncpy(path_alloced, path, plen); path_alloced[plen] = 0; - host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced, mode); + host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced); kfree(path_alloced); } } else - host_err = vfs_symlink(dentry->d_inode, dnew, path, mode); + host_err = vfs_symlink(dentry->d_inode, dnew, path); if (!host_err) { if (EX_ISSYNC(fhp->fh_export)) diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a3546e69f9e..25998e803fc2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1139,7 +1139,7 @@ extern int vfs_permission(struct nameidata *, int); extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *); extern int vfs_mkdir(struct inode *, struct dentry *, int); extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *, int); +extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *); -- cgit From a110343f0d6d41f68b7cf8c00b57a3172c67f816 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Jul 2008 09:19:08 -0400 Subject: [PATCH] fix MAY_CHDIR/MAY_ACCESS/LOOKUP_ACCESS mess * MAY_CHDIR is redundant - it's an equivalent of MAY_ACCESS * MAY_ACCESS on fuse should affect only the last step of pathname resolution * fchdir() and chroot() should pass MAY_ACCESS, for the same reason why chdir() needs that. * now that we pass MAY_ACCESS explicitly in all cases, LOOKUP_ACCESS can be removed; it has no business being in nameidata. Signed-off-by: Al Viro --- fs/fuse/dir.c | 2 +- fs/namei.c | 2 -- fs/open.c | 10 +++++----- include/linux/fs.h | 3 +-- include/linux/namei.h | 1 - 5 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 48a7934cb950..fd03330cadeb 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -962,7 +962,7 @@ static int fuse_permission(struct inode *inode, int mask) exist. So if permissions are revoked this won't be noticed immediately, only after the attribute timeout has expired */ - } else if (mask & (MAY_ACCESS | MAY_CHDIR)) { + } else if (mask & MAY_ACCESS) { err = fuse_access(inode, mask); } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) { if (!(inode->i_mode & S_IXUGO)) { diff --git a/fs/namei.c b/fs/namei.c index 095818089ac1..33dcaf025c49 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -265,8 +265,6 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) if (inode->i_op && inode->i_op->permission) { int extra = 0; if (nd) { - if (nd->flags & LOOKUP_ACCESS) - extra |= MAY_ACCESS; if (nd->flags & LOOKUP_OPEN) extra |= MAY_OPEN; } diff --git a/fs/open.c b/fs/open.c index d3a2a00f52dc..3317e1909b2c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -457,11 +457,11 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) old_cap = cap_set_effective(current->cap_permitted); } - res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd); + res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd); if (res) goto out; - res = vfs_permission(&nd, mode); + res = vfs_permission(&nd, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if(res || !(mode & S_IWOTH) || special_file(nd.path.dentry->d_inode->i_mode)) @@ -505,7 +505,7 @@ asmlinkage long sys_chdir(const char __user * filename) if (error) goto out; - error = vfs_permission(&nd, MAY_EXEC | MAY_CHDIR); + error = vfs_permission(&nd, MAY_EXEC | MAY_ACCESS); if (error) goto dput_and_out; @@ -534,7 +534,7 @@ asmlinkage long sys_fchdir(unsigned int fd) if (!S_ISDIR(inode->i_mode)) goto out_putf; - error = file_permission(file, MAY_EXEC); + error = file_permission(file, MAY_EXEC | MAY_ACCESS); if (!error) set_fs_pwd(current->fs, &file->f_path); out_putf: @@ -552,7 +552,7 @@ asmlinkage long sys_chroot(const char __user * filename) if (error) goto out; - error = vfs_permission(&nd, MAY_EXEC); + error = vfs_permission(&nd, MAY_EXEC | MAY_ACCESS); if (error) goto dput_and_out; diff --git a/include/linux/fs.h b/include/linux/fs.h index 25998e803fc2..d8721e818b45 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -61,8 +61,7 @@ extern int dir_notify_enable; #define MAY_READ 4 #define MAY_APPEND 8 #define MAY_ACCESS 16 -#define MAY_CHDIR 32 -#define MAY_OPEN 64 +#define MAY_OPEN 32 #define FMODE_READ 1 #define FMODE_WRITE 2 diff --git a/include/linux/namei.h b/include/linux/namei.h index 768773d57857..60e35a02f6cb 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -53,7 +53,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; */ #define LOOKUP_OPEN (0x0100) #define LOOKUP_CREATE (0x0200) -#define LOOKUP_ACCESS (0x0400) extern int __user_walk(const char __user *, unsigned, struct nameidata *); extern int __user_walk_fd(int dfd, const char __user *, unsigned, struct nameidata *); -- cgit From 9767d74957450da6365c363d69e3d02d605d7375 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 1 Jul 2008 15:01:26 +0200 Subject: [patch 1/4] vfs: utimes: move owner check into inode_change_ok() Add a new ia_valid flag: ATTR_TIMES_SET, to handle the UTIMES_OMIT/UTIMES_NOW and UTIMES_NOW/UTIMES_OMIT cases. In these cases neither ATTR_MTIME_SET nor ATTR_ATIME_SET is in the flags, yet the POSIX draft specifies that permission checking is performed the same way as if one or both of the times was explicitly set to a timestamp. See the path "vfs: utimensat(): fix error checking for {UTIME_NOW,UTIME_OMIT} case" by Michael Kerrisk for the patch introducing this behavior. This is a cleanup, as well as allowing filesystems (NFS/fuse/...) to perform their own permission checking instead of the default. CC: Ulrich Drepper CC: Michael Kerrisk Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- fs/attr.c | 2 +- fs/utimes.c | 17 ++++------------- include/linux/fs.h | 33 +++++++++++++++++---------------- 3 files changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/attr.c b/fs/attr.c index 966b73e25f82..765fc75fab3b 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -51,7 +51,7 @@ int inode_change_ok(struct inode *inode, struct iattr *attr) } /* Check for setting the inode time. */ - if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) { + if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!is_owner_or_cap(inode)) goto error; } diff --git a/fs/utimes.c b/fs/utimes.c index b6b664e7145e..ecf8941ba34a 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -101,7 +101,6 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags times[1].tv_nsec == UTIME_NOW) times = NULL; - /* In most cases, the checks are done in inode_change_ok() */ newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; if (times) { error = -EPERM; @@ -123,21 +122,13 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags newattrs.ia_mtime.tv_nsec = times[1].tv_nsec; newattrs.ia_valid |= ATTR_MTIME_SET; } - /* - * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT - * cases, we need to make an extra check that is not done by - * inode_change_ok(). + * Tell inode_change_ok(), that this is an explicit time + * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET + * were used. */ - if (((times[0].tv_nsec == UTIME_NOW && - times[1].tv_nsec == UTIME_OMIT) - || - (times[0].tv_nsec == UTIME_OMIT && - times[1].tv_nsec == UTIME_NOW)) - && !is_owner_or_cap(inode)) - goto mnt_drop_write_and_out; + newattrs.ia_valid |= ATTR_TIMES_SET; } else { - /* * If times is NULL (or both times are UTIME_NOW), * then we need to check permissions, because diff --git a/include/linux/fs.h b/include/linux/fs.h index d8721e818b45..527b9e482f99 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -320,22 +320,23 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Attribute flags. These should be or-ed together to figure out what * has been changed! */ -#define ATTR_MODE 1 -#define ATTR_UID 2 -#define ATTR_GID 4 -#define ATTR_SIZE 8 -#define ATTR_ATIME 16 -#define ATTR_MTIME 32 -#define ATTR_CTIME 64 -#define ATTR_ATIME_SET 128 -#define ATTR_MTIME_SET 256 -#define ATTR_FORCE 512 /* Not a change, but a change it */ -#define ATTR_ATTR_FLAG 1024 -#define ATTR_KILL_SUID 2048 -#define ATTR_KILL_SGID 4096 -#define ATTR_FILE 8192 -#define ATTR_KILL_PRIV 16384 -#define ATTR_OPEN 32768 /* Truncating from open(O_TRUNC) */ +#define ATTR_MODE (1 << 0) +#define ATTR_UID (1 << 1) +#define ATTR_GID (1 << 2) +#define ATTR_SIZE (1 << 3) +#define ATTR_ATIME (1 << 4) +#define ATTR_MTIME (1 << 5) +#define ATTR_CTIME (1 << 6) +#define ATTR_ATIME_SET (1 << 7) +#define ATTR_MTIME_SET (1 << 8) +#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ +#define ATTR_ATTR_FLAG (1 << 10) +#define ATTR_KILL_SUID (1 << 11) +#define ATTR_KILL_SGID (1 << 12) +#define ATTR_FILE (1 << 13) +#define ATTR_KILL_PRIV (1 << 14) +#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ +#define ATTR_TIMES_SET (1 << 16) /* * This is the Inode Attributes structure, used for notify_change(). It -- cgit From f419a2e3b64def707e1384ee38abb77f99af5f6d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 22 Jul 2008 00:07:17 -0400 Subject: [PATCH] kill nameidata passing to permission(), rename to inode_permission() Incidentally, the name that gives hundreds of false positives on grep is not a good idea... Signed-off-by: Al Viro --- fs/ecryptfs/inode.c | 2 +- fs/namei.c | 22 +++++++++------------- fs/nfsd/nfsfh.c | 2 +- fs/nfsd/vfs.c | 4 ++-- fs/utimes.c | 2 +- fs/xattr.c | 2 +- include/linux/fs.h | 2 +- ipc/mqueue.c | 2 +- 8 files changed, 17 insertions(+), 21 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index f25caf2b0887..89209f00f9c7 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -830,7 +830,7 @@ out: static int ecryptfs_permission(struct inode *inode, int mask) { - return permission(ecryptfs_inode_to_lower(inode), mask, NULL); + return inode_permission(ecryptfs_inode_to_lower(inode), mask); } /** diff --git a/fs/namei.c b/fs/namei.c index 396cb3e5c364..5029b93ebbd5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -227,13 +227,9 @@ int generic_permission(struct inode *inode, int mask, return -EACCES; } -int permission(struct inode *inode, int mask, struct nameidata *nd) +int inode_permission(struct inode *inode, int mask) { int retval; - struct vfsmount *mnt = NULL; - - if (nd) - mnt = nd->path.mnt; if (mask & MAY_WRITE) { umode_t mode = inode->i_mode; @@ -293,7 +289,7 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) */ int vfs_permission(struct nameidata *nd, int mask) { - return permission(nd->path.dentry->d_inode, mask, nd); + return inode_permission(nd->path.dentry->d_inode, mask); } /** @@ -310,7 +306,7 @@ int vfs_permission(struct nameidata *nd, int mask) */ int file_permission(struct file *file, int mask) { - return permission(file->f_path.dentry->d_inode, mask, NULL); + return inode_permission(file->f_path.dentry->d_inode, mask); } /* @@ -1262,7 +1258,7 @@ static struct dentry *lookup_hash(struct nameidata *nd) { int err; - err = permission(nd->path.dentry->d_inode, MAY_EXEC, nd); + err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC); if (err) return ERR_PTR(err); return __lookup_hash(&nd->last, nd->path.dentry, nd); @@ -1310,7 +1306,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) if (err) return ERR_PTR(err); - err = permission(base->d_inode, MAY_EXEC, NULL); + err = inode_permission(base->d_inode, MAY_EXEC); if (err) return ERR_PTR(err); return __lookup_hash(&this, base, NULL); @@ -1400,7 +1396,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir) BUG_ON(victim->d_parent->d_inode != dir); audit_inode_child(victim->d_name.name, victim, dir); - error = permission(dir,MAY_WRITE | MAY_EXEC, NULL); + error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) @@ -1437,7 +1433,7 @@ static inline int may_create(struct inode *dir, struct dentry *child, return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; - return permission(dir,MAY_WRITE | MAY_EXEC, nd); + return inode_permission(dir, MAY_WRITE | MAY_EXEC); } /* @@ -2543,7 +2539,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, * we'll need to flip '..'. */ if (new_dir != old_dir) { - error = permission(old_dentry->d_inode, MAY_WRITE, NULL); + error = inode_permission(old_dentry->d_inode, MAY_WRITE); if (error) return error; } @@ -2897,7 +2893,7 @@ EXPORT_SYMBOL(page_symlink); EXPORT_SYMBOL(page_symlink_inode_operations); EXPORT_SYMBOL(path_lookup); EXPORT_SYMBOL(vfs_path_lookup); -EXPORT_SYMBOL(permission); +EXPORT_SYMBOL(inode_permission); EXPORT_SYMBOL(vfs_permission); EXPORT_SYMBOL(file_permission); EXPORT_SYMBOL(unlock_rename); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index f45451eb1e38..ea37c96f0445 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -51,7 +51,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) /* make sure parents give x permission to user */ int err; parent = dget_parent(tdentry); - err = permission(parent->d_inode, MAY_EXEC, NULL); + err = inode_permission(parent->d_inode, MAY_EXEC); if (err < 0) { dput(parent); break; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ad1ad59e3742..18060bed5267 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1953,12 +1953,12 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ - err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL); + err = inode_permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC)); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE)) - err = permission(inode, MAY_EXEC, NULL); + err = inode_permission(inode, MAY_EXEC); return err? nfserrno(err) : 0; } diff --git a/fs/utimes.c b/fs/utimes.c index dad679d3a158..dc28b7826259 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -96,7 +96,7 @@ static int utimes_common(struct path *path, struct timespec *times) goto mnt_drop_write_and_out; if (!is_owner_or_cap(inode)) { - error = permission(inode, MAY_WRITE, NULL); + error = inode_permission(inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; } diff --git a/fs/xattr.c b/fs/xattr.c index 4706a8b1f495..b96222e05ba0 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -63,7 +63,7 @@ xattr_permission(struct inode *inode, const char *name, int mask) return -EPERM; } - return permission(inode, mask, NULL); + return inode_permission(inode, mask); } int diff --git a/include/linux/fs.h b/include/linux/fs.h index 527b9e482f99..9d2de4cadabd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1770,7 +1770,7 @@ extern int do_remount_sb(struct super_block *sb, int flags, extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); -extern int permission(struct inode *, int, struct nameidata *); +extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int, int (*check_acl)(struct inode *, int)); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 474984f9e032..96fb36cd9874 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -638,7 +638,7 @@ static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, return ERR_PTR(-EINVAL); } - if (permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE], NULL)) { + if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) { dput(dentry); mntput(mqueue_mnt); return ERR_PTR(-EACCES); -- cgit From 516e0cc5646f377ab80fcc2ee639892eccb99853 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 26 Jul 2008 00:39:17 -0400 Subject: [PATCH] f_count may wrap around make it atomic_long_t; while we are at it, get rid of useless checks in affs, hfs and hpfs - ->open() always has it equal to 1, ->release() - to 0. Signed-off-by: Al Viro --- drivers/net/ppp_generic.c | 6 +++--- fs/affs/file.c | 4 ---- fs/aio.c | 6 +++--- fs/file_table.c | 10 +++++----- fs/hfs/inode.c | 4 ---- fs/hfsplus/inode.c | 4 ---- include/linux/fs.h | 6 +++--- include/net/af_unix.h | 2 +- net/sched/sch_atm.c | 4 ++-- net/unix/af_unix.c | 2 +- net/unix/garbage.c | 18 +++++++++--------- 11 files changed, 27 insertions(+), 39 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 739b3ab7bccc..ddccc074a76a 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -581,12 +581,12 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (file == ppp->owner) ppp_shutdown_interface(ppp); } - if (atomic_read(&file->f_count) <= 2) { + if (atomic_long_read(&file->f_count) <= 2) { ppp_release(NULL, file); err = 0; } else - printk(KERN_DEBUG "PPPIOCDETACH file->f_count=%d\n", - atomic_read(&file->f_count)); + printk(KERN_DEBUG "PPPIOCDETACH file->f_count=%ld\n", + atomic_long_read(&file->f_count)); unlock_kernel(); return err; } diff --git a/fs/affs/file.c b/fs/affs/file.c index 6eac7bdeec94..1377b1240b6e 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -46,8 +46,6 @@ const struct inode_operations affs_file_inode_operations = { static int affs_file_open(struct inode *inode, struct file *filp) { - if (atomic_read(&filp->f_count) != 1) - return 0; pr_debug("AFFS: open(%lu,%d)\n", inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt)); atomic_inc(&AFFS_I(inode)->i_opencnt); @@ -57,8 +55,6 @@ affs_file_open(struct inode *inode, struct file *filp) static int affs_file_release(struct inode *inode, struct file *filp) { - if (atomic_read(&filp->f_count) != 0) - return 0; pr_debug("AFFS: release(%lu, %d)\n", inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt)); diff --git a/fs/aio.c b/fs/aio.c index 0051fd94b44e..f658441d5666 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -512,8 +512,8 @@ static void aio_fput_routine(struct work_struct *data) */ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) { - dprintk(KERN_DEBUG "aio_put(%p): f_count=%d\n", - req, atomic_read(&req->ki_filp->f_count)); + dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n", + req, atomic_long_read(&req->ki_filp->f_count)); assert_spin_locked(&ctx->ctx_lock); @@ -528,7 +528,7 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) /* Must be done under the lock to serialise against cancellation. * Call this aio_fput as it duplicates fput via the fput_work. */ - if (unlikely(atomic_dec_and_test(&req->ki_filp->f_count))) { + if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) { get_ioctx(ctx); spin_lock(&fput_lock); list_add(&req->ki_list, &fput_head); diff --git a/fs/file_table.c b/fs/file_table.c index 83084225b4c3..f45a4493f9e7 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -120,7 +120,7 @@ struct file *get_empty_filp(void) tsk = current; INIT_LIST_HEAD(&f->f_u.fu_list); - atomic_set(&f->f_count, 1); + atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); f->f_uid = tsk->fsuid; f->f_gid = tsk->fsgid; @@ -219,7 +219,7 @@ EXPORT_SYMBOL(init_file); void fput(struct file *file) { - if (atomic_dec_and_test(&file->f_count)) + if (atomic_long_dec_and_test(&file->f_count)) __fput(file); } @@ -294,7 +294,7 @@ struct file *fget(unsigned int fd) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (!atomic_inc_not_zero(&file->f_count)) { + if (!atomic_long_inc_not_zero(&file->f_count)) { /* File object ref couldn't be taken */ rcu_read_unlock(); return NULL; @@ -326,7 +326,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (atomic_inc_not_zero(&file->f_count)) + if (atomic_long_inc_not_zero(&file->f_count)) *fput_needed = 1; else /* Didn't get the reference, someone's freed */ @@ -341,7 +341,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed) void put_filp(struct file *file) { - if (atomic_dec_and_test(&file->f_count)) { + if (atomic_long_dec_and_test(&file->f_count)) { security_file_free(file); file_kill(file); file_free(file); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index aa73f3fd5dd9..7e19835efa2e 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -522,8 +522,6 @@ static int hfs_file_open(struct inode *inode, struct file *file) { if (HFS_IS_RSRC(inode)) inode = HFS_I(inode)->rsrc_inode; - if (atomic_read(&file->f_count) != 1) - return 0; atomic_inc(&HFS_I(inode)->opencnt); return 0; } @@ -534,8 +532,6 @@ static int hfs_file_release(struct inode *inode, struct file *file) if (HFS_IS_RSRC(inode)) inode = HFS_I(inode)->rsrc_inode; - if (atomic_read(&file->f_count) != 0) - return 0; if (atomic_dec_and_test(&HFS_I(inode)->opencnt)) { mutex_lock(&inode->i_mutex); hfs_file_truncate(inode); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index d4014e3044d2..b085d64a2b67 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -254,8 +254,6 @@ static int hfsplus_file_open(struct inode *inode, struct file *file) { if (HFSPLUS_IS_RSRC(inode)) inode = HFSPLUS_I(inode).rsrc_inode; - if (atomic_read(&file->f_count) != 1) - return 0; atomic_inc(&HFSPLUS_I(inode).opencnt); return 0; } @@ -266,8 +264,6 @@ static int hfsplus_file_release(struct inode *inode, struct file *file) if (HFSPLUS_IS_RSRC(inode)) inode = HFSPLUS_I(inode).rsrc_inode; - if (atomic_read(&file->f_count) != 0) - return 0; if (atomic_dec_and_test(&HFSPLUS_I(inode).opencnt)) { mutex_lock(&inode->i_mutex); hfsplus_file_truncate(inode); diff --git a/include/linux/fs.h b/include/linux/fs.h index 9d2de4cadabd..7676fa1c20ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -795,7 +795,7 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; - atomic_t f_count; + atomic_long_t f_count; unsigned int f_flags; mode_t f_mode; loff_t f_pos; @@ -824,8 +824,8 @@ extern spinlock_t files_lock; #define file_list_lock() spin_lock(&files_lock); #define file_list_unlock() spin_unlock(&files_lock); -#define get_file(x) atomic_inc(&(x)->f_count) -#define file_count(x) atomic_read(&(x)->f_count) +#define get_file(x) atomic_long_inc(&(x)->f_count) +#define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT static inline void file_take_write(struct file *f) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 2dfa96b0575e..7dd29b7e461d 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -51,7 +51,7 @@ struct unix_sock { struct sock *peer; struct sock *other; struct list_head link; - atomic_t inflight; + atomic_long_t inflight; spinlock_t lock; unsigned int gc_candidate : 1; wait_queue_head_t peer_wait; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 04faa835be17..6b517b9dac5b 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -162,7 +162,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) qdisc_destroy(flow->q); tcf_destroy_chain(&flow->filter_list); if (flow->sock) { - pr_debug("atm_tc_put: f_count %d\n", + pr_debug("atm_tc_put: f_count %ld\n", file_count(flow->sock->file)); flow->vcc->pop = flow->old_pop; sockfd_put(flow->sock); @@ -259,7 +259,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, sock = sockfd_lookup(fd, &error); if (!sock) return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %d\n", file_count(sock->file)); + pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { error = -EPROTOTYPE; goto err_out; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 70ceb1604ad8..6e7fec74bdb3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -603,7 +603,7 @@ static struct sock * unix_create1(struct net *net, struct socket *sock) u->dentry = NULL; u->mnt = NULL; spin_lock_init(&u->lock); - atomic_set(&u->inflight, 0); + atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index ebdff3d877a1..2a27b84f740b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -127,7 +127,7 @@ void unix_inflight(struct file *fp) if(s) { struct unix_sock *u = unix_sk(s); spin_lock(&unix_gc_lock); - if (atomic_inc_return(&u->inflight) == 1) { + if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { @@ -145,7 +145,7 @@ void unix_notinflight(struct file *fp) struct unix_sock *u = unix_sk(s); spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); - if (atomic_dec_and_test(&u->inflight)) + if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; spin_unlock(&unix_gc_lock); @@ -237,17 +237,17 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_dec(&usk->inflight); + atomic_long_dec(&usk->inflight); } static void inc_inflight(struct unix_sock *usk) { - atomic_inc(&usk->inflight); + atomic_long_inc(&usk->inflight); } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_inc(&u->inflight); + atomic_long_inc(&u->inflight); /* * If this is still a candidate, move it to the end of the * list, so that it's checked even if it was already passed @@ -288,11 +288,11 @@ void unix_gc(void) * before the detach without atomicity guarantees. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - int total_refs; - int inflight_refs; + long total_refs; + long inflight_refs; total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_read(&u->inflight); + inflight_refs = atomic_long_read(&u->inflight); BUG_ON(inflight_refs < 1); BUG_ON(total_refs < inflight_refs); @@ -324,7 +324,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_read(&u->inflight) > 0) { + if (atomic_long_read(&u->inflight) > 0) { list_move_tail(&u->link, &gc_inflight_list); u->gc_candidate = 0; scan_children(&u->sk, inc_inflight_move_tail, NULL); -- cgit From 3f8206d496e9e9495afb1d4e70d29712b4d403c9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 26 Jul 2008 03:46:43 -0400 Subject: [PATCH] get rid of indirect users of namei.h fs.h needs path.h, not namei.h; nfs_fs.h doesn't need it at all. Several places in the tree needed direct include. Signed-off-by: Al Viro --- fs/nfsd/nfsctl.c | 1 + fs/ubifs/file.c | 1 + include/linux/fs.h | 2 +- include/linux/nfs_fs.h | 1 - kernel/cgroup.c | 1 + 5 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1955a2702e60..c53e65f8f3a2 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 005a3b854d96..8565e586e533 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -53,6 +53,7 @@ #include "ubifs.h" #include +#include static int read_block(struct inode *inode, void *addr, unsigned int block, struct ubifs_data_node *dn) diff --git a/include/linux/fs.h b/include/linux/fs.h index 7676fa1c20ae..8252b045e624 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -279,7 +279,7 @@ extern int dir_notify_enable; #include #include #include -#include +#include #include #include #include diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f08f9ca602af..78a5922a2f11 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 89bd6fb7894f..657f8f8d93a5 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -45,6 +45,7 @@ #include #include #include +#include #include -- cgit