diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-08-10 11:39:13 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-08-10 11:39:13 -0700 |
commit | 8c8946f509a494769a8c602b5ed189df01917d39 (patch) | |
tree | dfd96bd6ca5ea6803c6d77f65ba37e04f78b2d3b | |
parent | 5f248c9c251c60af3403902b26e08de43964ea0b (diff) | |
parent | 1968f5eed54ce47bde488fd9a450912e4a2d7138 (diff) |
Merge branch 'for-linus' of git://git.infradead.org/users/eparis/notify
* 'for-linus' of git://git.infradead.org/users/eparis/notify: (132 commits)
fanotify: use both marks when possible
fsnotify: pass both the vfsmount mark and inode mark
fsnotify: walk the inode and vfsmount lists simultaneously
fsnotify: rework ignored mark flushing
fsnotify: remove global fsnotify groups lists
fsnotify: remove group->mask
fsnotify: remove the global masks
fsnotify: cleanup should_send_event
fanotify: use the mark in handler functions
audit: use the mark in handler functions
dnotify: use the mark in handler functions
inotify: use the mark in handler functions
fsnotify: send fsnotify_mark to groups in event handling functions
fsnotify: Exchange list heads instead of moving elements
fsnotify: srcu to protect read side of inode and vfsmount locks
fsnotify: use an explicit flag to indicate fsnotify_destroy_mark has been called
fsnotify: use _rcu functions for mark list traversal
fsnotify: place marks on object in order of group memory address
vfs/fsnotify: fsnotify_close can delay the final work in fput
fsnotify: store struct file not struct path
...
Fix up trivial delete/modify conflict in fs/notify/inotify/inotify.c.
58 files changed, 3197 insertions, 2378 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 56cee4727b1..b16cbe4152e 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -360,14 +360,6 @@ When: 2.6.33 Why: Should be implemented in userspace, policy daemon. Who: Johannes Berg <johannes@sipsolutions.net> ---------------------------- - -What: CONFIG_INOTIFY -When: 2.6.33 -Why: last user (audit) will be converted to the newer more generic - and more easily maintained fsnotify subsystem -Who: Eric Paris <eparis@redhat.com> - ---------------------------- What: sound-slot/service-* module aliases and related clutters in diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index e790bc1fbfa..17cf65c9480 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -842,4 +842,6 @@ ia32_sys_call_table: .quad compat_sys_rt_tgsigqueueinfo /* 335 */ .quad sys_perf_event_open .quad compat_sys_recvmmsg + .quad sys_fanotify_init + .quad sys32_fanotify_mark ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 626be156d88..3d093311d5e 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -546,3 +546,12 @@ asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +asmlinkage long sys32_fanotify_mark(int fanotify_fd, unsigned int flags, + u32 mask_lo, u32 mask_hi, + int fd, const char __user *pathname) +{ + return sys_fanotify_mark(fanotify_fd, flags, + ((u64)mask_hi << 32) | mask_lo, + fd, pathname); +} diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3ad421784ae..cf4e2e381cb 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -80,4 +80,7 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *); /* ia32/ipc32.c */ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32); + +asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int, + const char __user *); #endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index beb9b5f8f8a..80b799cd74f 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -343,10 +343,12 @@ #define __NR_rt_tgsigqueueinfo 335 #define __NR_perf_event_open 336 #define __NR_recvmmsg 337 +#define __NR_fanotify_init 338 +#define __NR_fanotify_mark 339 #ifdef __KERNEL__ -#define NR_syscalls 338 +#define NR_syscalls 340 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index ff4307b0e81..5b7b1d58561 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -663,6 +663,10 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_recvmmsg 299 __SYSCALL(__NR_recvmmsg, sys_recvmmsg) +#define __NR_fanotify_init 300 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 301 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 8b372934121..07ad5eb7cc5 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -337,3 +337,5 @@ ENTRY(sys_call_table) .long sys_rt_tgsigqueueinfo /* 335 */ .long sys_perf_event_open .long sys_recvmmsg + .long sys_fanotify_init + .long sys_fanotify_mark diff --git a/fs/compat.c b/fs/compat.c index 3e57e8162a3..e6d5d70cf3c 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1193,11 +1193,10 @@ out: if (iov != iovstack) kfree(iov); if ((ret + (type == READ)) > 0) { - struct dentry *dentry = file->f_path.dentry; if (type == READ) - fsnotify_access(dentry); + fsnotify_access(file); else - fsnotify_modify(dentry); + fsnotify_modify(file); } return ret; } diff --git a/fs/exec.c b/fs/exec.c index dab85ecad68..7761837e450 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -128,7 +128,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; - fsnotify_open(file->f_path.dentry); + fsnotify_open(file); error = -ENOEXEC; if(file->f_op) { @@ -683,7 +683,7 @@ struct file *open_exec(const char *name) if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; - fsnotify_open(file->f_path.dentry); + fsnotify_open(file); err = deny_write_access(file); if (err) diff --git a/fs/file_table.c b/fs/file_table.c index 5c7d10ead4a..b8a0bb63cbd 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -230,6 +230,15 @@ static void __fput(struct file *file) might_sleep(); fsnotify_close(file); + + /* + * fsnotify_create_event may have taken one or more references on this + * file. If it did so it left one reference for us to drop to make sure + * its calls to fput could not prematurely destroy the file. + */ + if (atomic_long_read(&file->f_count)) + return fput(file); + /* * The function eventpoll_release() should be the first called * in the file cleanup chain. diff --git a/fs/inode.c b/fs/inode.c index 2575244640a..86464332e59 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -20,7 +20,6 @@ #include <linux/pagemap.h> #include <linux/cdev.h> #include <linux/bootmem.h> -#include <linux/inotify.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/async.h> @@ -264,12 +263,8 @@ void inode_init_once(struct inode *inode) INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap); INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear); i_size_ordered_init(inode); -#ifdef CONFIG_INOTIFY - INIT_LIST_HEAD(&inode->inotify_watches); - mutex_init(&inode->inotify_mutex); -#endif #ifdef CONFIG_FSNOTIFY - INIT_HLIST_HEAD(&inode->i_fsnotify_mark_entries); + INIT_HLIST_HEAD(&inode->i_fsnotify_marks); #endif } EXPORT_SYMBOL(inode_init_once); @@ -413,7 +408,6 @@ int invalidate_inodes(struct super_block *sb) down_write(&iprune_sem); spin_lock(&inode_lock); - inotify_unmount_inodes(&sb->s_inodes); fsnotify_unmount_inodes(&sb->s_inodes); busy = invalidate_list(&sb->s_inodes, &throw_away); spin_unlock(&inode_lock); diff --git a/fs/namei.c b/fs/namei.c index 42d2d28fb82..13ff4abdbdc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2633,7 +2633,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, { int error; int is_dir = S_ISDIR(old_dentry->d_inode->i_mode); - const char *old_name; + const unsigned char *old_name; if (old_dentry->d_inode == new_dentry->d_inode) return 0; diff --git a/fs/namespace.c b/fs/namespace.c index 32dcd24bbc9..66c4f7e781c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -29,6 +29,7 @@ #include <linux/log2.h> #include <linux/idr.h> #include <linux/fs_struct.h> +#include <linux/fsnotify.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include "pnode.h" @@ -150,6 +151,9 @@ struct vfsmount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); +#ifdef CONFIG_FSNOTIFY + INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks); +#endif #ifdef CONFIG_SMP mnt->mnt_writers = alloc_percpu(int); if (!mnt->mnt_writers) @@ -610,6 +614,7 @@ static inline void __mntput(struct vfsmount *mnt) * provides barriers, so count_mnt_writers() below is safe. AV */ WARN_ON(count_mnt_writers(mnt)); + fsnotify_vfsmount_delete(mnt); dput(mnt->mnt_root); free_vfsmnt(mnt); deactivate_super(sb); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 8812f6b9396..96360a83cb9 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -934,7 +934,7 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, nfsdstats.io_read += host_err; *count = host_err; err = 0; - fsnotify_access(file->f_path.dentry); + fsnotify_access(file); } else err = nfserrno(host_err); out: @@ -1045,7 +1045,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, goto out_nfserr; *cnt = host_err; nfsdstats.io_write += host_err; - fsnotify_modify(file->f_path.dentry); + fsnotify_modify(file); /* clear setuid/setgid flag after write */ if (inode->i_mode & (S_ISUID | S_ISGID)) diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index dffbb0911d0..22c629eedd8 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -3,3 +3,4 @@ config FSNOTIFY source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" +source "fs/notify/fanotify/Kconfig" diff --git a/fs/notify/Makefile b/fs/notify/Makefile index 0922cc826c4..ae5f33a6d86 100644 --- a/fs/notify/Makefile +++ b/fs/notify/Makefile @@ -1,4 +1,6 @@ -obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o +obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o \ + mark.o vfsmount_mark.o obj-y += dnotify/ obj-y += inotify/ +obj-y += fanotify/ diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 7e54e52964d..3344bdd5506 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -29,17 +29,17 @@ int dir_notify_enable __read_mostly = 1; static struct kmem_cache *dnotify_struct_cache __read_mostly; -static struct kmem_cache *dnotify_mark_entry_cache __read_mostly; +static struct kmem_cache *dnotify_mark_cache __read_mostly; static struct fsnotify_group *dnotify_group __read_mostly; static DEFINE_MUTEX(dnotify_mark_mutex); /* - * dnotify will attach one of these to each inode (i_fsnotify_mark_entries) which + * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ -struct dnotify_mark_entry { - struct fsnotify_mark_entry fsn_entry; +struct dnotify_mark { + struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; @@ -51,27 +51,27 @@ struct dnotify_mark_entry { * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ -static void dnotify_recalc_inode_mask(struct fsnotify_mark_entry *entry) +static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask, old_mask; struct dnotify_struct *dn; - struct dnotify_mark_entry *dnentry = container_of(entry, - struct dnotify_mark_entry, - fsn_entry); + struct dnotify_mark *dn_mark = container_of(fsn_mark, + struct dnotify_mark, + fsn_mark); - assert_spin_locked(&entry->lock); + assert_spin_locked(&fsn_mark->lock); - old_mask = entry->mask; + old_mask = fsn_mark->mask; new_mask = 0; - for (dn = dnentry->dn; dn != NULL; dn = dn->dn_next) + for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); - entry->mask = new_mask; + fsnotify_set_mark_mask_locked(fsn_mark, new_mask); if (old_mask == new_mask) return; - if (entry->inode) - fsnotify_recalc_inode_mask(entry->inode); + if (fsn_mark->i.inode) + fsnotify_recalc_inode_mask(fsn_mark->i.inode); } /* @@ -83,29 +83,25 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark_entry *entry) * events. */ static int dnotify_handle_event(struct fsnotify_group *group, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, struct fsnotify_event *event) { - struct fsnotify_mark_entry *entry = NULL; - struct dnotify_mark_entry *dnentry; + struct dnotify_mark *dn_mark; struct inode *to_tell; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = event->mask & ~FS_EVENT_ON_CHILD; - to_tell = event->to_tell; + BUG_ON(vfsmount_mark); - spin_lock(&to_tell->i_lock); - entry = fsnotify_find_mark_entry(group, to_tell); - spin_unlock(&to_tell->i_lock); + to_tell = event->to_tell; - /* unlikely since we alreay passed dnotify_should_send_event() */ - if (unlikely(!entry)) - return 0; - dnentry = container_of(entry, struct dnotify_mark_entry, fsn_entry); + dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); - spin_lock(&entry->lock); - prev = &dnentry->dn; + spin_lock(&inode_mark->lock); + prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; @@ -118,12 +114,11 @@ static int dnotify_handle_event(struct fsnotify_group *group, else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); - dnotify_recalc_inode_mask(entry); + dnotify_recalc_inode_mask(inode_mark); } } - spin_unlock(&entry->lock); - fsnotify_put_mark(entry); + spin_unlock(&inode_mark->lock); return 0; } @@ -133,44 +128,27 @@ static int dnotify_handle_event(struct fsnotify_group *group, * userspace notification for that pair. */ static bool dnotify_should_send_event(struct fsnotify_group *group, - struct inode *inode, __u32 mask) + struct inode *inode, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, + __u32 mask, void *data, int data_type) { - struct fsnotify_mark_entry *entry; - bool send; - - /* !dir_notify_enable should never get here, don't waste time checking - if (!dir_notify_enable) - return 0; */ - /* not a dir, dnotify doesn't care */ if (!S_ISDIR(inode->i_mode)) return false; - spin_lock(&inode->i_lock); - entry = fsnotify_find_mark_entry(group, inode); - spin_unlock(&inode->i_lock); - - /* no mark means no dnotify watch */ - if (!entry) - return false; - - mask = (mask & ~FS_EVENT_ON_CHILD); - send = (mask & entry->mask); - - fsnotify_put_mark(entry); /* matches fsnotify_find_mark_entry */ - - return send; + return true; } -static void dnotify_free_mark(struct fsnotify_mark_entry *entry) +static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { - struct dnotify_mark_entry *dnentry = container_of(entry, - struct dnotify_mark_entry, - fsn_entry); + struct dnotify_mark *dn_mark = container_of(fsn_mark, + struct dnotify_mark, + fsn_mark); - BUG_ON(dnentry->dn); + BUG_ON(dn_mark->dn); - kmem_cache_free(dnotify_mark_entry_cache, dnentry); + kmem_cache_free(dnotify_mark_cache, dn_mark); } static struct fsnotify_ops dnotify_fsnotify_ops = { @@ -183,15 +161,15 @@ static struct fsnotify_ops dnotify_fsnotify_ops = { /* * Called every time a file is closed. Looks first for a dnotify mark on the - * inode. If one is found run all of the ->dn entries attached to that + * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the - * fsnotify_mark_entry. + * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { - struct fsnotify_mark_entry *entry; - struct dnotify_mark_entry *dnentry; + struct fsnotify_mark *fsn_mark; + struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; @@ -200,38 +178,34 @@ void dnotify_flush(struct file *filp, fl_owner_t id) if (!S_ISDIR(inode->i_mode)) return; - spin_lock(&inode->i_lock); - entry = fsnotify_find_mark_entry(dnotify_group, inode); - spin_unlock(&inode->i_lock); - if (!entry) + fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode); + if (!fsn_mark) return; - dnentry = container_of(entry, struct dnotify_mark_entry, fsn_entry); + dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); mutex_lock(&dnotify_mark_mutex); - spin_lock(&entry->lock); - prev = &dnentry->dn; + spin_lock(&fsn_mark->lock); + prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); - dnotify_recalc_inode_mask(entry); + dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } - spin_unlock(&entry->lock); + spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_mark_mutex */ - if (dnentry->dn == NULL) - fsnotify_destroy_mark_by_entry(entry); - - fsnotify_recalc_group_mask(dnotify_group); + if (dn_mark->dn == NULL) + fsnotify_destroy_mark(fsn_mark); mutex_unlock(&dnotify_mark_mutex); - fsnotify_put_mark(entry); + fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ @@ -259,16 +233,16 @@ static __u32 convert_arg(unsigned long arg) /* * If multiple processes watch the same inode with dnotify there is only one - * dnotify mark in inode->i_fsnotify_mark_entries but we chain a dnotify_struct + * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ -static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark_entry *dnentry, +static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; - odn = dnentry->dn; + odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { @@ -283,8 +257,8 @@ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark_entry *dnent dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; - dn->dn_next = dnentry->dn; - dnentry->dn = dn; + dn->dn_next = dn_mark->dn; + dn_mark->dn = dn; return 0; } @@ -296,8 +270,8 @@ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark_entry *dnent */ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) { - struct dnotify_mark_entry *new_dnentry, *dnentry; - struct fsnotify_mark_entry *new_entry, *entry; + struct dnotify_mark *new_dn_mark, *dn_mark; + struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; |