From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2011 08:52:07 +0100 Subject: block: remove per-queue plugging Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index bd3215940c37..9f2cf69911b8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -583,7 +583,6 @@ typedef int (*read_actor_t)(read_descriptor_t *, struct page *, struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); - void (*sync_page)(struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); -- cgit v1.2.2 From 721a9602e6607417c6bc15b18e97a2f35266c690 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Mar 2011 11:56:30 +0100 Subject: block: kill off REQ_UNPLUG With the plugging now being explicitly controlled by the submitter, callers need not pass down unplugging hints to the block layer. If they want to unplug, it's because they manually plugged on their own - in which case, they should just unplug at will. Signed-off-by: Jens Axboe --- include/linux/fs.h | 28 +++++++++------------------- 1 file changed, 9 insertions(+), 19 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9f2cf69911b8..543e226ea6a3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -135,16 +135,10 @@ struct inodes_stat_t { * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. - * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down + * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO - * shortly. The device must still be unplugged explicitly, - * WRITE_SYNC_PLUG does not do this as we could be - * submitting more writes before we actually wait on any - * of them. - * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device - * immediately after submission. The write equivalent - * of READ_SYNC. - * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. + * shortly. The write equivalent of READ_SYNC. + * WRITE_ODIRECT Special case write for O_DIRECT only. * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on * non-volatile media on completion. @@ -160,18 +154,14 @@ struct inodes_stat_t { #define WRITE RW_MASK #define READA RWA_MASK -#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_SYNC (READ | REQ_SYNC) #define READ_META (READ | REQ_META) -#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) -#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) -#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_ODIRECT (WRITE | REQ_SYNC) #define WRITE_META (WRITE | REQ_META) -#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FLUSH) -#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FUA) -#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FLUSH | REQ_FUA) +#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) +#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) +#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define SEL_IN 1 #define SEL_OUT 2 -- cgit v1.2.2 From f3ccfcdaf3986f8c541886606e950de52cab7ad3 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Tue, 22 Mar 2011 16:33:56 -0700 Subject: fs.h: remove 8 bytes of padding from block_device on 64bit builds Re-ordering struct block_inode to remove 8 bytes of padding on 64 bit builds, which also shrinks bdev_inode by 8 bytes (776 -> 768) allowing it to fit into one fewer cache lines. Signed-off-by: Richard Kennedy Cc: Al Viro Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7061a8587ee3..12529e966350 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -662,9 +662,9 @@ struct address_space { struct block_device { dev_t bd_dev; /* not a kdev_t - it's a search key */ + int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; - int bd_openers; struct mutex bd_mutex; /* open/close mutex */ struct list_head bd_inodes; void * bd_claiming; -- cgit v1.2.2 From e795b71799ff0b27365020c9ddaa25d0d83f99c8 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:25 -0700 Subject: userns: userns: check user namespace for task->file uid equivalence checks Cheat for now and say all files belong to init_user_ns. Next step will be to let superblocks belong to a user_ns, and derive inode_userns(inode) from inode->i_sb->s_user_ns. Finally we'll introduce more flexible arrangements. Changelog: Feb 15: make is_owner_or_cap take const struct inode Feb 23: make is_owner_or_cap bool [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 12529e966350..9eebc646d14a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1457,8 +1457,13 @@ enum { #define put_fs_excl() atomic_dec(¤t->fs_excl) #define has_fs_excl() atomic_read(¤t->fs_excl) -#define is_owner_or_cap(inode) \ - ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER)) +/* + * until VFS tracks user namespaces for inodes, just make all files + * belong to init_user_ns + */ +extern struct user_namespace init_user_ns; +#define inode_userns(inode) (&init_user_ns) +extern bool is_owner_or_cap(const struct inode *inode); /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); -- cgit v1.2.2 From 2e1496707560ecf98e9b0604622c0990f94861d3 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:26 -0700 Subject: userns: rename is_owner_or_cap to inode_owner_or_capable And give it a kernel-doc comment. [akpm@linux-foundation.org: btrfs changed in linux-next] Signed-off-by: Serge E. Hallyn Cc: "Eric W. Biederman" Cc: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9eebc646d14a..4dda076c24a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1463,7 +1463,7 @@ enum { */ extern struct user_namespace init_user_ns; #define inode_userns(inode) (&init_user_ns) -extern bool is_owner_or_cap(const struct inode *inode); +extern bool inode_owner_or_capable(const struct inode *inode); /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); -- cgit v1.2.2 From 250df6ed274d767da844a5d9f05720b804240197 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:36 +1100 Subject: fs: protect inode->i_state with inode->i_lock Protect inode state transitions and validity checks with the inode->i_lock. This enables us to make inode state transitions independently of the inode_lock and is the first step to peeling away the inode_lock from the code. This requires that __iget() is done atomically with i_state checks during list traversals so that we don't race with another thread marking the inode I_FREEING between the state check and grabbing the reference. Also remove the unlock_new_inode() memory barrier optimisation required to avoid taking the inode_lock when clearing I_NEW. Simplify the code by simply taking the inode->i_lock around the state change and wakeup. Because the wakeup is no longer tricky, remove the wake_up_inode() function and open code the wakeup where necessary. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4dda076c24a1..ed6fdcc1484c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1647,7 +1647,7 @@ struct super_operations { }; /* - * Inode state bits. Protected by inode_lock. + * Inode state bits. Protected by inode->i_lock * * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, * I_DIRTY_DATASYNC and I_DIRTY_PAGES. -- cgit v1.2.2 From 32471f6e1983922473573da62cbee58699574aa4 Mon Sep 17 00:00:00 2001 From: liubo Date: Mon, 21 Mar 2011 08:54:27 +0000 Subject: Btrfs: add datacow flag in inode flag For datacow control, the corresponding inode flags are needed. This is for btrfs use. v1->v2: Change FS_COW_FL to another bit due to conflict with the upstream e2fsprogs Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index e38b50a4b9d2..de9dd8119b71 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -364,6 +364,8 @@ struct inodes_stat_t { #define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define FS_EXTENT_FL 0x00080000 /* Extents */ #define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ +#define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_COW_FL 0x02000000 /* Cow file */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -- cgit v1.2.2