From e1e8fb6a1ff3f9487e03a4cbf85b81d1316068ce Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 15 Apr 2011 03:02:49 +0000 Subject: fs: remove FS_COW_FL FS_COW_FL and FS_NOCOW_FL were newly introduced to control per file COW in btrfs, but FS_NOCOW_FL is sufficient. The fact is we don't have corresponding BTRFS_INODE_COW flag. COW is default, and FS_NOCOW_FL can be used to switch off COW for a single file. If we mount btrfs with nodatacow, a newly created file will be set with the FS_NOCOW_FL flag. So to turn on COW for it, we can just clear the FS_NOCOW_FL flag. Signed-off-by: Li Zefan Signed-off-by: Chris Mason --- 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 de9dd8119b71..56a41412903d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -365,7 +365,6 @@ struct inodes_stat_t { #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 v1.2.3 From 97a894136f29802da19a15541de3c019e1ca147e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:04 -0700 Subject: mm: Remove i_mmap_lock lockbreak Hugh says: "The only significant loser, I think, would be page reclaim (when concurrent with truncation): could spin for a long time waiting for the i_mmap_mutex it expects would soon be dropped? " Counter points: - cpu contention makes the spin stop (need_resched()) - zap pages should be freeing pages at a higher rate than reclaim ever can I think the simplification of the truncate code is definitely worth it. Effectively reverts: 2aa15890f3c ("mm: prevent concurrent unmap_mapping_range() on the same inode") and takes out the code that caused its problem. Signed-off-by: Peter Zijlstra Reviewed-by: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index cdf9495df204..5d2c86bdf5ba 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -635,7 +635,6 @@ struct address_space { struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ spinlock_t i_mmap_lock; /* protect tree, count, list */ - unsigned int truncate_count; /* Cover race condition with truncate */ unsigned long nrpages; /* number of total pages */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ @@ -644,7 +643,6 @@ struct address_space { spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ struct address_space *assoc_mapping; /* ditto */ - struct mutex unmap_mutex; /* to protect unmapping */ } __attribute__((aligned(sizeof(long)))); /* * On most architectures that alignment is already the case; but -- cgit v1.2.3 From 3d48ae45e72390ddf8cc5256ac32ed6f7a19cbea Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:06 -0700 Subject: mm: Convert i_mmap_lock to a mutex Straightforward conversion of i_mmap_lock to a mutex. Signed-off-by: Peter Zijlstra Acked-by: Hugh Dickins Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim 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 5d2c86bdf5ba..5bb9e826019b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -634,7 +634,7 @@ struct address_space { 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 */ - spinlock_t i_mmap_lock; /* protect tree, count, list */ + struct mutex i_mmap_mutex; /* protect tree, count, list */ unsigned long nrpages; /* number of total pages */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ -- cgit v1.2.3 From 0ac1ee0bfec2a4ad118f907ce586d0dfd8db7641 Mon Sep 17 00:00:00 2001 From: Tim Gardner Date: Tue, 24 May 2011 17:13:05 -0700 Subject: ulimit: raise default hard ulimit on number of files to 4096 Apps are increasingly using more than 1024 file descriptors. See discussion in several distro bug trackers, e.g. BugLink: http://bugs.launchpad.net/bugs/663090 https://issues.rpath.com/browse/RPL-2054 You don't want to raise the default soft limit, since that might break apps that use select(), but it's safe to raise the default hard limit; that way, apps that know they need lots of file descriptors can raise their soft limit without needing root, and without user intervention. Ubuntu is doing this with a kernel change because they have a policy of not changing kernel defaults in userland. While 4096 might not be enough for *all* apps, it seems to be plenty for the apps I've seen lately that are unhappy with 1024. Signed-off-by: Tim Gardner Cc: Dan Kegel Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5bb9e826019b..3f9d3251790d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -23,7 +23,8 @@ /* Fixed constants first: */ #undef NR_OPEN -#define INR_OPEN 1024 /* Initial setting for nfile rlimits */ +#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ +#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ #define BLOCK_SIZE_BITS 10 #define BLOCK_SIZE (1< Date: Thu, 26 May 2011 10:01:19 -0600 Subject: fs: add field to superblock to support cleancache This second patch of eight in this cleancache series adds a field to the generic superblock to squirrel away a pool identifier that is dynamically provided by cleancache-enabled filesystems at mount time to uniquely identify files and pages belonging to this mounted filesystem. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v8: trivial merge conflict update] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Cc: Andrew Morton Cc: Al Viro Cc: Matthew Wilcox Cc: Nick Piggin Cc: Mel Gorman Cc: Rik Van Riel Cc: Jan Beulich Cc: Chris Mason Cc: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index cdf9495df204..0169ed3f106e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1429,6 +1429,11 @@ struct super_block { */ char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ + + /* + * Saved pool identifier for cleancache (-1 means none) + */ + int cleancache_poolid; }; extern struct timespec current_fs_time(struct super_block *sb); -- cgit v1.2.3 From aa38572954ade525817fe88c54faebf85e5a61c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 May 2011 06:53:02 -0400 Subject: fs: pass exact type of data dirties to ->dirty_inode Tell the filesystem if we just updated timestamp (I_DIRTY_SYNC) or anything else, so that the filesystem can track internally if it needs to push out a transaction for fdatasync or not. This is just the prototype change with no user for it yet. I plan to push large XFS changes for the next merge window, and getting this trivial infrastructure in this window would help a lot to avoid tree interdependencies. Also remove incorrect comments that ->dirty_inode can't block. That has been changed a long time ago, and many implementations rely on it. Signed-off-by: Christoph Hellwig 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 241609346dfb..573028df050d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1618,7 +1618,7 @@ struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); - void (*dirty_inode) (struct inode *); + void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); -- cgit v1.2.3 From 69b4573296469fd3f70cf7044693074980517067 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 28 May 2011 08:25:51 -0700 Subject: Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn Signed-off-by: Andi Kleen Signed-off-by: Al Viro --- include/linux/fs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 573028df050d..c55d6b7cd5d6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -237,6 +237,7 @@ struct inodes_stat_t { #define S_PRIVATE 512 /* Inode is fs-internal */ #define S_IMA 1024 /* Inode has an associated IMA struct */ #define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ +#define S_NOSEC 4096 /* no suid or xattr security attributes */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -273,6 +274,7 @@ struct inodes_stat_t { #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) +#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) /* the read-only stuff doesn't really belong here, but any other place is probably as bad and I don't want to create yet another include file. */ @@ -2582,5 +2584,16 @@ int __init get_filesystem_list(char *buf); #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) +static inline int is_sxid(mode_t mode) +{ + return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); +} + +static inline void inode_has_no_xattr(struct inode *inode) +{ + if (!is_sxid(inode->i_mode)) + inode->i_flags |= S_NOSEC; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ -- cgit v1.2.3 From 9e1f1de02c2275d7172e18dc4e7c2065777611bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 3 Jun 2011 18:24:58 -0400 Subject: more conservative S_NOSEC handling Caching "we have already removed suid/caps" was overenthusiastic as merged. On network filesystems we might have had suid/caps set on another client, silently picked by this client on revalidate, all of that *without* clearing the S_NOSEC flag. AFAICS, the only reasonably sane way to deal with that is * new superblock flag; unless set, S_NOSEC is not going to be set. * local block filesystems set it in their ->mount() (more accurately, mount_bdev() does, so does btrfs ->mount(), users of mount_bdev() other than local block ones clear it) * if any network filesystem (or a cluster one) wants to use S_NOSEC, it'll need to set MS_NOSEC in sb->s_flags *AND* take care to clear S_NOSEC when inode attribute changes are picked from other clients. It's not an earth-shattering hole (anybody that can set suid on another client will almost certainly be able to write to the file before doing that anyway), but it's a bug that needs fixing. Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c55d6b7cd5d6..646a1836152a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -208,6 +208,7 @@ struct inodes_stat_t { #define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ #define MS_I_VERSION (1<<23) /* Update inode I_version field */ #define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_NOSEC (1<<28) #define MS_BORN (1<<29) #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -2591,7 +2592,7 @@ static inline int is_sxid(mode_t mode) static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) inode->i_flags |= S_NOSEC; } -- cgit v1.2.3 From 13e12d14e2dccc7995b8f15a5678a338ab4e6a8c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 8 Jun 2011 15:18:19 -0700 Subject: vfs: reorganize 'struct inode' layout a bit This tries to make the 'struct inode' accesses denser in the data cache by moving a commonly accessed field (i_security) closer to other fields that are accessed often. It also makes 'i_state' just an 'unsigned int' rather than 'unsigned long', since we only use a few bits of that field, and moves it next to the existing 'i_flags' so that we potentially get better structure layout (although depending on config options, i_flags may already have packed in the same word as i_lock, so this improves packing only for the case of spinlock debugging) Out 'struct inode' is still way too big, and we should probably move some other fields around too (the acl fields in particular) for better data cache access density. Other fields (like the inode hash) are likely to be entirely irrelevant under most loads. Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 646a1836152a..1c777878f1ea 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,9 +744,13 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned int i_flags; + unsigned int i_state; +#ifdef CONFIG_SECURITY + void *i_security; +#endif struct mutex i_mutex; - unsigned long i_state; + unsigned long dirtied_when; /* jiffies of first dirtying */ struct hlist_node i_hash; @@ -798,9 +802,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif atomic_t i_writecount; -#ifdef CONFIG_SECURITY - void *i_security; -#endif #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; -- cgit v1.2.3 From 79568f5be06c91071697c065f01f3ebfbeb25a61 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Jun 2011 20:13:49 -0700 Subject: vfs: i_state needs to be 'unsigned long' for now Commit 13e12d14e2dc ("vfs: reorganize 'struct inode' layout a bit") moved things around a bit changed i_state to be unsigned int instead of unsigned long. That was to help structure layout for the 64-bit case, and shrink 'struct inode' a bit (admittedly that only happened when spinlock debugging was on and i_flags didn't pack with i_lock). However, Meelis Roos reports that this results in unaligned exceptions on sprc, and it turns out that the bit-locking primitives that we use for the I_NEW bit want to use the bitops. Which want 'unsigned long', not 'unsigned int'. We really should fix the bit locking code to not have that kind of requirement, but that's a much bigger change. So for now, revert that field back to 'unsigned long' (but keep the other re-ordering changes from the commit that caused this). Andi points out that we have played games with this in 'struct page', so it's solvable with other hacks too, but since right now the struct inode size advantage only happens with some rare config options, it's not worth fighting. It _would_ be worth fixing the bitlocking code, though. Especially since there is no type safety in the bitlocking code (this never caused any warnings, and worked fine on x86-64, because the bitlocks take a 'void *' and x86-64 doesn't care that deeply about alignment). So it's currently a very easy problem to trigger by mistake and never notice. Reported-by: Meelis Roos Cc: Andi Kleen Cc: David Miller 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 1c777878f1ea..6e73e2e9ae33 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,7 +744,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned int i_flags; - unsigned int i_state; + unsigned long i_state; #ifdef CONFIG_SECURITY void *i_security; #endif -- cgit v1.2.3