OpenCloudOS-Kernel/include/linux/mount.h

117 lines
3.6 KiB
C
Raw Normal View History

/*
*
* Definitions for mount interface. This describes the in the kernel build
* linkedlist with mounted filesystems.
*
* Author: Marco van Wieringen <mvw@planets.elm.net>
*
* Version: $Id: mount.h,v 2.0 1996/11/17 16:48:14 mvw Exp mvw $
*
*/
#ifndef _LINUX_MOUNT_H
#define _LINUX_MOUNT_H
#include <linux/types.h>
#include <linux/list.h>
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-16 06:37:59 +08:00
#include <linux/nodemask.h>
#include <linux/spinlock.h>
#include <asm/atomic.h>
struct super_block;
struct vfsmount;
struct dentry;
struct mnt_namespace;
#define MNT_NOSUID 0x01
#define MNT_NODEV 0x02
#define MNT_NOEXEC 0x04
#define MNT_NOATIME 0x08
#define MNT_NODIRATIME 0x10
#define MNT_RELATIME 0x20
#define MNT_READONLY 0x40 /* does the user want this to be r/o? */
#define MNT_SHRINKABLE 0x100
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-16 06:37:59 +08:00
#define MNT_IMBALANCED_WRITE_COUNT 0x200 /* just for debugging */
#define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */
#define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */
#define MNT_PNODE_MASK 0x3000 /* propagation flag mask */
struct vfsmount {
struct list_head mnt_hash;
struct vfsmount *mnt_parent; /* fs we are mounted on */
struct dentry *mnt_mountpoint; /* dentry of mountpoint */
struct dentry *mnt_root; /* root of the mounted tree */
struct super_block *mnt_sb; /* pointer to superblock */
struct list_head mnt_mounts; /* list of children, anchored here */
struct list_head mnt_child; /* and going through their mnt_child */
int mnt_flags;
/* 4 bytes hole on 64bits arches */
char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */
struct list_head mnt_list;
struct list_head mnt_expire; /* link in fs-specific expiry list */
struct list_head mnt_share; /* circular list of shared mounts */
struct list_head mnt_slave_list;/* list of slave mounts */
struct list_head mnt_slave; /* slave list entry */
struct vfsmount *mnt_master; /* slave is on master->mnt_slave_list */
struct mnt_namespace *mnt_ns; /* containing namespace */
int mnt_id; /* mount identifier */
int mnt_group_id; /* peer group identifier */
/*
* We put mnt_count & mnt_expiry_mark at the end of struct vfsmount
* to let these frequently modified fields in a separate cache line
* (so that reads of mnt_flags wont ping-pong on SMP machines)
*/
atomic_t mnt_count;
int mnt_expiry_mark; /* true if marked for expiry */
[PATCH] saner handling of auto_acct_off() and DQUOT_OFF() in umount The way we currently deal with quota and process accounting that might keep vfsmount busy at umount time is inherently broken; we try to turn them off just in case (not quite correctly, at that) and a) pray umount doesn't fail (otherwise they'll stay turned off) b) pray nobody doesn anything funny just as we turn quota off Moreover, LSM provides hooks for doing the same sort of broken logics. The proper way to deal with that is to introduce the second kind of reference to vfsmount. Semantics: - when the last normal reference is dropped, all special ones are converted to normal ones and if there had been any, cleanup is done. - normal reference can be cloned into a special one - special reference can be converted to normal one; that's a no-op if we'd already passed the point of no return (i.e. mntput() had converted special references to normal and started cleanup). The way it works: e.g. starting process accounting converts the vfsmount reference pinned by the opened file into special one and turns it back to normal when it gets shut down; acct_auto_close() is done when no normal references are left. That way it does *not* obstruct umount(2) and it silently gets turned off when the last normal reference to vfsmount is gone. Which is exactly what we want... The same should be done by LSM module that holds some internal references to vfsmount and wants to shut them down on umount - it should make them special and security_sb_umount_close() will be called exactly when the last normal reference to vfsmount is gone. quota handling is even simpler - we don't use normal file IO anymore, so there's no need to hold vfsmounts at all. DQUOT_OFF() is done from deactivate_super(), where it really belongs. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-08 06:13:39 +08:00
int mnt_pinned;
int mnt_ghosts;
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-16 06:37:59 +08:00
/*
* This value is not stable unless all of the mnt_writers[] spinlocks
* are held, and all mnt_writer[]s on this mount have 0 as their ->count
*/
atomic_t __mnt_writers;
};
static inline struct vfsmount *mntget(struct vfsmount *mnt)
{
if (mnt)
atomic_inc(&mnt->mnt_count);
return mnt;
}
extern int mnt_want_write(struct vfsmount *mnt);
extern void mnt_drop_write(struct vfsmount *mnt);
[PATCH] saner handling of auto_acct_off() and DQUOT_OFF() in umount The way we currently deal with quota and process accounting that might keep vfsmount busy at umount time is inherently broken; we try to turn them off just in case (not quite correctly, at that) and a) pray umount doesn't fail (otherwise they'll stay turned off) b) pray nobody doesn anything funny just as we turn quota off Moreover, LSM provides hooks for doing the same sort of broken logics. The proper way to deal with that is to introduce the second kind of reference to vfsmount. Semantics: - when the last normal reference is dropped, all special ones are converted to normal ones and if there had been any, cleanup is done. - normal reference can be cloned into a special one - special reference can be converted to normal one; that's a no-op if we'd already passed the point of no return (i.e. mntput() had converted special references to normal and started cleanup). The way it works: e.g. starting process accounting converts the vfsmount reference pinned by the opened file into special one and turns it back to normal when it gets shut down; acct_auto_close() is done when no normal references are left. That way it does *not* obstruct umount(2) and it silently gets turned off when the last normal reference to vfsmount is gone. Which is exactly what we want... The same should be done by LSM module that holds some internal references to vfsmount and wants to shut them down on umount - it should make them special and security_sb_umount_close() will be called exactly when the last normal reference to vfsmount is gone. quota handling is even simpler - we don't use normal file IO anymore, so there's no need to hold vfsmounts at all. DQUOT_OFF() is done from deactivate_super(), where it really belongs. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-08 06:13:39 +08:00
extern void mntput_no_expire(struct vfsmount *mnt);
extern void mnt_pin(struct vfsmount *mnt);
extern void mnt_unpin(struct vfsmount *mnt);
extern int __mnt_is_readonly(struct vfsmount *mnt);
static inline void mntput(struct vfsmount *mnt)
{
if (mnt) {
mnt->mnt_expiry_mark = 0;
mntput_no_expire(mnt);
}
}
extern struct vfsmount *do_kern_mount(const char *fstype, int flags,
const char *name, void *data);
struct file_system_type;
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
int flags, const char *name,
void *data);
struct nameidata;
extern int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
int mnt_flags, struct list_head *fslist);
extern void mark_mounts_for_expiry(struct list_head *mounts);
extern spinlock_t vfsmount_lock;
extern dev_t name_to_dev_t(char *name);
#endif /* _LINUX_MOUNT_H */