From b3e19d924b6eaf2ca7d22cba99a517c5171007b6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:11 +1100 Subject: fs: scale mntget/mntput The problem that this patch aims to fix is vfsmount refcounting scalability. We need to take a reference on the vfsmount for every successful path lookup, which often go to the same mount point. The fundamental difficulty is that a "simple" reference count can never be made scalable, because any time a reference is dropped, we must check whether that was the last reference. To do that requires communication with all other CPUs that may have taken a reference count. We can make refcounts more scalable in a couple of ways, involving keeping distributed counters, and checking for the global-zero condition less frequently. - check the global sum once every interval (this will delay zero detection for some interval, so it's probably a showstopper for vfsmounts). - keep a local count and only taking the global sum when local reaches 0 (this is difficult for vfsmounts, because we can't hold preempt off for the life of a reference, so a counter would need to be per-thread or tied strongly to a particular CPU which requires more locking). - keep a local difference of increments and decrements, which allows us to sum the total difference and hence find the refcount when summing all CPUs. Then, keep a single integer "long" refcount for slow and long lasting references, and only take the global sum of local counters when the long refcount is 0. This last scheme is what I implemented here. Attached mounts and process root and working directory references are "long" references, and everything else is a short reference. This allows scalable vfsmount references during path walking over mounted subtrees and unattached (lazy umounted) mounts with processes still running in them. This results in one fewer atomic op in the fastpath: mntget is now just a per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock and non-atomic decrement in the common case. However code is otherwise bigger and heavier, so single threaded performance is basically a wash. Signed-off-by: Nick Piggin --- include/linux/mount.h | 53 +++++++++++++++++---------------------------------- 1 file changed, 17 insertions(+), 36 deletions(-) (limited to 'include/linux/mount.h') diff --git a/include/linux/mount.h b/include/linux/mount.h index 5e7a59408dd4..1869ea24a739 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -13,6 +13,7 @@ #include #include #include +#include #include struct super_block; @@ -46,12 +47,24 @@ struct mnt_namespace; #define MNT_INTERNAL 0x4000 +struct mnt_pcp { + int mnt_count; + int mnt_writers; +}; + 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 */ +#ifdef CONFIG_SMP + struct mnt_pcp __percpu *mnt_pcp; + atomic_t mnt_longrefs; +#else + int mnt_count; + int mnt_writers; +#endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ int mnt_flags; @@ -70,57 +83,25 @@ struct vfsmount { 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 */ int mnt_pinned; int mnt_ghosts; -#ifdef CONFIG_SMP - int __percpu *mnt_writers; -#else - int mnt_writers; -#endif }; -static inline int *get_mnt_writers_ptr(struct vfsmount *mnt) -{ -#ifdef CONFIG_SMP - return mnt->mnt_writers; -#else - return &mnt->mnt_writers; -#endif -} - -static inline struct vfsmount *mntget(struct vfsmount *mnt) -{ - if (mnt) - atomic_inc(&mnt->mnt_count); - return mnt; -} - struct file; /* forward dec */ extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); -extern void mntput_no_expire(struct vfsmount *mnt); +extern void mntput(struct vfsmount *mnt); +extern struct vfsmount *mntget(struct vfsmount *mnt); +extern void mntput_long(struct vfsmount *mnt); +extern struct vfsmount *mntget_long(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); -- cgit v1.2.2 From ea5b778a8b98c85a87d66bf844904f9c3802b869 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 19:10:03 +0000 Subject: Unexport do_add_mount() and add in follow_automount(), not ->d_automount() Unexport do_add_mount() and make ->d_automount() return the vfsmount to be added rather than calling do_add_mount() itself. follow_automount() will then do the addition. This slightly complicates things as ->d_automount() normally wants to add the new vfsmount to an expiration list and start an expiration timer. The problem with that is that the vfsmount will be deleted if it has a refcount of 1 and the timer will not repeat if the expiration list is empty. To this end, we require the vfsmount to be returned from d_automount() with a refcount of (at least) 2. One of these refs will be dropped unconditionally. In addition, follow_automount() must get a 3rd ref around the call to do_add_mount() lest it eat a ref and return an error, leaving the mount we have open to being expired as we would otherwise have only 1 ref on it. d_automount() should also add the the vfsmount to the expiration list (by calling mnt_set_expiry()) and start the expiration timer before returning, if this mechanism is to be used. The vfsmount will be unlinked from the expiration list by follow_automount() if do_add_mount() fails. This patch also fixes the call to do_add_mount() for AFS to propagate the mount flags from the parent vfsmount. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/mount.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux/mount.h') diff --git a/include/linux/mount.h b/include/linux/mount.h index 1869ea24a739..af4765ea8fde 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -110,12 +110,7 @@ extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); -struct nameidata; - -struct path; -extern int do_add_mount(struct vfsmount *newmnt, struct path *path, - int mnt_flags, struct list_head *fslist); - +extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(char *name); -- cgit v1.2.2 From f03c65993b98eeb909a4012ce7833c5857d74755 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 14 Jan 2011 22:30:21 -0500 Subject: sanitize vfsmount refcounting changes Instead of splitting refcount between (per-cpu) mnt_count and (SMP-only) mnt_longrefs, make all references contribute to mnt_count again and keep track of how many are longterm ones. Accounting rules for longterm count: * 1 for each fs_struct.root.mnt * 1 for each fs_struct.pwd.mnt * 1 for having non-NULL ->mnt_ns * decrement to 0 happens only under vfsmount lock exclusive That allows nice common case for mntput() - since we can't drop the final reference until after mnt_longterm has reached 0 due to the rules above, mntput() can grab vfsmount lock shared and check mnt_longterm. If it turns out to be non-zero (which is the common case), we know that this is not the final mntput() and can just blindly decrement percpu mnt_count. Otherwise we grab vfsmount lock exclusive and do usual decrement-and-check of percpu mnt_count. For fs_struct.c we have mnt_make_longterm() and mnt_make_shortterm(); namespace.c uses the latter in places where we don't already hold vfsmount lock exclusive and opencodes a few remaining spots where we need to manipulate mnt_longterm. Note that we mostly revert the code outside of fs/namespace.c back to what we used to have; in particular, normal code doesn't need to care about two kinds of references, etc. And we get to keep the optimization Nick's variant had bought us... Signed-off-by: Al Viro --- include/linux/mount.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/mount.h') diff --git a/include/linux/mount.h b/include/linux/mount.h index af4765ea8fde..604f122a2326 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -60,7 +60,7 @@ struct vfsmount { struct super_block *mnt_sb; /* pointer to superblock */ #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; - atomic_t mnt_longrefs; + atomic_t mnt_longterm; /* how many of the refs are longterm */ #else int mnt_count; int mnt_writers; @@ -96,8 +96,6 @@ extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); -extern void mntput_long(struct vfsmount *mnt); -extern struct vfsmount *mntget_long(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); -- cgit v1.2.2