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 --- fs/notify/inode_mark.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'fs/notify/inode_mark.c') diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 4c29fcf..4dd53fb 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -254,8 +254,11 @@ void fsnotify_unmount_inodes(struct list_head *list) * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) + spin_lock(&inode->i_lock); + if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { + spin_unlock(&inode->i_lock); continue; + } /* * If i_count is zero, the inode cannot have any watches and @@ -263,8 +266,10 @@ void fsnotify_unmount_inodes(struct list_head *list) * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. */ - if (!atomic_read(&inode->i_count)) + if (!atomic_read(&inode->i_count)) { + spin_unlock(&inode->i_lock); continue; + } need_iput_tmp = need_iput; need_iput = NULL; @@ -274,13 +279,17 @@ void fsnotify_unmount_inodes(struct list_head *list) __iget(inode); else need_iput_tmp = NULL; + spin_unlock(&inode->i_lock); /* In case the dropping of a reference would nuke next_i. */ if ((&next_i->i_sb_list != list) && - atomic_read(&next_i->i_count) && - !(next_i->i_state & (I_FREEING | I_WILL_FREE))) { - __iget(next_i); - need_iput = next_i; + atomic_read(&next_i->i_count)) { + spin_lock(&next_i->i_lock); + if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) { + __iget(next_i); + need_iput = next_i; + } + spin_unlock(&next_i->i_lock); } /* -- cgit v1.1 From 55fa6091d83160ca772fc37cebae45d42695a708 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:40 +1100 Subject: fs: move i_sb_list out from under inode_lock Protect the per-sb inode list with a new global lock inode_sb_list_lock and use it to protect the list manipulations and traversals. This lock replaces the inode_lock as the inodes on the list can be validity checked while holding the inode->i_lock and hence the inode_lock is no longer needed to protect the list. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- fs/notify/inode_mark.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'fs/notify/inode_mark.c') diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 4dd53fb..fb3b3c5 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -29,6 +29,8 @@ #include #include "fsnotify.h" +#include "../internal.h" + /* * Recalculate the mask of events relevant to a given inode locked. */ @@ -237,15 +239,14 @@ out: * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @list: list of inodes being unmounted (sb->s_inodes) * - * Called with inode_lock held, protecting the unmounting super block's list - * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay. - * We temporarily drop inode_lock, however, and CAN block. + * Called during unmount with no locks held, so needs to be safe against + * concurrent modifiers. We temporarily drop inode_sb_list_lock and CAN block. */ void fsnotify_unmount_inodes(struct list_head *list) { struct inode *inode, *next_i, *need_iput = NULL; - spin_lock(&inode_lock); + spin_lock(&inode_sb_list_lock); list_for_each_entry_safe(inode, next_i, list, i_sb_list) { struct inode *need_iput_tmp; @@ -293,12 +294,11 @@ void fsnotify_unmount_inodes(struct list_head *list) } /* - * We can safely drop inode_lock here because we hold + * We can safely drop inode_sb_list_lock here because we hold * references on both inode and next_i. Also no new inodes - * will be added since the umount has begun. Finally, - * iprune_mutex keeps shrink_icache_memory() away. + * will be added since the umount has begun. */ - spin_unlock(&inode_lock); + spin_unlock(&inode_sb_list_lock); if (need_iput_tmp) iput(need_iput_tmp); @@ -310,7 +310,7 @@ void fsnotify_unmount_inodes(struct list_head *list) iput(inode); - spin_lock(&inode_lock); + spin_lock(&inode_sb_list_lock); } - spin_unlock(&inode_lock); + spin_unlock(&inode_sb_list_lock); } -- cgit v1.1 From 67a23c494621ff1d5431c3bc320947865b224625 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:42 +1100 Subject: fs: rename inode_lock to inode_hash_lock All that remains of the inode_lock is protecting the inode hash list manipulation and traversals. Rename the inode_lock to inode_hash_lock to reflect it's actual function. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- fs/notify/inode_mark.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/notify/inode_mark.c') diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index fb3b3c5..07ea8d3 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -22,7 +22,6 @@ #include #include #include -#include /* for inode_lock */ #include -- cgit v1.1