#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
+#include <linux/rwsem.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
DEFINE_SPINLOCK(inode_lock);
/*
- * iprune_mutex provides exclusion between the kswapd or try_to_free_pages
+ * iprune_sem provides exclusion between the kswapd or try_to_free_pages
* icache shrinking path, and the umount path. Without this exclusion,
* by the time prune_icache calls iput for the inode whose pages it has
* been invalidating, or by the time it calls clear_inode & destroy_inode
* from its final dispose_list, the struct super_block they refer to
* (for inode->i_sb->s_op) may already have been freed and reused.
+ *
+ * We make this an rwsem because the fastpath is icache shrinking. In
+ * some cases a filesystem may be doing a significant amount of work in
+ * its inode reclaim code, so this should improve parallelism.
*/
-static DEFINE_MUTEX(iprune_mutex);
+static DECLARE_RWSEM(iprune_sem);
/*
* Statistics gathering..
* These are initializations that need to be done on every inode
* allocation as the fields are not initialised by slab allocation.
*/
-struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
+int inode_init_always(struct super_block *sb, struct inode *inode)
{
static const struct address_space_operations empty_aops;
- static struct inode_operations empty_iops;
+ static const struct inode_operations empty_iops;
static const struct file_operations empty_fops;
-
struct address_space *const mapping = &inode->i_data;
inode->i_sb = sb;
inode->dirtied_when = 0;
if (security_inode_alloc(inode))
- goto out_free_inode;
+ goto out;
/* allocate and initialize an i_integrity */
if (ima_inode_alloc(inode))
if (sb->s_bdev) {
struct backing_dev_info *bdi;
- bdi = sb->s_bdev->bd_inode_backing_dev_info;
- if (!bdi)
- bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
+ bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
mapping->backing_dev_info = bdi;
}
inode->i_private = NULL;
inode->i_fsnotify_mask = 0;
#endif
- return inode;
+ return 0;
out_free_security:
security_inode_free(inode);
-out_free_inode:
- if (inode->i_sb->s_op->destroy_inode)
- inode->i_sb->s_op->destroy_inode(inode);
- else
- kmem_cache_free(inode_cachep, (inode));
- return NULL;
+out:
+ return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);
else
inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
- if (inode)
- return inode_init_always(sb, inode);
- return NULL;
+ if (!inode)
+ return NULL;
+
+ if (unlikely(inode_init_always(sb, inode))) {
+ if (inode->i_sb->s_op->destroy_inode)
+ inode->i_sb->s_op->destroy_inode(inode);
+ else
+ kmem_cache_free(inode_cachep, inode);
+ return NULL;
+ }
+
+ return inode;
}
-void destroy_inode(struct inode *inode)
+void __destroy_inode(struct inode *inode)
{
BUG_ON(inode_has_buffers(inode));
ima_inode_free(inode);
if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_default_acl);
#endif
+}
+EXPORT_SYMBOL(__destroy_inode);
+
+void destroy_inode(struct inode *inode)
+{
+ __destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, (inode));
}
-EXPORT_SYMBOL(destroy_inode);
-
/*
* These are initializations that only need to be done
/*
* We can reschedule here without worrying about the list's
* consistency because the per-sb list of inodes must not
- * change during umount anymore, and because iprune_mutex keeps
+ * change during umount anymore, and because iprune_sem keeps
* shrink_icache_memory() away.
*/
cond_resched_lock(&inode_lock);
int busy;
LIST_HEAD(throw_away);
- mutex_lock(&iprune_mutex);
+ down_write(&iprune_sem);
spin_lock(&inode_lock);
inotify_unmount_inodes(&sb->s_inodes);
fsnotify_unmount_inodes(&sb->s_inodes);
spin_unlock(&inode_lock);
dispose_list(&throw_away);
- mutex_unlock(&iprune_mutex);
+ up_write(&iprune_sem);
return busy;
}
int nr_scanned;
unsigned long reap = 0;
- mutex_lock(&iprune_mutex);
+ down_read(&iprune_sem);
spin_lock(&inode_lock);
for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
struct inode *inode;
spin_unlock(&inode_lock);
dispose_list(&freeable);
- mutex_unlock(&iprune_mutex);
+ up_read(&iprune_sem);
}
/*
}
#endif
/*
- * This is special! We do not need the spinlock
- * when clearing I_LOCK, because we're guaranteed
- * that nobody else tries to do anything about the
- * state of the inode when it is locked, as we
- * just created it (so there can be no old holders
- * that haven't tested I_LOCK).
+ * This is special! We do not need the spinlock when clearing I_LOCK,
+ * because we're guaranteed that nobody else tries to do anything about
+ * the state of the inode when it is locked, as we just created it (so
+ * there can be no old holders that haven't tested I_LOCK).
+ * However we must emit the memory barrier so that other CPUs reliably
+ * see the clearing of I_LOCK after the other inode initialisation has
+ * completed.
*/
+ smp_mb();
WARN_ON((inode->i_state & (I_LOCK|I_NEW)) != (I_LOCK|I_NEW));
inode->i_state &= ~(I_LOCK|I_NEW);
wake_up_inode(inode);