#include <linux/mount.h>
#include <linux/async.h>
#include <linux/posix_acl.h>
+#include <linux/ima.h>
/*
* This is needed for the following functions:
* - inode_has_buffers
- * - invalidate_inode_buffers
* - invalidate_bdev
*
* FIXME: remove all knowledge of the buffer layer from this file
* allowing for low-overhead inode sync() operations.
*/
-static LIST_HEAD(inode_unused);
+static LIST_HEAD(inode_lru);
static struct hlist_head *inode_hashtable __read_mostly;
/*
static void destroy_inode(struct inode *inode)
{
+ BUG_ON(!list_empty(&inode->i_lru));
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
- INIT_LIST_HEAD(&inode->i_list);
+ INIT_LIST_HEAD(&inode->i_wb_list);
+ INIT_LIST_HEAD(&inode->i_lru);
INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
spin_lock_init(&inode->i_data.tree_lock);
spin_lock_init(&inode->i_data.i_mmap_lock);
atomic_inc(&inode->i_count);
}
+/*
+ * get additional reference to inode; caller must already hold one.
+ */
+void ihold(struct inode *inode)
+{
+ WARN_ON(atomic_inc_return(&inode->i_count) < 2);
+}
+EXPORT_SYMBOL(ihold);
+
static void inode_lru_list_add(struct inode *inode)
{
- if (list_empty(&inode->i_list)) {
- list_add(&inode->i_list, &inode_unused);
+ if (list_empty(&inode->i_lru)) {
+ list_add(&inode->i_lru, &inode_lru);
percpu_counter_inc(&nr_inodes_unused);
}
}
static void inode_lru_list_del(struct inode *inode)
{
- if (!list_empty(&inode->i_list)) {
- list_del_init(&inode->i_list);
+ if (!list_empty(&inode->i_lru)) {
+ list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
}
}
while (!list_empty(head)) {
struct inode *inode;
- inode = list_first_entry(head, struct inode, i_list);
- list_del_init(&inode->i_list);
+ inode = list_first_entry(head, struct inode, i_lru);
+ list_del_init(&inode->i_lru);
evict(inode);
}
}
-/*
- * Invalidate all inodes for a device.
+/**
+ * evict_inodes - evict all evictable inodes for a superblock
+ * @sb: superblock to operate on
+ *
+ * Make sure that no inodes with zero refcount are retained. This is
+ * called by superblock shutdown after having MS_ACTIVE flag removed,
+ * so any inode reaching zero refcount during or after that call will
+ * be immediately evicted.
*/
-static int invalidate_list(struct list_head *head, struct list_head *dispose)
+void evict_inodes(struct super_block *sb)
{
- struct list_head *next;
- int busy = 0;
-
- next = head->next;
- for (;;) {
- struct list_head *tmp = next;
- struct inode *inode;
+ struct inode *inode, *next;
+ LIST_HEAD(dispose);
- /*
- * 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_sem keeps
- * shrink_icache_memory() away.
- */
- cond_resched_lock(&inode_lock);
+ down_write(&iprune_sem);
- next = next->next;
- if (tmp == head)
- break;
- inode = list_entry(tmp, struct inode, i_sb_list);
- if (inode->i_state & I_NEW)
+ spin_lock(&inode_lock);
+ list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ if (atomic_read(&inode->i_count))
continue;
- invalidate_inode_buffers(inode);
- if (!atomic_read(&inode->i_count)) {
- list_move(&inode->i_list, dispose);
- WARN_ON(inode->i_state & I_NEW);
- inode->i_state |= I_FREEING;
- if (!(inode->i_state & (I_DIRTY | I_SYNC)))
- percpu_counter_dec(&nr_inodes_unused);
+
+ if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+ WARN_ON(1);
continue;
}
- busy = 1;
+
+ inode->i_state |= I_FREEING;
+
+ /*
+ * Move the inode off the IO lists and LRU once I_FREEING is
+ * set so that it won't get moved back on there if it is dirty.
+ */
+ list_move(&inode->i_lru, &dispose);
+ list_del_init(&inode->i_wb_list);
+ if (!(inode->i_state & (I_DIRTY | I_SYNC)))
+ percpu_counter_dec(&nr_inodes_unused);
}
- return busy;
+ spin_unlock(&inode_lock);
+
+ dispose_list(&dispose);
+ up_write(&iprune_sem);
}
/**
- * invalidate_inodes - discard the inodes on a device
- * @sb: superblock
+ * invalidate_inodes - attempt to free all inodes on a superblock
+ * @sb: superblock to operate on
*
- * Discard all of the inodes for a given superblock. If the discard
- * fails because there are busy inodes then a non zero value is returned.
- * If the discard is successful all the inodes have been discarded.
+ * Attempts to free all inodes for a given superblock. If there were any
+ * busy inodes return a non-zero value, else zero.
*/
int invalidate_inodes(struct super_block *sb)
{
- int busy;
- LIST_HEAD(throw_away);
+ int busy = 0;
+ struct inode *inode, *next;
+ LIST_HEAD(dispose);
down_write(&iprune_sem);
+
spin_lock(&inode_lock);
- fsnotify_unmount_inodes(&sb->s_inodes);
- busy = invalidate_list(&sb->s_inodes, &throw_away);
+ list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
+ continue;
+ if (atomic_read(&inode->i_count)) {
+ busy = 1;
+ continue;
+ }
+
+ inode->i_state |= I_FREEING;
+
+ /*
+ * Move the inode off the IO lists and LRU once I_FREEING is
+ * set so that it won't get moved back on there if it is dirty.
+ */
+ list_move(&inode->i_lru, &dispose);
+ list_del_init(&inode->i_wb_list);
+ if (!(inode->i_state & (I_DIRTY | I_SYNC)))
+ percpu_counter_dec(&nr_inodes_unused);
+ }
spin_unlock(&inode_lock);
- dispose_list(&throw_away);
+ dispose_list(&dispose);
up_write(&iprune_sem);
return busy;
for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
struct inode *inode;
- if (list_empty(&inode_unused))
+ if (list_empty(&inode_lru))
break;
- inode = list_entry(inode_unused.prev, struct inode, i_list);
+ inode = list_entry(inode_lru.prev, struct inode, i_lru);
/*
* Referenced or dirty inodes are still in use. Give them
*/
if (atomic_read(&inode->i_count) ||
(inode->i_state & ~I_REFERENCED)) {
- list_del_init(&inode->i_list);
+ list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
continue;
}
/* recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
- list_move(&inode->i_list, &inode_unused);
+ list_move(&inode->i_lru, &inode_lru);
inode->i_state &= ~I_REFERENCED;
continue;
}
iput(inode);
spin_lock(&inode_lock);
- if (inode != list_entry(inode_unused.next,
- struct inode, i_list))
+ if (inode != list_entry(inode_lru.next,
+ struct inode, i_lru))
continue; /* wrong inode or list_empty */
if (!can_unuse(inode))
continue;
}
- list_move(&inode->i_list, &freeable);
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
+
+ /*
+ * Move the inode off the IO lists and LRU once I_FREEING is
+ * set so that it won't get moved back on there if it is dirty.
+ */
+ list_move(&inode->i_lru, &freeable);
+ list_del_init(&inode->i_wb_list);
percpu_counter_dec(&nr_inodes_unused);
}
if (current_is_kswapd())
return NULL;
}
+/*
+ * Each cpu owns a range of LAST_INO_BATCH numbers.
+ * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
+ * to renew the exhausted range.
+ *
+ * This does not significantly increase overflow rate because every CPU can
+ * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
+ * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
+ * 2^32 range, and is a worst-case. Even a 50% wastage would only increase
+ * overflow rate by 2x, which does not seem too significant.
+ *
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
+ */
+#define LAST_INO_BATCH 1024
+static DEFINE_PER_CPU(unsigned int, last_ino);
+
+unsigned int get_next_ino(void)
+{
+ unsigned int *p = &get_cpu_var(last_ino);
+ unsigned int res = *p;
+
+#ifdef CONFIG_SMP
+ if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
+ static atomic_t shared_last_ino;
+ int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);
+
+ res = next - LAST_INO_BATCH;
+ }
+#endif
+
+ *p = ++res;
+ put_cpu_var(last_ino);
+ return res;
+}
+EXPORT_SYMBOL(get_next_ino);
+
/**
* new_inode - obtain an inode
* @sb: superblock
*/
struct inode *new_inode(struct super_block *sb)
{
- /*
- * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
- * error if st_ino won't fit in target struct field. Use 32bit counter
- * here to attempt to avoid that.
- */
- static unsigned int last_ino;
struct inode *inode;
spin_lock_prefetch(&inode_lock);
if (inode) {
spin_lock(&inode_lock);
__inode_sb_list_add(inode);
- inode->i_ino = ++last_ino;
inode->i_state = 0;
spin_unlock(&inode_lock);
}
inode->i_state &= ~I_WILL_FREE;
__remove_inode_hash(inode);
}
+
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
/*
- * After we delete the inode from the LRU here, we avoid moving dirty
- * inodes back onto the LRU now because I_FREEING is set and hence
- * writeback_single_inode() won't move the inode around.
+ * Move the inode off the IO lists and LRU once I_FREEING is
+ * set so that it won't get moved back on there if it is dirty.
*/
inode_lru_list_del(inode);
+ list_del_init(&inode->i_wb_list);
__inode_sb_list_del(inode);
spin_unlock(&inode_lock);