iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'xfs-4.7-inode-reclaim' into for-next

Browse Source
This commit is contained in:
Dave Chinner 2016-05-20 10:34:00 +10:00
commit 555b67e4e7
4 changed files with 250 additions and 199 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
fs/xfs/libxfs/xfs_inode_fork.c
View File

@ -1518,6 +1518,24 @@ xfs_iext_indirect_to_direct(
}
}
/*
* Remove all records from the indirection array.
*/
STATIC void
xfs_iext_irec_remove_all(
struct xfs_ifork *ifp)
{
int nlists;
int i;
ASSERT(ifp->if_flags & XFS_IFEXTIREC);
nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
for (i = 0; i < nlists; i++)
kmem_free(ifp->if_u1.if_ext_irec[i].er_extbuf);
kmem_free(ifp->if_u1.if_ext_irec);
ifp->if_flags &= ~XFS_IFEXTIREC;
}
/*
* Free incore file extents.
*/
@ -1526,14 +1544,7 @@ xfs_iext_destroy(
xfs_ifork_t *ifp) /* inode fork pointer */
{
if (ifp->if_flags & XFS_IFEXTIREC) {
int erp_idx;
int nlists;
nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
for (erp_idx = nlists - 1; erp_idx >= 0 ; erp_idx--) {
xfs_iext_irec_remove(ifp, erp_idx);
}
ifp->if_flags &= ~XFS_IFEXTIREC;
xfs_iext_irec_remove_all(ifp);
} else if (ifp->if_real_bytes) {
kmem_free(ifp->if_u1.if_extents);
} else if (ifp->if_bytes) {

290
fs/xfs/xfs_icache.c
View File

@ -37,9 +37,6 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
STATIC void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp,
struct xfs_perag *pag, struct xfs_inode *ip);
/*
* Allocate and initialise an xfs_inode.
*/
@ -94,13 +91,6 @@ xfs_inode_free_callback(
struct inode *inode = container_of(head, struct inode, i_rcu);
struct xfs_inode *ip = XFS_I(inode);
kmem_zone_free(xfs_inode_zone, ip);
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (VFS_I(ip)->i_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
@ -118,6 +108,25 @@ xfs_inode_free(
ip->i_itemp = NULL;
}
kmem_zone_free(xfs_inode_zone, ip);
}
static void
__xfs_inode_free(
struct xfs_inode *ip)
{
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!xfs_isiflocked(ip));
XFS_STATS_DEC(ip->i_mount, vn_active);
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
}
void
xfs_inode_free(
struct xfs_inode *ip)
{
/*
* Because we use RCU freeing we need to ensure the inode always
* appears to be reclaimed with an invalid inode number when in the
@ -129,12 +138,123 @@ xfs_inode_free(
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!xfs_isiflocked(ip));
XFS_STATS_DEC(ip->i_mount, vn_active);
__xfs_inode_free(ip);
}
call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
/*
* Queue a new inode reclaim pass if there are reclaimable inodes and there
* isn't a reclaim pass already in progress. By default it runs every 5s based
* on the xfs periodic sync default of 30s. Perhaps this should have it's own
* tunable, but that can be done if this method proves to be ineffective or too
* aggressive.
*/
static void
xfs_reclaim_work_queue(
struct xfs_mount *mp)
{
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
}
rcu_read_unlock();
}
/*
* This is a fast pass over the inode cache to try to get reclaim moving on as
* many inodes as possible in a short period of time. It kicks itself every few
* seconds, as well as being kicked by the inode cache shrinker when memory
* goes low. It scans as quickly as possible avoiding locked inodes or those
* already being flushed, and once done schedules a future pass.
*/
void
xfs_reclaim_worker(
struct work_struct *work)
{
struct xfs_mount *mp = container_of(to_delayed_work(work),
struct xfs_mount, m_reclaim_work);
xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
xfs_reclaim_work_queue(mp);
}
static void
xfs_perag_set_reclaim_tag(
struct xfs_perag *pag)
{
struct xfs_mount *mp = pag->pag_mount;
ASSERT(spin_is_locked(&pag->pag_ici_lock));
if (pag->pag_ici_reclaimable++)
return;
/* propagate the reclaim tag up into the perag radix tree */
spin_lock(&mp->m_perag_lock);
radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno,
XFS_ICI_RECLAIM_TAG);
spin_unlock(&mp->m_perag_lock);
/* schedule periodic background inode reclaim */
xfs_reclaim_work_queue(mp);
trace_xfs_perag_set_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
}
static void
xfs_perag_clear_reclaim_tag(
struct xfs_perag *pag)
{
struct xfs_mount *mp = pag->pag_mount;
ASSERT(spin_is_locked(&pag->pag_ici_lock));
if (--pag->pag_ici_reclaimable)
return;
/* clear the reclaim tag from the perag radix tree */
spin_lock(&mp->m_perag_lock);
radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno,
XFS_ICI_RECLAIM_TAG);
spin_unlock(&mp->m_perag_lock);
trace_xfs_perag_clear_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
}
/*
* We set the inode flag atomically with the radix tree tag.
* Once we get tag lookups on the radix tree, this inode flag
* can go away.
*/
void
xfs_inode_set_reclaim_tag(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
radix_tree_tag_set(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
xfs_perag_set_reclaim_tag(pag);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
STATIC void
xfs_inode_clear_reclaim_tag(
struct xfs_perag *pag,
xfs_ino_t ino)
{
radix_tree_tag_clear(&pag->pag_ici_root,
XFS_INO_TO_AGINO(pag->pag_mount, ino),
XFS_ICI_RECLAIM_TAG);
xfs_perag_clear_reclaim_tag(pag);
}
/*
@ -264,7 +384,7 @@ xfs_iget_cache_hit(
*/
ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
ip->i_flags |= XFS_INEW;
__xfs_inode_clear_reclaim_tag(mp, pag, ip);
xfs_inode_clear_reclaim_tag(pag, ip->i_ino);
inode->i_state = I_NEW;
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
@ -722,121 +842,6 @@ xfs_inode_ag_iterator_tag(
return last_error;
}
/*
* Queue a new inode reclaim pass if there are reclaimable inodes and there
* isn't a reclaim pass already in progress. By default it runs every 5s based
* on the xfs periodic sync default of 30s. Perhaps this should have it's own
* tunable, but that can be done if this method proves to be ineffective or too
* aggressive.
*/
static void
xfs_reclaim_work_queue(
struct xfs_mount *mp)
{
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
}
rcu_read_unlock();
}
/*
* This is a fast pass over the inode cache to try to get reclaim moving on as
* many inodes as possible in a short period of time. It kicks itself every few
* seconds, as well as being kicked by the inode cache shrinker when memory
* goes low. It scans as quickly as possible avoiding locked inodes or those
* already being flushed, and once done schedules a future pass.
*/
void
xfs_reclaim_worker(
struct work_struct *work)
{
struct xfs_mount *mp = container_of(to_delayed_work(work),
struct xfs_mount, m_reclaim_work);
xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
xfs_reclaim_work_queue(mp);
}
static void
__xfs_inode_set_reclaim_tag(
struct xfs_perag *pag,
struct xfs_inode *ip)
{
radix_tree_tag_set(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
if (!pag->pag_ici_reclaimable) {
/* propagate the reclaim tag up into the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_set(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
spin_unlock(&ip->i_mount->m_perag_lock);
/* schedule periodic background inode reclaim */
xfs_reclaim_work_queue(ip->i_mount);
trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
-1, _RET_IP_);
}
pag->pag_ici_reclaimable++;
}
/*
* We set the inode flag atomically with the radix tree tag.
* Once we get tag lookups on the radix tree, this inode flag
* can go away.
*/
void
xfs_inode_set_reclaim_tag(
xfs_inode_t *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
spin_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
__xfs_inode_set_reclaim_tag(pag, ip);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
spin_unlock(&pag->pag_ici_lock);
xfs_perag_put(pag);
}
STATIC void
__xfs_inode_clear_reclaim(
xfs_perag_t *pag,
xfs_inode_t *ip)
{
pag->pag_ici_reclaimable--;
if (!pag->pag_ici_reclaimable) {
/* clear the reclaim tag from the perag radix tree */
spin_lock(&ip->i_mount->m_perag_lock);
radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
XFS_ICI_RECLAIM_TAG);
spin_unlock(&ip->i_mount->m_perag_lock);
trace_xfs_perag_clear_reclaim(ip->i_mount, pag->pag_agno,
-1, _RET_IP_);
}
}
STATIC void
__xfs_inode_clear_reclaim_tag(
xfs_mount_t *mp,
xfs_perag_t *pag,
xfs_inode_t *ip)
{
radix_tree_tag_clear(&pag->pag_ici_root,
XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
__xfs_inode_clear_reclaim(pag, ip);
}
/*
* Grab the inode for reclaim exclusively.
* Return 0 if we grabbed it, non-zero otherwise.
@ -929,6 +934,7 @@ xfs_reclaim_inode(
int sync_mode)
{
struct xfs_buf *bp = NULL;
xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */
int error;
restart:
@ -993,6 +999,22 @@ restart:
xfs_iflock(ip);
reclaim:
/*
* Because we use RCU freeing we need to ensure the inode always appears
* to be reclaimed with an invalid inode number when in the free state.
* We do this as early as possible under the ILOCK and flush lock so
* that xfs_iflush_cluster() can be guaranteed to detect races with us
* here. By doing this, we guarantee that once xfs_iflush_cluster has
* locked both the XFS_ILOCK and the flush lock that it will see either
* a valid, flushable inode that will serialise correctly against the
* locks below, or it will see a clean (and invalid) inode that it can
* skip.
*/
spin_lock(&ip->i_flags_lock);
ip->i_flags = XFS_IRECLAIM;
ip->i_ino = 0;
spin_unlock(&ip->i_flags_lock);
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
@ -1006,9 +1028,9 @@ reclaim:
*/
spin_lock(&pag->pag_ici_lock);
if (!radix_tree_delete(&pag->pag_ici_root,
XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
XFS_INO_TO_AGINO(ip->i_mount, ino)))
ASSERT(0);
__xfs_inode_clear_reclaim(pag, ip);
xfs_perag_clear_reclaim_tag(pag);
spin_unlock(&pag->pag_ici_lock);
/*
@ -1023,7 +1045,7 @@ reclaim:
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
__xfs_inode_free(ip);
return error;
out_ifunlock:

104
fs/xfs/xfs_inode.c
View File

@ -3149,16 +3149,16 @@ out_release_wip:
STATIC int
xfs_iflush_cluster(
xfs_inode_t *ip,
xfs_buf_t *bp)
struct xfs_inode *ip,
struct xfs_buf *bp)
{
xfs_mount_t *mp = ip->i_mount;
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
unsigned long first_index, mask;
unsigned long inodes_per_cluster;
int ilist_size;
xfs_inode_t **ilist;
xfs_inode_t *iq;
int cilist_size;
struct xfs_inode **cilist;
struct xfs_inode *cip;
int nr_found;
int clcount = 0;
int bufwasdelwri;
@ -3167,23 +3167,23 @@ xfs_iflush_cluster(
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
ilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
ilist = kmem_alloc(ilist_size, KM_MAYFAIL|KM_NOFS);
if (!ilist)
cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
if (!cilist)
goto out_put;
mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1);
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
rcu_read_lock();
/* really need a gang lookup range call here */
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
first_index, inodes_per_cluster);
if (nr_found == 0)
goto out_free;
for (i = 0; i < nr_found; i++) {
iq = ilist[i];
if (iq == ip)
cip = cilist[i];
if (cip == ip)
continue;
/*
@ -3192,20 +3192,30 @@ xfs_iflush_cluster(
* We need to check under the i_flags_lock for a valid inode
* here. Skip it if it is not valid or the wrong inode.
*/
spin_lock(&ip->i_flags_lock);
if (!ip->i_ino ||
(XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index) {
spin_unlock(&ip->i_flags_lock);
spin_lock(&cip->i_flags_lock);
if (!cip->i_ino ||
__xfs_iflags_test(cip, XFS_ISTALE)) {
spin_unlock(&cip->i_flags_lock);
continue;
}
spin_unlock(&ip->i_flags_lock);
/*
* Once we fall off the end of the cluster, no point checking
* any more inodes in the list because they will also all be
* outside the cluster.
*/
if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
spin_unlock(&cip->i_flags_lock);
break;
}
spin_unlock(&cip->i_flags_lock);
/*
* Do an un-protected check to see if the inode is dirty and
* is a candidate for flushing. These checks will be repeated
* later after the appropriate locks are acquired.
*/
if (xfs_inode_clean(iq) && xfs_ipincount(iq) == 0)
if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
continue;
/*
@ -3213,15 +3223,28 @@ xfs_iflush_cluster(
* then this inode cannot be flushed and is skipped.
*/
if (!xfs_ilock_nowait(iq, XFS_ILOCK_SHARED))
if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
continue;
if (!xfs_iflock_nowait(iq)) {
xfs_iunlock(iq, XFS_ILOCK_SHARED);
if (!xfs_iflock_nowait(cip)) {
xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
}
if (xfs_ipincount(iq)) {
xfs_ifunlock(iq);
xfs_iunlock(iq, XFS_ILOCK_SHARED);
if (xfs_ipincount(cip)) {
xfs_ifunlock(cip);
xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
}
/*
* Check the inode number again, just to be certain we are not
* racing with freeing in xfs_reclaim_inode(). See the comments
* in that function for more information as to why the initial
* check is not sufficient.
*/
if (!cip->i_ino) {
xfs_ifunlock(cip);
xfs_iunlock(cip, XFS_ILOCK_SHARED);
continue;
}
@ -3229,18 +3252,18 @@ xfs_iflush_cluster(
* arriving here means that this inode can be flushed. First
* re-check that it's dirty before flushing.
*/
if (!xfs_inode_clean(iq)) {
if (!xfs_inode_clean(cip)) {
int error;
error = xfs_iflush_int(iq, bp);
error = xfs_iflush_int(cip, bp);
if (error) {
xfs_iunlock(iq, XFS_ILOCK_SHARED);
xfs_iunlock(cip, XFS_ILOCK_SHARED);
goto cluster_corrupt_out;
}
clcount++;
} else {
xfs_ifunlock(iq);
xfs_ifunlock(cip);
}
xfs_iunlock(iq, XFS_ILOCK_SHARED);
xfs_iunlock(cip, XFS_ILOCK_SHARED);
}
if (clcount) {
@ -3250,7 +3273,7 @@ xfs_iflush_cluster(
out_free:
rcu_read_unlock();
kmem_free(ilist);
kmem_free(cilist);
out_put:
xfs_perag_put(pag);
return 0;
@ -3293,8 +3316,8 @@ cluster_corrupt_out:
/*
* Unlocks the flush lock
*/
xfs_iflush_abort(iq, false);
kmem_free(ilist);
xfs_iflush_abort(cip, false);
kmem_free(cilist);
xfs_perag_put(pag);
return -EFSCORRUPTED;
}
@ -3314,7 +3337,7 @@ xfs_iflush(
struct xfs_buf **bpp)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_buf *bp;
struct xfs_buf *bp = NULL;
struct xfs_dinode *dip;
int error;
@ -3356,14 +3379,22 @@ xfs_iflush(
}
/*
* Get the buffer containing the on-disk inode.
* Get the buffer containing the on-disk inode. We are doing a try-lock
* operation here, so we may get an EAGAIN error. In that case, we
* simply want to return with the inode still dirty.
*
* If we get any other error, we effectively have a corruption situation
* and we cannot flush the inode, so we treat it the same as failing
* xfs_iflush_int().
*/
error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
0);
if (error || !bp) {
if (error == -EAGAIN) {
xfs_ifunlock(ip);
return error;
}
if (error)
goto corrupt_out;
/*
* First flush out the inode that xfs_iflush was called with.
@ -3391,7 +3422,8 @@ xfs_iflush(
return 0;
corrupt_out:
xfs_buf_relse(bp);
if (bp)
xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
cluster_corrupt_out:
error = -EFSCORRUPTED;

28
fs/xfs/xfs_super.c
View File

@ -928,7 +928,7 @@ xfs_fs_alloc_inode(
/*
* Now that the generic code is guaranteed not to be accessing
* the linux inode, we can reclaim the inode.
* the linux inode, we can inactivate and reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
@ -938,9 +938,14 @@ xfs_fs_destroy_inode(
trace_xfs_destroy_inode(ip);
XFS_STATS_INC(ip->i_mount, vn_reclaim);
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
xfs_inactive(ip);
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
XFS_STATS_INC(ip->i_mount, vn_reclaim);
/*
* We should never get here with one of the reclaim flags already set.
@ -987,24 +992,6 @@ xfs_fs_inode_init_once(
"xfsino", ip->i_ino);
}
STATIC void
xfs_fs_evict_inode(
struct inode *inode)
{
xfs_inode_t *ip = XFS_I(inode);
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
trace_xfs_evict_inode(ip);
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
xfs_inactive(ip);
}
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
@ -1673,7 +1660,6 @@ xfs_fs_free_cached_objects(
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
.evict_inode = xfs_fs_evict_inode,
.drop_inode = xfs_fs_drop_inode,
.put_super = xfs_fs_put_super,
.sync_fs = xfs_fs_sync_fs,