[PATCH v2 08/10] locks: add a dedicated spinlock to protect i_flctx lists

From: Jeff Layton
Date: Thu Jan 08 2015 - 13:36:11 EST

We can now add a dedicated spinlock without expanding struct inode.
Change to using that to protect the various i_flctx lists. We do still
use the i_lock to protect the i_flctx pointer itself, but once the
context is assigned to the inode we no longer need it.

Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxxxxxxx>
---
fs/ceph/locks.c | 8 +++---
fs/cifs/file.c | 8 +++---
fs/lockd/svcsubs.c | 12 ++++----
fs/locks.c | 81 +++++++++++++++++++++++++++--------------------------
fs/nfs/delegation.c | 8 +++---
fs/nfs/nfs4state.c | 8 +++---
fs/nfs/write.c | 4 +--
fs/nfsd/nfs4state.c | 4 +--
include/linux/fs.h | 1 +
9 files changed, 68 insertions(+), 66 deletions(-)

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 4ee44165f10c..3f225c61024f 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -255,12 +255,12 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)

ctx = inode->i_flctx;
if (ctx) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
list_for_each_entry(lock, &ctx->flc_posix, fl_list)
++(*fcntl_count);
list_for_each_entry(lock, &ctx->flc_flock, fl_list)
++(*flock_count);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
}

dout("counted %d flock locks and %d fcntl locks",
@@ -289,7 +289,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
if (!ctx)
return 0;

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
++seen_fcntl;
if (seen_fcntl > num_fcntl_locks) {
@@ -313,7 +313,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
++l;
}
fail:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
return err;
}

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ea78f6f81ce2..b65166eb111e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1136,11 +1136,11 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
if (!flctx)
goto out;

- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
list_for_each(el, &flctx->flc_posix) {
count++;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);

INIT_LIST_HEAD(&locks_to_send);

@@ -1159,7 +1159,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
}

el = locks_to_send.next;
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
if (el == &locks_to_send) {
/*
@@ -1181,7 +1181,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
lck->type = type;
lck->offset = flock->fl_start;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);

list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
int stored_rc;
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 34567b22dff0..aaa5e2600e01 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -171,7 +171,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
return 0;
again:
file->f_locks = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
if (fl->fl_lmops != &nlmsvc_lock_operations)
continue;
@@ -183,7 +183,7 @@ again:
if (match(lockhost, host)) {
struct file_lock lock = *fl;

- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
lock.fl_type = F_UNLCK;
lock.fl_start = 0;
lock.fl_end = OFFSET_MAX;
@@ -195,7 +195,7 @@ again:
goto again;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);

return 0;
}
@@ -232,14 +232,14 @@ nlm_file_inuse(struct nlm_file *file)
return 1;

if (flctx && !list_empty(&flctx->flc_posix)) {
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
if (fl->fl_lmops == &nlmsvc_lock_operations) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
return 1;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
}
file->f_locks = 0;
return 0;
diff --git a/fs/locks.c b/fs/locks.c
index acfad02bc136..2cded21b99ac 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -161,7 +161,7 @@ int lease_break_time = 45;
* The global file_lock_list is only used for displaying /proc/locks, so we
* keep a list on each CPU, with each list protected by its own spinlock via
* the file_lock_lglock. Note that alterations to the list also require that
- * the relevant i_lock is held.
+ * the relevant flc_lock is held.
*/
DEFINE_STATIC_LGLOCK(file_lock_lglock);
static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
@@ -189,12 +189,12 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
* contrast to those that are acting as records of acquired locks).
*
* Note that when we acquire this lock in order to change the above fields,
- * we often hold the i_lock as well. In certain cases, when reading the fields
+ * we often hold the flc_lock as well. In certain cases, when reading the fields
* protected by this lock, we can skip acquiring it iff we already hold the
- * i_lock.
+ * flc_lock.
*
* In particular, adding an entry to the fl_block list requires that you hold
- * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting
+ * both the flc_lock and the blocked_lock_lock (acquired in that order). Deleting
* an entry from the list however only requires the file_lock_lock.
*/
static DEFINE_SPINLOCK(blocked_lock_lock);
@@ -214,6 +214,7 @@ locks_get_lock_context(struct inode *inode)
if (!new)
goto out;

+ spin_lock_init(&new->flc_lock);
INIT_LIST_HEAD(&new->flc_flock);
INIT_LIST_HEAD(&new->flc_posix);
INIT_LIST_HEAD(&new->flc_lease);
@@ -550,7 +551,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
return fl1->fl_owner == fl2->fl_owner;
}

-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock *fl)
{
lg_local_lock(&file_lock_lglock);
@@ -559,12 +560,12 @@ static void locks_insert_global_locks(struct file_lock *fl)
lg_local_unlock(&file_lock_lglock);
}

-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock *fl)
{
/*
* Avoid taking lock if already unhashed. This is safe since this check
- * is done while holding the i_lock, and new insertions into the list
+ * is done while holding the flc_lock, and new insertions into the list
* also require that it be held.
*/
if (hlist_unhashed(&fl->fl_link))
@@ -616,9 +617,9 @@ static void locks_delete_block(struct file_lock *waiter)
* the order they blocked. The documentation doesn't require this but
* it seems like the reasonable thing to do.
*
- * Must be called with both the i_lock and blocked_lock_lock held. The fl_block
+ * Must be called with both the flc_lock and blocked_lock_lock held. The fl_block
* list itself is protected by the blocked_lock_lock, but by ensuring that the
- * i_lock is also held on insertions we can avoid taking the blocked_lock_lock
+ * flc_lock is also held on insertions we can avoid taking the blocked_lock_lock
* in some cases when we see that the fl_block list is empty.
*/
static void __locks_insert_block(struct file_lock *blocker,
@@ -631,7 +632,7 @@ static void __locks_insert_block(struct file_lock *blocker,
locks_insert_global_blocked(waiter);
}

-/* Must be called with i_lock held. */
+/* Must be called with flc_lock held. */
static void locks_insert_block(struct file_lock *blocker,
struct file_lock *waiter)
{
@@ -643,15 +644,15 @@ static void locks_insert_block(struct file_lock *blocker,
/*
* Wake up processes blocked waiting for blocker.
*
- * Must be called with the inode->i_lock held!
+ * Must be called with the inode->flc_lock held!
*/
static void locks_wake_up_blocks(struct file_lock *blocker)
{
/*
* Avoid taking global lock if list is empty. This is safe since new
- * blocked requests are only added to the list under the i_lock, and
- * the i_lock is always held here. Note that removal from the fl_block
- * list does not require the i_lock, so we must recheck list_empty()
+ * blocked requests are only added to the list under the flc_lock, and
+ * the flc_lock is always held here. Note that removal from the fl_block
+ * list does not require the flc_lock, so we must recheck list_empty()
* after acquiring the blocked_lock_lock.
*/
if (list_empty(&blocker->fl_block))
@@ -761,7 +762,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
return;
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
if (posix_locks_conflict(fl, cfl)) {
locks_copy_conflock(fl, cfl);
@@ -772,7 +773,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
}
fl->fl_type = F_UNLCK;
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
return;
}
EXPORT_SYMBOL(posix_test_lock);
@@ -873,7 +874,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
return -ENOMEM;
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
if (request->fl_flags & FL_ACCESS)
goto find_conflict;

@@ -898,9 +899,9 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
* give it the opportunity to lock the file.
*/
if (found) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
cond_resched();
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
}

find_conflict:
@@ -922,7 +923,7 @@ find_conflict:
error = 0;

out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
if (new_fl)
locks_free_lock(new_fl);
locks_dispose_list(&dispose);
@@ -958,7 +959,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
new_fl2 = locks_alloc_lock();
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
* there are any, either return error or put the request on the
@@ -1129,7 +1130,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
locks_wake_up_blocks(left);
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
/*
* Free any unused locks.
*/
@@ -1211,7 +1212,7 @@ int locks_mandatory_locked(struct file *file)
/*
* Search the lock list for this inode for any POSIX locks.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
ret = 0;
list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
if (fl->fl_owner != current->files &&
@@ -1220,7 +1221,7 @@ int locks_mandatory_locked(struct file *file)
break;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
return ret;
}

@@ -1339,7 +1340,7 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
struct file_lock_context *ctx = inode->i_flctx;
struct file_lock *fl, *tmp;

- lockdep_assert_held(&inode->i_lock);
+ lockdep_assert_held(&ctx->flc_lock);

list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
trace_time_out_leases(inode, fl);
@@ -1363,7 +1364,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker)
struct file_lock_context *ctx = inode->i_flctx;
struct file_lock *fl;

- lockdep_assert_held(&inode->i_lock);
+ lockdep_assert_held(&ctx->flc_lock);

list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (leases_conflict(fl, breaker))
@@ -1406,7 +1407,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
return error;
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);

time_out_leases(inode, &dispose);

@@ -1456,11 +1457,11 @@ restart:
break_time++;
locks_insert_block(fl, new_fl);
trace_break_lease_block(inode, new_fl);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
error = wait_event_interruptible_timeout(new_fl->fl_wait,
!new_fl->fl_next, break_time);
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
trace_break_lease_unblock(inode, new_fl);
locks_delete_block(new_fl);
if (error >= 0) {
@@ -1475,7 +1476,7 @@ restart:
error = 0;
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
locks_free_lock(new_fl);
return error;
@@ -1499,13 +1500,13 @@ void lease_get_mtime(struct inode *inode, struct timespec *time)
struct file_lock *fl;

if (ctx) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
if (!list_empty(&ctx->flc_lease)) {
fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
if (fl->fl_type == F_WRLCK)
has_lease = true;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
}

if (has_lease)
@@ -1548,7 +1549,7 @@ int fcntl_getlease(struct file *filp)
LIST_HEAD(dispose);

if (ctx) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
time_out_leases(file_inode(filp), &dispose);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file != filp)
@@ -1556,7 +1557,7 @@ int fcntl_getlease(struct file *filp)
type = target_leasetype(fl);
break;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
}
return type;
@@ -1624,7 +1625,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
return -EINVAL;
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
error = check_conflicting_open(dentry, arg);
if (error)
@@ -1691,7 +1692,7 @@ out_setup:
if (lease->fl_lmops->lm_setup)
lease->fl_lmops->lm_setup(lease, priv);
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
if (is_deleg)
mutex_unlock(&inode->i_mutex);
@@ -1714,7 +1715,7 @@ static int generic_delete_lease(struct file *filp)
return error;
}

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file == filp) {
victim = fl;
@@ -1724,7 +1725,7 @@ static int generic_delete_lease(struct file *filp)
trace_generic_delete_lease(inode, fl);
if (victim)
error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
return error;
}
@@ -2414,10 +2415,10 @@ locks_remove_lease(struct file *filp)
if (!ctx)
return;

- spin_lock(&inode->i_lock);
+ spin_lock(&ctx->flc_lock);
list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
lease_modify(&fl, F_UNLCK, &dispose);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ctx->flc_lock);
locks_dispose_list(&dispose);
}

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 3fb1caa3874d..8cdb2b28a104 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -93,22 +93,22 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
goto out;

list = &flctx->flc_posix;
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
restart:
list_for_each_entry(fl, list, fl_list) {
if (nfs_file_open_context(fl->fl_file) != ctx)
continue;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
status = nfs4_lock_delegation_recall(fl, state, stateid);
if (status < 0)
goto out;
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
}
if (list == &flctx->flc_posix) {
list = &flctx->flc_flock;
goto restart;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
out:
return status;
}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6d0a2bd1ecb1..2f4515bd2c7b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1377,12 +1377,12 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
/* Guard against delegation returns and new lock/unlock calls */
down_write(&nfsi->rwsem);
/* Protect inode->i_flock using the BKL */
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
restart:
list_for_each_entry(fl, list, fl_list) {
if (nfs_file_open_context(fl->fl_file)->state != state)
continue;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
status = ops->recover_lock(state, fl);
switch (status) {
case 0:
@@ -1409,13 +1409,13 @@ restart:
/* kill_proc(fl->fl_pid, SIGLOST, 1); */
status = 0;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
}
if (list == &flctx->flc_posix) {
list = &flctx->flc_flock;
goto restart;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
out:
up_write(&nfsi->rwsem);
return status;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index ee43aad0fb4e..df245bccd10a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1204,7 +1204,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino

/* Check to see if there are whole file write locks */
ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
if (!list_empty(&flctx->flc_posix)) {
fl = list_first_entry(&flctx->flc_posix, struct file_lock, fl_list);
if (is_whole_file_wrlock(fl))
@@ -1214,7 +1214,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
if (fl->fl_type == F_WRLCK)
ret = 1;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
return ret;
}

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ee4c660b2e47..159a3a79df83 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5572,14 +5572,14 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
flctx = inode->i_flctx;

if (flctx && !list_empty(&flctx->flc_posix)) {
- spin_lock(&inode->i_lock);
+ spin_lock(&flctx->flc_lock);
list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
if (fl->fl_owner == (fl_owner_t)lowner) {
status = true;
break;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&flctx->flc_lock);
}
fput(filp);
return status;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7da02cb90b30..cbf89d9085a5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -968,6 +968,7 @@ struct file_lock {
};

struct file_lock_context {
+ spinlock_t flc_lock;
struct list_head flc_flock;
struct list_head flc_posix;
struct list_head flc_lease;
--
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/