*/
#include <linux/types.h>
+#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/nlm.h>
#include <linux/lockd/lockd.h>
+#include <linux/kthread.h>
#define NLMDBG_FACILITY NLMDBG_SVCLOCK
static inline int nlm_cookie_match(struct nlm_cookie *a, struct nlm_cookie *b)
{
- if(a->len != b->len)
+ if (a->len != b->len)
return 0;
- if(memcmp(a->data,b->data,a->len))
+ if (memcmp(a->data, b->data, a->len))
return 0;
return 1;
}
* GRANTED_RES message by cookie, without having to rely on the client's IP
* address. --okir
*/
-static inline struct nlm_block *
-nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_file *file,
- struct nlm_lock *lock, struct nlm_cookie *cookie)
+static struct nlm_block *
+nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
+ struct nlm_file *file, struct nlm_lock *lock,
+ struct nlm_cookie *cookie)
{
struct nlm_block *block;
- struct nlm_host *host;
struct nlm_rqst *call = NULL;
- /* Create host handle for callback */
- host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
- if (host == NULL)
- return NULL;
-
+ nlm_get_host(host);
call = nlm_alloc_call(host);
if (call == NULL)
return NULL;
block->b_daemon = rqstp->rq_server;
block->b_host = host;
block->b_file = file;
+ block->b_fl = NULL;
file->f_count++;
/* Add to file's list of blocks */
}
/*
- * Delete a block. If the lock was cancelled or the grant callback
- * failed, unlock is set to 1.
+ * Delete a block.
* It is the caller's responsibility to check whether the file
* can be closed hereafter.
*/
nlmsvc_freegrantargs(block->b_call);
nlm_release_call(block->b_call);
nlm_release_file(block->b_file);
+ kfree(block->b_fl);
kfree(block);
}
{
if (call->a_args.lock.oh.data != call->a_owner)
kfree(call->a_args.lock.oh.data);
+
+ locks_release_private(&call->a_args.lock.fl);
+}
+
+/*
+ * Deferred lock request handling for non-blocking lock
+ */
+static __be32
+nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
+{
+ __be32 status = nlm_lck_denied_nolocks;
+
+ block->b_flags |= B_QUEUED;
+
+ nlmsvc_insert_block(block, NLM_TIMEOUT);
+
+ block->b_cache_req = &rqstp->rq_chandle;
+ if (rqstp->rq_chandle.defer) {
+ block->b_deferred_req =
+ rqstp->rq_chandle.defer(block->b_cache_req);
+ if (block->b_deferred_req != NULL)
+ status = nlm_drop_reply;
+ }
+ dprintk("lockd: nlmsvc_defer_lock_rqst block %p flags %d status %d\n",
+ block, block->b_flags, ntohl(status));
+
+ return status;
}
/*
*/
__be32
nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
- struct nlm_lock *lock, int wait, struct nlm_cookie *cookie)
+ struct nlm_host *host, struct nlm_lock *lock, int wait,
+ struct nlm_cookie *cookie, int reclaim)
{
- struct nlm_block *block, *newblock = NULL;
+ struct nlm_block *block = NULL;
int error;
__be32 ret;
(long long)lock->fl.fl_end,
wait);
-
- lock->fl.fl_flags &= ~FL_SLEEP;
-again:
/* Lock file against concurrent access */
mutex_lock(&file->f_mutex);
- /* Get existing block (in case client is busy-waiting) */
+ /* Get existing block (in case client is busy-waiting)
+ * or create new block
+ */
block = nlmsvc_lookup_block(file, lock);
if (block == NULL) {
- if (newblock != NULL)
- lock = &newblock->b_call->a_args.lock;
- } else
+ block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
+ ret = nlm_lck_denied_nolocks;
+ if (block == NULL)
+ goto out;
lock = &block->b_call->a_args.lock;
+ } else
+ lock->fl.fl_flags &= ~FL_SLEEP;
- error = posix_lock_file(file->f_file, &lock->fl);
- lock->fl.fl_flags &= ~FL_SLEEP;
+ if (block->b_flags & B_QUEUED) {
+ dprintk("lockd: nlmsvc_lock deferred block %p flags %d\n",
+ block, block->b_flags);
+ if (block->b_granted) {
+ nlmsvc_unlink_block(block);
+ ret = nlm_granted;
+ goto out;
+ }
+ if (block->b_flags & B_TIMED_OUT) {
+ nlmsvc_unlink_block(block);
+ ret = nlm_lck_denied;
+ goto out;
+ }
+ ret = nlm_drop_reply;
+ goto out;
+ }
+
+ if (locks_in_grace() && !reclaim) {
+ ret = nlm_lck_denied_grace_period;
+ goto out;
+ }
+ if (reclaim && !locks_in_grace()) {
+ ret = nlm_lck_denied_grace_period;
+ goto out;
+ }
- dprintk("lockd: posix_lock_file returned %d\n", error);
+ if (!wait)
+ lock->fl.fl_flags &= ~FL_SLEEP;
+ error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
+ lock->fl.fl_flags &= ~FL_SLEEP;
- switch(error) {
+ dprintk("lockd: vfs_lock_file returned %d\n", error);
+ switch (error) {
case 0:
ret = nlm_granted;
goto out;
case -EAGAIN:
- break;
+ /*
+ * If this is a blocking request for an
+ * already pending lock request then we need
+ * to put it back on lockd's block list
+ */
+ if (wait)
+ break;
+ ret = nlm_lck_denied;
+ goto out;
+ case FILE_LOCK_DEFERRED:
+ if (wait)
+ break;
+ /* Filesystem lock operation is in progress
+ Add it to the queue waiting for callback */
+ ret = nlmsvc_defer_lock_rqst(rqstp, block);
+ goto out;
case -EDEADLK:
ret = nlm_deadlock;
goto out;
goto out;
}
- ret = nlm_lck_denied;
- if (!wait)
- goto out;
-
ret = nlm_lck_blocked;
- if (block != NULL)
- goto out;
-
- /* If we don't have a block, create and initialize it. Then
- * retry because we may have slept in kmalloc. */
- /* We have to release f_mutex as nlmsvc_create_block may try to
- * to claim it while doing host garbage collection */
- if (newblock == NULL) {
- mutex_unlock(&file->f_mutex);
- dprintk("lockd: blocking on this lock (allocating).\n");
- if (!(newblock = nlmsvc_create_block(rqstp, file, lock, cookie)))
- return nlm_lck_denied_nolocks;
- goto again;
- }
/* Append to list of blocked */
- nlmsvc_insert_block(newblock, NLM_NEVER);
+ nlmsvc_insert_block(block, NLM_NEVER);
out:
mutex_unlock(&file->f_mutex);
- nlmsvc_release_block(newblock);
nlmsvc_release_block(block);
dprintk("lockd: nlmsvc_lock returned %u\n", ret);
return ret;
* Test for presence of a conflicting lock.
*/
__be32
-nlmsvc_testlock(struct nlm_file *file, struct nlm_lock *lock,
- struct nlm_lock *conflock)
+nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
+ struct nlm_host *host, struct nlm_lock *lock,
+ struct nlm_lock *conflock, struct nlm_cookie *cookie)
{
+ struct nlm_block *block = NULL;
+ int error;
+ __be32 ret;
+
dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
file->f_file->f_path.dentry->d_inode->i_sb->s_id,
file->f_file->f_path.dentry->d_inode->i_ino,
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end);
- if (posix_test_lock(file->f_file, &lock->fl, &conflock->fl)) {
- dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
- conflock->fl.fl_type,
- (long long)conflock->fl.fl_start,
- (long long)conflock->fl.fl_end);
- conflock->caller = "somehost"; /* FIXME */
- conflock->len = strlen(conflock->caller);
- conflock->oh.len = 0; /* don't return OH info */
- conflock->svid = conflock->fl.fl_pid;
- return nlm_lck_denied;
+ /* Get existing block (in case client is busy-waiting) */
+ block = nlmsvc_lookup_block(file, lock);
+
+ if (block == NULL) {
+ struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
+
+ if (conf == NULL)
+ return nlm_granted;
+ block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
+ if (block == NULL) {
+ kfree(conf);
+ return nlm_granted;
+ }
+ block->b_fl = conf;
+ }
+ if (block->b_flags & B_QUEUED) {
+ dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
+ block, block->b_flags, block->b_fl);
+ if (block->b_flags & B_TIMED_OUT) {
+ nlmsvc_unlink_block(block);
+ ret = nlm_lck_denied;
+ goto out;
+ }
+ if (block->b_flags & B_GOT_CALLBACK) {
+ nlmsvc_unlink_block(block);
+ if (block->b_fl != NULL
+ && block->b_fl->fl_type != F_UNLCK) {
+ lock->fl = *block->b_fl;
+ goto conf_lock;
+ } else {
+ ret = nlm_granted;
+ goto out;
+ }
+ }
+ ret = nlm_drop_reply;
+ goto out;
+ }
+
+ if (locks_in_grace()) {
+ ret = nlm_lck_denied_grace_period;
+ goto out;
+ }
+ error = vfs_test_lock(file->f_file, &lock->fl);
+ if (error == FILE_LOCK_DEFERRED) {
+ ret = nlmsvc_defer_lock_rqst(rqstp, block);
+ goto out;
+ }
+ if (error) {
+ ret = nlm_lck_denied_nolocks;
+ goto out;
+ }
+ if (lock->fl.fl_type == F_UNLCK) {
+ ret = nlm_granted;
+ goto out;
}
- return nlm_granted;
+conf_lock:
+ dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
+ lock->fl.fl_type, (long long)lock->fl.fl_start,
+ (long long)lock->fl.fl_end);
+ conflock->caller = "somehost"; /* FIXME */
+ conflock->len = strlen(conflock->caller);
+ conflock->oh.len = 0; /* don't return OH info */
+ conflock->svid = lock->fl.fl_pid;
+ conflock->fl.fl_type = lock->fl.fl_type;
+ conflock->fl.fl_start = lock->fl.fl_start;
+ conflock->fl.fl_end = lock->fl.fl_end;
+ ret = nlm_lck_denied;
+out:
+ if (block)
+ nlmsvc_release_block(block);
+ return ret;
}
/*
nlmsvc_cancel_blocked(file, lock);
lock->fl.fl_type = F_UNLCK;
- error = posix_lock_file(file->f_file, &lock->fl);
+ error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
}
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end);
+ if (locks_in_grace())
+ return nlm_lck_denied_grace_period;
+
mutex_lock(&file->f_mutex);
block = nlmsvc_lookup_block(file, lock);
mutex_unlock(&file->f_mutex);
if (block != NULL) {
+ vfs_cancel_lock(block->b_file->f_file,
+ &block->b_call->a_args.lock.fl);
status = nlmsvc_unlink_block(block);
nlmsvc_release_block(block);
}
}
/*
+ * This is a callback from the filesystem for VFS file lock requests.
+ * It will be used if fl_grant is defined and the filesystem can not
+ * respond to the request immediately.
+ * For GETLK request it will copy the reply to the nlm_block.
+ * For SETLK or SETLKW request it will get the local posix lock.
+ * In all cases it will move the block to the head of nlm_blocked q where
+ * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
+ * deferred rpc for GETLK and SETLK.
+ */
+static void
+nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
+ int result)
+{
+ block->b_flags |= B_GOT_CALLBACK;
+ if (result == 0)
+ block->b_granted = 1;
+ else
+ block->b_flags |= B_TIMED_OUT;
+ if (conf) {
+ if (block->b_fl)
+ __locks_copy_lock(block->b_fl, conf);
+ }
+}
+
+static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
+ int result)
+{
+ struct nlm_block *block;
+ int rc = -ENOENT;
+
+ lock_kernel();
+ list_for_each_entry(block, &nlm_blocked, b_list) {
+ if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
+ dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
+ block, block->b_flags);
+ if (block->b_flags & B_QUEUED) {
+ if (block->b_flags & B_TIMED_OUT) {
+ rc = -ENOLCK;
+ break;
+ }
+ nlmsvc_update_deferred_block(block, conf, result);
+ } else if (result == 0)
+ block->b_granted = 1;
+
+ nlmsvc_insert_block(block, 0);
+ svc_wake_up(block->b_daemon);
+ rc = 0;
+ break;
+ }
+ }
+ unlock_kernel();
+ if (rc == -ENOENT)
+ printk(KERN_WARNING "lockd: grant for unknown block\n");
+ return rc;
+}
+
+/*
* Unblock a blocked lock request. This is a callback invoked from the
* VFS layer when a lock on which we blocked is removed.
*
return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
}
-struct lock_manager_operations nlmsvc_lock_operations = {
+const struct lock_manager_operations nlmsvc_lock_operations = {
.fl_compare_owner = nlmsvc_same_owner,
.fl_notify = nlmsvc_notify_blocked,
+ .fl_grant = nlmsvc_grant_deferred,
};
/*
dprintk("lockd: grant blocked lock %p\n", block);
+ kref_get(&block->b_count);
+
/* Unlink block request from list */
nlmsvc_unlink_block(block);
/* Try the lock operation again */
lock->fl.fl_flags |= FL_SLEEP;
- error = posix_lock_file(file->f_file, &lock->fl);
+ error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
lock->fl.fl_flags &= ~FL_SLEEP;
switch (error) {
case 0:
break;
- case -EAGAIN:
- dprintk("lockd: lock still blocked\n");
+ case FILE_LOCK_DEFERRED:
+ dprintk("lockd: lock still blocked error %d\n", error);
nlmsvc_insert_block(block, NLM_NEVER);
+ nlmsvc_release_block(block);
return;
default:
printk(KERN_WARNING "lockd: unexpected error %d in %s!\n",
- -error, __FUNCTION__);
+ -error, __func__);
nlmsvc_insert_block(block, 10 * HZ);
+ nlmsvc_release_block(block);
return;
}
dprintk("lockd: GRANTing blocked lock.\n");
block->b_granted = 1;
- /* Schedule next grant callback in 30 seconds */
- nlmsvc_insert_block(block, 30 * HZ);
+ /* keep block on the list, but don't reattempt until the RPC
+ * completes or the submission fails
+ */
+ nlmsvc_insert_block(block, NLM_NEVER);
- /* Call the client */
- kref_get(&block->b_count);
- nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);
+ /* Call the client -- use a soft RPC task since nlmsvc_retry_blocked
+ * will queue up a new one if this one times out
+ */
+ error = nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG,
+ &nlmsvc_grant_ops);
+
+ /* RPC submission failed, wait a bit and retry */
+ if (error < 0)
+ nlmsvc_insert_block(block, 10 * HZ);
}
/*
dprintk("lockd: GRANT_MSG RPC callback\n");
+ lock_kernel();
+ /* if the block is not on a list at this point then it has
+ * been invalidated. Don't try to requeue it.
+ *
+ * FIXME: it's possible that the block is removed from the list
+ * after this check but before the nlmsvc_insert_block. In that
+ * case it will be added back. Perhaps we need better locking
+ * for nlm_blocked?
+ */
+ if (list_empty(&block->b_list))
+ goto out;
+
/* Technically, we should down the file semaphore here. Since we
* move the block towards the head of the queue only, no harm
* can be done, though. */
}
nlmsvc_insert_block(block, timeout);
svc_wake_up(block->b_daemon);
+out:
+ unlock_kernel();
}
static void nlmsvc_grant_release(void *data)
{
struct nlm_rqst *call = data;
+ lock_kernel();
nlmsvc_release_block(call->a_block);
+ unlock_kernel();
}
static const struct rpc_call_ops nlmsvc_grant_ops = {
nlmsvc_release_block(block);
}
+/* Helper function to handle retry of a deferred block.
+ * If it is a blocking lock, call grant_blocked.
+ * For a non-blocking lock or test lock, revisit the request.
+ */
+static void
+retry_deferred_block(struct nlm_block *block)
+{
+ if (!(block->b_flags & B_GOT_CALLBACK))
+ block->b_flags |= B_TIMED_OUT;
+ nlmsvc_insert_block(block, NLM_TIMEOUT);
+ dprintk("revisit block %p flags %d\n", block, block->b_flags);
+ if (block->b_deferred_req) {
+ block->b_deferred_req->revisit(block->b_deferred_req, 0);
+ block->b_deferred_req = NULL;
+ }
+}
+
/*
* Retry all blocked locks that have been notified. This is where lockd
* picks up locks that can be granted, or grant notifications that must
unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
struct nlm_block *block;
- while (!list_empty(&nlm_blocked)) {
+ while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
if (block->b_when == NLM_NEVER)
break;
- if (time_after(block->b_when,jiffies)) {
+ if (time_after(block->b_when, jiffies)) {
timeout = block->b_when - jiffies;
break;
}
dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
block, block->b_when);
- kref_get(&block->b_count);
- nlmsvc_grant_blocked(block);
- nlmsvc_release_block(block);
+ if (block->b_flags & B_QUEUED) {
+ dprintk("nlmsvc_retry_blocked delete block (%p, granted=%d, flags=%d)\n",
+ block, block->b_granted, block->b_flags);
+ retry_deferred_block(block);
+ } else
+ nlmsvc_grant_blocked(block);
}
return timeout;