locks: move flock locks to file_lock_context

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>

6 files changed, 152 insertions, 35 deletions

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 366dc2412605..917656ea8dcf 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -239,14 +239,16 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
         return err;
 }
 
-/**
- * Must be called with lock_flocks() already held. Fills in the passed
- * counter variables, so you can prepare pagelist metadata before calling
- * ceph_encode_locks.
+/*
+ * Fills in the passed counter variables, so you can prepare pagelist metadata
+ * before calling ceph_encode_locks.
+ *
+ * FIXME: add counters to struct file_lock_context so we don't need to do this?
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
         struct file_lock *lock;
+        struct file_lock_context *ctx;
 
         *fcntl_count = 0;
         *flock_count = 0;
@@ -255,7 +257,11 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
         for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
                 if (lock->fl_flags & FL_POSIX)
                         ++(*fcntl_count);
-                else if (lock->fl_flags & FL_FLOCK)
+        }
+
+        ctx = inode->i_flctx;
+        if (ctx) {
+                list_for_each_entry(lock, &ctx->flc_flock, fl_list)
                         ++(*flock_count);
         }
         spin_unlock(&inode->i_lock);
@@ -273,6 +279,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
                                 int num_fcntl_locks, int num_flock_locks)
 {
         struct file_lock *lock;
+        struct file_lock_context *ctx;
         int err = 0;
         int seen_fcntl = 0;
         int seen_flock = 0;
@@ -295,8 +302,10 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
                         ++l;
                 }
         }
-        for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-                if (lock->fl_flags & FL_FLOCK) {
+
+        ctx = inode->i_flctx;
+        if (ctx) {
+                list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
                         ++seen_flock;
                         if (seen_flock > num_flock_locks) {
                                 err = -ENOSPC;
diff --git a/fs/locks.c b/fs/locks.c
index 526d5fca67c8..055df53f19de 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -694,6 +694,14 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
         locks_insert_global_locks(fl);
 }
 
+static void
+locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
+{
+        fl->fl_nspid = get_pid(task_tgid(current));
+        list_add_tail(&fl->fl_list, before);
+        locks_insert_global_locks(fl);
+}
+
 /**
  * locks_delete_lock - Delete a lock and then free it.
  * @thisfl_p: pointer that points to the fl_next field of the previous
@@ -739,6 +747,18 @@ static void locks_delete_lock(struct file_lock **thisfl_p,
                 locks_free_lock(fl);
 }
 
+static void
+locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
+{
+        locks_delete_global_locks(fl);
+        if (fl->fl_nspid) {
+                put_pid(fl->fl_nspid);
+                fl->fl_nspid = NULL;
+        }
+        locks_wake_up_blocks(fl);
+        list_move(&fl->fl_list, dispose);
+}
+
 /* Determine if lock sys_fl blocks lock caller_fl. Common functionality
  * checks for shared/exclusive status of overlapping locks.
  */
@@ -888,12 +908,17 @@ static int posix_locks_deadlock(struct file_lock *caller_fl,
 static int flock_lock_file(struct file *filp, struct file_lock *request)
 {
         struct file_lock *new_fl = NULL;
-        struct file_lock **before;
-        struct inode * inode = file_inode(filp);
+        struct file_lock *fl;
+        struct file_lock_context *ctx;
+        struct inode *inode = file_inode(filp);
         int error = 0;
-        int found = 0;
+        bool found = false;
         LIST_HEAD(dispose);
 
+        ctx = locks_get_lock_context(inode);
+        if (!ctx)
+                return -ENOMEM;
+
         if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) {
                 new_fl = locks_alloc_lock();
                 if (!new_fl)
@@ -904,18 +929,13 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
         if (request->fl_flags & FL_ACCESS)
                 goto find_conflict;
 
-        for_each_lock(inode, before) {
-                struct file_lock *fl = *before;
-                if (IS_POSIX(fl))
-                        break;
-                if (IS_LEASE(fl))
-                        continue;
+        list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
                 if (filp != fl->fl_file)
                         continue;
                 if (request->fl_type == fl->fl_type)
                         goto out;
-                found = 1;
-                locks_delete_lock(before, &dispose);
+                found = true;
+                locks_delete_lock_ctx(fl, &dispose);
                 break;
         }
 
@@ -936,12 +956,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
         }
 
 find_conflict:
-        for_each_lock(inode, before) {
-                struct file_lock *fl = *before;
-                if (IS_POSIX(fl))
-                        break;
-                if (IS_LEASE(fl))
-                        continue;
+        list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
                 if (!flock_locks_conflict(request, fl))
                         continue;
                 error = -EAGAIN;
@@ -954,7 +969,7 @@ find_conflict:
         if (request->fl_flags & FL_ACCESS)
                 goto out;
         locks_copy_lock(new_fl, request);
-        locks_insert_lock(before, new_fl);
+        locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
         new_fl = NULL;
         error = 0;
 
@@ -2412,8 +2427,9 @@ locks_remove_flock(struct file *filp)
                 .fl_type = F_UNLCK,
                 .fl_end = OFFSET_MAX,
         };
+        struct file_lock_context *flctx = file_inode(filp)->i_flctx;
 
-        if (!file_inode(filp)->i_flock)
+        if (!flctx || list_empty(&flctx->flc_flock))
                 return;
 
         if (filp->f_op->flock)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f3f60641344..9f9f67b17e2b 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -85,15 +85,16 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 {
         struct inode *inode = state->inode;
         struct file_lock *fl;
+        struct file_lock_context *flctx;
         int status = 0;
 
-        if (inode->i_flock == NULL)
+        if (inode->i_flock == NULL && inode->i_flctx == NULL)
                 goto out;
 
         /* Protect inode->i_flock using the i_lock */
         spin_lock(&inode->i_lock);
         for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-                if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
+                if (!(fl->fl_flags & (FL_POSIX)))
                         continue;
                 if (nfs_file_open_context(fl->fl_file) != ctx)
                         continue;
@@ -103,6 +104,20 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
                         goto out;
                 spin_lock(&inode->i_lock);
         }
+
+        flctx = inode->i_flctx;
+        if (flctx) {
+                list_for_each_entry(fl, &flctx->flc_flock, fl_list) {
+                        if (nfs_file_open_context(fl->fl_file) != ctx)
+                                continue;
+                        spin_unlock(&inode->i_lock);
+                        status = nfs4_lock_delegation_recall(fl, state,
+                                                                stateid);
+                        if (status < 0)
+                                goto out;
+                        spin_lock(&inode->i_lock);
+                }
+        }
         spin_unlock(&inode->i_lock);
 out:
         return status;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5194933ed419..65c404bf61ae 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1366,8 +1366,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
         struct nfs_inode *nfsi = NFS_I(inode);
         struct file_lock *fl;
         int status = 0;
+        struct file_lock_context *flctx = inode->i_flctx;
 
-        if (inode->i_flock == NULL)
+        if (inode->i_flock == NULL && flctx == NULL)
                 return 0;
 
         /* Guard against delegation returns and new lock/unlock calls */
@@ -1375,7 +1376,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
         /* Protect inode->i_flock using the BKL */
         spin_lock(&inode->i_lock);
         for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-                if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
+                if (!(fl->fl_flags & FL_POSIX))
                         continue;
                 if (nfs_file_open_context(fl->fl_file)->state != state)
                         continue;
@@ -1408,6 +1409,43 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
                 }
                 spin_lock(&inode->i_lock);
         }
+
+        if (!flctx)
+                goto out_unlock;
+
+        list_for_each_entry(fl, &flctx->flc_flock, fl_list) {
+                if (nfs_file_open_context(fl->fl_file)->state != state)
+                        continue;
+                spin_unlock(&inode->i_lock);
+                status = ops->recover_lock(state, fl);
+                switch (status) {
+                case 0:
+                        break;
+                case -ESTALE:
+                case -NFS4ERR_ADMIN_REVOKED:
+                case -NFS4ERR_STALE_STATEID:
+                case -NFS4ERR_BAD_STATEID:
+                case -NFS4ERR_EXPIRED:
+                case -NFS4ERR_NO_GRACE:
+                case -NFS4ERR_STALE_CLIENTID:
+                case -NFS4ERR_BADSESSION:
+                case -NFS4ERR_BADSLOT:
+                case -NFS4ERR_BAD_HIGH_SLOT:
+                case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+                        goto out;
+                default:
+                        pr_err("NFS: %s: unhandled error %d\n",
+                                        __func__, status);
+                case -ENOMEM:
+                case -NFS4ERR_DENIED:
+                case -NFS4ERR_RECLAIM_BAD:
+                case -NFS4ERR_RECLAIM_CONFLICT:
+                        /* kill_proc(fl->fl_pid, SIGLOST, 1); */
+                        status = 0;
+                }
+                spin_lock(&inode->i_lock);
+        }
+out_unlock:
         spin_unlock(&inode->i_lock);
 out:
         up_write(&nfsi->rwsem);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 2b5e769beb16..a3b62e15b444 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -826,6 +826,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
                                       struct nfs_pageio_descriptor *pgio)
 {
         size_t size;
+        struct file_lock_context *flctx;
 
         if (prev) {
                 if (!nfs_match_open_context(req->wb_context, prev->wb_context))
@@ -834,6 +835,11 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
                     !nfs_match_lock_context(req->wb_lock_context,
                                             prev->wb_lock_context))
                         return false;
+                flctx = req->wb_context->dentry->d_inode->i_flctx;
+                if (flctx != NULL && !list_empty_careful(&flctx->flc_flock) &&
+                    !nfs_match_lock_context(req->wb_lock_context,
+                                            prev->wb_lock_context))
+                        return false;
                 if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
                         return false;
                 if (req->wb_page == prev->wb_page) {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af685a9e3..e072aeb34195 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1113,6 +1113,11 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
                         do_flush |= l_ctx->lockowner.l_owner != current->files
                                 || l_ctx->lockowner.l_pid != current->tgid;
                 }
+                if (l_ctx && ctx->dentry->d_inode->i_flctx &&
+                    !list_empty_careful(&ctx->dentry->d_inode->i_flctx->flc_flock)) {
+                        do_flush |= l_ctx->lockowner.l_owner != current->files
+                                || l_ctx->lockowner.l_pid != current->tgid;
+                }
                 nfs_release_request(req);
                 if (!do_flush)
                         return 0;
@@ -1170,6 +1175,13 @@ out:
         return PageUptodate(page) != 0;
 }
 
+static bool
+is_whole_file_wrlock(struct file_lock *fl)
+{
+        return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
+                        fl->fl_type == F_WRLCK;
+}
+
 /* If we know the page is up to date, and we're not using byte range locks (or
  * if we have the whole file locked for writing), it may be more efficient to
  * extend the write to cover the entire page in order to avoid fragmentation
@@ -1180,17 +1192,38 @@ out:
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
+        int ret;
+        struct file_lock_context *flctx = inode->i_flctx;
+        struct file_lock *fl;
+
         if (file->f_flags & O_DSYNC)
                 return 0;
         if (!nfs_write_pageuptodate(page, inode))
                 return 0;
         if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
                 return 1;
-        if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
-                        inode->i_flock->fl_end == OFFSET_MAX &&
-                        inode->i_flock->fl_type != F_RDLCK))
-                return 1;
-        return 0;
+        if (!inode->i_flock && !flctx)
+                return 0;
+
+        /* Check to see if there are whole file write locks */
+        spin_lock(&inode->i_lock);
+        ret = 0;
+
+        fl = inode->i_flock;
+        if (fl && is_whole_file_wrlock(fl)) {
+                ret = 1;
+                goto out;
+        }
+
+        if (!list_empty(&flctx->flc_flock)) {
+                fl = list_first_entry(&flctx->flc_flock, struct file_lock,
+                                        fl_list);
+                if (fl->fl_type == F_WRLCK)
+                        ret = 1;
+        }
+out:
+        spin_unlock(&inode->i_lock);
+        return ret;
 }
 
 /*