Merge tag 'nfs-for-3.14-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "Highlights:

   - Fix several races in nfs_revalidate_mapping
   - NFSv4.1 slot leakage in the pNFS files driver
   - Stable fix for a slot leak in nfs40_sequence_done
   - Don't reject NFSv4 servers that support ACLs with only ALLOW aces"

* tag 'nfs-for-3.14-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  nfs: initialize the ACL support bits to zero.
  NFSv4.1: Cleanup
  NFSv4.1: Clean up nfs41_sequence_done
  NFSv4: Fix a slot leak in nfs40_sequence_done
  NFSv4.1 free slot before resending I/O to MDS
  nfs: add memory barriers around NFS_INO_INVALID_DATA and NFS_INO_INVALIDATING
  NFS: Fix races in nfs_revalidate_mapping
  sunrpc: turn warn_gssd() log message into a dprintk()
  NFS: fix the handling of NFS_INO_INVALID_DATA flag in nfs_revalidate_mapping
  nfs: handle servers that support only ALLOW ACE type.

9 files changed, 84 insertions, 35 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b266f734bd53..be38b573495a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -274,6 +274,15 @@ out_eof:
         return -EBADCOOKIE;
 }
 
+static bool
+nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
+{
+        if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+                return false;
+        smp_rmb();
+        return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
+}
+
 static
 int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
 {
@@ -287,8 +296,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
                         struct nfs_open_dir_context *ctx = desc->file->private_data;
 
                         new_pos = desc->current_index + i;
-                        if (ctx->attr_gencount != nfsi->attr_gencount
-                            || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+                        if (ctx->attr_gencount != nfsi->attr_gencount ||
+                            !nfs_readdir_inode_mapping_valid(nfsi)) {
                                 ctx->duped = 0;
                                 ctx->attr_gencount = nfsi->attr_gencount;
                         } else if (new_pos < desc->ctx->pos) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ea00b34ff071..28a0a3cbd3b7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -977,11 +977,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
                 if (ret < 0)
                         return ret;
         }
-        spin_lock(&inode->i_lock);
-        nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
-        if (S_ISDIR(inode->i_mode))
+        if (S_ISDIR(inode->i_mode)) {
+                spin_lock(&inode->i_lock);
                 memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
-        spin_unlock(&inode->i_lock);
+                spin_unlock(&inode->i_lock);
+        }
         nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
         nfs_fscache_wait_on_invalidate(inode);
 
@@ -1008,6 +1008,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
+        unsigned long *bitlock = &nfsi->flags;
         int ret = 0;
 
         /* swapfiles are not supposed to be shared. */
@@ -1019,12 +1020,46 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
                 if (ret < 0)
                         goto out;
         }
-        if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
-                trace_nfs_invalidate_mapping_enter(inode);
-                ret = nfs_invalidate_mapping(inode, mapping);
-                trace_nfs_invalidate_mapping_exit(inode, ret);
+
+        /*
+         * We must clear NFS_INO_INVALID_DATA first to ensure that
+         * invalidations that come in while we're shooting down the mappings
+         * are respected. But, that leaves a race window where one revalidator
+         * can clear the flag, and then another checks it before the mapping
+         * gets invalidated. Fix that by serializing access to this part of
+         * the function.
+         *
+         * At the same time, we need to allow other tasks to see whether we
+         * might be in the middle of invalidating the pages, so we only set
+         * the bit lock here if it looks like we're going to be doing that.
+         */
+        for (;;) {
+                ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+                                  nfs_wait_bit_killable, TASK_KILLABLE);
+                if (ret)
+                        goto out;
+                spin_lock(&inode->i_lock);
+                if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+                        spin_unlock(&inode->i_lock);
+                        continue;
+                }
+                if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+                        break;
+                spin_unlock(&inode->i_lock);
+                goto out;
         }
 
+        set_bit(NFS_INO_INVALIDATING, bitlock);
+        smp_wmb();
+        nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+        spin_unlock(&inode->i_lock);
+        trace_nfs_invalidate_mapping_enter(inode);
+        ret = nfs_invalidate_mapping(inode, mapping);
+        trace_nfs_invalidate_mapping_exit(inode, ret);
+
+        clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+        smp_mb__after_clear_bit();
+        wake_up_bit(bitlock, NFS_INO_INVALIDATING);
 out:
         return ret;
 }
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 5609edc742a0..a5b27c2d9689 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -270,6 +270,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 extern int nfs41_setup_sequence(struct nfs4_session *session,
                 struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
                 struct rpc_task *task);
+extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 73d4ecda1e36..dbb3e1f30c68 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -372,10 +372,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
         __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
         __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 
-        error = -EINVAL;
-        if (gssd_running(clp->cl_net))
-                error = nfs_create_rpc_client(clp, timeparms,
-                                              RPC_AUTH_GSS_KRB5I);
+        error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
         if (error == -EINVAL)
                 error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
         if (error < 0)
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 03fd8be8c0c5..12c8132ad408 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -335,8 +335,10 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
         dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
         if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
-            task->tk_status == 0)
+            task->tk_status == 0) {
+                nfs41_sequence_done(task, &rdata->res.seq_res);
                 return;
+        }
 
         /* Note this may cause RPC to be resent */
         rdata->header->mds_ops->rpc_call_done(task, data);
@@ -442,8 +444,10 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
         struct nfs_write_data *wdata = data;
 
         if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
-            task->tk_status == 0)
+            task->tk_status == 0) {
+                nfs41_sequence_done(task, &wdata->res.seq_res);
                 return;
+        }
 
         /* Note this may cause RPC to be resent */
         wdata->header->mds_ops->rpc_call_done(task, data);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a1965329a12c..42da6af77587 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -539,7 +539,7 @@ static int nfs40_sequence_done(struct rpc_task *task,
         struct nfs4_slot *slot = res->sr_slot;
         struct nfs4_slot_table *tbl;
 
-        if (!RPC_WAS_SENT(task))
+        if (slot == NULL)
                 goto out;
 
         tbl = slot->table;
@@ -559,15 +559,10 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 {
         struct nfs4_session *session;
         struct nfs4_slot_table *tbl;
+        struct nfs4_slot *slot = res->sr_slot;
         bool send_new_highest_used_slotid = false;
 
-        if (!res->sr_slot) {
-                /* just wake up the next guy waiting since
-                 * we may have not consumed a slot after all */
-                dprintk("%s: No slot\n", __func__);
-                return;
-        }
-        tbl = res->sr_slot->table;
+        tbl = slot->table;
         session = tbl->session;
 
         spin_lock(&tbl->slot_tbl_lock);
@@ -577,11 +572,11 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
         if (tbl->highest_used_slotid > tbl->target_highest_slotid)
                 send_new_highest_used_slotid = true;
 
-        if (nfs41_wake_and_assign_slot(tbl, res->sr_slot)) {
+        if (nfs41_wake_and_assign_slot(tbl, slot)) {
                 send_new_highest_used_slotid = false;
                 goto out_unlock;
         }
-        nfs4_free_slot(tbl, res->sr_slot);
+        nfs4_free_slot(tbl, slot);
 
         if (tbl->highest_used_slotid != NFS4_NO_SLOT)
                 send_new_highest_used_slotid = false;
@@ -592,19 +587,20 @@ out_unlock:
                 nfs41_server_notify_highest_slotid_update(session->clp);
 }
 
-static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
         struct nfs4_session *session;
-        struct nfs4_slot *slot;
+        struct nfs4_slot *slot = res->sr_slot;
         struct nfs_client *clp;
         bool interrupted = false;
         int ret = 1;
 
+        if (slot == NULL)
+                goto out_noaction;
         /* don't increment the sequence number if the task wasn't sent */
         if (!RPC_WAS_SENT(task))
                 goto out;
 
-        slot = res->sr_slot;
         session = slot->table->session;
 
         if (slot->interrupted) {
@@ -679,6 +675,7 @@ out:
         /* The session may be reset by one of the error handlers. */
         dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
         nfs41_sequence_free_slot(res);
+out_noaction:
         return ret;
 retry_nowait:
         if (rpc_restart_call_prepare(task)) {
@@ -692,6 +689,7 @@ out_retry:
         rpc_delay(task, NFS4_POLL_RETRY_MAX);
         return 0;
 }
+EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
 static int nfs4_sequence_done(struct rpc_task *task,
                                struct nfs4_sequence_res *res)
@@ -2744,7 +2742,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
                                 NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
                                 NFS_CAP_CTIME|NFS_CAP_MTIME|
                                 NFS_CAP_SECURITY_LABEL);
-                if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
+                if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
+                                res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
                         server->caps |= NFS_CAP_ACLS;
                 if (res.has_links != 0)
                         server->caps |= NFS_CAP_HARDLINKS;
@@ -4321,9 +4320,7 @@ static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
 
 static inline int nfs4_server_supports_acls(struct nfs_server *server)
 {
-        return (server->caps & NFS_CAP_ACLS)
-                && (server->acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
-                && (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL);
+        return server->caps & NFS_CAP_ACLS;
 }
 
 /* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8c21d69a9dc1..72f3bf1754ef 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3449,7 +3449,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
 {
         __be32 *p;
 
-        *res = ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL;
+        *res = 0;
         if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 89fe741e58b1..59f838cdc009 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,6 +36,7 @@
         __print_flags(v, "|", \
                         { 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
                         { 1 << NFS_INO_STALE, "STALE" }, \
+                        { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
                         { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
                         { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
                         { 1 << NFS_INO_COMMIT, "COMMIT" }, \
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index a44a87268a6e..9a3b6a4cd6b9 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -909,9 +909,14 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
  */
 static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 {
+        struct nfs_inode *nfsi = NFS_I(inode);
+
         if (nfs_have_delegated_attributes(inode))
                 goto out;
-        if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+        if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+                return false;
+        smp_rmb();
+        if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
                 return false;
 out:
         return PageUptodate(page) != 0;