Merge tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Features:

   - Switch NFS to use readahead instead of the obsolete readpages.

   - Readdir fixes to improve cacheability of large directories when
     there are multiple readers and writers.

   - Readdir performance improvements when doing a seekdir() immediately
     after opening the directory (common when re-exporting NFS).

   - NFS swap improvements from Neil Brown.

   - Loosen up memory allocation to permit direct reclaim and write back
     in cases where there is no danger of deadlocking the writeback code
     or NFS swap.

   - Avoid sillyrename when the NFSv4 server claims to support the
     necessary features to recover the unlinked but open file after
     reboot.

  Bugfixes:

   - Patch from Olga to add a mount option to control NFSv4.1 session
     trunking discovery, and default it to being off.

   - Fix a lockup in nfs_do_recoalesce().

   - Two fixes for list iterator variables being used when pointing to
     the list head.

   - Fix a kernel memory scribble when reading from a non-socket
     transport in /sys/kernel/sunrpc.

   - Fix a race where reconnecting to a server could leave the TCP
     socket stuck forever in the connecting state.

   - Patch from Neil to fix a shutdown race which can leave the SUNRPC
     transport timer primed after we free the struct xprt itself.

   - Patch from Xin Xiong to fix reference count leaks in the NFSv4.2
     copy offload.

   - Sunrpc patch from Olga to avoid resending a task on an offlined
     transport.

  Cleanups:

   - Patches from Dave Wysochanski to clean up the fscache code"

* tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (91 commits)
  NFSv4/pNFS: Fix another issue with a list iterator pointing to the head
  NFS: Don't loop forever in nfs_do_recoalesce()
  SUNRPC: Don't return error values in sysfs read of closed files
  SUNRPC: Do not dereference non-socket transports in sysfs
  NFSv4.1: don't retry BIND_CONN_TO_SESSION on session error
  SUNRPC don't resend a task on an offlined transport
  NFS: replace usage of found with dedicated list iterator variable
  SUNRPC: avoid race between mod_timer() and del_timer_sync()
  pNFS/files: Ensure pNFS allocation modes are consistent with nfsiod
  pNFS/flexfiles: Ensure pNFS allocation modes are consistent with nfsiod
  NFSv4/pnfs: Ensure pNFS allocation modes are consistent with nfsiod
  NFS: Avoid writeback threads getting stuck in mempool_alloc()
  NFS: nfsiod should not block forever in mempool_alloc()
  SUNRPC: Make the rpciod and xprtiod slab allocation modes consistent
  SUNRPC: Fix unx_lookup_cred() allocation
  NFS: Fix memory allocation in rpc_alloc_task()
  NFS: Fix memory allocation in rpc_malloc()
  SUNRPC: Improve accuracy of socket ENOBUFS determination
  SUNRPC: Replace internal use of SOCKWQ_ASYNC_NOSPACE
  SUNRPC: Fix socket waits for write buffer space
  ...

1 files changed, 49 insertions, 10 deletions

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 02a899e4390f..9e1c987c81e7 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -49,6 +49,7 @@
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
+#include <linux/sched/mm.h>
 
 #include <linux/sunrpc/clnt.h>
 
@@ -666,7 +667,7 @@ nfs4_alloc_open_state(void)
 {
 	struct nfs4_state *state;
 
-	state = kzalloc(sizeof(*state), GFP_NOFS);
+	state = kzalloc(sizeof(*state), GFP_KERNEL_ACCOUNT);
 	if (!state)
 		return NULL;
 	refcount_set(&state->count, 1);
@@ -820,7 +821,7 @@ static void __nfs4_close(struct nfs4_state *state,
 
 void nfs4_close_state(struct nfs4_state *state, fmode_t fmode)
 {
-	__nfs4_close(state, fmode, GFP_NOFS, 0);
+	__nfs4_close(state, fmode, GFP_KERNEL, 0);
 }
 
 void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
@@ -869,14 +870,15 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = state->owner->so_server;
 
-	lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
+	lsp = kzalloc(sizeof(*lsp), GFP_KERNEL_ACCOUNT);
 	if (lsp == NULL)
 		return NULL;
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
 	refcount_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
 	lsp->ls_owner = fl_owner;
-	lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
+	lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id,
+						0, 0, GFP_KERNEL_ACCOUNT);
 	if (lsp->ls_seqid.owner_id < 0)
 		goto out_free;
 	INIT_LIST_HEAD(&lsp->ls_locks);
@@ -1205,10 +1207,17 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 {
 	struct task_struct *task;
 	char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
+	struct rpc_clnt *cl = clp->cl_rpcclient;
+
+	while (cl != cl->cl_parent)
+		cl = cl->cl_parent;
 
 	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
-	if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
+	if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) {
+		wake_up_var(&clp->cl_state);
 		return;
+	}
+	set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
 	__module_get(THIS_MODULE);
 	refcount_inc(&clp->cl_count);
 
@@ -1224,6 +1233,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 		printk(KERN_ERR "%s: kthread_run: %ld\n",
 			__func__, PTR_ERR(task));
 		nfs4_clear_state_manager_bit(clp);
+		clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
 		nfs_put_client(clp);
 		module_put(THIS_MODULE);
 	}
@@ -2560,9 +2570,17 @@ static void nfs4_layoutreturn_any_run(struct nfs_client *clp)
 
 static void nfs4_state_manager(struct nfs_client *clp)
 {
+	unsigned int memflags;
 	int status = 0;
 	const char *section = "", *section_sep = "";
 
+	/*
+	 * State recovery can deadlock if the direct reclaim code tries
+	 * start NFS writeback. So ensure memory allocations are all
+	 * GFP_NOFS.
+	 */
+	memflags = memalloc_nofs_save();
+
 	/* Ensure exclusive access to NFSv4 state */
 	do {
 		trace_nfs4_state_mgr(clp);
@@ -2657,6 +2675,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
 		}
 
+		memalloc_nofs_restore(memflags);
 		nfs4_end_drain_session(clp);
 		nfs4_clear_state_manager_bit(clp);
 
@@ -2669,11 +2688,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			clear_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state);
 		}
 
-		/* Did we race with an attempt to give us more work? */
-		if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
-			return;
-		if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
-			return;
+		return;
+
 	} while (refcount_read(&clp->cl_count) > 1 && !signalled());
 	goto out_drain;
 
@@ -2686,6 +2702,7 @@ out_error:
 			clp->cl_hostname, -status);
 	ssleep(1);
 out_drain:
+	memalloc_nofs_restore(memflags);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }
@@ -2693,9 +2710,31 @@ out_drain:
 static int nfs4_run_state_manager(void *ptr)
 {
 	struct nfs_client *clp = ptr;
+	struct rpc_clnt *cl = clp->cl_rpcclient;
+
+	while (cl != cl->cl_parent)
+		cl = cl->cl_parent;
 
 	allow_signal(SIGKILL);
+again:
+	set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
 	nfs4_state_manager(clp);
+	if (atomic_read(&cl->cl_swapper)) {
+		wait_var_event_interruptible(&clp->cl_state,
+					     test_bit(NFS4CLNT_RUN_MANAGER,
+						      &clp->cl_state));
+		if (atomic_read(&cl->cl_swapper) &&
+		    test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
+			goto again;
+		/* Either no longer a swapper, or were signalled */
+	}
+	clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+
+	if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
+	    test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
+	    !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state))
+		goto again;
+
 	nfs_put_client(clp);
 	return 0;
 }