From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp

---
 kernel/fs/nfs/nfs4state.c |  584 ++++++++++++++++++++++++++++++++--------------------------
 1 files changed, 322 insertions(+), 262 deletions(-)

diff --git a/kernel/fs/nfs/nfs4state.c b/kernel/fs/nfs/nfs4state.c
index 184b549..a77a3d8 100644
--- a/kernel/fs/nfs/nfs4state.c
+++ b/kernel/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>
 
@@ -60,6 +61,7 @@
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_STATE
 
@@ -87,7 +89,26 @@
 
 static DEFINE_MUTEX(nfs_clid_init_mutex);
 
-int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
+static int nfs4_setup_state_renewal(struct nfs_client *clp)
+{
+	int status;
+	struct nfs_fsinfo fsinfo;
+
+	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
+		nfs4_schedule_state_renewal(clp);
+		return 0;
+	}
+
+	status = nfs4_proc_get_lease_time(clp, &fsinfo);
+	if (status == 0) {
+		nfs4_set_lease_period(clp, fsinfo.lease_time * HZ);
+		nfs4_schedule_state_renewal(clp);
+	}
+
+	return status;
+}
+
+int nfs4_init_clientid(struct nfs_client *clp, const struct cred *cred)
 {
 	struct nfs4_setclientid_res clid = {
 		.clientid = clp->cl_clientid,
@@ -114,7 +135,7 @@
 	if (status != 0)
 		goto out;
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-	nfs4_schedule_state_renewal(clp);
+	nfs4_setup_state_renewal(clp);
 out:
 	return status;
 }
@@ -134,7 +155,7 @@
  */
 int nfs40_discover_server_trunking(struct nfs_client *clp,
 				   struct nfs_client **result,
-				   struct rpc_cred *cred)
+				   const struct cred *cred)
 {
 	struct nfs4_setclientid_res clid = {
 		.clientid = clp->cl_clientid,
@@ -168,32 +189,23 @@
 	return status;
 }
 
-struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
+const struct cred *nfs4_get_machine_cred(struct nfs_client *clp)
 {
-	struct rpc_cred *cred = NULL;
-
-	if (clp->cl_machine_cred != NULL)
-		cred = get_rpccred(clp->cl_machine_cred);
-	return cred;
+	return get_cred(rpc_machine_cred());
 }
 
 static void nfs4_root_machine_cred(struct nfs_client *clp)
 {
-	struct rpc_cred *cred, *new;
 
-	new = rpc_lookup_machine_cred(NULL);
-	spin_lock(&clp->cl_lock);
-	cred = clp->cl_machine_cred;
-	clp->cl_machine_cred = new;
-	spin_unlock(&clp->cl_lock);
-	if (cred != NULL)
-		put_rpccred(cred);
+	/* Force root creds instead of machine */
+	clp->cl_principal = NULL;
+	clp->cl_rpcclient->cl_principal = NULL;
 }
 
-static struct rpc_cred *
+static const struct cred *
 nfs4_get_renew_cred_server_locked(struct nfs_server *server)
 {
-	struct rpc_cred *cred = NULL;
+	const struct cred *cred = NULL;
 	struct nfs4_state_owner *sp;
 	struct rb_node *pos;
 
@@ -203,29 +215,30 @@
 		sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
 		if (list_empty(&sp->so_states))
 			continue;
-		cred = get_rpccred(sp->so_cred);
+		cred = get_cred(sp->so_cred);
 		break;
 	}
 	return cred;
 }
 
 /**
- * nfs4_get_renew_cred_locked - Acquire credential for a renew operation
+ * nfs4_get_renew_cred - Acquire credential for a renew operation
  * @clp: client state handle
  *
  * Returns an rpc_cred with reference count bumped, or NULL.
  * Caller must hold clp->cl_lock.
  */
-struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
+const struct cred *nfs4_get_renew_cred(struct nfs_client *clp)
 {
-	struct rpc_cred *cred = NULL;
+	const struct cred *cred = NULL;
 	struct nfs_server *server;
 
 	/* Use machine credentials if available */
-	cred = nfs4_get_machine_cred_locked(clp);
+	cred = nfs4_get_machine_cred(clp);
 	if (cred != NULL)
 		goto out;
 
+	spin_lock(&clp->cl_lock);
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		cred = nfs4_get_renew_cred_server_locked(server);
@@ -233,6 +246,7 @@
 			break;
 	}
 	rcu_read_unlock();
+	spin_unlock(&clp->cl_lock);
 
 out:
 	return cred;
@@ -293,37 +307,16 @@
 
 #if defined(CONFIG_NFS_V4_1)
 
-static int nfs41_setup_state_renewal(struct nfs_client *clp)
-{
-	int status;
-	struct nfs_fsinfo fsinfo;
-	unsigned long now;
-
-	if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
-		nfs4_schedule_state_renewal(clp);
-		return 0;
-	}
-
-	now = jiffies;
-	status = nfs4_proc_get_lease_time(clp, &fsinfo);
-	if (status == 0) {
-		nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
-		nfs4_schedule_state_renewal(clp);
-	}
-
-	return status;
-}
-
 static void nfs41_finish_session_reset(struct nfs_client *clp)
 {
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 	clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 	/* create_session negotiated new slot table */
 	clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
-	nfs41_setup_state_renewal(clp);
+	nfs4_setup_state_renewal(clp);
 }
 
-int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs41_init_clientid(struct nfs_client *clp, const struct cred *cred)
 {
 	int status;
 
@@ -358,7 +351,7 @@
  */
 int nfs41_discover_server_trunking(struct nfs_client *clp,
 				   struct nfs_client **result,
-				   struct rpc_cred *cred)
+				   const struct cred *cred)
 {
 	int status;
 
@@ -396,32 +389,32 @@
  * nfs4_get_clid_cred - Acquire credential for a setclientid operation
  * @clp: client state handle
  *
- * Returns an rpc_cred with reference count bumped, or NULL.
+ * Returns a cred with reference count bumped, or NULL.
  */
-struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp)
+const struct cred *nfs4_get_clid_cred(struct nfs_client *clp)
 {
-	struct rpc_cred *cred;
+	const struct cred *cred;
 
-	spin_lock(&clp->cl_lock);
-	cred = nfs4_get_machine_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
+	cred = nfs4_get_machine_cred(clp);
 	return cred;
 }
 
 static struct nfs4_state_owner *
-nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
+nfs4_find_state_owner_locked(struct nfs_server *server, const struct cred *cred)
 {
 	struct rb_node **p = &server->state_owners.rb_node,
 		       *parent = NULL;
 	struct nfs4_state_owner *sp;
+	int cmp;
 
 	while (*p != NULL) {
 		parent = *p;
 		sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
+		cmp = cred_fscmp(cred, sp->so_cred);
 
-		if (cred < sp->so_cred)
+		if (cmp < 0)
 			p = &parent->rb_left;
-		else if (cred > sp->so_cred)
+		else if (cmp > 0)
 			p = &parent->rb_right;
 		else {
 			if (!list_empty(&sp->so_lru))
@@ -440,14 +433,16 @@
 	struct rb_node **p = &server->state_owners.rb_node,
 		       *parent = NULL;
 	struct nfs4_state_owner *sp;
+	int cmp;
 
 	while (*p != NULL) {
 		parent = *p;
 		sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
+		cmp = cred_fscmp(new->so_cred, sp->so_cred);
 
-		if (new->so_cred < sp->so_cred)
+		if (cmp < 0)
 			p = &parent->rb_left;
-		else if (new->so_cred > sp->so_cred)
+		else if (cmp > 0)
 			p = &parent->rb_right;
 		else {
 			if (!list_empty(&sp->so_lru))
@@ -494,7 +489,7 @@
  */
 static struct nfs4_state_owner *
 nfs4_alloc_state_owner(struct nfs_server *server,
-		struct rpc_cred *cred,
+		const struct cred *cred,
 		gfp_t gfp_flags)
 {
 	struct nfs4_state_owner *sp;
@@ -509,13 +504,13 @@
 		return NULL;
 	}
 	sp->so_server = server;
-	sp->so_cred = get_rpccred(cred);
+	sp->so_cred = get_cred(cred);
 	spin_lock_init(&sp->so_lock);
 	INIT_LIST_HEAD(&sp->so_states);
 	nfs4_init_seqid_counter(&sp->so_seqid);
 	atomic_set(&sp->so_count, 1);
 	INIT_LIST_HEAD(&sp->so_lru);
-	seqlock_init(&sp->so_reclaim_seqlock);
+	seqcount_spinlock_init(&sp->so_reclaim_seqcount, &sp->so_lock);
 	mutex_init(&sp->so_delegreturn_mutex);
 	return sp;
 }
@@ -538,7 +533,7 @@
 static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
 {
 	nfs4_destroy_seqid_counter(&sp->so_seqid);
-	put_rpccred(sp->so_cred);
+	put_cred(sp->so_cred);
 	ida_simple_remove(&sp->so_server->openowner_id, sp->so_seqid.owner_id);
 	kfree(sp);
 }
@@ -572,11 +567,12 @@
  * nfs4_get_state_owner - Look up a state owner given a credential
  * @server: nfs_server to search
  * @cred: RPC credential to match
+ * @gfp_flags: allocation mode
  *
  * Returns a pointer to an instantiated nfs4_state_owner struct, or NULL.
  */
 struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
-					      struct rpc_cred *cred,
+					      const struct cred *cred,
 					      gfp_t gfp_flags)
 {
 	struct nfs_client *clp = server->nfs_client;
@@ -674,7 +670,7 @@
 	state = kzalloc(sizeof(*state), GFP_NOFS);
 	if (!state)
 		return NULL;
-	atomic_set(&state->count, 1);
+	refcount_set(&state->count, 1);
 	INIT_LIST_HEAD(&state->lock_states);
 	spin_lock_init(&state->state_lock);
 	seqlock_init(&state->seqlock);
@@ -703,12 +699,12 @@
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_state *state;
 
-	list_for_each_entry(state, &nfsi->open_states, inode_states) {
+	list_for_each_entry_rcu(state, &nfsi->open_states, inode_states) {
 		if (state->owner != owner)
 			continue;
 		if (!nfs4_valid_open_stateid(state))
 			continue;
-		if (atomic_inc_not_zero(&state->count))
+		if (refcount_inc_not_zero(&state->count))
 			return state;
 	}
 	return NULL;
@@ -717,7 +713,7 @@
 static void
 nfs4_free_open_state(struct nfs4_state *state)
 {
-	kfree(state);
+	kfree_rcu(state, rcu_head);
 }
 
 struct nfs4_state *
@@ -726,9 +722,9 @@
 	struct nfs4_state *state, *new;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	spin_lock(&inode->i_lock);
+	rcu_read_lock();
 	state = __nfs4_find_state_byowner(inode, owner);
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	if (state)
 		goto out;
 	new = nfs4_alloc_open_state();
@@ -739,9 +735,9 @@
 		state = new;
 		state->owner = owner;
 		atomic_inc(&owner->so_count);
-		list_add(&state->inode_states, &nfsi->open_states);
 		ihold(inode);
 		state->inode = inode;
+		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		spin_unlock(&inode->i_lock);
 		/* Note: The reclaim code dictates that we add stateless
 		 * and read-only stateids to the end of the list */
@@ -762,13 +758,14 @@
 	struct inode *inode = state->inode;
 	struct nfs4_state_owner *owner = state->owner;
 
-	if (!atomic_dec_and_lock(&state->count, &owner->so_lock))
+	if (!refcount_dec_and_lock(&state->count, &owner->so_lock))
 		return;
 	spin_lock(&inode->i_lock);
-	list_del(&state->inode_states);
+	list_del_rcu(&state->inode_states);
 	list_del(&state->open_states);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&owner->so_lock);
+	nfs4_inode_return_delegation_on_close(inode);
 	iput(inode);
 	nfs4_free_open_state(state);
 	nfs4_put_state_owner(owner);
@@ -1019,22 +1016,6 @@
 	return ret;
 }
 
-bool nfs4_refresh_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
-{
-	bool ret;
-	int seq;
-
-	do {
-		ret = false;
-		seq = read_seqbegin(&state->seqlock);
-		if (nfs4_state_match_open_stateid_other(state, dst)) {
-			dst->seqid = state->open_stateid.seqid;
-			ret = true;
-		}
-	} while (read_seqretry(&state->seqlock, seq));
-	return ret;
-}
-
 bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 {
 	bool ret;
@@ -1060,7 +1041,7 @@
  */
 int nfs4_select_rw_stateid(struct nfs4_state *state,
 		fmode_t fmode, const struct nfs_lock_context *l_ctx,
-		nfs4_stateid *dst, struct rpc_cred **cred)
+		nfs4_stateid *dst, const struct cred **cred)
 {
 	int ret;
 
@@ -1083,8 +1064,7 @@
 		 * choose to use.
 		 */
 		goto out;
-	nfs4_copy_open_stateid(dst, state);
-	ret = 0;
+	ret = nfs4_copy_open_stateid(dst, state) ? 0 : -EAGAIN;
 out:
 	if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
 		dst->seqid = 0;
@@ -1155,7 +1135,7 @@
 		case -NFS4ERR_MOVED:
 			/* Non-seqid mutating errors */
 			return;
-	};
+	}
 	/*
 	 * Note: no locking needed as we are guaranteed to be first
 	 * on the sequence list
@@ -1428,7 +1408,7 @@
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
 		if (!test_bit(NFS_LOCK_INITIALIZED, &pos->ls_flags))
 			continue;
-		if (nfs4_stateid_match_other(&pos->ls_stateid, stateid))
+		if (nfs4_stateid_match_or_older(&pos->ls_stateid, stateid))
 			return pos;
 	}
 	return NULL;
@@ -1457,17 +1437,18 @@
 	struct nfs4_state *state;
 	bool found = false;
 
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		state = ctx->state;
 		if (state == NULL)
 			continue;
-		if (nfs4_stateid_match_other(&state->stateid, stateid) &&
+		if (nfs4_stateid_match_or_older(&state->stateid, stateid) &&
 		    nfs4_state_mark_reclaim_nograce(clp, state)) {
 			found = true;
 			continue;
 		}
-		if (nfs4_stateid_match_other(&state->open_stateid, stateid) &&
+		if (test_bit(NFS_OPEN_STATE, &state->flags) &&
+		    nfs4_stateid_match_or_older(&state->open_stateid, stateid) &&
 		    nfs4_state_mark_reclaim_nograce(clp, state)) {
 			found = true;
 			continue;
@@ -1476,32 +1457,34 @@
 		    nfs4_state_mark_reclaim_nograce(clp, state))
 			found = true;
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 
 	nfs_inode_find_delegation_state_and_recover(inode, stateid);
 	if (found)
 		nfs4_schedule_state_manager(clp);
 }
 
-static void nfs4_state_mark_open_context_bad(struct nfs4_state *state)
+static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err)
 {
 	struct inode *inode = state->inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
 
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		if (ctx->state != state)
 			continue;
 		set_bit(NFS_CONTEXT_BAD, &ctx->flags);
+		pr_warn("NFSv4: state recovery failed for open file %pd2, "
+				"error = %d\n", ctx->dentry, err);
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 }
 
 static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error)
 {
 	set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags);
-	nfs4_state_mark_open_context_bad(state);
+	nfs4_state_mark_open_context_bad(state, error);
 }
 
 
@@ -1532,6 +1515,7 @@
 		switch (status) {
 		case 0:
 			break;
+		case -ETIMEDOUT:
 		case -ESTALE:
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
@@ -1547,7 +1531,7 @@
 		default:
 			pr_err("NFS: %s: unhandled error %d\n",
 					__func__, status);
-			/* Fall through */
+			fallthrough;
 		case -ENOMEM:
 		case -NFS4ERR_DENIED:
 		case -NFS4ERR_RECLAIM_BAD:
@@ -1569,11 +1553,84 @@
 	return status;
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	struct nfs4_copy_state *copy;
+
+	if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+		!test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags))
+		return;
+
+	spin_lock(&sp->so_server->nfs_client->cl_lock);
+	list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
+		if ((test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) &&
+				!nfs4_stateid_match_other(&state->stateid,
+				&copy->parent_dst_state->stateid)))
+				continue;
+		copy->flags = 1;
+		if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+				&state->flags)) {
+			clear_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags);
+			complete(&copy->completion);
+		}
+	}
+	list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) {
+		if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) &&
+				!nfs4_stateid_match_other(&state->stateid,
+				&copy->parent_src_state->stateid)))
+				continue;
+		copy->flags = 1;
+		if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE,
+				&state->flags))
+			complete(&copy->completion);
+	}
+	spin_unlock(&sp->so_server->nfs_client->cl_lock);
+}
+#else /* !CONFIG_NFS_V4_2 */
+static inline void nfs42_complete_copies(struct nfs4_state_owner *sp,
+					 struct nfs4_state *state)
+{
+}
+#endif /* CONFIG_NFS_V4_2 */
+
+static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state,
+				     const struct nfs4_state_recovery_ops *ops)
+{
+	struct nfs4_lock_state *lock;
+	int status;
+
+	status = ops->recover_open(sp, state);
+	if (status < 0)
+		return status;
+
+	status = nfs4_reclaim_locks(state, ops);
+	if (status < 0)
+		return status;
+
+	if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
+		spin_lock(&state->state_lock);
+		list_for_each_entry(lock, &state->lock_states, ls_locks) {
+			trace_nfs4_state_lock_reclaim(state, lock);
+			if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
+				pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
+		}
+		spin_unlock(&state->state_lock);
+	}
+
+	nfs42_complete_copies(sp, state);
+	clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
+	return status;
+}
+
 static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
 {
 	struct nfs4_state *state;
-	struct nfs4_lock_state *lock;
+	unsigned int loop = 0;
 	int status = 0;
+#ifdef CONFIG_NFS_V4_2
+	bool found_ssc_copy_state = false;
+#endif /* CONFIG_NFS_V4_2 */
 
 	/* Note: we rely on the sp->so_states list being ordered 
 	 * so that we always reclaim open(O_RDWR) and/or open(O_WRITE)
@@ -1583,12 +1640,8 @@
 	 * recovering after a network partition or a reboot from a
 	 * server that doesn't support a grace period.
 	 */
-#ifdef CONFIG_PREEMPT_RT_FULL
-	write_seqlock(&sp->so_reclaim_seqlock);
-#else
-	write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
-#endif
 	spin_lock(&sp->so_lock);
+	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1597,98 +1650,77 @@
 			continue;
 		if (state->state == 0)
 			continue;
-		atomic_inc(&state->count);
-		spin_unlock(&sp->so_lock);
-		status = ops->recover_open(sp, state);
-		if (status >= 0) {
-			status = nfs4_reclaim_locks(state, ops);
-			if (status >= 0) {
-				if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
-					spin_lock(&state->state_lock);
-					list_for_each_entry(lock, &state->lock_states, ls_locks) {
-						if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
-							pr_warn_ratelimited("NFS: "
-									    "%s: Lock reclaim "
-									    "failed!\n", __func__);
-					}
-					spin_unlock(&state->state_lock);
-				}
-				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
-					&state->flags);
 #ifdef CONFIG_NFS_V4_2
-				if (test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) {
-					struct nfs4_copy_state *copy;
-
-					spin_lock(&sp->so_server->nfs_client->cl_lock);
-					list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
-						if (memcmp(&state->stateid.other, &copy->parent_state->stateid.other, NFS4_STATEID_SIZE))
-							continue;
-						copy->flags = 1;
-						complete(&copy->completion);
-						printk("AGLO: server rebooted waking up the copy\n");
-						break;
-					}
-					spin_unlock(&sp->so_server->nfs_client->cl_lock);
-				}
-#endif /* CONFIG_NFS_V4_2 */
-				nfs4_put_open_state(state);
-				spin_lock(&sp->so_lock);
-				goto restart;
-			}
+		if (test_bit(NFS_SRV_SSC_COPY_STATE, &state->flags)) {
+			nfs4_state_mark_recovery_failed(state, -EIO);
+			found_ssc_copy_state = true;
+			continue;
 		}
+#endif /* CONFIG_NFS_V4_2 */
+		refcount_inc(&state->count);
+		spin_unlock(&sp->so_lock);
+		status = __nfs4_reclaim_open_state(sp, state, ops);
+
 		switch (status) {
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
-					__func__, status);
-				/* Fall through */
-			case -ENOENT:
-			case -ENOMEM:
-			case -EACCES:
-			case -EROFS:
-			case -EIO:
-			case -ESTALE:
-				/* Open state on this file cannot be recovered */
-				nfs4_state_mark_recovery_failed(state, status);
+		default:
+			if (status >= 0) {
+				loop = 0;
 				break;
-			case -EAGAIN:
-				ssleep(1);
-				/* Fall through */
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_OLD_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+			}
+			printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
+			fallthrough;
+		case -ENOENT:
+		case -ENOMEM:
+		case -EACCES:
+		case -EROFS:
+		case -EIO:
+		case -ESTALE:
+			/* Open state on this file cannot be recovered */
+			nfs4_state_mark_recovery_failed(state, status);
+			break;
+		case -EAGAIN:
+			ssleep(1);
+			if (loop++ < 10) {
+				set_bit(ops->state_flag_bit, &state->flags);
 				break;
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out_err;
+			}
+			fallthrough;
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_STALE_STATEID:
+		case -NFS4ERR_OLD_STATEID:
+		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_RECLAIM_BAD:
+		case -NFS4ERR_RECLAIM_CONFLICT:
+			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+			break;
+		case -NFS4ERR_EXPIRED:
+		case -NFS4ERR_NO_GRACE:
+			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+			fallthrough;
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		case -ETIMEDOUT:
+			goto out_err;
 		}
 		nfs4_put_open_state(state);
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
-#ifdef CONFIG_PREEMPT_RT_FULL
-	write_sequnlock(&sp->so_reclaim_seqlock);
-#else
-	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
-#endif
+#ifdef CONFIG_NFS_V4_2
+	if (found_ssc_copy_state)
+		return -EIO;
+#endif /* CONFIG_NFS_V4_2 */
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
-#ifdef CONFIG_PREEMPT_RT_FULL
-	write_sequnlock(&sp->so_reclaim_seqlock);
-#else
-	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
-#endif
+	spin_lock(&sp->so_lock);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
+	spin_unlock(&sp->so_lock);
 	return status;
 }
 
@@ -1745,6 +1777,7 @@
 
 static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
 {
+	set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
 	/* Mark all delegations for reclaim */
 	nfs_delegation_mark_reclaim(clp);
 	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
@@ -1752,7 +1785,7 @@
 
 static int nfs4_reclaim_complete(struct nfs_client *clp,
 				 const struct nfs4_state_recovery_ops *ops,
-				 struct rpc_cred *cred)
+				 const struct cred *cred)
 {
 	/* Notify the server we're done reclaiming our state */
 	if (ops->reclaim_complete)
@@ -1803,7 +1836,7 @@
 static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 {
 	const struct nfs4_state_recovery_ops *ops;
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	int err;
 
 	if (!nfs4_state_clear_reclaim_reboot(clp))
@@ -1811,7 +1844,7 @@
 	ops = clp->cl_mvops->reboot_recovery_ops;
 	cred = nfs4_get_clid_cred(clp);
 	err = nfs4_reclaim_complete(clp, ops, cred);
-	put_rpccred(cred);
+	put_cred(cred);
 	if (err == -NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
 		set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
 }
@@ -1825,38 +1858,38 @@
 static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 {
 	switch (error) {
-		case 0:
-			break;
-		case -NFS4ERR_CB_PATH_DOWN:
-			nfs40_handle_cb_pathdown(clp);
-			break;
-		case -NFS4ERR_NO_GRACE:
-			nfs4_state_end_reclaim_reboot(clp);
-			break;
-		case -NFS4ERR_STALE_CLIENTID:
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_start_reclaim_reboot(clp);
-			break;
-		case -NFS4ERR_EXPIRED:
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_start_reclaim_nograce(clp);
-			break;
-		case -NFS4ERR_BADSESSION:
-		case -NFS4ERR_BADSLOT:
-		case -NFS4ERR_BAD_HIGH_SLOT:
-		case -NFS4ERR_DEADSESSION:
-		case -NFS4ERR_SEQ_FALSE_RETRY:
-		case -NFS4ERR_SEQ_MISORDERED:
-			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
-			/* Zero session reset errors */
-			break;
-		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-			set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
-			break;
-		default:
-			dprintk("%s: failed to handle error %d for server %s\n",
-					__func__, error, clp->cl_hostname);
-			return error;
+	case 0:
+		break;
+	case -NFS4ERR_CB_PATH_DOWN:
+		nfs40_handle_cb_pathdown(clp);
+		break;
+	case -NFS4ERR_NO_GRACE:
+		nfs4_state_end_reclaim_reboot(clp);
+		break;
+	case -NFS4ERR_STALE_CLIENTID:
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		nfs4_state_start_reclaim_reboot(clp);
+		break;
+	case -NFS4ERR_EXPIRED:
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		nfs4_state_start_reclaim_nograce(clp);
+		break;
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_BADSLOT:
+	case -NFS4ERR_BAD_HIGH_SLOT:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+	case -NFS4ERR_SEQ_MISORDERED:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		/* Zero session reset errors */
+		break;
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+		break;
+	default:
+		dprintk("%s: failed to handle error %d for server %s\n",
+				__func__, error, clp->cl_hostname);
+		return error;
 	}
 	dprintk("%s: handled error %d for server %s\n", __func__, error,
 			clp->cl_hostname);
@@ -1909,7 +1942,7 @@
 
 static int nfs4_check_lease(struct nfs_client *clp)
 {
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	const struct nfs4_state_maintenance_ops *ops =
 		clp->cl_mvops->state_renewal_ops;
 	int status;
@@ -1917,9 +1950,7 @@
 	/* Is the client already known to have an expired lease? */
 	if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 		return 0;
-	spin_lock(&clp->cl_lock);
-	cred = ops->get_state_renewal_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred(clp);
 	if (cred == NULL) {
 		cred = nfs4_get_clid_cred(clp);
 		status = -ENOKEY;
@@ -1927,7 +1958,7 @@
 			goto out;
 	}
 	status = ops->renew_lease(clp, cred);
-	put_rpccred(cred);
+	put_cred(cred);
 	if (status == -ETIMEDOUT) {
 		set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
 		return 0;
@@ -1961,7 +1992,6 @@
 		return -EPERM;
 	case -EACCES:
 	case -NFS4ERR_DELAY:
-	case -ETIMEDOUT:
 	case -EAGAIN:
 		ssleep(1);
 		break;
@@ -1987,7 +2017,7 @@
 
 static int nfs4_establish_lease(struct nfs_client *clp)
 {
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	const struct nfs4_state_recovery_ops *ops =
 		clp->cl_mvops->reboot_recovery_ops;
 	int status;
@@ -1999,7 +2029,7 @@
 	if (cred == NULL)
 		return -ENOENT;
 	status = ops->establish_clid(clp, cred);
-	put_rpccred(cred);
+	put_cred(cred);
 	if (status != 0)
 		return status;
 	pnfs_destroy_all_layouts(clp);
@@ -2046,7 +2076,7 @@
  *
  * Returns zero or a negative NFS4ERR status code.
  */
-static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred)
+static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_fs_locations *locations = NULL;
@@ -2086,8 +2116,10 @@
 	}
 
 	status = nfs4_begin_drain_session(clp);
-	if (status != 0)
-		return status;
+	if (status != 0) {
+		result = status;
+		goto out;
+	}
 
 	status = nfs4_replace_transport(server, locations);
 	if (status != 0) {
@@ -2119,14 +2151,12 @@
 	const struct nfs4_state_maintenance_ops *ops =
 				clp->cl_mvops->state_renewal_ops;
 	struct nfs_server *server;
-	struct rpc_cred *cred;
+	const struct cred *cred;
 
 	dprintk("%s: migration reported on \"%s\"\n", __func__,
 			clp->cl_hostname);
 
-	spin_lock(&clp->cl_lock);
-	cred = ops->get_state_renewal_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred(clp);
 	if (cred == NULL)
 		return -NFS4ERR_NOENT;
 
@@ -2147,13 +2177,13 @@
 		rcu_read_unlock();
 		status = nfs4_try_migration(server, cred);
 		if (status < 0) {
-			put_rpccred(cred);
+			put_cred(cred);
 			return status;
 		}
 		goto restart;
 	}
 	rcu_read_unlock();
-	put_rpccred(cred);
+	put_cred(cred);
 	return 0;
 }
 
@@ -2167,14 +2197,12 @@
 	const struct nfs4_state_maintenance_ops *ops =
 				clp->cl_mvops->state_renewal_ops;
 	struct nfs_server *server;
-	struct rpc_cred *cred;
+	const struct cred *cred;
 
 	dprintk("%s: lease moved reported on \"%s\"\n", __func__,
 			clp->cl_hostname);
 
-	spin_lock(&clp->cl_lock);
-	cred = ops->get_state_renewal_cred_locked(clp);
-	spin_unlock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred(clp);
 	if (cred == NULL)
 		return -NFS4ERR_NOENT;
 
@@ -2202,7 +2230,7 @@
 	rcu_read_unlock();
 
 out:
-	put_rpccred(cred);
+	put_cred(cred);
 	return 0;
 }
 
@@ -2225,7 +2253,7 @@
 	const struct nfs4_state_recovery_ops *ops =
 				clp->cl_mvops->reboot_recovery_ops;
 	struct rpc_clnt *clnt;
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	int i, status;
 
 	dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
@@ -2241,7 +2269,7 @@
 		goto out_unlock;
 
 	status = ops->detect_trunking(clp, result, cred);
-	put_rpccred(cred);
+	put_cred(cred);
 	switch (status) {
 	case 0:
 	case -EINTR:
@@ -2250,11 +2278,11 @@
 	case -ETIMEDOUT:
 		if (clnt->cl_softrtry)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_DELAY:
 	case -EAGAIN:
 		ssleep(1);
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_STALE_CLIENTID:
 		dprintk("NFS: %s after status %d, retrying\n",
 			__func__, status);
@@ -2266,7 +2294,7 @@
 		}
 		if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_WRONGSEC:
 		/* No point in retrying if we already used RPC_AUTH_UNIX */
@@ -2372,8 +2400,7 @@
 {
 	/* FIXME: For now, we destroy all layouts. */
 	pnfs_destroy_all_layouts(clp);
-	/* FIXME: For now, we test all delegations+open state+locks. */
-	nfs41_handle_some_state_revoked(clp);
+	nfs_test_expired_all_delegations(clp);
 	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
 			clp->cl_hostname);
 }
@@ -2432,7 +2459,7 @@
 
 static int nfs4_reset_session(struct nfs_client *clp)
 {
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	int status;
 
 	if (!nfs4_has_session(clp))
@@ -2470,14 +2497,13 @@
 	dprintk("%s: session reset was successful for server %s!\n",
 			__func__, clp->cl_hostname);
 out:
-	if (cred)
-		put_rpccred(cred);
+	put_cred(cred);
 	return status;
 }
 
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {
-	struct rpc_cred *cred;
+	const struct cred *cred;
 	int ret;
 
 	if (!nfs4_has_session(clp))
@@ -2487,8 +2513,7 @@
 		return ret;
 	cred = nfs4_get_clid_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
-	if (cred)
-		put_rpccred(cred);
+	put_cred(cred);
 	clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
 	switch (ret) {
 	case 0:
@@ -2504,6 +2529,21 @@
 	}
 	return 0;
 }
+
+static void nfs4_layoutreturn_any_run(struct nfs_client *clp)
+{
+	int iomode = 0;
+
+	if (test_and_clear_bit(NFS4CLNT_RECALL_ANY_LAYOUT_READ, &clp->cl_state))
+		iomode += IOMODE_READ;
+	if (test_and_clear_bit(NFS4CLNT_RECALL_ANY_LAYOUT_RW, &clp->cl_state))
+		iomode += IOMODE_RW;
+	/* Note: IOMODE_READ + IOMODE_RW == IOMODE_ANY */
+	if (iomode) {
+		pnfs_layout_return_unused_byclid(clp, iomode);
+		set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
+	}
+}
 #else /* CONFIG_NFS_V4_1 */
 static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
 
@@ -2511,15 +2551,28 @@
 {
 	return 0;
 }
+
+static void nfs4_layoutreturn_any_run(struct nfs_client *clp)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 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);
 		clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
 			section = "purge state";
@@ -2590,6 +2643,7 @@
 			if (status < 0)
 				goto out_error;
 			nfs4_state_end_reclaim_reboot(clp);
+			continue;
 		}
 
 		/* Detect expired delegations... */
@@ -2600,7 +2654,7 @@
 		}
 
 		/* Now recover expired state... */
-		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+		if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
 			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
@@ -2608,17 +2662,20 @@
 				continue;
 			if (status < 0)
 				goto out_error;
+			clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
 		}
 
+		memalloc_nofs_restore(memflags);
 		nfs4_end_drain_session(clp);
 		nfs4_clear_state_manager_bit(clp);
 
-		if (!test_and_set_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state)) {
+		if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) {
 			if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
 				nfs_client_return_marked_delegations(clp);
 				set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
 			}
-			clear_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state);
+			nfs4_layoutreturn_any_run(clp);
+			clear_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state);
 		}
 
 		/* Did we race with an attempt to give us more work? */
@@ -2626,17 +2683,20 @@
 			return;
 		if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 			return;
+		memflags = memalloc_nofs_save();
 	} while (refcount_read(&clp->cl_count) > 1 && !signalled());
 	goto out_drain;
 
 out_error:
 	if (strlen(section))
 		section_sep = ": ";
+	trace_nfs4_state_mgr_failed(clp, section, status);
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
 	ssleep(1);
 out_drain:
+	memalloc_nofs_restore(memflags);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }

--
Gitblit v1.6.2