[LTP] Patch "NFSD: Replace nfsd_prune_bucket()" has been added to the 6.1-stable tree

[<gregkh@linuxfoundation.org>]

This is a note to let you know that I've just added the patch titled

    NFSD: Replace nfsd_prune_bucket()

to the 6.1-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     nfsd-replace-nfsd_prune_bucket.patch
and it can be found in the queue-6.1 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


From stable+bounces-66326-greg=kroah.com@vger.kernel.org Sat Aug 10 22:00:52 2024
From: cel@kernel.org
Date: Sat, 10 Aug 2024 15:59:56 -0400
Subject: NFSD: Replace nfsd_prune_bucket()
To: <stable@vger.kernel.org>
Cc: <linux-nfs@vger.kernel.org>, pvorel@suse.cz, sherry.yang@oracle.com, calum.mackay@oracle.com, kernel-team@fb.com, ltp@lists.linux.it, Chuck Lever <chuck.lever@oracle.com>, Jeff Layton <jlayton@kernel.org>
Message-ID: <20240810200009.9882-6-cel@kernel.org>

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit a9507f6af1450ed26a4a36d979af518f5bb21e5d ]

Enable nfsd_prune_bucket() to drop the bucket lock while calling
kfree(). Use the same pattern that Jeff recently introduced in the
NFSD filecache.

A few percpu operations are moved outside the lock since they
temporarily disable local IRQs which is expensive and does not
need to be done while the lock is held.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Stable-dep-of: c135e1269f34 ("NFSD: Refactor the duplicate reply cache shrinker")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/nfsd/nfscache.c |   78 ++++++++++++++++++++++++++++++++++++++++++-----------
 fs/nfsd/trace.h    |   22 ++++++++++++++
 2 files changed, 85 insertions(+), 15 deletions(-)

--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -117,6 +117,21 @@ static void nfsd_cacherep_free(struct sv
 	kmem_cache_free(drc_slab, rp);
 }
 
+static unsigned long
+nfsd_cacherep_dispose(struct list_head *dispose)
+{
+	struct svc_cacherep *rp;
+	unsigned long freed = 0;
+
+	while (!list_empty(dispose)) {
+		rp = list_first_entry(dispose, struct svc_cacherep, c_lru);
+		list_del(&rp->c_lru);
+		nfsd_cacherep_free(rp);
+		freed++;
+	}
+	return freed;
+}
+
 static void
 nfsd_cacherep_unlink_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
 			    struct svc_cacherep *rp)
@@ -260,6 +275,41 @@ nfsd_cache_bucket_find(__be32 xid, struc
 	return &nn->drc_hashtbl[hash];
 }
 
+/*
+ * Remove and return no more than @max expired entries in bucket @b.
+ * If @max is zero, do not limit the number of removed entries.
+ */
+static void
+nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
+			 unsigned int max, struct list_head *dispose)
+{
+	unsigned long expiry = jiffies - RC_EXPIRE;
+	struct svc_cacherep *rp, *tmp;
+	unsigned int freed = 0;
+
+	lockdep_assert_held(&b->cache_lock);
+
+	/* The bucket LRU is ordered oldest-first. */
+	list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
+		/*
+		 * Don't free entries attached to calls that are still
+		 * in-progress, but do keep scanning the list.
+		 */
+		if (rp->c_state == RC_INPROG)
+			continue;
+
+		if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries &&
+		    time_before(expiry, rp->c_timestamp))
+			break;
+
+		nfsd_cacherep_unlink_locked(nn, b, rp);
+		list_add(&rp->c_lru, dispose);
+
+		if (max && ++freed > max)
+			break;
+	}
+}
+
 static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn,
 			 unsigned int max)
 {
@@ -283,11 +333,6 @@ static long prune_bucket(struct nfsd_drc
 	return freed;
 }
 
-static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
-{
-	return prune_bucket(b, nn, 3);
-}
-
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -466,6 +511,8 @@ int nfsd_cache_lookup(struct svc_rqst *r
 	__wsum			csum;
 	struct nfsd_drc_bucket	*b;
 	int type = rqstp->rq_cachetype;
+	unsigned long freed;
+	LIST_HEAD(dispose);
 	int rtn = RC_DOIT;
 
 	rqstp->rq_cacherep = NULL;
@@ -490,20 +537,18 @@ int nfsd_cache_lookup(struct svc_rqst *r
 	found = nfsd_cache_insert(b, rp, nn);
 	if (found != rp)
 		goto found_entry;
-
-	nfsd_stats_rc_misses_inc();
 	rqstp->rq_cacherep = rp;
 	rp->c_state = RC_INPROG;
+	nfsd_prune_bucket_locked(nn, b, 3, &dispose);
+	spin_unlock(&b->cache_lock);
 
+	freed = nfsd_cacherep_dispose(&dispose);
+	trace_nfsd_drc_gc(nn, freed);
+
+	nfsd_stats_rc_misses_inc();
 	atomic_inc(&nn->num_drc_entries);
 	nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
-
-	nfsd_prune_bucket(b, nn);
-
-out_unlock:
-	spin_unlock(&b->cache_lock);
-out:
-	return rtn;
+	goto out;
 
 found_entry:
 	/* We found a matching entry which is either in progress or done. */
@@ -541,7 +586,10 @@ found_entry:
 
 out_trace:
 	trace_nfsd_drc_found(nn, rqstp, rtn);
-	goto out_unlock;
+out_unlock:
+	spin_unlock(&b->cache_lock);
+out:
+	return rtn;
 }
 
 /**
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1261,6 +1261,28 @@ TRACE_EVENT(nfsd_drc_mismatch,
 		__entry->ingress)
 );
 
+TRACE_EVENT_CONDITION(nfsd_drc_gc,
+	TP_PROTO(
+		const struct nfsd_net *nn,
+		unsigned long freed
+	),
+	TP_ARGS(nn, freed),
+	TP_CONDITION(freed > 0),
+	TP_STRUCT__entry(
+		__field(unsigned long long, boot_time)
+		__field(unsigned long, freed)
+		__field(int, total)
+	),
+	TP_fast_assign(
+		__entry->boot_time = nn->boot_time;
+		__entry->freed = freed;
+		__entry->total = atomic_read(&nn->num_drc_entries);
+	),
+	TP_printk("boot_time=%16llx total=%d freed=%lu",
+		__entry->boot_time, __entry->total, __entry->freed
+	)
+);
+
 TRACE_EVENT(nfsd_cb_args,
 	TP_PROTO(
 		const struct nfs4_client *clp,


Patches currently in stable-queue which might be from kroah.com@vger.kernel.org are

queue-6.1/nfsd-remove-nfsd_stats-make-th_cnt-a-global-counter.patch
queue-6.1/nfsd-move-reply-cache-initialization-into-nfsd-startup.patch
queue-6.1/sunrpc-remove-pg_stats-from-svc_program.patch
queue-6.1/mptcp-pm-don-t-try-to-create-sf-if-alloc-failed.patch
queue-6.1/nfsd-rename-nfsd_reply_cache_alloc.patch
queue-6.1/nfsd-make-all-of-the-nfsd-stats-per-network-namespace.patch
queue-6.1/mptcp-pass-addr-to-mptcp_pm_alloc_anno_list.patch
queue-6.1/nfsd-move-init-of-percpu-reply_cache_stats-counters-back-to-nfsd_init_net.patch
queue-6.1/nfsd-replace-nfsd_prune_bucket.patch
queue-6.1/nfsd-stop-setting-pg_stats-for-unused-stats.patch
queue-6.1/sunrpc-don-t-change-sv_stats-if-it-doesn-t-exist.patch
queue-6.1/nfsd-make-svc_stat-per-network-namespace-instead-of-global.patch
queue-6.1/nfsd-fix-frame-size-warning-in-svc_export_parse.patch
queue-6.1/nfsd-rename-nfsd_net_-to-nfsd_stats_.patch
queue-6.1/mptcp-pm-do-not-ignore-subflow-if-signal-flag-is-also-set.patch
queue-6.1/nfsd-refactor-nfsd_reply_cache_free_locked.patch
queue-6.1/mptcp-fully-established-after-add_addr-echo-on-mpj.patch
queue-6.1/sunrpc-use-the-struct-net-as-the-svc-proc-private.patch
queue-6.1/selftests-mptcp-join-test-both-signal-subflow.patch
queue-6.1/sunrpc-pass-in-the-sv_stats-struct-through-svc_create_pooled.patch
queue-6.1/mptcp-pm-reduce-indentation-blocks.patch
queue-6.1/nfsd-rewrite-synopsis-of-nfsd_percpu_counters_init.patch
queue-6.1/nfsd-expose-proc-net-sunrpc-nfsd-in-net-namespaces.patch
queue-6.1/nfsd-refactor-the-duplicate-reply-cache-shrinker.patch

-- 
Mailing list info: https://lists.linux.it/listinfo/ltp