[PATCH 5.15.y 05/18] NFSD: Replace nfsd_prune_bucket()

[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>
---
 fs/nfsd/nfscache.c | 78 +++++++++++++++++++++++++++++++++++++---------
 fs/nfsd/trace.h    | 22 +++++++++++++
 2 files changed, 85 insertions(+), 15 deletions(-)

diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 938b37dc1679..e60313ce0fb6 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -117,6 +117,21 @@ static void nfsd_cacherep_free(struct svc_cacherep *rp)
 	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)
@@ -259,6 +274,41 @@ nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn)
 	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)
 {
@@ -282,11 +332,6 @@ static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn,
 	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.
@@ -442,6 +487,8 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
 	__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;
@@ -466,20 +513,18 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
 	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. */
@@ -517,7 +562,10 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
 
 out_trace:
 	trace_nfsd_drc_found(nn, rqstp, rtn);
-	goto out_unlock;
+out_unlock:
+	spin_unlock(&b->cache_lock);
+out:
+	return rtn;
 }
 
 /**
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 276420ea3b8d..91e9921db725 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1260,6 +1260,28 @@ 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,
-- 
2.45.2