Use percpu_counter for obj_alloc counter of Linux-backed caches

A previous commit enabled the tracking of object allocations
in Linux-backed caches from the SPL layer for debuggability.
The commit is: 9a170fc6fe54f1e852b6c39630fe5ef2bbd97c16

Unfortunately, it also introduced minor performance regressions
that were highlighted by the ZFS perf test-suite. Within Delphix
we found that the regression would be from -1%, all the way up
to -8% for some workloads.

This commit brings performance back up to par by creating a
separate counter for those caches and making it a percpu in
order to avoid lock-contention.

The initial performance testing was done by myself, and the
final round was conducted by @tonynguien who was also the one
that discovered the regression and highlighted the culprit.

Reviewed-by: Matt Ahrens <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Serapheim Dimitropoulos <[email protected]>
Closes #10397 

3 files changed, 46 insertions, 0 deletions

diff --git a/include/os/linux/kernel/linux/Makefile.am b/include/os/linux/kernel/linux/Makefile.am
index c142aac33..86b253304 100644
--- a/include/os/linux/kernel/linux/Makefile.am
+++ b/include/os/linux/kernel/linux/Makefile.am
@@ -5,6 +5,7 @@ KERNEL_H = \
 	blkdev_compat.h \
 	utsname_compat.h \
 	kmap_compat.h \
+	percpu_compat.h \
 	simd.h \
 	simd_x86.h \
 	simd_aarch64.h \
diff --git a/include/os/linux/kernel/linux/percpu_compat.h b/include/os/linux/kernel/linux/percpu_compat.h
new file mode 100644
index 000000000..e7a4242c4
--- /dev/null
+++ b/include/os/linux/kernel/linux/percpu_compat.h
@@ -0,0 +1,44 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2020 by Delphix. All rights reserved.
+ */
+
+#ifndef _ZFS_PERCPU_H
+#define	_ZFS_PERCPU_H
+
+#include <linux/percpu_counter.h>
+
+/*
+ * 3.18 API change,
+ * percpu_counter_init() now must be passed a gfp mask which will be
+ * used for the dynamic allocation of the actual counter.
+ */
+#ifdef HAVE_PERCPU_COUNTER_INIT_WITH_GFP
+#define	percpu_counter_init_common(counter, n, gfp) \
+	percpu_counter_init(counter, n, gfp)
+#else
+#define	percpu_counter_init_common(counter, n, gfp) \
+	percpu_counter_init(counter, n)
+#endif
+
+#endif /* _ZFS_PERCPU_H */
diff --git a/include/os/linux/spl/sys/kmem_cache.h b/include/os/linux/spl/sys/kmem_cache.h
index 5667382f7..ed63f4000 100644
--- a/include/os/linux/spl/sys/kmem_cache.h
+++ b/include/os/linux/spl/sys/kmem_cache.h
@@ -202,6 +202,7 @@ typedef struct spl_kmem_cache {
 	uint64_t		skc_slab_max;	/* Slab max historic  */
 	uint64_t		skc_obj_total;	/* Obj total current */
 	uint64_t		skc_obj_alloc;	/* Obj alloc current */
+	struct percpu_counter	skc_linux_alloc;   /* Linux-backed Obj alloc  */
 	uint64_t		skc_obj_max;	/* Obj max historic */
 	uint64_t		skc_obj_deadlock;  /* Obj emergency deadlocks */
 	uint64_t		skc_obj_emergency; /* Obj emergency current */