Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Yongxin Liu <yongxin.liu@windriver.com>
To:     <linux-kernel@vger.kernel.org>, <linux-rt-users@vger.kernel.org>
CC:     <bigeasy@linutronix.de>, <tglx@linutronix.de>,
        <rostedt@goodmis.org>, <dan.j.williams@intel.com>,
        <pagupta@redhat.com>, <paul.gortmaker@windriver.com>,
        <linux-nvdimm@lists.01.org>
Subject: [PATCH RT] nvdimm: make lane acquirement RT aware
Date:   Wed, 6 Mar 2019 17:57:09 +0800
Message-ID: <20190306095709.23138-1-yongxin.liu@windriver.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Currently, nvdimm driver isn't RT compatible.
nd_region_acquire_lane() disables preemption with get_cpu() which
causes "scheduling while atomic" spews on RT, when using fio to test
pmem as block device.

In this change, we replace get_cpu/put_cpu with local_lock_cpu/
local_unlock_cpu, and introduce per CPU variable "ndl_local_lock".
Due to preemption on RT, this lock can avoid race condition for the
same lane on the same CPU. When CPU number is greater than the lane
number, lane can be shared among CPUs. "ndl_lock->lock" is used to
protect the lane in this situation.

This patch is derived from Dan Williams and Pankaj Gupta's proposal from
https://www.mail-archive.com/linux-nvdimm@lists.01.org/msg13359.html
and https://www.spinics.net/lists/linux-rt-users/msg20280.html.
Many thanks to them.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pagupta@redhat.com>
Cc: linux-rt-users <linux-rt-users@vger.kernel.org>
Cc: linux-nvdimm <linux-nvdimm@lists.01.org>
Signed-off-by: Yongxin Liu <yongxin.liu@windriver.com>
---
 drivers/nvdimm/region_devs.c | 40 +++++++++++++++++++---------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index fa37afcd43ff..6c5388cf2477 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -18,9 +18,13 @@
 #include <linux/sort.h>
 #include <linux/io.h>
 #include <linux/nd.h>
+#include <linux/locallock.h>
 #include "nd-core.h"
 #include "nd.h"
 
+/* lock for tasks on the same CPU to sequence the access to the lane */
+static DEFINE_LOCAL_IRQ_LOCK(ndl_local_lock);
+
 /*
  * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
  * irrelevant.
@@ -935,18 +939,15 @@ int nd_blk_region_init(struct nd_region *nd_region)
 unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
 {
 	unsigned int cpu, lane;
+	struct nd_percpu_lane *ndl_lock, *ndl_count;
 
-	cpu = get_cpu();
-	if (nd_region->num_lanes < nr_cpu_ids) {
-		struct nd_percpu_lane *ndl_lock, *ndl_count;
+	cpu = local_lock_cpu(ndl_local_lock);
 
-		lane = cpu % nd_region->num_lanes;
-		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
-		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
-		if (ndl_count->count++ == 0)
-			spin_lock(&ndl_lock->lock);
-	} else
-		lane = cpu;
+	lane = cpu % nd_region->num_lanes;
+	ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+	ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+	if (ndl_count->count++ == 0)
+		spin_lock(&ndl_lock->lock);
 
 	return lane;
 }
@@ -954,17 +955,14 @@ EXPORT_SYMBOL(nd_region_acquire_lane);
 
 void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
 {
-	if (nd_region->num_lanes < nr_cpu_ids) {
-		unsigned int cpu = get_cpu();
-		struct nd_percpu_lane *ndl_lock, *ndl_count;
-
-		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
-		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
-		if (--ndl_count->count == 0)
-			spin_unlock(&ndl_lock->lock);
-		put_cpu();
-	}
-	put_cpu();
+	struct nd_percpu_lane *ndl_lock, *ndl_count;
+	unsigned int cpu = smp_processor_id();
+
+	ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+	ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+	if (--ndl_count->count == 0)
+		spin_unlock(&ndl_lock->lock);
+	local_unlock_cpu(ndl_local_lock);
 }
 EXPORT_SYMBOL(nd_region_release_lane);
 
-- 
2.14.4