[PATCH RT 1/2] locallock: provide {get,put}_locked_ptr() variants

[PATCH RT 1/2] locallock: provide {get,put}_locked_ptr() variants

[Julia Cartwright]

Provide a set of locallocked accessors for pointers to per-CPU data;
this is useful for dynamically-allocated per-CPU regions, for example.

These are symmetric with the {get,put}_cpu_ptr() per-CPU accessor
variants.

Signed-off-by: Julia Cartwright <julia@ni.com>
---
 include/linux/locallock.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/linux/locallock.h b/include/linux/locallock.h
index d658c2552601..921eab83cd34 100644
--- a/include/linux/locallock.h
+++ b/include/linux/locallock.h
@@ -222,6 +222,14 @@ static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
 
 #define put_locked_var(lvar, var)	local_unlock(lvar);
 
+#define get_locked_ptr(lvar, var)					\
+	({								\
+		local_lock(lvar);					\
+		this_cpu_ptr(var);					\
+	})
+
+#define put_locked_ptr(lvar, var)	local_unlock(lvar);
+
 #define local_lock_cpu(lvar)						\
 	({								\
 		local_lock(lvar);					\
@@ -262,6 +270,8 @@ static inline void local_irq_lock_init(int lvar) { }
 
 #define get_locked_var(lvar, var)		get_cpu_var(var)
 #define put_locked_var(lvar, var)		put_cpu_var(var)
+#define get_locked_ptr(lvar, var)		get_cpu_ptr(var)
+#define put_locked_ptr(lvar, var)		put_cpu_ptr(var)
 
 #define local_lock_cpu(lvar)			get_cpu()
 #define local_unlock_cpu(lvar)			put_cpu()
-- 
2.17.0

[PATCH RT 2/2] squashfs: make use of local lock in multi_cpu decompressor

[Julia Cartwright]

Currently, the squashfs multi_cpu decompressor makes use of
get_cpu_ptr()/put_cpu_ptr(), which unconditionally disable preemption
during decompression.

Because the workload is distributed across CPUs, all CPUs can observe a
very high wakeup latency, which has been seen to be as much as 8000us.

Convert this decompressor to make use of a local lock, which will allow
execution of the decompressor with preemption-enabled, but also ensure
concurrent accesses to the percpu compressor data on the local CPU will
be serialized.

Reported-by: Alexander Stein <alexander.stein@systec-electronic.com>
Tested-by: Alexander Stein <alexander.stein@systec-electronic.com>
Signed-off-by: Julia Cartwright <julia@ni.com>
---
 fs/squashfs/decompressor_multi_percpu.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 23a9c28ad8ea..6a73c4fa88e7 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/buffer_head.h>
+#include <linux/locallock.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -25,6 +26,8 @@ struct squashfs_stream {
 	void		*stream;
 };
 
+static DEFINE_LOCAL_IRQ_LOCK(stream_lock);
+
 void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
 						void *comp_opts)
 {
@@ -79,10 +82,15 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
 {
 	struct squashfs_stream __percpu *percpu =
 			(struct squashfs_stream __percpu *) msblk->stream;
-	struct squashfs_stream *stream = get_cpu_ptr(percpu);
-	int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
-		offset, length, output);
-	put_cpu_ptr(stream);
+	struct squashfs_stream *stream;
+	int res;
+
+	stream = get_locked_ptr(stream_lock, percpu);
+
+	res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+			offset, length, output);
+
+	put_locked_ptr(stream_lock, stream);
 
 	if (res < 0)
 		ERROR("%s decompression failed, data probably corrupt\n",
-- 
2.17.0