All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Will Deacon <will@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	"Paul E . McKenney" <paulmck@kernel.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Julia Cartwright <julia@ni.com>,
	Phillip Lougher <phillip@squashfs.org.uk>,
	Alexander Stein <alexander.stein@systec-electronic.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Subject: [PATCH 5/8] squashfs: make use of local lock in multi_cpu decompressor
Date: Tue, 19 May 2020 22:19:09 +0200	[thread overview]
Message-ID: <20200519201912.1564477-6-bigeasy@linutronix.de> (raw)
In-Reply-To: <20200519201912.1564477-1-bigeasy@linutronix.de>

From: Julia Cartwright <julia@ni.com>

The squashfs multi CPU decompressor makes use of get_cpu_ptr() to
acquire a pointer to per-CPU data. get_cpu_ptr() implicitly disables
preemption which serializes the access to the per-CPU data.

But decompression can take quite some time depending on the size. The
observed preempt disabled times in real world scenarios went up to 8ms,
causing massive wakeup latencies. This happens on all CPUs as the
decompression is fully parallelized.

Replace the implicit preemption control with an explicit local lock.
This allows RT kernels to substitute it with a real per CPU lock, which
serializes the access but keeps the code section preemptible. On non RT
kernels this maps to preempt_disable() as before, i.e. no functional
change.

[ bigeasy: Use local_lock(), patch description]

Cc: Phillip Lougher <phillip@squashfs.org.uk>
Reported-by: Alexander Stein <alexander.stein@systec-electronic.com>
Signed-off-by: Julia Cartwright <julia@ni.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Alexander Stein <alexander.stein@systec-electronic.com>
---
 fs/squashfs/decompressor_multi_percpu.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 2a2a2d106440e..8a77a2741c176 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -8,6 +8,7 @@
 #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"
@@ -23,6 +24,8 @@ struct squashfs_stream {
 	void		*stream;
 };
 
+static DEFINE_LOCAL_LOCK(stream_lock);
+
 void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
 						void *comp_opts)
 {
@@ -75,12 +78,16 @@ void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
 int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
 	int b, int offset, int length, struct squashfs_page_actor *output)
 {
-	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;
+
+	local_lock(stream_lock);
+	stream = this_cpu_ptr(msblk->stream);
+
+	res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+			offset, length, output);
+
+	local_unlock(stream_lock);
 
 	if (res < 0)
 		ERROR("%s decompression failed, data probably corrupt\n",
-- 
2.26.2


  parent reply	other threads:[~2020-05-19 20:20 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-19 20:19 [PATCH 0/8] Introduce local_lock() Sebastian Andrzej Siewior
2020-05-19 20:19 ` [PATCH 1/8] locking: " Sebastian Andrzej Siewior
2020-05-20 12:04   ` Peter Zijlstra
2020-05-22 11:05     ` Sebastian Andrzej Siewior
2020-05-22 13:01       ` Peter Zijlstra
2020-05-19 20:19 ` [PATCH 2/8] radix-tree: Use local_lock for protection Sebastian Andrzej Siewior
2020-05-19 20:45   ` Matthew Wilcox
2020-05-19 20:54     ` Steven Rostedt
2020-05-20  2:05       ` Matthew Wilcox
2020-05-20 10:13         ` Sebastian Andrzej Siewior
2020-05-20 10:21   ` Peter Zijlstra
2020-05-20 12:28     ` Thomas Gleixner
2020-05-19 20:19 ` [PATCH 3/8] srcu: Use local_lock() for per-CPU struct srcu_data access Sebastian Andrzej Siewior
2020-05-20 10:24   ` Peter Zijlstra
2020-05-20 12:06     ` Sebastian Andrzej Siewior
2020-05-20 13:27       ` Peter Zijlstra
2020-05-20 17:42       ` Joel Fernandes
2020-05-20 18:28         ` Sebastian Andrzej Siewior
2020-05-20 18:35           ` Peter Zijlstra
2020-05-20 18:44             ` Joel Fernandes
2020-05-20 18:50               ` Uladzislau Rezki
2020-05-20 18:59           ` Joel Fernandes
2020-05-20 18:43       ` Paul E. McKenney
2020-05-22 15:12         ` Sebastian Andrzej Siewior
2020-05-22 17:39           ` Paul E. McKenney
2020-05-23 15:08             ` Sebastian Andrzej Siewior
2020-05-23 16:59               ` Paul E. McKenney
2020-05-24 19:03               ` Sebastian Andrzej Siewior
2020-05-25  3:27                 ` Paul E. McKenney
2020-05-26 13:41                   ` [PATCH] srcu: Avoid local_irq_save() before acquiring spinlock_t Sebastian Andrzej Siewior
2020-05-26 16:16                     ` Paul E. McKenney
2020-05-26 16:31                       ` Sebastian Andrzej Siewior
2020-05-19 20:19 ` [PATCH 4/8] mm/swap: Use local_lock for protection Sebastian Andrzej Siewior
2020-05-19 23:58   ` Andrew Morton
2020-05-20  2:17     ` Matthew Wilcox
2020-05-20 10:53   ` Peter Zijlstra
2020-05-19 20:19 ` Sebastian Andrzej Siewior [this message]
2020-05-20 10:56   ` [PATCH 5/8] squashfs: make use of local lock in multi_cpu decompressor Peter Zijlstra
2020-05-19 20:19 ` [PATCH 6/8] connector/cn_proc: Protect send_msg() with a local lock Sebastian Andrzej Siewior
2020-05-20 11:03   ` Peter Zijlstra
2020-05-19 20:19 ` [PATCH 7/8] zram: Use local lock to protect per-CPU data Sebastian Andrzej Siewior
2020-05-20 11:07   ` Peter Zijlstra
2020-05-19 20:19 ` [PATCH 8/8] mm/zswap: " Sebastian Andrzej Siewior
2020-05-19 21:46   ` Song Bao Hua
2020-05-20 10:26     ` Sebastian Andrzej Siewior
2020-05-20 11:13       ` Song Bao Hua
2020-05-20 11:57         ` Sebastian Andrzej Siewior
2020-05-20 12:01           ` Song Bao Hua

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200519201912.1564477-6-bigeasy@linutronix.de \
    --to=bigeasy@linutronix.de \
    --cc=alexander.stein@systec-electronic.com \
    --cc=julia@ni.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=phillip@squashfs.org.uk \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.