linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vitaly Wool <vitaly.wool@konsulko.com>
To: Mike Galbraith <efault@gmx.de>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>
Cc: Barry Song <song.bao.hua@hisilicon.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Minchan Kim <minchan@kernel.org>, NitinGupta <ngupta@vflare.org>,
	Vitaly Wool <vitaly.wool@konsulko.com>
Subject: [PATCH] zsmalloc: do not use bit_spin_lock
Date: Sun, 20 Dec 2020 02:22:28 +0200	[thread overview]
Message-ID: <20201220002228.38697-1-vitaly.wool@konsulko.com> (raw)
In-Reply-To: <18669bd607ae9efbf4e00e36532c7aa167d0fa12.camel@gmx.de>

zsmalloc takes bit spinlock in its _map() callback and releases it
only in unmap() which is unsafe and leads to zswap complaining
about scheduling in atomic context.

To fix that and to improve RT properties of zsmalloc, remove that
bit spinlock completely and use a bit flag instead.

Signed-off-by: Vitaly Wool <vitaly.wool@konsulko.com>
---
 mm/zsmalloc.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 7289f502ffac..ff26546a7fed 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -876,22 +876,25 @@ static unsigned long obj_to_head(struct page *page, void *obj)
 
 static inline int testpin_tag(unsigned long handle)
 {
-	return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
+	return test_bit(HANDLE_PIN_BIT, (unsigned long *)handle);
 }
 
 static inline int trypin_tag(unsigned long handle)
 {
-	return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
+	return !test_and_set_bit(HANDLE_PIN_BIT, (unsigned long *)handle);
 }
 
-static void pin_tag(unsigned long handle) __acquires(bitlock)
+static void pin_tag(unsigned long handle)
 {
-	bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
+	preempt_disable();
+	while(test_and_set_bit(HANDLE_PIN_BIT, (unsigned long *)handle))
+		cpu_relax();
+	preempt_enable();
 }
 
 static void unpin_tag(unsigned long handle) __releases(bitlock)
 {
-	bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
+	clear_bit(HANDLE_PIN_BIT, (unsigned long *)handle);
 }
 
 static void reset_page(struct page *page)
-- 
2.20.1


  parent reply	other threads:[~2020-12-20  0:23 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-19 10:04 [patch] zswap: fix zswap_frontswap_load() vs zsmalloc::map/unmap() might_sleep() splat Mike Galbraith
2020-12-19 10:12 ` Mike Galbraith
2020-12-19 10:20   ` Vitaly Wool
2020-12-19 10:27     ` Mike Galbraith
2020-12-19 10:46       ` Vitaly Wool
2020-12-19 10:59         ` Mike Galbraith
2020-12-19 11:03           ` Mike Galbraith
2020-12-20  0:22           ` Vitaly Wool [this message]
2020-12-20  1:18             ` [PATCH] zsmalloc: do not use bit_spin_lock Matthew Wilcox
2020-12-20  7:21               ` Vitaly Wool
2021-01-14 16:17                 ` Sebastian Andrzej Siewior
2020-12-20  1:23             ` Mike Galbraith
2020-12-20  4:11               ` Mike Galbraith
2020-12-20  7:47               ` Mike Galbraith
2020-12-20 21:20                 ` Song Bao Hua (Barry Song)
2020-12-20 22:10                   ` Mike Galbraith
2020-12-20  1:56             ` Mike Galbraith
2020-12-21 17:24             ` Minchan Kim
2020-12-21 19:20               ` Vitaly Wool
2020-12-21 19:50                 ` Shakeel Butt
2020-12-21 20:05                   ` Song Bao Hua (Barry Song)
2020-12-21 21:02                     ` Shakeel Butt
2020-12-21 21:25                       ` Song Bao Hua (Barry Song)
2020-12-21 22:11                         ` Vitaly Wool
2020-12-21 22:42                           ` Song Bao Hua (Barry Song)
2020-12-21 23:35                           ` Song Bao Hua (Barry Song)
2020-12-22  0:59                             ` Vitaly Wool
2020-12-22  1:10                               ` Song Bao Hua (Barry Song)
2020-12-22  1:42                               ` Song Bao Hua (Barry Song)
     [not found]                                 ` <CAM4kBBK=5eBdCjWc5VJXcdr=Z4PV1=ZQ2n8fZmJ6ahJbpUyv2A@mail.gmail.com>
2020-12-22  2:07                                   ` Song Bao Hua (Barry Song)
2020-12-22  2:10                                   ` Song Bao Hua (Barry Song)
2020-12-22  9:44                                     ` Vitaly Wool
2020-12-22 21:06                                       ` Song Bao Hua (Barry Song)
2020-12-23  0:11                                         ` Vitaly Wool
2020-12-23 12:44                                           ` tiantao (H)
2020-12-23 18:25                                             ` Vitaly Wool
2021-01-14 16:18                                               ` Sebastian Andrzej Siewior
2021-01-14 16:29                                                 ` Vitaly Wool
2021-01-14 16:56                                                   ` Sebastian Andrzej Siewior
2021-01-14 17:15                                                     ` Vitaly Wool
2021-01-14 17:18                                                       ` Sebastian Andrzej Siewior
2020-12-21 22:46                         ` Shakeel Butt
2020-12-21 23:02                           ` Song Bao Hua (Barry Song)
2020-12-22  9:20                             ` David Laight
2020-12-21 20:22                 ` Minchan Kim

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=20201220002228.38697-1-vitaly.wool@konsulko.com \
    --to=vitaly.wool@konsulko.com \
    --cc=bigeasy@linutronix.de \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=ngupta@vflare.org \
    --cc=song.bao.hua@hisilicon.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).