From: Mike Galbraith <efault@gmx.de>
To: "Song Bao Hua (Barry Song)" <song.bao.hua@hisilicon.com>,
Vitaly Wool <vitaly.wool@konsulko.com>,
LKML <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Minchan Kim <minchan@kernel.org>, NitinGupta <ngupta@vflare.org>
Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
Date: Sun, 20 Dec 2020 23:10:41 +0100 [thread overview]
Message-ID: <afa2dee794ae7b2d1f23fed85ff514d43485762b.camel@gmx.de> (raw)
In-Reply-To: <44a69faf3ac54b5883a4b0d99d51a0b0@hisilicon.com>
On Sun, 2020-12-20 at 21:20 +0000, Song Bao Hua (Barry Song) wrote:
>
> > -----Original Message-----
> > From: Mike Galbraith [mailto:efault@gmx.de]
> > Sent: Sunday, December 20, 2020 8:48 PM
> > To: Vitaly Wool <vitaly.wool@konsulko.com>; LKML
> > <linux-kernel@vger.kernel.org>; linux-mm <linux-mm@kvack.org>
> > Cc: Song Bao Hua (Barry Song) <song.bao.hua@hisilicon.com>; Sebastian Andrzej
> > Siewior <bigeasy@linutronix.de>; Minchan Kim <minchan@kernel.org>; NitinGupta
> > <ngupta@vflare.org>
> > Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock
> >
> > On Sun, 2020-12-20 at 02:23 +0100, Mike Galbraith wrote:
> > > On Sun, 2020-12-20 at 02:22 +0200, Vitaly Wool wrote:
> > > > 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.
> > >
> > > It also does get_cpu_var() in map(), put_cpu_var() in unmap().
> >
> > That aside, the bit spinlock removal seems to hold up to beating in RT.
> > I stripped out the RT changes to replace the bit spinlocks, applied the
> > still needed atm might_sleep() fix, and ltp zram and zswap test are
> > running in a loop with no signs that it's a bad idea, so I hope that
> > makes it in (minus the preempt disabled spin which I whacked), as it
> > makes zsmalloc markedly more RT friendly.
> >
> > RT changes go from:
> > 1 file changed, 79 insertions(+), 6 deletions(-)
> > to:
> > 1 file changed, 8 insertions(+), 3 deletions(-)
> >
>
> Sorry, would you like to show the change for
> "8 insertions(+), 3 deletions(-)"?
Sure.
---
mm/zsmalloc.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -57,6 +57,7 @@
#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
+#include <linux/local_lock.h>
#define ZSPAGE_MAGIC 0x58
@@ -293,6 +294,7 @@ struct zspage {
};
struct mapping_area {
+ local_lock_t lock;
char *vm_buf; /* copy buffer for objects that span pages */
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
@@ -455,7 +457,9 @@ MODULE_ALIAS("zpool-zsmalloc");
#endif /* CONFIG_ZPOOL */
/* per-cpu VM mapping areas for zspage accesses that cross page
boundaries */
-static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
static bool is_zspage_isolated(struct zspage *zspage)
{
@@ -1276,7 +1280,8 @@ void *zs_map_object(struct zs_pool *pool
class = pool->size_class[class_idx];
off = (class->size * obj_idx) & ~PAGE_MASK;
- area = &get_cpu_var(zs_map_area);
+ local_lock(&zs_map_area.lock);
+ area = this_cpu_ptr(&zs_map_area);
area->vm_mm = mm;
if (off + class->size <= PAGE_SIZE) {
/* this object is contained entirely within a page */
@@ -1330,7 +1335,7 @@ void zs_unmap_object(struct zs_pool *poo
__zs_unmap_object(area, pages, off, class->size);
}
- put_cpu_var(zs_map_area);
+ local_unlock(&zs_map_area.lock);
migrate_read_unlock(zspage);
unpin_tag(handle);
> BTW, your original patch looks not right as
> crypto_wait_req(crypto_acomp_decompress()...)
> can sleep too.
>
> [copy from your original patch with comment]
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1258,20 +1258,20 @@ static int zswap_frontswap_load(unsigned
>
> /* decompress */
> dlen = PAGE_SIZE;
> + acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> + mutex_lock(acomp_ctx->mutex);
> src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
> if (zpool_evictable(entry->pool->zpool))
> src += sizeof(struct zswap_header);
>
> - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
> - mutex_lock(acomp_ctx->mutex);
> sg_init_one(&input, src, entry->length);
> sg_init_table(&output, 1);
> sg_set_page(&output, page, PAGE_SIZE, 0);
> acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
>
> /*!!!!!!!!!!!!!!!!
> * here crypto could sleep
> !!!!!!!!!!!!!!*/
Hohum, another one for my Bitmaster-9000 patch shredder.
-Mike
next prev parent reply other threads:[~2020-12-20 22:10 UTC|newest]
Thread overview: 47+ 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 ` [PATCH] zsmalloc: do not use bit_spin_lock Vitaly Wool
2020-12-20 1:18 ` 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 [this message]
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)
2020-12-22 1:57 ` Vitaly Wool
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
2020-12-22 9:32 ` Vitaly Wool
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=afa2dee794ae7b2d1f23fed85ff514d43485762b.camel@gmx.de \
--to=efault@gmx.de \
--cc=bigeasy@linutronix.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 \
--cc=vitaly.wool@konsulko.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).