linux-kernel - Re: [PATCH] zsmalloc: do not use bit_spin

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <afa2dee794ae7b2d1f23fed85ff514d43485762b.camel@gmx.de>
Date:   Sun, 20 Dec 2020 23:10:41 +0100
From:   Mike Galbraith <efault@....de>
To:     "Song Bao Hua (Barry Song)" <song.bao.hua@...ilicon.com>,
        Vitaly Wool <vitaly.wool@...sulko.com>,
        LKML <linux-kernel@...r.kernel.org>,
        linux-mm <linux-mm@...ck.org>
Cc:     Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Minchan Kim <minchan@...nel.org>,
        NitinGupta <ngupta@...are.org>
Subject: Re: [PATCH] zsmalloc: do not use bit_spin_lock

On Sun, 2020-12-20 at 21:20 +0000, Song Bao Hua (Barry Song) wrote:
>
> > -----Original Message-----
> > From: Mike Galbraith [mailto:efault@....de]
> > Sent: Sunday, December 20, 2020 8:48 PM
> > To: Vitaly Wool <vitaly.wool@...sulko.com>; LKML
> > <linux-kernel@...r.kernel.org>; linux-mm <linux-mm@...ck.org>
> > Cc: Song Bao Hua (Barry Song) <song.bao.hua@...ilicon.com>; Sebastian Andrzej
> > Siewior <bigeasy@...utronix.de>; Minchan Kim <minchan@...nel.org>; NitinGupta
> > <ngupta@...are.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