linux-kernel - [PATCH 5.15 619/667] Revert "mm/cma.c: remove redundant cma

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]

Date:   Tue,  7 Jun 2022 19:04:44 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Dong Aisheng <aisheng.dong@....com>,
        Minchan Kim <minchan@...nel.org>,
        David Hildenbrand <david@...hat.com>,
        Marek Szyprowski <m.szyprowski@...sung.com>,
        Lecopzer Chen <lecopzer.chen@...iatek.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Andrew Morton <akpm@...ux-foundation.org>
Subject: [PATCH 5.15 619/667] Revert "mm/cma.c: remove redundant cma_mutex lock"

From: Dong Aisheng <aisheng.dong@....com>

commit 60a60e32cf91169840abcb4a80f0b0df31708ba7 upstream.

This reverts commit a4efc174b382fcdb which introduced a regression issue
that when there're multiple processes allocating dma memory in parallel by
calling dma_alloc_coherent(), it may fail sometimes as follows:

Error log:
cma: cma_alloc: linux,cma: alloc failed, req-size: 148 pages, ret: -16
cma: number of available pages:
3@...+20@...+12@...+4@...+32@...+17@...7+23@...3+20@...76+99@...77+108@...52+44@...08+20@...96+108@...64+108@...20+
108@...00+108@...56+483@...61+1763@...41+1440@...12+20@...24+20@...88+5076@...52+2304@...40+35@...41+20@...20+20@...84+
7188@...48+84@...20+7276@...52+227@...25+6371@...49=> 33161 free of 81920 total pages

When issue happened, we saw there were still 33161 pages (129M) free CMA
memory and a lot available free slots for 148 pages in CMA bitmap that we
want to allocate.

When dumping memory info, we found that there was also ~342M normal
memory, but only 1352K CMA memory left in buddy system while a lot of
pageblocks were isolated.

Memory info log:
Normal free:351096kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB
	    active_anon:98060kB inactive_anon:98948kB active_file:60864kB inactive_file:31776kB
	    unevictable:0kB writepending:0kB present:1048576kB managed:1018328kB mlocked:0kB
	    bounce:0kB free_pcp:220kB local_pcp:192kB free_cma:1352kB lowmem_reserve[]: 0 0 0
Normal: 78*4kB (UECI) 1772*8kB (UMECI) 1335*16kB (UMECI) 360*32kB (UMECI) 65*64kB (UMCI)
	36*128kB (UMECI) 16*256kB (UMCI) 6*512kB (EI) 8*1024kB (UEI) 4*2048kB (MI) 8*4096kB (EI)
	8*8192kB (UI) 3*16384kB (EI) 8*32768kB (M) = 489288kB

The root cause of this issue is that since commit a4efc174b382 ("mm/cma.c:
remove redundant cma_mutex lock"), CMA supports concurrent memory
allocation.  It's possible that the memory range process A trying to alloc
has already been isolated by the allocation of process B during memory
migration.

The problem here is that the memory range isolated during one allocation
by start_isolate_page_range() could be much bigger than the real size we
want to alloc due to the range is aligned to MAX_ORDER_NR_PAGES.

Taking an ARMv7 platform with 1G memory as an example, when
MAX_ORDER_NR_PAGES is big (e.g.  32M with max_order 14) and CMA memory is
relatively small (e.g.  128M), there're only 4 MAX_ORDER slot, then it's
very easy that all CMA memory may have already been isolated by other
processes when one trying to allocate memory using dma_alloc_coherent().
Since current CMA code will only scan one time of whole available CMA
memory, then dma_alloc_coherent() may easy fail due to contention with
other processes.

This patch simply falls back to the original method that using cma_mutex
to make alloc_contig_range() run sequentially to avoid the issue.

Link: https://lkml.kernel.org/r/20220509094551.3596244-1-aisheng.dong@nxp.com
Link: https://lore.kernel.org/all/20220315144521.3810298-2-aisheng.dong@nxp.com/
Fixes: a4efc174b382 ("mm/cma.c: remove redundant cma_mutex lock")
Signed-off-by: Dong Aisheng <aisheng.dong@....com>
Acked-by: Minchan Kim <minchan@...nel.org>
Acked-by: David Hildenbrand <david@...hat.com>
Cc: Marek Szyprowski <m.szyprowski@...sung.com>
Cc: Lecopzer Chen <lecopzer.chen@...iatek.com>
Cc: Vlastimil Babka <vbabka@...e.cz>
Cc: <stable@...r.kernel.org>	[5.11+]
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 mm/cma.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/mm/cma.c
+++ b/mm/cma.c
@@ -37,6 +37,7 @@

 struct cma cma_areas[MAX_CMA_AREAS];
 unsigned cma_area_count;
+static DEFINE_MUTEX(cma_mutex);

 phys_addr_t cma_get_base(const struct cma *cma)
 {
@@ -471,9 +472,10 @@ struct page *cma_alloc(struct cma *cma,
 		spin_unlock_irq(&cma->lock);

 		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
+		mutex_lock(&cma_mutex);
 		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
 				     GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0));
-
+		mutex_unlock(&cma_mutex);
 		if (ret == 0) {
 			page = pfn_to_page(pfn);
 			break;