linux-kernel - Re: block: DMA alignment of IO buffer allocated from slab

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:   Fri, 21 Sep 2018 15:04:18 +0200
From:   Vitaly Kuznetsov <vkuznets@...hat.com>
To:     Christoph Hellwig <hch@....de>
Cc:     Ming Lei <tom.leiming@...il.com>,
        linux-block <linux-block@...r.kernel.org>,
        linux-mm <linux-mm@...ck.org>,
        Linux FS Devel <linux-fsdevel@...r.kernel.org>,
        "open list\:XFS FILESYSTEM" <linux-xfs@...r.kernel.org>,
        Dave Chinner <dchinner@...hat.com>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Jens Axboe <axboe@...nel.dk>, Ming Lei <ming.lei@...hat.com>,
        Christoph Lameter <cl@...ux.com>
Subject: Re: block: DMA alignment of IO buffer allocated from slab

Christoph Hellwig <hch@....de> writes:

> On Wed, Sep 19, 2018 at 05:15:43PM +0800, Ming Lei wrote:
>> 1) does kmalloc-N slab guarantee to return N-byte aligned buffer?  If
>> yes, is it a stable rule?
>
> This is the assumption in a lot of the kernel, so I think if somethings
> breaks this we are in a lot of pain.

It seems that SLUB debug breaks this assumption. Kernel built with

CONFIG_SLUB_DEBUG=y
CONFIG_SLUB=y
CONFIG_SLUB_DEBUG_ON=y

And the following patch:
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3b20607d581b..56713b201921 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1771,3 +1771,28 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
        e820__range_add(addr, size, E820_TYPE_ACPI);
        e820__update_table_print();
 }
+
+#define KMALLOCS 16
+
+static __init int kmalloc_check_512(void)
+{
+       void *buf[KMALLOCS];
+       int i;
+
+       pr_info("kmalloc_check_512: start\n");
+
+       for (i = 0; i < KMALLOCS; i++) {
+               buf[i] = kmalloc(512, GFP_KERNEL);
+       }
+
+       for (i = 0; i < KMALLOCS; i++) {
+               pr_info("%lx %x\n", (unsigned long)buf[i], ((unsigned long)buf[i]) % 512);
+               kfree(buf[i]);
+       }
+
+       pr_info("kmalloc_check_512: done\n");
+
+       return 0;
+}
+
+late_initcall(kmalloc_check_512);

gives me the following output:

[    8.417468] kmalloc_check_512: start
[    8.429572] ffff9a3258bb09f8 1f8
[    8.435513] ffff9a3258bb70a8 a8
[    8.441352] ffff9a3258bb0d48 148
[    8.447139] ffff9a3258bb6d58 158
[    8.452864] ffff9a3258bb1098 98
[    8.458536] ffff9a3258bb6a08 8
[    8.464103] ffff9a3258bb13e8 1e8
[    8.469534] ffff9a3258bb66b8 b8
[    8.474907] ffff9a3258bb1738 138
[    8.480214] ffff9a3258bb6368 168
[    8.480217] ffff9a3258bb1a88 88
[    8.496178] ffff9a3258bb6018 18
[    8.501218] ffff9a3258bb1dd8 1d8
[    8.506138] ffff9a3258bb5cc8 c8
[    8.511010] ffff9a3258bb2128 128
[    8.515795] ffff9a3258bb5978 178
[    8.520517] kmalloc_check_512: done

(without SLUB_DEBUG_ON all addresses are 512b aligned).

-- 
  Vitaly