| 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
| ||
|
Message-ID: <c64398f7-d470-4b30-a5a2-d3884581d9fc@canonical.com>
Date: Wed, 26 Nov 2025 13:10:03 -0800
From: John Johansen <john.johansen@...onical.com>
To: Helge Deller <deller@...nel.org>
Cc: david laight <david.laight@...box.com>, Helge Deller <deller@....de>,
John Paul Adrian Glaubitz <glaubitz@...sik.fu-berlin.de>,
linux-kernel@...r.kernel.org, apparmor@...ts.ubuntu.com,
linux-security-module@...r.kernel.org, linux-parisc@...r.kernel.org
Subject: Re: [PATCH 0/2] apparmor unaligned memory fixes
On 11/26/25 12:15, Helge Deller wrote:
> * John Johansen <john.johansen@...onical.com>:
>> On 11/26/25 07:12, Helge Deller wrote:
>>> * david laight <david.laight@...box.com>:
>>>> On Wed, 26 Nov 2025 12:03:03 +0100
>>>> Helge Deller <deller@....de> wrote:
>>>>
>>>>> On 11/26/25 11:44, david laight wrote:
>>>> ...
>>>>>>> diff --git a/security/apparmor/match.c b/security/apparmor/match.c
>>>>>>> index 26e82ba879d44..3dcc342337aca 100644
>>>>>>> --- a/security/apparmor/match.c
>>>>>>> +++ b/security/apparmor/match.c
>>>>>>> @@ -71,10 +71,10 @@ static struct table_header *unpack_table(char *blob, size_t bsize)
>>>>>>> u8, u8, byte_to_byte);
>>>>>>
>>>>>> Is that that just memcpy() ?
>>>>>
>>>>> No, it's memcpy() only on big-endian machines.
>>>>
>>>> You've misread the quoting...
>>>> The 'data8' case that was only half there is a memcpy().
>>>>
>>>>> On little-endian machines it converts from big-endian
>>>>> 16/32-bit ints to little-endian 16/32-bit ints.
>>>>>
>>>>> But I see some potential for optimization here:
>>>>> a) on big-endian machines just use memcpy()
>>>>
>>>> true
>>>>
>>>>> b) on little-endian machines use memcpy() to copy from possibly-unaligned
>>>>> memory to then known-to-be-aligned destination. Then use a loop with
>>>>> be32_to_cpu() instead of get_unaligned_xx() as it's faster.
>>>>
>>>> There is a function that does a loop byteswap of a buffer - no reason
>>>> to re-invent it.
>>>
>>> I assumed there must be something, but I did not see it. Which one?
>>>
>>>> But I doubt it is always (if ever) faster to do a copy and then byteswap.
>>>> The loop control and extra memory accesses kill performance.
>>>
>>> Yes, you are probably right.
>>>
>>>> Not that I've seen a fast get_unaligned() - I don't think gcc or clang
>>>> generate optimal code - For LE I think it is something like:
>>>> low = *(addr & ~3);
>>>> high = *((addr + 3) & ~3);
>>>> shift = (addr & 3) * 8;
>>>> value = low << shift | high >> (32 - shift);
>>>> Note that it is only 2 aligned memory reads - even for 64bit.
>>>
>>> Ok, then maybe we should keep it simple like this patch:
>>>
>>> [PATCH v2] apparmor: Optimize table creation from possibly unaligned memory
>>>
>>> Source blob may come from userspace and might be unaligned.
>>> Try to optize the copying process by avoiding unaligned memory accesses.
>>>
>>> Signed-off-by: Helge Deller <deller@....de>
>>>
>>> diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h
>>> index 1fbe82f5021b..386da2023d50 100644
>>> --- a/security/apparmor/include/match.h
>>> +++ b/security/apparmor/include/match.h
>>> @@ -104,16 +104,20 @@ struct aa_dfa {
>>> struct table_header *tables[YYTD_ID_TSIZE];
>>> };
>>> -#define byte_to_byte(X) (X)
>>> +#define byte_to_byte(X) (*(X))
>>> #define UNPACK_ARRAY(TABLE, BLOB, LEN, TTYPE, BTYPE, NTOHX) \
>>> do { \
>>> typeof(LEN) __i; \
>>> TTYPE *__t = (TTYPE *) TABLE; \
>>> BTYPE *__b = (BTYPE *) BLOB; \
>>> - for (__i = 0; __i < LEN; __i++) { \
>>> - __t[__i] = NTOHX(__b[__i]); \
>>> - } \
>>> + BUILD_BUG_ON(sizeof(TTYPE) != sizeof(BTYPE)); \
>>> + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) || sizeof(BTYPE) == 1) \
>>> + memcpy(__t, __b, (LEN) * sizeof(BTYPE)); \
>>> + else /* copy & convert convert from big-endian */ \
>>> + for (__i = 0; __i < LEN; __i++) { \
>>> + __t[__i] = NTOHX(&__b[__i]); \
>>> + } \
>>> } while (0)
>>> static inline size_t table_size(size_t len, size_t el_size)
>>> diff --git a/security/apparmor/match.c b/security/apparmor/match.c
>>> index c5a91600842a..13e2f6873329 100644
>>> --- a/security/apparmor/match.c
>>> +++ b/security/apparmor/match.c
>>> @@ -15,6 +15,7 @@
>>> #include <linux/vmalloc.h>
>>> #include <linux/err.h>
>>> #include <linux/kref.h>
>>> +#include <linux/unaligned.h>
>>> #include "include/lib.h"
>>> #include "include/match.h"
>>> @@ -70,10 +71,10 @@ static struct table_header *unpack_table(char *blob, size_t bsize)
>>> u8, u8, byte_to_byte);
>>> else if (th.td_flags == YYTD_DATA16)
>>> UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
>>> - u16, __be16, be16_to_cpu);
>>> + u16, __be16, get_unaligned_be16);
>>> else if (th.td_flags == YYTD_DATA32)
>>> UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
>>> - u32, __be32, be32_to_cpu);
>>> + u32, __be32, get_unaligned_be32);
>>> else
>>> goto fail;
>>> /* if table was vmalloced make sure the page tables are synced
>>
>> I think we can make one more tweak, in just not using UNPACK_ARRAY at all for the byte case
>> ie.
>>
>> diff --git a/security/apparmor/match.c b/security/apparmor/match.c
>> index 26e82ba879d44..389202560675c 100644
>> --- a/security/apparmor/match.c
>> +++ b/security/apparmor/match.c
>> @@ -67,8 +67,7 @@ static struct table_header *unpack_table(char *blob, size_t bsize)
>> table->td_flags = th.td_flags;
>> table->td_lolen = th.td_lolen;
>> if (th.td_flags == YYTD_DATA8)
>> - UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
>> - u8, u8, byte_to_byte);
>> + memcp(table->td_data, blob, th.td_lolen);
>
> True.
> Then byte_to_byte() can go away in match.h as well.
> So, here is a (untested) v3:
>
and lightly tested now
I will pull it into my tree
>
> [PATCH v3] apparmor: Optimize table creation from possibly unaligned memory
>
> Source blob may come from userspace and might be unaligned.
> Try to optize the copying process by avoiding unaligned memory accesses.
>
> Signed-off-by: Helge Deller <deller@....de>
>
Acked-by: John Johansen <john.johansen@...onical.com>
> diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h
> index 1fbe82f5021b..19e72b3e8f49 100644
> --- a/security/apparmor/include/match.h
> +++ b/security/apparmor/include/match.h
> @@ -104,16 +104,18 @@ struct aa_dfa {
> struct table_header *tables[YYTD_ID_TSIZE];
> };
>
> -#define byte_to_byte(X) (X)
> -
> #define UNPACK_ARRAY(TABLE, BLOB, LEN, TTYPE, BTYPE, NTOHX) \
> do { \
> typeof(LEN) __i; \
> TTYPE *__t = (TTYPE *) TABLE; \
> BTYPE *__b = (BTYPE *) BLOB; \
> - for (__i = 0; __i < LEN; __i++) { \
> - __t[__i] = NTOHX(__b[__i]); \
> - } \
> + BUILD_BUG_ON(sizeof(TTYPE) != sizeof(BTYPE)); \
> + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \
> + memcpy(__t, __b, (LEN) * sizeof(BTYPE)); \
> + else /* copy & convert convert from big-endian */ \
> + for (__i = 0; __i < LEN; __i++) { \
> + __t[__i] = NTOHX(&__b[__i]); \
> + } \
> } while (0)
>
> static inline size_t table_size(size_t len, size_t el_size)
> diff --git a/security/apparmor/match.c b/security/apparmor/match.c
> index c5a91600842a..1e32c8ba14ae 100644
> --- a/security/apparmor/match.c
> +++ b/security/apparmor/match.c
> @@ -15,6 +15,7 @@
> #include <linux/vmalloc.h>
> #include <linux/err.h>
> #include <linux/kref.h>
> +#include <linux/unaligned.h>
>
> #include "include/lib.h"
> #include "include/match.h"
> @@ -66,14 +67,13 @@ static struct table_header *unpack_table(char *blob, size_t bsize)
> table->td_flags = th.td_flags;
> table->td_lolen = th.td_lolen;
> if (th.td_flags == YYTD_DATA8)
> - UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
> - u8, u8, byte_to_byte);
> + memcpy(table->td_data, blob, th.td_lolen);
> else if (th.td_flags == YYTD_DATA16)
> UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
> - u16, __be16, be16_to_cpu);
> + u16, __be16, get_unaligned_be16);
> else if (th.td_flags == YYTD_DATA32)
> UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
> - u32, __be32, be32_to_cpu);
> + u32, __be32, get_unaligned_be32);
> else
> goto fail;
> /* if table was vmalloced make sure the page tables are synced
Powered by blists - more mailing lists