linux-kernel - Re: [PATCH v2 2/2] iommu/arm-smmu-v3: Simplify useless instructions in arm_smmu_cmdq_build

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] [day] [month] [year] [list]

Message-ID: <68742c41-8610-9b3f-49b7-7ae04dc87ec2@huawei.com>
Date:   Wed, 20 Oct 2021 15:29:44 +0800
From:   "Leizhen (ThunderTown)" <thunder.leizhen@...wei.com>
To:     Will Deacon <will@...nel.org>
CC:     Robin Murphy <robin.murphy@....com>,
        Joerg Roedel <joro@...tes.org>,
        linux-arm-kernel <linux-arm-kernel@...ts.infradead.org>,
        iommu <iommu@...ts.linux-foundation.org>,
        <linux-kernel@...r.kernel.org>,
        "John Garry" <john.garry@...wei.com>
Subject: Re: [PATCH v2 2/2] iommu/arm-smmu-v3: Simplify useless instructions
 in arm_smmu_cmdq_build_cmd()



On 2021/10/4 20:07, Will Deacon wrote:
> On Wed, Aug 18, 2021 at 04:04:52PM +0800, Zhen Lei wrote:
>> Although the parameter 'cmd' is always passed by a local array variable,
>> and only this function modifies it, the compiler does not know this. The
>> compiler almost always reads the value of cmd[i] from memory rather than
>> directly using the value cached in the register. This generates many
>> useless instruction operations and affects the performance to some extent.
>>
>> To guide the compiler for proper optimization, 'cmd' is defined as a local
>> array variable, marked as register, and copied to the output parameter at
>> a time when the function is returned.
>>
>> The optimization effect can be viewed by running the "size arm-smmu-v3.o"
>> command.
>>
>> Before:
>>    text    data     bss     dec     hex
>>   26954    1348      56   28358    6ec6
>>
>> After:
>>    text    data     bss     dec     hex
>>   26762    1348      56   28166    6e06
>>
>> Signed-off-by: Zhen Lei <thunder.leizhen@...wei.com>
>> ---
>>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 11 ++++++++---
>>  1 file changed, 8 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>> index 01e95b56ffa07d1..7cec0c967f71d86 100644
>> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
>> @@ -234,10 +234,12 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
>>  }
>>  
>>  /* High-level queue accessors */
>> -static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
>> +static int arm_smmu_cmdq_build_cmd(u64 *out_cmd, struct arm_smmu_cmdq_ent *ent)
>>  {
>> -	memset(cmd, 0, 1 << CMDQ_ENT_SZ_SHIFT);
>> -	cmd[0] |= FIELD_PREP(CMDQ_0_OP, ent->opcode);
>> +	register u64 cmd[CMDQ_ENT_DWORDS];
> 
> 'register' is pretty badly specified outside of a handful of limited uses in
> conjunction with inline asm, so I really don't think we should be using it
> here.

OK, I think I was overly aggressive in the beginning, and I just tried to
remove the register modifier and get the same optimization.

> 
>> +	cmd[0] = FIELD_PREP(CMDQ_0_OP, ent->opcode);
> 
> This generates a compiler warning about taking the address of a 'register'
> variable.
> 
> Will
> .
>