On 10/28/2024 1:56 PM, Dmitry Baryshkov wrote:
> On Sun, Oct 27, 2024 at 11:35:47PM +0530, Akhil P Oommen wrote:
>> Clang-19 and above sometimes end up with multiple copies of the large
>> a6xx_hfi_msg_bw_table structure on the stack. The problem is that
>> a6xx_hfi_send_bw_table() calls a number of device specific functions to
>> fill the structure, but these create another copy of the structure on
>> the stack which gets copied to the first.
>>
>> If the functions get inlined, that busts the warning limit:
>>
>> drivers/gpu/drm/msm/adreno/a6xx_hfi.c:631:12: error: stack frame size (1032) exceeds limit (1024) in 'a6xx_hfi_send_bw_table' [-Werror,-Wframe-larger-than]
>>
>> Fix this by kmalloc-ating struct a6xx_hfi_msg_bw_table instead of using
>> the stack. Also, use this opportunity to skip re-initializing this table
>> to optimize gpu wake up latency.
>>
>> Cc: Arnd Bergmann <arnd@xxxxxxxxxx>
>>
>> Signed-off-by: Akhil P Oommen <quic_akhilpo@xxxxxxxxxxx>
>> ---
>> drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 1 +
>> drivers/gpu/drm/msm/adreno/a6xx_hfi.c | 34 ++++++++++++++++++++++------------
>> 2 files changed, 23 insertions(+), 12 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
>> index 94b6c5cab6f4..b4a79f88ccf4 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
>> @@ -99,6 +99,7 @@ struct a6xx_gmu {
>> struct completion pd_gate;
>>
>> struct qmp *qmp;
>> + struct a6xx_hfi_msg_bw_table *bw_table;
>> };
>>
>> static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset)
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> index cdb3f6e74d3e..55e51c81be1f 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
>> @@ -630,32 +630,42 @@ static void a6xx_build_bw_table(struct a6xx_hfi_msg_bw_table *msg)
>>
>> static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu)
>> {
>> - struct a6xx_hfi_msg_bw_table msg = { 0 };
>> + struct a6xx_hfi_msg_bw_table *msg;
>> struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
>> struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
>>
>> + if (gmu->bw_table)
>> + goto send;
>> +
>> + msg = devm_kzalloc(gmu->dev, sizeof(*msg), GFP_KERNEL);
>
> Is it necessary after being sent? Isn't it better to just kzalloc() it
> and then kfree() it at the end of the function?
Keeping it around will help to cut down unnecessary work during
subsequent gpu wake ups.
-Akhil.
>
>> + if (!msg)
>> + return -ENOMEM;
>> +
>> if (adreno_is_a618(adreno_gpu))
>> - a618_build_bw_table(&msg);
>> + a618_build_bw_table(msg);
>> else if (adreno_is_a619(adreno_gpu))
>> - a619_build_bw_table(&msg);
>> + a619_build_bw_table(msg);
>> else if (adreno_is_a640_family(adreno_gpu))
>> - a640_build_bw_table(&msg);
>> + a640_build_bw_table(msg);
>> else if (adreno_is_a650(adreno_gpu))
>> - a650_build_bw_table(&msg);
>> + a650_build_bw_table(msg);
>> else if (adreno_is_7c3(adreno_gpu))
>> - adreno_7c3_build_bw_table(&msg);
>> + adreno_7c3_build_bw_table(msg);
>> else if (adreno_is_a660(adreno_gpu))
>> - a660_build_bw_table(&msg);
>> + a660_build_bw_table(msg);
>> else if (adreno_is_a690(adreno_gpu))
>> - a690_build_bw_table(&msg);
>> + a690_build_bw_table(msg);
>> else if (adreno_is_a730(adreno_gpu))
>> - a730_build_bw_table(&msg);
>> + a730_build_bw_table(msg);
>> else if (adreno_is_a740_family(adreno_gpu))
>> - a740_build_bw_table(&msg);
>> + a740_build_bw_table(msg);
>> else
>> - a6xx_build_bw_table(&msg);
>> + a6xx_build_bw_table(msg);
>> +
>> + gmu->bw_table = msg;
>>
>> - return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, &msg, sizeof(msg),
>> +send:
>> + return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_BW_TABLE, gmu->bw_table, sizeof(*(gmu->bw_table)),
>> NULL, 0);
>> }
>>
>>
>> ---
>> base-commit: 74c374648ed08efb2ef339656f2764c28c046956
>> change-id: 20241024-stack-size-fix-28af7abd3fab
>>
>> Best regards,
>> --
>> Akhil P Oommen <quic_akhilpo@xxxxxxxxxxx>
>>
>
