linux-kernel - Re: [PATCH 3/4] drm/msm/a6xx: Get HBB dynamically, if available

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]

Message-ID: <c2dac38b-bbe5-4cd1-9d33-b4bba629d54b@oss.qualcomm.com>
Date: Wed, 9 Apr 2025 17:22:28 +0200
From: Konrad Dybcio <konrad.dybcio@....qualcomm.com>
To: Connor Abbott <cwabbott0@...il.com>,
        Konrad Dybcio <konradybcio@...nel.org>
Cc: Bjorn Andersson <andersson@...nel.org>, Kees Cook <kees@...nel.org>,
        "Gustavo A. R. Silva" <gustavoars@...nel.org>,
        Rob Clark <robdclark@...il.com>, Sean Paul <sean@...rly.run>,
        Abhinav Kumar <quic_abhinavk@...cinc.com>,
        Dmitry Baryshkov <dmitry.baryshkov@....qualcomm.com>,
        David Airlie <airlied@...il.com>, Simona Vetter <simona@...ll.ch>,
        Dmitry Baryshkov <lumag@...nel.org>,
        Marijn Suijten <marijn.suijten@...ainline.org>,
        linux-kernel@...r.kernel.org, linux-arm-msm@...r.kernel.org,
        linux-hardening@...r.kernel.org, dri-devel@...ts.freedesktop.org,
        freedreno@...ts.freedesktop.org,
        Konrad Dybcio <konrad.dybcio@....qualcomm.com>
Subject: Re: [PATCH 3/4] drm/msm/a6xx: Get HBB dynamically, if available

On 4/9/25 5:12 PM, Connor Abbott wrote:
> On Wed, Apr 9, 2025 at 10:48 AM Konrad Dybcio <konradybcio@...nel.org> wrote:
>>
>> From: Konrad Dybcio <konrad.dybcio@....qualcomm.com>
>>
>> The Highest Bank address Bit value can change based on memory type used.
>>
>> Attempt to retrieve it dynamically, and fall back to a reasonable
>> default (the one used prior to this change) on error.
>>
>> Signed-off-by: Konrad Dybcio <konrad.dybcio@....qualcomm.com>
>> ---
>>  drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 22 ++++++++++++++++------
>>  1 file changed, 16 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> index 06465bc2d0b4b128cddfcfcaf1fe4252632b6777..0cc397378c99db35315209d0265ad9223e8b55c7 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> @@ -13,6 +13,7 @@
>>  #include <linux/firmware/qcom/qcom_scm.h>
>>  #include <linux/pm_domain.h>
>>  #include <linux/soc/qcom/llcc-qcom.h>
>> +#include <linux/soc/qcom/smem.h>
>>
>>  #define GPU_PAS_ID 13
>>
>> @@ -669,17 +670,22 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
>>  static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
>>  {
>>         struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
>> +       u32 hbb = qcom_smem_dram_get_hbb();
>> +       u32 ubwc_mode = adreno_gpu->ubwc_config.ubwc_swizzle & 1;
>> +       u32 level2_swizzling_dis = !(adreno_gpu->ubwc_config.ubwc_swizzle & 2);
>> +       u32 hbb_hi, hbb_lo;
>> +
>>         /*
>>          * We subtract 13 from the highest bank bit (13 is the minimum value
>>          * allowed by hw) and write the lowest two bits of the remaining value
>>          * as hbb_lo and the one above it as hbb_hi to the hardware.
>>          */
>> -       BUG_ON(adreno_gpu->ubwc_config.highest_bank_bit < 13);
>> -       u32 hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
>> -       u32 hbb_hi = hbb >> 2;
>> -       u32 hbb_lo = hbb & 3;
>> -       u32 ubwc_mode = adreno_gpu->ubwc_config.ubwc_swizzle & 1;
>> -       u32 level2_swizzling_dis = !(adreno_gpu->ubwc_config.ubwc_swizzle & 2);
>> +       if (hbb < 0)
>> +               hbb = adreno_gpu->ubwc_config.highest_bank_bit;
> 
> No. The value we expose to userspace must match what we program.
> You'll break VK_EXT_host_image_copy otherwise.

I didn't know that was exposed to userspace.

The value must be altered either way - ultimately, the hardware must
receive the correct information. ubwc_config doesn't seem to be const,
so I can edit it there if you like it better.

Konrad