From: Konrad Dybcio <konrad.dybcio@linaro.org>
To: Akhil P Oommen <quic_akhilpo@quicinc.com>
Cc: Rob Clark <robdclark@gmail.com>, Sean Paul <sean@poorly.run>,
Abhinav Kumar <quic_abhinavk@quicinc.com>,
Dmitry Baryshkov <dmitry.baryshkov@linaro.org>,
Marijn Suijten <marijn.suijten@somainline.org>,
David Airlie <airlied@gmail.com>, Daniel Vetter <daniel@ffwll.ch>,
Rob Clark <robdclark@chromium.org>,
linux-arm-msm@vger.kernel.org, dri-devel@lists.freedesktop.org,
freedreno@lists.freedesktop.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] drm/msm/adreno: De-spaghettify the use of memory barriers
Date: Tue, 4 Jun 2024 19:35:04 +0200 [thread overview]
Message-ID: <5ff40fba-e45a-4a5c-b5a7-7ef5a799a008@linaro.org> (raw)
In-Reply-To: <20240514183849.6lpyplifero5u35r@hu-akhilpo-hyd.qualcomm.com>
On 5/14/24 20:38, Akhil P Oommen wrote:
> On Wed, May 08, 2024 at 07:46:31PM +0200, Konrad Dybcio wrote:
>> Memory barriers help ensure instruction ordering, NOT time and order
>> of actual write arrival at other observers (e.g. memory-mapped IP).
>> On architectures employing weak memory ordering, the latter can be a
>> giant pain point, and it has been as part of this driver.
>>
>> Moreover, the gpu_/gmu_ accessors already use non-relaxed versions of
>> readl/writel, which include r/w (respectively) barriers.
>>
>> Replace the barriers with a readback that ensures the previous writes
>> have exited the write buffer (as the CPU must flush the write to the
>> register it's trying to read back) and subsequently remove the hack
>> introduced in commit b77532803d11 ("drm/msm/a6xx: Poll for GBIF unhalt
>> status in hw_init").
>>
>> Fixes: b77532803d11 ("drm/msm/a6xx: Poll for GBIF unhalt status in hw_init")
>> Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
>> ---
>> drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 5 ++---
>> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 14 ++++----------
>> 2 files changed, 6 insertions(+), 13 deletions(-)
>
> I prefer this version compared to the v2. A helper routine is
> unnecessary here because:
> 1. there are very few scenarios where we have to read back the same
> register.
> 2. we may accidently readback a write only register.
Which would still trigger an address dependency on the CPU, no?
>
>>
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> index 0e3dfd4c2bc8..4135a53b55a7 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
>> @@ -466,9 +466,8 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu)
>> int ret;
>> u32 val;
>>
>> - gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1 << 1);
>> - /* Wait for the register to finish posting */
>> - wmb();
>> + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, BIT(1));
>> + gmu_read(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ);
>
> This is unnecessary because we are polling on a register on the same port below. But I think we
> can replace "wmb()" above with "mb()" to avoid reordering between read
> and write IO instructions.
Ok on the dropping readback part
+ AFAIU from Will's response, we can drop the barrier as well
>
>>
>> ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_RSCC_CONTROL_ACK, val,
>> val & (1 << 1), 100, 10000);
>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> index 973872ad0474..0acbc38b8e70 100644
>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>> @@ -1713,22 +1713,16 @@ static int hw_init(struct msm_gpu *gpu)
>> }
>>
>> /* Clear GBIF halt in case GX domain was not collapsed */
>> + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0);
>
> We need a full barrier here to avoid reordering. Also, lets add a
> comment about why we are doing this odd looking sequence.
>
>> + gpu_read(gpu, REG_A6XX_GBIF_HALT);
>> if (adreno_is_a619_holi(adreno_gpu)) {
>> - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0);
>> gpu_write(gpu, REG_A6XX_RBBM_GPR0_CNTL, 0);
>> - /* Let's make extra sure that the GPU can access the memory.. */
>> - mb();
>
> We need a full barrier here.
>
>> + gpu_read(gpu, REG_A6XX_RBBM_GPR0_CNTL);
>> } else if (a6xx_has_gbif(adreno_gpu)) {
>> - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0);
>> gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 0);
>> - /* Let's make extra sure that the GPU can access the memory.. */
>> - mb();
>
> We need a full barrier here.
Not sure we do between REG_A6XX_GBIF_HALT & REG_A6XX_RBBM_(GBIF_HALT/GPR0_CNTL),
but I suppose keeping the one after REG_A6XX_RBBM_(GBIF_HALT/GPR0_CNTL) makes
sense to avoid the possibility of configuring the GPU before it can access DRAM..
>
>> + gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT);
>> }
>>
>> - /* Some GPUs are stubborn and take their sweet time to unhalt GBIF! */
>> - if (adreno_is_a7xx(adreno_gpu) && a6xx_has_gbif(adreno_gpu))
>> - spin_until(!gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK));
>> -
>
> Why is this removed?
Because it was a hack in the first place and the enforcement of GBIF
unhalt requests coming through before proceeding further removes the
necessity to check this (unless there's some hw-mandated delay we should
keep in mind, but kgsl doesn't have that and there doesn't seem to be
any from testing on 8[456]50).
Konrad
next prev parent reply other threads:[~2024-06-04 17:35 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-08 17:46 Konrad Dybcio
2024-05-14 18:38 ` Akhil P Oommen
2024-05-16 13:15 ` Andrew Halaney
2024-05-16 14:50 ` Akhil P Oommen
2024-05-16 18:55 ` Andrew Halaney
2024-06-04 14:40 ` Will Deacon
2024-06-06 12:03 ` Konrad Dybcio
2024-06-18 15:34 ` Will Deacon
2024-06-18 16:11 ` Akhil P Oommen
2024-06-20 13:04 ` Will Deacon
2024-06-25 18:02 ` Akhil P Oommen
2024-06-04 17:35 ` Konrad Dybcio [this message]
2024-06-18 16:38 ` Akhil P Oommen
2024-06-25 18:08 ` Akhil P Oommen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5ff40fba-e45a-4a5c-b5a7-7ef5a799a008@linaro.org \
--to=konrad.dybcio@linaro.org \
--cc=airlied@gmail.com \
--cc=daniel@ffwll.ch \
--cc=dmitry.baryshkov@linaro.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=freedreno@lists.freedesktop.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=marijn.suijten@somainline.org \
--cc=quic_abhinavk@quicinc.com \
--cc=quic_akhilpo@quicinc.com \
--cc=robdclark@chromium.org \
--cc=robdclark@gmail.com \
--cc=sean@poorly.run \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®