linux-kernel - [PATCH v4 06/14] drm/msm/a6xx: Remove both GBIF and RBBM GBIF halt on hw init

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: <20230223-topic-gmuwrapper-v4-6-e987eb79d03f@linaro.org>
Date:   Tue, 14 Mar 2023 16:28:37 +0100
From:   Konrad Dybcio <konrad.dybcio@...aro.org>
To:     Rob Clark <robdclark@...il.com>,
        Abhinav Kumar <quic_abhinavk@...cinc.com>,
        Dmitry Baryshkov <dmitry.baryshkov@...aro.org>,
        Sean Paul <sean@...rly.run>, David Airlie <airlied@...il.com>,
        Daniel Vetter <daniel@...ll.ch>,
        Rob Herring <robh+dt@...nel.org>,
        Krzysztof Kozlowski <krzysztof.kozlowski+dt@...aro.org>,
        Bjorn Andersson <andersson@...nel.org>,
        Konrad Dybcio <konrad.dybcio@...ainline.org>,
        Akhil P Oommen <quic_akhilpo@...cinc.com>
Cc:     linux-arm-msm@...r.kernel.org, dri-devel@...ts.freedesktop.org,
        freedreno@...ts.freedesktop.org, devicetree@...r.kernel.org,
        linux-kernel@...r.kernel.org, Rob Clark <robdclark@...omium.org>,
        Marijn Suijten <marijn.suijten@...ainline.org>,
        Konrad Dybcio <konrad.dybcio@...aro.org>
Subject: [PATCH v4 06/14] drm/msm/a6xx: Remove both GBIF and RBBM GBIF halt
 on hw init

Currently we're only deasserting REG_A6XX_RBBM_GBIF_HALT, but we also
need REG_A6XX_GBIF_HALT to be set to 0. For GMU-equipped GPUs this is
done in a6xx_bus_clear_pending_transactions(), but for the GMU-less
ones we have to do it *somewhere*. Unhalting both side by side sounds
like a good plan and it won't cause any issues if it's unnecessary.

Also, add a memory barrier to ensure it's gone through.

Signed-off-by: Konrad Dybcio <konrad.dybcio@...aro.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index a90847a3379a..70e9bd21ba3b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1015,8 +1015,12 @@ static int hw_init(struct msm_gpu *gpu)
 	}
 
 	/* Clear GBIF halt in case GX domain was not collapsed */
-	if (a6xx_has_gbif(adreno_gpu))
+	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();
+	}
 
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0);
 

-- 
2.39.2