[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240728154805.2049226-5-sashal@kernel.org>
Date: Sun, 28 Jul 2024 11:47:15 -0400
From: Sasha Levin <sashal@...nel.org>
To: linux-kernel@...r.kernel.org,
stable@...r.kernel.org
Cc: Victor Skvortsov <victor.skvortsov@....com>,
Zhigang Luo <zhigang.luo@....com>,
Alex Deucher <alexander.deucher@....com>,
Sasha Levin <sashal@...nel.org>,
christian.koenig@....com,
Xinhui.Pan@....com,
airlied@...il.com,
daniel@...ll.ch,
Hawking.Zhang@....com,
mario.limonciello@....com,
lijo.lazar@....com,
Jun.Ma2@....com,
candice.li@....com,
victorchengchi.lu@....com,
andrealmeid@...lia.com,
hamza.mahfooz@....com,
Jingwen.Chen2@....com,
Zhigang.Luo@....com,
surbhi.kakarya@....com,
sunran001@...suo.com,
chongli2@....com,
danijel.slivka@....com,
bokun.zhang@....com,
YiPeng.Chai@....com,
amd-gfx@...ts.freedesktop.org,
dri-devel@...ts.freedesktop.org
Subject: [PATCH AUTOSEL 6.1 05/17] drm/amdgpu: Add lock around VF RLCG interface
From: Victor Skvortsov <victor.skvortsov@....com>
[ Upstream commit e864180ee49b4d30e640fd1e1d852b86411420c9 ]
flush_gpu_tlb may be called from another thread while
device_gpu_recover is running.
Both of these threads access registers through the VF
RLCG interface during VF Full Access. Add a lock around this interface
to prevent race conditions between these threads.
Signed-off-by: Victor Skvortsov <victor.skvortsov@....com>
Reviewed-by: Zhigang Luo <zhigang.luo@....com>
Signed-off-by: Alex Deucher <alexander.deucher@....com>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 6 ++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 2 ++
3 files changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 157441dd07041..6d70b386c21ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3631,6 +3631,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
mutex_init(&adev->grbm_idx_mutex);
mutex_init(&adev->mn_lock);
mutex_init(&adev->virt.vf_errors.lock);
+ mutex_init(&adev->virt.rlcg_reg_lock);
hash_init(adev->mn_hash);
mutex_init(&adev->psp.mutex);
mutex_init(&adev->notifier_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 81549f1edfe01..5ee9211c503c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -956,6 +956,9 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v
scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1;
scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2;
scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3;
+
+ mutex_lock(&adev->virt.rlcg_reg_lock);
+
if (reg_access_ctrl->spare_int)
spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int;
@@ -1009,6 +1012,9 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v
}
ret = readl(scratch_reg0);
+
+ mutex_unlock(&adev->virt.rlcg_reg_lock);
+
return ret;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 2b9d806e23afb..dc6aaa4d67be7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -260,6 +260,8 @@ struct amdgpu_virt {
/* the ucode id to signal the autoload */
uint32_t autoload_ucode_id;
+
+ struct mutex rlcg_reg_lock;
};
struct amdgpu_video_codec_info;
--
2.43.0
Powered by blists - more mailing lists