This is a note to let you know that I've just added the patch titled
drm/amdgpu: Fix ecc irq enable/disable unpaired
to the 6.7-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdgpu-fix-ecc-irq-enable-disable-unpaired.patch
and it can be found in the queue-6.7 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 404cd9d530e10c01c33c1a4b79fb1dc12a661af2
Author: Stanley.Yang <Stanley.Yang@xxxxxxx>
Date: Fri Dec 15 16:13:23 2023 +0800
drm/amdgpu: Fix ecc irq enable/disable unpaired
[ Upstream commit a32c6f7f5737cc7e31cd7ad5133f0d96fca12ea6 ]
The ecc_irq is disabled while GPU mode2 reset suspending process,
but not be enabled during GPU mode2 reset resume process.
Changed from V1:
only do sdma/gfx ras_late_init in aldebaran_mode2_restore_ip
delete amdgpu_ras_late_resume function
Changed from V2:
check umc ras supported before put ecc_irq
Signed-off-by: Stanley.Yang <Stanley.Yang@xxxxxxx>
Reviewed-by: Tao Zhou <tao.zhou1@xxxxxxx>
Reviewed-by: Hawking Zhang <Hawking.Zhang@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
index 02f4c6f9d4f6..576067d66bb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -330,6 +330,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
{
struct list_head *reset_device_list = reset_context->reset_device_list;
struct amdgpu_device *tmp_adev = NULL;
+ struct amdgpu_ras *con;
int r;
if (reset_device_list == NULL)
@@ -355,7 +356,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
*/
amdgpu_register_gpu_instance(tmp_adev);
- /* Resume RAS */
+ /* Resume RAS, ecc_irq */
+ con = amdgpu_ras_get_context(tmp_adev);
+ if (!amdgpu_sriov_vf(tmp_adev) && con) {
+ if (tmp_adev->sdma.ras &&
+ tmp_adev->sdma.ras->ras_block.ras_late_init) {
+ r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev,
+ &tmp_adev->sdma.ras->ras_block.ras_comm);
+ if (r) {
+ dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r);
+ goto end;
+ }
+ }
+
+ if (tmp_adev->gfx.ras &&
+ tmp_adev->gfx.ras->ras_block.ras_late_init) {
+ r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev,
+ &tmp_adev->gfx.ras->ras_block.ras_comm);
+ if (r) {
+ dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r);
+ goto end;
+ }
+ }
+ }
+
amdgpu_ras_resume(tmp_adev);
/* Update PSP FW topology after reset */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index a5a05c16c10d..6c5185608854 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1041,6 +1041,10 @@ static int gmc_v10_0_hw_fini(void *handle)
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+ if (adev->gmc.ecc_irq.funcs &&
+ amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+ amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 23d7b548d13f..c9c653cfc765 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -941,6 +941,11 @@ static int gmc_v11_0_hw_fini(void *handle)
}
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+
+ if (adev->gmc.ecc_irq.funcs &&
+ amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+ amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
gmc_v11_0_gart_disable(adev);
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 77e625f24cd0..776acdfc7209 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -2381,6 +2381,10 @@ static int gmc_v9_0_hw_fini(void *handle)
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+ if (adev->gmc.ecc_irq.funcs &&
+ amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+ amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
return 0;
}
