Reviewed-by: Yang Wang <kevinyang.wang@xxxxxxx>
Best Regards,
Kevin
-----Original Message-----
From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of Yang Wang
Sent: Wednesday, November 8, 2023 8:58 PM
To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Zhang, Hawking <Hawking.Zhang@xxxxxxx>
Subject: [PATCH 6/7] drm/amdgpu: correct acclerator check architecutre dump
From: Hawking Zhang <Hawking.Zhang@xxxxxxx>
So driver doesn't touch invalid aca entries.
Signed-off-by: Hawking Zhang <Hawking.Zhang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c | 15 +++++++++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h | 2 --
2 files changed, 11 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index 3302f4a29387..65926f3c708a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -202,10 +202,17 @@ int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry) {
- int i;
-
- for (i = 0; i < ARRAY_SIZE(entry->regs); i++)
- dev_dbg(adev->dev, "mca entry[%02d].regs[%02d]=0x%016llx\n", idx, i, entry->regs[i]);
+ dev_info(adev->dev, "[Hardware error] Accelerator Check Architecture events logged\n");
+ dev_info(adev->dev, "[Hardware error] aca entry[%02d].STATUS=0x%016llx\n",
+ idx, entry->regs[MCA_REG_IDX_STATUS]);
+ dev_info(adev->dev, "[Hardware error] aca entry[%02d].ADDR=0x%016llx\n",
+ idx, entry->regs[MCA_REG_IDX_ADDR]);
+ dev_info(adev->dev, "[Hardware error] aca entry[%02d].MISC0=0x%016llx\n",
+ idx, entry->regs[MCA_REG_IDX_MISC0]);
+ dev_info(adev->dev, "[Hardware error] aca entry[%02d].IPID=0x%016llx\n",
+ idx, entry->regs[MCA_REG_IDX_IPID]);
+ dev_info(adev->dev, "[Hardware error] aca entry[%02d].SYND=0x%016llx\n",
+ idx, entry->regs[MCA_REG_IDX_SYND]);
}
int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_block blk, enum amdgpu_mca_error_type type, struct ras_err_data *err_data) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index 45f90edf2283..e4f30d20170f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -79,11 +79,9 @@ struct amdgpu_mca {
};
enum mca_reg_idx {
- MCA_REG_IDX_CONTROL = 0,
MCA_REG_IDX_STATUS = 1,
MCA_REG_IDX_ADDR = 2,
MCA_REG_IDX_MISC0 = 3,
- MCA_REG_IDX_CONFIG = 4,
MCA_REG_IDX_IPID = 5,
MCA_REG_IDX_SYND = 6,
MCA_REG_IDX_COUNT = 16,
--
2.34.1
