[AMD Official Use Only - General]
This Patch looks good to me.
Reviewed-By: Frank.Min <Frank.Min@xxxxxxx>
-----Original Message-----
From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of Hawking Zhang
Sent: Monday, January 29, 2024 10:35 PM
To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
Cc: Zhang, Hawking <Hawking.Zhang@xxxxxxx>
Subject: [PATCH] drm/amdgpu: Update boot time errors polling sequence
Update boot time errors polling seqeunce to align with the latest firmware change.
Signed-off-by: Hawking Zhang <Hawking.Zhang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 +++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 5 +++++
2 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 9e67355d4718..9b7a5c1c9af5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -4122,6 +4122,18 @@ static int amdgpu_ras_wait_for_boot_complete(struct amdgpu_device *adev,
u32 reg_data;
int retry_loop;
+ reg_addr = (mmMP0_SMN_C2PMSG_92 << 2) +
+ aqua_vanjaram_encode_ext_smn_addressing(instance);
+
+ for (retry_loop = 0; retry_loop < AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT; retry_loop++) {
+ reg_data = amdgpu_device_indirect_rreg_ext(adev, reg_addr);
+ if ((reg_data & AMDGPU_RAS_BOOT_STATUS_MASK) == AMDGPU_RAS_BOOT_STEADY_STATUS) {
+ *boot_error = AMDGPU_RAS_BOOT_SUCEESS;
+ return 0;
+ }
+ msleep(1);
+ }
+
/* The pattern for smn addressing in other SOC could be different from
* the one for aqua_vanjaram. We should revisit the code if the pattern
* is changed. In such case, replace the aqua_vanjaram implementation @@ -4129,7 +4141,7 @@ static int amdgpu_ras_wait_for_boot_complete(struct amdgpu_device *adev,
reg_addr = (mmMP0_SMN_C2PMSG_126 << 2) +
aqua_vanjaram_encode_ext_smn_addressing(instance);
- for (retry_loop = 0; retry_loop < 1000; retry_loop++) {
+ for (retry_loop = 0; retry_loop <
+AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT; retry_loop++) {
reg_data = amdgpu_device_indirect_rreg_ext(adev, reg_addr);
if (AMDGPU_RAS_GPU_ERR_BOOT_STATUS(reg_data)) {
*boot_error = reg_data;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 0b6ffae1e8bb..d10e5bb0e52f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -46,6 +46,11 @@ struct amdgpu_iv_entry;
#define AMDGPU_RAS_GPU_ERR_HBM_ID(x) AMDGPU_GET_REG_FIELD(x, 13, 13)
#define AMDGPU_RAS_GPU_ERR_BOOT_STATUS(x) AMDGPU_GET_REG_FIELD(x, 31, 31)
+#define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT 1000
+#define AMDGPU_RAS_BOOT_STEADY_STATUS 0xBA
+#define AMDGPU_RAS_BOOT_STATUS_MASK 0xFF
+#define AMDGPU_RAS_BOOT_SUCEESS 0x80000000
+
#define AMDGPU_RAS_FLAG_INIT_BY_VBIOS (0x1 << 0)
/* position of instance value in sub_block_index of
* ta_ras_trigger_error_input, the sub block uses lower 12 bits
--
2.17.1
