drm/amdgpu/ras: only check bad page for address-based UMC injection
Subsystems (2)
PATCH v2 1/1 drm/amdgpu/ras: only check bad page for address-based UMC injection
UMC error injection on MI300 series is dispatched by the RAS TA via the (sub-block, method) pair; only the "coherent" methods are address based, the single-shot/persistent/ac-parity ones ignore the address.
The debugfs control path validated the injection address against the bad page list for every UMC injection. Restrict that check to address-based injections and warn when a non address-based one is given a non-zero address. Other ASICs keep injecting by address.
Changed from V1:
move address based checking to uniras layer
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 +++- .../gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c | 58 ++++++++++++++++++- 2 files changed, 65 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +8 -2
@@ -606,8 +606,14 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, ret =amdgpu_ras_feature_enable (adev, &data.head,1 );break ;case 2 : -/* umc ce/ue error injection for a bad page is not allowed */ -if (data.head.block ==AMDGPU_RAS_BLOCK__UMC ) +/* +* UMC ce/ue error injection for a bad page is not allowed. For +* uniras (SMU v13+) devices the injection address is validated by +* the ras_mgr inject handler, so only run the legacy bad page +* check for the legacy RAS path. +*/ +if (data.head.block ==AMDGPU_RAS_BLOCK__UMC && + !amdgpu_uniras_enabled (adev)) ret =amdgpu_ras_check_bad_page (adev, data.inject.address);if (ret == -EINVAL ) { dev_warn(adev->dev, "RAS WARN: input address 0x%llx is invalid.",
drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +57 -1
76 lines not on this page · raw message
Signature · 1 line
2.43.0
AMD General
Thinking about it more, would it be better to add error-checking logic in the debugfs parser?
When the address parameter is set, we should also check the sub_block parameter to ensure the injection method is applied correctly to the intended sub-blocks. Otherwise, we should reject the debugfs ctrl command.
Any thoughts?
Regards,
Hawking
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Stanley.Yang
Sent: Thursday, July 2, 2026 6:32 PM
To: [email protected]
Cc: Yang, Stanley <[email protected]>
Subject: [PATCH V2 1/1] drm/amdgpu/ras: only check bad page for address-based UMC injection
UMC error injection on MI300 series is dispatched by the RAS TA via the (sub-block, method) pair; only the "coherent" methods are address based, the single-shot/persistent/ac-parity ones ignore the address.
The debugfs control path validated the injection address against the bad page list for every UMC injection. Restrict that check to address-based injections and warn when a non address-based one is given a non-zero address. Other ASICs keep injecting by address.
Changed from V1:
move address based checking to uniras layer
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 +++- .../gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c | 58 ++++++++++++++++++- 2 files changed, 65 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +8 -2
@@ -606,8 +606,14 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, ret =amdgpu_ras_feature_enable (adev, &data.head,1 );break ;case 2 : -/* umc ce/ue error injection for a bad page is not allowed */ -if (data.head.block ==AMDGPU_RAS_BLOCK__UMC ) +/* +* UMC ce/ue error injection for a bad page is not allowed. For +* uniras (SMU v13+) devices the injection address is validated by +* the ras_mgr inject handler, so only run the legacy bad page +* check for the legacy RAS path. +*/ +if (data.head.block ==AMDGPU_RAS_BLOCK__UMC && + !amdgpu_uniras_enabled (adev)) ret =amdgpu_ras_check_bad_page (adev, data.inject.address);if (ret == -EINVAL ) { dev_warn(adev->dev, "RAS WARN: input address 0x%llx is invalid.", diff --git a/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c b/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c
index bfbfdffbfbe6..063c7b0a7b00 100644
drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +54 -0
57 lines not on this page · raw message
struct ras_cmd_ctx *cmd, void *data) { @@ -90,7 +141,8 @@ static int amdgpu_ras_inject_error(struct ras_core_context *ras_core,
(struct ras_cmd_inject_error_req *)cmd->input_buff_raw;
int ret = RAS_CMD__ERROR_GENERIC;- if (req->block_id == RAS_BLOCK_ID__UMC) {
+ if (req->block_id == RAS_BLOCK_ID__UMC &&
+ amdgpu_ras_umc_inject_is_address_based(req->subblock_id,
+req->method)) {
if (amdgpu_ras_mgr_check_retired_addr(adev, req->address)) {
RAS_DEV_WARN(ras_core->dev,
"RAS WARN: inject: 0x%llx has already been marked as bad!\n", @@ -111,6 +163,10 @@ static int amdgpu_ras_inject_error(struct ras_core_context *ras_core,
req->block_id != RAS_BLOCK_ID__GFX) {
req->address = local_addr_to_xgmi_global_addr(ras_core, req->address);
}
+ } else if (req->block_id == RAS_BLOCK_ID__UMC && req->address) {
+ RAS_DEV_WARN(adev,
+ "RAS WARN: non address based injection, ignore the injection address 0x%llx\n",
+ req->address);
}
amdgpu_ras_trigger_error_prepare(ras_core, req);--
2.43.0
AMD General
Quoted 8 lines
-----Original Message-----
From: Zhang, Hawking <[email protected]>
Sent: Friday, July 3, 2026 9:57 PM
To: Yang, Stanley <[email protected]>; [email protected]
Cc: Yang, Stanley <[email protected]>
Subject: RE: [PATCH V2 1/1] drm/amdgpu/ras: only check bad page for address-based UMC injection
Quoted 4 lines
AMD General
Thinking about it more, would it be better to add error-checking logic in the debugfs parser?
[Stanley]: We should consider the introduction of ioctl interface in future, so the debugfs parser will not be called.
Quoted 4 lines
When the address parameter is set, we should also check the
sub_blockparameter to ensure the injection method is applied correctly to the intended sub-blocks. Otherwise, we should reject the debugfs ctrl command.
[Stanley]: How to handle the injection address 0x0 if user wants to inject address 0x0, currently, driver cannot distinguish whether the user injects address 0x0 or non-address-based injection.
Quoted 151 lines
Any thoughts?
Regards,
Hawking-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Stanley.Yang
Sent: Thursday, July 2, 2026 6:32 PM
To: [email protected]
Cc: Yang, Stanley <[email protected]>
Subject: [PATCH V2 1/1] drm/amdgpu/ras: only check bad page for address- based UMC injectionUMC error injection on MI300 series is dispatched by the RAS TA via the (sub- block, method) pair; only the "coherent" methods are address based, the single-shot/persistent/ac-parity ones ignore the address.
The debugfs control path validated the injection address against the bad page list for every UMC injection. Restrict that check to address-based injections and warn when a non address-based one is given a non-zero address. Other ASICs keep injecting by address.
Changed from V1:
move address based checking to uniras layerSigned-off-by Stanley.Yang <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 +++- .../gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c | 58 ++++++++++++++++++- 2 files changed, 65 insertions(+), 3 deletions(-)drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +8
-2@@ -606,8 +606,14 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(structfile *f, ret =amdgpu_ras_feature_enable (adev, &data.head,1 );break ;case 2 : -/* umc ce/ue error injection for a bad page is not allowed */ -if (data.head.block ==AMDGPU_RAS_BLOCK__UMC ) +/* +* UMC ce/ue error injection for a bad page is not allowed. For +* uniras (SMU v13+) devices the injection address is validated by +* the ras_mgr inject handler, so only run the legacy bad page +* check for the legacy RAS path. +*/ +if (data.head.block ==AMDGPU_RAS_BLOCK__UMC && + !amdgpu_uniras_enabled (adev)) ret =amdgpu_ras_check_bad_page (adev, data.inject.address);if (ret == -EINVAL ) {dev_warn(adev->dev, "RAS WARN: input address 0x%llx isinvalid.", diff --git
a/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.cb/drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c
indexbfbfdffbfbe6..063c7b0a7b00100644drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +0
-0@@ -82,6 +82,57 @@ static uint64_t local_addr_to_xgmi_global_addr(struct
ras_core_context*ras_corereturn (addr + xgmi->physical_node_id * xgmi->node_segment_size); }drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +5
-0+/* +* UMC error injection is dispatched by the RAS TA using the +(sub-block, method) +* pair carried in struct ras_cmd_inject_error_req as subblock_id (enum +* error_sub_block_umc) and method (enum inject_method_umc). Only the "coherent"
+ * methods program an explicit injection address and are thereforedrivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +48
-0+address-based; +* the single-shot, persistent and ac-parity methods ignore the address. +* +* Keep the values below in sync with the RAS TA. +*/ +enum umc_error_sub_block { +UMC_ERROR_CRC =0 , +UMC_ERROR_SRAM =1 , +UMC_ERROR_ODECC =2 , +UMC_ERROR_PARITY_DATA =3 , +UMC_ERROR_PARITY_CMD =4 , +}; + +enum umc_inject_method { +UMC_METH_COHERENT =0 , +UMC_METH_SINGLE_SHOT =1 , +UMC_METH_PERSISTENT =2 , +UMC_METH_PERSISTENT_DISABLE =3 , +UMC_METH_COHERENT_NO_DETECTION =4 , +UMC_METH_COHERENT_WR =5 , +UMC_METH_SINGLE_SHOT_WR =6 , +UMC_METH_PERSISTENT_WR =7 , +UMC_METH_SINGLE_SHOT_CLEAN =8 , +}; + +/* +* Return true if a UMC error injection using @sub_block and @method is +* address-based, i.e. it programs an explicit injection address that +must be +* validated. The non address-based methods ignore the address. +*/ +static bool amdgpu_ras_umc_inject_is_address_based (u32 sub_block,u64 +method) { +switch (sub_block) { +case UMC_ERROR_CRC : +return method ==UMC_METH_COHERENT || + method ==UMC_METH_COHERENT_NO_DETECTION || + method ==UMC_METH_COHERENT_WR ; +case UMC_ERROR_ODECC : +return method ==UMC_METH_COHERENT ; +case UMC_ERROR_PARITY_DATA : +return method ==UMC_METH_COHERENT || + method ==UMC_METH_COHERENT_WR ; +default : +return false; + } +} +static int amdgpu_ras_inject_error (struct ras_core_context *ras_core, struct ras_cmd_ctx *cmd, void *data) { @@ -90,7 +141,8 @@static int amdgpu_ras_inject_error(struct
ras_core_context*ras_core,(struct ras_cmd_inject_error_req *)cmd->input_buff_raw; int ret = RAS_CMD__ERROR_GENERIC;drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +3
-1-if (req->block_id ==RAS_BLOCK_ID__UMC ) { +if (req->block_id ==RAS_BLOCK_ID__UMC && +amdgpu_ras_umc_inject_is_address_based (req->subblock_id, +req->method)) {if (amdgpu_ras_mgr_check_retired_addr (adev, req->address)) { RAS_DEV_WARN(ras_core->dev, "RAS WARN: inject: 0x%llx has already been marked asbad!\n", @@ -111,6 +163,10 @@ static int amdgpu_ras_inject_error(struct
ras_core_context*ras_core,req->block_id != RAS_BLOCK_ID__GFX) { req->address = local_addr_to_xgmi_global_addr(ras_core, req-Quoted 1 line
address);
}drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_ras_cmd.c +3
-0+ }else if (req->block_id ==RAS_BLOCK_ID__UMC && req->address) { + RAS_DEV_WARN(adev, + "RAS WARN: non address based injection, ignore the injectionaddress 0x%llx\n",
+ req->address); } amdgpu_ras_trigger_error_prepare(ras_core, req);--
2.43.0