[PATCH] drm/amdgpu: Drop unnecessary sentences about CE and deferred error.

Zhang, Hawking Hawking.Zhang at amd.com
Thu Jan 4 06:15:48 UTC 2024


[AMD Official Use Only - General]

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

Regards,
Hawking
-----Original Message-----
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Candice Li
Sent: Thursday, January 4, 2024 13:25
To: amd-gfx at lists.freedesktop.org
Cc: Li, Candice <Candice.Li at amd.com>
Subject: [PATCH] drm/amdgpu: Drop unnecessary sentences about CE and deferred error.

Remove "no user action is needed" for correctable and deferred error to avoid confusion.

Signed-off-by: Candice Li <candice.li at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 +++++---------  drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c  |  3 +--  drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c  |  3 +--
 drivers/gpu/drm/amd/amdgpu/umc_v6_7.c   |  2 +-
 4 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b21eadd7c975df..caf00df669bf7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1069,8 +1069,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
                        mcm_info = &err_info->mcm_info;
                        if (err_info->ce_count) {
                                dev_info(adev->dev, "socket: %d, die: %d, "
-                                        "%lld new correctable hardware errors detected in %s block, "
-                                        "no user action is needed\n",
+                                        "%lld new correctable hardware errors detected in %s block\n",
                                         mcm_info->socket_id,
                                         mcm_info->die_id,
                                         err_info->ce_count,
@@ -1082,8 +1081,7 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
                        err_info = &err_node->err_info;
                        mcm_info = &err_info->mcm_info;
                        dev_info(adev->dev, "socket: %d, die: %d, "
-                                "%lld correctable hardware errors detected in total in %s block, "
-                                "no user action is needed\n",
+                                "%lld correctable hardware errors detected in total in %s
+block\n",
                                 mcm_info->socket_id, mcm_info->die_id, err_info->ce_count, blk_name);
                }
                break;
@@ -1139,16 +1137,14 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev,
                           adev->smuio.funcs->get_die_id) {
                        dev_info(adev->dev, "socket: %d, die: %d "
                                 "%ld correctable hardware errors "
-                                "detected in %s block, no user "
-                                "action is needed.\n",
+                                "detected in %s block\n",
                                 adev->smuio.funcs->get_socket_id(adev),
                                 adev->smuio.funcs->get_die_id(adev),
                                 ras_mgr->err_data.ce_count,
                                 blk_name);
                } else {
                        dev_info(adev->dev, "%ld correctable hardware errors "
-                                "detected in %s block, no user "
-                                "action is needed.\n",
+                                "detected in %s block\n",
                                 ras_mgr->err_data.ce_count,
                                 blk_name);
                }
@@ -1978,7 +1974,7 @@ static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj
                                struct amdgpu_iv_entry *entry)
 {
        dev_info(obj->adev->dev,
-               "Poison is created, no user action is needed.\n");
+               "Poison is created\n");
 }

 static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj, diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 6d24c84924cb5d..19986ff6a48d7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -401,8 +401,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device

                        if (err_data.ce_count)
                                dev_info(adev->dev, "%ld correctable hardware "
-                                               "errors detected in %s block, "
-                                               "no user action is needed.\n",
+                                               "errors detected in %s block\n",
                                                obj->err_data.ce_count,
                                                get_ras_block_str(adev->nbio.ras_if));

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 25a3da83e0fb97..e90f3378080345 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -597,8 +597,7 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device

                        if (err_data.ce_count)
                                dev_info(adev->dev, "%ld correctable hardware "
-                                               "errors detected in %s block, "
-                                               "no user action is needed.\n",
+                                               "errors detected in %s block\n",
                                                obj->err_data.ce_count,
                                                get_ras_block_str(adev->nbio.ras_if));

diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
index 530549314ce46c..a3ee3c4c650feb 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c
@@ -64,7 +64,7 @@ static void umc_v6_7_query_error_status_helper(struct amdgpu_device *adev,
        uint64_t reg_value;

        if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1)
-               dev_info(adev->dev, "Deferred error, no user action is needed.\n");
+               dev_info(adev->dev, "Deferred error\n");

        if (mc_umc_status)
                dev_info(adev->dev, "MCA STATUS 0x%llx, umc_reg_offset 0x%x\n", mc_umc_status, umc_reg_offset);
--
2.25.1



More information about the amd-gfx mailing list