From: Aravind Iddamsetty <aravind.iddamsetty@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: riana.tauro@intel.com, rodrigo.vivi@intel.com,
himal.prasad.ghimiray@intel.com, anshuman.gupta@intel.com
Subject: [PATCH 07/10] drm/xe: Support SOC NONFATAL error handling for PVC.
Date: Wed, 30 Jul 2025 11:18:11 +0530 [thread overview]
Message-ID: <20250730054814.1376770-8-aravind.iddamsetty@linux.intel.com> (raw)
In-Reply-To: <20250730054814.1376770-1-aravind.iddamsetty@linux.intel.com>
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Report the SOC nonfatal hardware error and update the counters which
will increment incase of error.
v2
- Use xe_assign_hw_err_regs to initilaize registers.
- Dont use the counters if error is being reported by second level
registers.
- Fix Num of IEH to 2.
- Follow the convention source_typeoferror_errorname for enum and error
reporting.(Aravind)
Cc: Aravind Iddamsetty <aravind.iddamsetty@linux.intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@linux.intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
drivers/gpu/drm/xe/xe_hw_error.c | 70 +++++++++++++++++++++++++++++++-
drivers/gpu/drm/xe/xe_hw_error.h | 39 ++++++++++++++++++
2 files changed, 108 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 927bf2ab401f..705a670f01fc 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -260,6 +260,67 @@ static const struct err_name_index_pair pvc_soc_mstr_lcl_err_reg_fatal[] = {
[14 ... 31] = {"Undefined", XE_HW_ERR_SOC_FATAL_UNKNOWN},
};
+static const struct err_name_index_pair pvc_soc_mstr_glbl_err_reg_nonfatal[] = {
+ [0] = {"MASTER LOCAL Reported", XE_HW_ERR_TILE_UNSPEC},
+ [1] = {"SLAVE GLOBAL Reported", XE_HW_ERR_TILE_UNSPEC},
+ [2] = {"HBM SS0: Channel0", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL0},
+ [3] = {"HBM SS0: Channel1", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL1},
+ [4] = {"HBM SS0: Channel2", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL2},
+ [5] = {"HBM SS0: Channel3", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL3},
+ [6] = {"HBM SS0: Channel4", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL4},
+ [7] = {"HBM SS0: Channel5", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL5},
+ [8] = {"HBM SS0: Channel6", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL6},
+ [9] = {"HBM SS0: Channel7", XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL7},
+ [10] = {"HBM SS1: Channel0", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL0},
+ [11] = {"HBM SS1: Channel1", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL1},
+ [12] = {"HBM SS1: Channel2", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL2},
+ [13] = {"HBM SS1: Channel3", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL3},
+ [14] = {"HBM SS1: Channel4", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL4},
+ [15] = {"HBM SS1: Channel5", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL5},
+ [16] = {"HBM SS1: Channel6", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL6},
+ [17] = {"HBM SS1: Channel7", XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL7},
+ [18 ... 31] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+};
+
+static const struct err_name_index_pair pvc_soc_slave_glbl_err_reg_nonfatal[] = {
+ [0] = {"SLAVE LOCAL Reported", XE_HW_ERR_TILE_UNSPEC},
+ [1] = {"HBM SS2: Channel0", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL0},
+ [2] = {"HBM SS2: Channel1", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL1},
+ [3] = {"HBM SS2: Channel2", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL2},
+ [4] = {"HBM SS2: Channel3", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL3},
+ [5] = {"HBM SS2: Channel4", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL4},
+ [6] = {"HBM SS2: Channel5", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL5},
+ [7] = {"HBM SS2: Channel6", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL6},
+ [8] = {"HBM SS2: Channel7", XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL7},
+ [9] = {"HBM SS3: Channel0", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL0},
+ [10] = {"HBM SS3: Channel1", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL1},
+ [11] = {"HBM SS3: Channel2", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL2},
+ [12] = {"HBM SS3: Channel3", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL3},
+ [13] = {"HBM SS3: Channel4", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL4},
+ [14] = {"HBM SS3: Channel5", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL5},
+ [15] = {"HBM SS3: Channel6", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL6},
+ [16] = {"HBM SS3: Channel7", XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL7},
+ [18] = {"ANR MDFI", XE_HW_ERR_SOC_NONFATAL_ANR_MDFI},
+ [17] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+ [19 ... 31] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+};
+
+static const struct err_name_index_pair pvc_soc_slave_lcl_err_reg_nonfatal[] = {
+ [0 ... 31] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+};
+
+static const struct err_name_index_pair pvc_soc_mstr_lcl_err_reg_nonfatal[] = {
+ [0 ... 3] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+ [4] = {"Base Die MDFI T2T", XE_HW_ERR_SOC_NONFATAL_MDFI_T2T},
+ [5] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+ [6] = {"Base Die MDFI T2C", XE_HW_ERR_SOC_NONFATAL_MDFI_T2C},
+ [7] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+ [8] = {"Invalid CSC PSF Command Parity", XE_HW_ERR_SOC_NONFATAL_CSC_PSF_CMD},
+ [9] = {"Invalid CSC PSF Unexpected Completion", XE_HW_ERR_SOC_NONFATAL_CSC_PSF_CMP},
+ [10] = {"Invalid CSC PSF Unsupported Request", XE_HW_ERR_SOC_NONFATAL_CSC_PSF_REQ},
+ [11 ... 31] = {"Undefined", XE_HW_ERR_SOC_NONFATAL_UNKNOWN},
+};
+
static void xe_assign_hw_err_regs(struct xe_device *xe)
{
const struct err_name_index_pair **dev_err_stat = xe->hw_err_regs.dev_err_stat;
@@ -294,6 +355,10 @@ static void xe_assign_hw_err_regs(struct xe_device *xe)
soc_mstr_lcl[HARDWARE_ERROR_FATAL] = pvc_soc_mstr_lcl_err_reg_fatal;
soc_slave_glbl[HARDWARE_ERROR_FATAL] = pvc_soc_slave_glbl_err_reg_fatal;
soc_slave_lcl[HARDWARE_ERROR_FATAL] = pvc_soc_slave_lcl_err_reg_fatal;
+ soc_mstr_glbl[HARDWARE_ERROR_NONFATAL] = pvc_soc_mstr_glbl_err_reg_nonfatal;
+ soc_mstr_lcl[HARDWARE_ERROR_NONFATAL] = pvc_soc_mstr_lcl_err_reg_nonfatal;
+ soc_slave_glbl[HARDWARE_ERROR_NONFATAL] = pvc_soc_slave_glbl_err_reg_nonfatal;
+ soc_slave_lcl[HARDWARE_ERROR_NONFATAL] = pvc_soc_slave_lcl_err_reg_nonfatal;
}
}
@@ -556,7 +621,10 @@ xe_soc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
lockdep_assert_held(&tile_to_xe(tile)->irq.lock);
- if ((tile_to_xe(tile)->info.platform != XE_PVC) || hw_err != HARDWARE_ERROR_FATAL)
+ if (tile_to_xe(tile)->info.platform != XE_PVC)
+ return;
+
+ if (hw_err == HARDWARE_ERROR_CORRECTABLE)
return;
base = SOC_PVC_BASE;
diff --git a/drivers/gpu/drm/xe/xe_hw_error.h b/drivers/gpu/drm/xe/xe_hw_error.h
index ecd7edfcd38b..e43157aae938 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.h
+++ b/drivers/gpu/drm/xe/xe_hw_error.h
@@ -100,6 +100,45 @@ enum xe_tile_hw_errors {
XE_HW_ERR_SOC_FATAL_PCIE_PSF_CMD,
XE_HW_ERR_SOC_FATAL_PCIE_PSF_CMP,
XE_HW_ERR_SOC_FATAL_PCIE_PSF_REQ,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL0,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL1,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL2,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL3,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL4,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL5,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL6,
+ XE_HW_ERR_SOC_NONFATAL_HBM0_CHNL7,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL0,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL1,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL2,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL3,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL4,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL5,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL6,
+ XE_HW_ERR_SOC_NONFATAL_HBM1_CHNL7,
+ XE_HW_ERR_SOC_NONFATAL_UNKNOWN,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL0,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL1,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL2,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL3,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL4,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL5,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL6,
+ XE_HW_ERR_SOC_NONFATAL_HBM2_CHNL7,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL0,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL1,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL2,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL3,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL4,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL5,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL6,
+ XE_HW_ERR_SOC_NONFATAL_HBM3_CHNL7,
+ XE_HW_ERR_SOC_NONFATAL_ANR_MDFI,
+ XE_HW_ERR_SOC_NONFATAL_MDFI_T2T,
+ XE_HW_ERR_SOC_NONFATAL_MDFI_T2C,
+ XE_HW_ERR_SOC_NONFATAL_CSC_PSF_CMD,
+ XE_HW_ERR_SOC_NONFATAL_CSC_PSF_CMP,
+ XE_HW_ERR_SOC_NONFATAL_CSC_PSF_REQ,
};
enum gt_vctr_registers {
--
2.25.1
next prev parent reply other threads:[~2025-07-30 5:49 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-30 5:48 [PATCH 00/10] Supporting RAS on XE Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 01/10] drm/xe: Handle errors from various components Aravind Iddamsetty
2025-07-30 9:08 ` Michal Wajdeczko
2025-07-30 19:59 ` Rodrigo Vivi
2025-07-30 5:48 ` [PATCH 02/10] drm/xe: Add new helpers to log hardware errrors Aravind Iddamsetty
2025-07-30 8:55 ` Michal Wajdeczko
2025-07-30 5:48 ` [PATCH 03/10] drm/xe: Log and count the GT hardware errors Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 04/10] drm/xe: Support GT hardware error reporting for PVC Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 05/10] drm/xe: Support GSC " Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 06/10] drm/xe: Support SOC FATAL error handling " Aravind Iddamsetty
2025-07-30 5:48 ` Aravind Iddamsetty [this message]
2025-07-30 5:48 ` [PATCH 08/10] drm/xe: Handle MDFI error severity Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 09/10] drm/xe: Clear SOC CORRECTABLE error registers Aravind Iddamsetty
2025-07-30 5:48 ` [PATCH 10/10] drm/xe: Clear all SoC errors post warm reset Aravind Iddamsetty
2025-07-30 5:57 ` ✗ CI.checkpatch: warning for Supporting RAS on XE Patchwork
2025-07-30 5:58 ` ✓ CI.KUnit: success " Patchwork
2025-07-30 6:59 ` ✗ Xe.CI.BAT: failure " Patchwork
2025-07-30 8:03 ` ✗ Xe.CI.Full: " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250730054814.1376770-8-aravind.iddamsetty@linux.intel.com \
--to=aravind.iddamsetty@linux.intel.com \
--cc=anshuman.gupta@intel.com \
--cc=himal.prasad.ghimiray@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=riana.tauro@intel.com \
--cc=rodrigo.vivi@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).