[PATCH] amd/amdkfd: add ras page retirement handling for sq/sdma interrupt

[Zhang, Hawking]

[AMD Official Use Only]

How about we add a new member in ras context (amdgpu_ras) to indicate the poison consumption handling mode/approach? In such way, we can initialize that member per ASIC.

Regards,
Hawking

-----Original Message-----
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Zhang, Hawking
Sent: Tuesday, August 24, 2021 17:04
To: Zhou1, Tao <Tao.Zhou1 at amd.com>; amd-gfx at lists.freedesktop.org; Yang, Stanley <Stanley.Yang at amd.com>; Clements, John <John.Clements at amd.com>; Kuehling, Felix <Felix.Kuehling at amd.com>
Subject: RE: [PATCH] amd/amdkfd: add ras page retirement handling for sq/sdma interrupt

[AMD Official Use Only]

Hi Tao,

This will break mode 2 reset solution, right? But we have to keep mode 2 reset solution as the default one for now. I think we need a new interface to allow KFD switch between unmap_queue and mode 2 reset solution

Regards,
Hawking

-----Original Message-----
From: Zhou1, Tao <Tao.Zhou1 at amd.com> 
Sent: Tuesday, August 24, 2021 16:43
To: amd-gfx at lists.freedesktop.org; Zhang, Hawking <Hawking.Zhang at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>; Clements, John <John.Clements at amd.com>; Kuehling, Felix <Felix.Kuehling at amd.com>
Cc: Zhou1, Tao <Tao.Zhou1 at amd.com>
Subject: [PATCH] amd/amdkfd: add ras page retirement handling for sq/sdma interrupt

In ras poison mode, page retirement will be handled by the irq handler of the module which consumes corrupted data.

Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c    | 13 ++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c     | 10 ++++++++--
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h     |  1 +
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
index 46cd4ee6bafb..eb5e9c1b1073 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c
@@ -23,6 +23,16 @@
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_amdkfd_arcturus.h"
 #include "amdgpu_amdkfd_gfx_v9.h"
+#include "amdgpu_ras.h"
+#include "amdgpu_umc.h"
+
+int kgd_aldebaran_ras_process_cb(struct kgd_dev *kgd) {
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	struct ras_err_data err_data = {0, 0, 0, NULL};
+
+	return amdgpu_umc_process_ras_data_cb(adev, &err_data, NULL); }
 
 const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
@@ -44,5 +54,6 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
+	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings,
+	.ras_process_cb = kgd_aldebaran_ras_process_cb
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 12d91e53556c..851b5120927a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -231,7 +231,10 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 				if (sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_ILLEGAL_INST &&
 					sq_intr_err != SQ_INTERRUPT_ERROR_TYPE_MEMVIOL) {
 					kfd_signal_poison_consumed_event(dev, pasid);
-					amdgpu_amdkfd_gpu_reset(dev->kgd);
+					if (dev->kfd2kgd->ras_process_cb)
+						dev->kfd2kgd->ras_process_cb(dev->kgd);
+					else
+						amdgpu_amdkfd_gpu_reset(dev->kgd);
 					return;
 				}
 				break;
@@ -253,7 +256,10 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 			kfd_signal_event_interrupt(pasid, context_id0 & 0xfffffff, 28);
 		} else if (source_id == SOC15_INTSRC_SDMA_ECC) {
 			kfd_signal_poison_consumed_event(dev, pasid);
-			amdgpu_amdkfd_gpu_reset(dev->kgd);
+			if (dev->kfd2kgd->ras_process_cb)
+				dev->kfd2kgd->ras_process_cb(dev->kgd);
+			else
+				amdgpu_amdkfd_gpu_reset(dev->kgd);
 			return;
 		}
 	} else if (client_id == SOC15_IH_CLIENTID_VMC || diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index c84bd7b2cf59..9e6525871ad4 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -301,6 +301,7 @@ struct kfd2kgd_calls {
 			int *max_waves_per_cu);
 	void (*program_trap_handler_settings)(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr);
+	int (*ras_process_cb)(struct kgd_dev *kgd);
 };
 
 #endif	/* KGD_KFD_INTERFACE_H_INCLUDED */
--
2.17.1