From 13e3151a8f6d7a66300932ac0148597b47a9452e Mon Sep 17 00:00:00 2001
From: Victor Zhao <Victor.Zhao@amd.com>
Date: Thu, 13 Oct 2022 11:06:33 +0800
Subject: Revert "drm/amdgpu: let mode2 reset fallback to default when failure"
Git-commit: a340847b0214aa9b8fd9839f7b2822ccc607edab
Patch-mainline: v6.1-rc2
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849
Alt-commit: b98a1648d6616d288e888c6dc6dcd4fa543585b3
This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957.
This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts with
the original design of reset handler. Will redesign it.
Fixes: dac6b80818ac23 ("drm/amdgpu: let mode2 reset fallback to default when failure")
Signed-off-by: Victor Zhao <Victor.Zhao@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +------
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 6 ------
drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h | 3 +--
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 1 -
drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c | 1 -
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 1 -
9 files changed, 2 insertions(+), 20 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 03bbfaa51cbc..0561812aa0a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -134,7 +134,6 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ab8f970b2849..bb73fb420ffc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5210,7 +5210,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
reset_context->job = job;
reset_context->hive = hive;
-
/*
* Build list of devices to reset.
* In case we are in XGMI hive mode, resort the device list
@@ -5337,11 +5336,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
amdgpu_ras_resume(adev);
} else {
r = amdgpu_do_asic_reset(device_list_handle, reset_context);
- if (r && r == -EAGAIN) {
- set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags);
- adev->asic_reset_res = 0;
+ if (r && r == -EAGAIN)
goto retry;
- }
if (!r && gpu_reset_for_dev_remove)
goto recover_end;
@@ -5777,7 +5773,6 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
reset_context.reset_req_dev = adev;
set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
- set_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
adev->no_hw_access = true;
r = amdgpu_device_pre_asic_reset(adev, &reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 46c99331d7f1..cd968e781077 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -72,7 +72,6 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 2dad7aa9a03b..75f1402101f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1950,7 +1950,6 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index 831fb222139c..f778466bb9db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -74,9 +74,6 @@ int amdgpu_reset_prepare_hwcontext(struct amdgpu_device *adev,
{
struct amdgpu_reset_handler *reset_handler = NULL;
- if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
- return -ENOSYS;
-
if (adev->reset_cntl && adev->reset_cntl->get_reset_handler)
reset_handler = adev->reset_cntl->get_reset_handler(
adev->reset_cntl, reset_context);
@@ -93,9 +90,6 @@ int amdgpu_reset_perform_reset(struct amdgpu_device *adev,
int ret;
struct amdgpu_reset_handler *reset_handler = NULL;
- if (test_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context->flags))
- return -ENOSYS;
-
if (adev->reset_cntl)
reset_handler = adev->reset_cntl->get_reset_handler(
adev->reset_cntl, reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index f5318fedf2f0..f4a501ff87d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -30,8 +30,7 @@ enum AMDGPU_RESET_FLAGS {
AMDGPU_NEED_FULL_RESET = 0,
AMDGPU_SKIP_HW_RESET = 1,
- AMDGPU_SKIP_MODE2_RESET = 2,
- AMDGPU_RESET_FOR_DEVICE_REMOVE = 3,
+ AMDGPU_RESET_FOR_DEVICE_REMOVE = 2,
};
struct amdgpu_reset_context {
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index a2f04b249132..12906ba74462 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -290,7 +290,6 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index a977f0027928..e07757eea7ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -317,7 +317,6 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index fd14fa9b9cd7..288c414babdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -529,7 +529,6 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
reset_context.method = AMD_RESET_METHOD_NONE;
reset_context.reset_req_dev = adev;
clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
- clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags);
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
--
2.38.1