[PATCH 1/2] drm/amdgpu: Separate vf2pf work item init from virt data exchange

Victor Skvortsov victor.skvortsov at amd.com
Thu Dec 9 16:48:08 UTC 2021


We want to be able to call virt data exchange conditionally
after gmc sw init to reserve bad pages as early as possible.
Since this is a conditional call, we will need to call
it again unconditionally later in the init sequence.

Refactor the data exchange function so it can be
called multiple times without re-initializing the work item.

Signed-off-by: Victor Skvortsov <victor.skvortsov at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c   | 42 ++++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h   |  5 +--
 drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c      |  2 +-
 drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c      |  2 +-
 5 files changed, 45 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ce9bdef185c0..3992c4086d26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2181,7 +2181,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 
 			/*get pf2vf msg info at it's earliest time*/
 			if (amdgpu_sriov_vf(adev))
-				amdgpu_virt_init_data_exchange(adev);
+				amdgpu_virt_exchange_data(adev);
 
 		}
 	}
@@ -2345,8 +2345,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 	}
 
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_init_data_exchange(adev);
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_exchange_data(adev);
+		amdgpu_virt_init_vf2pf_work_item(adev);
+	}
 
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
@@ -2949,7 +2951,7 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	int r;
 
 	if (amdgpu_sriov_vf(adev)) {
-		amdgpu_virt_fini_data_exchange(adev);
+		amdgpu_virt_fini_vf2pf_work_item(adev);
 		amdgpu_virt_request_full_gpu(adev, false);
 	}
 
@@ -3839,7 +3841,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	 * */
 	if (amdgpu_sriov_vf(adev)) {
 		amdgpu_virt_request_full_gpu(adev, false);
-		amdgpu_virt_fini_data_exchange(adev);
+		amdgpu_virt_fini_vf2pf_work_item(adev);
 	}
 
 	/* disable all interrupts */
@@ -4317,7 +4319,9 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	amdgpu_virt_init_data_exchange(adev);
+	amdgpu_virt_exchange_data(adev);
+	amdgpu_virt_init_vf2pf_work_item(adev);
+
 	/* we need recover gart prior to run SMC/CP/SDMA resume */
 	amdgpu_gtt_mgr_recover(ttm_manager_type(&adev->mman.bdev, TTM_PL_TT));
 
@@ -4495,7 +4499,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 	if (amdgpu_sriov_vf(adev)) {
 		/* stop the data exchange thread */
-		amdgpu_virt_fini_data_exchange(adev);
+		amdgpu_virt_fini_vf2pf_work_item(adev);
 	}
 
 	/* block all schedulers and reset given job's ring */
@@ -4898,7 +4902,7 @@ static void amdgpu_device_recheck_guilty_jobs(
 retry:
 			/* do hw reset */
 			if (amdgpu_sriov_vf(adev)) {
-				amdgpu_virt_fini_data_exchange(adev);
+				amdgpu_virt_fini_vf2pf_work_item(adev);
 				r = amdgpu_device_reset_sriov(adev, false);
 				if (r)
 					adev->asic_reset_res = r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 3fc49823f527..b6e3d379a86a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -611,16 +611,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
 	schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
 }
 
-void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev)
-{
-	if (adev->virt.vf2pf_update_interval_ms != 0) {
-		DRM_INFO("clean up the vf2pf work item\n");
-		cancel_delayed_work_sync(&adev->virt.vf2pf_work);
-		adev->virt.vf2pf_update_interval_ms = 0;
-	}
-}
-
-void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
+void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 {
 	uint64_t bp_block_offset = 0;
 	uint32_t bp_block_size = 0;
@@ -628,11 +619,8 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 
 	adev->virt.fw_reserve.p_pf2vf = NULL;
 	adev->virt.fw_reserve.p_vf2pf = NULL;
-	adev->virt.vf2pf_update_interval_ms = 0;
 
 	if (adev->mman.fw_vram_usage_va != NULL) {
-		adev->virt.vf2pf_update_interval_ms = 2000;
-
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amd_sriov_msg_pf2vf_info_header *)
 			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
@@ -666,13 +654,39 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 
 		return;
 	}
+}
+
+void amdgpu_virt_init_vf2pf_work_item(struct amdgpu_device *adev)
+{
+	if (adev->mman.fw_vram_usage_va != NULL) {
+
+		/* Inverval value is passed from the host.
+		 * Correct too large or too little interval value
+		 */
+		if (adev->virt.vf2pf_update_interval_ms < 200 || adev->virt.vf2pf_update_interval_ms > 10000)
+			adev->virt.vf2pf_update_interval_ms = 2000;
+
+		adev->virt.fw_reserve.p_pf2vf =
+			(struct amd_sriov_msg_pf2vf_info_header *)
+			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
+		adev->virt.fw_reserve.p_vf2pf =
+			(struct amd_sriov_msg_vf2pf_info_header *)
+			(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
 
-	if (adev->virt.vf2pf_update_interval_ms != 0) {
 		INIT_DELAYED_WORK(&adev->virt.vf2pf_work, amdgpu_virt_update_vf2pf_work_item);
 		schedule_delayed_work(&(adev->virt.vf2pf_work), adev->virt.vf2pf_update_interval_ms);
 	}
 }
 
+void amdgpu_virt_fini_vf2pf_work_item(struct amdgpu_device *adev)
+{
+	if (adev->virt.vf2pf_update_interval_ms != 0) {
+		DRM_INFO("clean up the vf2pf work item\n");
+		cancel_delayed_work_sync(&adev->virt.vf2pf_work);
+		adev->virt.vf2pf_update_interval_ms = 0;
+	}
+}
+
 void amdgpu_detect_virtualization(struct amdgpu_device *adev)
 {
 	uint32_t reg;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 8d4c20bb71c5..c18a7daab693 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -307,8 +307,9 @@ int amdgpu_virt_wait_reset(struct amdgpu_device *adev);
 int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_free_mm_table(struct amdgpu_device *adev);
 void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev);
-void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
-void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev);
+void amdgpu_virt_exchange_data(struct amdgpu_device *adev);
+void amdgpu_virt_init_vf2pf_work_item(struct amdgpu_device *adev);
+void amdgpu_virt_fini_vf2pf_work_item(struct amdgpu_device *adev);
 void amdgpu_detect_virtualization(struct amdgpu_device *adev);
 
 bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 23b066bcffb2..cd2719bc0139 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -255,7 +255,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	if (!down_write_trylock(&adev->reset_sem))
 		return;
 
-	amdgpu_virt_fini_data_exchange(adev);
+	amdgpu_virt_fini_vf2pf_work_item(adev);
 	atomic_set(&adev->in_gpu_reset, 1);
 
 	xgpu_ai_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index a35e6d87e537..2bc93808469a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -284,7 +284,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	if (!down_write_trylock(&adev->reset_sem))
 		return;
 
-	amdgpu_virt_fini_data_exchange(adev);
+	amdgpu_virt_fini_vf2pf_work_item(adev);
 	atomic_set(&adev->in_gpu_reset, 1);
 
 	xgpu_nv_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
-- 
2.25.1



More information about the amd-gfx mailing list