[PATCH v3] drm/amd/amdgpu: fixing read wrong pf2vf data in SRIOV

Skvortsov, Victor Victor.Skvortsov at amd.com
Fri Jan 14 06:12:00 UTC 2022


[AMD Official Use Only]

+Shaoyun

-----Original Message-----
From: Chen, JingWen <JingWen.Chen2 at amd.com> 
Sent: Thursday, January 13, 2022 11:09 PM
To: amd-gfx at lists.freedesktop.org
Cc: Liu, Monk <Monk.Liu at amd.com>; Chen, Horace <Horace.Chen at amd.com>; Skvortsov, Victor <Victor.Skvortsov at amd.com>; Chen, JingWen <JingWen.Chen2 at amd.com>
Subject: [PATCH v3] drm/amd/amdgpu: fixing read wrong pf2vf data in SRIOV

[Why]
This fixes 35709bd76d229a51b0c571a768b741650ec47828.
we should read pf2vf data based at mman.fw_vram_usage_va after gmc sw_init. patch 35709bd76 breaks this logic.

[How]
calling amdgpu_virt_exchange_data in amdgpu_virt_init_data_exchange to set the right base in the right sequence.

v2:
call amdgpu_virt_init_data_exchange after gmc sw_init to make data exchange workqueue run

v3:
clean up the code logic

Signed-off-by: Jingwen Chen <Jingwen.Chen2 at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c   | 12 ++++--------
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index da3348fa7b0e..5610eae8ef0c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2353,7 +2353,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_exchange_data(adev);
+		amdgpu_virt_init_data_exchange(adev);
 
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 894444ab0032..d83dfdc64d49 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -625,14 +625,16 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 	adev->virt.fw_reserve.p_vf2pf = NULL;
 	adev->virt.vf2pf_update_interval_ms = 0;
 
-	if (adev->bios != NULL) {
+	if (adev->mman.fw_vram_usage_va != NULL) {
 		adev->virt.vf2pf_update_interval_ms = 2000;
-
+		amdgpu_virt_exchange_data(adev);
+	} else if (adev->bios != NULL) {
 		adev->virt.fw_reserve.p_pf2vf =
 			(struct amd_sriov_msg_pf2vf_info_header *)
 			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
 
 		amdgpu_virt_read_pf2vf_data(adev);
+		return;
 	}
 
 	if (adev->virt.vf2pf_update_interval_ms != 0) { @@ -674,12 +676,6 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 				if (adev->virt.ras_init_done)
 					amdgpu_virt_add_bad_page(adev, bp_block_offset, bp_block_size);
 			}
-	} else if (adev->bios != NULL) {
-		adev->virt.fw_reserve.p_pf2vf =
-			(struct amd_sriov_msg_pf2vf_info_header *)
-			(adev->bios + (AMD_SRIOV_MSG_PF2VF_OFFSET_KB << 10));
-
-		amdgpu_virt_read_pf2vf_data(adev);
 	}
 }
 
--
2.30.2


More information about the amd-gfx mailing list