Commit f9fbc338 authored by Victor Skvortsov's avatar Victor Skvortsov Committed by Alex Deucher
Browse files

drm/amdgpu: Fix CPER error handling on VFs 



CPER read will loop infinitely if an error is encountered and
the more bit is set. Add error checks to break upon failure.

v2: added function pointer checks

Suggested-by: default avatarTony Yi <Tony.Yi@amd.com>
Signed-off-by: default avatarVictor Skvortsov <Victor.Skvortsov@amd.com>
Reviewed-by: default avatarHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 7bb430f0

drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c

+12 −4
Original line number Diff line number Diff line
@@ -1323,6 +1323,9 @@ static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bo 
{

	struct amdgpu_virt *virt = &adev->virt;



	if (!virt->ops || !virt->ops->req_ras_err_count)

		return -EOPNOTSUPP;



	/* Host allows 15 ras telemetry requests per 60 seconds. Afterwhich, the Host

	 * will ignore incoming guest messages. Ratelimit the guest messages to

	 * prevent guest self DOS.
@@ -1378,14 +1381,16 @@ amdgpu_virt_write_cpers_to_ring(struct amdgpu_device *adev, 
	used_size = host_telemetry->header.used_size;



	if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10))

		return 0;

		return -EINVAL;



	cper_dump = kmemdup(&host_telemetry->body.cper_dump, used_size, GFP_KERNEL);

	if (!cper_dump)

		return -ENOMEM;



	if (checksum != amd_sriov_msg_checksum(cper_dump, used_size, 0, 0))

	if (checksum != amd_sriov_msg_checksum(cper_dump, used_size, 0, 0)) {

		ret = -EINVAL;

		goto out;

	}



	*more = cper_dump->more;
@@ -1425,7 +1430,7 @@ static int amdgpu_virt_req_ras_cper_dump_internal(struct amdgpu_device *adev) 
	int ret = 0;

	uint32_t more = 0;



	if (!amdgpu_sriov_ras_cper_en(adev))

	if (!virt->ops || !virt->ops->req_ras_cper_dump)

		return -EOPNOTSUPP;



	do {
@@ -1434,7 +1439,7 @@ static int amdgpu_virt_req_ras_cper_dump_internal(struct amdgpu_device *adev) 
				adev, virt->fw_reserve.ras_telemetry, &more);

		else

			ret = 0;

	} while (more);

	} while (more && !ret);



	return ret;

}
@@ -1444,6 +1449,9 @@ int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update) 
	struct amdgpu_virt *virt = &adev->virt;

	int ret = 0;



	if (!amdgpu_sriov_ras_cper_en(adev))

		return -EOPNOTSUPP;



	if ((__ratelimit(&virt->ras.ras_cper_dump_rs) || force_update) &&

	    down_read_trylock(&adev->reset_domain->sem)) {

		mutex_lock(&virt->ras.ras_telemetry_mutex);