git/linux-cryptodev-2.6
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git synced 2026-04-18 11:33:36 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: Fix CPER error handling on VFs

Browse Source 
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: Tony Yi <Tony.Yi@amd.com>
Signed-off-by: Victor Skvortsov <Victor.Skvortsov@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Victor Skvortsov
2025-03-30 13:54:06 -05:00
committed by Alex Deucher
parent 7bb430f087
commit f9fbc33881
1 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
View File

@@ -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);