kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c, branch v6.6.131Linux kernel stable tree (mirror)https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.1312023-06-15T15:06:59+00:00drm/amdgpu: Optimize checking ras supported2023-06-15T15:06:59+00:00Stanley.YangStanley.Yang@amd.com2023-06-12T07:25:05+00:00urn:sha1:38298ce6fc35c65ba1364e4221a289dfa07bf5ea
Using "is_app_apu" to identify device in the native
APU mode or carveout mode.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: optimize redundant code in umc_v8_102023-04-11T22:03:44+00:00YiPeng ChaiYiPeng.Chai@amd.com2023-03-27T06:23:30+00:00urn:sha1:e86bd8b21d57670e38c23ed435a053e7e4cc9e21
Optimize redundant code in umc_v8_10
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Initialize umc ras callback2023-03-22T04:48:01+00:00Hawking ZhangHawking.Zhang@amd.com2023-03-20T09:33:47+00:00urn:sha1:cfa075982768840c468c874219dbec558722cb7f
Fix a coding error which results to null interrupt
handler for umc ras.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Move umc ras block init to gmc ras sw_init2023-03-13T21:27:48+00:00Hawking ZhangHawking.Zhang@amd.com2023-03-11T09:36:11+00:00urn:sha1:a6dcf9a7ccfed57abd44c24cc505b559281d44b9
Initialize umc ras block only when umc ip block
supports ras. Driver queries ras capabilities after
early_init, ras block init needs to be moved to
sw_init.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: exclude duplicate pages from UMC RAS UE count2023-02-23T22:35:59+00:00Tao Zhoutao.zhou1@amd.com2023-02-10T08:33:58+00:00urn:sha1:4d33e0f1340b3d08002ff8f9bcbf256cfdc4f3ba
If a UMC bad page is reserved but not freed by an application, the
application may trigger uncorrectable error repeatly by accessing the page.
v2: add specific function to do the check.
v3: remove duplicate pages, calculate new added bad page number.
v4: reuse save_bad_pages to calculate new added bad page number.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: add RAS poison consumption handler for SRIOV2022-12-15T17:18:19+00:00Tao Zhoutao.zhou1@amd.com2022-12-08T03:17:56+00:00urn:sha1:e643823d62f2f30badaa72358b927a1de113024e
Send message to PF if VF receives RAS poison consumption interrupt.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: remove ras_error_status parameter for UMC poison handler2022-10-27T19:12:08+00:00Tao Zhoutao.zhou1@amd.com2022-10-18T02:31:09+00:00urn:sha1:1ed0e176902483e67cd02530d387a7551b0e99a4
Make the code simpler.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: add RAS poison handling for MCA2022-10-27T19:12:08+00:00Tao Zhoutao.zhou1@amd.com2022-10-17T10:31:20+00:00urn:sha1:ae45a18b80d9d0d29f0ecfc52fb4e7831671b299
For MCA poison, if unmap queue fails, only gpu reset should be
triggered without page retirement handling, MCA notifier will do it.
v2: handle MCA poison consumption in umc_poison_handler directly.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: add RAS page retirement functions for MCA2022-10-27T19:12:08+00:00Tao Zhoutao.zhou1@amd.com2022-10-17T10:22:13+00:00urn:sha1:cbe4d43ea5e903ae3e8555cc39047b0ed027738a
Define page retirement functions for MCA platform.
v2: remove page retirement handling from MCA poison handler,
let MCA notifier do page retirement.
v3: remove specific poison handler for MCA to simplify code.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: message smu to update bad channel info2022-03-15T18:25:16+00:00Stanley.YangStanley.Yang@amd.com2022-03-03T09:56:33+00:00urn:sha1:69691c823531c36c7283ecaa040e99e9c12ece07
It should notice SMU to update bad channel info when detected
uncorrectable error in UMC block
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>