diff options
author | Luben Tuikov <luben.tuikov@amd.com> | 2023-06-10 06:19:15 -0400 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2023-07-19 16:21:32 +0200 |
commit | 0e2c51a16fcb9e69923906bdaecdbbe1ea4fb8e9 (patch) | |
tree | f3d08f34a20c23aed7d685e9780e941c5b1b5e5c | |
parent | 8d68ba92554b79a93f52bea0cf778eb7821c9901 (diff) | |
download | linux-stable-0e2c51a16fcb9e69923906bdaecdbbe1ea4fb8e9.tar.gz linux-stable-0e2c51a16fcb9e69923906bdaecdbbe1ea4fb8e9.tar.bz2 linux-stable-0e2c51a16fcb9e69923906bdaecdbbe1ea4fb8e9.zip |
drm/amdgpu: Fix usage of UMC fill record in RAS
[ Upstream commit 71344a718a9fda8c551cdc4381d354f9a9907f6f ]
The fixed commit listed in the Fixes tag below, introduced a bug in
amdgpu_ras.c::amdgpu_reserve_page_direct(), in that when introducing the new
amdgpu_umc_fill_error_record() and internally in that new function the physical
address (argument "uint64_t retired_page"--wrong name) is right-shifted by
AMDGPU_GPU_PAGE_SHIFT. Thus, in amdgpu_reserve_page_direct() when we pass
"address" to that new function, we should NOT right-shift it, since this
results, erroneously, in the page address to be 0 for first
2^(2*AMDGPU_GPU_PAGE_SHIFT) memory addresses.
This commit fixes this bug.
Cc: Tao Zhou <tao.zhou1@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: Alex Deucher <Alexander.Deucher@amd.com>
Fixes: 400013b268cb ("drm/amdgpu: add umc_fill_error_record to make code more simple")
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Link: https://lore.kernel.org/r/20230610113536.10621-1-luben.tuikov@amd.com
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index a4b47e1bd111..09fc464f5f12 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -170,8 +170,7 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre memset(&err_rec, 0x0, sizeof(struct eeprom_table_record)); err_data.err_addr = &err_rec; - amdgpu_umc_fill_error_record(&err_data, address, - (address >> AMDGPU_GPU_PAGE_SHIFT), 0, 0); + amdgpu_umc_fill_error_record(&err_data, address, address, 0, 0); if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, |