diff options
| author | Hawking Zhang <Hawking.Zhang@amd.com> | 2023-03-13 09:18:34 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-03-16 01:45:27 +0300 |
| commit | fdc94d3a8c887e4e06a7ff8dcb51d55cd70e16cf (patch) | |
| tree | 0c5e36c606d8d27b6b92066bbbec16108c23d3bd /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
| parent | da9d669eab152dbd6e9410606a7c8c8a212a7959 (diff) | |
| download | linux-fdc94d3a8c887e4e06a7ff8dcb51d55cd70e16cf.tar.xz | |
drm/amdgpu: Rework pcie_bif ras sw_init
pcie_bif ras blocks needs to be initialized as early
as possible to handle fatal error detected in hw_init
phase. also align the pcie_bif ras sw_init with other
ras blocks
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>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 19 |
1 files changed, 11 insertions, 8 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 63dfcc98152d..b0d050ffc200 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2554,21 +2554,24 @@ int amdgpu_ras_init(struct amdgpu_device *adev) /* initialize nbio ras function ahead of any other * ras functions so hardware fatal error interrupt * can be enabled as early as possible */ - switch (adev->asic_type) { - case CHIP_VEGA20: - case CHIP_ARCTURUS: - case CHIP_ALDEBARAN: - if (!adev->gmc.xgmi.connected_to_cpu) { + switch (adev->ip_versions[NBIO_HWIP][0]) { + case IP_VERSION(7, 4, 0): + case IP_VERSION(7, 4, 1): + case IP_VERSION(7, 4, 4): + if (!adev->gmc.xgmi.connected_to_cpu) adev->nbio.ras = &nbio_v7_4_ras; - amdgpu_ras_register_ras_block(adev, &adev->nbio.ras->ras_block); - adev->nbio.ras_if = &adev->nbio.ras->ras_block.ras_comm; - } break; default: /* nbio ras is not available */ break; } + /* nbio ras block needs to be enabled ahead of other ras blocks + * to handle fatal error */ + r = amdgpu_nbio_ras_sw_init(adev); + if (r) + return r; + if (adev->nbio.ras && adev->nbio.ras->init_ras_controller_interrupt) { r = adev->nbio.ras->init_ras_controller_interrupt(adev); |