Similar to commit <b82175750131>("drm/amdgpu: fix IH overflow on Vega10 v2"). When an ring buffer overflow happens the appropriate bit is set in the WPTR register which is also written back to memory. But clearing the bit in the WPTR doesn't trigger another memory writeback.
So what can happen is that we end up processing the buffer overflow over and over again because the bit is never cleared. Resulting in a random system lockup because of an infinite loop in an interrupt handler.
Signed-off-by: Defang Bo bodefang@126.com --- Changes since v1: - Modify the code and correct the wrong fix. --- --- drivers/gpu/drm/amd/amdgpu/cz_ih.c | 38 ++++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c index 1dca0cabc326..45dd47f45fa2 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c @@ -190,22 +190,32 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih) { u32 wptr, tmp; - + wptr = le32_to_cpu(*ih->wptr_cpu);
- if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) { - wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0); - /* When a ring buffer overflow happen start parsing interrupt - * from the last not overwritten vector (wptr + 16). Hopefully - * this should allow us to catchup. - */ - dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n", - wptr, ih->rptr, (wptr + 16) & ih->ptr_mask); - ih->rptr = (wptr + 16) & ih->ptr_mask; - tmp = RREG32(mmIH_RB_CNTL); - tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); - WREG32(mmIH_RB_CNTL, tmp); - } + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) + goto out; + + wptr = RREG32(mmIH_RB_CNTL); + + if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) + goto out; + + wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0); + + /* When a ring buffer overflow happen start parsing interrupt + * from the last not overwritten vector (wptr + 16). Hopefully + * this should allow us to catchup. + */ + dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n", + wptr, ih->rptr, (wptr + 16) & ih->ptr_mask); + ih->rptr = (wptr + 16) & ih->ptr_mask; + tmp = RREG32(mmIH_RB_CNTL); + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); + WREG32(mmIH_RB_CNTL, tmp); + + +out: return (wptr & ih->ptr_mask); }