[AMD Official Use Only - AMD Internal Distribution Only] Thanks for pointing that out. You are right, kiq is taking logical xcc id and should not be affected. I'm sending out a new patch, please help review again. Thanks, Victor -----Original Message----- From: Lazar, Lijo <Lijo.Lazar@xxxxxxx> Sent: Monday, May 20, 2024 8:02 PM To: Zhao, Victor <Victor.Zhao@xxxxxxx>; amd-gfx@xxxxxxxxxxxxxxxxxxxxx Subject: Re: [PATCH] drm/amd/amdgpu: fix the inst passed to reg read write under sriov On 5/20/2024 4:44 PM, Victor Zhao wrote: > the inst passed to reg read/write should be physical instance. > Fix the miss matched code. > > Signed-off-by: Victor Zhao <Victor.Zhao@xxxxxxx> > --- > .../drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c | 6 ++--- > .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 2 +- > drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 8 +++--- > drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 26 +++++++++---------- > 4 files changed, 21 insertions(+), 21 deletions(-) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c > index a5c7259cf2a3..319e6793053a 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c > @@ -300,7 +300,7 @@ static int kgd_gfx_v9_4_3_hqd_load(struct amdgpu_device *adev, void *mqd, > hqd_end = SOC15_REG_OFFSET(GC, GET_INST(GC, inst), > regCP_HQD_AQL_DISPATCH_ID_HI); > > for (reg = hqd_base; reg <= hqd_end; reg++) > - WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst); > + WREG32_XCC(reg, mqd_hqd[reg - hqd_base], GET_INST(GC, inst)); Why this needs to be done? Isn't the expectation that it goes to the right KIQ/RLCG as those are also indexed by logical XCC ids? Thanks, Lijo > > > /* Activate doorbell logic before triggering WPTR poll. */ @@ > -493,12 +493,12 @@ static uint32_t kgd_gfx_v9_4_3_set_address_watch( > WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), > regTCP_WATCH0_ADDR_H) + > (watch_id * TCP_WATCH_STRIDE)), > - watch_address_high, inst); > + watch_address_high, GET_INST(GC, inst)); > > WREG32_XCC((SOC15_REG_OFFSET(GC, GET_INST(GC, inst), > regTCP_WATCH0_ADDR_L) + > (watch_id * TCP_WATCH_STRIDE)), > - watch_address_low, inst); > + watch_address_low, GET_INST(GC, inst)); > > return watch_address_cntl; > } > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c > index 5a35a8ca8922..76be23dcea31 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c > @@ -239,7 +239,7 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device > *adev, void *mqd, > > for (reg = hqd_base; > reg <= SOC15_REG_OFFSET(GC, GET_INST(GC, inst), mmCP_HQD_PQ_WPTR_HI); reg++) > - WREG32_XCC(reg, mqd_hqd[reg - hqd_base], inst); > + WREG32_XCC(reg, mqd_hqd[reg - hqd_base], GET_INST(GC, inst)); > > > /* Activate doorbell logic before triggering WPTR poll. */ diff > --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > index 07b299ec7169..349ece5a27ee 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > @@ -2812,16 +2812,16 @@ static void > gfx_v9_4_3_xcc_set_compute_eop_interrupt_state( > > switch (state) { > case AMDGPU_IRQ_STATE_DISABLE: > - mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, xcc_id); > + mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, GET_INST(GC, xcc_id)); > mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL, > TIME_STAMP_INT_ENABLE, 0); > - WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, xcc_id); > + WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, GET_INST(GC, xcc_id)); > break; > case AMDGPU_IRQ_STATE_ENABLE: > - mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, xcc_id); > + mec_int_cntl = RREG32_XCC(mec_int_cntl_reg, GET_INST(GC, xcc_id)); > mec_int_cntl = REG_SET_FIELD(mec_int_cntl, CP_ME1_PIPE0_INT_CNTL, > TIME_STAMP_INT_ENABLE, 1); > - WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, xcc_id); > + WREG32_XCC(mec_int_cntl_reg, mec_int_cntl, GET_INST(GC, xcc_id)); > break; > default: > break; > diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c > b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c > index 094c08cb98e7..aca842668c56 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c > @@ -496,14 +496,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev, > if (j >= AMDGPU_MMHUB0(0)) > tmp = RREG32_SOC15_IP(MMHUB, reg); > else > - tmp = RREG32_XCC(reg, j); > + tmp = RREG32_XCC(reg, GET_INST(GC, j)); > > tmp &= ~bits; > > if (j >= AMDGPU_MMHUB0(0)) > WREG32_SOC15_IP(MMHUB, reg, tmp); > else > - WREG32_XCC(reg, tmp, j); > + WREG32_XCC(reg, tmp, GET_INST(GC, j)); > } > } > break; > @@ -524,14 +524,14 @@ static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev, > if (j >= AMDGPU_MMHUB0(0)) > tmp = RREG32_SOC15_IP(MMHUB, reg); > else > - tmp = RREG32_XCC(reg, j); > + tmp = RREG32_XCC(reg, GET_INST(GC, j)); > > tmp |= bits; > > if (j >= AMDGPU_MMHUB0(0)) > WREG32_SOC15_IP(MMHUB, reg, tmp); > else > - WREG32_XCC(reg, tmp, j); > + WREG32_XCC(reg, tmp, GET_INST(GC, j)); > } > } > break; > @@ -844,7 +844,7 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, > ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng; > > if (vmhub >= AMDGPU_MMHUB0(0)) > - inst = GET_INST(GC, 0); > + inst = 0; > else > inst = vmhub; > > @@ -876,9 +876,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, > for (j = 0; j < adev->usec_timeout; j++) { > /* a read return value of 1 means semaphore acquire */ > if (vmhub >= AMDGPU_MMHUB0(0)) > - tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem, inst); > + tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, sem, GET_INST(GC, inst)); > else > - tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem, inst); > + tmp = RREG32_SOC15_IP_NO_KIQ(GC, sem, GET_INST(GC, inst)); > if (tmp & 0x1) > break; > udelay(1); > @@ -889,9 +889,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, > } > > if (vmhub >= AMDGPU_MMHUB0(0)) > - WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req, inst); > + WREG32_SOC15_IP_NO_KIQ(MMHUB, req, inv_req, GET_INST(GC, inst)); > else > - WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req, inst); > + WREG32_SOC15_IP_NO_KIQ(GC, req, inv_req, GET_INST(GC, inst)); > > /* > * Issue a dummy read to wait for the ACK register to @@ -904,9 > +904,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device > *adev, uint32_t vmid, > > for (j = 0; j < adev->usec_timeout; j++) { > if (vmhub >= AMDGPU_MMHUB0(0)) > - tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack, inst); > + tmp = RREG32_SOC15_IP_NO_KIQ(MMHUB, ack, GET_INST(GC, inst)); > else > - tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack, inst); > + tmp = RREG32_SOC15_IP_NO_KIQ(GC, ack, GET_INST(GC, inst)); > if (tmp & (1 << vmid)) > break; > udelay(1); > @@ -919,9 +919,9 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid, > * write with 0 means semaphore release > */ > if (vmhub >= AMDGPU_MMHUB0(0)) > - WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0, inst); > + WREG32_SOC15_IP_NO_KIQ(MMHUB, sem, 0, GET_INST(GC, inst)); > else > - WREG32_SOC15_IP_NO_KIQ(GC, sem, 0, inst); > + WREG32_SOC15_IP_NO_KIQ(GC, sem, 0, GET_INST(GC, inst)); > } > > spin_unlock(&adev->gmc.invalidate_lock);