On 11/12/26 22:48, Alex Deucher wrote: > This largely reverts commit 90b1b26bb030d6c666f8cad52cd3d8019d404ad9. > > Not emitting the spm update via the ring causes CI flakeyness on > gfx11. Add back the SPM ring emission, but skip the MMIO path > if ring is specified. > > v2: drop ring code in gfx 12.1. We aren't supporting KCQs on 12.1 > so the code is not used. > > Cc: Vitaly Prosyak <[email protected]> > Cc: Pierre-Eric Pelloux-Prayer <[email protected]> > Cc: Sunil Khatri <[email protected]> > Cc: Christian König <[email protected]> > Fixes: d44428868e5b ("drm/amdgpu: re-enable SPM updates in the the IB path") > Signed-off-by: Alex Deucher <[email protected]>
Acked-by: Christian König <[email protected]> > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 2 +- > drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 2 +- > drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h | 2 +- > drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 +- > drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 16 +++++++++++++--- > drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 15 +++++++++++++-- > drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c | 7 ++++--- > drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 4 ++-- > drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 4 ++-- > drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- > drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 4 ++-- > 11 files changed, 41 insertions(+), 19 deletions(-) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c > index 324d25c77897a..1ff5d5cfb141d 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c > @@ -750,7 +750,7 @@ void amdgpu_ring_set_fence_errors_and_reemit(struct > amdgpu_ring *ring, > ring->reemit = true; > amdgpu_ring_alloc(ring, ring->ring_backup_entries_to_copy); > if (emit_spm_needed) > - ring->adev->gfx.rlc.funcs->update_spm_vmid(ring->adev, > ring->xcc_id, > + ring->adev->gfx.rlc.funcs->update_spm_vmid(ring->adev, > ring->xcc_id, NULL, > > ring->adev->vm_manager.spm_vmid); > spin_lock_irqsave(&ring->fence_drv.lock, flags); > do { > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > index 6210edf1937aa..a24cdf5852a32 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > @@ -213,7 +213,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, struct > amdgpu_job *job, > amdgpu_ring_emit_pipeline_sync(ring); > > if (emit_spm_needed) > - adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, > + adev->gfx.rlc.funcs->update_spm_vmid(adev, ring->xcc_id, ring, > adev->vm_manager.spm_vmid); > > if (emit_gds_needed) > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h > b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h > index e38a8ea02c520..2ae2c1d0f702b 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h > @@ -292,7 +292,7 @@ struct amdgpu_rlc_funcs { > void (*reset)(struct amdgpu_device *adev); > void (*start)(struct amdgpu_device *adev); > void (*update_spm_vmid)(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid); > + struct amdgpu_ring *ring, unsigned vmid); > bool (*is_rlcg_access_range)(struct amdgpu_device *adev, uint32_t reg); > }; > > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c > index 7683e8a0a4380..f226758b15467 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c > @@ -8187,7 +8187,7 @@ static void gfx_v10_0_update_spm_vmid_internal(struct > amdgpu_device *adev, > } > > static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, unsigned int vmid) > { > amdgpu_gfx_off_ctrl(adev, false); > > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c > index 5d068a9d9c72c..ac814c12d60f2 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c > @@ -363,6 +363,7 @@ static void gfx_v11_0_ring_invalidate_tlbs(struct > amdgpu_ring *ring, > static void gfx_v11_0_set_safe_mode(struct amdgpu_device *adev, int xcc_id); > static void gfx_v11_0_unset_safe_mode(struct amdgpu_device *adev, int > xcc_id); > static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > + struct amdgpu_ring *ring, > unsigned int vmid); > static void gfx_v11_0_userq_priv_fault_work(struct work_struct *work); > static void gfx_v11_0_update_perf_clk(struct amdgpu_device *adev, > @@ -2606,7 +2607,7 @@ static int gfx_v11_0_rlc_resume(struct amdgpu_device > *adev) > * The RLC comes up with RLC_SPM_MC_CNTL cleared, program the SPM VMID > * once it runs, also after a GPU reset or a resume. > */ > - gfx_v11_0_update_spm_vmid(adev, 0, adev->vm_manager.spm_vmid); > + gfx_v11_0_update_spm_vmid(adev, 0, NULL, adev->vm_manager.spm_vmid); > > return 0; > } > @@ -5615,12 +5616,21 @@ static int gfx_v11_0_update_gfx_clock_gating(struct > amdgpu_device *adev, > } > > static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, unsigned vmid) > { > u32 reg, pre_data, data; > > - amdgpu_gfx_off_ctrl(adev, false); > reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); > + > + if (ring && amdgpu_sriov_is_pp_one_vf(adev) && > + ((ring->funcs->type == AMDGPU_RING_TYPE_GFX) || > + (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE))) { > + data = (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << > RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT; > + amdgpu_ring_emit_wreg(ring, reg, data); > + return; > + } > + > + amdgpu_gfx_off_ctrl(adev, false); > if (amdgpu_sriov_is_pp_one_vf(adev) && !amdgpu_sriov_runtime(adev)) > pre_data = RREG32_NO_KIQ(reg); > else > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c > index df2fb09bbcd86..07f981f27bcc8 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c > @@ -287,6 +287,7 @@ static void gfx_v12_0_ring_invalidate_tlbs(struct > amdgpu_ring *ring, > static void gfx_v12_0_set_safe_mode(struct amdgpu_device *adev, int xcc_id); > static void gfx_v12_0_unset_safe_mode(struct amdgpu_device *adev, int > xcc_id); > static void gfx_v12_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > + struct amdgpu_ring *ring, > unsigned int vmid); > static void gfx_v12_0_userq_priv_fault_work(struct work_struct *work); > static void gfx_v12_0_update_perf_clk(struct amdgpu_device *adev, > @@ -2158,7 +2159,7 @@ static int gfx_v12_0_rlc_resume(struct amdgpu_device > *adev) > * The RLC comes up with RLC_SPM_MC_CNTL cleared, program the SPM VMID > * once it runs, also after a GPU reset or a resume. > */ > - gfx_v12_0_update_spm_vmid(adev, 0, adev->vm_manager.spm_vmid); > + gfx_v12_0_update_spm_vmid(adev, 0, NULL, adev->vm_manager.spm_vmid); > > return 0; > } > @@ -3978,12 +3979,22 @@ static void gfx_v12_0_update_perf_clk(struct > amdgpu_device *adev, > > static void gfx_v12_0_update_spm_vmid(struct amdgpu_device *adev, > int xcc_id, > + struct amdgpu_ring *ring, > unsigned vmid) > { > u32 reg, data; > > - amdgpu_gfx_off_ctrl(adev, false); > reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); > + > + if (ring && amdgpu_sriov_is_pp_one_vf(adev) && > + ((ring->funcs->type == AMDGPU_RING_TYPE_GFX) || > + (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE))) { > + data = (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << > RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT; > + amdgpu_ring_emit_wreg(ring, reg, data); > + return; > + } > + > + amdgpu_gfx_off_ctrl(adev, false); > if (amdgpu_sriov_is_pp_one_vf(adev)) > data = RREG32_NO_KIQ(reg); > else > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c > index 1f57d0fa2c044..bf69d71e6b065 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c > @@ -217,7 +217,7 @@ static int gfx_v12_1_init_cp_compute_microcode_bo(struct > amdgpu_device *adev); > static void gfx_v12_1_xcc_update_medium_grain_clock_gating( > struct amdgpu_device *adev, bool enable, int xcc_id, bool force); > static void gfx_v12_1_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid); > + struct amdgpu_ring *ring, unsigned vmid); > > static void gfx_v12_1_wait_reg_mem(struct amdgpu_ring *ring, int eng_sel, > int mem_space, int opt, uint32_t addr0, > @@ -1866,7 +1866,7 @@ static int gfx_v12_1_xcc_rlc_resume(struct > amdgpu_device *adev, > int r; > > /* init spm vmid with 0xf */ > - gfx_v12_1_update_spm_vmid(adev, xcc_id, adev->vm_manager.spm_vmid); > + gfx_v12_1_update_spm_vmid(adev, xcc_id, NULL, > adev->vm_manager.spm_vmid); > > if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { > gfx_v12_1_xcc_init_csb(adev, xcc_id); > @@ -2945,7 +2945,8 @@ static void gfx_v12_1_update_perf_clk(struct > amdgpu_device *adev, > > static void gfx_v12_1_update_spm_vmid(struct amdgpu_device *adev, > int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, > + unsigned vmid) > { > u32 reg, data; > > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c > index 72c84b61fda16..43dea0810137b 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c > @@ -3256,7 +3256,7 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev) > > /* init spm vmid with 0xf */ > if (adev->gfx.rlc.funcs->update_spm_vmid) > - adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, > adev->vm_manager.spm_vmid); > + adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, NULL, > adev->vm_manager.spm_vmid); > > return 0; > } > @@ -3483,7 +3483,7 @@ static int gfx_v7_0_rlc_resume(struct amdgpu_device > *adev) > } > > static void gfx_v7_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, unsigned vmid) > { > u32 data; > > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c > index 4666aa5b38c75..360a958f7577d 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c > @@ -1276,7 +1276,7 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev) > > /* init spm vmid with 0xf */ > if (adev->gfx.rlc.funcs->update_spm_vmid) > - adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, > adev->vm_manager.spm_vmid); > + adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, NULL, > adev->vm_manager.spm_vmid); > > return 0; > } > @@ -5484,7 +5484,7 @@ static void gfx_v8_0_unset_safe_mode(struct > amdgpu_device *adev, int xcc_id) > } > > static void gfx_v8_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, unsigned vmid) > { > u32 data; > > diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c > b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c > index 2e2673a6dbbf5..0b01801b0571b 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c > @@ -5227,7 +5227,7 @@ static void gfx_v9_0_update_spm_vmid_internal(struct > amdgpu_device *adev, > } > > static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, int xcc_id, > - unsigned int vmid) > + struct amdgpu_ring *ring, unsigned int vmid) > { > amdgpu_gfx_off_ctrl(adev, false); > > 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 da031caa4e9e6..30c8b751849cd 100644 > --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c > @@ -1397,7 +1397,7 @@ static int gfx_v9_4_3_rlc_init(struct amdgpu_device > *adev) > { > /* init spm vmid with 0xf */ > if (adev->gfx.rlc.funcs->update_spm_vmid) > - adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, > adev->vm_manager.spm_vmid); > + adev->gfx.rlc.funcs->update_spm_vmid(adev, 0, NULL, > adev->vm_manager.spm_vmid); > > return 0; > } > @@ -1609,7 +1609,7 @@ static int gfx_v9_4_3_rlc_resume(struct amdgpu_device > *adev) > } > > static void gfx_v9_4_3_update_spm_vmid(struct amdgpu_device *adev, > - int inst, unsigned int vmid) > + int inst, struct amdgpu_ring > *ring, unsigned int vmid) > { > u32 reg, pre_data, data; >
