From 972282c4cf2454af7dca3fec16b8f2cc72d4238c Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Thu, 7 May 2020 17:20:45 +0300 Subject: [PATCH] drm/i915/gen12: Add aux table invalidate for all engines All engines, exception being blitter as it does not care about the form, can access compressed surfaces. So we need to add forced aux table invalidates for those engines. v2: virtual instance masking (Chris) v3: bug on if not found (Chris) References: d248b371f747 ("drm/i915/gen12: Invalidate aux table entries forcibly") References bspec#43904, hsdes#1809175790 Cc: Chris Wilson Cc: Chuansheng Liu Cc: Rafael Antognolli Signed-off-by: Mika Kuoppala Acked-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20200507142045.8668-1-mika.kuoppala@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_lrc.c | 86 +++++++++++++++++++++++++++-- drivers/gpu/drm/i915/i915_reg.h | 6 ++ 2 files changed, 87 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 59c99e2f02573..400b9b5a6882f 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -4540,11 +4540,36 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } +static i915_reg_t aux_inv_reg(const struct intel_engine_cs *engine) +{ + static const i915_reg_t vd[] = { + GEN12_VD0_AUX_NV, + GEN12_VD1_AUX_NV, + GEN12_VD2_AUX_NV, + GEN12_VD3_AUX_NV, + }; + + static const i915_reg_t ve[] = { + GEN12_VE0_AUX_NV, + GEN12_VE1_AUX_NV, + }; + + if (engine->class == VIDEO_DECODE_CLASS) + return vd[engine->instance]; + + if (engine->class == VIDEO_ENHANCEMENT_CLASS) + return ve[engine->instance]; + + GEM_BUG_ON("unknown aux_inv_reg\n"); + + return INVALID_MMIO_REG; +} + static u32 * -gen12_emit_aux_table_inv(struct i915_request *rq, u32 *cs) +gen12_emit_aux_table_inv(const i915_reg_t inv_reg, u32 *cs) { *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN12_GFX_CCS_AUX_NV); + *cs++ = i915_mmio_reg_offset(inv_reg); *cs++ = AUX_INV; *cs++ = MI_NOOP; @@ -4613,7 +4638,7 @@ static int gen12_emit_flush_render(struct i915_request *request, cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(request, cs); + cs = gen12_emit_aux_table_inv(GEN12_GFX_CCS_AUX_NV, cs); *cs++ = preparser_disable(false); intel_ring_advance(request, cs); @@ -4622,6 +4647,56 @@ static int gen12_emit_flush_render(struct i915_request *request, return 0; } +static int gen12_emit_flush(struct i915_request *request, u32 mode) +{ + intel_engine_mask_t aux_inv = 0; + u32 cmd, *cs; + + if (mode & EMIT_INVALIDATE) + aux_inv = request->engine->mask & ~BIT(BCS0); + + cs = intel_ring_begin(request, + 4 + (aux_inv ? 2 * hweight8(aux_inv) + 2 : 0)); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + cmd = MI_FLUSH_DW + 1; + + /* We always require a command barrier so that subsequent + * commands, such as breadcrumb interrupts, are strictly ordered + * wrt the contents of the write cache being flushed to memory + * (and thus being coherent from the CPU). + */ + cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW; + + if (mode & EMIT_INVALIDATE) { + cmd |= MI_INVALIDATE_TLB; + if (request->engine->class == VIDEO_DECODE_CLASS) + cmd |= MI_INVALIDATE_BSD; + } + + *cs++ = cmd; + *cs++ = LRC_PPHWSP_SCRATCH_ADDR; + *cs++ = 0; /* upper addr */ + *cs++ = 0; /* value */ + + if (aux_inv) { /* hsdes: 1809175790 */ + struct intel_engine_cs *engine; + unsigned int tmp; + + *cs++ = MI_LOAD_REGISTER_IMM(hweight8(aux_inv)); + for_each_engine_masked(engine, request->engine->gt, + aux_inv, tmp) { + *cs++ = i915_mmio_reg_offset(aux_inv_reg(engine)); + *cs++ = AUX_INV; + } + *cs++ = MI_NOOP; + } + intel_ring_advance(request, cs); + + return 0; +} + /* * Reserve space for 2 NOOPs at the end of each request to be * used as a workaround for not being allowed to do lite @@ -4855,9 +4930,10 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) engine->emit_flush = gen8_emit_flush; engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb; engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb; - if (INTEL_GEN(engine->i915) >= 12) + if (INTEL_GEN(engine->i915) >= 12) { engine->emit_fini_breadcrumb = gen12_emit_fini_breadcrumb; - + engine->emit_flush = gen12_emit_flush; + } engine->set_default_submission = intel_execlists_set_default_submission; if (INTEL_GEN(engine->i915) < 11) { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index dc5952200a073..6c076a24eb822 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2558,6 +2558,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN12_PAT_INDEX(index) _MMIO(0x4800 + (index) * 4) #define BSD_HWS_PGA_GEN7 _MMIO(0x04180) #define GEN12_GFX_CCS_AUX_NV _MMIO(0x4208) +#define GEN12_VD0_AUX_NV _MMIO(0x4218) +#define GEN12_VD1_AUX_NV _MMIO(0x4228) +#define GEN12_VD2_AUX_NV _MMIO(0x4298) +#define GEN12_VD3_AUX_NV _MMIO(0x42A8) +#define GEN12_VE0_AUX_NV _MMIO(0x4238) +#define GEN12_VE1_AUX_NV _MMIO(0x42B8) #define AUX_INV REG_BIT(0) #define BLT_HWS_PGA_GEN7 _MMIO(0x04280) #define VEBOX_HWS_PGA_GEN7 _MMIO(0x04380) -- 2.39.5