From patchwork Mon Jul 24 11:32:46 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [01/10] drm/i915/gt: Cleanup aux invalidation registers From: Andi Shyti X-Patchwork-Id: 549109 Message-Id: <20230724113255.873932-1-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:46 +0200 Fix the 'NV' definition postfix that is supposed to be INV. Take the chance to also order properly the registers based on their address and call the GEN12_GFX_CCS_AUX_INV address as GEN12_CCS_AUX_INV like all the other similar registers. Remove also VD1, VD3 and VE1 registers that don't exist and add BCS0 and CCS0. Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 8 ++++---- drivers/gpu/drm/i915/gt/intel_gt_regs.h | 16 ++++++++-------- drivers/gpu/drm/i915/gt/intel_lrc.c | 6 +++--- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 23857cc08eca1..563efee055602 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -287,8 +287,8 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (!HAS_FLAT_CCS(rq->engine->i915)) { /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, + GEN12_CCS_AUX_INV); } *cs++ = preparser_disable(false); @@ -348,10 +348,10 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (aux_inv) { /* hsdes: 1809175790 */ if (rq->engine->class == VIDEO_DECODE_CLASS) cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_NV); + cs, GEN12_VD0_AUX_INV); else cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_NV); + cs, GEN12_VE0_AUX_INV); } if (mode & EMIT_INVALIDATE) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 718cb2c80f79e..2cdfb2f713d02 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -332,9 +332,11 @@ #define GEN8_PRIVATE_PAT_HI _MMIO(0x40e0 + 4) #define GEN10_PAT_INDEX(index) _MMIO(0x40e0 + (index) * 4) #define BSD_HWS_PGA_GEN7 _MMIO(0x4180) -#define GEN12_GFX_CCS_AUX_NV _MMIO(0x4208) -#define GEN12_VD0_AUX_NV _MMIO(0x4218) -#define GEN12_VD1_AUX_NV _MMIO(0x4228) + +#define GEN12_CCS_AUX_INV _MMIO(0x4208) +#define GEN12_VD0_AUX_INV _MMIO(0x4218) +#define GEN12_VE0_AUX_INV _MMIO(0x4238) +#define GEN12_BCS0_AUX_INV _MMIO(0x4248) #define GEN8_RTCR _MMIO(0x4260) #define GEN8_M1TCR _MMIO(0x4264) @@ -342,14 +344,12 @@ #define GEN8_BTCR _MMIO(0x426c) #define GEN8_VTCR _MMIO(0x4270) -#define GEN12_VD2_AUX_NV _MMIO(0x4298) -#define GEN12_VD3_AUX_NV _MMIO(0x42a8) -#define GEN12_VE0_AUX_NV _MMIO(0x4238) - #define BLT_HWS_PGA_GEN7 _MMIO(0x4280) -#define GEN12_VE1_AUX_NV _MMIO(0x42b8) +#define GEN12_VD2_AUX_INV _MMIO(0x4298) +#define GEN12_CCS0_AUX_INV _MMIO(0x42c8) #define AUX_INV REG_BIT(0) + #define VEBOX_HWS_PGA_GEN7 _MMIO(0x4380) #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 1b710102390bf..235f3fab60a98 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1374,7 +1374,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) /* hsdes: 1809175790 */ if (!HAS_FLAT_CCS(ce->engine->i915)) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_GFX_CCS_AUX_NV); + cs, GEN12_CCS_AUX_INV); /* Wa_16014892111 */ if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) || @@ -1403,10 +1403,10 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) if (!HAS_FLAT_CCS(ce->engine->i915)) { if (ce->engine->class == VIDEO_DECODE_CLASS) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_NV); + cs, GEN12_VD0_AUX_INV); else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_NV); + cs, GEN12_VE0_AUX_INV); } return cs; From patchwork Mon Jul 24 11:32:47 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [02/10] drm/i915: Add the gen12_needs_ccs_aux_inv helper From: Andi Shyti X-Patchwork-Id: 549106 Message-Id: <20230724113255.873932-2-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:47 +0200 We always assumed that a device might either have AUX or FLAT CCS, but this is an approximation that is not always true, e.g. PVC represents an exception. Set the basis for future finer selection by implementing a boolean gen12_needs_ccs_aux_inv() function that tells whether aux invalidation is needed or not. Currently PVC is the only exception to the above mentioned rule. Signed-off-by: Andi Shyti Cc: Matt Roper Cc: Jonathan Cavitt Cc: # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 563efee055602..460c9225a50fc 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,6 +165,18 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } +static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) +{ + if (IS_PONTEVECCHIO(engine->i915)) + return false; + + /* + * so far platforms supported by i915 having + * flat ccs do not require AUX invalidation + */ + return !HAS_FLAT_CCS(engine->i915); +} + u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) { u32 gsi_offset = gt->uncore->gsi_offset; @@ -267,7 +279,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; - if (!HAS_FLAT_CCS(rq->engine->i915)) + if (gen12_needs_ccs_aux_inv(rq->engine)) count = 8 + 4; else count = 8; @@ -285,7 +297,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (!HAS_FLAT_CCS(rq->engine->i915)) { + if (gen12_needs_ccs_aux_inv(rq->engine)) { /* hsdes: 1809175790 */ cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, GEN12_CCS_AUX_INV); @@ -307,7 +319,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (mode & EMIT_INVALIDATE) { cmd += 2; - if (!HAS_FLAT_CCS(rq->engine->i915) && + if (gen12_needs_ccs_aux_inv(rq->engine) && (rq->engine->class == VIDEO_DECODE_CLASS || rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { aux_inv = rq->engine->mask & From patchwork Mon Jul 24 11:32:48 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [03/10] drm/i915/gt: Ensure memory quiesced before invalidation From: Andi Shyti X-Patchwork-Id: 549111 Message-Id: <20230724113255.873932-3-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:48 +0200 From: Jonathan Cavitt All memory traffic must be quiesced before requesting an aux invalidation on platforms that use Aux CCS. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Jonathan Cavitt Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 460c9225a50fc..6210b38a2d382 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -214,7 +214,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) { struct intel_engine_cs *engine = rq->engine; - if (mode & EMIT_FLUSH) { + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { u32 flags = 0; int err; u32 *cs; From patchwork Mon Jul 24 11:32:49 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [04/10] drm/i915/gt: Rename flags with bit_group_X according to the datasheet From: Andi Shyti X-Patchwork-Id: 549107 Message-Id: <20230724113255.873932-4-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:49 +0200 In preparation of the next patch align with the datasheet (BSPEC 47112) with the naming of the pipe control set of flag values. The variable "flags" in gen12_emit_flush_rcs() is applied as a set of flags called Bit Group 1. Define also the Bit Group 0 as bit_group_0 where currently only PIPE_CONTROL0_HDC_PIPELINE_FLUSH bit is set. Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Matt Roper Reviewed-by: Andrzej Hajda Reviewed-by: Nirmoy Das --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 34 +++++++++++++----------- drivers/gpu/drm/i915/gt/gen8_engine_cs.h | 18 ++++++++----- 2 files changed, 29 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 6210b38a2d382..5d2175e918dd2 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -219,7 +219,8 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) * table requires quiescing memory traffic beforehand */ if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) { - u32 flags = 0; + u32 bit_group_0 = 0; + u32 bit_group_1 = 0; int err; u32 *cs; @@ -227,32 +228,33 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (err) return err; - flags |= PIPE_CONTROL_TILE_CACHE_FLUSH; - flags |= PIPE_CONTROL_FLUSH_L3; - flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; - flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH; + + bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH; + bit_group_1 |= PIPE_CONTROL_FLUSH_L3; + bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; + bit_group_1 |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; /* Wa_1409600907:tgl,adl-p */ - flags |= PIPE_CONTROL_DEPTH_STALL; - flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; - flags |= PIPE_CONTROL_FLUSH_ENABLE; + bit_group_1 |= PIPE_CONTROL_DEPTH_STALL; + bit_group_1 |= PIPE_CONTROL_DC_FLUSH_ENABLE; + bit_group_1 |= PIPE_CONTROL_FLUSH_ENABLE; - flags |= PIPE_CONTROL_STORE_DATA_INDEX; - flags |= PIPE_CONTROL_QW_WRITE; + bit_group_1 |= PIPE_CONTROL_STORE_DATA_INDEX; + bit_group_1 |= PIPE_CONTROL_QW_WRITE; - flags |= PIPE_CONTROL_CS_STALL; + bit_group_1 |= PIPE_CONTROL_CS_STALL; if (!HAS_3D_PIPELINE(engine->i915)) - flags &= ~PIPE_CONTROL_3D_ARCH_FLAGS; + bit_group_1 &= ~PIPE_CONTROL_3D_ARCH_FLAGS; else if (engine->class == COMPUTE_CLASS) - flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + bit_group_1 &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) return PTR_ERR(cs); - cs = gen12_emit_pipe_control(cs, - PIPE_CONTROL0_HDC_PIPELINE_FLUSH, - flags, LRC_PPHWSP_SCRATCH_ADDR); + cs = gen12_emit_pipe_control(cs, bit_group_0, bit_group_1, + LRC_PPHWSP_SCRATCH_ADDR); intel_ring_advance(rq, cs); } diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index 655e5c00ddc27..a44eda096557c 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -49,25 +49,29 @@ u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); static inline u32 * -__gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) +__gen8_emit_pipe_control(u32 *batch, u32 bit_group_0, + u32 bit_group_1, u32 offset) { memset(batch, 0, 6 * sizeof(u32)); - batch[0] = GFX_OP_PIPE_CONTROL(6) | flags0; - batch[1] = flags1; + batch[0] = GFX_OP_PIPE_CONTROL(6) | bit_group_0; + batch[1] = bit_group_1; batch[2] = offset; return batch + 6; } -static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset) +static inline u32 *gen8_emit_pipe_control(u32 *batch, + u32 bit_group_1, u32 offset) { - return __gen8_emit_pipe_control(batch, 0, flags, offset); + return __gen8_emit_pipe_control(batch, 0, bit_group_1, offset); } -static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) +static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 bit_group_0, + u32 bit_group_1, u32 offset) { - return __gen8_emit_pipe_control(batch, flags0, flags1, offset); + return __gen8_emit_pipe_control(batch, bit_group_0, + bit_group_1, offset); } static inline u32 * From patchwork Mon Jul 24 11:32:50 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [05/10] drm/i915/gt: Enable the CCS_FLUSH bit in the pipe control From: Andi Shyti X-Patchwork-Id: 549108 Message-Id: <20230724113255.873932-5-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:50 +0200 Enable the CCS_FLUSH bit 13 in the control pipe for render and compute engines in platforms starting from Meteor Lake (BSPEC 43904 and 47112). Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Andi Shyti Cc: Jonathan Cavitt Cc: Nirmoy Das Cc: # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 7 +++++++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 5d2175e918dd2..139a7e69f5c4d 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -230,6 +230,13 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) bit_group_0 |= PIPE_CONTROL0_HDC_PIPELINE_FLUSH; + /* + * When required, in MTL and beyond platforms we + * need to set the CCS_FLUSH bit in the pipe control + */ + if (GRAPHICS_VER_FULL(rq->i915) >= IP_VER(12, 70)) + bit_group_0 |= PIPE_CONTROL_CCS_FLUSH; + bit_group_1 |= PIPE_CONTROL_TILE_CACHE_FLUSH; bit_group_1 |= PIPE_CONTROL_FLUSH_L3; bit_group_1 |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 5d143e2a8db03..5df7cce23197c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -299,6 +299,7 @@ #define PIPE_CONTROL_QW_WRITE (1<<14) #define PIPE_CONTROL_POST_SYNC_OP_MASK (3<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) +#define PIPE_CONTROL_CCS_FLUSH (1<<13) /* MTL+ */ #define PIPE_CONTROL_WRITE_FLUSH (1<<12) #define PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH (1<<12) /* gen6+ */ #define PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE (1<<11) /* MBZ on ILK */ From patchwork Mon Jul 24 11:32:51 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [06/10] drm/i915/gt: Refactor intel_emit_pipe_control_cs() in a single function From: Andi Shyti X-Patchwork-Id: 549110 Message-Id: <20230724113255.873932-6-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:51 +0200 Just a trivial refactoring for reducing the number of code duplicate. This will come at handy in the next commits. Meantime, propagate the error to the above layers if we fail to emit the pipe control. Signed-off-by: Andi Shyti Cc: # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 47 +++++++++++++----------- 1 file changed, 26 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 139a7e69f5c4d..5e19b45a5cabe 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -7,6 +7,7 @@ #include "i915_drv.h" #include "intel_engine_regs.h" #include "intel_gpu_commands.h" +#include "intel_gt_print.h" #include "intel_lrc.h" #include "intel_ring.h" @@ -189,23 +190,30 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv return cs; } +static int gen12_emit_pipe_control_cs(struct i915_request *rq, u32 bit_group_0, + u32 bit_group_1, u32 offset) +{ + u32 *cs; + + cs = intel_ring_begin(rq, 6); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + cs = gen12_emit_pipe_control(cs, bit_group_0, bit_group_1, + LRC_PPHWSP_SCRATCH_ADDR); + intel_ring_advance(rq, cs); + + return 0; +} + static int mtl_dummy_pipe_control(struct i915_request *rq) { /* Wa_14016712196 */ if (IS_MTL_GRAPHICS_STEP(rq->engine->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(rq->engine->i915, P, STEP_A0, STEP_B0)) { - u32 *cs; - - /* dummy PIPE_CONTROL + depth flush */ - cs = intel_ring_begin(rq, 6); - if (IS_ERR(cs)) - return PTR_ERR(cs); - cs = gen12_emit_pipe_control(cs, - 0, - PIPE_CONTROL_DEPTH_CACHE_FLUSH, - LRC_PPHWSP_SCRATCH_ADDR); - intel_ring_advance(rq, cs); - } + IS_MTL_GRAPHICS_STEP(rq->engine->i915, P, STEP_A0, STEP_B0)) + return gen12_emit_pipe_control_cs(rq, 0, + PIPE_CONTROL_DEPTH_CACHE_FLUSH, + LRC_PPHWSP_SCRATCH_ADDR); return 0; } @@ -222,7 +230,6 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) u32 bit_group_0 = 0; u32 bit_group_1 = 0; int err; - u32 *cs; err = mtl_dummy_pipe_control(rq); if (err) @@ -256,13 +263,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) bit_group_1 &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; - cs = intel_ring_begin(rq, 6); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - cs = gen12_emit_pipe_control(cs, bit_group_0, bit_group_1, - LRC_PPHWSP_SCRATCH_ADDR); - intel_ring_advance(rq, cs); + err = gen12_emit_pipe_control_cs(rq, bit_group_0, bit_group_1, + LRC_PPHWSP_SCRATCH_ADDR); + if (err) + gt_warn(engine->gt, + "Failed to emit flush pipe control\n"); } if (mode & EMIT_INVALIDATE) { From patchwork Mon Jul 24 11:32:52 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [07/10] drm/i915/gt: Ensure memory quiesced before invalidation for all engines From: Andi Shyti X-Patchwork-Id: 549112 Message-Id: <20230724113255.873932-7-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:52 +0200 Commit af9e423a8aae ("drm/i915/gt: Ensure memory quiesced before invalidation") has made sure that the memory is quiesced before invalidating the AUX CCS table. Do it for all the other engines and not just RCS. Signed-off-by: Andi Shyti Cc: Jonathan Cavitt Cc: Matt Roper Cc: # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 36 ++++++++++++++++-------- 1 file changed, 25 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 5e19b45a5cabe..646151e1b5deb 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -331,26 +331,40 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { intel_engine_mask_t aux_inv = 0; - u32 cmd, *cs; + u32 cmd_flush = 0; + u32 cmd = 4; + u32 *cs; - cmd = 4; - if (mode & EMIT_INVALIDATE) { + if (mode & EMIT_INVALIDATE) cmd += 2; - if (gen12_needs_ccs_aux_inv(rq->engine) && - (rq->engine->class == VIDEO_DECODE_CLASS || - rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) { - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - if (aux_inv) - cmd += 4; - } + if (gen12_needs_ccs_aux_inv(rq->engine)) + aux_inv = rq->engine->mask & + ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); + + /* + * On Aux CCS platforms the invalidation of the Aux + * table requires quiescing memory traffic beforehand + */ + if (aux_inv) { + cmd += 4; /* for the AUX invalidation */ + cmd += 2; /* for the engine quiescing */ + + cmd_flush = MI_FLUSH_DW; + + if (rq->engine->class == COPY_ENGINE_CLASS) + cmd_flush |= MI_FLUSH_DW_CCS; } cs = intel_ring_begin(rq, cmd); if (IS_ERR(cs)) return PTR_ERR(cs); + if (cmd_flush) { + *cs++ = cmd_flush; + *cs++ = 0; + } + if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(true); From patchwork Mon Jul 24 11:32:53 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [08/10] drm/i915/gt: Poll aux invalidation register bit on invalidation From: Andi Shyti X-Patchwork-Id: 549113 Message-Id: <20230724113255.873932-8-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:53 +0200 From: Jonathan Cavitt For platforms that use Aux CCS, wait for aux invalidation to complete by checking the aux invalidation register bit is cleared. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Jonathan Cavitt Signed-off-by: Andi Shyti Cc: # v5.8+ Reviewed-by: Nirmoy Das Reviewed-by: Andrzej Hajda Reviewed-by: Matt Roper --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 17 ++++++++++++----- drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 + 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 646151e1b5deb..6daf7d99700e0 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -185,7 +185,15 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; - *cs++ = MI_NOOP; + + *cs++ = MI_SEMAPHORE_WAIT_TOKEN | + MI_SEMAPHORE_REGISTER_POLL | + MI_SEMAPHORE_POLL | + MI_SEMAPHORE_SAD_EQ_SDD; + *cs++ = 0; + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; + *cs++ = 0; + *cs++ = 0; return cs; } @@ -297,10 +305,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) else if (engine->class == COMPUTE_CLASS) flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS; + count = 8; if (gen12_needs_ccs_aux_inv(rq->engine)) - count = 8 + 4; - else - count = 8; + count += 8; cs = intel_ring_begin(rq, count); if (IS_ERR(cs)) @@ -347,7 +354,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) * table requires quiescing memory traffic beforehand */ if (aux_inv) { - cmd += 4; /* for the AUX invalidation */ + cmd += 8; /* for the AUX invalidation */ cmd += 2; /* for the engine quiescing */ cmd_flush = MI_FLUSH_DW; diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 5df7cce23197c..2bd8d98d21102 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -121,6 +121,7 @@ #define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_SEMAPHORE_WAIT MI_INSTR(0x1c, 2) /* GEN8+ */ #define MI_SEMAPHORE_WAIT_TOKEN MI_INSTR(0x1c, 3) /* GEN12+ */ +#define MI_SEMAPHORE_REGISTER_POLL (1 << 16) #define MI_SEMAPHORE_POLL (1 << 15) #define MI_SEMAPHORE_SAD_GT_SDD (0 << 12) #define MI_SEMAPHORE_SAD_GTE_SDD (1 << 12) From patchwork Mon Jul 24 11:32:54 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [09/10] drm/i915/gt: Support aux invalidation on all engines From: Andi Shyti X-Patchwork-Id: 549114 Message-Id: <20230724113255.873932-9-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:54 +0200 Perform some refactoring with the purpose of keeping in one single place all the operations around the aux table invalidation. With this refactoring add more engines where the invalidation should be performed. Fixes: 972282c4cf24 ("drm/i915/gen12: Add aux table invalidate for all engines") Signed-off-by: Andi Shyti Cc: Jonathan Cavitt Cc: Matt Roper Cc: # v5.8+ --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 53 ++++++++++++++---------- drivers/gpu/drm/i915/gt/gen8_engine_cs.h | 3 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 17 +------- 3 files changed, 36 insertions(+), 37 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 6daf7d99700e0..6d3738a2cfbdc 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -178,9 +178,36 @@ static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine) return !HAS_FLAT_CCS(engine->i915); } -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) +static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine) +{ + if (!gen12_needs_ccs_aux_inv(engine)) + return INVALID_MMIO_REG; + + switch (engine->id) { + case RCS0: + return GEN12_CCS_AUX_INV; + case BCS0: + return GEN12_BCS0_AUX_INV; + case VCS0: + return GEN12_VD0_AUX_INV; + case VCS2: + return GEN12_VD2_AUX_INV; + case VECS0: + return GEN12_VE0_AUX_INV; + case CCS0: + return GEN12_CCS0_AUX_INV; + default: + return INVALID_MMIO_REG; + } +} + +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs) { - u32 gsi_offset = gt->uncore->gsi_offset; + i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine); + u32 gsi_offset = engine->gt->uncore->gsi_offset; + + if (!i915_mmio_reg_valid(inv_reg)) + return cs; *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; @@ -322,11 +349,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR); - if (gen12_needs_ccs_aux_inv(rq->engine)) { - /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(rq->engine->gt, cs, - GEN12_CCS_AUX_INV); - } + cs = gen12_emit_aux_table_inv(engine, cs); *cs++ = preparser_disable(false); intel_ring_advance(rq, cs); @@ -337,7 +360,6 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) { - intel_engine_mask_t aux_inv = 0; u32 cmd_flush = 0; u32 cmd = 4; u32 *cs; @@ -345,15 +367,11 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (mode & EMIT_INVALIDATE) cmd += 2; - if (gen12_needs_ccs_aux_inv(rq->engine)) - aux_inv = rq->engine->mask & - ~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0); - /* * On Aux CCS platforms the invalidation of the Aux * table requires quiescing memory traffic beforehand */ - if (aux_inv) { + if (gen12_needs_ccs_aux_inv(rq->engine)) { cmd += 8; /* for the AUX invalidation */ cmd += 2; /* for the engine quiescing */ @@ -396,14 +414,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */ - if (aux_inv) { /* hsdes: 1809175790 */ - if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VD0_AUX_INV); - else - cs = gen12_emit_aux_table_inv(rq->engine->gt, - cs, GEN12_VE0_AUX_INV); - } + cs = gen12_emit_aux_table_inv(rq->engine, cs); if (mode & EMIT_INVALIDATE) *cs++ = preparser_disable(false); diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index a44eda096557c..867ba697aceb8 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h" +struct intel_engine_cs; struct intel_gt; struct i915_request; @@ -46,7 +47,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs); static inline u32 * __gen8_emit_pipe_control(u32 *batch, u32 bit_group_0, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 235f3fab60a98..119deb9f938c7 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1371,10 +1371,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_CCS_AUX_INV); + cs = gen12_emit_aux_table_inv(ce->engine, cs); /* Wa_16014892111 */ if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) || @@ -1399,17 +1396,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); - /* hsdes: 1809175790 */ - if (!HAS_FLAT_CCS(ce->engine->i915)) { - if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VD0_AUX_INV); - else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(ce->engine->gt, - cs, GEN12_VE0_AUX_INV); - } - - return cs; + return gen12_emit_aux_table_inv(ce->engine, cs); } static void From patchwork Mon Jul 24 11:32:55 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [10/10] change flush position From: Andi Shyti X-Patchwork-Id: 549115 Message-Id: <20230724113255.873932-10-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Mon, 24 Jul 2023 13:32:55 +0200 --- drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 6d3738a2cfbdc..23f4bca5befb8 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -385,13 +385,10 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (IS_ERR(cs)) return PTR_ERR(cs); - if (cmd_flush) { - *cs++ = cmd_flush; - *cs++ = 0; - } - - if (mode & EMIT_INVALIDATE) + if (mode & EMIT_INVALIDATE) { *cs++ = preparser_disable(true); + *cs++ = MI_NOOP; + } cmd = MI_FLUSH_DW + 1; @@ -414,6 +411,11 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) *cs++ = 0; /* upper addr */ *cs++ = 0; /* value */ + if (cmd_flush) { + *cs++ = cmd_flush; + *cs++ = 0; + } + cs = gen12_emit_aux_table_inv(rq->engine, cs); if (mode & EMIT_INVALIDATE)