On Mon, Jul 17, 2023 at 07:30:59PM +0200, Andi Shyti wrote:
> 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 <andi.sh...@linux.intel.com>
> Cc: <sta...@vger.kernel.org> # v5.8+
> ---
> drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 63 +++++++++++++++---------
> drivers/gpu/drm/i915/gt/gen8_engine_cs.h | 3 +-
> drivers/gpu/drm/i915/gt/intel_lrc.c | 17 +------
> 3 files changed, 44 insertions(+), 39 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> index fbc70f3b7f2fd..6d21a1ac06e73 100644
> --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
> @@ -165,7 +165,8 @@ static u32 preparser_disable(bool state)
> return MI_ARB_CHECK | 1 << 8 | state;
> }
>
> -u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t
> inv_reg)
> +static 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;
>
> @@ -187,6 +188,40 @@ u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32
> *cs, const i915_reg_t inv
> return cs;
> }
>
> +static i915_reg_t intel_get_aux_inv_reg(struct intel_engine_cs *engine)
Generally we try to avoid putting "intel_" and "i915_" prefixes on
static functions.
> +{
> + if (HAS_FLAT_CCS(engine->i915))
> + return _MMIO(0);
> +
> + switch (engine->id) {
> + case RCS0:
> + return GEN12_CCS_AUX_INV;
> + case VCS0:
> + return GEN12_VD0_AUX_INV;
> + case VCS2:
> + return GEN12_VD2_AUX_INV;
> + case VECS0:
> + return GEN12_VE0_AUX_INV;
We need CCS0 here (0x42c0). And on graphics versions 12.70 and beyond
we also need BCS0 too (0x4248) since the blitter gained the ability to
interpret CCS compression.
> + default:
> + return _MMIO(0);
It might be cleaner to use INVALID_MMIO_REG here (and then check for
i915_mmio_reg_valid() below).
> + }
> +}
> +
> +static bool intel_engine_has_aux_inv(struct intel_engine_cs *engine)
> +{
> + i915_reg_t reg = intel_get_aux_inv_reg(engine);
> +
> + return !!reg.reg;
> +}
> +
> +u32 *intel_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs)
> +{
> + i915_reg_t reg = intel_get_aux_inv_reg(engine);
> + struct intel_gt *gt = engine->gt;
> +
> + return reg.reg ? gen12_emit_aux_table_inv(gt, cs, reg) : cs;
> +}
Rather than adding this new wrapper function, can we just do the
register lookup at the top of gen12_emit_aux_table_inv() (and bail out
of that function early if there isn't a valid register)?
Keeping the non-static function as the one with "gen12" in the name also
helps reduce confusion about whether this is something that older
platforms should have been calling as well.
Matt
> +
> static int mtl_dummy_pipe_control(struct i915_request *rq)
> {
> /* Wa_14016712196 */
> @@ -311,11 +346,7 @@ 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)) {
> - /* hsdes: 1809175790 */
> - cs = gen12_emit_aux_table_inv(rq->engine->gt, cs,
> - GEN12_CCS_AUX_INV);
> - }
> + cs = intel_emit_aux_table_inv(engine, cs);
>
> *cs++ = preparser_disable(false);
> intel_ring_advance(rq, cs);
> @@ -326,21 +357,14 @@ 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;
>
> cmd = 4;
> if (mode & EMIT_INVALIDATE) {
> cmd += 2;
>
> - if (!HAS_FLAT_CCS(rq->engine->i915) &&
> - (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 += 10;
> - }
> + if (intel_engine_has_aux_inv(rq->engine))
> + cmd += 10;
> }
>
> cs = intel_ring_begin(rq, cmd);
> @@ -371,14 +395,7 @@ 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 = intel_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 655e5c00ddc27..d938c94524510 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 *intel_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs);
>
> static inline u32 *
> __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c
> b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index 235f3fab60a98..70054767c88c3 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 = intel_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 intel_emit_aux_table_inv(ce->engine, cs);
> }
>
> static void
> --
> 2.40.1
>
--
Matt Roper
Graphics Software Engineer
Linux GPU Platform Enablement
Intel Corporation
