diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2018-06-18 10:41:50 +0100 |
---|---|---|
committer | Chris Wilson <chris@chris-wilson.co.uk> | 2018-06-18 14:43:47 +0100 |
commit | 5ee4a7a6db8eb46aafdfea1f26cbdbbb4cef76b3 (patch) | |
tree | 6b8d75fa70ecc6369e56b6455627bccc553244e1 /drivers/gpu/drm/i915/intel_lrc.c | |
parent | bcc2661e3243fe75b91ec682de01e7cbedfbe7f9 (diff) |
drm/i915/execlists: Pull the w/a LRI emission into a helper
Having the w/a registers as an open-coded table leaves a trap for the
unwary; it would be easy to miss incrementing the LRI counter when
adding a new register to the list. Instead, pull the list of registers
into a table, so that we only need add new registers to that table
rather than try and remember important side-effects of earlier chunks of
GPU instructions.
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618094150.30895-1-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/intel_lrc.c')
-rw-r--r-- | drivers/gpu/drm/i915/intel_lrc.c | 59 |
1 files changed, 43 insertions, 16 deletions
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index b6c230bd7d6e..10deebe49543 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1566,29 +1566,56 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) return batch; } -static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) +struct lri { + i915_reg_t reg; + u32 value; +}; + +static u32 *emit_lri(u32 *batch, const struct lri *lri, unsigned int count) { - *batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; + GEM_BUG_ON(!count || count > 63); - /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ - batch = gen8_emit_flush_coherentl3_wa(engine, batch); + *batch++ = MI_LOAD_REGISTER_IMM(count); + do { + *batch++ = i915_mmio_reg_offset(lri->reg); + *batch++ = lri->value; + } while (lri++, --count); + *batch++ = MI_NOOP; - *batch++ = MI_LOAD_REGISTER_IMM(3); + return batch; +} - /* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */ - *batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2); - *batch++ = _MASKED_BIT_DISABLE( - GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE); +static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) +{ + static const struct lri lri[] = { + /* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */ + { + COMMON_SLICE_CHICKEN2, + __MASKED_FIELD(GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE, + 0), + }, + + /* BSpec: 11391 */ + { + FF_SLICE_CHICKEN, + __MASKED_FIELD(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX, + FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX), + }, + + /* BSpec: 11299 */ + { + _3D_CHICKEN3, + __MASKED_FIELD(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX, + _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX), + } + }; - /* BSpec: 11391 */ - *batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN); - *batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX); + *batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; - /* BSpec: 11299 */ - *batch++ = i915_mmio_reg_offset(_3D_CHICKEN3); - *batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX); + /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ + batch = gen8_emit_flush_coherentl3_wa(engine, batch); - *batch++ = MI_NOOP; + batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); /* WaClearSlmSpaceAtContextSwitch:kbl */ /* Actual scratch location is at 128 bytes offset */ |