From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 18 Jun 2018 10:41:50 +0100
Subject: drm/i915/execlists: Pull the w/a LRI emission into a helper
Git-commit: 5ee4a7a6db8eb46aafdfea1f26cbdbbb4cef76b3
Patch-mainline: v4.19-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166
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
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
drivers/gpu/drm/i915/i915_reg.h | 3 +
drivers/gpu/drm/i915/intel_lrc.c | 59 ++++++++++++++++++++++++++++-----------
2 files changed, 45 insertions(+), 17 deletions(-)
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -156,6 +156,7 @@ static inline bool i915_mmio_reg_valid(i
#define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
#define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
+#define __MASKED_FIELD(mask, value) ((mask) << 16 | (value))
#define _MASKED_FIELD(mask, value) ({ \
if (__builtin_constant_p(mask)) \
BUILD_BUG_ON_MSG(((mask) & 0xffff0000), "Incorrect mask"); \
@@ -164,7 +165,7 @@ static inline bool i915_mmio_reg_valid(i
if (__builtin_constant_p(mask) && __builtin_constant_p(value)) \
BUILD_BUG_ON_MSG((value) & ~(mask), \
"Incorrect value for mask"); \
- (mask) << 16 | (value); })
+ __MASKED_FIELD(mask, value); })
#define _MASKED_BIT_ENABLE(a) ({ typeof(a) _a = (a); _MASKED_FIELD(_a, _a); })
#define _MASKED_BIT_DISABLE(a) (_MASKED_FIELD((a), 0))
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1565,29 +1565,56 @@ static u32 *gen8_init_indirectctx_bb(str
return batch;
}
+struct lri {
+ i915_reg_t reg;
+ u32 value;
+};
+
+static u32 *emit_lri(u32 *batch, const struct lri *lri, unsigned int count)
+{
+ GEM_BUG_ON(!count || count > 63);
+
+ *batch++ = MI_LOAD_REGISTER_IMM(count);
+ do {
+ *batch++ = i915_mmio_reg_offset(lri->reg);
+ *batch++ = lri->value;
+ } while (lri++, --count);
+ *batch++ = MI_NOOP;
+
+ return batch;
+}
+
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),
+ }
+ };
+
*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
batch = gen8_emit_flush_coherentl3_wa(engine, batch);
- *batch++ = MI_LOAD_REGISTER_IMM(3);
-
- /* 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);
-
- /* BSpec: 11391 */
- *batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
- *batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
-
- /* BSpec: 11299 */
- *batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
- *batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
-
- *batch++ = MI_NOOP;
+ batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
/* WaClearSlmSpaceAtContextSwitch:kbl */
/* Actual scratch location is at 128 bytes offset */