@@ -514,7 +514,7 @@ static void set_offsets(u32 *regs,
#define REG16(x) \
(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
(((x) >> 2) & 0x7f)
-#define END(x) 0, (x)
+#define END(total_state_size) 0, (total_state_size)
{
const u32 base = engine->mmio_base;
@@ -922,8 +922,63 @@ static const u8 gen12_rcs_offsets[] = {
NOP(6),
LRI(1, 0),
REG(0x0c8),
+ NOP(3+9+1),
+
+ LRI(51, POSTED),
+ REG16(0x588),
+ REG16(0x588),
+ REG16(0x588),
+ REG16(0x588),
+ REG16(0x588),
+ REG16(0x588),
+ REG(0x028),
+ REG(0x09c),
+ REG(0x0c0),
+ REG(0x178),
+ REG(0x17c),
+ REG16(0x358),
+ REG(0x170),
+ REG(0x150),
+ REG(0x154),
+ REG(0x158),
+ REG16(0x41c),
+ REG16(0x600),
+ REG16(0x604),
+ REG16(0x608),
+ REG16(0x60c),
+ REG16(0x610),
+ REG16(0x614),
+ REG16(0x618),
+ REG16(0x61c),
+ REG16(0x620),
+ REG16(0x624),
+ REG16(0x628),
+ REG16(0x62c),
+ REG16(0x630),
+ REG16(0x634),
+ REG16(0x638),
+ REG16(0x63c),
+ REG16(0x640),
+ REG16(0x644),
+ REG16(0x648),
+ REG16(0x64c),
+ REG16(0x650),
+ REG16(0x654),
+ REG16(0x658),
+ REG16(0x65c),
+ REG16(0x660),
+ REG16(0x664),
+ REG16(0x668),
+ REG16(0x66c),
+ REG16(0x670),
+ REG16(0x674),
+ REG16(0x678),
+ REG16(0x67c),
+ REG(0x068),
+ REG(0x084),
+ NOP(1),
- END(80)
+ END(192)
};
#undef END
@@ -3207,7 +3262,7 @@ gen12_emit_timestamp_wa_lrm(struct intel_context *ce, u32 *cs)
}
static u32 *
-gen12_emit_timestamp_wa_lrr(struct intel_context *ce, u32 *cs)
+gen12_emit_render_ctx_wa(struct intel_context *ce, u32 *cs)
{
const u32 lrc_offset = i915_ggtt_offset(ce->state) +
LRC_STATE_OFFSET;
@@ -3227,6 +3282,16 @@ gen12_emit_timestamp_wa_lrr(struct intel_context *ce, u32 *cs)
*cs++ = scratch_reg;
*cs++ = i915_mmio_reg_offset(RING_CTX_TIMESTAMP(0));
+ *cs++ = MI_LOAD_REGISTER_MEM_GEN8 |
+ MI_SRM_LRM_GLOBAL_GTT | MI_LRI_LRM_CS_MMIO;
+ *cs++ = scratch_reg;
+ *cs++ = lrc_offset + CTX_CMD_BUF_CCTL * sizeof(u32);
+ *cs++ = 0;
+
+ *cs++ = MI_LOAD_REGISTER_REG | MI_LRI_LRM_CS_MMIO;
+ *cs++ = scratch_reg;
+ *cs++ = i915_mmio_reg_offset(RING_CMD_BUF_CCTL(0));
+
return cs;
}
@@ -3290,7 +3355,7 @@ gen12_setup_timestamp_ctx_wa(struct intel_context *ce)
fn = gen12_emit_timestamp_wa_lrm;
if (ce->engine->class == RENDER_CLASS)
- fn = gen12_emit_timestamp_wa_lrr;
+ fn = gen12_emit_render_ctx_wa;
setup_indirect_ctx_bb(ce, fn);
}
@@ -27,6 +27,7 @@
#define CTX_PDP0_UDW (0x30 + 1)
#define CTX_PDP0_LDW (0x32 + 1)
#define CTX_R_PWR_CLK_STATE (0x42 + 1)
+#define CTX_CMD_BUF_CCTL (0xB6 + 1)
#define GEN9_CTX_RING_MI_MODE 0x54
@@ -2657,6 +2657,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define RING_DMA_FADD_UDW(base) _MMIO((base) + 0x60) /* gen8+ */
#define RING_INSTPM(base) _MMIO((base) + 0xc0)
#define RING_MI_MODE(base) _MMIO((base) + 0x9c)
+#define RING_CMD_BUF_CCTL(base) _MMIO((base) + 0x84)
#define INSTPS _MMIO(0x2070) /* 965+ only */
#define GEN4_INSTDONE1 _MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
#define ACTHD_I965 _MMIO(0x2074)
Use indirect ctx bb to load cmd buffer control value from context image to avoid corruption. v2: add to lrc layout (Chris) v3: end to a cacheline (Chris) Testcase: igt/i915_selftest/gt_lrc Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> --- drivers/gpu/drm/i915/gt/intel_lrc.c | 73 +++++++++++++++++++++++-- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 1 + drivers/gpu/drm/i915/i915_reg.h | 1 + 3 files changed, 71 insertions(+), 4 deletions(-)