[PATCH 1/3] drm/i915/selftests: Verify the LRC register layout between init and HW
Chris Wilson
chris at chris-wilson.co.uk
Sun Sep 8 13:50:05 UTC 2019
Before we submit the first context to HW, we need to construct a valid
image of the register state. This layout is defined by the HW and should
match the layout generated by HW when it saves the context image.
Asserting that this should be equivalent should help avoid any undefined
behaviour and verify that we haven't missed anything important!
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 631 ++++++++++++------
drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 13 -
drivers/gpu/drm/i915/gt/selftest_lrc.c | 140 ++++
.../drm/i915/selftests/i915_live_selftests.h | 1 +
4 files changed, 584 insertions(+), 201 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0ddfbebbcbbc..f747815d3837 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -230,9 +230,9 @@ static int __execlists_context_alloc(struct intel_context *ce,
struct intel_engine_cs *engine);
static void execlists_init_reg_state(u32 *reg_state,
- struct intel_context *ce,
- struct intel_engine_cs *engine,
- struct intel_ring *ring);
+ const struct intel_context *ce,
+ const struct intel_engine_cs *engine,
+ const struct intel_ring *ring);
static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
{
@@ -464,6 +464,405 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
return desc;
}
+static u32 *set_offsets(u32 *regs,
+ const u8 *data,
+ const struct intel_engine_cs *engine)
+#define NOP(x) (BIT(7) | (x))
+#define LRI(count, flags) ((flags) << 6 | (count))
+#define POSTED BIT(0)
+#define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
+#define REG16(x) \
+ (((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
+ (((x) >> 2) & 0x7f)
+#define END() 0
+{
+ const u32 base = engine->mmio_base;
+
+ while (*data) {
+ u8 count, flags;
+
+ if (*data & BIT(7)) { /* skip */
+ regs += *data++ & ~BIT(7);
+ continue;
+ }
+
+ count = *data & 0x3f;
+ flags = *data >> 6;
+ data++;
+
+ *regs = MI_LOAD_REGISTER_IMM(count);
+ if (flags & POSTED)
+ *regs |= MI_LRI_FORCE_POSTED;
+ if (intel_engine_has_relative_mmio(engine))
+ *regs |= MI_LRI_CS_MMIO;
+ regs++;
+
+ do {
+ u32 offset = 0;
+ u8 v;
+
+ do {
+ v = *data++;
+ offset <<= 7;
+ offset |= v & ~BIT(7);
+ } while (v & BIT(7));
+
+ *regs = base + (offset << 2);
+ regs += 2;
+ } while (--count);
+ }
+
+ return regs;
+}
+
+static const u8 gen8_xcs_offsets[] = {
+ NOP(1),
+ LRI(11, 0),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x11c),
+ REG(0x114),
+ REG(0x118),
+
+ NOP(9),
+ LRI(9, 0),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ NOP(13),
+ LRI(2, 0),
+ REG16(0x200),
+ REG(0x028),
+
+ END(),
+};
+
+static const u8 gen9_xcs_offsets[] = {
+ NOP(1),
+ LRI(14, POSTED),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x11c),
+ REG(0x114),
+ REG(0x118),
+ REG(0x1c0),
+ REG(0x1c4),
+ REG(0x1c8),
+
+ NOP(3),
+ LRI(9, POSTED),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ NOP(13),
+ LRI(1, POSTED),
+ REG16(0x200),
+
+ NOP(13),
+ LRI(44, POSTED),
+ 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),
+
+ END(),
+};
+
+static const u8 gen12_xcs_offsets[] = {
+ NOP(1),
+ LRI(13, POSTED),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x1c0),
+ REG(0x1c4),
+ REG(0x1c8),
+ REG(0x180),
+ REG16(0x2b4),
+
+ NOP(5),
+ LRI(9, POSTED),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ NOP(13),
+ LRI(2, POSTED),
+ REG16(0x200),
+ REG16(0x204),
+
+ NOP(11),
+ LRI(50, POSTED),
+ REG16(588),
+ REG16(588),
+ REG16(588),
+ REG16(588),
+ REG16(588),
+ REG16(588),
+ 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),
+
+ END(),
+};
+
+static const u8 gen8_rcs_offsets[] = {
+ NOP(1),
+ LRI(14, POSTED),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x11c),
+ REG(0x114),
+ REG(0x118),
+ REG(0x1c0),
+ REG(0x1c4),
+ REG(0x1c8),
+
+ NOP(3),
+ LRI(9, POSTED),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ NOP(13),
+ LRI(1, 0),
+ REG(0x0c8),
+
+ END(),
+};
+
+static const u8 gen11_rcs_offsets[] = {
+ NOP(1),
+ LRI(15, POSTED),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x11c),
+ REG(0x114),
+ REG(0x118),
+ REG(0x1c0),
+ REG(0x1c4),
+ REG(0x1c8),
+ REG(0x180),
+
+ NOP(1),
+ LRI(9, POSTED),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ LRI(1, POSTED),
+ REG(0x1b0),
+
+ NOP(10),
+ LRI(1, 0),
+ REG(0x0c8),
+
+ END(),
+};
+
+static const u8 gen12_rcs_offsets[] = {
+ NOP(1),
+ LRI(13, POSTED),
+ REG16(0x244),
+ REG(0x034),
+ REG(0x030),
+ REG(0x038),
+ REG(0x03c),
+ REG(0x168),
+ REG(0x140),
+ REG(0x110),
+ REG(0x1c0),
+ REG(0x1c4),
+ REG(0x168),
+ REG(0x140),
+ REG(0x180),
+ REG16(0x2b4),
+
+ NOP(5),
+ LRI(9, POSTED),
+ REG16(0x3a8),
+ REG16(0x28c),
+ REG16(0x288),
+ REG16(0x284),
+ REG16(0x280),
+ REG16(0x27c),
+ REG16(0x278),
+ REG16(0x274),
+ REG16(0x270),
+
+ LRI(3, POSTED),
+ REG(0x1b0),
+ REG16(0x5a8),
+ REG16(0x5ac),
+
+ NOP(6),
+ LRI(1, 0),
+ REG(0x0c8),
+
+ END(),
+};
+
+static const u8 *reg_offsets(const struct intel_engine_cs *engine)
+{
+ if (engine->class == RENDER_CLASS) {
+ if (INTEL_GEN(engine->i915) >= 12)
+ return gen12_rcs_offsets;
+ else if (INTEL_GEN(engine->i915) >= 11)
+ return gen11_rcs_offsets;
+ else
+ return gen8_rcs_offsets;
+ } else {
+ if (INTEL_GEN(engine->i915) >= 12)
+ return gen12_xcs_offsets;
+ else if (INTEL_GEN(engine->i915) >= 9)
+ return gen9_xcs_offsets;
+ else
+ return gen8_xcs_offsets;
+ }
+}
+
static void unwind_wa_tail(struct i915_request *rq)
{
rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
@@ -806,54 +1205,7 @@ static bool can_merge_rq(const struct i915_request *prev,
static void virtual_update_register_offsets(u32 *regs,
struct intel_engine_cs *engine)
{
- u32 base = engine->mmio_base;
-
- /* Refactor so that we only have one place that knows all the offsets! */
- GEM_WARN_ON(INTEL_GEN(engine->i915) >= 12);
-
- /* Must match execlists_init_reg_state()! */
-
- /* Common part */
- regs[CTX_CONTEXT_CONTROL] =
- i915_mmio_reg_offset(RING_CONTEXT_CONTROL(base));
- regs[CTX_RING_HEAD] = i915_mmio_reg_offset(RING_HEAD(base));
- regs[CTX_RING_TAIL] = i915_mmio_reg_offset(RING_TAIL(base));
- regs[CTX_RING_BUFFER_START] = i915_mmio_reg_offset(RING_START(base));
- regs[CTX_RING_BUFFER_CONTROL] = i915_mmio_reg_offset(RING_CTL(base));
-
- regs[CTX_BB_HEAD_U] = i915_mmio_reg_offset(RING_BBADDR_UDW(base));
- regs[CTX_BB_HEAD_L] = i915_mmio_reg_offset(RING_BBADDR(base));
- regs[CTX_BB_STATE] = i915_mmio_reg_offset(RING_BBSTATE(base));
-
- regs[CTX_SECOND_BB_HEAD_U] =
- i915_mmio_reg_offset(RING_SBBADDR_UDW(base));
- regs[CTX_SECOND_BB_HEAD_L] = i915_mmio_reg_offset(RING_SBBADDR(base));
- regs[CTX_SECOND_BB_STATE] = i915_mmio_reg_offset(RING_SBBSTATE(base));
-
- /* PPGTT part */
- regs[CTX_CTX_TIMESTAMP] =
- i915_mmio_reg_offset(RING_CTX_TIMESTAMP(base));
-
- regs[CTX_PDP3_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 3));
- regs[CTX_PDP3_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 3));
- regs[CTX_PDP2_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 2));
- regs[CTX_PDP2_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 2));
- regs[CTX_PDP1_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 1));
- regs[CTX_PDP1_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 1));
- regs[CTX_PDP0_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0));
- regs[CTX_PDP0_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 0));
-
- if (engine->class == RENDER_CLASS) {
- regs[CTX_RCS_INDIRECT_CTX] =
- i915_mmio_reg_offset(RING_INDIRECT_CTX(base));
- regs[CTX_RCS_INDIRECT_CTX_OFFSET] =
- i915_mmio_reg_offset(RING_INDIRECT_CTX_OFFSET(base));
- regs[CTX_BB_PER_CTX_PTR] =
- i915_mmio_reg_offset(RING_BB_PER_CTX_PTR(base));
-
- regs[CTX_R_PWR_CLK_STATE] =
- i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
- }
+ set_offsets(regs, reg_offsets(engine), engine);
}
static bool virtual_matches(const struct virtual_engine *ve,
@@ -2950,7 +3302,7 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
engine->flags |= I915_ENGINE_HAS_PREEMPTION;
}
- if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
+ if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 11)
engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
}
@@ -3096,7 +3448,7 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine)
return 0;
}
-static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
+static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
{
u32 indirect_ctx_offset;
@@ -3131,75 +3483,49 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
static void init_common_reg_state(u32 * const regs,
- struct i915_ppgtt * const ppgtt,
- struct intel_engine_cs *engine,
- struct intel_ring *ring)
+ const struct intel_engine_cs *engine,
+ const struct intel_ring *ring)
{
- const u32 base = engine->mmio_base;
-
- CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
+ regs[CTX_CONTEXT_CONTROL + 1] =
_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
- _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH));
- if (INTEL_GEN(engine->i915) < 11) {
+ _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+ if (INTEL_GEN(engine->i915) < 11)
regs[CTX_CONTEXT_CONTROL + 1] |=
_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
CTX_CTRL_RS_CTX_ENABLE);
- }
- CTX_REG(regs, CTX_RING_HEAD, RING_HEAD(base), 0);
- CTX_REG(regs, CTX_RING_TAIL, RING_TAIL(base), 0);
- CTX_REG(regs, CTX_RING_BUFFER_START, RING_START(base), 0);
- CTX_REG(regs, CTX_RING_BUFFER_CONTROL, RING_CTL(base),
- RING_CTL_SIZE(ring->size) | RING_VALID);
- CTX_REG(regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0);
- CTX_REG(regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0);
- CTX_REG(regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT);
+
+ regs[CTX_RING_BUFFER_CONTROL + 1] =
+ RING_CTL_SIZE(ring->size) | RING_VALID;
+ regs[CTX_BB_STATE + 1] = RING_BB_PPGTT;
}
static void init_wa_bb_reg_state(u32 * const regs,
- struct intel_engine_cs *engine,
+ const struct intel_engine_cs *engine,
u32 pos_bb_per_ctx)
{
- struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;
- const u32 base = engine->mmio_base;
- const u32 pos_indirect_ctx = pos_bb_per_ctx + 2;
- const u32 pos_indirect_ctx_offset = pos_indirect_ctx + 2;
+ const struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;
+
+ if (wa_ctx->per_ctx.size) {
+ const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
+
+ regs[pos_bb_per_ctx + 1] =
+ (ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
+ }
- CTX_REG(regs, pos_indirect_ctx, RING_INDIRECT_CTX(base), 0);
- CTX_REG(regs, pos_indirect_ctx_offset,
- RING_INDIRECT_CTX_OFFSET(base), 0);
if (wa_ctx->indirect_ctx.size) {
const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
- regs[pos_indirect_ctx + 1] =
+ regs[pos_bb_per_ctx + 2 + 1] =
(ggtt_offset + wa_ctx->indirect_ctx.offset) |
(wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
- regs[pos_indirect_ctx_offset + 1] =
+ regs[pos_bb_per_ctx + 4 + 1] =
intel_lr_indirect_ctx_offset(engine) << 6;
}
-
- CTX_REG(regs, pos_bb_per_ctx, RING_BB_PER_CTX_PTR(base), 0);
- if (wa_ctx->per_ctx.size) {
- const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
-
- regs[pos_bb_per_ctx + 1] =
- (ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
- }
}
-static void init_ppgtt_reg_state(u32 *regs, u32 base,
- struct i915_ppgtt *ppgtt)
+static void init_ppgtt_reg_state(u32 *regs, const struct i915_ppgtt *ppgtt)
{
- /* PDP values well be assigned later if needed */
- CTX_REG(regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0);
- CTX_REG(regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0);
- CTX_REG(regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0);
- CTX_REG(regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0);
- CTX_REG(regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0);
- CTX_REG(regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0);
- CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0);
- CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0);
-
if (i915_vm_is_4lvl(&ppgtt->vm)) {
/* 64b PPGTT (48bit canonical)
* PDP0_DESCRIPTOR contains the base address to PML4 and
@@ -3222,91 +3548,10 @@ static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
return i915_vm_to_ppgtt(vm);
}
-static void gen8_init_reg_state(u32 * const regs,
- struct intel_context *ce,
- struct intel_engine_cs *engine,
- struct intel_ring *ring)
-{
- struct i915_ppgtt * const ppgtt = vm_alias(ce->vm);
- const bool rcs = engine->class == RENDER_CLASS;
- const u32 base = engine->mmio_base;
- const u32 lri_base =
- intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
-
- regs[CTX_LRI_HEADER_0] =
- MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
- MI_LRI_FORCE_POSTED |
- lri_base;
-
- init_common_reg_state(regs, ppgtt, engine, ring);
- CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
- CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0);
- CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0);
- if (rcs)
- init_wa_bb_reg_state(regs, engine, CTX_BB_PER_CTX_PTR);
-
- regs[CTX_LRI_HEADER_1] =
- MI_LOAD_REGISTER_IMM(9) |
- MI_LRI_FORCE_POSTED |
- lri_base;
-
- CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
-
- init_ppgtt_reg_state(regs, base, ppgtt);
-
- if (rcs) {
- regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1) | lri_base;
- CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
- }
-
- regs[CTX_END] = MI_BATCH_BUFFER_END;
- if (INTEL_GEN(engine->i915) >= 10)
- regs[CTX_END] |= BIT(0);
-}
-
-static void gen12_init_reg_state(u32 * const regs,
- struct intel_context *ce,
- struct intel_engine_cs *engine,
- struct intel_ring *ring)
-{
- struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(ce->vm);
- const bool rcs = engine->class == RENDER_CLASS;
- const u32 base = engine->mmio_base;
- const u32 lri_base =
- intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
-
- regs[CTX_LRI_HEADER_0] =
- MI_LOAD_REGISTER_IMM(rcs ? 11 : 9) |
- MI_LRI_FORCE_POSTED |
- lri_base;
-
- init_common_reg_state(regs, ppgtt, engine, ring);
-
- /* We want ctx_ptr for all engines to be set */
- init_wa_bb_reg_state(regs, engine, GEN12_CTX_BB_PER_CTX_PTR);
-
- regs[CTX_LRI_HEADER_1] =
- MI_LOAD_REGISTER_IMM(9) |
- MI_LRI_FORCE_POSTED |
- lri_base;
-
- CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
-
- init_ppgtt_reg_state(regs, base, ppgtt);
-
- if (rcs) {
- regs[GEN12_CTX_LRI_HEADER_3] =
- MI_LOAD_REGISTER_IMM(1) | lri_base;
- CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
-
- /* TODO: oa_init_reg_state ? */
- }
-}
-
static void execlists_init_reg_state(u32 *regs,
- struct intel_context *ce,
- struct intel_engine_cs *engine,
- struct intel_ring *ring)
+ const struct intel_context *ce,
+ const struct intel_engine_cs *engine,
+ const struct intel_ring *ring)
{
/*
* A context is actually a big batch buffer with several
@@ -3318,10 +3563,20 @@ static void execlists_init_reg_state(u32 *regs,
*
* Must keep consistent with virtual_update_register_offsets().
*/
- if (INTEL_GEN(engine->i915) >= 12)
- gen12_init_reg_state(regs, ce, engine, ring);
- else
- gen8_init_reg_state(regs, ce, engine, ring);
+ u32 *bbe = set_offsets(regs, reg_offsets(engine), engine);
+
+ /* Close the batch; used mainly by live_lrc_layout() */
+ *bbe = MI_BATCH_BUFFER_END;
+ if (INTEL_GEN(engine->i915) >= 10)
+ *bbe |= BIT(0);
+
+ init_common_reg_state(regs, engine, ring);
+ init_ppgtt_reg_state(regs, vm_alias(ce->vm));
+
+ init_wa_bb_reg_state(regs, engine,
+ INTEL_GEN(engine->i915) >= 12 ?
+ GEN12_CTX_BB_PER_CTX_PTR :
+ CTX_BB_PER_CTX_PTR);
}
static int
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 68caf8541866..17381be2f0a4 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -10,23 +10,13 @@
#include <linux/types.h>
/* GEN8 to GEN11 Reg State Context */
-#define CTX_LRI_HEADER_0 0x01
#define CTX_CONTEXT_CONTROL 0x02
#define CTX_RING_HEAD 0x04
#define CTX_RING_TAIL 0x06
#define CTX_RING_BUFFER_START 0x08
#define CTX_RING_BUFFER_CONTROL 0x0a
-#define CTX_BB_HEAD_U 0x0c
-#define CTX_BB_HEAD_L 0x0e
#define CTX_BB_STATE 0x10
-#define CTX_SECOND_BB_HEAD_U 0x12
-#define CTX_SECOND_BB_HEAD_L 0x14
-#define CTX_SECOND_BB_STATE 0x16
#define CTX_BB_PER_CTX_PTR 0x18
-#define CTX_RCS_INDIRECT_CTX 0x1a
-#define CTX_RCS_INDIRECT_CTX_OFFSET 0x1c
-#define CTX_LRI_HEADER_1 0x21
-#define CTX_CTX_TIMESTAMP 0x22
#define CTX_PDP3_UDW 0x24
#define CTX_PDP3_LDW 0x26
#define CTX_PDP2_UDW 0x28
@@ -35,13 +25,10 @@
#define CTX_PDP1_LDW 0x2e
#define CTX_PDP0_UDW 0x30
#define CTX_PDP0_LDW 0x32
-#define CTX_LRI_HEADER_2 0x41
#define CTX_R_PWR_CLK_STATE 0x42
-#define CTX_END 0x44
/* GEN12+ Reg State Context */
#define GEN12_CTX_BB_PER_CTX_PTR 0x12
-#define GEN12_CTX_LRI_HEADER_3 0x41
#define CTX_REG(reg_state, pos, reg, val) do { \
u32 *reg_state__ = (reg_state); \
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index d791158988d6..90ef882c5755 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -2191,3 +2191,143 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
return i915_live_subtests(tests, i915);
}
+
+static void hexdump(const void *buf, size_t len)
+{
+ const size_t rowsize = 8 * sizeof(u32);
+ const void *prev = NULL;
+ bool skip = false;
+ size_t pos;
+
+ for (pos = 0; pos < len; pos += rowsize) {
+ char line[128];
+
+ if (prev && !memcmp(prev, buf + pos, rowsize)) {
+ if (!skip) {
+ pr_info("*\n");
+ skip = true;
+ }
+ continue;
+ }
+
+ WARN_ON_ONCE(hex_dump_to_buffer(buf + pos, len - pos,
+ rowsize, sizeof(u32),
+ line, sizeof(line),
+ false) >= sizeof(line));
+ pr_info("[%04zx] %s\n", pos, line);
+
+ prev = buf + pos;
+ skip = false;
+ }
+}
+
+static int live_lrc_layout(void *arg)
+{
+ struct intel_gt *gt = arg;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ u32 *mem, *lrc;
+ int err = 0;
+
+ /*
+ * Check the registers offsets we use to create the initial reg state
+ * match the layout saved by HW.
+ */
+
+ mem = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!mem)
+ return -ENOMEM;
+
+ for_each_engine(engine, gt->i915, id) {
+ u32 *hw;
+ int dw;
+
+ if (!engine->default_state)
+ continue;
+
+ hw = i915_gem_object_pin_map(engine->default_state,
+ I915_MAP_WB);
+ if (IS_ERR(hw)) {
+ err = PTR_ERR(hw);
+ break;
+ }
+ hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+
+ lrc = memset(mem, 0, PAGE_SIZE);
+ execlists_init_reg_state(lrc,
+ engine->kernel_context,
+ engine,
+ engine->kernel_context->ring);
+
+ dw = 0;
+ do {
+ u32 lri = hw[dw];
+
+ if (lri == 0) {
+ dw++;
+ continue;
+ }
+
+ if ((lri & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) {
+ pr_err("%s: Expected LRI command at dword %d, found %08x\n",
+ engine->name, dw, lri);
+ err = -EINVAL;
+ break;
+ }
+
+ if (lrc[dw] != lri) {
+ pr_err("%s: LRI command mismatch at dword %d, expected %08x found %08x\n",
+ engine->name, dw, lri, lrc[dw]);
+ err = -EINVAL;
+ break;
+ }
+
+ lri &= 0x7f;
+ lri++;
+ dw++;
+
+ while (lri) {
+ if (hw[dw] != lrc[dw]) {
+ pr_err("%s: Different registers found at dword %d, expected %x, found %x\n",
+ engine->name, dw, hw[dw], lrc[dw]);
+ err = -EINVAL;
+ break;
+ }
+
+ /*
+ * Skip over the actual register value as we
+ * expect that to differ.
+ */
+ dw += 2;
+ lri -= 2;
+ }
+ } while ((lrc[dw] & ~BIT(0)) != MI_BATCH_BUFFER_END);
+
+ if (err) {
+ pr_info("%s: HW register image:\n", engine->name);
+ hexdump(hw, PAGE_SIZE);
+
+ pr_info("%s: SW register image:\n", engine->name);
+ hexdump(lrc, PAGE_SIZE);
+ }
+
+ i915_gem_object_unpin_map(engine->default_state);
+ if (err)
+ break;
+ }
+
+ kfree(lrc);
+ return err;
+}
+
+int intel_lrc_live_selftests(struct drm_i915_private *i915)
+{
+ static const struct i915_subtest tests[] = {
+ SUBTEST(live_lrc_layout),
+ };
+
+ if (!HAS_LOGICAL_RING_CONTEXTS(i915))
+ return 0;
+
+ return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 1ccf0f731ac0..66d83c1390c1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -15,6 +15,7 @@ selftest(workarounds, intel_workarounds_live_selftests)
selftest(gt_engines, intel_engine_live_selftests)
selftest(gt_timelines, intel_timeline_live_selftests)
selftest(gt_contexts, intel_context_live_selftests)
+selftest(gt_lrc, intel_lrc_live_selftests)
selftest(requests, i915_request_live_selftests)
selftest(active, i915_active_live_selftests)
selftest(objects, i915_gem_object_live_selftests)
--
2.23.0
More information about the Intel-gfx-trybot
mailing list