}
}
-static void unwind_wa_tail(struct i915_request *rq)
-{
- rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
- assert_ring_tail_valid(rq->ring, rq->tail);
-}
-
static struct i915_request *
__unwind_incomplete_requests(struct intel_engine_cs *engine)
{
list_for_each_entry_safe_reverse(rq, rn,
&engine->active.requests,
sched.link) {
-
if (i915_request_completed(rq))
continue; /* XXX */
__i915_request_unsubmit(rq);
- unwind_wa_tail(rq);
/*
* Push the request back into the queue for later resubmission.
i915_request_put(rq);
}
-static u64 execlists_update_context(const struct i915_request *rq)
+static u64 execlists_update_context(struct i915_request *rq)
{
struct intel_context *ce = rq->hw_context;
- u64 desc;
+ u64 desc = ce->lrc_desc;
+ u32 tail;
- ce->lrc_reg_state[CTX_RING_TAIL] =
- intel_ring_set_tail(rq->ring, rq->tail);
+ /*
+ * WaIdleLiteRestore:bdw,skl
+ *
+ * We should never submit the context with the same RING_TAIL twice
+ * just in case we submit an empty ring, which confuses the HW.
+ *
+ * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of
+ * the normal request to be able to always advance the RING_TAIL on
+ * subsequent resubmissions (for lite restore). Should that fail us,
+ * and we try and submit the same tail again, force the context
+ * reload.
+ */
+ tail = intel_ring_set_tail(rq->ring, rq->tail);
+ if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+ desc |= CTX_DESC_FORCE_RESTORE;
+ ce->lrc_reg_state[CTX_RING_TAIL] = tail;
+ rq->tail = rq->wa_tail;
/*
* Make sure the context image is complete before we submit it to HW.
*/
mb();
- desc = ce->lrc_desc;
- ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
-
/* Wa_1607138340:tgl */
if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
desc |= CTX_DESC_FORCE_RESTORE;
+ ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
return desc;
}
return;
}
-
- /*
- * WaIdleLiteRestore:bdw,skl
- * Apply the wa NOOPs to prevent
- * ring:HEAD == rq:TAIL as we resubmit the
- * request. See gen8_emit_fini_breadcrumb() for
- * where we prepare the padding after the
- * end of the request.
- */
- last->tail = last->wa_tail;
}
}
for (n = 0; n < ve->num_siblings; n++) {
struct intel_engine_cs *sibling = ve->siblings[n];
struct rb_node *node = &ve->nodes[sibling->id].rb;
+ unsigned long flags;
if (RB_EMPTY_NODE(node))
continue;
- spin_lock_irq(&sibling->active.lock);
+ spin_lock_irqsave(&sibling->active.lock, flags);
/* Detachment is lazily performed in the execlists tasklet */
if (!RB_EMPTY_NODE(node))
rb_erase_cached(node, &sibling->execlists.virtual);
- spin_unlock_irq(&sibling->active.lock);
+ spin_unlock_irqrestore(&sibling->active.lock, flags);
}
GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet));
u32 *reg_state = ce->lrc_reg_state;
int i;
- if (IS_GEN(stream->perf->i915, 12)) {
- u32 format = stream->oa_buffer.format;
+ reg_state[ctx_oactxctrl + 1] =
+ (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+ (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+ GEN8_OA_COUNTER_RESUME;
- reg_state[ctx_oactxctrl + 1] =
- (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
- (stream->oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
- } else {
- reg_state[ctx_oactxctrl + 1] =
- (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
- (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
- GEN8_OA_COUNTER_RESUME;
- }
-
- for (i = 0; !!ctx_flexeu0 && i < ARRAY_SIZE(flex_regs); i++)
+ for (i = 0; i < ARRAY_SIZE(flex_regs); i++)
reg_state[ctx_flexeu0 + i * 2 + 1] =
oa_config_flex_reg(stream->oa_config, flex_regs[i]);
return err;
}
-static int gen12_emit_oar_config(struct intel_context *ce, bool enable)
+static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable)
{
- struct i915_request *rq;
- u32 *cs;
- int err = 0;
-
- rq = i915_request_create(ce);
- if (IS_ERR(rq))
- return PTR_ERR(rq);
-
- cs = intel_ring_begin(rq, 4);
- if (IS_ERR(cs)) {
- err = PTR_ERR(cs);
- goto out;
- }
-
- *cs++ = MI_LOAD_REGISTER_IMM(1);
- *cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base));
- *cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
- enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0);
- *cs++ = MI_NOOP;
+ int err;
+ struct intel_context *ce = stream->pinned_ctx;
+ u32 format = stream->oa_buffer.format;
+ struct flex regs_context[] = {
+ {
+ GEN8_OACTXCONTROL,
+ stream->perf->ctx_oactxctrl_offset + 1,
+ enable ? GEN8_OA_COUNTER_RESUME : 0,
+ },
+ };
+ /* Offsets in regs_lri are not used since this configuration is only
+ * applied using LRI. Initialize the correct offsets for posterity.
+ */
+#define GEN12_OAR_OACONTROL_OFFSET 0x5B0
+ struct flex regs_lri[] = {
+ {
+ GEN12_OAR_OACONTROL,
+ GEN12_OAR_OACONTROL_OFFSET + 1,
+ (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
+ (enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0)
+ },
+ {
+ RING_CONTEXT_CONTROL(ce->engine->mmio_base),
+ CTX_CONTEXT_CONTROL,
+ _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
+ enable ?
+ GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :
+ 0)
+ },
+ };
- intel_ring_advance(rq, cs);
+ /* Modify the context image of pinned context with regs_context*/
+ err = intel_context_lock_pinned(ce);
+ if (err)
+ return err;
-out:
- i915_request_add(rq);
+ err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context));
+ intel_context_unlock_pinned(ce);
+ if (err)
+ return err;
- return err;
+ /* Apply regs_lri using LRI with pinned context */
+ return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri));
}
/*
* per-context OA state.
*
* Note: it's only the RCS/Render context that has any OA state.
+ * Note: the first flex register passed must always be R_PWR_CLK_STATE
*/
-static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
- const struct i915_oa_config *oa_config)
+static int oa_configure_all_contexts(struct i915_perf_stream *stream,
+ struct flex *regs,
+ size_t num_regs)
{
struct drm_i915_private *i915 = stream->perf->i915;
- /* The MMIO offsets for Flex EU registers aren't contiguous */
- const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
-#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
- struct flex regs[] = {
- {
- GEN8_R_PWR_CLK_STATE,
- CTX_R_PWR_CLK_STATE,
- },
- {
- IS_GEN(i915, 12) ?
- GEN12_OAR_OACONTROL : GEN8_OACTXCONTROL,
- stream->perf->ctx_oactxctrl_offset + 1,
- },
- { EU_PERF_CNTL0, ctx_flexeuN(0) },
- { EU_PERF_CNTL1, ctx_flexeuN(1) },
- { EU_PERF_CNTL2, ctx_flexeuN(2) },
- { EU_PERF_CNTL3, ctx_flexeuN(3) },
- { EU_PERF_CNTL4, ctx_flexeuN(4) },
- { EU_PERF_CNTL5, ctx_flexeuN(5) },
- { EU_PERF_CNTL6, ctx_flexeuN(6) },
- };
-#undef ctx_flexeuN
struct intel_engine_cs *engine;
struct i915_gem_context *ctx, *cn;
- size_t array_size = IS_GEN(i915, 12) ? 2 : ARRAY_SIZE(regs);
- int i, err;
-
- if (IS_GEN(i915, 12)) {
- u32 format = stream->oa_buffer.format;
-
- regs[1].value =
- (format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
- (oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
- } else {
- regs[1].value =
- (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
- (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
- GEN8_OA_COUNTER_RESUME;
- }
-
- for (i = 2; !!ctx_flexeu0 && i < array_size; i++)
- regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
+ int err;
lockdep_assert_held(&stream->perf->lock);
spin_unlock(&i915->gem.contexts.lock);
- err = gen8_configure_context(ctx, regs, array_size);
+ err = gen8_configure_context(ctx, regs, num_regs);
if (err) {
i915_gem_context_put(ctx);
return err;
regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu);
- err = gen8_modify_self(ce, regs, array_size);
+ err = gen8_modify_self(ce, regs, num_regs);
if (err)
return err;
}
return 0;
}
+static int gen12_configure_all_contexts(struct i915_perf_stream *stream,
+ const struct i915_oa_config *oa_config)
+{
+ struct flex regs[] = {
+ {
+ GEN8_R_PWR_CLK_STATE,
+ CTX_R_PWR_CLK_STATE,
+ },
+ };
+
+ return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+}
+
+static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
+ const struct i915_oa_config *oa_config)
+{
+ /* The MMIO offsets for Flex EU registers aren't contiguous */
+ const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
+#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
+ struct flex regs[] = {
+ {
+ GEN8_R_PWR_CLK_STATE,
+ CTX_R_PWR_CLK_STATE,
+ },
+ {
+ GEN8_OACTXCONTROL,
+ stream->perf->ctx_oactxctrl_offset + 1,
+ },
+ { EU_PERF_CNTL0, ctx_flexeuN(0) },
+ { EU_PERF_CNTL1, ctx_flexeuN(1) },
+ { EU_PERF_CNTL2, ctx_flexeuN(2) },
+ { EU_PERF_CNTL3, ctx_flexeuN(3) },
+ { EU_PERF_CNTL4, ctx_flexeuN(4) },
+ { EU_PERF_CNTL5, ctx_flexeuN(5) },
+ { EU_PERF_CNTL6, ctx_flexeuN(6) },
+ };
+#undef ctx_flexeuN
+ int i;
+
+ regs[1].value =
+ (stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+ (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+ GEN8_OA_COUNTER_RESUME;
+
+ for (i = 2; i < ARRAY_SIZE(regs); i++)
+ regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
+
+ return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+}
+
static int gen8_enable_metric_set(struct i915_perf_stream *stream)
{
struct intel_uncore *uncore = stream->uncore;
* to make sure all slices/subslices are ON before writing to NOA
* registers.
*/
- ret = lrc_configure_all_contexts(stream, oa_config);
+ ret = gen12_configure_all_contexts(stream, oa_config);
if (ret)
return ret;
* requested this.
*/
if (stream->ctx) {
- ret = gen12_emit_oar_config(stream->pinned_ctx,
- oa_config != NULL);
+ ret = gen12_configure_oar_context(stream, true);
if (ret)
return ret;
}
struct intel_uncore *uncore = stream->uncore;
/* Reset all contexts' slices/subslices configurations. */
- lrc_configure_all_contexts(stream, NULL);
+ gen12_configure_all_contexts(stream, NULL);
/* disable the context save/restore or OAR counters */
if (stream->ctx)
- gen12_emit_oar_config(stream->pinned_ctx, false);
+ gen12_configure_oar_context(stream, false);
/* Make sure we disable noa to save power. */
intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
return -EINVAL;
}
- if (!(props->sample_flags & SAMPLE_OA_REPORT)) {
+ if (!(props->sample_flags & SAMPLE_OA_REPORT) &&
+ (INTEL_GEN(perf->i915) < 12 || !stream->ctx)) {
DRM_DEBUG("Only OA report sampling supported\n");
return -EINVAL;
}
format_size = perf->oa_formats[props->oa_format].size;
- stream->sample_flags |= SAMPLE_OA_REPORT;
+ stream->sample_flags = props->sample_flags;
stream->sample_size += format_size;
stream->oa_buffer.format_size = format_size;
return;
stream = engine->i915->perf.exclusive_stream;
- if (stream)
+ /*
+ * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller
+ * is already doing that, so nothing to be done for gen12 here.
+ */
+ if (stream && INTEL_GEN(stream->perf->i915) < 12)
gen8_update_reg_state_unlocked(ce, stream);
}
git.samba.org / sfrench / cifs-2.6.git / commitdiff