diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_perf.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 550 |
1 files changed, 443 insertions, 107 deletions
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 004074936300..050b8ae7b8e7 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -192,6 +192,7 @@ */ #include <linux/anon_inodes.h> +#include <linux/nospec.h> #include <linux/sizes.h> #include <linux/uuid.h> @@ -208,6 +209,7 @@ #include "gt/intel_gt_regs.h" #include "gt/intel_lrc.h" #include "gt/intel_lrc_reg.h" +#include "gt/intel_rc6.h" #include "gt/intel_ring.h" #include "gt/uc/intel_guc_slpc.h" @@ -326,6 +328,12 @@ static const struct i915_oa_format oa_formats[I915_OA_FORMAT_MAX] = { [I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 }, [I915_OAR_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 }, [I915_OA_FORMAT_A24u40_A14u32_B8_C8] = { 5, 256 }, + [I915_OAM_FORMAT_MPEC8u64_B8_C8] = { 1, 192, TYPE_OAM, HDR_64_BIT }, + [I915_OAM_FORMAT_MPEC8u32_B8_C8] = { 2, 128, TYPE_OAM, HDR_64_BIT }, +}; + +static const u32 mtl_oa_base[] = { + [PERF_GROUP_OAM_SAMEDIA_0] = 0x393000, }; #define SAMPLE_OA_REPORT (1<<0) @@ -418,11 +426,17 @@ static void free_oa_config_bo(struct i915_oa_config_bo *oa_bo) kfree(oa_bo); } +static inline const +struct i915_perf_regs *__oa_regs(struct i915_perf_stream *stream) +{ + return &stream->engine->oa_group->regs; +} + static u32 gen12_oa_hw_tail_read(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; - return intel_uncore_read(uncore, GEN12_OAG_OATAILPTR) & + return intel_uncore_read(uncore, __oa_regs(stream)->oa_tail_ptr) & GEN12_OAG_OATAILPTR_MASK; } @@ -441,6 +455,67 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream) return oastatus1 & GEN7_OASTATUS1_TAIL_MASK; } +#define oa_report_header_64bit(__s) \ + ((__s)->oa_buffer.format->header == HDR_64_BIT) + +static u64 oa_report_id(struct i915_perf_stream *stream, void *report) +{ + return oa_report_header_64bit(stream) ? *(u64 *)report : *(u32 *)report; +} + +static u64 oa_report_reason(struct i915_perf_stream *stream, void *report) +{ + return (oa_report_id(stream, report) >> OAREPORT_REASON_SHIFT) & + (GRAPHICS_VER(stream->perf->i915) == 12 ? + OAREPORT_REASON_MASK_EXTENDED : + OAREPORT_REASON_MASK); +} + +static void oa_report_id_clear(struct i915_perf_stream *stream, u32 *report) +{ + if (oa_report_header_64bit(stream)) + *(u64 *)report = 0; + else + *report = 0; +} + +static bool oa_report_ctx_invalid(struct i915_perf_stream *stream, void *report) +{ + return !(oa_report_id(stream, report) & + stream->perf->gen8_valid_ctx_bit) && + GRAPHICS_VER(stream->perf->i915) <= 11; +} + +static u64 oa_timestamp(struct i915_perf_stream *stream, void *report) +{ + return oa_report_header_64bit(stream) ? + *((u64 *)report + 1) : + *((u32 *)report + 1); +} + +static void oa_timestamp_clear(struct i915_perf_stream *stream, u32 *report) +{ + if (oa_report_header_64bit(stream)) + *(u64 *)&report[2] = 0; + else + report[1] = 0; +} + +static u32 oa_context_id(struct i915_perf_stream *stream, u32 *report) +{ + u32 ctx_id = oa_report_header_64bit(stream) ? report[4] : report[2]; + + return ctx_id & stream->specific_ctx_id_mask; +} + +static void oa_context_id_squash(struct i915_perf_stream *stream, u32 *report) +{ + if (oa_report_header_64bit(stream)) + report[4] = INVALID_CTX_ID; + else + report[2] = INVALID_CTX_ID; +} + /** * oa_buffer_check_unlocked - check for data and update tail ptr state * @stream: i915 stream instance @@ -473,6 +548,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) bool pollin; u32 hw_tail; u64 now; + u32 partial_report_size; /* We have to consider the (unlikely) possibility that read() errors * could result in an OA buffer reset which might reset the head and @@ -482,10 +558,15 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) hw_tail = stream->perf->ops.oa_hw_tail_read(stream); - /* The tail pointer increases in 64 byte increments, - * not in report_size steps... + /* The tail pointer increases in 64 byte increments, not in report_size + * steps. Also the report size may not be a power of 2. Compute + * potentially partially landed report in the OA buffer */ - hw_tail &= ~(report_size - 1); + partial_report_size = OA_TAKEN(hw_tail, stream->oa_buffer.tail); + partial_report_size %= report_size; + + /* Subtract partial amount off the tail */ + hw_tail = gtt_offset + OA_TAKEN(hw_tail, partial_report_size); now = ktime_get_mono_fast_ns(); @@ -509,21 +590,22 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) hw_tail -= gtt_offset; tail = hw_tail; - /* Walk the stream backward until we find a report with dword 0 - * & 1 not at 0. Since the circular buffer pointers progress by - * increments of 64 bytes and that reports can be up to 256 - * bytes long, we can't tell whether a report has fully landed - * in memory before the first 2 dwords of the following report - * have effectively landed. + /* Walk the stream backward until we find a report with report + * id and timestmap not at 0. Since the circular buffer pointers + * progress by increments of 64 bytes and that reports can be up + * to 256 bytes long, we can't tell whether a report has fully + * landed in memory before the report id and timestamp of the + * following report have effectively landed. * * This is assuming that the writes of the OA unit land in * memory in the order they were written to. * If not : (╯°□°）╯︵ ┻━┻ */ while (OA_TAKEN(tail, aged_tail) >= report_size) { - u32 *report32 = (void *)(stream->oa_buffer.vaddr + tail); + void *report = stream->oa_buffer.vaddr + tail; - if (report32[0] != 0 || report32[1] != 0) + if (oa_report_id(stream, report) || + oa_timestamp(stream, report)) break; tail = (tail - report_size) & (OA_BUFFER_SIZE - 1); @@ -607,6 +689,8 @@ static int append_oa_sample(struct i915_perf_stream *stream, { int report_size = stream->oa_buffer.format->size; struct drm_i915_perf_record_header header; + int report_size_partial; + u8 *oa_buf_end; header.type = DRM_I915_PERF_RECORD_SAMPLE; header.pad = 0; @@ -620,8 +704,20 @@ static int append_oa_sample(struct i915_perf_stream *stream, return -EFAULT; buf += sizeof(header); - if (copy_to_user(buf, report, report_size)) + oa_buf_end = stream->oa_buffer.vaddr + OA_BUFFER_SIZE; + report_size_partial = oa_buf_end - report; + + if (report_size_partial < report_size) { + if (copy_to_user(buf, report, report_size_partial)) + return -EFAULT; + buf += report_size_partial; + + if (copy_to_user(buf, stream->oa_buffer.vaddr, + report_size - report_size_partial)) + return -EFAULT; + } else if (copy_to_user(buf, report, report_size)) { return -EFAULT; + } (*offset) += header.size; @@ -685,12 +781,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * An out of bounds or misaligned head or tail pointer implies a driver * bug since we validate + align the tail pointers we read from the * hardware and we are in full control of the head pointer which should - * only be incremented by multiples of the report size (notably also - * all a power of two). + * only be incremented by multiples of the report size. */ if (drm_WARN_ONCE(&uncore->i915->drm, - head > OA_BUFFER_SIZE || head % report_size || - tail > OA_BUFFER_SIZE || tail % report_size, + head > OA_BUFFER_SIZE || + tail > OA_BUFFER_SIZE, "Inconsistent OA buffer pointers: head = %u, tail = %u\n", head, tail)) return -EIO; @@ -702,39 +797,19 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, u8 *report = oa_buf_base + head; u32 *report32 = (void *)report; u32 ctx_id; - u32 reason; - - /* - * All the report sizes factor neatly into the buffer - * size so we never expect to see a report split - * between the beginning and end of the buffer. - * - * Given the initial alignment check a misalignment - * here would imply a driver bug that would result - * in an overrun. - */ - if (drm_WARN_ON(&uncore->i915->drm, - (OA_BUFFER_SIZE - head) < report_size)) { - drm_err(&uncore->i915->drm, - "Spurious OA head ptr: non-integral report offset\n"); - break; - } + u64 reason; /* * The reason field includes flags identifying what * triggered this specific report (mostly timer * triggered or e.g. due to a context switch). * - * This field is never expected to be zero so we can - * check that the report isn't invalid before copying - * it to userspace... + * In MMIO triggered reports, some platforms do not set the + * reason bit in this field and it is valid to have a reason + * field of zero. */ - reason = ((report32[0] >> OAREPORT_REASON_SHIFT) & - (GRAPHICS_VER(stream->perf->i915) == 12 ? - OAREPORT_REASON_MASK_EXTENDED : - OAREPORT_REASON_MASK)); - - ctx_id = report32[2] & stream->specific_ctx_id_mask; + reason = oa_report_reason(stream, report); + ctx_id = oa_context_id(stream, report32); /* * Squash whatever is in the CTX_ID field if it's marked as @@ -744,9 +819,10 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * Note: that we don't clear the valid_ctx_bit so userspace can * understand that the ID has been squashed by the kernel. */ - if (!(report32[0] & stream->perf->gen8_valid_ctx_bit) && - GRAPHICS_VER(stream->perf->i915) <= 11) - ctx_id = report32[2] = INVALID_CTX_ID; + if (oa_report_ctx_invalid(stream, report)) { + ctx_id = INVALID_CTX_ID; + oa_context_id_squash(stream, report32); + } /* * NB: For Gen 8 the OA unit no longer supports clock gating @@ -790,7 +866,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, */ if (stream->ctx && stream->specific_ctx_id != ctx_id) { - report32[2] = INVALID_CTX_ID; + oa_context_id_squash(stream, report32); } ret = append_oa_sample(stream, buf, count, offset, @@ -802,18 +878,19 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, } /* - * Clear out the first 2 dword as a mean to detect unlanded + * Clear out the report id and timestamp as a means to detect unlanded * reports. */ - report32[0] = 0; - report32[1] = 0; + oa_report_id_clear(stream, report32); + oa_timestamp_clear(stream, report32); } if (start_offset != *offset) { i915_reg_t oaheadptr; oaheadptr = GRAPHICS_VER(stream->perf->i915) == 12 ? - GEN12_OAG_OAHEADPTR : GEN8_OAHEADPTR; + __oa_regs(stream)->oa_head_ptr : + GEN8_OAHEADPTR; spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); @@ -866,7 +943,8 @@ static int gen8_oa_read(struct i915_perf_stream *stream, return -EIO; oastatus_reg = GRAPHICS_VER(stream->perf->i915) == 12 ? - GEN12_OAG_OASTATUS : GEN8_OASTATUS; + __oa_regs(stream)->oa_status : + GEN8_OASTATUS; oastatus = intel_uncore_read(uncore, oastatus_reg); @@ -1570,12 +1648,23 @@ free_noa_wait(struct i915_perf_stream *stream) i915_vma_unpin_and_release(&stream->noa_wait, 0); } +static bool engine_supports_oa(const struct intel_engine_cs *engine) +{ + return engine->oa_group; +} + +static bool engine_supports_oa_format(struct intel_engine_cs *engine, int type) +{ + return engine->oa_group && engine->oa_group->type == type; +} + static void i915_oa_stream_destroy(struct i915_perf_stream *stream) { struct i915_perf *perf = stream->perf; struct intel_gt *gt = stream->engine->gt; + struct i915_perf_group *g = stream->engine->oa_group; - if (WARN_ON(stream != gt->perf.exclusive_stream)) + if (WARN_ON(stream != g->exclusive_stream)) return; /* @@ -1584,7 +1673,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) * * See i915_oa_init_reg_state() and lrc_configure_all_contexts() */ - WRITE_ONCE(gt->perf.exclusive_stream, NULL); + WRITE_ONCE(g->exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); @@ -1720,8 +1809,8 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); - intel_uncore_write(uncore, GEN12_OAG_OASTATUS, 0); - intel_uncore_write(uncore, GEN12_OAG_OAHEADPTR, + intel_uncore_write(uncore, __oa_regs(stream)->oa_status, 0); + intel_uncore_write(uncore, __oa_regs(stream)->oa_head_ptr, gtt_offset & GEN12_OAG_OAHEADPTR_MASK); stream->oa_buffer.head = gtt_offset; @@ -1733,9 +1822,9 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) * to enable proper functionality of the overflow * bit." */ - intel_uncore_write(uncore, GEN12_OAG_OABUFFER, gtt_offset | + intel_uncore_write(uncore, __oa_regs(stream)->oa_buffer, gtt_offset | OABUFFER_SIZE_16M | GEN8_OABUFFER_MEM_SELECT_GGTT); - intel_uncore_write(uncore, GEN12_OAG_OATAILPTR, + intel_uncore_write(uncore, __oa_regs(stream)->oa_tail_ptr, gtt_offset & GEN12_OAG_OATAILPTR_MASK); /* Mark that we need updated tail pointers to read from... */ @@ -2495,7 +2584,8 @@ err_add_request: return err; } -static int gen8_configure_context(struct i915_gem_context *ctx, +static int gen8_configure_context(struct i915_perf_stream *stream, + struct i915_gem_context *ctx, struct flex *flex, unsigned int count) { struct i915_gem_engines_iter it; @@ -2636,7 +2726,7 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, spin_unlock(&i915->gem.contexts.lock); - err = gen8_configure_context(ctx, regs, num_regs); + err = gen8_configure_context(stream, ctx, regs, num_regs); if (err) { i915_gem_context_put(ctx); return err; @@ -2681,6 +2771,9 @@ gen12_configure_all_contexts(struct i915_perf_stream *stream, }, }; + if (stream->engine->class != RENDER_CLASS) + return 0; + return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs), active); @@ -2810,7 +2903,7 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, _MASKED_BIT_ENABLE(GEN12_DISABLE_DOP_GATING)); } - intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG, + intel_uncore_write(uncore, __oa_regs(stream)->oa_debug, /* Disable clk ratio reports, like previous Gens. */ _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS | GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO) | @@ -2820,7 +2913,7 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, */ oag_report_ctx_switches(stream)); - intel_uncore_write(uncore, GEN12_OAG_OAGLBCTXCTRL, periodic ? + intel_uncore_write(uncore, __oa_regs(stream)->oa_ctx_ctrl, periodic ? (GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME | GEN12_OAG_OAGLBCTXCTRL_TIMER_ENABLE | (period_exponent << GEN12_OAG_OAGLBCTXCTRL_TIMER_PERIOD_SHIFT)) @@ -2974,8 +3067,8 @@ static void gen8_oa_enable(struct i915_perf_stream *stream) static void gen12_oa_enable(struct i915_perf_stream *stream) { - struct intel_uncore *uncore = stream->uncore; - u32 report_format = stream->oa_buffer.format->format; + const struct i915_perf_regs *regs; + u32 val; /* * If we don't want OA reports from the OA buffer, then we don't even @@ -2986,9 +3079,11 @@ static void gen12_oa_enable(struct i915_perf_stream *stream) gen12_init_oa_buffer(stream); - intel_uncore_write(uncore, GEN12_OAG_OACONTROL, - (report_format << GEN12_OAG_OACONTROL_OA_COUNTER_FORMAT_SHIFT) | - GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE); + regs = __oa_regs(stream); + val = (stream->oa_buffer.format->format << regs->oa_ctrl_counter_format_shift) | + GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE; + + intel_uncore_write(stream->uncore, regs->oa_ctrl, val); } /** @@ -3040,9 +3135,9 @@ static void gen12_oa_disable(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; - intel_uncore_write(uncore, GEN12_OAG_OACONTROL, 0); + intel_uncore_write(uncore, __oa_regs(stream)->oa_ctrl, 0); if (intel_wait_for_register(uncore, - GEN12_OAG_OACONTROL, + __oa_regs(stream)->oa_ctrl, GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE, 0, 50)) drm_err(&stream->perf->i915->drm, @@ -3182,6 +3277,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct i915_perf *perf = stream->perf; + struct i915_perf_group *g; struct intel_gt *gt; int ret; @@ -3191,6 +3287,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return -EINVAL; } gt = props->engine->gt; + g = props->engine->oa_group; /* * If the sysfs metrics/ directory wasn't registered for some @@ -3221,7 +3318,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, * counter reports and marshal to the appropriate client * we currently only allow exclusive access */ - if (gt->perf.exclusive_stream) { + if (g->exclusive_stream) { drm_dbg(&stream->perf->i915->drm, "OA unit already in use\n"); return -EBUSY; @@ -3316,7 +3413,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; stream->engine->gt->perf.sseu = props->sseu; - WRITE_ONCE(gt->perf.exclusive_stream, stream); + WRITE_ONCE(g->exclusive_stream, stream); ret = i915_perf_stream_enable_sync(stream); if (ret) { @@ -3339,7 +3436,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return 0; err_enable: - WRITE_ONCE(gt->perf.exclusive_stream, NULL); + WRITE_ONCE(g->exclusive_stream, NULL); perf->ops.disable_metric_set(stream); free_oa_buffer(stream); @@ -3373,7 +3470,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce, return; /* perf.exclusive_stream serialised by lrc_configure_all_contexts() */ - stream = READ_ONCE(engine->gt->perf.exclusive_stream); + stream = READ_ONCE(engine->oa_group->exclusive_stream); if (stream && GRAPHICS_VER(stream->perf->i915) < 12) gen8_update_reg_state_unlocked(ce, stream); } @@ -3940,41 +4037,35 @@ static int read_properties_unlocked(struct i915_perf *perf, u32 n_props, struct perf_open_properties *props) { + struct drm_i915_gem_context_param_sseu user_sseu; + const struct i915_oa_format *f; u64 __user *uprop = uprops; + bool config_instance = false; + bool config_class = false; + bool config_sseu = false; + u8 class, instance; u32 i; int ret; memset(props, 0, sizeof(struct perf_open_properties)); props->poll_oa_period = DEFAULT_POLL_PERIOD_NS; - if (!n_props) { - drm_dbg(&perf->i915->drm, - "No i915 perf properties given\n"); - return -EINVAL; - } - - /* At the moment we only support using i915-perf on the RCS. */ - props->engine = intel_engine_lookup_user(perf->i915, - I915_ENGINE_CLASS_RENDER, - 0); - if (!props->engine) { - drm_dbg(&perf->i915->drm, - "No RENDER-capable engines\n"); - return -EINVAL; - } - /* Considering that ID = 0 is reserved and assuming that we don't * (currently) expect any configurations to ever specify duplicate * values for a particular property ID then the last _PROP_MAX value is * one greater than the maximum number of properties we expect to get * from userspace. */ - if (n_props >= DRM_I915_PERF_PROP_MAX) { + if (!n_props || n_props >= DRM_I915_PERF_PROP_MAX) { drm_dbg(&perf->i915->drm, - "More i915 perf properties specified than exist\n"); + "Invalid number of i915 perf properties given\n"); return -EINVAL; } + /* Defaults when class:instance is not passed */ + class = I915_ENGINE_CLASS_RENDER; + instance = 0; + for (i = 0; i < n_props; i++) { u64 oa_period, oa_freq_hz; u64 id, value; @@ -4069,8 +4160,6 @@ static int read_properties_unlocked(struct i915_perf *perf, props->hold_preemption = !!value; break; case DRM_I915_PERF_PROP_GLOBAL_SSEU: { - struct drm_i915_gem_context_param_sseu user_sseu; - if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 50)) { drm_dbg(&perf->i915->drm, "SSEU config not supported on gfx %x\n", @@ -4085,14 +4174,7 @@ static int read_properties_unlocked(struct i915_perf *perf, "Unable to copy global sseu parameter\n"); return -EFAULT; } - - ret = get_sseu_config(&props->sseu, props->engine, &user_sseu); - if (ret) { - drm_dbg(&perf->i915->drm, - "Invalid SSEU configuration\n"); - return ret; - } - props->has_sseu = true; + config_sseu = true; break; } case DRM_I915_PERF_PROP_POLL_OA_PERIOD: @@ -4104,7 +4186,15 @@ static int read_properties_unlocked(struct i915_perf *perf, } props->poll_oa_period = value; break; - case DRM_I915_PERF_PROP_MAX: + case DRM_I915_PERF_PROP_OA_ENGINE_CLASS: + class = (u8)value; + config_class = true; + break; + case DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE: + instance = (u8)value; + config_instance = true; + break; + default: MISSING_CASE(id); return -EINVAL; } @@ -4112,6 +4202,60 @@ static int read_properties_unlocked(struct i915_perf *perf, uprop += 2; } + if ((config_class && !config_instance) || + (config_instance && !config_class)) { + drm_dbg(&perf->i915->drm, + "OA engine-class and engine-instance parameters must be passed together\n"); + return -EINVAL; + } + + props->engine = intel_engine_lookup_user(perf->i915, class, instance); + if (!props->engine) { + drm_dbg(&perf->i915->drm, + "OA engine class and instance invalid %d:%d\n", + class, instance); + return -EINVAL; + } + + if (!engine_supports_oa(props->engine)) { + drm_dbg(&perf->i915->drm, + "Engine not supported by OA %d:%d\n", + class, instance); + return -EINVAL; + } + + /* + * Wa_14017512683: mtl[a0..c0): Use of OAM must be preceded with Media + * C6 disable in BIOS. Fail if Media C6 is enabled on steppings where OAM + * does not work as expected. + */ + if (IS_MTL_MEDIA_STEP(props->engine->i915, STEP_A0, STEP_C0) && + props->engine->oa_group->type == TYPE_OAM && + intel_check_bios_c6_setup(&props->engine->gt->rc6)) { + drm_dbg(&perf->i915->drm, + "OAM requires media C6 to be disabled in BIOS\n"); + return -EINVAL; + } + + i = array_index_nospec(props->oa_format, I915_OA_FORMAT_MAX); + f = &perf->oa_formats[i]; + if (!engine_supports_oa_format(props->engine, f->type)) { + drm_dbg(&perf->i915->drm, + "Invalid OA format %d for class %d\n", + f->type, props->engine->class); + return -EINVAL; + } + + if (config_sseu) { + ret = get_sseu_config(&props->sseu, props->engine, &user_sseu); + if (ret) { + drm_dbg(&perf->i915->drm, + "Invalid SSEU configuration\n"); + return ret; + } + props->has_sseu = true; + } + return 0; } @@ -4282,6 +4426,14 @@ static const struct i915_range gen12_oa_b_counters[] = { {} }; +static const struct i915_range mtl_oam_b_counters[] = { + { .start = 0x393000, .end = 0x39301c }, /* GEN12_OAM_STARTTRIG1[1-8] */ + { .start = 0x393020, .end = 0x39303c }, /* GEN12_OAM_REPORTTRIG1[1-8] */ + { .start = 0x393040, .end = 0x39307c }, /* GEN12_OAM_CEC[0-7][0-1] */ + { .start = 0x393200, .end = 0x39323C }, /* MPES[0-7] */ + {} +}; + static const struct i915_range xehp_oa_b_counters[] = { { .start = 0xdc48, .end = 0xdc48 }, /* OAA_ENABLE_REG */ { .start = 0xdd00, .end = 0xdd48 }, /* OAG_LCE0_0 - OAA_LENABLE_REG */ @@ -4335,6 +4487,8 @@ static const struct i915_range mtl_oa_mux_regs[] = { { .start = 0x0d0c, .end = 0x0d2c }, /* NOA_CONFIG[0-8] */ { .start = 0x9840, .end = 0x9840 }, /* GDT_CHICKEN_BITS */ { .start = 0x9884, .end = 0x9888 }, /* NOA_WRITE */ + { .start = 0x38d100, .end = 0x38d114}, /* VISACTL */ + {} }; static bool gen7_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) @@ -4372,10 +4526,20 @@ static bool gen12_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) return reg_in_range_table(addr, gen12_oa_b_counters); } +static bool mtl_is_valid_oam_b_counter_addr(struct i915_perf *perf, u32 addr) +{ + if (HAS_OAM(perf->i915) && + GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 70)) + return reg_in_range_table(addr, mtl_oam_b_counters); + + return false; +} + static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) { return reg_in_range_table(addr, xehp_oa_b_counters) || - reg_in_range_table(addr, gen12_oa_b_counters); + reg_in_range_table(addr, gen12_oa_b_counters) || + mtl_is_valid_oam_b_counter_addr(perf, addr); } static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr) @@ -4740,6 +4904,136 @@ static struct ctl_table oa_table[] = { {} }; +static u32 num_perf_groups_per_gt(struct intel_gt *gt) +{ + return 1; +} + +static u32 __oam_engine_group(struct intel_engine_cs *engine) +{ + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) { + /* + * There's 1 SAMEDIA gt and 1 OAM per SAMEDIA gt. All media slices + * within the gt use the same OAM. All MTL SKUs list 1 SA MEDIA. + */ + drm_WARN_ON(&engine->i915->drm, + engine->gt->type != GT_MEDIA); + + return PERF_GROUP_OAM_SAMEDIA_0; + } + + return PERF_GROUP_INVALID; +} + +static u32 __oa_engine_group(struct intel_engine_cs *engine) +{ + switch (engine->class) { + case RENDER_CLASS: + return PERF_GROUP_OAG; + + case VIDEO_DECODE_CLASS: + case VIDEO_ENHANCEMENT_CLASS: + return __oam_engine_group(engine); + + default: + return PERF_GROUP_INVALID; + } +} + +static struct i915_perf_regs __oam_regs(u32 base) +{ + return (struct i915_perf_regs) { + base, + GEN12_OAM_HEAD_POINTER(base), + GEN12_OAM_TAIL_POINTER(base), + GEN12_OAM_BUFFER(base), + GEN12_OAM_CONTEXT_CONTROL(base), + GEN12_OAM_CONTROL(base), + GEN12_OAM_DEBUG(base), + GEN12_OAM_STATUS(base), + GEN12_OAM_CONTROL_COUNTER_FORMAT_SHIFT, + }; +} + +static struct i915_perf_regs __oag_regs(void) +{ + return (struct i915_perf_regs) { + 0, + GEN12_OAG_OAHEADPTR, + GEN12_OAG_OATAILPTR, + GEN12_OAG_OABUFFER, + GEN12_OAG_OAGLBCTXCTRL, + GEN12_OAG_OACONTROL, + GEN12_OAG_OA_DEBUG, + GEN12_OAG_OASTATUS, + GEN12_OAG_OACONTROL_OA_COUNTER_FORMAT_SHIFT, + }; +} + +static void oa_init_groups(struct intel_gt *gt) +{ + int i, num_groups = gt->perf.num_perf_groups; + + for (i = 0; i < num_groups; i++) { + struct i915_perf_group *g = >->perf.group[i]; + + /* Fused off engines can result in a group with num_engines == 0 */ + if (g->num_engines == 0) + continue; + + if (i == PERF_GROUP_OAG && gt->type != GT_MEDIA) { + g->regs = __oag_regs(); + g->type = TYPE_OAG; + } else if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) { + g->regs = __oam_regs(mtl_oa_base[i]); + g->type = TYPE_OAM; + } + } +} + +static int oa_init_gt(struct intel_gt *gt) +{ + u32 num_groups = num_perf_groups_per_gt(gt); + struct intel_engine_cs *engine; + struct i915_perf_group *g; + intel_engine_mask_t tmp; + + g = kcalloc(num_groups, sizeof(*g), GFP_KERNEL); + if (!g) + return -ENOMEM; + + for_each_engine_masked(engine, gt, ALL_ENGINES, tmp) { + u32 index = __oa_engine_group(engine); + + engine->oa_group = NULL; + if (index < num_groups) { + g[index].num_engines++; + engine->oa_group = &g[index]; + } + } + + gt->perf.num_perf_groups = num_groups; + gt->perf.group = g; + + oa_init_groups(gt); + + return 0; +} + +static int oa_init_engine_groups(struct i915_perf *perf) +{ + struct intel_gt *gt; + int i, ret; + + for_each_gt(gt, perf->i915, i) { + ret = oa_init_gt(gt); + if (ret) + return ret; + } + + return 0; +} + static void oa_init_supported_formats(struct i915_perf *perf) { struct drm_i915_private *i915 = perf->i915; @@ -4780,9 +5074,15 @@ static void oa_init_supported_formats(struct i915_perf *perf) break; case INTEL_DG2: + oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8); + oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8); + break; + case INTEL_METEORLAKE: oa_format_add(perf, I915_OAR_FORMAT_A32u40_A4u32_B8_C8); oa_format_add(perf, I915_OA_FORMAT_A24u40_A14u32_B8_C8); + oa_format_add(perf, I915_OAM_FORMAT_MPEC8u64_B8_C8); + oa_format_add(perf, I915_OAM_FORMAT_MPEC8u32_B8_C8); break; default: @@ -4830,7 +5130,7 @@ static void i915_perf_init_info(struct drm_i915_private *i915) * Note: i915-perf initialization is split into an 'init' and 'register' * phase with the i915_perf_register() exposing state to userspace. */ -void i915_perf_init(struct drm_i915_private *i915) +int i915_perf_init(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; @@ -4906,7 +5206,7 @@ void i915_perf_init(struct drm_i915_private *i915) if (perf->ops.enable_metric_set) { struct intel_gt *gt; - int i; + int i, ret; for_each_gt(gt, i915, i) mutex_init(>->perf.lock); @@ -4945,8 +5245,17 @@ void i915_perf_init(struct drm_i915_private *i915) perf->i915 = i915; + ret = oa_init_engine_groups(perf); + if (ret) { + drm_err(&i915->drm, + "OA initialization failed %d\n", ret); + return ret; + } + oa_init_supported_formats(perf); } + + return 0; } static int destroy_config(int id, void *p, void *data) @@ -4973,10 +5282,15 @@ void i915_perf_sysctl_unregister(void) void i915_perf_fini(struct drm_i915_private *i915) { struct i915_perf *perf = &i915->perf; + struct intel_gt *gt; + int i; if (!perf->i915) return; + for_each_gt(gt, perf->i915, i) + kfree(gt->perf.group); + idr_for_each(&perf->metrics_idr, destroy_config, perf); idr_destroy(&perf->metrics_idr); @@ -4989,7 +5303,7 @@ void i915_perf_fini(struct drm_i915_private *i915) * * This version number is used by userspace to detect available features. */ -int i915_perf_ioctl_version(void) +int i915_perf_ioctl_version(struct drm_i915_private *i915) { /* * 1: Initial version @@ -5010,8 +5324,30 @@ int i915_perf_ioctl_version(void) * * 5: Add DRM_I915_PERF_PROP_POLL_OA_PERIOD parameter that controls the * interval for the hrtimer used to check for OA data. + * + * 6: Add DRM_I915_PERF_PROP_OA_ENGINE_CLASS and + * DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE + * + * 7: Add support for video decode and enhancement classes. + */ + + /* + * Wa_14017512683: mtl[a0..c0): Use of OAM must be preceded with Media + * C6 disable in BIOS. If Media C6 is enabled in BIOS, return version 6 + * to indicate that OA media is not supported. */ - return 5; + if (IS_MTL_MEDIA_STEP(i915, STEP_A0, STEP_C0)) { + struct intel_gt *gt; + int i; + + for_each_gt(gt, i915, i) { + if (gt->type == GT_MEDIA && + intel_check_bios_c6_setup(>->rc6)) + return 6; + } + } + + return 7; } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) |