diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_perf.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 87 |
1 files changed, 28 insertions, 59 deletions
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index bd9d812b1afa..1658f1246c6f 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -292,7 +292,7 @@ static u32 i915_perf_stream_paranoid = true; #define OAREPORT_REASON_CTX_SWITCH (1<<3) #define OAREPORT_REASON_CLK_RATIO (1<<5) -#define HAS_MI_SET_PREDICATE(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) +#define HAS_MI_SET_PREDICATE(i915) (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 55)) /* For sysctl proc_dointvec_minmax of i915_oa_max_sample_rate * @@ -548,7 +548,8 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) bool pollin; u32 partial_report_size; - /* We have to consider the (unlikely) possibility that read() errors + /* + * We have to consider the (unlikely) possibility that read() errors * could result in an OA buffer reset which might reset the head and * tail state. */ @@ -557,7 +558,8 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) hw_tail = stream->perf->ops.oa_hw_tail_read(stream); hw_tail -= gtt_offset; - /* The tail pointer increases in 64 byte increments, not in report_size + /* + * 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 */ @@ -569,8 +571,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) tail = hw_tail; - /* Walk the stream backward until we find a report with report - * id and timestmap not at 0. Since the circular buffer pointers + /* + * Walk the stream backward until we find a report with report + * id and timestamp 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 @@ -817,7 +820,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, */ if (oa_report_ctx_invalid(stream, report) && - GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 50)) { + GRAPHICS_VER_FULL(stream->engine->i915) < IP_VER(12, 55)) { ctx_id = INVALID_CTX_ID; oa_context_id_squash(stream, report32); } @@ -1419,7 +1422,7 @@ static int gen12_get_render_context_id(struct i915_perf_stream *stream) mask = ((1U << GEN12_GUC_SW_CTX_ID_WIDTH) - 1) << (GEN12_GUC_SW_CTX_ID_SHIFT - 32); - } else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 50)) { + } else if (GRAPHICS_VER_FULL(stream->engine->i915) >= IP_VER(12, 55)) { ctx_id = (XEHP_MAX_CONTEXT_HW_ID - 1) << (XEHP_SW_CTX_ID_SHIFT - 32); @@ -1663,6 +1666,7 @@ 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; + int m; if (WARN_ON(stream != g->exclusive_stream)) return; @@ -1687,10 +1691,9 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) free_oa_configs(stream); free_noa_wait(stream); - if (perf->spurious_report_rs.missed) { - gt_notice(gt, "%d spurious OA report notices suppressed due to ratelimiting\n", - perf->spurious_report_rs.missed); - } + m = ratelimit_state_get_miss(&perf->spurious_report_rs); + if (m) + gt_notice(gt, "%d spurious OA report notices suppressed due to ratelimiting\n", m); } static void gen7_init_oa_buffer(struct i915_perf_stream *stream) @@ -2749,26 +2752,6 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, } static int -gen12_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config, - struct i915_active *active) -{ - struct flex regs[] = { - { - GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE), - CTX_R_PWR_CLK_STATE, - }, - }; - - if (stream->engine->class != RENDER_CLASS) - return 0; - - return oa_configure_all_contexts(stream, - regs, ARRAY_SIZE(regs), - active); -} - -static int lrc_configure_all_contexts(struct i915_perf_stream *stream, const struct i915_oa_config *oa_config, struct i915_active *active) @@ -2874,18 +2857,17 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct intel_uncore *uncore = stream->uncore; - struct i915_oa_config *oa_config = stream->oa_config; bool periodic = stream->periodic; u32 period_exponent = stream->period_exponent; u32 sqcnt1; int ret; /* - * Wa_1508761755:xehpsdv, dg2 + * Wa_1508761755 * EU NOA signals behave incorrectly if EU clock gating is enabled. * Disable thread stall DOP gating and EU DOP gating. */ - if (IS_XEHPSDV(i915) || IS_DG2(i915)) { + if (IS_DG2(i915)) { intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN, _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE)); intel_uncore_write(uncore, GEN7_ROW_CHICKEN2, @@ -2911,7 +2893,7 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, /* * Initialize Super Queue Internal Cnt Register * Set PMON Enable in order to collect valid metrics. - * Enable byets per clock reporting in OA for XEHPSDV onward. + * Enable bytes per clock reporting in OA. */ sqcnt1 = GEN12_SQCNT1_PMON_ENABLE | (HAS_OA_BPC_REPORTING(i915) ? GEN12_SQCNT1_OABPC : 0); @@ -2919,15 +2901,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1); /* - * Update all contexts prior writing the mux configurations as we need - * to make sure all slices/subslices are ON before writing to NOA - * registers. - */ - ret = gen12_configure_all_contexts(stream, oa_config, active); - if (ret) - return ret; - - /* * For Gen12, performance counters are context * saved/restored. Only enable it for the context that * requested this. @@ -2971,19 +2944,15 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) u32 sqcnt1; /* - * Wa_1508761755:xehpsdv, dg2 - * Enable thread stall DOP gating and EU DOP gating. + * Wa_1508761755: Enable thread stall DOP gating and EU DOP gating. */ - if (IS_XEHPSDV(i915) || IS_DG2(i915)) { + if (IS_DG2(i915)) { intel_gt_mcr_multicast_write(uncore->gt, GEN8_ROW_CHICKEN, _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE)); intel_uncore_write(uncore, GEN7_ROW_CHICKEN2, _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING)); } - /* Reset all contexts' slices/subslices configurations. */ - gen12_configure_all_contexts(stream, NULL, NULL); - /* disable the context save/restore or OAR counters */ if (stream->ctx) gen12_configure_oar_context(stream, NULL); @@ -3393,9 +3362,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, "opening stream oa config uuid=%s\n", stream->oa_config->uuid); - hrtimer_init(&stream->poll_check_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); - stream->poll_check_timer.function = oa_poll_check_timer_cb; + hrtimer_setup(&stream->poll_check_timer, oa_poll_check_timer_cb, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); init_waitqueue_head(&stream->poll_wq); spin_lock_init(&stream->oa_buffer.ptr_lock); mutex_init(&stream->lock); @@ -3785,7 +3753,6 @@ static int i915_perf_release(struct inode *inode, struct file *file) static const struct file_operations fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .release = i915_perf_release, .poll = i915_perf_poll, .read = i915_perf_read, @@ -3884,7 +3851,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, } /* - * Asking for SSEU configuration is a priviliged operation. + * Asking for SSEU configuration is a privileged operation. */ if (props->has_sseu) privileged_op = true; @@ -4123,7 +4090,7 @@ static int read_properties_unlocked(struct i915_perf *perf, props->hold_preemption = !!value; break; case DRM_I915_PERF_PROP_GLOBAL_SSEU: { - if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 50)) { + if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 55)) { drm_dbg(&perf->i915->drm, "SSEU config not supported on gfx %x\n", GRAPHICS_VER_FULL(perf->i915)); @@ -4513,14 +4480,16 @@ static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr) static u32 mask_reg_value(u32 reg, u32 val) { - /* HALF_SLICE_CHICKEN2 is programmed with a the + /* + * HALF_SLICE_CHICKEN2 is programmed with a the * WaDisableSTUnitPowerOptimization workaround. Make sure the value * programmed by userspace doesn't change this. */ if (REG_EQUAL(reg, HALF_SLICE_CHICKEN2)) val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE); - /* WAIT_FOR_RC6_EXIT has only one bit fullfilling the function + /* + * WAIT_FOR_RC6_EXIT has only one bit fulfilling the function * indicated by its name and a bunch of selection fields used by OA * configs. */ @@ -4837,7 +4806,7 @@ err_unlock: return ret; } -static struct ctl_table oa_table[] = { +static const struct ctl_table oa_table[] = { { .procname = "perf_stream_paranoid", .data = &i915_perf_stream_paranoid, |