#define IIR(offset) XE_REG(offset + 0x8)
#define IER(offset) XE_REG(offset + 0xc)
-/*
- * Interrupt statistic for PMU. Increments the counter only if the
- * interrupt originated from the GPU so interrupts from a device which
- * shares the interrupt line are not accounted.
- */
-static __always_inline void xe_pmu_irq_stats(struct xe_device *xe)
-{
- /*
- * A clever compiler translates that into INC. A not so clever one
- * should at least prevent store tearing.
- */
- WRITE_ONCE(xe->pmu.irq_count, xe->pmu.irq_count + 1);
-}
-
static void assert_iir_is_zero(struct xe_gt *mmio, struct xe_reg reg)
{
u32 val = xe_mmio_read32(mmio, reg);
xe_display_irq_enable(xe, gu_misc_iir);
- xe_pmu_irq_stats(xe);
-
return IRQ_HANDLED;
}
dg1_intr_enable(xe, false);
xe_display_irq_enable(xe, gu_misc_iir);
- xe_pmu_irq_stats(xe);
-
return IRQ_HANDLED;
}
static u64 engine_group_busyness_read(struct xe_gt *gt, u64 config)
{
- int sample_type = config_counter(config) - 1;
+ int sample_type = config_counter(config);
const unsigned int gt_id = gt->info.id;
struct xe_device *xe = gt->tile->xe;
struct xe_pmu *pmu = &xe->pmu;
return -ENOENT;
switch (config_counter(config)) {
- case XE_PMU_INTERRUPTS(0):
- if (gt_id)
- return -ENOENT;
- break;
case XE_PMU_RENDER_GROUP_BUSY(0):
case XE_PMU_COPY_GROUP_BUSY(0):
case XE_PMU_ANY_ENGINE_GROUP_BUSY(0):
const unsigned int gt_id = config_gt_id(event->attr.config);
const u64 config = event->attr.config;
struct xe_gt *gt = xe_device_get_gt(xe, gt_id);
- struct xe_pmu *pmu = &xe->pmu;
u64 val;
switch (config_counter(config)) {
- case XE_PMU_INTERRUPTS(0):
- val = READ_ONCE(pmu->irq_count);
- break;
case XE_PMU_RENDER_GROUP_BUSY(0):
case XE_PMU_COPY_GROUP_BUSY(0):
case XE_PMU_ANY_ENGINE_GROUP_BUSY(0):
const char *unit;
bool global;
} events[] = {
- __global_event(0, "interrupts", NULL),
- __event(1, "render-group-busy", "ns"),
- __event(2, "copy-group-busy", "ns"),
- __event(3, "media-group-busy", "ns"),
- __event(4, "any-engine-group-busy", "ns"),
+ __event(0, "render-group-busy", "ns"),
+ __event(1, "copy-group-busy", "ns"),
+ __event(2, "media-group-busy", "ns"),
+ __event(3, "any-engine-group-busy", "ns"),
};
struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter;
*
*/
u64 sample[XE_PMU_MAX_GT][__XE_NUM_PMU_SAMPLERS];
- /**
- * @irq_count: Number of interrupts
- *
- * Intentionally unsigned long to avoid atomics or heuristics on 32bit.
- * 4e9 interrupts are a lot and postprocessing can really deal with an
- * occasional wraparound easily. It's 32bit after all.
- */
- unsigned long irq_count;
/**
* @events_attr_group: Device events attribute group.
*/
* in 'struct perf_event_attr' as part of perf_event_open syscall to read a
* particular event.
*
- * For example to open the XE_PMU_INTERRUPTS(0):
+ * For example to open the XE_PMU_RENDER_GROUP_BUSY(0):
*
* .. code-block:: C
*
* attr.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED;
* attr.use_clockid = 1;
* attr.clockid = CLOCK_MONOTONIC;
- * attr.config = XE_PMU_INTERRUPTS(0);
+ * attr.config = XE_PMU_RENDER_GROUP_BUSY(0);
*
* fd = syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0);
*/
#define ___XE_PMU_OTHER(gt, x) \
(((__u64)(x)) | ((__u64)(gt) << __XE_PMU_GT_SHIFT))
-#define XE_PMU_INTERRUPTS(gt) ___XE_PMU_OTHER(gt, 0)
-#define XE_PMU_RENDER_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 1)
-#define XE_PMU_COPY_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 2)
-#define XE_PMU_MEDIA_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 3)
-#define XE_PMU_ANY_ENGINE_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 4)
+#define XE_PMU_RENDER_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 0)
+#define XE_PMU_COPY_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 1)
+#define XE_PMU_MEDIA_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 2)
+#define XE_PMU_ANY_ENGINE_GROUP_BUSY(gt) ___XE_PMU_OTHER(gt, 3)
#if defined(__cplusplus)
}