Perf measurements rely on CPU and engine timestamps to correlate
events of interest across these time domains. Current mechanisms get
these timestamps separately and the calculated delta between these
timestamps lack enough accuracy.
To improve the accuracy of these time measurements to within a few us,
add a query that returns the engine and cpu timestamps captured as
close to each other as possible.
v2: (Tvrtko)
- document clock reference used
- return cpu timestamp always
- capture cpu time just before lower dword of cs timestamp
v3: (Chris)
- use uncore-rpm
- use __query_cs_timestamp helper
v4: (Lionel)
- Kernel perf subsytem allows users to specify the clock id to be used
in perf_event_open. This clock id is used by the perf subsystem to
return the appropriate cpu timestamp in perf events. Similarly, let
the user pass the clockid to this query so that cpu timestamp
corresponds to the clock id requested.
v5: (Tvrtko)
- Use normal ktime accessors instead of fast versions
- Add more uApi documentation
v6: (Lionel)
- Move switch out of spinlock
v7: (Chris)
- cs_timestamp is a misnomer, use cs_cycles instead
- return the cs cycle frequency as well in the query
v8:
- Add platform and engine specific checks
v9: (Lionel)
- Return 2 cpu timestamps in the query - captured before and after the
register read
v10: (Chris)
- Use local_clock() to measure time taken to read lower dword of
register and return it to user.
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_query.c | 145 ++++++++++++++++++++++++++++++
include/uapi/drm/i915_drm.h | 48 ++++++++++
2 files changed, 193 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_query.c
b/drivers/gpu/drm/i915/i915_query.c
index fed337ad7b68..25b96927ab92 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -6,6 +6,8 @@
#include <linux/nospec.h>
+#include "gt/intel_engine_pm.h"
+#include "gt/intel_engine_user.h"
#include "i915_drv.h"
#include "i915_perf.h"
#include "i915_query.h"
@@ -90,6 +92,148 @@ static int query_topology_info(struct
drm_i915_private *dev_priv,
return total_length;
}
+typedef u64 (*__ktime_func_t)(void);
+static __ktime_func_t __clock_id_to_func(clockid_t clk_id)
+{
+ /*
+ * Use logic same as the perf subsystem to allow user to select
the
+ * reference clock id to be used for timestamps.
+ */
+ switch (clk_id) {
+ case CLOCK_MONOTONIC:
+ return &ktime_get_ns;
+ case CLOCK_MONOTONIC_RAW:
+ return &ktime_get_raw_ns;
+ case CLOCK_REALTIME:
+ return &ktime_get_real_ns;
+ case CLOCK_BOOTTIME:
+ return &ktime_get_boottime_ns;
+ case CLOCK_TAI:
+ return &ktime_get_clocktai_ns;
+ default:
+ return NULL;
+ }
+}
+
+static inline int
+__read_timestamps(struct intel_uncore *uncore,
+ i915_reg_t lower_reg,
+ i915_reg_t upper_reg,
+ u64 *cs_ts,
+ u64 *cpu_ts,
+ __ktime_func_t cpu_clock)
+{
+ u32 upper, lower, old_upper, loop = 0;
+
+ upper = intel_uncore_read_fw(uncore, upper_reg);
+ do {
+ cpu_ts[1] = local_clock();
+ cpu_ts[0] = cpu_clock();
+ lower = intel_uncore_read_fw(uncore, lower_reg);
+ cpu_ts[1] = local_clock() - cpu_ts[1];
+ old_upper = upper;
+ upper = intel_uncore_read_fw(uncore, upper_reg);
+ } while (upper != old_upper && loop++ < 2);
+
+ *cs_ts = (u64)upper << 32 | lower;
+
+ return 0;
+}
+
+static int
+__query_cs_cycles(struct intel_engine_cs *engine,
+ u64 *cs_ts, u64 *cpu_ts,
+ __ktime_func_t cpu_clock)
+{
+ struct intel_uncore *uncore = engine->uncore;
+ enum forcewake_domains fw_domains;
+ u32 base = engine->mmio_base;
+ intel_wakeref_t wakeref;
+ int ret;
+
+ fw_domains = intel_uncore_forcewake_for_reg(uncore,
+ RING_TIMESTAMP(base),
+ FW_REG_READ);
+
+ with_intel_runtime_pm(uncore->rpm, wakeref) {
+ spin_lock_irq(&uncore->lock);
+ intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+ ret = __read_timestamps(uncore,
+ RING_TIMESTAMP(base),
+ RING_TIMESTAMP_UDW(base),
+ cs_ts,
+ cpu_ts,
+ cpu_clock);
+
+ intel_uncore_forcewake_put__locked(uncore, fw_domains);
+ spin_unlock_irq(&uncore->lock);
+ }
+
+ return ret;
+}
+
+static int
+query_cs_cycles(struct drm_i915_private *i915,
+ struct drm_i915_query_item *query_item)
+{
+ struct drm_i915_query_cs_cycles __user *query_ptr;
+ struct drm_i915_query_cs_cycles query;
+ struct intel_engine_cs *engine;
+ __ktime_func_t cpu_clock;
+ int ret;
+
+ if (INTEL_GEN(i915) < 6)
+ return -ENODEV;
