From: Piotr Maciejewski <piotr.maciejewski@xxxxxxxxx>
It is useful to have markers in the OA reports to identify triggered
reports. Whitelist some OA counters that can be used as markers.
A triggered report can be found faster if we can sample the HW tail and
head registers when the report was triggered. Whitelist OA buffer
specific registers.
v2:
- Bump up the perf revision (Lionel)
- Use indexing for counters (Lionel)
- Fix selftest for oa ticking register (Umesh)
v3: Pardon whitelisted registers for selftest (Umesh)
v4:
- Document whitelisted registers (Lionel)
- Fix live isolated whitelist for OA regs (Umesh)
Signed-off-by: Piotr Maciejewski <piotr.maciejewski@xxxxxxxxx>
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@xxxxxxxxx>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@xxxxxxxxx>
---
drivers/gpu/drm/i915/gt/intel_workarounds.c | 34 +++++++++++++++++++
.../gpu/drm/i915/gt/selftest_workarounds.c | 30 +++++++++++++++-
drivers/gpu/drm/i915/i915_perf.c | 8 ++++-
drivers/gpu/drm/i915/i915_reg.h | 10 ++++++
4 files changed, 80 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index a72ebfd115e5..c950d07beec3 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1392,6 +1392,23 @@ static void gen9_whitelist_build_performance_counters(struct i915_wa_list *w)
/* OA buffer trigger report 2/6 used by performance query */
whitelist_reg(w, OAREPORTTRIG2);
whitelist_reg(w, OAREPORTTRIG6);
+
+ /* Performance counters A18-20 used by tbs marker query */
+ whitelist_reg_ext(w, OA_PERF_COUNTER_A(18),
+ RING_FORCE_TO_NONPRIV_ACCESS_RW |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
+
+ whitelist_reg(w, OA_PERF_COUNTER_A(20));
+ whitelist_reg(w, OA_PERF_COUNTER_A_UPPER(20));
+
+ /* Read access to gpu ticks */
+ whitelist_reg_ext(w, GEN8_GPU_TICKS,
+ RING_FORCE_TO_NONPRIV_ACCESS_RD);
+
+ /* Read access to: oa status, head, tail, buffer settings */
+ whitelist_reg_ext(w, GEN8_OASTATUS,
+ RING_FORCE_TO_NONPRIV_ACCESS_RD |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
}
static void gen12_whitelist_build_performance_counters(struct i915_wa_list *w)
@@ -1399,6 +1416,23 @@ static void gen12_whitelist_build_performance_counters(struct i915_wa_list *w)
/* OA buffer trigger report 2/6 used by performance query */
whitelist_reg(w, GEN12_OAG_OAREPORTTRIG2);
whitelist_reg(w, GEN12_OAG_OAREPORTTRIG6);
+
+ /* Performance counters A18-20 used by tbs marker query */
+ whitelist_reg_ext(w, GEN12_OAG_PERF_COUNTER_A(18),
+ RING_FORCE_TO_NONPRIV_ACCESS_RW |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
+
+ whitelist_reg(w, GEN12_OAG_PERF_COUNTER_A(20));
+ whitelist_reg(w, GEN12_OAG_PERF_COUNTER_A_UPPER(20));
+
+ /* Read access to gpu ticks */
+ whitelist_reg_ext(w, GEN12_OAG_GPU_TICKS,
+ RING_FORCE_TO_NONPRIV_ACCESS_RD);
+
+ /* Read access to: oa status, head, tail, buffer settings */
+ whitelist_reg_ext(w, GEN12_OAG_OASTATUS,
+ RING_FORCE_TO_NONPRIV_ACCESS_RD |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
}
static void gen9_whitelist_build(struct i915_wa_list *w)
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 3b1d3dbcd477..7c2c2be8d212 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -431,6 +431,19 @@ static bool timestamp(const struct intel_engine_cs *engine, u32 reg)
}
}
+static bool oa_gpu_ticks(u32 reg)
+{
+ reg = reg & ~RING_FORCE_TO_NONPRIV_ACCESS_MASK;
+ switch (reg) {
+ case 0x2910:
+ case 0xda90:
+ return true;
+
+ default:
+ return false;
+ }
+}
+
static bool ro_register(u32 reg)
{
if ((reg & RING_FORCE_TO_NONPRIV_ACCESS_MASK) ==
@@ -511,7 +524,7 @@ static int check_dirty_whitelist(struct intel_context *ce)
if (wo_register(engine, reg))
continue;
- if (timestamp(engine, reg))
+ if (timestamp(engine, reg) || oa_gpu_ticks(reg))
continue; /* timestamps are expected to autoincrement */
ro_reg = ro_register(reg);
@@ -918,6 +931,9 @@ static bool find_reg(struct drm_i915_private *i915,
{
u32 offset = i915_mmio_reg_offset(reg);
+ /* Clear non priv flags */
+ offset &= RING_FORCE_TO_NONPRIV_ADDRESS_MASK;
+
while (count--) {
if (INTEL_INFO(i915)->gen_mask & tbl->gen_mask &&
i915_mmio_reg_offset(tbl->reg) == offset)
@@ -938,6 +954,12 @@ static bool pardon_reg(struct drm_i915_private *i915, i915_reg_t reg)
{ OAREPORTTRIG6, INTEL_GEN_MASK(8, 11) },
{ GEN12_OAG_OAREPORTTRIG2, INTEL_GEN_MASK(12, 12) },
{ GEN12_OAG_OAREPORTTRIG6, INTEL_GEN_MASK(12, 12) },
+ { OA_PERF_COUNTER_A(18), INTEL_GEN_MASK(8, 11) },
+ { OA_PERF_COUNTER_A(20), INTEL_GEN_MASK(8, 11) },
+ { OA_PERF_COUNTER_A_UPPER(20), INTEL_GEN_MASK(8, 11) },
+ { GEN12_OAG_PERF_COUNTER_A(18), INTEL_GEN_MASK(12, 12) },
+ { GEN12_OAG_PERF_COUNTER_A(20), INTEL_GEN_MASK(12, 12) },
+ { GEN12_OAG_PERF_COUNTER_A_UPPER(20), INTEL_GEN_MASK(12, 12) },
};
return find_reg(i915, reg, pardon, ARRAY_SIZE(pardon));
@@ -964,6 +986,12 @@ static bool writeonly_reg(struct drm_i915_private *i915, i915_reg_t reg)
{ OAREPORTTRIG6, INTEL_GEN_MASK(8, 11) },
{ GEN12_OAG_OAREPORTTRIG2, INTEL_GEN_MASK(12, 12) },
{ GEN12_OAG_OAREPORTTRIG6, INTEL_GEN_MASK(12, 12) },
+ { OA_PERF_COUNTER_A(18), INTEL_GEN_MASK(8, 11) },
+ { OA_PERF_COUNTER_A(20), INTEL_GEN_MASK(8, 11) },
+ { OA_PERF_COUNTER_A_UPPER(20), INTEL_GEN_MASK(8, 11) },
+ { GEN12_OAG_PERF_COUNTER_A(18), INTEL_GEN_MASK(12, 12) },
+ { GEN12_OAG_PERF_COUNTER_A(20), INTEL_GEN_MASK(12, 12) },
+ { GEN12_OAG_PERF_COUNTER_A_UPPER(20), INTEL_GEN_MASK(12, 12) },
};
return find_reg(i915, reg, wo, ARRAY_SIZE(wo));
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 30f6aeb819aa..2f23aad12c60 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4450,8 +4450,14 @@ int i915_perf_ioctl_version(void)
*
* 6: Whitelist OATRIGGER registers to allow user to trigger reports
* into the OA buffer. This applies only to gen8+.
+ *
+ * 7: Whitelist below OA registers for user to identify the location of
+ * triggered reports in the OA buffer. This applies only to gen8+.
+ *
+ * - OA buffer head/tail/status/buffer registers for read only
+ * - OA counters A18, A19, A20 for read/write
*/
- return 6;
+ return 7;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9cc3e312b6b7..c68dc3f39e62 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -675,6 +675,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define GEN7_OASTATUS2_HEAD_MASK 0xffffffc0
#define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */
+#define GEN8_GPU_TICKS _MMIO(0x2910)
#define GEN8_OASTATUS _MMIO(0x2b08)
#define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3)
#define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2)
@@ -733,6 +734,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define GEN12_OAG_OA_DEBUG_DISABLE_GO_1_0_REPORTS (1 << 2)
#define GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS (1 << 1)
+#define GEN12_OAG_GPU_TICKS _MMIO(0xda90)
#define GEN12_OAG_OASTATUS _MMIO(0xdafc)
#define GEN12_OAG_OASTATUS_COUNTER_OVERFLOW (1 << 2)
#define GEN12_OAG_OASTATUS_BUFFER_OVERFLOW (1 << 1)
@@ -974,6 +976,14 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define OAREPORTTRIG8_NOA_SELECT_6_SHIFT 24
#define OAREPORTTRIG8_NOA_SELECT_7_SHIFT 28
+/* Performance counters registers */
+#define OA_PERF_COUNTER_A(idx) _MMIO(0x2800 + 8 * (idx))
+#define OA_PERF_COUNTER_A_UPPER(idx) _MMIO(0x2800 + 8 * (idx) + 4)
+
+/* Gen12 Performance counters registers */
+#define GEN12_OAG_PERF_COUNTER_A(idx) _MMIO(0xD980 + 8 * (idx))
+#define GEN12_OAG_PERF_COUNTER_A_UPPER(idx) _MMIO(0xD980 + 8 * (idx) + 4)
+
/* Same layout as OASTARTTRIGX */
#define GEN12_OAG_OASTARTTRIG1 _MMIO(0xd900)
#define GEN12_OAG_OASTARTTRIG2 _MMIO(0xd904)
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
