On 03/03/2022 22:42, Matt Roper wrote:
From: Akeem G Abodunrin <akeem.g.abodunrin@xxxxxxxxx>
Starting with DG2, preemption can no longer be controlled using userspace
on a per-context basis. Instead, the hardware only allows us to enable or
disable preemption in a global, system-wide basis. Also, we lose the
ability to specify the preemption granularity (such as batch-level vs
command-level vs object-level).
As a result of this - for debugging purposes, this patch adds debugfs
interface to configure (disable/enable) preemption globally.
Jira: VLK-27831
Cc: Matt Roper <matthew.d.roper@xxxxxxxxx>
Cc: Prathap Kumar Valsan <prathap.kumar.valsan@xxxxxxxxx>
Cc: John Harrison <john.c.harrison@xxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Signed-off-by: Akeem G Abodunrin <akeem.g.abodunrin@xxxxxxxxx>
Signed-off-by: Matt Roper <matthew.d.roper@xxxxxxxxx>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 3 ++
drivers/gpu/drm/i915/gt/intel_workarounds.c | 2 +-
drivers/gpu/drm/i915/i915_debugfs.c | 50 +++++++++++++++++++++
drivers/gpu/drm/i915/i915_drv.h | 3 ++
4 files changed, 57 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 19cd34f24263..21ede1887b9f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -468,6 +468,9 @@
#define VF_PREEMPTION _MMIO(0x83a4)
#define PREEMPTION_VERTEX_COUNT REG_GENMASK(15, 0)
+#define GEN12_VFG_PREEMPTION_CHICKEN _MMIO(0x83b4)
+#define GEN12_VFG_PREEMPT_CHICKEN_DISABLE REG_BIT(8)
+
#define GEN8_RC6_CTX_INFO _MMIO(0x8504)
#define GEN12_SQCM _MMIO(0x8724)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index c014b40d2e9f..18dc82f29776 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -2310,7 +2310,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
FF_DOP_CLOCK_GATE_DISABLE);
}
- if (IS_GRAPHICS_VER(i915, 9, 12)) {
+ if (HAS_PERCTX_PREEMPT_CTRL(i915)) {
/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl,tgl */
wa_masked_en(wal,
GEN7_FF_SLICE_CS_CHICKEN1,
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 747fe9f41e1f..40e6e17e2950 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -571,6 +571,55 @@ static int i915_wa_registers(struct seq_file *m, void *unused)
return 0;
}
+static void i915_global_preemption_config(struct drm_i915_private *i915,
+ u32 val)
+{
+ const u32 bit = GEN12_VFG_PREEMPT_CHICKEN_DISABLE;
+
+ if (val)
+ intel_uncore_write(&i915->uncore, GEN12_VFG_PREEMPTION_CHICKEN,
+ _MASKED_BIT_DISABLE(bit));
+ else
+ intel_uncore_write(&i915->uncore, GEN12_VFG_PREEMPTION_CHICKEN,
+ _MASKED_BIT_ENABLE(bit));
In addition to what Jani suggested some other questions:
Does this setting survive GT reset?
Would intel_reg read/write work?
Can we not add the debugfs file to start with if register is n/a for a platform?
+}
+
+static int i915_global_preempt_support_get(void *data, u64 *val)
+{
+ struct drm_i915_private *i915 = data;
+ intel_wakeref_t wakeref;
+ u32 curr_status = 0;
+
+ if (HAS_PERCTX_PREEMPT_CTRL(i915) || GRAPHICS_VER(i915) < 11)
+ return -EINVAL;
What is the purpose of the "< 11" condition here? Because HAS_PERCTX_PREEMPT_CTRL is defined as starting on Gen9? Is the 11 arbitrary then or has some deeper meaning?
Regards,
Tvrtko
+
+ with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+ curr_status = intel_uncore_read(&i915->uncore,
+ GEN12_VFG_PREEMPTION_CHICKEN);
+ *val = (curr_status & GEN12_VFG_PREEMPT_CHICKEN_DISABLE) ? 0 : 1;
+
+ return 0;
+}
+
+static int i915_global_preempt_support_set(void *data, u64 val)
+{
+ struct drm_i915_private *i915 = data;
+ intel_wakeref_t wakeref;
+
+ if (HAS_PERCTX_PREEMPT_CTRL(i915) || GRAPHICS_VER(i915) < 11)
+ return -EINVAL;
+
+ with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+ i915_global_preemption_config(i915, val);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_global_preempt_support_fops,
+ i915_global_preempt_support_get,
+ i915_global_preempt_support_set,
+ "%lld\n");
+
static int i915_wedged_get(void *data, u64 *val)
{
struct drm_i915_private *i915 = data;
@@ -765,6 +814,7 @@ static const struct i915_debugfs_files {
const struct file_operations *fops;
} i915_debugfs_files[] = {
{"i915_perf_noa_delay", &i915_perf_noa_delay_fops},
+ {"i915_global_preempt_support", &i915_global_preempt_support_fops},
{"i915_wedged", &i915_wedged_fops},
{"i915_gem_drop_caches", &i915_drop_caches_fops},
#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 457bc1993d19..8c3f69c87d36 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1407,6 +1407,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define HAS_GUC_DEPRIVILEGE(dev_priv) \
(INTEL_INFO(dev_priv)->has_guc_deprivilege)
+#define HAS_PERCTX_PREEMPT_CTRL(i915) \
+ ((GRAPHICS_VER(i915) >= 9) && GRAPHICS_VER_FULL(i915) < IP_VER(12, 55))
+
static inline bool run_as_guest(void)
{
return !hypervisor_is_type(X86_HYPER_NATIVE);
