Merge tag 'drm-intel-gt-next-2021-01-14' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:
- Deprecate I915_PMU_LAST and optimize state tracking (Tvrtko)

  Avoid relying on last item ABI marker in i915_drm.h, add a
  comment to mark as deprecated.

Cross-subsystem Changes:

Core Changes:

Driver Changes:

- Restore clear residuals security mitigations for Ivybridge and
  Baytrail (Chris)
- Close #1858: Allow sysadmin to choose applied GPU security mitigations
  through i915.mitigations=... similar to CPU (Chris)
- Fix for #2024: GPU hangs on HSW GT1 (Chris)
- Fix for #2707: Driver hang when editing UVs in Blender (Chris, Ville)
- Fix for #2797: False positive GuC loading error message (Chris)
- Fix for #2859: Missing GuC firmware for older Cometlakes (Chris)
- Lessen probability of GPU hang due to DMAR faults [reason 7,
  next page table ptr is invalid] on Tigerlake (Chris)
- Fix REVID macros for TGL to fetch correct stepping (Aditya)
- Limit frequency drop to RPe on parking (Chris, Edward)
- Limit W/A 1406941453 to TGL, RKL and DG1 (Swathi)
- Make W/A 22010271021 permanent on DG1 (Lucas)
- Implement W/A 16011163337 to prevent a HS/DS hang on DG1 (Swathi)
- Only disable preemption on gen8 render engines (Chris)
- Disable arbitration around Braswell's PDP updates (Chris)
- Disable arbitration on no-preempt requests (Chris)
- Check for arbitration after writing start seqno before busywaiting (Chris)
- Retain default context state across shrinking (Venkata, CQ)
- Fix mismatch between misplaced vma check and vma insert for 32-bit
  addressing userspaces (Chris, CQ)
- Propagate error for vmap() failure instead kernel NULL deref (Chris)
- Propagate error from cancelled submit due to context closure
  immediately (Chris)
- Fix RCU race on HWSP tracking per request (Chris)
- Clear CMD parser shadow and GPU reloc batches (Matt A)

- Populate logical context during first pin (Maarten)
- Optimistically prune dma-resv from the shrinker (Chris)
- Fix for virtual engine ownership race (Chris)
- Remove timeslice suppression to restore fairness for virtual engines (Chris)
- Rearrange IVB/HSW workarounds properly between GT and engine (Chris)
- Taint the reset mutex with the shrinker (Chris)
- Replace direct submit with direct call to tasklet (Chris)
- Multiple corrections to virtual engine dequeue and breadcrumbs code (Chris)
- Avoid wakeref from potentially hard IRQ context in PMU (Tvrtko)
- Use raw clock for RC6 time estimation in PMU (Tvrtko)
- Differentiate OOM failures from invalid map types (Chris)
- Fix Gen9 to have 64 MOCS entries similar to Gen11 (Chris)
- Ignore repeated attempts to suspend request flow across reset (Chris)
- Remove livelock from "do_idle_maps" VT-d W/A (Chris)
- Cancel the preemption timeout early in case engine reset fails (Chris)
- Code flow optimization in the scheduling code (Chris)
- Clear the execlists timers upon reset (Chris)
- Drain the breadcrumbs just once (Chris, Matt A)
- Track the overall GT awake/busy time (Chris)
- Tweak submission tasklet flushing to avoid starvation (Chris)
- Track timelines created using the HWSP to restore on resume (Chris)
- Use cmpxchg64 for 32b compatilibity for active tracking (Chris)
- Prefer recycling an idle GGTT fence to avoid GPU wait (Chris)

- Restructure GT code organization for clearer split between GuC
  and execlists (Chris, Daniele, John, Matt A)
- Remove GuC code that will remain unused by new interfaces (Matt B)
- Restructure the CS timestamp clocks code to local to GT (Chris)
- Fix error return paths in perf code (Zhang)
- Replace idr_init() by idr_init_base() in perf (Deepak)
- Fix shmem_pin_map error path (Colin)
- Drop redundant free_work worker for GEM contexts (Chris, Mika)
- Increase readability and understandability of intel_workarounds.c (Lucas)
- Defer enabling the breadcrumb interrupt to after submission (Chris)
- Deal with buddy alloc block sizes beyond 4G (Venkata, Chris)
- Encode fence specific waitqueue behaviour into the wait.flags (Chris)
- Don't cancel the breadcrumb interrupt shadow too early (Chris)
- Cancel submitted requests upon context reset (Chris)
- Use correct locks in GuC code (Tvrtko)
- Prevent use of engine->wa_ctx after error (Chris, Matt R)

- Fix build warning on 32-bit (Arnd)
- Avoid memory leak if platform would have more than 16 W/A (Tvrtko)
- Avoid unnecessary #if CONFIG_PM in PMU code (Chris, Tvrtko)
- Improve debugging output (Chris, Tvrtko, Matt R)
- Make file local variables static (Jani)
- Avoid uint*_t types in i915 (Jani)
- Selftest improvements (Chris, Matt A, Dan)
- Documentation fixes (Chris, Jose)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
#	drivers/gpu/drm/i915/gt/intel_lrc.c
#	drivers/gpu/drm/i915/gvt/mmio_context.h
#	drivers/gpu/drm/i915/i915_drv.h
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210114152232.GA21588@jlahtine-mobl.ger.corp.intel.com

1 files changed, 157 insertions, 40 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 999079686846..a4242ca8dcd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -7,34 +7,146 @@
 #include "intel_gt.h"
 #include "intel_gt_clock_utils.h"
 
-#define MHZ_12   12000000 /* 12MHz (24MHz/2), 83.333ns */
-#define MHZ_12_5 12500000 /* 12.5MHz (25MHz/2), 80ns */
-#define MHZ_19_2 19200000 /* 19.2MHz, 52.083ns */
+static u32 read_reference_ts_freq(struct intel_uncore *uncore)
+{
+	u32 ts_override = intel_uncore_read(uncore, GEN9_TIMESTAMP_OVERRIDE);
+	u32 base_freq, frac_freq;
+
+	base_freq = ((ts_override & GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_MASK) >>
+		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DIVIDER_SHIFT) + 1;
+	base_freq *= 1000000;
+
+	frac_freq = ((ts_override &
+		      GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_MASK) >>
+		     GEN9_TIMESTAMP_OVERRIDE_US_COUNTER_DENOMINATOR_SHIFT);
+	frac_freq = 1000000 / (frac_freq + 1);
+
+	return base_freq + frac_freq;
+}
+
+static u32 gen10_get_crystal_clock_freq(struct intel_uncore *uncore,
+					u32 rpm_config_reg)
+{
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+	u32 crystal_clock =
+		(rpm_config_reg & GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+		GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
 
-static u32 read_clock_frequency(const struct intel_gt *gt)
+	switch (crystal_clock) {
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
+static u32 gen11_get_crystal_clock_freq(struct intel_uncore *uncore,
+					u32 rpm_config_reg)
 {
-	if (INTEL_GEN(gt->i915) >= 11) {
-		u32 config;
-
-		config = intel_uncore_read(gt->uncore, RPM_CONFIG0);
-		config &= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK;
-		config >>= GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
-
-		switch (config) {
-		case 0: return MHZ_12;
-		case 1:
-		case 2: return MHZ_19_2;
-		default:
-		case 3: return MHZ_12_5;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+	u32 f25_mhz = 25000000;
+	u32 f38_4_mhz = 38400000;
+	u32 crystal_clock =
+		(rpm_config_reg & GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >>
+		GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT;
+
+	switch (crystal_clock) {
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ:
+		return f24_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ:
+		return f19_2_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_38_4_MHZ:
+		return f38_4_mhz;
+	case GEN11_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_25_MHZ:
+		return f25_mhz;
+	default:
+		MISSING_CASE(crystal_clock);
+		return 0;
+	}
+}
+
+static u32 read_clock_frequency(struct intel_uncore *uncore)
+{
+	u32 f12_5_mhz = 12500000;
+	u32 f19_2_mhz = 19200000;
+	u32 f24_mhz = 24000000;
+
+	if (INTEL_GEN(uncore->i915) <= 4) {
+		/*
+		 * PRMs say:
+		 *
+		 *     "The value in this register increments once every 16
+		 *      hclks." (through the “Clocking Configuration”
+		 *      (“CLKCFG”) MCHBAR register)
+		 */
+		return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16;
+	} else if (INTEL_GEN(uncore->i915) <= 8) {
+		/*
+		 * PRMs say:
+		 *
+		 *     "The PCU TSC counts 10ns increments; this timestamp
+		 *      reflects bits 38:3 of the TSC (i.e. 80ns granularity,
+		 *      rolling over every 1.5 hours).
+		 */
+		return f12_5_mhz;
+	} else if (INTEL_GEN(uncore->i915) <= 9) {
+		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
+		u32 freq = 0;
+
+		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
+			freq = read_reference_ts_freq(uncore);
+		} else {
+			freq = IS_GEN9_LP(uncore->i915) ? f19_2_mhz : f24_mhz;
+
+			/*
+			 * Now figure out how the command stream's timestamp
+			 * register increments from this frequency (it might
+			 * increment only every few clock cycle).
+			 */
+			freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >>
+				      CTC_SHIFT_PARAMETER_SHIFT);
 		}
-	} else if (INTEL_GEN(gt->i915) >= 9) {
-		if (IS_GEN9_LP(gt->i915))
-			return MHZ_19_2;
-		else
-			return MHZ_12;
-	} else {
-		return MHZ_12_5;
+
+		return freq;
+	} else if (INTEL_GEN(uncore->i915) <= 12) {
+		u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE);
+		u32 freq = 0;
+
+		/*
+		 * First figure out the reference frequency. There are 2 ways
+		 * we can compute the frequency, either through the
+		 * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE
+		 * tells us which one we should use.
+		 */
+		if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) {
+			freq = read_reference_ts_freq(uncore);
+		} else {
+			u32 c0 = intel_uncore_read(uncore, RPM_CONFIG0);
+
+			if (INTEL_GEN(uncore->i915) <= 10)
+				freq = gen10_get_crystal_clock_freq(uncore, c0);
+			else
+				freq = gen11_get_crystal_clock_freq(uncore, c0);
+
+			/*
+			 * Now figure out how the command stream's timestamp
+			 * register increments from this frequency (it might
+			 * increment only every few clock cycle).
+			 */
+			freq >>= 3 - ((c0 & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
+				      GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT);
+		}
+
+		return freq;
 	}
+
+	MISSING_CASE("Unknown gen, unable to read command streamer timestamp frequency\n");
+	return 0;
 }
 
 void intel_gt_init_clock_frequency(struct intel_gt *gt)
@@ -43,20 +155,27 @@ void intel_gt_init_clock_frequency(struct intel_gt *gt)
 	 * Note that on gen11+, the clock frequency may be reconfigured.
 	 * We do not, and we assume nobody else does.
 	 */
-	gt->clock_frequency = read_clock_frequency(gt);
+	gt->clock_frequency = read_clock_frequency(gt->uncore);
+	if (gt->clock_frequency)
+		gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1);
+
 	GT_TRACE(gt,
-		 "Using clock frequency: %dkHz\n",
-		 gt->clock_frequency / 1000);
+		 "Using clock frequency: %dkHz, period: %dns, wrap: %lldms\n",
+		 gt->clock_frequency / 1000,
+		 gt->clock_period_ns,
+		 div_u64(mul_u32_u32(gt->clock_period_ns, S32_MAX),
+			 USEC_PER_SEC));
+
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 void intel_gt_check_clock_frequency(const struct intel_gt *gt)
 {
-	if (gt->clock_frequency != read_clock_frequency(gt)) {
+	if (gt->clock_frequency != read_clock_frequency(gt->uncore)) {
 		dev_err(gt->i915->drm.dev,
 			"GT clock frequency changed, was %uHz, now %uHz!\n",
 			gt->clock_frequency,
-			read_clock_frequency(gt));
+			read_clock_frequency(gt->uncore));
 	}
 }
 #endif
@@ -66,26 +185,24 @@ static u64 div_u64_roundup(u64 nom, u32 den)
 	return div_u64(nom + den - 1, den);
 }
 
-u32 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u32 count)
+u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
-	return div_u64_roundup(mul_u32_u32(count, 1000 * 1000 * 1000),
-			       gt->clock_frequency);
+	return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency);
 }
 
-u32 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u32 count)
+u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
 {
 	return intel_gt_clock_interval_to_ns(gt, 16 * count);
 }
 
-u32 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u32 ns)
+u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns)
 {
-	return div_u64_roundup(mul_u32_u32(gt->clock_frequency, ns),
-			       1000 * 1000 * 1000);
+	return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC);
 }
 
-u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns)
+u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns)
 {
-	u32 val;
+	u64 val;
 
 	/*
 	 * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS
@@ -94,9 +211,9 @@ u32 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u32 ns)
 	 * EI/thresholds are "bad", leading to a very sluggish or even
 	 * frozen machine.
 	 */
-	val = DIV_ROUND_UP(intel_gt_ns_to_clock_interval(gt, ns), 16);
+	val = div_u64_roundup(intel_gt_ns_to_clock_interval(gt, ns), 16);
 	if (IS_GEN(gt->i915, 6))
-		val = roundup(val, 25);
+		val = div_u64_roundup(val, 25) * 25;
 
 	return val;
 }