Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

1 files changed, 146 insertions, 26 deletions

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 8c2ce81f01c2..89547b614aa6 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -69,17 +69,104 @@ fw_domain_arm_timer(struct intel_uncore_forcewake_domain *d)
 			       HRTIMER_MODE_REL);
 }
 
+static inline int
+__wait_for_ack(const struct drm_i915_private *i915,
+	       const struct intel_uncore_forcewake_domain *d,
+	       const u32 ack,
+	       const u32 value)
+{
+	return wait_for_atomic((__raw_i915_read32(i915, d->reg_ack) & ack) == value,
+			       FORCEWAKE_ACK_TIMEOUT_MS);
+}
+
+static inline int
+wait_ack_clear(const struct drm_i915_private *i915,
+	       const struct intel_uncore_forcewake_domain *d,
+	       const u32 ack)
+{
+	return __wait_for_ack(i915, d, ack, 0);
+}
+
+static inline int
+wait_ack_set(const struct drm_i915_private *i915,
+	     const struct intel_uncore_forcewake_domain *d,
+	     const u32 ack)
+{
+	return __wait_for_ack(i915, d, ack, ack);
+}
+
 static inline void
 fw_domain_wait_ack_clear(const struct drm_i915_private *i915,
 			 const struct intel_uncore_forcewake_domain *d)
 {
-	if (wait_for_atomic((__raw_i915_read32(i915, d->reg_ack) &
-			     FORCEWAKE_KERNEL) == 0,
-			    FORCEWAKE_ACK_TIMEOUT_MS))
+	if (wait_ack_clear(i915, d, FORCEWAKE_KERNEL))
 		DRM_ERROR("%s: timed out waiting for forcewake ack to clear.\n",
 			  intel_uncore_forcewake_domain_to_str(d->id));
 }
 
+enum ack_type {
+	ACK_CLEAR = 0,
+	ACK_SET
+};
+
+static int
+fw_domain_wait_ack_with_fallback(const struct drm_i915_private *i915,
+				 const struct intel_uncore_forcewake_domain *d,
+				 const enum ack_type type)
+{
+	const u32 ack_bit = FORCEWAKE_KERNEL;
+	const u32 value = type == ACK_SET ? ack_bit : 0;
+	unsigned int pass;
+	bool ack_detected;
+
+	/*
+	 * There is a possibility of driver's wake request colliding
+	 * with hardware's own wake requests and that can cause
+	 * hardware to not deliver the driver's ack message.
+	 *
+	 * Use a fallback bit toggle to kick the gpu state machine
+	 * in the hope that the original ack will be delivered along with
+	 * the fallback ack.
+	 *
+	 * This workaround is described in HSDES #1604254524
+	 */
+
+	pass = 1;
+	do {
+		wait_ack_clear(i915, d, FORCEWAKE_KERNEL_FALLBACK);
+
+		__raw_i915_write32(i915, d->reg_set,
+				   _MASKED_BIT_ENABLE(FORCEWAKE_KERNEL_FALLBACK));
+		/* Give gt some time to relax before the polling frenzy */
+		udelay(10 * pass);
+		wait_ack_set(i915, d, FORCEWAKE_KERNEL_FALLBACK);
+
+		ack_detected = (__raw_i915_read32(i915, d->reg_ack) & ack_bit) == value;
+
+		__raw_i915_write32(i915, d->reg_set,
+				   _MASKED_BIT_DISABLE(FORCEWAKE_KERNEL_FALLBACK));
+	} while (!ack_detected && pass++ < 10);
+
+	DRM_DEBUG_DRIVER("%s had to use fallback to %s ack, 0x%x (passes %u)\n",
+			 intel_uncore_forcewake_domain_to_str(d->id),
+			 type == ACK_SET ? "set" : "clear",
+			 __raw_i915_read32(i915, d->reg_ack),
+			 pass);
+
+	return ack_detected ? 0 : -ETIMEDOUT;
+}
+
+static inline void
+fw_domain_wait_ack_clear_fallback(const struct drm_i915_private *i915,
+				  const struct intel_uncore_forcewake_domain *d)
+{
+	if (likely(!wait_ack_clear(i915, d, FORCEWAKE_KERNEL)))
+		return;
+
+	if (fw_domain_wait_ack_with_fallback(i915, d, ACK_CLEAR))
+		fw_domain_wait_ack_clear(i915, d);
+}
+
 static inline void
 fw_domain_get(struct drm_i915_private *i915,
 	      const struct intel_uncore_forcewake_domain *d)
@@ -88,17 +175,26 @@ fw_domain_get(struct drm_i915_private *i915,
 }
 
 static inline void
-fw_domain_wait_ack(const struct drm_i915_private *i915,
-		   const struct intel_uncore_forcewake_domain *d)
+fw_domain_wait_ack_set(const struct drm_i915_private *i915,
+		       const struct intel_uncore_forcewake_domain *d)
 {
-	if (wait_for_atomic((__raw_i915_read32(i915, d->reg_ack) &
-			     FORCEWAKE_KERNEL),
-			    FORCEWAKE_ACK_TIMEOUT_MS))
+	if (wait_ack_set(i915, d, FORCEWAKE_KERNEL))
 		DRM_ERROR("%s: timed out waiting for forcewake ack request.\n",
 			  intel_uncore_forcewake_domain_to_str(d->id));
 }
 
 static inline void
+fw_domain_wait_ack_set_fallback(const struct drm_i915_private *i915,
+				const struct intel_uncore_forcewake_domain *d)
+{
+	if (likely(!wait_ack_set(i915, d, FORCEWAKE_KERNEL)))
+		return;
+
+	if (fw_domain_wait_ack_with_fallback(i915, d, ACK_SET))
+		fw_domain_wait_ack_set(i915, d);
+}
+
+static inline void
 fw_domain_put(const struct drm_i915_private *i915,
 	      const struct intel_uncore_forcewake_domain *d)
 {
@@ -119,7 +215,27 @@ fw_domains_get(struct drm_i915_private *i915, enum forcewake_domains fw_domains)
 	}
 
 	for_each_fw_domain_masked(d, fw_domains, i915, tmp)
-		fw_domain_wait_ack(i915, d);
+		fw_domain_wait_ack_set(i915, d);
+
+	i915->uncore.fw_domains_active |= fw_domains;
+}
+
+static void
+fw_domains_get_with_fallback(struct drm_i915_private *i915,
+			     enum forcewake_domains fw_domains)
+{
+	struct intel_uncore_forcewake_domain *d;
+	unsigned int tmp;
+
+	GEM_BUG_ON(fw_domains & ~i915->uncore.fw_domains);
+
+	for_each_fw_domain_masked(d, fw_domains, i915, tmp) {
+		fw_domain_wait_ack_clear_fallback(i915, d);
+		fw_domain_get(i915, d);
+	}
+
+	for_each_fw_domain_masked(d, fw_domains, i915, tmp)
+		fw_domain_wait_ack_set_fallback(i915, d);
 
 	i915->uncore.fw_domains_active |= fw_domains;
 }
@@ -229,6 +345,7 @@ intel_uncore_fw_release_timer(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+/* Note callers must have acquired the PUNIT->PMIC bus, before calling this. */
 static void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv,
 					 bool restore)
 {
@@ -237,6 +354,8 @@ static void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv,
 	int retry_count = 100;
 	enum forcewake_domains fw, active_domains;
 
+	iosf_mbi_assert_punit_acquired();
+
 	/* Hold uncore.lock across reset to prevent any register access
 	 * with forcewake not set correctly. Wait until all pending
 	 * timers are run before holding.
@@ -416,14 +535,18 @@ static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv,
 				   GT_FIFO_CTL_RC6_POLICY_STALL);
 	}
 
+	iosf_mbi_punit_acquire();
 	intel_uncore_forcewake_reset(dev_priv, restore_forcewake);
+	iosf_mbi_punit_release();
 }
 
 void intel_uncore_suspend(struct drm_i915_private *dev_priv)
 {
-	iosf_mbi_unregister_pmic_bus_access_notifier(
+	iosf_mbi_punit_acquire();
+	iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
 		&dev_priv->uncore.pmic_bus_access_nb);
 	intel_uncore_forcewake_reset(dev_priv, false);
+	iosf_mbi_punit_release();
 }
 
 void intel_uncore_resume_early(struct drm_i915_private *dev_priv)
@@ -442,9 +565,6 @@ void intel_uncore_runtime_resume(struct drm_i915_private *dev_priv)
 
 void intel_uncore_sanitize(struct drm_i915_private *dev_priv)
 {
-	i915_modparams.enable_rc6 =
-		sanitize_rc6_option(dev_priv, i915_modparams.enable_rc6);
-
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
 	intel_sanitize_gt_powersave(dev_priv);
 }
@@ -1148,7 +1268,8 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv)
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		dev_priv->uncore.funcs.force_wake_get = fw_domains_get;
+		dev_priv->uncore.funcs.force_wake_get =
+			fw_domains_get_with_fallback;
 		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_RENDER_GEN9,
@@ -1309,18 +1430,18 @@ void intel_uncore_init(struct drm_i915_private *dev_priv)
 
 	iosf_mbi_register_pmic_bus_access_notifier(
 		&dev_priv->uncore.pmic_bus_access_nb);
-
-	i915_check_and_clear_faults(dev_priv);
 }
 
 void intel_uncore_fini(struct drm_i915_private *dev_priv)
 {
-	iosf_mbi_unregister_pmic_bus_access_notifier(
-		&dev_priv->uncore.pmic_bus_access_nb);
-
 	/* Paranoia: make sure we have disabled everything before we exit. */
 	intel_uncore_sanitize(dev_priv);
+
+	iosf_mbi_punit_acquire();
+	iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
+		&dev_priv->uncore.pmic_bus_access_nb);
 	intel_uncore_forcewake_reset(dev_priv, false);
+	iosf_mbi_punit_release();
 }
 
 static const struct reg_whitelist {
@@ -1400,10 +1521,14 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
 				 engine->name);
 
-	I915_WRITE_FW(RING_CTL(base), 0);
+	I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
+
 	I915_WRITE_FW(RING_HEAD(base), 0);
 	I915_WRITE_FW(RING_TAIL(base), 0);
 
+	/* The ring must be empty before it is disabled */
+	I915_WRITE_FW(RING_CTL(base), 0);
+
 	/* Check acts as a post */
 	if (I915_READ_FW(RING_HEAD(base)) != 0)
 		DRM_DEBUG_DRIVER("%s: ring head not parked\n",
@@ -1801,18 +1926,13 @@ bool intel_has_gpu_reset(struct drm_i915_private *dev_priv)
 	return intel_get_gpu_reset(dev_priv) != NULL;
 }
 
-/*
- * When GuC submission is enabled, GuC manages ELSP and can initiate the
- * engine reset too. For now, fall back to full GPU reset if it is enabled.
- */
 bool intel_has_reset_engine(struct drm_i915_private *dev_priv)
 {
 	return (dev_priv->info.has_reset_engine &&
-		!dev_priv->guc.execbuf_client &&
 		i915_modparams.reset >= 2);
 }
 
-int intel_guc_reset(struct drm_i915_private *dev_priv)
+int intel_reset_guc(struct drm_i915_private *dev_priv)
 {
 	int ret;