Merge tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The usual lots of work all over the place.

  i915 has gotten some Alderlake work and prelim DG1 code, along with a
  major locking rework over the GEM code, and brings back the property
  of timing out long running jobs using a watchdog. amdgpu has some
  Alderbran support (new GPU), freesync HDMI support along with a lot
  other fixes.

  Outside of the drm, there is a new printf specifier added which should
  have all the correct acks/sobs:

   - printk fourcc modifier support added %p4cc

  Summary:

  core:
   - drm_crtc_commit_wait
   - atomic plane state helpers reworked for full state
   - dma-buf heaps API rework
   - edid: rework and improvements for displayid

  dp-mst:
   - better topology logging

  bridge:
   - Chipone ICN6211
   - Lontium LT8912B
   - anx7625 regulator support

  panel:
   - fix lt9611 4k panels handling

  simple-kms:
   - add plane state helpers

  ttm:
   - debugfs support
   - removal of unused sysfs
   - ignore signaled moved fences
   - ioremap buffer according to mem caching

  i915:
   - Alderlake S enablement
   - Conversion to dma_resv_locking
   - Bring back watchdog timeout support
   - legacy ioctl cleanups
   - add GEM TDDO and RFC process
   - DG1 LMEM preparation work
   - intel_display.c refactoring
   - Gen9/TGL PCH combination support
   - eDP MSO Support
   - multiple PSR instance support
   - Link training debug updates
   - Disable PSR2 support on JSL/EHL
   - DDR5/LPDDR5 support for bw calcs
   - LSPCON limited to gen9/10 platforms
   - HSW/BDW async flip/VTd corruption workaround
   - SAGV watermark fixes
   - SNB hard hang on ring resume fix
   - Limit imported dma-buf size
   - move to use new tasklet API
   - refactor KBL/TGL/ADL-S display/gt steppings
   - refactoring legacy DP/HDMI, FB plane code out

  amdgpu:
   - uapi: add ioctl to query video capabilities
   - Iniital AMD Freesync HDMI support
   - Initial Adebaran support
   - 10bpc dithering improvements
   - DCN secure display support
   - Drop legacy IO BAR requirements
   - PCIE/S0ix/RAS/Prime/Reset fixes
   - Display ASSR support
   - SMU gfx busy queues for RV/PCO
   - Initial LTTPR display work

  amdkfd:
   - MMU notifier fixes
   - APU fixes

  radeon:
   - debugfs cleanps
   - fw error handling ifix
   - Flexible array cleanups

  msm:
   - big DSI phy/pll cleanup
   - sc7280 initial support
   - commong bandwidth scaling path
   - shrinker locking contention fixes
   - unpin/swap support for GEM objcets

  ast:
   - cursor plane handling reworked

  tegra:
   - don't register DP AUX channels before connectors

  zynqmp:
   - fix OOB struct padding memset

  gma500:
   - drop ttm and medfield support

  exynos:
   - request_irq cleanup function

  mediatek:
   - fine tune line time for EOTp
   - MT8192 dpi support
   - atomic crtc config updates
   - don't support HDMI connector creation

  mxsdb:
   - imx8mm support

  panfrost:
   - MMU IRQ handling rework

  qxl:
   - locking fixes
   - resource deallocation changes

  sun4i:
   - add alpha properties to UI/VI layers

  vc4:
   - RPi4 CEC support

  vmwgfx:
   - doc cleanups

  arc:
   - moved to drm/tiny"

* tag 'drm-next-2021-04-28' of git://anongit.freedesktop.org/drm/drm: (1390 commits)
  drm/ttm: Don't count pages in SG BOs against pages_limit
  drm/ttm: fix return value check
  drm/bridge: lt8912b: fix incorrect handling of of_* return values
  drm: bridge: fix LONTIUM use of mipi_dsi_() functions
  drm: bridge: fix ANX7625 use of mipi_dsi_() functions
  drm/amdgpu: page retire over debugfs mechanism
  drm/radeon: Fix a missing check bug in radeon_dp_mst_detect()
  drm/amd/display: Fix the Wunused-function warning
  drm/radeon/r600: Fix variables that are not used after assignment
  drm/amdgpu/smu7: fix CAC setting on TOPAZ
  drm/amd/display: Update DCN302 SR Exit Latency
  drm/amdgpu: enable ras eeprom on aldebaran
  drm/amdgpu: RAS harvest on driver load
  drm/amdgpu: add ras aldebaran ras eeprom driver
  drm/amd/pm: increase time out value when sending msg to SMU
  drm/amdgpu: add DMUB outbox event IRQ source define/complete/debug flag
  drm/amd/pm: add the callback to get vbios bootup values for vangogh
  drm/radeon: Fix size overflow
  drm/amdgpu: Fix size overflow
  drm/amdgpu: move mmhub ras_func init to ip specific file
  ...

1 files changed, 133 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 22e39d938f17f..9165971c3c47a 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -33,7 +33,10 @@
 #include "gem/i915_gem_context.h"
 #include "gt/intel_breadcrumbs.h"
 #include "gt/intel_context.h"
+#include "gt/intel_engine.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gpu_commands.h"
+#include "gt/intel_reset.h"
 #include "gt/intel_ring.h"
 #include "gt/intel_rps.h"
 
@@ -244,6 +247,50 @@ static void __i915_request_fill(struct i915_request *rq, u8 val)
 	memset(vaddr + head, val, rq->postfix - head);
 }
 
+/**
+ * i915_request_active_engine
+ * @rq: request to inspect
+ * @active: pointer in which to return the active engine
+ *
+ * Fills the currently active engine to the @active pointer if the request
+ * is active and still not completed.
+ *
+ * Returns true if request was active or false otherwise.
+ */
+bool
+i915_request_active_engine(struct i915_request *rq,
+			   struct intel_engine_cs **active)
+{
+	struct intel_engine_cs *engine, *locked;
+	bool ret = false;
+
+	/*
+	 * Serialise with __i915_request_submit() so that it sees
+	 * is-banned?, or we know the request is already inflight.
+	 *
+	 * Note that rq->engine is unstable, and so we double
+	 * check that we have acquired the lock on the final engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock_irq(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		locked = engine;
+		spin_lock(&locked->active.lock);
+	}
+
+	if (i915_request_is_active(rq)) {
+		if (!__i915_request_is_complete(rq))
+			*active = locked;
+		ret = true;
+	}
+
+	spin_unlock_irq(&locked->active.lock);
+
+	return ret;
+}
+
+
 static void remove_from_engine(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine, *locked;
@@ -274,6 +321,53 @@ static void remove_from_engine(struct i915_request *rq)
 	__notify_execute_cb_imm(rq);
 }
 
+static void __rq_init_watchdog(struct i915_request *rq)
+{
+	rq->watchdog.timer.function = NULL;
+}
+
+static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer)
+{
+	struct i915_request *rq =
+		container_of(hrtimer, struct i915_request, watchdog.timer);
+	struct intel_gt *gt = rq->engine->gt;
+
+	if (!i915_request_completed(rq)) {
+		if (llist_add(&rq->watchdog.link, &gt->watchdog.list))
+			schedule_work(&gt->watchdog.work);
+	} else {
+		i915_request_put(rq);
+	}
+
+	return HRTIMER_NORESTART;
+}
+
+static void __rq_arm_watchdog(struct i915_request *rq)
+{
+	struct i915_request_watchdog *wdg = &rq->watchdog;
+	struct intel_context *ce = rq->context;
+
+	if (!ce->watchdog.timeout_us)
+		return;
+
+	hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	wdg->timer.function = __rq_watchdog_expired;
+	hrtimer_start_range_ns(&wdg->timer,
+			       ns_to_ktime(ce->watchdog.timeout_us *
+					   NSEC_PER_USEC),
+			       NSEC_PER_MSEC,
+			       HRTIMER_MODE_REL);
+	i915_request_get(rq);
+}
+
+static void __rq_cancel_watchdog(struct i915_request *rq)
+{
+	struct i915_request_watchdog *wdg = &rq->watchdog;
+
+	if (wdg->timer.function && hrtimer_try_to_cancel(&wdg->timer) > 0)
+		i915_request_put(rq);
+}
+
 bool i915_request_retire(struct i915_request *rq)
 {
 	if (!__i915_request_is_complete(rq))
@@ -285,6 +379,8 @@ bool i915_request_retire(struct i915_request *rq)
 	trace_i915_request_retire(rq);
 	i915_request_mark_complete(rq);
 
+	__rq_cancel_watchdog(rq);
+
 	/*
 	 * We know the GPU must have read the request to have
 	 * sent us the seqno + interrupt, so use the position
@@ -498,31 +594,38 @@ void __i915_request_skip(struct i915_request *rq)
 	rq->infix = rq->postfix;
 }
 
-void i915_request_set_error_once(struct i915_request *rq, int error)
+bool i915_request_set_error_once(struct i915_request *rq, int error)
 {
 	int old;
 
 	GEM_BUG_ON(!IS_ERR_VALUE((long)error));
 
 	if (i915_request_signaled(rq))
-		return;
+		return false;
 
 	old = READ_ONCE(rq->fence.error);
 	do {
 		if (fatal_error(old))
-			return;
+			return false;
 	} while (!try_cmpxchg(&rq->fence.error, &old, error));
+
+	return true;
 }
 
-void i915_request_mark_eio(struct i915_request *rq)
+struct i915_request *i915_request_mark_eio(struct i915_request *rq)
 {
 	if (__i915_request_is_complete(rq))
-		return;
+		return NULL;
 
 	GEM_BUG_ON(i915_request_signaled(rq));
 
+	/* As soon as the request is completed, it may be retired */
+	rq = i915_request_get(rq);
+
 	i915_request_set_error_once(rq, -EIO);
 	i915_request_mark_complete(rq);
+
+	return rq;
 }
 
 bool __i915_request_submit(struct i915_request *request)
@@ -678,6 +781,28 @@ void i915_request_unsubmit(struct i915_request *request)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void __cancel_request(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = NULL;
+
+	i915_request_active_engine(rq, &engine);
+
+	if (engine && intel_engine_pulse(engine))
+		intel_gt_handle_error(engine->gt, engine->mask, 0,
+				      "request cancellation by %s",
+				      current->comm);
+}
+
+void i915_request_cancel(struct i915_request *rq, int error)
+{
+	if (!i915_request_set_error_once(rq, error))
+		return;
+
+	set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
+
+	__cancel_request(rq);
+}
+
 static int __i915_sw_fence_call
 submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 {
@@ -690,6 +815,8 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 		if (unlikely(fence->error))
 			i915_request_set_error_once(request, fence->error);
+		else
+			__rq_arm_watchdog(request);
 
 		/*
 		 * We need to serialize use of the submit_request() callback
@@ -863,7 +990,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->fence.seqno = seqno;
 
 	RCU_INIT_POINTER(rq->timeline, tl);
-	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
 	GEM_BUG_ON(__i915_request_is_complete(rq));
 
@@ -877,6 +1003,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 
 	/* No zalloc, everything must be cleared after use */
 	rq->batch = NULL;
+	__rq_init_watchdog(rq);
 	GEM_BUG_ON(rq->capture_list);
 	GEM_BUG_ON(!llist_empty(&rq->execute_cb));
 
@@ -1108,9 +1235,6 @@ emit_semaphore_wait(struct i915_request *to,
 	if (i915_request_has_initial_breadcrumb(to))
 		goto await_fence;
 
-	if (!rcu_access_pointer(from->hwsp_cacheline))
-		goto await_fence;
-
 	/*
 	 * If this or its dependents are waiting on an external fence
 	 * that may fail catastrophically, then we want to avoid using