diff mbox

[v9,17/21] drm/i915: Watchdog timeout: IRQ handler for gen8+

Message ID 20170615201828.23144-18-michel.thierry@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Michel Thierry June 15, 2017, 8:18 p.m. UTC
*** General ***

Watchdog timeout (or "media engine reset") is a feature that allows
userland applications to enable hang detection on individual batch buffers.
The detection mechanism itself is mostly bound to the hardware and the only
thing that the driver needs to do to support this form of hang detection
is to implement the interrupt handling support as well as watchdog command
emission before and after the emitted batch buffer start instruction in the
ring buffer.

The principle of the hang detection mechanism is as follows:

1. Once the decision has been made to enable watchdog timeout for a
particular batch buffer and the driver is in the process of emitting the
batch buffer start instruction into the ring buffer it also emits a
watchdog timer start instruction before and a watchdog timer cancellation
instruction after the batch buffer start instruction in the ring buffer.

2. Once the GPU execution reaches the watchdog timer start instruction
the hardware watchdog counter is started by the hardware. The counter
keeps counting until either reaching a previously configured threshold
value or the timer cancellation instruction is executed.

2a. If the counter reaches the threshold value the hardware fires a
watchdog interrupt that is picked up by the watchdog interrupt handler.
This means that a hang has been detected and the driver needs to deal with
it the same way it would deal with a engine hang detected by the periodic
hang checker. The only difference between the two is that we already blamed
the active request (to ensure an engine reset).

2b. If the batch buffer completes and the execution reaches the watchdog
cancellation instruction before the watchdog counter reaches its
threshold value the watchdog is cancelled and nothing more comes of it.
No hang is detected.

Note about future interaction with preemption: Preemption could happen
in a command sequence prior to watchdog counter getting disabled,
resulting in watchdog being triggered following preemption (e.g. when
watchdog had been enabled in the low priority batch). The driver will
need to explicitly disable the watchdog counter as part of the
preemption sequence.

*** This patch introduces: ***

1. IRQ handler code for watchdog timeout allowing direct hang recovery
based on hardware-driven hang detection, which then integrates directly
with the hang recovery path. This is independent of having per-engine reset
or just full gpu reset.

2. Watchdog specific register information.

Currently the render engine and all available media engines support
watchdog timeout (VECS is only supported in GEN9). The specifications elude
to the BCS engine being supported but that is currently not supported by
this commit.

Note that the value to stop the counter is different between render and
non-render engines in GEN8; GEN9 onwards it's the same.

v2: Move irq handler to tasklet, arm watchdog for a 2nd time to check
against false-positives.

v3: Don't use high priority tasklet, use engine_last_submit while
checking for false-positives. From GEN9 onwards, the stop counter bit is
the same for all engines.

v4: Remove unnecessary brackets, use current_seqno to mark the request
as guilty in the hangcheck/capture code.

v5: Rebased after RESET_ENGINEs flag.

v6: Don't capture error state in case of watchdog timeout. The capture
process is time consuming and this will align to what happens when we
use GuC to handle the watchdog timeout. (Chris)

Signed-off-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Ian Lister <ian.lister@intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  4 ++
 drivers/gpu/drm/i915/i915_irq.c         | 19 +++++++--
 drivers/gpu/drm/i915/i915_reg.h         |  6 +++
 drivers/gpu/drm/i915/intel_hangcheck.c  | 13 +++++--
 drivers/gpu/drm/i915/intel_lrc.c        | 69 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++
 6 files changed, 108 insertions(+), 7 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9869acacb548..94c7d856174c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1550,6 +1550,9 @@  struct i915_gpu_error {
 	 * inspect the bit and do the reset directly, otherwise the worker
 	 * waits for the struct_mutex.
 	 *
+	 * #I915_RESET_WATCHDOG - When hw detects a hang before us, we can use
+	 * I915_RESET_WATCHDOG to report the hang detection cause accurately.
+	 *
 	 * #I915_RESET_ENGINE[num_engines] - Since the driver doesn't need to
 	 * acquire the struct_mutex to reset an engine, we need an explicit
 	 * flag to prevent two concurrent reset attempts in the same engine.
@@ -1564,6 +1567,7 @@  struct i915_gpu_error {
 	unsigned long flags;
 #define I915_RESET_BACKOFF	0
 #define I915_RESET_HANDOFF	1
+#define I915_RESET_WATCHDOG	2
 #define I915_WEDGED		(BITS_PER_LONG - 1)
 #define I915_RESET_ENGINE	(I915_WEDGED - I915_NUM_ENGINES)
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8088b5151fca..211ec1110ef4 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1336,6 +1336,9 @@  gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir, int test_shift)
 
 	if (tasklet)
 		tasklet_hi_schedule(&engine->irq_tasklet);
+
+	if (iir & (GT_GEN8_WATCHDOG_INTERRUPT << test_shift))
+		tasklet_schedule(&engine->watchdog_tasklet);
 }
 
 static irqreturn_t gen8_gt_irq_ack(struct drm_i915_private *dev_priv,
@@ -2740,7 +2743,10 @@  void i915_handle_error(struct drm_i915_private *dev_priv,
 	 */
 	intel_runtime_pm_get(dev_priv);
 
-	i915_capture_error_state(dev_priv, engine_mask, error_msg);
+	if (strstr(error_msg, "Watchdog timeout"))
+		DRM_INFO("%s", error_msg);
+	else
+		i915_capture_error_state(dev_priv, engine_mask, error_msg);
 	i915_clear_error_registers(dev_priv);
 
 	if (!engine_mask)
@@ -2752,7 +2758,7 @@  void i915_handle_error(struct drm_i915_private *dev_priv,
 	 */
 	if (intel_has_reset_engine(dev_priv)) {
 		for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
-			BUILD_BUG_ON(I915_RESET_HANDOFF >= I915_RESET_ENGINE);
+			BUILD_BUG_ON(I915_RESET_WATCHDOG >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					     &dev_priv->gpu_error.flags))
 				continue;
@@ -3437,12 +3443,15 @@  static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	uint32_t gt_interrupts[] = {
 		GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
 			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
+			GT_GEN8_WATCHDOG_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
 			GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT |
 			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT,
 		GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT |
 			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT |
+			GT_GEN8_WATCHDOG_INTERRUPT << GEN8_VCS1_IRQ_SHIFT |
 			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT |
-			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT,
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT |
+			GT_GEN8_WATCHDOG_INTERRUPT << GEN8_VCS2_IRQ_SHIFT,
 		0,
 		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT |
 			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT
@@ -3451,6 +3460,10 @@  static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	if (HAS_L3_DPF(dev_priv))
 		gt_interrupts[0] |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
 
+	/* VECS watchdog is only available in skl+ */
+	if (INTEL_GEN(dev_priv) >= 9)
+		gt_interrupts[3] |= GT_GEN8_WATCHDOG_INTERRUPT;
+
 	dev_priv->pm_ier = 0x0;
 	dev_priv->pm_imr = ~dev_priv->pm_ier;
 	GEN8_IRQ_INIT_NDX(GT, 0, ~gt_interrupts[0], gt_interrupts[0]);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index bd535f12db18..35845c0be46f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2096,6 +2096,11 @@  enum skl_disp_power_wells {
 #define RING_START(base)	_MMIO((base)+0x38)
 #define RING_CTL(base)		_MMIO((base)+0x3c)
 #define   RING_CTL_SIZE(size)	((size) - PAGE_SIZE) /* in bytes -> pages */
+#define RING_CNTR(base)        _MMIO((base) + 0x178)
+#define   GEN8_WATCHDOG_ENABLE		0
+#define   GEN8_WATCHDOG_DISABLE	1
+#define   GEN8_XCS_WATCHDOG_DISABLE	0xFFFFFFFF /* GEN8 & non-render only */
+#define RING_THRESH(base)      _MMIO((base) + 0x17C)
 #define RING_SYNC_0(base)	_MMIO((base)+0x40)
 #define RING_SYNC_1(base)	_MMIO((base)+0x44)
 #define RING_SYNC_2(base)	_MMIO((base)+0x48)
@@ -2577,6 +2582,7 @@  enum skl_disp_power_wells {
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_CONTEXT_SWITCH_INTERRUPT		(1 <<  8)
+#define GT_GEN8_WATCHDOG_INTERRUPT		(1 <<  6) /* gen8+ */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index 9b0ece427bdc..254155ebab45 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -388,7 +388,8 @@  static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 
 static void hangcheck_declare_hang(struct drm_i915_private *i915,
 				   unsigned int hung,
-				   unsigned int stuck)
+				   unsigned int stuck,
+				   unsigned int watchdog)
 {
 	struct intel_engine_cs *engine;
 	char msg[80];
@@ -401,7 +402,8 @@  static void hangcheck_declare_hang(struct drm_i915_private *i915,
 	if (stuck != hung)
 		hung &= ~stuck;
 	len = scnprintf(msg, sizeof(msg),
-			"%s on ", stuck == hung ? "No progress" : "Hang");
+			"%s on ", watchdog ? "Watchdog timeout" :
+				  stuck == hung ? "No progress" : "Hang");
 	for_each_engine_masked(engine, i915, hung, tmp)
 		len += scnprintf(msg + len, sizeof(msg) - len,
 				 "%s, ", engine->name);
@@ -425,7 +427,7 @@  static void i915_hangcheck_elapsed(struct work_struct *work)
 			     gpu_error.hangcheck_work.work);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	unsigned int hung = 0, stuck = 0;
+	unsigned int hung = 0, stuck = 0, watchdog = 0;
 	int busy_count = 0;
 
 	if (!i915.enable_hangcheck)
@@ -437,6 +439,9 @@  static void i915_hangcheck_elapsed(struct work_struct *work)
 	if (i915_terminally_wedged(&dev_priv->gpu_error))
 		return;
 
+	if (test_and_clear_bit(I915_RESET_WATCHDOG, &dev_priv->gpu_error.flags))
+		watchdog = 1;
+
 	/* As enabling the GPU requires fairly extensive mmio access,
 	 * periodically arm the mmio checker to see if we are triggering
 	 * any invalid access.
@@ -463,7 +468,7 @@  static void i915_hangcheck_elapsed(struct work_struct *work)
 	}
 
 	if (hung)
-		hangcheck_declare_hang(dev_priv, hung, stuck);
+		hangcheck_declare_hang(dev_priv, hung, stuck, watchdog);
 
 	/* Reset timer in case GPU hangs without another request being added */
 	if (busy_count)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7404cf2aac28..a66c23de80dc 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1539,6 +1539,53 @@  static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 	return 0;
 }
 
+/* From GEN9 onwards, all engines use the same RING_CNTR format */
+static inline u32 get_watchdog_disable(struct intel_engine_cs *engine)
+{
+	if (engine->id == RCS || INTEL_GEN(engine->i915) >= 9)
+		return GEN8_WATCHDOG_DISABLE;
+	else
+		return GEN8_XCS_WATCHDOG_DISABLE;
+}
+
+#define GEN8_WATCHDOG_1000US 0x2ee0 //XXX: Temp, replace with helper function
+static void gen8_watchdog_irq_handler(unsigned long data)
+{
+	struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
+	struct drm_i915_private *dev_priv = engine->i915;
+	u32 current_seqno;
+
+	intel_uncore_forcewake_get(dev_priv, engine->fw_domains);
+
+	/* Stop the counter to prevent further timeout interrupts */
+	I915_WRITE_FW(RING_CNTR(engine->mmio_base), get_watchdog_disable(engine));
+
+	current_seqno = intel_engine_get_seqno(engine);
+
+	/* did the request complete after the timer expired? */
+	if (intel_engine_last_submit(engine) == current_seqno)
+		goto fw_put;
+
+	if (engine->hangcheck.watchdog == current_seqno) {
+		/* Make sure the active request will be marked as guilty */
+		engine->hangcheck.stalled = true;
+		engine->hangcheck.seqno = current_seqno;
+
+		/* And try to run the hangcheck_work as soon as possible */
+		set_bit(I915_RESET_WATCHDOG, &dev_priv->gpu_error.flags);
+		queue_delayed_work(system_long_wq,
+				   &dev_priv->gpu_error.hangcheck_work, 0);
+	} else {
+		engine->hangcheck.watchdog = current_seqno;
+		/* Re-start the counter, if really hung, it will expire again */
+		I915_WRITE_FW(RING_THRESH(engine->mmio_base), GEN8_WATCHDOG_1000US);
+		I915_WRITE_FW(RING_CNTR(engine->mmio_base), GEN8_WATCHDOG_ENABLE);
+	}
+
+fw_put:
+	intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
+}
+
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -1632,6 +1679,9 @@  void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->irq_tasklet.state)))
 		tasklet_kill(&engine->irq_tasklet);
 
+	if (WARN_ON(test_bit(TASKLET_STATE_SCHED, &engine->watchdog_tasklet.state)))
+		tasklet_kill(&engine->watchdog_tasklet);
+
 	dev_priv = engine->i915;
 
 	if (engine->buffer) {
@@ -1690,6 +1740,22 @@  logical_ring_default_irqs(struct intel_engine_cs *engine)
 	unsigned shift = engine->irq_shift;
 	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
 	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
+
+	switch (engine->id) {
+	default:
+		/* BCS engine does not support hw watchdog */
+		break;
+	case RCS:
+	case VCS:
+	case VCS2:
+		engine->irq_keep_mask |= (GT_GEN8_WATCHDOG_INTERRUPT << shift);
+		break;
+	case VECS:
+		if (INTEL_GEN(engine->i915) >= 9)
+			engine->irq_keep_mask |=
+				(GT_GEN8_WATCHDOG_INTERRUPT << shift);
+		break;
+	}
 }
 
 static int
@@ -1738,6 +1804,9 @@  logical_ring_setup(struct intel_engine_cs *engine)
 	tasklet_init(&engine->irq_tasklet,
 		     intel_lrc_irq_handler, (unsigned long)engine);
 
+	tasklet_init(&engine->watchdog_tasklet,
+		     gen8_watchdog_irq_handler, (unsigned long)engine);
+
 	logical_ring_default_vfuncs(engine);
 	logical_ring_default_irqs(engine);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index d33c93444c0d..3906b33f5e74 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -117,6 +117,7 @@  struct intel_instdone {
 struct intel_engine_hangcheck {
 	u64 acthd;
 	u32 seqno;
+	u32 watchdog;
 	enum intel_engine_hangcheck_action action;
 	unsigned long action_timestamp;
 	int deadlock;
@@ -416,6 +417,9 @@  struct intel_engine_cs {
 
 	struct intel_engine_hangcheck hangcheck;
 
+	/* watchdog_tasklet: stop counter and re-schedule hangcheck_work asap */
+	struct tasklet_struct watchdog_tasklet;
+
 	bool needs_cmd_parser;
 
 	/*