diff mbox

[v5,16/18] drm/i915: Watchdog timeout: Ringbuffer command emission for gen8+

Message ID 20170325013010.36244-17-michel.thierry@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Michel Thierry March 25, 2017, 1:30 a.m. UTC
Emit the required commands into the ring buffer for starting and
stopping the watchdog timer before/after batch buffer start during
batch buffer submission.

v2: Support watchdog threshold per context engine, merge lri commands,
and move watchdog commands emission to emit_bb_start. Request space of
combined start_watchdog, bb_start and stop_watchdog to avoid any error
after emitting bb_start.

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_gem_context.h |  4 ++
 drivers/gpu/drm/i915/intel_lrc.c        | 86 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++
 3 files changed, 92 insertions(+), 2 deletions(-)

Comments

Chris Wilson March 25, 2017, 9:46 a.m. UTC | #1
On Fri, Mar 24, 2017 at 06:30:08PM -0700, Michel Thierry wrote:
> Emit the required commands into the ring buffer for starting and
> stopping the watchdog timer before/after batch buffer start during
> batch buffer submission.
> 
> v2: Support watchdog threshold per context engine, merge lri commands,
> and move watchdog commands emission to emit_bb_start. Request space of
> combined start_watchdog, bb_start and stop_watchdog to avoid any error
> after emitting bb_start.
> 
> 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_gem_context.h |  4 ++
>  drivers/gpu/drm/i915/intel_lrc.c        | 86 ++++++++++++++++++++++++++++++++-
>  drivers/gpu/drm/i915/intel_ringbuffer.h |  4 ++
>  3 files changed, 92 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
> index 4af2ab94558b..88700bdbb4e1 100644
> --- a/drivers/gpu/drm/i915/i915_gem_context.h
> +++ b/drivers/gpu/drm/i915/i915_gem_context.h
> @@ -150,6 +150,10 @@ struct i915_gem_context {
>  		u32 *lrc_reg_state;
>  		u64 lrc_desc;
>  		int pin_count;
> +		/** watchdog_threshold: hw watchdog threshold value,
> +		 * in clock counts
> +		 */
> +		u32 watchdog_threshold;
>  		bool initialised;
>  	} engine[I915_NUM_ENGINES];
>  
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 73f8fbdcf1fb..2736f642dc76 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1319,6 +1319,8 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
>  			      const unsigned int flags)
>  {
>  	u32 *cs;
> +	u32 num_dwords;
> +	bool watchdog_running = false;
>  	int ret;
>  
>  	/* Don't rely in hw updating PDPs, specially in lite-restore.
> @@ -1338,10 +1340,29 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
>  		req->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(req->engine);
>  	}
>  
> -	cs = intel_ring_begin(req, 4);
> +	/* bb_start only */
> +	num_dwords = 4;
> +
> +	/* check if watchdog will be required */
> +	if (req->ctx->engine[req->engine->id].watchdog_threshold != 0) {
> +		if (!req->engine->emit_start_watchdog ||
> +		    !req->engine->emit_stop_watchdog)
> +			return -EINVAL;

A bit late! This will already be checked before we set the threshold.

> +		/* start_watchdog (6) + bb_start (4) + stop_watchdog (4) */

Don't mention bb_start since it isn't in the additional 10 and you just
confused me! :)

> +		num_dwords += 10;
> +		watchdog_running = true;
> +	}
> +
> +	cs = intel_ring_begin(req, num_dwords);
>  	if (IS_ERR(cs))
>  		return PTR_ERR(cs);
>  
> +	if (watchdog_running) {
> +		/* Start watchdog timer */
> +		cs = req->engine->emit_start_watchdog(req, cs);

Are they going to be specialised vfuncs in the near future? i.e.
something other than LRI. If the only advantage is for checking feature
compatability, we could just a bit instead?

> +	}
> +
>  	/* FIXME(BDW): Address space and security selectors. */
>  	*cs++ = MI_BATCH_BUFFER_START_GEN8 |
>  		(flags & I915_DISPATCH_SECURE ? 0 : BIT(8)) |
> @@ -1349,8 +1370,13 @@ static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
>  	*cs++ = lower_32_bits(offset);
>  	*cs++ = upper_32_bits(offset);
>  	*cs++ = MI_NOOP;
> -	intel_ring_advance(req, cs);
>  
> +	if (watchdog_running) {
> +		/* Cancel watchdog timer */
> +		cs = req->engine->emit_stop_watchdog(req, cs);
> +	}
> +
> +	intel_ring_advance(req, cs);
>  	return 0;
>  }
>  
> @@ -1512,6 +1538,54 @@ static void gen8_watchdog_irq_handler(unsigned long data)
>  	intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
>  }
>  
> +static u32 *gen8_emit_start_watchdog(struct drm_i915_gem_request *req, u32 *cs)
> +{
> +	struct intel_engine_cs *engine = req->engine;
> +	struct i915_gem_context *ctx = req->ctx;
> +	struct intel_context *ce = &ctx->engine[engine->id];
> +
> +	/* XXX: no watchdog support in BCS engine */
> +	GEM_BUG_ON(engine->id == BCS);
> +
> +	/*
> +	 * watchdog register must never be programmed to zero. This would
> +	 * cause the watchdog counter to exceed and not allow the engine to
> +	 * go into IDLE state
> +	 */
> +	GEM_BUG_ON(ce->watchdog_threshold == 0);
> +
> +	/* Set counter period */
> +	*cs++ = MI_LOAD_REGISTER_IMM(2);
> +	*cs++ = i915_mmio_reg_offset(RING_THRESH(engine->mmio_base));
> +	*cs++ = ce->watchdog_threshold;
> +	/* Start counter */
> +	*cs++ = i915_mmio_reg_offset(RING_CNTR(engine->mmio_base));
> +	*cs++ = GEN8_WATCHDOG_ENABLE;
> +	*cs++ = MI_NOOP;
> +
> +	return cs;
> +}
> +
> +static u32 *gen8_emit_stop_watchdog(struct drm_i915_gem_request *req, u32 *cs)
> +{
> +	struct intel_engine_cs *engine = req->engine;
> +
> +	/* XXX: no watchdog support in BCS engine */
> +	GEM_BUG_ON(engine->id == BCS);
> +
> +	*cs++ = MI_LOAD_REGISTER_IMM(2);
> +	*cs++ = i915_mmio_reg_offset(RING_CNTR(engine->mmio_base));
> +
> +	if (engine->id == RCS)
> +		*cs++ = GEN8_RCS_WATCHDOG_DISABLE;
> +	else
> +		*cs++ = GEN8_XCS_WATCHDOG_DISABLE;
> +
> +	*cs++ = MI_NOOP;

2 spare NOOPS, cancel out.
-Chris
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 4af2ab94558b..88700bdbb4e1 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -150,6 +150,10 @@  struct i915_gem_context {
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
+		/** watchdog_threshold: hw watchdog threshold value,
+		 * in clock counts
+		 */
+		u32 watchdog_threshold;
 		bool initialised;
 	} engine[I915_NUM_ENGINES];
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 73f8fbdcf1fb..2736f642dc76 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1319,6 +1319,8 @@  static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 			      const unsigned int flags)
 {
 	u32 *cs;
+	u32 num_dwords;
+	bool watchdog_running = false;
 	int ret;
 
 	/* Don't rely in hw updating PDPs, specially in lite-restore.
@@ -1338,10 +1340,29 @@  static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 		req->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(req->engine);
 	}
 
-	cs = intel_ring_begin(req, 4);
+	/* bb_start only */
+	num_dwords = 4;
+
+	/* check if watchdog will be required */
+	if (req->ctx->engine[req->engine->id].watchdog_threshold != 0) {
+		if (!req->engine->emit_start_watchdog ||
+		    !req->engine->emit_stop_watchdog)
+			return -EINVAL;
+
+		/* start_watchdog (6) + bb_start (4) + stop_watchdog (4) */
+		num_dwords += 10;
+		watchdog_running = true;
+	}
+
+	cs = intel_ring_begin(req, num_dwords);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
+	if (watchdog_running) {
+		/* Start watchdog timer */
+		cs = req->engine->emit_start_watchdog(req, cs);
+	}
+
 	/* FIXME(BDW): Address space and security selectors. */
 	*cs++ = MI_BATCH_BUFFER_START_GEN8 |
 		(flags & I915_DISPATCH_SECURE ? 0 : BIT(8)) |
@@ -1349,8 +1370,13 @@  static int gen8_emit_bb_start(struct drm_i915_gem_request *req,
 	*cs++ = lower_32_bits(offset);
 	*cs++ = upper_32_bits(offset);
 	*cs++ = MI_NOOP;
-	intel_ring_advance(req, cs);
 
+	if (watchdog_running) {
+		/* Cancel watchdog timer */
+		cs = req->engine->emit_stop_watchdog(req, cs);
+	}
+
+	intel_ring_advance(req, cs);
 	return 0;
 }
 
@@ -1512,6 +1538,54 @@  static void gen8_watchdog_irq_handler(unsigned long data)
 	intel_uncore_forcewake_put(dev_priv, engine->fw_domains);
 }
 
+static u32 *gen8_emit_start_watchdog(struct drm_i915_gem_request *req, u32 *cs)
+{
+	struct intel_engine_cs *engine = req->engine;
+	struct i915_gem_context *ctx = req->ctx;
+	struct intel_context *ce = &ctx->engine[engine->id];
+
+	/* XXX: no watchdog support in BCS engine */
+	GEM_BUG_ON(engine->id == BCS);
+
+	/*
+	 * watchdog register must never be programmed to zero. This would
+	 * cause the watchdog counter to exceed and not allow the engine to
+	 * go into IDLE state
+	 */
+	GEM_BUG_ON(ce->watchdog_threshold == 0);
+
+	/* Set counter period */
+	*cs++ = MI_LOAD_REGISTER_IMM(2);
+	*cs++ = i915_mmio_reg_offset(RING_THRESH(engine->mmio_base));
+	*cs++ = ce->watchdog_threshold;
+	/* Start counter */
+	*cs++ = i915_mmio_reg_offset(RING_CNTR(engine->mmio_base));
+	*cs++ = GEN8_WATCHDOG_ENABLE;
+	*cs++ = MI_NOOP;
+
+	return cs;
+}
+
+static u32 *gen8_emit_stop_watchdog(struct drm_i915_gem_request *req, u32 *cs)
+{
+	struct intel_engine_cs *engine = req->engine;
+
+	/* XXX: no watchdog support in BCS engine */
+	GEM_BUG_ON(engine->id == BCS);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(2);
+	*cs++ = i915_mmio_reg_offset(RING_CNTR(engine->mmio_base));
+
+	if (engine->id == RCS)
+		*cs++ = GEN8_RCS_WATCHDOG_DISABLE;
+	else
+		*cs++ = GEN8_XCS_WATCHDOG_DISABLE;
+
+	*cs++ = MI_NOOP;
+
+	return cs;
+}
+
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -1780,6 +1854,8 @@  int logical_render_ring_init(struct intel_engine_cs *engine)
 	engine->emit_flush = gen8_emit_flush_render;
 	engine->emit_breadcrumb = gen8_emit_breadcrumb_render;
 	engine->emit_breadcrumb_sz = gen8_emit_breadcrumb_render_sz;
+	engine->emit_start_watchdog = gen8_emit_start_watchdog;
+	engine->emit_stop_watchdog = gen8_emit_stop_watchdog;
 
 	ret = intel_engine_create_scratch(engine, PAGE_SIZE);
 	if (ret)
@@ -1803,6 +1879,12 @@  int logical_xcs_ring_init(struct intel_engine_cs *engine)
 {
 	logical_ring_setup(engine);
 
+	/* BCS engine does not have a watchdog-expired irq */
+	if (engine->id != BCS) {
+		engine->emit_start_watchdog = gen8_emit_start_watchdog;
+		engine->emit_stop_watchdog = gen8_emit_stop_watchdog;
+	}
+
 	return logical_ring_init(engine);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index fffe69f5aed2..34ca0c5ac5b9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -275,6 +275,10 @@  struct intel_engine_cs {
 
 	int		(*emit_flush)(struct drm_i915_gem_request *request,
 				      u32 mode);
+	u32 *		(*emit_start_watchdog)(struct drm_i915_gem_request *req,
+					       u32 *cs);
+	u32 *		(*emit_stop_watchdog)(struct drm_i915_gem_request *req,
+					      u32 *cs);
 #define EMIT_INVALIDATE	BIT(0)
 #define EMIT_FLUSH	BIT(1)
 #define EMIT_BARRIER	(EMIT_INVALIDATE | EMIT_FLUSH)