Skip to contentSkip to conversation

drm/i915: Handle RC6 counter wrap

PATCH Superseded Tvrtko Ursulin 5 participants 17 messages Feb 8, 2018 – Feb 13, 2018 1 message not in the archive

Subsystems (2)
lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): 151807682017.28809.17040553218386245341@mail.alporthouse.com151807682017.28809.17040553218386245341@mail.alporthouse.com

Tvrtko Ursulin

author maintainer
#1 lore raw

PATCH v3 1/1 drm/i915: Handle RC6 counter wrap

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 62 +++++++++++++++++++++++++++++++++++------
 2 files changed, 55 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
 };
 
 struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +53 -9

106 lines not on this page · raw message

Signature · 6 lines
2.14.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw
Quoted 147 lines · Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 62 +++++++++++++++++++++++++++++++++++------
 2 files changed, 55 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
 };
 
 struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +44 -9
index 41f26ab46501..063c885175e7 100644
@@ -9417,15 +9417,16 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
 			     const i915_reg_t reg)
 {
 	u32 lower, upper, tmp;
-	unsigned long flags;
 	int loop = 2;
 
-	/* The register accessed do not need forcewake. We borrow
+	/*
+	 * The register accessed do not need forcewake. We borrow
 	 * uncore lock to prevent concurrent access to range reg.
 	 */
-	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	lockdep_assert_held(&dev_priv->uncore.lock);
 
-	/* vlv and chv residency counters are 40 bits in width.
+	/*
+	 * vlv and chv residency counters are 40 bits in width.
 	 * With a control bit, we can choose between upper or lower
 	 * 32bit window into this counter.
 	 *
@@ -9449,29 +9450,49 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
 		upper = I915_READ_FW(reg);
 	} while (upper != tmp && --loop);
 
-	/* Everywhere else we always use VLV_COUNTER_CONTROL with the
+	/*
+	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
 	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
 	 * now.
 	 */
 
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
 	return lower | (u64)upper << 8;
 }
 
 u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
 			   const i915_reg_t reg)
 {
-	u64 time_hw;
+	u64 time_hw, prev_hw, overflow_hw;
+	unsigned int fw_domains;
+	unsigned long flags;
+	unsigned int i;
 	u32 mul, div;
 
 	if (!HAS_RC6(dev_priv))
 		return 0;
 
+	/*
+	 * Store previous hw counter values for counter wrap-around handling.
+	 *
+	 * There are only four interesting registers and they live next to each
+	 * other so we can use the relative address, compared to the smallest
+	 * one as the index into driver storage.
+	 */
+	i = (i915_mmio_reg_offset(reg) -
+	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+	if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
+		return 0;
+
+	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+
 	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		mul = 1000000;
 		div = dev_priv->czclk_freq;
+		overflow_hw = BIT_ULL(40);
 		time_hw = vlv_residency_raw(dev_priv, reg);
 	} else {
 		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
@@ -9483,9 +9504,32 @@ u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
 			div = 1;
 		}
 
-		time_hw = I915_READ(reg);
+		overflow_hw = BIT_ULL(32);
+		time_hw = I915_READ_FW(reg);
 	}
 
+	/*
+	 * Counter wrap handling.
+	 *
+	 * But relying on a sufficient frequency of queries otherwise counters
+	 * can still wrap.
+	 */
+	prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
+	dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
+
+	/* RC6 delta from last sample. */
+	if (time_hw >= prev_hw)
+		time_hw -= prev_hw;
+	else

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9533

Quoted 10 lines
drivers/gpu/drm/i915/intel_pm.c +9 -0
+		time_hw += overflow_hw - prev_hw;
+
+	/* Add delta to RC6 extended raw driver copy. */
+	time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
+	dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
+
+	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
 	return DIV_ROUND_UP_ULL(time_hw * mul, div);

What happens when time_hw*mul+div-1 overflows?

Quoted 9 lines
drivers/gpu/drm/i915/intel_pm.c +0 -0
 }
 
Signature · 6 lines
2.14.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 6 lines
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw
Quoted 152 lines · Ville Syrjälä
Quoted 151 lines · Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

---
  drivers/gpu/drm/i915/i915_drv.h |  2 ++
  drivers/gpu/drm/i915/intel_pm.c | 62 +++++++++++++++++++++++++++++++++++------
  2 files changed, 55 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
  struct intel_rc6 {
  	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
  };
 
  struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +48 -9
index 41f26ab46501..063c885175e7 100644
@@ -9417,15 +9417,16 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
  			     const i915_reg_t reg)
  {
  	u32 lower, upper, tmp;
-	unsigned long flags;
  	int loop = 2;
 
-	/* The register accessed do not need forcewake. We borrow
+	/*
+	 * The register accessed do not need forcewake. We borrow
  	 * uncore lock to prevent concurrent access to range reg.
  	 */
-	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	lockdep_assert_held(&dev_priv->uncore.lock);
 
-	/* vlv and chv residency counters are 40 bits in width.
+	/*
+	 * vlv and chv residency counters are 40 bits in width.
  	 * With a control bit, we can choose between upper or lower
  	 * 32bit window into this counter.
  	 *
@@ -9449,29 +9450,49 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
  		upper = I915_READ_FW(reg);
  	} while (upper != tmp && --loop);
 
-	/* Everywhere else we always use VLV_COUNTER_CONTROL with the
+	/*
+	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
  	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
  	 * now.
  	 */
 
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
  	return lower | (u64)upper << 8;
  }
 
  u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
  			   const i915_reg_t reg)
  {
-	u64 time_hw;
+	u64 time_hw, prev_hw, overflow_hw;
+	unsigned int fw_domains;
+	unsigned long flags;
+	unsigned int i;
  	u32 mul, div;
 
  	if (!HAS_RC6(dev_priv))
  		return 0;
 
+	/*
+	 * Store previous hw counter values for counter wrap-around handling.
+	 *
+	 * There are only four interesting registers and they live next to each
+	 * other so we can use the relative address, compared to the smallest
+	 * one as the index into driver storage.
+	 */
+	i = (i915_mmio_reg_offset(reg) -
+	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+	if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
+		return 0;
+
+	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+
  	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
  	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
  		mul = 1000000;
  		div = dev_priv->czclk_freq;
+		overflow_hw = BIT_ULL(40);
  		time_hw = vlv_residency_raw(dev_priv, reg);
  	} else {
  		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
@@ -9483,9 +9504,32 @@ u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
  			div = 1;
  		}
 
-		time_hw = I915_READ(reg);
+		overflow_hw = BIT_ULL(32);
+		time_hw = I915_READ_FW(reg);
  	}
 
+	/*
+	 * Counter wrap handling.
+	 *
+	 * But relying on a sufficient frequency of queries otherwise counters
+	 * can still wrap.
+	 */
+	prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
+	dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
+
+	/* RC6 delta from last sample. */
+	if (time_hw >= prev_hw)
+		time_hw -= prev_hw;
+	else
+		time_hw += overflow_hw - prev_hw;
+
+	/* Add delta to RC6 extended raw driver copy. */
+	time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
Quoted 8 lines

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9533

Quoted 6 lines
drivers/gpu/drm/i915/intel_pm.c +5 -0
+	dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
+
+	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
  	return DIV_ROUND_UP_ULL(time_hw * mul, div);

What happens when time_hw*mul+div-1 overflows?

It overflows. :I

Apart on Valleyview multipler is 14 bits max, so we still get 64 - 14 - 1 = 49 bits of software stored RC6 before it happens. Given that the info if 32-bits is 50 minutes or so, 49 bits sounds good enough.

On Valleyview multiplier is 20 bits so 64 - 20 - 1 = 43 bits before overflow. A bit less than above, and I am not sure what the 40-bit hw counter overflow period is there to start with? Is 8 times that enough? Or not?

Suggestions?

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#4 lore raw

Quoting Tvrtko Ursulin (2018-02-08 14:31:05)

Quoted 165 lines · Ville Syrjälä
Quoted 152 lines · Tvrtko Ursulin
Quoted 151 lines

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

---
  drivers/gpu/drm/i915/i915_drv.h |  2 ++
  drivers/gpu/drm/i915/intel_pm.c | 62 +++++++++++++++++++++++++++++++++++------
  2 files changed, 55 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
  struct intel_rc6 {
     bool enabled;
+    u64 prev_hw_residency[4];
+    u64 cur_residency[4];
  };
 
  struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +48 -9
index 41f26ab46501..063c885175e7 100644
@@ -9417,15 +9417,16 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
                          const i915_reg_t reg)
  {
     u32 lower, upper, tmp;
-    unsigned long flags;
     int loop = 2;
 
-    /* The register accessed do not need forcewake. We borrow
+    /*
+     * The register accessed do not need forcewake. We borrow
      * uncore lock to prevent concurrent access to range reg.
      */
-    spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+    lockdep_assert_held(&dev_priv->uncore.lock);
 
-    /* vlv and chv residency counters are 40 bits in width.
+    /*
+     * vlv and chv residency counters are 40 bits in width.
      * With a control bit, we can choose between upper or lower
      * 32bit window into this counter.
      *
@@ -9449,29 +9450,49 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
             upper = I915_READ_FW(reg);
     } while (upper != tmp && --loop);
 
-    /* Everywhere else we always use VLV_COUNTER_CONTROL with the
+    /*
+     * Everywhere else we always use VLV_COUNTER_CONTROL with the
      * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
      * now.
      */
 
-    spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
     return lower | (u64)upper << 8;
  }
 
  u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
                        const i915_reg_t reg)
  {
-    u64 time_hw;
+    u64 time_hw, prev_hw, overflow_hw;
+    unsigned int fw_domains;
+    unsigned long flags;
+    unsigned int i;
     u32 mul, div;
 
     if (!HAS_RC6(dev_priv))
             return 0;
 
+    /*
+     * Store previous hw counter values for counter wrap-around handling.
+     *
+     * There are only four interesting registers and they live next to each
+     * other so we can use the relative address, compared to the smallest
+     * one as the index into driver storage.
+     */
+    i = (i915_mmio_reg_offset(reg) -
+         i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+    if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
+            return 0;
+
+    fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+
+    spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+    intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+
     /* On VLV and CHV, residency time is in CZ units rather than 1.28us */
     if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
             mul = 1000000;
             div = dev_priv->czclk_freq;
+            overflow_hw = BIT_ULL(40);
             time_hw = vlv_residency_raw(dev_priv, reg);
     } else {
             /* 833.33ns units on Gen9LP, 1.28us elsewhere. */
@@ -9483,9 +9504,32 @@ u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
                     div = 1;
             }
 
-            time_hw = I915_READ(reg);
+            overflow_hw = BIT_ULL(32);
+            time_hw = I915_READ_FW(reg);
     }
 
+    /*
+     * Counter wrap handling.
+     *
+     * But relying on a sufficient frequency of queries otherwise counters
+     * can still wrap.
+     */
+    prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
+    dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
+
+    /* RC6 delta from last sample. */
+    if (time_hw >= prev_hw)
+            time_hw -= prev_hw;
+    else
+            time_hw += overflow_hw - prev_hw;
+
+    /* Add delta to RC6 extended raw driver copy. */
+    time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
Quoted 8 lines

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9533

Quoted 6 lines
drivers/gpu/drm/i915/intel_pm.c +5 -0
+    dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
+
+    intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
+    spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
     return DIV_ROUND_UP_ULL(time_hw * mul, div);

What happens when time_hw*mul+div-1 overflows?

It overflows. :I

Quoted 8 lines

Apart on Valleyview multipler is 14 bits max, so we still get 64 - 14 - 1 = 49 bits of software stored RC6 before it happens. Given that the info if 32-bits is 50 minutes or so, 49 bits sounds good enough.

On Valleyview multiplier is 20 bits so 64 - 20 - 1 = 43 bits before overflow. A bit less than above, and I am not sure what the 40-bit hw counter overflow period is there to start with? Is 8 times that enough? Or not?

Off the top of my head, 8 hours. Definitely within a timescale that someone could be monitoring.

Quoted 1 line

Suggestions?

We can extend to uint128_t quite easily on 64b platforms (hmm, but how much is allowed for freestanding?), otherwise time to whip up a 128b math library ;)
https://cgit.freedesktop.org/cairo/tree/src/cairo-wideint.c

u64_mul_u64_u32_div_u32_roundup ?
-Chris
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

author maintainer
#5 lore raw

PATCH v4 1/1 drm/i915: Handle RC6 counter wrap

In reply to Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 72 +++++++++++++++++++++++++++++++++++------
 2 files changed, 64 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
 };
 
 struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +62 -10

116 lines not on this page · raw message

Signature · 6 lines
2.14.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#6 lore raw
Quoted 160 lines · Tvrtko Ursulin

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
---
  drivers/gpu/drm/i915/i915_drv.h |  2 ++
  drivers/gpu/drm/i915/intel_pm.c | 72 +++++++++++++++++++++++++++++++++++------
  2 files changed, 64 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
  struct intel_rc6 {
  	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
  };
 
  struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +52 -10
index 41f26ab46501..24d9423c5f9e 100644
@@ -9417,15 +9417,16 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
  			     const i915_reg_t reg)
  {
  	u32 lower, upper, tmp;
-	unsigned long flags;
  	int loop = 2;
 
-	/* The register accessed do not need forcewake. We borrow
+	/*
+	 * The register accessed do not need forcewake. We borrow
  	 * uncore lock to prevent concurrent access to range reg.
  	 */
-	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	lockdep_assert_held(&dev_priv->uncore.lock);
 
-	/* vlv and chv residency counters are 40 bits in width.
+	/*
+	 * vlv and chv residency counters are 40 bits in width.
  	 * With a control bit, we can choose between upper or lower
  	 * 32bit window into this counter.
  	 *
@@ -9449,29 +9450,54 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
  		upper = I915_READ_FW(reg);
  	} while (upper != tmp && --loop);
 
-	/* Everywhere else we always use VLV_COUNTER_CONTROL with the
+	/*
+	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
  	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
  	 * now.
  	 */
 
-	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
  	return lower | (u64)upper << 8;
  }
 
  u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
  			   const i915_reg_t reg)
  {
-	u64 time_hw;
+#if IS_ENABLED(CONFIG_ARCH_SUPPORTS_INT128)
+	unsigned __int128 acc;
+#else
+	u64 acc;
+#endif
+	u64 time_hw, prev_hw, overflow_hw;
+	unsigned int fw_domains;
+	unsigned long flags;
+	unsigned int i;
  	u32 mul, div;
 
  	if (!HAS_RC6(dev_priv))
  		return 0;
 
+	/*
+	 * Store previous hw counter values for counter wrap-around handling.
+	 *
+	 * There are only four interesting registers and they live next to each
+	 * other so we can use the relative address, compared to the smallest
+	 * one as the index into driver storage.
+	 */
+	i = (i915_mmio_reg_offset(reg) -
+	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+	if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
+		return 0;
+
+	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+
  	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
  	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
  		mul = 1000000;
  		div = dev_priv->czclk_freq;
+		overflow_hw = BIT_ULL(40);
  		time_hw = vlv_residency_raw(dev_priv, reg);
  	} else {
  		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
@@ -9483,10 +9509,36 @@ u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
  			div = 1;
  		}
 
-		time_hw = I915_READ(reg);
+		overflow_hw = BIT_ULL(32);
+		time_hw = I915_READ_FW(reg);
  	}
 
-	return DIV_ROUND_UP_ULL(time_hw * mul, div);
+	/*
+	 * Counter wrap handling.
+	 *
+	 * But relying on a sufficient frequency of queries otherwise counters
+	 * can still wrap.
+	 */
+	prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
+	dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
+
+	/* RC6 delta from last sample. */
+	if (time_hw >= prev_hw)
+		time_hw -= prev_hw;
+	else
+		time_hw += overflow_hw - prev_hw;
+
+	/* Add delta to RC6 extended raw driver copy. */

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9541

Quoted 10 lines
drivers/gpu/drm/i915/intel_pm.c +10 -0
+	time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
+	dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
+
+	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
+	acc = time_hw;
+	acc *= mul;
+
+	return DIV_ROUND_UP_ULL(acc, div);

Nope, this casts to 64-bit before division..

Regards,

Tvrtko

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9544

Quoted 4 lines
drivers/gpu/drm/i915/intel_pm.c +0 -0
  }
 
  u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#7 lore raw
In reply to Tvrtko Ursulin

Quoting Tvrtko Ursulin (2018-02-08 15:46:38)

Quoted 160 lines

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 72 +++++++++++++++++++++++++++++++++++------
 2 files changed, 64 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
 struct intel_rc6 {
        bool enabled;
+       u64 prev_hw_residency[4];
+       u64 cur_residency[4];
 };
 
 struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +52 -10
index 41f26ab46501..24d9423c5f9e 100644
@@ -9417,15 +9417,16 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
                             const i915_reg_t reg)
 {
        u32 lower, upper, tmp;
-       unsigned long flags;
        int loop = 2;
 
-       /* The register accessed do not need forcewake. We borrow
+       /*
+        * The register accessed do not need forcewake. We borrow
         * uncore lock to prevent concurrent access to range reg.
         */
-       spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+       lockdep_assert_held(&dev_priv->uncore.lock);
 
-       /* vlv and chv residency counters are 40 bits in width.
+       /*
+        * vlv and chv residency counters are 40 bits in width.
         * With a control bit, we can choose between upper or lower
         * 32bit window into this counter.
         *
@@ -9449,29 +9450,54 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
                upper = I915_READ_FW(reg);
        } while (upper != tmp && --loop);
 
-       /* Everywhere else we always use VLV_COUNTER_CONTROL with the
+       /*
+        * Everywhere else we always use VLV_COUNTER_CONTROL with the
         * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
         * now.
         */
 
-       spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
-
        return lower | (u64)upper << 8;
 }
 
 u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
                           const i915_reg_t reg)
 {
-       u64 time_hw;
+#if IS_ENABLED(CONFIG_ARCH_SUPPORTS_INT128)
+       unsigned __int128 acc;
+#else
+       u64 acc;
+#endif
+       u64 time_hw, prev_hw, overflow_hw;
+       unsigned int fw_domains;
+       unsigned long flags;
+       unsigned int i;
        u32 mul, div;
 
        if (!HAS_RC6(dev_priv))
                return 0;
 
+       /*
+        * Store previous hw counter values for counter wrap-around handling.
+        *
+        * There are only four interesting registers and they live next to each
+        * other so we can use the relative address, compared to the smallest
+        * one as the index into driver storage.
+        */
+       i = (i915_mmio_reg_offset(reg) -
+            i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+       if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
+               return 0;
+
+       fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
+
+       spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+       intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
+
        /* On VLV and CHV, residency time is in CZ units rather than 1.28us */
        if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
                mul = 1000000;
                div = dev_priv->czclk_freq;
+               overflow_hw = BIT_ULL(40);
                time_hw = vlv_residency_raw(dev_priv, reg);
        } else {
                /* 833.33ns units on Gen9LP, 1.28us elsewhere. */
@@ -9483,10 +9509,36 @@ u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
                        div = 1;
                }
 
-               time_hw = I915_READ(reg);
+               overflow_hw = BIT_ULL(32);
+               time_hw = I915_READ_FW(reg);
        }
 
-       return DIV_ROUND_UP_ULL(time_hw * mul, div);
+       /*
+        * Counter wrap handling.
+        *
+        * But relying on a sufficient frequency of queries otherwise counters
+        * can still wrap.
+        */
+       prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
+       dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
+
+       /* RC6 delta from last sample. */
+       if (time_hw >= prev_hw)
+               time_hw -= prev_hw;
+       else
+               time_hw += overflow_hw - prev_hw;
+
+       /* Add delta to RC6 extended raw driver copy. */

drivers/gpu/drm/i915/intel_pm.c u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, · line 9541

Quoted 10 lines
drivers/gpu/drm/i915/intel_pm.c +10 -0
+       time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
+       dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
+
+       intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
+       spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
+       acc = time_hw;
+       acc *= mul;
+
+       return DIV_ROUND_UP_ULL(acc, div);

return mul_u64_u32_div(time_hw, mul, div).

Loses roundup. But meh.
-Chris
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

author maintainer
#8 lore raw

PATCH v5 1/1 drm/i915: Handle RC6 counter wrap

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

v5:
* Use mul_u64_u32_div. (Chris Wilson)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 64 ++++++++++++++++++++++++++++++++++-------
 2 files changed, 56 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -0
index ad1fc845cd1b..28a2671a26c7 100644
@@ -946,6 +946,8 @@ struct intel_rps {
 
 struct intel_rc6 {
 	bool enabled;
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
 };
 
 struct intel_llc_pstate {
drivers/gpu/drm/i915/intel_pm.c +54 -10

108 lines not on this page · raw message

Signature · 6 lines
2.14.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v5 1/1
#9 lore raw

Quoting Tvrtko Ursulin (2018-02-08 16:00:36)

Quoted 27 lines

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

Quoted 8 lines

v5:
* Use mul_u64_u32_div. (Chris Wilson)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>

Ville better not complain he liked the round up behaviour :-p -Chris
_______________________________________________
Intel-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#10 lore raw
Quoted 37 lines · Chris Wilson

Quoting Tvrtko Ursulin (2018-02-08 16:00:36)

Quoted 27 lines

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

Quoted 8 lines

v5:
* Use mul_u64_u32_div. (Chris Wilson)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
Quoted 3 lines

Ville better not complain he liked the round up behaviour :-p

Ping Ville - ack?

Regards,

Tvrtko

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#11 lore raw
Quoted 39 lines · Tvrtko Ursulin
Quoted 37 lines · Chris Wilson

Quoting Tvrtko Ursulin (2018-02-08 16:00:36)

Quoted 35 lines

From: Tvrtko Ursulin <[email protected]>

We can implement limited RC6 counter wrap-around protection under the assumption that clients will be reading this value more frequently than the wrap period on a given platform.

With the typical wrap-around period being ~90 minutes, even with the exception of Baytrail which wraps every 13 seconds, this sounds like a reasonable assumption.

Implementation works by storing a 64-bit software copy of a hardware RC6 counter, along with the previous HW counter snapshot. This enables it to detect wrap is polled frequently enough and keep the software copy monotonically incrementing.

v2:
* Missed GEN6_GT_GFX_RC6_LOCKED when considering slot sizing and indexing.
* Fixed off-by-one in wrap-around handling. (Chris Wilson)

v3:
* Simplify index checking by using unsigned int. (Chris Wilson)
* Expand the comment to explain why indexing works.

v4:
* Use __int128 if supported.

v5:
* Use mul_u64_u32_div. (Chris Wilson)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94852

Cc Chris Wilson <[email protected]>
Cc Ville Syrjälä <[email protected]>
Quoted 5 lines
Quoted 3 lines

Ville better not complain he liked the round up behaviour :-p

Ping Ville - ack?

ack

Signature · 6 lines
Ville Syrjälä
Intel OTC
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#12 lore raw

✓ Fi.CI.BAT: success for drm/i915: Handle RC6 counter wrap (rev3)

In reply to a message not in the archive
== Series Details ==

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev3)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Series 37824v3 drm/i915: Handle RC6 counter wrap
https://patchwork.freedesktop.org/api/1.0/series/37824/revisions/3/mbox/

Test debugfs_test:

        Subgroup read_all_entries:
                incomplete -> PASS       (fi-snb-2520m) fdo#103713 +1
Test gem_mmap_gtt:
        Subgroup basic-small-bo-tiledx:
                pass       -> FAIL       (fi-gdg-551) fdo#102575

fdo#103713 https://bugs.freedesktop.org/show_bug.cgi?id=103713
fdo#102575 https://bugs.freedesktop.org/show_bug.cgi?id=102575

fi-bdw-5557u     total:288  pass:267  dwarn:0   dfail:0   fail:0   skip:21  time:417s
fi-bdw-gvtdvm    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:423s
fi-blb-e6850     total:288  pass:223  dwarn:1   dfail:0   fail:0   skip:64  time:374s
fi-bsw-n3050     total:288  pass:242  dwarn:0   dfail:0   fail:0   skip:46  time:484s
fi-bwr-2160      total:288  pass:183  dwarn:0   dfail:0   fail:0   skip:105 time:284s
fi-bxt-dsi       total:288  pass:258  dwarn:0   dfail:0   fail:0   skip:30  time:484s
fi-bxt-j4205     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:483s
fi-byt-j1900     total:288  pass:253  dwarn:0   dfail:0   fail:0   skip:35  time:470s
fi-byt-n2820     total:288  pass:249  dwarn:0   dfail:0   fail:0   skip:39  time:456s
fi-cfl-s2        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:564s
fi-cnl-y3        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:583s
fi-elk-e7500     total:288  pass:229  dwarn:0   dfail:0   fail:0   skip:59  time:417s
fi-gdg-551       total:288  pass:179  dwarn:0   dfail:0   fail:1   skip:108 time:280s
fi-glk-1         total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:511s
fi-hsw-4770      total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:388s
fi-ilk-650       total:288  pass:228  dwarn:0   dfail:0   fail:0   skip:60  time:413s
fi-ivb-3520m     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:457s
fi-ivb-3770      total:288  pass:255  dwarn:0   dfail:0   fail:0   skip:33  time:415s
fi-kbl-7500u     total:288  pass:263  dwarn:1   dfail:0   fail:0   skip:24  time:456s
fi-kbl-7560u     total:288  pass:269  dwarn:0   dfail:0   fail:0   skip:19  time:496s
fi-kbl-7567u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:452s
fi-kbl-r         total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:508s
fi-pnv-d510      total:288  pass:222  dwarn:1   dfail:0   fail:0   skip:65  time:601s
fi-skl-6260u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:437s
fi-skl-6600u     total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:505s
fi-skl-6700hq    total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:525s
fi-skl-6700k2    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:486s
fi-skl-6770hq    total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:484s
fi-skl-guc       total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:416s
fi-skl-gvtdvm    total:288  pass:265  dwarn:0   dfail:0   fail:0   skip:23  time:428s
fi-snb-2520m     total:245  pass:211  dwarn:0   dfail:0   fail:0   skip:33 
fi-snb-2600      total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:398s

Blacklisted hosts:
fi-glk-dsi total:288 pass:258 dwarn:0 dfail:0 fail:0 skip:30 time:473s

ede4b1ac40b2c32511532ddb6849b11c0183020e drm-tip: 2018y-02m-08d-07h-43m-06s UTC integration manifest 918da7b9c87b drm/i915: Handle RC6 counter wrap

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_7939/issues.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#13 lore raw

✓ Fi.CI.IGT: success for drm/i915: Handle RC6 counter wrap (rev3)

In reply to a message not in the archive
== Series Details ==

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev3)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Test kms_cursor_legacy:

        Subgroup cursor-vs-flip-legacy:
                pass       -> FAIL       (shard-apl) fdo#103355
Test gem_eio:
        Subgroup in-flight-contexts:
                pass       -> FAIL       (shard-hsw) fdo#104676
Test drv_suspend:
        Subgroup debugfs-reader:
                pass       -> SKIP       (shard-snb) fdo#102365
Test kms_flip:
        Subgroup flip-vs-panning-vs-hang-interruptible:
                dmesg-warn -> PASS       (shard-snb) fdo#103821
        Subgroup plain-flip-fb-recreate-interruptible:
                fail       -> PASS       (shard-hsw) fdo#100368
Test kms_plane:
        Subgroup plane-panning-bottom-right-suspend-pipe-b-planes:
                pass       -> SKIP       (shard-hsw) fdo#103540
Test testdisplay:
                pass       -> DMESG-WARN (shard-apl) fdo#104727
Test kms_frontbuffer_tracking:
        Subgroup fbc-1p-offscren-pri-indfb-draw-blt:
                pass       -> FAIL       (shard-apl) fdo#101623
        Subgroup fbc-tilingchange:
                pass       -> FAIL       (shard-apl) fdo#103167

fdo#103355 https://bugs.freedesktop.org/show_bug.cgi?id=103355
fdo#104676 https://bugs.freedesktop.org/show_bug.cgi?id=104676
fdo#102365 https://bugs.freedesktop.org/show_bug.cgi?id=102365
fdo#103821 https://bugs.freedesktop.org/show_bug.cgi?id=103821
fdo#100368 https://bugs.freedesktop.org/show_bug.cgi?id=100368
fdo#103540 https://bugs.freedesktop.org/show_bug.cgi?id=103540
fdo#104727 https://bugs.freedesktop.org/show_bug.cgi?id=104727
fdo#101623 https://bugs.freedesktop.org/show_bug.cgi?id=101623
fdo#103167 https://bugs.freedesktop.org/show_bug.cgi?id=103167

shard-apl        total:3354 pass:1735 dwarn:2   dfail:0   fail:22  skip:1594 time:12408s
shard-hsw        total:3444 pass:1758 dwarn:1   dfail:0   fail:12  skip:1672 time:11835s
shard-snb        total:3444 pass:1349 dwarn:1   dfail:0   fail:10  skip:2084 time:6533s

Blacklisted hosts:
shard-kbl total:3380 pass:1871 dwarn:8 dfail:3 fail:19 skip:1478 time:9415s

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_7939/shards.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#14 lore raw

✓ Fi.CI.BAT: success for drm/i915: Handle RC6 counter wrap (rev4)

In reply to a message not in the archive
== Series Details ==

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev4)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Series 37824v4 drm/i915: Handle RC6 counter wrap
https://patchwork.freedesktop.org/api/1.0/series/37824/revisions/4/mbox/

Test kms_pipe_crc_basic:

        Subgroup suspend-read-crc-pipe-a:
                pass       -> INCOMPLETE (fi-bdw-5557u) fdo#104944

fdo#104944 https://bugs.freedesktop.org/show_bug.cgi?id=104944

fi-bdw-5557u     total:244  pass:226  dwarn:0   dfail:0   fail:0   skip:17 
fi-bdw-gvtdvm    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:422s
fi-blb-e6850     total:288  pass:223  dwarn:1   dfail:0   fail:0   skip:64  time:375s
fi-bsw-n3050     total:288  pass:242  dwarn:0   dfail:0   fail:0   skip:46  time:492s
fi-bwr-2160      total:288  pass:183  dwarn:0   dfail:0   fail:0   skip:105 time:286s
fi-bxt-dsi       total:288  pass:258  dwarn:0   dfail:0   fail:0   skip:30  time:485s
fi-bxt-j4205     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:484s
fi-byt-j1900     total:288  pass:253  dwarn:0   dfail:0   fail:0   skip:35  time:466s
fi-byt-n2820     total:288  pass:249  dwarn:0   dfail:0   fail:0   skip:39  time:455s
fi-cfl-s2        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:569s
fi-cnl-y3        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:575s
fi-elk-e7500     total:288  pass:229  dwarn:0   dfail:0   fail:0   skip:59  time:414s
fi-gdg-551       total:288  pass:179  dwarn:0   dfail:0   fail:1   skip:108 time:285s
fi-glk-1         total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:509s
fi-hsw-4770      total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:388s
fi-ilk-650       total:288  pass:228  dwarn:0   dfail:0   fail:0   skip:60  time:412s
fi-ivb-3520m     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:461s
fi-ivb-3770      total:288  pass:255  dwarn:0   dfail:0   fail:0   skip:33  time:419s
fi-kbl-7500u     total:288  pass:263  dwarn:1   dfail:0   fail:0   skip:24  time:456s
fi-kbl-7560u     total:288  pass:269  dwarn:0   dfail:0   fail:0   skip:19  time:497s
fi-kbl-7567u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:454s
fi-kbl-r         total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:503s
fi-pnv-d510      total:288  pass:222  dwarn:1   dfail:0   fail:0   skip:65  time:601s
fi-skl-6260u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:428s
fi-skl-6600u     total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:506s
fi-skl-6700hq    total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:523s
fi-skl-6700k2    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:488s
fi-skl-6770hq    total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:481s
fi-skl-guc       total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:412s
fi-skl-gvtdvm    total:288  pass:265  dwarn:0   dfail:0   fail:0   skip:23  time:427s
fi-snb-2520m     total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:528s
fi-snb-2600      total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:393s

Blacklisted hosts:
fi-glk-dsi total:288 pass:258 dwarn:0 dfail:0 fail:0 skip:30 time:471s

ead13f6504ef40dfb905830e57360f461f6803c3 drm-tip: 2018y-02m-08d-13h-43m-51s UTC integration manifest 58fbc88124eb drm/i915: Handle RC6 counter wrap

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_7955/issues.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#15 lore raw

✓ Fi.CI.BAT: success for drm/i915: Handle RC6 counter wrap (rev5)

In reply to a message not in the archive
== Series Details ==

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev5)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Series 37824v5 drm/i915: Handle RC6 counter wrap
https://patchwork.freedesktop.org/api/1.0/series/37824/revisions/5/mbox/

Test gem_exec_suspend:

        Subgroup basic-s4-devices:
                pass       -> INCOMPLETE (fi-bdw-5557u) fdo#104162
Test kms_pipe_crc_basic:
        Subgroup suspend-read-crc-pipe-a:
                pass       -> INCOMPLETE (fi-hsw-4770) fdo#103375
        Subgroup suspend-read-crc-pipe-c:
                pass       -> DMESG-WARN (fi-cnl-y3) fdo#104951

fdo#104162 https://bugs.freedesktop.org/show_bug.cgi?id=104162
fdo#103375 https://bugs.freedesktop.org/show_bug.cgi?id=103375
fdo#104951 https://bugs.freedesktop.org/show_bug.cgi?id=104951

fi-bdw-5557u     total:109  pass:105  dwarn:0   dfail:0   fail:0   skip:3  
fi-bdw-gvtdvm    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:422s
fi-blb-e6850     total:288  pass:223  dwarn:1   dfail:0   fail:0   skip:64  time:381s
fi-bsw-n3050     total:288  pass:242  dwarn:0   dfail:0   fail:0   skip:46  time:488s
fi-bwr-2160      total:288  pass:183  dwarn:0   dfail:0   fail:0   skip:105 time:286s
fi-bxt-dsi       total:288  pass:258  dwarn:0   dfail:0   fail:0   skip:30  time:482s
fi-bxt-j4205     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:488s
fi-byt-j1900     total:288  pass:253  dwarn:0   dfail:0   fail:0   skip:35  time:471s
fi-byt-n2820     total:288  pass:249  dwarn:0   dfail:0   fail:0   skip:39  time:456s
fi-cfl-s2        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:558s
fi-cnl-y3        total:288  pass:261  dwarn:1   dfail:0   fail:0   skip:26  time:571s
fi-elk-e7500     total:288  pass:229  dwarn:0   dfail:0   fail:0   skip:59  time:416s
fi-gdg-551       total:288  pass:179  dwarn:0   dfail:0   fail:1   skip:108 time:285s
fi-glk-1         total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:510s
fi-hsw-4770      total:244  pass:220  dwarn:0   dfail:0   fail:0   skip:23 
fi-ilk-650       total:288  pass:228  dwarn:0   dfail:0   fail:0   skip:60  time:413s
fi-ivb-3520m     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:458s
fi-ivb-3770      total:288  pass:255  dwarn:0   dfail:0   fail:0   skip:33  time:413s
fi-kbl-7500u     total:288  pass:263  dwarn:1   dfail:0   fail:0   skip:24  time:457s
fi-kbl-7560u     total:288  pass:269  dwarn:0   dfail:0   fail:0   skip:19  time:493s
fi-kbl-7567u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:460s
fi-kbl-r         total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:499s
fi-pnv-d510      total:288  pass:222  dwarn:1   dfail:0   fail:0   skip:65  time:596s
fi-skl-6260u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:424s
fi-skl-6600u     total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:506s
fi-skl-6700hq    total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:525s
fi-skl-6700k2    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:482s
fi-skl-6770hq    total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:480s
fi-skl-guc       total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:414s
fi-skl-gvtdvm    total:288  pass:265  dwarn:0   dfail:0   fail:0   skip:23  time:430s
fi-snb-2520m     total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:529s
fi-snb-2600      total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:399s

Blacklisted hosts:
fi-glk-dsi total:288 pass:258 dwarn:0 dfail:0 fail:0 skip:30 time:468s

ead13f6504ef40dfb905830e57360f461f6803c3 drm-tip: 2018y-02m-08d-13h-43m-51s UTC integration manifest a540ad853d1e drm/i915: Handle RC6 counter wrap

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_7956/issues.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#16 lore raw

Re: ✓ Fi.CI.BAT: success for drm/i915: Handle RC6 counter wrap (rev5)

Quoted 56 lines · Patchwork

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev5)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Series 37824v5 drm/i915: Handle RC6 counter wrap
https://patchwork.freedesktop.org/api/1.0/series/37824/revisions/5/mbox/

Test gem_exec_suspend:

         Subgroup basic-s4-devices:
                 pass       -> INCOMPLETE (fi-bdw-5557u) fdo#104162
Test kms_pipe_crc_basic:
         Subgroup suspend-read-crc-pipe-a:
                 pass       -> INCOMPLETE (fi-hsw-4770) fdo#103375
         Subgroup suspend-read-crc-pipe-c:
                 pass       -> DMESG-WARN (fi-cnl-y3) fdo#104951

fdo#104162 https://bugs.freedesktop.org/show_bug.cgi?id=104162
fdo#103375 https://bugs.freedesktop.org/show_bug.cgi?id=103375
fdo#104951 https://bugs.freedesktop.org/show_bug.cgi?id=104951

fi-bdw-5557u     total:109  pass:105  dwarn:0   dfail:0   fail:0   skip:3
fi-bdw-gvtdvm    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:422s
fi-blb-e6850     total:288  pass:223  dwarn:1   dfail:0   fail:0   skip:64  time:381s
fi-bsw-n3050     total:288  pass:242  dwarn:0   dfail:0   fail:0   skip:46  time:488s
fi-bwr-2160      total:288  pass:183  dwarn:0   dfail:0   fail:0   skip:105 time:286s
fi-bxt-dsi       total:288  pass:258  dwarn:0   dfail:0   fail:0   skip:30  time:482s
fi-bxt-j4205     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:488s
fi-byt-j1900     total:288  pass:253  dwarn:0   dfail:0   fail:0   skip:35  time:471s
fi-byt-n2820     total:288  pass:249  dwarn:0   dfail:0   fail:0   skip:39  time:456s
fi-cfl-s2        total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:558s
fi-cnl-y3        total:288  pass:261  dwarn:1   dfail:0   fail:0   skip:26  time:571s
fi-elk-e7500     total:288  pass:229  dwarn:0   dfail:0   fail:0   skip:59  time:416s
fi-gdg-551       total:288  pass:179  dwarn:0   dfail:0   fail:1   skip:108 time:285s
fi-glk-1         total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:510s
fi-hsw-4770      total:244  pass:220  dwarn:0   dfail:0   fail:0   skip:23
fi-ilk-650       total:288  pass:228  dwarn:0   dfail:0   fail:0   skip:60  time:413s
fi-ivb-3520m     total:288  pass:259  dwarn:0   dfail:0   fail:0   skip:29  time:458s
fi-ivb-3770      total:288  pass:255  dwarn:0   dfail:0   fail:0   skip:33  time:413s
fi-kbl-7500u     total:288  pass:263  dwarn:1   dfail:0   fail:0   skip:24  time:457s
fi-kbl-7560u     total:288  pass:269  dwarn:0   dfail:0   fail:0   skip:19  time:493s
fi-kbl-7567u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:460s
fi-kbl-r         total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:499s
fi-pnv-d510      total:288  pass:222  dwarn:1   dfail:0   fail:0   skip:65  time:596s
fi-skl-6260u     total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:424s
fi-skl-6600u     total:288  pass:261  dwarn:0   dfail:0   fail:0   skip:27  time:506s
fi-skl-6700hq    total:288  pass:262  dwarn:0   dfail:0   fail:0   skip:26  time:525s
fi-skl-6700k2    total:288  pass:264  dwarn:0   dfail:0   fail:0   skip:24  time:482s
fi-skl-6770hq    total:288  pass:268  dwarn:0   dfail:0   fail:0   skip:20  time:480s
fi-skl-guc       total:288  pass:260  dwarn:0   dfail:0   fail:0   skip:28  time:414s
fi-skl-gvtdvm    total:288  pass:265  dwarn:0   dfail:0   fail:0   skip:23  time:430s
fi-snb-2520m     total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:529s
fi-snb-2600      total:288  pass:248  dwarn:0   dfail:0   fail:0   skip:40  time:399s
Quoted 5 lines

Blacklisted hosts:
fi-glk-dsi total:288 pass:258 dwarn:0 dfail:0 fail:0 skip:30 time:468s

ead13f6504ef40dfb905830e57360f461f6803c3 drm-tip: 2018y-02m-08d-13h-43m-51s UTC integration manifest a540ad853d1e drm/i915: Handle RC6 counter wrap

Pushed, thanks for the review!

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#17 lore raw

✓ Fi.CI.IGT: success for drm/i915: Handle RC6 counter wrap (rev5)

In reply to a message not in the archive
== Series Details ==

== Series Details ==

Series: drm/i915: Handle RC6 counter wrap (rev5)
URL : https://patchwork.freedesktop.org/series/37824/
State : success

== Summary ==

Test gem_eio:

        Subgroup in-flight-contexts:
                pass       -> FAIL       (shard-hsw) fdo#104676 +1
Test kms_cursor_crc:
        Subgroup cursor-64x64-suspend:
                pass       -> FAIL       (shard-snb) fdo#102365 +1
Test kms_cursor_legacy:
        Subgroup cursor-vs-flip-legacy:
                fail       -> PASS       (shard-apl) fdo#103355
Test gem_exec_suspend:
        Subgroup basic-s4:
                fail       -> SKIP       (shard-snb) fdo#103375

fdo#104676 https://bugs.freedesktop.org/show_bug.cgi?id=104676
fdo#102365 https://bugs.freedesktop.org/show_bug.cgi?id=102365
fdo#103355 https://bugs.freedesktop.org/show_bug.cgi?id=103355
fdo#103375 https://bugs.freedesktop.org/show_bug.cgi?id=103375

shard-apl        total:3354 pass:1738 dwarn:1   dfail:0   fail:20  skip:1594 time:12346s
shard-hsw        total:3444 pass:1760 dwarn:1   dfail:0   fail:11  skip:1671 time:11820s
shard-snb        total:3444 pass:1350 dwarn:1   dfail:0   fail:10  skip:2083 time:6528s

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_7956/shards.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx