[Intel-gfx] [PATCH 2/2] drm/i915: Use wait_for_atomic_us when waiting for gt fifo

Mika Kuoppala mika.kuoppala at linux.intel.com
Tue May 2 14:03:44 UTC 2017


From: Mika Kuoppala <mika.kuoppala at linux.intel.com>

Replace the handcrafter loop when checking for fifo slots
with atomic wait for. This brings this wait in line with
the other waits on register access. We also get a readable
timeout constraint, so make it to fail after 10ms.

Chris suggested that we should fail silently as the fifo debug
handler, now attached to unclaimed mmio handling, will take care of the
possible errors at later stage.

Note that the decision to wait was changed so that we avoid
allocating the first reserved entry. Nor do we reduce the count
if we fail the wait, removing the possiblity to wrap the
count if the hw fifo returned zero.

v2: remove unclaimed check on timeout (Chris)
v3: use void return (Chris)

References: https://bugs.freedesktop.org/show_bug.cgi?id=100247
Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_uncore.c | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index ba7e9e8..aa9d306 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -29,6 +29,7 @@
 #include <linux/pm_runtime.h>
 
 #define FORCEWAKE_ACK_TIMEOUT_MS 50
+#define GT_FIFO_TIMEOUT_MS	 10
 
 #define __raw_posting_read(dev_priv__, reg__) (void)__raw_i915_read32((dev_priv__), (reg__))
 
@@ -179,30 +180,27 @@ static inline u32 fifo_free_entries(struct drm_i915_private *dev_priv)
 	return count & GT_FIFO_FREE_ENTRIES_MASK;
 }
 
-static int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
+static void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
 {
-	int ret = 0;
+	u32 n;
 
 	/* On VLV, FIFO will be shared by both SW and HW.
 	 * So, we need to read the FREE_ENTRIES everytime */
 	if (IS_VALLEYVIEW(dev_priv))
-		dev_priv->uncore.fifo_count = fifo_free_entries(dev_priv);
-
-	if (dev_priv->uncore.fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) {
-		int loop = 500;
-		u32 fifo = fifo_free_entries(dev_priv);
-
-		while (fifo <= GT_FIFO_NUM_RESERVED_ENTRIES && loop--) {
-			udelay(10);
-			fifo = fifo_free_entries(dev_priv);
+		n = fifo_free_entries(dev_priv);
+	else
+		n = dev_priv->uncore.fifo_count;
+
+	if (n <= GT_FIFO_NUM_RESERVED_ENTRIES) {
+		if (wait_for_atomic((n = fifo_free_entries(dev_priv)) >
+				    GT_FIFO_NUM_RESERVED_ENTRIES,
+				    GT_FIFO_TIMEOUT_MS)) {
+			DRM_DEBUG("GT_FIFO timeout, entries: %u\n", n);
+			return;
 		}
-		if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES))
-			++ret;
-		dev_priv->uncore.fifo_count = fifo;
 	}
-	dev_priv->uncore.fifo_count--;
 
-	return ret;
+	dev_priv->uncore.fifo_count = n - 1;
 }
 
 static enum hrtimer_restart
-- 
2.7.4



More information about the Intel-gfx mailing list