We acquire the forcewake and use I915_READ_FW instead for the atomic
wait within intel_uncore_wait_for_register. However, this still leaves
us vulnerable to concurrent mmio access to the register, which can cause
system hangs on gen7. The protection is to acquire uncore.lock around
each register, so lets add it back.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Michal Wajdeczko <michal.wajdeczko@xxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/intel_uncore.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 53c8457869f6..d2ba3011c2f0 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1661,14 +1661,18 @@ int intel_wait_for_register(struct drm_i915_private *dev_priv,
u32 value,
unsigned int timeout_ms)
{
-
unsigned fw =
intel_uncore_forcewake_for_reg(dev_priv, reg, FW_REG_READ);
int ret;
- intel_uncore_forcewake_get(dev_priv, fw);
+ spin_lock_irq(&dev_priv->uncore.lock);
+ intel_uncore_forcewake_get__locked(dev_priv, fw);
+
ret = wait_for_us((I915_READ_FW(reg) & mask) == value, 2);
- intel_uncore_forcewake_put(dev_priv, fw);
+
+ intel_uncore_forcewake_put__locked(dev_priv, fw);
+ spin_unlock_irq(&dev_priv->uncore.lock);
+
if (ret)
ret = wait_for((I915_READ_NOTRACE(reg) & mask) == value,
timeout_ms);
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
