diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 44f747c78128ac49034cf0dde03ae2fe7ec0ae9d..e68265b6fb46769bb864a31ff4c7bd54f8de7380 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1146,14 +1146,57 @@ static bool missed_irq(struct drm_i915_private *dev_priv, return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings); } +static unsigned long local_clock_us(unsigned *cpu) +{ + unsigned long t; + + /* Cheaply and approximately convert from nanoseconds to microseconds. + * The result and subsequent calculations are also defined in the same + * approximate microseconds units. The principal source of timing + * error here is from the simple truncation. + * + * Note that local_clock() is only defined wrt to the current CPU; + * the comparisons are no longer valid if we switch CPUs. Instead of + * blocking preemption for the entire busywait, we can detect the CPU + * switch and use that as indicator of system load and a reason to + * stop busywaiting, see busywait_stop(). + */ + *cpu = get_cpu(); + t = local_clock() >> 10; + put_cpu(); + + return t; +} + +static bool busywait_stop(unsigned long timeout, unsigned cpu) +{ + unsigned this_cpu; + + if (time_after(local_clock_us(&this_cpu), timeout)) + return true; + + return this_cpu != cpu; +} + static int __i915_spin_request(struct drm_i915_gem_request *req, int state) { unsigned long timeout; + unsigned cpu; + + /* When waiting for high frequency requests, e.g. during synchronous + * rendering split between the CPU and GPU, the finite amount of time + * required to set up the irq and wait upon it limits the response + * rate. By busywaiting on the request completion for a short while we + * can service the high frequency waits as quick as possible. However, + * if it is a slow request, we want to sleep as quickly as possible. + * The tradeoff between waiting and sleeping is roughly the time it + * takes to sleep on a request, on the order of a microsecond. + */ if (i915_gem_request_get_ring(req)->irq_refcount) return -EBUSY; - timeout = jiffies + 1; + timeout = local_clock_us(&cpu) + 5; while (!need_resched()) { if (i915_gem_request_completed(req, true)) return 0; @@ -1161,7 +1204,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state) if (signal_pending_state(state, current)) break; - if (time_after_eq(jiffies, timeout)) + if (busywait_stop(timeout, cpu)) break; cpu_relax_lowlatency();