From 899f6204c0f8117d33226e586d3a630b3cf9bce0 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 21 Mar 2017 11:33:20 +0000 Subject: [PATCH] drm/i915/execlists: Split the atomic test_and_clear_bit for irq handler Rather than impose the cost of a locked test before queuing a new request, reduce it to a simple test_bit() with a following clear_bit() prior to doing the CSB check. This ensure that if an interrupt does occur whilst reading from the CSB, we still detect it (the interrupt would trigger a rescheduling of the tasklet anyway). Signed-off-by: Chris Wilson Link: http://patchwork.freedesktop.org/patch/msgid/20170321113320.2603-1-chris@chris-wilson.co.uk Reviewed-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/intel_lrc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index dab73e7d9a6b..a88380876ce9 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -530,13 +530,18 @@ static void intel_lrc_irq_handler(unsigned long data) intel_uncore_forcewake_get(dev_priv, engine->fw_domains); - while (test_and_clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) { + /* Prefer doing test_and_clear_bit() as a two stage operation to avoid + * imposing the cost of a locked atomic transaction when submitting a + * new request (outside of the context-switch interrupt). + */ + while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) { u32 __iomem *csb_mmio = dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)); u32 __iomem *buf = dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)); unsigned int csb, head, tail; + clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); csb = readl(csb_mmio); head = GEN8_CSB_READ_PTR(csb); tail = GEN8_CSB_WRITE_PTR(csb);