From 90aca4d2740255bd130ea71a91530b9920c70abe Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Tue, 9 Mar 2010 14:45:12 +0000 Subject: drm/radeon/kms: simplify & improve GPU reset V2 This simplify and improve GPU reset for R1XX-R6XX hw, it's not 100% reliable here are result: - R1XX/R2XX works bunch of time in a row, sometimes it seems it can work indifinitly - R3XX/R3XX the most unreliable one, sometimes you will be able to reset few times, sometimes not even once - R5XX more reliable than previous hw, seems to work most of the times but once in a while it fails for no obvious reasons (same status than previous reset just no same happy ending) - R6XX/R7XX are lot more reliable with this patch, still it seems that it can fail after a bunch (reset every 2sec for 3hour bring down the GPU & computer) This have been tested on various hw, for some odd reasons i wasn't able to lockup RS480/RS690 (while they use to love locking up). Note that on R1XX-R5XX the cursor will disapear after lockup haven't checked why, switch to console and back to X will restore cursor. Next step is to record the bogus command that leaded to the lockup. V2 Fix r6xx resume path to avoid reinitializing blit module, use the gpu_lockup boolean to avoid entering inifinite waiting loop on fence while reiniting the GPU Signed-off-by: Jerome Glisse Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_fence.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'drivers/gpu/drm/radeon/radeon_fence.c') diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 2560740ff92..fcd7802d8a7 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -209,8 +209,9 @@ retry: r = wait_event_interruptible_timeout(rdev->fence_drv.queue, radeon_fence_signaled(fence), timeout); radeon_irq_kms_sw_irq_put(rdev); - if (unlikely(r < 0)) + if (unlikely(r < 0)) { return r; + } } else { radeon_irq_kms_sw_irq_get(rdev); r = wait_event_timeout(rdev->fence_drv.queue, @@ -230,14 +231,16 @@ retry: */ if (seq == rdev->fence_drv.last_seq && radeon_gpu_is_lockup(rdev)) { /* good news we believe it's a lockup */ - dev_warn(rdev->dev, "GPU lockup (last fence id 0x%08X)\n", seq); - r = radeon_asic_reset(rdev); - if (r) - return r; + WARN(1, "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n", fence->seq, seq); /* FIXME: what should we do ? marking everyone * as signaled for now */ + rdev->gpu_lockup = true; WREG32(rdev->fence_drv.scratch_reg, fence->seq); + r = radeon_gpu_reset(rdev); + if (r) + return r; + rdev->gpu_lockup = false; } timeout = RADEON_FENCE_JIFFIES_TIMEOUT; write_lock_irqsave(&rdev->fence_drv.lock, irq_flags); -- cgit v1.2.3-70-g09d2