diff options
| author |   Chris Wilson <chris@chris-wilson.co.uk> | 2020-01-28 20:43:15 +0000 |
|---|---|---|
| committer | Chris Wilson <chris@chris-wilson.co.uk> | 2020-01-29 15:16:52 +0000 |
| commit | 70a76a9b8e9d553c02deaf8503cd01a316016be0 (patch) | |
| tree | e547bf99e3a9f96c0739357696410aeac962b8be /drivers/gpu/drm/i915/gt/intel_gt_irq.c | |
| parent | drm/i915/execlist: Mark up racy read of execlists->pending[0] (diff) | |
| download | wireguard-linux-70a76a9b8e9d553c02deaf8503cd01a316016be0.tar.xz wireguard-linux-70a76a9b8e9d553c02deaf8503cd01a316016be0.zip | |
drm/i915/gt: Hook up CS_MASTER_ERROR_INTERRUPT
Now that we have offline error capture and can reset an engine from
inside an atomic context while also preserving the GPU state for
post-mortem analysis, it is time to handle error interrupts thrown by
the command parser.
This provides a much, much faster mechanism for us to detect known
problems than using heartbeats/hangchecks, and also provides a mechanism
for when those are disabled. However, it is limited to problems the HW
can detect in the CS and so not a complete solution for detecting lockups.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200128204318.4182039-2-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_gt_irq.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gt_irq.c | 27 |
1 files changed, 24 insertions, 3 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 7278b10e1a03..f0e7fd95165a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -24,6 +24,21 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) { bool tasklet = false; + if (unlikely(iir & GT_CS_MASTER_ERROR_INTERRUPT)) { + u32 eir; + + eir = ENGINE_READ(engine, RING_EIR); + ENGINE_TRACE(engine, "CS error: %x\n", eir); + + /* Disable the error interrupt until after the reset */ + if (likely(eir)) { + ENGINE_WRITE(engine, RING_EMR, ~0u); + ENGINE_WRITE(engine, RING_EIR, eir); + WRITE_ONCE(engine->execlists.error_interrupt, eir); + tasklet = true; + } + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -210,7 +225,10 @@ void gen11_gt_irq_reset(struct intel_gt *gt) void gen11_gt_irq_postinstall(struct intel_gt *gt) { - const u32 irqs = GT_RENDER_USER_INTERRUPT | GT_CONTEXT_SWITCH_INTERRUPT; + const u32 irqs = + GT_CS_MASTER_ERROR_INTERRUPT | + GT_RENDER_USER_INTERRUPT | + GT_CONTEXT_SWITCH_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -279,7 +297,7 @@ void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT | GT_BSD_CS_ERROR_INTERRUPT | - GT_RENDER_CS_MASTER_ERROR_INTERRUPT)) + GT_CS_MASTER_ERROR_INTERRUPT)) DRM_DEBUG("Command parser error, gt_iir 0x%08x\n", gt_iir); if (gt_iir & GT_PARITY_ERROR(gt->i915)) @@ -345,7 +363,10 @@ void gen8_gt_irq_reset(struct intel_gt *gt) void gen8_gt_irq_postinstall(struct intel_gt *gt) { /* These are interrupts we'll toggle with the ring mask register */ - const u32 irqs = GT_RENDER_USER_INTERRUPT | GT_CONTEXT_SWITCH_INTERRUPT; + const u32 irqs = + GT_CS_MASTER_ERROR_INTERRUPT | + GT_RENDER_USER_INTERRUPT | + GT_CONTEXT_SWITCH_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, |