From 8830f26bcd3cf1ff07d9078cd310a534c03b6a10 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 2 Nov 2018 16:12:12 +0000 Subject: drm/i915: Prevent machine hang from Broxton's vtd w/a and error capture Since capturing the error state requires fiddling around with the GGTT to read arbitrary buffers and is itself run under stop_machine(), it deadlocks the machine (effectively a hard hang) when run in conjunction with Broxton's VTd workaround to serialize GGTT access. v2: Store the ERR_PTR in first_error so that the error can be reported to the user via sysfs. v3: Mention the quirk in dmesg (using info as per usual) Fixes: 0ef34ad6222a ("drm/i915: Serialize GTT/Aperture accesses on BXT") Signed-off-by: Chris Wilson Cc: Jon Bloomfield Cc: John Harrison Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: Daniel Vetter Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20181102161232.17742-5-chris@chris-wilson.co.uk (cherry picked from commit fb6f0b64e455b207a636346588e65bf9598d30eb) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_gpu_error.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'drivers/gpu/drm/i915/i915_gpu_error.c') diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8762d17b6659..3eb33e000d6f 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -648,6 +648,9 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, return 0; } + if (IS_ERR(error)) + return PTR_ERR(error); + if (*error->error_msg) err_printf(m, "%s\n", error->error_msg); err_printf(m, "Kernel: " UTS_RELEASE "\n"); @@ -1859,6 +1862,7 @@ void i915_capture_error_state(struct drm_i915_private *i915, error = i915_capture_gpu_state(i915); if (!error) { DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); + i915_disable_error_state(i915, -ENOMEM); return; } @@ -1914,5 +1918,14 @@ void i915_reset_error_state(struct drm_i915_private *i915) i915->gpu_error.first_error = NULL; spin_unlock_irq(&i915->gpu_error.lock); - i915_gpu_state_put(error); + if (!IS_ERR(error)) + i915_gpu_state_put(error); +} + +void i915_disable_error_state(struct drm_i915_private *i915, int err) +{ + spin_lock_irq(&i915->gpu_error.lock); + if (!i915->gpu_error.first_error) + i915->gpu_error.first_error = ERR_PTR(err); + spin_unlock_irq(&i915->gpu_error.lock); } -- cgit