[Intel-gfx] [PATCH] RFC drm/i915: Stop the machine whilst capturing the GPU crash dump

[Chris Wilson]

The error state is purposefully racy as we expect it to be called at any
time and so have avoided any locking whilst capturing the crash dump.
However, with multi-engine GPUs and multiple CPUs, those races can
manifest into OOPSes as we attempt to chase dangling pointers freed on
other CPUs. Under discussion are lots of ways to slow down normal
operation in order to protect the post-mortem error capture, but what it
we take the opposite approach and freeze the machine whilst the error
catpure runs (note the GPU may still running, but as long as we don't
process any of the results the driver's bookkeeping will be static).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig          |  1 +
 drivers/gpu/drm/i915/i915_drv.h       |  2 ++
 drivers/gpu/drm/i915/i915_gpu_error.c | 31 +++++++++++++++++++++----------
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 99e819767204..63df28910c8f 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -7,6 +7,7 @@ config DRM_I915
 	select AGP_INTEL if AGP
 	select INTERVAL_TREE
 	select ZLIB_DEFLATE
+	select STOP_MACHINE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
 	select SHMEM
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9d16fc1189d6..14a882fe486c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -488,6 +488,8 @@ struct drm_i915_error_state {
 	struct kref ref;
 	struct timeval time;
 
+	struct drm_i915_private *i915;
+
 	char error_msg[128];
 	int iommu;
 	u32 reset_count;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 64bdffcffb50..29cbec67bcfc 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -29,6 +29,7 @@
 
 #include <generated/utsrelease.h>
 #include <linux/zlib.h>
+#include <linux/stop_machine.h>
 #include "i915_drv.h"
 
 static const char *yesno(int v)
@@ -1352,6 +1353,24 @@ static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
 	error->suspend_count = dev_priv->suspend_count;
 }
 
+static int capture(void *data)
+{
+	struct drm_i915_error_state *error = data;
+
+	i915_capture_gen_state(error->i915, error);
+	i915_capture_reg_state(error->i915, error);
+	i915_gem_capture_buffers(error->i915, error);
+	i915_gem_record_fences(error->i915->dev, error);
+	i915_gem_record_rings(error->i915->dev, error);
+
+	do_gettimeofday(&error->time);
+
+	error->overlay = intel_overlay_capture_error_state(error->i915->dev);
+	error->display = intel_display_capture_error_state(error->i915->dev);
+
+	return 0;
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -1377,17 +1396,9 @@ void i915_capture_error_state(struct drm_device *dev, bool wedged,
 	}
 
 	kref_init(&error->ref);
+	error->i915 = dev_priv;
 
-	i915_capture_gen_state(dev_priv, error);
-	i915_capture_reg_state(dev_priv, error);
-	i915_gem_capture_buffers(dev_priv, error);
-	i915_gem_record_fences(dev, error);
-	i915_gem_record_rings(dev, error);
-
-	do_gettimeofday(&error->time);
-
-	error->overlay = intel_overlay_capture_error_state(dev);
-	error->display = intel_display_capture_error_state(dev);
+	stop_machine(capture, error, NULL);
 
 	i915_error_capture_msg(dev, error, wedged, error_msg);
 	DRM_INFO("%s\n", error->error_msg);
-- 
2.6.1