Intel-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
* Compress the GPU error state
@ 2016-08-15 11:38 Chris Wilson
  2016-08-15 11:38 ` [PATCH 1/5] drm/i915: Allow disabling error capture Chris Wilson
                   ` (5 more replies)
  0 siblings, 6 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

After adjusting how we track the data to capture exactly what we use
via VMA, then adjusting the way we inspect the VMA we can finally
compress it.
-Chris

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply	[flat|nested] 7+ messages in thread

* [PATCH 1/5] drm/i915: Allow disabling error capture
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
@ 2016-08-15 11:38 ` Chris Wilson
  2016-08-15 11:38 ` [PATCH 2/5] drm/i915: Stop the machine whilst capturing the GPU crash dump Chris Wilson
                   ` (4 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

We currently capture the GPU state after we detect a hang. This is vital
for us to both triage and debug hangs in the wild (post-mortem
debugging). However, it comes at the cost of running some potentially
dangerous code (since it has to make very few assumption about the state
of the driver) that is quite resource intensive.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig          | 10 ++++++++++
 drivers/gpu/drm/i915/i915_debugfs.c   |  6 ++++++
 drivers/gpu/drm/i915/i915_drv.h       | 11 +++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.c |  7 +++++++
 drivers/gpu/drm/i915/i915_params.c    |  9 +++++++++
 drivers/gpu/drm/i915/i915_params.h    |  1 +
 drivers/gpu/drm/i915/i915_sysfs.c     |  8 ++++++++
 drivers/gpu/drm/i915/intel_display.c  |  4 ++++
 drivers/gpu/drm/i915/intel_overlay.c  |  4 ++++
 9 files changed, 60 insertions(+)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 7769e469118f..10a6ac11b6a9 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -46,6 +46,16 @@ config DRM_I915_PRELIMINARY_HW_SUPPORT
 
 	  If in doubt, say "N".
 
+config DRM_I915_CAPTURE_ERROR
+	bool "Enable capturing GPU state following a hang"
+	depends on DRM_I915
+	default y
+	help
+	  This option enables capturing the GPU state when a hang is detected.
+	  This information is vital for triaging hangs and assists in debugging.
+
+	  If in doubt, say "Y".
+
 config DRM_I915_USERPTR
 	bool "Always enable userptr support"
 	depends on DRM_I915
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b89478a8d19a..f41ebf25655c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -973,6 +973,8 @@ static int i915_hws_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
 static ssize_t
 i915_error_state_write(struct file *filp,
 		       const char __user *ubuf,
@@ -1062,6 +1064,8 @@ static const struct file_operations i915_error_state_fops = {
 	.release = i915_error_state_release,
 };
 
+#endif
+
 static int
 i915_next_seqno_get(void *data, u64 *val)
 {
@@ -5399,7 +5403,9 @@ static const struct i915_debugfs_files {
 	{"i915_ring_missed_irq", &i915_ring_missed_irq_fops},
 	{"i915_ring_test_irq", &i915_ring_test_irq_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
 	{"i915_error_state", &i915_error_state_fops},
+#endif
 	{"i915_next_seqno", &i915_next_seqno_fops},
 	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 35caa9b2f36a..20caac1796ef 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3482,6 +3482,7 @@ static inline void intel_display_crc_init(struct drm_device *dev) {}
 #endif
 
 /* i915_gpu_error.c */
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
 __printf(2, 3)
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
 int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
@@ -3501,6 +3502,16 @@ void i915_error_state_get(struct drm_device *dev,
 			  struct i915_error_state_file_priv *error_priv);
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
 void i915_destroy_error_state(struct drm_device *dev);
+#else
+static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
+					    u32 engine_mask,
+					    const char *error_msg)
+{
+}
+static inline void i915_destroy_error_state(struct drm_device *dev)
+{
+}
+#endif
 
 void i915_get_extra_instdone(struct drm_i915_private *dev_priv, uint32_t *instdone);
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0c3f30ce85c3..0bbc22f9a705 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -30,6 +30,8 @@
 #include <generated/utsrelease.h>
 #include "i915_drv.h"
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
 static const char *engine_str(int engine)
 {
 	switch (engine) {
@@ -1419,6 +1421,9 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
 	struct drm_i915_error_state *error;
 	unsigned long flags;
 
+	if (!i915.error_capture)
+		return;
+
 	if (READ_ONCE(dev_priv->gpu_error.first_error))
 		return;
 
@@ -1504,6 +1509,8 @@ void i915_destroy_error_state(struct drm_device *dev)
 		kref_put(&error->ref, i915_error_state_free);
 }
 
+#endif
+
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 768ad89d9cd4..e72a41223535 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -47,6 +47,7 @@ struct i915_params i915 __read_mostly = {
 	.load_detect_test = 0,
 	.force_reset_modeset_test = 0,
 	.reset = true,
+	.error_capture = true,
 	.invert_brightness = 0,
 	.disable_display = 0,
 	.enable_cmd_parser = 1,
@@ -115,6 +116,14 @@ MODULE_PARM_DESC(vbt_sdvo_panel_type,
 module_param_named_unsafe(reset, i915.reset, bool, 0600);
 MODULE_PARM_DESC(reset, "Attempt GPU resets (default: true)");
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+module_param_named(error_capture, i915.error_capture, bool, 0600);
+MODULE_PARM_DESC(error_capture,
+	"Record the GPU state following a hang. "
+	"This information in /sys/class/drm/card<N>/error is vital for "
+	"triaging and debugging hangs.");
+#endif
+
 module_param_named_unsafe(enable_hangcheck, i915.enable_hangcheck, bool, 0644);
 MODULE_PARM_DESC(enable_hangcheck,
 	"Periodically check GPU activity for detecting hangs. "
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 3a0dd78ddb38..94efc899c1ef 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -59,6 +59,7 @@ struct i915_params {
 	bool load_detect_test;
 	bool force_reset_modeset_test;
 	bool reset;
+	bool error_capture;
 	bool disable_display;
 	bool verbose_state_checks;
 	bool nuclear_pageflip;
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index f1ffde7f7c0b..36a18345492c 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -532,6 +532,8 @@ static const struct attribute *vlv_attrs[] = {
 	NULL,
 };
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
 static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 				struct bin_attribute *attr, char *buf,
 				loff_t off, size_t count)
@@ -597,6 +599,8 @@ static struct bin_attribute error_state_attr = {
 	.write = error_state_write,
 };
 
+#endif
+
 void i915_setup_sysfs(struct drm_device *dev)
 {
 	int ret;
@@ -642,15 +646,19 @@ void i915_setup_sysfs(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("RPS sysfs setup failed\n");
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
 	ret = sysfs_create_bin_file(&dev->primary->kdev->kobj,
 				    &error_state_attr);
 	if (ret)
 		DRM_ERROR("error_state sysfs setup failed\n");
+#endif
 }
 
 void i915_teardown_sysfs(struct drm_device *dev)
 {
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
 	sysfs_remove_bin_file(&dev->primary->kdev->kobj, &error_state_attr);
+#endif
 	if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))
 		sysfs_remove_files(&dev->primary->kdev->kobj, vlv_attrs);
 	else
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 781d22eee774..bb4473b26fd2 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -16879,6 +16879,8 @@ int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
 	return 0;
 }
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
 struct intel_display_error_state {
 
 	u32 power_well_driver;
@@ -17061,3 +17063,5 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  VSYNC: %08x\n", error->transcoder[i].vsync);
 	}
 }
+
+#endif
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 72f8990a13d2..87689df7f514 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -1470,6 +1470,8 @@ void intel_cleanup_overlay(struct drm_i915_private *dev_priv)
 	kfree(dev_priv->overlay);
 }
 
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
 struct intel_overlay_error_state {
 	struct overlay_registers regs;
 	unsigned long base;
@@ -1587,3 +1589,5 @@ intel_overlay_print_error_state(struct drm_i915_error_state_buf *m,
 	P(UVSCALEV);
 #undef P
 }
+
+#endif
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH 2/5] drm/i915: Stop the machine whilst capturing the GPU crash dump
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
  2016-08-15 11:38 ` [PATCH 1/5] drm/i915: Allow disabling error capture Chris Wilson
@ 2016-08-15 11:38 ` Chris Wilson
  2016-08-15 11:38 ` [PATCH 3/5] drm/i915: Always use the GTT for error capture Chris Wilson
                   ` (3 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

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
capture 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).

Note that by of itself, this is not a complete fix. It also depends on
the compiler barriers in list_add/list_del to prevent traversing the
lists into the void. We also depend that we only require state from
carefully controlled sources - i.e. all the state we require for
post-mortem debugging should be reachable from the request itself so
that we only have to worry about retrieving the request carefully. Once
we have the request, we know that all pointers from it are intact.

v2: Avoid drm_clflush_pages() inside stop_machine() as it may use
stop_machine() itself for its wbinvd fallback.

Signed-off-by: Chris Wilson <chris@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 | 46 +++++++++++++++++++++--------------
 3 files changed, 31 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 10a6ac11b6a9..0f46a9c04c0e 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -4,6 +4,7 @@ config DRM_I915
 	depends on X86 && PCI
 	select INTEL_GTT
 	select INTERVAL_TREE
+	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 20caac1796ef..52facd4a7179 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -705,6 +705,8 @@ struct drm_i915_error_state {
 	struct kref ref;
 	struct timeval time;
 
+	struct drm_i915_private *i915;
+
 	char error_msg[128];
 	bool simulated;
 	int iommu;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0bbc22f9a705..0815e5c47431 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -28,6 +28,7 @@
  */
 
 #include <generated/utsrelease.h>
+#include <linux/stop_machine.h>
 #include "i915_drv.h"
 
 #ifdef CONFIG_DRM_I915_CAPTURE_ERROR
@@ -715,14 +716,12 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 
 	dst->page_count = num_pages;
 	while (num_pages--) {
-		unsigned long flags;
 		void *d;
 
 		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
 		if (d == NULL)
 			goto unwind;
 
-		local_irq_save(flags);
 		if (use_ggtt) {
 			void __iomem *s;
 
@@ -741,15 +740,10 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 
 			page = i915_gem_object_get_page(src, i);
 
-			drm_clflush_pages(&page, 1);
-
 			s = kmap_atomic(page);
 			memcpy(d, s, PAGE_SIZE);
 			kunmap_atomic(s);
-
-			drm_clflush_pages(&page, 1);
 		}
-		local_irq_restore(flags);
 
 		dst->pages[i++] = d;
 		reloc_offset += PAGE_SIZE;
@@ -1404,6 +1398,31 @@ static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
 	       sizeof(error->device_info));
 }
 
+static int capture(void *data)
+{
+	struct drm_i915_error_state *error = data;
+
+	/* Ensure that what we readback from memory matches what the GPU sees */
+	wbinvd();
+
+	i915_capture_gen_state(error->i915, error);
+	i915_capture_reg_state(error->i915, error);
+	i915_gem_record_fences(error->i915, error);
+	i915_gem_record_rings(error->i915, error);
+	i915_capture_active_buffers(error->i915, error);
+	i915_capture_pinned_buffers(error->i915, error);
+
+	do_gettimeofday(&error->time);
+
+	error->overlay = intel_overlay_capture_error_state(error->i915);
+	error->display = intel_display_capture_error_state(error->i915);
+
+	/* And make sure we don't leave trash in the CPU cache */
+	wbinvd();
+
+	return 0;
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -1435,18 +1454,9 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
 	}
 
 	kref_init(&error->ref);
+	error->i915 = dev_priv;
 
-	i915_capture_gen_state(dev_priv, error);
-	i915_capture_reg_state(dev_priv, error);
-	i915_gem_record_fences(dev_priv, error);
-	i915_gem_record_rings(dev_priv, error);
-	i915_capture_active_buffers(dev_priv, error);
-	i915_capture_pinned_buffers(dev_priv, error);
-
-	do_gettimeofday(&error->time);
-
-	error->overlay = intel_overlay_capture_error_state(dev_priv);
-	error->display = intel_display_capture_error_state(dev_priv);
+	stop_machine(capture, error, NULL);
 
 	i915_error_capture_msg(dev_priv, error, engine_mask, error_msg);
 	DRM_INFO("%s\n", error->error_msg);
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH 3/5] drm/i915: Always use the GTT for error capture
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
  2016-08-15 11:38 ` [PATCH 1/5] drm/i915: Allow disabling error capture Chris Wilson
  2016-08-15 11:38 ` [PATCH 2/5] drm/i915: Stop the machine whilst capturing the GPU crash dump Chris Wilson
@ 2016-08-15 11:38 ` Chris Wilson
  2016-08-15 11:38 ` [PATCH 4/5] drm/i915: Consolidate error object printing Chris Wilson
                   ` (2 subsequent siblings)
  5 siblings, 0 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

Since the GTT provides universal access to any GPU page, we can use it
to reduce our plethora of read methods to just one. It also has the
important characteristic of being exactly what the GPU sees - if there
are incoherency problems, seeing the batch as executed (rather than as
trapped inside the cpu cache) is important.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c   |  43 ++++++++----
 drivers/gpu/drm/i915/i915_gem_gtt.h   |   2 +
 drivers/gpu/drm/i915/i915_gpu_error.c | 122 ++++++++++++----------------------
 3 files changed, 75 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3631944ac2d9..cbeec4cfe8a4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2729,6 +2729,7 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	 */
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	unsigned long hole_start, hole_end;
+	struct i915_hw_ppgtt *ppgtt;
 	struct drm_mm_node *entry;
 	int ret;
 
@@ -2736,6 +2737,15 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
+	/* Reserve a mappable slot for our lockless error capture */
+	ret = drm_mm_insert_node_in_range_generic(&ggtt->base.mm,
+						  &ggtt->gpu_error,
+						  4096, 0, -1,
+						  0, ggtt->mappable_end,
+						  0, 0);
+	if (ret)
+		return ret;
+
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) {
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
@@ -2750,25 +2760,21 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 			       true);
 
 	if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) {
-		struct i915_hw_ppgtt *ppgtt;
-
 		ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-		if (!ppgtt)
-			return -ENOMEM;
+		if (!ppgtt) {
+			ret = -ENOMEM;
+			goto err;
+		}
 
 		ret = __hw_ppgtt_init(ppgtt, dev_priv);
-		if (ret) {
-			kfree(ppgtt);
-			return ret;
-		}
+		if (ret)
+			goto err_ppgtt;
 
-		if (ppgtt->base.allocate_va_range)
+		if (ppgtt->base.allocate_va_range) {
 			ret = ppgtt->base.allocate_va_range(&ppgtt->base, 0,
 							    ppgtt->base.total);
-		if (ret) {
-			ppgtt->base.cleanup(&ppgtt->base);
-			kfree(ppgtt);
-			return ret;
+			if (ret)
+				goto err_ppgtt_cleanup;
 		}
 
 		ppgtt->base.clear_range(&ppgtt->base,
@@ -2782,6 +2788,14 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	}
 
 	return 0;
+
+err_ppgtt_cleanup:
+	ppgtt->base.cleanup(&ppgtt->base);
+err_ppgtt:
+	kfree(ppgtt);
+err:
+	drm_mm_remove_node(&ggtt->gpu_error);
+	return ret;
 }
 
 /**
@@ -2801,6 +2815,9 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	i915_gem_cleanup_stolen(&dev_priv->drm);
 
+	if (drm_mm_node_allocated(&ggtt->gpu_error))
+		drm_mm_remove_node(&ggtt->gpu_error);
+
 	if (drm_mm_initialized(&ggtt->base.mm)) {
 		intel_vgt_deballoon(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d6e4b6529196..79a08a050487 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -439,6 +439,8 @@ struct i915_ggtt {
 	bool do_idle_maps;
 
 	int mtrr;
+
+	struct drm_mm_node gpu_error;
 };
 
 struct i915_hw_ppgtt {
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 0815e5c47431..185adcff0f2d 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -628,7 +628,7 @@ static void i915_error_object_free(struct drm_i915_error_object *obj)
 		return;
 
 	for (page = 0; page < obj->page_count; page++)
-		kfree(obj->pages[page]);
+		free_page((unsigned long)obj->pages[page]);
 
 	kfree(obj);
 }
@@ -664,98 +664,69 @@ static void i915_error_state_free(struct kref *error_ref)
 	kfree(error);
 }
 
+static int compress_page(void *src, struct drm_i915_error_object *dst)
+{
+	unsigned long page;
+
+	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page)
+		return -ENOMEM;
+
+	dst->pages[dst->page_count++] = (void *)page;
+
+	memcpy((void *)page, src, PAGE_SIZE);
+	return 0;
+}
+
 static struct drm_i915_error_object *
-i915_error_object_create(struct drm_i915_private *dev_priv,
+i915_error_object_create(struct drm_i915_private *i915,
 			 struct i915_vma *vma)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct drm_i915_gem_object *src;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	const u64 slot = ggtt->gpu_error.start;
 	struct drm_i915_error_object *dst;
-	int num_pages;
-	bool use_ggtt;
-	int i = 0;
-	u64 reloc_offset;
+	unsigned long num_pages;
+	struct sgt_iter iter;
+	dma_addr_t dma;
 
 	if (!vma)
 		return NULL;
 
-	src = vma->obj;
-	if (!src->pages)
-		return NULL;
-
-	num_pages = src->base.size >> PAGE_SHIFT;
-
-	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
+	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
+	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *),
+		      GFP_ATOMIC | __GFP_NOWARN);
 	if (!dst)
 		return NULL;
 
 	dst->gtt_offset = vma->node.start;
-	dst->gtt_size = vma->node.size;
-
-	reloc_offset = dst->gtt_offset;
-	use_ggtt = (src->cache_level == I915_CACHE_NONE &&
-		   (vma->flags & I915_VMA_GLOBAL_BIND) &&
-		   reloc_offset + num_pages * PAGE_SIZE <= ggtt->mappable_end);
+	dst->page_count = 0;
 
-	/* Cannot access stolen address directly, try to use the aperture */
-	if (src->stolen) {
-		use_ggtt = true;
-
-		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
-			goto unwind;
-
-		reloc_offset = vma->node.start;
-		if (reloc_offset + num_pages * PAGE_SIZE > ggtt->mappable_end)
-			goto unwind;
-	}
+	for_each_sgt_dma(dma, iter, vma->pages) {
+		int ret;
+		void *s;
 
-	/* Cannot access snooped pages through the aperture */
-	if (use_ggtt && src->cache_level != I915_CACHE_NONE &&
-	    !HAS_LLC(dev_priv))
-		goto unwind;
+		ggtt->base.insert_page(&ggtt->base, dma, slot,
+				       I915_CACHE_NONE, 0);
 
-	dst->page_count = num_pages;
-	while (num_pages--) {
-		void *d;
+		s = (void *__force)
+			io_mapping_map_atomic_wc(ggtt->mappable, slot);
+		ret = compress_page(s, dst);
+		io_mapping_unmap_atomic(s);
 
-		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
-		if (d == NULL)
+		if (ret)
 			goto unwind;
-
-		if (use_ggtt) {
-			void __iomem *s;
-
-			/* Simply ignore tiling or any overlapping fence.
-			 * It's part of the error state, and this hopefully
-			 * captures what the GPU read.
-			 */
-
-			s = io_mapping_map_atomic_wc(ggtt->mappable,
-						     reloc_offset);
-			memcpy_fromio(d, s, PAGE_SIZE);
-			io_mapping_unmap_atomic(s);
-		} else {
-			struct page *page;
-			void *s;
-
-			page = i915_gem_object_get_page(src, i);
-
-			s = kmap_atomic(page);
-			memcpy(d, s, PAGE_SIZE);
-			kunmap_atomic(s);
-		}
-
-		dst->pages[i++] = d;
-		reloc_offset += PAGE_SIZE;
 	}
-
-	return dst;
+	goto out;
 
 unwind:
-	while (i--)
-		kfree(dst->pages[i]);
+	while (dst->page_count--)
+		free_page((unsigned long)dst->pages[dst->page_count]);
 	kfree(dst);
-	return NULL;
+	dst = NULL;
+
+out:
+	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE, true);
+	return dst;
 }
 
 /* The error capture is special as tries to run underneath the normal
@@ -1402,9 +1373,6 @@ static int capture(void *data)
 {
 	struct drm_i915_error_state *error = data;
 
-	/* Ensure that what we readback from memory matches what the GPU sees */
-	wbinvd();
-
 	i915_capture_gen_state(error->i915, error);
 	i915_capture_reg_state(error->i915, error);
 	i915_gem_record_fences(error->i915, error);
@@ -1417,9 +1385,6 @@ static int capture(void *data)
 	error->overlay = intel_overlay_capture_error_state(error->i915);
 	error->display = intel_display_capture_error_state(error->i915);
 
-	/* And make sure we don't leave trash in the CPU cache */
-	wbinvd();
-
 	return 0;
 }
 
@@ -1496,7 +1461,6 @@ void i915_error_state_get(struct drm_device *dev,
 	if (error_priv->error)
 		kref_get(&error_priv->error->ref);
 	spin_unlock_irq(&dev_priv->gpu_error.lock);
-
 }
 
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH 4/5] drm/i915: Consolidate error object printing
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
                   ` (2 preceding siblings ...)
  2016-08-15 11:38 ` [PATCH 3/5] drm/i915: Always use the GTT for error capture Chris Wilson
@ 2016-08-15 11:38 ` Chris Wilson
  2016-08-15 11:38 ` [PATCH 5/5] drm/i915: Compress GPU objects in error state Chris Wilson
  2016-08-15 12:02 ` ✗ Ro.CI.BAT: failure for series starting with [1/5] drm/i915: Allow disabling error capture Patchwork
  5 siblings, 0 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

Leave all the pretty printing to userspace and simplify the error
capture to only have a single common object printer. It makes the kernel
code more compact, and the refactoring allows us to apply more complex
transformations like compressing the output.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 100 +++++++++-------------------------
 1 file changed, 25 insertions(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 185adcff0f2d..ae0b98eee9ec 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -311,10 +311,22 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 }
 
 static void print_error_obj(struct drm_i915_error_state_buf *m,
+			    struct intel_engine_cs *engine,
+			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
 	int page, offset, elt;
 
+	if (!obj)
+		return;
+
+	if (name) {
+		err_printf(m, "%s --- %s = 0x%08x %08x\n",
+			   engine ? engine->name : "global", name,
+			   upper_32_bits(obj->gtt_offset),
+			   lower_32_bits(obj->gtt_offset));
+	}
+
 	for (page = offset = 0; page < obj->page_count; page++) {
 		for (elt = 0; elt < PAGE_SIZE/4; elt++) {
 			err_printf(m, "%08x :  %08x\n", offset,
@@ -341,8 +353,8 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_error_state *error = error_priv->error;
 	struct drm_i915_error_object *obj;
-	int i, j, offset, elt;
 	int max_hangcheck_score;
+	int i, j;
 
 	if (!error) {
 		err_printf(m, "no error state collected\n");
@@ -466,15 +478,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
-
-		obj = ee->wa_batchbuffer;
-		if (obj) {
-			err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
+			print_error_obj(m, &dev_priv->engine[i], NULL, obj);
 		}
 
 		if (ee->num_requests) {
@@ -503,77 +507,23 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
-		if ((obj = ee->ringbuffer)) {
-			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"ringbuffer", ee->ringbuffer);
 
-		if ((obj = ee->hws_page)) {
-			u64 hws_offset = obj->gtt_offset;
-			u32 *hws_page = &obj->pages[0][0];
+		print_error_obj(m, &dev_priv->engine[i],
+				"HW Status", ee->hws_page);
 
-			if (i915.enable_execlists) {
-				hws_offset += LRC_PPHWSP_PN * PAGE_SIZE;
-				hws_page = &obj->pages[LRC_PPHWSP_PN][0];
-			}
-			err_printf(m, "%s --- HW Status = 0x%08llx\n",
-				   dev_priv->engine[i].name, hws_offset);
-			offset = 0;
-			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   hws_page[elt],
-					   hws_page[elt+1],
-					   hws_page[elt+2],
-					   hws_page[elt+3]);
-				offset += 16;
-			}
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"HW context", ee->ctx);
 
-		obj = ee->wa_ctx;
-		if (obj) {
-			u64 wa_ctx_offset = obj->gtt_offset;
-			u32 *wa_ctx_page = &obj->pages[0][0];
-			struct intel_engine_cs *engine = &dev_priv->engine[RCS];
-			u32 wa_ctx_size = (engine->wa_ctx.indirect_ctx.size +
-					   engine->wa_ctx.per_ctx.size);
-
-			err_printf(m, "%s --- WA ctx batch buffer = 0x%08llx\n",
-				   dev_priv->engine[i].name, wa_ctx_offset);
-			offset = 0;
-			for (elt = 0; elt < wa_ctx_size; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   wa_ctx_page[elt + 0],
-					   wa_ctx_page[elt + 1],
-					   wa_ctx_page[elt + 2],
-					   wa_ctx_page[elt + 3]);
-				offset += 16;
-			}
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"WA context", ee->wa_ctx);
 
-		if ((obj = ee->ctx)) {
-			err_printf(m, "%s --- HW Context = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"WA batchbuffer", ee->wa_batchbuffer);
 	}
 
-	if ((obj = error->semaphore)) {
-		err_printf(m, "Semaphore page = 0x%08x\n",
-			   lower_32_bits(obj->gtt_offset));
-		for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-			err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-				   elt * 4,
-				   obj->pages[0][elt],
-				   obj->pages[0][elt+1],
-				   obj->pages[0][elt+2],
-				   obj->pages[0][elt+3]);
-		}
-	}
+	print_error_obj(m, NULL, "Semaphores", error->semaphore);
 
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH 5/5] drm/i915: Compress GPU objects in error state
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
                   ` (3 preceding siblings ...)
  2016-08-15 11:38 ` [PATCH 4/5] drm/i915: Consolidate error object printing Chris Wilson
@ 2016-08-15 11:38 ` Chris Wilson
  2016-08-15 12:02 ` ✗ Ro.CI.BAT: failure for series starting with [1/5] drm/i915: Allow disabling error capture Patchwork
  5 siblings, 0 replies; 7+ messages in thread
From: Chris Wilson @ 2016-08-15 11:38 UTC (permalink / raw)
  To: intel-gfx

Our error states are quickly growing, pinning kernel memory with them.
The majority of the space is taken up by the error objects. These
compress well using zlib and without decode are mostly meaningless, so
encoding them does not hinder quickly parsing the error state for
familiarity.

v2: Make the zlib dependency optional

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig          |  12 +++
 drivers/gpu/drm/i915/i915_drv.h       |   3 +-
 drivers/gpu/drm/i915/i915_gpu_error.c | 170 +++++++++++++++++++++++++++++-----
 3 files changed, 163 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 0f46a9c04c0e..69657629d750 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -57,6 +57,18 @@ config DRM_I915_CAPTURE_ERROR
 
 	  If in doubt, say "Y".
 
+config DRM_I915_COMPRESS_ERROR
+	bool "Compress GPU error state"
+	depends on DRM_I915
+	select ZLIB_DEFLATE
+	default y
+	help
+	  This option selects ZLIB_DEFLATE if it isn't already
+	  selected and causes any error state captured upon a GPU hang
+	  to be compressed using zlib.
+
+	  If in doubt, say "Y".
+
 config DRM_I915_USERPTR
 	bool "Always enable userptr support"
 	depends on DRM_I915
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 52facd4a7179..6bb39301999e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -776,9 +776,10 @@ struct drm_i915_error_state {
 		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
 
 		struct drm_i915_error_object {
-			int page_count;
 			u64 gtt_offset;
 			u64 gtt_size;
+			int page_count;
+			int unused;
 			u32 *pages[0];
 		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index ae0b98eee9ec..404ae3356beb 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/stop_machine.h>
+#include <linux/zlib.h>
 #include "i915_drv.h"
 
 #ifdef CONFIG_DRM_I915_CAPTURE_ERROR
@@ -175,6 +176,110 @@ static void i915_error_puts(struct drm_i915_error_state_buf *e,
 #define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
 #define err_puts(e, s) i915_error_puts(e, s)
 
+#ifdef CONFIG_DRM_I915_COMPRESS_ERROR
+
+static bool compress_init(struct z_stream_s *zstream)
+{
+	memset(zstream, 0, sizeof(*zstream));
+
+	zstream->workspace =
+		kmalloc(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
+			GFP_ATOMIC | __GFP_NOWARN);
+	if (!zstream->workspace)
+		return NULL;
+
+	if (zlib_deflateInit(zstream, Z_DEFAULT_COMPRESSION) != Z_OK) {
+		kfree(zstream->workspace);
+		return false;
+	}
+
+	return true;
+}
+
+static int compress_page(struct z_stream_s *zstream,
+			 void *src,
+			 struct drm_i915_error_object *dst)
+{
+	zstream->next_in = src;
+	zstream->avail_in = PAGE_SIZE;
+
+	do {
+		if (zstream->avail_out == 0) {
+			unsigned long page;
+
+			page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+			if (!page)
+				return -ENOMEM;
+
+			dst->pages[dst->page_count++] = (void *)page;
+
+			zstream->next_out = (void *)page;
+			zstream->avail_out = PAGE_SIZE;
+		}
+
+		if (zlib_deflate(zstream, Z_SYNC_FLUSH) != Z_OK)
+			return -EIO;
+
+		/* Fallback to uncompressed if we increase size? */
+		if (0 && zstream->total_out > zstream->total_in)
+			return -E2BIG;
+	} while (zstream->avail_in);
+
+	return 0;
+}
+
+static void compress_fini(struct z_stream_s *zstream,
+			  struct drm_i915_error_object *dst)
+{
+	if (dst) {
+		zlib_deflate(zstream, Z_FINISH);
+		dst->unused = zstream->avail_out;
+	}
+
+	zlib_deflateEnd(zstream);
+	kfree(zstream->workspace);
+}
+
+static void err_compression_marker(struct drm_i915_error_state_buf *m)
+{
+	err_puts(m, ":");
+}
+
+#else
+
+static bool compress_init(struct z_stream_s *zstream)
+{
+	return true;
+}
+
+static int compress_page(struct z_stream_s *zstream,
+			 void *src,
+			 struct drm_i915_error_object *dst)
+{
+	unsigned long page;
+
+	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page)
+		return -ENOMEM;
+
+	dst->pages[dst->page_count++] =
+		memcpy((void *)page, src, PAGE_SIZE);
+
+	return 0;
+}
+
+static void compress_fini(struct z_stream_s *zstream,
+			  struct drm_i915_error_object *dst)
+{
+}
+
+static void err_compression_marker(struct drm_i915_error_state_buf *m)
+{
+	err_puts(m, "~");
+}
+
+#endif
+
 static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				const char *name,
 				struct drm_i915_error_buffer *err,
@@ -310,12 +415,30 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
+static bool
+ascii85_encode(u32 in, char *out)
+{
+	int i;
+
+	if (in == 0)
+		return false;
+
+	out[5] = '\0';
+	for (i = 5; i--; ) {
+		out[i] = '!' + in % 85;
+		in /= 85;
+	}
+
+	return true;
+}
+
 static void print_error_obj(struct drm_i915_error_state_buf *m,
 			    struct intel_engine_cs *engine,
 			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
-	int page, offset, elt;
+	char out[6];
+	int page;
 
 	if (!obj)
 		return;
@@ -327,13 +450,23 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			   lower_32_bits(obj->gtt_offset));
 	}
 
-	for (page = offset = 0; page < obj->page_count; page++) {
-		for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-			err_printf(m, "%08x :  %08x\n", offset,
-				   obj->pages[page][elt]);
-			offset += 4;
+	err_compression_marker(m);
+	for (page = 0; page < obj->page_count; page++) {
+		int i, len;
+
+		len = PAGE_SIZE;
+		if (page == obj->page_count - 1)
+			len -= obj->unused;
+		len = (len + 3) / 4;
+
+		for (i = 0; i < len; i++) {
+			if (ascii85_encode(obj->pages[page][i], out))
+				err_puts(m, out);
+			else
+				err_puts(m, "z");
 		}
 	}
+	err_puts(m, "\n");
 }
 
 static void err_print_capabilities(struct drm_i915_error_state_buf *m,
@@ -614,20 +747,6 @@ static void i915_error_state_free(struct kref *error_ref)
 	kfree(error);
 }
 
-static int compress_page(void *src, struct drm_i915_error_object *dst)
-{
-	unsigned long page;
-
-	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
-	if (!page)
-		return -ENOMEM;
-
-	dst->pages[dst->page_count++] = (void *)page;
-
-	memcpy((void *)page, src, PAGE_SIZE);
-	return 0;
-}
-
 static struct drm_i915_error_object *
 i915_error_object_create(struct drm_i915_private *i915,
 			 struct i915_vma *vma)
@@ -635,6 +754,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	const u64 slot = ggtt->gpu_error.start;
 	struct drm_i915_error_object *dst;
+	struct z_stream_s zstream;
 	unsigned long num_pages;
 	struct sgt_iter iter;
 	dma_addr_t dma;
@@ -643,6 +763,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 		return NULL;
 
 	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
+	num_pages = DIV_ROUND_UP(10 * num_pages, 8); /* worstcase zlib growth */
 	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *),
 		      GFP_ATOMIC | __GFP_NOWARN);
 	if (!dst)
@@ -650,6 +771,12 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 	dst->gtt_offset = vma->node.start;
 	dst->page_count = 0;
+	dst->unused = 0;
+
+	if (!compress_init(&zstream)) {
+		kfree(dst);
+		return NULL;
+	}
 
 	for_each_sgt_dma(dma, iter, vma->pages) {
 		int ret;
@@ -660,7 +787,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 		s = (void *__force)
 			io_mapping_map_atomic_wc(ggtt->mappable, slot);
-		ret = compress_page(s, dst);
+		ret = compress_page(&zstream, s, dst);
 		io_mapping_unmap_atomic(s);
 
 		if (ret)
@@ -675,6 +802,7 @@ unwind:
 	dst = NULL;
 
 out:
+	compress_fini(&zstream, dst);
 	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE, true);
 	return dst;
 }
-- 
2.8.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* ✗ Ro.CI.BAT: failure for series starting with [1/5] drm/i915: Allow disabling error capture
  2016-08-15 11:38 Compress the GPU error state Chris Wilson
                   ` (4 preceding siblings ...)
  2016-08-15 11:38 ` [PATCH 5/5] drm/i915: Compress GPU objects in error state Chris Wilson
@ 2016-08-15 12:02 ` Patchwork
  5 siblings, 0 replies; 7+ messages in thread
From: Patchwork @ 2016-08-15 12:02 UTC (permalink / raw)
  To: Chris Wilson; +Cc: intel-gfx

== Series Details ==

Series: series starting with [1/5] drm/i915: Allow disabling error capture
URL   : https://patchwork.freedesktop.org/series/11096/
State : failure

== Summary ==

Series 11096v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/11096/revisions/1/mbox

Test drv_module_reload_basic:
                pass       -> SKIP       (ro-ivb-i7-3770)
Test kms_cursor_legacy:
        Subgroup basic-cursor-vs-flip-varying-size:
                fail       -> PASS       (ro-ilk1-i5-650)
        Subgroup basic-flip-vs-cursor-legacy:
                fail       -> PASS       (ro-ivb2-i7-3770)
                fail       -> PASS       (ro-byt-n2820)
                pass       -> FAIL       (ro-bdw-i5-5250u)
Test kms_pipe_crc_basic:
        Subgroup suspend-read-crc-pipe-a:
                pass       -> INCOMPLETE (fi-hsw-i7-4770k)

fi-hsw-i7-4770k  total:201  pass:180  dwarn:0   dfail:0   fail:0   skip:20 
fi-kbl-qkkr      total:244  pass:185  dwarn:29  dfail:0   fail:3   skip:27 
fi-skl-i7-6700k  total:244  pass:208  dwarn:4   dfail:2   fail:2   skip:28 
fi-snb-i7-2600   total:244  pass:202  dwarn:0   dfail:0   fail:0   skip:42 
ro-bdw-i5-5250u  total:240  pass:218  dwarn:1   dfail:0   fail:2   skip:19 
ro-bdw-i7-5600u  total:240  pass:207  dwarn:0   dfail:0   fail:1   skip:32 
ro-bsw-n3050     total:240  pass:194  dwarn:0   dfail:0   fail:4   skip:42 
ro-byt-n2820     total:240  pass:198  dwarn:0   dfail:0   fail:2   skip:40 
ro-hsw-i3-4010u  total:240  pass:214  dwarn:0   dfail:0   fail:0   skip:26 
ro-hsw-i7-4770r  total:240  pass:185  dwarn:0   dfail:0   fail:0   skip:55 
ro-ilk1-i5-650   total:235  pass:174  dwarn:0   dfail:0   fail:1   skip:60 
ro-ivb-i7-3770   total:240  pass:204  dwarn:0   dfail:0   fail:0   skip:36 
ro-ivb2-i7-3770  total:240  pass:209  dwarn:0   dfail:0   fail:0   skip:31 
ro-skl3-i5-6260u total:240  pass:223  dwarn:0   dfail:0   fail:3   skip:14 

Results at /archive/results/CI_IGT_test/RO_Patchwork_1869/

e56d79f drm-intel-nightly: 2016y-08m-15d-10h-16m-44s UTC integration manifest
b8c5ad5 drm/i915: Compress GPU objects in error state
7d5601b drm/i915: Consolidate error object printing
716ad20 drm/i915: Always use the GTT for error capture
5f76742 drm/i915: Stop the machine whilst capturing the GPU crash dump
5476ea87 drm/i915: Allow disabling error capture

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2016-08-15 12:02 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2016-08-15 11:38 Compress the GPU error state Chris Wilson
2016-08-15 11:38 ` [PATCH 1/5] drm/i915: Allow disabling error capture Chris Wilson
2016-08-15 11:38 ` [PATCH 2/5] drm/i915: Stop the machine whilst capturing the GPU crash dump Chris Wilson
2016-08-15 11:38 ` [PATCH 3/5] drm/i915: Always use the GTT for error capture Chris Wilson
2016-08-15 11:38 ` [PATCH 4/5] drm/i915: Consolidate error object printing Chris Wilson
2016-08-15 11:38 ` [PATCH 5/5] drm/i915: Compress GPU objects in error state Chris Wilson
2016-08-15 12:02 ` ✗ Ro.CI.BAT: failure for series starting with [1/5] drm/i915: Allow disabling error capture Patchwork

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox