Periodically check the scratch page to see if it changes. Scratch page
changes almost always indicate something is wrong.
We never expect a non-zero filled page, so potentially we could directly
put that md5 value for checking. I think the code as it is will be a bit
more robust.
Pretty RFC here since I've only compiled and run it for a few seconds.
Recommended-by: Stephane Marchesin <marcheu at chromium.org>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/Kconfig | 2 +
drivers/gpu/drm/i915/i915_drv.c | 5 +++
drivers/gpu/drm/i915/i915_drv.h | 14 +++++++
drivers/gpu/drm/i915/i915_gem_gtt.c | 73 +++++++++++++++++++++++++++++++++++++
4 files changed, 94 insertions(+)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 19b8e0d..44efe74 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -125,6 +125,8 @@ config DRM_I915
depends on DRM
depends on AGP
depends on AGP_INTEL
+ select CRYPTO
+ select CRYPTO_MD5
# 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.c b/drivers/gpu/drm/i915/i915_drv.c
index 9ebe895..a1f6142 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -128,6 +128,11 @@ module_param_named(disable_power_well, i915_disable_power_well, int, 0600);
MODULE_PARM_DESC(disable_power_well,
"Disable the power well when possible (default: false)");
+int i915_enable_scratch_checker __read_mostly = 0;
+module_param_named(enable_scratch_checker, i915_enable_scratch_checker, int, 0600);
+MODULE_PARM_DESC(enable_scratch_checker,
+ "Enable periodic timer to find stray writes to the scratch page (default: false)");
+
static struct drm_driver driver;
extern int intel_agp_enabled;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d5dcf7f..c1f4ef7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -43,6 +43,8 @@
#include <linux/intel-iommu.h>
#include <linux/kref.h>
#include <linux/pm_qos.h>
+#include <linux/crypto.h>
+#include <crypto/md5.h>
/* General customization:
*/
@@ -869,6 +871,16 @@ struct i915_gpu_error {
unsigned int stop_rings;
};
+struct i915_scratch_checker {
+ struct scatterlist sg; /* sg for scratch page */
+ struct hash_desc hash;
+ char last_hash[MD5_DIGEST_SIZE];
+
+#define I915_SCRATCH_DIRT_PERIOD 1000 /* in ms */
+#define I915_SCRATCH_DIRT_JIFFIES msecs_to_jiffies(I915_SCRATCH_DIRT_PERIOD)
+ struct timer_list timer;
+};
+
enum modeset_restore {
MODESET_ON_LID_OPEN,
MODESET_DONE,
@@ -1058,6 +1070,7 @@ typedef struct drm_i915_private {
struct drm_mm_node *compressed_llb;
struct i915_gpu_error gpu_error;
+ struct i915_scratch_checker scratch_checker;
/* list of fbdev register on this device */
struct intel_fbdev *fbdev;
@@ -1435,6 +1448,7 @@ extern bool i915_enable_hangcheck __read_mostly;
extern int i915_enable_ppgtt __read_mostly;
extern unsigned int i915_preliminary_hw_support __read_mostly;
extern int i915_disable_power_well __read_mostly;
+extern int i915_enable_scratch_checker __read_mostly;
extern int i915_suspend(struct drm_device *dev, pm_message_t state);
extern int i915_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 50df194..df7a3a8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -660,6 +660,72 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
}
+static void scratch_checker(unsigned long data)
+{
+ struct drm_i915_private *dev_priv = (struct drm_i915_private *)data;
+ char hash[MD5_DIGEST_SIZE];
+ int ret;
+
+ ret = crypto_hash_digest(&dev_priv->scratch_checker.hash,
+ &dev_priv->scratch_checker.sg, PAGE_SIZE,
+ hash);
+ if (ret) {
+ DRM_DEBUG_DRIVER("Couldn't hash scratch\n");
+ goto out;
+ }
+
+ if (!memcmp(hash, dev_priv->scratch_checker.last_hash, MD5_DIGEST_SIZE))
+ goto out;
+
+ DRM_DEBUG("Scratch page contents changed\n");
+ memcpy(dev_priv->scratch_checker.last_hash, hash, MD5_DIGEST_SIZE);
+
+out:
+ mod_timer(&dev_priv->scratch_checker.timer,
+ round_jiffies_up(jiffies + I915_SCRATCH_DIRT_JIFFIES));
+}
+
+static void scratch_checker_init(struct drm_i915_private *dev_priv)
+{
+ int ret;
+
+ sg_init_table(&dev_priv->scratch_checker.sg, 1);
+ sg_set_page(&dev_priv->scratch_checker.sg, dev_priv->gtt.scratch_page,
+ 4096, 0);
+
+ dev_priv->scratch_checker.hash.tfm = crypto_alloc_hash("md5", 0,
+ CRYPTO_ALG_ASYNC);
+ if (IS_ERR_OR_NULL(dev_priv->scratch_checker.hash.tfm))
+ return;
+
+ ret = crypto_hash_init(&dev_priv->scratch_checker.hash);
+ if (ret)
+ goto err;
+
+ ret = crypto_hash_digest(&dev_priv->scratch_checker.hash,
+ &dev_priv->scratch_checker.sg, PAGE_SIZE,
+ dev_priv->scratch_checker.last_hash);
+ if (ret)
+ goto err;
+
+ setup_timer(&dev_priv->scratch_checker.timer, scratch_checker,
+ (unsigned long) dev_priv);
+ return;
+
+err:
+ crypto_free_hash(dev_priv->scratch_checker.hash.tfm);
+ dev_priv->scratch_checker.hash.tfm = NULL;
+}
+
+static void scratch_checker_fini(struct drm_i915_private *dev_priv)
+{
+ if (dev_priv->scratch_checker.hash.tfm)
+ return;
+
+ del_timer_sync(&dev_priv->scratch_checker.timer);
+ crypto_free_hash(dev_priv->scratch_checker.hash.tfm);
+}
+
static int setup_scratch_page(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -682,6 +748,7 @@ static int setup_scratch_page(struct drm_device *dev)
#endif
dev_priv->gtt.scratch_page = page;
dev_priv->gtt.scratch_page_dma = dma_addr;
+ scratch_checker_init(dev_priv);
return 0;
}
@@ -689,6 +756,7 @@ static int setup_scratch_page(struct drm_device *dev)
static void teardown_scratch_page(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ scratch_checker_fini(dev_priv);
set_pages_wb(dev_priv->gtt.scratch_page, 1);
pci_unmap_page(dev->pdev, dev_priv->gtt.scratch_page_dma,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
@@ -811,6 +879,7 @@ static void i915_gmch_remove(struct drm_device *dev)
intel_gmch_remove();
}
+
int i915_gem_gtt_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -840,5 +909,9 @@ int i915_gem_gtt_init(struct drm_device *dev)
DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n",
dev_priv->gtt.stolen_size >> 20);
+ if (i915_enable_scratch_checker)
+ mod_timer(&dev_priv->scratch_checker.timer,
+ jiffies + I915_SCRATCH_DIRT_JIFFIES);
+
return 0;
}
--
1.8.2.1
