Re: [PATCH 5/5] drm/i915: l3 parity sysfs interface

[Daniel Vetter <daniel@ffwll.ch>]

On Fri, Apr 27, 2012 at 05:40:21PM -0700, Ben Widawsky wrote:
> Dumb binary interfaces which allow root-only updates of the cache
> remapping registers. As mentioned in a previous patch, software using
> this interface needs to know about HW limits, and other programming
> considerations as the kernel interface does no checking for these things
> on the root-only interface.
> 
> v1: Drop extra posting reads (Chris)
> Return negative values in the sysfs interfaces on errors (Chris)
> 
> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> ---
>  drivers/gpu/drm/i915/i915_sysfs.c |  128 ++++++++++++++++++++++++++++++++++++-
>  1 file changed, 126 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
> index 79f8344..ed77cbf 100644
> --- a/drivers/gpu/drm/i915/i915_sysfs.c
> +++ b/drivers/gpu/drm/i915/i915_sysfs.c
> @@ -29,6 +29,7 @@
>  #include <linux/module.h>
>  #include <linux/stat.h>
>  #include <linux/sysfs.h>
> +#include "intel_drv.h"
>  #include "i915_drv.h"
>  
>  static u32 calc_residency(struct drm_device *dev, const u32 reg)
> @@ -92,20 +93,143 @@ static struct attribute_group rc6_attr_group = {
>  	.attrs =  rc6_attrs
>  };
>  
> +static int l3_access_valid(struct drm_device *dev, loff_t offset)
> +{
> +	if (!IS_IVYBRIDGE(dev))
> +		return -EPERM;
> +
> +	if (offset % 4 != 0)
> +		return -EPERM;
> +
> +	if (offset >= GEN7_L3LOG_SIZE)
> +		return -ENXIO;
> +
> +	return 0;
> +}
> +
> +static ssize_t
> +i915_l3_read(struct file *filp, struct kobject *kobj,
> +	     struct bin_attribute *attr, char *buf,
> +	     loff_t offset, size_t count)
> +{
> +	struct device *dev = container_of(kobj, struct device, kobj);
> +	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
> +	struct drm_device *drm_dev = dminor->dev;
> +	struct drm_i915_private *dev_priv = drm_dev->dev_private;
> +	uint32_t misccpctl;
> +	int i, ret;
> +
> +	ret = l3_access_valid(drm_dev, offset);
> +	if (ret)
> +		return ret;
> +
> +	ret = i915_mutex_lock_interruptible(drm_dev);
> +	if (ret)
> +		return ret;
> +
> +	misccpctl = I915_READ(GEN7_MISCCPCTL);
> +	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
> +
> +	for (i = offset; count >= 4 && i < GEN7_L3LOG_SIZE; i += 4, count -= 4)
> +		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + i);
> +
> +	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
> +
> +	mutex_unlock(&drm_dev->struct_mutex);
> +
> +	return i - offset;
> +}
> +
> +static ssize_t
> +i915_l3_write(struct file *filp, struct kobject *kobj,
> +	      struct bin_attribute *attr, char *buf,
> +	      loff_t offset, size_t count)
> +{
> +	struct device *dev = container_of(kobj, struct device, kobj);
> +	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
> +	struct drm_device *drm_dev = dminor->dev;
> +	struct drm_i915_private *dev_priv = drm_dev->dev_private;
> +	u32 *temp = NULL;
> +	int i, ret;
> +
> +	ret = l3_access_valid(drm_dev, offset);
> +	if (ret)
> +		return ret;
> +
> +	ret = i915_mutex_lock_interruptible(drm_dev);
> +	if (ret)
> +		return ret;
> +
> +	if (!dev_priv->mm.l3_remap_info) {
> +		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
> +		if (!temp) {
> +			mutex_unlock(&drm_dev->struct_mutex);
> +			return -ENOMEM;
> +		}
> +	}
> +
> +	ret = i915_gpu_idle(drm_dev, true);
> +	if (ret) {
> +		kfree(temp);
> +		mutex_unlock(&drm_dev->struct_mutex);
> +		return ret;
> +	}
> +
> +	/* TODO: Ideally we really want a GPU reset here to make sure errors
> +	 * aren't propagated Since I cannot find a stable way to reset the GPU
> +	 * at this point it is left as a TODO.
> +	*/
> +
> +	if (dev_priv->mm.l3_remap_info)
> +		temp = dev_priv->mm.l3_remap_info;
> +
> +	dev_priv->mm.l3_remap_info = temp;
> +
> +	for (i = offset; count >= 4 && i < GEN7_L3LOG_SIZE; i += 4, count -= 4) {
> +		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
> +		if (remap && remap != *temp)
> +			DRM_ERROR("0x%x was already programmed to %x\n",
> +				  GEN7_L3LOG_BASE + i, remap);
> +		*temp++ = *(uint32_t *)(&buf[i]);
> +	}
> +
> +	i915_gem_l3_remap(drm_dev);
> +
> +	mutex_unlock(&drm_dev->struct_mutex);
> +
> +	return offset - i;
> +}
> +
> +static struct bin_attribute dpf_attrs = {
> +	.attr = {.name = "l3_parity", .mode = (S_IRUSR | S_IWUSR)},
> +	.size = GEN7_L3LOG_SIZE,
> +	.read = i915_l3_read,
> +	.write = i915_l3_write,
> +	.mmap = NULL
> +};
> +
>  void i915_setup_sysfs(struct drm_device *dev)
>  {
>  	int ret;
>  
> -	/* ILK doesn't have any residency information */
> +	/* ILK and below don't yet have relevant sysfs files */
>  	if (INTEL_INFO(dev)->gen < 6)
>  		return;
>  
>  	ret = sysfs_merge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
>  	if (ret)
> -		DRM_ERROR("sysfs setup failed\n");
> +		DRM_ERROR("RC6 residency sysfs setup failed\n");
> +
> +	if (!IS_IVYBRIDGE(dev))
> +		return;
> +
> +	ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
> +	if (ret)
> +		DRM_ERROR("l3 parity sysfs setup failed\n");

Imo these checks are confusing, usually we check for features instead of
their absence and enclose the relevant code in the if block, i.e.

if (gen >= 6)
	merge_rc6_residency_stuff;

if (IS_IVB)
	merge_dpf_attrs_file;

-Daniel

>  }
>  
>  void i915_teardown_sysfs(struct drm_device *dev)
>  {
> +	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
>  	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
>  }
> -- 
> 1.7.10
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Mail: daniel@ffwll.ch
Mobile: +41 (0)79 365 57 48