drm/i915: Introduce mapping of user pages into video memory (userptr) ioctl

By exporting the ability to map user address and inserting PTEs
representing their backing pages into the GTT, we can exploit UMA in order
to utilize normal application data as a texture source or even as a
render target (depending upon the capabilities of the chipset). This has
a number of uses, with zero-copy downloads to the GPU and efficient
readback making the intermixed streaming of CPU and GPU operations
fairly efficient. This ability has many widespread implications from
faster rendering of client-side software rasterisers (chromium),
mitigation of stalls due to read back (firefox) and to faster pipelining
of texture data (such as pixel buffer objects in GL or data blobs in CL).

v2: Compile with CONFIG_MMU_NOTIFIER
v3: We can sleep while performing invalidate-range, which we can utilise
to drop our page references prior to the kernel manipulating the vma
(for either discard or cloning) and so protect normal users.
v4: Only run the invalidate notifier if the range intercepts the bo.
v5: Prevent userspace from attempting to GTT mmap non-page aligned buffers
v6: Recheck after reacquire mutex for lost mmu.
v7: Fix implicit padding of ioctl struct by rounding to next 64bit boundary.
v8: Fix rebasing error after forwarding porting the back port.
v9: Limit the userptr to page aligned entries. We now expect userspace
    to handle all the offset-in-page adjustments itself.
v10: Prevent vma from being copied across fork to avoid issues with cow.
v11: Drop vma behaviour changes -- locking is nigh on impossible.
     Use a worker to load user pages to avoid lock inversions.
v12: Use get_task_mm()/mmput() for correct refcounting of mm.
v13: Use a worker to release the mmu_notifier to avoid lock inversion
v14: Decouple mmu_notifier from struct_mutex using a custom mmu_notifer
     with its own locking and tree of objects for each mm/mmu_notifier.
v15: Prevent overlapping userptr objects, and invalidate all objects
     within the mmu_notifier range
v16: Fix a typo for iterating over multiple objects in the range and
     rearrange error path to destroy the mmu_notifier locklessly.
     Also close a race between invalidate_range and the get_pages_worker.
v17: Close a race between get_pages_worker/invalidate_range and fresh
     allocations of the same userptr range - and notice that
     struct_mutex was presumed to be held when during creation it wasn't.
v18: Sigh. Fix the refactor of st_set_pages() to allocate enough memory
     for the struct sg_table and to clear it before reporting an error.
v19: Always error out on read-only userptr requests as we don't have the
     hardware infrastructure to support them at the moment.
v20: Refuse to implement read-only support until we have the required
     infrastructure - but reserve the bit in flags for future use.
v21: use_mm() is not required for get_user_pages(). It is only meant to
     be used to fix up the kernel thread's current->mm for use with
     copy_user().
v22: Use sg_alloc_table_from_pages for that chunky feeling
v23: Export a function for sanity checking dma-buf rather than encode
     userptr details elsewhere, and clean up comments based on
     suggestions by Bradley.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: "Gong, Zhipeng" <zhipeng.gong@intel.com>
Cc: Akash Goel <akash.goel@intel.com>
Cc: "Volkin, Bradley D" <bradley.d.volkin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Brad Volkin <bradley.d.volkin@intel.com>
[danvet: Frob ioctl allocation to pick the next one - will cause a bit
of fuss with create2 apparently, but such are the rules.]
[danvet2: oops, forgot to git add after manual patch application]
[danvet3: Appease sparse.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 24 insertions, 1 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9e9e8166a1f3..a270e0773e2d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -41,6 +41,7 @@
 #include <linux/i2c-algo-bit.h>
 #include <drm/intel-gtt.h>
 #include <linux/backlight.h>
+#include <linux/hashtable.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
 #include <linux/pm_qos.h>
@@ -178,6 +179,7 @@ enum hpd_pin {
                 if ((intel_connector)->base.encoder == (__encoder))
 
 struct drm_i915_private;
+struct i915_mmu_object;
 
 enum intel_dpll_id {
         DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */
@@ -403,6 +405,7 @@ struct drm_i915_error_state {
                 u32 tiling:2;
                 u32 dirty:1;
                 u32 purgeable:1;
+                u32 userptr:1;
                 s32 ring:4;
                 u32 cache_level:3;
         } **active_bo, **pinned_bo;
@@ -1447,6 +1450,9 @@ struct drm_i915_private {
         struct i915_gtt gtt; /* VM representing the global address space */
 
         struct i915_gem_mm mm;
+#if defined(CONFIG_MMU_NOTIFIER)
+        DECLARE_HASHTABLE(mmu_notifiers, 7);
+#endif
 
         /* Kernel Modesetting */
 
@@ -1580,6 +1586,8 @@ struct drm_i915_gem_object_ops {
          */
         int (*get_pages)(struct drm_i915_gem_object *);
         void (*put_pages)(struct drm_i915_gem_object *);
+        int (*dmabuf_export)(struct drm_i915_gem_object *);
+        void (*release)(struct drm_i915_gem_object *);
 };
 
 struct drm_i915_gem_object {
@@ -1693,8 +1701,20 @@ struct drm_i915_gem_object {
 
         /** for phy allocated objects */
         struct drm_i915_gem_phys_object *phys_obj;
-};
 
+        union {
+                struct i915_gem_userptr {
+                        uintptr_t ptr;
+                        unsigned read_only :1;
+                        unsigned workers :4;
+#define I915_GEM_USERPTR_MAX_WORKERS 15
+
+                        struct mm_struct *mm;
+                        struct i915_mmu_object *mn;
+                        struct work_struct *work;
+                } userptr;
+        };
+};
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
 /**
@@ -2119,6 +2139,9 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data,
                         struct drm_file *file_priv);
 int i915_gem_get_tiling(struct drm_device *dev, void *data,
                         struct drm_file *file_priv);
+int i915_gem_init_userptr(struct drm_device *dev);
+int i915_gem_userptr_ioctl(struct drm_device *dev, void *data,
+                           struct drm_file *file);
 int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
                                 struct drm_file *file_priv);
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,