drm/radeon: add userptr support v8

This patch adds an IOCTL for turning a pointer supplied by
userspace into a buffer object.

It imposes several restrictions upon the memory being mapped:

1. It must be page aligned (both start/end addresses, i.e ptr and size).

2. It must be normal system memory, not a pointer into another map of IO
space (e.g. it must not be a GTT mmapping of another object).

3. The BO is mapped into GTT, so the maximum amount of memory mapped at
all times is still the GTT limit.

4. The BO is only mapped readonly for now, so no write support.

5. List of backing pages is only acquired once, so they represent a
snapshot of the first use.

Exporting and sharing as well as mapping of buffer objects created by
this function is forbidden and results in an -EPERM.

v2: squash all previous changes into first public version
v3: fix tabs, map readonly, don't use MM callback any more
v4: set TTM_PAGE_FLAG_SG so that TTM never messes with the pages,
    pin/unpin pages on bind/unbind instead of populate/unpopulate
v5: rebased on 3.17-wip, IOCTL renamed to userptr, reject any unknown
    flags, better handle READONLY flag, improve permission check
v6: fix ptr cast warning, use set_page_dirty/mark_page_accessed on unpin
v7: add warning about it's availability in the API definition
v8: drop access_ok check, fix VM mapping bits

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v4)
Reviewed-by: Jérôme Glisse <jglisse@redhat.com> (v4)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

10 files changed, 279 insertions, 3 deletions

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9e1732eb402c..6f38a23a5810 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2138,6 +2138,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
                           struct drm_file *filp);
 int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
                             struct drm_file *filp);
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+                             struct drm_file *filp);
 int radeon_gem_pin_ioctl(struct drm_device *dev, void *data,
                          struct drm_file *file_priv);
 int radeon_gem_unpin_ioctl(struct drm_device *dev, void *data,
@@ -2871,6 +2873,10 @@ extern void radeon_legacy_set_clock_gating(struct radeon_device *rdev, int enabl
 extern void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable);
 extern void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain);
 extern bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo);
+extern int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
+                                     uint32_t flags);
+extern bool radeon_ttm_tt_has_userptr(struct ttm_tt *ttm);
+extern bool radeon_ttm_tt_is_readonly(struct ttm_tt *ttm);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ee712c199b25..1321491cf499 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -78,7 +78,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
         struct radeon_cs_chunk *chunk;
         struct radeon_cs_buckets buckets;
         unsigned i, j;
-        bool duplicate;
+        bool duplicate, need_mmap_lock = false;
+        int r;
 
         if (p->chunk_relocs_idx == -1) {
                 return 0;
@@ -164,6 +165,19 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
                         p->relocs[i].allowed_domains = domain;
                 }
 
+                if (radeon_ttm_tt_has_userptr(p->relocs[i].robj->tbo.ttm)) {
+                        uint32_t domain = p->relocs[i].prefered_domains;
+                        if (!(domain & RADEON_GEM_DOMAIN_GTT)) {
+                                DRM_ERROR("Only RADEON_GEM_DOMAIN_GTT is "
+                                          "allowed for userptr BOs\n");
+                                return -EINVAL;
+                        }
+                        need_mmap_lock = true;
+                        domain = RADEON_GEM_DOMAIN_GTT;
+                        p->relocs[i].prefered_domains = domain;
+                        p->relocs[i].allowed_domains = domain;
+                }
+
                 p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
                 p->relocs[i].handle = r->handle;
 
@@ -176,8 +190,15 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
         if (p->cs_flags & RADEON_CS_USE_VM)
                 p->vm_bos = radeon_vm_get_bos(p->rdev, p->ib.vm,
                                               &p->validated);
+        if (need_mmap_lock)
+                down_read(&current->mm->mmap_sem);
+
+        r = radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
 
-        return radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
+        if (need_mmap_lock)
+                up_read(&current->mm->mmap_sem);
+
+        return r;
 }
 
 static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority)
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index a773830c6c40..5b18af926527 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -114,6 +114,9 @@ int radeon_gem_object_open(struct drm_gem_object *obj,
                                 struct drm_file *file_priv);
 void radeon_gem_object_close(struct drm_gem_object *obj,
                                 struct drm_file *file_priv);
+struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
+                                        struct drm_gem_object *gobj,
+                                        int flags);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
                                       unsigned int flags,
                                       int *vpos, int *hpos, ktime_t *stime,
@@ -568,7 +571,7 @@ static struct drm_driver kms_driver = {
 
         .prime_handle_to_fd = drm_gem_prime_handle_to_fd,
         .prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-        .gem_prime_export = drm_gem_prime_export,
+        .gem_prime_export = radeon_gem_prime_export,
         .gem_prime_import = drm_gem_prime_import,
         .gem_prime_pin = radeon_gem_prime_pin,
         .gem_prime_unpin = radeon_gem_prime_unpin,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index bfd7e1b0ff3f..993ab223b503 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -272,6 +272,65 @@ int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
         return 0;
 }
 
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+                             struct drm_file *filp)
+{
+        struct radeon_device *rdev = dev->dev_private;
+        struct drm_radeon_gem_userptr *args = data;
+        struct drm_gem_object *gobj;
+        struct radeon_bo *bo;
+        uint32_t handle;
+        int r;
+
+        if (offset_in_page(args->addr | args->size))
+                return -EINVAL;
+
+        /* we only support read only mappings for now */
+        if (!(args->flags & RADEON_GEM_USERPTR_READONLY))
+                return -EACCES;
+
+        /* reject unknown flag values */
+        if (args->flags & ~RADEON_GEM_USERPTR_READONLY)
+                return -EINVAL;
+
+        /* readonly pages not tested on older hardware */
+        if (rdev->family < CHIP_R600)
+                return -EINVAL;
+
+        down_read(&rdev->exclusive_lock);
+
+        /* create a gem object to contain this object in */
+        r = radeon_gem_object_create(rdev, args->size, 0,
+                                     RADEON_GEM_DOMAIN_CPU, 0,
+                                     false, &gobj);
+        if (r)
+                goto handle_lockup;
+
+        bo = gem_to_radeon_bo(gobj);
+        r = radeon_ttm_tt_set_userptr(bo->tbo.ttm, args->addr, args->flags);
+        if (r)
+                goto release_object;
+
+        r = drm_gem_handle_create(filp, gobj, &handle);
+        /* drop reference from allocate - handle holds it now */
+        drm_gem_object_unreference_unlocked(gobj);
+        if (r)
+                goto handle_lockup;
+