[Intel-gfx] [PATCH 06/16] drm/i915/vm_bind: Support for VM private BOs
Niranjana Vishwanathapura
niranjana.vishwanathapura at intel.com
Wed Sep 28 06:19:08 UTC 2022
Each VM creates a root_obj and shares it with all of its private objects
to use it as dma_resv object. This has a performance advantage as it
requires a single dma_resv object update for all private BOs vs list of
dma_resv objects update for shared BOs, in the execbuf path.
VM private BOs can be only mapped on specified VM and cannot be dmabuf
exported. Also, they are supported only in vm_bind mode.
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura at intel.com>
Signed-off-by: Andi Shyti <andi.shyti at linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_create.c | 41 ++++++++++++++++++-
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 6 +++
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 4 ++
drivers/gpu/drm/i915/gem/i915_gem_object.c | 3 ++
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 3 ++
.../drm/i915/gem/i915_gem_vm_bind_object.c | 9 ++++
drivers/gpu/drm/i915/gt/intel_gtt.c | 4 ++
drivers/gpu/drm/i915/gt/intel_gtt.h | 2 +
drivers/gpu/drm/i915/i915_vma.c | 1 +
drivers/gpu/drm/i915/i915_vma_types.h | 2 +
include/uapi/drm/i915_drm.h | 30 ++++++++++++++
12 files changed, 106 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index 4aa7b5582b8e..692d95ef5d3e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -11,6 +11,7 @@
#include "pxp/intel_pxp.h"
#include "i915_drv.h"
+#include "i915_gem_context.h"
#include "i915_gem_create.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
@@ -252,6 +253,7 @@ struct create_ext {
unsigned int n_placements;
unsigned int placement_mask;
unsigned long flags;
+ u32 vm_id;
};
static void repr_placements(char *buf, size_t size,
@@ -401,9 +403,24 @@ static int ext_set_protected(struct i915_user_extension __user *base, void *data
return 0;
}
+static int ext_set_vm_private(struct i915_user_extension __user *base,
+ void *data)
+{
+ struct drm_i915_gem_create_ext_vm_private ext;
+ struct create_ext *ext_data = data;
+
+ if (copy_from_user(&ext, base, sizeof(ext)))
+ return -EFAULT;
+
+ ext_data->vm_id = ext.vm_id;
+
+ return 0;
+}
+
static const i915_user_extension_fn create_extensions[] = {
[I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements,
[I915_GEM_CREATE_EXT_PROTECTED_CONTENT] = ext_set_protected,
+ [I915_GEM_CREATE_EXT_VM_PRIVATE] = ext_set_vm_private,
};
/**
@@ -419,6 +436,7 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
struct drm_i915_private *i915 = to_i915(dev);
struct drm_i915_gem_create_ext *args = data;
struct create_ext ext_data = { .i915 = i915 };
+ struct i915_address_space *vm = NULL;
struct drm_i915_gem_object *obj;
int ret;
@@ -432,6 +450,12 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
if (ret)
return ret;
+ if (ext_data.vm_id) {
+ vm = i915_gem_vm_lookup(file->driver_priv, ext_data.vm_id);
+ if (unlikely(!vm))
+ return -ENOENT;
+ }
+
if (!ext_data.n_placements) {
ext_data.placements[0] =
intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM);
@@ -458,8 +482,21 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data,
ext_data.placements,
ext_data.n_placements,
ext_data.flags);
- if (IS_ERR(obj))
- return PTR_ERR(obj);
+ if (IS_ERR(obj)) {
+ ret = PTR_ERR(obj);
+ goto vm_put;
+ }
+
+ if (vm) {
+ obj->base.resv = vm->root_obj->base.resv;
+ obj->priv_root = i915_gem_object_get(vm->root_obj);
+ i915_vm_put(vm);
+ }
return i915_gem_publish(obj, file, &args->size, &args->handle);
+vm_put:
+ if (vm)
+ i915_vm_put(vm);
+
+ return ret;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index f5062d0c6333..6433173c3e84 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -218,6 +218,12 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+ if (obj->priv_root) {
+ drm_dbg(obj->base.dev,
+ "Exporting VM private objects is not allowed\n");
+ return ERR_PTR(-EINVAL);
+ }
+
exp_info.ops = &i915_dmabuf_ops;
exp_info.size = gem_obj->size;
exp_info.flags = flags;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index f85f10cf9c34..33d989a20227 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -864,6 +864,10 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
if (unlikely(!obj))
return ERR_PTR(-ENOENT);
+ /* VM private objects are not supported here */
+ if (obj->priv_root)
+ return ERR_PTR(-EINVAL);
+
/*
* If the user has opted-in for protected-object tracking, make
* sure the object encryption can be used.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 7ff9c7877bec..271ad62b3245 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -108,6 +108,9 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
*/
void __i915_gem_object_fini(struct drm_i915_gem_object *obj)
{
+ if (obj->priv_root && !obj->ttm.created)
+ i915_gem_object_put(obj->priv_root);
+
mutex_destroy(&obj->mm.get_page.lock);
mutex_destroy(&obj->mm.get_dma_page.lock);
dma_resv_fini(&obj->base._resv);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 40305e2bcd49..2e79cfc0b06a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -241,6 +241,9 @@ struct drm_i915_gem_object {
const struct drm_i915_gem_object_ops *ops;
+ /* For VM private BO, points to root_obj in VM. NULL otherwise */
+ struct drm_i915_gem_object *priv_root;
+
struct {
/**
* @vma.lock: protect the list/tree of vmas
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index e3fc38dd5db0..b4d8cb33df8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -1153,6 +1153,9 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo)
mutex_destroy(&obj->ttm.get_io_page.lock);
if (obj->ttm.created) {
+ if (obj->priv_root)
+ i915_gem_object_put(obj->priv_root);
+
/*
* We freely manage the shrinker LRU outide of the mm.pages life
* cycle. As a result when destroying the object we should be
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c
index e529162abd2c..809c78455d2e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_vm_bind_object.c
@@ -86,6 +86,7 @@ static void i915_gem_vm_bind_remove(struct i915_vma *vma, bool release_obj)
lockdep_assert_held(&vma->vm->vm_bind_lock);
list_del_init(&vma->vm_bind_link);
+ list_del_init(&vma->non_priv_vm_bind_link);
i915_vm_bind_it_remove(vma, &vma->vm->va);
/* Release object */
@@ -205,6 +206,11 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm,
goto put_obj;
}
+ if (obj->priv_root && obj->priv_root != vm->root_obj) {
+ ret = -EINVAL;
+ goto put_obj;
+ }
+
ret = mutex_lock_interruptible(&vm->vm_bind_lock);
if (ret)
goto put_obj;
@@ -231,6 +237,9 @@ static int i915_gem_vm_bind_obj(struct i915_address_space *vm,
list_add_tail(&vma->vm_bind_link, &vm->vm_bound_list);
i915_vm_bind_it_insert(vma, &vm->va);
+ if (!obj->priv_root)
+ list_add_tail(&vma->non_priv_vm_bind_link,
+ &vm->non_priv_vm_bind_list);
/* Hold object reference until vm_unbind */
i915_gem_object_get(vma->obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 0daa70c6ed0d..da4f9dee0397 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -177,6 +177,7 @@ int i915_vm_lock_objects(struct i915_address_space *vm,
void i915_address_space_fini(struct i915_address_space *vm)
{
drm_mm_takedown(&vm->mm);
+ i915_gem_object_put(vm->root_obj);
GEM_BUG_ON(!RB_EMPTY_ROOT(&vm->va.rb_root));
mutex_destroy(&vm->vm_bind_lock);
}
@@ -292,6 +293,9 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass)
INIT_LIST_HEAD(&vm->vm_bind_list);
INIT_LIST_HEAD(&vm->vm_bound_list);
mutex_init(&vm->vm_bind_lock);
+ INIT_LIST_HEAD(&vm->non_priv_vm_bind_list);
+ vm->root_obj = i915_gem_object_create_internal(vm->i915, PAGE_SIZE);
+ GEM_BUG_ON(IS_ERR(vm->root_obj));
}
void *__px_vaddr(struct drm_i915_gem_object *p)
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index b52061858161..3f2e87d3bf34 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -275,6 +275,8 @@ struct i915_address_space {
struct list_head vm_bound_list;
/* @va: tree of persistent vmas */
struct rb_root_cached va;
+ struct list_head non_priv_vm_bind_list;
+ struct drm_i915_gem_object *root_obj;
/* Global GTT */
bool is_ggtt:1;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 33f910473263..89c276163916 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -240,6 +240,7 @@ vma_create(struct drm_i915_gem_object *obj,
mutex_unlock(&vm->mutex);
INIT_LIST_HEAD(&vma->vm_bind_link);
+ INIT_LIST_HEAD(&vma->non_priv_vm_bind_link);
return vma;
err_unlock:
diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h
index f56ac07c6cfa..3d5ffc3e666b 100644
--- a/drivers/gpu/drm/i915/i915_vma_types.h
+++ b/drivers/gpu/drm/i915/i915_vma_types.h
@@ -298,6 +298,8 @@ struct i915_vma {
/** @vm_bind_link: node for the vm_bind related lists of vm */
struct list_head vm_bind_link;
+ /* @non_priv_vm_bind_link: Link in non-private persistent VMA list */
+ struct list_head non_priv_vm_bind_link;
/** Interval tree structures for persistent vma */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 9760564b4693..3eee3071ad60 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -3601,9 +3601,13 @@ struct drm_i915_gem_create_ext {
*
* For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
* struct drm_i915_gem_create_ext_protected_content.
+ *
+ * For I915_GEM_CREATE_EXT_VM_PRIVATE usage see
+ * struct drm_i915_gem_create_ext_vm_private.
*/
#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_VM_PRIVATE 2
__u64 extensions;
};
@@ -3721,6 +3725,32 @@ struct drm_i915_gem_create_ext_protected_content {
/* ID of the protected content session managed by i915 when PXP is active */
#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+/**
+ * struct drm_i915_gem_create_ext_vm_private - Extension to make the object
+ * private to the specified VM.
+ *
+ * See struct drm_i915_gem_create_ext.
+ *
+ * By default, BOs can be mapped on multiple VMs and can also be dma-buf
+ * exported. Hence these BOs are referred to as Shared BOs.
+ * During each execbuf3 submission, the request fence must be added to the
+ * dma-resv fence list of all shared BOs mapped on the VM.
+ *
+ * Unlike Shared BOs, these VM private BOs can only be mapped on the VM they
+ * are private to and can't be dma-buf exported. All private BOs of a VM share
+ * the dma-resv object. Hence during each execbuf3 submission, they need only
+ * one dma-resv fence list updated. Thus, the fast path (where required
+ * mappings are already bound) submission latency is O(1) w.r.t the number of
+ * VM private BOs.
+ */
+struct drm_i915_gem_create_ext_vm_private {
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+
+ /** @vm_id: Id of the VM to which Object is private */
+ __u32 vm_id;
+};
+
/**
* struct drm_i915_gem_vm_bind - VA to object mapping to bind.
*
--
2.21.0.rc0.32.g243a4c7e27
More information about the Intel-gfx
mailing list