This commit adds the notion of MMU notifier types GFX and HSA. GFX
continues to work like MMU notifiers did before. HSA adds support for
KFD userptr BOs. The implementation of KFD userptr eviction is a stub
for now.
Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 7 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 94 ++++++++++++++++++++----
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h | 11 ++-
5 files changed, 97 insertions(+), 18 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index c2c2bea..83e0c5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -104,6 +104,7 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev);
+int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
uint32_t vmid, uint64_t gpu_addr,
uint32_t *ib_cmd, uint32_t ib_len);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 2f42c60..2d6f13a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1418,6 +1418,13 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
return ret;
}
+int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem,
+ struct mm_struct *mm)
+{
+ /* TODO */
+ return 0;
+}
+
/** amdgpu_amdkfd_gpuvm_restore_process_bos - Restore all BOs for the given
* KFD process identified by process_info
*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dc34b50..8e66f37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -536,7 +536,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
if (p->bo_list) {
amdgpu_bo_list_get_list(p->bo_list, &p->validated);
if (p->bo_list->first_userptr != p->bo_list->num_entries)
- p->mn = amdgpu_mn_get(p->adev);
+ p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
}
INIT_LIST_HEAD(&duplicates);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index bd67f4c..f2ed18e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -36,12 +36,14 @@
#include <drm/drm.h>
#include "amdgpu.h"
+#include "amdgpu_amdkfd.h"
struct amdgpu_mn {
/* constant after initialisation */
struct amdgpu_device *adev;
struct mm_struct *mm;
struct mmu_notifier mn;
+ enum amdgpu_mn_type type;
/* only used on destruction */
struct work_struct work;
@@ -185,7 +187,7 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
}
/**
- * amdgpu_mn_invalidate_range_start - callback to notify about mm change
+ * amdgpu_mn_invalidate_range_start_gfx - callback to notify about mm change
*
* @mn: our notifier
* @mn: the mm this callback is about
@@ -195,10 +197,10 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
* We block for all BOs between start and end to be idle and
* unmap them by move them into system domain again.
*/
-static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
- struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
+static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
{
struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
struct interval_tree_node *it;
@@ -220,6 +222,49 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
}
/**
+ * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ * @start: start of updated range
+ * @end: end of updated range
+ *
+ * We temporarily evict all BOs between start and end. This
+ * necessitates evicting all user-mode queues of the process. The BOs
+ * are restorted in amdgpu_mn_invalidate_range_end_hsa.
+ */
+static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+ struct interval_tree_node *it;
+
+ /* notification is exclusive, but interval is inclusive */
+ end -= 1;
+
+ amdgpu_mn_read_lock(rmn);
+
+ it = interval_tree_iter_first(&rmn->objects, start, end);
+ while (it) {
+ struct amdgpu_mn_node *node;
+ struct amdgpu_bo *bo;
+
+ node = container_of(it, struct amdgpu_mn_node, it);
+ it = interval_tree_iter_next(it, start, end);
+
+ list_for_each_entry(bo, &node->bos, mn_list) {
+ struct kgd_mem *mem = bo->kfd_bo;
+
+ if (amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm,
+ start, end))
+ amdgpu_amdkfd_evict_userptr(mem, mm);
+ }
+ }
+}
+
+/**
* amdgpu_mn_invalidate_range_end - callback to notify about mm change
*
* @mn: our notifier
@@ -239,23 +284,39 @@ static void amdgpu_mn_invalidate_range_end(struct mmu_notifier *mn,
amdgpu_mn_read_unlock(rmn);
}
-static const struct mmu_notifier_ops amdgpu_mn_ops = {
- .release = amdgpu_mn_release,
- .invalidate_range_start = amdgpu_mn_invalidate_range_start,
- .invalidate_range_end = amdgpu_mn_invalidate_range_end,
+static const struct mmu_notifier_ops amdgpu_mn_ops[] = {
+ [AMDGPU_MN_TYPE_GFX] = {
+ .release = amdgpu_mn_release,
+ .invalidate_range_start = amdgpu_mn_invalidate_range_start_gfx,
+ .invalidate_range_end = amdgpu_mn_invalidate_range_end,
+ },
+ [AMDGPU_MN_TYPE_HSA] = {
+ .release = amdgpu_mn_release,
+ .invalidate_range_start = amdgpu_mn_invalidate_range_start_hsa,
+ .invalidate_range_end = amdgpu_mn_invalidate_range_end,
+ },
};
+/* Low bits of any reasonable mm pointer will be unused due to struct
+ * alignment. Use these bits to make a unique key from the mm pointer
+ * and notifier type.
+ */
+#define AMDGPU_MN_KEY(mm, type) ((unsigned long)(mm) + (type))
+
/**
* amdgpu_mn_get - create notifier context
*
* @adev: amdgpu device pointer
+ * @type: type of MMU notifier context
*
* Creates a notifier context for current->mm.
*/
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
+struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+ enum amdgpu_mn_type type)
{
struct mm_struct *mm = current->mm;
struct amdgpu_mn *rmn;
+ unsigned long key = AMDGPU_MN_KEY(mm, type);
int r;
mutex_lock(&adev->mn_lock);
@@ -264,8 +325,8 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
return ERR_PTR(-EINTR);
}
- hash_for_each_possible(adev->mn_hash, rmn, node, (unsigned long)mm)
- if (rmn->mm == mm)
+ hash_for_each_possible(adev->mn_hash, rmn, node, key)
+ if (AMDGPU_MN_KEY(rmn->mm, rmn->type) == key)
goto release_locks;
rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
@@ -276,8 +337,9 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
rmn->adev = adev;
rmn->mm = mm;
- rmn->mn.ops = &amdgpu_mn_ops;
init_rwsem(&rmn->lock);
+ rmn->type = type;
+ rmn->mn.ops = &amdgpu_mn_ops[type];
rmn->objects = RB_ROOT_CACHED;
mutex_init(&rmn->read_lock);
atomic_set(&rmn->recursion, 0);
@@ -286,7 +348,7 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
if (r)
goto free_rmn;
- hash_add(adev->mn_hash, &rmn->node, (unsigned long)mm);
+ hash_add(adev->mn_hash, &rmn->node, AMDGPU_MN_KEY(mm, type));
release_locks:
up_write(&mm->mmap_sem);
@@ -315,12 +377,14 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
{
unsigned long end = addr + amdgpu_bo_size(bo) - 1;
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ enum amdgpu_mn_type type =
+ bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
struct amdgpu_mn *rmn;
struct amdgpu_mn_node *node = NULL;
struct list_head bos;
struct interval_tree_node *it;
- rmn = amdgpu_mn_get(adev);
+ rmn = amdgpu_mn_get(adev, type);
if (IS_ERR(rmn))
return PTR_ERR(rmn);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index d0095a3..eb0f432 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
@@ -29,16 +29,23 @@
*/
struct amdgpu_mn;
+enum amdgpu_mn_type {
+ AMDGPU_MN_TYPE_GFX,
+ AMDGPU_MN_TYPE_HSA,
+};
+
#if defined(CONFIG_MMU_NOTIFIER)
void amdgpu_mn_lock(struct amdgpu_mn *mn);
void amdgpu_mn_unlock(struct amdgpu_mn *mn);
-struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev);
+struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+ enum amdgpu_mn_type type);
int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr);
void amdgpu_mn_unregister(struct amdgpu_bo *bo);
#else
static inline void amdgpu_mn_lock(struct amdgpu_mn *mn) {}
static inline void amdgpu_mn_unlock(struct amdgpu_mn *mn) {}
-static inline struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev)
+static inline struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
+ enum amdgpu_mn_type type)
{
return NULL;
}
--
2.7.4
