Queue CWSR area maybe registered to GPU as svm memory, create queue to
ensure svm mapped to GPU with KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED flag.
Add queue_refcount to struct svm_range, to track queue CWSR area usage.
Because unmap mmu notifier callback return value is ignored, if
application unmap the CWSR area while queue is active, pr_warn message
in dmesg log. To be safe, evict user queue.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 110 ++++++++++++++++++++++++-
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 12 +++
drivers/gpu/drm/amd/amdkfd/kfd_svm.h | 1 +
3 files changed, 122 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index 3fd386dcb011..67242ce051b5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include "kfd_priv.h"
+#include "kfd_svm.h"
void print_queue_properties(struct queue_properties *q)
{
@@ -83,6 +84,100 @@ void uninit_queue(struct queue *q)
kfree(q);
}
+static int kfd_queue_buffer_svm_get(struct kfd_process_device *pdd, u64 addr, u64 size)
+{
+ struct kfd_process *p = pdd->process;
+ struct list_head update_list;
+ struct svm_range *prange;
+ int ret = -EINVAL;
+
+ INIT_LIST_HEAD(&update_list);
+ addr >>= PAGE_SHIFT;
+ size >>= PAGE_SHIFT;
+
+ mutex_lock(&p->svms.lock);
+
+ /*
+ * range may split to multiple svm pranges aligned to granularity boundaery.
+ */
+ while (size) {
+ uint32_t gpuid, gpuidx;
+ int r;
+
+ prange = svm_range_from_addr(&p->svms, addr, NULL);
+ if (!prange)
+ break;
+
+ if (!prange->mapped_to_gpu)
+ break;
+
+ r = kfd_process_gpuid_from_node(p, pdd->dev, &gpuid, &gpuidx);
+ if (r < 0)
+ break;
+ if (!test_bit(gpuidx, prange->bitmap_access) &&
+ !test_bit(gpuidx, prange->bitmap_aip))
+ break;
+
+ if (!(prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED))
+ break;
+
+ list_add(&prange->update_list, &update_list);
+
+ if (prange->last - prange->start + 1 >= size) {
+ size = 0;
+ break;
+ }
+
+ size -= prange->last - prange->start + 1;
+ addr += prange->last - prange->start + 1;
+ }
+ if (size) {
+ pr_debug("[0x%llx 0x%llx] not registered\n", addr, addr + size - 1);
+ goto out_unlock;
+ }
+
+ list_for_each_entry(prange, &update_list, update_list)
+ atomic_inc(&prange->queue_refcount);
+ ret = 0;
+
+out_unlock:
+ mutex_unlock(&p->svms.lock);
+ return ret;
+}
+
+static void kfd_queue_buffer_svm_put(struct kfd_process_device *pdd, u64 addr, u64 size)
+{
+ struct kfd_process *p = pdd->process;
+ struct svm_range *prange, *pchild;
+ struct interval_tree_node *node;
+ unsigned long last;
+
+ addr >>= PAGE_SHIFT;
+ last = addr + (size >> PAGE_SHIFT) - 1;
+
+ mutex_lock(&p->svms.lock);
+
+ node = interval_tree_iter_first(&p->svms.objects, addr, last);
+ while (node) {
+ struct interval_tree_node *next_node;
+ unsigned long next_start;
+
+ prange = container_of(node, struct svm_range, it_node);
+ next_node = interval_tree_iter_next(node, addr, last);
+ next_start = min(node->last, last) + 1;
+
+ if (atomic_add_unless(&prange->queue_refcount, -1, 0)) {
+ list_for_each_entry(pchild, &prange->child_list, child_list)
+ atomic_add_unless(&pchild->queue_refcount, -1, 0);
+ }
+
+ node = next_node;
+ addr = next_start;
+ }
+
+ mutex_unlock(&p->svms.lock);
+}
+
int kfd_queue_buffer_get(struct amdgpu_vm *vm, void __user *addr, struct amdgpu_bo **pbo,
u64 expected_size)
{
@@ -165,8 +260,17 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address,
&properties->cwsr_bo, 0);
+ if (!err)
+ goto out_unreserve;
+
+ amdgpu_bo_unreserve(vm->root.bo);
+
+ err = kfd_queue_buffer_svm_get(pdd, properties->ctx_save_restore_area_address,
+ properties->ctx_save_restore_area_size);
if (err)
- goto out_err_unreserve;
+ goto out_err_release;
+
+ return 0;
out_unreserve:
amdgpu_bo_unreserve(vm->root.bo);
@@ -174,6 +278,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
out_err_unreserve:
amdgpu_bo_unreserve(vm->root.bo);
+out_err_release:
kfd_queue_release_buffers(pdd, properties);
return err;
}
@@ -195,5 +300,8 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope
kfd_queue_buffer_put(vm, &properties->cwsr_bo);
amdgpu_bo_unreserve(vm->root.bo);
+
+ kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address,
+ properties->ctx_save_restore_area_size);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index bd9c2921e0dc..2339bbdf452f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1051,6 +1051,7 @@ svm_range_split_adjust(struct svm_range *new, struct svm_range *old,
new->mapped_to_gpu = old->mapped_to_gpu;
bitmap_copy(new->bitmap_access, old->bitmap_access, MAX_GPU_INSTANCE);
bitmap_copy(new->bitmap_aip, old->bitmap_aip, MAX_GPU_INSTANCE);
+ atomic_set(&new->queue_refcount, atomic_read(&old->queue_refcount));
return 0;
}
@@ -1992,6 +1993,7 @@ static struct svm_range *svm_range_clone(struct svm_range *old)
new->vram_pages = old->vram_pages;
bitmap_copy(new->bitmap_access, old->bitmap_access, MAX_GPU_INSTANCE);
bitmap_copy(new->bitmap_aip, old->bitmap_aip, MAX_GPU_INSTANCE);
+ atomic_set(&new->queue_refcount, atomic_read(&old->queue_refcount));
return new;
}
@@ -2444,6 +2446,16 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
unsigned long s, l;
bool unmap_parent;
+ if (atomic_read(&prange->queue_refcount)) {
+ int r;
+
+ pr_warn("Freeing queue vital buffer 0x%lx, queue evicted\n",
+ prange->start << PAGE_SHIFT);
+ r = kgd2kfd_quiesce_mm(mm, KFD_QUEUE_EVICTION_TRIGGER_SVM);
+ if (r)
+ pr_debug("failed %d to quiesce KFD queues\n", r);
+ }
+
p = kfd_lookup_process_by_mm(mm);
if (!p)
return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 70c1776611c4..747325a2ea89 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -137,6 +137,7 @@ struct svm_range {
DECLARE_BITMAP(bitmap_access, MAX_GPU_INSTANCE);
DECLARE_BITMAP(bitmap_aip, MAX_GPU_INSTANCE);
bool mapped_to_gpu;
+ atomic_t queue_refcount;
};
static inline void svm_range_lock(struct svm_range *prange)
--
2.43.2
