habanalabs: don't free phys_pg_pack inside lock

Freeing phys_pg_pack includes calling to scrubbing functions of the
device's memory, taking locks and possibly even calling reset.

This is not something that should be done while holding a device-wide
spinlock.

Therefore, save the relevant objects on a local linked-list and after
releasing the spinlock, traverse that list and free the phys_pg_pack
objects.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

drivers/misc/habanalabs/common/habanalabs.h

@@ -1738,6 +1738,8 @@ struct hl_vm_hw_block_list_node {
  * @pages: the physical page array.
  * @npages: num physical pages in the pack.
  * @total_size: total size of all the pages in this list.
+ * @node: used to attach to deletion list that is used when all the allocations are cleared
+ *        at the teardown of the context.
  * @mapping_cnt: number of shared mappings.
  * @exporting_cnt: number of dma-buf exporting.
  * @asid: the context related to this list.
@@ -1753,6 +1755,7 @@ struct hl_vm_phys_pg_pack {
 	u64			*pages;
 	u64			npages;
 	u64			total_size;
+	struct list_head	node;
 	atomic_t		mapping_cnt;
 	u32			exporting_cnt;
 	u32			asid;

drivers/misc/habanalabs/common/memory.c

@@ -2607,11 +2607,12 @@ int hl_vm_ctx_init(struct hl_ctx *ctx)
  */
 void hl_vm_ctx_fini(struct hl_ctx *ctx)
 {
-	struct hl_device *hdev = ctx->hdev;
-	struct hl_vm *vm = &hdev->vm;
 	struct hl_vm_phys_pg_pack *phys_pg_list;
+	struct hl_device *hdev = ctx->hdev;
 	struct hl_vm_hash_node *hnode;
+	struct hl_vm *vm = &hdev->vm;
 	struct hlist_node *tmp_node;
+	struct list_head free_list;
 	struct hl_mem_in args;
 	int i;
 
@@ -2644,19 +2645,24 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
 
 	mutex_unlock(&ctx->mmu_lock);
 
+	INIT_LIST_HEAD(&free_list);
+
 	spin_lock(&vm->idr_lock);
 	idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_list, i)
 		if (phys_pg_list->asid == ctx->asid) {
 			dev_dbg(hdev->dev,
 				"page list 0x%px of asid %d is still alive\n",
 				phys_pg_list, ctx->asid);
-			atomic64_sub(phys_pg_list->total_size,
-					&hdev->dram_used_mem);
-			free_phys_pg_pack(hdev, phys_pg_list);
+
+			atomic64_sub(phys_pg_list->total_size, &hdev->dram_used_mem);
 			idr_remove(&vm->phys_pg_pack_handles, i);
+			list_add(&phys_pg_list->node, &free_list);
 		}
 	spin_unlock(&vm->idr_lock);
 
+	list_for_each_entry(phys_pg_list, &free_list, node)
+		free_phys_pg_pack(hdev, phys_pg_list);
+
 	va_range_fini(hdev, ctx->va_range[HL_VA_RANGE_TYPE_DRAM]);
 	va_range_fini(hdev, ctx->va_range[HL_VA_RANGE_TYPE_HOST]);