[PATCH v7 20/22] dma: swiotlb: free dynamic pools from process context

["Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>]

swiotlb_dyn_free() is used after removing a dynamic swiotlb pool from
RCU-protected lists. It can call swiotlb_free_tlb(), which may need to
restore the encryption state of an unencrypted pool with
set_memory_encrypted() before freeing the pages.

RCU callbacks run in atomic context, but set_memory_encrypted() is not
guaranteed to be atomic-safe on all architectures. For example, page
attribute updates may allocate page tables or take sleeping locks.

Use queue_rcu_work() for dynamic pool freeing instead. This keeps the RCU
grace period before freeing a published pool, while running the actual pool
teardown from workqueue context. Use the same helper for the transient-pool
error path, since that path may also be reached from atomic DMA mapping
context.

Tested-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Petr Tesarik <ptesarik@suse.com>
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
 include/linux/swiotlb.h |  4 ++--
 kernel/dma/swiotlb.c    | 19 +++++++++++--------
 2 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ee42f7588847..c3bf7ed6f7a6 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -64,7 +64,7 @@ extern void __init swiotlb_update_mem_attributes(void);
  * @areas:	Array of memory area descriptors.
  * @slots:	Array of slot descriptors.
  * @node:	Member of the IO TLB memory pool list.
- * @rcu:	RCU head for swiotlb_dyn_free().
+ * @dyn_free:	RCU work item used to free the pool from process context.
  * @transient:  %true if transient memory pool.
  * @cc_shared:	%true if the pool memory is shared for confidential computing.
  */
@@ -80,7 +80,7 @@ struct io_tlb_pool {
 	struct io_tlb_slot *slots;
 #ifdef CONFIG_SWIOTLB_DYNAMIC
 	struct list_head node;
-	struct rcu_head rcu;
+	struct rcu_work dyn_free;
 	bool transient;
 	bool cc_shared;
 #endif
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b5960c2e98d8..4d0f2c04d891 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -779,13 +779,10 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
 	add_mem_pool(mem, pool);
 }
 
-/**
- * swiotlb_dyn_free() - RCU callback to free a memory pool
- * @rcu:	RCU head in the corresponding struct io_tlb_pool.
- */
-static void swiotlb_dyn_free(struct rcu_head *rcu)
+static void swiotlb_dyn_free_work(struct work_struct *work)
 {
-	struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu);
+	struct io_tlb_pool *pool =
+		container_of(to_rcu_work(work), struct io_tlb_pool, dyn_free);
 	size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs);
 	size_t tlb_size = pool->end - pool->start;
 
@@ -794,6 +791,12 @@ static void swiotlb_dyn_free(struct rcu_head *rcu)
 	kfree(pool);
 }
 
+static void swiotlb_schedule_dyn_free(struct io_tlb_pool *pool)
+{
+	INIT_RCU_WORK(&pool->dyn_free, swiotlb_dyn_free_work);
+	queue_rcu_work(system_wq, &pool->dyn_free);
+}
+
 /**
  * __swiotlb_find_pool() - find the IO TLB pool for a physical address
  * @dev:        Device which has mapped the DMA buffer.
@@ -840,7 +843,7 @@ static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool)
 	list_del_rcu(&pool->node);
 	spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
 
-	call_rcu(&pool->rcu, swiotlb_dyn_free);
+	swiotlb_schedule_dyn_free(pool);
 }
 
 #endif	/* CONFIG_SWIOTLB_DYNAMIC */
@@ -1281,7 +1284,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, tbl_dma_addr,
 					 alloc_size, alloc_align_mask);
 	if (index < 0) {
-		swiotlb_dyn_free(&pool->rcu);
+		swiotlb_schedule_dyn_free(pool);
 		return -1;
 	}
 
-- 
2.43.0