[PATCH v3 7/7] swiotlb: search the software IO TLB only if a device makes use of it

[Petr Tesarik <petrtesarik@xxxxxxxxxxxxxxx>]

From: Petr Tesarik <petr.tesarik.ext@xxxxxxxxxx>

Skip searching the software IO TLB if a device has never used it, making
sure these devices are not affected by the introduction of multiple IO TLB
memory pools.

Additional memory barrier is required to ensure that the new value of the
flag is visible to other CPUs after mapping a new bounce buffer. For
efficiency, the flag check should be inlined, and then the memory barrier
must be moved to is_swiotlb_buffer(). However, it can replace the existing
barrier in swiotlb_find_pool(), because all callers use is_swiotlb_buffer()
first to verify that the buffer address belongs to the software IO TLB.

Signed-off-by: Petr Tesarik <petr.tesarik.ext@xxxxxxxxxx>
---
 include/linux/device.h  |  2 ++
 include/linux/swiotlb.h |  6 +++++-
 kernel/dma/swiotlb.c    | 14 ++++++--------
 3 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/include/linux/device.h b/include/linux/device.h
index a1ee4c5924b8..d4b35925a6d1 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -512,6 +512,7 @@ struct device_physical_location {
  * @dma_io_tlb_mem: Software IO TLB allocator.  Not for driver use.
  * @dma_io_tlb_pools:	List of transient swiotlb memory pools.
  * @dma_io_tlb_lock:	Protects changes to the list of active pools.
+ * @dma_uses_io_tlb: %true if device has used the software IO TLB.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
  * @fwnode:	Associated device node supplied by platform firmware.
@@ -619,6 +620,7 @@ struct device {
 	struct io_tlb_mem *dma_io_tlb_mem;
 	struct list_head dma_io_tlb_pools;
 	spinlock_t dma_io_tlb_lock;
+	bool dma_uses_io_tlb;
 #endif
 	/* arch specific additions */
 	struct dev_archdata	archdata;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ae402890ba41..eb30b5c624f1 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -148,7 +148,11 @@ struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr);
  */
 static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
 {
-	return dev->dma_io_tlb_mem &&
+	/* Pairs with smp_wmb() in swiotlb_find_slots() and
+	 * swiotlb_dyn_alloc(), which modify the RCU lists.
+	 */
+	smp_rmb();
+	return dev->dma_uses_io_tlb &&
 		!!swiotlb_find_pool(dev, paddr);
 }
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 7661a6402e80..26ab9ed2921b 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -701,7 +701,7 @@ static void swiotlb_dyn_alloc(struct work_struct *work)
 
 	add_mem_pool(mem, pool);
 
-	/* Pairs with smp_rmb() in swiotlb_find_pool(). */
+	/* Pairs with smp_rmb() in is_swiotlb_buffer(). */
 	smp_wmb();
 }
 
@@ -729,6 +729,7 @@ void swiotlb_dev_init(struct device *dev)
 	dev->dma_io_tlb_mem = &io_tlb_default_mem;
 	INIT_LIST_HEAD(&dev->dma_io_tlb_pools);
 	spin_lock_init(&dev->dma_io_tlb_lock);
+	dev->dma_uses_io_tlb = false;
 }
 
 /**
@@ -746,11 +747,6 @@ struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr)
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
 	struct io_tlb_pool *pool;
 
-	/* Pairs with smp_wmb() in swiotlb_find_slots() and
-	 * swiotlb_dyn_alloc(), which modify the RCU lists.
-	 */
-	smp_rmb();
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(pool, &mem->pools, node) {
 		if (paddr >= pool->start && paddr < pool->end)
@@ -1125,9 +1121,11 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
 	list_add_rcu(&pool->node, &dev->dma_io_tlb_pools);
 	spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
 
-	/* Pairs with smp_rmb() in swiotlb_find_pool(). */
-	smp_wmb();
 found:
+	dev->dma_uses_io_tlb = true;
+	/* Pairs with smp_rmb() in is_swiotlb_buffer() */
+	smp_wmb();
+
 	*retpool = pool;
 	return index;
 }
-- 
2.25.1