swiotlb: reduce swiotlb pool lookups

With CONFIG_SWIOTLB_DYNAMIC enabled, each round-trip map/unmap pair
in the swiotlb results in 6 calls to swiotlb_find_pool(). In multiple
places, the pool is found and used in one function, and then must
be found again in the next function that is called because only the
tlb_addr is passed as an argument. These are the six call sites:

dma_direct_map_page:
 1. swiotlb_map -> swiotlb_tbl_map_single -> swiotlb_bounce

dma_direct_unmap_page:
 2. dma_direct_sync_single_for_cpu -> is_swiotlb_buffer
 3. dma_direct_sync_single_for_cpu -> swiotlb_sync_single_for_cpu ->
	swiotlb_bounce
 4. is_swiotlb_buffer
 5. swiotlb_tbl_unmap_single -> swiotlb_del_transient
 6. swiotlb_tbl_unmap_single -> swiotlb_release_slots

Reduce the number of calls by finding the pool at a higher level, and
passing it as an argument instead of searching again. A key change is
for is_swiotlb_buffer() to return a pool pointer instead of a boolean,
and then pass this pool pointer to subsequent swiotlb functions.

There are 9 occurrences of is_swiotlb_buffer() used to test if a buffer
is a swiotlb buffer before calling a swiotlb function. To reduce code
duplication in getting the pool pointer and passing it as an argument,
introduce inline wrappers for this pattern. The generated code is
essentially unchanged.

Since is_swiotlb_buffer() no longer returns a boolean, rename some
functions to reflect the change:

 * swiotlb_find_pool() becomes __swiotlb_find_pool()
 * is_swiotlb_buffer() becomes swiotlb_find_pool()
 * is_xen_swiotlb_buffer() becomes xen_swiotlb_find_pool()

With these changes, a round-trip map/unmap pair requires only 2 pool
lookups (listed using the new names and wrappers):

dma_direct_unmap_page:
 1. dma_direct_sync_single_for_cpu -> swiotlb_find_pool
 2. swiotlb_tbl_unmap_single -> swiotlb_find_pool

These changes come from noticing the inefficiencies in a code review,
not from performance measurements. With CONFIG_SWIOTLB_DYNAMIC,
__swiotlb_find_pool() is not trivial, and it uses an RCU read lock,
so avoiding the redundant calls helps performance in a hot path.
When CONFIG_SWIOTLB_DYNAMIC is *not* set, the code size reduction
is minimal and the perf benefits are likely negligible, but no
harm is done.

No functional change is intended.

Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Petr Tesarik <petr@tesarici.cz>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 20 insertions, 11 deletions

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 6579ae3f6dac..35155258a7e2 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -88,7 +88,8 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 	return 0;
 }
 
-static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
+static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev,
+						 dma_addr_t dma_addr)
 {
 	unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr));
 	unsigned long xen_pfn = bfn_to_local_pfn(bfn);
@@ -99,8 +100,8 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 	 * in our domain. Therefore _only_ check address within our domain.
 	 */
 	if (pfn_valid(PFN_DOWN(paddr)))
-		return is_swiotlb_buffer(dev, paddr);
-	return 0;
+		return swiotlb_find_pool(dev, paddr);
+	return NULL;
 }
 
 #ifdef CONFIG_X86
@@ -227,8 +228,9 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * Ensure that the address returned is DMA'ble
 	 */
 	if (unlikely(!dma_capable(dev, dev_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir,
-				attrs | DMA_ATTR_SKIP_CPU_SYNC);
+		__swiotlb_tbl_unmap_single(dev, map, size, dir,
+				attrs | DMA_ATTR_SKIP_CPU_SYNC,
+				swiotlb_find_pool(dev, map));
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -254,6 +256,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	phys_addr_t paddr = xen_dma_to_phys(hwdev, dev_addr);
+	struct io_tlb_pool *pool;
 
 	BUG_ON(dir == DMA_NONE);
 
@@ -265,8 +268,10 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 	}
 
 	/* NOTE: We use dev_addr here, not paddr! */
-	if (is_xen_swiotlb_buffer(hwdev, dev_addr))
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
+	pool = xen_swiotlb_find_pool(hwdev, dev_addr);
+	if (pool)
+		__swiotlb_tbl_unmap_single(hwdev, paddr, size, dir,
+					   attrs, pool);
 }
 
 static void
@@ -274,6 +279,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
+	struct io_tlb_pool *pool;
 
 	if (!dev_is_dma_coherent(dev)) {
 		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
@@ -282,8 +288,9 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 			xen_dma_sync_for_cpu(dev, dma_addr, size, dir);
 	}
 
-	if (is_xen_swiotlb_buffer(dev, dma_addr))
-		swiotlb_sync_single_for_cpu(dev, paddr, size, dir);
+	pool = xen_swiotlb_find_pool(dev, dma_addr);
+	if (pool)
+		__swiotlb_sync_single_for_cpu(dev, paddr, size, dir, pool);
 }
 
 static void
@@ -291,9 +298,11 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
+	struct io_tlb_pool *pool;
 
-	if (is_xen_swiotlb_buffer(dev, dma_addr))
-		swiotlb_sync_single_for_device(dev, paddr, size, dir);
+	pool = xen_swiotlb_find_pool(dev, dma_addr);
+	if (pool)
+		__swiotlb_sync_single_for_device(dev, paddr, size, dir, pool);
 
 	if (!dev_is_dma_coherent(dev)) {
 		if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))