[PATCH net] xsk: remove cheap_dma optimization

[BjÃrn TÃpel]

From: BjÃrn TÃpel <bjorn.topel@xxxxxxxxx>

When the AF_XDP buffer allocation API was introduced it had an
optimization, "cheap_dma". The idea was that when the umem was DMA
mapped, the pool also checked whether the mapping required a
synchronization (CPU to device, and vice versa). If not, it would be
marked as "cheap_dma" and the synchronization would be elided.

In [1] Christoph points out that the optimization above breaks the DMA
API abstraction, and should be removed. Further, Christoph points out
that optimizations like this should be done within the DMA mapping
core, and not elsewhere.

Unfortunately this has implications for the packet rate
performance. The AF_XDP rxdrop scenario shows a 9% decrease in packets
per second.

[1] https://lore.kernel.org/netdev/20200626074725.GA21790@xxxxxx/

Cc: Christoph Hellwig <hch@xxxxxx>
Fixes: 2b43470add8c ("xsk: Introduce AF_XDP buffer allocation API")
Signed-off-by: BjÃrn TÃpel <bjorn.topel@xxxxxxxxx>
---
 include/net/xsk_buff_pool.h | 16 +++------
 net/xdp/xsk_buff_pool.c     | 69 ++-----------------------------------
 2 files changed, 6 insertions(+), 79 deletions(-)

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index a4ff226505c9..3ea9b9654632 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -40,7 +40,6 @@ struct xsk_buff_pool {
 	u32 headroom;
 	u32 chunk_size;
 	u32 frame_len;
-	bool cheap_dma;
 	bool unaligned;
 	void *addrs;
 	struct device *dev;
@@ -77,24 +76,17 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
 	return xskb->frame_dma;
 }
 
-void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
 static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
 {
-	if (xskb->pool->cheap_dma)
-		return;
-
-	xp_dma_sync_for_cpu_slow(xskb);
+	dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
+				      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
 }
 
-void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
-				 size_t size);
 static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool,
 					  dma_addr_t dma, size_t size)
 {
-	if (pool->cheap_dma)
-		return;
-
-	xp_dma_sync_for_device_slow(pool, dma, size);
+	dma_sync_single_range_for_device(pool->dev, dma, 0,
+					 size, DMA_BIDIRECTIONAL);
 }
 
 /* Masks for xdp_umem_page flags.
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 540ed75e4482..c330e5f3aadf 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,9 +2,6 @@
 
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
-#include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/swiotlb.h>
 
 #include "xsk_queue.h"
 
@@ -55,7 +52,6 @@ struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
 	pool->free_heads_cnt = chunks;
 	pool->headroom = headroom;
 	pool->chunk_size = chunk_size;
-	pool->cheap_dma = true;
 	pool->unaligned = unaligned;
 	pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
 	INIT_LIST_HEAD(&pool->free_list);
@@ -125,48 +121,6 @@ static void xp_check_dma_contiguity(struct xsk_buff_pool *pool)
 	}
 }
 
-static bool __maybe_unused xp_check_swiotlb_dma(struct xsk_buff_pool *pool)
-{
-#if defined(CONFIG_SWIOTLB)
-	phys_addr_t paddr;
-	u32 i;
-
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
-		paddr = dma_to_phys(pool->dev, pool->dma_pages[i]);
-		if (is_swiotlb_buffer(paddr))
-			return false;
-	}
-#endif
-	return true;
-}
-
-static bool xp_check_cheap_dma(struct xsk_buff_pool *pool)
-{
-#if defined(CONFIG_HAS_DMA)
-	const struct dma_map_ops *ops = get_dma_ops(pool->dev);
-
-	if (ops) {
-		return !ops->sync_single_for_cpu &&
-			!ops->sync_single_for_device;
-	}
-
-	if (!dma_is_direct(ops))
-		return false;
-
-	if (!xp_check_swiotlb_dma(pool))
-		return false;
-
-	if (!dev_is_dma_coherent(pool->dev)) {
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) ||		\
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) ||	\
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE)
-		return false;
-#endif
-	}
-#endif
-	return true;
-}
-
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages)
 {
@@ -195,7 +149,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 		xp_check_dma_contiguity(pool);
 
 	pool->dev = dev;
-	pool->cheap_dma = xp_check_cheap_dma(pool);
 	return 0;
 }
 EXPORT_SYMBOL(xp_dma_map);
@@ -280,11 +233,8 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
 
-	if (!pool->cheap_dma) {
-		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
-						 pool->frame_len,
-						 DMA_BIDIRECTIONAL);
-	}
+	dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,
+					 pool->frame_len, DMA_BIDIRECTIONAL);
 	return &xskb->xdp;
 }
 EXPORT_SYMBOL(xp_alloc);
@@ -319,18 +269,3 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
 		(addr & ~PAGE_MASK);
 }
 EXPORT_SYMBOL(xp_raw_get_dma);
-
-void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb)
-{
-	dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0,
-				      xskb->pool->frame_len, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow);
-
-void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma,
-				 size_t size)
-{
-	dma_sync_single_range_for_device(pool->dev, dma, 0,
-					 size, DMA_BIDIRECTIONAL);
-}
-EXPORT_SYMBOL(xp_dma_sync_for_device_slow);

base-commit: 4a21185cda0fbb860580eeeb4f1a70a9cda332a4
-- 
2.25.1