xsk: Optimize for aligned case

Optimize for the aligned case by precomputing the parameter values of
the xdp_buff_xsk and xdp_buff structures in the heads array. We can do
this as the heads array size is equal to the number of chunks in the
umem for the aligned case. Then every entry in this array will reflect
a certain chunk/frame and can therefore be prepopulated with the
correct values and we can drop the use of the free_heads stack. Note
that it is not possible to allocate more buffers than what has been
allocated in the aligned case since each chunk can only contain a
single buffer.

We can unfortunately not do this in the unaligned case as one chunk
might contain multiple buffers. In this case, we keep the old scheme
of populating a heads entry every time it is used and using
the free_heads stack.

Also move xp_release() and xp_get_handle() to xsk_buff_pool.h. They
were for some reason in xsk.c even though they are buffer pool
operations.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-7-magnus.karlsson@gmail.com

1 files changed, 45 insertions, 1 deletions

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b7068f97639f..ddeefc4a1040 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -7,6 +7,7 @@
 #include <linux/if_xdp.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
+#include <linux/bpf.h>
 #include <net/xdp.h>
 
 struct xsk_buff_pool;
@@ -66,6 +67,7 @@ struct xsk_buff_pool {
 	u32 free_heads_cnt;
 	u32 headroom;
 	u32 chunk_size;
+	u32 chunk_shift;
 	u32 frame_len;
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
@@ -80,6 +82,13 @@ struct xsk_buff_pool {
 	struct xdp_buff_xsk *free_heads[];
 };
 
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
+
 /* AF_XDP core. */
 struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
@@ -88,7 +97,6 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
 			 struct net_device *dev, u16 queue_id);
 void xp_destroy(struct xsk_buff_pool *pool);
-void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
 bool xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
@@ -98,6 +106,21 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
 
+static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				     u64 addr)
+{
+	xskb->orig_addr = addr;
+	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
+}
+
+static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				    dma_addr_t *dma_pages, u64 addr)
+{
+	xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) +
+		(addr & ~PAGE_MASK);
+	xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
+}
+
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
@@ -180,4 +203,25 @@ static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
 		xp_unaligned_extract_offset(addr);
 }
 
+static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr)
+{
+	return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift;
+}
+
+static inline void xp_release(struct xdp_buff_xsk *xskb)
+{
+	if (xskb->pool->unaligned)
+		xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
+}
+
+static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
+{
+	u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+
+	offset += xskb->pool->headroom;
+	if (!xskb->pool->unaligned)
+		return xskb->orig_addr + offset;
+	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+}
+
 #endif /* XSK_BUFF_POOL_H_ */