Merge branch 'bpf-af-xdp-mlx5e'

Tariq Toukan says:

====================
This series contains improvements to the AF_XDP kernel infrastructure
and AF_XDP support in mlx5e. The infrastructure improvements are
required for mlx5e, but also some of them benefit to all drivers, and
some can be useful for other drivers that want to implement AF_XDP.

The performance testing was performed on a machine with the following
configuration:

- 24 cores of Intel Xeon E5-2620 v3 @ 2.40 GHz
- Mellanox ConnectX-5 Ex with 100 Gbit/s link

The results with retpoline disabled, single stream:

txonly: 33.3 Mpps (21.5 Mpps with queue and app pinned to the same CPU)
rxdrop: 12.2 Mpps
l2fwd: 9.4 Mpps

The results with retpoline enabled, single stream:

txonly: 21.3 Mpps (14.1 Mpps with queue and app pinned to the same CPU)
rxdrop: 9.9 Mpps
l2fwd: 6.8 Mpps

v2 changes:

Added patches for mlx5e and addressed the comments for v1. Rebased for
bpf-next.

v3 changes:

Rebased for the newer bpf-next, resolved conflicts in libbpf. Addressed
Björn's comments for coding style. Fixed a bug in error handling flow in
mlx5e_open_xsk.

v4 changes:

UAPI is not changed, XSK RX queues are exposed to the kernel. The lower
half of the available amount of RX queues are regular queues, and the
upper half are XSK RX queues. The patch "xsk: Extend channels to support
combined XSK/non-XSK traffic" was dropped. The final patch was reworked
accordingly.

Added "net/mlx5e: Attach/detach XDP program safely", as the changes
introduced in the XSK patch base on the stuff from this one.

Added "libbpf: Support drivers with non-combined channels", which aligns
the condition in libbpf with the condition in the kernel.

Rebased over the newer bpf-next.

v5 changes:

In v4, ethtool reports the number of channels as 'combined' and the
number of XSK RX queues as 'rx' for mlx5e. It was changed, so that 'rx'
is 0, and 'combined' reports the double amount of channels if there is
an active UMEM - to make libbpf happy.

The patch for libbpf was dropped. Although it's still useful and fixes
things, it raises some disagreement, so I'm dropping it - it's no longer
useful for mlx5e anymore after the change above.

v6 changes:

As Maxim is out of office, I rebased the series on behalf of him,
solved some conflicts, and re-spinned.
====================

Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

2 files changed, 32 insertions, 3 deletions

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index ae0f368a62bb..057b159ff8b9 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -77,10 +77,11 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 void xsk_flush(struct xdp_sock *xs);
 bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
 /* Used from netdev driver */
+bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
 u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
 void xsk_umem_discard_addr(struct xdp_umem *umem);
 void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len);
+bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
 void xsk_umem_consume_tx_done(struct xdp_umem *umem);
 struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
 struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
@@ -99,6 +100,16 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
 }
 
 /* Reuse-queue aware version of FILL queue helpers */
+static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
+{
+	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
+
+	if (rq->length >= cnt)
+		return true;
+
+	return xsk_umem_has_addrs(umem, cnt - rq->length);
+}
+
 static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
 {
 	struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
@@ -146,6 +157,11 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 	return false;
 }
 
+static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
+{
+	return false;
+}
+
 static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
 {
 	return NULL;
@@ -159,8 +175,8 @@ static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
 {
 }
 
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma,
-				       u32 *len)
+static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
+				       struct xdp_desc *desc)
 {
 	return false;
 }
@@ -200,6 +216,11 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
 	return 0;
 }
 
+static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
+{
+	return false;
+}
+
 static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
 {
 	return NULL;
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index caed8b1614ff..faaa5ca2a117 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -46,6 +46,7 @@ struct xdp_mmap_offsets {
 #define XDP_UMEM_FILL_RING		5
 #define XDP_UMEM_COMPLETION_RING	6
 #define XDP_STATISTICS			7
+#define XDP_OPTIONS			8
 
 struct xdp_umem_reg {
 	__u64 addr; /* Start of packet data area */
@@ -60,6 +61,13 @@ struct xdp_statistics {
 	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
 };
 
+struct xdp_options {
+	__u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
 /* Pgoff for mmaping the rings */
 #define XDP_PGOFF_RX_RING			  0
 #define XDP_PGOFF_TX_RING		 0x80000000