Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-01-07

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add a start of a framework for extending struct xdp_buff without
   having the overhead of populating every data at runtime. Idea
   is to have a new per-queue struct xdp_rxq_info that holds read
   mostly data (currently that is, queue number and a pointer to
   the corresponding netdev) which is set up during rxqueue config
   time. When a XDP program is invoked, struct xdp_buff holds a
   pointer to struct xdp_rxq_info that the BPF program can then
   walk. The user facing BPF program that uses struct xdp_md for
   context can use these members directly, and the verifier rewrites
   context access transparently by walking the xdp_rxq_info and
   net_device pointers to load the data, from Jesper.

2) Redo the reporting of offload device information to user space
   such that it works in combination with network namespaces. The
   latter is reported through a device/inode tuple as similarly
   done in other subsystems as well (e.g. perf) in order to identify
   the namespace. For this to work, ns_get_path() has been generalized
   such that the namespace can be retrieved not only from a specific
   task (perf case), but also from a callback where we deduce the
   netns (ns_common) from a netdevice. bpftool support using the new
   uapi info and extensive test cases for test_offload.py in BPF
   selftests have been added as well, from Jakub.

3) Add two bpftool improvements: i) properly report the bpftool
   version such that it corresponds to the version from the kernel
   source tree. So pick the right linux/version.h from the source
   tree instead of the installed one. ii) fix bpftool and also
   bpf_jit_disasm build with bintutils >= 2.9. The reason for the
   build breakage is that binutils library changed the function
   signature to select the disassembler. Given this is needed in
   multiple tools, add a proper feature detection to the
   tools/build/features infrastructure, from Roman.

4) Implement the BPF syscall command BPF_MAP_GET_NEXT_KEY for the
   stacktrace map. It is currently unimplemented, but there are
   use cases where user space needs to walk all stacktrace map
   entries e.g. for dumping or deleting map entries w/o having to
   close and recreate the map. Add BPF selftests along with it,
   from Yonghong.

5) Few follow-up cleanups for the bpftool cgroup code: i) rename
   the cgroup 'list' command into 'show' as we have it for other
   subcommands as well, ii) then alias the 'show' command such that
   'list' is accepted which is also common practice in iproute2,
   and iii) remove couple of newlines from error messages using
   p_err(), from Jakub.

6) Two follow-up cleanups to sockmap code: i) remove the unused
   bpf_compute_data_end_sk_skb() function and ii) only build the
   sockmap infrastructure when CONFIG_INET is enabled since it's
   only aware of TCP sockets at this time, from John.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 29 insertions, 5 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 21bc17fa3854..8fc51bc29003 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2172,8 +2172,9 @@ static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 
 		if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
 					   prof->rx_ring_size, priv->stride,
-					   node))
+					   node, i))
 			goto err;
+
 	}
 
 #ifdef CONFIG_RFS_ACCEL
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 5f9dbc9a7f5b..b4d144e67514 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -262,7 +262,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
 
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
-			   u32 size, u16 stride, int node)
+			   u32 size, u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_rx_ring *ring;
@@ -286,6 +286,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index) < 0)
+		goto err_ring;
+
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
 	ring->rx_info = vzalloc_node(tmp, node);
@@ -293,7 +296,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 		ring->rx_info = vzalloc(tmp);
 		if (!ring->rx_info) {
 			err = -ENOMEM;
-			goto err_ring;
+			goto err_xdp_info;
 		}
 	}
 
@@ -317,6 +320,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 err_info:
 	vfree(ring->rx_info);
 	ring->rx_info = NULL;
+err_xdp_info:
+	xdp_rxq_info_unreg(&ring->xdp_rxq);
 err_ring:
 	kfree(ring);
 	*pring = NULL;
@@ -440,6 +445,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 					lockdep_is_held(&mdev->state_lock));
 	if (old_prog)
 		bpf_prog_put(old_prog);
+	xdp_rxq_info_unreg(&ring->xdp_rxq);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	vfree(ring->rx_info);
 	ring->rx_info = NULL;
@@ -652,6 +658,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	int cq_ring = cq->ring;
 	bool doorbell_pending;
 	struct mlx4_cqe *cqe;
+	struct xdp_buff xdp;
 	int polled = 0;
 	int index;
 
@@ -666,6 +673,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	/* Protect accesses to: ring->xdp_prog, priv->mac_hash list */
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(ring->xdp_prog);
+	xdp.rxq = &ring->xdp_rxq;
 	doorbell_pending = 0;
 
 	/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
@@ -750,7 +758,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		 * read bytes but not past the end of the frag.
 		 */
 		if (xdp_prog) {
-			struct xdp_buff xdp;
 			dma_addr_t dma;
 			void *orig_data;
 			u32 act;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 7db3d0d9bfce..f470ae37d937 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -46,6 +46,7 @@
 #endif
 #include <linux/cpu_rmap.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/xdp.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/qp.h>
@@ -356,6 +357,7 @@ struct mlx4_en_rx_ring {
 	unsigned long dropped;
 	int hwtstamp_rx_filter;
 	cpumask_var_t affinity_mask;
+	struct xdp_rxq_info xdp_rxq;
 };
 
 struct mlx4_en_cq {
@@ -720,7 +722,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
 void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
-			   u32 size, u16 stride, int node);
+			   u32 size, u16 stride, int node, int queue_index);
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 543060c305a0..5299310f2481 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -46,6 +46,7 @@
 #include <linux/mlx5/transobj.h>
 #include <linux/rhashtable.h>
 #include <net/switchdev.h>
+#include <net/xdp.h>
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
@@ -571,6 +572,9 @@ struct mlx5e_rq {
 	u32                    rqn;
 	struct mlx5_core_dev  *mdev;
 	struct mlx5_core_mkey  umr_mkey;
+
+	/* XDP read-mostly */
+	struct xdp_rxq_info    xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_channel {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3aa1c90e7c86..539bd1d24396 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -582,6 +582,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		goto err_rq_wq_destroy;
 	}
 
+	if (xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix) < 0)
+		goto err_rq_wq_destroy;
+
 	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = params->rq_headroom;
 
@@ -687,6 +690,7 @@ err_destroy_umr_mkey:
 err_rq_wq_destroy:
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 
 	return err;
@@ -699,6 +703,8 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
 
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		mlx5e_rq_free_mpwqe_info(rq);
@@ -2766,6 +2772,9 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	/* Mark as unused given "Drop-RQ" packets never reach XDP */
+	xdp_rxq_info_unused(&rq->xdp_rxq);
+
 	rq->mdev = mdev;
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 5b499c7a698f..7b38480811d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -812,6 +812,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 	xdp.data_hard_start = va;
+	xdp.rxq = &rq->xdp_rxq;
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 	switch (act) {