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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-07-03

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

There is a minor merge conflict in mlx5 due to 8960b38932be ("linux/dim:
Rename externally used net_dim members") which has been pulled into your
tree in the meantime, but resolution seems not that bad ... getting current
bpf-next out now before there's coming more on mlx5. ;) I'm Cc'ing Saeed
just so he's aware of the resolution below:

** First conflict in drivers/net/ethernet/mellanox/mlx5/core/en_main.c:

  <<<<<<< HEAD
  static int mlx5e_open_cq(struct mlx5e_channel *c,
                           struct dim_cq_moder moder,
                           struct mlx5e_cq_param *param,
                           struct mlx5e_cq *cq)
  =======
  int mlx5e_open_cq(struct mlx5e_channel *c, struct net_dim_cq_moder moder,
                    struct mlx5e_cq_param *param, struct mlx5e_cq *cq)
  >>>>>>> e5a3e259ef239f443951d401db10db7d426c9497

Resolution is to take the second chunk and rename net_dim_cq_moder into
dim_cq_moder. Also the signature for mlx5e_open_cq() in ...

  drivers/net/ethernet/mellanox/mlx5/core/en.h +977

... and in mlx5e_open_xsk() ...

  drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +64

... needs the same rename from net_dim_cq_moder into dim_cq_moder.

** Second conflict in drivers/net/ethernet/mellanox/mlx5/core/en_main.c:

  <<<<<<< HEAD
          int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
          struct dim_cq_moder icocq_moder = {0, 0};
          struct net_device *netdev = priv->netdev;
          struct mlx5e_channel *c;
          unsigned int irq;
  =======
          struct net_dim_cq_moder icocq_moder = {0, 0};
  >>>>>>> e5a3e259ef239f443951d401db10db7d426c9497

Take the second chunk and rename net_dim_cq_moder into dim_cq_moder
as well.

Let me know if you run into any issues. Anyway, the main changes are:

1) Long-awaited AF_XDP support for mlx5e driver, from Maxim.

2) Addition of two new per-cgroup BPF hooks for getsockopt and
   setsockopt along with a new sockopt program type which allows more
   fine-grained pass/reject settings for containers. Also add a sock_ops
   callback that can be selectively enabled on a per-socket basis and is
   executed for every RTT to help tracking TCP statistics, both features
   from Stanislav.

3) Follow-up fix from loops in precision tracking which was not propagating
   precision marks and as a result verifier assumed that some branches were
   not taken and therefore wrongly removed as dead code, from Alexei.

4) Fix BPF cgroup release synchronization race which could lead to a
   double-free if a leaf's cgroup_bpf object is released and a new BPF
   program is attached to the one of ancestor cgroups in parallel, from Roman.

5) Support for bulking XDP_TX on veth devices which improves performance
   in some cases by around 9%, from Toshiaki.

6) Allow for lookups into BPF devmap and improve feedback when calling into
   bpf_redirect_map() as lookup is now performed right away in the helper
   itself, from Toke.

7) Add support for fq's Earliest Departure Time to the Host Bandwidth
   Manager (HBM) sample BPF program, from Lawrence.

8) Various cleanups and minor fixes all over the place from many others.
====================

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

4 files changed, 30 insertions, 11 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4259c9f0cfe7..4907997289e9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -778,7 +778,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 	if (obj->nr_maps < obj->maps_cap)
 		return &obj->maps[obj->nr_maps++];
 
-	new_cap = max(4ul, obj->maps_cap * 3 / 2);
+	new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
 	new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
 	if (!new_maps) {
 		pr_warning("alloc maps for object failed\n");
@@ -1169,7 +1169,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			pr_debug("map '%s': found key_size = %u.\n",
 				 map_name, sz);
 			if (map->def.key_size && map->def.key_size != sz) {
-				pr_warning("map '%s': conflictling key size %u != %u.\n",
+				pr_warning("map '%s': conflicting key size %u != %u.\n",
 					   map_name, map->def.key_size, sz);
 				return -EINVAL;
 			}
@@ -1197,7 +1197,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			pr_debug("map '%s': found key [%u], sz = %lld.\n",
 				 map_name, t->type, sz);
 			if (map->def.key_size && map->def.key_size != sz) {
-				pr_warning("map '%s': conflictling key size %u != %lld.\n",
+				pr_warning("map '%s': conflicting key size %u != %lld.\n",
 					   map_name, map->def.key_size, sz);
 				return -EINVAL;
 			}
@@ -1212,7 +1212,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			pr_debug("map '%s': found value_size = %u.\n",
 				 map_name, sz);
 			if (map->def.value_size && map->def.value_size != sz) {
-				pr_warning("map '%s': conflictling value size %u != %u.\n",
+				pr_warning("map '%s': conflicting value size %u != %u.\n",
 					   map_name, map->def.value_size, sz);
 				return -EINVAL;
 			}
@@ -1240,7 +1240,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			pr_debug("map '%s': found value [%u], sz = %lld.\n",
 				 map_name, t->type, sz);
 			if (map->def.value_size && map->def.value_size != sz) {
-				pr_warning("map '%s': conflictling value size %u != %lld.\n",
+				pr_warning("map '%s': conflicting value size %u != %lld.\n",
 					   map_name, map->def.value_size, sz);
 				return -EINVAL;
 			}
@@ -2646,6 +2646,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		return false;
 	case BPF_PROG_TYPE_KPROBE:
 	default:
@@ -3604,6 +3605,10 @@ static const struct {
 						BPF_CGROUP_UDP6_RECVMSG),
 	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
 						BPF_CGROUP_SYSCTL),
+	BPF_EAPROG_SEC("cgroup/getsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
+						BPF_CGROUP_GETSOCKOPT),
+	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
+						BPF_CGROUP_SETSOCKOPT),
 };
 
 #undef BPF_PROG_SEC_IMPL
@@ -3867,10 +3872,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			struct bpf_object **pobj, int *prog_fd)
 {
-	struct bpf_object_open_attr open_attr = {
-		.file		= attr->file,
-		.prog_type	= attr->prog_type,
-	};
+	struct bpf_object_open_attr open_attr = {};
 	struct bpf_program *prog, *first_prog = NULL;
 	enum bpf_attach_type expected_attach_type;
 	enum bpf_prog_type prog_type;
@@ -3883,6 +3885,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!attr->file)
 		return -EINVAL;
 
+	open_attr.file = attr->file;
+	open_attr.prog_type = attr->prog_type;
+
 	obj = bpf_object__open_xattr(&open_attr);
 	if (IS_ERR_OR_NULL(obj))
 		return -ENOENT;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 6635a31a7a16..ace1a0708d99 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -101,6 +101,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	default:
 		break;
 	}
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 7ef6293b4fd7..b33740221b7e 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -65,6 +65,7 @@ struct xsk_socket {
 	int xsks_map_fd;
 	__u32 queue_id;
 	char ifname[IFNAMSIZ];
+	bool zc;
 };
 
 struct xsk_nl_info {
@@ -326,7 +327,8 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 
 	channels.cmd = ETHTOOL_GCHANNELS;
 	ifr.ifr_data = (void *)&channels;
-	strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ);
+	strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
@@ -480,6 +482,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
+	struct xdp_options opts;
 	struct xsk_socket *xsk;
 	socklen_t optlen;
 	int err;
@@ -597,6 +600,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	}
 
 	xsk->prog_fd = -1;
+
+	optlen = sizeof(opts);
+	err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen);
+	if (err) {
+		err = -errno;
+		goto out_mmap_tx;
+	}
+
+	xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY;
+
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
 		err = xsk_setup_xdp_prog(xsk);
 		if (err)
diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 82ea71a0f3ec..833a6e60d065 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -167,7 +167,7 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
-#define XSK_UMEM__DEFAULT_FRAME_SHIFT    11 /* 2048 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT    12 /* 4096 bytes */
 #define XSK_UMEM__DEFAULT_FRAME_SIZE     (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
 #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0