Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-07-19

We've added 45 non-merge commits during the last 3 day(s) which contain
a total of 71 files changed, 7808 insertions(+), 592 deletions(-).

The main changes are:

1) multi-buffer support in AF_XDP, from Maciej Fijalkowski,
   Magnus Karlsson, Tirthendu Sarkar.

2) BPF link support for tc BPF programs, from Daniel Borkmann.

3) Enable bpf_map_sum_elem_count kfunc for all program types,
   from Anton Protopopov.

4) Add 'owner' field to bpf_rb_node to fix races in shared ownership,
   Dave Marchevsky.

5) Prevent potential skb_header_pointer() misuse, from Alexei Starovoitov.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
  bpf, net: Introduce skb_pointer_if_linear().
  bpf: sync tools/ uapi header with
  selftests/bpf: Add mprog API tests for BPF tcx links
  selftests/bpf: Add mprog API tests for BPF tcx opts
  bpftool: Extend net dump with tcx progs
  libbpf: Add helper macro to clear opts structs
  libbpf: Add link-based API for tcx
  libbpf: Add opts-based attach/detach/query API for tcx
  bpf: Add fd-based tcx multi-prog infra with link support
  bpf: Add generic attach/detach/query API for multi-progs
  selftests/xsk: reset NIC settings to default after running test suite
  selftests/xsk: add test for too many frags
  selftests/xsk: add metadata copy test for multi-buff
  selftests/xsk: add invalid descriptor test for multi-buffer
  selftests/xsk: add unaligned mode test for multi-buffer
  selftests/xsk: add basic multi-buffer test
  selftests/xsk: transmit and receive multi-buffer packets
  xsk: add multi-buffer documentation
  i40e: xsk: add TX multi-buffer support
  ice: xsk: Tx multi-buffer support
  ...
====================

Link: https://lore.kernel.org/r/20230719175424.75717-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 69 insertions, 13 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ee8cb1a174aa..7f4e8c357a6a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -37,6 +37,8 @@
 #include <linux/trace_events.h>
 #include <net/netfilter/nf_bpf_link.h>
 
+#include <net/tcx.h>
+
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
@@ -3740,31 +3742,45 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_XDP;
 	case BPF_LSM_CGROUP:
 		return BPF_PROG_TYPE_LSM;
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		return BPF_PROG_TYPE_SCHED_CLS;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
 }
 
-#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd
+#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
+
+#define BPF_F_ATTACH_MASK_BASE	\
+	(BPF_F_ALLOW_OVERRIDE |	\
+	 BPF_F_ALLOW_MULTI |	\
+	 BPF_F_REPLACE)
 
-#define BPF_F_ATTACH_MASK \
-	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE)
+#define BPF_F_ATTACH_MASK_MPROG	\
+	(BPF_F_REPLACE |	\
+	 BPF_F_BEFORE |		\
+	 BPF_F_AFTER |		\
+	 BPF_F_ID |		\
+	 BPF_F_LINK)
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
+	u32 mask;
 	int ret;
 
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
-	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
-		return -EINVAL;
-
 	ptype = attach_type_to_prog_type(attr->attach_type);
 	if (ptype == BPF_PROG_TYPE_UNSPEC)
 		return -EINVAL;
+	mask = bpf_mprog_supported(ptype) ?
+	       BPF_F_ATTACH_MASK_MPROG : BPF_F_ATTACH_MASK_BASE;
+	if (attr->attach_flags & ~mask)
+		return -EINVAL;
 
 	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
 	if (IS_ERR(prog))
@@ -3800,6 +3816,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		else
 			ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_prog_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -3809,25 +3828,41 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	return ret;
 }
 
-#define BPF_PROG_DETACH_LAST_FIELD attach_type
+#define BPF_PROG_DETACH_LAST_FIELD expected_revision
 
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
+	struct bpf_prog *prog = NULL;
 	enum bpf_prog_type ptype;
+	int ret;
 
 	if (CHECK_ATTR(BPF_PROG_DETACH))
 		return -EINVAL;
 
 	ptype = attach_type_to_prog_type(attr->attach_type);
+	if (bpf_mprog_supported(ptype)) {
+		if (ptype == BPF_PROG_TYPE_UNSPEC)
+			return -EINVAL;
+		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+			return -EINVAL;
+		if (attr->attach_bpf_fd) {
+			prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+			if (IS_ERR(prog))
+				return PTR_ERR(prog);
+		}
+	}
 
 	switch (ptype) {
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_SK_SKB:
-		return sock_map_prog_detach(attr, ptype);
+		ret = sock_map_prog_detach(attr, ptype);
+		break;
 	case BPF_PROG_TYPE_LIRC_MODE2:
-		return lirc_prog_detach(attr);
+		ret = lirc_prog_detach(attr);
+		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return netns_bpf_prog_detach(attr, ptype);
+		ret = netns_bpf_prog_detach(attr, ptype);
+		break;
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -3836,13 +3871,21 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_LSM:
-		return cgroup_bpf_prog_detach(attr, ptype);
+		ret = cgroup_bpf_prog_detach(attr, ptype);
+		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_prog_detach(attr, prog);
+		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
 	}
+
+	if (prog)
+		bpf_prog_put(prog);
+	return ret;
 }
 
-#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.link_attach_flags
 
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
@@ -3890,6 +3933,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_SK_MSG_VERDICT:
 	case BPF_SK_SKB_VERDICT:
 		return sock_map_bpf_prog_query(attr, uattr);
+	case BPF_TCX_INGRESS:
+	case BPF_TCX_EGRESS:
+		return tcx_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
@@ -4852,6 +4898,13 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 			goto out;
 		}
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		if (attr->link_create.attach_type != BPF_TCX_INGRESS &&
+		    attr->link_create.attach_type != BPF_TCX_EGRESS) {
+			ret = -EINVAL;
+			goto out;
+		}
+		break;
 	default:
 		ptype = attach_type_to_prog_type(attr->link_create.attach_type);
 		if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
@@ -4903,6 +4956,9 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_XDP:
 		ret = bpf_xdp_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		ret = tcx_link_attach(attr, prog);
+		break;
 	case BPF_PROG_TYPE_NETFILTER:
 		ret = bpf_nf_link_attach(attr, prog);
 		break;