Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

  1) Fix jmp to 1st instruction in x64 JIT, from Alexei Starovoitov.

  2) Severl kTLS fixes in mlx5 driver, from Tariq Toukan.

  3) Fix severe performance regression due to lack of SKB coalescing of
     fragments during local delivery, from Guillaume Nault.

  4) Error path memory leak in sch_taprio, from Ivan Khoronzhuk.

  5) Fix batched events in skbedit packet action, from Roman Mashak.

  6) Propagate VLAN TX offload to hw_enc_features in bond and team
     drivers, from Yue Haibing.

  7) RXRPC local endpoint refcounting fix and read after free in
     rxrpc_queue_local(), from David Howells.

  8) Fix endian bug in ibmveth multicast list handling, from Thomas
     Falcon.

  9) Oops, make nlmsg_parse() wrap around the correct function,
     __nlmsg_parse not __nla_parse(). Fix from David Ahern.

 10) Memleak in sctp_scend_reset_streams(), fro Zheng Bin.

 11) Fix memory leak in cxgb4, from Wenwen Wang.

 12) Yet another race in AF_PACKET, from Eric Dumazet.

 13) Fix false detection of retransmit failures in tipc, from Tuong
     Lien.

 14) Use after free in ravb_tstamp_skb, from Tho Vu.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (101 commits)
  ravb: Fix use-after-free ravb_tstamp_skb
  netfilter: nf_tables: map basechain priority to hardware priority
  net: sched: use major priority number as hardware priority
  wimax/i2400m: fix a memory leak bug
  net: cavium: fix driver name
  ibmvnic: Unmap DMA address of TX descriptor buffers after use
  bnxt_en: Fix to include flow direction in L2 key
  bnxt_en: Use correct src_fid to determine direction of the flow
  bnxt_en: Suppress HWRM errors for HWRM_NVM_GET_VARIABLE command
  bnxt_en: Fix handling FRAG_ERR when NVM_INSTALL_UPDATE cmd fails
  bnxt_en: Improve RX doorbell sequence.
  bnxt_en: Fix VNIC clearing logic for 57500 chips.
  net: kalmia: fix memory leaks
  cx82310_eth: fix a memory leak bug
  bnx2x: Fix VF's VLAN reconfiguration in reload.
  Bluetooth: Add debug setting for changing minimum encryption key size
  tipc: fix false detection of retransmit failures
  lan78xx: Fix memory leaks
  MAINTAINERS: r8169: Update path to the driver
  MAINTAINERS: PHY LIBRARY: Update files in the record
  ...

7 files changed, 155 insertions, 22 deletions

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 5215e0870bcb..6a71324be628 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -204,7 +204,11 @@ int do_pin_fd(int fd, const char *name)
 	if (err)
 		return err;
 
-	return bpf_obj_pin(fd, name);
+	err = bpf_obj_pin(fd, name);
+	if (err)
+		p_err("can't pin the object (%s): %s", name, strerror(errno));
+
+	return err;
 }
 
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
@@ -237,7 +241,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
-		p_err("can't get prog by id (%u): %s", id, strerror(errno));
+		p_err("can't open object by id (%u): %s", id, strerror(errno));
 		return -1;
 	}
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e455018da65..a5aa7d3ac6a1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1466,8 +1466,8 @@ union bpf_attr {
  * 		If no cookie has been set yet, generate a new cookie. Once
  * 		generated, the socket cookie remains stable for the life of the
  * 		socket. This helper can be useful for monitoring per socket
- * 		networking traffic statistics as it provides a unique socket
- * 		identifier per namespace.
+ * 		networking traffic statistics as it provides a global socket
+ * 		identifier that can be assumed unique.
  * 	Return
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
@@ -1571,8 +1571,11 @@ union bpf_attr {
  * 		but this is only implemented for native XDP (with driver
  * 		support) as of this writing).
  *
- * 		All values for *flags* are reserved for future usage, and must
- * 		be left at zero.
+ * 		The lower two bits of *flags* are used as the return code if
+ * 		the map lookup fails. This is so that the return value can be
+ * 		one of the XDP program return codes up to XDP_TX, as chosen by
+ * 		the caller. Any higher bits in the *flags* argument must be
+ * 		unset.
  *
  * 		When used to redirect packets to net devices, this helper
  * 		provides a high performance increase over **bpf_redirect**\ ().
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2586b6cb8f34..2b57d7ea7836 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -182,7 +182,6 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	enum bpf_attach_type expected_attach_type;
-	int btf_fd;
 	void *func_info;
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
@@ -313,7 +312,6 @@ void bpf_program__unload(struct bpf_program *prog)
 	prog->instances.nr = -1;
 	zfree(&prog->instances.fds);
 
-	zclose(prog->btf_fd);
 	zfree(&prog->func_info);
 	zfree(&prog->line_info);
 }
@@ -392,7 +390,6 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
 	prog->type = BPF_PROG_TYPE_UNSPEC;
-	prog->btf_fd = -1;
 
 	return 0;
 errout:
@@ -2288,9 +2285,6 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
 		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
 	}
 
-	if (!insn_offset)
-		prog->btf_fd = btf__fd(obj->btf);
-
 	return 0;
 }
 
@@ -2463,7 +2457,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int log_buf_size = BPF_LOG_BUF_SIZE;
 	char *log_buf;
-	int ret;
+	int btf_fd, ret;
 
 	if (!insns || !insns_cnt)
 		return -EINVAL;
@@ -2478,7 +2472,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
-	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
+	/* if .BTF.ext was loaded, kernel supports associated BTF for prog */
+	if (prog->obj->btf_ext)
+		btf_fd = bpf_object__btf_fd(prog->obj);
+	else
+		btf_fd = -1;
+	load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0;
 	load_attr.func_info = prog->func_info;
 	load_attr.func_info_rec_size = prog->func_info_rec_size;
 	load_attr.func_info_cnt = prog->func_info_cnt;
@@ -5000,13 +4999,15 @@ int libbpf_num_possible_cpus(void)
 	static const char *fcpu = "/sys/devices/system/cpu/possible";
 	int len = 0, n = 0, il = 0, ir = 0;
 	unsigned int start = 0, end = 0;
+	int tmp_cpus = 0;
 	static int cpus;
 	char buf[128];
 	int error = 0;
 	int fd = -1;
 
-	if (cpus > 0)
-		return cpus;
+	tmp_cpus = READ_ONCE(cpus);
+	if (tmp_cpus > 0)
+		return tmp_cpus;
 
 	fd = open(fcpu, O_RDONLY);
 	if (fd < 0) {
@@ -5029,7 +5030,7 @@ int libbpf_num_possible_cpus(void)
 	}
 	buf[len] = '\0';
 
-	for (ir = 0, cpus = 0; ir <= len; ir++) {
+	for (ir = 0, tmp_cpus = 0; ir <= len; ir++) {
 		/* Each sub string separated by ',' has format \d+-\d+ or \d+ */
 		if (buf[ir] == ',' || buf[ir] == '\0') {
 			buf[ir] = '\0';
@@ -5041,13 +5042,15 @@ int libbpf_num_possible_cpus(void)
 			} else if (n == 1) {
 				end = start;
 			}
-			cpus += end - start + 1;
+			tmp_cpus += end - start + 1;
 			il = ir + 1;
 		}
 	}
-	if (cpus <= 0) {
-		pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu);
+	if (tmp_cpus <= 0) {
+		pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu);
 		return -EINVAL;
 	}
-	return cpus;
+
+	WRITE_ONCE(cpus, tmp_cpus);
+	return tmp_cpus;
 }
diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c
index 5e980a5ab69d..1fc4e61e9f9f 100644
--- a/tools/testing/selftests/bpf/verifier/loops1.c
+++ b/tools/testing/selftests/bpf/verifier/loops1.c
@@ -159,3 +159,31 @@
 	.errstr = "loop detected",
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
+{
+	"not-taken loop with back jump to 1st insn",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 123),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 4, -2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.retval = 123,
+},
+{
+	"taken loop with back jump to 1st insn",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_1, 10),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, -3),
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.retval = 55,
+},
diff --git a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
index 41476399e184..f6e65674b83c 100755
--- a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
+++ b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh
@@ -30,7 +30,7 @@ do_test() {
 	ip netns exec "${NETNS}" ./tcp_fastopen_backup_key "$1"
 	val=$(ip netns exec "${NETNS}" nstat -az | \
 		grep TcpExtTCPFastOpenPassiveFail | awk '{print $2}')
-	if [ $val -ne 0 ]; then
+	if [ "$val" != 0 ]; then
 		echo "FAIL: TcpExtTCPFastOpenPassiveFail non-zero"
 		return 1
 	fi
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index fe52488a6f72..16571ac1dab4 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -321,4 +321,52 @@ else
 	ip netns exec nsr1 nft list ruleset
 fi
 
+KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
+KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
+SPI1=$RANDOM
+SPI2=$RANDOM
+
+if [ $SPI1 -eq $SPI2 ]; then
+	SPI2=$((SPI2+1))
+fi
+
+do_esp() {
+    local ns=$1
+    local me=$2
+    local remote=$3
+    local lnet=$4
+    local rnet=$5
+    local spi_out=$6
+    local spi_in=$7
+
+    ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in  enc aes $KEY_AES  auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
+    ip -net $ns xfrm state add src $me  dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+    # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+    ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+    # to fwd decrypted packets after esp processing:
+    ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 1 action allow
+
+}
+
+do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+
+do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+
+ip netns exec nsr1 nft delete table ip nat
+
+# restore default routes
+ip -net ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net ns2 route add default via 10.0.2.1
+ip -net ns2 route add default via dead:2::1
+
+test_tcp_forwarding ns1 ns2
+if [ $? -eq 0 ] ;then
+	echo "PASS: ipsec tunnel mode for ns1/ns2"
+else
+	echo "FAIL: ipsec tunnel mode for ns1/ns2"
+	ip netns exec nsr1 nft list ruleset 1>&2
+	ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index bf5ebf59c2d4..9cdd2e31ac2c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -670,5 +670,52 @@
         "teardown": [
             "$TC actions flush action skbedit"
         ]
+    },
+    {
+        "id": "630c",
+        "name": "Add batch of 32 skbedit actions with all parameters and cookie",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "32",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "706d",
+        "name": "Delete batch of 32 skbedit actions with all parameters",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+        ],
+        "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "^[ \t]+index [0-9]+ ref",
+        "matchCount": "0",
+        "teardown": []
     }
 ]