From b13b8787c95c156b093305e9f006a6fb7d9119b1 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 7 Nov 2018 13:36:07 -0800
Subject: [PATCH 01/53] bpf: Fix IPv6 dport byte order in bpf_sk_lookup_udp

Lookup functions in sk_lookup have different expectations about byte
order of provided arguments.

Specifically __inet_lookup, __udp4_lib_lookup and __udp6_lib_lookup
expect dport to be in network byte order and do ntohs(dport) internally.

At the same time __inet6_lookup expects dport to be in host byte order
and correspondingly name the argument hnum.

sk_lookup works correctly with __inet_lookup, __udp4_lib_lookup and
__inet6_lookup with regard to dport. But in __udp6_lib_lookup case it
uses host instead of expected network byte order. It makes result
returned by bpf_sk_lookup_udp for IPv6 incorrect.

The patch fixes byte order of dport passed to __udp6_lib_lookup.

Originally sk_lookup properly handled UDPv6, but not TCPv6. 5ef0ae84f02a
fixes TCPv6 but breaks UDPv6.

Fixes: 5ef0ae84f02a ("bpf: Fix IPv6 dport byte-order in bpf_sk_lookup")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Joe Stringer <joe@wand.net.nz>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/filter.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5ebc7d1..9a1327eb25fa 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
-		u16 hnum = ntohs(tuple->ipv6.dport);
 		int sdif = inet6_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
 			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
 					    src6, tuple->ipv6.sport,
-					    dst6, hnum,
+					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);
 		else if (likely(ipv6_bpf_stub))
 			sk = ipv6_bpf_stub->udp6_lib_lookup(net,
 							    src6, tuple->ipv6.sport,
-							    dst6, hnum,
+							    dst6, tuple->ipv6.dport,
 							    dif, sdif,
 							    &udp_table, skb);
 #endif

From 49a249c387268882e8393dd1fafc51e3b21cb7a2 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 7 Nov 2018 19:55:36 -0800
Subject: [PATCH 02/53] tools/bpftool: copy a few net uapi headers to tools
 directory

Commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
added certain networking support to bpftool.
The implementation relies on a relatively recent uapi header file
linux/tc_act/tc_bpf.h on the host which contains the marco
definition of TCA_ACT_BPF_ID.

Unfortunately, this is not the case for all distributions.
See the email message below where rhel-7.2 does not have
an up-to-date linux/tc_act/tc_bpf.h.
  https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1799211.html
Further investigation found that linux/pkt_cls.h is also needed for macro
TCA_BPF_TAG.

This patch fixed the issue by copying linux/tc_act/tc_bpf.h
and linux/pkt_cls.h from kernel include/uapi directory to
tools/include/uapi directory so building the bpftool does not depend
on host system for these files.

Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Cc: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/pkt_cls.h       | 612 +++++++++++++++++++++++
 tools/include/uapi/linux/tc_act/tc_bpf.h |  37 ++
 2 files changed, 649 insertions(+)
 create mode 100644 tools/include/uapi/linux/pkt_cls.h
 create mode 100644 tools/include/uapi/linux/tc_act/tc_bpf.h

diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 000000000000..401d0c1e612d
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 000000000000..6e89a5df49a4
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	TCA_ACT_BPF_FD,
+	TCA_ACT_BPF_NAME,
+	TCA_ACT_BPF_PAD,
+	TCA_ACT_BPF_TAG,
+	TCA_ACT_BPF_ID,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif

From 53909030aa29bffe1f8490df62176c2375135652 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 8 Nov 2018 11:52:25 +0000
Subject: [PATCH 03/53] tools: bpftool: prevent infinite loop in get_fdinfo()

Function getline() returns -1 on failure to read a line, thus creating
an infinite loop in get_fdinfo() if the key is not found. Fix it by
calling the function only as long as we get a strictly positive return
value.

Found by copying the code for a key which is not always present...

Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 25af85304ebe..e070b00ac309 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -304,7 +304,7 @@ char *get_fdinfo(int fd, const char *key)
 		return NULL;
 	}
 
-	while ((n = getline(&line, &line_n, fdi))) {
+	while ((n = getline(&line, &line_n, fdi)) > 0) {
 		char *value;
 		int len;
 

From a8bfd2bc29f3bf35c7b588b102662375b0184475 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 8 Nov 2018 11:52:26 +0000
Subject: [PATCH 04/53] tools: bpftool: fix plain output and doc for --bpffs
 option

Edit the documentation of the -f|--bpffs option to make it explicit that
it dumps paths of pinned programs when bpftool is used to list the
programs only, so that users do not believe they will see the name of
the newly pinned program with "bpftool prog pin" or "bpftool prog load".

Also fix the plain output: do not add a blank line after each program
block, in order to remain consistent with what bpftool does when the
option is not passed.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 3 ++-
 tools/bpf/bpftool/prog.c                         | 3 +--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..81fb97acfaeb 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -124,7 +124,8 @@ OPTIONS
 		  Generate human-readable JSON output. Implies **-j**.
 
 	-f, --bpffs
-		  Show file names of pinned programs.
+		  When showing BPF programs, show file names of pinned
+		  programs.
 
 EXAMPLES
 ========
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 5302ee282409..9785244acc7b 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -357,10 +357,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (!hash_empty(prog_table.table)) {
 		struct pinned_obj *obj;
 
-		printf("\n");
 		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
 			if (obj->id == info->id)
-				printf("\tpinned %s\n", obj->path);
+				printf("\n\tpinned %s", obj->path);
 		}
 	}
 

From f120919f9905a2cad9dea792a28a11fb623f72c1 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 8 Nov 2018 11:52:27 +0000
Subject: [PATCH 05/53] tools: bpftool: pass an argument to silence
 open_obj_pinned()

Function open_obj_pinned() prints error messages when it fails to open a
link in the BPF virtual file system. However, in some occasions it is
not desirable to print an error, for example when we parse all links
under the bpffs root, and the error is due to some paths actually being
symbolic links.

Example output:

    # ls -l /sys/fs/bpf/
    lrwxrwxrwx 1 root root 0 Oct 18 19:00 ip -> /sys/fs/bpf/tc/
    drwx------ 3 root root 0 Oct 18 19:00 tc
    lrwxrwxrwx 1 root root 0 Oct 18 19:00 xdp -> /sys/fs/bpf/tc/

    # bpftool --bpffs prog show
    Error: bpf obj get (/sys/fs/bpf): Permission denied
    Error: bpf obj get (/sys/fs/bpf): Permission denied

    # strace -e bpf bpftool --bpffs prog show
    bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/ip", bpf_fd=0}, 72) = -1 EACCES (Permission denied)
    Error: bpf obj get (/sys/fs/bpf): Permission denied
    bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/xdp", bpf_fd=0}, 72) = -1 EACCES (Permission denied)
    Error: bpf obj get (/sys/fs/bpf): Permission denied
    ...

To fix it, pass a bool as a second argument to the function, and prevent
it from printing an error when the argument is set to true.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c | 15 ++++++++-------
 tools/bpf/bpftool/main.h   |  2 +-
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index e070b00ac309..70fd48d79f61 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -130,16 +130,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 	return 0;
 }
 
-int open_obj_pinned(char *path)
+int open_obj_pinned(char *path, bool quiet)
 {
 	int fd;
 
 	fd = bpf_obj_get(path);
 	if (fd < 0) {
-		p_err("bpf obj get (%s): %s", path,
-		      errno == EACCES && !is_bpffs(dirname(path)) ?
-		    "directory not in bpf file system (bpffs)" :
-		    strerror(errno));
+		if (!quiet)
+			p_err("bpf obj get (%s): %s", path,
+			      errno == EACCES && !is_bpffs(dirname(path)) ?
+			    "directory not in bpf file system (bpffs)" :
+			    strerror(errno));
 		return -1;
 	}
 
@@ -151,7 +152,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
 	enum bpf_obj_type type;
 	int fd;
 
-	fd = open_obj_pinned(path);
+	fd = open_obj_pinned(path, false);
 	if (fd < 0)
 		return -1;
 
@@ -384,7 +385,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
 		while ((ftse = fts_read(fts))) {
 			if (!(ftse->fts_info & FTS_F))
 				continue;
-			fd = open_obj_pinned(ftse->fts_path);
+			fd = open_obj_pinned(ftse->fts_path, true);
 			if (fd < 0)
 				continue;
 
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 28322ace2856..a8bf1e2d9818 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -127,7 +127,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv,
 int get_fd_type(int fd);
 const char *get_fd_type_name(enum bpf_obj_type type);
 char *get_fdinfo(int fd, const char *key);
-int open_obj_pinned(char *path);
+int open_obj_pinned(char *path, bool quiet);
 int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
 int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
 int do_pin_fd(int fd, const char *name);

From f98e46a251d04e1f9a7a14a7f2d166b34da525e5 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 8 Nov 2018 11:52:28 +0000
Subject: [PATCH 06/53] tools: bpftool: update references to other man pages in
 documentation

Update references to other bpftool man pages at the bottom of each
manual page. Also reference the "bpf(2)" and "bpf-helpers(7)" man pages.

References are sorted by number of man section, then by
"prog-and-map-go-first", the other pages in alphabetical order.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 8 +++++++-
 tools/bpf/bpftool/Documentation/bpftool-map.rst    | 8 +++++++-
 tools/bpf/bpftool/Documentation/bpftool-net.rst    | 8 +++++++-
 tools/bpf/bpftool/Documentation/bpftool-perf.rst   | 8 +++++++-
 tools/bpf/bpftool/Documentation/bpftool-prog.rst   | 8 +++++++-
 tools/bpf/bpftool/Documentation/bpftool.rst        | 9 +++++++--
 6 files changed, 42 insertions(+), 7 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index edbe81534c6d..d07ccf8a23f7 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -137,4 +137,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..7bb787cfa971 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -171,4 +171,10 @@ The following three commands are equivalent:
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 408ec30d8872..ed87c9b619ad 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -136,4 +136,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index e3eb0eab7641..f4c5e5538bb8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -78,4 +78,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 81fb97acfaeb..ecf618807125 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -207,4 +207,10 @@ EXAMPLES
 
 SEE ALSO
 ========
-	**bpftool**\ (8), **bpftool-map**\ (8), **bpftool-cgroup**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 04cd4f92ab89..129b7a9c0f9b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -63,5 +63,10 @@ OPTIONS
 
 SEE ALSO
 ========
-	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
-        **bpftool-perf**\ (8), **bpftool-net**\ (8)
+	**bpf**\ (2),
+	**bpf-helpers**\ (7),
+	**bpftool-prog**\ (8),
+	**bpftool-map**\ (8),
+	**bpftool-cgroup**\ (8),
+	**bpftool-net**\ (8),
+	**bpftool-perf**\ (8)

From da85d8bfd1512461bcfb64929e8426cf340b3707 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@cn.fujitsu.com>
Date: Mon, 5 Nov 2018 16:57:48 +0800
Subject: [PATCH 07/53] kselftests/bpf: use ping6 as the default ipv6 ping
 binary when it exists

At commit deee2cae27d1 ("kselftests/bpf: use ping6 as the default ipv6 ping
binary if it exists"), it fixed similar issues for shell script, but it
missed a same issue in the C code.

Fixes: 371e4fcc9d96 ("selftests/bpf: cgroup local storage-based network counters")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
CC: Philip Li <philip.li@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_netcnt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
index 7887df693399..44ed7f29f8ab 100644
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ b/tools/testing/selftests/bpf/test_netcnt.c
@@ -81,7 +81,10 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0);
+	if (system("which ping6 &>/dev/null") == 0)
+		assert(!system("ping6 localhost -c 10000 -f -q > /dev/null"));
+	else
+		assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null"));
 
 	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
 			   &prog_cnt)) {

From fd3e71a9f71e232181a225301a75936373636ccc Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 03:43:19 +0900
Subject: [PATCH 08/53] netfilter: nf_conncount: use spin_lock_bh instead of
 spin_lock

conn_free() holds lock with spin_lock() and it is called by both
nf_conncount_lookup() and nf_conncount_gc_list(). nf_conncount_lookup()
is called from bottom-half context and nf_conncount_gc_list() from
process context. So that spin_lock() call is not safe. Hence
conn_free() should use spin_lock_bh() instead of spin_lock().

test commands:
   %nft add table ip filter
   %nft add chain ip filter input { type filter hook input priority 0\; }
   %nft add rule filter input meter test { ip saddr ct count over 2 } \
	   counter

splat looks like:
[  461.996507] ================================
[  461.998999] WARNING: inconsistent lock state
[  461.998999] 4.19.0-rc6+ #22 Not tainted
[  461.998999] --------------------------------
[  461.998999] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[  461.998999] kworker/0:2/134 [HC0[0]:SC0[0]:HE1:SE1] takes:
[  461.998999] 00000000a71a559a (&(&list->list_lock)->rlock){+.?.}, at: conn_free+0x69/0x2b0 [nf_conncount]
[  461.998999] {IN-SOFTIRQ-W} state was registered at:
[  461.998999]   _raw_spin_lock+0x30/0x70
[  461.998999]   nf_conncount_add+0x28a/0x520 [nf_conncount]
[  461.998999]   nft_connlimit_eval+0x401/0x580 [nft_connlimit]
[  461.998999]   nft_dynset_eval+0x32b/0x590 [nf_tables]
[  461.998999]   nft_do_chain+0x497/0x1430 [nf_tables]
[  461.998999]   nft_do_chain_ipv4+0x255/0x330 [nf_tables]
[  461.998999]   nf_hook_slow+0xb1/0x160
[ ... ]
[  461.998999] other info that might help us debug this:
[  461.998999]  Possible unsafe locking scenario:
[  461.998999]
[  461.998999]        CPU0
[  461.998999]        ----
[  461.998999]   lock(&(&list->list_lock)->rlock);
[  461.998999]   <Interrupt>
[  461.998999]     lock(&(&list->list_lock)->rlock);
[  461.998999]
[  461.998999]  *** DEADLOCK ***
[  461.998999]
[ ... ]

Fixes: 5c789e131cbb ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 02ca7df793f5..71b1f4f99580 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -106,15 +106,15 @@ nf_conncount_add(struct nf_conncount_list *list,
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
-	spin_lock(&list->list_lock);
+	spin_lock_bh(&list->list_lock);
 	if (list->dead == true) {
 		kmem_cache_free(conncount_conn_cachep, conn);
-		spin_unlock(&list->list_lock);
+		spin_unlock_bh(&list->list_lock);
 		return NF_CONNCOUNT_SKIP;
 	}
 	list_add_tail(&conn->node, &list->head);
 	list->count++;
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	return NF_CONNCOUNT_ADDED;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
@@ -132,10 +132,10 @@ static bool conn_free(struct nf_conncount_list *list,
 {
 	bool free_entry = false;
 
-	spin_lock(&list->list_lock);
+	spin_lock_bh(&list->list_lock);
 
 	if (list->count == 0) {
-		spin_unlock(&list->list_lock);
+		spin_unlock_bh(&list->list_lock);
                 return free_entry;
 	}
 
@@ -144,7 +144,7 @@ static bool conn_free(struct nf_conncount_list *list,
 	if (list->count == 0)
 		free_entry = true;
 
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	call_rcu(&conn->rcu_head, __conn_free);
 	return free_entry;
 }

From 31568ec09ea02a050249921698c9729419539cce Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 03:44:11 +0900
Subject: [PATCH 09/53] netfilter: nf_conncount: fix list_del corruption in
 conn_free

nf_conncount_tuple is an element of nft_connlimit and that is deleted by
conn_free(). Elements can be deleted by both GC routine and data path
functions (nf_conncount_lookup, nf_conncount_add) and they call
conn_free() to free elements. But conn_free() only protects lists, not
each element. So that list_del corruption could occurred.

The conn_free() doesn't check whether element is already deleted. In
order to protect elements, dead flag is added. If an element is deleted,
dead flag is set. The only conn_free() can delete elements so that both
list lock and dead flag are enough to protect it.

test commands:
   %nft add table ip filter
   %nft add chain ip filter input { type filter hook input priority 0\; }
   %nft add rule filter input meter test { ip id ct count over 2 } counter

splat looks like:
[ 1779.495778] list_del corruption, ffff8800b6e12008->prev is LIST_POISON2 (dead000000000200)
[ 1779.505453] ------------[ cut here ]------------
[ 1779.506260] kernel BUG at lib/list_debug.c:50!
[ 1779.515831] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 1779.516772] CPU: 0 PID: 33 Comm: kworker/0:2 Not tainted 4.19.0-rc6+ #22
[ 1779.516772] Workqueue: events_power_efficient nft_rhash_gc [nf_tables_set]
[ 1779.516772] RIP: 0010:__list_del_entry_valid+0xd8/0x150
[ 1779.516772] Code: 39 48 83 c4 08 b8 01 00 00 00 5b 5d c3 48 89 ea 48 c7 c7 00 c3 5b 98 e8 0f dc 40 ff 0f 0b 48 c7 c7 60 c3 5b 98 e8 01 dc 40 ff <0f> 0b 48 c7 c7 c0 c3 5b 98 e8 f3 db 40 ff 0f 0b 48 c7 c7 20 c4 5b
[ 1779.516772] RSP: 0018:ffff880119127420 EFLAGS: 00010286
[ 1779.516772] RAX: 000000000000004e RBX: dead000000000200 RCX: 0000000000000000
[ 1779.516772] RDX: 000000000000004e RSI: 0000000000000008 RDI: ffffed0023224e7a
[ 1779.516772] RBP: ffff88011934bc10 R08: ffffed002367cea9 R09: ffffed002367cea9
[ 1779.516772] R10: 0000000000000001 R11: ffffed002367cea8 R12: ffff8800b6e12008
[ 1779.516772] R13: ffff8800b6e12010 R14: ffff88011934bc20 R15: ffff8800b6e12008
[ 1779.516772] FS:  0000000000000000(0000) GS:ffff88011b200000(0000) knlGS:0000000000000000
[ 1779.516772] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1779.516772] CR2: 00007fc876534010 CR3: 000000010da16000 CR4: 00000000001006f0
[ 1779.516772] Call Trace:
[ 1779.516772]  conn_free+0x9f/0x2b0 [nf_conncount]
[ 1779.516772]  ? nf_ct_tmpl_alloc+0x2a0/0x2a0 [nf_conntrack]
[ 1779.516772]  ? nf_conncount_add+0x520/0x520 [nf_conncount]
[ 1779.516772]  ? do_raw_spin_trylock+0x1a0/0x1a0
[ 1779.516772]  ? do_raw_spin_trylock+0x10/0x1a0
[ 1779.516772]  find_or_evict+0xe5/0x150 [nf_conncount]
[ 1779.516772]  nf_conncount_gc_list+0x162/0x360 [nf_conncount]
[ 1779.516772]  ? nf_conncount_lookup+0xee0/0xee0 [nf_conncount]
[ 1779.516772]  ? _raw_spin_unlock_irqrestore+0x45/0x50
[ 1779.516772]  ? trace_hardirqs_off+0x6b/0x220
[ 1779.516772]  ? trace_hardirqs_on_caller+0x220/0x220
[ 1779.516772]  nft_rhash_gc+0x16b/0x540 [nf_tables_set]
[ ... ]

Fixes: 5c789e131cbb ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 71b1f4f99580..cb33709138df 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -49,6 +49,7 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
+	bool				dead;
 	struct rcu_head			rcu_head;
 };
 
@@ -106,6 +107,7 @@ nf_conncount_add(struct nf_conncount_list *list,
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
+	conn->dead = false;
 	spin_lock_bh(&list->list_lock);
 	if (list->dead == true) {
 		kmem_cache_free(conncount_conn_cachep, conn);
@@ -134,12 +136,13 @@ static bool conn_free(struct nf_conncount_list *list,
 
 	spin_lock_bh(&list->list_lock);
 
-	if (list->count == 0) {
+	if (conn->dead) {
 		spin_unlock_bh(&list->list_lock);
-                return free_entry;
+		return free_entry;
 	}
 
 	list->count--;
+	conn->dead = true;
 	list_del_rcu(&conn->node);
 	if (list->count == 0)
 		free_entry = true;

From 3c5cdb17c3be76714dfd0d03e384f70579545614 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 5 Nov 2018 03:44:39 +0900
Subject: [PATCH 10/53] netfilter: nf_conncount: fix unexpected permanent node
 of list.

When list->count is 0, the list is deleted by GC. But list->count is
never reached 0 because initial count value is 1 and it is increased
when node is inserted. So that initial value of list->count should be 0.

Originally GC always finds zero count list through deleting node and
decreasing count. However, list may be left empty since node insertion
may fail eg.  allocaton problem. In order to solve this problem, GC
routine also finds zero count list without deleting node.

Fixes: cb2b36f5a97d ("netfilter: nf_conncount: Switch to plain list")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index cb33709138df..8acae4a3e4c0 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -144,8 +144,10 @@ static bool conn_free(struct nf_conncount_list *list,
 	list->count--;
 	conn->dead = true;
 	list_del_rcu(&conn->node);
-	if (list->count == 0)
+	if (list->count == 0) {
+		list->dead = true;
 		free_entry = true;
+	}
 
 	spin_unlock_bh(&list->list_lock);
 	call_rcu(&conn->rcu_head, __conn_free);
@@ -248,7 +250,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list)
 {
 	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
-	list->count = 1;
+	list->count = 0;
 	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
@@ -262,6 +264,7 @@ bool nf_conncount_gc_list(struct net *net,
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
 	bool free_entry = false;
+	bool ret = false;
 
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
 		found = find_or_evict(net, list, conn, &free_entry);
@@ -291,7 +294,15 @@ bool nf_conncount_gc_list(struct net *net,
 		if (collected > CONNCOUNT_GC_MAX_NODES)
 			return false;
 	}
-	return false;
+
+	spin_lock_bh(&list->list_lock);
+	if (!list->count) {
+		list->dead = true;
+		ret = true;
+	}
+	spin_unlock_bh(&list->list_lock);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
@@ -417,6 +428,7 @@ insert_tree(struct net *net,
 	nf_conncount_list_init(&rbconn->list);
 	list_add(&conn->node, &rbconn->list.head);
 	count = 1;
+	rbconn->list.count = count;
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);

From 0fb39bbe43d4481fcf300d2b5822de60942fd189 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 31 Oct 2018 18:26:20 +0100
Subject: [PATCH 11/53] netfilter: nf_tables: don't skip inactive chains during
 update

There is no synchronization between packet path and the configuration plane.

The packet path uses two arrays with rules, one contains the current (active)
generation.  The other either contains the last (obsolete) generation or
the future one.

Consider:
cpu1               cpu2
                   nft_do_chain(c);
delete c
net->gen++;
                   genbit = !!net->gen;
                   rules = c->rg[genbit];

cpu1 ignores c when updating if c is not active anymore in the new
generation.

On cpu2, we now use rules from wrong generation, as c->rg[old]
contains the rules matching 'c' whereas c->rg[new] was not updated and
can even point to rules that have been free'd already, causing a crash.

To fix this, make sure that 'current' to the 'next' generation are
identical for chains that are going away so that c->rg[new] will just
use the matching rules even if genbit was incremented already.

Fixes: 0cbc06b3faba7 ("netfilter: nf_tables: remove synchronize_rcu in commit phase")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 42487d01a3ed..dd577e7d100c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6324,7 +6324,7 @@ static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules)
 	call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old);
 }
 
-static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain)
+static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain)
 {
 	struct nft_rule **g0, **g1;
 	bool next_genbit;
@@ -6441,11 +6441,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	/* step 2.  Make rules_gen_X visible to packet path */
 	list_for_each_entry(table, &net->nft.tables, list) {
-		list_for_each_entry(chain, &table->chains, list) {
-			if (!nft_is_active_next(net, chain))
-				continue;
-			nf_tables_commit_chain_active(net, chain);
-		}
+		list_for_each_entry(chain, &table->chains, list)
+			nf_tables_commit_chain(net, chain);
 	}
 
 	/*

From 25d8bcedbf4329895dbaf9dd67baa6f18dad918c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 31 Oct 2018 18:26:21 +0100
Subject: [PATCH 12/53] selftests: add script to stress-test nft packet path
 vs. control plane

Start flood ping for each cpu while loading/flushing rulesets to make
sure we do not access already-free'd rules from nf_tables evaluation loop.

Also add this to TARGETS so 'make run_tests' in selftest dir runs it
automatically.

This would have caught the bug fixed in previous change
("netfilter: nf_tables: do not skip inactive chains during generation update")
sooner.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/Makefile              |  1 +
 tools/testing/selftests/netfilter/Makefile    |  6 ++
 tools/testing/selftests/netfilter/config      |  2 +
 .../selftests/netfilter/nft_trans_stress.sh   | 78 +++++++++++++++++++
 4 files changed, 87 insertions(+)
 create mode 100644 tools/testing/selftests/netfilter/Makefile
 create mode 100644 tools/testing/selftests/netfilter/config
 create mode 100755 tools/testing/selftests/netfilter/nft_trans_stress.sh

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index f1fe492c8e17..f0017c831e57 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -24,6 +24,7 @@ TARGETS += memory-hotplug
 TARGETS += mount
 TARGETS += mqueue
 TARGETS += net
+TARGETS += netfilter
 TARGETS += nsfs
 TARGETS += powerpc
 TARGETS += proc
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
new file mode 100644
index 000000000000..47ed6cef93fb
--- /dev/null
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for netfilter selftests
+
+TEST_PROGS := nft_trans_stress.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
new file mode 100644
index 000000000000..1017313e41a8
--- /dev/null
+++ b/tools/testing/selftests/netfilter/config
@@ -0,0 +1,2 @@
+CONFIG_NET_NS=y
+NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
new file mode 100755
index 000000000000..f1affd12c4b1
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -0,0 +1,78 @@
+#!/bin/bash
+#
+# This test is for stress-testing the nf_tables config plane path vs.
+# packet path processing: Make sure we never release rules that are
+# still visible to other cpus.
+#
+# set -e
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+testns=testns1
+tables="foo bar baz quux"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+tmp=$(mktemp)
+
+for table in $tables; do
+	echo add table inet "$table" >> "$tmp"
+	echo flush table inet "$table" >> "$tmp"
+
+	echo "add chain inet $table INPUT { type filter hook input priority 0; }" >> "$tmp"
+	echo "add chain inet $table OUTPUT { type filter hook output priority 0; }" >> "$tmp"
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		echo "add chain inet $table $chain" >> "$tmp"
+	done
+
+	for c in $(seq 1 400); do
+		chain=$(printf "chain%03u" "$c")
+		for BASE in INPUT OUTPUT; do
+			echo "add rule inet $table $BASE counter jump $chain" >> "$tmp"
+		done
+		echo "add rule inet $table $chain counter return" >> "$tmp"
+	done
+done
+
+ip netns add "$testns"
+ip -netns "$testns" link set lo up
+
+lscpu | grep ^CPU\(s\): | ( read cpu cpunum ;
+cpunum=$((cpunum-1))
+for i in $(seq 0 $cpunum);do
+	mask=$(printf 0x%x $((1<<$i)))
+        ip netns exec "$testns" taskset $mask ping -4 127.0.0.1 -fq > /dev/null &
+        ip netns exec "$testns" taskset $mask ping -6 ::1 -fq > /dev/null &
+done)
+
+sleep 1
+
+for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done
+
+for table in $tables;do
+	randsleep=$((RANDOM%10))
+	sleep $randsleep
+	ip netns exec "$testns" nft delete table inet $table 2>/dev/null
+done
+
+randsleep=$((RANDOM%10))
+sleep $randsleep
+
+pkill -9 ping
+
+wait
+
+rm -f "$tmp"
+ip netns del "$testns"

From 447750f281abef547be44fdcfe3bc4447b3115a8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sun, 4 Nov 2018 12:07:14 +0100
Subject: [PATCH 13/53] netfilter: nf_tables: don't use position attribute on
 rule replacement

Its possible to set both HANDLE and POSITION when replacing a rule.
In this case, the rule at POSITION gets replaced using the
userspace-provided handle.  Rule handles are supposed to be generated
by the kernel only.

Duplicate handles should be harmless, however better disable this "feature"
by only checking for the POSITION attribute on insert operations.

Fixes: 5e94846686d0 ("netfilter: nf_tables: add insert operation")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index dd577e7d100c..e496030fdc3b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2589,17 +2589,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 
 		if (chain->use == UINT_MAX)
 			return -EOVERFLOW;
-	}
 
-	if (nla[NFTA_RULE_POSITION]) {
-		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
-			return -EOPNOTSUPP;
-
-		pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
-		old_rule = __nft_rule_lookup(chain, pos_handle);
-		if (IS_ERR(old_rule)) {
-			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
-			return PTR_ERR(old_rule);
+		if (nla[NFTA_RULE_POSITION]) {
+			pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
+			old_rule = __nft_rule_lookup(chain, pos_handle);
+			if (IS_ERR(old_rule)) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
+				return PTR_ERR(old_rule);
+			}
 		}
 	}
 

From 0fbcc5b568edab7d848b7c7fa66d44ffbd4133c0 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 19 Oct 2018 00:27:57 +0900
Subject: [PATCH 14/53] netfilter: xt_RATEEST: remove netns exit routine

xt_rateest_net_exit() was added to check whether rules are flushed
successfully. but ->net_exit() callback is called earlier than
->destroy() callback.
So that ->net_exit() callback can't check that.

test commands:
   %ip netns add vm1
   %ip netns exec vm1 iptables -t mangle -I PREROUTING -p udp \
	   --dport 1111 -j RATEEST --rateest-name ap \
	   --rateest-interval 250ms --rateest-ewma 0.5s
   %ip netns del vm1

splat looks like:
[  668.813518] WARNING: CPU: 0 PID: 87 at net/netfilter/xt_RATEEST.c:210 xt_rateest_net_exit+0x210/0x340 [xt_RATEEST]
[  668.813518] Modules linked in: xt_RATEEST xt_tcpudp iptable_mangle bpfilter ip_tables x_tables
[  668.813518] CPU: 0 PID: 87 Comm: kworker/u4:2 Not tainted 4.19.0-rc7+ #21
[  668.813518] Workqueue: netns cleanup_net
[  668.813518] RIP: 0010:xt_rateest_net_exit+0x210/0x340 [xt_RATEEST]
[  668.813518] Code: 00 48 8b 85 30 ff ff ff 4c 8b 23 80 38 00 0f 85 24 01 00 00 48 8b 85 30 ff ff ff 4d 85 e4 4c 89 a5 58 ff ff ff c6 00 f8 74 b2 <0f> 0b 48 83 c3 08 4c 39 f3 75 b0 48 b8 00 00 00 00 00 fc ff df 49
[  668.813518] RSP: 0018:ffff8801156c73f8 EFLAGS: 00010282
[  668.813518] RAX: ffffed0022ad8e85 RBX: ffff880118928e98 RCX: 5db8012a00000000
[  668.813518] RDX: ffff8801156c7428 RSI: 00000000cb1d185f RDI: ffff880115663b74
[  668.813518] RBP: ffff8801156c74d0 R08: ffff8801156633c0 R09: 1ffff100236440be
[  668.813518] R10: 0000000000000001 R11: ffffed002367d852 R12: ffff880115142b08
[  668.813518] R13: 1ffff10022ad8e81 R14: ffff880118928ea8 R15: dffffc0000000000
[  668.813518] FS:  0000000000000000(0000) GS:ffff88011b200000(0000) knlGS:0000000000000000
[  668.813518] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  668.813518] CR2: 0000563aa69f4f28 CR3: 0000000105a16000 CR4: 00000000001006f0
[  668.813518] Call Trace:
[  668.813518]  ? unregister_netdevice_many+0xe0/0xe0
[  668.813518]  ? xt_rateest_net_init+0x2c0/0x2c0 [xt_RATEEST]
[  668.813518]  ? default_device_exit+0x1ca/0x270
[  668.813518]  ? remove_proc_entry+0x1cd/0x390
[  668.813518]  ? dev_change_net_namespace+0xd00/0xd00
[  668.813518]  ? __init_waitqueue_head+0x130/0x130
[  668.813518]  ops_exit_list.isra.10+0x94/0x140
[  668.813518]  cleanup_net+0x45b/0x900
[  668.813518]  ? net_drop_ns+0x110/0x110
[  668.813518]  ? swapgs_restore_regs_and_return_to_usermode+0x3c/0x80
[  668.813518]  ? save_trace+0x300/0x300
[  668.813518]  ? lock_acquire+0x196/0x470
[  668.813518]  ? lock_acquire+0x196/0x470
[  668.813518]  ? process_one_work+0xb60/0x1de0
[  668.813518]  ? _raw_spin_unlock_irq+0x29/0x40
[  668.813518]  ? _raw_spin_unlock_irq+0x29/0x40
[  668.813518]  ? __lock_acquire+0x4500/0x4500
[  668.813518]  ? __lock_is_held+0xb4/0x140
[  668.813518]  process_one_work+0xc13/0x1de0
[  668.813518]  ? pwq_dec_nr_in_flight+0x3c0/0x3c0
[  668.813518]  ? set_load_weight+0x270/0x270
[ ... ]

Fixes: 3427b2ab63fa ("netfilter: make xt_rateest hash table per net")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_RATEEST.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index dec843cadf46..9e05c86ba5c4 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -201,18 +201,8 @@ static __net_init int xt_rateest_net_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit xt_rateest_net_exit(struct net *net)
-{
-	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
-		WARN_ON_ONCE(!hlist_empty(&xn->hash[i]));
-}
-
 static struct pernet_operations xt_rateest_net_ops = {
 	.init = xt_rateest_net_init,
-	.exit = xt_rateest_net_exit,
 	.id   = &xt_rateest_id,
 	.size = sizeof(struct xt_rateest_net),
 };

From 29e3880109e357fdc607b4393f8308cef6af9413 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 12 Nov 2018 22:43:45 +0100
Subject: [PATCH 15/53] netfilter: nf_tables: fix use-after-free when deleting
 compat expressions

nft_compat ops do not have static storage duration, unlike all other
expressions.

When nf_tables_expr_destroy() returns, expr->ops might have been
free'd already, so we need to store next address before calling
expression destructor.

For same reason, we can't deref match pointer after nft_xt_put().

This can be easily reproduced by adding msleep() before
nft_match_destroy() returns.

Fixes: 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
Reported-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 5 +++--
 net/netfilter/nft_compat.c    | 3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e496030fdc3b..ddeaa1990e1e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2457,7 +2457,7 @@ err:
 static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 				   struct nft_rule *rule)
 {
-	struct nft_expr *expr;
+	struct nft_expr *expr, *next;
 
 	/*
 	 * Careful: some expressions might not be initialized in case this
@@ -2465,8 +2465,9 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 */
 	expr = nft_expr_first(rule);
 	while (expr != nft_expr_last(rule) && expr->ops) {
+		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
-		expr = nft_expr_next(expr);
+		expr = next;
 	}
 	kfree(rule);
 }
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 9d0ede474224..7334e0b80a5e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -520,6 +520,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		    void *info)
 {
 	struct xt_match *match = expr->ops->data;
+	struct module *me = match->me;
 	struct xt_mtdtor_param par;
 
 	par.net = ctx->net;
@@ -530,7 +531,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		par.match->destroy(&par);
 
 	if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
-		module_put(match->me);
+		module_put(me);
 }
 
 static void

From afd594240806acc138cf696c09f2f4829d55d02f Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 16 Nov 2018 12:00:07 +0000
Subject: [PATCH 16/53] bpf: fix off-by-one error in adjust_subprog_starts

When patching in a new sequence for the first insn of a subprog, the start
 of that subprog does not change (it's the first insn of the sequence), so
 adjust_subprog_starts should check start <= off (rather than < off).
Also added a test to test_verifier.c (it's essentially the syz reproducer).

Fixes: cc8b0b92a169 ("bpf: introduce function calls (function boundaries)")
Reported-by: syzbot+4fc427c7af994b0948be@syzkaller.appspotmail.com
Signed-off-by: Edward Cree <ecree@solarflare.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                       |  2 +-
 tools/testing/selftests/bpf/test_verifier.c | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1971ca325fb4..6dd419550aba 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 		return;
 	/* NOTE: fake 'exit' subprog should be updated as well. */
 	for (i = 0; i <= env->subprog_cnt; i++) {
-		if (env->subprog_info[i].start < off)
+		if (env->subprog_info[i].start <= off)
 			continue;
 		env->subprog_info[i].start += len - 1;
 	}
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 6f61df62f690..550b7e46bf4a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -13896,6 +13896,25 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"calls: ctx read at start of subprog",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+			BPF_JMP_REG(BPF_JSGT, BPF_REG_0, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)

From 569a933b03f3c48b392fe67c0086b3a6b9306b5a Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guroan@gmail.com>
Date: Wed, 14 Nov 2018 10:00:34 -0800
Subject: [PATCH 17/53] bpf: allocate local storage buffers using GFP_ATOMIC

Naresh reported an issue with the non-atomic memory allocation of
cgroup local storage buffers:

[   73.047526] BUG: sleeping function called from invalid context at
/srv/oe/build/tmp-rpb-glibc/work-shared/intel-corei7-64/kernel-source/mm/slab.h:421
[   73.060915] in_atomic(): 1, irqs_disabled(): 0, pid: 3157, name: test_cgroup_sto
[   73.068342] INFO: lockdep is turned off.
[   73.072293] CPU: 2 PID: 3157 Comm: test_cgroup_sto Not tainted
4.20.0-rc2-next-20181113 #1
[   73.080548] Hardware name: Supermicro SYS-5019S-ML/X11SSH-F, BIOS
2.0b 07/27/2017
[   73.088018] Call Trace:
[   73.090463]  dump_stack+0x70/0xa5
[   73.093783]  ___might_sleep+0x152/0x240
[   73.097619]  __might_sleep+0x4a/0x80
[   73.101191]  __kmalloc_node+0x1cf/0x2f0
[   73.105031]  ? cgroup_storage_update_elem+0x46/0x90
[   73.109909]  cgroup_storage_update_elem+0x46/0x90

cgroup_storage_update_elem() (as well as other update map update
callbacks) is called with disabled preemption, so GFP_ATOMIC
allocation should be used: e.g. alloc_htab_elem() in hashtab.c.

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/local_storage.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..bed9d48a7ae9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
 		return -ENOENT;
 
 	new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
-			   map->value_size, __GFP_ZERO | GFP_USER,
+			   map->value_size,
+			   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
 			   map->numa_node);
 	if (!new)
 		return -ENOMEM;

From b4e955e9f372035361fbc6f07b21fe2cc6a5be4a Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Fri, 16 Nov 2018 21:32:35 +0900
Subject: [PATCH 18/53] netfilter: xt_hashlimit: fix a possible memory leak in
 htable_create()

In the htable_create(), hinfo is allocated by vmalloc()
So that if error occurred, hinfo should be freed.

Fixes: 11d5f15723c9 ("netfilter: xt_hashlimit: Create revision 2 to support higher pps rates")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_hashlimit.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 3e7d259e5d8d..1ad4017f9b73 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -295,9 +295,10 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 
 	/* copy match config into hashtable config */
 	ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3);
-
-	if (ret)
+	if (ret) {
+		vfree(hinfo);
 		return ret;
+	}
 
 	hinfo->cfg.size = size;
 	if (hinfo->cfg.max == 0)
@@ -814,7 +815,6 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -830,7 +830,6 @@ hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 
@@ -921,7 +920,6 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -940,7 +938,6 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 

From dde7011a824cfa815b03f853ec985ff46b740939 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 21 Nov 2018 13:53:17 -0800
Subject: [PATCH 19/53] tools: bpftool: fix potential NULL pointer dereference
 in do_load

This patch fixes a possible null pointer dereference in
do_load, detected by the semantic patch deref_null.cocci,
with the following warning:

./tools/bpf/bpftool/prog.c:1021:23-25: ERROR: map_replace is NULL but dereferenced.

The following code has potential null pointer references:
881             map_replace = reallocarray(map_replace, old_map_fds + 1,
882                                        sizeof(*map_replace));
883             if (!map_replace) {
884                     p_err("mem alloc failed");
885                     goto err_free_reuse_maps;
886             }

...
1019 err_free_reuse_maps:
1020         for (i = 0; i < old_map_fds; i++)
1021                 close(map_replace[i].fd);
1022         free(map_replace);

Fixes: 3ff5a4dc5d89 ("tools: bpftool: allow reuse of maps with bpftool prog load")
Co-developed-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/prog.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9785244acc7b..ccee180dfb76 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -844,6 +844,7 @@ static int do_load(int argc, char **argv)
 			}
 			NEXT_ARG();
 		} else if (is_prefix(*argv, "map")) {
+			void *new_map_replace;
 			char *endptr, *name;
 			int fd;
 
@@ -877,12 +878,15 @@ static int do_load(int argc, char **argv)
 			if (fd < 0)
 				goto err_free_reuse_maps;
 
-			map_replace = reallocarray(map_replace, old_map_fds + 1,
-						   sizeof(*map_replace));
-			if (!map_replace) {
+			new_map_replace = reallocarray(map_replace,
+						       old_map_fds + 1,
+						       sizeof(*map_replace));
+			if (!new_map_replace) {
 				p_err("mem alloc failed");
 				goto err_free_reuse_maps;
 			}
+			map_replace = new_map_replace;
+
 			map_replace[old_map_fds].idx = idx;
 			map_replace[old_map_fds].name = name;
 			map_replace[old_map_fds].fd = fd;

From 813961de3ee6474dd5703e883471fd941d6c8f69 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 22 Nov 2018 10:49:56 -0800
Subject: [PATCH 20/53] bpf: fix integer overflow in queue_stack_map

Fix the following issues:

- allow queue_stack_map for root only
- fix u32 max_entries overflow
- disallow value_size == 0

Fixes: f1a2e44a3aec ("bpf: add queue and stack maps")
Reported-by: Wei Wu <ww9210@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/queue_stack_maps.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8bbd72d3a121..b384ea9f3254 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -7,6 +7,7 @@
 #include <linux/bpf.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/capability.h>
 #include "percpu_freelist.h"
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
 /* Called from syscall */
 static int queue_stack_map_alloc_check(union bpf_attr *attr)
 {
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 0 ||
+	    attr->value_size == 0 ||
 	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
 		return -EINVAL;
 
@@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
 {
 	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	struct bpf_queue_stack *qs;
-	u32 size, value_size;
-	u64 queue_size, cost;
+	u64 size, queue_size, cost;
 
-	size = attr->max_entries + 1;
-	value_size = attr->value_size;
-
-	queue_size = sizeof(*qs) + (u64) value_size * size;
-
-	cost = queue_size;
+	size = (u64) attr->max_entries + 1;
+	cost = queue_size = sizeof(*qs) + size * attr->value_size;
 	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 

From 1efb6ee3edea57f57f9fb05dba8dcb3f7333f61f Mon Sep 17 00:00:00 2001
From: Martynas Pumputis <m@lambda.lt>
Date: Fri, 23 Nov 2018 17:43:26 +0100
Subject: [PATCH 21/53] bpf: fix check of allowed specifiers in
 bpf_trace_printk

A format string consisting of "%p" or "%s" followed by an invalid
specifier (e.g. "%p%\n" or "%s%") could pass the check which
would make format_decode (lib/vsprintf.c) to warn.

Fixes: 9c959c863f82 ("tracing: Allow BPF programs to call bpf_trace_printk()")
Reported-by: syzbot+1ec5c5ec949c4adaa0c4@syzkaller.appspotmail.com
Signed-off-by: Martynas Pumputis <m@lambda.lt>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/trace/bpf_trace.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 08fcfe440c63..9864a35c8bb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 			i++;
 		} else if (fmt[i] == 'p' || fmt[i] == 's') {
 			mod[fmt_cnt]++;
-			i++;
-			if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+			/* disallow any further format extensions */
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1]))
 				return -EINVAL;
 			fmt_cnt++;
-			if (fmt[i - 1] == 's') {
+			if (fmt[i] == 's') {
 				if (str_seen)
 					/* allow only one '%s' per fmt string */
 					return -EINVAL;

From 9efdda4e3abed13f0903b7b6e4d4c2102019440a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 24 Nov 2018 09:12:24 -0800
Subject: [PATCH 22/53] tcp: address problems caused by EDT misshaps

When a qdisc setup including pacing FQ is dismantled and recreated,
some TCP packets are sent earlier than instructed by TCP stack.

TCP can be fooled when ACK comes back, because the following
operation can return a negative value.

    tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;

Some paths in TCP stack were not dealing properly with this,
this patch addresses four of them.

Fixes: ab408b6dc744 ("tcp: switch tcp and sch_fq to new earliest departure time model")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 16 ++++++++++------
 net/ipv4/tcp_timer.c | 10 ++++++----
 2 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1e37c1388189..a9d9555a973f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 		u32 delta_us;
 
-		if (!delta)
-			delta = 1;
-		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
-		tcp_rcv_rtt_update(tp, delta_us, 0);
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
+			delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			tcp_rcv_rtt_update(tp, delta_us, 0);
+		}
 	}
 }
 
@@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 	    flag & FLAG_ACKED) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-		u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 
-		seq_rtt_us = ca_rtt_us = delta_us;
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			ca_rtt_us = seq_rtt_us;
+		}
 	}
 	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
 	if (seq_rtt_us < 0)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5f8b6d3cd855..091c53925e4d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 elapsed, start_ts;
+	s32 remaining;
 
 	start_ts = tcp_retransmit_stamp(sk);
 	if (!icsk->icsk_user_timeout || !start_ts)
 		return icsk->icsk_rto;
 	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
-	if (elapsed >= icsk->icsk_user_timeout)
+	remaining = icsk->icsk_user_timeout - elapsed;
+	if (remaining <= 0)
 		return 1; /* user timeout has passed; fire ASAP */
-	else
-		return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
+
+	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
 /**
@@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk,
 				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 		timeout = jiffies_to_msecs(timeout);
 	}
-	return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
+	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
 
 /* A write timeout has occurred. Process the after effects. */

From aba36930a35e7f1fe1319b203f25c05d6c119936 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 24 Nov 2018 14:21:16 -0500
Subject: [PATCH 23/53] net: always initialize pagedlen

In ip packet generation, pagedlen is initialized for each skb at the
start of the loop in __ip(6)_append_data, before label alloc_new_skb.

Depending on compiler options, code can be generated that jumps to
this label, triggering use of an an uninitialized variable.

In practice, at -O2, the generated code moves the initialization below
the label. But the code should not rely on that for correctness.

Fixes: 15e36f5b8e98 ("udp: paged allocation with gso")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 3 ++-
 net/ipv6/ip6_output.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c09219e7f230..5dbec21856f4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 			struct sk_buff *skb_prev;
 alloc_new_skb:
 			skb_prev = skb;
@@ -956,6 +956,7 @@ alloc_new_skb:
 			if (datalen > mtu - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89e0d5118afe..827a3f5ff3bb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1354,7 +1354,7 @@ emsgsize:
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 alloc_new_skb:
 			/* There's no room in the current skb */
 			if (skb)
@@ -1378,6 +1378,7 @@ alloc_new_skb:
 			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))

From 2a31e4bd9ad255ee40809b5c798c4b1c2b09703b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 15 Nov 2018 15:14:30 +0800
Subject: [PATCH 24/53] ipvs: call ip_vs_dst_notifier earlier than
 ipv6_dev_notf

ip_vs_dst_event is supposed to clean up all dst used in ipvs'
destinations when a net dev is going down. But it works only
when the dst's dev is the same as the dev from the event.

Now with the same priority but late registration,
ip_vs_dst_notifier is always called later than ipv6_dev_notf
where the dst's dev is set to lo for NETDEV_DOWN event.

As the dst's dev lo is not the same as the dev from the event
in ip_vs_dst_event, ip_vs_dst_notifier doesn't actually work.
Also as these dst have to wait for dest_trash_timer to clean
them up. It would cause some non-permanent kernel warnings:

  unregister_netdevice: waiting for br0 to become free. Usage count = 3

To fix it, call ip_vs_dst_notifier earlier than ipv6_dev_notf
by increasing its priority to ADDRCONF_NOTIFY_PRIORITY + 5.

Note that for ipv4 route fib_netdev_notifier doesn't set dst's
dev to lo in NETDEV_DOWN event, so this fix is only needed when
IP_VS_IPV6 is defined.

Fixes: 7a4f0761fce3 ("IPVS: init and cleanup restructuring")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 83395bf6dc35..432141f04af3 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3980,6 +3980,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
 
 static struct notifier_block ip_vs_dst_notifier = {
 	.notifier_call = ip_vs_dst_event,
+#ifdef CONFIG_IP_VS_IPV6
+	.priority = ADDRCONF_NOTIFY_PRIORITY + 5,
+#endif
 };
 
 int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)

From 89259088c1b7fecb43e8e245dc931909132a4e03 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 17 Nov 2018 11:32:29 +0100
Subject: [PATCH 25/53] netfilter: nfnetlink_cttimeout: fetch timeouts for
 udplite and gre, too

syzbot was able to trigger the WARN in cttimeout_default_get() by
passing UDPLITE as l4protocol.  Alias UDPLITE to UDP, both use
same timeout values.

Furthermore, also fetch GRE timeouts.  GRE is a bit more complicated,
as it still can be a module and its netns_proto_gre struct layout isn't
visible outside of the gre module. Can't move timeouts around, it
appears conntrack sysctl unregister assumes net_generic() returns
nf_proto_net, so we get crash. Expose layout of netns_proto_gre instead.

A followup nf-next patch could make gre tracker be built-in as well
if needed, its not that large.

Last, make the WARN() mention the missing protocol value in case
anything else is missing.

Reported-by: syzbot+2fae8fa157dd92618cae@syzkaller.appspotmail.com
Fixes: 8866df9264a3 ("netfilter: nfnetlink_cttimeout: pass default timeout policy to obj_to_nlattr")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_proto_gre.h | 13 +++++++++++++
 net/netfilter/nf_conntrack_proto_gre.c           | 14 ++------------
 net/netfilter/nfnetlink_cttimeout.c              | 15 +++++++++++++--
 3 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index b8d95564bd53..14edb795ab43 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -21,6 +21,19 @@ struct nf_ct_gre_keymap {
 	struct nf_conntrack_tuple tuple;
 };
 
+enum grep_conntrack {
+	GRE_CT_UNREPLIED,
+	GRE_CT_REPLIED,
+	GRE_CT_MAX
+};
+
+struct netns_proto_gre {
+	struct nf_proto_net	nf;
+	rwlock_t		keymap_lock;
+	struct list_head	keymap_list;
+	unsigned int		gre_timeouts[GRE_CT_MAX];
+};
+
 /* add new tuple->key_reply pair to keymap */
 int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 			 struct nf_conntrack_tuple *t);
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9b48dc8b4b88..2a5e56c6d8d9 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -43,24 +43,12 @@
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 
-enum grep_conntrack {
-	GRE_CT_UNREPLIED,
-	GRE_CT_REPLIED,
-	GRE_CT_MAX
-};
-
 static const unsigned int gre_timeouts[GRE_CT_MAX] = {
 	[GRE_CT_UNREPLIED]	= 30*HZ,
 	[GRE_CT_REPLIED]	= 180*HZ,
 };
 
 static unsigned int proto_gre_net_id __read_mostly;
-struct netns_proto_gre {
-	struct nf_proto_net	nf;
-	rwlock_t		keymap_lock;
-	struct list_head	keymap_list;
-	unsigned int		gre_timeouts[GRE_CT_MAX];
-};
 
 static inline struct netns_proto_gre *gre_pernet(struct net *net)
 {
@@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0);
+
 	ret = register_pernet_subsys(&proto_gre_net_ops);
 	if (ret < 0)
 		goto out_pernet;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index a518eb162344..109b0d27345a 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -455,7 +455,8 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 	case IPPROTO_TCP:
 		timeouts = nf_tcp_pernet(net)->timeouts;
 		break;
-	case IPPROTO_UDP:
+	case IPPROTO_UDP: /* fallthrough */
+	case IPPROTO_UDPLITE:
 		timeouts = nf_udp_pernet(net)->timeouts;
 		break;
 	case IPPROTO_DCCP:
@@ -469,13 +470,23 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 	case IPPROTO_SCTP:
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 		timeouts = nf_sctp_pernet(net)->timeouts;
+#endif
+		break;
+	case IPPROTO_GRE:
+#ifdef CONFIG_NF_CT_PROTO_GRE
+		if (l4proto->net_id) {
+			struct netns_proto_gre *net_gre;
+
+			net_gre = net_generic(net, *l4proto->net_id);
+			timeouts = net_gre->gre_timeouts;
+		}
 #endif
 		break;
 	case 255:
 		timeouts = &nf_generic_pernet(net)->timeout;
 		break;
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto);
 		break;
 	}
 

From 508b09046c0f21678652fb66fd1e9959d55591d2 Mon Sep 17 00:00:00 2001
From: Alin Nastac <alin.nastac@gmail.com>
Date: Wed, 21 Nov 2018 14:00:30 +0100
Subject: [PATCH 26/53] netfilter: ipv6: Preserve link scope traffic original
 oif

When ip6_route_me_harder is invoked, it resets outgoing interface of:
  - link-local scoped packets sent by neighbor discovery
  - multicast packets sent by MLD host
  - multicast packets send by MLD proxy daemon that sets outgoing
    interface through IPV6_PKTINFO ipi6_ifindex

Link-local and multicast packets must keep their original oif after
ip6_route_me_harder is called.

Signed-off-by: Alin Nastac <alin.nastac@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv6/netfilter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 5ae8e1c51079..8b075f0bc351 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
-		.flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
+		.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
+			rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
 		.flowi6_mark = skb->mark,
 		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,

From 584eab291c67894cb17cc87544b9d086228ea70f Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 22 Nov 2018 19:59:46 +0900
Subject: [PATCH 27/53] netfilter: add missing error handling code for register
 functions

register_{netdevice/inetaddr/inet6addr}_notifier may return an error
value, this patch adds the code to handle these error paths.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 .../net/netfilter/ipv4/nf_nat_masquerade.h    |  2 +-
 .../net/netfilter/ipv6/nf_nat_masquerade.h    |  2 +-
 net/ipv4/netfilter/ipt_MASQUERADE.c           |  7 ++--
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c   | 21 +++++++++---
 net/ipv4/netfilter/nft_masq_ipv4.c            |  4 ++-
 net/ipv6/netfilter/ip6t_MASQUERADE.c          |  8 +++--
 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c   | 32 +++++++++++++------
 net/ipv6/netfilter/nft_masq_ipv6.c            |  4 ++-
 net/netfilter/nft_flow_offload.c              |  5 ++-
 9 files changed, 63 insertions(+), 22 deletions(-)

diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
index cd24be4c4a99..13d55206bb9f 100644
--- a/include/net/netfilter/ipv4/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h
@@ -9,7 +9,7 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 		       const struct nf_nat_range2 *range,
 		       const struct net_device *out);
 
-void nf_nat_masquerade_ipv4_register_notifier(void);
+int nf_nat_masquerade_ipv4_register_notifier(void);
 void nf_nat_masquerade_ipv4_unregister_notifier(void);
 
 #endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
index 0c3b5ebf0bb8..2917bf95c437 100644
--- a/include/net/netfilter/ipv6/nf_nat_masquerade.h
+++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h
@@ -5,7 +5,7 @@
 unsigned int
 nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		       const struct net_device *out);
-void nf_nat_masquerade_ipv6_register_notifier(void);
+int nf_nat_masquerade_ipv6_register_notifier(void);
 void nf_nat_masquerade_ipv6_unregister_notifier(void);
 
 #endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index ce1512b02cb2..fd3f9e8a74da 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void)
 	int ret;
 
 	ret = xt_register_target(&masquerade_tg_reg);
+	if (ret)
+		return ret;
 
-	if (ret == 0)
-		nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		xt_unregister_target(&masquerade_tg_reg);
 
 	return ret;
 }
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index a9d5e013e555..c7d7fa4fc369 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -149,16 +149,29 @@ static struct notifier_block masq_inet_notifier = {
 
 static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
 
-void nf_nat_masquerade_ipv4_register_notifier(void)
+int nf_nat_masquerade_ipv4_register_notifier(void)
 {
+	int ret;
+
 	/* check if the notifier was already set */
 	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+		return 0;
 
 	/* Register for device down reports */
-	register_netdevice_notifier(&masq_dev_notifier);
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
 	/* Register IP address change reports */
-	register_inetaddr_notifier(&masq_inet_notifier);
+	ret = register_inetaddr_notifier(&masq_inet_notifier);
+	if (ret)
+		goto err_unregister;
+
+	return ret;
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	atomic_dec(&masquerade_notifier_refcount);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
 
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index f1193e1e928a..6847de1d1db8 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv4_type);
 
 	return ret;
 }
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 491f808e356a..29c7f1915a96 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0)
-		nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		return err;
+
+	err = nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		xt_unregister_target(&masquerade_tg6_reg);
 
 	return err;
 }
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 3e4bf2286abe..7afd1e63d2db 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work)
  * of ipv6 addresses being deleted), we also need to add an upper
  * limit to the number of queued work items.
  */
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
+static int masq_inet6_event(struct notifier_block *this,
+			    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = ptr;
 	const struct net_device *dev;
@@ -171,20 +171,34 @@ static int masq_inet_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
+static struct notifier_block masq_inet6_notifier = {
+	.notifier_call	= masq_inet6_event,
 };
 
 static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
 
-void nf_nat_masquerade_ipv6_register_notifier(void)
+int nf_nat_masquerade_ipv6_register_notifier(void)
 {
+	int ret;
+
 	/* check if the notifier is already set */
 	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+		return 0;
 
-	register_netdevice_notifier(&masq_dev_notifier);
-	register_inet6addr_notifier(&masq_inet_notifier);
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
+
+	ret = register_inet6addr_notifier(&masq_inet6_notifier);
+	if (ret)
+		goto err_unregister;
+
+	return ret;
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	atomic_dec(&masquerade_notifier_refcount);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
 
@@ -194,7 +208,7 @@ void nf_nat_masquerade_ipv6_unregister_notifier(void)
 	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
 		return;
 
-	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_inet6addr_notifier(&masq_inet6_notifier);
 	unregister_netdevice_notifier(&masq_dev_notifier);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index dd0122f3cffe..e06c82e9dfcd 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv6_register_notifier();
+	ret = nf_nat_masquerade_ipv6_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv6_type);
 
 	return ret;
 }
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index e82d9a966c45..974525eb92df 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -214,7 +214,9 @@ static int __init nft_flow_offload_module_init(void)
 {
 	int err;
 
-	register_netdevice_notifier(&flow_offload_netdev_notifier);
+	err = register_netdevice_notifier(&flow_offload_netdev_notifier);
+	if (err)
+		goto err;
 
 	err = nft_register_expr(&nft_flow_offload_type);
 	if (err < 0)
@@ -224,6 +226,7 @@ static int __init nft_flow_offload_module_init(void)
 
 register_expr:
 	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+err:
 	return err;
 }
 

From 095faf45e64be00bff4da2d6182dface3d69c9b7 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 22 Nov 2018 19:59:57 +0900
Subject: [PATCH 28/53] netfilter: nat: fix double register in masquerade
 modules

There is a reference counter to ensure that masquerade modules register
notifiers only once. However, the existing reference counter approach is
not safe, test commands are:

   while :
   do
   	   modprobe ip6t_MASQUERADE &
	   modprobe nft_masq_ipv6 &
	   modprobe -rv ip6t_MASQUERADE &
	   modprobe -rv nft_masq_ipv6 &
   done

numbers below represent the reference counter.
--------------------------------------------------------
CPU0        CPU1        CPU2        CPU3        CPU4
[insmod]    [insmod]    [rmmod]     [rmmod]     [insmod]
--------------------------------------------------------
0->1
register    1->2
            returns     2->1
			returns     1->0
                                                0->1
                                                register <--
                                    unregister
--------------------------------------------------------

The unregistation of CPU3 should be processed before the
registration of CPU4.

In order to fix this, use a mutex instead of reference counter.

splat looks like:
[  323.869557] watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [modprobe:1381]
[  323.869574] Modules linked in: nf_tables(+) nf_nat_ipv6(-) nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 n]
[  323.869574] irq event stamp: 194074
[  323.898930] hardirqs last  enabled at (194073): [<ffffffff90004a0d>] trace_hardirqs_on_thunk+0x1a/0x1c
[  323.898930] hardirqs last disabled at (194074): [<ffffffff90004a29>] trace_hardirqs_off_thunk+0x1a/0x1c
[  323.898930] softirqs last  enabled at (182132): [<ffffffff922006ec>] __do_softirq+0x6ec/0xa3b
[  323.898930] softirqs last disabled at (182109): [<ffffffff90193426>] irq_exit+0x1a6/0x1e0
[  323.898930] CPU: 0 PID: 1381 Comm: modprobe Not tainted 4.20.0-rc2+ #27
[  323.898930] RIP: 0010:raw_notifier_chain_register+0xea/0x240
[  323.898930] Code: 3c 03 0f 8e f2 00 00 00 44 3b 6b 10 7f 4d 49 bc 00 00 00 00 00 fc ff df eb 22 48 8d 7b 10 488
[  323.898930] RSP: 0018:ffff888101597218 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13
[  323.898930] RAX: 0000000000000000 RBX: ffffffffc04361c0 RCX: 0000000000000000
[  323.898930] RDX: 1ffffffff26132ae RSI: ffffffffc04aa3c0 RDI: ffffffffc04361d0
[  323.898930] RBP: ffffffffc04361c8 R08: 0000000000000000 R09: 0000000000000001
[  323.898930] R10: ffff8881015972b0 R11: fffffbfff26132c4 R12: dffffc0000000000
[  323.898930] R13: 0000000000000000 R14: 1ffff110202b2e44 R15: ffffffffc04aa3c0
[  323.898930] FS:  00007f813ed41540(0000) GS:ffff88811ae00000(0000) knlGS:0000000000000000
[  323.898930] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  323.898930] CR2: 0000559bf2c9f120 CR3: 000000010bc80000 CR4: 00000000001006f0
[  323.898930] Call Trace:
[  323.898930]  ? atomic_notifier_chain_register+0x2d0/0x2d0
[  323.898930]  ? down_read+0x150/0x150
[  323.898930]  ? sched_clock_cpu+0x126/0x170
[  323.898930]  ? nf_tables_core_module_init+0xe4/0xe4 [nf_tables]
[  323.898930]  ? nf_tables_core_module_init+0xe4/0xe4 [nf_tables]
[  323.898930]  register_netdevice_notifier+0xbb/0x790
[  323.898930]  ? __dev_close_many+0x2d0/0x2d0
[  323.898930]  ? __mutex_unlock_slowpath+0x17f/0x740
[  323.898930]  ? wait_for_completion+0x710/0x710
[  323.898930]  ? nf_tables_core_module_init+0xe4/0xe4 [nf_tables]
[  323.898930]  ? up_write+0x6c/0x210
[  323.898930]  ? nf_tables_core_module_init+0xe4/0xe4 [nf_tables]
[  324.127073]  ? nf_tables_core_module_init+0xe4/0xe4 [nf_tables]
[  324.127073]  nft_chain_filter_init+0x1e/0xe8a [nf_tables]
[  324.127073]  nf_tables_module_init+0x37/0x92 [nf_tables]
[ ... ]

Fixes: 8dd33cc93ec9 ("netfilter: nf_nat: generalize IPv4 masquerading support for nf_tables")
Fixes: be6b635cd674 ("netfilter: nf_nat: generalize IPv6 masquerading support for nf_tables")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 23 ++++++++++++++-------
 net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 23 ++++++++++++++-------
 2 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c7d7fa4fc369..41327bb99093 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -147,15 +147,17 @@ static struct notifier_block masq_inet_notifier = {
 	.notifier_call	= masq_inet_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
 int nf_nat_masquerade_ipv4_register_notifier(void)
 {
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&masq_mutex);
 	/* check if the notifier was already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return 0;
+	if (++masq_refcnt > 1)
+		goto out_unlock;
 
 	/* Register for device down reports */
 	ret = register_netdevice_notifier(&masq_dev_notifier);
@@ -166,22 +168,29 @@ int nf_nat_masquerade_ipv4_register_notifier(void)
 	if (ret)
 		goto err_unregister;
 
+	mutex_unlock(&masq_mutex);
 	return ret;
+
 err_unregister:
 	unregister_netdevice_notifier(&masq_dev_notifier);
 err_dec:
-	atomic_dec(&masquerade_notifier_refcount);
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
 
 void nf_nat_masquerade_ipv4_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
 	unregister_netdevice_notifier(&masq_dev_notifier);
 	unregister_inetaddr_notifier(&masq_inet_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 7afd1e63d2db..0ad0da5a2600 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -175,15 +175,17 @@ static struct notifier_block masq_inet6_notifier = {
 	.notifier_call	= masq_inet6_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
 int nf_nat_masquerade_ipv6_register_notifier(void)
 {
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&masq_mutex);
 	/* check if the notifier is already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return 0;
+	if (++masq_refcnt > 1)
+		goto out_unlock;
 
 	ret = register_netdevice_notifier(&masq_dev_notifier);
 	if (ret)
@@ -193,22 +195,29 @@ int nf_nat_masquerade_ipv6_register_notifier(void)
 	if (ret)
 		goto err_unregister;
 
+	mutex_unlock(&masq_mutex);
 	return ret;
+
 err_unregister:
 	unregister_netdevice_notifier(&masq_dev_notifier);
 err_dec:
-	atomic_dec(&masquerade_notifier_refcount);
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
 
 void nf_nat_masquerade_ipv6_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
 	unregister_inet6addr_notifier(&masq_inet6_notifier);
 	unregister_netdevice_notifier(&masq_dev_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);

From 53ca0f2fec39c80ccd19e6e3f30cc8daef174b70 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 25 Nov 2018 18:47:13 +0900
Subject: [PATCH 29/53] netfilter: nf_conncount: remove wrong condition check
 routine

All lists that reach the tree_nodes_free() function have both zero
counter and true dead flag. The reason for this is that lists to be
release are selected by nf_conncount_gc_list() which already decrements
the list counter and sets on the dead flag. Therefore, this if statement
in tree_nodes_free() is unnecessary and wrong.

Fixes: 31568ec09ea0 ("netfilter: nf_conncount: fix list_del corruption in conn_free")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 8acae4a3e4c0..b6d0f6deea86 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -323,11 +323,8 @@ static void tree_nodes_free(struct rb_root *root,
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
 		spin_lock(&rbconn->list.list_lock);
-		if (rbconn->list.count == 0 && rbconn->list.dead == false) {
-			rbconn->list.dead = true;
-			rb_erase(&rbconn->node, root);
-			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
-		}
+		rb_erase(&rbconn->node, root);
+		call_rcu(&rbconn->rcu_head, __tree_nodes_free);
 		spin_unlock(&rbconn->list.list_lock);
 	}
 }

From e2c95a61656d29ceaac97b6a975c8a1f26e26f15 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 26 Nov 2018 14:05:38 +0100
Subject: [PATCH 30/53] bpf, ppc64: generalize fetching subprog into
 bpf_jit_get_func_addr

Make fetching of the BPF call address from ppc64 JIT generic. ppc64
was using a slightly different variant rather than through the insns'
imm field encoding as the target address would not fit into that space.
Therefore, the target subprog number was encoded into the insns' offset
and fetched through fp->aux->func[off]->bpf_func instead. Given there
are other JITs with this issue and the mechanism of fetching the address
is JIT-generic, move it into the core as a helper instead. On the JIT
side, we get information on whether the retrieved address is a fixed
one, that is, not changing through JIT passes, or a dynamic one. For
the former, JITs can optimize their imm emission because this doesn't
change jump offsets throughout JIT process.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
Tested-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/powerpc/net/bpf_jit_comp64.c | 57 ++++++++++++++++++++-----------
 include/linux/filter.h            |  4 +++
 kernel/bpf/core.c                 | 34 ++++++++++++++++++
 3 files changed, 76 insertions(+), 19 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 50b129785aee..17482f5de3e2 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	PPC_BLR();
 }
 
-static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
+static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx,
+				       u64 func)
+{
+#ifdef PPC64_ELF_ABI_v1
+	/* func points to the function descriptor */
+	PPC_LI64(b2p[TMP_REG_2], func);
+	/* Load actual entry point from function descriptor */
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
+	/* ... and move it to LR */
+	PPC_MTLR(b2p[TMP_REG_1]);
+	/*
+	 * Load TOC from function descriptor at offset 8.
+	 * We can clobber r2 since we get called through a
+	 * function pointer (so caller will save/restore r2)
+	 * and since we don't use a TOC ourself.
+	 */
+	PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
+#else
+	/* We can clobber r12 */
+	PPC_FUNC_ADDR(12, func);
+	PPC_MTLR(12);
+#endif
+	PPC_BLRL();
+}
+
+static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx,
+				       u64 func)
 {
 	unsigned int i, ctx_idx = ctx->idx;
 
@@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
-	int i;
+	int i, ret;
 
 	/* Start of epilogue code - will only be valid 2nd pass onwards */
 	u32 exit_addr = addrs[flen];
@@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u32 src_reg = b2p[insn[i].src_reg];
 		s16 off = insn[i].off;
 		s32 imm = insn[i].imm;
+		bool func_addr_fixed;
+		u64 func_addr;
 		u64 imm64;
-		u8 *func;
 		u32 true_cond;
 		u32 tmp_idx;
 
@@ -711,23 +738,15 @@ emit_clear:
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
 
-			/* bpf function call */
-			if (insn[i].src_reg == BPF_PSEUDO_CALL)
-				if (!extra_pass)
-					func = NULL;
-				else if (fp->aux->func && off < fp->aux->func_cnt)
-					/* use the subprog id from the off
-					 * field to lookup the callee address
-					 */
-					func = (u8 *) fp->aux->func[off]->bpf_func;
-				else
-					return -EINVAL;
-			/* kernel helper call */
+			ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
+						    &func_addr, &func_addr_fixed);
+			if (ret < 0)
+				return ret;
+
+			if (func_addr_fixed)
+				bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
 			else
-				func = (u8 *) __bpf_call_base + imm;
-
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
+				bpf_jit_emit_func_call_rel(image, ctx, func_addr);
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
 			break;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index de629b706d1d..448dcc448f1f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr);
 
 void bpf_jit_free(struct bpf_prog *fp);
 
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+			  const struct bpf_insn *insn, bool extra_pass,
+			  u64 *func_addr, bool *func_addr_fixed);
+
 struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
 void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1a796e0799ec..b1a3545d0ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	bpf_prog_unlock_free(fp);
 }
 
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+			  const struct bpf_insn *insn, bool extra_pass,
+			  u64 *func_addr, bool *func_addr_fixed)
+{
+	s16 off = insn->off;
+	s32 imm = insn->imm;
+	u8 *addr;
+
+	*func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+	if (!*func_addr_fixed) {
+		/* Place-holder address till the last pass has collected
+		 * all addresses for JITed subprograms in which case we
+		 * can pick them up from prog->aux.
+		 */
+		if (!extra_pass)
+			addr = NULL;
+		else if (prog->aux->func &&
+			 off >= 0 && off < prog->aux->func_cnt)
+			addr = (u8 *)prog->aux->func[off]->bpf_func;
+		else
+			return -EINVAL;
+	} else {
+		/* Address of a BPF helper call. Since part of the core
+		 * kernel, it's always at a fixed location. __bpf_call_base
+		 * and the helper with imm relative to it are both in core
+		 * kernel.
+		 */
+		addr = (u8 *)__bpf_call_base + imm;
+	}
+
+	*func_addr = (unsigned long)addr;
+	return 0;
+}
+
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
 			      struct bpf_insn *to_buff)

From 8c11ea5ce13da0252fc92f91e90b0cb0c8fe5619 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 26 Nov 2018 14:05:39 +0100
Subject: [PATCH 31/53] bpf, arm64: fix getting subprog addr from aux for calls

The arm64 JIT has the same issue as ppc64 JIT in that the relative BPF
to BPF call offset can be too far away from core kernel in that relative
encoding into imm is not sufficient and could potentially be truncated,
see also fd045f6cd98e ("arm64: add support for module PLTs") which adds
spill-over space for module_alloc() and therefore bpf_jit_binary_alloc().
Therefore, use the recently added bpf_jit_get_func_addr() helper for
properly fetching the address through prog->aux->func[off]->bpf_func
instead. This also has the benefit to optimize normal helper calls since
their address can use the optimized emission. Tested on Cavium ThunderX
CN8890.

Fixes: db496944fdaa ("bpf: arm64: add JIT support for multi-function programs")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a6fdaea07c63..89198017e8e6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -351,7 +351,8 @@ static void build_epilogue(struct jit_ctx *ctx)
  * >0 - successfully JITed a 16-byte eBPF instruction.
  * <0 - failed to JIT.
  */
-static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
+static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
+		      bool extra_pass)
 {
 	const u8 code = insn->code;
 	const u8 dst = bpf2a64[insn->dst_reg];
@@ -625,12 +626,19 @@ emit_cond_jmp:
 	case BPF_JMP | BPF_CALL:
 	{
 		const u8 r0 = bpf2a64[BPF_REG_0];
-		const u64 func = (u64)__bpf_call_base + imm;
+		bool func_addr_fixed;
+		u64 func_addr;
+		int ret;
 
-		if (ctx->prog->is_func)
-			emit_addr_mov_i64(tmp, func, ctx);
+		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
+					    &func_addr, &func_addr_fixed);
+		if (ret < 0)
+			return ret;
+		if (func_addr_fixed)
+			/* We can use optimized emission here. */
+			emit_a64_mov_i64(tmp, func_addr, ctx);
 		else
-			emit_a64_mov_i64(tmp, func, ctx);
+			emit_addr_mov_i64(tmp, func_addr, ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
 		break;
@@ -753,7 +761,7 @@ emit_cond_jmp:
 	return 0;
 }
 
-static int build_body(struct jit_ctx *ctx)
+static int build_body(struct jit_ctx *ctx, bool extra_pass)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
@@ -762,7 +770,7 @@ static int build_body(struct jit_ctx *ctx)
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
-		ret = build_insn(insn, ctx);
+		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
 			if (ctx->image == NULL)
@@ -858,7 +866,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* 1. Initial fake pass to compute ctx->idx. */
 
 	/* Fake pass to fill in ctx->offset. */
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		prog = orig_prog;
 		goto out_off;
 	}
@@ -888,7 +896,7 @@ skip_init_ctx:
 
 	build_prologue(&ctx, was_classic);
 
-	if (build_body(&ctx)) {
+	if (build_body(&ctx, extra_pass)) {
 		bpf_jit_binary_free(header);
 		prog = orig_prog;
 		goto out_off;

From c44768a33da81b4a0986e79bbf0588f1a0651dec Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Mon, 26 Nov 2018 13:03:46 -0800
Subject: [PATCH 32/53] sparc: Fix JIT fused branch convergance.

On T4 and later sparc64 cpus we can use the fused compare and branch
instruction.

However, it can only be used if the branch destination is in the range
of a signed 10-bit immediate offset.  This amounts to 1024
instructions forwards or backwards.

After the commit referenced in the Fixes: tag, the largest possible
size program seen by the JIT explodes by a significant factor.

As a result of this convergance takes many more passes since the
expanded "BPF_LDX | BPF_MSH | BPF_B" code sequence, for example,
contains several embedded branch on condition instructions.

On each pass, as suddenly new fused compare and branch instances
become valid, this makes thousands more in range for the next pass.
And so on and so forth.

This is most greatly exemplified by "BPF_MAXINSNS: exec all MSH" which
takes 35 passes to converge, and shrinks the image by about 64K.

To decrease the cost of this number of convergance passes, do the
convergance pass before we have the program image allocated, just like
other JITs (such as x86) do.

Fixes: e0cea7ce988c ("bpf: implement ld_abs/ld_ind in native bpf")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/sparc/net/bpf_jit_comp_64.c | 77 ++++++++++++++++++++------------
 1 file changed, 49 insertions(+), 28 deletions(-)

diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 222785af550b..7217d6359643 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1425,12 +1425,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct sparc64_jit_data *jit_data;
 	struct bpf_binary_header *header;
+	u32 prev_image_size, image_size;
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
-	u32 image_size;
 	u8 *image_ptr;
-	int pass;
+	int pass, i;
 
 	if (!prog->jit_requested)
 		return orig_prog;
@@ -1461,27 +1461,52 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		header = jit_data->header;
 		extra_pass = true;
 		image_size = sizeof(u32) * ctx.idx;
+		prev_image_size = image_size;
+		pass = 1;
 		goto skip_init_ctx;
 	}
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL);
+	ctx.offset = kmalloc_array(prog->len, sizeof(unsigned int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
 	}
 
-	/* Fake pass to detect features used, and get an accurate assessment
-	 * of what the final image size will be.
+	/* Longest sequence emitted is for bswap32, 12 instructions.  Pre-cook
+	 * the offset array so that we converge faster.
 	 */
-	if (build_body(&ctx)) {
-		prog = orig_prog;
-		goto out_off;
+	for (i = 0; i < prog->len; i++)
+		ctx.offset[i] = i * (12 * 4);
+
+	prev_image_size = ~0U;
+	for (pass = 1; pass < 40; pass++) {
+		ctx.idx = 0;
+
+		build_prologue(&ctx);
+		if (build_body(&ctx)) {
+			prog = orig_prog;
+			goto out_off;
+		}
+		build_epilogue(&ctx);
+
+		if (bpf_jit_enable > 1)
+			pr_info("Pass %d: size = %u, seen = [%c%c%c%c%c%c]\n", pass,
+				ctx.idx * 4,
+				ctx.tmp_1_used ? '1' : ' ',
+				ctx.tmp_2_used ? '2' : ' ',
+				ctx.tmp_3_used ? '3' : ' ',
+				ctx.saw_frame_pointer ? 'F' : ' ',
+				ctx.saw_call ? 'C' : ' ',
+				ctx.saw_tail_call ? 'T' : ' ');
+
+		if (ctx.idx * 4 == prev_image_size)
+			break;
+		prev_image_size = ctx.idx * 4;
+		cond_resched();
 	}
-	build_prologue(&ctx);
-	build_epilogue(&ctx);
 
 	/* Now we know the actual image size. */
 	image_size = sizeof(u32) * ctx.idx;
@@ -1494,28 +1519,24 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	ctx.image = (u32 *)image_ptr;
 skip_init_ctx:
-	for (pass = 1; pass < 3; pass++) {
-		ctx.idx = 0;
+	ctx.idx = 0;
 
-		build_prologue(&ctx);
+	build_prologue(&ctx);
 
-		if (build_body(&ctx)) {
-			bpf_jit_binary_free(header);
-			prog = orig_prog;
-			goto out_off;
-		}
+	if (build_body(&ctx)) {
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_off;
+	}
 
-		build_epilogue(&ctx);
+	build_epilogue(&ctx);
 
-		if (bpf_jit_enable > 1)
-			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
-				image_size - (ctx.idx * 4),
-				ctx.tmp_1_used ? '1' : ' ',
-				ctx.tmp_2_used ? '2' : ' ',
-				ctx.tmp_3_used ? '3' : ' ',
-				ctx.saw_frame_pointer ? 'F' : ' ',
-				ctx.saw_call ? 'C' : ' ',
-				ctx.saw_tail_call ? 'T' : ' ');
+	if (ctx.idx * 4 != prev_image_size) {
+		pr_err("bpf_jit: Failed to converge, prev_size=%u size=%d\n",
+		       prev_image_size, ctx.idx * 4);
+		bpf_jit_binary_free(header);
+		prog = orig_prog;
+		goto out_off;
 	}
 
 	if (bpf_jit_enable > 1)

From e2ac579a7a18bcd9e8cf14cf42eac0b8a2ba6c4b Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Mon, 26 Nov 2018 14:52:18 -0800
Subject: [PATCH 33/53] sparc: Correct ctx->saw_frame_pointer logic.

We need to initialize the frame pointer register not just if it is
seen as a source operand, but also if it is seen as the destination
operand of a store or an atomic instruction (which effectively is a
source operand).

This is exercised by test_verifier's "non-invalid fp arithmetic"

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/sparc/net/bpf_jit_comp_64.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 7217d6359643..ec4da4dc98f1 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1270,6 +1270,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		u32 opcode = 0, rs2;
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_2_used = true;
 		emit_loadimm(imm, tmp2, ctx);
 
@@ -1308,6 +1311,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		u32 opcode = 0, rs2;
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		switch (BPF_SIZE(code)) {
 		case BPF_W:
 			opcode = ST32;
@@ -1340,6 +1346,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_1_used = true;
 		ctx->tmp_2_used = true;
 		ctx->tmp_3_used = true;
@@ -1360,6 +1369,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->dst_reg == BPF_REG_FP)
+			ctx->saw_frame_pointer = true;
+
 		ctx->tmp_1_used = true;
 		ctx->tmp_2_used = true;
 		ctx->tmp_3_used = true;

From fa1e0c9690bfa19eadd2adbaf511fb4fef9270e6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 27 Nov 2018 01:21:00 +0100
Subject: [PATCH 34/53] bpf, doc: add entries of who looks over which jits

Make the high-level BPF JIT entry a general 'catch-all' and add
architecture specific entries to make it more clear who actively
maintains which BPF JIT compiler. The list (L) address implies
that this eventually lands in the bpf patchwork bucket. Goal is
that this set of responsible developers listed here is always up
to date and a point of contact for helping out in e.g. feature
development, fixes, review or testing patches in order to help
long-term in ensuring quality of the BPF JITs and therefore BPF
core under a given architecture. Every new JIT in future /must/
have an entry here as well.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Zi Shen Lim <zlim.lnx@gmail.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 62 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 03c46f483143..bfaa41119902 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2801,7 +2801,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
 Q:	https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
 S:	Supported
-F:	arch/x86/net/bpf_jit*
+F:	arch/*/net/*
 F:	Documentation/networking/filter.txt
 F:	Documentation/bpf/
 F:	include/linux/bpf*
@@ -2821,6 +2821,67 @@ F:	tools/bpf/
 F:	tools/lib/bpf/
 F:	tools/testing/selftests/bpf/
 
+BPF JIT for ARM
+M:	Shubham Bansal <illusionist.neo@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/arm/net/
+
+BPF JIT for ARM64
+M:	Daniel Borkmann <daniel@iogearbox.net>
+M:	Alexei Starovoitov <ast@kernel.org>
+M:	Zi Shen Lim <zlim.lnx@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	arch/arm64/net/
+
+BPF JIT for MIPS (32-BIT AND 64-BIT)
+M:	Paul Burton <paul.burton@mips.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/mips/net/
+
+BPF JIT for NFP NICs
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/netronome/nfp/bpf/
+
+BPF JIT for POWERPC (32-BIT AND 64-BIT)
+M:	Naveen N. Rao <naveen.n.rao@linux.ibm.com>
+M:	Sandipan Das <sandipan@linux.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/powerpc/net/
+
+BPF JIT for S390
+M:	Martin Schwidefsky <schwidefsky@de.ibm.com>
+M:	Heiko Carstens <heiko.carstens@de.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/s390/net/
+X:	arch/s390/net/pnet.c
+
+BPF JIT for SPARC (32-BIT AND 64-BIT)
+M:	David S. Miller <davem@davemloft.net>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/sparc/net/
+
+BPF JIT for X86 32-BIT
+M:	Wang YanQing <udknight@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	arch/x86/net/bpf_jit_comp32.c
+
+BPF JIT for X86 64-BIT
+M:	Alexei Starovoitov <ast@kernel.org>
+M:	Daniel Borkmann <daniel@iogearbox.net>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	arch/x86/net/
+X:	arch/x86/net/bpf_jit_comp32.c
+
 BROADCOM B44 10/100 ETHERNET DRIVER
 M:	Michael Chan <michael.chan@broadcom.com>
 L:	netdev@vger.kernel.org

From 2b9034b5eaddc09c0e9529b93446eb975f97f814 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Mon, 26 Nov 2018 21:55:09 -0800
Subject: [PATCH 35/53] sparc: Adjust bpf JIT prologue for PSEUDO calls.

Move all arguments into output registers from input registers.

This path is exercised by test_verifier.c's "calls: two calls with
args" test.  Adjust BPF_TAILCALL_PROLOGUE_SKIP as needed.

Let's also make the prologue length a constant size regardless of
the combination of ->saw_frame_pointer and ->saw_tail_call
settings.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/sparc/net/bpf_jit_comp_64.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index ec4da4dc98f1..5fda4f7bf15d 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -791,7 +791,7 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
 }
 
 /* Just skip the save instruction and the ctx register move.  */
-#define BPF_TAILCALL_PROLOGUE_SKIP	16
+#define BPF_TAILCALL_PROLOGUE_SKIP	32
 #define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
 
 static void build_prologue(struct jit_ctx *ctx)
@@ -824,9 +824,15 @@ static void build_prologue(struct jit_ctx *ctx)
 		const u8 vfp = bpf2sparc[BPF_REG_FP];
 
 		emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx);
+	} else {
+		emit_nop(ctx);
 	}
 
 	emit_reg_move(I0, O0, ctx);
+	emit_reg_move(I1, O1, ctx);
+	emit_reg_move(I2, O2, ctx);
+	emit_reg_move(I3, O3, ctx);
+	emit_reg_move(I4, O4, ctx);
 	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
 }
 

From 45611c61dd503454b2edae00aabe1e429ec49ebe Mon Sep 17 00:00:00 2001
From: Bernd Eckstein <3erndeckstein@gmail.com>
Date: Fri, 23 Nov 2018 13:51:26 +0100
Subject: [PATCH 36/53] usbnet: ipheth: fix potential recvmsg bug and recvmsg
 bug 2

The bug is not easily reproducable, as it may occur very infrequently
(we had machines with 20minutes heavy downloading before it occurred)
However, on a virual machine (VMWare on Windows 10 host) it occurred
pretty frequently (1-2 seconds after a speedtest was started)

dev->tx_skb mab be freed via dev_kfree_skb_irq on a callback
before it is set.

This causes the following problems:
- double free of the skb or potential memory leak
- in dmesg: 'recvmsg bug' and 'recvmsg bug 2' and eventually
  general protection fault

Example dmesg output:
[  134.841986] ------------[ cut here ]------------
[  134.841987] recvmsg bug: copied 9C24A555 seq 9C24B557 rcvnxt 9C25A6B3 fl 0
[  134.841993] WARNING: CPU: 7 PID: 2629 at /build/linux-hwe-On9fm7/linux-hwe-4.15.0/net/ipv4/tcp.c:1865 tcp_recvmsg+0x44d/0xab0
[  134.841994] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842046] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842046] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842048] RIP: 0010:tcp_recvmsg+0x44d/0xab0
[  134.842048] RSP: 0018:ffffa6630422bcc8 EFLAGS: 00010286
[  134.842049] RAX: 0000000000000000 RBX: ffff997616f4f200 RCX: 0000000000000006
[  134.842049] RDX: 0000000000000007 RSI: 0000000000000082 RDI: ffff9976257d6490
[  134.842050] RBP: ffffa6630422bd98 R08: 0000000000000001 R09: 000000000004bba4
[  134.842050] R10: 0000000001e00c6f R11: 000000000004bba4 R12: ffff99760dee3000
[  134.842051] R13: 0000000000000000 R14: ffff99760dee3514 R15: 0000000000000000
[  134.842051] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842052] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842053] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842055] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842055] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842057] Call Trace:
[  134.842060]  ? aa_sk_perm+0x53/0x1a0
[  134.842064]  inet_recvmsg+0x51/0xc0
[  134.842066]  sock_recvmsg+0x43/0x50
[  134.842070]  SYSC_recvfrom+0xe4/0x160
[  134.842072]  ? __schedule+0x3de/0x8b0
[  134.842075]  ? ktime_get_ts64+0x4c/0xf0
[  134.842079]  SyS_recvfrom+0xe/0x10
[  134.842082]  do_syscall_64+0x73/0x130
[  134.842086]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842086] RIP: 0033:0x7fe331f5a81d
[  134.842088] RSP: 002b:00007ffe8da98398 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
[  134.842090] RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 00007fe331f5a81d
[  134.842094] RDX: 00000000000003fb RSI: 0000000001e00874 RDI: 0000000000000003
[  134.842095] RBP: 00007fe32f642c70 R08: 0000000000000000 R09: 0000000000000000
[  134.842097] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe332347698
[  134.842099] R13: 0000000001b7e0a0 R14: 0000000001e00874 R15: 0000000000000000
[  134.842103] Code: 24 fd ff ff e9 cc fe ff ff 48 89 d8 41 8b 8c 24 10 05 00 00 44 8b 45 80 48 c7 c7 08 bd 59 8b 48 89 85 68 ff ff ff e8 b3 c4 7d ff <0f> 0b 48 8b 85 68 ff ff ff e9 e9 fe ff ff 41 8b 8c 24 10 05 00
[  134.842126] ---[ end trace b7138fc08c83147f ]---
[  134.842144] general protection fault: 0000 [#1] SMP PTI
[  134.842145] Modules linked in: ipheth(OE) kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd glue_helper cryptd vmw_balloon intel_rapl_perf joydev input_leds serio_raw vmw_vsock_vmci_transport vsock shpchp i2c_piix4 mac_hid binfmt_misc vmw_vmci parport_pc ppdev lp parport autofs4 vmw_pvscsi vmxnet3 hid_generic usbhid hid vmwgfx ttm drm_kms_helper syscopyarea sysfillrect mptspi mptscsih sysimgblt ahci psmouse fb_sys_fops pata_acpi mptbase libahci e1000 drm scsi_transport_spi
[  134.842161] CPU: 7 PID: 2629 Comm: python Tainted: G        W  OE    4.15.0-34-generic #37~16.04.1-Ubuntu
[  134.842162] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
[  134.842164] RIP: 0010:tcp_close+0x2c6/0x440
[  134.842165] RSP: 0018:ffffa6630422bde8 EFLAGS: 00010202
[  134.842167] RAX: 0000000000000000 RBX: ffff99760dee3000 RCX: 0000000180400034
[  134.842168] RDX: 5c4afd407207a6c4 RSI: ffffe868495bd300 RDI: ffff997616f4f200
[  134.842169] RBP: ffffa6630422be08 R08: 0000000016f4d401 R09: 0000000180400034
[  134.842169] R10: ffffa6630422bd98 R11: 0000000000000000 R12: 000000000000600c
[  134.842170] R13: 0000000000000000 R14: ffff99760dee30c8 R15: ffff9975bd44fe00
[  134.842171] FS:  00007fe332347700(0000) GS:ffff9976257c0000(0000) knlGS:0000000000000000
[  134.842173] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  134.842174] CR2: 0000000001e41000 CR3: 000000020e9b4006 CR4: 00000000003606e0
[  134.842177] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  134.842178] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  134.842179] Call Trace:
[  134.842181]  inet_release+0x42/0x70
[  134.842183]  __sock_release+0x42/0xb0
[  134.842184]  sock_close+0x15/0x20
[  134.842187]  __fput+0xea/0x220
[  134.842189]  ____fput+0xe/0x10
[  134.842191]  task_work_run+0x8a/0xb0
[  134.842193]  exit_to_usermode_loop+0xc4/0xd0
[  134.842195]  do_syscall_64+0xf4/0x130
[  134.842197]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[  134.842197] RIP: 0033:0x7fe331f5a560
[  134.842198] RSP: 002b:00007ffe8da982e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[  134.842200] RAX: 0000000000000000 RBX: 00007fe32f642c70 RCX: 00007fe331f5a560
[  134.842201] RDX: 00000000008f5320 RSI: 0000000001cd4b50 RDI: 0000000000000003
[  134.842202] RBP: 00007fe32f6500f8 R08: 000000000000003c R09: 00000000009343c0
[  134.842203] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe32f6500d0
[  134.842204] R13: 00000000008f5320 R14: 00000000008f5320 R15: 0000000001cd4770
[  134.842205] Code: c8 00 00 00 45 31 e4 49 39 fe 75 4d eb 50 83 ab d8 00 00 00 01 48 8b 17 48 8b 47 08 48 c7 07 00 00 00 00 48 c7 47 08 00 00 00 00 <48> 89 42 08 48 89 10 0f b6 57 34 8b 47 2c 2b 47 28 83 e2 01 80
[  134.842226] RIP: tcp_close+0x2c6/0x440 RSP: ffffa6630422bde8
[  134.842227] ---[ end trace b7138fc08c831480 ]---

The proposed patch eliminates a potential racing condition.
Before, usb_submit_urb was called and _after_ that, the skb was attached
(dev->tx_skb). So, on a callback it was possible, however unlikely that the
skb was freed before it was set. That way (because dev->tx_skb was not set
to NULL after it was freed), it could happen that a skb from a earlier
transmission was freed a second time (and the skb we should have freed did
not get freed at all)

Now we free the skb directly in ipheth_tx(). It is not passed to the
callback anymore, eliminating the posibility of a double free of the same
skb. Depending on the retval of usb_submit_urb() we use dev_kfree_skb_any()
respectively dev_consume_skb_any() to free the skb.

Signed-off-by: Oliver Zweigle <Oliver.Zweigle@faro.com>
Signed-off-by: Bernd Eckstein <3ernd.Eckstein@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/ipheth.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 7275761a1177..3d8a70d3ea9b 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -140,7 +140,6 @@ struct ipheth_device {
 	struct usb_device *udev;
 	struct usb_interface *intf;
 	struct net_device *net;
-	struct sk_buff *tx_skb;
 	struct urb *tx_urb;
 	struct urb *rx_urb;
 	unsigned char *tx_buf;
@@ -230,6 +229,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
 	case -ENOENT:
 	case -ECONNRESET:
 	case -ESHUTDOWN:
+	case -EPROTO:
 		return;
 	case 0:
 		break;
@@ -281,7 +281,6 @@ static void ipheth_sndbulk_callback(struct urb *urb)
 		dev_err(&dev->intf->dev, "%s: urb status: %d\n",
 		__func__, status);
 
-	dev_kfree_skb_irq(dev->tx_skb);
 	if (status == 0)
 		netif_wake_queue(dev->net);
 	else
@@ -423,7 +422,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 	if (skb->len > IPHETH_BUF_SIZE) {
 		WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len);
 		dev->net->stats.tx_dropped++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -443,12 +442,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net)
 		dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n",
 			__func__, retval);
 		dev->net->stats.tx_errors++;
-		dev_kfree_skb_irq(skb);
+		dev_kfree_skb_any(skb);
 	} else {
-		dev->tx_skb = skb;
-
 		dev->net->stats.tx_packets++;
 		dev->net->stats.tx_bytes += skb->len;
+		dev_consume_skb_any(skb);
 		netif_stop_queue(net);
 	}
 

From c85ddecae6e5e82ca3ae6f20c63f1d865e2ff5ea Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 23 Nov 2018 19:41:29 +0100
Subject: [PATCH 37/53] net: phy: add workaround for issue where PHY driver
 doesn't bind to the device

After switching the r8169 driver to use phylib some user reported that
their network is broken. This was caused by the genphy PHY driver being
used instead of the dedicated PHY driver for the RTL8211B. Users
reported that loading the Realtek PHY driver module upfront fixes the
issue. See also this mail thread:
https://marc.info/?t=154279781800003&r=1&w=2
The issue is quite weird and the root cause seems to be somewhere in
the base driver core. The patch works around the issue and may be
removed once the actual issue is fixed.

The Fixes tag refers to the first reported occurrence of the issue.
The issue itself may have been existing much longer and it may affect
users of other network chips as well. Users typically will recognize
this issue only if their PHY stops working when being used with the
genphy driver.

Fixes: f1e911d5d0df ("r8169: add basic phylib support")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ab33d1777132..23ee3967c166 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2197,6 +2197,14 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner)
 	new_driver->mdiodrv.driver.remove = phy_remove;
 	new_driver->mdiodrv.driver.owner = owner;
 
+	/* The following works around an issue where the PHY driver doesn't bind
+	 * to the device, resulting in the genphy driver being used instead of
+	 * the dedicated driver. The root cause of the issue isn't known yet
+	 * and seems to be in the base driver core. Once this is fixed we may
+	 * remove this workaround.
+	 */
+	new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS;
+
 	retval = driver_register(&new_driver->mdiodrv.driver);
 	if (retval) {
 		pr_err("%s: Error %d in registering driver\n",

From a8842e975503191e4982efb886299fc19972c97f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 25 Nov 2018 23:21:08 +0000
Subject: [PATCH 38/53] firestream: fix spelling mistake: "Inititing" ->
 "Initializing"

There are spelling mistakes in debug messages, fix them.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/firestream.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 4e46dc9e41ad..11e1663bdc4d 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1410,7 +1410,7 @@ static int init_q(struct fs_dev *dev, struct queue *txq, int queue,
 
 	func_enter ();
 
-	fs_dprintk (FS_DEBUG_INIT, "Inititing queue at %x: %d entries:\n", 
+	fs_dprintk (FS_DEBUG_INIT, "Initializing queue at %x: %d entries:\n",
 		    queue, nentries);
 
 	p = aligned_kmalloc (sz, GFP_KERNEL, 0x10);
@@ -1443,7 +1443,7 @@ static int init_fp(struct fs_dev *dev, struct freepool *fp, int queue,
 {
 	func_enter ();
 
-	fs_dprintk (FS_DEBUG_INIT, "Inititing free pool at %x:\n", queue);
+	fs_dprintk (FS_DEBUG_INIT, "Initializing free pool at %x:\n", queue);
 
 	write_fs (dev, FP_CNF(queue), (bufsize * RBFP_RBS) | RBFP_RBSVAL | RBFP_CME);
 	write_fs (dev, FP_SA(queue),  0);

From 0d32f17717e65e76cbdb248374dd162acdfe2fff Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 26 Nov 2018 14:52:44 +0800
Subject: [PATCH 39/53] sctp: increase sk_wmem_alloc when head->truesize is
 increased

I changed to count sk_wmem_alloc by skb truesize instead of 1 to
fix the sk_wmem_alloc leak caused by later truesize's change in
xfrm in Commit 02968ccf0125 ("sctp: count sk_wmem_alloc by skb
truesize in sctp_packet_transmit").

But I should have also increased sk_wmem_alloc when head->truesize
is increased in sctp_packet_gso_append() as xfrm does. Otherwise,
sctp gso packet will cause sk_wmem_alloc underflow.

Fixes: 02968ccf0125 ("sctp: count sk_wmem_alloc by skb truesize in sctp_packet_transmit")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sctp/output.c b/net/sctp/output.c
index b0e74a3e77ec..025f48e14a91 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -410,6 +410,7 @@ static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
 	head->truesize += skb->truesize;
 	head->data_len += skb->len;
 	head->len += skb->len;
+	refcount_add(skb->truesize, &head->sk->sk_wmem_alloc);
 
 	__skb_header_release(skb);
 }

From 24a6d2dd263bc910de018c78d1148b3e33b94512 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 26 Nov 2018 15:07:16 +0100
Subject: [PATCH 40/53] net: thunderx: fix NULL pointer dereference in
 nic_remove

Fix a possible NULL pointer dereference in nic_remove routine
removing the nicpf module if nic_probe fails.
The issue can be triggered with the following reproducer:

$rmmod nicvf
$rmmod nicpf

[  521.412008] Unable to handle kernel access to user memory outside uaccess routines at virtual address 0000000000000014
[  521.422777] Mem abort info:
[  521.425561]   ESR = 0x96000004
[  521.428624]   Exception class = DABT (current EL), IL = 32 bits
[  521.434535]   SET = 0, FnV = 0
[  521.437579]   EA = 0, S1PTW = 0
[  521.440730] Data abort info:
[  521.443603]   ISV = 0, ISS = 0x00000004
[  521.447431]   CM = 0, WnR = 0
[  521.450417] user pgtable: 4k pages, 48-bit VAs, pgdp = 0000000072a3da42
[  521.457022] [0000000000000014] pgd=0000000000000000
[  521.461916] Internal error: Oops: 96000004 [#1] SMP
[  521.511801] Hardware name: GIGABYTE H270-T70/MT70-HD0, BIOS T49 02/02/2018
[  521.518664] pstate: 80400005 (Nzcv daif +PAN -UAO)
[  521.523451] pc : nic_remove+0x24/0x88 [nicpf]
[  521.527808] lr : pci_device_remove+0x48/0xd8
[  521.532066] sp : ffff000013433cc0
[  521.535370] x29: ffff000013433cc0 x28: ffff810f6ac50000
[  521.540672] x27: 0000000000000000 x26: 0000000000000000
[  521.545974] x25: 0000000056000000 x24: 0000000000000015
[  521.551274] x23: ffff8007ff89a110 x22: ffff000001667070
[  521.556576] x21: ffff8007ffb170b0 x20: ffff8007ffb17000
[  521.561877] x19: 0000000000000000 x18: 0000000000000025
[  521.567178] x17: 0000000000000000 x16: 000000000000010ffc33ff98 x8 : 0000000000000000
[  521.593683] x7 : 0000000000000000 x6 : 0000000000000001
[  521.598983] x5 : 0000000000000002 x4 : 0000000000000003
[  521.604284] x3 : ffff8007ffb17184 x2 : ffff8007ffb17184
[  521.609585] x1 : ffff000001662118 x0 : ffff000008557be0
[  521.614887] Process rmmod (pid: 1897, stack limit = 0x00000000859535c3)
[  521.621490] Call trace:
[  521.623928]  nic_remove+0x24/0x88 [nicpf]
[  521.627927]  pci_device_remove+0x48/0xd8
[  521.631847]  device_release_driver_internal+0x1b0/0x248
[  521.637062]  driver_detach+0x50/0xc0
[  521.640628]  bus_remove_driver+0x60/0x100
[  521.644627]  driver_unregister+0x34/0x60
[  521.648538]  pci_unregister_driver+0x24/0xd8
[  521.652798]  nic_cleanup_module+0x14/0x111c [nicpf]
[  521.657672]  __arm64_sys_delete_module+0x150/0x218
[  521.662460]  el0_svc_handler+0x94/0x110
[  521.666287]  el0_svc+0x8/0xc
[  521.669160] Code: aa1e03e0 9102c295 d503201f f9404eb3 (b9401660)

Fixes: 4863dea3fab0 ("net: Adding support for Cavium ThunderX network controller")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nic_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 55af04fa03a7..6c8dcb65ff03 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1441,6 +1441,9 @@ static void nic_remove(struct pci_dev *pdev)
 {
 	struct nicpf *nic = pci_get_drvdata(pdev);
 
+	if (!nic)
+		return;
+
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 

From 1d510657ac7e486dd443cabbbd0677253aeb705f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 26 Nov 2018 15:53:54 +0000
Subject: [PATCH 41/53] qed: fix spelling mistake "attnetion" -> "attention"

The text in array s_igu_fifo_error_strs contains a spelling mistake,
fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 78a638ec7c0a..979f1e4bc18b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -6071,7 +6071,7 @@ static const char * const s_igu_fifo_error_strs[] = {
 	"no error",
 	"length error",
 	"function disabled",
-	"VF sent command to attnetion address",
+	"VF sent command to attention address",
 	"host sent prod update command",
 	"read of during interrupt register while in MIMD mode",
 	"access to PXP BAR reserved address",

From 4b5adba07c945e191ac2ecd83627dd520dca152f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 26 Nov 2018 15:34:01 +0000
Subject: [PATCH 42/53] net: via: via-velocity: fix spelling mistake
 "alignement" -> "alignment"

The text in array velocity_gstrings contains a spelling mistake,
rename rx_frame_alignement_errors to rx_frame_alignment_errors.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/via/via-velocity.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index ef9538ee53d0..82412691ee66 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -3605,7 +3605,7 @@ static const char velocity_gstrings[][ETH_GSTRING_LEN] = {
 	"tx_jumbo",
 	"rx_mac_control_frames",
 	"tx_mac_control_frames",
-	"rx_frame_alignement_errors",
+	"rx_frame_alignment_errors",
 	"rx_long_ok",
 	"rx_long_err",
 	"tx_sqe_errors",

From cc5922054131f9abefdc0622ae64fc55e6b2671d Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 26 Nov 2018 12:04:57 -0500
Subject: [PATCH 43/53] lan743x: fix return value for lan743x_tx_napi_poll

The lan743x driver, when under heavy traffic load, has been noticed
to sometimes hang, or cause a kernel panic.

Debugging reveals that the TX napi poll routine was returning
the wrong value, 'weight'. Most other drivers return 0.
And call napi_complete, instead of napi_complete_done.

Additionally when creating the tx napi poll routine.
Changed netif_napi_add, to netif_tx_napi_add.

Updates for v3:
    changed 'fixes' tag to match defined format

Updates for v2:
use napi_complete, instead of napi_complete_done in
    lan743x_tx_napi_poll
use netif_tx_napi_add, instead of netif_napi_add for
    registration of tx napi poll routine

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 867cddba840f..d627129c0adc 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1672,7 +1672,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 		netif_wake_queue(adapter->netdev);
 	}
 
-	if (!napi_complete_done(napi, weight))
+	if (!napi_complete(napi))
 		goto done;
 
 	/* enable isr */
@@ -1681,7 +1681,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight)
 	lan743x_csr_read(adapter, INT_STS);
 
 done:
-	return weight;
+	return 0;
 }
 
 static void lan743x_tx_ring_cleanup(struct lan743x_tx *tx)
@@ -1870,9 +1870,9 @@ static int lan743x_tx_open(struct lan743x_tx *tx)
 	tx->vector_flags = lan743x_intr_get_vector_flags(adapter,
 							 INT_BIT_DMA_TX_
 							 (tx->channel_number));
-	netif_napi_add(adapter->netdev,
-		       &tx->napi, lan743x_tx_napi_poll,
-		       tx->ring_size - 1);
+	netif_tx_napi_add(adapter->netdev,
+			  &tx->napi, lan743x_tx_napi_poll,
+			  tx->ring_size - 1);
 	napi_enable(&tx->napi);
 
 	data = 0;

From ec835f891232d7763dea9da0358f31e24ca6dfb7 Mon Sep 17 00:00:00 2001
From: Jon Maloy <donmalo99@gmail.com>
Date: Mon, 26 Nov 2018 12:26:14 -0500
Subject: [PATCH 44/53] tipc: fix lockdep warning during node delete

We see the following lockdep warning:

[ 2284.078521] ======================================================
[ 2284.078604] WARNING: possible circular locking dependency detected
[ 2284.078604] 4.19.0+ #42 Tainted: G            E
[ 2284.078604] ------------------------------------------------------
[ 2284.078604] rmmod/254 is trying to acquire lock:
[ 2284.078604] 00000000acd94e28 ((&n->timer)#2){+.-.}, at: del_timer_sync+0x5/0xa0
[ 2284.078604]
[ 2284.078604] but task is already holding lock:
[ 2284.078604] 00000000f997afc0 (&(&tn->node_list_lock)->rlock){+.-.}, at: tipc_node_stop+0xac/0x190 [tipc]
[ 2284.078604]
[ 2284.078604] which lock already depends on the new lock.
[ 2284.078604]
[ 2284.078604]
[ 2284.078604] the existing dependency chain (in reverse order) is:
[ 2284.078604]
[ 2284.078604] -> #1 (&(&tn->node_list_lock)->rlock){+.-.}:
[ 2284.078604]        tipc_node_timeout+0x20a/0x330 [tipc]
[ 2284.078604]        call_timer_fn+0xa1/0x280
[ 2284.078604]        run_timer_softirq+0x1f2/0x4d0
[ 2284.078604]        __do_softirq+0xfc/0x413
[ 2284.078604]        irq_exit+0xb5/0xc0
[ 2284.078604]        smp_apic_timer_interrupt+0xac/0x210
[ 2284.078604]        apic_timer_interrupt+0xf/0x20
[ 2284.078604]        default_idle+0x1c/0x140
[ 2284.078604]        do_idle+0x1bc/0x280
[ 2284.078604]        cpu_startup_entry+0x19/0x20
[ 2284.078604]        start_secondary+0x187/0x1c0
[ 2284.078604]        secondary_startup_64+0xa4/0xb0
[ 2284.078604]
[ 2284.078604] -> #0 ((&n->timer)#2){+.-.}:
[ 2284.078604]        del_timer_sync+0x34/0xa0
[ 2284.078604]        tipc_node_delete+0x1a/0x40 [tipc]
[ 2284.078604]        tipc_node_stop+0xcb/0x190 [tipc]
[ 2284.078604]        tipc_net_stop+0x154/0x170 [tipc]
[ 2284.078604]        tipc_exit_net+0x16/0x30 [tipc]
[ 2284.078604]        ops_exit_list.isra.8+0x36/0x70
[ 2284.078604]        unregister_pernet_operations+0x87/0xd0
[ 2284.078604]        unregister_pernet_subsys+0x1d/0x30
[ 2284.078604]        tipc_exit+0x11/0x6f2 [tipc]
[ 2284.078604]        __x64_sys_delete_module+0x1df/0x240
[ 2284.078604]        do_syscall_64+0x66/0x460
[ 2284.078604]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 2284.078604]
[ 2284.078604] other info that might help us debug this:
[ 2284.078604]
[ 2284.078604]  Possible unsafe locking scenario:
[ 2284.078604]
[ 2284.078604]        CPU0                    CPU1
[ 2284.078604]        ----                    ----
[ 2284.078604]   lock(&(&tn->node_list_lock)->rlock);
[ 2284.078604]                                lock((&n->timer)#2);
[ 2284.078604]                                lock(&(&tn->node_list_lock)->rlock);
[ 2284.078604]   lock((&n->timer)#2);
[ 2284.078604]
[ 2284.078604]  *** DEADLOCK ***
[ 2284.078604]
[ 2284.078604] 3 locks held by rmmod/254:
[ 2284.078604]  #0: 000000003368be9b (pernet_ops_rwsem){+.+.}, at: unregister_pernet_subsys+0x15/0x30
[ 2284.078604]  #1: 0000000046ed9c86 (rtnl_mutex){+.+.}, at: tipc_net_stop+0x144/0x170 [tipc]
[ 2284.078604]  #2: 00000000f997afc0 (&(&tn->node_list_lock)->rlock){+.-.}, at: tipc_node_stop+0xac/0x19
[...}

The reason is that the node timer handler sometimes needs to delete a
node which has been disconnected for too long. To do this, it grabs
the lock 'node_list_lock', which may at the same time be held by the
generic node cleanup function, tipc_node_stop(), during module removal.
Since the latter is calling del_timer_sync() inside the same lock, we
have a potential deadlock.

We fix this letting the timer cleanup function use spin_trylock()
instead of just spin_lock(), and when it fails to grab the lock it
just returns so that the timer handler can terminate its execution.
This is safe to do, since tipc_node_stop() anyway is about to
delete both the timer and the node instance.

Fixes: 6a939f365bdb ("tipc: Auto removal of peer down node instance")
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 2afc4f8c37a7..488019766433 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -584,12 +584,15 @@ static void  tipc_node_clear_links(struct tipc_node *node)
 /* tipc_node_cleanup - delete nodes that does not
  * have active links for NODE_CLEANUP_AFTER time
  */
-static int tipc_node_cleanup(struct tipc_node *peer)
+static bool tipc_node_cleanup(struct tipc_node *peer)
 {
 	struct tipc_net *tn = tipc_net(peer->net);
 	bool deleted = false;
 
-	spin_lock_bh(&tn->node_list_lock);
+	/* If lock held by tipc_node_stop() the node will be deleted anyway */
+	if (!spin_trylock_bh(&tn->node_list_lock))
+		return false;
+
 	tipc_node_write_lock(peer);
 
 	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {

From 4df5ce9bc03e47d05f400e64aa32a82ec4cef419 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 26 Nov 2018 12:27:10 -0500
Subject: [PATCH 45/53] lan743x: Enable driver to work with LAN7431

This driver was designed to work with both LAN7430 and LAN7431.
The only difference between the two is the LAN7431 has support
for external phy.

This change adds LAN7431 to the list of recognized devices
supported by this driver.

Updates for v2:
    changed 'fixes' tag to match defined format

fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 1 +
 drivers/net/ethernet/microchip/lan743x_main.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index d627129c0adc..e8ca98c070f6 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -3017,6 +3017,7 @@ static const struct dev_pm_ops lan743x_pm_ops = {
 
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) },
 	{ 0, }
 };
 
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 0e82b6368798..2d6eea18973e 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -548,6 +548,7 @@ struct lan743x_adapter;
 /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */
 #define PCI_VENDOR_ID_SMSC		PCI_VENDOR_ID_EFAR
 #define PCI_DEVICE_ID_SMSC_LAN7430	(0x7430)
+#define PCI_DEVICE_ID_SMSC_LAN7431	(0x7431)
 
 #define PCI_CONFIG_LENGTH		(0x1000)
 

From ca08987885a147643817d02bf260bc4756ce8cd4 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Wed, 28 Nov 2018 11:27:28 +0900
Subject: [PATCH 46/53] netfilter: nf_tables: deactivate expressions in rule
 replecement routine

There is no expression deactivation call from the rule replacement path,
hence, chain counter is not decremented. A few steps to reproduce the
problem:

   %nft add table ip filter
   %nft add chain ip filter c1
   %nft add chain ip filter c1
   %nft add rule ip filter c1 jump c2
   %nft replace rule ip filter c1 handle 3 accept
   %nft flush ruleset

<jump c2> expression means immediate NFT_JUMP to chain c2.
Reference count of chain c2 is increased when the rule is added.

When rule is deleted or replaced, the reference counter of c2 should be
decreased via nft_rule_expr_deactivate() which calls
nft_immediate_deactivate().

Splat looks like:
[  214.396453] WARNING: CPU: 1 PID: 21 at net/netfilter/nf_tables_api.c:1432 nf_tables_chain_destroy.isra.38+0x2f9/0x3a0 [nf_tables]
[  214.398983] Modules linked in: nf_tables nfnetlink
[  214.398983] CPU: 1 PID: 21 Comm: kworker/1:1 Not tainted 4.20.0-rc2+ #44
[  214.398983] Workqueue: events nf_tables_trans_destroy_work [nf_tables]
[  214.398983] RIP: 0010:nf_tables_chain_destroy.isra.38+0x2f9/0x3a0 [nf_tables]
[  214.398983] Code: 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 8e 00 00 00 48 8b 7b 58 e8 e1 2c 4e c6 48 89 df e8 d9 2c 4e c6 eb 9a <0f> 0b eb 96 0f 0b e9 7e fe ff ff e8 a7 7e 4e c6 e9 a4 fe ff ff e8
[  214.398983] RSP: 0018:ffff8881152874e8 EFLAGS: 00010202
[  214.398983] RAX: 0000000000000001 RBX: ffff88810ef9fc28 RCX: ffff8881152876f0
[  214.398983] RDX: dffffc0000000000 RSI: 1ffff11022a50ede RDI: ffff88810ef9fc78
[  214.398983] RBP: 1ffff11022a50e9d R08: 0000000080000000 R09: 0000000000000000
[  214.398983] R10: 0000000000000000 R11: 0000000000000000 R12: 1ffff11022a50eba
[  214.398983] R13: ffff888114446e08 R14: ffff8881152876f0 R15: ffffed1022a50ed6
[  214.398983] FS:  0000000000000000(0000) GS:ffff888116400000(0000) knlGS:0000000000000000
[  214.398983] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  214.398983] CR2: 00007fab9bb5f868 CR3: 000000012aa16000 CR4: 00000000001006e0
[  214.398983] Call Trace:
[  214.398983]  ? nf_tables_table_destroy.isra.37+0x100/0x100 [nf_tables]
[  214.398983]  ? __kasan_slab_free+0x145/0x180
[  214.398983]  ? nf_tables_trans_destroy_work+0x439/0x830 [nf_tables]
[  214.398983]  ? kfree+0xdb/0x280
[  214.398983]  nf_tables_trans_destroy_work+0x5f5/0x830 [nf_tables]
[ ... ]

Fixes: bb7b40aecbf7 ("netfilter: nf_tables: bogus EBUSY in chain deletions")
Reported by: Christoph Anton Mitterer <calestyo@scientia.net>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=914505
Link: https://bugzilla.kernel.org/show_bug.cgi?id=201791
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ddeaa1990e1e..2e61aab6ed73 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2667,21 +2667,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		if (!nft_is_active_next(net, old_rule)) {
-			err = -ENOENT;
-			goto err2;
-		}
-		trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
-					   old_rule);
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
 		if (trans == NULL) {
 			err = -ENOMEM;
 			goto err2;
 		}
-		nft_deactivate_next(net, old_rule);
-		chain->use--;
-
-		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
-			err = -ENOMEM;
+		err = nft_delrule(&ctx, old_rule);
+		if (err < 0) {
+			nft_trans_destroy(trans);
 			goto err2;
 		}
 

From e4c39f7926b4de355f7df75651d75003806aae09 Mon Sep 17 00:00:00 2001
From: Yunjian Wang <wangyunjian@huawei.com>
Date: Tue, 6 Nov 2018 16:27:12 +0800
Subject: [PATCH 47/53] igb: fix uninitialized variables

This patch fixes the variable 'phy_word' may be used uninitialized.

Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/e1000_i210.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index c54ebedca6da..c393cb2c0f16 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -842,6 +842,7 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw)
 		nvm_word = E1000_INVM_DEFAULT_AL;
 	tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL;
 	igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, E1000_PHY_PLL_FREQ_PAGE);
+	phy_word = E1000_PHY_PLL_UNCONF;
 	for (i = 0; i < E1000_MAX_PLL_TRIES; i++) {
 		/* check current state directly from internal PHY */
 		igb_read_phy_reg_82580(hw, E1000_PHY_PLL_FREQ_REG, &phy_word);

From eab077aa84331afbda071a213925d4cdbca58941 Mon Sep 17 00:00:00 2001
From: Lihong Yang <lihong.yang@intel.com>
Date: Wed, 21 Nov 2018 09:15:37 -0800
Subject: [PATCH 48/53] i40e: Fix deletion of MAC filters

In __i40e_del_filter function, the flag __I40E_MACVLAN_SYNC_PENDING for
the PF state is wrongly set for the VSI. Deleting any of the MAC filters
has caused the incorrect syncing for the PF. Fix it by setting this state
flag to the intended PF.

CC: stable <stable@vger.kernel.org>
Signed-off-by: Lihong Yang <lihong.yang@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 21c2688d6308..a3f45335437c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1413,7 +1413,7 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f)
 	}
 
 	vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
-	set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->state);
+	set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state);
 }
 
 /**

From a8bf879af7b1999eba36303ce9cc60e0e7dd816c Mon Sep 17 00:00:00 2001
From: Josh Elsasser <jelsasser@appneta.com>
Date: Sat, 24 Nov 2018 12:57:33 -0800
Subject: [PATCH 49/53] ixgbe: recognize 1000BaseLX SFP modules as 1Gbps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the two 1000BaseLX enum values to the X550's check for 1Gbps modules,
allowing the core driver code to establish a link over this SFP type.

This is done by the out-of-tree driver but the fix wasn't in mainline.

Fixes: e23f33367882 ("ixgbe: Fix 1G and 10G link stability for X550EM_x SFP+”)
Fixes: 6a14ee0cfb19 ("ixgbe: Add X550 support function pointers")
Signed-off-by: Josh Elsasser <jelsasser@appneta.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 10dbaf4f6e80..9c42f741ed5e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -2262,7 +2262,9 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 		*autoneg = false;
 
 		if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
-		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) {
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 ||
+		    hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) {
 			*speed = IXGBE_LINK_SPEED_1GB_FULL;
 			return 0;
 		}

From 529eb362a3477189224e7b7d24983d49448a85db Mon Sep 17 00:00:00 2001
From: Jan Sokolowski <jan.sokolowski@intel.com>
Date: Tue, 27 Nov 2018 09:35:35 -0800
Subject: [PATCH 50/53] i40e: fix kerneldoc for xsk methods

One method, xsk_umem_setup, had an incorrect kernel doc
description, which has been corrected.

Also fixes small typos found in the comments.

Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index add1e457886d..433c8e688c78 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -33,7 +33,7 @@ static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi)
 }
 
 /**
- * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid
+ * i40e_add_xsk_umem - Store a UMEM for a certain ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to store
  * @qid: Ring/qid to associate with the UMEM
@@ -56,7 +56,7 @@ static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid
+ * i40e_remove_xsk_umem - Remove a UMEM for a certain ring/qid
  * @vsi: Current VSI
  * @qid: Ring/qid associated with the UMEM
  **/
@@ -130,7 +130,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
 }
 
 /**
- * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid
+ * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid
  * @vsi: Current VSI
  * @umem: UMEM
  * @qid: Rx ring to associate UMEM to
@@ -189,7 +189,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 }
 
 /**
- * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid
+ * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid
  * @vsi: Current VSI
  * @qid: Rx ring to associate UMEM to
  *
@@ -255,12 +255,12 @@ int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
 }
 
 /**
- * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
+ * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to enable/associate to a ring, or NULL to disable
  * @qid: Rx ring to (dis)associate UMEM (from)to
  *
- * This function enables or disables an UMEM to a certain ring.
+ * This function enables or disables a UMEM to a certain ring.
  *
  * Returns 0 on success, <0 on failure
  **/
@@ -276,7 +276,7 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
  * @rx_ring: Rx ring
  * @xdp: xdp_buff used as input to the XDP program
  *
- * This function enables or disables an UMEM to a certain ring.
+ * This function enables or disables a UMEM to a certain ring.
  *
  * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR}
  **/

From cfc435198f53a6fa1f656d98466b24967ff457d0 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Wed, 28 Nov 2018 14:53:19 +0800
Subject: [PATCH 51/53] rapidio/rionet: do not free skb before reading its
 length

skb is freed via dev_kfree_skb_any, however, skb->len is read then. This
may result in a use-after-free bug.

Fixes: e6161d64263 ("rapidio/rionet: rework driver initialization and removal")
Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/rionet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index e9f101c9bae2..bfbb39f93554 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			 * it just report sending a packet to the target
 			 * (without actual packet transfer).
 			 */
-			dev_kfree_skb_any(skb);
 			ndev->stats.tx_packets++;
 			ndev->stats.tx_bytes += skb->len;
+			dev_kfree_skb_any(skb);
 		}
 	}
 

From c758940158bf29fe14e9d0f89d5848f227b48134 Mon Sep 17 00:00:00 2001
From: Pan Bian <bianpan2016@163.com>
Date: Wed, 28 Nov 2018 15:30:24 +0800
Subject: [PATCH 52/53] net: hisilicon: remove unexpected free_netdev

The net device ndev is freed via free_netdev when failing to register
the device. The control flow then jumps to the error handling code
block. ndev is used and freed again. Resulting in a use-after-free bug.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hip04_eth.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index be268dcde8fa..f9a4e76c5a8b 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -915,10 +915,8 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	}
 
 	ret = register_netdev(ndev);
-	if (ret) {
-		free_netdev(ndev);
+	if (ret)
 		goto alloc_fail;
-	}
 
 	return 0;
 

From 9a764c1e59684c0358e16ccaafd870629f2cfe67 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 28 Nov 2018 16:20:50 +0100
Subject: [PATCH 53/53] s390/qeth: fix length check in SNMP processing

The response for a SNMP request can consist of multiple parts, which
the cmd callback stages into a kernel buffer until all parts have been
received. If the callback detects that the staging buffer provides
insufficient space, it bails out with error.
This processing is buggy for the first part of the response - while it
initially checks for a length of 'data_len', it later copies an
additional amount of 'offsetof(struct qeth_snmp_cmd, data)' bytes.

Fix the calculation of 'data_len' for the first part of the response.
This also nicely cleans up the memcpy code.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4bce5ae65a55..254065271867 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4518,8 +4518,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_arp_query_info *qinfo;
-	struct qeth_snmp_cmd *snmp;
 	unsigned char *data;
+	void *snmp_data;
 	__u16 data_len;
 
 	QETH_CARD_TEXT(card, 3, "snpcmdcb");
@@ -4527,7 +4527,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	cmd = (struct qeth_ipa_cmd *) sdata;
 	data = (unsigned char *)((char *)cmd - reply->offset);
 	qinfo = (struct qeth_arp_query_info *) reply->param;
-	snmp = &cmd->data.setadapterparms.data.snmp;
 
 	if (cmd->hdr.return_code) {
 		QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code);
@@ -4540,10 +4539,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 		return 0;
 	}
 	data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data));
-	if (cmd->data.setadapterparms.hdr.seq_no == 1)
-		data_len -= (__u16)((char *)&snmp->data - (char *)cmd);
-	else
-		data_len -= (__u16)((char *)&snmp->request - (char *)cmd);
+	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
+		snmp_data = &cmd->data.setadapterparms.data.snmp;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp);
+	} else {
+		snmp_data = &cmd->data.setadapterparms.data.snmp.request;
+		data_len -= offsetof(struct qeth_ipa_cmd,
+				     data.setadapterparms.data.snmp.request);
+	}
 
 	/* check if there is enough room in userspace */
 	if ((qinfo->udata_len - qinfo->udata_offset) < data_len) {
@@ -4556,16 +4560,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card,
 	QETH_CARD_TEXT_(card, 4, "sseqn%i",
 		cmd->data.setadapterparms.hdr.seq_no);
 	/*copy entries to user buffer*/
-	if (cmd->data.setadapterparms.hdr.seq_no == 1) {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)snmp,
-		       data_len + offsetof(struct qeth_snmp_cmd, data));
-		qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data);
-	} else {
-		memcpy(qinfo->udata + qinfo->udata_offset,
-		       (char *)&snmp->request, data_len);
-	}
+	memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len);
 	qinfo->udata_offset += data_len;
+
 	/* check if all replies received ... */
 		QETH_CARD_TEXT_(card, 4, "srtot%i",
 			       cmd->data.setadapterparms.hdr.used_total);