KERNEL_PATCHVER:=$(KERNEL_TESTING_PATCHVER)
endif
-LINUX_VERSION-5.4 = .101
+LINUX_VERSION-5.4 = .102
LINUX_VERSION-5.10 = .18
-LINUX_KERNEL_HASH-5.4.101 = 4e118c072dbe3209ddeaff32ecc558f7e809d54e661550342079f1ee76d9349d
+LINUX_KERNEL_HASH-5.4.102 = fd697ce1c3f6024d4ae77d4eb5a1552199407b60cb8e90bc621e23cbce639aed
LINUX_KERNEL_HASH-5.10.18 = 3bc1ee2b1bf73b5ba936721953f3f9599fd165cef906cd5163c68d23cb9bb611
remove_uri_prefix=$(subst git://,,$(subst http://,,$(subst https://,,$(1))))
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -1985,7 +1985,7 @@ static int sr2_bit7_quad_enable(struct s
+@@ -1987,7 +1987,7 @@ static int sr2_bit7_quad_enable(struct s
static int spi_nor_clear_sr_bp(struct spi_nor *nor)
{
int ret;
static void pxa_camera_setup_cicr(struct pxa_camera_dev *pcdev,
unsigned long flags, __u32 pixfmt)
{
-@@ -1598,99 +1537,78 @@ static int pxa_camera_init_videobuf2(str
+@@ -1601,99 +1540,78 @@ static int pxa_camera_init_videobuf2(str
*/
static int pxa_camera_set_bus_param(struct pxa_camera_dev *pcdev)
{
}
static const struct pxa_mbus_pixelfmt pxa_camera_formats[] = {
-@@ -1738,11 +1656,6 @@ static int pxa_camera_get_formats(struct
+@@ -1741,11 +1659,6 @@ static int pxa_camera_get_formats(struct
return 0;
}
/* 240-255: Unused at present */
--- a/drivers/mtd/parsers/parser_imagetag.c
+++ b/drivers/mtd/parsers/parser_imagetag.c
-@@ -132,7 +132,8 @@ static int bcm963xx_parse_imagetag_parti
+@@ -136,7 +136,8 @@ static int bcm963xx_parse_imagetag_parti
} else {
/* OpenWrt layout */
rootfsaddr = kerneladdr + kernellen;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 11 Feb 2020 20:47:05 +0100
-Subject: [PATCH] icmp: introduce helper for nat'd source address in network
- device context
-
-commit 0b41713b606694257b90d61ba7e2712d8457648b upstream.
-
-This introduces a helper function to be called only by network drivers
-that wraps calls to icmp[v6]_send in a conntrack transformation, in case
-NAT has been used. We don't want to pollute the non-driver path, though,
-so we introduce this as a helper to be called by places that actually
-make use of this, as suggested by Florian.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Cc: Florian Westphal <fw@strlen.de>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- include/linux/icmpv6.h | 10 ++++++++++
- include/net/icmp.h | 6 ++++++
- net/ipv4/icmp.c | 33 +++++++++++++++++++++++++++++++++
- net/ipv6/ip6_icmp.c | 34 ++++++++++++++++++++++++++++++++++
- 4 files changed, 83 insertions(+)
-
---- a/include/linux/icmpv6.h
-+++ b/include/linux/icmpv6.h
-@@ -22,12 +22,22 @@ extern int inet6_unregister_icmp_sender(
- int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
- unsigned int data_len);
-
-+#if IS_ENABLED(CONFIG_NF_NAT)
-+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
-+#else
-+#define icmpv6_ndo_send icmpv6_send
-+#endif
-+
- #else
-
- static inline void icmpv6_send(struct sk_buff *skb,
- u8 type, u8 code, __u32 info)
- {
-+}
-
-+static inline void icmpv6_ndo_send(struct sk_buff *skb,
-+ u8 type, u8 code, __u32 info)
-+{
- }
- #endif
-
---- a/include/net/icmp.h
-+++ b/include/net/icmp.h
-@@ -43,6 +43,12 @@ static inline void icmp_send(struct sk_b
- __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt);
- }
-
-+#if IS_ENABLED(CONFIG_NF_NAT)
-+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
-+#else
-+#define icmp_ndo_send icmp_send
-+#endif
-+
- int icmp_rcv(struct sk_buff *skb);
- int icmp_err(struct sk_buff *skb, u32 info);
- int icmp_init(void);
---- a/net/ipv4/icmp.c
-+++ b/net/ipv4/icmp.c
-@@ -750,6 +750,39 @@ out:;
- }
- EXPORT_SYMBOL(__icmp_send);
-
-+#if IS_ENABLED(CONFIG_NF_NAT)
-+#include <net/netfilter/nf_conntrack.h>
-+void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
-+{
-+ struct sk_buff *cloned_skb = NULL;
-+ enum ip_conntrack_info ctinfo;
-+ struct nf_conn *ct;
-+ __be32 orig_ip;
-+
-+ ct = nf_ct_get(skb_in, &ctinfo);
-+ if (!ct || !(ct->status & IPS_SRC_NAT)) {
-+ icmp_send(skb_in, type, code, info);
-+ return;
-+ }
-+
-+ if (skb_shared(skb_in))
-+ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
-+
-+ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
-+ (skb_network_header(skb_in) + sizeof(struct iphdr)) >
-+ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
-+ skb_network_offset(skb_in) + sizeof(struct iphdr))))
-+ goto out;
-+
-+ orig_ip = ip_hdr(skb_in)->saddr;
-+ ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
-+ icmp_send(skb_in, type, code, info);
-+ ip_hdr(skb_in)->saddr = orig_ip;
-+out:
-+ consume_skb(cloned_skb);
-+}
-+EXPORT_SYMBOL(icmp_ndo_send);
-+#endif
-
- static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
- {
---- a/net/ipv6/ip6_icmp.c
-+++ b/net/ipv6/ip6_icmp.c
-@@ -45,4 +45,38 @@ out:
- rcu_read_unlock();
- }
- EXPORT_SYMBOL(icmpv6_send);
-+
-+#if IS_ENABLED(CONFIG_NF_NAT)
-+#include <net/netfilter/nf_conntrack.h>
-+void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
-+{
-+ struct sk_buff *cloned_skb = NULL;
-+ enum ip_conntrack_info ctinfo;
-+ struct in6_addr orig_ip;
-+ struct nf_conn *ct;
-+
-+ ct = nf_ct_get(skb_in, &ctinfo);
-+ if (!ct || !(ct->status & IPS_SRC_NAT)) {
-+ icmpv6_send(skb_in, type, code, info);
-+ return;
-+ }
-+
-+ if (skb_shared(skb_in))
-+ skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
-+
-+ if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
-+ (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) >
-+ skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
-+ skb_network_offset(skb_in) + sizeof(struct ipv6hdr))))
-+ goto out;
-+
-+ orig_ip = ipv6_hdr(skb_in)->saddr;
-+ ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
-+ icmpv6_send(skb_in, type, code, info);
-+ ipv6_hdr(skb_in)->saddr = orig_ip;
-+out:
-+ consume_skb(cloned_skb);
-+}
-+EXPORT_SYMBOL(icmpv6_ndo_send);
-+#endif
- #endif
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 9 Dec 2019 00:27:34 +0100
+Subject: [PATCH] net: WireGuard secure network tunnel
+
+commit e7096c131e5161fa3b8e52a650d7719d2857adfd upstream.
+
+WireGuard is a layer 3 secure networking tunnel made specifically for
+the kernel, that aims to be much simpler and easier to audit than IPsec.
+Extensive documentation and description of the protocol and
+considerations, along with formal proofs of the cryptography, are
+available at:
+
+ * https://www.wireguard.com/
+ * https://www.wireguard.com/papers/wireguard.pdf
+
+This commit implements WireGuard as a simple network device driver,
+accessible in the usual RTNL way used by virtual network drivers. It
+makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of
+networking subsystem APIs. It has a somewhat novel multicore queueing
+system designed for maximum throughput and minimal latency of encryption
+operations, but it is implemented modestly using workqueues and NAPI.
+Configuration is done via generic Netlink, and following a review from
+the Netlink maintainer a year ago, several high profile userspace tools
+have already implemented the API.
+
+This commit also comes with several different tests, both in-kernel
+tests and out-of-kernel tests based on network namespaces, taking profit
+of the fact that sockets used by WireGuard intentionally stay in the
+namespace the WireGuard interface was originally created, exactly like
+the semantics of userspace tun devices. See wireguard.com/netns/ for
+pictures and examples.
+
+The source code is fairly short, but rather than combining everything
+into a single file, WireGuard is developed as cleanly separable files,
+making auditing and comprehension easier. Things are laid out as
+follows:
+
+ * noise.[ch], cookie.[ch], messages.h: These implement the bulk of the
+ cryptographic aspects of the protocol, and are mostly data-only in
+ nature, taking in buffers of bytes and spitting out buffers of
+ bytes. They also handle reference counting for their various shared
+ pieces of data, like keys and key lists.
+
+ * ratelimiter.[ch]: Used as an integral part of cookie.[ch] for
+ ratelimiting certain types of cryptographic operations in accordance
+ with particular WireGuard semantics.
+
+ * allowedips.[ch], peerlookup.[ch]: The main lookup structures of
+ WireGuard, the former being trie-like with particular semantics, an
+ integral part of the design of the protocol, and the latter just
+ being nice helper functions around the various hashtables we use.
+
+ * device.[ch]: Implementation of functions for the netdevice and for
+ rtnl, responsible for maintaining the life of a given interface and
+ wiring it up to the rest of WireGuard.
+
+ * peer.[ch]: Each interface has a list of peers, with helper functions
+ available here for creation, destruction, and reference counting.
+
+ * socket.[ch]: Implementation of functions related to udp_socket and
+ the general set of kernel socket APIs, for sending and receiving
+ ciphertext UDP packets, and taking care of WireGuard-specific sticky
+ socket routing semantics for the automatic roaming.
+
+ * netlink.[ch]: Userspace API entry point for configuring WireGuard
+ peers and devices. The API has been implemented by several userspace
+ tools and network management utility, and the WireGuard project
+ distributes the basic wg(8) tool.
+
+ * queueing.[ch]: Shared function on the rx and tx path for handling
+ the various queues used in the multicore algorithms.
+
+ * send.c: Handles encrypting outgoing packets in parallel on
+ multiple cores, before sending them in order on a single core, via
+ workqueues and ring buffers. Also handles sending handshake and cookie
+ messages as part of the protocol, in parallel.
+
+ * receive.c: Handles decrypting incoming packets in parallel on
+ multiple cores, before passing them off in order to be ingested via
+ the rest of the networking subsystem with GRO via the typical NAPI
+ poll function. Also handles receiving handshake and cookie messages
+ as part of the protocol, in parallel.
+
+ * timers.[ch]: Uses the timer wheel to implement protocol particular
+ event timeouts, and gives a set of very simple event-driven entry
+ point functions for callers.
+
+ * main.c, version.h: Initialization and deinitialization of the module.
+
+ * selftest/*.h: Runtime unit tests for some of the most security
+ sensitive functions.
+
+ * tools/testing/selftests/wireguard/netns.sh: Aforementioned testing
+ script using network namespaces.
+
+This commit aims to be as self-contained as possible, implementing
+WireGuard as a standalone module not needing much special handling or
+coordination from the network subsystem. I expect for future
+optimizations to the network stack to positively improve WireGuard, and
+vice-versa, but for the time being, this exists as intentionally
+standalone.
+
+We introduce a menu option for CONFIG_WIREGUARD, as well as providing a
+verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Cc: David Miller <davem@davemloft.net>
+Cc: Greg KH <gregkh@linuxfoundation.org>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Herbert Xu <herbert@gondor.apana.org.au>
+Cc: linux-crypto@vger.kernel.org
+Cc: linux-kernel@vger.kernel.org
+Cc: netdev@vger.kernel.org
+Signed-off-by: David S. Miller <davem@davemloft.net>
+[Jason: ported to 5.4 by doing the following:
+ - wg_get_device_start uses genl_family_attrbuf
+ - trival skb_redirect_reset change from 2c64605b590e is folded in
+ - skb_list_walk_safe was already backported prior]
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ MAINTAINERS | 8 +
+ drivers/net/Kconfig | 41 +
+ drivers/net/Makefile | 1 +
+ drivers/net/wireguard/Makefile | 18 +
+ drivers/net/wireguard/allowedips.c | 381 +++++++++
+ drivers/net/wireguard/allowedips.h | 59 ++
+ drivers/net/wireguard/cookie.c | 236 ++++++
+ drivers/net/wireguard/cookie.h | 59 ++
+ drivers/net/wireguard/device.c | 458 ++++++++++
+ drivers/net/wireguard/device.h | 65 ++
+ drivers/net/wireguard/main.c | 64 ++
+ drivers/net/wireguard/messages.h | 128 +++
+ drivers/net/wireguard/netlink.c | 648 +++++++++++++++
+ drivers/net/wireguard/netlink.h | 12 +
+ drivers/net/wireguard/noise.c | 828 +++++++++++++++++++
+ drivers/net/wireguard/noise.h | 137 +++
+ drivers/net/wireguard/peer.c | 240 ++++++
+ drivers/net/wireguard/peer.h | 83 ++
+ drivers/net/wireguard/peerlookup.c | 221 +++++
+ drivers/net/wireguard/peerlookup.h | 64 ++
+ drivers/net/wireguard/queueing.c | 53 ++
+ drivers/net/wireguard/queueing.h | 197 +++++
+ drivers/net/wireguard/ratelimiter.c | 223 +++++
+ drivers/net/wireguard/ratelimiter.h | 19 +
+ drivers/net/wireguard/receive.c | 595 +++++++++++++
+ drivers/net/wireguard/selftest/allowedips.c | 683 +++++++++++++++
+ drivers/net/wireguard/selftest/counter.c | 104 +++
+ drivers/net/wireguard/selftest/ratelimiter.c | 226 +++++
+ drivers/net/wireguard/send.c | 413 +++++++++
+ drivers/net/wireguard/socket.c | 437 ++++++++++
+ drivers/net/wireguard/socket.h | 44 +
+ drivers/net/wireguard/timers.c | 243 ++++++
+ drivers/net/wireguard/timers.h | 31 +
+ drivers/net/wireguard/version.h | 1 +
+ include/uapi/linux/wireguard.h | 196 +++++
+ tools/testing/selftests/wireguard/netns.sh | 537 ++++++++++++
+ 36 files changed, 7753 insertions(+)
+ create mode 100644 drivers/net/wireguard/Makefile
+ create mode 100644 drivers/net/wireguard/allowedips.c
+ create mode 100644 drivers/net/wireguard/allowedips.h
+ create mode 100644 drivers/net/wireguard/cookie.c
+ create mode 100644 drivers/net/wireguard/cookie.h
+ create mode 100644 drivers/net/wireguard/device.c
+ create mode 100644 drivers/net/wireguard/device.h
+ create mode 100644 drivers/net/wireguard/main.c
+ create mode 100644 drivers/net/wireguard/messages.h
+ create mode 100644 drivers/net/wireguard/netlink.c
+ create mode 100644 drivers/net/wireguard/netlink.h
+ create mode 100644 drivers/net/wireguard/noise.c
+ create mode 100644 drivers/net/wireguard/noise.h
+ create mode 100644 drivers/net/wireguard/peer.c
+ create mode 100644 drivers/net/wireguard/peer.h
+ create mode 100644 drivers/net/wireguard/peerlookup.c
+ create mode 100644 drivers/net/wireguard/peerlookup.h
+ create mode 100644 drivers/net/wireguard/queueing.c
+ create mode 100644 drivers/net/wireguard/queueing.h
+ create mode 100644 drivers/net/wireguard/ratelimiter.c
+ create mode 100644 drivers/net/wireguard/ratelimiter.h
+ create mode 100644 drivers/net/wireguard/receive.c
+ create mode 100644 drivers/net/wireguard/selftest/allowedips.c
+ create mode 100644 drivers/net/wireguard/selftest/counter.c
+ create mode 100644 drivers/net/wireguard/selftest/ratelimiter.c
+ create mode 100644 drivers/net/wireguard/send.c
+ create mode 100644 drivers/net/wireguard/socket.c
+ create mode 100644 drivers/net/wireguard/socket.h
+ create mode 100644 drivers/net/wireguard/timers.c
+ create mode 100644 drivers/net/wireguard/timers.h
+ create mode 100644 drivers/net/wireguard/version.h
+ create mode 100644 include/uapi/linux/wireguard.h
+ create mode 100755 tools/testing/selftests/wireguard/netns.sh
+
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -17584,6 +17584,14 @@ L: linux-gpio@vger.kernel.org
+ S: Maintained
+ F: drivers/gpio/gpio-ws16c48.c
+
++WIREGUARD SECURE NETWORK TUNNEL
++M: Jason A. Donenfeld <Jason@zx2c4.com>
++S: Maintained
++F: drivers/net/wireguard/
++F: tools/testing/selftests/wireguard/
++L: wireguard@lists.zx2c4.com
++L: netdev@vger.kernel.org
++
+ WISTRON LAPTOP BUTTON DRIVER
+ M: Miloslav Trmac <mitr@volny.cz>
+ S: Maintained
+--- a/drivers/net/Kconfig
++++ b/drivers/net/Kconfig
+@@ -71,6 +71,47 @@ config DUMMY
+ To compile this driver as a module, choose M here: the module
+ will be called dummy.
+
++config WIREGUARD
++ tristate "WireGuard secure network tunnel"
++ depends on NET && INET
++ depends on IPV6 || !IPV6
++ select NET_UDP_TUNNEL
++ select DST_CACHE
++ select CRYPTO
++ select CRYPTO_LIB_CURVE25519
++ select CRYPTO_LIB_CHACHA20POLY1305
++ select CRYPTO_LIB_BLAKE2S
++ select CRYPTO_CHACHA20_X86_64 if X86 && 64BIT
++ select CRYPTO_POLY1305_X86_64 if X86 && 64BIT
++ select CRYPTO_BLAKE2S_X86 if X86 && 64BIT
++ select CRYPTO_CURVE25519_X86 if X86 && 64BIT
++ select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
++ select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
++ select CRYPTO_POLY1305_ARM if ARM
++ select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
++ select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
++ select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
++ help
++ WireGuard is a secure, fast, and easy to use replacement for IPSec
++ that uses modern cryptography and clever networking tricks. It's
++ designed to be fairly general purpose and abstract enough to fit most
++ use cases, while at the same time remaining extremely simple to
++ configure. See www.wireguard.com for more info.
++
++ It's safe to say Y or M here, as the driver is very lightweight and
++ is only in use when an administrator chooses to add an interface.
++
++config WIREGUARD_DEBUG
++ bool "Debugging checks and verbose messages"
++ depends on WIREGUARD
++ help
++ This will write log messages for handshake and other events
++ that occur for a WireGuard interface. It will also perform some
++ extra validation checks and unit tests at various points. This is
++ only useful for debugging.
++
++ Say N here unless you know what you're doing.
++
+ config EQUALIZER
+ tristate "EQL (serial line load balancing) support"
+ ---help---
+--- a/drivers/net/Makefile
++++ b/drivers/net/Makefile
+@@ -10,6 +10,7 @@ obj-$(CONFIG_BONDING) += bonding/
+ obj-$(CONFIG_IPVLAN) += ipvlan/
+ obj-$(CONFIG_IPVTAP) += ipvlan/
+ obj-$(CONFIG_DUMMY) += dummy.o
++obj-$(CONFIG_WIREGUARD) += wireguard/
+ obj-$(CONFIG_EQUALIZER) += eql.o
+ obj-$(CONFIG_IFB) += ifb.o
+ obj-$(CONFIG_MACSEC) += macsec.o
+--- /dev/null
++++ b/drivers/net/wireguard/Makefile
+@@ -0,0 +1,18 @@
++ccflags-y := -O3
++ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
++ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG
++wireguard-y := main.o
++wireguard-y += noise.o
++wireguard-y += device.o
++wireguard-y += peer.o
++wireguard-y += timers.o
++wireguard-y += queueing.o
++wireguard-y += send.o
++wireguard-y += receive.o
++wireguard-y += socket.o
++wireguard-y += peerlookup.o
++wireguard-y += allowedips.o
++wireguard-y += ratelimiter.o
++wireguard-y += cookie.o
++wireguard-y += netlink.o
++obj-$(CONFIG_WIREGUARD) := wireguard.o
+--- /dev/null
++++ b/drivers/net/wireguard/allowedips.c
+@@ -0,0 +1,381 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "allowedips.h"
++#include "peer.h"
++
++static void swap_endian(u8 *dst, const u8 *src, u8 bits)
++{
++ if (bits == 32) {
++ *(u32 *)dst = be32_to_cpu(*(const __be32 *)src);
++ } else if (bits == 128) {
++ ((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]);
++ ((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]);
++ }
++}
++
++static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
++ u8 cidr, u8 bits)
++{
++ node->cidr = cidr;
++ node->bit_at_a = cidr / 8U;
++#ifdef __LITTLE_ENDIAN
++ node->bit_at_a ^= (bits / 8U - 1U) % 8U;
++#endif
++ node->bit_at_b = 7U - (cidr % 8U);
++ node->bitlen = bits;
++ memcpy(node->bits, src, bits / 8U);
++}
++#define CHOOSE_NODE(parent, key) \
++ parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
++
++static void node_free_rcu(struct rcu_head *rcu)
++{
++ kfree(container_of(rcu, struct allowedips_node, rcu));
++}
++
++static void push_rcu(struct allowedips_node **stack,
++ struct allowedips_node __rcu *p, unsigned int *len)
++{
++ if (rcu_access_pointer(p)) {
++ WARN_ON(IS_ENABLED(DEBUG) && *len >= 128);
++ stack[(*len)++] = rcu_dereference_raw(p);
++ }
++}
++
++static void root_free_rcu(struct rcu_head *rcu)
++{
++ struct allowedips_node *node, *stack[128] = {
++ container_of(rcu, struct allowedips_node, rcu) };
++ unsigned int len = 1;
++
++ while (len > 0 && (node = stack[--len])) {
++ push_rcu(stack, node->bit[0], &len);
++ push_rcu(stack, node->bit[1], &len);
++ kfree(node);
++ }
++}
++
++static void root_remove_peer_lists(struct allowedips_node *root)
++{
++ struct allowedips_node *node, *stack[128] = { root };
++ unsigned int len = 1;
++
++ while (len > 0 && (node = stack[--len])) {
++ push_rcu(stack, node->bit[0], &len);
++ push_rcu(stack, node->bit[1], &len);
++ if (rcu_access_pointer(node->peer))
++ list_del(&node->peer_list);
++ }
++}
++
++static void walk_remove_by_peer(struct allowedips_node __rcu **top,
++ struct wg_peer *peer, struct mutex *lock)
++{
++#define REF(p) rcu_access_pointer(p)
++#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
++#define PUSH(p) ({ \
++ WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \
++ stack[len++] = p; \
++ })
++
++ struct allowedips_node __rcu **stack[128], **nptr;
++ struct allowedips_node *node, *prev;
++ unsigned int len;
++
++ if (unlikely(!peer || !REF(*top)))
++ return;
++
++ for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
++ nptr = stack[len - 1];
++ node = DEREF(nptr);
++ if (!node) {
++ --len;
++ continue;
++ }
++ if (!prev || REF(prev->bit[0]) == node ||
++ REF(prev->bit[1]) == node) {
++ if (REF(node->bit[0]))
++ PUSH(&node->bit[0]);
++ else if (REF(node->bit[1]))
++ PUSH(&node->bit[1]);
++ } else if (REF(node->bit[0]) == prev) {
++ if (REF(node->bit[1]))
++ PUSH(&node->bit[1]);
++ } else {
++ if (rcu_dereference_protected(node->peer,
++ lockdep_is_held(lock)) == peer) {
++ RCU_INIT_POINTER(node->peer, NULL);
++ list_del_init(&node->peer_list);
++ if (!node->bit[0] || !node->bit[1]) {
++ rcu_assign_pointer(*nptr, DEREF(
++ &node->bit[!REF(node->bit[0])]));
++ call_rcu(&node->rcu, node_free_rcu);
++ node = DEREF(nptr);
++ }
++ }
++ --len;
++ }
++ }
++
++#undef REF
++#undef DEREF
++#undef PUSH
++}
++
++static unsigned int fls128(u64 a, u64 b)
++{
++ return a ? fls64(a) + 64U : fls64(b);
++}
++
++static u8 common_bits(const struct allowedips_node *node, const u8 *key,
++ u8 bits)
++{
++ if (bits == 32)
++ return 32U - fls(*(const u32 *)node->bits ^ *(const u32 *)key);
++ else if (bits == 128)
++ return 128U - fls128(
++ *(const u64 *)&node->bits[0] ^ *(const u64 *)&key[0],
++ *(const u64 *)&node->bits[8] ^ *(const u64 *)&key[8]);
++ return 0;
++}
++
++static bool prefix_matches(const struct allowedips_node *node, const u8 *key,
++ u8 bits)
++{
++ /* This could be much faster if it actually just compared the common
++ * bits properly, by precomputing a mask bswap(~0 << (32 - cidr)), and
++ * the rest, but it turns out that common_bits is already super fast on
++ * modern processors, even taking into account the unfortunate bswap.
++ * So, we just inline it like this instead.
++ */
++ return common_bits(node, key, bits) >= node->cidr;
++}
++
++static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
++ const u8 *key)
++{
++ struct allowedips_node *node = trie, *found = NULL;
++
++ while (node && prefix_matches(node, key, bits)) {
++ if (rcu_access_pointer(node->peer))
++ found = node;
++ if (node->cidr == bits)
++ break;
++ node = rcu_dereference_bh(CHOOSE_NODE(node, key));
++ }
++ return found;
++}
++
++/* Returns a strong reference to a peer */
++static struct wg_peer *lookup(struct allowedips_node __rcu *root, u8 bits,
++ const void *be_ip)
++{
++ /* Aligned so it can be passed to fls/fls64 */
++ u8 ip[16] __aligned(__alignof(u64));
++ struct allowedips_node *node;
++ struct wg_peer *peer = NULL;
++
++ swap_endian(ip, be_ip, bits);
++
++ rcu_read_lock_bh();
++retry:
++ node = find_node(rcu_dereference_bh(root), bits, ip);
++ if (node) {
++ peer = wg_peer_get_maybe_zero(rcu_dereference_bh(node->peer));
++ if (!peer)
++ goto retry;
++ }
++ rcu_read_unlock_bh();
++ return peer;
++}
++
++static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
++ u8 cidr, u8 bits, struct allowedips_node **rnode,
++ struct mutex *lock)
++{
++ struct allowedips_node *node = rcu_dereference_protected(trie,
++ lockdep_is_held(lock));
++ struct allowedips_node *parent = NULL;
++ bool exact = false;
++
++ while (node && node->cidr <= cidr && prefix_matches(node, key, bits)) {
++ parent = node;
++ if (parent->cidr == cidr) {
++ exact = true;
++ break;
++ }
++ node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
++ lockdep_is_held(lock));
++ }
++ *rnode = parent;
++ return exact;
++}
++
++static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
++ u8 cidr, struct wg_peer *peer, struct mutex *lock)
++{
++ struct allowedips_node *node, *parent, *down, *newnode;
++
++ if (unlikely(cidr > bits || !peer))
++ return -EINVAL;
++
++ if (!rcu_access_pointer(*trie)) {
++ node = kzalloc(sizeof(*node), GFP_KERNEL);
++ if (unlikely(!node))
++ return -ENOMEM;
++ RCU_INIT_POINTER(node->peer, peer);
++ list_add_tail(&node->peer_list, &peer->allowedips_list);
++ copy_and_assign_cidr(node, key, cidr, bits);
++ rcu_assign_pointer(*trie, node);
++ return 0;
++ }
++ if (node_placement(*trie, key, cidr, bits, &node, lock)) {
++ rcu_assign_pointer(node->peer, peer);
++ list_move_tail(&node->peer_list, &peer->allowedips_list);
++ return 0;
++ }
++
++ newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
++ if (unlikely(!newnode))
++ return -ENOMEM;
++ RCU_INIT_POINTER(newnode->peer, peer);
++ list_add_tail(&newnode->peer_list, &peer->allowedips_list);
++ copy_and_assign_cidr(newnode, key, cidr, bits);
++
++ if (!node) {
++ down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
++ } else {
++ down = rcu_dereference_protected(CHOOSE_NODE(node, key),
++ lockdep_is_held(lock));
++ if (!down) {
++ rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
++ return 0;
++ }
++ }
++ cidr = min(cidr, common_bits(down, key, bits));
++ parent = node;
++
++ if (newnode->cidr == cidr) {
++ rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
++ if (!parent)
++ rcu_assign_pointer(*trie, newnode);
++ else
++ rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
++ newnode);
++ } else {
++ node = kzalloc(sizeof(*node), GFP_KERNEL);
++ if (unlikely(!node)) {
++ kfree(newnode);
++ return -ENOMEM;
++ }
++ INIT_LIST_HEAD(&node->peer_list);
++ copy_and_assign_cidr(node, newnode->bits, cidr, bits);
++
++ rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
++ rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
++ if (!parent)
++ rcu_assign_pointer(*trie, node);
++ else
++ rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
++ node);
++ }
++ return 0;
++}
++
++void wg_allowedips_init(struct allowedips *table)
++{
++ table->root4 = table->root6 = NULL;
++ table->seq = 1;
++}
++
++void wg_allowedips_free(struct allowedips *table, struct mutex *lock)
++{
++ struct allowedips_node __rcu *old4 = table->root4, *old6 = table->root6;
++
++ ++table->seq;
++ RCU_INIT_POINTER(table->root4, NULL);
++ RCU_INIT_POINTER(table->root6, NULL);
++ if (rcu_access_pointer(old4)) {
++ struct allowedips_node *node = rcu_dereference_protected(old4,
++ lockdep_is_held(lock));
++
++ root_remove_peer_lists(node);
++ call_rcu(&node->rcu, root_free_rcu);
++ }
++ if (rcu_access_pointer(old6)) {
++ struct allowedips_node *node = rcu_dereference_protected(old6,
++ lockdep_is_held(lock));
++
++ root_remove_peer_lists(node);
++ call_rcu(&node->rcu, root_free_rcu);
++ }
++}
++
++int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
++ u8 cidr, struct wg_peer *peer, struct mutex *lock)
++{
++ /* Aligned so it can be passed to fls */
++ u8 key[4] __aligned(__alignof(u32));
++
++ ++table->seq;
++ swap_endian(key, (const u8 *)ip, 32);
++ return add(&table->root4, 32, key, cidr, peer, lock);
++}
++
++int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
++ u8 cidr, struct wg_peer *peer, struct mutex *lock)
++{
++ /* Aligned so it can be passed to fls64 */
++ u8 key[16] __aligned(__alignof(u64));
++
++ ++table->seq;
++ swap_endian(key, (const u8 *)ip, 128);
++ return add(&table->root6, 128, key, cidr, peer, lock);
++}
++
++void wg_allowedips_remove_by_peer(struct allowedips *table,
++ struct wg_peer *peer, struct mutex *lock)
++{
++ ++table->seq;
++ walk_remove_by_peer(&table->root4, peer, lock);
++ walk_remove_by_peer(&table->root6, peer, lock);
++}
++
++int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
++{
++ const unsigned int cidr_bytes = DIV_ROUND_UP(node->cidr, 8U);
++ swap_endian(ip, node->bits, node->bitlen);
++ memset(ip + cidr_bytes, 0, node->bitlen / 8U - cidr_bytes);
++ if (node->cidr)
++ ip[cidr_bytes - 1U] &= ~0U << (-node->cidr % 8U);
++
++ *cidr = node->cidr;
++ return node->bitlen == 32 ? AF_INET : AF_INET6;
++}
++
++/* Returns a strong reference to a peer */
++struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
++ struct sk_buff *skb)
++{
++ if (skb->protocol == htons(ETH_P_IP))
++ return lookup(table->root4, 32, &ip_hdr(skb)->daddr);
++ else if (skb->protocol == htons(ETH_P_IPV6))
++ return lookup(table->root6, 128, &ipv6_hdr(skb)->daddr);
++ return NULL;
++}
++
++/* Returns a strong reference to a peer */
++struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
++ struct sk_buff *skb)
++{
++ if (skb->protocol == htons(ETH_P_IP))
++ return lookup(table->root4, 32, &ip_hdr(skb)->saddr);
++ else if (skb->protocol == htons(ETH_P_IPV6))
++ return lookup(table->root6, 128, &ipv6_hdr(skb)->saddr);
++ return NULL;
++}
++
++#include "selftest/allowedips.c"
+--- /dev/null
++++ b/drivers/net/wireguard/allowedips.h
+@@ -0,0 +1,59 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_ALLOWEDIPS_H
++#define _WG_ALLOWEDIPS_H
++
++#include <linux/mutex.h>
++#include <linux/ip.h>
++#include <linux/ipv6.h>
++
++struct wg_peer;
++
++struct allowedips_node {
++ struct wg_peer __rcu *peer;
++ struct allowedips_node __rcu *bit[2];
++ /* While it may seem scandalous that we waste space for v4,
++ * we're alloc'ing to the nearest power of 2 anyway, so this
++ * doesn't actually make a difference.
++ */
++ u8 bits[16] __aligned(__alignof(u64));
++ u8 cidr, bit_at_a, bit_at_b, bitlen;
++
++ /* Keep rarely used list at bottom to be beyond cache line. */
++ union {
++ struct list_head peer_list;
++ struct rcu_head rcu;
++ };
++};
++
++struct allowedips {
++ struct allowedips_node __rcu *root4;
++ struct allowedips_node __rcu *root6;
++ u64 seq;
++};
++
++void wg_allowedips_init(struct allowedips *table);
++void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
++int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
++ u8 cidr, struct wg_peer *peer, struct mutex *lock);
++int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
++ u8 cidr, struct wg_peer *peer, struct mutex *lock);
++void wg_allowedips_remove_by_peer(struct allowedips *table,
++ struct wg_peer *peer, struct mutex *lock);
++/* The ip input pointer should be __aligned(__alignof(u64))) */
++int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr);
++
++/* These return a strong reference to a peer: */
++struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
++ struct sk_buff *skb);
++struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
++ struct sk_buff *skb);
++
++#ifdef DEBUG
++bool wg_allowedips_selftest(void);
++#endif
++
++#endif /* _WG_ALLOWEDIPS_H */
+--- /dev/null
++++ b/drivers/net/wireguard/cookie.c
+@@ -0,0 +1,236 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "cookie.h"
++#include "peer.h"
++#include "device.h"
++#include "messages.h"
++#include "ratelimiter.h"
++#include "timers.h"
++
++#include <crypto/blake2s.h>
++#include <crypto/chacha20poly1305.h>
++
++#include <net/ipv6.h>
++#include <crypto/algapi.h>
++
++void wg_cookie_checker_init(struct cookie_checker *checker,
++ struct wg_device *wg)
++{
++ init_rwsem(&checker->secret_lock);
++ checker->secret_birthdate = ktime_get_coarse_boottime_ns();
++ get_random_bytes(checker->secret, NOISE_HASH_LEN);
++ checker->device = wg;
++}
++
++enum { COOKIE_KEY_LABEL_LEN = 8 };
++static const u8 mac1_key_label[COOKIE_KEY_LABEL_LEN] = "mac1----";
++static const u8 cookie_key_label[COOKIE_KEY_LABEL_LEN] = "cookie--";
++
++static void precompute_key(u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN],
++ const u8 label[COOKIE_KEY_LABEL_LEN])
++{
++ struct blake2s_state blake;
++
++ blake2s_init(&blake, NOISE_SYMMETRIC_KEY_LEN);
++ blake2s_update(&blake, label, COOKIE_KEY_LABEL_LEN);
++ blake2s_update(&blake, pubkey, NOISE_PUBLIC_KEY_LEN);
++ blake2s_final(&blake, key);
++}
++
++/* Must hold peer->handshake.static_identity->lock */
++void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker)
++{
++ if (likely(checker->device->static_identity.has_identity)) {
++ precompute_key(checker->cookie_encryption_key,
++ checker->device->static_identity.static_public,
++ cookie_key_label);
++ precompute_key(checker->message_mac1_key,
++ checker->device->static_identity.static_public,
++ mac1_key_label);
++ } else {
++ memset(checker->cookie_encryption_key, 0,
++ NOISE_SYMMETRIC_KEY_LEN);
++ memset(checker->message_mac1_key, 0, NOISE_SYMMETRIC_KEY_LEN);
++ }
++}
++
++void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer)
++{
++ precompute_key(peer->latest_cookie.cookie_decryption_key,
++ peer->handshake.remote_static, cookie_key_label);
++ precompute_key(peer->latest_cookie.message_mac1_key,
++ peer->handshake.remote_static, mac1_key_label);
++}
++
++void wg_cookie_init(struct cookie *cookie)
++{
++ memset(cookie, 0, sizeof(*cookie));
++ init_rwsem(&cookie->lock);
++}
++
++static void compute_mac1(u8 mac1[COOKIE_LEN], const void *message, size_t len,
++ const u8 key[NOISE_SYMMETRIC_KEY_LEN])
++{
++ len = len - sizeof(struct message_macs) +
++ offsetof(struct message_macs, mac1);
++ blake2s(mac1, message, key, COOKIE_LEN, len, NOISE_SYMMETRIC_KEY_LEN);
++}
++
++static void compute_mac2(u8 mac2[COOKIE_LEN], const void *message, size_t len,
++ const u8 cookie[COOKIE_LEN])
++{
++ len = len - sizeof(struct message_macs) +
++ offsetof(struct message_macs, mac2);
++ blake2s(mac2, message, cookie, COOKIE_LEN, len, COOKIE_LEN);
++}
++
++static void make_cookie(u8 cookie[COOKIE_LEN], struct sk_buff *skb,
++ struct cookie_checker *checker)
++{
++ struct blake2s_state state;
++
++ if (wg_birthdate_has_expired(checker->secret_birthdate,
++ COOKIE_SECRET_MAX_AGE)) {
++ down_write(&checker->secret_lock);
++ checker->secret_birthdate = ktime_get_coarse_boottime_ns();
++ get_random_bytes(checker->secret, NOISE_HASH_LEN);
++ up_write(&checker->secret_lock);
++ }
++
++ down_read(&checker->secret_lock);
++
++ blake2s_init_key(&state, COOKIE_LEN, checker->secret, NOISE_HASH_LEN);
++ if (skb->protocol == htons(ETH_P_IP))
++ blake2s_update(&state, (u8 *)&ip_hdr(skb)->saddr,
++ sizeof(struct in_addr));
++ else if (skb->protocol == htons(ETH_P_IPV6))
++ blake2s_update(&state, (u8 *)&ipv6_hdr(skb)->saddr,
++ sizeof(struct in6_addr));
++ blake2s_update(&state, (u8 *)&udp_hdr(skb)->source, sizeof(__be16));
++ blake2s_final(&state, cookie);
++
++ up_read(&checker->secret_lock);
++}
++
++enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker,
++ struct sk_buff *skb,
++ bool check_cookie)
++{
++ struct message_macs *macs = (struct message_macs *)
++ (skb->data + skb->len - sizeof(*macs));
++ enum cookie_mac_state ret;
++ u8 computed_mac[COOKIE_LEN];
++ u8 cookie[COOKIE_LEN];
++
++ ret = INVALID_MAC;
++ compute_mac1(computed_mac, skb->data, skb->len,
++ checker->message_mac1_key);
++ if (crypto_memneq(computed_mac, macs->mac1, COOKIE_LEN))
++ goto out;
++
++ ret = VALID_MAC_BUT_NO_COOKIE;
++
++ if (!check_cookie)
++ goto out;
++
++ make_cookie(cookie, skb, checker);
++
++ compute_mac2(computed_mac, skb->data, skb->len, cookie);
++ if (crypto_memneq(computed_mac, macs->mac2, COOKIE_LEN))
++ goto out;
++
++ ret = VALID_MAC_WITH_COOKIE_BUT_RATELIMITED;
++ if (!wg_ratelimiter_allow(skb, dev_net(checker->device->dev)))
++ goto out;
++
++ ret = VALID_MAC_WITH_COOKIE;
++
++out:
++ return ret;
++}
++
++void wg_cookie_add_mac_to_packet(void *message, size_t len,
++ struct wg_peer *peer)
++{
++ struct message_macs *macs = (struct message_macs *)
++ ((u8 *)message + len - sizeof(*macs));
++
++ down_write(&peer->latest_cookie.lock);
++ compute_mac1(macs->mac1, message, len,
++ peer->latest_cookie.message_mac1_key);
++ memcpy(peer->latest_cookie.last_mac1_sent, macs->mac1, COOKIE_LEN);
++ peer->latest_cookie.have_sent_mac1 = true;
++ up_write(&peer->latest_cookie.lock);
++
++ down_read(&peer->latest_cookie.lock);
++ if (peer->latest_cookie.is_valid &&
++ !wg_birthdate_has_expired(peer->latest_cookie.birthdate,
++ COOKIE_SECRET_MAX_AGE - COOKIE_SECRET_LATENCY))
++ compute_mac2(macs->mac2, message, len,
++ peer->latest_cookie.cookie);
++ else
++ memset(macs->mac2, 0, COOKIE_LEN);
++ up_read(&peer->latest_cookie.lock);
++}
++
++void wg_cookie_message_create(struct message_handshake_cookie *dst,
++ struct sk_buff *skb, __le32 index,
++ struct cookie_checker *checker)
++{
++ struct message_macs *macs = (struct message_macs *)
++ ((u8 *)skb->data + skb->len - sizeof(*macs));
++ u8 cookie[COOKIE_LEN];
++
++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE);
++ dst->receiver_index = index;
++ get_random_bytes_wait(dst->nonce, COOKIE_NONCE_LEN);
++
++ make_cookie(cookie, skb, checker);
++ xchacha20poly1305_encrypt(dst->encrypted_cookie, cookie, COOKIE_LEN,
++ macs->mac1, COOKIE_LEN, dst->nonce,
++ checker->cookie_encryption_key);
++}
++
++void wg_cookie_message_consume(struct message_handshake_cookie *src,
++ struct wg_device *wg)
++{
++ struct wg_peer *peer = NULL;
++ u8 cookie[COOKIE_LEN];
++ bool ret;
++
++ if (unlikely(!wg_index_hashtable_lookup(wg->index_hashtable,
++ INDEX_HASHTABLE_HANDSHAKE |
++ INDEX_HASHTABLE_KEYPAIR,
++ src->receiver_index, &peer)))
++ return;
++
++ down_read(&peer->latest_cookie.lock);
++ if (unlikely(!peer->latest_cookie.have_sent_mac1)) {
++ up_read(&peer->latest_cookie.lock);
++ goto out;
++ }
++ ret = xchacha20poly1305_decrypt(
++ cookie, src->encrypted_cookie, sizeof(src->encrypted_cookie),
++ peer->latest_cookie.last_mac1_sent, COOKIE_LEN, src->nonce,
++ peer->latest_cookie.cookie_decryption_key);
++ up_read(&peer->latest_cookie.lock);
++
++ if (ret) {
++ down_write(&peer->latest_cookie.lock);
++ memcpy(peer->latest_cookie.cookie, cookie, COOKIE_LEN);
++ peer->latest_cookie.birthdate = ktime_get_coarse_boottime_ns();
++ peer->latest_cookie.is_valid = true;
++ peer->latest_cookie.have_sent_mac1 = false;
++ up_write(&peer->latest_cookie.lock);
++ } else {
++ net_dbg_ratelimited("%s: Could not decrypt invalid cookie response\n",
++ wg->dev->name);
++ }
++
++out:
++ wg_peer_put(peer);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/cookie.h
+@@ -0,0 +1,59 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_COOKIE_H
++#define _WG_COOKIE_H
++
++#include "messages.h"
++#include <linux/rwsem.h>
++
++struct wg_peer;
++
++struct cookie_checker {
++ u8 secret[NOISE_HASH_LEN];
++ u8 cookie_encryption_key[NOISE_SYMMETRIC_KEY_LEN];
++ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN];
++ u64 secret_birthdate;
++ struct rw_semaphore secret_lock;
++ struct wg_device *device;
++};
++
++struct cookie {
++ u64 birthdate;
++ bool is_valid;
++ u8 cookie[COOKIE_LEN];
++ bool have_sent_mac1;
++ u8 last_mac1_sent[COOKIE_LEN];
++ u8 cookie_decryption_key[NOISE_SYMMETRIC_KEY_LEN];
++ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN];
++ struct rw_semaphore lock;
++};
++
++enum cookie_mac_state {
++ INVALID_MAC,
++ VALID_MAC_BUT_NO_COOKIE,
++ VALID_MAC_WITH_COOKIE_BUT_RATELIMITED,
++ VALID_MAC_WITH_COOKIE
++};
++
++void wg_cookie_checker_init(struct cookie_checker *checker,
++ struct wg_device *wg);
++void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker);
++void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer);
++void wg_cookie_init(struct cookie *cookie);
++
++enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker,
++ struct sk_buff *skb,
++ bool check_cookie);
++void wg_cookie_add_mac_to_packet(void *message, size_t len,
++ struct wg_peer *peer);
++
++void wg_cookie_message_create(struct message_handshake_cookie *src,
++ struct sk_buff *skb, __le32 index,
++ struct cookie_checker *checker);
++void wg_cookie_message_consume(struct message_handshake_cookie *src,
++ struct wg_device *wg);
++
++#endif /* _WG_COOKIE_H */
+--- /dev/null
++++ b/drivers/net/wireguard/device.c
+@@ -0,0 +1,458 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "queueing.h"
++#include "socket.h"
++#include "timers.h"
++#include "device.h"
++#include "ratelimiter.h"
++#include "peer.h"
++#include "messages.h"
++
++#include <linux/module.h>
++#include <linux/rtnetlink.h>
++#include <linux/inet.h>
++#include <linux/netdevice.h>
++#include <linux/inetdevice.h>
++#include <linux/if_arp.h>
++#include <linux/icmp.h>
++#include <linux/suspend.h>
++#include <net/icmp.h>
++#include <net/rtnetlink.h>
++#include <net/ip_tunnels.h>
++#include <net/addrconf.h>
++
++static LIST_HEAD(device_list);
++
++static int wg_open(struct net_device *dev)
++{
++ struct in_device *dev_v4 = __in_dev_get_rtnl(dev);
++ struct inet6_dev *dev_v6 = __in6_dev_get(dev);
++ struct wg_device *wg = netdev_priv(dev);
++ struct wg_peer *peer;
++ int ret;
++
++ if (dev_v4) {
++ /* At some point we might put this check near the ip_rt_send_
++ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar
++ * to the current secpath check.
++ */
++ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
++ IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false;
++ }
++ if (dev_v6)
++ dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
++
++ ret = wg_socket_init(wg, wg->incoming_port);
++ if (ret < 0)
++ return ret;
++ mutex_lock(&wg->device_update_lock);
++ list_for_each_entry(peer, &wg->peer_list, peer_list) {
++ wg_packet_send_staged_packets(peer);
++ if (peer->persistent_keepalive_interval)
++ wg_packet_send_keepalive(peer);
++ }
++ mutex_unlock(&wg->device_update_lock);
++ return 0;
++}
++
++#ifdef CONFIG_PM_SLEEP
++static int wg_pm_notification(struct notifier_block *nb, unsigned long action,
++ void *data)
++{
++ struct wg_device *wg;
++ struct wg_peer *peer;
++
++ /* If the machine is constantly suspending and resuming, as part of
++ * its normal operation rather than as a somewhat rare event, then we
++ * don't actually want to clear keys.
++ */
++ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_ANDROID))
++ return 0;
++
++ if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE)
++ return 0;
++
++ rtnl_lock();
++ list_for_each_entry(wg, &device_list, device_list) {
++ mutex_lock(&wg->device_update_lock);
++ list_for_each_entry(peer, &wg->peer_list, peer_list) {
++ del_timer(&peer->timer_zero_key_material);
++ wg_noise_handshake_clear(&peer->handshake);
++ wg_noise_keypairs_clear(&peer->keypairs);
++ }
++ mutex_unlock(&wg->device_update_lock);
++ }
++ rtnl_unlock();
++ rcu_barrier();
++ return 0;
++}
++
++static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification };
++#endif
++
++static int wg_stop(struct net_device *dev)
++{
++ struct wg_device *wg = netdev_priv(dev);
++ struct wg_peer *peer;
++
++ mutex_lock(&wg->device_update_lock);
++ list_for_each_entry(peer, &wg->peer_list, peer_list) {
++ wg_packet_purge_staged_packets(peer);
++ wg_timers_stop(peer);
++ wg_noise_handshake_clear(&peer->handshake);
++ wg_noise_keypairs_clear(&peer->keypairs);
++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
++ }
++ mutex_unlock(&wg->device_update_lock);
++ skb_queue_purge(&wg->incoming_handshakes);
++ wg_socket_reinit(wg, NULL, NULL);
++ return 0;
++}
++
++static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
++{
++ struct wg_device *wg = netdev_priv(dev);
++ struct sk_buff_head packets;
++ struct wg_peer *peer;
++ struct sk_buff *next;
++ sa_family_t family;
++ u32 mtu;
++ int ret;
++
++ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) {
++ ret = -EPROTONOSUPPORT;
++ net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
++ goto err;
++ }
++
++ peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb);
++ if (unlikely(!peer)) {
++ ret = -ENOKEY;
++ if (skb->protocol == htons(ETH_P_IP))
++ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n",
++ dev->name, &ip_hdr(skb)->daddr);
++ else if (skb->protocol == htons(ETH_P_IPV6))
++ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
++ dev->name, &ipv6_hdr(skb)->daddr);
++ goto err;
++ }
++
++ family = READ_ONCE(peer->endpoint.addr.sa_family);
++ if (unlikely(family != AF_INET && family != AF_INET6)) {
++ ret = -EDESTADDRREQ;
++ net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n",
++ dev->name, peer->internal_id);
++ goto err_peer;
++ }
++
++ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
++
++ __skb_queue_head_init(&packets);
++ if (!skb_is_gso(skb)) {
++ skb_mark_not_on_list(skb);
++ } else {
++ struct sk_buff *segs = skb_gso_segment(skb, 0);
++
++ if (unlikely(IS_ERR(segs))) {
++ ret = PTR_ERR(segs);
++ goto err_peer;
++ }
++ dev_kfree_skb(skb);
++ skb = segs;
++ }
++
++ skb_list_walk_safe(skb, skb, next) {
++ skb_mark_not_on_list(skb);
++
++ skb = skb_share_check(skb, GFP_ATOMIC);
++ if (unlikely(!skb))
++ continue;
++
++ /* We only need to keep the original dst around for icmp,
++ * so at this point we're in a position to drop it.
++ */
++ skb_dst_drop(skb);
++
++ PACKET_CB(skb)->mtu = mtu;
++
++ __skb_queue_tail(&packets, skb);
++ }
++
++ spin_lock_bh(&peer->staged_packet_queue.lock);
++ /* If the queue is getting too big, we start removing the oldest packets
++ * until it's small again. We do this before adding the new packet, so
++ * we don't remove GSO segments that are in excess.
++ */
++ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
++ dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
++ ++dev->stats.tx_dropped;
++ }
++ skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
++ spin_unlock_bh(&peer->staged_packet_queue.lock);
++
++ wg_packet_send_staged_packets(peer);
++
++ wg_peer_put(peer);
++ return NETDEV_TX_OK;
++
++err_peer:
++ wg_peer_put(peer);
++err:
++ ++dev->stats.tx_errors;
++ if (skb->protocol == htons(ETH_P_IP))
++ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
++ else if (skb->protocol == htons(ETH_P_IPV6))
++ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
++ kfree_skb(skb);
++ return ret;
++}
++
++static const struct net_device_ops netdev_ops = {
++ .ndo_open = wg_open,
++ .ndo_stop = wg_stop,
++ .ndo_start_xmit = wg_xmit,
++ .ndo_get_stats64 = ip_tunnel_get_stats64
++};
++
++static void wg_destruct(struct net_device *dev)
++{
++ struct wg_device *wg = netdev_priv(dev);
++
++ rtnl_lock();
++ list_del(&wg->device_list);
++ rtnl_unlock();
++ mutex_lock(&wg->device_update_lock);
++ wg->incoming_port = 0;
++ wg_socket_reinit(wg, NULL, NULL);
++ /* The final references are cleared in the below calls to destroy_workqueue. */
++ wg_peer_remove_all(wg);
++ destroy_workqueue(wg->handshake_receive_wq);
++ destroy_workqueue(wg->handshake_send_wq);
++ destroy_workqueue(wg->packet_crypt_wq);
++ wg_packet_queue_free(&wg->decrypt_queue, true);
++ wg_packet_queue_free(&wg->encrypt_queue, true);
++ rcu_barrier(); /* Wait for all the peers to be actually freed. */
++ wg_ratelimiter_uninit();
++ memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
++ skb_queue_purge(&wg->incoming_handshakes);
++ free_percpu(dev->tstats);
++ free_percpu(wg->incoming_handshakes_worker);
++ if (wg->have_creating_net_ref)
++ put_net(wg->creating_net);
++ kvfree(wg->index_hashtable);
++ kvfree(wg->peer_hashtable);
++ mutex_unlock(&wg->device_update_lock);
++
++ pr_debug("%s: Interface deleted\n", dev->name);
++ free_netdev(dev);
++}
++
++static const struct device_type device_type = { .name = KBUILD_MODNAME };
++
++static void wg_setup(struct net_device *dev)
++{
++ struct wg_device *wg = netdev_priv(dev);
++ enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
++ NETIF_F_SG | NETIF_F_GSO |
++ NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
++
++ dev->netdev_ops = &netdev_ops;
++ dev->hard_header_len = 0;
++ dev->addr_len = 0;
++ dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
++ dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE);
++ dev->type = ARPHRD_NONE;
++ dev->flags = IFF_POINTOPOINT | IFF_NOARP;
++ dev->priv_flags |= IFF_NO_QUEUE;
++ dev->features |= NETIF_F_LLTX;
++ dev->features |= WG_NETDEV_FEATURES;
++ dev->hw_features |= WG_NETDEV_FEATURES;
++ dev->hw_enc_features |= WG_NETDEV_FEATURES;
++ dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
++ sizeof(struct udphdr) -
++ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
++
++ SET_NETDEV_DEVTYPE(dev, &device_type);
++
++ /* We need to keep the dst around in case of icmp replies. */
++ netif_keep_dst(dev);
++
++ memset(wg, 0, sizeof(*wg));
++ wg->dev = dev;
++}
++
++static int wg_newlink(struct net *src_net, struct net_device *dev,
++ struct nlattr *tb[], struct nlattr *data[],
++ struct netlink_ext_ack *extack)
++{
++ struct wg_device *wg = netdev_priv(dev);
++ int ret = -ENOMEM;
++
++ wg->creating_net = src_net;
++ init_rwsem(&wg->static_identity.lock);
++ mutex_init(&wg->socket_update_lock);
++ mutex_init(&wg->device_update_lock);
++ skb_queue_head_init(&wg->incoming_handshakes);
++ wg_allowedips_init(&wg->peer_allowedips);
++ wg_cookie_checker_init(&wg->cookie_checker, wg);
++ INIT_LIST_HEAD(&wg->peer_list);
++ wg->device_update_gen = 1;
++
++ wg->peer_hashtable = wg_pubkey_hashtable_alloc();
++ if (!wg->peer_hashtable)
++ return ret;
++
++ wg->index_hashtable = wg_index_hashtable_alloc();
++ if (!wg->index_hashtable)
++ goto err_free_peer_hashtable;
++
++ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
++ if (!dev->tstats)
++ goto err_free_index_hashtable;
++
++ wg->incoming_handshakes_worker =
++ wg_packet_percpu_multicore_worker_alloc(
++ wg_packet_handshake_receive_worker, wg);
++ if (!wg->incoming_handshakes_worker)
++ goto err_free_tstats;
++
++ wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
++ WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
++ if (!wg->handshake_receive_wq)
++ goto err_free_incoming_handshakes;
++
++ wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
++ WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
++ if (!wg->handshake_send_wq)
++ goto err_destroy_handshake_receive;
++
++ wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s",
++ WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name);
++ if (!wg->packet_crypt_wq)
++ goto err_destroy_handshake_send;
++
++ ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
++ true, MAX_QUEUED_PACKETS);
++ if (ret < 0)
++ goto err_destroy_packet_crypt;
++
++ ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
++ true, MAX_QUEUED_PACKETS);
++ if (ret < 0)
++ goto err_free_encrypt_queue;
++
++ ret = wg_ratelimiter_init();
++ if (ret < 0)
++ goto err_free_decrypt_queue;
++
++ ret = register_netdevice(dev);
++ if (ret < 0)
++ goto err_uninit_ratelimiter;
++
++ list_add(&wg->device_list, &device_list);
++
++ /* We wait until the end to assign priv_destructor, so that
++ * register_netdevice doesn't call it for us if it fails.
++ */
++ dev->priv_destructor = wg_destruct;
++
++ pr_debug("%s: Interface created\n", dev->name);
++ return ret;
++
++err_uninit_ratelimiter:
++ wg_ratelimiter_uninit();
++err_free_decrypt_queue:
++ wg_packet_queue_free(&wg->decrypt_queue, true);
++err_free_encrypt_queue:
++ wg_packet_queue_free(&wg->encrypt_queue, true);
++err_destroy_packet_crypt:
++ destroy_workqueue(wg->packet_crypt_wq);
++err_destroy_handshake_send:
++ destroy_workqueue(wg->handshake_send_wq);
++err_destroy_handshake_receive:
++ destroy_workqueue(wg->handshake_receive_wq);
++err_free_incoming_handshakes:
++ free_percpu(wg->incoming_handshakes_worker);
++err_free_tstats:
++ free_percpu(dev->tstats);
++err_free_index_hashtable:
++ kvfree(wg->index_hashtable);
++err_free_peer_hashtable:
++ kvfree(wg->peer_hashtable);
++ return ret;
++}
++
++static struct rtnl_link_ops link_ops __read_mostly = {
++ .kind = KBUILD_MODNAME,
++ .priv_size = sizeof(struct wg_device),
++ .setup = wg_setup,
++ .newlink = wg_newlink,
++};
++
++static int wg_netdevice_notification(struct notifier_block *nb,
++ unsigned long action, void *data)
++{
++ struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
++ struct wg_device *wg = netdev_priv(dev);
++
++ ASSERT_RTNL();
++
++ if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
++ return 0;
++
++ if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
++ put_net(wg->creating_net);
++ wg->have_creating_net_ref = false;
++ } else if (dev_net(dev) != wg->creating_net &&
++ !wg->have_creating_net_ref) {
++ wg->have_creating_net_ref = true;
++ get_net(wg->creating_net);
++ }
++ return 0;
++}
++
++static struct notifier_block netdevice_notifier = {
++ .notifier_call = wg_netdevice_notification
++};
++
++int __init wg_device_init(void)
++{
++ int ret;
++
++#ifdef CONFIG_PM_SLEEP
++ ret = register_pm_notifier(&pm_notifier);
++ if (ret)
++ return ret;
++#endif
++
++ ret = register_netdevice_notifier(&netdevice_notifier);
++ if (ret)
++ goto error_pm;
++
++ ret = rtnl_link_register(&link_ops);
++ if (ret)
++ goto error_netdevice;
++
++ return 0;
++
++error_netdevice:
++ unregister_netdevice_notifier(&netdevice_notifier);
++error_pm:
++#ifdef CONFIG_PM_SLEEP
++ unregister_pm_notifier(&pm_notifier);
++#endif
++ return ret;
++}
++
++void wg_device_uninit(void)
++{
++ rtnl_link_unregister(&link_ops);
++ unregister_netdevice_notifier(&netdevice_notifier);
++#ifdef CONFIG_PM_SLEEP
++ unregister_pm_notifier(&pm_notifier);
++#endif
++ rcu_barrier();
++}
+--- /dev/null
++++ b/drivers/net/wireguard/device.h
+@@ -0,0 +1,65 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_DEVICE_H
++#define _WG_DEVICE_H
++
++#include "noise.h"
++#include "allowedips.h"
++#include "peerlookup.h"
++#include "cookie.h"
++
++#include <linux/types.h>
++#include <linux/netdevice.h>
++#include <linux/workqueue.h>
++#include <linux/mutex.h>
++#include <linux/net.h>
++#include <linux/ptr_ring.h>
++
++struct wg_device;
++
++struct multicore_worker {
++ void *ptr;
++ struct work_struct work;
++};
++
++struct crypt_queue {
++ struct ptr_ring ring;
++ union {
++ struct {
++ struct multicore_worker __percpu *worker;
++ int last_cpu;
++ };
++ struct work_struct work;
++ };
++};
++
++struct wg_device {
++ struct net_device *dev;
++ struct crypt_queue encrypt_queue, decrypt_queue;
++ struct sock __rcu *sock4, *sock6;
++ struct net *creating_net;
++ struct noise_static_identity static_identity;
++ struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
++ struct workqueue_struct *packet_crypt_wq;
++ struct sk_buff_head incoming_handshakes;
++ int incoming_handshake_cpu;
++ struct multicore_worker __percpu *incoming_handshakes_worker;
++ struct cookie_checker cookie_checker;
++ struct pubkey_hashtable *peer_hashtable;
++ struct index_hashtable *index_hashtable;
++ struct allowedips peer_allowedips;
++ struct mutex device_update_lock, socket_update_lock;
++ struct list_head device_list, peer_list;
++ unsigned int num_peers, device_update_gen;
++ u32 fwmark;
++ u16 incoming_port;
++ bool have_creating_net_ref;
++};
++
++int wg_device_init(void);
++void wg_device_uninit(void);
++
++#endif /* _WG_DEVICE_H */
+--- /dev/null
++++ b/drivers/net/wireguard/main.c
+@@ -0,0 +1,64 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "version.h"
++#include "device.h"
++#include "noise.h"
++#include "queueing.h"
++#include "ratelimiter.h"
++#include "netlink.h"
++
++#include <uapi/linux/wireguard.h>
++
++#include <linux/version.h>
++#include <linux/init.h>
++#include <linux/module.h>
++#include <linux/genetlink.h>
++#include <net/rtnetlink.h>
++
++static int __init mod_init(void)
++{
++ int ret;
++
++#ifdef DEBUG
++ if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() ||
++ !wg_ratelimiter_selftest())
++ return -ENOTRECOVERABLE;
++#endif
++ wg_noise_init();
++
++ ret = wg_device_init();
++ if (ret < 0)
++ goto err_device;
++
++ ret = wg_genetlink_init();
++ if (ret < 0)
++ goto err_netlink;
++
++ pr_info("WireGuard " WIREGUARD_VERSION " loaded. See www.wireguard.com for information.\n");
++ pr_info("Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.\n");
++
++ return 0;
++
++err_netlink:
++ wg_device_uninit();
++err_device:
++ return ret;
++}
++
++static void __exit mod_exit(void)
++{
++ wg_genetlink_uninit();
++ wg_device_uninit();
++}
++
++module_init(mod_init);
++module_exit(mod_exit);
++MODULE_LICENSE("GPL v2");
++MODULE_DESCRIPTION("WireGuard secure network tunnel");
++MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
++MODULE_VERSION(WIREGUARD_VERSION);
++MODULE_ALIAS_RTNL_LINK(KBUILD_MODNAME);
++MODULE_ALIAS_GENL_FAMILY(WG_GENL_NAME);
+--- /dev/null
++++ b/drivers/net/wireguard/messages.h
+@@ -0,0 +1,128 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_MESSAGES_H
++#define _WG_MESSAGES_H
++
++#include <crypto/curve25519.h>
++#include <crypto/chacha20poly1305.h>
++#include <crypto/blake2s.h>
++
++#include <linux/kernel.h>
++#include <linux/param.h>
++#include <linux/skbuff.h>
++
++enum noise_lengths {
++ NOISE_PUBLIC_KEY_LEN = CURVE25519_KEY_SIZE,
++ NOISE_SYMMETRIC_KEY_LEN = CHACHA20POLY1305_KEY_SIZE,
++ NOISE_TIMESTAMP_LEN = sizeof(u64) + sizeof(u32),
++ NOISE_AUTHTAG_LEN = CHACHA20POLY1305_AUTHTAG_SIZE,
++ NOISE_HASH_LEN = BLAKE2S_HASH_SIZE
++};
++
++#define noise_encrypted_len(plain_len) ((plain_len) + NOISE_AUTHTAG_LEN)
++
++enum cookie_values {
++ COOKIE_SECRET_MAX_AGE = 2 * 60,
++ COOKIE_SECRET_LATENCY = 5,
++ COOKIE_NONCE_LEN = XCHACHA20POLY1305_NONCE_SIZE,
++ COOKIE_LEN = 16
++};
++
++enum counter_values {
++ COUNTER_BITS_TOTAL = 2048,
++ COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
++ COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
++};
++
++enum limits {
++ REKEY_AFTER_MESSAGES = 1ULL << 60,
++ REJECT_AFTER_MESSAGES = U64_MAX - COUNTER_WINDOW_SIZE - 1,
++ REKEY_TIMEOUT = 5,
++ REKEY_TIMEOUT_JITTER_MAX_JIFFIES = HZ / 3,
++ REKEY_AFTER_TIME = 120,
++ REJECT_AFTER_TIME = 180,
++ INITIATIONS_PER_SECOND = 50,
++ MAX_PEERS_PER_DEVICE = 1U << 20,
++ KEEPALIVE_TIMEOUT = 10,
++ MAX_TIMER_HANDSHAKES = 90 / REKEY_TIMEOUT,
++ MAX_QUEUED_INCOMING_HANDSHAKES = 4096, /* TODO: replace this with DQL */
++ MAX_STAGED_PACKETS = 128,
++ MAX_QUEUED_PACKETS = 1024 /* TODO: replace this with DQL */
++};
++
++enum message_type {
++ MESSAGE_INVALID = 0,
++ MESSAGE_HANDSHAKE_INITIATION = 1,
++ MESSAGE_HANDSHAKE_RESPONSE = 2,
++ MESSAGE_HANDSHAKE_COOKIE = 3,
++ MESSAGE_DATA = 4
++};
++
++struct message_header {
++ /* The actual layout of this that we want is:
++ * u8 type
++ * u8 reserved_zero[3]
++ *
++ * But it turns out that by encoding this as little endian,
++ * we achieve the same thing, and it makes checking faster.
++ */
++ __le32 type;
++};
++
++struct message_macs {
++ u8 mac1[COOKIE_LEN];
++ u8 mac2[COOKIE_LEN];
++};
++
++struct message_handshake_initiation {
++ struct message_header header;
++ __le32 sender_index;
++ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
++ u8 encrypted_static[noise_encrypted_len(NOISE_PUBLIC_KEY_LEN)];
++ u8 encrypted_timestamp[noise_encrypted_len(NOISE_TIMESTAMP_LEN)];
++ struct message_macs macs;
++};
++
++struct message_handshake_response {
++ struct message_header header;
++ __le32 sender_index;
++ __le32 receiver_index;
++ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
++ u8 encrypted_nothing[noise_encrypted_len(0)];
++ struct message_macs macs;
++};
++
++struct message_handshake_cookie {
++ struct message_header header;
++ __le32 receiver_index;
++ u8 nonce[COOKIE_NONCE_LEN];
++ u8 encrypted_cookie[noise_encrypted_len(COOKIE_LEN)];
++};
++
++struct message_data {
++ struct message_header header;
++ __le32 key_idx;
++ __le64 counter;
++ u8 encrypted_data[];
++};
++
++#define message_data_len(plain_len) \
++ (noise_encrypted_len(plain_len) + sizeof(struct message_data))
++
++enum message_alignments {
++ MESSAGE_PADDING_MULTIPLE = 16,
++ MESSAGE_MINIMUM_LENGTH = message_data_len(0)
++};
++
++#define SKB_HEADER_LEN \
++ (max(sizeof(struct iphdr), sizeof(struct ipv6hdr)) + \
++ sizeof(struct udphdr) + NET_SKB_PAD)
++#define DATA_PACKET_HEAD_ROOM \
++ ALIGN(sizeof(struct message_data) + SKB_HEADER_LEN, 4)
++
++enum { HANDSHAKE_DSCP = 0x88 /* AF41, plus 00 ECN */ };
++
++#endif /* _WG_MESSAGES_H */
+--- /dev/null
++++ b/drivers/net/wireguard/netlink.c
+@@ -0,0 +1,648 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "netlink.h"
++#include "device.h"
++#include "peer.h"
++#include "socket.h"
++#include "queueing.h"
++#include "messages.h"
++
++#include <uapi/linux/wireguard.h>
++
++#include <linux/if.h>
++#include <net/genetlink.h>
++#include <net/sock.h>
++#include <crypto/algapi.h>
++
++static struct genl_family genl_family;
++
++static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = {
++ [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 },
++ [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
++ [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
++ [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
++ [WGDEVICE_A_FLAGS] = { .type = NLA_U32 },
++ [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 },
++ [WGDEVICE_A_FWMARK] = { .type = NLA_U32 },
++ [WGDEVICE_A_PEERS] = { .type = NLA_NESTED }
++};
++
++static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
++ [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
++ [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN },
++ [WGPEER_A_FLAGS] = { .type = NLA_U32 },
++ [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
++ [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
++ [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) },
++ [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
++ [WGPEER_A_TX_BYTES] = { .type = NLA_U64 },
++ [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED },
++ [WGPEER_A_PROTOCOL_VERSION] = { .type = NLA_U32 }
++};
++
++static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = {
++ [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 },
++ [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) },
++ [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }
++};
++
++static struct wg_device *lookup_interface(struct nlattr **attrs,
++ struct sk_buff *skb)
++{
++ struct net_device *dev = NULL;
++
++ if (!attrs[WGDEVICE_A_IFINDEX] == !attrs[WGDEVICE_A_IFNAME])
++ return ERR_PTR(-EBADR);
++ if (attrs[WGDEVICE_A_IFINDEX])
++ dev = dev_get_by_index(sock_net(skb->sk),
++ nla_get_u32(attrs[WGDEVICE_A_IFINDEX]));
++ else if (attrs[WGDEVICE_A_IFNAME])
++ dev = dev_get_by_name(sock_net(skb->sk),
++ nla_data(attrs[WGDEVICE_A_IFNAME]));
++ if (!dev)
++ return ERR_PTR(-ENODEV);
++ if (!dev->rtnl_link_ops || !dev->rtnl_link_ops->kind ||
++ strcmp(dev->rtnl_link_ops->kind, KBUILD_MODNAME)) {
++ dev_put(dev);
++ return ERR_PTR(-EOPNOTSUPP);
++ }
++ return netdev_priv(dev);
++}
++
++static int get_allowedips(struct sk_buff *skb, const u8 *ip, u8 cidr,
++ int family)
++{
++ struct nlattr *allowedip_nest;
++
++ allowedip_nest = nla_nest_start(skb, 0);
++ if (!allowedip_nest)
++ return -EMSGSIZE;
++
++ if (nla_put_u8(skb, WGALLOWEDIP_A_CIDR_MASK, cidr) ||
++ nla_put_u16(skb, WGALLOWEDIP_A_FAMILY, family) ||
++ nla_put(skb, WGALLOWEDIP_A_IPADDR, family == AF_INET6 ?
++ sizeof(struct in6_addr) : sizeof(struct in_addr), ip)) {
++ nla_nest_cancel(skb, allowedip_nest);
++ return -EMSGSIZE;
++ }
++
++ nla_nest_end(skb, allowedip_nest);
++ return 0;
++}
++
++struct dump_ctx {
++ struct wg_device *wg;
++ struct wg_peer *next_peer;
++ u64 allowedips_seq;
++ struct allowedips_node *next_allowedip;
++};
++
++#define DUMP_CTX(cb) ((struct dump_ctx *)(cb)->args)
++
++static int
++get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx)
++{
++
++ struct nlattr *allowedips_nest, *peer_nest = nla_nest_start(skb, 0);
++ struct allowedips_node *allowedips_node = ctx->next_allowedip;
++ bool fail;
++
++ if (!peer_nest)
++ return -EMSGSIZE;
++
++ down_read(&peer->handshake.lock);
++ fail = nla_put(skb, WGPEER_A_PUBLIC_KEY, NOISE_PUBLIC_KEY_LEN,
++ peer->handshake.remote_static);
++ up_read(&peer->handshake.lock);
++ if (fail)
++ goto err;
++
++ if (!allowedips_node) {
++ const struct __kernel_timespec last_handshake = {
++ .tv_sec = peer->walltime_last_handshake.tv_sec,
++ .tv_nsec = peer->walltime_last_handshake.tv_nsec
++ };
++
++ down_read(&peer->handshake.lock);
++ fail = nla_put(skb, WGPEER_A_PRESHARED_KEY,
++ NOISE_SYMMETRIC_KEY_LEN,
++ peer->handshake.preshared_key);
++ up_read(&peer->handshake.lock);
++ if (fail)
++ goto err;
++
++ if (nla_put(skb, WGPEER_A_LAST_HANDSHAKE_TIME,
++ sizeof(last_handshake), &last_handshake) ||
++ nla_put_u16(skb, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL,
++ peer->persistent_keepalive_interval) ||
++ nla_put_u64_64bit(skb, WGPEER_A_TX_BYTES, peer->tx_bytes,
++ WGPEER_A_UNSPEC) ||
++ nla_put_u64_64bit(skb, WGPEER_A_RX_BYTES, peer->rx_bytes,
++ WGPEER_A_UNSPEC) ||
++ nla_put_u32(skb, WGPEER_A_PROTOCOL_VERSION, 1))
++ goto err;
++
++ read_lock_bh(&peer->endpoint_lock);
++ if (peer->endpoint.addr.sa_family == AF_INET)
++ fail = nla_put(skb, WGPEER_A_ENDPOINT,
++ sizeof(peer->endpoint.addr4),
++ &peer->endpoint.addr4);
++ else if (peer->endpoint.addr.sa_family == AF_INET6)
++ fail = nla_put(skb, WGPEER_A_ENDPOINT,
++ sizeof(peer->endpoint.addr6),
++ &peer->endpoint.addr6);
++ read_unlock_bh(&peer->endpoint_lock);
++ if (fail)
++ goto err;
++ allowedips_node =
++ list_first_entry_or_null(&peer->allowedips_list,
++ struct allowedips_node, peer_list);
++ }
++ if (!allowedips_node)
++ goto no_allowedips;
++ if (!ctx->allowedips_seq)
++ ctx->allowedips_seq = peer->device->peer_allowedips.seq;
++ else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq)
++ goto no_allowedips;
++
++ allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS);
++ if (!allowedips_nest)
++ goto err;
++
++ list_for_each_entry_from(allowedips_node, &peer->allowedips_list,
++ peer_list) {
++ u8 cidr, ip[16] __aligned(__alignof(u64));
++ int family;
++
++ family = wg_allowedips_read_node(allowedips_node, ip, &cidr);
++ if (get_allowedips(skb, ip, cidr, family)) {
++ nla_nest_end(skb, allowedips_nest);
++ nla_nest_end(skb, peer_nest);
++ ctx->next_allowedip = allowedips_node;
++ return -EMSGSIZE;
++ }
++ }
++ nla_nest_end(skb, allowedips_nest);
++no_allowedips:
++ nla_nest_end(skb, peer_nest);
++ ctx->next_allowedip = NULL;
++ ctx->allowedips_seq = 0;
++ return 0;
++err:
++ nla_nest_cancel(skb, peer_nest);
++ return -EMSGSIZE;
++}
++
++static int wg_get_device_start(struct netlink_callback *cb)
++{
++ struct nlattr **attrs = genl_family_attrbuf(&genl_family);
++ struct wg_device *wg;
++ int ret;
++
++ ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + genl_family.hdrsize, attrs,
++ genl_family.maxattr, device_policy, NULL);
++ if (ret < 0)
++ return ret;
++ wg = lookup_interface(attrs, cb->skb);
++ if (IS_ERR(wg))
++ return PTR_ERR(wg);
++ DUMP_CTX(cb)->wg = wg;
++ return 0;
++}
++
++static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb)
++{
++ struct wg_peer *peer, *next_peer_cursor;
++ struct dump_ctx *ctx = DUMP_CTX(cb);
++ struct wg_device *wg = ctx->wg;
++ struct nlattr *peers_nest;
++ int ret = -EMSGSIZE;
++ bool done = true;
++ void *hdr;
++
++ rtnl_lock();
++ mutex_lock(&wg->device_update_lock);
++ cb->seq = wg->device_update_gen;
++ next_peer_cursor = ctx->next_peer;
++
++ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
++ &genl_family, NLM_F_MULTI, WG_CMD_GET_DEVICE);
++ if (!hdr)
++ goto out;
++ genl_dump_check_consistent(cb, hdr);
++
++ if (!ctx->next_peer) {
++ if (nla_put_u16(skb, WGDEVICE_A_LISTEN_PORT,
++ wg->incoming_port) ||
++ nla_put_u32(skb, WGDEVICE_A_FWMARK, wg->fwmark) ||
++ nla_put_u32(skb, WGDEVICE_A_IFINDEX, wg->dev->ifindex) ||
++ nla_put_string(skb, WGDEVICE_A_IFNAME, wg->dev->name))
++ goto out;
++
++ down_read(&wg->static_identity.lock);
++ if (wg->static_identity.has_identity) {
++ if (nla_put(skb, WGDEVICE_A_PRIVATE_KEY,
++ NOISE_PUBLIC_KEY_LEN,
++ wg->static_identity.static_private) ||
++ nla_put(skb, WGDEVICE_A_PUBLIC_KEY,
++ NOISE_PUBLIC_KEY_LEN,
++ wg->static_identity.static_public)) {
++ up_read(&wg->static_identity.lock);
++ goto out;
++ }
++ }
++ up_read(&wg->static_identity.lock);
++ }
++
++ peers_nest = nla_nest_start(skb, WGDEVICE_A_PEERS);
++ if (!peers_nest)
++ goto out;
++ ret = 0;
++ /* If the last cursor was removed via list_del_init in peer_remove, then
++ * we just treat this the same as there being no more peers left. The
++ * reason is that seq_nr should indicate to userspace that this isn't a
++ * coherent dump anyway, so they'll try again.
++ */
++ if (list_empty(&wg->peer_list) ||
++ (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) {
++ nla_nest_cancel(skb, peers_nest);
++ goto out;
++ }
++ lockdep_assert_held(&wg->device_update_lock);
++ peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list);
++ list_for_each_entry_continue(peer, &wg->peer_list, peer_list) {
++ if (get_peer(peer, skb, ctx)) {
++ done = false;
++ break;
++ }
++ next_peer_cursor = peer;
++ }
++ nla_nest_end(skb, peers_nest);
++
++out:
++ if (!ret && !done && next_peer_cursor)
++ wg_peer_get(next_peer_cursor);
++ wg_peer_put(ctx->next_peer);
++ mutex_unlock(&wg->device_update_lock);
++ rtnl_unlock();
++
++ if (ret) {
++ genlmsg_cancel(skb, hdr);
++ return ret;
++ }
++ genlmsg_end(skb, hdr);
++ if (done) {
++ ctx->next_peer = NULL;
++ return 0;
++ }
++ ctx->next_peer = next_peer_cursor;
++ return skb->len;
++
++ /* At this point, we can't really deal ourselves with safely zeroing out
++ * the private key material after usage. This will need an additional API
++ * in the kernel for marking skbs as zero_on_free.
++ */
++}
++
++static int wg_get_device_done(struct netlink_callback *cb)
++{
++ struct dump_ctx *ctx = DUMP_CTX(cb);
++
++ if (ctx->wg)
++ dev_put(ctx->wg->dev);
++ wg_peer_put(ctx->next_peer);
++ return 0;
++}
++
++static int set_port(struct wg_device *wg, u16 port)
++{
++ struct wg_peer *peer;
++
++ if (wg->incoming_port == port)
++ return 0;
++ list_for_each_entry(peer, &wg->peer_list, peer_list)
++ wg_socket_clear_peer_endpoint_src(peer);
++ if (!netif_running(wg->dev)) {
++ wg->incoming_port = port;
++ return 0;
++ }
++ return wg_socket_init(wg, port);
++}
++
++static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs)
++{
++ int ret = -EINVAL;
++ u16 family;
++ u8 cidr;
++
++ if (!attrs[WGALLOWEDIP_A_FAMILY] || !attrs[WGALLOWEDIP_A_IPADDR] ||
++ !attrs[WGALLOWEDIP_A_CIDR_MASK])
++ return ret;
++ family = nla_get_u16(attrs[WGALLOWEDIP_A_FAMILY]);
++ cidr = nla_get_u8(attrs[WGALLOWEDIP_A_CIDR_MASK]);
++
++ if (family == AF_INET && cidr <= 32 &&
++ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr))
++ ret = wg_allowedips_insert_v4(
++ &peer->device->peer_allowedips,
++ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer,
++ &peer->device->device_update_lock);
++ else if (family == AF_INET6 && cidr <= 128 &&
++ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr))
++ ret = wg_allowedips_insert_v6(
++ &peer->device->peer_allowedips,
++ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer,
++ &peer->device->device_update_lock);
++
++ return ret;
++}
++
++static int set_peer(struct wg_device *wg, struct nlattr **attrs)
++{
++ u8 *public_key = NULL, *preshared_key = NULL;
++ struct wg_peer *peer = NULL;
++ u32 flags = 0;
++ int ret;
++
++ ret = -EINVAL;
++ if (attrs[WGPEER_A_PUBLIC_KEY] &&
++ nla_len(attrs[WGPEER_A_PUBLIC_KEY]) == NOISE_PUBLIC_KEY_LEN)
++ public_key = nla_data(attrs[WGPEER_A_PUBLIC_KEY]);
++ else
++ goto out;
++ if (attrs[WGPEER_A_PRESHARED_KEY] &&
++ nla_len(attrs[WGPEER_A_PRESHARED_KEY]) == NOISE_SYMMETRIC_KEY_LEN)
++ preshared_key = nla_data(attrs[WGPEER_A_PRESHARED_KEY]);
++
++ if (attrs[WGPEER_A_FLAGS])
++ flags = nla_get_u32(attrs[WGPEER_A_FLAGS]);
++ ret = -EOPNOTSUPP;
++ if (flags & ~__WGPEER_F_ALL)
++ goto out;
++
++ ret = -EPFNOSUPPORT;
++ if (attrs[WGPEER_A_PROTOCOL_VERSION]) {
++ if (nla_get_u32(attrs[WGPEER_A_PROTOCOL_VERSION]) != 1)
++ goto out;
++ }
++
++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable,
++ nla_data(attrs[WGPEER_A_PUBLIC_KEY]));
++ ret = 0;
++ if (!peer) { /* Peer doesn't exist yet. Add a new one. */
++ if (flags & (WGPEER_F_REMOVE_ME | WGPEER_F_UPDATE_ONLY))
++ goto out;
++
++ /* The peer is new, so there aren't allowed IPs to remove. */
++ flags &= ~WGPEER_F_REPLACE_ALLOWEDIPS;
++
++ down_read(&wg->static_identity.lock);
++ if (wg->static_identity.has_identity &&
++ !memcmp(nla_data(attrs[WGPEER_A_PUBLIC_KEY]),
++ wg->static_identity.static_public,
++ NOISE_PUBLIC_KEY_LEN)) {
++ /* We silently ignore peers that have the same public
++ * key as the device. The reason we do it silently is
++ * that we'd like for people to be able to reuse the
++ * same set of API calls across peers.
++ */
++ up_read(&wg->static_identity.lock);
++ ret = 0;
++ goto out;
++ }
++ up_read(&wg->static_identity.lock);
++
++ peer = wg_peer_create(wg, public_key, preshared_key);
++ if (IS_ERR(peer)) {
++ /* Similar to the above, if the key is invalid, we skip
++ * it without fanfare, so that services don't need to
++ * worry about doing key validation themselves.
++ */
++ ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer);
++ peer = NULL;
++ goto out;
++ }
++ /* Take additional reference, as though we've just been
++ * looked up.
++ */
++ wg_peer_get(peer);
++ }
++
++ if (flags & WGPEER_F_REMOVE_ME) {
++ wg_peer_remove(peer);
++ goto out;
++ }
++
++ if (preshared_key) {
++ down_write(&peer->handshake.lock);
++ memcpy(&peer->handshake.preshared_key, preshared_key,
++ NOISE_SYMMETRIC_KEY_LEN);
++ up_write(&peer->handshake.lock);
++ }
++
++ if (attrs[WGPEER_A_ENDPOINT]) {
++ struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]);
++ size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]);
++
++ if ((len == sizeof(struct sockaddr_in) &&
++ addr->sa_family == AF_INET) ||
++ (len == sizeof(struct sockaddr_in6) &&
++ addr->sa_family == AF_INET6)) {
++ struct endpoint endpoint = { { { 0 } } };
++
++ memcpy(&endpoint.addr, addr, len);
++ wg_socket_set_peer_endpoint(peer, &endpoint);
++ }
++ }
++
++ if (flags & WGPEER_F_REPLACE_ALLOWEDIPS)
++ wg_allowedips_remove_by_peer(&wg->peer_allowedips, peer,
++ &wg->device_update_lock);
++
++ if (attrs[WGPEER_A_ALLOWEDIPS]) {
++ struct nlattr *attr, *allowedip[WGALLOWEDIP_A_MAX + 1];
++ int rem;
++
++ nla_for_each_nested(attr, attrs[WGPEER_A_ALLOWEDIPS], rem) {
++ ret = nla_parse_nested(allowedip, WGALLOWEDIP_A_MAX,
++ attr, allowedip_policy, NULL);
++ if (ret < 0)
++ goto out;
++ ret = set_allowedip(peer, allowedip);
++ if (ret < 0)
++ goto out;
++ }
++ }
++
++ if (attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]) {
++ const u16 persistent_keepalive_interval = nla_get_u16(
++ attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]);
++ const bool send_keepalive =
++ !peer->persistent_keepalive_interval &&
++ persistent_keepalive_interval &&
++ netif_running(wg->dev);
++
++ peer->persistent_keepalive_interval = persistent_keepalive_interval;
++ if (send_keepalive)
++ wg_packet_send_keepalive(peer);
++ }
++
++ if (netif_running(wg->dev))
++ wg_packet_send_staged_packets(peer);
++
++out:
++ wg_peer_put(peer);
++ if (attrs[WGPEER_A_PRESHARED_KEY])
++ memzero_explicit(nla_data(attrs[WGPEER_A_PRESHARED_KEY]),
++ nla_len(attrs[WGPEER_A_PRESHARED_KEY]));
++ return ret;
++}
++
++static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
++{
++ struct wg_device *wg = lookup_interface(info->attrs, skb);
++ u32 flags = 0;
++ int ret;
++
++ if (IS_ERR(wg)) {
++ ret = PTR_ERR(wg);
++ goto out_nodev;
++ }
++
++ rtnl_lock();
++ mutex_lock(&wg->device_update_lock);
++
++ if (info->attrs[WGDEVICE_A_FLAGS])
++ flags = nla_get_u32(info->attrs[WGDEVICE_A_FLAGS]);
++ ret = -EOPNOTSUPP;
++ if (flags & ~__WGDEVICE_F_ALL)
++ goto out;
++
++ ret = -EPERM;
++ if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
++ info->attrs[WGDEVICE_A_FWMARK]) &&
++ !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
++ goto out;
++
++ ++wg->device_update_gen;
++
++ if (info->attrs[WGDEVICE_A_FWMARK]) {
++ struct wg_peer *peer;
++
++ wg->fwmark = nla_get_u32(info->attrs[WGDEVICE_A_FWMARK]);
++ list_for_each_entry(peer, &wg->peer_list, peer_list)
++ wg_socket_clear_peer_endpoint_src(peer);
++ }
++
++ if (info->attrs[WGDEVICE_A_LISTEN_PORT]) {
++ ret = set_port(wg,
++ nla_get_u16(info->attrs[WGDEVICE_A_LISTEN_PORT]));
++ if (ret)
++ goto out;
++ }
++
++ if (flags & WGDEVICE_F_REPLACE_PEERS)
++ wg_peer_remove_all(wg);
++
++ if (info->attrs[WGDEVICE_A_PRIVATE_KEY] &&
++ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY]) ==
++ NOISE_PUBLIC_KEY_LEN) {
++ u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]);
++ u8 public_key[NOISE_PUBLIC_KEY_LEN];
++ struct wg_peer *peer, *temp;
++
++ if (!crypto_memneq(wg->static_identity.static_private,
++ private_key, NOISE_PUBLIC_KEY_LEN))
++ goto skip_set_private_key;
++
++ /* We remove before setting, to prevent race, which means doing
++ * two 25519-genpub ops.
++ */
++ if (curve25519_generate_public(public_key, private_key)) {
++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable,
++ public_key);
++ if (peer) {
++ wg_peer_put(peer);
++ wg_peer_remove(peer);
++ }
++ }
++
++ down_write(&wg->static_identity.lock);
++ wg_noise_set_static_identity_private_key(&wg->static_identity,
++ private_key);
++ list_for_each_entry_safe(peer, temp, &wg->peer_list,
++ peer_list) {
++ if (wg_noise_precompute_static_static(peer))
++ wg_noise_expire_current_peer_keypairs(peer);
++ else
++ wg_peer_remove(peer);
++ }
++ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
++ up_write(&wg->static_identity.lock);
++ }
++skip_set_private_key:
++
++ if (info->attrs[WGDEVICE_A_PEERS]) {
++ struct nlattr *attr, *peer[WGPEER_A_MAX + 1];
++ int rem;
++
++ nla_for_each_nested(attr, info->attrs[WGDEVICE_A_PEERS], rem) {
++ ret = nla_parse_nested(peer, WGPEER_A_MAX, attr,
++ peer_policy, NULL);
++ if (ret < 0)
++ goto out;
++ ret = set_peer(wg, peer);
++ if (ret < 0)
++ goto out;
++ }
++ }
++ ret = 0;
++
++out:
++ mutex_unlock(&wg->device_update_lock);
++ rtnl_unlock();
++ dev_put(wg->dev);
++out_nodev:
++ if (info->attrs[WGDEVICE_A_PRIVATE_KEY])
++ memzero_explicit(nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]),
++ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY]));
++ return ret;
++}
++
++static const struct genl_ops genl_ops[] = {
++ {
++ .cmd = WG_CMD_GET_DEVICE,
++ .start = wg_get_device_start,
++ .dumpit = wg_get_device_dump,
++ .done = wg_get_device_done,
++ .flags = GENL_UNS_ADMIN_PERM
++ }, {
++ .cmd = WG_CMD_SET_DEVICE,
++ .doit = wg_set_device,
++ .flags = GENL_UNS_ADMIN_PERM
++ }
++};
++
++static struct genl_family genl_family __ro_after_init = {
++ .ops = genl_ops,
++ .n_ops = ARRAY_SIZE(genl_ops),
++ .name = WG_GENL_NAME,
++ .version = WG_GENL_VERSION,
++ .maxattr = WGDEVICE_A_MAX,
++ .module = THIS_MODULE,
++ .policy = device_policy,
++ .netnsok = true
++};
++
++int __init wg_genetlink_init(void)
++{
++ return genl_register_family(&genl_family);
++}
++
++void __exit wg_genetlink_uninit(void)
++{
++ genl_unregister_family(&genl_family);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/netlink.h
+@@ -0,0 +1,12 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_NETLINK_H
++#define _WG_NETLINK_H
++
++int wg_genetlink_init(void);
++void wg_genetlink_uninit(void);
++
++#endif /* _WG_NETLINK_H */
+--- /dev/null
++++ b/drivers/net/wireguard/noise.c
+@@ -0,0 +1,828 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "noise.h"
++#include "device.h"
++#include "peer.h"
++#include "messages.h"
++#include "queueing.h"
++#include "peerlookup.h"
++
++#include <linux/rcupdate.h>
++#include <linux/slab.h>
++#include <linux/bitmap.h>
++#include <linux/scatterlist.h>
++#include <linux/highmem.h>
++#include <crypto/algapi.h>
++
++/* This implements Noise_IKpsk2:
++ *
++ * <- s
++ * ******
++ * -> e, es, s, ss, {t}
++ * <- e, ee, se, psk, {}
++ */
++
++static const u8 handshake_name[37] = "Noise_IKpsk2_25519_ChaChaPoly_BLAKE2s";
++static const u8 identifier_name[34] = "WireGuard v1 zx2c4 Jason@zx2c4.com";
++static u8 handshake_init_hash[NOISE_HASH_LEN] __ro_after_init;
++static u8 handshake_init_chaining_key[NOISE_HASH_LEN] __ro_after_init;
++static atomic64_t keypair_counter = ATOMIC64_INIT(0);
++
++void __init wg_noise_init(void)
++{
++ struct blake2s_state blake;
++
++ blake2s(handshake_init_chaining_key, handshake_name, NULL,
++ NOISE_HASH_LEN, sizeof(handshake_name), 0);
++ blake2s_init(&blake, NOISE_HASH_LEN);
++ blake2s_update(&blake, handshake_init_chaining_key, NOISE_HASH_LEN);
++ blake2s_update(&blake, identifier_name, sizeof(identifier_name));
++ blake2s_final(&blake, handshake_init_hash);
++}
++
++/* Must hold peer->handshake.static_identity->lock */
++bool wg_noise_precompute_static_static(struct wg_peer *peer)
++{
++ bool ret = true;
++
++ down_write(&peer->handshake.lock);
++ if (peer->handshake.static_identity->has_identity)
++ ret = curve25519(
++ peer->handshake.precomputed_static_static,
++ peer->handshake.static_identity->static_private,
++ peer->handshake.remote_static);
++ else
++ memset(peer->handshake.precomputed_static_static, 0,
++ NOISE_PUBLIC_KEY_LEN);
++ up_write(&peer->handshake.lock);
++ return ret;
++}
++
++bool wg_noise_handshake_init(struct noise_handshake *handshake,
++ struct noise_static_identity *static_identity,
++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
++ struct wg_peer *peer)
++{
++ memset(handshake, 0, sizeof(*handshake));
++ init_rwsem(&handshake->lock);
++ handshake->entry.type = INDEX_HASHTABLE_HANDSHAKE;
++ handshake->entry.peer = peer;
++ memcpy(handshake->remote_static, peer_public_key, NOISE_PUBLIC_KEY_LEN);
++ if (peer_preshared_key)
++ memcpy(handshake->preshared_key, peer_preshared_key,
++ NOISE_SYMMETRIC_KEY_LEN);
++ handshake->static_identity = static_identity;
++ handshake->state = HANDSHAKE_ZEROED;
++ return wg_noise_precompute_static_static(peer);
++}
++
++static void handshake_zero(struct noise_handshake *handshake)
++{
++ memset(&handshake->ephemeral_private, 0, NOISE_PUBLIC_KEY_LEN);
++ memset(&handshake->remote_ephemeral, 0, NOISE_PUBLIC_KEY_LEN);
++ memset(&handshake->hash, 0, NOISE_HASH_LEN);
++ memset(&handshake->chaining_key, 0, NOISE_HASH_LEN);
++ handshake->remote_index = 0;
++ handshake->state = HANDSHAKE_ZEROED;
++}
++
++void wg_noise_handshake_clear(struct noise_handshake *handshake)
++{
++ wg_index_hashtable_remove(
++ handshake->entry.peer->device->index_hashtable,
++ &handshake->entry);
++ down_write(&handshake->lock);
++ handshake_zero(handshake);
++ up_write(&handshake->lock);
++ wg_index_hashtable_remove(
++ handshake->entry.peer->device->index_hashtable,
++ &handshake->entry);
++}
++
++static struct noise_keypair *keypair_create(struct wg_peer *peer)
++{
++ struct noise_keypair *keypair = kzalloc(sizeof(*keypair), GFP_KERNEL);
++
++ if (unlikely(!keypair))
++ return NULL;
++ keypair->internal_id = atomic64_inc_return(&keypair_counter);
++ keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
++ keypair->entry.peer = peer;
++ kref_init(&keypair->refcount);
++ return keypair;
++}
++
++static void keypair_free_rcu(struct rcu_head *rcu)
++{
++ kzfree(container_of(rcu, struct noise_keypair, rcu));
++}
++
++static void keypair_free_kref(struct kref *kref)
++{
++ struct noise_keypair *keypair =
++ container_of(kref, struct noise_keypair, refcount);
++
++ net_dbg_ratelimited("%s: Keypair %llu destroyed for peer %llu\n",
++ keypair->entry.peer->device->dev->name,
++ keypair->internal_id,
++ keypair->entry.peer->internal_id);
++ wg_index_hashtable_remove(keypair->entry.peer->device->index_hashtable,
++ &keypair->entry);
++ call_rcu(&keypair->rcu, keypair_free_rcu);
++}
++
++void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now)
++{
++ if (unlikely(!keypair))
++ return;
++ if (unlikely(unreference_now))
++ wg_index_hashtable_remove(
++ keypair->entry.peer->device->index_hashtable,
++ &keypair->entry);
++ kref_put(&keypair->refcount, keypair_free_kref);
++}
++
++struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair)
++{
++ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(),
++ "Taking noise keypair reference without holding the RCU BH read lock");
++ if (unlikely(!keypair || !kref_get_unless_zero(&keypair->refcount)))
++ return NULL;
++ return keypair;
++}
++
++void wg_noise_keypairs_clear(struct noise_keypairs *keypairs)
++{
++ struct noise_keypair *old;
++
++ spin_lock_bh(&keypairs->keypair_update_lock);
++
++ /* We zero the next_keypair before zeroing the others, so that
++ * wg_noise_received_with_keypair returns early before subsequent ones
++ * are zeroed.
++ */
++ old = rcu_dereference_protected(keypairs->next_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
++ wg_noise_keypair_put(old, true);
++
++ old = rcu_dereference_protected(keypairs->previous_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
++ wg_noise_keypair_put(old, true);
++
++ old = rcu_dereference_protected(keypairs->current_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ RCU_INIT_POINTER(keypairs->current_keypair, NULL);
++ wg_noise_keypair_put(old, true);
++
++ spin_unlock_bh(&keypairs->keypair_update_lock);
++}
++
++void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer)
++{
++ struct noise_keypair *keypair;
++
++ wg_noise_handshake_clear(&peer->handshake);
++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
++
++ spin_lock_bh(&peer->keypairs.keypair_update_lock);
++ keypair = rcu_dereference_protected(peer->keypairs.next_keypair,
++ lockdep_is_held(&peer->keypairs.keypair_update_lock));
++ if (keypair)
++ keypair->sending.is_valid = false;
++ keypair = rcu_dereference_protected(peer->keypairs.current_keypair,
++ lockdep_is_held(&peer->keypairs.keypair_update_lock));
++ if (keypair)
++ keypair->sending.is_valid = false;
++ spin_unlock_bh(&peer->keypairs.keypair_update_lock);
++}
++
++static void add_new_keypair(struct noise_keypairs *keypairs,
++ struct noise_keypair *new_keypair)
++{
++ struct noise_keypair *previous_keypair, *next_keypair, *current_keypair;
++
++ spin_lock_bh(&keypairs->keypair_update_lock);
++ previous_keypair = rcu_dereference_protected(keypairs->previous_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ next_keypair = rcu_dereference_protected(keypairs->next_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ current_keypair = rcu_dereference_protected(keypairs->current_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ if (new_keypair->i_am_the_initiator) {
++ /* If we're the initiator, it means we've sent a handshake, and
++ * received a confirmation response, which means this new
++ * keypair can now be used.
++ */
++ if (next_keypair) {
++ /* If there already was a next keypair pending, we
++ * demote it to be the previous keypair, and free the
++ * existing current. Note that this means KCI can result
++ * in this transition. It would perhaps be more sound to
++ * always just get rid of the unused next keypair
++ * instead of putting it in the previous slot, but this
++ * might be a bit less robust. Something to think about
++ * for the future.
++ */
++ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
++ rcu_assign_pointer(keypairs->previous_keypair,
++ next_keypair);
++ wg_noise_keypair_put(current_keypair, true);
++ } else /* If there wasn't an existing next keypair, we replace
++ * the previous with the current one.
++ */
++ rcu_assign_pointer(keypairs->previous_keypair,
++ current_keypair);
++ /* At this point we can get rid of the old previous keypair, and
++ * set up the new keypair.
++ */
++ wg_noise_keypair_put(previous_keypair, true);
++ rcu_assign_pointer(keypairs->current_keypair, new_keypair);
++ } else {
++ /* If we're the responder, it means we can't use the new keypair
++ * until we receive confirmation via the first data packet, so
++ * we get rid of the existing previous one, the possibly
++ * existing next one, and slide in the new next one.
++ */
++ rcu_assign_pointer(keypairs->next_keypair, new_keypair);
++ wg_noise_keypair_put(next_keypair, true);
++ RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
++ wg_noise_keypair_put(previous_keypair, true);
++ }
++ spin_unlock_bh(&keypairs->keypair_update_lock);
++}
++
++bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs,
++ struct noise_keypair *received_keypair)
++{
++ struct noise_keypair *old_keypair;
++ bool key_is_new;
++
++ /* We first check without taking the spinlock. */
++ key_is_new = received_keypair ==
++ rcu_access_pointer(keypairs->next_keypair);
++ if (likely(!key_is_new))
++ return false;
++
++ spin_lock_bh(&keypairs->keypair_update_lock);
++ /* After locking, we double check that things didn't change from
++ * beneath us.
++ */
++ if (unlikely(received_keypair !=
++ rcu_dereference_protected(keypairs->next_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock)))) {
++ spin_unlock_bh(&keypairs->keypair_update_lock);
++ return false;
++ }
++
++ /* When we've finally received the confirmation, we slide the next
++ * into the current, the current into the previous, and get rid of
++ * the old previous.
++ */
++ old_keypair = rcu_dereference_protected(keypairs->previous_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock));
++ rcu_assign_pointer(keypairs->previous_keypair,
++ rcu_dereference_protected(keypairs->current_keypair,
++ lockdep_is_held(&keypairs->keypair_update_lock)));
++ wg_noise_keypair_put(old_keypair, true);
++ rcu_assign_pointer(keypairs->current_keypair, received_keypair);
++ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
++
++ spin_unlock_bh(&keypairs->keypair_update_lock);
++ return true;
++}
++
++/* Must hold static_identity->lock */
++void wg_noise_set_static_identity_private_key(
++ struct noise_static_identity *static_identity,
++ const u8 private_key[NOISE_PUBLIC_KEY_LEN])
++{
++ memcpy(static_identity->static_private, private_key,
++ NOISE_PUBLIC_KEY_LEN);
++ curve25519_clamp_secret(static_identity->static_private);
++ static_identity->has_identity = curve25519_generate_public(
++ static_identity->static_public, private_key);
++}
++
++/* This is Hugo Krawczyk's HKDF:
++ * - https://eprint.iacr.org/2010/264.pdf
++ * - https://tools.ietf.org/html/rfc5869
++ */
++static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
++ size_t first_len, size_t second_len, size_t third_len,
++ size_t data_len, const u8 chaining_key[NOISE_HASH_LEN])
++{
++ u8 output[BLAKE2S_HASH_SIZE + 1];
++ u8 secret[BLAKE2S_HASH_SIZE];
++
++ WARN_ON(IS_ENABLED(DEBUG) &&
++ (first_len > BLAKE2S_HASH_SIZE ||
++ second_len > BLAKE2S_HASH_SIZE ||
++ third_len > BLAKE2S_HASH_SIZE ||
++ ((second_len || second_dst || third_len || third_dst) &&
++ (!first_len || !first_dst)) ||
++ ((third_len || third_dst) && (!second_len || !second_dst))));
++
++ /* Extract entropy from data into secret */
++ blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN);
++
++ if (!first_dst || !first_len)
++ goto out;
++
++ /* Expand first key: key = secret, data = 0x1 */
++ output[0] = 1;
++ blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE);
++ memcpy(first_dst, output, first_len);
++
++ if (!second_dst || !second_len)
++ goto out;
++
++ /* Expand second key: key = secret, data = first-key || 0x2 */
++ output[BLAKE2S_HASH_SIZE] = 2;
++ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
++ BLAKE2S_HASH_SIZE);
++ memcpy(second_dst, output, second_len);
++
++ if (!third_dst || !third_len)
++ goto out;
++
++ /* Expand third key: key = secret, data = second-key || 0x3 */
++ output[BLAKE2S_HASH_SIZE] = 3;
++ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
++ BLAKE2S_HASH_SIZE);
++ memcpy(third_dst, output, third_len);
++
++out:
++ /* Clear sensitive data from stack */
++ memzero_explicit(secret, BLAKE2S_HASH_SIZE);
++ memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
++}
++
++static void symmetric_key_init(struct noise_symmetric_key *key)
++{
++ spin_lock_init(&key->counter.receive.lock);
++ atomic64_set(&key->counter.counter, 0);
++ memset(key->counter.receive.backtrack, 0,
++ sizeof(key->counter.receive.backtrack));
++ key->birthdate = ktime_get_coarse_boottime_ns();
++ key->is_valid = true;
++}
++
++static void derive_keys(struct noise_symmetric_key *first_dst,
++ struct noise_symmetric_key *second_dst,
++ const u8 chaining_key[NOISE_HASH_LEN])
++{
++ kdf(first_dst->key, second_dst->key, NULL, NULL,
++ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
++ chaining_key);
++ symmetric_key_init(first_dst);
++ symmetric_key_init(second_dst);
++}
++
++static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
++ u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ const u8 private[NOISE_PUBLIC_KEY_LEN],
++ const u8 public[NOISE_PUBLIC_KEY_LEN])
++{
++ u8 dh_calculation[NOISE_PUBLIC_KEY_LEN];
++
++ if (unlikely(!curve25519(dh_calculation, private, public)))
++ return false;
++ kdf(chaining_key, key, NULL, dh_calculation, NOISE_HASH_LEN,
++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key);
++ memzero_explicit(dh_calculation, NOISE_PUBLIC_KEY_LEN);
++ return true;
++}
++
++static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len)
++{
++ struct blake2s_state blake;
++
++ blake2s_init(&blake, NOISE_HASH_LEN);
++ blake2s_update(&blake, hash, NOISE_HASH_LEN);
++ blake2s_update(&blake, src, src_len);
++ blake2s_final(&blake, hash);
++}
++
++static void mix_psk(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN],
++ u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ const u8 psk[NOISE_SYMMETRIC_KEY_LEN])
++{
++ u8 temp_hash[NOISE_HASH_LEN];
++
++ kdf(chaining_key, temp_hash, key, psk, NOISE_HASH_LEN, NOISE_HASH_LEN,
++ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, chaining_key);
++ mix_hash(hash, temp_hash, NOISE_HASH_LEN);
++ memzero_explicit(temp_hash, NOISE_HASH_LEN);
++}
++
++static void handshake_init(u8 chaining_key[NOISE_HASH_LEN],
++ u8 hash[NOISE_HASH_LEN],
++ const u8 remote_static[NOISE_PUBLIC_KEY_LEN])
++{
++ memcpy(hash, handshake_init_hash, NOISE_HASH_LEN);
++ memcpy(chaining_key, handshake_init_chaining_key, NOISE_HASH_LEN);
++ mix_hash(hash, remote_static, NOISE_PUBLIC_KEY_LEN);
++}
++
++static void message_encrypt(u8 *dst_ciphertext, const u8 *src_plaintext,
++ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ u8 hash[NOISE_HASH_LEN])
++{
++ chacha20poly1305_encrypt(dst_ciphertext, src_plaintext, src_len, hash,
++ NOISE_HASH_LEN,
++ 0 /* Always zero for Noise_IK */, key);
++ mix_hash(hash, dst_ciphertext, noise_encrypted_len(src_len));
++}
++
++static bool message_decrypt(u8 *dst_plaintext, const u8 *src_ciphertext,
++ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ u8 hash[NOISE_HASH_LEN])
++{
++ if (!chacha20poly1305_decrypt(dst_plaintext, src_ciphertext, src_len,
++ hash, NOISE_HASH_LEN,
++ 0 /* Always zero for Noise_IK */, key))
++ return false;
++ mix_hash(hash, src_ciphertext, src_len);
++ return true;
++}
++
++static void message_ephemeral(u8 ephemeral_dst[NOISE_PUBLIC_KEY_LEN],
++ const u8 ephemeral_src[NOISE_PUBLIC_KEY_LEN],
++ u8 chaining_key[NOISE_HASH_LEN],
++ u8 hash[NOISE_HASH_LEN])
++{
++ if (ephemeral_dst != ephemeral_src)
++ memcpy(ephemeral_dst, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
++ mix_hash(hash, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
++ kdf(chaining_key, NULL, NULL, ephemeral_src, NOISE_HASH_LEN, 0, 0,
++ NOISE_PUBLIC_KEY_LEN, chaining_key);
++}
++
++static void tai64n_now(u8 output[NOISE_TIMESTAMP_LEN])
++{
++ struct timespec64 now;
++
++ ktime_get_real_ts64(&now);
++
++ /* In order to prevent some sort of infoleak from precise timers, we
++ * round down the nanoseconds part to the closest rounded-down power of
++ * two to the maximum initiations per second allowed anyway by the
++ * implementation.
++ */
++ now.tv_nsec = ALIGN_DOWN(now.tv_nsec,
++ rounddown_pow_of_two(NSEC_PER_SEC / INITIATIONS_PER_SECOND));
++
++ /* https://cr.yp.to/libtai/tai64.html */
++ *(__be64 *)output = cpu_to_be64(0x400000000000000aULL + now.tv_sec);
++ *(__be32 *)(output + sizeof(__be64)) = cpu_to_be32(now.tv_nsec);
++}
++
++bool
++wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
++ struct noise_handshake *handshake)
++{
++ u8 timestamp[NOISE_TIMESTAMP_LEN];
++ u8 key[NOISE_SYMMETRIC_KEY_LEN];
++ bool ret = false;
++
++ /* We need to wait for crng _before_ taking any locks, since
++ * curve25519_generate_secret uses get_random_bytes_wait.
++ */
++ wait_for_random_bytes();
++
++ down_read(&handshake->static_identity->lock);
++ down_write(&handshake->lock);
++
++ if (unlikely(!handshake->static_identity->has_identity))
++ goto out;
++
++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION);
++
++ handshake_init(handshake->chaining_key, handshake->hash,
++ handshake->remote_static);
++
++ /* e */
++ curve25519_generate_secret(handshake->ephemeral_private);
++ if (!curve25519_generate_public(dst->unencrypted_ephemeral,
++ handshake->ephemeral_private))
++ goto out;
++ message_ephemeral(dst->unencrypted_ephemeral,
++ dst->unencrypted_ephemeral, handshake->chaining_key,
++ handshake->hash);
++
++ /* es */
++ if (!mix_dh(handshake->chaining_key, key, handshake->ephemeral_private,
++ handshake->remote_static))
++ goto out;
++
++ /* s */
++ message_encrypt(dst->encrypted_static,
++ handshake->static_identity->static_public,
++ NOISE_PUBLIC_KEY_LEN, key, handshake->hash);
++
++ /* ss */
++ kdf(handshake->chaining_key, key, NULL,
++ handshake->precomputed_static_static, NOISE_HASH_LEN,
++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
++ handshake->chaining_key);
++
++ /* {t} */
++ tai64n_now(timestamp);
++ message_encrypt(dst->encrypted_timestamp, timestamp,
++ NOISE_TIMESTAMP_LEN, key, handshake->hash);
++
++ dst->sender_index = wg_index_hashtable_insert(
++ handshake->entry.peer->device->index_hashtable,
++ &handshake->entry);
++
++ handshake->state = HANDSHAKE_CREATED_INITIATION;
++ ret = true;
++
++out:
++ up_write(&handshake->lock);
++ up_read(&handshake->static_identity->lock);
++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
++ return ret;
++}
++
++struct wg_peer *
++wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
++ struct wg_device *wg)
++{
++ struct wg_peer *peer = NULL, *ret_peer = NULL;
++ struct noise_handshake *handshake;
++ bool replay_attack, flood_attack;
++ u8 key[NOISE_SYMMETRIC_KEY_LEN];
++ u8 chaining_key[NOISE_HASH_LEN];
++ u8 hash[NOISE_HASH_LEN];
++ u8 s[NOISE_PUBLIC_KEY_LEN];
++ u8 e[NOISE_PUBLIC_KEY_LEN];
++ u8 t[NOISE_TIMESTAMP_LEN];
++ u64 initiation_consumption;
++
++ down_read(&wg->static_identity.lock);
++ if (unlikely(!wg->static_identity.has_identity))
++ goto out;
++
++ handshake_init(chaining_key, hash, wg->static_identity.static_public);
++
++ /* e */
++ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
++
++ /* es */
++ if (!mix_dh(chaining_key, key, wg->static_identity.static_private, e))
++ goto out;
++
++ /* s */
++ if (!message_decrypt(s, src->encrypted_static,
++ sizeof(src->encrypted_static), key, hash))
++ goto out;
++
++ /* Lookup which peer we're actually talking to */
++ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, s);
++ if (!peer)
++ goto out;
++ handshake = &peer->handshake;
++
++ /* ss */
++ kdf(chaining_key, key, NULL, handshake->precomputed_static_static,
++ NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
++ chaining_key);
++
++ /* {t} */
++ if (!message_decrypt(t, src->encrypted_timestamp,
++ sizeof(src->encrypted_timestamp), key, hash))
++ goto out;
++
++ down_read(&handshake->lock);
++ replay_attack = memcmp(t, handshake->latest_timestamp,
++ NOISE_TIMESTAMP_LEN) <= 0;
++ flood_attack = (s64)handshake->last_initiation_consumption +
++ NSEC_PER_SEC / INITIATIONS_PER_SECOND >
++ (s64)ktime_get_coarse_boottime_ns();
++ up_read(&handshake->lock);
++ if (replay_attack || flood_attack)
++ goto out;
++
++ /* Success! Copy everything to peer */
++ down_write(&handshake->lock);
++ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
++ if (memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) > 0)
++ memcpy(handshake->latest_timestamp, t, NOISE_TIMESTAMP_LEN);
++ memcpy(handshake->hash, hash, NOISE_HASH_LEN);
++ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
++ handshake->remote_index = src->sender_index;
++ if ((s64)(handshake->last_initiation_consumption -
++ (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
++ handshake->last_initiation_consumption = initiation_consumption;
++ handshake->state = HANDSHAKE_CONSUMED_INITIATION;
++ up_write(&handshake->lock);
++ ret_peer = peer;
++
++out:
++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
++ memzero_explicit(hash, NOISE_HASH_LEN);
++ memzero_explicit(chaining_key, NOISE_HASH_LEN);
++ up_read(&wg->static_identity.lock);
++ if (!ret_peer)
++ wg_peer_put(peer);
++ return ret_peer;
++}
++
++bool wg_noise_handshake_create_response(struct message_handshake_response *dst,
++ struct noise_handshake *handshake)
++{
++ u8 key[NOISE_SYMMETRIC_KEY_LEN];
++ bool ret = false;
++
++ /* We need to wait for crng _before_ taking any locks, since
++ * curve25519_generate_secret uses get_random_bytes_wait.
++ */
++ wait_for_random_bytes();
++
++ down_read(&handshake->static_identity->lock);
++ down_write(&handshake->lock);
++
++ if (handshake->state != HANDSHAKE_CONSUMED_INITIATION)
++ goto out;
++
++ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE);
++ dst->receiver_index = handshake->remote_index;
++
++ /* e */
++ curve25519_generate_secret(handshake->ephemeral_private);
++ if (!curve25519_generate_public(dst->unencrypted_ephemeral,
++ handshake->ephemeral_private))
++ goto out;
++ message_ephemeral(dst->unencrypted_ephemeral,
++ dst->unencrypted_ephemeral, handshake->chaining_key,
++ handshake->hash);
++
++ /* ee */
++ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
++ handshake->remote_ephemeral))
++ goto out;
++
++ /* se */
++ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
++ handshake->remote_static))
++ goto out;
++
++ /* psk */
++ mix_psk(handshake->chaining_key, handshake->hash, key,
++ handshake->preshared_key);
++
++ /* {} */
++ message_encrypt(dst->encrypted_nothing, NULL, 0, key, handshake->hash);
++
++ dst->sender_index = wg_index_hashtable_insert(
++ handshake->entry.peer->device->index_hashtable,
++ &handshake->entry);
++
++ handshake->state = HANDSHAKE_CREATED_RESPONSE;
++ ret = true;
++
++out:
++ up_write(&handshake->lock);
++ up_read(&handshake->static_identity->lock);
++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
++ return ret;
++}
++
++struct wg_peer *
++wg_noise_handshake_consume_response(struct message_handshake_response *src,
++ struct wg_device *wg)
++{
++ enum noise_handshake_state state = HANDSHAKE_ZEROED;
++ struct wg_peer *peer = NULL, *ret_peer = NULL;
++ struct noise_handshake *handshake;
++ u8 key[NOISE_SYMMETRIC_KEY_LEN];
++ u8 hash[NOISE_HASH_LEN];
++ u8 chaining_key[NOISE_HASH_LEN];
++ u8 e[NOISE_PUBLIC_KEY_LEN];
++ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
++ u8 static_private[NOISE_PUBLIC_KEY_LEN];
++
++ down_read(&wg->static_identity.lock);
++
++ if (unlikely(!wg->static_identity.has_identity))
++ goto out;
++
++ handshake = (struct noise_handshake *)wg_index_hashtable_lookup(
++ wg->index_hashtable, INDEX_HASHTABLE_HANDSHAKE,
++ src->receiver_index, &peer);
++ if (unlikely(!handshake))
++ goto out;
++
++ down_read(&handshake->lock);
++ state = handshake->state;
++ memcpy(hash, handshake->hash, NOISE_HASH_LEN);
++ memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
++ memcpy(ephemeral_private, handshake->ephemeral_private,
++ NOISE_PUBLIC_KEY_LEN);
++ up_read(&handshake->lock);
++
++ if (state != HANDSHAKE_CREATED_INITIATION)
++ goto fail;
++
++ /* e */
++ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
++
++ /* ee */
++ if (!mix_dh(chaining_key, NULL, ephemeral_private, e))
++ goto fail;
++
++ /* se */
++ if (!mix_dh(chaining_key, NULL, wg->static_identity.static_private, e))
++ goto fail;
++
++ /* psk */
++ mix_psk(chaining_key, hash, key, handshake->preshared_key);
++
++ /* {} */
++ if (!message_decrypt(NULL, src->encrypted_nothing,
++ sizeof(src->encrypted_nothing), key, hash))
++ goto fail;
++
++ /* Success! Copy everything to peer */
++ down_write(&handshake->lock);
++ /* It's important to check that the state is still the same, while we
++ * have an exclusive lock.
++ */
++ if (handshake->state != state) {
++ up_write(&handshake->lock);
++ goto fail;
++ }
++ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
++ memcpy(handshake->hash, hash, NOISE_HASH_LEN);
++ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
++ handshake->remote_index = src->sender_index;
++ handshake->state = HANDSHAKE_CONSUMED_RESPONSE;
++ up_write(&handshake->lock);
++ ret_peer = peer;
++ goto out;
++
++fail:
++ wg_peer_put(peer);
++out:
++ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
++ memzero_explicit(hash, NOISE_HASH_LEN);
++ memzero_explicit(chaining_key, NOISE_HASH_LEN);
++ memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
++ memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
++ up_read(&wg->static_identity.lock);
++ return ret_peer;
++}
++
++bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
++ struct noise_keypairs *keypairs)
++{
++ struct noise_keypair *new_keypair;
++ bool ret = false;
++
++ down_write(&handshake->lock);
++ if (handshake->state != HANDSHAKE_CREATED_RESPONSE &&
++ handshake->state != HANDSHAKE_CONSUMED_RESPONSE)
++ goto out;
++
++ new_keypair = keypair_create(handshake->entry.peer);
++ if (!new_keypair)
++ goto out;
++ new_keypair->i_am_the_initiator = handshake->state ==
++ HANDSHAKE_CONSUMED_RESPONSE;
++ new_keypair->remote_index = handshake->remote_index;
++
++ if (new_keypair->i_am_the_initiator)
++ derive_keys(&new_keypair->sending, &new_keypair->receiving,
++ handshake->chaining_key);
++ else
++ derive_keys(&new_keypair->receiving, &new_keypair->sending,
++ handshake->chaining_key);
++
++ handshake_zero(handshake);
++ rcu_read_lock_bh();
++ if (likely(!READ_ONCE(container_of(handshake, struct wg_peer,
++ handshake)->is_dead))) {
++ add_new_keypair(keypairs, new_keypair);
++ net_dbg_ratelimited("%s: Keypair %llu created for peer %llu\n",
++ handshake->entry.peer->device->dev->name,
++ new_keypair->internal_id,
++ handshake->entry.peer->internal_id);
++ ret = wg_index_hashtable_replace(
++ handshake->entry.peer->device->index_hashtable,
++ &handshake->entry, &new_keypair->entry);
++ } else {
++ kzfree(new_keypair);
++ }
++ rcu_read_unlock_bh();
++
++out:
++ up_write(&handshake->lock);
++ return ret;
++}
+--- /dev/null
++++ b/drivers/net/wireguard/noise.h
+@@ -0,0 +1,137 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++#ifndef _WG_NOISE_H
++#define _WG_NOISE_H
++
++#include "messages.h"
++#include "peerlookup.h"
++
++#include <linux/types.h>
++#include <linux/spinlock.h>
++#include <linux/atomic.h>
++#include <linux/rwsem.h>
++#include <linux/mutex.h>
++#include <linux/kref.h>
++
++union noise_counter {
++ struct {
++ u64 counter;
++ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
++ spinlock_t lock;
++ } receive;
++ atomic64_t counter;
++};
++
++struct noise_symmetric_key {
++ u8 key[NOISE_SYMMETRIC_KEY_LEN];
++ union noise_counter counter;
++ u64 birthdate;
++ bool is_valid;
++};
++
++struct noise_keypair {
++ struct index_hashtable_entry entry;
++ struct noise_symmetric_key sending;
++ struct noise_symmetric_key receiving;
++ __le32 remote_index;
++ bool i_am_the_initiator;
++ struct kref refcount;
++ struct rcu_head rcu;
++ u64 internal_id;
++};
++
++struct noise_keypairs {
++ struct noise_keypair __rcu *current_keypair;
++ struct noise_keypair __rcu *previous_keypair;
++ struct noise_keypair __rcu *next_keypair;
++ spinlock_t keypair_update_lock;
++};
++
++struct noise_static_identity {
++ u8 static_public[NOISE_PUBLIC_KEY_LEN];
++ u8 static_private[NOISE_PUBLIC_KEY_LEN];
++ struct rw_semaphore lock;
++ bool has_identity;
++};
++
++enum noise_handshake_state {
++ HANDSHAKE_ZEROED,
++ HANDSHAKE_CREATED_INITIATION,
++ HANDSHAKE_CONSUMED_INITIATION,
++ HANDSHAKE_CREATED_RESPONSE,
++ HANDSHAKE_CONSUMED_RESPONSE
++};
++
++struct noise_handshake {
++ struct index_hashtable_entry entry;
++
++ enum noise_handshake_state state;
++ u64 last_initiation_consumption;
++
++ struct noise_static_identity *static_identity;
++
++ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
++ u8 remote_static[NOISE_PUBLIC_KEY_LEN];
++ u8 remote_ephemeral[NOISE_PUBLIC_KEY_LEN];
++ u8 precomputed_static_static[NOISE_PUBLIC_KEY_LEN];
++
++ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
++
++ u8 hash[NOISE_HASH_LEN];
++ u8 chaining_key[NOISE_HASH_LEN];
++
++ u8 latest_timestamp[NOISE_TIMESTAMP_LEN];
++ __le32 remote_index;
++
++ /* Protects all members except the immutable (after noise_handshake_
++ * init): remote_static, precomputed_static_static, static_identity.
++ */
++ struct rw_semaphore lock;
++};
++
++struct wg_device;
++
++void wg_noise_init(void);
++bool wg_noise_handshake_init(struct noise_handshake *handshake,
++ struct noise_static_identity *static_identity,
++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
++ struct wg_peer *peer);
++void wg_noise_handshake_clear(struct noise_handshake *handshake);
++static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns)
++{
++ atomic64_set(handshake_ns, ktime_get_coarse_boottime_ns() -
++ (u64)(REKEY_TIMEOUT + 1) * NSEC_PER_SEC);
++}
++
++void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now);
++struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair);
++void wg_noise_keypairs_clear(struct noise_keypairs *keypairs);
++bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs,
++ struct noise_keypair *received_keypair);
++void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer);
++
++void wg_noise_set_static_identity_private_key(
++ struct noise_static_identity *static_identity,
++ const u8 private_key[NOISE_PUBLIC_KEY_LEN]);
++bool wg_noise_precompute_static_static(struct wg_peer *peer);
++
++bool
++wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
++ struct noise_handshake *handshake);
++struct wg_peer *
++wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
++ struct wg_device *wg);
++
++bool wg_noise_handshake_create_response(struct message_handshake_response *dst,
++ struct noise_handshake *handshake);
++struct wg_peer *
++wg_noise_handshake_consume_response(struct message_handshake_response *src,
++ struct wg_device *wg);
++
++bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
++ struct noise_keypairs *keypairs);
++
++#endif /* _WG_NOISE_H */
+--- /dev/null
++++ b/drivers/net/wireguard/peer.c
+@@ -0,0 +1,240 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "peer.h"
++#include "device.h"
++#include "queueing.h"
++#include "timers.h"
++#include "peerlookup.h"
++#include "noise.h"
++
++#include <linux/kref.h>
++#include <linux/lockdep.h>
++#include <linux/rcupdate.h>
++#include <linux/list.h>
++
++static atomic64_t peer_counter = ATOMIC64_INIT(0);
++
++struct wg_peer *wg_peer_create(struct wg_device *wg,
++ const u8 public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN])
++{
++ struct wg_peer *peer;
++ int ret = -ENOMEM;
++
++ lockdep_assert_held(&wg->device_update_lock);
++
++ if (wg->num_peers >= MAX_PEERS_PER_DEVICE)
++ return ERR_PTR(ret);
++
++ peer = kzalloc(sizeof(*peer), GFP_KERNEL);
++ if (unlikely(!peer))
++ return ERR_PTR(ret);
++ peer->device = wg;
++
++ if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
++ public_key, preshared_key, peer)) {
++ ret = -EKEYREJECTED;
++ goto err_1;
++ }
++ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
++ goto err_1;
++ if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
++ MAX_QUEUED_PACKETS))
++ goto err_2;
++ if (wg_packet_queue_init(&peer->rx_queue, NULL, false,
++ MAX_QUEUED_PACKETS))
++ goto err_3;
++
++ peer->internal_id = atomic64_inc_return(&peer_counter);
++ peer->serial_work_cpu = nr_cpumask_bits;
++ wg_cookie_init(&peer->latest_cookie);
++ wg_timers_init(peer);
++ wg_cookie_checker_precompute_peer_keys(peer);
++ spin_lock_init(&peer->keypairs.keypair_update_lock);
++ INIT_WORK(&peer->transmit_handshake_work,
++ wg_packet_handshake_send_worker);
++ rwlock_init(&peer->endpoint_lock);
++ kref_init(&peer->refcount);
++ skb_queue_head_init(&peer->staged_packet_queue);
++ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
++ set_bit(NAPI_STATE_NO_BUSY_POLL, &peer->napi.state);
++ netif_napi_add(wg->dev, &peer->napi, wg_packet_rx_poll,
++ NAPI_POLL_WEIGHT);
++ napi_enable(&peer->napi);
++ list_add_tail(&peer->peer_list, &wg->peer_list);
++ INIT_LIST_HEAD(&peer->allowedips_list);
++ wg_pubkey_hashtable_add(wg->peer_hashtable, peer);
++ ++wg->num_peers;
++ pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id);
++ return peer;
++
++err_3:
++ wg_packet_queue_free(&peer->tx_queue, false);
++err_2:
++ dst_cache_destroy(&peer->endpoint_cache);
++err_1:
++ kfree(peer);
++ return ERR_PTR(ret);
++}
++
++struct wg_peer *wg_peer_get_maybe_zero(struct wg_peer *peer)
++{
++ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(),
++ "Taking peer reference without holding the RCU read lock");
++ if (unlikely(!peer || !kref_get_unless_zero(&peer->refcount)))
++ return NULL;
++ return peer;
++}
++
++static void peer_make_dead(struct wg_peer *peer)
++{
++ /* Remove from configuration-time lookup structures. */
++ list_del_init(&peer->peer_list);
++ wg_allowedips_remove_by_peer(&peer->device->peer_allowedips, peer,
++ &peer->device->device_update_lock);
++ wg_pubkey_hashtable_remove(peer->device->peer_hashtable, peer);
++
++ /* Mark as dead, so that we don't allow jumping contexts after. */
++ WRITE_ONCE(peer->is_dead, true);
++
++ /* The caller must now synchronize_rcu() for this to take effect. */
++}
++
++static void peer_remove_after_dead(struct wg_peer *peer)
++{
++ WARN_ON(!peer->is_dead);
++
++ /* No more keypairs can be created for this peer, since is_dead protects
++ * add_new_keypair, so we can now destroy existing ones.
++ */
++ wg_noise_keypairs_clear(&peer->keypairs);
++
++ /* Destroy all ongoing timers that were in-flight at the beginning of
++ * this function.
++ */
++ wg_timers_stop(peer);
++
++ /* The transition between packet encryption/decryption queues isn't
++ * guarded by is_dead, but each reference's life is strictly bounded by
++ * two generations: once for parallel crypto and once for serial
++ * ingestion, so we can simply flush twice, and be sure that we no
++ * longer have references inside these queues.
++ */
++
++ /* a) For encrypt/decrypt. */
++ flush_workqueue(peer->device->packet_crypt_wq);
++ /* b.1) For send (but not receive, since that's napi). */
++ flush_workqueue(peer->device->packet_crypt_wq);
++ /* b.2.1) For receive (but not send, since that's wq). */
++ napi_disable(&peer->napi);
++ /* b.2.1) It's now safe to remove the napi struct, which must be done
++ * here from process context.
++ */
++ netif_napi_del(&peer->napi);
++
++ /* Ensure any workstructs we own (like transmit_handshake_work or
++ * clear_peer_work) no longer are in use.
++ */
++ flush_workqueue(peer->device->handshake_send_wq);
++
++ /* After the above flushes, a peer might still be active in a few
++ * different contexts: 1) from xmit(), before hitting is_dead and
++ * returning, 2) from wg_packet_consume_data(), before hitting is_dead
++ * and returning, 3) from wg_receive_handshake_packet() after a point
++ * where it has processed an incoming handshake packet, but where
++ * all calls to pass it off to timers fails because of is_dead. We won't
++ * have new references in (1) eventually, because we're removed from
++ * allowedips; we won't have new references in (2) eventually, because
++ * wg_index_hashtable_lookup will always return NULL, since we removed
++ * all existing keypairs and no more can be created; we won't have new
++ * references in (3) eventually, because we're removed from the pubkey
++ * hash table, which allows for a maximum of one handshake response,
++ * via the still-uncleared index hashtable entry, but not more than one,
++ * and in wg_cookie_message_consume, the lookup eventually gets a peer
++ * with a refcount of zero, so no new reference is taken.
++ */
++
++ --peer->device->num_peers;
++ wg_peer_put(peer);
++}
++
++/* We have a separate "remove" function make sure that all active places where
++ * a peer is currently operating will eventually come to an end and not pass
++ * their reference onto another context.
++ */
++void wg_peer_remove(struct wg_peer *peer)
++{
++ if (unlikely(!peer))
++ return;
++ lockdep_assert_held(&peer->device->device_update_lock);
++
++ peer_make_dead(peer);
++ synchronize_rcu();
++ peer_remove_after_dead(peer);
++}
++
++void wg_peer_remove_all(struct wg_device *wg)
++{
++ struct wg_peer *peer, *temp;
++ LIST_HEAD(dead_peers);
++
++ lockdep_assert_held(&wg->device_update_lock);
++
++ /* Avoid having to traverse individually for each one. */
++ wg_allowedips_free(&wg->peer_allowedips, &wg->device_update_lock);
++
++ list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) {
++ peer_make_dead(peer);
++ list_add_tail(&peer->peer_list, &dead_peers);
++ }
++ synchronize_rcu();
++ list_for_each_entry_safe(peer, temp, &dead_peers, peer_list)
++ peer_remove_after_dead(peer);
++}
++
++static void rcu_release(struct rcu_head *rcu)
++{
++ struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu);
++
++ dst_cache_destroy(&peer->endpoint_cache);
++ wg_packet_queue_free(&peer->rx_queue, false);
++ wg_packet_queue_free(&peer->tx_queue, false);
++
++ /* The final zeroing takes care of clearing any remaining handshake key
++ * material and other potentially sensitive information.
++ */
++ kzfree(peer);
++}
++
++static void kref_release(struct kref *refcount)
++{
++ struct wg_peer *peer = container_of(refcount, struct wg_peer, refcount);
++
++ pr_debug("%s: Peer %llu (%pISpfsc) destroyed\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++
++ /* Remove ourself from dynamic runtime lookup structures, now that the
++ * last reference is gone.
++ */
++ wg_index_hashtable_remove(peer->device->index_hashtable,
++ &peer->handshake.entry);
++
++ /* Remove any lingering packets that didn't have a chance to be
++ * transmitted.
++ */
++ wg_packet_purge_staged_packets(peer);
++
++ /* Free the memory used. */
++ call_rcu(&peer->rcu, rcu_release);
++}
++
++void wg_peer_put(struct wg_peer *peer)
++{
++ if (unlikely(!peer))
++ return;
++ kref_put(&peer->refcount, kref_release);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/peer.h
+@@ -0,0 +1,83 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_PEER_H
++#define _WG_PEER_H
++
++#include "device.h"
++#include "noise.h"
++#include "cookie.h"
++
++#include <linux/types.h>
++#include <linux/netfilter.h>
++#include <linux/spinlock.h>
++#include <linux/kref.h>
++#include <net/dst_cache.h>
++
++struct wg_device;
++
++struct endpoint {
++ union {
++ struct sockaddr addr;
++ struct sockaddr_in addr4;
++ struct sockaddr_in6 addr6;
++ };
++ union {
++ struct {
++ struct in_addr src4;
++ /* Essentially the same as addr6->scope_id */
++ int src_if4;
++ };
++ struct in6_addr src6;
++ };
++};
++
++struct wg_peer {
++ struct wg_device *device;
++ struct crypt_queue tx_queue, rx_queue;
++ struct sk_buff_head staged_packet_queue;
++ int serial_work_cpu;
++ struct noise_keypairs keypairs;
++ struct endpoint endpoint;
++ struct dst_cache endpoint_cache;
++ rwlock_t endpoint_lock;
++ struct noise_handshake handshake;
++ atomic64_t last_sent_handshake;
++ struct work_struct transmit_handshake_work, clear_peer_work;
++ struct cookie latest_cookie;
++ struct hlist_node pubkey_hash;
++ u64 rx_bytes, tx_bytes;
++ struct timer_list timer_retransmit_handshake, timer_send_keepalive;
++ struct timer_list timer_new_handshake, timer_zero_key_material;
++ struct timer_list timer_persistent_keepalive;
++ unsigned int timer_handshake_attempts;
++ u16 persistent_keepalive_interval;
++ bool timer_need_another_keepalive;
++ bool sent_lastminute_handshake;
++ struct timespec64 walltime_last_handshake;
++ struct kref refcount;
++ struct rcu_head rcu;
++ struct list_head peer_list;
++ struct list_head allowedips_list;
++ u64 internal_id;
++ struct napi_struct napi;
++ bool is_dead;
++};
++
++struct wg_peer *wg_peer_create(struct wg_device *wg,
++ const u8 public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]);
++
++struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer);
++static inline struct wg_peer *wg_peer_get(struct wg_peer *peer)
++{
++ kref_get(&peer->refcount);
++ return peer;
++}
++void wg_peer_put(struct wg_peer *peer);
++void wg_peer_remove(struct wg_peer *peer);
++void wg_peer_remove_all(struct wg_device *wg);
++
++#endif /* _WG_PEER_H */
+--- /dev/null
++++ b/drivers/net/wireguard/peerlookup.c
+@@ -0,0 +1,221 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "peerlookup.h"
++#include "peer.h"
++#include "noise.h"
++
++static struct hlist_head *pubkey_bucket(struct pubkey_hashtable *table,
++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
++{
++ /* siphash gives us a secure 64bit number based on a random key. Since
++ * the bits are uniformly distributed, we can then mask off to get the
++ * bits we need.
++ */
++ const u64 hash = siphash(pubkey, NOISE_PUBLIC_KEY_LEN, &table->key);
++
++ return &table->hashtable[hash & (HASH_SIZE(table->hashtable) - 1)];
++}
++
++struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void)
++{
++ struct pubkey_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
++
++ if (!table)
++ return NULL;
++
++ get_random_bytes(&table->key, sizeof(table->key));
++ hash_init(table->hashtable);
++ mutex_init(&table->lock);
++ return table;
++}
++
++void wg_pubkey_hashtable_add(struct pubkey_hashtable *table,
++ struct wg_peer *peer)
++{
++ mutex_lock(&table->lock);
++ hlist_add_head_rcu(&peer->pubkey_hash,
++ pubkey_bucket(table, peer->handshake.remote_static));
++ mutex_unlock(&table->lock);
++}
++
++void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table,
++ struct wg_peer *peer)
++{
++ mutex_lock(&table->lock);
++ hlist_del_init_rcu(&peer->pubkey_hash);
++ mutex_unlock(&table->lock);
++}
++
++/* Returns a strong reference to a peer */
++struct wg_peer *
++wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table,
++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
++{
++ struct wg_peer *iter_peer, *peer = NULL;
++
++ rcu_read_lock_bh();
++ hlist_for_each_entry_rcu_bh(iter_peer, pubkey_bucket(table, pubkey),
++ pubkey_hash) {
++ if (!memcmp(pubkey, iter_peer->handshake.remote_static,
++ NOISE_PUBLIC_KEY_LEN)) {
++ peer = iter_peer;
++ break;
++ }
++ }
++ peer = wg_peer_get_maybe_zero(peer);
++ rcu_read_unlock_bh();
++ return peer;
++}
++
++static struct hlist_head *index_bucket(struct index_hashtable *table,
++ const __le32 index)
++{
++ /* Since the indices are random and thus all bits are uniformly
++ * distributed, we can find its bucket simply by masking.
++ */
++ return &table->hashtable[(__force u32)index &
++ (HASH_SIZE(table->hashtable) - 1)];
++}
++
++struct index_hashtable *wg_index_hashtable_alloc(void)
++{
++ struct index_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
++
++ if (!table)
++ return NULL;
++
++ hash_init(table->hashtable);
++ spin_lock_init(&table->lock);
++ return table;
++}
++
++/* At the moment, we limit ourselves to 2^20 total peers, which generally might
++ * amount to 2^20*3 items in this hashtable. The algorithm below works by
++ * picking a random number and testing it. We can see that these limits mean we
++ * usually succeed pretty quickly:
++ *
++ * >>> def calculation(tries, size):
++ * ... return (size / 2**32)**(tries - 1) * (1 - (size / 2**32))
++ * ...
++ * >>> calculation(1, 2**20 * 3)
++ * 0.999267578125
++ * >>> calculation(2, 2**20 * 3)
++ * 0.0007318854331970215
++ * >>> calculation(3, 2**20 * 3)
++ * 5.360489012673497e-07
++ * >>> calculation(4, 2**20 * 3)
++ * 3.9261394135792216e-10
++ *
++ * At the moment, we don't do any masking, so this algorithm isn't exactly
++ * constant time in either the random guessing or in the hash list lookup. We
++ * could require a minimum of 3 tries, which would successfully mask the
++ * guessing. this would not, however, help with the growing hash lengths, which
++ * is another thing to consider moving forward.
++ */
++
++__le32 wg_index_hashtable_insert(struct index_hashtable *table,
++ struct index_hashtable_entry *entry)
++{
++ struct index_hashtable_entry *existing_entry;
++
++ spin_lock_bh(&table->lock);
++ hlist_del_init_rcu(&entry->index_hash);
++ spin_unlock_bh(&table->lock);
++
++ rcu_read_lock_bh();
++
++search_unused_slot:
++ /* First we try to find an unused slot, randomly, while unlocked. */
++ entry->index = (__force __le32)get_random_u32();
++ hlist_for_each_entry_rcu_bh(existing_entry,
++ index_bucket(table, entry->index),
++ index_hash) {
++ if (existing_entry->index == entry->index)
++ /* If it's already in use, we continue searching. */
++ goto search_unused_slot;
++ }
++
++ /* Once we've found an unused slot, we lock it, and then double-check
++ * that nobody else stole it from us.
++ */
++ spin_lock_bh(&table->lock);
++ hlist_for_each_entry_rcu_bh(existing_entry,
++ index_bucket(table, entry->index),
++ index_hash) {
++ if (existing_entry->index == entry->index) {
++ spin_unlock_bh(&table->lock);
++ /* If it was stolen, we start over. */
++ goto search_unused_slot;
++ }
++ }
++ /* Otherwise, we know we have it exclusively (since we're locked),
++ * so we insert.
++ */
++ hlist_add_head_rcu(&entry->index_hash,
++ index_bucket(table, entry->index));
++ spin_unlock_bh(&table->lock);
++
++ rcu_read_unlock_bh();
++
++ return entry->index;
++}
++
++bool wg_index_hashtable_replace(struct index_hashtable *table,
++ struct index_hashtable_entry *old,
++ struct index_hashtable_entry *new)
++{
++ if (unlikely(hlist_unhashed(&old->index_hash)))
++ return false;
++ spin_lock_bh(&table->lock);
++ new->index = old->index;
++ hlist_replace_rcu(&old->index_hash, &new->index_hash);
++
++ /* Calling init here NULLs out index_hash, and in fact after this
++ * function returns, it's theoretically possible for this to get
++ * reinserted elsewhere. That means the RCU lookup below might either
++ * terminate early or jump between buckets, in which case the packet
++ * simply gets dropped, which isn't terrible.
++ */
++ INIT_HLIST_NODE(&old->index_hash);
++ spin_unlock_bh(&table->lock);
++ return true;
++}
++
++void wg_index_hashtable_remove(struct index_hashtable *table,
++ struct index_hashtable_entry *entry)
++{
++ spin_lock_bh(&table->lock);
++ hlist_del_init_rcu(&entry->index_hash);
++ spin_unlock_bh(&table->lock);
++}
++
++/* Returns a strong reference to a entry->peer */
++struct index_hashtable_entry *
++wg_index_hashtable_lookup(struct index_hashtable *table,
++ const enum index_hashtable_type type_mask,
++ const __le32 index, struct wg_peer **peer)
++{
++ struct index_hashtable_entry *iter_entry, *entry = NULL;
++
++ rcu_read_lock_bh();
++ hlist_for_each_entry_rcu_bh(iter_entry, index_bucket(table, index),
++ index_hash) {
++ if (iter_entry->index == index) {
++ if (likely(iter_entry->type & type_mask))
++ entry = iter_entry;
++ break;
++ }
++ }
++ if (likely(entry)) {
++ entry->peer = wg_peer_get_maybe_zero(entry->peer);
++ if (likely(entry->peer))
++ *peer = entry->peer;
++ else
++ entry = NULL;
++ }
++ rcu_read_unlock_bh();
++ return entry;
++}
+--- /dev/null
++++ b/drivers/net/wireguard/peerlookup.h
+@@ -0,0 +1,64 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_PEERLOOKUP_H
++#define _WG_PEERLOOKUP_H
++
++#include "messages.h"
++
++#include <linux/hashtable.h>
++#include <linux/mutex.h>
++#include <linux/siphash.h>
++
++struct wg_peer;
++
++struct pubkey_hashtable {
++ /* TODO: move to rhashtable */
++ DECLARE_HASHTABLE(hashtable, 11);
++ siphash_key_t key;
++ struct mutex lock;
++};
++
++struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void);
++void wg_pubkey_hashtable_add(struct pubkey_hashtable *table,
++ struct wg_peer *peer);
++void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table,
++ struct wg_peer *peer);
++struct wg_peer *
++wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table,
++ const u8 pubkey[NOISE_PUBLIC_KEY_LEN]);
++
++struct index_hashtable {
++ /* TODO: move to rhashtable */
++ DECLARE_HASHTABLE(hashtable, 13);
++ spinlock_t lock;
++};
++
++enum index_hashtable_type {
++ INDEX_HASHTABLE_HANDSHAKE = 1U << 0,
++ INDEX_HASHTABLE_KEYPAIR = 1U << 1
++};
++
++struct index_hashtable_entry {
++ struct wg_peer *peer;
++ struct hlist_node index_hash;
++ enum index_hashtable_type type;
++ __le32 index;
++};
++
++struct index_hashtable *wg_index_hashtable_alloc(void);
++__le32 wg_index_hashtable_insert(struct index_hashtable *table,
++ struct index_hashtable_entry *entry);
++bool wg_index_hashtable_replace(struct index_hashtable *table,
++ struct index_hashtable_entry *old,
++ struct index_hashtable_entry *new);
++void wg_index_hashtable_remove(struct index_hashtable *table,
++ struct index_hashtable_entry *entry);
++struct index_hashtable_entry *
++wg_index_hashtable_lookup(struct index_hashtable *table,
++ const enum index_hashtable_type type_mask,
++ const __le32 index, struct wg_peer **peer);
++
++#endif /* _WG_PEERLOOKUP_H */
+--- /dev/null
++++ b/drivers/net/wireguard/queueing.c
+@@ -0,0 +1,53 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "queueing.h"
++
++struct multicore_worker __percpu *
++wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
++{
++ int cpu;
++ struct multicore_worker __percpu *worker =
++ alloc_percpu(struct multicore_worker);
++
++ if (!worker)
++ return NULL;
++
++ for_each_possible_cpu(cpu) {
++ per_cpu_ptr(worker, cpu)->ptr = ptr;
++ INIT_WORK(&per_cpu_ptr(worker, cpu)->work, function);
++ }
++ return worker;
++}
++
++int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
++ bool multicore, unsigned int len)
++{
++ int ret;
++
++ memset(queue, 0, sizeof(*queue));
++ ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
++ if (ret)
++ return ret;
++ if (function) {
++ if (multicore) {
++ queue->worker = wg_packet_percpu_multicore_worker_alloc(
++ function, queue);
++ if (!queue->worker)
++ return -ENOMEM;
++ } else {
++ INIT_WORK(&queue->work, function);
++ }
++ }
++ return 0;
++}
++
++void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
++{
++ if (multicore)
++ free_percpu(queue->worker);
++ WARN_ON(!__ptr_ring_empty(&queue->ring));
++ ptr_ring_cleanup(&queue->ring, NULL);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/queueing.h
+@@ -0,0 +1,197 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_QUEUEING_H
++#define _WG_QUEUEING_H
++
++#include "peer.h"
++#include <linux/types.h>
++#include <linux/skbuff.h>
++#include <linux/ip.h>
++#include <linux/ipv6.h>
++
++struct wg_device;
++struct wg_peer;
++struct multicore_worker;
++struct crypt_queue;
++struct sk_buff;
++
++/* queueing.c APIs: */
++int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
++ bool multicore, unsigned int len);
++void wg_packet_queue_free(struct crypt_queue *queue, bool multicore);
++struct multicore_worker __percpu *
++wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
++
++/* receive.c APIs: */
++void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb);
++void wg_packet_handshake_receive_worker(struct work_struct *work);
++/* NAPI poll function: */
++int wg_packet_rx_poll(struct napi_struct *napi, int budget);
++/* Workqueue worker: */
++void wg_packet_decrypt_worker(struct work_struct *work);
++
++/* send.c APIs: */
++void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer,
++ bool is_retry);
++void wg_packet_send_handshake_response(struct wg_peer *peer);
++void wg_packet_send_handshake_cookie(struct wg_device *wg,
++ struct sk_buff *initiating_skb,
++ __le32 sender_index);
++void wg_packet_send_keepalive(struct wg_peer *peer);
++void wg_packet_purge_staged_packets(struct wg_peer *peer);
++void wg_packet_send_staged_packets(struct wg_peer *peer);
++/* Workqueue workers: */
++void wg_packet_handshake_send_worker(struct work_struct *work);
++void wg_packet_tx_worker(struct work_struct *work);
++void wg_packet_encrypt_worker(struct work_struct *work);
++
++enum packet_state {
++ PACKET_STATE_UNCRYPTED,
++ PACKET_STATE_CRYPTED,
++ PACKET_STATE_DEAD
++};
++
++struct packet_cb {
++ u64 nonce;
++ struct noise_keypair *keypair;
++ atomic_t state;
++ u32 mtu;
++ u8 ds;
++};
++
++#define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb))
++#define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
++
++/* Returns either the correct skb->protocol value, or 0 if invalid. */
++static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb)
++{
++ if (skb_network_header(skb) >= skb->head &&
++ (skb_network_header(skb) + sizeof(struct iphdr)) <=
++ skb_tail_pointer(skb) &&
++ ip_hdr(skb)->version == 4)
++ return htons(ETH_P_IP);
++ if (skb_network_header(skb) >= skb->head &&
++ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <=
++ skb_tail_pointer(skb) &&
++ ipv6_hdr(skb)->version == 6)
++ return htons(ETH_P_IPV6);
++ return 0;
++}
++
++static inline void wg_reset_packet(struct sk_buff *skb)
++{
++ const int pfmemalloc = skb->pfmemalloc;
++
++ skb_scrub_packet(skb, true);
++ memset(&skb->headers_start, 0,
++ offsetof(struct sk_buff, headers_end) -
++ offsetof(struct sk_buff, headers_start));
++ skb->pfmemalloc = pfmemalloc;
++ skb->queue_mapping = 0;
++ skb->nohdr = 0;
++ skb->peeked = 0;
++ skb->mac_len = 0;
++ skb->dev = NULL;
++#ifdef CONFIG_NET_SCHED
++ skb->tc_index = 0;
++#endif
++ skb_reset_redirect(skb);
++ skb->hdr_len = skb_headroom(skb);
++ skb_reset_mac_header(skb);
++ skb_reset_network_header(skb);
++ skb_reset_transport_header(skb);
++ skb_probe_transport_header(skb);
++ skb_reset_inner_headers(skb);
++}
++
++static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id)
++{
++ unsigned int cpu = *stored_cpu, cpu_index, i;
++
++ if (unlikely(cpu == nr_cpumask_bits ||
++ !cpumask_test_cpu(cpu, cpu_online_mask))) {
++ cpu_index = id % cpumask_weight(cpu_online_mask);
++ cpu = cpumask_first(cpu_online_mask);
++ for (i = 0; i < cpu_index; ++i)
++ cpu = cpumask_next(cpu, cpu_online_mask);
++ *stored_cpu = cpu;
++ }
++ return cpu;
++}
++
++/* This function is racy, in the sense that next is unlocked, so it could return
++ * the same CPU twice. A race-free version of this would be to instead store an
++ * atomic sequence number, do an increment-and-return, and then iterate through
++ * every possible CPU until we get to that index -- choose_cpu. However that's
++ * a bit slower, and it doesn't seem like this potential race actually
++ * introduces any performance loss, so we live with it.
++ */
++static inline int wg_cpumask_next_online(int *next)
++{
++ int cpu = *next;
++
++ while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask)))
++ cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
++ *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
++ return cpu;
++}
++
++static inline int wg_queue_enqueue_per_device_and_peer(
++ struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
++ struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
++{
++ int cpu;
++
++ atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED);
++ /* We first queue this up for the peer ingestion, but the consumer
++ * will wait for the state to change to CRYPTED or DEAD before.
++ */
++ if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
++ return -ENOSPC;
++ /* Then we queue it up in the device queue, which consumes the
++ * packet as soon as it can.
++ */
++ cpu = wg_cpumask_next_online(next_cpu);
++ if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb)))
++ return -EPIPE;
++ queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work);
++ return 0;
++}
++
++static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
++ struct sk_buff *skb,
++ enum packet_state state)
++{
++ /* We take a reference, because as soon as we call atomic_set, the
++ * peer can be freed from below us.
++ */
++ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
++
++ atomic_set_release(&PACKET_CB(skb)->state, state);
++ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
++ peer->internal_id),
++ peer->device->packet_crypt_wq, &queue->work);
++ wg_peer_put(peer);
++}
++
++static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb,
++ enum packet_state state)
++{
++ /* We take a reference, because as soon as we call atomic_set, the
++ * peer can be freed from below us.
++ */
++ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
++
++ atomic_set_release(&PACKET_CB(skb)->state, state);
++ napi_schedule(&peer->napi);
++ wg_peer_put(peer);
++}
++
++#ifdef DEBUG
++bool wg_packet_counter_selftest(void);
++#endif
++
++#endif /* _WG_QUEUEING_H */
+--- /dev/null
++++ b/drivers/net/wireguard/ratelimiter.c
+@@ -0,0 +1,223 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "ratelimiter.h"
++#include <linux/siphash.h>
++#include <linux/mm.h>
++#include <linux/slab.h>
++#include <net/ip.h>
++
++static struct kmem_cache *entry_cache;
++static hsiphash_key_t key;
++static spinlock_t table_lock = __SPIN_LOCK_UNLOCKED("ratelimiter_table_lock");
++static DEFINE_MUTEX(init_lock);
++static u64 init_refcnt; /* Protected by init_lock, hence not atomic. */
++static atomic_t total_entries = ATOMIC_INIT(0);
++static unsigned int max_entries, table_size;
++static void wg_ratelimiter_gc_entries(struct work_struct *);
++static DECLARE_DEFERRABLE_WORK(gc_work, wg_ratelimiter_gc_entries);
++static struct hlist_head *table_v4;
++#if IS_ENABLED(CONFIG_IPV6)
++static struct hlist_head *table_v6;
++#endif
++
++struct ratelimiter_entry {
++ u64 last_time_ns, tokens, ip;
++ void *net;
++ spinlock_t lock;
++ struct hlist_node hash;
++ struct rcu_head rcu;
++};
++
++enum {
++ PACKETS_PER_SECOND = 20,
++ PACKETS_BURSTABLE = 5,
++ PACKET_COST = NSEC_PER_SEC / PACKETS_PER_SECOND,
++ TOKEN_MAX = PACKET_COST * PACKETS_BURSTABLE
++};
++
++static void entry_free(struct rcu_head *rcu)
++{
++ kmem_cache_free(entry_cache,
++ container_of(rcu, struct ratelimiter_entry, rcu));
++ atomic_dec(&total_entries);
++}
++
++static void entry_uninit(struct ratelimiter_entry *entry)
++{
++ hlist_del_rcu(&entry->hash);
++ call_rcu(&entry->rcu, entry_free);
++}
++
++/* Calling this function with a NULL work uninits all entries. */
++static void wg_ratelimiter_gc_entries(struct work_struct *work)
++{
++ const u64 now = ktime_get_coarse_boottime_ns();
++ struct ratelimiter_entry *entry;
++ struct hlist_node *temp;
++ unsigned int i;
++
++ for (i = 0; i < table_size; ++i) {
++ spin_lock(&table_lock);
++ hlist_for_each_entry_safe(entry, temp, &table_v4[i], hash) {
++ if (unlikely(!work) ||
++ now - entry->last_time_ns > NSEC_PER_SEC)
++ entry_uninit(entry);
++ }
++#if IS_ENABLED(CONFIG_IPV6)
++ hlist_for_each_entry_safe(entry, temp, &table_v6[i], hash) {
++ if (unlikely(!work) ||
++ now - entry->last_time_ns > NSEC_PER_SEC)
++ entry_uninit(entry);
++ }
++#endif
++ spin_unlock(&table_lock);
++ if (likely(work))
++ cond_resched();
++ }
++ if (likely(work))
++ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ);
++}
++
++bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net)
++{
++ /* We only take the bottom half of the net pointer, so that we can hash
++ * 3 words in the end. This way, siphash's len param fits into the final
++ * u32, and we don't incur an extra round.
++ */
++ const u32 net_word = (unsigned long)net;
++ struct ratelimiter_entry *entry;
++ struct hlist_head *bucket;
++ u64 ip;
++
++ if (skb->protocol == htons(ETH_P_IP)) {
++ ip = (u64 __force)ip_hdr(skb)->saddr;
++ bucket = &table_v4[hsiphash_2u32(net_word, ip, &key) &
++ (table_size - 1)];
++ }
++#if IS_ENABLED(CONFIG_IPV6)
++ else if (skb->protocol == htons(ETH_P_IPV6)) {
++ /* Only use 64 bits, so as to ratelimit the whole /64. */
++ memcpy(&ip, &ipv6_hdr(skb)->saddr, sizeof(ip));
++ bucket = &table_v6[hsiphash_3u32(net_word, ip >> 32, ip, &key) &
++ (table_size - 1)];
++ }
++#endif
++ else
++ return false;
++ rcu_read_lock();
++ hlist_for_each_entry_rcu(entry, bucket, hash) {
++ if (entry->net == net && entry->ip == ip) {
++ u64 now, tokens;
++ bool ret;
++ /* Quasi-inspired by nft_limit.c, but this is actually a
++ * slightly different algorithm. Namely, we incorporate
++ * the burst as part of the maximum tokens, rather than
++ * as part of the rate.
++ */
++ spin_lock(&entry->lock);
++ now = ktime_get_coarse_boottime_ns();
++ tokens = min_t(u64, TOKEN_MAX,
++ entry->tokens + now -
++ entry->last_time_ns);
++ entry->last_time_ns = now;
++ ret = tokens >= PACKET_COST;
++ entry->tokens = ret ? tokens - PACKET_COST : tokens;
++ spin_unlock(&entry->lock);
++ rcu_read_unlock();
++ return ret;
++ }
++ }
++ rcu_read_unlock();
++
++ if (atomic_inc_return(&total_entries) > max_entries)
++ goto err_oom;
++
++ entry = kmem_cache_alloc(entry_cache, GFP_KERNEL);
++ if (unlikely(!entry))
++ goto err_oom;
++
++ entry->net = net;
++ entry->ip = ip;
++ INIT_HLIST_NODE(&entry->hash);
++ spin_lock_init(&entry->lock);
++ entry->last_time_ns = ktime_get_coarse_boottime_ns();
++ entry->tokens = TOKEN_MAX - PACKET_COST;
++ spin_lock(&table_lock);
++ hlist_add_head_rcu(&entry->hash, bucket);
++ spin_unlock(&table_lock);
++ return true;
++
++err_oom:
++ atomic_dec(&total_entries);
++ return false;
++}
++
++int wg_ratelimiter_init(void)
++{
++ mutex_lock(&init_lock);
++ if (++init_refcnt != 1)
++ goto out;
++
++ entry_cache = KMEM_CACHE(ratelimiter_entry, 0);
++ if (!entry_cache)
++ goto err;
++
++ /* xt_hashlimit.c uses a slightly different algorithm for ratelimiting,
++ * but what it shares in common is that it uses a massive hashtable. So,
++ * we borrow their wisdom about good table sizes on different systems
++ * dependent on RAM. This calculation here comes from there.
++ */
++ table_size = (totalram_pages() > (1U << 30) / PAGE_SIZE) ? 8192 :
++ max_t(unsigned long, 16, roundup_pow_of_two(
++ (totalram_pages() << PAGE_SHIFT) /
++ (1U << 14) / sizeof(struct hlist_head)));
++ max_entries = table_size * 8;
++
++ table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL);
++ if (unlikely(!table_v4))
++ goto err_kmemcache;
++
++#if IS_ENABLED(CONFIG_IPV6)
++ table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL);
++ if (unlikely(!table_v6)) {
++ kvfree(table_v4);
++ goto err_kmemcache;
++ }
++#endif
++
++ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ);
++ get_random_bytes(&key, sizeof(key));
++out:
++ mutex_unlock(&init_lock);
++ return 0;
++
++err_kmemcache:
++ kmem_cache_destroy(entry_cache);
++err:
++ --init_refcnt;
++ mutex_unlock(&init_lock);
++ return -ENOMEM;
++}
++
++void wg_ratelimiter_uninit(void)
++{
++ mutex_lock(&init_lock);
++ if (!init_refcnt || --init_refcnt)
++ goto out;
++
++ cancel_delayed_work_sync(&gc_work);
++ wg_ratelimiter_gc_entries(NULL);
++ rcu_barrier();
++ kvfree(table_v4);
++#if IS_ENABLED(CONFIG_IPV6)
++ kvfree(table_v6);
++#endif
++ kmem_cache_destroy(entry_cache);
++out:
++ mutex_unlock(&init_lock);
++}
++
++#include "selftest/ratelimiter.c"
+--- /dev/null
++++ b/drivers/net/wireguard/ratelimiter.h
+@@ -0,0 +1,19 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_RATELIMITER_H
++#define _WG_RATELIMITER_H
++
++#include <linux/skbuff.h>
++
++int wg_ratelimiter_init(void);
++void wg_ratelimiter_uninit(void);
++bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net);
++
++#ifdef DEBUG
++bool wg_ratelimiter_selftest(void);
++#endif
++
++#endif /* _WG_RATELIMITER_H */
+--- /dev/null
++++ b/drivers/net/wireguard/receive.c
+@@ -0,0 +1,595 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "queueing.h"
++#include "device.h"
++#include "peer.h"
++#include "timers.h"
++#include "messages.h"
++#include "cookie.h"
++#include "socket.h"
++
++#include <linux/ip.h>
++#include <linux/ipv6.h>
++#include <linux/udp.h>
++#include <net/ip_tunnels.h>
++
++/* Must be called with bh disabled. */
++static void update_rx_stats(struct wg_peer *peer, size_t len)
++{
++ struct pcpu_sw_netstats *tstats =
++ get_cpu_ptr(peer->device->dev->tstats);
++
++ u64_stats_update_begin(&tstats->syncp);
++ ++tstats->rx_packets;
++ tstats->rx_bytes += len;
++ peer->rx_bytes += len;
++ u64_stats_update_end(&tstats->syncp);
++ put_cpu_ptr(tstats);
++}
++
++#define SKB_TYPE_LE32(skb) (((struct message_header *)(skb)->data)->type)
++
++static size_t validate_header_len(struct sk_buff *skb)
++{
++ if (unlikely(skb->len < sizeof(struct message_header)))
++ return 0;
++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_DATA) &&
++ skb->len >= MESSAGE_MINIMUM_LENGTH)
++ return sizeof(struct message_data);
++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION) &&
++ skb->len == sizeof(struct message_handshake_initiation))
++ return sizeof(struct message_handshake_initiation);
++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE) &&
++ skb->len == sizeof(struct message_handshake_response))
++ return sizeof(struct message_handshake_response);
++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE) &&
++ skb->len == sizeof(struct message_handshake_cookie))
++ return sizeof(struct message_handshake_cookie);
++ return 0;
++}
++
++static int prepare_skb_header(struct sk_buff *skb, struct wg_device *wg)
++{
++ size_t data_offset, data_len, header_len;
++ struct udphdr *udp;
++
++ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol ||
++ skb_transport_header(skb) < skb->head ||
++ (skb_transport_header(skb) + sizeof(struct udphdr)) >
++ skb_tail_pointer(skb)))
++ return -EINVAL; /* Bogus IP header */
++ udp = udp_hdr(skb);
++ data_offset = (u8 *)udp - skb->data;
++ if (unlikely(data_offset > U16_MAX ||
++ data_offset + sizeof(struct udphdr) > skb->len))
++ /* Packet has offset at impossible location or isn't big enough
++ * to have UDP fields.
++ */
++ return -EINVAL;
++ data_len = ntohs(udp->len);
++ if (unlikely(data_len < sizeof(struct udphdr) ||
++ data_len > skb->len - data_offset))
++ /* UDP packet is reporting too small of a size or lying about
++ * its size.
++ */
++ return -EINVAL;
++ data_len -= sizeof(struct udphdr);
++ data_offset = (u8 *)udp + sizeof(struct udphdr) - skb->data;
++ if (unlikely(!pskb_may_pull(skb,
++ data_offset + sizeof(struct message_header)) ||
++ pskb_trim(skb, data_len + data_offset) < 0))
++ return -EINVAL;
++ skb_pull(skb, data_offset);
++ if (unlikely(skb->len != data_len))
++ /* Final len does not agree with calculated len */
++ return -EINVAL;
++ header_len = validate_header_len(skb);
++ if (unlikely(!header_len))
++ return -EINVAL;
++ __skb_push(skb, data_offset);
++ if (unlikely(!pskb_may_pull(skb, data_offset + header_len)))
++ return -EINVAL;
++ __skb_pull(skb, data_offset);
++ return 0;
++}
++
++static void wg_receive_handshake_packet(struct wg_device *wg,
++ struct sk_buff *skb)
++{
++ enum cookie_mac_state mac_state;
++ struct wg_peer *peer = NULL;
++ /* This is global, so that our load calculation applies to the whole
++ * system. We don't care about races with it at all.
++ */
++ static u64 last_under_load;
++ bool packet_needs_cookie;
++ bool under_load;
++
++ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE)) {
++ net_dbg_skb_ratelimited("%s: Receiving cookie response from %pISpfsc\n",
++ wg->dev->name, skb);
++ wg_cookie_message_consume(
++ (struct message_handshake_cookie *)skb->data, wg);
++ return;
++ }
++
++ under_load = skb_queue_len(&wg->incoming_handshakes) >=
++ MAX_QUEUED_INCOMING_HANDSHAKES / 8;
++ if (under_load)
++ last_under_load = ktime_get_coarse_boottime_ns();
++ else if (last_under_load)
++ under_load = !wg_birthdate_has_expired(last_under_load, 1);
++ mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
++ under_load);
++ if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
++ (!under_load && mac_state == VALID_MAC_BUT_NO_COOKIE)) {
++ packet_needs_cookie = false;
++ } else if (under_load && mac_state == VALID_MAC_BUT_NO_COOKIE) {
++ packet_needs_cookie = true;
++ } else {
++ net_dbg_skb_ratelimited("%s: Invalid MAC of handshake, dropping packet from %pISpfsc\n",
++ wg->dev->name, skb);
++ return;
++ }
++
++ switch (SKB_TYPE_LE32(skb)) {
++ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): {
++ struct message_handshake_initiation *message =
++ (struct message_handshake_initiation *)skb->data;
++
++ if (packet_needs_cookie) {
++ wg_packet_send_handshake_cookie(wg, skb,
++ message->sender_index);
++ return;
++ }
++ peer = wg_noise_handshake_consume_initiation(message, wg);
++ if (unlikely(!peer)) {
++ net_dbg_skb_ratelimited("%s: Invalid handshake initiation from %pISpfsc\n",
++ wg->dev->name, skb);
++ return;
++ }
++ wg_socket_set_peer_endpoint_from_skb(peer, skb);
++ net_dbg_ratelimited("%s: Receiving handshake initiation from peer %llu (%pISpfsc)\n",
++ wg->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++ wg_packet_send_handshake_response(peer);
++ break;
++ }
++ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): {
++ struct message_handshake_response *message =
++ (struct message_handshake_response *)skb->data;
++
++ if (packet_needs_cookie) {
++ wg_packet_send_handshake_cookie(wg, skb,
++ message->sender_index);
++ return;
++ }
++ peer = wg_noise_handshake_consume_response(message, wg);
++ if (unlikely(!peer)) {
++ net_dbg_skb_ratelimited("%s: Invalid handshake response from %pISpfsc\n",
++ wg->dev->name, skb);
++ return;
++ }
++ wg_socket_set_peer_endpoint_from_skb(peer, skb);
++ net_dbg_ratelimited("%s: Receiving handshake response from peer %llu (%pISpfsc)\n",
++ wg->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++ if (wg_noise_handshake_begin_session(&peer->handshake,
++ &peer->keypairs)) {
++ wg_timers_session_derived(peer);
++ wg_timers_handshake_complete(peer);
++ /* Calling this function will either send any existing
++ * packets in the queue and not send a keepalive, which
++ * is the best case, Or, if there's nothing in the
++ * queue, it will send a keepalive, in order to give
++ * immediate confirmation of the session.
++ */
++ wg_packet_send_keepalive(peer);
++ }
++ break;
++ }
++ }
++
++ if (unlikely(!peer)) {
++ WARN(1, "Somehow a wrong type of packet wound up in the handshake queue!\n");
++ return;
++ }
++
++ local_bh_disable();
++ update_rx_stats(peer, skb->len);
++ local_bh_enable();
++
++ wg_timers_any_authenticated_packet_received(peer);
++ wg_timers_any_authenticated_packet_traversal(peer);
++ wg_peer_put(peer);
++}
++
++void wg_packet_handshake_receive_worker(struct work_struct *work)
++{
++ struct wg_device *wg = container_of(work, struct multicore_worker,
++ work)->ptr;
++ struct sk_buff *skb;
++
++ while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) {
++ wg_receive_handshake_packet(wg, skb);
++ dev_kfree_skb(skb);
++ cond_resched();
++ }
++}
++
++static void keep_key_fresh(struct wg_peer *peer)
++{
++ struct noise_keypair *keypair;
++ bool send = false;
++
++ if (peer->sent_lastminute_handshake)
++ return;
++
++ rcu_read_lock_bh();
++ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
++ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
++ keypair->i_am_the_initiator &&
++ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
++ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT)))
++ send = true;
++ rcu_read_unlock_bh();
++
++ if (send) {
++ peer->sent_lastminute_handshake = true;
++ wg_packet_send_queued_handshake_initiation(peer, false);
++ }
++}
++
++static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
++{
++ struct scatterlist sg[MAX_SKB_FRAGS + 8];
++ struct sk_buff *trailer;
++ unsigned int offset;
++ int num_frags;
++
++ if (unlikely(!key))
++ return false;
++
++ if (unlikely(!READ_ONCE(key->is_valid) ||
++ wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
++ key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
++ WRITE_ONCE(key->is_valid, false);
++ return false;
++ }
++
++ PACKET_CB(skb)->nonce =
++ le64_to_cpu(((struct message_data *)skb->data)->counter);
++
++ /* We ensure that the network header is part of the packet before we
++ * call skb_cow_data, so that there's no chance that data is removed
++ * from the skb, so that later we can extract the original endpoint.
++ */
++ offset = skb->data - skb_network_header(skb);
++ skb_push(skb, offset);
++ num_frags = skb_cow_data(skb, 0, &trailer);
++ offset += sizeof(struct message_data);
++ skb_pull(skb, offset);
++ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg)))
++ return false;
++
++ sg_init_table(sg, num_frags);
++ if (skb_to_sgvec(skb, sg, 0, skb->len) <= 0)
++ return false;
++
++ if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
++ PACKET_CB(skb)->nonce,
++ key->key))
++ return false;
++
++ /* Another ugly situation of pushing and pulling the header so as to
++ * keep endpoint information intact.
++ */
++ skb_push(skb, offset);
++ if (pskb_trim(skb, skb->len - noise_encrypted_len(0)))
++ return false;
++ skb_pull(skb, offset);
++
++ return true;
++}
++
++/* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
++static bool counter_validate(union noise_counter *counter, u64 their_counter)
++{
++ unsigned long index, index_current, top, i;
++ bool ret = false;
++
++ spin_lock_bh(&counter->receive.lock);
++
++ if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
++ their_counter >= REJECT_AFTER_MESSAGES))
++ goto out;
++
++ ++their_counter;
++
++ if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
++ counter->receive.counter))
++ goto out;
++
++ index = their_counter >> ilog2(BITS_PER_LONG);
++
++ if (likely(their_counter > counter->receive.counter)) {
++ index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
++ top = min_t(unsigned long, index - index_current,
++ COUNTER_BITS_TOTAL / BITS_PER_LONG);
++ for (i = 1; i <= top; ++i)
++ counter->receive.backtrack[(i + index_current) &
++ ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
++ counter->receive.counter = their_counter;
++ }
++
++ index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
++ ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
++ &counter->receive.backtrack[index]);
++
++out:
++ spin_unlock_bh(&counter->receive.lock);
++ return ret;
++}
++
++#include "selftest/counter.c"
++
++static void wg_packet_consume_data_done(struct wg_peer *peer,
++ struct sk_buff *skb,
++ struct endpoint *endpoint)
++{
++ struct net_device *dev = peer->device->dev;
++ unsigned int len, len_before_trim;
++ struct wg_peer *routed_peer;
++
++ wg_socket_set_peer_endpoint(peer, endpoint);
++
++ if (unlikely(wg_noise_received_with_keypair(&peer->keypairs,
++ PACKET_CB(skb)->keypair))) {
++ wg_timers_handshake_complete(peer);
++ wg_packet_send_staged_packets(peer);
++ }
++
++ keep_key_fresh(peer);
++
++ wg_timers_any_authenticated_packet_received(peer);
++ wg_timers_any_authenticated_packet_traversal(peer);
++
++ /* A packet with length 0 is a keepalive packet */
++ if (unlikely(!skb->len)) {
++ update_rx_stats(peer, message_data_len(0));
++ net_dbg_ratelimited("%s: Receiving keepalive packet from peer %llu (%pISpfsc)\n",
++ dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++ goto packet_processed;
++ }
++
++ wg_timers_data_received(peer);
++
++ if (unlikely(skb_network_header(skb) < skb->head))
++ goto dishonest_packet_size;
++ if (unlikely(!(pskb_network_may_pull(skb, sizeof(struct iphdr)) &&
++ (ip_hdr(skb)->version == 4 ||
++ (ip_hdr(skb)->version == 6 &&
++ pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))))))
++ goto dishonest_packet_type;
++
++ skb->dev = dev;
++ /* We've already verified the Poly1305 auth tag, which means this packet
++ * was not modified in transit. We can therefore tell the networking
++ * stack that all checksums of every layer of encapsulation have already
++ * been checked "by the hardware" and therefore is unneccessary to check
++ * again in software.
++ */
++ skb->ip_summed = CHECKSUM_UNNECESSARY;
++ skb->csum_level = ~0; /* All levels */
++ skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb);
++ if (skb->protocol == htons(ETH_P_IP)) {
++ len = ntohs(ip_hdr(skb)->tot_len);
++ if (unlikely(len < sizeof(struct iphdr)))
++ goto dishonest_packet_size;
++ if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
++ IP_ECN_set_ce(ip_hdr(skb));
++ } else if (skb->protocol == htons(ETH_P_IPV6)) {
++ len = ntohs(ipv6_hdr(skb)->payload_len) +
++ sizeof(struct ipv6hdr);
++ if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
++ IP6_ECN_set_ce(skb, ipv6_hdr(skb));
++ } else {
++ goto dishonest_packet_type;
++ }
++
++ if (unlikely(len > skb->len))
++ goto dishonest_packet_size;
++ len_before_trim = skb->len;
++ if (unlikely(pskb_trim(skb, len)))
++ goto packet_processed;
++
++ routed_peer = wg_allowedips_lookup_src(&peer->device->peer_allowedips,
++ skb);
++ wg_peer_put(routed_peer); /* We don't need the extra reference. */
++
++ if (unlikely(routed_peer != peer))
++ goto dishonest_packet_peer;
++
++ if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
++ ++dev->stats.rx_dropped;
++ net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
++ dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++ } else {
++ update_rx_stats(peer, message_data_len(len_before_trim));
++ }
++ return;
++
++dishonest_packet_peer:
++ net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n",
++ dev->name, skb, peer->internal_id,
++ &peer->endpoint.addr);
++ ++dev->stats.rx_errors;
++ ++dev->stats.rx_frame_errors;
++ goto packet_processed;
++dishonest_packet_type:
++ net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n",
++ dev->name, peer->internal_id, &peer->endpoint.addr);
++ ++dev->stats.rx_errors;
++ ++dev->stats.rx_frame_errors;
++ goto packet_processed;
++dishonest_packet_size:
++ net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n",
++ dev->name, peer->internal_id, &peer->endpoint.addr);
++ ++dev->stats.rx_errors;
++ ++dev->stats.rx_length_errors;
++ goto packet_processed;
++packet_processed:
++ dev_kfree_skb(skb);
++}
++
++int wg_packet_rx_poll(struct napi_struct *napi, int budget)
++{
++ struct wg_peer *peer = container_of(napi, struct wg_peer, napi);
++ struct crypt_queue *queue = &peer->rx_queue;
++ struct noise_keypair *keypair;
++ struct endpoint endpoint;
++ enum packet_state state;
++ struct sk_buff *skb;
++ int work_done = 0;
++ bool free;
++
++ if (unlikely(budget <= 0))
++ return 0;
++
++ while ((skb = __ptr_ring_peek(&queue->ring)) != NULL &&
++ (state = atomic_read_acquire(&PACKET_CB(skb)->state)) !=
++ PACKET_STATE_UNCRYPTED) {
++ __ptr_ring_discard_one(&queue->ring);
++ peer = PACKET_PEER(skb);
++ keypair = PACKET_CB(skb)->keypair;
++ free = true;
++
++ if (unlikely(state != PACKET_STATE_CRYPTED))
++ goto next;
++
++ if (unlikely(!counter_validate(&keypair->receiving.counter,
++ PACKET_CB(skb)->nonce))) {
++ net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
++ peer->device->dev->name,
++ PACKET_CB(skb)->nonce,
++ keypair->receiving.counter.receive.counter);
++ goto next;
++ }
++
++ if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
++ goto next;
++
++ wg_reset_packet(skb);
++ wg_packet_consume_data_done(peer, skb, &endpoint);
++ free = false;
++
++next:
++ wg_noise_keypair_put(keypair, false);
++ wg_peer_put(peer);
++ if (unlikely(free))
++ dev_kfree_skb(skb);
++
++ if (++work_done >= budget)
++ break;
++ }
++
++ if (work_done < budget)
++ napi_complete_done(napi, work_done);
++
++ return work_done;
++}
++
++void wg_packet_decrypt_worker(struct work_struct *work)
++{
++ struct crypt_queue *queue = container_of(work, struct multicore_worker,
++ work)->ptr;
++ struct sk_buff *skb;
++
++ while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
++ enum packet_state state = likely(decrypt_packet(skb,
++ &PACKET_CB(skb)->keypair->receiving)) ?
++ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
++ wg_queue_enqueue_per_peer_napi(skb, state);
++ }
++}
++
++static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
++{
++ __le32 idx = ((struct message_data *)skb->data)->key_idx;
++ struct wg_peer *peer = NULL;
++ int ret;
++
++ rcu_read_lock_bh();
++ PACKET_CB(skb)->keypair =
++ (struct noise_keypair *)wg_index_hashtable_lookup(
++ wg->index_hashtable, INDEX_HASHTABLE_KEYPAIR, idx,
++ &peer);
++ if (unlikely(!wg_noise_keypair_get(PACKET_CB(skb)->keypair)))
++ goto err_keypair;
++
++ if (unlikely(READ_ONCE(peer->is_dead)))
++ goto err;
++
++ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue,
++ &peer->rx_queue, skb,
++ wg->packet_crypt_wq,
++ &wg->decrypt_queue.last_cpu);
++ if (unlikely(ret == -EPIPE))
++ wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD);
++ if (likely(!ret || ret == -EPIPE)) {
++ rcu_read_unlock_bh();
++ return;
++ }
++err:
++ wg_noise_keypair_put(PACKET_CB(skb)->keypair, false);
++err_keypair:
++ rcu_read_unlock_bh();
++ wg_peer_put(peer);
++ dev_kfree_skb(skb);
++}
++
++void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb)
++{
++ if (unlikely(prepare_skb_header(skb, wg) < 0))
++ goto err;
++ switch (SKB_TYPE_LE32(skb)) {
++ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION):
++ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE):
++ case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): {
++ int cpu;
++
++ if (skb_queue_len(&wg->incoming_handshakes) >
++ MAX_QUEUED_INCOMING_HANDSHAKES ||
++ unlikely(!rng_is_initialized())) {
++ net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n",
++ wg->dev->name, skb);
++ goto err;
++ }
++ skb_queue_tail(&wg->incoming_handshakes, skb);
++ /* Queues up a call to packet_process_queued_handshake_
++ * packets(skb):
++ */
++ cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu);
++ queue_work_on(cpu, wg->handshake_receive_wq,
++ &per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work);
++ break;
++ }
++ case cpu_to_le32(MESSAGE_DATA):
++ PACKET_CB(skb)->ds = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
++ wg_packet_consume_data(wg, skb);
++ break;
++ default:
++ net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n",
++ wg->dev->name, skb);
++ goto err;
++ }
++ return;
++
++err:
++ dev_kfree_skb(skb);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/selftest/allowedips.c
+@@ -0,0 +1,683 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ *
++ * This contains some basic static unit tests for the allowedips data structure.
++ * It also has two additional modes that are disabled and meant to be used by
++ * folks directly playing with this file. If you define the macro
++ * DEBUG_PRINT_TRIE_GRAPHVIZ to be 1, then every time there's a full tree in
++ * memory, it will be printed out as KERN_DEBUG in a format that can be passed
++ * to graphviz (the dot command) to visualize it. If you define the macro
++ * DEBUG_RANDOM_TRIE to be 1, then there will be an extremely costly set of
++ * randomized tests done against a trivial implementation, which may take
++ * upwards of a half-hour to complete. There's no set of users who should be
++ * enabling these, and the only developers that should go anywhere near these
++ * nobs are the ones who are reading this comment.
++ */
++
++#ifdef DEBUG
++
++#include <linux/siphash.h>
++
++static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits,
++ u8 cidr)
++{
++ swap_endian(dst, src, bits);
++ memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8);
++ if (cidr)
++ dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8);
++}
++
++static __init void print_node(struct allowedips_node *node, u8 bits)
++{
++ char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n";
++ char *fmt_declaration = KERN_DEBUG
++ "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
++ char *style = "dotted";
++ u8 ip1[16], ip2[16];
++ u32 color = 0;
++
++ if (bits == 32) {
++ fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n";
++ fmt_declaration = KERN_DEBUG
++ "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
++ } else if (bits == 128) {
++ fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n";
++ fmt_declaration = KERN_DEBUG
++ "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
++ }
++ if (node->peer) {
++ hsiphash_key_t key = { { 0 } };
++
++ memcpy(&key, &node->peer, sizeof(node->peer));
++ color = hsiphash_1u32(0xdeadbeef, &key) % 200 << 16 |
++ hsiphash_1u32(0xbabecafe, &key) % 200 << 8 |
++ hsiphash_1u32(0xabad1dea, &key) % 200;
++ style = "bold";
++ }
++ swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr);
++ printk(fmt_declaration, ip1, node->cidr, style, color);
++ if (node->bit[0]) {
++ swap_endian_and_apply_cidr(ip2,
++ rcu_dereference_raw(node->bit[0])->bits, bits,
++ node->cidr);
++ printk(fmt_connection, ip1, node->cidr, ip2,
++ rcu_dereference_raw(node->bit[0])->cidr);
++ print_node(rcu_dereference_raw(node->bit[0]), bits);
++ }
++ if (node->bit[1]) {
++ swap_endian_and_apply_cidr(ip2,
++ rcu_dereference_raw(node->bit[1])->bits,
++ bits, node->cidr);
++ printk(fmt_connection, ip1, node->cidr, ip2,
++ rcu_dereference_raw(node->bit[1])->cidr);
++ print_node(rcu_dereference_raw(node->bit[1]), bits);
++ }
++}
++
++static __init void print_tree(struct allowedips_node __rcu *top, u8 bits)
++{
++ printk(KERN_DEBUG "digraph trie {\n");
++ print_node(rcu_dereference_raw(top), bits);
++ printk(KERN_DEBUG "}\n");
++}
++
++enum {
++ NUM_PEERS = 2000,
++ NUM_RAND_ROUTES = 400,
++ NUM_MUTATED_ROUTES = 100,
++ NUM_QUERIES = NUM_RAND_ROUTES * NUM_MUTATED_ROUTES * 30
++};
++
++struct horrible_allowedips {
++ struct hlist_head head;
++};
++
++struct horrible_allowedips_node {
++ struct hlist_node table;
++ union nf_inet_addr ip;
++ union nf_inet_addr mask;
++ u8 ip_version;
++ void *value;
++};
++
++static __init void horrible_allowedips_init(struct horrible_allowedips *table)
++{
++ INIT_HLIST_HEAD(&table->head);
++}
++
++static __init void horrible_allowedips_free(struct horrible_allowedips *table)
++{
++ struct horrible_allowedips_node *node;
++ struct hlist_node *h;
++
++ hlist_for_each_entry_safe(node, h, &table->head, table) {
++ hlist_del(&node->table);
++ kfree(node);
++ }
++}
++
++static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr)
++{
++ union nf_inet_addr mask;
++
++ memset(&mask, 0x00, 128 / 8);
++ memset(&mask, 0xff, cidr / 8);
++ if (cidr % 32)
++ mask.all[cidr / 32] = (__force u32)htonl(
++ (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL);
++ return mask;
++}
++
++static __init inline u8 horrible_mask_to_cidr(union nf_inet_addr subnet)
++{
++ return hweight32(subnet.all[0]) + hweight32(subnet.all[1]) +
++ hweight32(subnet.all[2]) + hweight32(subnet.all[3]);
++}
++
++static __init inline void
++horrible_mask_self(struct horrible_allowedips_node *node)
++{
++ if (node->ip_version == 4) {
++ node->ip.ip &= node->mask.ip;
++ } else if (node->ip_version == 6) {
++ node->ip.ip6[0] &= node->mask.ip6[0];
++ node->ip.ip6[1] &= node->mask.ip6[1];
++ node->ip.ip6[2] &= node->mask.ip6[2];
++ node->ip.ip6[3] &= node->mask.ip6[3];
++ }
++}
++
++static __init inline bool
++horrible_match_v4(const struct horrible_allowedips_node *node,
++ struct in_addr *ip)
++{
++ return (ip->s_addr & node->mask.ip) == node->ip.ip;
++}
++
++static __init inline bool
++horrible_match_v6(const struct horrible_allowedips_node *node,
++ struct in6_addr *ip)
++{
++ return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) ==
++ node->ip.ip6[0] &&
++ (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) ==
++ node->ip.ip6[1] &&
++ (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) ==
++ node->ip.ip6[2] &&
++ (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3];
++}
++
++static __init void
++horrible_insert_ordered(struct horrible_allowedips *table,
++ struct horrible_allowedips_node *node)
++{
++ struct horrible_allowedips_node *other = NULL, *where = NULL;
++ u8 my_cidr = horrible_mask_to_cidr(node->mask);
++
++ hlist_for_each_entry(other, &table->head, table) {
++ if (!memcmp(&other->mask, &node->mask,
++ sizeof(union nf_inet_addr)) &&
++ !memcmp(&other->ip, &node->ip,
++ sizeof(union nf_inet_addr)) &&
++ other->ip_version == node->ip_version) {
++ other->value = node->value;
++ kfree(node);
++ return;
++ }
++ where = other;
++ if (horrible_mask_to_cidr(other->mask) <= my_cidr)
++ break;
++ }
++ if (!other && !where)
++ hlist_add_head(&node->table, &table->head);
++ else if (!other)
++ hlist_add_behind(&node->table, &where->table);
++ else
++ hlist_add_before(&node->table, &where->table);
++}
++
++static __init int
++horrible_allowedips_insert_v4(struct horrible_allowedips *table,
++ struct in_addr *ip, u8 cidr, void *value)
++{
++ struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
++ GFP_KERNEL);
++
++ if (unlikely(!node))
++ return -ENOMEM;
++ node->ip.in = *ip;
++ node->mask = horrible_cidr_to_mask(cidr);
++ node->ip_version = 4;
++ node->value = value;
++ horrible_mask_self(node);
++ horrible_insert_ordered(table, node);
++ return 0;
++}
++
++static __init int
++horrible_allowedips_insert_v6(struct horrible_allowedips *table,
++ struct in6_addr *ip, u8 cidr, void *value)
++{
++ struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
++ GFP_KERNEL);
++
++ if (unlikely(!node))
++ return -ENOMEM;
++ node->ip.in6 = *ip;
++ node->mask = horrible_cidr_to_mask(cidr);
++ node->ip_version = 6;
++ node->value = value;
++ horrible_mask_self(node);
++ horrible_insert_ordered(table, node);
++ return 0;
++}
++
++static __init void *
++horrible_allowedips_lookup_v4(struct horrible_allowedips *table,
++ struct in_addr *ip)
++{
++ struct horrible_allowedips_node *node;
++ void *ret = NULL;
++
++ hlist_for_each_entry(node, &table->head, table) {
++ if (node->ip_version != 4)
++ continue;
++ if (horrible_match_v4(node, ip)) {
++ ret = node->value;
++ break;
++ }
++ }
++ return ret;
++}
++
++static __init void *
++horrible_allowedips_lookup_v6(struct horrible_allowedips *table,
++ struct in6_addr *ip)
++{
++ struct horrible_allowedips_node *node;
++ void *ret = NULL;
++
++ hlist_for_each_entry(node, &table->head, table) {
++ if (node->ip_version != 6)
++ continue;
++ if (horrible_match_v6(node, ip)) {
++ ret = node->value;
++ break;
++ }
++ }
++ return ret;
++}
++
++static __init bool randomized_test(void)
++{
++ unsigned int i, j, k, mutate_amount, cidr;
++ u8 ip[16], mutate_mask[16], mutated[16];
++ struct wg_peer **peers, *peer;
++ struct horrible_allowedips h;
++ DEFINE_MUTEX(mutex);
++ struct allowedips t;
++ bool ret = false;
++
++ mutex_init(&mutex);
++
++ wg_allowedips_init(&t);
++ horrible_allowedips_init(&h);
++
++ peers = kcalloc(NUM_PEERS, sizeof(*peers), GFP_KERNEL);
++ if (unlikely(!peers)) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free;
++ }
++ for (i = 0; i < NUM_PEERS; ++i) {
++ peers[i] = kzalloc(sizeof(*peers[i]), GFP_KERNEL);
++ if (unlikely(!peers[i])) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free;
++ }
++ kref_init(&peers[i]->refcount);
++ }
++
++ mutex_lock(&mutex);
++
++ for (i = 0; i < NUM_RAND_ROUTES; ++i) {
++ prandom_bytes(ip, 4);
++ cidr = prandom_u32_max(32) + 1;
++ peer = peers[prandom_u32_max(NUM_PEERS)];
++ if (wg_allowedips_insert_v4(&t, (struct in_addr *)ip, cidr,
++ peer, &mutex) < 0) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ if (horrible_allowedips_insert_v4(&h, (struct in_addr *)ip,
++ cidr, peer) < 0) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) {
++ memcpy(mutated, ip, 4);
++ prandom_bytes(mutate_mask, 4);
++ mutate_amount = prandom_u32_max(32);
++ for (k = 0; k < mutate_amount / 8; ++k)
++ mutate_mask[k] = 0xff;
++ mutate_mask[k] = 0xff
++ << ((8 - (mutate_amount % 8)) % 8);
++ for (; k < 4; ++k)
++ mutate_mask[k] = 0;
++ for (k = 0; k < 4; ++k)
++ mutated[k] = (mutated[k] & mutate_mask[k]) |
++ (~mutate_mask[k] &
++ prandom_u32_max(256));
++ cidr = prandom_u32_max(32) + 1;
++ peer = peers[prandom_u32_max(NUM_PEERS)];
++ if (wg_allowedips_insert_v4(&t,
++ (struct in_addr *)mutated,
++ cidr, peer, &mutex) < 0) {
++ pr_err("allowedips random malloc: FAIL\n");
++ goto free_locked;
++ }
++ if (horrible_allowedips_insert_v4(&h,
++ (struct in_addr *)mutated, cidr, peer)) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ }
++ }
++
++ for (i = 0; i < NUM_RAND_ROUTES; ++i) {
++ prandom_bytes(ip, 16);
++ cidr = prandom_u32_max(128) + 1;
++ peer = peers[prandom_u32_max(NUM_PEERS)];
++ if (wg_allowedips_insert_v6(&t, (struct in6_addr *)ip, cidr,
++ peer, &mutex) < 0) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ if (horrible_allowedips_insert_v6(&h, (struct in6_addr *)ip,
++ cidr, peer) < 0) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) {
++ memcpy(mutated, ip, 16);
++ prandom_bytes(mutate_mask, 16);
++ mutate_amount = prandom_u32_max(128);
++ for (k = 0; k < mutate_amount / 8; ++k)
++ mutate_mask[k] = 0xff;
++ mutate_mask[k] = 0xff
++ << ((8 - (mutate_amount % 8)) % 8);
++ for (; k < 4; ++k)
++ mutate_mask[k] = 0;
++ for (k = 0; k < 4; ++k)
++ mutated[k] = (mutated[k] & mutate_mask[k]) |
++ (~mutate_mask[k] &
++ prandom_u32_max(256));
++ cidr = prandom_u32_max(128) + 1;
++ peer = peers[prandom_u32_max(NUM_PEERS)];
++ if (wg_allowedips_insert_v6(&t,
++ (struct in6_addr *)mutated,
++ cidr, peer, &mutex) < 0) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ if (horrible_allowedips_insert_v6(
++ &h, (struct in6_addr *)mutated, cidr,
++ peer)) {
++ pr_err("allowedips random self-test malloc: FAIL\n");
++ goto free_locked;
++ }
++ }
++ }
++
++ mutex_unlock(&mutex);
++
++ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) {
++ print_tree(t.root4, 32);
++ print_tree(t.root6, 128);
++ }
++
++ for (i = 0; i < NUM_QUERIES; ++i) {
++ prandom_bytes(ip, 4);
++ if (lookup(t.root4, 32, ip) !=
++ horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
++ pr_err("allowedips random self-test: FAIL\n");
++ goto free;
++ }
++ }
++
++ for (i = 0; i < NUM_QUERIES; ++i) {
++ prandom_bytes(ip, 16);
++ if (lookup(t.root6, 128, ip) !=
++ horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
++ pr_err("allowedips random self-test: FAIL\n");
++ goto free;
++ }
++ }
++ ret = true;
++
++free:
++ mutex_lock(&mutex);
++free_locked:
++ wg_allowedips_free(&t, &mutex);
++ mutex_unlock(&mutex);
++ horrible_allowedips_free(&h);
++ if (peers) {
++ for (i = 0; i < NUM_PEERS; ++i)
++ kfree(peers[i]);
++ }
++ kfree(peers);
++ return ret;
++}
++
++static __init inline struct in_addr *ip4(u8 a, u8 b, u8 c, u8 d)
++{
++ static struct in_addr ip;
++ u8 *split = (u8 *)&ip;
++
++ split[0] = a;
++ split[1] = b;
++ split[2] = c;
++ split[3] = d;
++ return &ip;
++}
++
++static __init inline struct in6_addr *ip6(u32 a, u32 b, u32 c, u32 d)
++{
++ static struct in6_addr ip;
++ __be32 *split = (__be32 *)&ip;
++
++ split[0] = cpu_to_be32(a);
++ split[1] = cpu_to_be32(b);
++ split[2] = cpu_to_be32(c);
++ split[3] = cpu_to_be32(d);
++ return &ip;
++}
++
++static __init struct wg_peer *init_peer(void)
++{
++ struct wg_peer *peer = kzalloc(sizeof(*peer), GFP_KERNEL);
++
++ if (!peer)
++ return NULL;
++ kref_init(&peer->refcount);
++ INIT_LIST_HEAD(&peer->allowedips_list);
++ return peer;
++}
++
++#define insert(version, mem, ipa, ipb, ipc, ipd, cidr) \
++ wg_allowedips_insert_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \
++ cidr, mem, &mutex)
++
++#define maybe_fail() do { \
++ ++i; \
++ if (!_s) { \
++ pr_info("allowedips self-test %zu: FAIL\n", i); \
++ success = false; \
++ } \
++ } while (0)
++
++#define test(version, mem, ipa, ipb, ipc, ipd) do { \
++ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \
++ ip##version(ipa, ipb, ipc, ipd)) == (mem); \
++ maybe_fail(); \
++ } while (0)
++
++#define test_negative(version, mem, ipa, ipb, ipc, ipd) do { \
++ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \
++ ip##version(ipa, ipb, ipc, ipd)) != (mem); \
++ maybe_fail(); \
++ } while (0)
++
++#define test_boolean(cond) do { \
++ bool _s = (cond); \
++ maybe_fail(); \
++ } while (0)
++
++bool __init wg_allowedips_selftest(void)
++{
++ bool found_a = false, found_b = false, found_c = false, found_d = false,
++ found_e = false, found_other = false;
++ struct wg_peer *a = init_peer(), *b = init_peer(), *c = init_peer(),
++ *d = init_peer(), *e = init_peer(), *f = init_peer(),
++ *g = init_peer(), *h = init_peer();
++ struct allowedips_node *iter_node;
++ bool success = false;
++ struct allowedips t;
++ DEFINE_MUTEX(mutex);
++ struct in6_addr ip;
++ size_t i = 0, count = 0;
++ __be64 part;
++
++ mutex_init(&mutex);
++ mutex_lock(&mutex);
++ wg_allowedips_init(&t);
++
++ if (!a || !b || !c || !d || !e || !f || !g || !h) {
++ pr_err("allowedips self-test malloc: FAIL\n");
++ goto free;
++ }
++
++ insert(4, a, 192, 168, 4, 0, 24);
++ insert(4, b, 192, 168, 4, 4, 32);
++ insert(4, c, 192, 168, 0, 0, 16);
++ insert(4, d, 192, 95, 5, 64, 27);
++ /* replaces previous entry, and maskself is required */
++ insert(4, c, 192, 95, 5, 65, 27);
++ insert(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128);
++ insert(6, c, 0x26075300, 0x60006b00, 0, 0, 64);
++ insert(4, e, 0, 0, 0, 0, 0);
++ insert(6, e, 0, 0, 0, 0, 0);
++ /* replaces previous entry */
++ insert(6, f, 0, 0, 0, 0, 0);
++ insert(6, g, 0x24046800, 0, 0, 0, 32);
++ /* maskself is required */
++ insert(6, h, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 64);
++ insert(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 128);
++ insert(6, c, 0x24446800, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128);
++ insert(6, b, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98);
++ insert(4, g, 64, 15, 112, 0, 20);
++ /* maskself is required */
++ insert(4, h, 64, 15, 123, 211, 25);
++ insert(4, a, 10, 0, 0, 0, 25);
++ insert(4, b, 10, 0, 0, 128, 25);
++ insert(4, a, 10, 1, 0, 0, 30);
++ insert(4, b, 10, 1, 0, 4, 30);
++ insert(4, c, 10, 1, 0, 8, 29);
++ insert(4, d, 10, 1, 0, 16, 29);
++
++ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) {
++ print_tree(t.root4, 32);
++ print_tree(t.root6, 128);
++ }
++
++ success = true;
++
++ test(4, a, 192, 168, 4, 20);
++ test(4, a, 192, 168, 4, 0);
++ test(4, b, 192, 168, 4, 4);
++ test(4, c, 192, 168, 200, 182);
++ test(4, c, 192, 95, 5, 68);
++ test(4, e, 192, 95, 5, 96);
++ test(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543);
++ test(6, c, 0x26075300, 0x60006b00, 0, 0xc02e01ee);
++ test(6, f, 0x26075300, 0x60006b01, 0, 0);
++ test(6, g, 0x24046800, 0x40040806, 0, 0x1006);
++ test(6, g, 0x24046800, 0x40040806, 0x1234, 0x5678);
++ test(6, f, 0x240467ff, 0x40040806, 0x1234, 0x5678);
++ test(6, f, 0x24046801, 0x40040806, 0x1234, 0x5678);
++ test(6, h, 0x24046800, 0x40040800, 0x1234, 0x5678);
++ test(6, h, 0x24046800, 0x40040800, 0, 0);
++ test(6, h, 0x24046800, 0x40040800, 0x10101010, 0x10101010);
++ test(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef);
++ test(4, g, 64, 15, 116, 26);
++ test(4, g, 64, 15, 127, 3);
++ test(4, g, 64, 15, 123, 1);
++ test(4, h, 64, 15, 123, 128);
++ test(4, h, 64, 15, 123, 129);
++ test(4, a, 10, 0, 0, 52);
++ test(4, b, 10, 0, 0, 220);
++ test(4, a, 10, 1, 0, 2);
++ test(4, b, 10, 1, 0, 6);
++ test(4, c, 10, 1, 0, 10);
++ test(4, d, 10, 1, 0, 20);
++
++ insert(4, a, 1, 0, 0, 0, 32);
++ insert(4, a, 64, 0, 0, 0, 32);
++ insert(4, a, 128, 0, 0, 0, 32);
++ insert(4, a, 192, 0, 0, 0, 32);
++ insert(4, a, 255, 0, 0, 0, 32);
++ wg_allowedips_remove_by_peer(&t, a, &mutex);
++ test_negative(4, a, 1, 0, 0, 0);
++ test_negative(4, a, 64, 0, 0, 0);
++ test_negative(4, a, 128, 0, 0, 0);
++ test_negative(4, a, 192, 0, 0, 0);
++ test_negative(4, a, 255, 0, 0, 0);
++
++ wg_allowedips_free(&t, &mutex);
++ wg_allowedips_init(&t);
++ insert(4, a, 192, 168, 0, 0, 16);
++ insert(4, a, 192, 168, 0, 0, 24);
++ wg_allowedips_remove_by_peer(&t, a, &mutex);
++ test_negative(4, a, 192, 168, 0, 1);
++
++ /* These will hit the WARN_ON(len >= 128) in free_node if something
++ * goes wrong.
++ */
++ for (i = 0; i < 128; ++i) {
++ part = cpu_to_be64(~(1LLU << (i % 64)));
++ memset(&ip, 0xff, 16);
++ memcpy((u8 *)&ip + (i < 64) * 8, &part, 8);
++ wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
++ }
++
++ wg_allowedips_free(&t, &mutex);
++
++ wg_allowedips_init(&t);
++ insert(4, a, 192, 95, 5, 93, 27);
++ insert(6, a, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128);
++ insert(4, a, 10, 1, 0, 20, 29);
++ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 83);
++ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 21);
++ list_for_each_entry(iter_node, &a->allowedips_list, peer_list) {
++ u8 cidr, ip[16] __aligned(__alignof(u64));
++ int family = wg_allowedips_read_node(iter_node, ip, &cidr);
++
++ count++;
++
++ if (cidr == 27 && family == AF_INET &&
++ !memcmp(ip, ip4(192, 95, 5, 64), sizeof(struct in_addr)))
++ found_a = true;
++ else if (cidr == 128 && family == AF_INET6 &&
++ !memcmp(ip, ip6(0x26075300, 0x60006b00, 0, 0xc05f0543),
++ sizeof(struct in6_addr)))
++ found_b = true;
++ else if (cidr == 29 && family == AF_INET &&
++ !memcmp(ip, ip4(10, 1, 0, 16), sizeof(struct in_addr)))
++ found_c = true;
++ else if (cidr == 83 && family == AF_INET6 &&
++ !memcmp(ip, ip6(0x26075300, 0x6d8a6bf8, 0xdab1e000, 0),
++ sizeof(struct in6_addr)))
++ found_d = true;
++ else if (cidr == 21 && family == AF_INET6 &&
++ !memcmp(ip, ip6(0x26075000, 0, 0, 0),
++ sizeof(struct in6_addr)))
++ found_e = true;
++ else
++ found_other = true;
++ }
++ test_boolean(count == 5);
++ test_boolean(found_a);
++ test_boolean(found_b);
++ test_boolean(found_c);
++ test_boolean(found_d);
++ test_boolean(found_e);
++ test_boolean(!found_other);
++
++ if (IS_ENABLED(DEBUG_RANDOM_TRIE) && success)
++ success = randomized_test();
++
++ if (success)
++ pr_info("allowedips self-tests: pass\n");
++
++free:
++ wg_allowedips_free(&t, &mutex);
++ kfree(a);
++ kfree(b);
++ kfree(c);
++ kfree(d);
++ kfree(e);
++ kfree(f);
++ kfree(g);
++ kfree(h);
++ mutex_unlock(&mutex);
++
++ return success;
++}
++
++#undef test_negative
++#undef test
++#undef remove
++#undef insert
++#undef init_peer
++
++#endif
+--- /dev/null
++++ b/drivers/net/wireguard/selftest/counter.c
+@@ -0,0 +1,104 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifdef DEBUG
++bool __init wg_packet_counter_selftest(void)
++{
++ unsigned int test_num = 0, i;
++ union noise_counter counter;
++ bool success = true;
++
++#define T_INIT do { \
++ memset(&counter, 0, sizeof(union noise_counter)); \
++ spin_lock_init(&counter.receive.lock); \
++ } while (0)
++#define T_LIM (COUNTER_WINDOW_SIZE + 1)
++#define T(n, v) do { \
++ ++test_num; \
++ if (counter_validate(&counter, n) != (v)) { \
++ pr_err("nonce counter self-test %u: FAIL\n", \
++ test_num); \
++ success = false; \
++ } \
++ } while (0)
++
++ T_INIT;
++ /* 1 */ T(0, true);
++ /* 2 */ T(1, true);
++ /* 3 */ T(1, false);
++ /* 4 */ T(9, true);
++ /* 5 */ T(8, true);
++ /* 6 */ T(7, true);
++ /* 7 */ T(7, false);
++ /* 8 */ T(T_LIM, true);
++ /* 9 */ T(T_LIM - 1, true);
++ /* 10 */ T(T_LIM - 1, false);
++ /* 11 */ T(T_LIM - 2, true);
++ /* 12 */ T(2, true);
++ /* 13 */ T(2, false);
++ /* 14 */ T(T_LIM + 16, true);
++ /* 15 */ T(3, false);
++ /* 16 */ T(T_LIM + 16, false);
++ /* 17 */ T(T_LIM * 4, true);
++ /* 18 */ T(T_LIM * 4 - (T_LIM - 1), true);
++ /* 19 */ T(10, false);
++ /* 20 */ T(T_LIM * 4 - T_LIM, false);
++ /* 21 */ T(T_LIM * 4 - (T_LIM + 1), false);
++ /* 22 */ T(T_LIM * 4 - (T_LIM - 2), true);
++ /* 23 */ T(T_LIM * 4 + 1 - T_LIM, false);
++ /* 24 */ T(0, false);
++ /* 25 */ T(REJECT_AFTER_MESSAGES, false);
++ /* 26 */ T(REJECT_AFTER_MESSAGES - 1, true);
++ /* 27 */ T(REJECT_AFTER_MESSAGES, false);
++ /* 28 */ T(REJECT_AFTER_MESSAGES - 1, false);
++ /* 29 */ T(REJECT_AFTER_MESSAGES - 2, true);
++ /* 30 */ T(REJECT_AFTER_MESSAGES + 1, false);
++ /* 31 */ T(REJECT_AFTER_MESSAGES + 2, false);
++ /* 32 */ T(REJECT_AFTER_MESSAGES - 2, false);
++ /* 33 */ T(REJECT_AFTER_MESSAGES - 3, true);
++ /* 34 */ T(0, false);
++
++ T_INIT;
++ for (i = 1; i <= COUNTER_WINDOW_SIZE; ++i)
++ T(i, true);
++ T(0, true);
++ T(0, false);
++
++ T_INIT;
++ for (i = 2; i <= COUNTER_WINDOW_SIZE + 1; ++i)
++ T(i, true);
++ T(1, true);
++ T(0, false);
++
++ T_INIT;
++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 0;)
++ T(i, true);
++
++ T_INIT;
++ for (i = COUNTER_WINDOW_SIZE + 2; i-- > 1;)
++ T(i, true);
++ T(0, false);
++
++ T_INIT;
++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;)
++ T(i, true);
++ T(COUNTER_WINDOW_SIZE + 1, true);
++ T(0, false);
++
++ T_INIT;
++ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;)
++ T(i, true);
++ T(0, true);
++ T(COUNTER_WINDOW_SIZE + 1, true);
++
++#undef T
++#undef T_LIM
++#undef T_INIT
++
++ if (success)
++ pr_info("nonce counter self-tests: pass\n");
++ return success;
++}
++#endif
+--- /dev/null
++++ b/drivers/net/wireguard/selftest/ratelimiter.c
+@@ -0,0 +1,226 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifdef DEBUG
++
++#include <linux/jiffies.h>
++
++static const struct {
++ bool result;
++ unsigned int msec_to_sleep_before;
++} expected_results[] __initconst = {
++ [0 ... PACKETS_BURSTABLE - 1] = { true, 0 },
++ [PACKETS_BURSTABLE] = { false, 0 },
++ [PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND },
++ [PACKETS_BURSTABLE + 2] = { false, 0 },
++ [PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
++ [PACKETS_BURSTABLE + 4] = { true, 0 },
++ [PACKETS_BURSTABLE + 5] = { false, 0 }
++};
++
++static __init unsigned int maximum_jiffies_at_index(int index)
++{
++ unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3;
++ int i;
++
++ for (i = 0; i <= index; ++i)
++ total_msecs += expected_results[i].msec_to_sleep_before;
++ return msecs_to_jiffies(total_msecs);
++}
++
++static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
++ struct sk_buff *skb6, struct ipv6hdr *hdr6,
++ int *test)
++{
++ unsigned long loop_start_time;
++ int i;
++
++ wg_ratelimiter_gc_entries(NULL);
++ rcu_barrier();
++ loop_start_time = jiffies;
++
++ for (i = 0; i < ARRAY_SIZE(expected_results); ++i) {
++ if (expected_results[i].msec_to_sleep_before)
++ msleep(expected_results[i].msec_to_sleep_before);
++
++ if (time_is_before_jiffies(loop_start_time +
++ maximum_jiffies_at_index(i)))
++ return -ETIMEDOUT;
++ if (wg_ratelimiter_allow(skb4, &init_net) !=
++ expected_results[i].result)
++ return -EXFULL;
++ ++(*test);
++
++ hdr4->saddr = htonl(ntohl(hdr4->saddr) + i + 1);
++ if (time_is_before_jiffies(loop_start_time +
++ maximum_jiffies_at_index(i)))
++ return -ETIMEDOUT;
++ if (!wg_ratelimiter_allow(skb4, &init_net))
++ return -EXFULL;
++ ++(*test);
++
++ hdr4->saddr = htonl(ntohl(hdr4->saddr) - i - 1);
++
++#if IS_ENABLED(CONFIG_IPV6)
++ hdr6->saddr.in6_u.u6_addr32[2] = htonl(i);
++ hdr6->saddr.in6_u.u6_addr32[3] = htonl(i);
++ if (time_is_before_jiffies(loop_start_time +
++ maximum_jiffies_at_index(i)))
++ return -ETIMEDOUT;
++ if (wg_ratelimiter_allow(skb6, &init_net) !=
++ expected_results[i].result)
++ return -EXFULL;
++ ++(*test);
++
++ hdr6->saddr.in6_u.u6_addr32[0] =
++ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) + i + 1);
++ if (time_is_before_jiffies(loop_start_time +
++ maximum_jiffies_at_index(i)))
++ return -ETIMEDOUT;
++ if (!wg_ratelimiter_allow(skb6, &init_net))
++ return -EXFULL;
++ ++(*test);
++
++ hdr6->saddr.in6_u.u6_addr32[0] =
++ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) - i - 1);
++
++ if (time_is_before_jiffies(loop_start_time +
++ maximum_jiffies_at_index(i)))
++ return -ETIMEDOUT;
++#endif
++ }
++ return 0;
++}
++
++static __init int capacity_test(struct sk_buff *skb4, struct iphdr *hdr4,
++ int *test)
++{
++ int i;
++
++ wg_ratelimiter_gc_entries(NULL);
++ rcu_barrier();
++
++ if (atomic_read(&total_entries))
++ return -EXFULL;
++ ++(*test);
++
++ for (i = 0; i <= max_entries; ++i) {
++ hdr4->saddr = htonl(i);
++ if (wg_ratelimiter_allow(skb4, &init_net) != (i != max_entries))
++ return -EXFULL;
++ ++(*test);
++ }
++ return 0;
++}
++
++bool __init wg_ratelimiter_selftest(void)
++{
++ enum { TRIALS_BEFORE_GIVING_UP = 5000 };
++ bool success = false;
++ int test = 0, trials;
++ struct sk_buff *skb4, *skb6;
++ struct iphdr *hdr4;
++ struct ipv6hdr *hdr6;
++
++ if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
++ return true;
++
++ BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0);
++
++ if (wg_ratelimiter_init())
++ goto out;
++ ++test;
++ if (wg_ratelimiter_init()) {
++ wg_ratelimiter_uninit();
++ goto out;
++ }
++ ++test;
++ if (wg_ratelimiter_init()) {
++ wg_ratelimiter_uninit();
++ wg_ratelimiter_uninit();
++ goto out;
++ }
++ ++test;
++
++ skb4 = alloc_skb(sizeof(struct iphdr), GFP_KERNEL);
++ if (unlikely(!skb4))
++ goto err_nofree;
++ skb4->protocol = htons(ETH_P_IP);
++ hdr4 = (struct iphdr *)skb_put(skb4, sizeof(*hdr4));
++ hdr4->saddr = htonl(8182);
++ skb_reset_network_header(skb4);
++ ++test;
++
++#if IS_ENABLED(CONFIG_IPV6)
++ skb6 = alloc_skb(sizeof(struct ipv6hdr), GFP_KERNEL);
++ if (unlikely(!skb6)) {
++ kfree_skb(skb4);
++ goto err_nofree;
++ }
++ skb6->protocol = htons(ETH_P_IPV6);
++ hdr6 = (struct ipv6hdr *)skb_put(skb6, sizeof(*hdr6));
++ hdr6->saddr.in6_u.u6_addr32[0] = htonl(1212);
++ hdr6->saddr.in6_u.u6_addr32[1] = htonl(289188);
++ skb_reset_network_header(skb6);
++ ++test;
++#endif
++
++ for (trials = TRIALS_BEFORE_GIVING_UP;;) {
++ int test_count = 0, ret;
++
++ ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
++ if (ret == -ETIMEDOUT) {
++ if (!trials--) {
++ test += test_count;
++ goto err;
++ }
++ msleep(500);
++ continue;
++ } else if (ret < 0) {
++ test += test_count;
++ goto err;
++ } else {
++ test += test_count;
++ break;
++ }
++ }
++
++ for (trials = TRIALS_BEFORE_GIVING_UP;;) {
++ int test_count = 0;
++
++ if (capacity_test(skb4, hdr4, &test_count) < 0) {
++ if (!trials--) {
++ test += test_count;
++ goto err;
++ }
++ msleep(50);
++ continue;
++ }
++ test += test_count;
++ break;
++ }
++
++ success = true;
++
++err:
++ kfree_skb(skb4);
++#if IS_ENABLED(CONFIG_IPV6)
++ kfree_skb(skb6);
++#endif
++err_nofree:
++ wg_ratelimiter_uninit();
++ wg_ratelimiter_uninit();
++ wg_ratelimiter_uninit();
++ /* Uninit one extra time to check underflow detection. */
++ wg_ratelimiter_uninit();
++out:
++ if (success)
++ pr_info("ratelimiter self-tests: pass\n");
++ else
++ pr_err("ratelimiter self-test %d: FAIL\n", test);
++
++ return success;
++}
++#endif
+--- /dev/null
++++ b/drivers/net/wireguard/send.c
+@@ -0,0 +1,413 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "queueing.h"
++#include "timers.h"
++#include "device.h"
++#include "peer.h"
++#include "socket.h"
++#include "messages.h"
++#include "cookie.h"
++
++#include <linux/uio.h>
++#include <linux/inetdevice.h>
++#include <linux/socket.h>
++#include <net/ip_tunnels.h>
++#include <net/udp.h>
++#include <net/sock.h>
++
++static void wg_packet_send_handshake_initiation(struct wg_peer *peer)
++{
++ struct message_handshake_initiation packet;
++
++ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake),
++ REKEY_TIMEOUT))
++ return; /* This function is rate limited. */
++
++ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns());
++ net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++
++ if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) {
++ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer);
++ wg_timers_any_authenticated_packet_traversal(peer);
++ wg_timers_any_authenticated_packet_sent(peer);
++ atomic64_set(&peer->last_sent_handshake,
++ ktime_get_coarse_boottime_ns());
++ wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet),
++ HANDSHAKE_DSCP);
++ wg_timers_handshake_initiated(peer);
++ }
++}
++
++void wg_packet_handshake_send_worker(struct work_struct *work)
++{
++ struct wg_peer *peer = container_of(work, struct wg_peer,
++ transmit_handshake_work);
++
++ wg_packet_send_handshake_initiation(peer);
++ wg_peer_put(peer);
++}
++
++void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer,
++ bool is_retry)
++{
++ if (!is_retry)
++ peer->timer_handshake_attempts = 0;
++
++ rcu_read_lock_bh();
++ /* We check last_sent_handshake here in addition to the actual function
++ * we're queueing up, so that we don't queue things if not strictly
++ * necessary:
++ */
++ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake),
++ REKEY_TIMEOUT) ||
++ unlikely(READ_ONCE(peer->is_dead)))
++ goto out;
++
++ wg_peer_get(peer);
++ /* Queues up calling packet_send_queued_handshakes(peer), where we do a
++ * peer_put(peer) after:
++ */
++ if (!queue_work(peer->device->handshake_send_wq,
++ &peer->transmit_handshake_work))
++ /* If the work was already queued, we want to drop the
++ * extra reference:
++ */
++ wg_peer_put(peer);
++out:
++ rcu_read_unlock_bh();
++}
++
++void wg_packet_send_handshake_response(struct wg_peer *peer)
++{
++ struct message_handshake_response packet;
++
++ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns());
++ net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++
++ if (wg_noise_handshake_create_response(&packet, &peer->handshake)) {
++ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer);
++ if (wg_noise_handshake_begin_session(&peer->handshake,
++ &peer->keypairs)) {
++ wg_timers_session_derived(peer);
++ wg_timers_any_authenticated_packet_traversal(peer);
++ wg_timers_any_authenticated_packet_sent(peer);
++ atomic64_set(&peer->last_sent_handshake,
++ ktime_get_coarse_boottime_ns());
++ wg_socket_send_buffer_to_peer(peer, &packet,
++ sizeof(packet),
++ HANDSHAKE_DSCP);
++ }
++ }
++}
++
++void wg_packet_send_handshake_cookie(struct wg_device *wg,
++ struct sk_buff *initiating_skb,
++ __le32 sender_index)
++{
++ struct message_handshake_cookie packet;
++
++ net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n",
++ wg->dev->name, initiating_skb);
++ wg_cookie_message_create(&packet, initiating_skb, sender_index,
++ &wg->cookie_checker);
++ wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet,
++ sizeof(packet));
++}
++
++static void keep_key_fresh(struct wg_peer *peer)
++{
++ struct noise_keypair *keypair;
++ bool send = false;
++
++ rcu_read_lock_bh();
++ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
++ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
++ (unlikely(atomic64_read(&keypair->sending.counter.counter) >
++ REKEY_AFTER_MESSAGES) ||
++ (keypair->i_am_the_initiator &&
++ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
++ REKEY_AFTER_TIME)))))
++ send = true;
++ rcu_read_unlock_bh();
++
++ if (send)
++ wg_packet_send_queued_handshake_initiation(peer, false);
++}
++
++static unsigned int calculate_skb_padding(struct sk_buff *skb)
++{
++ /* We do this modulo business with the MTU, just in case the networking
++ * layer gives us a packet that's bigger than the MTU. In that case, we
++ * wouldn't want the final subtraction to overflow in the case of the
++ * padded_size being clamped.
++ */
++ unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
++ unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
++
++ if (padded_size > PACKET_CB(skb)->mtu)
++ padded_size = PACKET_CB(skb)->mtu;
++ return padded_size - last_unit;
++}
++
++static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
++{
++ unsigned int padding_len, plaintext_len, trailer_len;
++ struct scatterlist sg[MAX_SKB_FRAGS + 8];
++ struct message_data *header;
++ struct sk_buff *trailer;
++ int num_frags;
++
++ /* Calculate lengths. */
++ padding_len = calculate_skb_padding(skb);
++ trailer_len = padding_len + noise_encrypted_len(0);
++ plaintext_len = skb->len + padding_len;
++
++ /* Expand data section to have room for padding and auth tag. */
++ num_frags = skb_cow_data(skb, trailer_len, &trailer);
++ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg)))
++ return false;
++
++ /* Set the padding to zeros, and make sure it and the auth tag are part
++ * of the skb.
++ */
++ memset(skb_tail_pointer(trailer), 0, padding_len);
++
++ /* Expand head section to have room for our header and the network
++ * stack's headers.
++ */
++ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0))
++ return false;
++
++ /* Finalize checksum calculation for the inner packet, if required. */
++ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL &&
++ skb_checksum_help(skb)))
++ return false;
++
++ /* Only after checksumming can we safely add on the padding at the end
++ * and the header.
++ */
++ skb_set_inner_network_header(skb, 0);
++ header = (struct message_data *)skb_push(skb, sizeof(*header));
++ header->header.type = cpu_to_le32(MESSAGE_DATA);
++ header->key_idx = keypair->remote_index;
++ header->counter = cpu_to_le64(PACKET_CB(skb)->nonce);
++ pskb_put(skb, trailer, trailer_len);
++
++ /* Now we can encrypt the scattergather segments */
++ sg_init_table(sg, num_frags);
++ if (skb_to_sgvec(skb, sg, sizeof(struct message_data),
++ noise_encrypted_len(plaintext_len)) <= 0)
++ return false;
++ return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0,
++ PACKET_CB(skb)->nonce,
++ keypair->sending.key);
++}
++
++void wg_packet_send_keepalive(struct wg_peer *peer)
++{
++ struct sk_buff *skb;
++
++ if (skb_queue_empty(&peer->staged_packet_queue)) {
++ skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH,
++ GFP_ATOMIC);
++ if (unlikely(!skb))
++ return;
++ skb_reserve(skb, DATA_PACKET_HEAD_ROOM);
++ skb->dev = peer->device->dev;
++ PACKET_CB(skb)->mtu = skb->dev->mtu;
++ skb_queue_tail(&peer->staged_packet_queue, skb);
++ net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr);
++ }
++
++ wg_packet_send_staged_packets(peer);
++}
++
++static void wg_packet_create_data_done(struct sk_buff *first,
++ struct wg_peer *peer)
++{
++ struct sk_buff *skb, *next;
++ bool is_keepalive, data_sent = false;
++
++ wg_timers_any_authenticated_packet_traversal(peer);
++ wg_timers_any_authenticated_packet_sent(peer);
++ skb_list_walk_safe(first, skb, next) {
++ is_keepalive = skb->len == message_data_len(0);
++ if (likely(!wg_socket_send_skb_to_peer(peer, skb,
++ PACKET_CB(skb)->ds) && !is_keepalive))
++ data_sent = true;
++ }
++
++ if (likely(data_sent))
++ wg_timers_data_sent(peer);
++
++ keep_key_fresh(peer);
++}
++
++void wg_packet_tx_worker(struct work_struct *work)
++{
++ struct crypt_queue *queue = container_of(work, struct crypt_queue,
++ work);
++ struct noise_keypair *keypair;
++ enum packet_state state;
++ struct sk_buff *first;
++ struct wg_peer *peer;
++
++ while ((first = __ptr_ring_peek(&queue->ring)) != NULL &&
++ (state = atomic_read_acquire(&PACKET_CB(first)->state)) !=
++ PACKET_STATE_UNCRYPTED) {
++ __ptr_ring_discard_one(&queue->ring);
++ peer = PACKET_PEER(first);
++ keypair = PACKET_CB(first)->keypair;
++
++ if (likely(state == PACKET_STATE_CRYPTED))
++ wg_packet_create_data_done(first, peer);
++ else
++ kfree_skb_list(first);
++
++ wg_noise_keypair_put(keypair, false);
++ wg_peer_put(peer);
++ }
++}
++
++void wg_packet_encrypt_worker(struct work_struct *work)
++{
++ struct crypt_queue *queue = container_of(work, struct multicore_worker,
++ work)->ptr;
++ struct sk_buff *first, *skb, *next;
++
++ while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) {
++ enum packet_state state = PACKET_STATE_CRYPTED;
++
++ skb_list_walk_safe(first, skb, next) {
++ if (likely(encrypt_packet(skb,
++ PACKET_CB(first)->keypair))) {
++ wg_reset_packet(skb);
++ } else {
++ state = PACKET_STATE_DEAD;
++ break;
++ }
++ }
++ wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
++ state);
++
++ }
++}
++
++static void wg_packet_create_data(struct sk_buff *first)
++{
++ struct wg_peer *peer = PACKET_PEER(first);
++ struct wg_device *wg = peer->device;
++ int ret = -EINVAL;
++
++ rcu_read_lock_bh();
++ if (unlikely(READ_ONCE(peer->is_dead)))
++ goto err;
++
++ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue,
++ &peer->tx_queue, first,
++ wg->packet_crypt_wq,
++ &wg->encrypt_queue.last_cpu);
++ if (unlikely(ret == -EPIPE))
++ wg_queue_enqueue_per_peer(&peer->tx_queue, first,
++ PACKET_STATE_DEAD);
++err:
++ rcu_read_unlock_bh();
++ if (likely(!ret || ret == -EPIPE))
++ return;
++ wg_noise_keypair_put(PACKET_CB(first)->keypair, false);
++ wg_peer_put(peer);
++ kfree_skb_list(first);
++}
++
++void wg_packet_purge_staged_packets(struct wg_peer *peer)
++{
++ spin_lock_bh(&peer->staged_packet_queue.lock);
++ peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen;
++ __skb_queue_purge(&peer->staged_packet_queue);
++ spin_unlock_bh(&peer->staged_packet_queue.lock);
++}
++
++void wg_packet_send_staged_packets(struct wg_peer *peer)
++{
++ struct noise_symmetric_key *key;
++ struct noise_keypair *keypair;
++ struct sk_buff_head packets;
++ struct sk_buff *skb;
++
++ /* Steal the current queue into our local one. */
++ __skb_queue_head_init(&packets);
++ spin_lock_bh(&peer->staged_packet_queue.lock);
++ skb_queue_splice_init(&peer->staged_packet_queue, &packets);
++ spin_unlock_bh(&peer->staged_packet_queue.lock);
++ if (unlikely(skb_queue_empty(&packets)))
++ return;
++
++ /* First we make sure we have a valid reference to a valid key. */
++ rcu_read_lock_bh();
++ keypair = wg_noise_keypair_get(
++ rcu_dereference_bh(peer->keypairs.current_keypair));
++ rcu_read_unlock_bh();
++ if (unlikely(!keypair))
++ goto out_nokey;
++ key = &keypair->sending;
++ if (unlikely(!READ_ONCE(key->is_valid)))
++ goto out_nokey;
++ if (unlikely(wg_birthdate_has_expired(key->birthdate,
++ REJECT_AFTER_TIME)))
++ goto out_invalid;
++
++ /* After we know we have a somewhat valid key, we now try to assign
++ * nonces to all of the packets in the queue. If we can't assign nonces
++ * for all of them, we just consider it a failure and wait for the next
++ * handshake.
++ */
++ skb_queue_walk(&packets, skb) {
++ /* 0 for no outer TOS: no leak. TODO: at some later point, we
++ * might consider using flowi->tos as outer instead.
++ */
++ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
++ PACKET_CB(skb)->nonce =
++ atomic64_inc_return(&key->counter.counter) - 1;
++ if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
++ goto out_invalid;
++ }
++
++ packets.prev->next = NULL;
++ wg_peer_get(keypair->entry.peer);
++ PACKET_CB(packets.next)->keypair = keypair;
++ wg_packet_create_data(packets.next);
++ return;
++
++out_invalid:
++ WRITE_ONCE(key->is_valid, false);
++out_nokey:
++ wg_noise_keypair_put(keypair, false);
++
++ /* We orphan the packets if we're waiting on a handshake, so that they
++ * don't block a socket's pool.
++ */
++ skb_queue_walk(&packets, skb)
++ skb_orphan(skb);
++ /* Then we put them back on the top of the queue. We're not too
++ * concerned about accidentally getting things a little out of order if
++ * packets are being added really fast, because this queue is for before
++ * packets can even be sent and it's small anyway.
++ */
++ spin_lock_bh(&peer->staged_packet_queue.lock);
++ skb_queue_splice(&packets, &peer->staged_packet_queue);
++ spin_unlock_bh(&peer->staged_packet_queue.lock);
++
++ /* If we're exiting because there's something wrong with the key, it
++ * means we should initiate a new handshake.
++ */
++ wg_packet_send_queued_handshake_initiation(peer, false);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/socket.c
+@@ -0,0 +1,437 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "device.h"
++#include "peer.h"
++#include "socket.h"
++#include "queueing.h"
++#include "messages.h"
++
++#include <linux/ctype.h>
++#include <linux/net.h>
++#include <linux/if_vlan.h>
++#include <linux/if_ether.h>
++#include <linux/inetdevice.h>
++#include <net/udp_tunnel.h>
++#include <net/ipv6.h>
++
++static int send4(struct wg_device *wg, struct sk_buff *skb,
++ struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
++{
++ struct flowi4 fl = {
++ .saddr = endpoint->src4.s_addr,
++ .daddr = endpoint->addr4.sin_addr.s_addr,
++ .fl4_dport = endpoint->addr4.sin_port,
++ .flowi4_mark = wg->fwmark,
++ .flowi4_proto = IPPROTO_UDP
++ };
++ struct rtable *rt = NULL;
++ struct sock *sock;
++ int ret = 0;
++
++ skb_mark_not_on_list(skb);
++ skb->dev = wg->dev;
++ skb->mark = wg->fwmark;
++
++ rcu_read_lock_bh();
++ sock = rcu_dereference_bh(wg->sock4);
++
++ if (unlikely(!sock)) {
++ ret = -ENONET;
++ goto err;
++ }
++
++ fl.fl4_sport = inet_sk(sock)->inet_sport;
++
++ if (cache)
++ rt = dst_cache_get_ip4(cache, &fl.saddr);
++
++ if (!rt) {
++ security_sk_classify_flow(sock, flowi4_to_flowi(&fl));
++ if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0,
++ fl.saddr, RT_SCOPE_HOST))) {
++ endpoint->src4.s_addr = 0;
++ *(__force __be32 *)&endpoint->src_if4 = 0;
++ fl.saddr = 0;
++ if (cache)
++ dst_cache_reset(cache);
++ }
++ rt = ip_route_output_flow(sock_net(sock), &fl, sock);
++ if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) &&
++ PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) &&
++ rt->dst.dev->ifindex != endpoint->src_if4)))) {
++ endpoint->src4.s_addr = 0;
++ *(__force __be32 *)&endpoint->src_if4 = 0;
++ fl.saddr = 0;
++ if (cache)
++ dst_cache_reset(cache);
++ if (!IS_ERR(rt))
++ ip_rt_put(rt);
++ rt = ip_route_output_flow(sock_net(sock), &fl, sock);
++ }
++ if (unlikely(IS_ERR(rt))) {
++ ret = PTR_ERR(rt);
++ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
++ wg->dev->name, &endpoint->addr, ret);
++ goto err;
++ } else if (unlikely(rt->dst.dev == skb->dev)) {
++ ip_rt_put(rt);
++ ret = -ELOOP;
++ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
++ wg->dev->name, &endpoint->addr);
++ goto err;
++ }
++ if (cache)
++ dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
++ }
++
++ skb->ignore_df = 1;
++ udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds,
++ ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport,
++ fl.fl4_dport, false, false);
++ goto out;
++
++err:
++ kfree_skb(skb);
++out:
++ rcu_read_unlock_bh();
++ return ret;
++}
++
++static int send6(struct wg_device *wg, struct sk_buff *skb,
++ struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
++{
++#if IS_ENABLED(CONFIG_IPV6)
++ struct flowi6 fl = {
++ .saddr = endpoint->src6,
++ .daddr = endpoint->addr6.sin6_addr,
++ .fl6_dport = endpoint->addr6.sin6_port,
++ .flowi6_mark = wg->fwmark,
++ .flowi6_oif = endpoint->addr6.sin6_scope_id,
++ .flowi6_proto = IPPROTO_UDP
++ /* TODO: addr->sin6_flowinfo */
++ };
++ struct dst_entry *dst = NULL;
++ struct sock *sock;
++ int ret = 0;
++
++ skb_mark_not_on_list(skb);
++ skb->dev = wg->dev;
++ skb->mark = wg->fwmark;
++
++ rcu_read_lock_bh();
++ sock = rcu_dereference_bh(wg->sock6);
++
++ if (unlikely(!sock)) {
++ ret = -ENONET;
++ goto err;
++ }
++
++ fl.fl6_sport = inet_sk(sock)->inet_sport;
++
++ if (cache)
++ dst = dst_cache_get_ip6(cache, &fl.saddr);
++
++ if (!dst) {
++ security_sk_classify_flow(sock, flowi6_to_flowi(&fl));
++ if (unlikely(!ipv6_addr_any(&fl.saddr) &&
++ !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) {
++ endpoint->src6 = fl.saddr = in6addr_any;
++ if (cache)
++ dst_cache_reset(cache);
++ }
++ dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl,
++ NULL);
++ if (unlikely(IS_ERR(dst))) {
++ ret = PTR_ERR(dst);
++ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
++ wg->dev->name, &endpoint->addr, ret);
++ goto err;
++ } else if (unlikely(dst->dev == skb->dev)) {
++ dst_release(dst);
++ ret = -ELOOP;
++ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
++ wg->dev->name, &endpoint->addr);
++ goto err;
++ }
++ if (cache)
++ dst_cache_set_ip6(cache, dst, &fl.saddr);
++ }
++
++ skb->ignore_df = 1;
++ udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds,
++ ip6_dst_hoplimit(dst), 0, fl.fl6_sport,
++ fl.fl6_dport, false);
++ goto out;
++
++err:
++ kfree_skb(skb);
++out:
++ rcu_read_unlock_bh();
++ return ret;
++#else
++ return -EAFNOSUPPORT;
++#endif
++}
++
++int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, u8 ds)
++{
++ size_t skb_len = skb->len;
++ int ret = -EAFNOSUPPORT;
++
++ read_lock_bh(&peer->endpoint_lock);
++ if (peer->endpoint.addr.sa_family == AF_INET)
++ ret = send4(peer->device, skb, &peer->endpoint, ds,
++ &peer->endpoint_cache);
++ else if (peer->endpoint.addr.sa_family == AF_INET6)
++ ret = send6(peer->device, skb, &peer->endpoint, ds,
++ &peer->endpoint_cache);
++ else
++ dev_kfree_skb(skb);
++ if (likely(!ret))
++ peer->tx_bytes += skb_len;
++ read_unlock_bh(&peer->endpoint_lock);
++
++ return ret;
++}
++
++int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *buffer,
++ size_t len, u8 ds)
++{
++ struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);
++
++ if (unlikely(!skb))
++ return -ENOMEM;
++
++ skb_reserve(skb, SKB_HEADER_LEN);
++ skb_set_inner_network_header(skb, 0);
++ skb_put_data(skb, buffer, len);
++ return wg_socket_send_skb_to_peer(peer, skb, ds);
++}
++
++int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg,
++ struct sk_buff *in_skb, void *buffer,
++ size_t len)
++{
++ int ret = 0;
++ struct sk_buff *skb;
++ struct endpoint endpoint;
++
++ if (unlikely(!in_skb))
++ return -EINVAL;
++ ret = wg_socket_endpoint_from_skb(&endpoint, in_skb);
++ if (unlikely(ret < 0))
++ return ret;
++
++ skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);
++ if (unlikely(!skb))
++ return -ENOMEM;
++ skb_reserve(skb, SKB_HEADER_LEN);
++ skb_set_inner_network_header(skb, 0);
++ skb_put_data(skb, buffer, len);
++
++ if (endpoint.addr.sa_family == AF_INET)
++ ret = send4(wg, skb, &endpoint, 0, NULL);
++ else if (endpoint.addr.sa_family == AF_INET6)
++ ret = send6(wg, skb, &endpoint, 0, NULL);
++ /* No other possibilities if the endpoint is valid, which it is,
++ * as we checked above.
++ */
++
++ return ret;
++}
++
++int wg_socket_endpoint_from_skb(struct endpoint *endpoint,
++ const struct sk_buff *skb)
++{
++ memset(endpoint, 0, sizeof(*endpoint));
++ if (skb->protocol == htons(ETH_P_IP)) {
++ endpoint->addr4.sin_family = AF_INET;
++ endpoint->addr4.sin_port = udp_hdr(skb)->source;
++ endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr;
++ endpoint->src4.s_addr = ip_hdr(skb)->daddr;
++ endpoint->src_if4 = skb->skb_iif;
++ } else if (skb->protocol == htons(ETH_P_IPV6)) {
++ endpoint->addr6.sin6_family = AF_INET6;
++ endpoint->addr6.sin6_port = udp_hdr(skb)->source;
++ endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr;
++ endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id(
++ &ipv6_hdr(skb)->saddr, skb->skb_iif);
++ endpoint->src6 = ipv6_hdr(skb)->daddr;
++ } else {
++ return -EINVAL;
++ }
++ return 0;
++}
++
++static bool endpoint_eq(const struct endpoint *a, const struct endpoint *b)
++{
++ return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET &&
++ a->addr4.sin_port == b->addr4.sin_port &&
++ a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr &&
++ a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) ||
++ (a->addr.sa_family == AF_INET6 &&
++ b->addr.sa_family == AF_INET6 &&
++ a->addr6.sin6_port == b->addr6.sin6_port &&
++ ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) &&
++ a->addr6.sin6_scope_id == b->addr6.sin6_scope_id &&
++ ipv6_addr_equal(&a->src6, &b->src6)) ||
++ unlikely(!a->addr.sa_family && !b->addr.sa_family);
++}
++
++void wg_socket_set_peer_endpoint(struct wg_peer *peer,
++ const struct endpoint *endpoint)
++{
++ /* First we check unlocked, in order to optimize, since it's pretty rare
++ * that an endpoint will change. If we happen to be mid-write, and two
++ * CPUs wind up writing the same thing or something slightly different,
++ * it doesn't really matter much either.
++ */
++ if (endpoint_eq(endpoint, &peer->endpoint))
++ return;
++ write_lock_bh(&peer->endpoint_lock);
++ if (endpoint->addr.sa_family == AF_INET) {
++ peer->endpoint.addr4 = endpoint->addr4;
++ peer->endpoint.src4 = endpoint->src4;
++ peer->endpoint.src_if4 = endpoint->src_if4;
++ } else if (endpoint->addr.sa_family == AF_INET6) {
++ peer->endpoint.addr6 = endpoint->addr6;
++ peer->endpoint.src6 = endpoint->src6;
++ } else {
++ goto out;
++ }
++ dst_cache_reset(&peer->endpoint_cache);
++out:
++ write_unlock_bh(&peer->endpoint_lock);
++}
++
++void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer,
++ const struct sk_buff *skb)
++{
++ struct endpoint endpoint;
++
++ if (!wg_socket_endpoint_from_skb(&endpoint, skb))
++ wg_socket_set_peer_endpoint(peer, &endpoint);
++}
++
++void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer)
++{
++ write_lock_bh(&peer->endpoint_lock);
++ memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6));
++ dst_cache_reset(&peer->endpoint_cache);
++ write_unlock_bh(&peer->endpoint_lock);
++}
++
++static int wg_receive(struct sock *sk, struct sk_buff *skb)
++{
++ struct wg_device *wg;
++
++ if (unlikely(!sk))
++ goto err;
++ wg = sk->sk_user_data;
++ if (unlikely(!wg))
++ goto err;
++ wg_packet_receive(wg, skb);
++ return 0;
++
++err:
++ kfree_skb(skb);
++ return 0;
++}
++
++static void sock_free(struct sock *sock)
++{
++ if (unlikely(!sock))
++ return;
++ sk_clear_memalloc(sock);
++ udp_tunnel_sock_release(sock->sk_socket);
++}
++
++static void set_sock_opts(struct socket *sock)
++{
++ sock->sk->sk_allocation = GFP_ATOMIC;
++ sock->sk->sk_sndbuf = INT_MAX;
++ sk_set_memalloc(sock->sk);
++}
++
++int wg_socket_init(struct wg_device *wg, u16 port)
++{
++ int ret;
++ struct udp_tunnel_sock_cfg cfg = {
++ .sk_user_data = wg,
++ .encap_type = 1,
++ .encap_rcv = wg_receive
++ };
++ struct socket *new4 = NULL, *new6 = NULL;
++ struct udp_port_cfg port4 = {
++ .family = AF_INET,
++ .local_ip.s_addr = htonl(INADDR_ANY),
++ .local_udp_port = htons(port),
++ .use_udp_checksums = true
++ };
++#if IS_ENABLED(CONFIG_IPV6)
++ int retries = 0;
++ struct udp_port_cfg port6 = {
++ .family = AF_INET6,
++ .local_ip6 = IN6ADDR_ANY_INIT,
++ .use_udp6_tx_checksums = true,
++ .use_udp6_rx_checksums = true,
++ .ipv6_v6only = true
++ };
++#endif
++
++#if IS_ENABLED(CONFIG_IPV6)
++retry:
++#endif
++
++ ret = udp_sock_create(wg->creating_net, &port4, &new4);
++ if (ret < 0) {
++ pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
++ return ret;
++ }
++ set_sock_opts(new4);
++ setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
++
++#if IS_ENABLED(CONFIG_IPV6)
++ if (ipv6_mod_enabled()) {
++ port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
++ ret = udp_sock_create(wg->creating_net, &port6, &new6);
++ if (ret < 0) {
++ udp_tunnel_sock_release(new4);
++ if (ret == -EADDRINUSE && !port && retries++ < 100)
++ goto retry;
++ pr_err("%s: Could not create IPv6 socket\n",
++ wg->dev->name);
++ return ret;
++ }
++ set_sock_opts(new6);
++ setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
++ }
++#endif
++
++ wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
++ return 0;
++}
++
++void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
++ struct sock *new6)
++{
++ struct sock *old4, *old6;
++
++ mutex_lock(&wg->socket_update_lock);
++ old4 = rcu_dereference_protected(wg->sock4,
++ lockdep_is_held(&wg->socket_update_lock));
++ old6 = rcu_dereference_protected(wg->sock6,
++ lockdep_is_held(&wg->socket_update_lock));
++ rcu_assign_pointer(wg->sock4, new4);
++ rcu_assign_pointer(wg->sock6, new6);
++ if (new4)
++ wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
++ mutex_unlock(&wg->socket_update_lock);
++ synchronize_rcu();
++ synchronize_net();
++ sock_free(old4);
++ sock_free(old6);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/socket.h
+@@ -0,0 +1,44 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_SOCKET_H
++#define _WG_SOCKET_H
++
++#include <linux/netdevice.h>
++#include <linux/udp.h>
++#include <linux/if_vlan.h>
++#include <linux/if_ether.h>
++
++int wg_socket_init(struct wg_device *wg, u16 port);
++void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
++ struct sock *new6);
++int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *data,
++ size_t len, u8 ds);
++int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb,
++ u8 ds);
++int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg,
++ struct sk_buff *in_skb,
++ void *out_buffer, size_t len);
++
++int wg_socket_endpoint_from_skb(struct endpoint *endpoint,
++ const struct sk_buff *skb);
++void wg_socket_set_peer_endpoint(struct wg_peer *peer,
++ const struct endpoint *endpoint);
++void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer,
++ const struct sk_buff *skb);
++void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer);
++
++#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG)
++#define net_dbg_skb_ratelimited(fmt, dev, skb, ...) do { \
++ struct endpoint __endpoint; \
++ wg_socket_endpoint_from_skb(&__endpoint, skb); \
++ net_dbg_ratelimited(fmt, dev, &__endpoint.addr, \
++ ##__VA_ARGS__); \
++ } while (0)
++#else
++#define net_dbg_skb_ratelimited(fmt, skb, ...)
++#endif
++
++#endif /* _WG_SOCKET_H */
+--- /dev/null
++++ b/drivers/net/wireguard/timers.c
+@@ -0,0 +1,243 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#include "timers.h"
++#include "device.h"
++#include "peer.h"
++#include "queueing.h"
++#include "socket.h"
++
++/*
++ * - Timer for retransmitting the handshake if we don't hear back after
++ * `REKEY_TIMEOUT + jitter` ms.
++ *
++ * - Timer for sending empty packet if we have received a packet but after have
++ * not sent one for `KEEPALIVE_TIMEOUT` ms.
++ *
++ * - Timer for initiating new handshake if we have sent a packet but after have
++ * not received one (even empty) for `(KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) +
++ * jitter` ms.
++ *
++ * - Timer for zeroing out all ephemeral keys after `(REJECT_AFTER_TIME * 3)` ms
++ * if no new keys have been received.
++ *
++ * - Timer for, if enabled, sending an empty authenticated packet every user-
++ * specified seconds.
++ */
++
++static inline void mod_peer_timer(struct wg_peer *peer,
++ struct timer_list *timer,
++ unsigned long expires)
++{
++ rcu_read_lock_bh();
++ if (likely(netif_running(peer->device->dev) &&
++ !READ_ONCE(peer->is_dead)))
++ mod_timer(timer, expires);
++ rcu_read_unlock_bh();
++}
++
++static void wg_expired_retransmit_handshake(struct timer_list *timer)
++{
++ struct wg_peer *peer = from_timer(peer, timer,
++ timer_retransmit_handshake);
++
++ if (peer->timer_handshake_attempts > MAX_TIMER_HANDSHAKES) {
++ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d attempts, giving up\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr, MAX_TIMER_HANDSHAKES + 2);
++
++ del_timer(&peer->timer_send_keepalive);
++ /* We drop all packets without a keypair and don't try again,
++ * if we try unsuccessfully for too long to make a handshake.
++ */
++ wg_packet_purge_staged_packets(peer);
++
++ /* We set a timer for destroying any residue that might be left
++ * of a partial exchange.
++ */
++ if (!timer_pending(&peer->timer_zero_key_material))
++ mod_peer_timer(peer, &peer->timer_zero_key_material,
++ jiffies + REJECT_AFTER_TIME * 3 * HZ);
++ } else {
++ ++peer->timer_handshake_attempts;
++ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d seconds, retrying (try %d)\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr, REKEY_TIMEOUT,
++ peer->timer_handshake_attempts + 1);
++
++ /* We clear the endpoint address src address, in case this is
++ * the cause of trouble.
++ */
++ wg_socket_clear_peer_endpoint_src(peer);
++
++ wg_packet_send_queued_handshake_initiation(peer, true);
++ }
++}
++
++static void wg_expired_send_keepalive(struct timer_list *timer)
++{
++ struct wg_peer *peer = from_timer(peer, timer, timer_send_keepalive);
++
++ wg_packet_send_keepalive(peer);
++ if (peer->timer_need_another_keepalive) {
++ peer->timer_need_another_keepalive = false;
++ mod_peer_timer(peer, &peer->timer_send_keepalive,
++ jiffies + KEEPALIVE_TIMEOUT * HZ);
++ }
++}
++
++static void wg_expired_new_handshake(struct timer_list *timer)
++{
++ struct wg_peer *peer = from_timer(peer, timer, timer_new_handshake);
++
++ pr_debug("%s: Retrying handshake with peer %llu (%pISpfsc) because we stopped hearing back after %d seconds\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr, KEEPALIVE_TIMEOUT + REKEY_TIMEOUT);
++ /* We clear the endpoint address src address, in case this is the cause
++ * of trouble.
++ */
++ wg_socket_clear_peer_endpoint_src(peer);
++ wg_packet_send_queued_handshake_initiation(peer, false);
++}
++
++static void wg_expired_zero_key_material(struct timer_list *timer)
++{
++ struct wg_peer *peer = from_timer(peer, timer, timer_zero_key_material);
++
++ rcu_read_lock_bh();
++ if (!READ_ONCE(peer->is_dead)) {
++ wg_peer_get(peer);
++ if (!queue_work(peer->device->handshake_send_wq,
++ &peer->clear_peer_work))
++ /* If the work was already on the queue, we want to drop
++ * the extra reference.
++ */
++ wg_peer_put(peer);
++ }
++ rcu_read_unlock_bh();
++}
++
++static void wg_queued_expired_zero_key_material(struct work_struct *work)
++{
++ struct wg_peer *peer = container_of(work, struct wg_peer,
++ clear_peer_work);
++
++ pr_debug("%s: Zeroing out all keys for peer %llu (%pISpfsc), since we haven't received a new one in %d seconds\n",
++ peer->device->dev->name, peer->internal_id,
++ &peer->endpoint.addr, REJECT_AFTER_TIME * 3);
++ wg_noise_handshake_clear(&peer->handshake);
++ wg_noise_keypairs_clear(&peer->keypairs);
++ wg_peer_put(peer);
++}
++
++static void wg_expired_send_persistent_keepalive(struct timer_list *timer)
++{
++ struct wg_peer *peer = from_timer(peer, timer,
++ timer_persistent_keepalive);
++
++ if (likely(peer->persistent_keepalive_interval))
++ wg_packet_send_keepalive(peer);
++}
++
++/* Should be called after an authenticated data packet is sent. */
++void wg_timers_data_sent(struct wg_peer *peer)
++{
++ if (!timer_pending(&peer->timer_new_handshake))
++ mod_peer_timer(peer, &peer->timer_new_handshake,
++ jiffies + (KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) * HZ +
++ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES));
++}
++
++/* Should be called after an authenticated data packet is received. */
++void wg_timers_data_received(struct wg_peer *peer)
++{
++ if (likely(netif_running(peer->device->dev))) {
++ if (!timer_pending(&peer->timer_send_keepalive))
++ mod_peer_timer(peer, &peer->timer_send_keepalive,
++ jiffies + KEEPALIVE_TIMEOUT * HZ);
++ else
++ peer->timer_need_another_keepalive = true;
++ }
++}
++
++/* Should be called after any type of authenticated packet is sent, whether
++ * keepalive, data, or handshake.
++ */
++void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer)
++{
++ del_timer(&peer->timer_send_keepalive);
++}
++
++/* Should be called after any type of authenticated packet is received, whether
++ * keepalive, data, or handshake.
++ */
++void wg_timers_any_authenticated_packet_received(struct wg_peer *peer)
++{
++ del_timer(&peer->timer_new_handshake);
++}
++
++/* Should be called after a handshake initiation message is sent. */
++void wg_timers_handshake_initiated(struct wg_peer *peer)
++{
++ mod_peer_timer(peer, &peer->timer_retransmit_handshake,
++ jiffies + REKEY_TIMEOUT * HZ +
++ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES));
++}
++
++/* Should be called after a handshake response message is received and processed
++ * or when getting key confirmation via the first data message.
++ */
++void wg_timers_handshake_complete(struct wg_peer *peer)
++{
++ del_timer(&peer->timer_retransmit_handshake);
++ peer->timer_handshake_attempts = 0;
++ peer->sent_lastminute_handshake = false;
++ ktime_get_real_ts64(&peer->walltime_last_handshake);
++}
++
++/* Should be called after an ephemeral key is created, which is before sending a
++ * handshake response or after receiving a handshake response.
++ */
++void wg_timers_session_derived(struct wg_peer *peer)
++{
++ mod_peer_timer(peer, &peer->timer_zero_key_material,
++ jiffies + REJECT_AFTER_TIME * 3 * HZ);
++}
++
++/* Should be called before a packet with authentication, whether
++ * keepalive, data, or handshakem is sent, or after one is received.
++ */
++void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer)
++{
++ if (peer->persistent_keepalive_interval)
++ mod_peer_timer(peer, &peer->timer_persistent_keepalive,
++ jiffies + peer->persistent_keepalive_interval * HZ);
++}
++
++void wg_timers_init(struct wg_peer *peer)
++{
++ timer_setup(&peer->timer_retransmit_handshake,
++ wg_expired_retransmit_handshake, 0);
++ timer_setup(&peer->timer_send_keepalive, wg_expired_send_keepalive, 0);
++ timer_setup(&peer->timer_new_handshake, wg_expired_new_handshake, 0);
++ timer_setup(&peer->timer_zero_key_material,
++ wg_expired_zero_key_material, 0);
++ timer_setup(&peer->timer_persistent_keepalive,
++ wg_expired_send_persistent_keepalive, 0);
++ INIT_WORK(&peer->clear_peer_work, wg_queued_expired_zero_key_material);
++ peer->timer_handshake_attempts = 0;
++ peer->sent_lastminute_handshake = false;
++ peer->timer_need_another_keepalive = false;
++}
++
++void wg_timers_stop(struct wg_peer *peer)
++{
++ del_timer_sync(&peer->timer_retransmit_handshake);
++ del_timer_sync(&peer->timer_send_keepalive);
++ del_timer_sync(&peer->timer_new_handshake);
++ del_timer_sync(&peer->timer_zero_key_material);
++ del_timer_sync(&peer->timer_persistent_keepalive);
++ flush_work(&peer->clear_peer_work);
++}
+--- /dev/null
++++ b/drivers/net/wireguard/timers.h
+@@ -0,0 +1,31 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#ifndef _WG_TIMERS_H
++#define _WG_TIMERS_H
++
++#include <linux/ktime.h>
++
++struct wg_peer;
++
++void wg_timers_init(struct wg_peer *peer);
++void wg_timers_stop(struct wg_peer *peer);
++void wg_timers_data_sent(struct wg_peer *peer);
++void wg_timers_data_received(struct wg_peer *peer);
++void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer);
++void wg_timers_any_authenticated_packet_received(struct wg_peer *peer);
++void wg_timers_handshake_initiated(struct wg_peer *peer);
++void wg_timers_handshake_complete(struct wg_peer *peer);
++void wg_timers_session_derived(struct wg_peer *peer);
++void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer);
++
++static inline bool wg_birthdate_has_expired(u64 birthday_nanoseconds,
++ u64 expiration_seconds)
++{
++ return (s64)(birthday_nanoseconds + expiration_seconds * NSEC_PER_SEC)
++ <= (s64)ktime_get_coarse_boottime_ns();
++}
++
++#endif /* _WG_TIMERS_H */
+--- /dev/null
++++ b/drivers/net/wireguard/version.h
+@@ -0,0 +1 @@
++#define WIREGUARD_VERSION "1.0.0"
+--- /dev/null
++++ b/include/uapi/linux/wireguard.h
+@@ -0,0 +1,196 @@
++/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ *
++ * Documentation
++ * =============
++ *
++ * The below enums and macros are for interfacing with WireGuard, using generic
++ * netlink, with family WG_GENL_NAME and version WG_GENL_VERSION. It defines two
++ * methods: get and set. Note that while they share many common attributes,
++ * these two functions actually accept a slightly different set of inputs and
++ * outputs.
++ *
++ * WG_CMD_GET_DEVICE
++ * -----------------
++ *
++ * May only be called via NLM_F_REQUEST | NLM_F_DUMP. The command should contain
++ * one but not both of:
++ *
++ * WGDEVICE_A_IFINDEX: NLA_U32
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ *
++ * The kernel will then return several messages (NLM_F_MULTI) containing the
++ * following tree of nested items:
++ *
++ * WGDEVICE_A_IFINDEX: NLA_U32
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
++ * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
++ * WGDEVICE_A_LISTEN_PORT: NLA_U16
++ * WGDEVICE_A_FWMARK: NLA_U32
++ * WGDEVICE_A_PEERS: NLA_NESTED
++ * 0: NLA_NESTED
++ * WGPEER_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
++ * WGPEER_A_PRESHARED_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
++ * WGPEER_A_ENDPOINT: NLA_MIN_LEN(struct sockaddr), struct sockaddr_in or struct sockaddr_in6
++ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16
++ * WGPEER_A_LAST_HANDSHAKE_TIME: NLA_EXACT_LEN, struct __kernel_timespec
++ * WGPEER_A_RX_BYTES: NLA_U64
++ * WGPEER_A_TX_BYTES: NLA_U64
++ * WGPEER_A_ALLOWEDIPS: NLA_NESTED
++ * 0: NLA_NESTED
++ * WGALLOWEDIP_A_FAMILY: NLA_U16
++ * WGALLOWEDIP_A_IPADDR: NLA_MIN_LEN(struct in_addr), struct in_addr or struct in6_addr
++ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8
++ * 0: NLA_NESTED
++ * ...
++ * 0: NLA_NESTED
++ * ...
++ * ...
++ * WGPEER_A_PROTOCOL_VERSION: NLA_U32
++ * 0: NLA_NESTED
++ * ...
++ * ...
++ *
++ * It is possible that all of the allowed IPs of a single peer will not
++ * fit within a single netlink message. In that case, the same peer will
++ * be written in the following message, except it will only contain
++ * WGPEER_A_PUBLIC_KEY and WGPEER_A_ALLOWEDIPS. This may occur several
++ * times in a row for the same peer. It is then up to the receiver to
++ * coalesce adjacent peers. Likewise, it is possible that all peers will
++ * not fit within a single message. So, subsequent peers will be sent
++ * in following messages, except those will only contain WGDEVICE_A_IFNAME
++ * and WGDEVICE_A_PEERS. It is then up to the receiver to coalesce these
++ * messages to form the complete list of peers.
++ *
++ * Since this is an NLA_F_DUMP command, the final message will always be
++ * NLMSG_DONE, even if an error occurs. However, this NLMSG_DONE message
++ * contains an integer error code. It is either zero or a negative error
++ * code corresponding to the errno.
++ *
++ * WG_CMD_SET_DEVICE
++ * -----------------
++ *
++ * May only be called via NLM_F_REQUEST. The command should contain the
++ * following tree of nested items, containing one but not both of
++ * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME:
++ *
++ * WGDEVICE_A_IFINDEX: NLA_U32
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current
++ * peers should be removed prior to adding the list below.
++ * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove
++ * WGDEVICE_A_LISTEN_PORT: NLA_U16, 0 to choose randomly
++ * WGDEVICE_A_FWMARK: NLA_U32, 0 to disable
++ * WGDEVICE_A_PEERS: NLA_NESTED
++ * 0: NLA_NESTED
++ * WGPEER_A_PUBLIC_KEY: len WG_KEY_LEN
++ * WGPEER_A_FLAGS: NLA_U32, 0 and/or WGPEER_F_REMOVE_ME if the
++ * specified peer should not exist at the end of the
++ * operation, rather than added/updated and/or
++ * WGPEER_F_REPLACE_ALLOWEDIPS if all current allowed
++ * IPs of this peer should be removed prior to adding
++ * the list below and/or WGPEER_F_UPDATE_ONLY if the
++ * peer should only be set if it already exists.
++ * WGPEER_A_PRESHARED_KEY: len WG_KEY_LEN, all zeros to remove
++ * WGPEER_A_ENDPOINT: struct sockaddr_in or struct sockaddr_in6
++ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16, 0 to disable
++ * WGPEER_A_ALLOWEDIPS: NLA_NESTED
++ * 0: NLA_NESTED
++ * WGALLOWEDIP_A_FAMILY: NLA_U16
++ * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr
++ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8
++ * 0: NLA_NESTED
++ * ...
++ * 0: NLA_NESTED
++ * ...
++ * ...
++ * WGPEER_A_PROTOCOL_VERSION: NLA_U32, should not be set or used at
++ * all by most users of this API, as the
++ * most recent protocol will be used when
++ * this is unset. Otherwise, must be set
++ * to 1.
++ * 0: NLA_NESTED
++ * ...
++ * ...
++ *
++ * It is possible that the amount of configuration data exceeds that of
++ * the maximum message length accepted by the kernel. In that case, several
++ * messages should be sent one after another, with each successive one
++ * filling in information not contained in the prior. Note that if
++ * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably
++ * should not be specified in fragments that come after, so that the list
++ * of peers is only cleared the first time but appened after. Likewise for
++ * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message
++ * of a peer, it likely should not be specified in subsequent fragments.
++ *
++ * If an error occurs, NLMSG_ERROR will reply containing an errno.
++ */
++
++#ifndef _WG_UAPI_WIREGUARD_H
++#define _WG_UAPI_WIREGUARD_H
++
++#define WG_GENL_NAME "wireguard"
++#define WG_GENL_VERSION 1
++
++#define WG_KEY_LEN 32
++
++enum wg_cmd {
++ WG_CMD_GET_DEVICE,
++ WG_CMD_SET_DEVICE,
++ __WG_CMD_MAX
++};
++#define WG_CMD_MAX (__WG_CMD_MAX - 1)
++
++enum wgdevice_flag {
++ WGDEVICE_F_REPLACE_PEERS = 1U << 0,
++ __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS
++};
++enum wgdevice_attribute {
++ WGDEVICE_A_UNSPEC,
++ WGDEVICE_A_IFINDEX,
++ WGDEVICE_A_IFNAME,
++ WGDEVICE_A_PRIVATE_KEY,
++ WGDEVICE_A_PUBLIC_KEY,
++ WGDEVICE_A_FLAGS,
++ WGDEVICE_A_LISTEN_PORT,
++ WGDEVICE_A_FWMARK,
++ WGDEVICE_A_PEERS,
++ __WGDEVICE_A_LAST
++};
++#define WGDEVICE_A_MAX (__WGDEVICE_A_LAST - 1)
++
++enum wgpeer_flag {
++ WGPEER_F_REMOVE_ME = 1U << 0,
++ WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1,
++ WGPEER_F_UPDATE_ONLY = 1U << 2,
++ __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS |
++ WGPEER_F_UPDATE_ONLY
++};
++enum wgpeer_attribute {
++ WGPEER_A_UNSPEC,
++ WGPEER_A_PUBLIC_KEY,
++ WGPEER_A_PRESHARED_KEY,
++ WGPEER_A_FLAGS,
++ WGPEER_A_ENDPOINT,
++ WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL,
++ WGPEER_A_LAST_HANDSHAKE_TIME,
++ WGPEER_A_RX_BYTES,
++ WGPEER_A_TX_BYTES,
++ WGPEER_A_ALLOWEDIPS,
++ WGPEER_A_PROTOCOL_VERSION,
++ __WGPEER_A_LAST
++};
++#define WGPEER_A_MAX (__WGPEER_A_LAST - 1)
++
++enum wgallowedip_attribute {
++ WGALLOWEDIP_A_UNSPEC,
++ WGALLOWEDIP_A_FAMILY,
++ WGALLOWEDIP_A_IPADDR,
++ WGALLOWEDIP_A_CIDR_MASK,
++ __WGALLOWEDIP_A_LAST
++};
++#define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1)
++
++#endif /* _WG_UAPI_WIREGUARD_H */
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -0,0 +1,537 @@
++#!/bin/bash
++# SPDX-License-Identifier: GPL-2.0
++#
++# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++#
++# This script tests the below topology:
++#
++# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐
++# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │
++# │ │ │ │ │ │
++# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│
++# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││
++# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│
++# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││
++# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││
++# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│
++# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘
++# └──────────────────────────────────┘
++#
++# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the
++# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0
++# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further
++# details on how this is accomplished.
++set -e
++
++exec 3>&1
++export WG_HIDE_KEYS=never
++netns0="wg-test-$$-0"
++netns1="wg-test-$$-1"
++netns2="wg-test-$$-2"
++pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; }
++pp() { pretty "" "$*"; "$@"; }
++maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; }
++n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; }
++n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; }
++n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; }
++ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
++ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
++ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
++sleep() { read -t "$1" -N 0 || true; }
++waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
++waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
++waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
++waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
++
++cleanup() {
++ set +e
++ exec 2>/dev/null
++ printf "$orig_message_cost" > /proc/sys/net/core/message_cost
++ ip0 link del dev wg0
++ ip1 link del dev wg0
++ ip2 link del dev wg0
++ local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
++ [[ -n $to_kill ]] && kill $to_kill
++ pp ip netns del $netns1
++ pp ip netns del $netns2
++ pp ip netns del $netns0
++ exit
++}
++
++orig_message_cost="$(< /proc/sys/net/core/message_cost)"
++trap cleanup EXIT
++printf 0 > /proc/sys/net/core/message_cost
++
++ip netns del $netns0 2>/dev/null || true
++ip netns del $netns1 2>/dev/null || true
++ip netns del $netns2 2>/dev/null || true
++pp ip netns add $netns0
++pp ip netns add $netns1
++pp ip netns add $netns2
++ip0 link set up dev lo
++
++ip0 link add dev wg0 type wireguard
++ip0 link set wg0 netns $netns1
++ip0 link add dev wg0 type wireguard
++ip0 link set wg0 netns $netns2
++key1="$(pp wg genkey)"
++key2="$(pp wg genkey)"
++key3="$(pp wg genkey)"
++pub1="$(pp wg pubkey <<<"$key1")"
++pub2="$(pp wg pubkey <<<"$key2")"
++pub3="$(pp wg pubkey <<<"$key3")"
++psk="$(pp wg genpsk)"
++[[ -n $key1 && -n $key2 && -n $psk ]]
++
++configure_peers() {
++ ip1 addr add 192.168.241.1/24 dev wg0
++ ip1 addr add fd00::1/24 dev wg0
++
++ ip2 addr add 192.168.241.2/24 dev wg0
++ ip2 addr add fd00::2/24 dev wg0
++
++ n1 wg set wg0 \
++ private-key <(echo "$key1") \
++ listen-port 1 \
++ peer "$pub2" \
++ preshared-key <(echo "$psk") \
++ allowed-ips 192.168.241.2/32,fd00::2/128
++ n2 wg set wg0 \
++ private-key <(echo "$key2") \
++ listen-port 2 \
++ peer "$pub1" \
++ preshared-key <(echo "$psk") \
++ allowed-ips 192.168.241.1/32,fd00::1/128
++
++ ip1 link set up dev wg0
++ ip2 link set up dev wg0
++}
++configure_peers
++
++tests() {
++ # Ping over IPv4
++ n2 ping -c 10 -f -W 1 192.168.241.1
++ n1 ping -c 10 -f -W 1 192.168.241.2
++
++ # Ping over IPv6
++ n2 ping6 -c 10 -f -W 1 fd00::1
++ n1 ping6 -c 10 -f -W 1 fd00::2
++
++ # TCP over IPv4
++ n2 iperf3 -s -1 -B 192.168.241.2 &
++ waitiperf $netns2
++ n1 iperf3 -Z -t 3 -c 192.168.241.2
++
++ # TCP over IPv6
++ n1 iperf3 -s -1 -B fd00::1 &
++ waitiperf $netns1
++ n2 iperf3 -Z -t 3 -c fd00::1
++
++ # UDP over IPv4
++ n1 iperf3 -s -1 -B 192.168.241.1 &
++ waitiperf $netns1
++ n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1
++
++ # UDP over IPv6
++ n2 iperf3 -s -1 -B fd00::2 &
++ waitiperf $netns2
++ n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
++}
++
++[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
++big_mtu=$(( 34816 - 1500 + $orig_mtu ))
++
++# Test using IPv4 as outer transport
++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
++n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1
++# Before calling tests, we first make sure that the stats counters and timestamper are working
++n2 ping -c 10 -f -W 1 192.168.241.1
++{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0)
++(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) ))
++{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0)
++(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) ))
++read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer)
++(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) ))
++read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer)
++(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) ))
++read _ timestamp < <(n1 wg show wg0 latest-handshakes)
++(( timestamp != 0 ))
++
++tests
++ip1 link set wg0 mtu $big_mtu
++ip2 link set wg0 mtu $big_mtu
++tests
++
++ip1 link set wg0 mtu $orig_mtu
++ip2 link set wg0 mtu $orig_mtu
++
++# Test using IPv6 as outer transport
++n1 wg set wg0 peer "$pub2" endpoint [::1]:2
++n2 wg set wg0 peer "$pub1" endpoint [::1]:1
++tests
++ip1 link set wg0 mtu $big_mtu
++ip2 link set wg0 mtu $big_mtu
++tests
++
++# Test that route MTUs work with the padding
++ip1 link set wg0 mtu 1300
++ip2 link set wg0 mtu 1300
++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
++n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1
++n0 iptables -A INPUT -m length --length 1360 -j DROP
++n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299
++n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299
++n2 ping -c 1 -W 1 -s 1269 192.168.241.1
++n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299
++n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299
++n0 iptables -F INPUT
++
++ip1 link set wg0 mtu $orig_mtu
++ip2 link set wg0 mtu $orig_mtu
++
++# Test using IPv4 that roaming works
++ip0 -4 addr del 127.0.0.1/8 dev lo
++ip0 -4 addr add 127.212.121.99/8 dev lo
++n1 wg set wg0 listen-port 9999
++n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
++n1 ping6 -W 1 -c 1 fd00::2
++[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]]
++
++# Test using IPv6 that roaming works
++n1 wg set wg0 listen-port 9998
++n1 wg set wg0 peer "$pub2" endpoint [::1]:2
++n1 ping -W 1 -c 1 192.168.241.2
++[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]]
++
++# Test that crypto-RP filter works
++n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24
++exec 4< <(n1 ncat -l -u -p 1111)
++ncat_pid=$!
++waitncatudp $netns1
++n2 ncat -u 192.168.241.1 1111 <<<"X"
++read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]]
++kill $ncat_pid
++more_specific_key="$(pp wg genkey | pp wg pubkey)"
++n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32
++n2 wg set wg0 listen-port 9997
++exec 4< <(n1 ncat -l -u -p 1111)
++ncat_pid=$!
++waitncatudp $netns1
++n2 ncat -u 192.168.241.1 1111 <<<"X"
++! read -r -N 1 -t 1 out <&4 || false
++kill $ncat_pid
++n1 wg set wg0 peer "$more_specific_key" remove
++[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]]
++
++# Test that we can change private keys keys and immediately handshake
++n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2
++n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32
++n1 ping -W 1 -c 1 192.168.241.2
++n1 wg set wg0 private-key <(echo "$key3")
++n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
++n1 ping -W 1 -c 1 192.168.241.2
++
++ip1 link del wg0
++ip2 link del wg0
++
++# Test using NAT. We now change the topology to this:
++# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐
++# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │
++# │ │ │ │ │ │
++# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │
++# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │
++# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │
++# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │
++# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │
++# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │
++# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘
++
++ip1 link add dev wg0 type wireguard
++ip2 link add dev wg0 type wireguard
++configure_peers
++
++ip0 link add vethrc type veth peer name vethc
++ip0 link add vethrs type veth peer name veths
++ip0 link set vethc netns $netns1
++ip0 link set veths netns $netns2
++ip0 link set vethrc up
++ip0 link set vethrs up
++ip0 addr add 192.168.1.1/24 dev vethrc
++ip0 addr add 10.0.0.1/24 dev vethrs
++ip1 addr add 192.168.1.100/24 dev vethc
++ip1 link set vethc up
++ip1 route add default via 192.168.1.1
++ip2 addr add 10.0.0.100/24 dev veths
++ip2 link set veths up
++waitiface $netns0 vethrc
++waitiface $netns0 vethrs
++waitiface $netns1 vethc
++waitiface $netns2 veths
++
++n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
++n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout'
++n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream'
++n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1
++
++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1
++n1 ping -W 1 -c 1 192.168.241.2
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
++# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`).
++pp sleep 3
++n2 ping -W 1 -c 1 192.168.241.1
++n1 wg set wg0 peer "$pub2" persistent-keepalive 0
++
++# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
++ip1 -6 addr add fc00::9/96 dev vethc
++ip1 -6 route add default via fc00::1
++ip2 -4 addr add 192.168.99.7/32 dev wg0
++ip2 -6 addr add abab::1111/128 dev wg0
++n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111
++ip1 -6 route add default dev wg0 table 51820
++ip1 -6 rule add not fwmark 51820 table 51820
++ip1 -6 rule add table main suppress_prefixlength 0
++ip1 -4 route add default dev wg0 table 51820
++ip1 -4 rule add not fwmark 51820 table 51820
++ip1 -4 rule add table main suppress_prefixlength 0
++# suppress_prefixlength only got added in 3.12, and we want to support 3.10+.
++if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then
++ # Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
++ n1 ping -W 1 -c 100 -f 192.168.99.7
++ n1 ping -W 1 -c 100 -f abab::1111
++fi
++
++n0 iptables -t nat -F
++ip0 link del vethrc
++ip0 link del vethrs
++ip1 link del wg0
++ip2 link del wg0
++
++# Test that saddr routing is sticky but not too sticky, changing to this topology:
++# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐
++# │ $ns1 namespace │ │ $ns2 namespace │
++# │ │ │ │
++# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │
++# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │
++# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │
++# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │
++# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │
++# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │
++# └────────────────────────────────────────┘ └────────────────────────────────────────┘
++
++ip1 link add dev wg0 type wireguard
++ip2 link add dev wg0 type wireguard
++configure_peers
++ip1 link add veth1 type veth peer name veth2
++ip1 link set veth2 netns $netns2
++n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad'
++n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad'
++n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad'
++n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad'
++n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries'
++
++# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed
++ip1 addr add 10.0.0.1/24 dev veth1
++ip1 addr add fd00:aa::1/96 dev veth1
++ip2 addr add 10.0.0.2/24 dev veth2
++ip2 addr add fd00:aa::2/96 dev veth2
++ip1 link set veth1 up
++ip2 link set veth2 up
++waitiface $netns1 veth1
++waitiface $netns2 veth2
++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2
++n1 ping -W 1 -c 1 192.168.241.2
++ip1 addr add 10.0.0.10/24 dev veth1
++ip1 addr del 10.0.0.1/24 dev veth1
++n1 ping -W 1 -c 1 192.168.241.2
++n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2
++n1 ping -W 1 -c 1 192.168.241.2
++ip1 addr add fd00:aa::10/96 dev veth1
++ip1 addr del fd00:aa::1/96 dev veth1
++n1 ping -W 1 -c 1 192.168.241.2
++
++# Now we show that we can successfully do reply to sender routing
++ip1 link set veth1 down
++ip2 link set veth2 down
++ip1 addr flush dev veth1
++ip2 addr flush dev veth2
++ip1 addr add 10.0.0.1/24 dev veth1
++ip1 addr add 10.0.0.2/24 dev veth1
++ip1 addr add fd00:aa::1/96 dev veth1
++ip1 addr add fd00:aa::2/96 dev veth1
++ip2 addr add 10.0.0.3/24 dev veth2
++ip2 addr add fd00:aa::3/96 dev veth2
++ip1 link set veth1 up
++ip2 link set veth2 up
++waitiface $netns1 veth1
++waitiface $netns2 veth2
++n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
++n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]]
++n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]]
++n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]]
++
++# What happens if the inbound destination address belongs to a different interface as the default route?
++ip1 link add dummy0 type dummy
++ip1 addr add 10.50.0.1/24 dev dummy0
++ip1 link set dummy0 up
++ip2 route add 10.50.0.0/24 dev veth2
++n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1
++n2 ping -W 1 -c 1 192.168.241.1
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]]
++
++ip1 link del dummy0
++ip1 addr flush dev veth1
++ip2 addr flush dev veth2
++ip1 route flush dev veth1
++ip2 route flush dev veth2
++
++# Now we see what happens if another interface route takes precedence over an ongoing one
++ip1 link add veth3 type veth peer name veth4
++ip1 link set veth4 netns $netns2
++ip1 addr add 10.0.0.1/24 dev veth1
++ip2 addr add 10.0.0.2/24 dev veth2
++ip1 addr add 10.0.0.3/24 dev veth3
++ip1 link set veth1 up
++ip2 link set veth2 up
++ip1 link set veth3 up
++ip2 link set veth4 up
++waitiface $netns1 veth1
++waitiface $netns2 veth2
++waitiface $netns1 veth3
++waitiface $netns2 veth4
++ip1 route flush dev veth1
++ip1 route flush dev veth3
++ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2
++n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2
++n1 ping -W 1 -c 1 192.168.241.2
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
++ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1
++n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter'
++n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter'
++n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter'
++n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter'
++n1 ping -W 1 -c 1 192.168.241.2
++[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]]
++
++ip1 link del veth1
++ip1 link del veth3
++ip1 link del wg0
++ip2 link del wg0
++
++# We test that Netlink/IPC is working properly by doing things that usually cause split responses
++ip0 link add dev wg0 type wireguard
++config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" )
++for a in {1..255}; do
++ for b in {0..255}; do
++ config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" )
++ done
++done
++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
++i=0
++for ip in $(n0 wg show wg0 allowed-ips); do
++ ((++i))
++done
++((i == 255*256*2+1))
++ip0 link del wg0
++ip0 link add dev wg0 type wireguard
++config=( "[Interface]" "PrivateKey=$(wg genkey)" )
++for a in {1..40}; do
++ config+=( "[Peer]" "PublicKey=$(wg genkey)" )
++ for b in {1..52}; do
++ config+=( "AllowedIPs=$a.$b.0.0/16" )
++ done
++done
++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
++i=0
++while read -r line; do
++ j=0
++ for ip in $line; do
++ ((++j))
++ done
++ ((j == 53))
++ ((++i))
++done < <(n0 wg show wg0 allowed-ips)
++((i == 40))
++ip0 link del wg0
++ip0 link add wg0 type wireguard
++config=( )
++for i in {1..29}; do
++ config+=( "[Peer]" "PublicKey=$(wg genkey)" )
++done
++config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" )
++n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
++n0 wg showconf wg0 > /dev/null
++ip0 link del wg0
++
++allowedips=( )
++for i in {1..197}; do
++ allowedips+=( abcd::$i )
++done
++saved_ifs="$IFS"
++IFS=,
++allowedips="${allowedips[*]}"
++IFS="$saved_ifs"
++ip0 link add wg0 type wireguard
++n0 wg set wg0 peer "$pub1"
++n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips"
++{
++ read -r pub allowedips
++ [[ $pub == "$pub1" && $allowedips == "(none)" ]]
++ read -r pub allowedips
++ [[ $pub == "$pub2" ]]
++ i=0
++ for _ in $allowedips; do
++ ((++i))
++ done
++ ((i == 197))
++} < <(n0 wg show wg0 allowed-ips)
++ip0 link del wg0
++
++! n0 wg show doesnotexist || false
++
++ip0 link add wg0 type wireguard
++n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk")
++[[ $(n0 wg show wg0 private-key) == "$key1" ]]
++[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]]
++n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null
++[[ $(n0 wg show wg0 private-key) == "(none)" ]]
++[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]]
++n0 wg set wg0 peer "$pub2"
++n0 wg set wg0 private-key <(echo "$key2")
++[[ $(n0 wg show wg0 public-key) == "$pub2" ]]
++[[ -z $(n0 wg show wg0 peers) ]]
++n0 wg set wg0 peer "$pub2"
++[[ -z $(n0 wg show wg0 peers) ]]
++n0 wg set wg0 private-key <(echo "$key1")
++n0 wg set wg0 peer "$pub2"
++[[ $(n0 wg show wg0 peers) == "$pub2" ]]
++n0 wg set wg0 private-key <(echo "/${key1:1}")
++[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]]
++n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16
++n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0
++n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
++n0 wg set wg0 peer "$pub2" allowed-ips ::/0
++ip0 link del wg0
++
++declare -A objects
++while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
++ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue
++ objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}"
++done < /dev/kmsg
++alldeleted=1
++for object in "${!objects[@]}"; do
++ if [[ ${objects["$object"]} != *createddestroyed ]]; then
++ echo "Error: $object: merely ${objects["$object"]}" >&3
++ alldeleted=0
++ fi
++done
++[[ $alldeleted -eq 1 ]]
++pretty "" "Objects that were created were also destroyed."
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 23 Feb 2021 14:18:58 +0100
-Subject: [PATCH] net: icmp: pass zeroed opts from icmp{,v6}_ndo_send before
- sending
-
-commit ee576c47db60432c37e54b1e2b43a8ca6d3a8dca upstream.
-
-The icmp{,v6}_send functions make all sorts of use of skb->cb, casting
-it with IPCB or IP6CB, assuming the skb to have come directly from the
-inet layer. But when the packet comes from the ndo layer, especially
-when forwarded, there's no telling what might be in skb->cb at that
-point. As a result, the icmp sending code risks reading bogus memory
-contents, which can result in nasty stack overflows such as this one
-reported by a user:
-
- panic+0x108/0x2ea
- __stack_chk_fail+0x14/0x20
- __icmp_send+0x5bd/0x5c0
- icmp_ndo_send+0x148/0x160
-
-In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read
-from it. The optlen parameter there is of particular note, as it can
-induce writes beyond bounds. There are quite a few ways that can happen
-in __ip_options_echo. For example:
-
- // sptr/skb are attacker-controlled skb bytes
- sptr = skb_network_header(skb);
- // dptr/dopt points to stack memory allocated by __icmp_send
- dptr = dopt->__data;
- // sopt is the corrupt skb->cb in question
- if (sopt->rr) {
- optlen = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data
- soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data
- // this now writes potentially attacker-controlled data, over
- // flowing the stack:
- memcpy(dptr, sptr+sopt->rr, optlen);
- }
-
-In the icmpv6_send case, the story is similar, but not as dire, as only
-IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is
-worse than the iif case, but it is passed to ipv6_find_tlv, which does
-a bit of bounds checking on the value.
-
-This is easy to simulate by doing a `memset(skb->cb, 0x41,
-sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by
-good fortune and the rarity of icmp sending from that context that we've
-avoided reports like this until now. For example, in KASAN:
-
- BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0
- Write of size 38 at addr ffff888006f1f80e by task ping/89
- CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5
- Call Trace:
- dump_stack+0x9a/0xcc
- print_address_description.constprop.0+0x1a/0x160
- __kasan_report.cold+0x20/0x38
- kasan_report+0x32/0x40
- check_memory_region+0x145/0x1a0
- memcpy+0x39/0x60
- __ip_options_echo+0xa0e/0x12b0
- __icmp_send+0x744/0x1700
-
-Actually, out of the 4 drivers that do this, only gtp zeroed the cb for
-the v4 case, while the rest did not. So this commit actually removes the
-gtp-specific zeroing, while putting the code where it belongs in the
-shared infrastructure of icmp{,v6}_ndo_send.
-
-This commit fixes the issue by passing an empty IPCB or IP6CB along to
-the functions that actually do the work. For the icmp_send, this was
-already trivial, thanks to __icmp_send providing the plumbing function.
-For icmpv6_send, this required a tiny bit of refactoring to make it
-behave like the v4 case, after which it was straight forward.
-
-Fixes: a2b78e9b2cac ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs")
-Reported-by: SinYu <liuxyon@gmail.com>
-Reviewed-by: Willem de Bruijn <willemb@google.com>
-Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA8AsP0w@mail.gmail.com/T/
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.com
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-[Jason: the gtp part didn't apply because it doesn't use icmp_ndo_send on 5.4]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- include/linux/icmpv6.h | 17 ++++++++++++++---
- include/linux/ipv6.h | 1 -
- include/net/icmp.h | 6 +++++-
- net/ipv4/icmp.c | 5 +++--
- net/ipv6/icmp.c | 16 ++++++++--------
- net/ipv6/ip6_icmp.c | 12 +++++++-----
- 6 files changed, 37 insertions(+), 20 deletions(-)
-
---- a/include/linux/icmpv6.h
-+++ b/include/linux/icmpv6.h
-@@ -3,6 +3,7 @@
- #define _LINUX_ICMPV6_H
-
- #include <linux/skbuff.h>
-+#include <linux/ipv6.h>
- #include <uapi/linux/icmpv6.h>
-
- static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb)
-@@ -13,10 +14,16 @@ static inline struct icmp6hdr *icmp6_hdr
- #include <linux/netdevice.h>
-
- #if IS_ENABLED(CONFIG_IPV6)
--extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info);
-+extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-+ const struct inet6_skb_parm *parm);
-
-+static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
-+{
-+ __icmpv6_send(skb, type, code, info, IP6CB(skb));
-+}
- typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-- const struct in6_addr *force_saddr);
-+ const struct in6_addr *force_saddr,
-+ const struct inet6_skb_parm *parm);
- extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn);
- extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn);
- int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
-@@ -25,7 +32,11 @@ int ip6_err_gen_icmpv6_unreach(struct sk
- #if IS_ENABLED(CONFIG_NF_NAT)
- void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info);
- #else
--#define icmpv6_ndo_send icmpv6_send
-+static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
-+{
-+ struct inet6_skb_parm parm = { 0 };
-+ __icmpv6_send(skb_in, type, code, info, &parm);
-+}
- #endif
-
- #else
---- a/include/linux/ipv6.h
-+++ b/include/linux/ipv6.h
-@@ -83,7 +83,6 @@ struct ipv6_params {
- __s32 autoconf;
- };
- extern struct ipv6_params ipv6_defaults;
--#include <linux/icmpv6.h>
- #include <linux/tcp.h>
- #include <linux/udp.h>
-
---- a/include/net/icmp.h
-+++ b/include/net/icmp.h
-@@ -46,7 +46,11 @@ static inline void icmp_send(struct sk_b
- #if IS_ENABLED(CONFIG_NF_NAT)
- void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info);
- #else
--#define icmp_ndo_send icmp_send
-+static inline void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
-+{
-+ struct ip_options opts = { 0 };
-+ __icmp_send(skb_in, type, code, info, &opts);
-+}
- #endif
-
- int icmp_rcv(struct sk_buff *skb);
---- a/net/ipv4/icmp.c
-+++ b/net/ipv4/icmp.c
-@@ -755,13 +755,14 @@ EXPORT_SYMBOL(__icmp_send);
- void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
- {
- struct sk_buff *cloned_skb = NULL;
-+ struct ip_options opts = { 0 };
- enum ip_conntrack_info ctinfo;
- struct nf_conn *ct;
- __be32 orig_ip;
-
- ct = nf_ct_get(skb_in, &ctinfo);
- if (!ct || !(ct->status & IPS_SRC_NAT)) {
-- icmp_send(skb_in, type, code, info);
-+ __icmp_send(skb_in, type, code, info, &opts);
- return;
- }
-
-@@ -776,7 +777,7 @@ void icmp_ndo_send(struct sk_buff *skb_i
-
- orig_ip = ip_hdr(skb_in)->saddr;
- ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
-- icmp_send(skb_in, type, code, info);
-+ __icmp_send(skb_in, type, code, info, &opts);
- ip_hdr(skb_in)->saddr = orig_ip;
- out:
- consume_skb(cloned_skb);
---- a/net/ipv6/icmp.c
-+++ b/net/ipv6/icmp.c
-@@ -312,10 +312,9 @@ static int icmpv6_getfrag(void *from, ch
- }
-
- #if IS_ENABLED(CONFIG_IPV6_MIP6)
--static void mip6_addr_swap(struct sk_buff *skb)
-+static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt)
- {
- struct ipv6hdr *iph = ipv6_hdr(skb);
-- struct inet6_skb_parm *opt = IP6CB(skb);
- struct ipv6_destopt_hao *hao;
- struct in6_addr tmp;
- int off;
-@@ -332,7 +331,7 @@ static void mip6_addr_swap(struct sk_buf
- }
- }
- #else
--static inline void mip6_addr_swap(struct sk_buff *skb) {}
-+static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {}
- #endif
-
- static struct dst_entry *icmpv6_route_lookup(struct net *net,
-@@ -427,7 +426,8 @@ static int icmp6_iif(const struct sk_buf
- * Send an ICMP message in response to a packet in error
- */
- static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-- const struct in6_addr *force_saddr)
-+ const struct in6_addr *force_saddr,
-+ const struct inet6_skb_parm *parm)
- {
- struct inet6_dev *idev = NULL;
- struct ipv6hdr *hdr = ipv6_hdr(skb);
-@@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *s
- if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
- goto out_bh_enable;
-
-- mip6_addr_swap(skb);
-+ mip6_addr_swap(skb, parm);
-
- memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_proto = IPPROTO_ICMPV6;
-@@ -605,7 +605,7 @@ out_bh_enable:
- */
- void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
- {
-- icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
-+ icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
- kfree_skb(skb);
- }
-
-@@ -662,10 +662,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk
- }
- if (type == ICMP_TIME_EXCEEDED)
- icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
-- info, &temp_saddr);
-+ info, &temp_saddr, IP6CB(skb2));
- else
- icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
-- info, &temp_saddr);
-+ info, &temp_saddr, IP6CB(skb2));
- if (rt)
- ip6_rt_put(rt);
-
---- a/net/ipv6/ip6_icmp.c
-+++ b/net/ipv6/ip6_icmp.c
-@@ -31,7 +31,8 @@ int inet6_unregister_icmp_sender(ip6_icm
- }
- EXPORT_SYMBOL(inet6_unregister_icmp_sender);
-
--void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
-+void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
-+ const struct inet6_skb_parm *parm)
- {
- ip6_icmp_send_t *send;
-
-@@ -40,16 +41,17 @@ void icmpv6_send(struct sk_buff *skb, u8
-
- if (!send)
- goto out;
-- send(skb, type, code, info, NULL);
-+ send(skb, type, code, info, NULL, parm);
- out:
- rcu_read_unlock();
- }
--EXPORT_SYMBOL(icmpv6_send);
-+EXPORT_SYMBOL(__icmpv6_send);
-
- #if IS_ENABLED(CONFIG_NF_NAT)
- #include <net/netfilter/nf_conntrack.h>
- void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
- {
-+ struct inet6_skb_parm parm = { 0 };
- struct sk_buff *cloned_skb = NULL;
- enum ip_conntrack_info ctinfo;
- struct in6_addr orig_ip;
-@@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb
-
- ct = nf_ct_get(skb_in, &ctinfo);
- if (!ct || !(ct->status & IPS_SRC_NAT)) {
-- icmpv6_send(skb_in, type, code, info);
-+ __icmpv6_send(skb_in, type, code, info, &parm);
- return;
- }
-
-@@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb
-
- orig_ip = ipv6_hdr(skb_in)->saddr;
- ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
-- icmpv6_send(skb_in, type, code, info);
-+ __icmpv6_send(skb_in, type, code, info, &parm);
- ipv6_hdr(skb_in)->saddr = orig_ip;
- out:
- consume_skb(cloned_skb);
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Sun, 15 Dec 2019 22:08:00 +0100
+Subject: [PATCH] wireguard: selftests: import harness makefile for test suite
+
+commit 65d88d04114bca7d85faebd5fed61069cb2b632c upstream.
+
+WireGuard has been using this on build.wireguard.com for the last
+several years with considerable success. It allows for very quick and
+iterative development cycles, and supports several platforms.
+
+To run the test suite on your current platform in QEMU:
+
+ $ make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
+
+To run it with KASAN and such turned on:
+
+ $ DEBUG_KERNEL=yes make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
+
+To run it emulated for another platform in QEMU:
+
+ $ ARCH=arm make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
+
+At the moment, we support aarch64_be, aarch64, arm, armeb, i686, m68k,
+mips64, mips64el, mips, mipsel, powerpc64le, powerpc, and x86_64.
+
+The system supports incremental rebuilding, so it should be very fast to
+change a single file and then test it out and have immediate feedback.
+
+This requires for the right toolchain and qemu to be installed prior.
+I've had success with those from musl.cc.
+
+This is tailored for WireGuard at the moment, though later projects
+might generalize it for other network testing.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ .../selftests/wireguard/qemu/.gitignore | 2 +
+ .../testing/selftests/wireguard/qemu/Makefile | 385 ++++++++++++++++++
+ .../wireguard/qemu/arch/aarch64.config | 5 +
+ .../wireguard/qemu/arch/aarch64_be.config | 6 +
+ .../selftests/wireguard/qemu/arch/arm.config | 9 +
+ .../wireguard/qemu/arch/armeb.config | 10 +
+ .../selftests/wireguard/qemu/arch/i686.config | 5 +
+ .../selftests/wireguard/qemu/arch/m68k.config | 9 +
+ .../selftests/wireguard/qemu/arch/mips.config | 11 +
+ .../wireguard/qemu/arch/mips64.config | 14 +
+ .../wireguard/qemu/arch/mips64el.config | 15 +
+ .../wireguard/qemu/arch/mipsel.config | 12 +
+ .../wireguard/qemu/arch/powerpc.config | 10 +
+ .../wireguard/qemu/arch/powerpc64le.config | 12 +
+ .../wireguard/qemu/arch/x86_64.config | 5 +
+ .../selftests/wireguard/qemu/debug.config | 67 +++
+ tools/testing/selftests/wireguard/qemu/init.c | 284 +++++++++++++
+ .../selftests/wireguard/qemu/kernel.config | 86 ++++
+ 18 files changed, 947 insertions(+)
+ create mode 100644 tools/testing/selftests/wireguard/qemu/.gitignore
+ create mode 100644 tools/testing/selftests/wireguard/qemu/Makefile
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/arm.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/armeb.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/i686.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/m68k.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64el.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mipsel.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/arch/x86_64.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/debug.config
+ create mode 100644 tools/testing/selftests/wireguard/qemu/init.c
+ create mode 100644 tools/testing/selftests/wireguard/qemu/kernel.config
+
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/.gitignore
+@@ -0,0 +1,2 @@
++build/
++distfiles/
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/Makefile
+@@ -0,0 +1,385 @@
++# SPDX-License-Identifier: GPL-2.0
++#
++# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++
++PWD := $(shell pwd)
++
++CHOST := $(shell gcc -dumpmachine)
++ifneq (,$(ARCH))
++CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
++ifeq (,$(CBUILD))
++$(error The toolchain for $(ARCH) is not installed)
++endif
++else
++CBUILD := $(CHOST)
++ARCH := $(firstword $(subst -, ,$(CBUILD)))
++endif
++
++# Set these from the environment to override
++KERNEL_PATH ?= $(PWD)/../../../../..
++BUILD_PATH ?= $(PWD)/build/$(ARCH)
++DISTFILES_PATH ?= $(PWD)/distfiles
++NR_CPUS ?= 4
++
++MIRROR := https://download.wireguard.com/qemu-test/distfiles/
++
++default: qemu
++
++# variable name, tarball project name, version, tarball extension, default URI base
++define tar_download =
++$(1)_VERSION := $(3)
++$(1)_NAME := $(2)-$$($(1)_VERSION)
++$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4)
++$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME)
++$(call file_download,$$($(1)_NAME)$(4),$(5),$(6))
++endef
++
++define file_download =
++$(DISTFILES_PATH)/$(1):
++ mkdir -p $(DISTFILES_PATH)
++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
++ if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
++endef
++
++$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61))
++$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
++$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f))
++$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
++$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2))
++$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5))
++$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21))
++$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a))
++$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071))
++
++KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
++rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
++WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*)
++
++export CFLAGS ?= -O3 -pipe
++export LDFLAGS ?=
++export CPPFLAGS := -I$(BUILD_PATH)/include
++
++ifeq ($(CHOST),$(CBUILD))
++CROSS_COMPILE_FLAG := --host=$(CHOST)
++NOPIE_GCC := gcc -fno-PIE
++CFLAGS += -march=native
++STRIP := strip
++else
++$(info Cross compilation: building for $(CBUILD) using $(CHOST))
++CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
++export CROSS_COMPILE=$(CBUILD)-
++NOPIE_GCC := $(CBUILD)-gcc -fno-PIE
++STRIP := $(CBUILD)-strip
++endif
++ifeq ($(ARCH),aarch64)
++QEMU_ARCH := aarch64
++KERNEL_ARCH := arm64
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
++else
++QEMU_MACHINE := -cpu cortex-a53 -machine virt
++CFLAGS += -march=armv8-a -mtune=cortex-a53
++endif
++else ifeq ($(ARCH),aarch64_be)
++QEMU_ARCH := aarch64
++KERNEL_ARCH := arm64
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
++else
++QEMU_MACHINE := -cpu cortex-a53 -machine virt
++CFLAGS += -march=armv8-a -mtune=cortex-a53
++endif
++else ifeq ($(ARCH),arm)
++QEMU_ARCH := arm
++KERNEL_ARCH := arm
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
++else
++QEMU_MACHINE := -cpu cortex-a15 -machine virt
++CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux
++endif
++else ifeq ($(ARCH),armeb)
++QEMU_ARCH := arm
++KERNEL_ARCH := arm
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
++else
++QEMU_MACHINE := -cpu cortex-a15 -machine virt
++CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian.
++LDFLAGS += -Wl,--be8
++endif
++else ifeq ($(ARCH),x86_64)
++QEMU_ARCH := x86_64
++KERNEL_ARCH := x86_64
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine q35,accel=kvm
++else
++QEMU_MACHINE := -cpu Skylake-Server -machine q35
++CFLAGS += -march=skylake-avx512
++endif
++else ifeq ($(ARCH),i686)
++QEMU_ARCH := i386
++KERNEL_ARCH := x86
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
++ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST))
++QEMU_MACHINE := -cpu host -machine q35,accel=kvm
++else
++QEMU_MACHINE := -cpu coreduo -machine q35
++CFLAGS += -march=prescott
++endif
++else ifeq ($(ARCH),mips64)
++QEMU_ARCH := mips64
++KERNEL_ARCH := mips
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine malta,accel=kvm
++CFLAGS += -EB
++else
++QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
++CFLAGS += -march=mips64r2 -EB
++endif
++else ifeq ($(ARCH),mips64el)
++QEMU_ARCH := mips64el
++KERNEL_ARCH := mips
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine malta,accel=kvm
++CFLAGS += -EL
++else
++QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
++CFLAGS += -march=mips64r2 -EL
++endif
++else ifeq ($(ARCH),mips)
++QEMU_ARCH := mips
++KERNEL_ARCH := mips
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine malta,accel=kvm
++CFLAGS += -EB
++else
++QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
++CFLAGS += -march=mips32r2 -EB
++endif
++else ifeq ($(ARCH),mipsel)
++QEMU_ARCH := mipsel
++KERNEL_ARCH := mips
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host -machine malta,accel=kvm
++CFLAGS += -EL
++else
++QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
++CFLAGS += -march=mips32r2 -EL
++endif
++else ifeq ($(ARCH),powerpc64le)
++QEMU_ARCH := ppc64
++KERNEL_ARCH := powerpc
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
++else
++QEMU_MACHINE := -machine pseries
++endif
++CFLAGS += -mcpu=powerpc64le -mlong-double-64
++else ifeq ($(ARCH),powerpc)
++QEMU_ARCH := ppc
++KERNEL_ARCH := powerpc
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
++else
++QEMU_MACHINE := -machine ppce500
++endif
++CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt
++else ifeq ($(ARCH),m68k)
++QEMU_ARCH := m68k
++KERNEL_ARCH := m68k
++KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
++ifeq ($(CHOST),$(CBUILD))
++QEMU_MACHINE := -cpu host,accel=kvm -machine q800
++else
++QEMU_MACHINE := -machine q800
++endif
++else
++$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
++endif
++
++REAL_CC := $(CBUILD)-gcc
++MUSL_CC := $(BUILD_PATH)/musl-gcc
++export CC := $(MUSL_CC)
++USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed
++
++build: $(KERNEL_BZIMAGE)
++qemu: $(KERNEL_BZIMAGE)
++ rm -f $(BUILD_PATH)/result
++ timeout --foreground 20m qemu-system-$(QEMU_ARCH) \
++ -nodefaults \
++ -nographic \
++ -smp $(NR_CPUS) \
++ $(QEMU_MACHINE) \
++ -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \
++ -serial stdio \
++ -serial file:$(BUILD_PATH)/result \
++ -no-reboot \
++ -monitor none \
++ -kernel $<
++ grep -Fq success $(BUILD_PATH)/result
++
++$(BUILD_PATH)/init-cpio-spec.txt:
++ mkdir -p $(BUILD_PATH)
++ echo "file /init $(BUILD_PATH)/init 755 0 0" > $@
++ echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@
++ echo "dir /dev 755 0 0" >> $@
++ echo "nod /dev/console 644 0 0 c 5 1" >> $@
++ echo "dir /bin 755 0 0" >> $@
++ echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@
++ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@
++ echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@
++ echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@
++ echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@
++ echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@
++ echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@
++ echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@
++ echo "slink /bin/iptables xtables-multi 777 0 0" >> $@
++ echo "slink /bin/ping6 ping 777 0 0" >> $@
++ echo "dir /lib 755 0 0" >> $@
++ echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
++ echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@
++
++$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config
++ mkdir -p $(KERNEL_BUILD_PATH)
++ cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config
++ printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config
++ cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig
++ cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
++ $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
++
++$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)"
++
++$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
++ touch $@
++
++$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD)
++ $(MAKE) -C $(MUSL_PATH)
++ $(STRIP) -s $@
++
++$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so
++ $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers
++ touch $@
++
++$(MUSL_CC): $(MUSL_PATH)/lib/libc.so
++ sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
++ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc
++ chmod +x $(BUILD_PATH)/musl-gcc
++
++$(IPERF_PATH)/.installed: $(IPERF_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ sed -i '1s/^/#include <stdint.h>/' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h
++ sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile*
++ touch $@
++
++$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
++ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
++ $(MAKE) -C $(IPERF_PATH)
++ $(STRIP) -s $@
++
++$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ touch $@
++
++$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
++ cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
++ $(MAKE) -C $(LIBMNL_PATH)
++ sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
++
++$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ touch $@
++
++$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
++ $(STRIP) -s $@
++
++$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
++ mkdir -p $(BUILD_PATH)
++ $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $<
++ $(STRIP) -s $@
++
++$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ touch $@
++
++$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS)
++ $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping
++ $(STRIP) -s $@
++
++$(BASH_PATH)/.installed: $(BASH_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ touch $@
++
++$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS)
++ cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble
++ $(MAKE) -C $(BASH_PATH)
++ $(STRIP) -s $@
++
++$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
++ printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
++ touch $@
++
++$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
++ $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
++
++$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
++ $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
++
++$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
++ touch $@
++
++$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++ cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
++ $(MAKE) -C $(IPTABLES_PATH)
++ $(STRIP) -s $@
++
++$(NMAP_PATH)/.installed: $(NMAP_TAR)
++ mkdir -p $(BUILD_PATH)
++ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
++ touch $@
++
++$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS)
++ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux
++ $(MAKE) -C $(NMAP_PATH) build-ncat
++ $(STRIP) -s $@
++
++clean:
++ rm -rf $(BUILD_PATH)
++
++distclean: clean
++ rm -rf $(DISTFILES_PATH)
++
++menuconfig: $(KERNEL_BUILD_PATH)/.config
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig
++
++.PHONY: qemu build clean distclean menuconfig
++.DELETE_ON_ERROR:
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config
+@@ -0,0 +1,5 @@
++CONFIG_SERIAL_AMBA_PL011=y
++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
+@@ -0,0 +1,6 @@
++CONFIG_CPU_BIG_ENDIAN=y
++CONFIG_SERIAL_AMBA_PL011=y
++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config
+@@ -0,0 +1,9 @@
++CONFIG_MMU=y
++CONFIG_ARCH_MULTI_V7=y
++CONFIG_ARCH_VIRT=y
++CONFIG_THUMB2_KERNEL=n
++CONFIG_SERIAL_AMBA_PL011=y
++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config
+@@ -0,0 +1,10 @@
++CONFIG_MMU=y
++CONFIG_ARCH_MULTI_V7=y
++CONFIG_ARCH_VIRT=y
++CONFIG_THUMB2_KERNEL=n
++CONFIG_SERIAL_AMBA_PL011=y
++CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
++CONFIG_CPU_BIG_ENDIAN=y
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config
+@@ -0,0 +1,5 @@
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
+@@ -0,0 +1,9 @@
++CONFIG_MMU=y
++CONFIG_M68040=y
++CONFIG_MAC=y
++CONFIG_SERIAL_PMACZILOG=y
++CONFIG_SERIAL_PMACZILOG_TTYS=y
++CONFIG_SERIAL_PMACZILOG_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config
+@@ -0,0 +1,11 @@
++CONFIG_CPU_MIPS32_R2=y
++CONFIG_MIPS_MALTA=y
++CONFIG_MIPS_CPS=y
++CONFIG_MIPS_FP_SUPPORT=y
++CONFIG_POWER_RESET=y
++CONFIG_POWER_RESET_SYSCON=y
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config
+@@ -0,0 +1,14 @@
++CONFIG_64BIT=y
++CONFIG_CPU_MIPS64_R2=y
++CONFIG_MIPS32_N32=y
++CONFIG_CPU_HAS_MSA=y
++CONFIG_MIPS_MALTA=y
++CONFIG_MIPS_CPS=y
++CONFIG_MIPS_FP_SUPPORT=y
++CONFIG_POWER_RESET=y
++CONFIG_POWER_RESET_SYSCON=y
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config
+@@ -0,0 +1,15 @@
++CONFIG_64BIT=y
++CONFIG_CPU_MIPS64_R2=y
++CONFIG_MIPS32_N32=y
++CONFIG_CPU_HAS_MSA=y
++CONFIG_MIPS_MALTA=y
++CONFIG_CPU_LITTLE_ENDIAN=y
++CONFIG_MIPS_CPS=y
++CONFIG_MIPS_FP_SUPPORT=y
++CONFIG_POWER_RESET=y
++CONFIG_POWER_RESET_SYSCON=y
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config
+@@ -0,0 +1,12 @@
++CONFIG_CPU_MIPS32_R2=y
++CONFIG_MIPS_MALTA=y
++CONFIG_CPU_LITTLE_ENDIAN=y
++CONFIG_MIPS_CPS=y
++CONFIG_MIPS_FP_SUPPORT=y
++CONFIG_POWER_RESET=y
++CONFIG_POWER_RESET_SYSCON=y
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config
+@@ -0,0 +1,10 @@
++CONFIG_PPC_QEMU_E500=y
++CONFIG_FSL_SOC_BOOKE=y
++CONFIG_PPC_85xx=y
++CONFIG_PHYS_64BIT=y
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_MATH_EMULATION=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1024
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+@@ -0,0 +1,12 @@
++CONFIG_PPC64=y
++CONFIG_PPC_PSERIES=y
++CONFIG_ALTIVEC=y
++CONFIG_VSX=y
++CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
++CONFIG_PPC_RADIX_MMU=y
++CONFIG_HVC_CONSOLE=y
++CONFIG_CPU_LITTLE_ENDIAN=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
++CONFIG_SECTION_MISMATCH_WARN_ONLY=y
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
+@@ -0,0 +1,5 @@
++CONFIG_SERIAL_8250=y
++CONFIG_SERIAL_8250_CONSOLE=y
++CONFIG_CMDLINE_BOOL=y
++CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
++CONFIG_FRAME_WARN=1280
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/debug.config
+@@ -0,0 +1,67 @@
++CONFIG_LOCALVERSION="-debug"
++CONFIG_ENABLE_WARN_DEPRECATED=y
++CONFIG_ENABLE_MUST_CHECK=y
++CONFIG_FRAME_POINTER=y
++CONFIG_STACK_VALIDATION=y
++CONFIG_DEBUG_KERNEL=y
++CONFIG_DEBUG_INFO=y
++CONFIG_DEBUG_INFO_DWARF4=y
++CONFIG_PAGE_EXTENSION=y
++CONFIG_PAGE_POISONING=y
++CONFIG_DEBUG_OBJECTS=y
++CONFIG_DEBUG_OBJECTS_FREE=y
++CONFIG_DEBUG_OBJECTS_TIMERS=y
++CONFIG_DEBUG_OBJECTS_WORK=y
++CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
++CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
++CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
++CONFIG_SLUB_DEBUG_ON=y
++CONFIG_DEBUG_VM=y
++CONFIG_DEBUG_MEMORY_INIT=y
++CONFIG_HAVE_DEBUG_STACKOVERFLOW=y
++CONFIG_DEBUG_STACKOVERFLOW=y
++CONFIG_HAVE_ARCH_KMEMCHECK=y
++CONFIG_HAVE_ARCH_KASAN=y
++CONFIG_KASAN=y
++CONFIG_KASAN_INLINE=y
++CONFIG_UBSAN=y
++CONFIG_UBSAN_SANITIZE_ALL=y
++CONFIG_UBSAN_NO_ALIGNMENT=y
++CONFIG_UBSAN_NULL=y
++CONFIG_DEBUG_KMEMLEAK=y
++CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192
++CONFIG_DEBUG_STACK_USAGE=y
++CONFIG_DEBUG_SHIRQ=y
++CONFIG_WQ_WATCHDOG=y
++CONFIG_SCHED_DEBUG=y
++CONFIG_SCHED_INFO=y
++CONFIG_SCHEDSTATS=y
++CONFIG_SCHED_STACK_END_CHECK=y
++CONFIG_DEBUG_TIMEKEEPING=y
++CONFIG_TIMER_STATS=y
++CONFIG_DEBUG_PREEMPT=y
++CONFIG_DEBUG_RT_MUTEXES=y
++CONFIG_DEBUG_SPINLOCK=y
++CONFIG_DEBUG_MUTEXES=y
++CONFIG_DEBUG_LOCK_ALLOC=y
++CONFIG_PROVE_LOCKING=y
++CONFIG_LOCKDEP=y
++CONFIG_DEBUG_ATOMIC_SLEEP=y
++CONFIG_TRACE_IRQFLAGS=y
++CONFIG_DEBUG_BUGVERBOSE=y
++CONFIG_DEBUG_LIST=y
++CONFIG_DEBUG_PI_LIST=y
++CONFIG_PROVE_RCU=y
++CONFIG_SPARSE_RCU_POINTER=y
++CONFIG_RCU_CPU_STALL_TIMEOUT=21
++CONFIG_RCU_TRACE=y
++CONFIG_RCU_EQS_DEBUG=y
++CONFIG_USER_STACKTRACE_SUPPORT=y
++CONFIG_DEBUG_SG=y
++CONFIG_DEBUG_NOTIFIERS=y
++CONFIG_DOUBLEFAULT=y
++CONFIG_X86_DEBUG_FPU=y
++CONFIG_DEBUG_SECTION_MISMATCH=y
++CONFIG_DEBUG_PAGEALLOC=y
++CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y
++CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/init.c
+@@ -0,0 +1,284 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
++ */
++
++#define _GNU_SOURCE
++#include <unistd.h>
++#include <errno.h>
++#include <string.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <stdbool.h>
++#include <fcntl.h>
++#include <sys/wait.h>
++#include <sys/mount.h>
++#include <sys/types.h>
++#include <sys/stat.h>
++#include <sys/types.h>
++#include <sys/io.h>
++#include <sys/ioctl.h>
++#include <sys/reboot.h>
++#include <sys/utsname.h>
++#include <sys/sendfile.h>
++#include <linux/random.h>
++#include <linux/version.h>
++
++__attribute__((noreturn)) static void poweroff(void)
++{
++ fflush(stdout);
++ fflush(stderr);
++ reboot(RB_AUTOBOOT);
++ sleep(30);
++ fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n");
++ exit(1);
++}
++
++static void panic(const char *what)
++{
++ fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno));
++ poweroff();
++}
++
++#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m")
++
++static void print_banner(void)
++{
++ struct utsname utsname;
++ int len;
++
++ if (uname(&utsname) < 0)
++ panic("uname");
++
++ len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine);
++ printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, "");
++}
++
++static void seed_rng(void)
++{
++ int fd;
++ struct {
++ int entropy_count;
++ int buffer_size;
++ unsigned char buffer[256];
++ } entropy = {
++ .entropy_count = sizeof(entropy.buffer) * 8,
++ .buffer_size = sizeof(entropy.buffer),
++ .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!"
++ };
++
++ if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9)))
++ panic("mknod(/dev/urandom)");
++ fd = open("/dev/urandom", O_WRONLY);
++ if (fd < 0)
++ panic("open(urandom)");
++ for (int i = 0; i < 256; ++i) {
++ if (ioctl(fd, RNDADDENTROPY, &entropy) < 0)
++ panic("ioctl(urandom)");
++ }
++ close(fd);
++}
++
++static void mount_filesystems(void)
++{
++ pretty_message("[+] Mounting filesystems...");
++ mkdir("/dev", 0755);
++ mkdir("/proc", 0755);
++ mkdir("/sys", 0755);
++ mkdir("/tmp", 0755);
++ mkdir("/run", 0755);
++ mkdir("/var", 0755);
++ if (mount("none", "/dev", "devtmpfs", 0, NULL))
++ panic("devtmpfs mount");
++ if (mount("none", "/proc", "proc", 0, NULL))
++ panic("procfs mount");
++ if (mount("none", "/sys", "sysfs", 0, NULL))
++ panic("sysfs mount");
++ if (mount("none", "/tmp", "tmpfs", 0, NULL))
++ panic("tmpfs mount");
++ if (mount("none", "/run", "tmpfs", 0, NULL))
++ panic("tmpfs mount");
++ if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL))
++ ; /* Not a problem if it fails.*/
++ if (symlink("/run", "/var/run"))
++ panic("run symlink");
++ if (symlink("/proc/self/fd", "/dev/fd"))
++ panic("fd symlink");
++}
++
++static void enable_logging(void)
++{
++ int fd;
++ pretty_message("[+] Enabling logging...");
++ fd = open("/proc/sys/kernel/printk", O_WRONLY);
++ if (fd >= 0) {
++ if (write(fd, "9\n", 2) != 2)
++ panic("write(printk)");
++ close(fd);
++ }
++ fd = open("/proc/sys/debug/exception-trace", O_WRONLY);
++ if (fd >= 0) {
++ if (write(fd, "1\n", 2) != 2)
++ panic("write(exception-trace)");
++ close(fd);
++ }
++ fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY);
++ if (fd >= 0) {
++ if (write(fd, "1\n", 2) != 2)
++ panic("write(panic_on_warn)");
++ close(fd);
++ }
++}
++
++static void kmod_selftests(void)
++{
++ FILE *file;
++ char line[2048], *start, *pass;
++ bool success = true;
++ pretty_message("[+] Module self-tests:");
++ file = fopen("/proc/kmsg", "r");
++ if (!file)
++ panic("fopen(kmsg)");
++ if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0)
++ panic("fcntl(kmsg, nonblock)");
++ while (fgets(line, sizeof(line), file)) {
++ start = strstr(line, "wireguard: ");
++ if (!start)
++ continue;
++ start += 11;
++ *strchrnul(start, '\n') = '\0';
++ if (strstr(start, "www.wireguard.com"))
++ break;
++ pass = strstr(start, ": pass");
++ if (!pass || pass[6] != '\0') {
++ success = false;
++ printf(" \x1b[31m* %s\x1b[0m\n", start);
++ } else
++ printf(" \x1b[32m* %s\x1b[0m\n", start);
++ }
++ fclose(file);
++ if (!success) {
++ puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m");
++ poweroff();
++ }
++}
++
++static void launch_tests(void)
++{
++ char cmdline[4096], *success_dev;
++ int status, fd;
++ pid_t pid;
++
++ pretty_message("[+] Launching tests...");
++ pid = fork();
++ if (pid == -1)
++ panic("fork");
++ else if (pid == 0) {
++ execl("/init.sh", "init", NULL);
++ panic("exec");
++ }
++ if (waitpid(pid, &status, 0) < 0)
++ panic("waitpid");
++ if (WIFEXITED(status) && WEXITSTATUS(status) == 0) {
++ pretty_message("[+] Tests successful! :-)");
++ fd = open("/proc/cmdline", O_RDONLY);
++ if (fd < 0)
++ panic("open(/proc/cmdline)");
++ if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0)
++ panic("read(/proc/cmdline)");
++ cmdline[sizeof(cmdline) - 1] = '\0';
++ for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) {
++ if (strncmp(success_dev, "wg.success=", 11))
++ continue;
++ memcpy(success_dev + 11 - 5, "/dev/", 5);
++ success_dev += 11 - 5;
++ break;
++ }
++ if (!success_dev || !strlen(success_dev))
++ panic("Unable to find success device");
++
++ fd = open(success_dev, O_WRONLY);
++ if (fd < 0)
++ panic("open(success_dev)");
++ if (write(fd, "success\n", 8) != 8)
++ panic("write(success_dev)");
++ close(fd);
++ } else {
++ const char *why = "unknown cause";
++ int what = -1;
++
++ if (WIFEXITED(status)) {
++ why = "exit code";
++ what = WEXITSTATUS(status);
++ } else if (WIFSIGNALED(status)) {
++ why = "signal";
++ what = WTERMSIG(status);
++ }
++ printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what);
++ }
++}
++
++static void ensure_console(void)
++{
++ for (unsigned int i = 0; i < 1000; ++i) {
++ int fd = open("/dev/console", O_RDWR);
++ if (fd < 0) {
++ usleep(50000);
++ continue;
++ }
++ dup2(fd, 0);
++ dup2(fd, 1);
++ dup2(fd, 2);
++ close(fd);
++ if (write(1, "\0\0\0\0\n", 5) == 5)
++ return;
++ }
++ panic("Unable to open console device");
++}
++
++static void clear_leaks(void)
++{
++ int fd;
++
++ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY);
++ if (fd < 0)
++ return;
++ pretty_message("[+] Starting memory leak detection...");
++ write(fd, "clear\n", 5);
++ close(fd);
++}
++
++static void check_leaks(void)
++{
++ int fd;
++
++ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY);
++ if (fd < 0)
++ return;
++ pretty_message("[+] Scanning for memory leaks...");
++ sleep(2); /* Wait for any grace periods. */
++ write(fd, "scan\n", 5);
++ close(fd);
++
++ fd = open("/sys/kernel/debug/kmemleak", O_RDONLY);
++ if (fd < 0)
++ return;
++ if (sendfile(1, fd, NULL, 0x7ffff000) > 0)
++ panic("Memory leaks encountered");
++ close(fd);
++}
++
++int main(int argc, char *argv[])
++{
++ seed_rng();
++ ensure_console();
++ print_banner();
++ mount_filesystems();
++ kmod_selftests();
++ enable_logging();
++ clear_leaks();
++ launch_tests();
++ check_leaks();
++ poweroff();
++ return 1;
++}
+--- /dev/null
++++ b/tools/testing/selftests/wireguard/qemu/kernel.config
+@@ -0,0 +1,86 @@
++CONFIG_LOCALVERSION=""
++CONFIG_NET=y
++CONFIG_NETDEVICES=y
++CONFIG_NET_CORE=y
++CONFIG_NET_IPIP=y
++CONFIG_DUMMY=y
++CONFIG_VETH=y
++CONFIG_MULTIUSER=y
++CONFIG_NAMESPACES=y
++CONFIG_NET_NS=y
++CONFIG_UNIX=y
++CONFIG_INET=y
++CONFIG_IPV6=y
++CONFIG_NETFILTER=y
++CONFIG_NETFILTER_ADVANCED=y
++CONFIG_NF_CONNTRACK=y
++CONFIG_NF_NAT=y
++CONFIG_NETFILTER_XTABLES=y
++CONFIG_NETFILTER_XT_NAT=y
++CONFIG_NETFILTER_XT_MATCH_LENGTH=y
++CONFIG_NF_CONNTRACK_IPV4=y
++CONFIG_NF_NAT_IPV4=y
++CONFIG_IP_NF_IPTABLES=y
++CONFIG_IP_NF_FILTER=y
++CONFIG_IP_NF_NAT=y
++CONFIG_IP_ADVANCED_ROUTER=y
++CONFIG_IP_MULTIPLE_TABLES=y
++CONFIG_IPV6_MULTIPLE_TABLES=y
++CONFIG_TTY=y
++CONFIG_BINFMT_ELF=y
++CONFIG_BINFMT_SCRIPT=y
++CONFIG_VDSO=y
++CONFIG_VIRTUALIZATION=y
++CONFIG_HYPERVISOR_GUEST=y
++CONFIG_PARAVIRT=y
++CONFIG_KVM_GUEST=y
++CONFIG_PARAVIRT_SPINLOCKS=y
++CONFIG_PRINTK=y
++CONFIG_KALLSYMS=y
++CONFIG_BUG=y
++CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
++CONFIG_EMBEDDED=n
++CONFIG_BASE_FULL=y
++CONFIG_FUTEX=y
++CONFIG_SHMEM=y
++CONFIG_SLUB=y
++CONFIG_SPARSEMEM_VMEMMAP=y
++CONFIG_SMP=y
++CONFIG_SCHED_SMT=y
++CONFIG_SCHED_MC=y
++CONFIG_NUMA=y
++CONFIG_PREEMPT=y
++CONFIG_NO_HZ=y
++CONFIG_NO_HZ_IDLE=y
++CONFIG_NO_HZ_FULL=n
++CONFIG_HZ_PERIODIC=n
++CONFIG_HIGH_RES_TIMERS=y
++CONFIG_ARCH_RANDOM=y
++CONFIG_FILE_LOCKING=y
++CONFIG_POSIX_TIMERS=y
++CONFIG_DEVTMPFS=y
++CONFIG_PROC_FS=y
++CONFIG_PROC_SYSCTL=y
++CONFIG_SYSFS=y
++CONFIG_TMPFS=y
++CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
++CONFIG_PRINTK_TIME=y
++CONFIG_BLK_DEV_INITRD=y
++CONFIG_LEGACY_VSYSCALL_NONE=y
++CONFIG_KERNEL_GZIP=y
++CONFIG_PANIC_ON_OOPS=y
++CONFIG_BUG_ON_DATA_CORRUPTION=y
++CONFIG_LOCKUP_DETECTOR=y
++CONFIG_SOFTLOCKUP_DETECTOR=y
++CONFIG_HARDLOCKUP_DETECTOR=y
++CONFIG_WQ_WATCHDOG=y
++CONFIG_DETECT_HUNG_TASK=y
++CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y
++CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
++CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
++CONFIG_PANIC_TIMEOUT=-1
++CONFIG_STACKTRACE=y
++CONFIG_EARLY_PRINTK=y
++CONFIG_GDB_SCRIPTS=y
++CONFIG_WIREGUARD=y
++CONFIG_WIREGUARD_DEBUG=y
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 9 Dec 2019 00:27:34 +0100
-Subject: [PATCH] net: WireGuard secure network tunnel
-
-commit e7096c131e5161fa3b8e52a650d7719d2857adfd upstream.
-
-WireGuard is a layer 3 secure networking tunnel made specifically for
-the kernel, that aims to be much simpler and easier to audit than IPsec.
-Extensive documentation and description of the protocol and
-considerations, along with formal proofs of the cryptography, are
-available at:
-
- * https://www.wireguard.com/
- * https://www.wireguard.com/papers/wireguard.pdf
-
-This commit implements WireGuard as a simple network device driver,
-accessible in the usual RTNL way used by virtual network drivers. It
-makes use of the udp_tunnel APIs, GRO, GSO, NAPI, and the usual set of
-networking subsystem APIs. It has a somewhat novel multicore queueing
-system designed for maximum throughput and minimal latency of encryption
-operations, but it is implemented modestly using workqueues and NAPI.
-Configuration is done via generic Netlink, and following a review from
-the Netlink maintainer a year ago, several high profile userspace tools
-have already implemented the API.
-
-This commit also comes with several different tests, both in-kernel
-tests and out-of-kernel tests based on network namespaces, taking profit
-of the fact that sockets used by WireGuard intentionally stay in the
-namespace the WireGuard interface was originally created, exactly like
-the semantics of userspace tun devices. See wireguard.com/netns/ for
-pictures and examples.
-
-The source code is fairly short, but rather than combining everything
-into a single file, WireGuard is developed as cleanly separable files,
-making auditing and comprehension easier. Things are laid out as
-follows:
-
- * noise.[ch], cookie.[ch], messages.h: These implement the bulk of the
- cryptographic aspects of the protocol, and are mostly data-only in
- nature, taking in buffers of bytes and spitting out buffers of
- bytes. They also handle reference counting for their various shared
- pieces of data, like keys and key lists.
-
- * ratelimiter.[ch]: Used as an integral part of cookie.[ch] for
- ratelimiting certain types of cryptographic operations in accordance
- with particular WireGuard semantics.
-
- * allowedips.[ch], peerlookup.[ch]: The main lookup structures of
- WireGuard, the former being trie-like with particular semantics, an
- integral part of the design of the protocol, and the latter just
- being nice helper functions around the various hashtables we use.
-
- * device.[ch]: Implementation of functions for the netdevice and for
- rtnl, responsible for maintaining the life of a given interface and
- wiring it up to the rest of WireGuard.
-
- * peer.[ch]: Each interface has a list of peers, with helper functions
- available here for creation, destruction, and reference counting.
-
- * socket.[ch]: Implementation of functions related to udp_socket and
- the general set of kernel socket APIs, for sending and receiving
- ciphertext UDP packets, and taking care of WireGuard-specific sticky
- socket routing semantics for the automatic roaming.
-
- * netlink.[ch]: Userspace API entry point for configuring WireGuard
- peers and devices. The API has been implemented by several userspace
- tools and network management utility, and the WireGuard project
- distributes the basic wg(8) tool.
-
- * queueing.[ch]: Shared function on the rx and tx path for handling
- the various queues used in the multicore algorithms.
-
- * send.c: Handles encrypting outgoing packets in parallel on
- multiple cores, before sending them in order on a single core, via
- workqueues and ring buffers. Also handles sending handshake and cookie
- messages as part of the protocol, in parallel.
-
- * receive.c: Handles decrypting incoming packets in parallel on
- multiple cores, before passing them off in order to be ingested via
- the rest of the networking subsystem with GRO via the typical NAPI
- poll function. Also handles receiving handshake and cookie messages
- as part of the protocol, in parallel.
-
- * timers.[ch]: Uses the timer wheel to implement protocol particular
- event timeouts, and gives a set of very simple event-driven entry
- point functions for callers.
-
- * main.c, version.h: Initialization and deinitialization of the module.
-
- * selftest/*.h: Runtime unit tests for some of the most security
- sensitive functions.
-
- * tools/testing/selftests/wireguard/netns.sh: Aforementioned testing
- script using network namespaces.
-
-This commit aims to be as self-contained as possible, implementing
-WireGuard as a standalone module not needing much special handling or
-coordination from the network subsystem. I expect for future
-optimizations to the network stack to positively improve WireGuard, and
-vice-versa, but for the time being, this exists as intentionally
-standalone.
-
-We introduce a menu option for CONFIG_WIREGUARD, as well as providing a
-verbose debug log and self-tests via CONFIG_WIREGUARD_DEBUG.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Cc: David Miller <davem@davemloft.net>
-Cc: Greg KH <gregkh@linuxfoundation.org>
-Cc: Linus Torvalds <torvalds@linux-foundation.org>
-Cc: Herbert Xu <herbert@gondor.apana.org.au>
-Cc: linux-crypto@vger.kernel.org
-Cc: linux-kernel@vger.kernel.org
-Cc: netdev@vger.kernel.org
-Signed-off-by: David S. Miller <davem@davemloft.net>
-[Jason: ported to 5.4 by doing the following:
- - wg_get_device_start uses genl_family_attrbuf
- - trival skb_redirect_reset change from 2c64605b590e is folded in
- - skb_list_walk_safe was already backported prior]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- MAINTAINERS | 8 +
- drivers/net/Kconfig | 41 +
- drivers/net/Makefile | 1 +
- drivers/net/wireguard/Makefile | 18 +
- drivers/net/wireguard/allowedips.c | 381 +++++++++
- drivers/net/wireguard/allowedips.h | 59 ++
- drivers/net/wireguard/cookie.c | 236 ++++++
- drivers/net/wireguard/cookie.h | 59 ++
- drivers/net/wireguard/device.c | 458 ++++++++++
- drivers/net/wireguard/device.h | 65 ++
- drivers/net/wireguard/main.c | 64 ++
- drivers/net/wireguard/messages.h | 128 +++
- drivers/net/wireguard/netlink.c | 648 +++++++++++++++
- drivers/net/wireguard/netlink.h | 12 +
- drivers/net/wireguard/noise.c | 828 +++++++++++++++++++
- drivers/net/wireguard/noise.h | 137 +++
- drivers/net/wireguard/peer.c | 240 ++++++
- drivers/net/wireguard/peer.h | 83 ++
- drivers/net/wireguard/peerlookup.c | 221 +++++
- drivers/net/wireguard/peerlookup.h | 64 ++
- drivers/net/wireguard/queueing.c | 53 ++
- drivers/net/wireguard/queueing.h | 197 +++++
- drivers/net/wireguard/ratelimiter.c | 223 +++++
- drivers/net/wireguard/ratelimiter.h | 19 +
- drivers/net/wireguard/receive.c | 595 +++++++++++++
- drivers/net/wireguard/selftest/allowedips.c | 683 +++++++++++++++
- drivers/net/wireguard/selftest/counter.c | 104 +++
- drivers/net/wireguard/selftest/ratelimiter.c | 226 +++++
- drivers/net/wireguard/send.c | 413 +++++++++
- drivers/net/wireguard/socket.c | 437 ++++++++++
- drivers/net/wireguard/socket.h | 44 +
- drivers/net/wireguard/timers.c | 243 ++++++
- drivers/net/wireguard/timers.h | 31 +
- drivers/net/wireguard/version.h | 1 +
- include/uapi/linux/wireguard.h | 196 +++++
- tools/testing/selftests/wireguard/netns.sh | 537 ++++++++++++
- 36 files changed, 7753 insertions(+)
- create mode 100644 drivers/net/wireguard/Makefile
- create mode 100644 drivers/net/wireguard/allowedips.c
- create mode 100644 drivers/net/wireguard/allowedips.h
- create mode 100644 drivers/net/wireguard/cookie.c
- create mode 100644 drivers/net/wireguard/cookie.h
- create mode 100644 drivers/net/wireguard/device.c
- create mode 100644 drivers/net/wireguard/device.h
- create mode 100644 drivers/net/wireguard/main.c
- create mode 100644 drivers/net/wireguard/messages.h
- create mode 100644 drivers/net/wireguard/netlink.c
- create mode 100644 drivers/net/wireguard/netlink.h
- create mode 100644 drivers/net/wireguard/noise.c
- create mode 100644 drivers/net/wireguard/noise.h
- create mode 100644 drivers/net/wireguard/peer.c
- create mode 100644 drivers/net/wireguard/peer.h
- create mode 100644 drivers/net/wireguard/peerlookup.c
- create mode 100644 drivers/net/wireguard/peerlookup.h
- create mode 100644 drivers/net/wireguard/queueing.c
- create mode 100644 drivers/net/wireguard/queueing.h
- create mode 100644 drivers/net/wireguard/ratelimiter.c
- create mode 100644 drivers/net/wireguard/ratelimiter.h
- create mode 100644 drivers/net/wireguard/receive.c
- create mode 100644 drivers/net/wireguard/selftest/allowedips.c
- create mode 100644 drivers/net/wireguard/selftest/counter.c
- create mode 100644 drivers/net/wireguard/selftest/ratelimiter.c
- create mode 100644 drivers/net/wireguard/send.c
- create mode 100644 drivers/net/wireguard/socket.c
- create mode 100644 drivers/net/wireguard/socket.h
- create mode 100644 drivers/net/wireguard/timers.c
- create mode 100644 drivers/net/wireguard/timers.h
- create mode 100644 drivers/net/wireguard/version.h
- create mode 100644 include/uapi/linux/wireguard.h
- create mode 100755 tools/testing/selftests/wireguard/netns.sh
-
---- a/MAINTAINERS
-+++ b/MAINTAINERS
-@@ -17584,6 +17584,14 @@ L: linux-gpio@vger.kernel.org
- S: Maintained
- F: drivers/gpio/gpio-ws16c48.c
-
-+WIREGUARD SECURE NETWORK TUNNEL
-+M: Jason A. Donenfeld <Jason@zx2c4.com>
-+S: Maintained
-+F: drivers/net/wireguard/
-+F: tools/testing/selftests/wireguard/
-+L: wireguard@lists.zx2c4.com
-+L: netdev@vger.kernel.org
-+
- WISTRON LAPTOP BUTTON DRIVER
- M: Miloslav Trmac <mitr@volny.cz>
- S: Maintained
---- a/drivers/net/Kconfig
-+++ b/drivers/net/Kconfig
-@@ -71,6 +71,47 @@ config DUMMY
- To compile this driver as a module, choose M here: the module
- will be called dummy.
-
-+config WIREGUARD
-+ tristate "WireGuard secure network tunnel"
-+ depends on NET && INET
-+ depends on IPV6 || !IPV6
-+ select NET_UDP_TUNNEL
-+ select DST_CACHE
-+ select CRYPTO
-+ select CRYPTO_LIB_CURVE25519
-+ select CRYPTO_LIB_CHACHA20POLY1305
-+ select CRYPTO_LIB_BLAKE2S
-+ select CRYPTO_CHACHA20_X86_64 if X86 && 64BIT
-+ select CRYPTO_POLY1305_X86_64 if X86 && 64BIT
-+ select CRYPTO_BLAKE2S_X86 if X86 && 64BIT
-+ select CRYPTO_CURVE25519_X86 if X86 && 64BIT
-+ select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
-+ select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
-+ select CRYPTO_POLY1305_ARM if ARM
-+ select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
-+ select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
-+ select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
-+ help
-+ WireGuard is a secure, fast, and easy to use replacement for IPSec
-+ that uses modern cryptography and clever networking tricks. It's
-+ designed to be fairly general purpose and abstract enough to fit most
-+ use cases, while at the same time remaining extremely simple to
-+ configure. See www.wireguard.com for more info.
-+
-+ It's safe to say Y or M here, as the driver is very lightweight and
-+ is only in use when an administrator chooses to add an interface.
-+
-+config WIREGUARD_DEBUG
-+ bool "Debugging checks and verbose messages"
-+ depends on WIREGUARD
-+ help
-+ This will write log messages for handshake and other events
-+ that occur for a WireGuard interface. It will also perform some
-+ extra validation checks and unit tests at various points. This is
-+ only useful for debugging.
-+
-+ Say N here unless you know what you're doing.
-+
- config EQUALIZER
- tristate "EQL (serial line load balancing) support"
- ---help---
---- a/drivers/net/Makefile
-+++ b/drivers/net/Makefile
-@@ -10,6 +10,7 @@ obj-$(CONFIG_BONDING) += bonding/
- obj-$(CONFIG_IPVLAN) += ipvlan/
- obj-$(CONFIG_IPVTAP) += ipvlan/
- obj-$(CONFIG_DUMMY) += dummy.o
-+obj-$(CONFIG_WIREGUARD) += wireguard/
- obj-$(CONFIG_EQUALIZER) += eql.o
- obj-$(CONFIG_IFB) += ifb.o
- obj-$(CONFIG_MACSEC) += macsec.o
---- /dev/null
-+++ b/drivers/net/wireguard/Makefile
-@@ -0,0 +1,18 @@
-+ccflags-y := -O3
-+ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
-+ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG
-+wireguard-y := main.o
-+wireguard-y += noise.o
-+wireguard-y += device.o
-+wireguard-y += peer.o
-+wireguard-y += timers.o
-+wireguard-y += queueing.o
-+wireguard-y += send.o
-+wireguard-y += receive.o
-+wireguard-y += socket.o
-+wireguard-y += peerlookup.o
-+wireguard-y += allowedips.o
-+wireguard-y += ratelimiter.o
-+wireguard-y += cookie.o
-+wireguard-y += netlink.o
-+obj-$(CONFIG_WIREGUARD) := wireguard.o
---- /dev/null
-+++ b/drivers/net/wireguard/allowedips.c
-@@ -0,0 +1,381 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "allowedips.h"
-+#include "peer.h"
-+
-+static void swap_endian(u8 *dst, const u8 *src, u8 bits)
-+{
-+ if (bits == 32) {
-+ *(u32 *)dst = be32_to_cpu(*(const __be32 *)src);
-+ } else if (bits == 128) {
-+ ((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]);
-+ ((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]);
-+ }
-+}
-+
-+static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
-+ u8 cidr, u8 bits)
-+{
-+ node->cidr = cidr;
-+ node->bit_at_a = cidr / 8U;
-+#ifdef __LITTLE_ENDIAN
-+ node->bit_at_a ^= (bits / 8U - 1U) % 8U;
-+#endif
-+ node->bit_at_b = 7U - (cidr % 8U);
-+ node->bitlen = bits;
-+ memcpy(node->bits, src, bits / 8U);
-+}
-+#define CHOOSE_NODE(parent, key) \
-+ parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
-+
-+static void node_free_rcu(struct rcu_head *rcu)
-+{
-+ kfree(container_of(rcu, struct allowedips_node, rcu));
-+}
-+
-+static void push_rcu(struct allowedips_node **stack,
-+ struct allowedips_node __rcu *p, unsigned int *len)
-+{
-+ if (rcu_access_pointer(p)) {
-+ WARN_ON(IS_ENABLED(DEBUG) && *len >= 128);
-+ stack[(*len)++] = rcu_dereference_raw(p);
-+ }
-+}
-+
-+static void root_free_rcu(struct rcu_head *rcu)
-+{
-+ struct allowedips_node *node, *stack[128] = {
-+ container_of(rcu, struct allowedips_node, rcu) };
-+ unsigned int len = 1;
-+
-+ while (len > 0 && (node = stack[--len])) {
-+ push_rcu(stack, node->bit[0], &len);
-+ push_rcu(stack, node->bit[1], &len);
-+ kfree(node);
-+ }
-+}
-+
-+static void root_remove_peer_lists(struct allowedips_node *root)
-+{
-+ struct allowedips_node *node, *stack[128] = { root };
-+ unsigned int len = 1;
-+
-+ while (len > 0 && (node = stack[--len])) {
-+ push_rcu(stack, node->bit[0], &len);
-+ push_rcu(stack, node->bit[1], &len);
-+ if (rcu_access_pointer(node->peer))
-+ list_del(&node->peer_list);
-+ }
-+}
-+
-+static void walk_remove_by_peer(struct allowedips_node __rcu **top,
-+ struct wg_peer *peer, struct mutex *lock)
-+{
-+#define REF(p) rcu_access_pointer(p)
-+#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
-+#define PUSH(p) ({ \
-+ WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \
-+ stack[len++] = p; \
-+ })
-+
-+ struct allowedips_node __rcu **stack[128], **nptr;
-+ struct allowedips_node *node, *prev;
-+ unsigned int len;
-+
-+ if (unlikely(!peer || !REF(*top)))
-+ return;
-+
-+ for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
-+ nptr = stack[len - 1];
-+ node = DEREF(nptr);
-+ if (!node) {
-+ --len;
-+ continue;
-+ }
-+ if (!prev || REF(prev->bit[0]) == node ||
-+ REF(prev->bit[1]) == node) {
-+ if (REF(node->bit[0]))
-+ PUSH(&node->bit[0]);
-+ else if (REF(node->bit[1]))
-+ PUSH(&node->bit[1]);
-+ } else if (REF(node->bit[0]) == prev) {
-+ if (REF(node->bit[1]))
-+ PUSH(&node->bit[1]);
-+ } else {
-+ if (rcu_dereference_protected(node->peer,
-+ lockdep_is_held(lock)) == peer) {
-+ RCU_INIT_POINTER(node->peer, NULL);
-+ list_del_init(&node->peer_list);
-+ if (!node->bit[0] || !node->bit[1]) {
-+ rcu_assign_pointer(*nptr, DEREF(
-+ &node->bit[!REF(node->bit[0])]));
-+ call_rcu(&node->rcu, node_free_rcu);
-+ node = DEREF(nptr);
-+ }
-+ }
-+ --len;
-+ }
-+ }
-+
-+#undef REF
-+#undef DEREF
-+#undef PUSH
-+}
-+
-+static unsigned int fls128(u64 a, u64 b)
-+{
-+ return a ? fls64(a) + 64U : fls64(b);
-+}
-+
-+static u8 common_bits(const struct allowedips_node *node, const u8 *key,
-+ u8 bits)
-+{
-+ if (bits == 32)
-+ return 32U - fls(*(const u32 *)node->bits ^ *(const u32 *)key);
-+ else if (bits == 128)
-+ return 128U - fls128(
-+ *(const u64 *)&node->bits[0] ^ *(const u64 *)&key[0],
-+ *(const u64 *)&node->bits[8] ^ *(const u64 *)&key[8]);
-+ return 0;
-+}
-+
-+static bool prefix_matches(const struct allowedips_node *node, const u8 *key,
-+ u8 bits)
-+{
-+ /* This could be much faster if it actually just compared the common
-+ * bits properly, by precomputing a mask bswap(~0 << (32 - cidr)), and
-+ * the rest, but it turns out that common_bits is already super fast on
-+ * modern processors, even taking into account the unfortunate bswap.
-+ * So, we just inline it like this instead.
-+ */
-+ return common_bits(node, key, bits) >= node->cidr;
-+}
-+
-+static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
-+ const u8 *key)
-+{
-+ struct allowedips_node *node = trie, *found = NULL;
-+
-+ while (node && prefix_matches(node, key, bits)) {
-+ if (rcu_access_pointer(node->peer))
-+ found = node;
-+ if (node->cidr == bits)
-+ break;
-+ node = rcu_dereference_bh(CHOOSE_NODE(node, key));
-+ }
-+ return found;
-+}
-+
-+/* Returns a strong reference to a peer */
-+static struct wg_peer *lookup(struct allowedips_node __rcu *root, u8 bits,
-+ const void *be_ip)
-+{
-+ /* Aligned so it can be passed to fls/fls64 */
-+ u8 ip[16] __aligned(__alignof(u64));
-+ struct allowedips_node *node;
-+ struct wg_peer *peer = NULL;
-+
-+ swap_endian(ip, be_ip, bits);
-+
-+ rcu_read_lock_bh();
-+retry:
-+ node = find_node(rcu_dereference_bh(root), bits, ip);
-+ if (node) {
-+ peer = wg_peer_get_maybe_zero(rcu_dereference_bh(node->peer));
-+ if (!peer)
-+ goto retry;
-+ }
-+ rcu_read_unlock_bh();
-+ return peer;
-+}
-+
-+static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
-+ u8 cidr, u8 bits, struct allowedips_node **rnode,
-+ struct mutex *lock)
-+{
-+ struct allowedips_node *node = rcu_dereference_protected(trie,
-+ lockdep_is_held(lock));
-+ struct allowedips_node *parent = NULL;
-+ bool exact = false;
-+
-+ while (node && node->cidr <= cidr && prefix_matches(node, key, bits)) {
-+ parent = node;
-+ if (parent->cidr == cidr) {
-+ exact = true;
-+ break;
-+ }
-+ node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
-+ lockdep_is_held(lock));
-+ }
-+ *rnode = parent;
-+ return exact;
-+}
-+
-+static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
-+ u8 cidr, struct wg_peer *peer, struct mutex *lock)
-+{
-+ struct allowedips_node *node, *parent, *down, *newnode;
-+
-+ if (unlikely(cidr > bits || !peer))
-+ return -EINVAL;
-+
-+ if (!rcu_access_pointer(*trie)) {
-+ node = kzalloc(sizeof(*node), GFP_KERNEL);
-+ if (unlikely(!node))
-+ return -ENOMEM;
-+ RCU_INIT_POINTER(node->peer, peer);
-+ list_add_tail(&node->peer_list, &peer->allowedips_list);
-+ copy_and_assign_cidr(node, key, cidr, bits);
-+ rcu_assign_pointer(*trie, node);
-+ return 0;
-+ }
-+ if (node_placement(*trie, key, cidr, bits, &node, lock)) {
-+ rcu_assign_pointer(node->peer, peer);
-+ list_move_tail(&node->peer_list, &peer->allowedips_list);
-+ return 0;
-+ }
-+
-+ newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
-+ if (unlikely(!newnode))
-+ return -ENOMEM;
-+ RCU_INIT_POINTER(newnode->peer, peer);
-+ list_add_tail(&newnode->peer_list, &peer->allowedips_list);
-+ copy_and_assign_cidr(newnode, key, cidr, bits);
-+
-+ if (!node) {
-+ down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
-+ } else {
-+ down = rcu_dereference_protected(CHOOSE_NODE(node, key),
-+ lockdep_is_held(lock));
-+ if (!down) {
-+ rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
-+ return 0;
-+ }
-+ }
-+ cidr = min(cidr, common_bits(down, key, bits));
-+ parent = node;
-+
-+ if (newnode->cidr == cidr) {
-+ rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
-+ if (!parent)
-+ rcu_assign_pointer(*trie, newnode);
-+ else
-+ rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
-+ newnode);
-+ } else {
-+ node = kzalloc(sizeof(*node), GFP_KERNEL);
-+ if (unlikely(!node)) {
-+ kfree(newnode);
-+ return -ENOMEM;
-+ }
-+ INIT_LIST_HEAD(&node->peer_list);
-+ copy_and_assign_cidr(node, newnode->bits, cidr, bits);
-+
-+ rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
-+ rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
-+ if (!parent)
-+ rcu_assign_pointer(*trie, node);
-+ else
-+ rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
-+ node);
-+ }
-+ return 0;
-+}
-+
-+void wg_allowedips_init(struct allowedips *table)
-+{
-+ table->root4 = table->root6 = NULL;
-+ table->seq = 1;
-+}
-+
-+void wg_allowedips_free(struct allowedips *table, struct mutex *lock)
-+{
-+ struct allowedips_node __rcu *old4 = table->root4, *old6 = table->root6;
-+
-+ ++table->seq;
-+ RCU_INIT_POINTER(table->root4, NULL);
-+ RCU_INIT_POINTER(table->root6, NULL);
-+ if (rcu_access_pointer(old4)) {
-+ struct allowedips_node *node = rcu_dereference_protected(old4,
-+ lockdep_is_held(lock));
-+
-+ root_remove_peer_lists(node);
-+ call_rcu(&node->rcu, root_free_rcu);
-+ }
-+ if (rcu_access_pointer(old6)) {
-+ struct allowedips_node *node = rcu_dereference_protected(old6,
-+ lockdep_is_held(lock));
-+
-+ root_remove_peer_lists(node);
-+ call_rcu(&node->rcu, root_free_rcu);
-+ }
-+}
-+
-+int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
-+ u8 cidr, struct wg_peer *peer, struct mutex *lock)
-+{
-+ /* Aligned so it can be passed to fls */
-+ u8 key[4] __aligned(__alignof(u32));
-+
-+ ++table->seq;
-+ swap_endian(key, (const u8 *)ip, 32);
-+ return add(&table->root4, 32, key, cidr, peer, lock);
-+}
-+
-+int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
-+ u8 cidr, struct wg_peer *peer, struct mutex *lock)
-+{
-+ /* Aligned so it can be passed to fls64 */
-+ u8 key[16] __aligned(__alignof(u64));
-+
-+ ++table->seq;
-+ swap_endian(key, (const u8 *)ip, 128);
-+ return add(&table->root6, 128, key, cidr, peer, lock);
-+}
-+
-+void wg_allowedips_remove_by_peer(struct allowedips *table,
-+ struct wg_peer *peer, struct mutex *lock)
-+{
-+ ++table->seq;
-+ walk_remove_by_peer(&table->root4, peer, lock);
-+ walk_remove_by_peer(&table->root6, peer, lock);
-+}
-+
-+int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
-+{
-+ const unsigned int cidr_bytes = DIV_ROUND_UP(node->cidr, 8U);
-+ swap_endian(ip, node->bits, node->bitlen);
-+ memset(ip + cidr_bytes, 0, node->bitlen / 8U - cidr_bytes);
-+ if (node->cidr)
-+ ip[cidr_bytes - 1U] &= ~0U << (-node->cidr % 8U);
-+
-+ *cidr = node->cidr;
-+ return node->bitlen == 32 ? AF_INET : AF_INET6;
-+}
-+
-+/* Returns a strong reference to a peer */
-+struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
-+ struct sk_buff *skb)
-+{
-+ if (skb->protocol == htons(ETH_P_IP))
-+ return lookup(table->root4, 32, &ip_hdr(skb)->daddr);
-+ else if (skb->protocol == htons(ETH_P_IPV6))
-+ return lookup(table->root6, 128, &ipv6_hdr(skb)->daddr);
-+ return NULL;
-+}
-+
-+/* Returns a strong reference to a peer */
-+struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
-+ struct sk_buff *skb)
-+{
-+ if (skb->protocol == htons(ETH_P_IP))
-+ return lookup(table->root4, 32, &ip_hdr(skb)->saddr);
-+ else if (skb->protocol == htons(ETH_P_IPV6))
-+ return lookup(table->root6, 128, &ipv6_hdr(skb)->saddr);
-+ return NULL;
-+}
-+
-+#include "selftest/allowedips.c"
---- /dev/null
-+++ b/drivers/net/wireguard/allowedips.h
-@@ -0,0 +1,59 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_ALLOWEDIPS_H
-+#define _WG_ALLOWEDIPS_H
-+
-+#include <linux/mutex.h>
-+#include <linux/ip.h>
-+#include <linux/ipv6.h>
-+
-+struct wg_peer;
-+
-+struct allowedips_node {
-+ struct wg_peer __rcu *peer;
-+ struct allowedips_node __rcu *bit[2];
-+ /* While it may seem scandalous that we waste space for v4,
-+ * we're alloc'ing to the nearest power of 2 anyway, so this
-+ * doesn't actually make a difference.
-+ */
-+ u8 bits[16] __aligned(__alignof(u64));
-+ u8 cidr, bit_at_a, bit_at_b, bitlen;
-+
-+ /* Keep rarely used list at bottom to be beyond cache line. */
-+ union {
-+ struct list_head peer_list;
-+ struct rcu_head rcu;
-+ };
-+};
-+
-+struct allowedips {
-+ struct allowedips_node __rcu *root4;
-+ struct allowedips_node __rcu *root6;
-+ u64 seq;
-+};
-+
-+void wg_allowedips_init(struct allowedips *table);
-+void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
-+int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip,
-+ u8 cidr, struct wg_peer *peer, struct mutex *lock);
-+int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
-+ u8 cidr, struct wg_peer *peer, struct mutex *lock);
-+void wg_allowedips_remove_by_peer(struct allowedips *table,
-+ struct wg_peer *peer, struct mutex *lock);
-+/* The ip input pointer should be __aligned(__alignof(u64))) */
-+int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr);
-+
-+/* These return a strong reference to a peer: */
-+struct wg_peer *wg_allowedips_lookup_dst(struct allowedips *table,
-+ struct sk_buff *skb);
-+struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
-+ struct sk_buff *skb);
-+
-+#ifdef DEBUG
-+bool wg_allowedips_selftest(void);
-+#endif
-+
-+#endif /* _WG_ALLOWEDIPS_H */
---- /dev/null
-+++ b/drivers/net/wireguard/cookie.c
-@@ -0,0 +1,236 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "cookie.h"
-+#include "peer.h"
-+#include "device.h"
-+#include "messages.h"
-+#include "ratelimiter.h"
-+#include "timers.h"
-+
-+#include <crypto/blake2s.h>
-+#include <crypto/chacha20poly1305.h>
-+
-+#include <net/ipv6.h>
-+#include <crypto/algapi.h>
-+
-+void wg_cookie_checker_init(struct cookie_checker *checker,
-+ struct wg_device *wg)
-+{
-+ init_rwsem(&checker->secret_lock);
-+ checker->secret_birthdate = ktime_get_coarse_boottime_ns();
-+ get_random_bytes(checker->secret, NOISE_HASH_LEN);
-+ checker->device = wg;
-+}
-+
-+enum { COOKIE_KEY_LABEL_LEN = 8 };
-+static const u8 mac1_key_label[COOKIE_KEY_LABEL_LEN] = "mac1----";
-+static const u8 cookie_key_label[COOKIE_KEY_LABEL_LEN] = "cookie--";
-+
-+static void precompute_key(u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ const u8 pubkey[NOISE_PUBLIC_KEY_LEN],
-+ const u8 label[COOKIE_KEY_LABEL_LEN])
-+{
-+ struct blake2s_state blake;
-+
-+ blake2s_init(&blake, NOISE_SYMMETRIC_KEY_LEN);
-+ blake2s_update(&blake, label, COOKIE_KEY_LABEL_LEN);
-+ blake2s_update(&blake, pubkey, NOISE_PUBLIC_KEY_LEN);
-+ blake2s_final(&blake, key);
-+}
-+
-+/* Must hold peer->handshake.static_identity->lock */
-+void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker)
-+{
-+ if (likely(checker->device->static_identity.has_identity)) {
-+ precompute_key(checker->cookie_encryption_key,
-+ checker->device->static_identity.static_public,
-+ cookie_key_label);
-+ precompute_key(checker->message_mac1_key,
-+ checker->device->static_identity.static_public,
-+ mac1_key_label);
-+ } else {
-+ memset(checker->cookie_encryption_key, 0,
-+ NOISE_SYMMETRIC_KEY_LEN);
-+ memset(checker->message_mac1_key, 0, NOISE_SYMMETRIC_KEY_LEN);
-+ }
-+}
-+
-+void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer)
-+{
-+ precompute_key(peer->latest_cookie.cookie_decryption_key,
-+ peer->handshake.remote_static, cookie_key_label);
-+ precompute_key(peer->latest_cookie.message_mac1_key,
-+ peer->handshake.remote_static, mac1_key_label);
-+}
-+
-+void wg_cookie_init(struct cookie *cookie)
-+{
-+ memset(cookie, 0, sizeof(*cookie));
-+ init_rwsem(&cookie->lock);
-+}
-+
-+static void compute_mac1(u8 mac1[COOKIE_LEN], const void *message, size_t len,
-+ const u8 key[NOISE_SYMMETRIC_KEY_LEN])
-+{
-+ len = len - sizeof(struct message_macs) +
-+ offsetof(struct message_macs, mac1);
-+ blake2s(mac1, message, key, COOKIE_LEN, len, NOISE_SYMMETRIC_KEY_LEN);
-+}
-+
-+static void compute_mac2(u8 mac2[COOKIE_LEN], const void *message, size_t len,
-+ const u8 cookie[COOKIE_LEN])
-+{
-+ len = len - sizeof(struct message_macs) +
-+ offsetof(struct message_macs, mac2);
-+ blake2s(mac2, message, cookie, COOKIE_LEN, len, COOKIE_LEN);
-+}
-+
-+static void make_cookie(u8 cookie[COOKIE_LEN], struct sk_buff *skb,
-+ struct cookie_checker *checker)
-+{
-+ struct blake2s_state state;
-+
-+ if (wg_birthdate_has_expired(checker->secret_birthdate,
-+ COOKIE_SECRET_MAX_AGE)) {
-+ down_write(&checker->secret_lock);
-+ checker->secret_birthdate = ktime_get_coarse_boottime_ns();
-+ get_random_bytes(checker->secret, NOISE_HASH_LEN);
-+ up_write(&checker->secret_lock);
-+ }
-+
-+ down_read(&checker->secret_lock);
-+
-+ blake2s_init_key(&state, COOKIE_LEN, checker->secret, NOISE_HASH_LEN);
-+ if (skb->protocol == htons(ETH_P_IP))
-+ blake2s_update(&state, (u8 *)&ip_hdr(skb)->saddr,
-+ sizeof(struct in_addr));
-+ else if (skb->protocol == htons(ETH_P_IPV6))
-+ blake2s_update(&state, (u8 *)&ipv6_hdr(skb)->saddr,
-+ sizeof(struct in6_addr));
-+ blake2s_update(&state, (u8 *)&udp_hdr(skb)->source, sizeof(__be16));
-+ blake2s_final(&state, cookie);
-+
-+ up_read(&checker->secret_lock);
-+}
-+
-+enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker,
-+ struct sk_buff *skb,
-+ bool check_cookie)
-+{
-+ struct message_macs *macs = (struct message_macs *)
-+ (skb->data + skb->len - sizeof(*macs));
-+ enum cookie_mac_state ret;
-+ u8 computed_mac[COOKIE_LEN];
-+ u8 cookie[COOKIE_LEN];
-+
-+ ret = INVALID_MAC;
-+ compute_mac1(computed_mac, skb->data, skb->len,
-+ checker->message_mac1_key);
-+ if (crypto_memneq(computed_mac, macs->mac1, COOKIE_LEN))
-+ goto out;
-+
-+ ret = VALID_MAC_BUT_NO_COOKIE;
-+
-+ if (!check_cookie)
-+ goto out;
-+
-+ make_cookie(cookie, skb, checker);
-+
-+ compute_mac2(computed_mac, skb->data, skb->len, cookie);
-+ if (crypto_memneq(computed_mac, macs->mac2, COOKIE_LEN))
-+ goto out;
-+
-+ ret = VALID_MAC_WITH_COOKIE_BUT_RATELIMITED;
-+ if (!wg_ratelimiter_allow(skb, dev_net(checker->device->dev)))
-+ goto out;
-+
-+ ret = VALID_MAC_WITH_COOKIE;
-+
-+out:
-+ return ret;
-+}
-+
-+void wg_cookie_add_mac_to_packet(void *message, size_t len,
-+ struct wg_peer *peer)
-+{
-+ struct message_macs *macs = (struct message_macs *)
-+ ((u8 *)message + len - sizeof(*macs));
-+
-+ down_write(&peer->latest_cookie.lock);
-+ compute_mac1(macs->mac1, message, len,
-+ peer->latest_cookie.message_mac1_key);
-+ memcpy(peer->latest_cookie.last_mac1_sent, macs->mac1, COOKIE_LEN);
-+ peer->latest_cookie.have_sent_mac1 = true;
-+ up_write(&peer->latest_cookie.lock);
-+
-+ down_read(&peer->latest_cookie.lock);
-+ if (peer->latest_cookie.is_valid &&
-+ !wg_birthdate_has_expired(peer->latest_cookie.birthdate,
-+ COOKIE_SECRET_MAX_AGE - COOKIE_SECRET_LATENCY))
-+ compute_mac2(macs->mac2, message, len,
-+ peer->latest_cookie.cookie);
-+ else
-+ memset(macs->mac2, 0, COOKIE_LEN);
-+ up_read(&peer->latest_cookie.lock);
-+}
-+
-+void wg_cookie_message_create(struct message_handshake_cookie *dst,
-+ struct sk_buff *skb, __le32 index,
-+ struct cookie_checker *checker)
-+{
-+ struct message_macs *macs = (struct message_macs *)
-+ ((u8 *)skb->data + skb->len - sizeof(*macs));
-+ u8 cookie[COOKIE_LEN];
-+
-+ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE);
-+ dst->receiver_index = index;
-+ get_random_bytes_wait(dst->nonce, COOKIE_NONCE_LEN);
-+
-+ make_cookie(cookie, skb, checker);
-+ xchacha20poly1305_encrypt(dst->encrypted_cookie, cookie, COOKIE_LEN,
-+ macs->mac1, COOKIE_LEN, dst->nonce,
-+ checker->cookie_encryption_key);
-+}
-+
-+void wg_cookie_message_consume(struct message_handshake_cookie *src,
-+ struct wg_device *wg)
-+{
-+ struct wg_peer *peer = NULL;
-+ u8 cookie[COOKIE_LEN];
-+ bool ret;
-+
-+ if (unlikely(!wg_index_hashtable_lookup(wg->index_hashtable,
-+ INDEX_HASHTABLE_HANDSHAKE |
-+ INDEX_HASHTABLE_KEYPAIR,
-+ src->receiver_index, &peer)))
-+ return;
-+
-+ down_read(&peer->latest_cookie.lock);
-+ if (unlikely(!peer->latest_cookie.have_sent_mac1)) {
-+ up_read(&peer->latest_cookie.lock);
-+ goto out;
-+ }
-+ ret = xchacha20poly1305_decrypt(
-+ cookie, src->encrypted_cookie, sizeof(src->encrypted_cookie),
-+ peer->latest_cookie.last_mac1_sent, COOKIE_LEN, src->nonce,
-+ peer->latest_cookie.cookie_decryption_key);
-+ up_read(&peer->latest_cookie.lock);
-+
-+ if (ret) {
-+ down_write(&peer->latest_cookie.lock);
-+ memcpy(peer->latest_cookie.cookie, cookie, COOKIE_LEN);
-+ peer->latest_cookie.birthdate = ktime_get_coarse_boottime_ns();
-+ peer->latest_cookie.is_valid = true;
-+ peer->latest_cookie.have_sent_mac1 = false;
-+ up_write(&peer->latest_cookie.lock);
-+ } else {
-+ net_dbg_ratelimited("%s: Could not decrypt invalid cookie response\n",
-+ wg->dev->name);
-+ }
-+
-+out:
-+ wg_peer_put(peer);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/cookie.h
-@@ -0,0 +1,59 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_COOKIE_H
-+#define _WG_COOKIE_H
-+
-+#include "messages.h"
-+#include <linux/rwsem.h>
-+
-+struct wg_peer;
-+
-+struct cookie_checker {
-+ u8 secret[NOISE_HASH_LEN];
-+ u8 cookie_encryption_key[NOISE_SYMMETRIC_KEY_LEN];
-+ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN];
-+ u64 secret_birthdate;
-+ struct rw_semaphore secret_lock;
-+ struct wg_device *device;
-+};
-+
-+struct cookie {
-+ u64 birthdate;
-+ bool is_valid;
-+ u8 cookie[COOKIE_LEN];
-+ bool have_sent_mac1;
-+ u8 last_mac1_sent[COOKIE_LEN];
-+ u8 cookie_decryption_key[NOISE_SYMMETRIC_KEY_LEN];
-+ u8 message_mac1_key[NOISE_SYMMETRIC_KEY_LEN];
-+ struct rw_semaphore lock;
-+};
-+
-+enum cookie_mac_state {
-+ INVALID_MAC,
-+ VALID_MAC_BUT_NO_COOKIE,
-+ VALID_MAC_WITH_COOKIE_BUT_RATELIMITED,
-+ VALID_MAC_WITH_COOKIE
-+};
-+
-+void wg_cookie_checker_init(struct cookie_checker *checker,
-+ struct wg_device *wg);
-+void wg_cookie_checker_precompute_device_keys(struct cookie_checker *checker);
-+void wg_cookie_checker_precompute_peer_keys(struct wg_peer *peer);
-+void wg_cookie_init(struct cookie *cookie);
-+
-+enum cookie_mac_state wg_cookie_validate_packet(struct cookie_checker *checker,
-+ struct sk_buff *skb,
-+ bool check_cookie);
-+void wg_cookie_add_mac_to_packet(void *message, size_t len,
-+ struct wg_peer *peer);
-+
-+void wg_cookie_message_create(struct message_handshake_cookie *src,
-+ struct sk_buff *skb, __le32 index,
-+ struct cookie_checker *checker);
-+void wg_cookie_message_consume(struct message_handshake_cookie *src,
-+ struct wg_device *wg);
-+
-+#endif /* _WG_COOKIE_H */
---- /dev/null
-+++ b/drivers/net/wireguard/device.c
-@@ -0,0 +1,458 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "queueing.h"
-+#include "socket.h"
-+#include "timers.h"
-+#include "device.h"
-+#include "ratelimiter.h"
-+#include "peer.h"
-+#include "messages.h"
-+
-+#include <linux/module.h>
-+#include <linux/rtnetlink.h>
-+#include <linux/inet.h>
-+#include <linux/netdevice.h>
-+#include <linux/inetdevice.h>
-+#include <linux/if_arp.h>
-+#include <linux/icmp.h>
-+#include <linux/suspend.h>
-+#include <net/icmp.h>
-+#include <net/rtnetlink.h>
-+#include <net/ip_tunnels.h>
-+#include <net/addrconf.h>
-+
-+static LIST_HEAD(device_list);
-+
-+static int wg_open(struct net_device *dev)
-+{
-+ struct in_device *dev_v4 = __in_dev_get_rtnl(dev);
-+ struct inet6_dev *dev_v6 = __in6_dev_get(dev);
-+ struct wg_device *wg = netdev_priv(dev);
-+ struct wg_peer *peer;
-+ int ret;
-+
-+ if (dev_v4) {
-+ /* At some point we might put this check near the ip_rt_send_
-+ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar
-+ * to the current secpath check.
-+ */
-+ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
-+ IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false;
-+ }
-+ if (dev_v6)
-+ dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
-+
-+ ret = wg_socket_init(wg, wg->incoming_port);
-+ if (ret < 0)
-+ return ret;
-+ mutex_lock(&wg->device_update_lock);
-+ list_for_each_entry(peer, &wg->peer_list, peer_list) {
-+ wg_packet_send_staged_packets(peer);
-+ if (peer->persistent_keepalive_interval)
-+ wg_packet_send_keepalive(peer);
-+ }
-+ mutex_unlock(&wg->device_update_lock);
-+ return 0;
-+}
-+
-+#ifdef CONFIG_PM_SLEEP
-+static int wg_pm_notification(struct notifier_block *nb, unsigned long action,
-+ void *data)
-+{
-+ struct wg_device *wg;
-+ struct wg_peer *peer;
-+
-+ /* If the machine is constantly suspending and resuming, as part of
-+ * its normal operation rather than as a somewhat rare event, then we
-+ * don't actually want to clear keys.
-+ */
-+ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_ANDROID))
-+ return 0;
-+
-+ if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE)
-+ return 0;
-+
-+ rtnl_lock();
-+ list_for_each_entry(wg, &device_list, device_list) {
-+ mutex_lock(&wg->device_update_lock);
-+ list_for_each_entry(peer, &wg->peer_list, peer_list) {
-+ del_timer(&peer->timer_zero_key_material);
-+ wg_noise_handshake_clear(&peer->handshake);
-+ wg_noise_keypairs_clear(&peer->keypairs);
-+ }
-+ mutex_unlock(&wg->device_update_lock);
-+ }
-+ rtnl_unlock();
-+ rcu_barrier();
-+ return 0;
-+}
-+
-+static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification };
-+#endif
-+
-+static int wg_stop(struct net_device *dev)
-+{
-+ struct wg_device *wg = netdev_priv(dev);
-+ struct wg_peer *peer;
-+
-+ mutex_lock(&wg->device_update_lock);
-+ list_for_each_entry(peer, &wg->peer_list, peer_list) {
-+ wg_packet_purge_staged_packets(peer);
-+ wg_timers_stop(peer);
-+ wg_noise_handshake_clear(&peer->handshake);
-+ wg_noise_keypairs_clear(&peer->keypairs);
-+ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
-+ }
-+ mutex_unlock(&wg->device_update_lock);
-+ skb_queue_purge(&wg->incoming_handshakes);
-+ wg_socket_reinit(wg, NULL, NULL);
-+ return 0;
-+}
-+
-+static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev)
-+{
-+ struct wg_device *wg = netdev_priv(dev);
-+ struct sk_buff_head packets;
-+ struct wg_peer *peer;
-+ struct sk_buff *next;
-+ sa_family_t family;
-+ u32 mtu;
-+ int ret;
-+
-+ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) {
-+ ret = -EPROTONOSUPPORT;
-+ net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
-+ goto err;
-+ }
-+
-+ peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb);
-+ if (unlikely(!peer)) {
-+ ret = -ENOKEY;
-+ if (skb->protocol == htons(ETH_P_IP))
-+ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n",
-+ dev->name, &ip_hdr(skb)->daddr);
-+ else if (skb->protocol == htons(ETH_P_IPV6))
-+ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
-+ dev->name, &ipv6_hdr(skb)->daddr);
-+ goto err;
-+ }
-+
-+ family = READ_ONCE(peer->endpoint.addr.sa_family);
-+ if (unlikely(family != AF_INET && family != AF_INET6)) {
-+ ret = -EDESTADDRREQ;
-+ net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n",
-+ dev->name, peer->internal_id);
-+ goto err_peer;
-+ }
-+
-+ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-+
-+ __skb_queue_head_init(&packets);
-+ if (!skb_is_gso(skb)) {
-+ skb_mark_not_on_list(skb);
-+ } else {
-+ struct sk_buff *segs = skb_gso_segment(skb, 0);
-+
-+ if (unlikely(IS_ERR(segs))) {
-+ ret = PTR_ERR(segs);
-+ goto err_peer;
-+ }
-+ dev_kfree_skb(skb);
-+ skb = segs;
-+ }
-+
-+ skb_list_walk_safe(skb, skb, next) {
-+ skb_mark_not_on_list(skb);
-+
-+ skb = skb_share_check(skb, GFP_ATOMIC);
-+ if (unlikely(!skb))
-+ continue;
-+
-+ /* We only need to keep the original dst around for icmp,
-+ * so at this point we're in a position to drop it.
-+ */
-+ skb_dst_drop(skb);
-+
-+ PACKET_CB(skb)->mtu = mtu;
-+
-+ __skb_queue_tail(&packets, skb);
-+ }
-+
-+ spin_lock_bh(&peer->staged_packet_queue.lock);
-+ /* If the queue is getting too big, we start removing the oldest packets
-+ * until it's small again. We do this before adding the new packet, so
-+ * we don't remove GSO segments that are in excess.
-+ */
-+ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) {
-+ dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue));
-+ ++dev->stats.tx_dropped;
-+ }
-+ skb_queue_splice_tail(&packets, &peer->staged_packet_queue);
-+ spin_unlock_bh(&peer->staged_packet_queue.lock);
-+
-+ wg_packet_send_staged_packets(peer);
-+
-+ wg_peer_put(peer);
-+ return NETDEV_TX_OK;
-+
-+err_peer:
-+ wg_peer_put(peer);
-+err:
-+ ++dev->stats.tx_errors;
-+ if (skb->protocol == htons(ETH_P_IP))
-+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
-+ else if (skb->protocol == htons(ETH_P_IPV6))
-+ icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-+ kfree_skb(skb);
-+ return ret;
-+}
-+
-+static const struct net_device_ops netdev_ops = {
-+ .ndo_open = wg_open,
-+ .ndo_stop = wg_stop,
-+ .ndo_start_xmit = wg_xmit,
-+ .ndo_get_stats64 = ip_tunnel_get_stats64
-+};
-+
-+static void wg_destruct(struct net_device *dev)
-+{
-+ struct wg_device *wg = netdev_priv(dev);
-+
-+ rtnl_lock();
-+ list_del(&wg->device_list);
-+ rtnl_unlock();
-+ mutex_lock(&wg->device_update_lock);
-+ wg->incoming_port = 0;
-+ wg_socket_reinit(wg, NULL, NULL);
-+ /* The final references are cleared in the below calls to destroy_workqueue. */
-+ wg_peer_remove_all(wg);
-+ destroy_workqueue(wg->handshake_receive_wq);
-+ destroy_workqueue(wg->handshake_send_wq);
-+ destroy_workqueue(wg->packet_crypt_wq);
-+ wg_packet_queue_free(&wg->decrypt_queue, true);
-+ wg_packet_queue_free(&wg->encrypt_queue, true);
-+ rcu_barrier(); /* Wait for all the peers to be actually freed. */
-+ wg_ratelimiter_uninit();
-+ memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
-+ skb_queue_purge(&wg->incoming_handshakes);
-+ free_percpu(dev->tstats);
-+ free_percpu(wg->incoming_handshakes_worker);
-+ if (wg->have_creating_net_ref)
-+ put_net(wg->creating_net);
-+ kvfree(wg->index_hashtable);
-+ kvfree(wg->peer_hashtable);
-+ mutex_unlock(&wg->device_update_lock);
-+
-+ pr_debug("%s: Interface deleted\n", dev->name);
-+ free_netdev(dev);
-+}
-+
-+static const struct device_type device_type = { .name = KBUILD_MODNAME };
-+
-+static void wg_setup(struct net_device *dev)
-+{
-+ struct wg_device *wg = netdev_priv(dev);
-+ enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
-+ NETIF_F_SG | NETIF_F_GSO |
-+ NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
-+
-+ dev->netdev_ops = &netdev_ops;
-+ dev->hard_header_len = 0;
-+ dev->addr_len = 0;
-+ dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
-+ dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE);
-+ dev->type = ARPHRD_NONE;
-+ dev->flags = IFF_POINTOPOINT | IFF_NOARP;
-+ dev->priv_flags |= IFF_NO_QUEUE;
-+ dev->features |= NETIF_F_LLTX;
-+ dev->features |= WG_NETDEV_FEATURES;
-+ dev->hw_features |= WG_NETDEV_FEATURES;
-+ dev->hw_enc_features |= WG_NETDEV_FEATURES;
-+ dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
-+ sizeof(struct udphdr) -
-+ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
-+
-+ SET_NETDEV_DEVTYPE(dev, &device_type);
-+
-+ /* We need to keep the dst around in case of icmp replies. */
-+ netif_keep_dst(dev);
-+
-+ memset(wg, 0, sizeof(*wg));
-+ wg->dev = dev;
-+}
-+
-+static int wg_newlink(struct net *src_net, struct net_device *dev,
-+ struct nlattr *tb[], struct nlattr *data[],
-+ struct netlink_ext_ack *extack)
-+{
-+ struct wg_device *wg = netdev_priv(dev);
-+ int ret = -ENOMEM;
-+
-+ wg->creating_net = src_net;
-+ init_rwsem(&wg->static_identity.lock);
-+ mutex_init(&wg->socket_update_lock);
-+ mutex_init(&wg->device_update_lock);
-+ skb_queue_head_init(&wg->incoming_handshakes);
-+ wg_allowedips_init(&wg->peer_allowedips);
-+ wg_cookie_checker_init(&wg->cookie_checker, wg);
-+ INIT_LIST_HEAD(&wg->peer_list);
-+ wg->device_update_gen = 1;
-+
-+ wg->peer_hashtable = wg_pubkey_hashtable_alloc();
-+ if (!wg->peer_hashtable)
-+ return ret;
-+
-+ wg->index_hashtable = wg_index_hashtable_alloc();
-+ if (!wg->index_hashtable)
-+ goto err_free_peer_hashtable;
-+
-+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-+ if (!dev->tstats)
-+ goto err_free_index_hashtable;
-+
-+ wg->incoming_handshakes_worker =
-+ wg_packet_percpu_multicore_worker_alloc(
-+ wg_packet_handshake_receive_worker, wg);
-+ if (!wg->incoming_handshakes_worker)
-+ goto err_free_tstats;
-+
-+ wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
-+ WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
-+ if (!wg->handshake_receive_wq)
-+ goto err_free_incoming_handshakes;
-+
-+ wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
-+ WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
-+ if (!wg->handshake_send_wq)
-+ goto err_destroy_handshake_receive;
-+
-+ wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s",
-+ WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name);
-+ if (!wg->packet_crypt_wq)
-+ goto err_destroy_handshake_send;
-+
-+ ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
-+ true, MAX_QUEUED_PACKETS);
-+ if (ret < 0)
-+ goto err_destroy_packet_crypt;
-+
-+ ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
-+ true, MAX_QUEUED_PACKETS);
-+ if (ret < 0)
-+ goto err_free_encrypt_queue;
-+
-+ ret = wg_ratelimiter_init();
-+ if (ret < 0)
-+ goto err_free_decrypt_queue;
-+
-+ ret = register_netdevice(dev);
-+ if (ret < 0)
-+ goto err_uninit_ratelimiter;
-+
-+ list_add(&wg->device_list, &device_list);
-+
-+ /* We wait until the end to assign priv_destructor, so that
-+ * register_netdevice doesn't call it for us if it fails.
-+ */
-+ dev->priv_destructor = wg_destruct;
-+
-+ pr_debug("%s: Interface created\n", dev->name);
-+ return ret;
-+
-+err_uninit_ratelimiter:
-+ wg_ratelimiter_uninit();
-+err_free_decrypt_queue:
-+ wg_packet_queue_free(&wg->decrypt_queue, true);
-+err_free_encrypt_queue:
-+ wg_packet_queue_free(&wg->encrypt_queue, true);
-+err_destroy_packet_crypt:
-+ destroy_workqueue(wg->packet_crypt_wq);
-+err_destroy_handshake_send:
-+ destroy_workqueue(wg->handshake_send_wq);
-+err_destroy_handshake_receive:
-+ destroy_workqueue(wg->handshake_receive_wq);
-+err_free_incoming_handshakes:
-+ free_percpu(wg->incoming_handshakes_worker);
-+err_free_tstats:
-+ free_percpu(dev->tstats);
-+err_free_index_hashtable:
-+ kvfree(wg->index_hashtable);
-+err_free_peer_hashtable:
-+ kvfree(wg->peer_hashtable);
-+ return ret;
-+}
-+
-+static struct rtnl_link_ops link_ops __read_mostly = {
-+ .kind = KBUILD_MODNAME,
-+ .priv_size = sizeof(struct wg_device),
-+ .setup = wg_setup,
-+ .newlink = wg_newlink,
-+};
-+
-+static int wg_netdevice_notification(struct notifier_block *nb,
-+ unsigned long action, void *data)
-+{
-+ struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
-+ struct wg_device *wg = netdev_priv(dev);
-+
-+ ASSERT_RTNL();
-+
-+ if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
-+ return 0;
-+
-+ if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
-+ put_net(wg->creating_net);
-+ wg->have_creating_net_ref = false;
-+ } else if (dev_net(dev) != wg->creating_net &&
-+ !wg->have_creating_net_ref) {
-+ wg->have_creating_net_ref = true;
-+ get_net(wg->creating_net);
-+ }
-+ return 0;
-+}
-+
-+static struct notifier_block netdevice_notifier = {
-+ .notifier_call = wg_netdevice_notification
-+};
-+
-+int __init wg_device_init(void)
-+{
-+ int ret;
-+
-+#ifdef CONFIG_PM_SLEEP
-+ ret = register_pm_notifier(&pm_notifier);
-+ if (ret)
-+ return ret;
-+#endif
-+
-+ ret = register_netdevice_notifier(&netdevice_notifier);
-+ if (ret)
-+ goto error_pm;
-+
-+ ret = rtnl_link_register(&link_ops);
-+ if (ret)
-+ goto error_netdevice;
-+
-+ return 0;
-+
-+error_netdevice:
-+ unregister_netdevice_notifier(&netdevice_notifier);
-+error_pm:
-+#ifdef CONFIG_PM_SLEEP
-+ unregister_pm_notifier(&pm_notifier);
-+#endif
-+ return ret;
-+}
-+
-+void wg_device_uninit(void)
-+{
-+ rtnl_link_unregister(&link_ops);
-+ unregister_netdevice_notifier(&netdevice_notifier);
-+#ifdef CONFIG_PM_SLEEP
-+ unregister_pm_notifier(&pm_notifier);
-+#endif
-+ rcu_barrier();
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/device.h
-@@ -0,0 +1,65 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_DEVICE_H
-+#define _WG_DEVICE_H
-+
-+#include "noise.h"
-+#include "allowedips.h"
-+#include "peerlookup.h"
-+#include "cookie.h"
-+
-+#include <linux/types.h>
-+#include <linux/netdevice.h>
-+#include <linux/workqueue.h>
-+#include <linux/mutex.h>
-+#include <linux/net.h>
-+#include <linux/ptr_ring.h>
-+
-+struct wg_device;
-+
-+struct multicore_worker {
-+ void *ptr;
-+ struct work_struct work;
-+};
-+
-+struct crypt_queue {
-+ struct ptr_ring ring;
-+ union {
-+ struct {
-+ struct multicore_worker __percpu *worker;
-+ int last_cpu;
-+ };
-+ struct work_struct work;
-+ };
-+};
-+
-+struct wg_device {
-+ struct net_device *dev;
-+ struct crypt_queue encrypt_queue, decrypt_queue;
-+ struct sock __rcu *sock4, *sock6;
-+ struct net *creating_net;
-+ struct noise_static_identity static_identity;
-+ struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
-+ struct workqueue_struct *packet_crypt_wq;
-+ struct sk_buff_head incoming_handshakes;
-+ int incoming_handshake_cpu;
-+ struct multicore_worker __percpu *incoming_handshakes_worker;
-+ struct cookie_checker cookie_checker;
-+ struct pubkey_hashtable *peer_hashtable;
-+ struct index_hashtable *index_hashtable;
-+ struct allowedips peer_allowedips;
-+ struct mutex device_update_lock, socket_update_lock;
-+ struct list_head device_list, peer_list;
-+ unsigned int num_peers, device_update_gen;
-+ u32 fwmark;
-+ u16 incoming_port;
-+ bool have_creating_net_ref;
-+};
-+
-+int wg_device_init(void);
-+void wg_device_uninit(void);
-+
-+#endif /* _WG_DEVICE_H */
---- /dev/null
-+++ b/drivers/net/wireguard/main.c
-@@ -0,0 +1,64 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "version.h"
-+#include "device.h"
-+#include "noise.h"
-+#include "queueing.h"
-+#include "ratelimiter.h"
-+#include "netlink.h"
-+
-+#include <uapi/linux/wireguard.h>
-+
-+#include <linux/version.h>
-+#include <linux/init.h>
-+#include <linux/module.h>
-+#include <linux/genetlink.h>
-+#include <net/rtnetlink.h>
-+
-+static int __init mod_init(void)
-+{
-+ int ret;
-+
-+#ifdef DEBUG
-+ if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() ||
-+ !wg_ratelimiter_selftest())
-+ return -ENOTRECOVERABLE;
-+#endif
-+ wg_noise_init();
-+
-+ ret = wg_device_init();
-+ if (ret < 0)
-+ goto err_device;
-+
-+ ret = wg_genetlink_init();
-+ if (ret < 0)
-+ goto err_netlink;
-+
-+ pr_info("WireGuard " WIREGUARD_VERSION " loaded. See www.wireguard.com for information.\n");
-+ pr_info("Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.\n");
-+
-+ return 0;
-+
-+err_netlink:
-+ wg_device_uninit();
-+err_device:
-+ return ret;
-+}
-+
-+static void __exit mod_exit(void)
-+{
-+ wg_genetlink_uninit();
-+ wg_device_uninit();
-+}
-+
-+module_init(mod_init);
-+module_exit(mod_exit);
-+MODULE_LICENSE("GPL v2");
-+MODULE_DESCRIPTION("WireGuard secure network tunnel");
-+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
-+MODULE_VERSION(WIREGUARD_VERSION);
-+MODULE_ALIAS_RTNL_LINK(KBUILD_MODNAME);
-+MODULE_ALIAS_GENL_FAMILY(WG_GENL_NAME);
---- /dev/null
-+++ b/drivers/net/wireguard/messages.h
-@@ -0,0 +1,128 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_MESSAGES_H
-+#define _WG_MESSAGES_H
-+
-+#include <crypto/curve25519.h>
-+#include <crypto/chacha20poly1305.h>
-+#include <crypto/blake2s.h>
-+
-+#include <linux/kernel.h>
-+#include <linux/param.h>
-+#include <linux/skbuff.h>
-+
-+enum noise_lengths {
-+ NOISE_PUBLIC_KEY_LEN = CURVE25519_KEY_SIZE,
-+ NOISE_SYMMETRIC_KEY_LEN = CHACHA20POLY1305_KEY_SIZE,
-+ NOISE_TIMESTAMP_LEN = sizeof(u64) + sizeof(u32),
-+ NOISE_AUTHTAG_LEN = CHACHA20POLY1305_AUTHTAG_SIZE,
-+ NOISE_HASH_LEN = BLAKE2S_HASH_SIZE
-+};
-+
-+#define noise_encrypted_len(plain_len) ((plain_len) + NOISE_AUTHTAG_LEN)
-+
-+enum cookie_values {
-+ COOKIE_SECRET_MAX_AGE = 2 * 60,
-+ COOKIE_SECRET_LATENCY = 5,
-+ COOKIE_NONCE_LEN = XCHACHA20POLY1305_NONCE_SIZE,
-+ COOKIE_LEN = 16
-+};
-+
-+enum counter_values {
-+ COUNTER_BITS_TOTAL = 2048,
-+ COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
-+ COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
-+};
-+
-+enum limits {
-+ REKEY_AFTER_MESSAGES = 1ULL << 60,
-+ REJECT_AFTER_MESSAGES = U64_MAX - COUNTER_WINDOW_SIZE - 1,
-+ REKEY_TIMEOUT = 5,
-+ REKEY_TIMEOUT_JITTER_MAX_JIFFIES = HZ / 3,
-+ REKEY_AFTER_TIME = 120,
-+ REJECT_AFTER_TIME = 180,
-+ INITIATIONS_PER_SECOND = 50,
-+ MAX_PEERS_PER_DEVICE = 1U << 20,
-+ KEEPALIVE_TIMEOUT = 10,
-+ MAX_TIMER_HANDSHAKES = 90 / REKEY_TIMEOUT,
-+ MAX_QUEUED_INCOMING_HANDSHAKES = 4096, /* TODO: replace this with DQL */
-+ MAX_STAGED_PACKETS = 128,
-+ MAX_QUEUED_PACKETS = 1024 /* TODO: replace this with DQL */
-+};
-+
-+enum message_type {
-+ MESSAGE_INVALID = 0,
-+ MESSAGE_HANDSHAKE_INITIATION = 1,
-+ MESSAGE_HANDSHAKE_RESPONSE = 2,
-+ MESSAGE_HANDSHAKE_COOKIE = 3,
-+ MESSAGE_DATA = 4
-+};
-+
-+struct message_header {
-+ /* The actual layout of this that we want is:
-+ * u8 type
-+ * u8 reserved_zero[3]
-+ *
-+ * But it turns out that by encoding this as little endian,
-+ * we achieve the same thing, and it makes checking faster.
-+ */
-+ __le32 type;
-+};
-+
-+struct message_macs {
-+ u8 mac1[COOKIE_LEN];
-+ u8 mac2[COOKIE_LEN];
-+};
-+
-+struct message_handshake_initiation {
-+ struct message_header header;
-+ __le32 sender_index;
-+ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
-+ u8 encrypted_static[noise_encrypted_len(NOISE_PUBLIC_KEY_LEN)];
-+ u8 encrypted_timestamp[noise_encrypted_len(NOISE_TIMESTAMP_LEN)];
-+ struct message_macs macs;
-+};
-+
-+struct message_handshake_response {
-+ struct message_header header;
-+ __le32 sender_index;
-+ __le32 receiver_index;
-+ u8 unencrypted_ephemeral[NOISE_PUBLIC_KEY_LEN];
-+ u8 encrypted_nothing[noise_encrypted_len(0)];
-+ struct message_macs macs;
-+};
-+
-+struct message_handshake_cookie {
-+ struct message_header header;
-+ __le32 receiver_index;
-+ u8 nonce[COOKIE_NONCE_LEN];
-+ u8 encrypted_cookie[noise_encrypted_len(COOKIE_LEN)];
-+};
-+
-+struct message_data {
-+ struct message_header header;
-+ __le32 key_idx;
-+ __le64 counter;
-+ u8 encrypted_data[];
-+};
-+
-+#define message_data_len(plain_len) \
-+ (noise_encrypted_len(plain_len) + sizeof(struct message_data))
-+
-+enum message_alignments {
-+ MESSAGE_PADDING_MULTIPLE = 16,
-+ MESSAGE_MINIMUM_LENGTH = message_data_len(0)
-+};
-+
-+#define SKB_HEADER_LEN \
-+ (max(sizeof(struct iphdr), sizeof(struct ipv6hdr)) + \
-+ sizeof(struct udphdr) + NET_SKB_PAD)
-+#define DATA_PACKET_HEAD_ROOM \
-+ ALIGN(sizeof(struct message_data) + SKB_HEADER_LEN, 4)
-+
-+enum { HANDSHAKE_DSCP = 0x88 /* AF41, plus 00 ECN */ };
-+
-+#endif /* _WG_MESSAGES_H */
---- /dev/null
-+++ b/drivers/net/wireguard/netlink.c
-@@ -0,0 +1,648 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "netlink.h"
-+#include "device.h"
-+#include "peer.h"
-+#include "socket.h"
-+#include "queueing.h"
-+#include "messages.h"
-+
-+#include <uapi/linux/wireguard.h>
-+
-+#include <linux/if.h>
-+#include <net/genetlink.h>
-+#include <net/sock.h>
-+#include <crypto/algapi.h>
-+
-+static struct genl_family genl_family;
-+
-+static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = {
-+ [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 },
-+ [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-+ [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-+ [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-+ [WGDEVICE_A_FLAGS] = { .type = NLA_U32 },
-+ [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 },
-+ [WGDEVICE_A_FWMARK] = { .type = NLA_U32 },
-+ [WGDEVICE_A_PEERS] = { .type = NLA_NESTED }
-+};
-+
-+static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
-+ [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-+ [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN },
-+ [WGPEER_A_FLAGS] = { .type = NLA_U32 },
-+ [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
-+ [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
-+ [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) },
-+ [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
-+ [WGPEER_A_TX_BYTES] = { .type = NLA_U64 },
-+ [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED },
-+ [WGPEER_A_PROTOCOL_VERSION] = { .type = NLA_U32 }
-+};
-+
-+static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = {
-+ [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 },
-+ [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) },
-+ [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }
-+};
-+
-+static struct wg_device *lookup_interface(struct nlattr **attrs,
-+ struct sk_buff *skb)
-+{
-+ struct net_device *dev = NULL;
-+
-+ if (!attrs[WGDEVICE_A_IFINDEX] == !attrs[WGDEVICE_A_IFNAME])
-+ return ERR_PTR(-EBADR);
-+ if (attrs[WGDEVICE_A_IFINDEX])
-+ dev = dev_get_by_index(sock_net(skb->sk),
-+ nla_get_u32(attrs[WGDEVICE_A_IFINDEX]));
-+ else if (attrs[WGDEVICE_A_IFNAME])
-+ dev = dev_get_by_name(sock_net(skb->sk),
-+ nla_data(attrs[WGDEVICE_A_IFNAME]));
-+ if (!dev)
-+ return ERR_PTR(-ENODEV);
-+ if (!dev->rtnl_link_ops || !dev->rtnl_link_ops->kind ||
-+ strcmp(dev->rtnl_link_ops->kind, KBUILD_MODNAME)) {
-+ dev_put(dev);
-+ return ERR_PTR(-EOPNOTSUPP);
-+ }
-+ return netdev_priv(dev);
-+}
-+
-+static int get_allowedips(struct sk_buff *skb, const u8 *ip, u8 cidr,
-+ int family)
-+{
-+ struct nlattr *allowedip_nest;
-+
-+ allowedip_nest = nla_nest_start(skb, 0);
-+ if (!allowedip_nest)
-+ return -EMSGSIZE;
-+
-+ if (nla_put_u8(skb, WGALLOWEDIP_A_CIDR_MASK, cidr) ||
-+ nla_put_u16(skb, WGALLOWEDIP_A_FAMILY, family) ||
-+ nla_put(skb, WGALLOWEDIP_A_IPADDR, family == AF_INET6 ?
-+ sizeof(struct in6_addr) : sizeof(struct in_addr), ip)) {
-+ nla_nest_cancel(skb, allowedip_nest);
-+ return -EMSGSIZE;
-+ }
-+
-+ nla_nest_end(skb, allowedip_nest);
-+ return 0;
-+}
-+
-+struct dump_ctx {
-+ struct wg_device *wg;
-+ struct wg_peer *next_peer;
-+ u64 allowedips_seq;
-+ struct allowedips_node *next_allowedip;
-+};
-+
-+#define DUMP_CTX(cb) ((struct dump_ctx *)(cb)->args)
-+
-+static int
-+get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx)
-+{
-+
-+ struct nlattr *allowedips_nest, *peer_nest = nla_nest_start(skb, 0);
-+ struct allowedips_node *allowedips_node = ctx->next_allowedip;
-+ bool fail;
-+
-+ if (!peer_nest)
-+ return -EMSGSIZE;
-+
-+ down_read(&peer->handshake.lock);
-+ fail = nla_put(skb, WGPEER_A_PUBLIC_KEY, NOISE_PUBLIC_KEY_LEN,
-+ peer->handshake.remote_static);
-+ up_read(&peer->handshake.lock);
-+ if (fail)
-+ goto err;
-+
-+ if (!allowedips_node) {
-+ const struct __kernel_timespec last_handshake = {
-+ .tv_sec = peer->walltime_last_handshake.tv_sec,
-+ .tv_nsec = peer->walltime_last_handshake.tv_nsec
-+ };
-+
-+ down_read(&peer->handshake.lock);
-+ fail = nla_put(skb, WGPEER_A_PRESHARED_KEY,
-+ NOISE_SYMMETRIC_KEY_LEN,
-+ peer->handshake.preshared_key);
-+ up_read(&peer->handshake.lock);
-+ if (fail)
-+ goto err;
-+
-+ if (nla_put(skb, WGPEER_A_LAST_HANDSHAKE_TIME,
-+ sizeof(last_handshake), &last_handshake) ||
-+ nla_put_u16(skb, WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL,
-+ peer->persistent_keepalive_interval) ||
-+ nla_put_u64_64bit(skb, WGPEER_A_TX_BYTES, peer->tx_bytes,
-+ WGPEER_A_UNSPEC) ||
-+ nla_put_u64_64bit(skb, WGPEER_A_RX_BYTES, peer->rx_bytes,
-+ WGPEER_A_UNSPEC) ||
-+ nla_put_u32(skb, WGPEER_A_PROTOCOL_VERSION, 1))
-+ goto err;
-+
-+ read_lock_bh(&peer->endpoint_lock);
-+ if (peer->endpoint.addr.sa_family == AF_INET)
-+ fail = nla_put(skb, WGPEER_A_ENDPOINT,
-+ sizeof(peer->endpoint.addr4),
-+ &peer->endpoint.addr4);
-+ else if (peer->endpoint.addr.sa_family == AF_INET6)
-+ fail = nla_put(skb, WGPEER_A_ENDPOINT,
-+ sizeof(peer->endpoint.addr6),
-+ &peer->endpoint.addr6);
-+ read_unlock_bh(&peer->endpoint_lock);
-+ if (fail)
-+ goto err;
-+ allowedips_node =
-+ list_first_entry_or_null(&peer->allowedips_list,
-+ struct allowedips_node, peer_list);
-+ }
-+ if (!allowedips_node)
-+ goto no_allowedips;
-+ if (!ctx->allowedips_seq)
-+ ctx->allowedips_seq = peer->device->peer_allowedips.seq;
-+ else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq)
-+ goto no_allowedips;
-+
-+ allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS);
-+ if (!allowedips_nest)
-+ goto err;
-+
-+ list_for_each_entry_from(allowedips_node, &peer->allowedips_list,
-+ peer_list) {
-+ u8 cidr, ip[16] __aligned(__alignof(u64));
-+ int family;
-+
-+ family = wg_allowedips_read_node(allowedips_node, ip, &cidr);
-+ if (get_allowedips(skb, ip, cidr, family)) {
-+ nla_nest_end(skb, allowedips_nest);
-+ nla_nest_end(skb, peer_nest);
-+ ctx->next_allowedip = allowedips_node;
-+ return -EMSGSIZE;
-+ }
-+ }
-+ nla_nest_end(skb, allowedips_nest);
-+no_allowedips:
-+ nla_nest_end(skb, peer_nest);
-+ ctx->next_allowedip = NULL;
-+ ctx->allowedips_seq = 0;
-+ return 0;
-+err:
-+ nla_nest_cancel(skb, peer_nest);
-+ return -EMSGSIZE;
-+}
-+
-+static int wg_get_device_start(struct netlink_callback *cb)
-+{
-+ struct nlattr **attrs = genl_family_attrbuf(&genl_family);
-+ struct wg_device *wg;
-+ int ret;
-+
-+ ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + genl_family.hdrsize, attrs,
-+ genl_family.maxattr, device_policy, NULL);
-+ if (ret < 0)
-+ return ret;
-+ wg = lookup_interface(attrs, cb->skb);
-+ if (IS_ERR(wg))
-+ return PTR_ERR(wg);
-+ DUMP_CTX(cb)->wg = wg;
-+ return 0;
-+}
-+
-+static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb)
-+{
-+ struct wg_peer *peer, *next_peer_cursor;
-+ struct dump_ctx *ctx = DUMP_CTX(cb);
-+ struct wg_device *wg = ctx->wg;
-+ struct nlattr *peers_nest;
-+ int ret = -EMSGSIZE;
-+ bool done = true;
-+ void *hdr;
-+
-+ rtnl_lock();
-+ mutex_lock(&wg->device_update_lock);
-+ cb->seq = wg->device_update_gen;
-+ next_peer_cursor = ctx->next_peer;
-+
-+ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
-+ &genl_family, NLM_F_MULTI, WG_CMD_GET_DEVICE);
-+ if (!hdr)
-+ goto out;
-+ genl_dump_check_consistent(cb, hdr);
-+
-+ if (!ctx->next_peer) {
-+ if (nla_put_u16(skb, WGDEVICE_A_LISTEN_PORT,
-+ wg->incoming_port) ||
-+ nla_put_u32(skb, WGDEVICE_A_FWMARK, wg->fwmark) ||
-+ nla_put_u32(skb, WGDEVICE_A_IFINDEX, wg->dev->ifindex) ||
-+ nla_put_string(skb, WGDEVICE_A_IFNAME, wg->dev->name))
-+ goto out;
-+
-+ down_read(&wg->static_identity.lock);
-+ if (wg->static_identity.has_identity) {
-+ if (nla_put(skb, WGDEVICE_A_PRIVATE_KEY,
-+ NOISE_PUBLIC_KEY_LEN,
-+ wg->static_identity.static_private) ||
-+ nla_put(skb, WGDEVICE_A_PUBLIC_KEY,
-+ NOISE_PUBLIC_KEY_LEN,
-+ wg->static_identity.static_public)) {
-+ up_read(&wg->static_identity.lock);
-+ goto out;
-+ }
-+ }
-+ up_read(&wg->static_identity.lock);
-+ }
-+
-+ peers_nest = nla_nest_start(skb, WGDEVICE_A_PEERS);
-+ if (!peers_nest)
-+ goto out;
-+ ret = 0;
-+ /* If the last cursor was removed via list_del_init in peer_remove, then
-+ * we just treat this the same as there being no more peers left. The
-+ * reason is that seq_nr should indicate to userspace that this isn't a
-+ * coherent dump anyway, so they'll try again.
-+ */
-+ if (list_empty(&wg->peer_list) ||
-+ (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) {
-+ nla_nest_cancel(skb, peers_nest);
-+ goto out;
-+ }
-+ lockdep_assert_held(&wg->device_update_lock);
-+ peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list);
-+ list_for_each_entry_continue(peer, &wg->peer_list, peer_list) {
-+ if (get_peer(peer, skb, ctx)) {
-+ done = false;
-+ break;
-+ }
-+ next_peer_cursor = peer;
-+ }
-+ nla_nest_end(skb, peers_nest);
-+
-+out:
-+ if (!ret && !done && next_peer_cursor)
-+ wg_peer_get(next_peer_cursor);
-+ wg_peer_put(ctx->next_peer);
-+ mutex_unlock(&wg->device_update_lock);
-+ rtnl_unlock();
-+
-+ if (ret) {
-+ genlmsg_cancel(skb, hdr);
-+ return ret;
-+ }
-+ genlmsg_end(skb, hdr);
-+ if (done) {
-+ ctx->next_peer = NULL;
-+ return 0;
-+ }
-+ ctx->next_peer = next_peer_cursor;
-+ return skb->len;
-+
-+ /* At this point, we can't really deal ourselves with safely zeroing out
-+ * the private key material after usage. This will need an additional API
-+ * in the kernel for marking skbs as zero_on_free.
-+ */
-+}
-+
-+static int wg_get_device_done(struct netlink_callback *cb)
-+{
-+ struct dump_ctx *ctx = DUMP_CTX(cb);
-+
-+ if (ctx->wg)
-+ dev_put(ctx->wg->dev);
-+ wg_peer_put(ctx->next_peer);
-+ return 0;
-+}
-+
-+static int set_port(struct wg_device *wg, u16 port)
-+{
-+ struct wg_peer *peer;
-+
-+ if (wg->incoming_port == port)
-+ return 0;
-+ list_for_each_entry(peer, &wg->peer_list, peer_list)
-+ wg_socket_clear_peer_endpoint_src(peer);
-+ if (!netif_running(wg->dev)) {
-+ wg->incoming_port = port;
-+ return 0;
-+ }
-+ return wg_socket_init(wg, port);
-+}
-+
-+static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs)
-+{
-+ int ret = -EINVAL;
-+ u16 family;
-+ u8 cidr;
-+
-+ if (!attrs[WGALLOWEDIP_A_FAMILY] || !attrs[WGALLOWEDIP_A_IPADDR] ||
-+ !attrs[WGALLOWEDIP_A_CIDR_MASK])
-+ return ret;
-+ family = nla_get_u16(attrs[WGALLOWEDIP_A_FAMILY]);
-+ cidr = nla_get_u8(attrs[WGALLOWEDIP_A_CIDR_MASK]);
-+
-+ if (family == AF_INET && cidr <= 32 &&
-+ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr))
-+ ret = wg_allowedips_insert_v4(
-+ &peer->device->peer_allowedips,
-+ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer,
-+ &peer->device->device_update_lock);
-+ else if (family == AF_INET6 && cidr <= 128 &&
-+ nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr))
-+ ret = wg_allowedips_insert_v6(
-+ &peer->device->peer_allowedips,
-+ nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer,
-+ &peer->device->device_update_lock);
-+
-+ return ret;
-+}
-+
-+static int set_peer(struct wg_device *wg, struct nlattr **attrs)
-+{
-+ u8 *public_key = NULL, *preshared_key = NULL;
-+ struct wg_peer *peer = NULL;
-+ u32 flags = 0;
-+ int ret;
-+
-+ ret = -EINVAL;
-+ if (attrs[WGPEER_A_PUBLIC_KEY] &&
-+ nla_len(attrs[WGPEER_A_PUBLIC_KEY]) == NOISE_PUBLIC_KEY_LEN)
-+ public_key = nla_data(attrs[WGPEER_A_PUBLIC_KEY]);
-+ else
-+ goto out;
-+ if (attrs[WGPEER_A_PRESHARED_KEY] &&
-+ nla_len(attrs[WGPEER_A_PRESHARED_KEY]) == NOISE_SYMMETRIC_KEY_LEN)
-+ preshared_key = nla_data(attrs[WGPEER_A_PRESHARED_KEY]);
-+
-+ if (attrs[WGPEER_A_FLAGS])
-+ flags = nla_get_u32(attrs[WGPEER_A_FLAGS]);
-+ ret = -EOPNOTSUPP;
-+ if (flags & ~__WGPEER_F_ALL)
-+ goto out;
-+
-+ ret = -EPFNOSUPPORT;
-+ if (attrs[WGPEER_A_PROTOCOL_VERSION]) {
-+ if (nla_get_u32(attrs[WGPEER_A_PROTOCOL_VERSION]) != 1)
-+ goto out;
-+ }
-+
-+ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable,
-+ nla_data(attrs[WGPEER_A_PUBLIC_KEY]));
-+ ret = 0;
-+ if (!peer) { /* Peer doesn't exist yet. Add a new one. */
-+ if (flags & (WGPEER_F_REMOVE_ME | WGPEER_F_UPDATE_ONLY))
-+ goto out;
-+
-+ /* The peer is new, so there aren't allowed IPs to remove. */
-+ flags &= ~WGPEER_F_REPLACE_ALLOWEDIPS;
-+
-+ down_read(&wg->static_identity.lock);
-+ if (wg->static_identity.has_identity &&
-+ !memcmp(nla_data(attrs[WGPEER_A_PUBLIC_KEY]),
-+ wg->static_identity.static_public,
-+ NOISE_PUBLIC_KEY_LEN)) {
-+ /* We silently ignore peers that have the same public
-+ * key as the device. The reason we do it silently is
-+ * that we'd like for people to be able to reuse the
-+ * same set of API calls across peers.
-+ */
-+ up_read(&wg->static_identity.lock);
-+ ret = 0;
-+ goto out;
-+ }
-+ up_read(&wg->static_identity.lock);
-+
-+ peer = wg_peer_create(wg, public_key, preshared_key);
-+ if (IS_ERR(peer)) {
-+ /* Similar to the above, if the key is invalid, we skip
-+ * it without fanfare, so that services don't need to
-+ * worry about doing key validation themselves.
-+ */
-+ ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer);
-+ peer = NULL;
-+ goto out;
-+ }
-+ /* Take additional reference, as though we've just been
-+ * looked up.
-+ */
-+ wg_peer_get(peer);
-+ }
-+
-+ if (flags & WGPEER_F_REMOVE_ME) {
-+ wg_peer_remove(peer);
-+ goto out;
-+ }
-+
-+ if (preshared_key) {
-+ down_write(&peer->handshake.lock);
-+ memcpy(&peer->handshake.preshared_key, preshared_key,
-+ NOISE_SYMMETRIC_KEY_LEN);
-+ up_write(&peer->handshake.lock);
-+ }
-+
-+ if (attrs[WGPEER_A_ENDPOINT]) {
-+ struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]);
-+ size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]);
-+
-+ if ((len == sizeof(struct sockaddr_in) &&
-+ addr->sa_family == AF_INET) ||
-+ (len == sizeof(struct sockaddr_in6) &&
-+ addr->sa_family == AF_INET6)) {
-+ struct endpoint endpoint = { { { 0 } } };
-+
-+ memcpy(&endpoint.addr, addr, len);
-+ wg_socket_set_peer_endpoint(peer, &endpoint);
-+ }
-+ }
-+
-+ if (flags & WGPEER_F_REPLACE_ALLOWEDIPS)
-+ wg_allowedips_remove_by_peer(&wg->peer_allowedips, peer,
-+ &wg->device_update_lock);
-+
-+ if (attrs[WGPEER_A_ALLOWEDIPS]) {
-+ struct nlattr *attr, *allowedip[WGALLOWEDIP_A_MAX + 1];
-+ int rem;
-+
-+ nla_for_each_nested(attr, attrs[WGPEER_A_ALLOWEDIPS], rem) {
-+ ret = nla_parse_nested(allowedip, WGALLOWEDIP_A_MAX,
-+ attr, allowedip_policy, NULL);
-+ if (ret < 0)
-+ goto out;
-+ ret = set_allowedip(peer, allowedip);
-+ if (ret < 0)
-+ goto out;
-+ }
-+ }
-+
-+ if (attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]) {
-+ const u16 persistent_keepalive_interval = nla_get_u16(
-+ attrs[WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL]);
-+ const bool send_keepalive =
-+ !peer->persistent_keepalive_interval &&
-+ persistent_keepalive_interval &&
-+ netif_running(wg->dev);
-+
-+ peer->persistent_keepalive_interval = persistent_keepalive_interval;
-+ if (send_keepalive)
-+ wg_packet_send_keepalive(peer);
-+ }
-+
-+ if (netif_running(wg->dev))
-+ wg_packet_send_staged_packets(peer);
-+
-+out:
-+ wg_peer_put(peer);
-+ if (attrs[WGPEER_A_PRESHARED_KEY])
-+ memzero_explicit(nla_data(attrs[WGPEER_A_PRESHARED_KEY]),
-+ nla_len(attrs[WGPEER_A_PRESHARED_KEY]));
-+ return ret;
-+}
-+
-+static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
-+{
-+ struct wg_device *wg = lookup_interface(info->attrs, skb);
-+ u32 flags = 0;
-+ int ret;
-+
-+ if (IS_ERR(wg)) {
-+ ret = PTR_ERR(wg);
-+ goto out_nodev;
-+ }
-+
-+ rtnl_lock();
-+ mutex_lock(&wg->device_update_lock);
-+
-+ if (info->attrs[WGDEVICE_A_FLAGS])
-+ flags = nla_get_u32(info->attrs[WGDEVICE_A_FLAGS]);
-+ ret = -EOPNOTSUPP;
-+ if (flags & ~__WGDEVICE_F_ALL)
-+ goto out;
-+
-+ ret = -EPERM;
-+ if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
-+ info->attrs[WGDEVICE_A_FWMARK]) &&
-+ !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
-+ goto out;
-+
-+ ++wg->device_update_gen;
-+
-+ if (info->attrs[WGDEVICE_A_FWMARK]) {
-+ struct wg_peer *peer;
-+
-+ wg->fwmark = nla_get_u32(info->attrs[WGDEVICE_A_FWMARK]);
-+ list_for_each_entry(peer, &wg->peer_list, peer_list)
-+ wg_socket_clear_peer_endpoint_src(peer);
-+ }
-+
-+ if (info->attrs[WGDEVICE_A_LISTEN_PORT]) {
-+ ret = set_port(wg,
-+ nla_get_u16(info->attrs[WGDEVICE_A_LISTEN_PORT]));
-+ if (ret)
-+ goto out;
-+ }
-+
-+ if (flags & WGDEVICE_F_REPLACE_PEERS)
-+ wg_peer_remove_all(wg);
-+
-+ if (info->attrs[WGDEVICE_A_PRIVATE_KEY] &&
-+ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY]) ==
-+ NOISE_PUBLIC_KEY_LEN) {
-+ u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]);
-+ u8 public_key[NOISE_PUBLIC_KEY_LEN];
-+ struct wg_peer *peer, *temp;
-+
-+ if (!crypto_memneq(wg->static_identity.static_private,
-+ private_key, NOISE_PUBLIC_KEY_LEN))
-+ goto skip_set_private_key;
-+
-+ /* We remove before setting, to prevent race, which means doing
-+ * two 25519-genpub ops.
-+ */
-+ if (curve25519_generate_public(public_key, private_key)) {
-+ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable,
-+ public_key);
-+ if (peer) {
-+ wg_peer_put(peer);
-+ wg_peer_remove(peer);
-+ }
-+ }
-+
-+ down_write(&wg->static_identity.lock);
-+ wg_noise_set_static_identity_private_key(&wg->static_identity,
-+ private_key);
-+ list_for_each_entry_safe(peer, temp, &wg->peer_list,
-+ peer_list) {
-+ if (wg_noise_precompute_static_static(peer))
-+ wg_noise_expire_current_peer_keypairs(peer);
-+ else
-+ wg_peer_remove(peer);
-+ }
-+ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
-+ up_write(&wg->static_identity.lock);
-+ }
-+skip_set_private_key:
-+
-+ if (info->attrs[WGDEVICE_A_PEERS]) {
-+ struct nlattr *attr, *peer[WGPEER_A_MAX + 1];
-+ int rem;
-+
-+ nla_for_each_nested(attr, info->attrs[WGDEVICE_A_PEERS], rem) {
-+ ret = nla_parse_nested(peer, WGPEER_A_MAX, attr,
-+ peer_policy, NULL);
-+ if (ret < 0)
-+ goto out;
-+ ret = set_peer(wg, peer);
-+ if (ret < 0)
-+ goto out;
-+ }
-+ }
-+ ret = 0;
-+
-+out:
-+ mutex_unlock(&wg->device_update_lock);
-+ rtnl_unlock();
-+ dev_put(wg->dev);
-+out_nodev:
-+ if (info->attrs[WGDEVICE_A_PRIVATE_KEY])
-+ memzero_explicit(nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]),
-+ nla_len(info->attrs[WGDEVICE_A_PRIVATE_KEY]));
-+ return ret;
-+}
-+
-+static const struct genl_ops genl_ops[] = {
-+ {
-+ .cmd = WG_CMD_GET_DEVICE,
-+ .start = wg_get_device_start,
-+ .dumpit = wg_get_device_dump,
-+ .done = wg_get_device_done,
-+ .flags = GENL_UNS_ADMIN_PERM
-+ }, {
-+ .cmd = WG_CMD_SET_DEVICE,
-+ .doit = wg_set_device,
-+ .flags = GENL_UNS_ADMIN_PERM
-+ }
-+};
-+
-+static struct genl_family genl_family __ro_after_init = {
-+ .ops = genl_ops,
-+ .n_ops = ARRAY_SIZE(genl_ops),
-+ .name = WG_GENL_NAME,
-+ .version = WG_GENL_VERSION,
-+ .maxattr = WGDEVICE_A_MAX,
-+ .module = THIS_MODULE,
-+ .policy = device_policy,
-+ .netnsok = true
-+};
-+
-+int __init wg_genetlink_init(void)
-+{
-+ return genl_register_family(&genl_family);
-+}
-+
-+void __exit wg_genetlink_uninit(void)
-+{
-+ genl_unregister_family(&genl_family);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/netlink.h
-@@ -0,0 +1,12 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_NETLINK_H
-+#define _WG_NETLINK_H
-+
-+int wg_genetlink_init(void);
-+void wg_genetlink_uninit(void);
-+
-+#endif /* _WG_NETLINK_H */
---- /dev/null
-+++ b/drivers/net/wireguard/noise.c
-@@ -0,0 +1,828 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "noise.h"
-+#include "device.h"
-+#include "peer.h"
-+#include "messages.h"
-+#include "queueing.h"
-+#include "peerlookup.h"
-+
-+#include <linux/rcupdate.h>
-+#include <linux/slab.h>
-+#include <linux/bitmap.h>
-+#include <linux/scatterlist.h>
-+#include <linux/highmem.h>
-+#include <crypto/algapi.h>
-+
-+/* This implements Noise_IKpsk2:
-+ *
-+ * <- s
-+ * ******
-+ * -> e, es, s, ss, {t}
-+ * <- e, ee, se, psk, {}
-+ */
-+
-+static const u8 handshake_name[37] = "Noise_IKpsk2_25519_ChaChaPoly_BLAKE2s";
-+static const u8 identifier_name[34] = "WireGuard v1 zx2c4 Jason@zx2c4.com";
-+static u8 handshake_init_hash[NOISE_HASH_LEN] __ro_after_init;
-+static u8 handshake_init_chaining_key[NOISE_HASH_LEN] __ro_after_init;
-+static atomic64_t keypair_counter = ATOMIC64_INIT(0);
-+
-+void __init wg_noise_init(void)
-+{
-+ struct blake2s_state blake;
-+
-+ blake2s(handshake_init_chaining_key, handshake_name, NULL,
-+ NOISE_HASH_LEN, sizeof(handshake_name), 0);
-+ blake2s_init(&blake, NOISE_HASH_LEN);
-+ blake2s_update(&blake, handshake_init_chaining_key, NOISE_HASH_LEN);
-+ blake2s_update(&blake, identifier_name, sizeof(identifier_name));
-+ blake2s_final(&blake, handshake_init_hash);
-+}
-+
-+/* Must hold peer->handshake.static_identity->lock */
-+bool wg_noise_precompute_static_static(struct wg_peer *peer)
-+{
-+ bool ret = true;
-+
-+ down_write(&peer->handshake.lock);
-+ if (peer->handshake.static_identity->has_identity)
-+ ret = curve25519(
-+ peer->handshake.precomputed_static_static,
-+ peer->handshake.static_identity->static_private,
-+ peer->handshake.remote_static);
-+ else
-+ memset(peer->handshake.precomputed_static_static, 0,
-+ NOISE_PUBLIC_KEY_LEN);
-+ up_write(&peer->handshake.lock);
-+ return ret;
-+}
-+
-+bool wg_noise_handshake_init(struct noise_handshake *handshake,
-+ struct noise_static_identity *static_identity,
-+ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-+ struct wg_peer *peer)
-+{
-+ memset(handshake, 0, sizeof(*handshake));
-+ init_rwsem(&handshake->lock);
-+ handshake->entry.type = INDEX_HASHTABLE_HANDSHAKE;
-+ handshake->entry.peer = peer;
-+ memcpy(handshake->remote_static, peer_public_key, NOISE_PUBLIC_KEY_LEN);
-+ if (peer_preshared_key)
-+ memcpy(handshake->preshared_key, peer_preshared_key,
-+ NOISE_SYMMETRIC_KEY_LEN);
-+ handshake->static_identity = static_identity;
-+ handshake->state = HANDSHAKE_ZEROED;
-+ return wg_noise_precompute_static_static(peer);
-+}
-+
-+static void handshake_zero(struct noise_handshake *handshake)
-+{
-+ memset(&handshake->ephemeral_private, 0, NOISE_PUBLIC_KEY_LEN);
-+ memset(&handshake->remote_ephemeral, 0, NOISE_PUBLIC_KEY_LEN);
-+ memset(&handshake->hash, 0, NOISE_HASH_LEN);
-+ memset(&handshake->chaining_key, 0, NOISE_HASH_LEN);
-+ handshake->remote_index = 0;
-+ handshake->state = HANDSHAKE_ZEROED;
-+}
-+
-+void wg_noise_handshake_clear(struct noise_handshake *handshake)
-+{
-+ wg_index_hashtable_remove(
-+ handshake->entry.peer->device->index_hashtable,
-+ &handshake->entry);
-+ down_write(&handshake->lock);
-+ handshake_zero(handshake);
-+ up_write(&handshake->lock);
-+ wg_index_hashtable_remove(
-+ handshake->entry.peer->device->index_hashtable,
-+ &handshake->entry);
-+}
-+
-+static struct noise_keypair *keypair_create(struct wg_peer *peer)
-+{
-+ struct noise_keypair *keypair = kzalloc(sizeof(*keypair), GFP_KERNEL);
-+
-+ if (unlikely(!keypair))
-+ return NULL;
-+ keypair->internal_id = atomic64_inc_return(&keypair_counter);
-+ keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
-+ keypair->entry.peer = peer;
-+ kref_init(&keypair->refcount);
-+ return keypair;
-+}
-+
-+static void keypair_free_rcu(struct rcu_head *rcu)
-+{
-+ kzfree(container_of(rcu, struct noise_keypair, rcu));
-+}
-+
-+static void keypair_free_kref(struct kref *kref)
-+{
-+ struct noise_keypair *keypair =
-+ container_of(kref, struct noise_keypair, refcount);
-+
-+ net_dbg_ratelimited("%s: Keypair %llu destroyed for peer %llu\n",
-+ keypair->entry.peer->device->dev->name,
-+ keypair->internal_id,
-+ keypair->entry.peer->internal_id);
-+ wg_index_hashtable_remove(keypair->entry.peer->device->index_hashtable,
-+ &keypair->entry);
-+ call_rcu(&keypair->rcu, keypair_free_rcu);
-+}
-+
-+void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now)
-+{
-+ if (unlikely(!keypair))
-+ return;
-+ if (unlikely(unreference_now))
-+ wg_index_hashtable_remove(
-+ keypair->entry.peer->device->index_hashtable,
-+ &keypair->entry);
-+ kref_put(&keypair->refcount, keypair_free_kref);
-+}
-+
-+struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair)
-+{
-+ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(),
-+ "Taking noise keypair reference without holding the RCU BH read lock");
-+ if (unlikely(!keypair || !kref_get_unless_zero(&keypair->refcount)))
-+ return NULL;
-+ return keypair;
-+}
-+
-+void wg_noise_keypairs_clear(struct noise_keypairs *keypairs)
-+{
-+ struct noise_keypair *old;
-+
-+ spin_lock_bh(&keypairs->keypair_update_lock);
-+
-+ /* We zero the next_keypair before zeroing the others, so that
-+ * wg_noise_received_with_keypair returns early before subsequent ones
-+ * are zeroed.
-+ */
-+ old = rcu_dereference_protected(keypairs->next_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
-+ wg_noise_keypair_put(old, true);
-+
-+ old = rcu_dereference_protected(keypairs->previous_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
-+ wg_noise_keypair_put(old, true);
-+
-+ old = rcu_dereference_protected(keypairs->current_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ RCU_INIT_POINTER(keypairs->current_keypair, NULL);
-+ wg_noise_keypair_put(old, true);
-+
-+ spin_unlock_bh(&keypairs->keypair_update_lock);
-+}
-+
-+void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer)
-+{
-+ struct noise_keypair *keypair;
-+
-+ wg_noise_handshake_clear(&peer->handshake);
-+ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
-+
-+ spin_lock_bh(&peer->keypairs.keypair_update_lock);
-+ keypair = rcu_dereference_protected(peer->keypairs.next_keypair,
-+ lockdep_is_held(&peer->keypairs.keypair_update_lock));
-+ if (keypair)
-+ keypair->sending.is_valid = false;
-+ keypair = rcu_dereference_protected(peer->keypairs.current_keypair,
-+ lockdep_is_held(&peer->keypairs.keypair_update_lock));
-+ if (keypair)
-+ keypair->sending.is_valid = false;
-+ spin_unlock_bh(&peer->keypairs.keypair_update_lock);
-+}
-+
-+static void add_new_keypair(struct noise_keypairs *keypairs,
-+ struct noise_keypair *new_keypair)
-+{
-+ struct noise_keypair *previous_keypair, *next_keypair, *current_keypair;
-+
-+ spin_lock_bh(&keypairs->keypair_update_lock);
-+ previous_keypair = rcu_dereference_protected(keypairs->previous_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ next_keypair = rcu_dereference_protected(keypairs->next_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ current_keypair = rcu_dereference_protected(keypairs->current_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ if (new_keypair->i_am_the_initiator) {
-+ /* If we're the initiator, it means we've sent a handshake, and
-+ * received a confirmation response, which means this new
-+ * keypair can now be used.
-+ */
-+ if (next_keypair) {
-+ /* If there already was a next keypair pending, we
-+ * demote it to be the previous keypair, and free the
-+ * existing current. Note that this means KCI can result
-+ * in this transition. It would perhaps be more sound to
-+ * always just get rid of the unused next keypair
-+ * instead of putting it in the previous slot, but this
-+ * might be a bit less robust. Something to think about
-+ * for the future.
-+ */
-+ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
-+ rcu_assign_pointer(keypairs->previous_keypair,
-+ next_keypair);
-+ wg_noise_keypair_put(current_keypair, true);
-+ } else /* If there wasn't an existing next keypair, we replace
-+ * the previous with the current one.
-+ */
-+ rcu_assign_pointer(keypairs->previous_keypair,
-+ current_keypair);
-+ /* At this point we can get rid of the old previous keypair, and
-+ * set up the new keypair.
-+ */
-+ wg_noise_keypair_put(previous_keypair, true);
-+ rcu_assign_pointer(keypairs->current_keypair, new_keypair);
-+ } else {
-+ /* If we're the responder, it means we can't use the new keypair
-+ * until we receive confirmation via the first data packet, so
-+ * we get rid of the existing previous one, the possibly
-+ * existing next one, and slide in the new next one.
-+ */
-+ rcu_assign_pointer(keypairs->next_keypair, new_keypair);
-+ wg_noise_keypair_put(next_keypair, true);
-+ RCU_INIT_POINTER(keypairs->previous_keypair, NULL);
-+ wg_noise_keypair_put(previous_keypair, true);
-+ }
-+ spin_unlock_bh(&keypairs->keypair_update_lock);
-+}
-+
-+bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs,
-+ struct noise_keypair *received_keypair)
-+{
-+ struct noise_keypair *old_keypair;
-+ bool key_is_new;
-+
-+ /* We first check without taking the spinlock. */
-+ key_is_new = received_keypair ==
-+ rcu_access_pointer(keypairs->next_keypair);
-+ if (likely(!key_is_new))
-+ return false;
-+
-+ spin_lock_bh(&keypairs->keypair_update_lock);
-+ /* After locking, we double check that things didn't change from
-+ * beneath us.
-+ */
-+ if (unlikely(received_keypair !=
-+ rcu_dereference_protected(keypairs->next_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock)))) {
-+ spin_unlock_bh(&keypairs->keypair_update_lock);
-+ return false;
-+ }
-+
-+ /* When we've finally received the confirmation, we slide the next
-+ * into the current, the current into the previous, and get rid of
-+ * the old previous.
-+ */
-+ old_keypair = rcu_dereference_protected(keypairs->previous_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock));
-+ rcu_assign_pointer(keypairs->previous_keypair,
-+ rcu_dereference_protected(keypairs->current_keypair,
-+ lockdep_is_held(&keypairs->keypair_update_lock)));
-+ wg_noise_keypair_put(old_keypair, true);
-+ rcu_assign_pointer(keypairs->current_keypair, received_keypair);
-+ RCU_INIT_POINTER(keypairs->next_keypair, NULL);
-+
-+ spin_unlock_bh(&keypairs->keypair_update_lock);
-+ return true;
-+}
-+
-+/* Must hold static_identity->lock */
-+void wg_noise_set_static_identity_private_key(
-+ struct noise_static_identity *static_identity,
-+ const u8 private_key[NOISE_PUBLIC_KEY_LEN])
-+{
-+ memcpy(static_identity->static_private, private_key,
-+ NOISE_PUBLIC_KEY_LEN);
-+ curve25519_clamp_secret(static_identity->static_private);
-+ static_identity->has_identity = curve25519_generate_public(
-+ static_identity->static_public, private_key);
-+}
-+
-+/* This is Hugo Krawczyk's HKDF:
-+ * - https://eprint.iacr.org/2010/264.pdf
-+ * - https://tools.ietf.org/html/rfc5869
-+ */
-+static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data,
-+ size_t first_len, size_t second_len, size_t third_len,
-+ size_t data_len, const u8 chaining_key[NOISE_HASH_LEN])
-+{
-+ u8 output[BLAKE2S_HASH_SIZE + 1];
-+ u8 secret[BLAKE2S_HASH_SIZE];
-+
-+ WARN_ON(IS_ENABLED(DEBUG) &&
-+ (first_len > BLAKE2S_HASH_SIZE ||
-+ second_len > BLAKE2S_HASH_SIZE ||
-+ third_len > BLAKE2S_HASH_SIZE ||
-+ ((second_len || second_dst || third_len || third_dst) &&
-+ (!first_len || !first_dst)) ||
-+ ((third_len || third_dst) && (!second_len || !second_dst))));
-+
-+ /* Extract entropy from data into secret */
-+ blake2s256_hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN);
-+
-+ if (!first_dst || !first_len)
-+ goto out;
-+
-+ /* Expand first key: key = secret, data = 0x1 */
-+ output[0] = 1;
-+ blake2s256_hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE);
-+ memcpy(first_dst, output, first_len);
-+
-+ if (!second_dst || !second_len)
-+ goto out;
-+
-+ /* Expand second key: key = secret, data = first-key || 0x2 */
-+ output[BLAKE2S_HASH_SIZE] = 2;
-+ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
-+ BLAKE2S_HASH_SIZE);
-+ memcpy(second_dst, output, second_len);
-+
-+ if (!third_dst || !third_len)
-+ goto out;
-+
-+ /* Expand third key: key = secret, data = second-key || 0x3 */
-+ output[BLAKE2S_HASH_SIZE] = 3;
-+ blake2s256_hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1,
-+ BLAKE2S_HASH_SIZE);
-+ memcpy(third_dst, output, third_len);
-+
-+out:
-+ /* Clear sensitive data from stack */
-+ memzero_explicit(secret, BLAKE2S_HASH_SIZE);
-+ memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
-+}
-+
-+static void symmetric_key_init(struct noise_symmetric_key *key)
-+{
-+ spin_lock_init(&key->counter.receive.lock);
-+ atomic64_set(&key->counter.counter, 0);
-+ memset(key->counter.receive.backtrack, 0,
-+ sizeof(key->counter.receive.backtrack));
-+ key->birthdate = ktime_get_coarse_boottime_ns();
-+ key->is_valid = true;
-+}
-+
-+static void derive_keys(struct noise_symmetric_key *first_dst,
-+ struct noise_symmetric_key *second_dst,
-+ const u8 chaining_key[NOISE_HASH_LEN])
-+{
-+ kdf(first_dst->key, second_dst->key, NULL, NULL,
-+ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
-+ chaining_key);
-+ symmetric_key_init(first_dst);
-+ symmetric_key_init(second_dst);
-+}
-+
-+static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ const u8 private[NOISE_PUBLIC_KEY_LEN],
-+ const u8 public[NOISE_PUBLIC_KEY_LEN])
-+{
-+ u8 dh_calculation[NOISE_PUBLIC_KEY_LEN];
-+
-+ if (unlikely(!curve25519(dh_calculation, private, public)))
-+ return false;
-+ kdf(chaining_key, key, NULL, dh_calculation, NOISE_HASH_LEN,
-+ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key);
-+ memzero_explicit(dh_calculation, NOISE_PUBLIC_KEY_LEN);
-+ return true;
-+}
-+
-+static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len)
-+{
-+ struct blake2s_state blake;
-+
-+ blake2s_init(&blake, NOISE_HASH_LEN);
-+ blake2s_update(&blake, hash, NOISE_HASH_LEN);
-+ blake2s_update(&blake, src, src_len);
-+ blake2s_final(&blake, hash);
-+}
-+
-+static void mix_psk(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN],
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ const u8 psk[NOISE_SYMMETRIC_KEY_LEN])
-+{
-+ u8 temp_hash[NOISE_HASH_LEN];
-+
-+ kdf(chaining_key, temp_hash, key, psk, NOISE_HASH_LEN, NOISE_HASH_LEN,
-+ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, chaining_key);
-+ mix_hash(hash, temp_hash, NOISE_HASH_LEN);
-+ memzero_explicit(temp_hash, NOISE_HASH_LEN);
-+}
-+
-+static void handshake_init(u8 chaining_key[NOISE_HASH_LEN],
-+ u8 hash[NOISE_HASH_LEN],
-+ const u8 remote_static[NOISE_PUBLIC_KEY_LEN])
-+{
-+ memcpy(hash, handshake_init_hash, NOISE_HASH_LEN);
-+ memcpy(chaining_key, handshake_init_chaining_key, NOISE_HASH_LEN);
-+ mix_hash(hash, remote_static, NOISE_PUBLIC_KEY_LEN);
-+}
-+
-+static void message_encrypt(u8 *dst_ciphertext, const u8 *src_plaintext,
-+ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ u8 hash[NOISE_HASH_LEN])
-+{
-+ chacha20poly1305_encrypt(dst_ciphertext, src_plaintext, src_len, hash,
-+ NOISE_HASH_LEN,
-+ 0 /* Always zero for Noise_IK */, key);
-+ mix_hash(hash, dst_ciphertext, noise_encrypted_len(src_len));
-+}
-+
-+static bool message_decrypt(u8 *dst_plaintext, const u8 *src_ciphertext,
-+ size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ u8 hash[NOISE_HASH_LEN])
-+{
-+ if (!chacha20poly1305_decrypt(dst_plaintext, src_ciphertext, src_len,
-+ hash, NOISE_HASH_LEN,
-+ 0 /* Always zero for Noise_IK */, key))
-+ return false;
-+ mix_hash(hash, src_ciphertext, src_len);
-+ return true;
-+}
-+
-+static void message_ephemeral(u8 ephemeral_dst[NOISE_PUBLIC_KEY_LEN],
-+ const u8 ephemeral_src[NOISE_PUBLIC_KEY_LEN],
-+ u8 chaining_key[NOISE_HASH_LEN],
-+ u8 hash[NOISE_HASH_LEN])
-+{
-+ if (ephemeral_dst != ephemeral_src)
-+ memcpy(ephemeral_dst, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
-+ mix_hash(hash, ephemeral_src, NOISE_PUBLIC_KEY_LEN);
-+ kdf(chaining_key, NULL, NULL, ephemeral_src, NOISE_HASH_LEN, 0, 0,
-+ NOISE_PUBLIC_KEY_LEN, chaining_key);
-+}
-+
-+static void tai64n_now(u8 output[NOISE_TIMESTAMP_LEN])
-+{
-+ struct timespec64 now;
-+
-+ ktime_get_real_ts64(&now);
-+
-+ /* In order to prevent some sort of infoleak from precise timers, we
-+ * round down the nanoseconds part to the closest rounded-down power of
-+ * two to the maximum initiations per second allowed anyway by the
-+ * implementation.
-+ */
-+ now.tv_nsec = ALIGN_DOWN(now.tv_nsec,
-+ rounddown_pow_of_two(NSEC_PER_SEC / INITIATIONS_PER_SECOND));
-+
-+ /* https://cr.yp.to/libtai/tai64.html */
-+ *(__be64 *)output = cpu_to_be64(0x400000000000000aULL + now.tv_sec);
-+ *(__be32 *)(output + sizeof(__be64)) = cpu_to_be32(now.tv_nsec);
-+}
-+
-+bool
-+wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
-+ struct noise_handshake *handshake)
-+{
-+ u8 timestamp[NOISE_TIMESTAMP_LEN];
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
-+ bool ret = false;
-+
-+ /* We need to wait for crng _before_ taking any locks, since
-+ * curve25519_generate_secret uses get_random_bytes_wait.
-+ */
-+ wait_for_random_bytes();
-+
-+ down_read(&handshake->static_identity->lock);
-+ down_write(&handshake->lock);
-+
-+ if (unlikely(!handshake->static_identity->has_identity))
-+ goto out;
-+
-+ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION);
-+
-+ handshake_init(handshake->chaining_key, handshake->hash,
-+ handshake->remote_static);
-+
-+ /* e */
-+ curve25519_generate_secret(handshake->ephemeral_private);
-+ if (!curve25519_generate_public(dst->unencrypted_ephemeral,
-+ handshake->ephemeral_private))
-+ goto out;
-+ message_ephemeral(dst->unencrypted_ephemeral,
-+ dst->unencrypted_ephemeral, handshake->chaining_key,
-+ handshake->hash);
-+
-+ /* es */
-+ if (!mix_dh(handshake->chaining_key, key, handshake->ephemeral_private,
-+ handshake->remote_static))
-+ goto out;
-+
-+ /* s */
-+ message_encrypt(dst->encrypted_static,
-+ handshake->static_identity->static_public,
-+ NOISE_PUBLIC_KEY_LEN, key, handshake->hash);
-+
-+ /* ss */
-+ kdf(handshake->chaining_key, key, NULL,
-+ handshake->precomputed_static_static, NOISE_HASH_LEN,
-+ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
-+ handshake->chaining_key);
-+
-+ /* {t} */
-+ tai64n_now(timestamp);
-+ message_encrypt(dst->encrypted_timestamp, timestamp,
-+ NOISE_TIMESTAMP_LEN, key, handshake->hash);
-+
-+ dst->sender_index = wg_index_hashtable_insert(
-+ handshake->entry.peer->device->index_hashtable,
-+ &handshake->entry);
-+
-+ handshake->state = HANDSHAKE_CREATED_INITIATION;
-+ ret = true;
-+
-+out:
-+ up_write(&handshake->lock);
-+ up_read(&handshake->static_identity->lock);
-+ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
-+ return ret;
-+}
-+
-+struct wg_peer *
-+wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
-+ struct wg_device *wg)
-+{
-+ struct wg_peer *peer = NULL, *ret_peer = NULL;
-+ struct noise_handshake *handshake;
-+ bool replay_attack, flood_attack;
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
-+ u8 chaining_key[NOISE_HASH_LEN];
-+ u8 hash[NOISE_HASH_LEN];
-+ u8 s[NOISE_PUBLIC_KEY_LEN];
-+ u8 e[NOISE_PUBLIC_KEY_LEN];
-+ u8 t[NOISE_TIMESTAMP_LEN];
-+ u64 initiation_consumption;
-+
-+ down_read(&wg->static_identity.lock);
-+ if (unlikely(!wg->static_identity.has_identity))
-+ goto out;
-+
-+ handshake_init(chaining_key, hash, wg->static_identity.static_public);
-+
-+ /* e */
-+ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
-+
-+ /* es */
-+ if (!mix_dh(chaining_key, key, wg->static_identity.static_private, e))
-+ goto out;
-+
-+ /* s */
-+ if (!message_decrypt(s, src->encrypted_static,
-+ sizeof(src->encrypted_static), key, hash))
-+ goto out;
-+
-+ /* Lookup which peer we're actually talking to */
-+ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, s);
-+ if (!peer)
-+ goto out;
-+ handshake = &peer->handshake;
-+
-+ /* ss */
-+ kdf(chaining_key, key, NULL, handshake->precomputed_static_static,
-+ NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
-+ chaining_key);
-+
-+ /* {t} */
-+ if (!message_decrypt(t, src->encrypted_timestamp,
-+ sizeof(src->encrypted_timestamp), key, hash))
-+ goto out;
-+
-+ down_read(&handshake->lock);
-+ replay_attack = memcmp(t, handshake->latest_timestamp,
-+ NOISE_TIMESTAMP_LEN) <= 0;
-+ flood_attack = (s64)handshake->last_initiation_consumption +
-+ NSEC_PER_SEC / INITIATIONS_PER_SECOND >
-+ (s64)ktime_get_coarse_boottime_ns();
-+ up_read(&handshake->lock);
-+ if (replay_attack || flood_attack)
-+ goto out;
-+
-+ /* Success! Copy everything to peer */
-+ down_write(&handshake->lock);
-+ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
-+ if (memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) > 0)
-+ memcpy(handshake->latest_timestamp, t, NOISE_TIMESTAMP_LEN);
-+ memcpy(handshake->hash, hash, NOISE_HASH_LEN);
-+ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
-+ handshake->remote_index = src->sender_index;
-+ if ((s64)(handshake->last_initiation_consumption -
-+ (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
-+ handshake->last_initiation_consumption = initiation_consumption;
-+ handshake->state = HANDSHAKE_CONSUMED_INITIATION;
-+ up_write(&handshake->lock);
-+ ret_peer = peer;
-+
-+out:
-+ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
-+ memzero_explicit(hash, NOISE_HASH_LEN);
-+ memzero_explicit(chaining_key, NOISE_HASH_LEN);
-+ up_read(&wg->static_identity.lock);
-+ if (!ret_peer)
-+ wg_peer_put(peer);
-+ return ret_peer;
-+}
-+
-+bool wg_noise_handshake_create_response(struct message_handshake_response *dst,
-+ struct noise_handshake *handshake)
-+{
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
-+ bool ret = false;
-+
-+ /* We need to wait for crng _before_ taking any locks, since
-+ * curve25519_generate_secret uses get_random_bytes_wait.
-+ */
-+ wait_for_random_bytes();
-+
-+ down_read(&handshake->static_identity->lock);
-+ down_write(&handshake->lock);
-+
-+ if (handshake->state != HANDSHAKE_CONSUMED_INITIATION)
-+ goto out;
-+
-+ dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE);
-+ dst->receiver_index = handshake->remote_index;
-+
-+ /* e */
-+ curve25519_generate_secret(handshake->ephemeral_private);
-+ if (!curve25519_generate_public(dst->unencrypted_ephemeral,
-+ handshake->ephemeral_private))
-+ goto out;
-+ message_ephemeral(dst->unencrypted_ephemeral,
-+ dst->unencrypted_ephemeral, handshake->chaining_key,
-+ handshake->hash);
-+
-+ /* ee */
-+ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
-+ handshake->remote_ephemeral))
-+ goto out;
-+
-+ /* se */
-+ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private,
-+ handshake->remote_static))
-+ goto out;
-+
-+ /* psk */
-+ mix_psk(handshake->chaining_key, handshake->hash, key,
-+ handshake->preshared_key);
-+
-+ /* {} */
-+ message_encrypt(dst->encrypted_nothing, NULL, 0, key, handshake->hash);
-+
-+ dst->sender_index = wg_index_hashtable_insert(
-+ handshake->entry.peer->device->index_hashtable,
-+ &handshake->entry);
-+
-+ handshake->state = HANDSHAKE_CREATED_RESPONSE;
-+ ret = true;
-+
-+out:
-+ up_write(&handshake->lock);
-+ up_read(&handshake->static_identity->lock);
-+ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
-+ return ret;
-+}
-+
-+struct wg_peer *
-+wg_noise_handshake_consume_response(struct message_handshake_response *src,
-+ struct wg_device *wg)
-+{
-+ enum noise_handshake_state state = HANDSHAKE_ZEROED;
-+ struct wg_peer *peer = NULL, *ret_peer = NULL;
-+ struct noise_handshake *handshake;
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
-+ u8 hash[NOISE_HASH_LEN];
-+ u8 chaining_key[NOISE_HASH_LEN];
-+ u8 e[NOISE_PUBLIC_KEY_LEN];
-+ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
-+ u8 static_private[NOISE_PUBLIC_KEY_LEN];
-+
-+ down_read(&wg->static_identity.lock);
-+
-+ if (unlikely(!wg->static_identity.has_identity))
-+ goto out;
-+
-+ handshake = (struct noise_handshake *)wg_index_hashtable_lookup(
-+ wg->index_hashtable, INDEX_HASHTABLE_HANDSHAKE,
-+ src->receiver_index, &peer);
-+ if (unlikely(!handshake))
-+ goto out;
-+
-+ down_read(&handshake->lock);
-+ state = handshake->state;
-+ memcpy(hash, handshake->hash, NOISE_HASH_LEN);
-+ memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
-+ memcpy(ephemeral_private, handshake->ephemeral_private,
-+ NOISE_PUBLIC_KEY_LEN);
-+ up_read(&handshake->lock);
-+
-+ if (state != HANDSHAKE_CREATED_INITIATION)
-+ goto fail;
-+
-+ /* e */
-+ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash);
-+
-+ /* ee */
-+ if (!mix_dh(chaining_key, NULL, ephemeral_private, e))
-+ goto fail;
-+
-+ /* se */
-+ if (!mix_dh(chaining_key, NULL, wg->static_identity.static_private, e))
-+ goto fail;
-+
-+ /* psk */
-+ mix_psk(chaining_key, hash, key, handshake->preshared_key);
-+
-+ /* {} */
-+ if (!message_decrypt(NULL, src->encrypted_nothing,
-+ sizeof(src->encrypted_nothing), key, hash))
-+ goto fail;
-+
-+ /* Success! Copy everything to peer */
-+ down_write(&handshake->lock);
-+ /* It's important to check that the state is still the same, while we
-+ * have an exclusive lock.
-+ */
-+ if (handshake->state != state) {
-+ up_write(&handshake->lock);
-+ goto fail;
-+ }
-+ memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN);
-+ memcpy(handshake->hash, hash, NOISE_HASH_LEN);
-+ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
-+ handshake->remote_index = src->sender_index;
-+ handshake->state = HANDSHAKE_CONSUMED_RESPONSE;
-+ up_write(&handshake->lock);
-+ ret_peer = peer;
-+ goto out;
-+
-+fail:
-+ wg_peer_put(peer);
-+out:
-+ memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN);
-+ memzero_explicit(hash, NOISE_HASH_LEN);
-+ memzero_explicit(chaining_key, NOISE_HASH_LEN);
-+ memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
-+ memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
-+ up_read(&wg->static_identity.lock);
-+ return ret_peer;
-+}
-+
-+bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
-+ struct noise_keypairs *keypairs)
-+{
-+ struct noise_keypair *new_keypair;
-+ bool ret = false;
-+
-+ down_write(&handshake->lock);
-+ if (handshake->state != HANDSHAKE_CREATED_RESPONSE &&
-+ handshake->state != HANDSHAKE_CONSUMED_RESPONSE)
-+ goto out;
-+
-+ new_keypair = keypair_create(handshake->entry.peer);
-+ if (!new_keypair)
-+ goto out;
-+ new_keypair->i_am_the_initiator = handshake->state ==
-+ HANDSHAKE_CONSUMED_RESPONSE;
-+ new_keypair->remote_index = handshake->remote_index;
-+
-+ if (new_keypair->i_am_the_initiator)
-+ derive_keys(&new_keypair->sending, &new_keypair->receiving,
-+ handshake->chaining_key);
-+ else
-+ derive_keys(&new_keypair->receiving, &new_keypair->sending,
-+ handshake->chaining_key);
-+
-+ handshake_zero(handshake);
-+ rcu_read_lock_bh();
-+ if (likely(!READ_ONCE(container_of(handshake, struct wg_peer,
-+ handshake)->is_dead))) {
-+ add_new_keypair(keypairs, new_keypair);
-+ net_dbg_ratelimited("%s: Keypair %llu created for peer %llu\n",
-+ handshake->entry.peer->device->dev->name,
-+ new_keypair->internal_id,
-+ handshake->entry.peer->internal_id);
-+ ret = wg_index_hashtable_replace(
-+ handshake->entry.peer->device->index_hashtable,
-+ &handshake->entry, &new_keypair->entry);
-+ } else {
-+ kzfree(new_keypair);
-+ }
-+ rcu_read_unlock_bh();
-+
-+out:
-+ up_write(&handshake->lock);
-+ return ret;
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/noise.h
-@@ -0,0 +1,137 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+#ifndef _WG_NOISE_H
-+#define _WG_NOISE_H
-+
-+#include "messages.h"
-+#include "peerlookup.h"
-+
-+#include <linux/types.h>
-+#include <linux/spinlock.h>
-+#include <linux/atomic.h>
-+#include <linux/rwsem.h>
-+#include <linux/mutex.h>
-+#include <linux/kref.h>
-+
-+union noise_counter {
-+ struct {
-+ u64 counter;
-+ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
-+ spinlock_t lock;
-+ } receive;
-+ atomic64_t counter;
-+};
-+
-+struct noise_symmetric_key {
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
-+ union noise_counter counter;
-+ u64 birthdate;
-+ bool is_valid;
-+};
-+
-+struct noise_keypair {
-+ struct index_hashtable_entry entry;
-+ struct noise_symmetric_key sending;
-+ struct noise_symmetric_key receiving;
-+ __le32 remote_index;
-+ bool i_am_the_initiator;
-+ struct kref refcount;
-+ struct rcu_head rcu;
-+ u64 internal_id;
-+};
-+
-+struct noise_keypairs {
-+ struct noise_keypair __rcu *current_keypair;
-+ struct noise_keypair __rcu *previous_keypair;
-+ struct noise_keypair __rcu *next_keypair;
-+ spinlock_t keypair_update_lock;
-+};
-+
-+struct noise_static_identity {
-+ u8 static_public[NOISE_PUBLIC_KEY_LEN];
-+ u8 static_private[NOISE_PUBLIC_KEY_LEN];
-+ struct rw_semaphore lock;
-+ bool has_identity;
-+};
-+
-+enum noise_handshake_state {
-+ HANDSHAKE_ZEROED,
-+ HANDSHAKE_CREATED_INITIATION,
-+ HANDSHAKE_CONSUMED_INITIATION,
-+ HANDSHAKE_CREATED_RESPONSE,
-+ HANDSHAKE_CONSUMED_RESPONSE
-+};
-+
-+struct noise_handshake {
-+ struct index_hashtable_entry entry;
-+
-+ enum noise_handshake_state state;
-+ u64 last_initiation_consumption;
-+
-+ struct noise_static_identity *static_identity;
-+
-+ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
-+ u8 remote_static[NOISE_PUBLIC_KEY_LEN];
-+ u8 remote_ephemeral[NOISE_PUBLIC_KEY_LEN];
-+ u8 precomputed_static_static[NOISE_PUBLIC_KEY_LEN];
-+
-+ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
-+
-+ u8 hash[NOISE_HASH_LEN];
-+ u8 chaining_key[NOISE_HASH_LEN];
-+
-+ u8 latest_timestamp[NOISE_TIMESTAMP_LEN];
-+ __le32 remote_index;
-+
-+ /* Protects all members except the immutable (after noise_handshake_
-+ * init): remote_static, precomputed_static_static, static_identity.
-+ */
-+ struct rw_semaphore lock;
-+};
-+
-+struct wg_device;
-+
-+void wg_noise_init(void);
-+bool wg_noise_handshake_init(struct noise_handshake *handshake,
-+ struct noise_static_identity *static_identity,
-+ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-+ struct wg_peer *peer);
-+void wg_noise_handshake_clear(struct noise_handshake *handshake);
-+static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns)
-+{
-+ atomic64_set(handshake_ns, ktime_get_coarse_boottime_ns() -
-+ (u64)(REKEY_TIMEOUT + 1) * NSEC_PER_SEC);
-+}
-+
-+void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now);
-+struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair);
-+void wg_noise_keypairs_clear(struct noise_keypairs *keypairs);
-+bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs,
-+ struct noise_keypair *received_keypair);
-+void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer);
-+
-+void wg_noise_set_static_identity_private_key(
-+ struct noise_static_identity *static_identity,
-+ const u8 private_key[NOISE_PUBLIC_KEY_LEN]);
-+bool wg_noise_precompute_static_static(struct wg_peer *peer);
-+
-+bool
-+wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
-+ struct noise_handshake *handshake);
-+struct wg_peer *
-+wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src,
-+ struct wg_device *wg);
-+
-+bool wg_noise_handshake_create_response(struct message_handshake_response *dst,
-+ struct noise_handshake *handshake);
-+struct wg_peer *
-+wg_noise_handshake_consume_response(struct message_handshake_response *src,
-+ struct wg_device *wg);
-+
-+bool wg_noise_handshake_begin_session(struct noise_handshake *handshake,
-+ struct noise_keypairs *keypairs);
-+
-+#endif /* _WG_NOISE_H */
---- /dev/null
-+++ b/drivers/net/wireguard/peer.c
-@@ -0,0 +1,240 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "peer.h"
-+#include "device.h"
-+#include "queueing.h"
-+#include "timers.h"
-+#include "peerlookup.h"
-+#include "noise.h"
-+
-+#include <linux/kref.h>
-+#include <linux/lockdep.h>
-+#include <linux/rcupdate.h>
-+#include <linux/list.h>
-+
-+static atomic64_t peer_counter = ATOMIC64_INIT(0);
-+
-+struct wg_peer *wg_peer_create(struct wg_device *wg,
-+ const u8 public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN])
-+{
-+ struct wg_peer *peer;
-+ int ret = -ENOMEM;
-+
-+ lockdep_assert_held(&wg->device_update_lock);
-+
-+ if (wg->num_peers >= MAX_PEERS_PER_DEVICE)
-+ return ERR_PTR(ret);
-+
-+ peer = kzalloc(sizeof(*peer), GFP_KERNEL);
-+ if (unlikely(!peer))
-+ return ERR_PTR(ret);
-+ peer->device = wg;
-+
-+ if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
-+ public_key, preshared_key, peer)) {
-+ ret = -EKEYREJECTED;
-+ goto err_1;
-+ }
-+ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
-+ goto err_1;
-+ if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
-+ MAX_QUEUED_PACKETS))
-+ goto err_2;
-+ if (wg_packet_queue_init(&peer->rx_queue, NULL, false,
-+ MAX_QUEUED_PACKETS))
-+ goto err_3;
-+
-+ peer->internal_id = atomic64_inc_return(&peer_counter);
-+ peer->serial_work_cpu = nr_cpumask_bits;
-+ wg_cookie_init(&peer->latest_cookie);
-+ wg_timers_init(peer);
-+ wg_cookie_checker_precompute_peer_keys(peer);
-+ spin_lock_init(&peer->keypairs.keypair_update_lock);
-+ INIT_WORK(&peer->transmit_handshake_work,
-+ wg_packet_handshake_send_worker);
-+ rwlock_init(&peer->endpoint_lock);
-+ kref_init(&peer->refcount);
-+ skb_queue_head_init(&peer->staged_packet_queue);
-+ wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
-+ set_bit(NAPI_STATE_NO_BUSY_POLL, &peer->napi.state);
-+ netif_napi_add(wg->dev, &peer->napi, wg_packet_rx_poll,
-+ NAPI_POLL_WEIGHT);
-+ napi_enable(&peer->napi);
-+ list_add_tail(&peer->peer_list, &wg->peer_list);
-+ INIT_LIST_HEAD(&peer->allowedips_list);
-+ wg_pubkey_hashtable_add(wg->peer_hashtable, peer);
-+ ++wg->num_peers;
-+ pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id);
-+ return peer;
-+
-+err_3:
-+ wg_packet_queue_free(&peer->tx_queue, false);
-+err_2:
-+ dst_cache_destroy(&peer->endpoint_cache);
-+err_1:
-+ kfree(peer);
-+ return ERR_PTR(ret);
-+}
-+
-+struct wg_peer *wg_peer_get_maybe_zero(struct wg_peer *peer)
-+{
-+ RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(),
-+ "Taking peer reference without holding the RCU read lock");
-+ if (unlikely(!peer || !kref_get_unless_zero(&peer->refcount)))
-+ return NULL;
-+ return peer;
-+}
-+
-+static void peer_make_dead(struct wg_peer *peer)
-+{
-+ /* Remove from configuration-time lookup structures. */
-+ list_del_init(&peer->peer_list);
-+ wg_allowedips_remove_by_peer(&peer->device->peer_allowedips, peer,
-+ &peer->device->device_update_lock);
-+ wg_pubkey_hashtable_remove(peer->device->peer_hashtable, peer);
-+
-+ /* Mark as dead, so that we don't allow jumping contexts after. */
-+ WRITE_ONCE(peer->is_dead, true);
-+
-+ /* The caller must now synchronize_rcu() for this to take effect. */
-+}
-+
-+static void peer_remove_after_dead(struct wg_peer *peer)
-+{
-+ WARN_ON(!peer->is_dead);
-+
-+ /* No more keypairs can be created for this peer, since is_dead protects
-+ * add_new_keypair, so we can now destroy existing ones.
-+ */
-+ wg_noise_keypairs_clear(&peer->keypairs);
-+
-+ /* Destroy all ongoing timers that were in-flight at the beginning of
-+ * this function.
-+ */
-+ wg_timers_stop(peer);
-+
-+ /* The transition between packet encryption/decryption queues isn't
-+ * guarded by is_dead, but each reference's life is strictly bounded by
-+ * two generations: once for parallel crypto and once for serial
-+ * ingestion, so we can simply flush twice, and be sure that we no
-+ * longer have references inside these queues.
-+ */
-+
-+ /* a) For encrypt/decrypt. */
-+ flush_workqueue(peer->device->packet_crypt_wq);
-+ /* b.1) For send (but not receive, since that's napi). */
-+ flush_workqueue(peer->device->packet_crypt_wq);
-+ /* b.2.1) For receive (but not send, since that's wq). */
-+ napi_disable(&peer->napi);
-+ /* b.2.1) It's now safe to remove the napi struct, which must be done
-+ * here from process context.
-+ */
-+ netif_napi_del(&peer->napi);
-+
-+ /* Ensure any workstructs we own (like transmit_handshake_work or
-+ * clear_peer_work) no longer are in use.
-+ */
-+ flush_workqueue(peer->device->handshake_send_wq);
-+
-+ /* After the above flushes, a peer might still be active in a few
-+ * different contexts: 1) from xmit(), before hitting is_dead and
-+ * returning, 2) from wg_packet_consume_data(), before hitting is_dead
-+ * and returning, 3) from wg_receive_handshake_packet() after a point
-+ * where it has processed an incoming handshake packet, but where
-+ * all calls to pass it off to timers fails because of is_dead. We won't
-+ * have new references in (1) eventually, because we're removed from
-+ * allowedips; we won't have new references in (2) eventually, because
-+ * wg_index_hashtable_lookup will always return NULL, since we removed
-+ * all existing keypairs and no more can be created; we won't have new
-+ * references in (3) eventually, because we're removed from the pubkey
-+ * hash table, which allows for a maximum of one handshake response,
-+ * via the still-uncleared index hashtable entry, but not more than one,
-+ * and in wg_cookie_message_consume, the lookup eventually gets a peer
-+ * with a refcount of zero, so no new reference is taken.
-+ */
-+
-+ --peer->device->num_peers;
-+ wg_peer_put(peer);
-+}
-+
-+/* We have a separate "remove" function make sure that all active places where
-+ * a peer is currently operating will eventually come to an end and not pass
-+ * their reference onto another context.
-+ */
-+void wg_peer_remove(struct wg_peer *peer)
-+{
-+ if (unlikely(!peer))
-+ return;
-+ lockdep_assert_held(&peer->device->device_update_lock);
-+
-+ peer_make_dead(peer);
-+ synchronize_rcu();
-+ peer_remove_after_dead(peer);
-+}
-+
-+void wg_peer_remove_all(struct wg_device *wg)
-+{
-+ struct wg_peer *peer, *temp;
-+ LIST_HEAD(dead_peers);
-+
-+ lockdep_assert_held(&wg->device_update_lock);
-+
-+ /* Avoid having to traverse individually for each one. */
-+ wg_allowedips_free(&wg->peer_allowedips, &wg->device_update_lock);
-+
-+ list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) {
-+ peer_make_dead(peer);
-+ list_add_tail(&peer->peer_list, &dead_peers);
-+ }
-+ synchronize_rcu();
-+ list_for_each_entry_safe(peer, temp, &dead_peers, peer_list)
-+ peer_remove_after_dead(peer);
-+}
-+
-+static void rcu_release(struct rcu_head *rcu)
-+{
-+ struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu);
-+
-+ dst_cache_destroy(&peer->endpoint_cache);
-+ wg_packet_queue_free(&peer->rx_queue, false);
-+ wg_packet_queue_free(&peer->tx_queue, false);
-+
-+ /* The final zeroing takes care of clearing any remaining handshake key
-+ * material and other potentially sensitive information.
-+ */
-+ kzfree(peer);
-+}
-+
-+static void kref_release(struct kref *refcount)
-+{
-+ struct wg_peer *peer = container_of(refcount, struct wg_peer, refcount);
-+
-+ pr_debug("%s: Peer %llu (%pISpfsc) destroyed\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+
-+ /* Remove ourself from dynamic runtime lookup structures, now that the
-+ * last reference is gone.
-+ */
-+ wg_index_hashtable_remove(peer->device->index_hashtable,
-+ &peer->handshake.entry);
-+
-+ /* Remove any lingering packets that didn't have a chance to be
-+ * transmitted.
-+ */
-+ wg_packet_purge_staged_packets(peer);
-+
-+ /* Free the memory used. */
-+ call_rcu(&peer->rcu, rcu_release);
-+}
-+
-+void wg_peer_put(struct wg_peer *peer)
-+{
-+ if (unlikely(!peer))
-+ return;
-+ kref_put(&peer->refcount, kref_release);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/peer.h
-@@ -0,0 +1,83 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_PEER_H
-+#define _WG_PEER_H
-+
-+#include "device.h"
-+#include "noise.h"
-+#include "cookie.h"
-+
-+#include <linux/types.h>
-+#include <linux/netfilter.h>
-+#include <linux/spinlock.h>
-+#include <linux/kref.h>
-+#include <net/dst_cache.h>
-+
-+struct wg_device;
-+
-+struct endpoint {
-+ union {
-+ struct sockaddr addr;
-+ struct sockaddr_in addr4;
-+ struct sockaddr_in6 addr6;
-+ };
-+ union {
-+ struct {
-+ struct in_addr src4;
-+ /* Essentially the same as addr6->scope_id */
-+ int src_if4;
-+ };
-+ struct in6_addr src6;
-+ };
-+};
-+
-+struct wg_peer {
-+ struct wg_device *device;
-+ struct crypt_queue tx_queue, rx_queue;
-+ struct sk_buff_head staged_packet_queue;
-+ int serial_work_cpu;
-+ struct noise_keypairs keypairs;
-+ struct endpoint endpoint;
-+ struct dst_cache endpoint_cache;
-+ rwlock_t endpoint_lock;
-+ struct noise_handshake handshake;
-+ atomic64_t last_sent_handshake;
-+ struct work_struct transmit_handshake_work, clear_peer_work;
-+ struct cookie latest_cookie;
-+ struct hlist_node pubkey_hash;
-+ u64 rx_bytes, tx_bytes;
-+ struct timer_list timer_retransmit_handshake, timer_send_keepalive;
-+ struct timer_list timer_new_handshake, timer_zero_key_material;
-+ struct timer_list timer_persistent_keepalive;
-+ unsigned int timer_handshake_attempts;
-+ u16 persistent_keepalive_interval;
-+ bool timer_need_another_keepalive;
-+ bool sent_lastminute_handshake;
-+ struct timespec64 walltime_last_handshake;
-+ struct kref refcount;
-+ struct rcu_head rcu;
-+ struct list_head peer_list;
-+ struct list_head allowedips_list;
-+ u64 internal_id;
-+ struct napi_struct napi;
-+ bool is_dead;
-+};
-+
-+struct wg_peer *wg_peer_create(struct wg_device *wg,
-+ const u8 public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]);
-+
-+struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer);
-+static inline struct wg_peer *wg_peer_get(struct wg_peer *peer)
-+{
-+ kref_get(&peer->refcount);
-+ return peer;
-+}
-+void wg_peer_put(struct wg_peer *peer);
-+void wg_peer_remove(struct wg_peer *peer);
-+void wg_peer_remove_all(struct wg_device *wg);
-+
-+#endif /* _WG_PEER_H */
---- /dev/null
-+++ b/drivers/net/wireguard/peerlookup.c
-@@ -0,0 +1,221 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "peerlookup.h"
-+#include "peer.h"
-+#include "noise.h"
-+
-+static struct hlist_head *pubkey_bucket(struct pubkey_hashtable *table,
-+ const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
-+{
-+ /* siphash gives us a secure 64bit number based on a random key. Since
-+ * the bits are uniformly distributed, we can then mask off to get the
-+ * bits we need.
-+ */
-+ const u64 hash = siphash(pubkey, NOISE_PUBLIC_KEY_LEN, &table->key);
-+
-+ return &table->hashtable[hash & (HASH_SIZE(table->hashtable) - 1)];
-+}
-+
-+struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void)
-+{
-+ struct pubkey_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
-+
-+ if (!table)
-+ return NULL;
-+
-+ get_random_bytes(&table->key, sizeof(table->key));
-+ hash_init(table->hashtable);
-+ mutex_init(&table->lock);
-+ return table;
-+}
-+
-+void wg_pubkey_hashtable_add(struct pubkey_hashtable *table,
-+ struct wg_peer *peer)
-+{
-+ mutex_lock(&table->lock);
-+ hlist_add_head_rcu(&peer->pubkey_hash,
-+ pubkey_bucket(table, peer->handshake.remote_static));
-+ mutex_unlock(&table->lock);
-+}
-+
-+void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table,
-+ struct wg_peer *peer)
-+{
-+ mutex_lock(&table->lock);
-+ hlist_del_init_rcu(&peer->pubkey_hash);
-+ mutex_unlock(&table->lock);
-+}
-+
-+/* Returns a strong reference to a peer */
-+struct wg_peer *
-+wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table,
-+ const u8 pubkey[NOISE_PUBLIC_KEY_LEN])
-+{
-+ struct wg_peer *iter_peer, *peer = NULL;
-+
-+ rcu_read_lock_bh();
-+ hlist_for_each_entry_rcu_bh(iter_peer, pubkey_bucket(table, pubkey),
-+ pubkey_hash) {
-+ if (!memcmp(pubkey, iter_peer->handshake.remote_static,
-+ NOISE_PUBLIC_KEY_LEN)) {
-+ peer = iter_peer;
-+ break;
-+ }
-+ }
-+ peer = wg_peer_get_maybe_zero(peer);
-+ rcu_read_unlock_bh();
-+ return peer;
-+}
-+
-+static struct hlist_head *index_bucket(struct index_hashtable *table,
-+ const __le32 index)
-+{
-+ /* Since the indices are random and thus all bits are uniformly
-+ * distributed, we can find its bucket simply by masking.
-+ */
-+ return &table->hashtable[(__force u32)index &
-+ (HASH_SIZE(table->hashtable) - 1)];
-+}
-+
-+struct index_hashtable *wg_index_hashtable_alloc(void)
-+{
-+ struct index_hashtable *table = kvmalloc(sizeof(*table), GFP_KERNEL);
-+
-+ if (!table)
-+ return NULL;
-+
-+ hash_init(table->hashtable);
-+ spin_lock_init(&table->lock);
-+ return table;
-+}
-+
-+/* At the moment, we limit ourselves to 2^20 total peers, which generally might
-+ * amount to 2^20*3 items in this hashtable. The algorithm below works by
-+ * picking a random number and testing it. We can see that these limits mean we
-+ * usually succeed pretty quickly:
-+ *
-+ * >>> def calculation(tries, size):
-+ * ... return (size / 2**32)**(tries - 1) * (1 - (size / 2**32))
-+ * ...
-+ * >>> calculation(1, 2**20 * 3)
-+ * 0.999267578125
-+ * >>> calculation(2, 2**20 * 3)
-+ * 0.0007318854331970215
-+ * >>> calculation(3, 2**20 * 3)
-+ * 5.360489012673497e-07
-+ * >>> calculation(4, 2**20 * 3)
-+ * 3.9261394135792216e-10
-+ *
-+ * At the moment, we don't do any masking, so this algorithm isn't exactly
-+ * constant time in either the random guessing or in the hash list lookup. We
-+ * could require a minimum of 3 tries, which would successfully mask the
-+ * guessing. this would not, however, help with the growing hash lengths, which
-+ * is another thing to consider moving forward.
-+ */
-+
-+__le32 wg_index_hashtable_insert(struct index_hashtable *table,
-+ struct index_hashtable_entry *entry)
-+{
-+ struct index_hashtable_entry *existing_entry;
-+
-+ spin_lock_bh(&table->lock);
-+ hlist_del_init_rcu(&entry->index_hash);
-+ spin_unlock_bh(&table->lock);
-+
-+ rcu_read_lock_bh();
-+
-+search_unused_slot:
-+ /* First we try to find an unused slot, randomly, while unlocked. */
-+ entry->index = (__force __le32)get_random_u32();
-+ hlist_for_each_entry_rcu_bh(existing_entry,
-+ index_bucket(table, entry->index),
-+ index_hash) {
-+ if (existing_entry->index == entry->index)
-+ /* If it's already in use, we continue searching. */
-+ goto search_unused_slot;
-+ }
-+
-+ /* Once we've found an unused slot, we lock it, and then double-check
-+ * that nobody else stole it from us.
-+ */
-+ spin_lock_bh(&table->lock);
-+ hlist_for_each_entry_rcu_bh(existing_entry,
-+ index_bucket(table, entry->index),
-+ index_hash) {
-+ if (existing_entry->index == entry->index) {
-+ spin_unlock_bh(&table->lock);
-+ /* If it was stolen, we start over. */
-+ goto search_unused_slot;
-+ }
-+ }
-+ /* Otherwise, we know we have it exclusively (since we're locked),
-+ * so we insert.
-+ */
-+ hlist_add_head_rcu(&entry->index_hash,
-+ index_bucket(table, entry->index));
-+ spin_unlock_bh(&table->lock);
-+
-+ rcu_read_unlock_bh();
-+
-+ return entry->index;
-+}
-+
-+bool wg_index_hashtable_replace(struct index_hashtable *table,
-+ struct index_hashtable_entry *old,
-+ struct index_hashtable_entry *new)
-+{
-+ if (unlikely(hlist_unhashed(&old->index_hash)))
-+ return false;
-+ spin_lock_bh(&table->lock);
-+ new->index = old->index;
-+ hlist_replace_rcu(&old->index_hash, &new->index_hash);
-+
-+ /* Calling init here NULLs out index_hash, and in fact after this
-+ * function returns, it's theoretically possible for this to get
-+ * reinserted elsewhere. That means the RCU lookup below might either
-+ * terminate early or jump between buckets, in which case the packet
-+ * simply gets dropped, which isn't terrible.
-+ */
-+ INIT_HLIST_NODE(&old->index_hash);
-+ spin_unlock_bh(&table->lock);
-+ return true;
-+}
-+
-+void wg_index_hashtable_remove(struct index_hashtable *table,
-+ struct index_hashtable_entry *entry)
-+{
-+ spin_lock_bh(&table->lock);
-+ hlist_del_init_rcu(&entry->index_hash);
-+ spin_unlock_bh(&table->lock);
-+}
-+
-+/* Returns a strong reference to a entry->peer */
-+struct index_hashtable_entry *
-+wg_index_hashtable_lookup(struct index_hashtable *table,
-+ const enum index_hashtable_type type_mask,
-+ const __le32 index, struct wg_peer **peer)
-+{
-+ struct index_hashtable_entry *iter_entry, *entry = NULL;
-+
-+ rcu_read_lock_bh();
-+ hlist_for_each_entry_rcu_bh(iter_entry, index_bucket(table, index),
-+ index_hash) {
-+ if (iter_entry->index == index) {
-+ if (likely(iter_entry->type & type_mask))
-+ entry = iter_entry;
-+ break;
-+ }
-+ }
-+ if (likely(entry)) {
-+ entry->peer = wg_peer_get_maybe_zero(entry->peer);
-+ if (likely(entry->peer))
-+ *peer = entry->peer;
-+ else
-+ entry = NULL;
-+ }
-+ rcu_read_unlock_bh();
-+ return entry;
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/peerlookup.h
-@@ -0,0 +1,64 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_PEERLOOKUP_H
-+#define _WG_PEERLOOKUP_H
-+
-+#include "messages.h"
-+
-+#include <linux/hashtable.h>
-+#include <linux/mutex.h>
-+#include <linux/siphash.h>
-+
-+struct wg_peer;
-+
-+struct pubkey_hashtable {
-+ /* TODO: move to rhashtable */
-+ DECLARE_HASHTABLE(hashtable, 11);
-+ siphash_key_t key;
-+ struct mutex lock;
-+};
-+
-+struct pubkey_hashtable *wg_pubkey_hashtable_alloc(void);
-+void wg_pubkey_hashtable_add(struct pubkey_hashtable *table,
-+ struct wg_peer *peer);
-+void wg_pubkey_hashtable_remove(struct pubkey_hashtable *table,
-+ struct wg_peer *peer);
-+struct wg_peer *
-+wg_pubkey_hashtable_lookup(struct pubkey_hashtable *table,
-+ const u8 pubkey[NOISE_PUBLIC_KEY_LEN]);
-+
-+struct index_hashtable {
-+ /* TODO: move to rhashtable */
-+ DECLARE_HASHTABLE(hashtable, 13);
-+ spinlock_t lock;
-+};
-+
-+enum index_hashtable_type {
-+ INDEX_HASHTABLE_HANDSHAKE = 1U << 0,
-+ INDEX_HASHTABLE_KEYPAIR = 1U << 1
-+};
-+
-+struct index_hashtable_entry {
-+ struct wg_peer *peer;
-+ struct hlist_node index_hash;
-+ enum index_hashtable_type type;
-+ __le32 index;
-+};
-+
-+struct index_hashtable *wg_index_hashtable_alloc(void);
-+__le32 wg_index_hashtable_insert(struct index_hashtable *table,
-+ struct index_hashtable_entry *entry);
-+bool wg_index_hashtable_replace(struct index_hashtable *table,
-+ struct index_hashtable_entry *old,
-+ struct index_hashtable_entry *new);
-+void wg_index_hashtable_remove(struct index_hashtable *table,
-+ struct index_hashtable_entry *entry);
-+struct index_hashtable_entry *
-+wg_index_hashtable_lookup(struct index_hashtable *table,
-+ const enum index_hashtable_type type_mask,
-+ const __le32 index, struct wg_peer **peer);
-+
-+#endif /* _WG_PEERLOOKUP_H */
---- /dev/null
-+++ b/drivers/net/wireguard/queueing.c
-@@ -0,0 +1,53 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "queueing.h"
-+
-+struct multicore_worker __percpu *
-+wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
-+{
-+ int cpu;
-+ struct multicore_worker __percpu *worker =
-+ alloc_percpu(struct multicore_worker);
-+
-+ if (!worker)
-+ return NULL;
-+
-+ for_each_possible_cpu(cpu) {
-+ per_cpu_ptr(worker, cpu)->ptr = ptr;
-+ INIT_WORK(&per_cpu_ptr(worker, cpu)->work, function);
-+ }
-+ return worker;
-+}
-+
-+int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-+ bool multicore, unsigned int len)
-+{
-+ int ret;
-+
-+ memset(queue, 0, sizeof(*queue));
-+ ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
-+ if (ret)
-+ return ret;
-+ if (function) {
-+ if (multicore) {
-+ queue->worker = wg_packet_percpu_multicore_worker_alloc(
-+ function, queue);
-+ if (!queue->worker)
-+ return -ENOMEM;
-+ } else {
-+ INIT_WORK(&queue->work, function);
-+ }
-+ }
-+ return 0;
-+}
-+
-+void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
-+{
-+ if (multicore)
-+ free_percpu(queue->worker);
-+ WARN_ON(!__ptr_ring_empty(&queue->ring));
-+ ptr_ring_cleanup(&queue->ring, NULL);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/queueing.h
-@@ -0,0 +1,197 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_QUEUEING_H
-+#define _WG_QUEUEING_H
-+
-+#include "peer.h"
-+#include <linux/types.h>
-+#include <linux/skbuff.h>
-+#include <linux/ip.h>
-+#include <linux/ipv6.h>
-+
-+struct wg_device;
-+struct wg_peer;
-+struct multicore_worker;
-+struct crypt_queue;
-+struct sk_buff;
-+
-+/* queueing.c APIs: */
-+int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-+ bool multicore, unsigned int len);
-+void wg_packet_queue_free(struct crypt_queue *queue, bool multicore);
-+struct multicore_worker __percpu *
-+wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
-+
-+/* receive.c APIs: */
-+void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb);
-+void wg_packet_handshake_receive_worker(struct work_struct *work);
-+/* NAPI poll function: */
-+int wg_packet_rx_poll(struct napi_struct *napi, int budget);
-+/* Workqueue worker: */
-+void wg_packet_decrypt_worker(struct work_struct *work);
-+
-+/* send.c APIs: */
-+void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer,
-+ bool is_retry);
-+void wg_packet_send_handshake_response(struct wg_peer *peer);
-+void wg_packet_send_handshake_cookie(struct wg_device *wg,
-+ struct sk_buff *initiating_skb,
-+ __le32 sender_index);
-+void wg_packet_send_keepalive(struct wg_peer *peer);
-+void wg_packet_purge_staged_packets(struct wg_peer *peer);
-+void wg_packet_send_staged_packets(struct wg_peer *peer);
-+/* Workqueue workers: */
-+void wg_packet_handshake_send_worker(struct work_struct *work);
-+void wg_packet_tx_worker(struct work_struct *work);
-+void wg_packet_encrypt_worker(struct work_struct *work);
-+
-+enum packet_state {
-+ PACKET_STATE_UNCRYPTED,
-+ PACKET_STATE_CRYPTED,
-+ PACKET_STATE_DEAD
-+};
-+
-+struct packet_cb {
-+ u64 nonce;
-+ struct noise_keypair *keypair;
-+ atomic_t state;
-+ u32 mtu;
-+ u8 ds;
-+};
-+
-+#define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb))
-+#define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
-+
-+/* Returns either the correct skb->protocol value, or 0 if invalid. */
-+static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb)
-+{
-+ if (skb_network_header(skb) >= skb->head &&
-+ (skb_network_header(skb) + sizeof(struct iphdr)) <=
-+ skb_tail_pointer(skb) &&
-+ ip_hdr(skb)->version == 4)
-+ return htons(ETH_P_IP);
-+ if (skb_network_header(skb) >= skb->head &&
-+ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <=
-+ skb_tail_pointer(skb) &&
-+ ipv6_hdr(skb)->version == 6)
-+ return htons(ETH_P_IPV6);
-+ return 0;
-+}
-+
-+static inline void wg_reset_packet(struct sk_buff *skb)
-+{
-+ const int pfmemalloc = skb->pfmemalloc;
-+
-+ skb_scrub_packet(skb, true);
-+ memset(&skb->headers_start, 0,
-+ offsetof(struct sk_buff, headers_end) -
-+ offsetof(struct sk_buff, headers_start));
-+ skb->pfmemalloc = pfmemalloc;
-+ skb->queue_mapping = 0;
-+ skb->nohdr = 0;
-+ skb->peeked = 0;
-+ skb->mac_len = 0;
-+ skb->dev = NULL;
-+#ifdef CONFIG_NET_SCHED
-+ skb->tc_index = 0;
-+#endif
-+ skb_reset_redirect(skb);
-+ skb->hdr_len = skb_headroom(skb);
-+ skb_reset_mac_header(skb);
-+ skb_reset_network_header(skb);
-+ skb_reset_transport_header(skb);
-+ skb_probe_transport_header(skb);
-+ skb_reset_inner_headers(skb);
-+}
-+
-+static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id)
-+{
-+ unsigned int cpu = *stored_cpu, cpu_index, i;
-+
-+ if (unlikely(cpu == nr_cpumask_bits ||
-+ !cpumask_test_cpu(cpu, cpu_online_mask))) {
-+ cpu_index = id % cpumask_weight(cpu_online_mask);
-+ cpu = cpumask_first(cpu_online_mask);
-+ for (i = 0; i < cpu_index; ++i)
-+ cpu = cpumask_next(cpu, cpu_online_mask);
-+ *stored_cpu = cpu;
-+ }
-+ return cpu;
-+}
-+
-+/* This function is racy, in the sense that next is unlocked, so it could return
-+ * the same CPU twice. A race-free version of this would be to instead store an
-+ * atomic sequence number, do an increment-and-return, and then iterate through
-+ * every possible CPU until we get to that index -- choose_cpu. However that's
-+ * a bit slower, and it doesn't seem like this potential race actually
-+ * introduces any performance loss, so we live with it.
-+ */
-+static inline int wg_cpumask_next_online(int *next)
-+{
-+ int cpu = *next;
-+
-+ while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask)))
-+ cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
-+ *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
-+ return cpu;
-+}
-+
-+static inline int wg_queue_enqueue_per_device_and_peer(
-+ struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
-+ struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
-+{
-+ int cpu;
-+
-+ atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED);
-+ /* We first queue this up for the peer ingestion, but the consumer
-+ * will wait for the state to change to CRYPTED or DEAD before.
-+ */
-+ if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
-+ return -ENOSPC;
-+ /* Then we queue it up in the device queue, which consumes the
-+ * packet as soon as it can.
-+ */
-+ cpu = wg_cpumask_next_online(next_cpu);
-+ if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb)))
-+ return -EPIPE;
-+ queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work);
-+ return 0;
-+}
-+
-+static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
-+ struct sk_buff *skb,
-+ enum packet_state state)
-+{
-+ /* We take a reference, because as soon as we call atomic_set, the
-+ * peer can be freed from below us.
-+ */
-+ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
-+
-+ atomic_set_release(&PACKET_CB(skb)->state, state);
-+ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
-+ peer->internal_id),
-+ peer->device->packet_crypt_wq, &queue->work);
-+ wg_peer_put(peer);
-+}
-+
-+static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb,
-+ enum packet_state state)
-+{
-+ /* We take a reference, because as soon as we call atomic_set, the
-+ * peer can be freed from below us.
-+ */
-+ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
-+
-+ atomic_set_release(&PACKET_CB(skb)->state, state);
-+ napi_schedule(&peer->napi);
-+ wg_peer_put(peer);
-+}
-+
-+#ifdef DEBUG
-+bool wg_packet_counter_selftest(void);
-+#endif
-+
-+#endif /* _WG_QUEUEING_H */
---- /dev/null
-+++ b/drivers/net/wireguard/ratelimiter.c
-@@ -0,0 +1,223 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "ratelimiter.h"
-+#include <linux/siphash.h>
-+#include <linux/mm.h>
-+#include <linux/slab.h>
-+#include <net/ip.h>
-+
-+static struct kmem_cache *entry_cache;
-+static hsiphash_key_t key;
-+static spinlock_t table_lock = __SPIN_LOCK_UNLOCKED("ratelimiter_table_lock");
-+static DEFINE_MUTEX(init_lock);
-+static u64 init_refcnt; /* Protected by init_lock, hence not atomic. */
-+static atomic_t total_entries = ATOMIC_INIT(0);
-+static unsigned int max_entries, table_size;
-+static void wg_ratelimiter_gc_entries(struct work_struct *);
-+static DECLARE_DEFERRABLE_WORK(gc_work, wg_ratelimiter_gc_entries);
-+static struct hlist_head *table_v4;
-+#if IS_ENABLED(CONFIG_IPV6)
-+static struct hlist_head *table_v6;
-+#endif
-+
-+struct ratelimiter_entry {
-+ u64 last_time_ns, tokens, ip;
-+ void *net;
-+ spinlock_t lock;
-+ struct hlist_node hash;
-+ struct rcu_head rcu;
-+};
-+
-+enum {
-+ PACKETS_PER_SECOND = 20,
-+ PACKETS_BURSTABLE = 5,
-+ PACKET_COST = NSEC_PER_SEC / PACKETS_PER_SECOND,
-+ TOKEN_MAX = PACKET_COST * PACKETS_BURSTABLE
-+};
-+
-+static void entry_free(struct rcu_head *rcu)
-+{
-+ kmem_cache_free(entry_cache,
-+ container_of(rcu, struct ratelimiter_entry, rcu));
-+ atomic_dec(&total_entries);
-+}
-+
-+static void entry_uninit(struct ratelimiter_entry *entry)
-+{
-+ hlist_del_rcu(&entry->hash);
-+ call_rcu(&entry->rcu, entry_free);
-+}
-+
-+/* Calling this function with a NULL work uninits all entries. */
-+static void wg_ratelimiter_gc_entries(struct work_struct *work)
-+{
-+ const u64 now = ktime_get_coarse_boottime_ns();
-+ struct ratelimiter_entry *entry;
-+ struct hlist_node *temp;
-+ unsigned int i;
-+
-+ for (i = 0; i < table_size; ++i) {
-+ spin_lock(&table_lock);
-+ hlist_for_each_entry_safe(entry, temp, &table_v4[i], hash) {
-+ if (unlikely(!work) ||
-+ now - entry->last_time_ns > NSEC_PER_SEC)
-+ entry_uninit(entry);
-+ }
-+#if IS_ENABLED(CONFIG_IPV6)
-+ hlist_for_each_entry_safe(entry, temp, &table_v6[i], hash) {
-+ if (unlikely(!work) ||
-+ now - entry->last_time_ns > NSEC_PER_SEC)
-+ entry_uninit(entry);
-+ }
-+#endif
-+ spin_unlock(&table_lock);
-+ if (likely(work))
-+ cond_resched();
-+ }
-+ if (likely(work))
-+ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ);
-+}
-+
-+bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net)
-+{
-+ /* We only take the bottom half of the net pointer, so that we can hash
-+ * 3 words in the end. This way, siphash's len param fits into the final
-+ * u32, and we don't incur an extra round.
-+ */
-+ const u32 net_word = (unsigned long)net;
-+ struct ratelimiter_entry *entry;
-+ struct hlist_head *bucket;
-+ u64 ip;
-+
-+ if (skb->protocol == htons(ETH_P_IP)) {
-+ ip = (u64 __force)ip_hdr(skb)->saddr;
-+ bucket = &table_v4[hsiphash_2u32(net_word, ip, &key) &
-+ (table_size - 1)];
-+ }
-+#if IS_ENABLED(CONFIG_IPV6)
-+ else if (skb->protocol == htons(ETH_P_IPV6)) {
-+ /* Only use 64 bits, so as to ratelimit the whole /64. */
-+ memcpy(&ip, &ipv6_hdr(skb)->saddr, sizeof(ip));
-+ bucket = &table_v6[hsiphash_3u32(net_word, ip >> 32, ip, &key) &
-+ (table_size - 1)];
-+ }
-+#endif
-+ else
-+ return false;
-+ rcu_read_lock();
-+ hlist_for_each_entry_rcu(entry, bucket, hash) {
-+ if (entry->net == net && entry->ip == ip) {
-+ u64 now, tokens;
-+ bool ret;
-+ /* Quasi-inspired by nft_limit.c, but this is actually a
-+ * slightly different algorithm. Namely, we incorporate
-+ * the burst as part of the maximum tokens, rather than
-+ * as part of the rate.
-+ */
-+ spin_lock(&entry->lock);
-+ now = ktime_get_coarse_boottime_ns();
-+ tokens = min_t(u64, TOKEN_MAX,
-+ entry->tokens + now -
-+ entry->last_time_ns);
-+ entry->last_time_ns = now;
-+ ret = tokens >= PACKET_COST;
-+ entry->tokens = ret ? tokens - PACKET_COST : tokens;
-+ spin_unlock(&entry->lock);
-+ rcu_read_unlock();
-+ return ret;
-+ }
-+ }
-+ rcu_read_unlock();
-+
-+ if (atomic_inc_return(&total_entries) > max_entries)
-+ goto err_oom;
-+
-+ entry = kmem_cache_alloc(entry_cache, GFP_KERNEL);
-+ if (unlikely(!entry))
-+ goto err_oom;
-+
-+ entry->net = net;
-+ entry->ip = ip;
-+ INIT_HLIST_NODE(&entry->hash);
-+ spin_lock_init(&entry->lock);
-+ entry->last_time_ns = ktime_get_coarse_boottime_ns();
-+ entry->tokens = TOKEN_MAX - PACKET_COST;
-+ spin_lock(&table_lock);
-+ hlist_add_head_rcu(&entry->hash, bucket);
-+ spin_unlock(&table_lock);
-+ return true;
-+
-+err_oom:
-+ atomic_dec(&total_entries);
-+ return false;
-+}
-+
-+int wg_ratelimiter_init(void)
-+{
-+ mutex_lock(&init_lock);
-+ if (++init_refcnt != 1)
-+ goto out;
-+
-+ entry_cache = KMEM_CACHE(ratelimiter_entry, 0);
-+ if (!entry_cache)
-+ goto err;
-+
-+ /* xt_hashlimit.c uses a slightly different algorithm for ratelimiting,
-+ * but what it shares in common is that it uses a massive hashtable. So,
-+ * we borrow their wisdom about good table sizes on different systems
-+ * dependent on RAM. This calculation here comes from there.
-+ */
-+ table_size = (totalram_pages() > (1U << 30) / PAGE_SIZE) ? 8192 :
-+ max_t(unsigned long, 16, roundup_pow_of_two(
-+ (totalram_pages() << PAGE_SHIFT) /
-+ (1U << 14) / sizeof(struct hlist_head)));
-+ max_entries = table_size * 8;
-+
-+ table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL);
-+ if (unlikely(!table_v4))
-+ goto err_kmemcache;
-+
-+#if IS_ENABLED(CONFIG_IPV6)
-+ table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL);
-+ if (unlikely(!table_v6)) {
-+ kvfree(table_v4);
-+ goto err_kmemcache;
-+ }
-+#endif
-+
-+ queue_delayed_work(system_power_efficient_wq, &gc_work, HZ);
-+ get_random_bytes(&key, sizeof(key));
-+out:
-+ mutex_unlock(&init_lock);
-+ return 0;
-+
-+err_kmemcache:
-+ kmem_cache_destroy(entry_cache);
-+err:
-+ --init_refcnt;
-+ mutex_unlock(&init_lock);
-+ return -ENOMEM;
-+}
-+
-+void wg_ratelimiter_uninit(void)
-+{
-+ mutex_lock(&init_lock);
-+ if (!init_refcnt || --init_refcnt)
-+ goto out;
-+
-+ cancel_delayed_work_sync(&gc_work);
-+ wg_ratelimiter_gc_entries(NULL);
-+ rcu_barrier();
-+ kvfree(table_v4);
-+#if IS_ENABLED(CONFIG_IPV6)
-+ kvfree(table_v6);
-+#endif
-+ kmem_cache_destroy(entry_cache);
-+out:
-+ mutex_unlock(&init_lock);
-+}
-+
-+#include "selftest/ratelimiter.c"
---- /dev/null
-+++ b/drivers/net/wireguard/ratelimiter.h
-@@ -0,0 +1,19 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_RATELIMITER_H
-+#define _WG_RATELIMITER_H
-+
-+#include <linux/skbuff.h>
-+
-+int wg_ratelimiter_init(void);
-+void wg_ratelimiter_uninit(void);
-+bool wg_ratelimiter_allow(struct sk_buff *skb, struct net *net);
-+
-+#ifdef DEBUG
-+bool wg_ratelimiter_selftest(void);
-+#endif
-+
-+#endif /* _WG_RATELIMITER_H */
---- /dev/null
-+++ b/drivers/net/wireguard/receive.c
-@@ -0,0 +1,595 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "queueing.h"
-+#include "device.h"
-+#include "peer.h"
-+#include "timers.h"
-+#include "messages.h"
-+#include "cookie.h"
-+#include "socket.h"
-+
-+#include <linux/ip.h>
-+#include <linux/ipv6.h>
-+#include <linux/udp.h>
-+#include <net/ip_tunnels.h>
-+
-+/* Must be called with bh disabled. */
-+static void update_rx_stats(struct wg_peer *peer, size_t len)
-+{
-+ struct pcpu_sw_netstats *tstats =
-+ get_cpu_ptr(peer->device->dev->tstats);
-+
-+ u64_stats_update_begin(&tstats->syncp);
-+ ++tstats->rx_packets;
-+ tstats->rx_bytes += len;
-+ peer->rx_bytes += len;
-+ u64_stats_update_end(&tstats->syncp);
-+ put_cpu_ptr(tstats);
-+}
-+
-+#define SKB_TYPE_LE32(skb) (((struct message_header *)(skb)->data)->type)
-+
-+static size_t validate_header_len(struct sk_buff *skb)
-+{
-+ if (unlikely(skb->len < sizeof(struct message_header)))
-+ return 0;
-+ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_DATA) &&
-+ skb->len >= MESSAGE_MINIMUM_LENGTH)
-+ return sizeof(struct message_data);
-+ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION) &&
-+ skb->len == sizeof(struct message_handshake_initiation))
-+ return sizeof(struct message_handshake_initiation);
-+ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE) &&
-+ skb->len == sizeof(struct message_handshake_response))
-+ return sizeof(struct message_handshake_response);
-+ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE) &&
-+ skb->len == sizeof(struct message_handshake_cookie))
-+ return sizeof(struct message_handshake_cookie);
-+ return 0;
-+}
-+
-+static int prepare_skb_header(struct sk_buff *skb, struct wg_device *wg)
-+{
-+ size_t data_offset, data_len, header_len;
-+ struct udphdr *udp;
-+
-+ if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol ||
-+ skb_transport_header(skb) < skb->head ||
-+ (skb_transport_header(skb) + sizeof(struct udphdr)) >
-+ skb_tail_pointer(skb)))
-+ return -EINVAL; /* Bogus IP header */
-+ udp = udp_hdr(skb);
-+ data_offset = (u8 *)udp - skb->data;
-+ if (unlikely(data_offset > U16_MAX ||
-+ data_offset + sizeof(struct udphdr) > skb->len))
-+ /* Packet has offset at impossible location or isn't big enough
-+ * to have UDP fields.
-+ */
-+ return -EINVAL;
-+ data_len = ntohs(udp->len);
-+ if (unlikely(data_len < sizeof(struct udphdr) ||
-+ data_len > skb->len - data_offset))
-+ /* UDP packet is reporting too small of a size or lying about
-+ * its size.
-+ */
-+ return -EINVAL;
-+ data_len -= sizeof(struct udphdr);
-+ data_offset = (u8 *)udp + sizeof(struct udphdr) - skb->data;
-+ if (unlikely(!pskb_may_pull(skb,
-+ data_offset + sizeof(struct message_header)) ||
-+ pskb_trim(skb, data_len + data_offset) < 0))
-+ return -EINVAL;
-+ skb_pull(skb, data_offset);
-+ if (unlikely(skb->len != data_len))
-+ /* Final len does not agree with calculated len */
-+ return -EINVAL;
-+ header_len = validate_header_len(skb);
-+ if (unlikely(!header_len))
-+ return -EINVAL;
-+ __skb_push(skb, data_offset);
-+ if (unlikely(!pskb_may_pull(skb, data_offset + header_len)))
-+ return -EINVAL;
-+ __skb_pull(skb, data_offset);
-+ return 0;
-+}
-+
-+static void wg_receive_handshake_packet(struct wg_device *wg,
-+ struct sk_buff *skb)
-+{
-+ enum cookie_mac_state mac_state;
-+ struct wg_peer *peer = NULL;
-+ /* This is global, so that our load calculation applies to the whole
-+ * system. We don't care about races with it at all.
-+ */
-+ static u64 last_under_load;
-+ bool packet_needs_cookie;
-+ bool under_load;
-+
-+ if (SKB_TYPE_LE32(skb) == cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE)) {
-+ net_dbg_skb_ratelimited("%s: Receiving cookie response from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ wg_cookie_message_consume(
-+ (struct message_handshake_cookie *)skb->data, wg);
-+ return;
-+ }
-+
-+ under_load = skb_queue_len(&wg->incoming_handshakes) >=
-+ MAX_QUEUED_INCOMING_HANDSHAKES / 8;
-+ if (under_load)
-+ last_under_load = ktime_get_coarse_boottime_ns();
-+ else if (last_under_load)
-+ under_load = !wg_birthdate_has_expired(last_under_load, 1);
-+ mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
-+ under_load);
-+ if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
-+ (!under_load && mac_state == VALID_MAC_BUT_NO_COOKIE)) {
-+ packet_needs_cookie = false;
-+ } else if (under_load && mac_state == VALID_MAC_BUT_NO_COOKIE) {
-+ packet_needs_cookie = true;
-+ } else {
-+ net_dbg_skb_ratelimited("%s: Invalid MAC of handshake, dropping packet from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ return;
-+ }
-+
-+ switch (SKB_TYPE_LE32(skb)) {
-+ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION): {
-+ struct message_handshake_initiation *message =
-+ (struct message_handshake_initiation *)skb->data;
-+
-+ if (packet_needs_cookie) {
-+ wg_packet_send_handshake_cookie(wg, skb,
-+ message->sender_index);
-+ return;
-+ }
-+ peer = wg_noise_handshake_consume_initiation(message, wg);
-+ if (unlikely(!peer)) {
-+ net_dbg_skb_ratelimited("%s: Invalid handshake initiation from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ return;
-+ }
-+ wg_socket_set_peer_endpoint_from_skb(peer, skb);
-+ net_dbg_ratelimited("%s: Receiving handshake initiation from peer %llu (%pISpfsc)\n",
-+ wg->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+ wg_packet_send_handshake_response(peer);
-+ break;
-+ }
-+ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE): {
-+ struct message_handshake_response *message =
-+ (struct message_handshake_response *)skb->data;
-+
-+ if (packet_needs_cookie) {
-+ wg_packet_send_handshake_cookie(wg, skb,
-+ message->sender_index);
-+ return;
-+ }
-+ peer = wg_noise_handshake_consume_response(message, wg);
-+ if (unlikely(!peer)) {
-+ net_dbg_skb_ratelimited("%s: Invalid handshake response from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ return;
-+ }
-+ wg_socket_set_peer_endpoint_from_skb(peer, skb);
-+ net_dbg_ratelimited("%s: Receiving handshake response from peer %llu (%pISpfsc)\n",
-+ wg->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+ if (wg_noise_handshake_begin_session(&peer->handshake,
-+ &peer->keypairs)) {
-+ wg_timers_session_derived(peer);
-+ wg_timers_handshake_complete(peer);
-+ /* Calling this function will either send any existing
-+ * packets in the queue and not send a keepalive, which
-+ * is the best case, Or, if there's nothing in the
-+ * queue, it will send a keepalive, in order to give
-+ * immediate confirmation of the session.
-+ */
-+ wg_packet_send_keepalive(peer);
-+ }
-+ break;
-+ }
-+ }
-+
-+ if (unlikely(!peer)) {
-+ WARN(1, "Somehow a wrong type of packet wound up in the handshake queue!\n");
-+ return;
-+ }
-+
-+ local_bh_disable();
-+ update_rx_stats(peer, skb->len);
-+ local_bh_enable();
-+
-+ wg_timers_any_authenticated_packet_received(peer);
-+ wg_timers_any_authenticated_packet_traversal(peer);
-+ wg_peer_put(peer);
-+}
-+
-+void wg_packet_handshake_receive_worker(struct work_struct *work)
-+{
-+ struct wg_device *wg = container_of(work, struct multicore_worker,
-+ work)->ptr;
-+ struct sk_buff *skb;
-+
-+ while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) {
-+ wg_receive_handshake_packet(wg, skb);
-+ dev_kfree_skb(skb);
-+ cond_resched();
-+ }
-+}
-+
-+static void keep_key_fresh(struct wg_peer *peer)
-+{
-+ struct noise_keypair *keypair;
-+ bool send = false;
-+
-+ if (peer->sent_lastminute_handshake)
-+ return;
-+
-+ rcu_read_lock_bh();
-+ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-+ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-+ keypair->i_am_the_initiator &&
-+ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-+ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT)))
-+ send = true;
-+ rcu_read_unlock_bh();
-+
-+ if (send) {
-+ peer->sent_lastminute_handshake = true;
-+ wg_packet_send_queued_handshake_initiation(peer, false);
-+ }
-+}
-+
-+static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
-+{
-+ struct scatterlist sg[MAX_SKB_FRAGS + 8];
-+ struct sk_buff *trailer;
-+ unsigned int offset;
-+ int num_frags;
-+
-+ if (unlikely(!key))
-+ return false;
-+
-+ if (unlikely(!READ_ONCE(key->is_valid) ||
-+ wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
-+ key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
-+ WRITE_ONCE(key->is_valid, false);
-+ return false;
-+ }
-+
-+ PACKET_CB(skb)->nonce =
-+ le64_to_cpu(((struct message_data *)skb->data)->counter);
-+
-+ /* We ensure that the network header is part of the packet before we
-+ * call skb_cow_data, so that there's no chance that data is removed
-+ * from the skb, so that later we can extract the original endpoint.
-+ */
-+ offset = skb->data - skb_network_header(skb);
-+ skb_push(skb, offset);
-+ num_frags = skb_cow_data(skb, 0, &trailer);
-+ offset += sizeof(struct message_data);
-+ skb_pull(skb, offset);
-+ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg)))
-+ return false;
-+
-+ sg_init_table(sg, num_frags);
-+ if (skb_to_sgvec(skb, sg, 0, skb->len) <= 0)
-+ return false;
-+
-+ if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
-+ PACKET_CB(skb)->nonce,
-+ key->key))
-+ return false;
-+
-+ /* Another ugly situation of pushing and pulling the header so as to
-+ * keep endpoint information intact.
-+ */
-+ skb_push(skb, offset);
-+ if (pskb_trim(skb, skb->len - noise_encrypted_len(0)))
-+ return false;
-+ skb_pull(skb, offset);
-+
-+ return true;
-+}
-+
-+/* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
-+static bool counter_validate(union noise_counter *counter, u64 their_counter)
-+{
-+ unsigned long index, index_current, top, i;
-+ bool ret = false;
-+
-+ spin_lock_bh(&counter->receive.lock);
-+
-+ if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
-+ their_counter >= REJECT_AFTER_MESSAGES))
-+ goto out;
-+
-+ ++their_counter;
-+
-+ if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
-+ counter->receive.counter))
-+ goto out;
-+
-+ index = their_counter >> ilog2(BITS_PER_LONG);
-+
-+ if (likely(their_counter > counter->receive.counter)) {
-+ index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
-+ top = min_t(unsigned long, index - index_current,
-+ COUNTER_BITS_TOTAL / BITS_PER_LONG);
-+ for (i = 1; i <= top; ++i)
-+ counter->receive.backtrack[(i + index_current) &
-+ ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
-+ counter->receive.counter = their_counter;
-+ }
-+
-+ index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
-+ ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
-+ &counter->receive.backtrack[index]);
-+
-+out:
-+ spin_unlock_bh(&counter->receive.lock);
-+ return ret;
-+}
-+
-+#include "selftest/counter.c"
-+
-+static void wg_packet_consume_data_done(struct wg_peer *peer,
-+ struct sk_buff *skb,
-+ struct endpoint *endpoint)
-+{
-+ struct net_device *dev = peer->device->dev;
-+ unsigned int len, len_before_trim;
-+ struct wg_peer *routed_peer;
-+
-+ wg_socket_set_peer_endpoint(peer, endpoint);
-+
-+ if (unlikely(wg_noise_received_with_keypair(&peer->keypairs,
-+ PACKET_CB(skb)->keypair))) {
-+ wg_timers_handshake_complete(peer);
-+ wg_packet_send_staged_packets(peer);
-+ }
-+
-+ keep_key_fresh(peer);
-+
-+ wg_timers_any_authenticated_packet_received(peer);
-+ wg_timers_any_authenticated_packet_traversal(peer);
-+
-+ /* A packet with length 0 is a keepalive packet */
-+ if (unlikely(!skb->len)) {
-+ update_rx_stats(peer, message_data_len(0));
-+ net_dbg_ratelimited("%s: Receiving keepalive packet from peer %llu (%pISpfsc)\n",
-+ dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+ goto packet_processed;
-+ }
-+
-+ wg_timers_data_received(peer);
-+
-+ if (unlikely(skb_network_header(skb) < skb->head))
-+ goto dishonest_packet_size;
-+ if (unlikely(!(pskb_network_may_pull(skb, sizeof(struct iphdr)) &&
-+ (ip_hdr(skb)->version == 4 ||
-+ (ip_hdr(skb)->version == 6 &&
-+ pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))))))
-+ goto dishonest_packet_type;
-+
-+ skb->dev = dev;
-+ /* We've already verified the Poly1305 auth tag, which means this packet
-+ * was not modified in transit. We can therefore tell the networking
-+ * stack that all checksums of every layer of encapsulation have already
-+ * been checked "by the hardware" and therefore is unneccessary to check
-+ * again in software.
-+ */
-+ skb->ip_summed = CHECKSUM_UNNECESSARY;
-+ skb->csum_level = ~0; /* All levels */
-+ skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb);
-+ if (skb->protocol == htons(ETH_P_IP)) {
-+ len = ntohs(ip_hdr(skb)->tot_len);
-+ if (unlikely(len < sizeof(struct iphdr)))
-+ goto dishonest_packet_size;
-+ if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-+ IP_ECN_set_ce(ip_hdr(skb));
-+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
-+ len = ntohs(ipv6_hdr(skb)->payload_len) +
-+ sizeof(struct ipv6hdr);
-+ if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-+ IP6_ECN_set_ce(skb, ipv6_hdr(skb));
-+ } else {
-+ goto dishonest_packet_type;
-+ }
-+
-+ if (unlikely(len > skb->len))
-+ goto dishonest_packet_size;
-+ len_before_trim = skb->len;
-+ if (unlikely(pskb_trim(skb, len)))
-+ goto packet_processed;
-+
-+ routed_peer = wg_allowedips_lookup_src(&peer->device->peer_allowedips,
-+ skb);
-+ wg_peer_put(routed_peer); /* We don't need the extra reference. */
-+
-+ if (unlikely(routed_peer != peer))
-+ goto dishonest_packet_peer;
-+
-+ if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
-+ ++dev->stats.rx_dropped;
-+ net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
-+ dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+ } else {
-+ update_rx_stats(peer, message_data_len(len_before_trim));
-+ }
-+ return;
-+
-+dishonest_packet_peer:
-+ net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n",
-+ dev->name, skb, peer->internal_id,
-+ &peer->endpoint.addr);
-+ ++dev->stats.rx_errors;
-+ ++dev->stats.rx_frame_errors;
-+ goto packet_processed;
-+dishonest_packet_type:
-+ net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n",
-+ dev->name, peer->internal_id, &peer->endpoint.addr);
-+ ++dev->stats.rx_errors;
-+ ++dev->stats.rx_frame_errors;
-+ goto packet_processed;
-+dishonest_packet_size:
-+ net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n",
-+ dev->name, peer->internal_id, &peer->endpoint.addr);
-+ ++dev->stats.rx_errors;
-+ ++dev->stats.rx_length_errors;
-+ goto packet_processed;
-+packet_processed:
-+ dev_kfree_skb(skb);
-+}
-+
-+int wg_packet_rx_poll(struct napi_struct *napi, int budget)
-+{
-+ struct wg_peer *peer = container_of(napi, struct wg_peer, napi);
-+ struct crypt_queue *queue = &peer->rx_queue;
-+ struct noise_keypair *keypair;
-+ struct endpoint endpoint;
-+ enum packet_state state;
-+ struct sk_buff *skb;
-+ int work_done = 0;
-+ bool free;
-+
-+ if (unlikely(budget <= 0))
-+ return 0;
-+
-+ while ((skb = __ptr_ring_peek(&queue->ring)) != NULL &&
-+ (state = atomic_read_acquire(&PACKET_CB(skb)->state)) !=
-+ PACKET_STATE_UNCRYPTED) {
-+ __ptr_ring_discard_one(&queue->ring);
-+ peer = PACKET_PEER(skb);
-+ keypair = PACKET_CB(skb)->keypair;
-+ free = true;
-+
-+ if (unlikely(state != PACKET_STATE_CRYPTED))
-+ goto next;
-+
-+ if (unlikely(!counter_validate(&keypair->receiving.counter,
-+ PACKET_CB(skb)->nonce))) {
-+ net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
-+ peer->device->dev->name,
-+ PACKET_CB(skb)->nonce,
-+ keypair->receiving.counter.receive.counter);
-+ goto next;
-+ }
-+
-+ if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
-+ goto next;
-+
-+ wg_reset_packet(skb);
-+ wg_packet_consume_data_done(peer, skb, &endpoint);
-+ free = false;
-+
-+next:
-+ wg_noise_keypair_put(keypair, false);
-+ wg_peer_put(peer);
-+ if (unlikely(free))
-+ dev_kfree_skb(skb);
-+
-+ if (++work_done >= budget)
-+ break;
-+ }
-+
-+ if (work_done < budget)
-+ napi_complete_done(napi, work_done);
-+
-+ return work_done;
-+}
-+
-+void wg_packet_decrypt_worker(struct work_struct *work)
-+{
-+ struct crypt_queue *queue = container_of(work, struct multicore_worker,
-+ work)->ptr;
-+ struct sk_buff *skb;
-+
-+ while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
-+ enum packet_state state = likely(decrypt_packet(skb,
-+ &PACKET_CB(skb)->keypair->receiving)) ?
-+ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
-+ wg_queue_enqueue_per_peer_napi(skb, state);
-+ }
-+}
-+
-+static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
-+{
-+ __le32 idx = ((struct message_data *)skb->data)->key_idx;
-+ struct wg_peer *peer = NULL;
-+ int ret;
-+
-+ rcu_read_lock_bh();
-+ PACKET_CB(skb)->keypair =
-+ (struct noise_keypair *)wg_index_hashtable_lookup(
-+ wg->index_hashtable, INDEX_HASHTABLE_KEYPAIR, idx,
-+ &peer);
-+ if (unlikely(!wg_noise_keypair_get(PACKET_CB(skb)->keypair)))
-+ goto err_keypair;
-+
-+ if (unlikely(READ_ONCE(peer->is_dead)))
-+ goto err;
-+
-+ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue,
-+ &peer->rx_queue, skb,
-+ wg->packet_crypt_wq,
-+ &wg->decrypt_queue.last_cpu);
-+ if (unlikely(ret == -EPIPE))
-+ wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD);
-+ if (likely(!ret || ret == -EPIPE)) {
-+ rcu_read_unlock_bh();
-+ return;
-+ }
-+err:
-+ wg_noise_keypair_put(PACKET_CB(skb)->keypair, false);
-+err_keypair:
-+ rcu_read_unlock_bh();
-+ wg_peer_put(peer);
-+ dev_kfree_skb(skb);
-+}
-+
-+void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb)
-+{
-+ if (unlikely(prepare_skb_header(skb, wg) < 0))
-+ goto err;
-+ switch (SKB_TYPE_LE32(skb)) {
-+ case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION):
-+ case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE):
-+ case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): {
-+ int cpu;
-+
-+ if (skb_queue_len(&wg->incoming_handshakes) >
-+ MAX_QUEUED_INCOMING_HANDSHAKES ||
-+ unlikely(!rng_is_initialized())) {
-+ net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ goto err;
-+ }
-+ skb_queue_tail(&wg->incoming_handshakes, skb);
-+ /* Queues up a call to packet_process_queued_handshake_
-+ * packets(skb):
-+ */
-+ cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu);
-+ queue_work_on(cpu, wg->handshake_receive_wq,
-+ &per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work);
-+ break;
-+ }
-+ case cpu_to_le32(MESSAGE_DATA):
-+ PACKET_CB(skb)->ds = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
-+ wg_packet_consume_data(wg, skb);
-+ break;
-+ default:
-+ net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n",
-+ wg->dev->name, skb);
-+ goto err;
-+ }
-+ return;
-+
-+err:
-+ dev_kfree_skb(skb);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/selftest/allowedips.c
-@@ -0,0 +1,683 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ *
-+ * This contains some basic static unit tests for the allowedips data structure.
-+ * It also has two additional modes that are disabled and meant to be used by
-+ * folks directly playing with this file. If you define the macro
-+ * DEBUG_PRINT_TRIE_GRAPHVIZ to be 1, then every time there's a full tree in
-+ * memory, it will be printed out as KERN_DEBUG in a format that can be passed
-+ * to graphviz (the dot command) to visualize it. If you define the macro
-+ * DEBUG_RANDOM_TRIE to be 1, then there will be an extremely costly set of
-+ * randomized tests done against a trivial implementation, which may take
-+ * upwards of a half-hour to complete. There's no set of users who should be
-+ * enabling these, and the only developers that should go anywhere near these
-+ * nobs are the ones who are reading this comment.
-+ */
-+
-+#ifdef DEBUG
-+
-+#include <linux/siphash.h>
-+
-+static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits,
-+ u8 cidr)
-+{
-+ swap_endian(dst, src, bits);
-+ memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8);
-+ if (cidr)
-+ dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8);
-+}
-+
-+static __init void print_node(struct allowedips_node *node, u8 bits)
-+{
-+ char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n";
-+ char *fmt_declaration = KERN_DEBUG
-+ "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
-+ char *style = "dotted";
-+ u8 ip1[16], ip2[16];
-+ u32 color = 0;
-+
-+ if (bits == 32) {
-+ fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n";
-+ fmt_declaration = KERN_DEBUG
-+ "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
-+ } else if (bits == 128) {
-+ fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n";
-+ fmt_declaration = KERN_DEBUG
-+ "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
-+ }
-+ if (node->peer) {
-+ hsiphash_key_t key = { { 0 } };
-+
-+ memcpy(&key, &node->peer, sizeof(node->peer));
-+ color = hsiphash_1u32(0xdeadbeef, &key) % 200 << 16 |
-+ hsiphash_1u32(0xbabecafe, &key) % 200 << 8 |
-+ hsiphash_1u32(0xabad1dea, &key) % 200;
-+ style = "bold";
-+ }
-+ swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr);
-+ printk(fmt_declaration, ip1, node->cidr, style, color);
-+ if (node->bit[0]) {
-+ swap_endian_and_apply_cidr(ip2,
-+ rcu_dereference_raw(node->bit[0])->bits, bits,
-+ node->cidr);
-+ printk(fmt_connection, ip1, node->cidr, ip2,
-+ rcu_dereference_raw(node->bit[0])->cidr);
-+ print_node(rcu_dereference_raw(node->bit[0]), bits);
-+ }
-+ if (node->bit[1]) {
-+ swap_endian_and_apply_cidr(ip2,
-+ rcu_dereference_raw(node->bit[1])->bits,
-+ bits, node->cidr);
-+ printk(fmt_connection, ip1, node->cidr, ip2,
-+ rcu_dereference_raw(node->bit[1])->cidr);
-+ print_node(rcu_dereference_raw(node->bit[1]), bits);
-+ }
-+}
-+
-+static __init void print_tree(struct allowedips_node __rcu *top, u8 bits)
-+{
-+ printk(KERN_DEBUG "digraph trie {\n");
-+ print_node(rcu_dereference_raw(top), bits);
-+ printk(KERN_DEBUG "}\n");
-+}
-+
-+enum {
-+ NUM_PEERS = 2000,
-+ NUM_RAND_ROUTES = 400,
-+ NUM_MUTATED_ROUTES = 100,
-+ NUM_QUERIES = NUM_RAND_ROUTES * NUM_MUTATED_ROUTES * 30
-+};
-+
-+struct horrible_allowedips {
-+ struct hlist_head head;
-+};
-+
-+struct horrible_allowedips_node {
-+ struct hlist_node table;
-+ union nf_inet_addr ip;
-+ union nf_inet_addr mask;
-+ u8 ip_version;
-+ void *value;
-+};
-+
-+static __init void horrible_allowedips_init(struct horrible_allowedips *table)
-+{
-+ INIT_HLIST_HEAD(&table->head);
-+}
-+
-+static __init void horrible_allowedips_free(struct horrible_allowedips *table)
-+{
-+ struct horrible_allowedips_node *node;
-+ struct hlist_node *h;
-+
-+ hlist_for_each_entry_safe(node, h, &table->head, table) {
-+ hlist_del(&node->table);
-+ kfree(node);
-+ }
-+}
-+
-+static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr)
-+{
-+ union nf_inet_addr mask;
-+
-+ memset(&mask, 0x00, 128 / 8);
-+ memset(&mask, 0xff, cidr / 8);
-+ if (cidr % 32)
-+ mask.all[cidr / 32] = (__force u32)htonl(
-+ (0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL);
-+ return mask;
-+}
-+
-+static __init inline u8 horrible_mask_to_cidr(union nf_inet_addr subnet)
-+{
-+ return hweight32(subnet.all[0]) + hweight32(subnet.all[1]) +
-+ hweight32(subnet.all[2]) + hweight32(subnet.all[3]);
-+}
-+
-+static __init inline void
-+horrible_mask_self(struct horrible_allowedips_node *node)
-+{
-+ if (node->ip_version == 4) {
-+ node->ip.ip &= node->mask.ip;
-+ } else if (node->ip_version == 6) {
-+ node->ip.ip6[0] &= node->mask.ip6[0];
-+ node->ip.ip6[1] &= node->mask.ip6[1];
-+ node->ip.ip6[2] &= node->mask.ip6[2];
-+ node->ip.ip6[3] &= node->mask.ip6[3];
-+ }
-+}
-+
-+static __init inline bool
-+horrible_match_v4(const struct horrible_allowedips_node *node,
-+ struct in_addr *ip)
-+{
-+ return (ip->s_addr & node->mask.ip) == node->ip.ip;
-+}
-+
-+static __init inline bool
-+horrible_match_v6(const struct horrible_allowedips_node *node,
-+ struct in6_addr *ip)
-+{
-+ return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) ==
-+ node->ip.ip6[0] &&
-+ (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) ==
-+ node->ip.ip6[1] &&
-+ (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) ==
-+ node->ip.ip6[2] &&
-+ (ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3];
-+}
-+
-+static __init void
-+horrible_insert_ordered(struct horrible_allowedips *table,
-+ struct horrible_allowedips_node *node)
-+{
-+ struct horrible_allowedips_node *other = NULL, *where = NULL;
-+ u8 my_cidr = horrible_mask_to_cidr(node->mask);
-+
-+ hlist_for_each_entry(other, &table->head, table) {
-+ if (!memcmp(&other->mask, &node->mask,
-+ sizeof(union nf_inet_addr)) &&
-+ !memcmp(&other->ip, &node->ip,
-+ sizeof(union nf_inet_addr)) &&
-+ other->ip_version == node->ip_version) {
-+ other->value = node->value;
-+ kfree(node);
-+ return;
-+ }
-+ where = other;
-+ if (horrible_mask_to_cidr(other->mask) <= my_cidr)
-+ break;
-+ }
-+ if (!other && !where)
-+ hlist_add_head(&node->table, &table->head);
-+ else if (!other)
-+ hlist_add_behind(&node->table, &where->table);
-+ else
-+ hlist_add_before(&node->table, &where->table);
-+}
-+
-+static __init int
-+horrible_allowedips_insert_v4(struct horrible_allowedips *table,
-+ struct in_addr *ip, u8 cidr, void *value)
-+{
-+ struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
-+ GFP_KERNEL);
-+
-+ if (unlikely(!node))
-+ return -ENOMEM;
-+ node->ip.in = *ip;
-+ node->mask = horrible_cidr_to_mask(cidr);
-+ node->ip_version = 4;
-+ node->value = value;
-+ horrible_mask_self(node);
-+ horrible_insert_ordered(table, node);
-+ return 0;
-+}
-+
-+static __init int
-+horrible_allowedips_insert_v6(struct horrible_allowedips *table,
-+ struct in6_addr *ip, u8 cidr, void *value)
-+{
-+ struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
-+ GFP_KERNEL);
-+
-+ if (unlikely(!node))
-+ return -ENOMEM;
-+ node->ip.in6 = *ip;
-+ node->mask = horrible_cidr_to_mask(cidr);
-+ node->ip_version = 6;
-+ node->value = value;
-+ horrible_mask_self(node);
-+ horrible_insert_ordered(table, node);
-+ return 0;
-+}
-+
-+static __init void *
-+horrible_allowedips_lookup_v4(struct horrible_allowedips *table,
-+ struct in_addr *ip)
-+{
-+ struct horrible_allowedips_node *node;
-+ void *ret = NULL;
-+
-+ hlist_for_each_entry(node, &table->head, table) {
-+ if (node->ip_version != 4)
-+ continue;
-+ if (horrible_match_v4(node, ip)) {
-+ ret = node->value;
-+ break;
-+ }
-+ }
-+ return ret;
-+}
-+
-+static __init void *
-+horrible_allowedips_lookup_v6(struct horrible_allowedips *table,
-+ struct in6_addr *ip)
-+{
-+ struct horrible_allowedips_node *node;
-+ void *ret = NULL;
-+
-+ hlist_for_each_entry(node, &table->head, table) {
-+ if (node->ip_version != 6)
-+ continue;
-+ if (horrible_match_v6(node, ip)) {
-+ ret = node->value;
-+ break;
-+ }
-+ }
-+ return ret;
-+}
-+
-+static __init bool randomized_test(void)
-+{
-+ unsigned int i, j, k, mutate_amount, cidr;
-+ u8 ip[16], mutate_mask[16], mutated[16];
-+ struct wg_peer **peers, *peer;
-+ struct horrible_allowedips h;
-+ DEFINE_MUTEX(mutex);
-+ struct allowedips t;
-+ bool ret = false;
-+
-+ mutex_init(&mutex);
-+
-+ wg_allowedips_init(&t);
-+ horrible_allowedips_init(&h);
-+
-+ peers = kcalloc(NUM_PEERS, sizeof(*peers), GFP_KERNEL);
-+ if (unlikely(!peers)) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free;
-+ }
-+ for (i = 0; i < NUM_PEERS; ++i) {
-+ peers[i] = kzalloc(sizeof(*peers[i]), GFP_KERNEL);
-+ if (unlikely(!peers[i])) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free;
-+ }
-+ kref_init(&peers[i]->refcount);
-+ }
-+
-+ mutex_lock(&mutex);
-+
-+ for (i = 0; i < NUM_RAND_ROUTES; ++i) {
-+ prandom_bytes(ip, 4);
-+ cidr = prandom_u32_max(32) + 1;
-+ peer = peers[prandom_u32_max(NUM_PEERS)];
-+ if (wg_allowedips_insert_v4(&t, (struct in_addr *)ip, cidr,
-+ peer, &mutex) < 0) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ if (horrible_allowedips_insert_v4(&h, (struct in_addr *)ip,
-+ cidr, peer) < 0) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) {
-+ memcpy(mutated, ip, 4);
-+ prandom_bytes(mutate_mask, 4);
-+ mutate_amount = prandom_u32_max(32);
-+ for (k = 0; k < mutate_amount / 8; ++k)
-+ mutate_mask[k] = 0xff;
-+ mutate_mask[k] = 0xff
-+ << ((8 - (mutate_amount % 8)) % 8);
-+ for (; k < 4; ++k)
-+ mutate_mask[k] = 0;
-+ for (k = 0; k < 4; ++k)
-+ mutated[k] = (mutated[k] & mutate_mask[k]) |
-+ (~mutate_mask[k] &
-+ prandom_u32_max(256));
-+ cidr = prandom_u32_max(32) + 1;
-+ peer = peers[prandom_u32_max(NUM_PEERS)];
-+ if (wg_allowedips_insert_v4(&t,
-+ (struct in_addr *)mutated,
-+ cidr, peer, &mutex) < 0) {
-+ pr_err("allowedips random malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ if (horrible_allowedips_insert_v4(&h,
-+ (struct in_addr *)mutated, cidr, peer)) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ }
-+ }
-+
-+ for (i = 0; i < NUM_RAND_ROUTES; ++i) {
-+ prandom_bytes(ip, 16);
-+ cidr = prandom_u32_max(128) + 1;
-+ peer = peers[prandom_u32_max(NUM_PEERS)];
-+ if (wg_allowedips_insert_v6(&t, (struct in6_addr *)ip, cidr,
-+ peer, &mutex) < 0) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ if (horrible_allowedips_insert_v6(&h, (struct in6_addr *)ip,
-+ cidr, peer) < 0) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ for (j = 0; j < NUM_MUTATED_ROUTES; ++j) {
-+ memcpy(mutated, ip, 16);
-+ prandom_bytes(mutate_mask, 16);
-+ mutate_amount = prandom_u32_max(128);
-+ for (k = 0; k < mutate_amount / 8; ++k)
-+ mutate_mask[k] = 0xff;
-+ mutate_mask[k] = 0xff
-+ << ((8 - (mutate_amount % 8)) % 8);
-+ for (; k < 4; ++k)
-+ mutate_mask[k] = 0;
-+ for (k = 0; k < 4; ++k)
-+ mutated[k] = (mutated[k] & mutate_mask[k]) |
-+ (~mutate_mask[k] &
-+ prandom_u32_max(256));
-+ cidr = prandom_u32_max(128) + 1;
-+ peer = peers[prandom_u32_max(NUM_PEERS)];
-+ if (wg_allowedips_insert_v6(&t,
-+ (struct in6_addr *)mutated,
-+ cidr, peer, &mutex) < 0) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ if (horrible_allowedips_insert_v6(
-+ &h, (struct in6_addr *)mutated, cidr,
-+ peer)) {
-+ pr_err("allowedips random self-test malloc: FAIL\n");
-+ goto free_locked;
-+ }
-+ }
-+ }
-+
-+ mutex_unlock(&mutex);
-+
-+ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) {
-+ print_tree(t.root4, 32);
-+ print_tree(t.root6, 128);
-+ }
-+
-+ for (i = 0; i < NUM_QUERIES; ++i) {
-+ prandom_bytes(ip, 4);
-+ if (lookup(t.root4, 32, ip) !=
-+ horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
-+ pr_err("allowedips random self-test: FAIL\n");
-+ goto free;
-+ }
-+ }
-+
-+ for (i = 0; i < NUM_QUERIES; ++i) {
-+ prandom_bytes(ip, 16);
-+ if (lookup(t.root6, 128, ip) !=
-+ horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
-+ pr_err("allowedips random self-test: FAIL\n");
-+ goto free;
-+ }
-+ }
-+ ret = true;
-+
-+free:
-+ mutex_lock(&mutex);
-+free_locked:
-+ wg_allowedips_free(&t, &mutex);
-+ mutex_unlock(&mutex);
-+ horrible_allowedips_free(&h);
-+ if (peers) {
-+ for (i = 0; i < NUM_PEERS; ++i)
-+ kfree(peers[i]);
-+ }
-+ kfree(peers);
-+ return ret;
-+}
-+
-+static __init inline struct in_addr *ip4(u8 a, u8 b, u8 c, u8 d)
-+{
-+ static struct in_addr ip;
-+ u8 *split = (u8 *)&ip;
-+
-+ split[0] = a;
-+ split[1] = b;
-+ split[2] = c;
-+ split[3] = d;
-+ return &ip;
-+}
-+
-+static __init inline struct in6_addr *ip6(u32 a, u32 b, u32 c, u32 d)
-+{
-+ static struct in6_addr ip;
-+ __be32 *split = (__be32 *)&ip;
-+
-+ split[0] = cpu_to_be32(a);
-+ split[1] = cpu_to_be32(b);
-+ split[2] = cpu_to_be32(c);
-+ split[3] = cpu_to_be32(d);
-+ return &ip;
-+}
-+
-+static __init struct wg_peer *init_peer(void)
-+{
-+ struct wg_peer *peer = kzalloc(sizeof(*peer), GFP_KERNEL);
-+
-+ if (!peer)
-+ return NULL;
-+ kref_init(&peer->refcount);
-+ INIT_LIST_HEAD(&peer->allowedips_list);
-+ return peer;
-+}
-+
-+#define insert(version, mem, ipa, ipb, ipc, ipd, cidr) \
-+ wg_allowedips_insert_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \
-+ cidr, mem, &mutex)
-+
-+#define maybe_fail() do { \
-+ ++i; \
-+ if (!_s) { \
-+ pr_info("allowedips self-test %zu: FAIL\n", i); \
-+ success = false; \
-+ } \
-+ } while (0)
-+
-+#define test(version, mem, ipa, ipb, ipc, ipd) do { \
-+ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \
-+ ip##version(ipa, ipb, ipc, ipd)) == (mem); \
-+ maybe_fail(); \
-+ } while (0)
-+
-+#define test_negative(version, mem, ipa, ipb, ipc, ipd) do { \
-+ bool _s = lookup(t.root##version, (version) == 4 ? 32 : 128, \
-+ ip##version(ipa, ipb, ipc, ipd)) != (mem); \
-+ maybe_fail(); \
-+ } while (0)
-+
-+#define test_boolean(cond) do { \
-+ bool _s = (cond); \
-+ maybe_fail(); \
-+ } while (0)
-+
-+bool __init wg_allowedips_selftest(void)
-+{
-+ bool found_a = false, found_b = false, found_c = false, found_d = false,
-+ found_e = false, found_other = false;
-+ struct wg_peer *a = init_peer(), *b = init_peer(), *c = init_peer(),
-+ *d = init_peer(), *e = init_peer(), *f = init_peer(),
-+ *g = init_peer(), *h = init_peer();
-+ struct allowedips_node *iter_node;
-+ bool success = false;
-+ struct allowedips t;
-+ DEFINE_MUTEX(mutex);
-+ struct in6_addr ip;
-+ size_t i = 0, count = 0;
-+ __be64 part;
-+
-+ mutex_init(&mutex);
-+ mutex_lock(&mutex);
-+ wg_allowedips_init(&t);
-+
-+ if (!a || !b || !c || !d || !e || !f || !g || !h) {
-+ pr_err("allowedips self-test malloc: FAIL\n");
-+ goto free;
-+ }
-+
-+ insert(4, a, 192, 168, 4, 0, 24);
-+ insert(4, b, 192, 168, 4, 4, 32);
-+ insert(4, c, 192, 168, 0, 0, 16);
-+ insert(4, d, 192, 95, 5, 64, 27);
-+ /* replaces previous entry, and maskself is required */
-+ insert(4, c, 192, 95, 5, 65, 27);
-+ insert(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128);
-+ insert(6, c, 0x26075300, 0x60006b00, 0, 0, 64);
-+ insert(4, e, 0, 0, 0, 0, 0);
-+ insert(6, e, 0, 0, 0, 0, 0);
-+ /* replaces previous entry */
-+ insert(6, f, 0, 0, 0, 0, 0);
-+ insert(6, g, 0x24046800, 0, 0, 0, 32);
-+ /* maskself is required */
-+ insert(6, h, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 64);
-+ insert(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef, 128);
-+ insert(6, c, 0x24446800, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128);
-+ insert(6, b, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98);
-+ insert(4, g, 64, 15, 112, 0, 20);
-+ /* maskself is required */
-+ insert(4, h, 64, 15, 123, 211, 25);
-+ insert(4, a, 10, 0, 0, 0, 25);
-+ insert(4, b, 10, 0, 0, 128, 25);
-+ insert(4, a, 10, 1, 0, 0, 30);
-+ insert(4, b, 10, 1, 0, 4, 30);
-+ insert(4, c, 10, 1, 0, 8, 29);
-+ insert(4, d, 10, 1, 0, 16, 29);
-+
-+ if (IS_ENABLED(DEBUG_PRINT_TRIE_GRAPHVIZ)) {
-+ print_tree(t.root4, 32);
-+ print_tree(t.root6, 128);
-+ }
-+
-+ success = true;
-+
-+ test(4, a, 192, 168, 4, 20);
-+ test(4, a, 192, 168, 4, 0);
-+ test(4, b, 192, 168, 4, 4);
-+ test(4, c, 192, 168, 200, 182);
-+ test(4, c, 192, 95, 5, 68);
-+ test(4, e, 192, 95, 5, 96);
-+ test(6, d, 0x26075300, 0x60006b00, 0, 0xc05f0543);
-+ test(6, c, 0x26075300, 0x60006b00, 0, 0xc02e01ee);
-+ test(6, f, 0x26075300, 0x60006b01, 0, 0);
-+ test(6, g, 0x24046800, 0x40040806, 0, 0x1006);
-+ test(6, g, 0x24046800, 0x40040806, 0x1234, 0x5678);
-+ test(6, f, 0x240467ff, 0x40040806, 0x1234, 0x5678);
-+ test(6, f, 0x24046801, 0x40040806, 0x1234, 0x5678);
-+ test(6, h, 0x24046800, 0x40040800, 0x1234, 0x5678);
-+ test(6, h, 0x24046800, 0x40040800, 0, 0);
-+ test(6, h, 0x24046800, 0x40040800, 0x10101010, 0x10101010);
-+ test(6, a, 0x24046800, 0x40040800, 0xdeadbeef, 0xdeadbeef);
-+ test(4, g, 64, 15, 116, 26);
-+ test(4, g, 64, 15, 127, 3);
-+ test(4, g, 64, 15, 123, 1);
-+ test(4, h, 64, 15, 123, 128);
-+ test(4, h, 64, 15, 123, 129);
-+ test(4, a, 10, 0, 0, 52);
-+ test(4, b, 10, 0, 0, 220);
-+ test(4, a, 10, 1, 0, 2);
-+ test(4, b, 10, 1, 0, 6);
-+ test(4, c, 10, 1, 0, 10);
-+ test(4, d, 10, 1, 0, 20);
-+
-+ insert(4, a, 1, 0, 0, 0, 32);
-+ insert(4, a, 64, 0, 0, 0, 32);
-+ insert(4, a, 128, 0, 0, 0, 32);
-+ insert(4, a, 192, 0, 0, 0, 32);
-+ insert(4, a, 255, 0, 0, 0, 32);
-+ wg_allowedips_remove_by_peer(&t, a, &mutex);
-+ test_negative(4, a, 1, 0, 0, 0);
-+ test_negative(4, a, 64, 0, 0, 0);
-+ test_negative(4, a, 128, 0, 0, 0);
-+ test_negative(4, a, 192, 0, 0, 0);
-+ test_negative(4, a, 255, 0, 0, 0);
-+
-+ wg_allowedips_free(&t, &mutex);
-+ wg_allowedips_init(&t);
-+ insert(4, a, 192, 168, 0, 0, 16);
-+ insert(4, a, 192, 168, 0, 0, 24);
-+ wg_allowedips_remove_by_peer(&t, a, &mutex);
-+ test_negative(4, a, 192, 168, 0, 1);
-+
-+ /* These will hit the WARN_ON(len >= 128) in free_node if something
-+ * goes wrong.
-+ */
-+ for (i = 0; i < 128; ++i) {
-+ part = cpu_to_be64(~(1LLU << (i % 64)));
-+ memset(&ip, 0xff, 16);
-+ memcpy((u8 *)&ip + (i < 64) * 8, &part, 8);
-+ wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex);
-+ }
-+
-+ wg_allowedips_free(&t, &mutex);
-+
-+ wg_allowedips_init(&t);
-+ insert(4, a, 192, 95, 5, 93, 27);
-+ insert(6, a, 0x26075300, 0x60006b00, 0, 0xc05f0543, 128);
-+ insert(4, a, 10, 1, 0, 20, 29);
-+ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 83);
-+ insert(6, a, 0x26075300, 0x6d8a6bf8, 0xdab1f1df, 0xc05f1523, 21);
-+ list_for_each_entry(iter_node, &a->allowedips_list, peer_list) {
-+ u8 cidr, ip[16] __aligned(__alignof(u64));
-+ int family = wg_allowedips_read_node(iter_node, ip, &cidr);
-+
-+ count++;
-+
-+ if (cidr == 27 && family == AF_INET &&
-+ !memcmp(ip, ip4(192, 95, 5, 64), sizeof(struct in_addr)))
-+ found_a = true;
-+ else if (cidr == 128 && family == AF_INET6 &&
-+ !memcmp(ip, ip6(0x26075300, 0x60006b00, 0, 0xc05f0543),
-+ sizeof(struct in6_addr)))
-+ found_b = true;
-+ else if (cidr == 29 && family == AF_INET &&
-+ !memcmp(ip, ip4(10, 1, 0, 16), sizeof(struct in_addr)))
-+ found_c = true;
-+ else if (cidr == 83 && family == AF_INET6 &&
-+ !memcmp(ip, ip6(0x26075300, 0x6d8a6bf8, 0xdab1e000, 0),
-+ sizeof(struct in6_addr)))
-+ found_d = true;
-+ else if (cidr == 21 && family == AF_INET6 &&
-+ !memcmp(ip, ip6(0x26075000, 0, 0, 0),
-+ sizeof(struct in6_addr)))
-+ found_e = true;
-+ else
-+ found_other = true;
-+ }
-+ test_boolean(count == 5);
-+ test_boolean(found_a);
-+ test_boolean(found_b);
-+ test_boolean(found_c);
-+ test_boolean(found_d);
-+ test_boolean(found_e);
-+ test_boolean(!found_other);
-+
-+ if (IS_ENABLED(DEBUG_RANDOM_TRIE) && success)
-+ success = randomized_test();
-+
-+ if (success)
-+ pr_info("allowedips self-tests: pass\n");
-+
-+free:
-+ wg_allowedips_free(&t, &mutex);
-+ kfree(a);
-+ kfree(b);
-+ kfree(c);
-+ kfree(d);
-+ kfree(e);
-+ kfree(f);
-+ kfree(g);
-+ kfree(h);
-+ mutex_unlock(&mutex);
-+
-+ return success;
-+}
-+
-+#undef test_negative
-+#undef test
-+#undef remove
-+#undef insert
-+#undef init_peer
-+
-+#endif
---- /dev/null
-+++ b/drivers/net/wireguard/selftest/counter.c
-@@ -0,0 +1,104 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifdef DEBUG
-+bool __init wg_packet_counter_selftest(void)
-+{
-+ unsigned int test_num = 0, i;
-+ union noise_counter counter;
-+ bool success = true;
-+
-+#define T_INIT do { \
-+ memset(&counter, 0, sizeof(union noise_counter)); \
-+ spin_lock_init(&counter.receive.lock); \
-+ } while (0)
-+#define T_LIM (COUNTER_WINDOW_SIZE + 1)
-+#define T(n, v) do { \
-+ ++test_num; \
-+ if (counter_validate(&counter, n) != (v)) { \
-+ pr_err("nonce counter self-test %u: FAIL\n", \
-+ test_num); \
-+ success = false; \
-+ } \
-+ } while (0)
-+
-+ T_INIT;
-+ /* 1 */ T(0, true);
-+ /* 2 */ T(1, true);
-+ /* 3 */ T(1, false);
-+ /* 4 */ T(9, true);
-+ /* 5 */ T(8, true);
-+ /* 6 */ T(7, true);
-+ /* 7 */ T(7, false);
-+ /* 8 */ T(T_LIM, true);
-+ /* 9 */ T(T_LIM - 1, true);
-+ /* 10 */ T(T_LIM - 1, false);
-+ /* 11 */ T(T_LIM - 2, true);
-+ /* 12 */ T(2, true);
-+ /* 13 */ T(2, false);
-+ /* 14 */ T(T_LIM + 16, true);
-+ /* 15 */ T(3, false);
-+ /* 16 */ T(T_LIM + 16, false);
-+ /* 17 */ T(T_LIM * 4, true);
-+ /* 18 */ T(T_LIM * 4 - (T_LIM - 1), true);
-+ /* 19 */ T(10, false);
-+ /* 20 */ T(T_LIM * 4 - T_LIM, false);
-+ /* 21 */ T(T_LIM * 4 - (T_LIM + 1), false);
-+ /* 22 */ T(T_LIM * 4 - (T_LIM - 2), true);
-+ /* 23 */ T(T_LIM * 4 + 1 - T_LIM, false);
-+ /* 24 */ T(0, false);
-+ /* 25 */ T(REJECT_AFTER_MESSAGES, false);
-+ /* 26 */ T(REJECT_AFTER_MESSAGES - 1, true);
-+ /* 27 */ T(REJECT_AFTER_MESSAGES, false);
-+ /* 28 */ T(REJECT_AFTER_MESSAGES - 1, false);
-+ /* 29 */ T(REJECT_AFTER_MESSAGES - 2, true);
-+ /* 30 */ T(REJECT_AFTER_MESSAGES + 1, false);
-+ /* 31 */ T(REJECT_AFTER_MESSAGES + 2, false);
-+ /* 32 */ T(REJECT_AFTER_MESSAGES - 2, false);
-+ /* 33 */ T(REJECT_AFTER_MESSAGES - 3, true);
-+ /* 34 */ T(0, false);
-+
-+ T_INIT;
-+ for (i = 1; i <= COUNTER_WINDOW_SIZE; ++i)
-+ T(i, true);
-+ T(0, true);
-+ T(0, false);
-+
-+ T_INIT;
-+ for (i = 2; i <= COUNTER_WINDOW_SIZE + 1; ++i)
-+ T(i, true);
-+ T(1, true);
-+ T(0, false);
-+
-+ T_INIT;
-+ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 0;)
-+ T(i, true);
-+
-+ T_INIT;
-+ for (i = COUNTER_WINDOW_SIZE + 2; i-- > 1;)
-+ T(i, true);
-+ T(0, false);
-+
-+ T_INIT;
-+ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;)
-+ T(i, true);
-+ T(COUNTER_WINDOW_SIZE + 1, true);
-+ T(0, false);
-+
-+ T_INIT;
-+ for (i = COUNTER_WINDOW_SIZE + 1; i-- > 1;)
-+ T(i, true);
-+ T(0, true);
-+ T(COUNTER_WINDOW_SIZE + 1, true);
-+
-+#undef T
-+#undef T_LIM
-+#undef T_INIT
-+
-+ if (success)
-+ pr_info("nonce counter self-tests: pass\n");
-+ return success;
-+}
-+#endif
---- /dev/null
-+++ b/drivers/net/wireguard/selftest/ratelimiter.c
-@@ -0,0 +1,226 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifdef DEBUG
-+
-+#include <linux/jiffies.h>
-+
-+static const struct {
-+ bool result;
-+ unsigned int msec_to_sleep_before;
-+} expected_results[] __initconst = {
-+ [0 ... PACKETS_BURSTABLE - 1] = { true, 0 },
-+ [PACKETS_BURSTABLE] = { false, 0 },
-+ [PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND },
-+ [PACKETS_BURSTABLE + 2] = { false, 0 },
-+ [PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 },
-+ [PACKETS_BURSTABLE + 4] = { true, 0 },
-+ [PACKETS_BURSTABLE + 5] = { false, 0 }
-+};
-+
-+static __init unsigned int maximum_jiffies_at_index(int index)
-+{
-+ unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3;
-+ int i;
-+
-+ for (i = 0; i <= index; ++i)
-+ total_msecs += expected_results[i].msec_to_sleep_before;
-+ return msecs_to_jiffies(total_msecs);
-+}
-+
-+static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4,
-+ struct sk_buff *skb6, struct ipv6hdr *hdr6,
-+ int *test)
-+{
-+ unsigned long loop_start_time;
-+ int i;
-+
-+ wg_ratelimiter_gc_entries(NULL);
-+ rcu_barrier();
-+ loop_start_time = jiffies;
-+
-+ for (i = 0; i < ARRAY_SIZE(expected_results); ++i) {
-+ if (expected_results[i].msec_to_sleep_before)
-+ msleep(expected_results[i].msec_to_sleep_before);
-+
-+ if (time_is_before_jiffies(loop_start_time +
-+ maximum_jiffies_at_index(i)))
-+ return -ETIMEDOUT;
-+ if (wg_ratelimiter_allow(skb4, &init_net) !=
-+ expected_results[i].result)
-+ return -EXFULL;
-+ ++(*test);
-+
-+ hdr4->saddr = htonl(ntohl(hdr4->saddr) + i + 1);
-+ if (time_is_before_jiffies(loop_start_time +
-+ maximum_jiffies_at_index(i)))
-+ return -ETIMEDOUT;
-+ if (!wg_ratelimiter_allow(skb4, &init_net))
-+ return -EXFULL;
-+ ++(*test);
-+
-+ hdr4->saddr = htonl(ntohl(hdr4->saddr) - i - 1);
-+
-+#if IS_ENABLED(CONFIG_IPV6)
-+ hdr6->saddr.in6_u.u6_addr32[2] = htonl(i);
-+ hdr6->saddr.in6_u.u6_addr32[3] = htonl(i);
-+ if (time_is_before_jiffies(loop_start_time +
-+ maximum_jiffies_at_index(i)))
-+ return -ETIMEDOUT;
-+ if (wg_ratelimiter_allow(skb6, &init_net) !=
-+ expected_results[i].result)
-+ return -EXFULL;
-+ ++(*test);
-+
-+ hdr6->saddr.in6_u.u6_addr32[0] =
-+ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) + i + 1);
-+ if (time_is_before_jiffies(loop_start_time +
-+ maximum_jiffies_at_index(i)))
-+ return -ETIMEDOUT;
-+ if (!wg_ratelimiter_allow(skb6, &init_net))
-+ return -EXFULL;
-+ ++(*test);
-+
-+ hdr6->saddr.in6_u.u6_addr32[0] =
-+ htonl(ntohl(hdr6->saddr.in6_u.u6_addr32[0]) - i - 1);
-+
-+ if (time_is_before_jiffies(loop_start_time +
-+ maximum_jiffies_at_index(i)))
-+ return -ETIMEDOUT;
-+#endif
-+ }
-+ return 0;
-+}
-+
-+static __init int capacity_test(struct sk_buff *skb4, struct iphdr *hdr4,
-+ int *test)
-+{
-+ int i;
-+
-+ wg_ratelimiter_gc_entries(NULL);
-+ rcu_barrier();
-+
-+ if (atomic_read(&total_entries))
-+ return -EXFULL;
-+ ++(*test);
-+
-+ for (i = 0; i <= max_entries; ++i) {
-+ hdr4->saddr = htonl(i);
-+ if (wg_ratelimiter_allow(skb4, &init_net) != (i != max_entries))
-+ return -EXFULL;
-+ ++(*test);
-+ }
-+ return 0;
-+}
-+
-+bool __init wg_ratelimiter_selftest(void)
-+{
-+ enum { TRIALS_BEFORE_GIVING_UP = 5000 };
-+ bool success = false;
-+ int test = 0, trials;
-+ struct sk_buff *skb4, *skb6;
-+ struct iphdr *hdr4;
-+ struct ipv6hdr *hdr6;
-+
-+ if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
-+ return true;
-+
-+ BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0);
-+
-+ if (wg_ratelimiter_init())
-+ goto out;
-+ ++test;
-+ if (wg_ratelimiter_init()) {
-+ wg_ratelimiter_uninit();
-+ goto out;
-+ }
-+ ++test;
-+ if (wg_ratelimiter_init()) {
-+ wg_ratelimiter_uninit();
-+ wg_ratelimiter_uninit();
-+ goto out;
-+ }
-+ ++test;
-+
-+ skb4 = alloc_skb(sizeof(struct iphdr), GFP_KERNEL);
-+ if (unlikely(!skb4))
-+ goto err_nofree;
-+ skb4->protocol = htons(ETH_P_IP);
-+ hdr4 = (struct iphdr *)skb_put(skb4, sizeof(*hdr4));
-+ hdr4->saddr = htonl(8182);
-+ skb_reset_network_header(skb4);
-+ ++test;
-+
-+#if IS_ENABLED(CONFIG_IPV6)
-+ skb6 = alloc_skb(sizeof(struct ipv6hdr), GFP_KERNEL);
-+ if (unlikely(!skb6)) {
-+ kfree_skb(skb4);
-+ goto err_nofree;
-+ }
-+ skb6->protocol = htons(ETH_P_IPV6);
-+ hdr6 = (struct ipv6hdr *)skb_put(skb6, sizeof(*hdr6));
-+ hdr6->saddr.in6_u.u6_addr32[0] = htonl(1212);
-+ hdr6->saddr.in6_u.u6_addr32[1] = htonl(289188);
-+ skb_reset_network_header(skb6);
-+ ++test;
-+#endif
-+
-+ for (trials = TRIALS_BEFORE_GIVING_UP;;) {
-+ int test_count = 0, ret;
-+
-+ ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
-+ if (ret == -ETIMEDOUT) {
-+ if (!trials--) {
-+ test += test_count;
-+ goto err;
-+ }
-+ msleep(500);
-+ continue;
-+ } else if (ret < 0) {
-+ test += test_count;
-+ goto err;
-+ } else {
-+ test += test_count;
-+ break;
-+ }
-+ }
-+
-+ for (trials = TRIALS_BEFORE_GIVING_UP;;) {
-+ int test_count = 0;
-+
-+ if (capacity_test(skb4, hdr4, &test_count) < 0) {
-+ if (!trials--) {
-+ test += test_count;
-+ goto err;
-+ }
-+ msleep(50);
-+ continue;
-+ }
-+ test += test_count;
-+ break;
-+ }
-+
-+ success = true;
-+
-+err:
-+ kfree_skb(skb4);
-+#if IS_ENABLED(CONFIG_IPV6)
-+ kfree_skb(skb6);
-+#endif
-+err_nofree:
-+ wg_ratelimiter_uninit();
-+ wg_ratelimiter_uninit();
-+ wg_ratelimiter_uninit();
-+ /* Uninit one extra time to check underflow detection. */
-+ wg_ratelimiter_uninit();
-+out:
-+ if (success)
-+ pr_info("ratelimiter self-tests: pass\n");
-+ else
-+ pr_err("ratelimiter self-test %d: FAIL\n", test);
-+
-+ return success;
-+}
-+#endif
---- /dev/null
-+++ b/drivers/net/wireguard/send.c
-@@ -0,0 +1,413 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "queueing.h"
-+#include "timers.h"
-+#include "device.h"
-+#include "peer.h"
-+#include "socket.h"
-+#include "messages.h"
-+#include "cookie.h"
-+
-+#include <linux/uio.h>
-+#include <linux/inetdevice.h>
-+#include <linux/socket.h>
-+#include <net/ip_tunnels.h>
-+#include <net/udp.h>
-+#include <net/sock.h>
-+
-+static void wg_packet_send_handshake_initiation(struct wg_peer *peer)
-+{
-+ struct message_handshake_initiation packet;
-+
-+ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake),
-+ REKEY_TIMEOUT))
-+ return; /* This function is rate limited. */
-+
-+ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns());
-+ net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+
-+ if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) {
-+ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer);
-+ wg_timers_any_authenticated_packet_traversal(peer);
-+ wg_timers_any_authenticated_packet_sent(peer);
-+ atomic64_set(&peer->last_sent_handshake,
-+ ktime_get_coarse_boottime_ns());
-+ wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet),
-+ HANDSHAKE_DSCP);
-+ wg_timers_handshake_initiated(peer);
-+ }
-+}
-+
-+void wg_packet_handshake_send_worker(struct work_struct *work)
-+{
-+ struct wg_peer *peer = container_of(work, struct wg_peer,
-+ transmit_handshake_work);
-+
-+ wg_packet_send_handshake_initiation(peer);
-+ wg_peer_put(peer);
-+}
-+
-+void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer,
-+ bool is_retry)
-+{
-+ if (!is_retry)
-+ peer->timer_handshake_attempts = 0;
-+
-+ rcu_read_lock_bh();
-+ /* We check last_sent_handshake here in addition to the actual function
-+ * we're queueing up, so that we don't queue things if not strictly
-+ * necessary:
-+ */
-+ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake),
-+ REKEY_TIMEOUT) ||
-+ unlikely(READ_ONCE(peer->is_dead)))
-+ goto out;
-+
-+ wg_peer_get(peer);
-+ /* Queues up calling packet_send_queued_handshakes(peer), where we do a
-+ * peer_put(peer) after:
-+ */
-+ if (!queue_work(peer->device->handshake_send_wq,
-+ &peer->transmit_handshake_work))
-+ /* If the work was already queued, we want to drop the
-+ * extra reference:
-+ */
-+ wg_peer_put(peer);
-+out:
-+ rcu_read_unlock_bh();
-+}
-+
-+void wg_packet_send_handshake_response(struct wg_peer *peer)
-+{
-+ struct message_handshake_response packet;
-+
-+ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns());
-+ net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+
-+ if (wg_noise_handshake_create_response(&packet, &peer->handshake)) {
-+ wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer);
-+ if (wg_noise_handshake_begin_session(&peer->handshake,
-+ &peer->keypairs)) {
-+ wg_timers_session_derived(peer);
-+ wg_timers_any_authenticated_packet_traversal(peer);
-+ wg_timers_any_authenticated_packet_sent(peer);
-+ atomic64_set(&peer->last_sent_handshake,
-+ ktime_get_coarse_boottime_ns());
-+ wg_socket_send_buffer_to_peer(peer, &packet,
-+ sizeof(packet),
-+ HANDSHAKE_DSCP);
-+ }
-+ }
-+}
-+
-+void wg_packet_send_handshake_cookie(struct wg_device *wg,
-+ struct sk_buff *initiating_skb,
-+ __le32 sender_index)
-+{
-+ struct message_handshake_cookie packet;
-+
-+ net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n",
-+ wg->dev->name, initiating_skb);
-+ wg_cookie_message_create(&packet, initiating_skb, sender_index,
-+ &wg->cookie_checker);
-+ wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet,
-+ sizeof(packet));
-+}
-+
-+static void keep_key_fresh(struct wg_peer *peer)
-+{
-+ struct noise_keypair *keypair;
-+ bool send = false;
-+
-+ rcu_read_lock_bh();
-+ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-+ if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-+ (unlikely(atomic64_read(&keypair->sending.counter.counter) >
-+ REKEY_AFTER_MESSAGES) ||
-+ (keypair->i_am_the_initiator &&
-+ unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-+ REKEY_AFTER_TIME)))))
-+ send = true;
-+ rcu_read_unlock_bh();
-+
-+ if (send)
-+ wg_packet_send_queued_handshake_initiation(peer, false);
-+}
-+
-+static unsigned int calculate_skb_padding(struct sk_buff *skb)
-+{
-+ /* We do this modulo business with the MTU, just in case the networking
-+ * layer gives us a packet that's bigger than the MTU. In that case, we
-+ * wouldn't want the final subtraction to overflow in the case of the
-+ * padded_size being clamped.
-+ */
-+ unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
-+ unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
-+
-+ if (padded_size > PACKET_CB(skb)->mtu)
-+ padded_size = PACKET_CB(skb)->mtu;
-+ return padded_size - last_unit;
-+}
-+
-+static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
-+{
-+ unsigned int padding_len, plaintext_len, trailer_len;
-+ struct scatterlist sg[MAX_SKB_FRAGS + 8];
-+ struct message_data *header;
-+ struct sk_buff *trailer;
-+ int num_frags;
-+
-+ /* Calculate lengths. */
-+ padding_len = calculate_skb_padding(skb);
-+ trailer_len = padding_len + noise_encrypted_len(0);
-+ plaintext_len = skb->len + padding_len;
-+
-+ /* Expand data section to have room for padding and auth tag. */
-+ num_frags = skb_cow_data(skb, trailer_len, &trailer);
-+ if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg)))
-+ return false;
-+
-+ /* Set the padding to zeros, and make sure it and the auth tag are part
-+ * of the skb.
-+ */
-+ memset(skb_tail_pointer(trailer), 0, padding_len);
-+
-+ /* Expand head section to have room for our header and the network
-+ * stack's headers.
-+ */
-+ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0))
-+ return false;
-+
-+ /* Finalize checksum calculation for the inner packet, if required. */
-+ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL &&
-+ skb_checksum_help(skb)))
-+ return false;
-+
-+ /* Only after checksumming can we safely add on the padding at the end
-+ * and the header.
-+ */
-+ skb_set_inner_network_header(skb, 0);
-+ header = (struct message_data *)skb_push(skb, sizeof(*header));
-+ header->header.type = cpu_to_le32(MESSAGE_DATA);
-+ header->key_idx = keypair->remote_index;
-+ header->counter = cpu_to_le64(PACKET_CB(skb)->nonce);
-+ pskb_put(skb, trailer, trailer_len);
-+
-+ /* Now we can encrypt the scattergather segments */
-+ sg_init_table(sg, num_frags);
-+ if (skb_to_sgvec(skb, sg, sizeof(struct message_data),
-+ noise_encrypted_len(plaintext_len)) <= 0)
-+ return false;
-+ return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0,
-+ PACKET_CB(skb)->nonce,
-+ keypair->sending.key);
-+}
-+
-+void wg_packet_send_keepalive(struct wg_peer *peer)
-+{
-+ struct sk_buff *skb;
-+
-+ if (skb_queue_empty(&peer->staged_packet_queue)) {
-+ skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH,
-+ GFP_ATOMIC);
-+ if (unlikely(!skb))
-+ return;
-+ skb_reserve(skb, DATA_PACKET_HEAD_ROOM);
-+ skb->dev = peer->device->dev;
-+ PACKET_CB(skb)->mtu = skb->dev->mtu;
-+ skb_queue_tail(&peer->staged_packet_queue, skb);
-+ net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr);
-+ }
-+
-+ wg_packet_send_staged_packets(peer);
-+}
-+
-+static void wg_packet_create_data_done(struct sk_buff *first,
-+ struct wg_peer *peer)
-+{
-+ struct sk_buff *skb, *next;
-+ bool is_keepalive, data_sent = false;
-+
-+ wg_timers_any_authenticated_packet_traversal(peer);
-+ wg_timers_any_authenticated_packet_sent(peer);
-+ skb_list_walk_safe(first, skb, next) {
-+ is_keepalive = skb->len == message_data_len(0);
-+ if (likely(!wg_socket_send_skb_to_peer(peer, skb,
-+ PACKET_CB(skb)->ds) && !is_keepalive))
-+ data_sent = true;
-+ }
-+
-+ if (likely(data_sent))
-+ wg_timers_data_sent(peer);
-+
-+ keep_key_fresh(peer);
-+}
-+
-+void wg_packet_tx_worker(struct work_struct *work)
-+{
-+ struct crypt_queue *queue = container_of(work, struct crypt_queue,
-+ work);
-+ struct noise_keypair *keypair;
-+ enum packet_state state;
-+ struct sk_buff *first;
-+ struct wg_peer *peer;
-+
-+ while ((first = __ptr_ring_peek(&queue->ring)) != NULL &&
-+ (state = atomic_read_acquire(&PACKET_CB(first)->state)) !=
-+ PACKET_STATE_UNCRYPTED) {
-+ __ptr_ring_discard_one(&queue->ring);
-+ peer = PACKET_PEER(first);
-+ keypair = PACKET_CB(first)->keypair;
-+
-+ if (likely(state == PACKET_STATE_CRYPTED))
-+ wg_packet_create_data_done(first, peer);
-+ else
-+ kfree_skb_list(first);
-+
-+ wg_noise_keypair_put(keypair, false);
-+ wg_peer_put(peer);
-+ }
-+}
-+
-+void wg_packet_encrypt_worker(struct work_struct *work)
-+{
-+ struct crypt_queue *queue = container_of(work, struct multicore_worker,
-+ work)->ptr;
-+ struct sk_buff *first, *skb, *next;
-+
-+ while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) {
-+ enum packet_state state = PACKET_STATE_CRYPTED;
-+
-+ skb_list_walk_safe(first, skb, next) {
-+ if (likely(encrypt_packet(skb,
-+ PACKET_CB(first)->keypair))) {
-+ wg_reset_packet(skb);
-+ } else {
-+ state = PACKET_STATE_DEAD;
-+ break;
-+ }
-+ }
-+ wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
-+ state);
-+
-+ }
-+}
-+
-+static void wg_packet_create_data(struct sk_buff *first)
-+{
-+ struct wg_peer *peer = PACKET_PEER(first);
-+ struct wg_device *wg = peer->device;
-+ int ret = -EINVAL;
-+
-+ rcu_read_lock_bh();
-+ if (unlikely(READ_ONCE(peer->is_dead)))
-+ goto err;
-+
-+ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue,
-+ &peer->tx_queue, first,
-+ wg->packet_crypt_wq,
-+ &wg->encrypt_queue.last_cpu);
-+ if (unlikely(ret == -EPIPE))
-+ wg_queue_enqueue_per_peer(&peer->tx_queue, first,
-+ PACKET_STATE_DEAD);
-+err:
-+ rcu_read_unlock_bh();
-+ if (likely(!ret || ret == -EPIPE))
-+ return;
-+ wg_noise_keypair_put(PACKET_CB(first)->keypair, false);
-+ wg_peer_put(peer);
-+ kfree_skb_list(first);
-+}
-+
-+void wg_packet_purge_staged_packets(struct wg_peer *peer)
-+{
-+ spin_lock_bh(&peer->staged_packet_queue.lock);
-+ peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen;
-+ __skb_queue_purge(&peer->staged_packet_queue);
-+ spin_unlock_bh(&peer->staged_packet_queue.lock);
-+}
-+
-+void wg_packet_send_staged_packets(struct wg_peer *peer)
-+{
-+ struct noise_symmetric_key *key;
-+ struct noise_keypair *keypair;
-+ struct sk_buff_head packets;
-+ struct sk_buff *skb;
-+
-+ /* Steal the current queue into our local one. */
-+ __skb_queue_head_init(&packets);
-+ spin_lock_bh(&peer->staged_packet_queue.lock);
-+ skb_queue_splice_init(&peer->staged_packet_queue, &packets);
-+ spin_unlock_bh(&peer->staged_packet_queue.lock);
-+ if (unlikely(skb_queue_empty(&packets)))
-+ return;
-+
-+ /* First we make sure we have a valid reference to a valid key. */
-+ rcu_read_lock_bh();
-+ keypair = wg_noise_keypair_get(
-+ rcu_dereference_bh(peer->keypairs.current_keypair));
-+ rcu_read_unlock_bh();
-+ if (unlikely(!keypair))
-+ goto out_nokey;
-+ key = &keypair->sending;
-+ if (unlikely(!READ_ONCE(key->is_valid)))
-+ goto out_nokey;
-+ if (unlikely(wg_birthdate_has_expired(key->birthdate,
-+ REJECT_AFTER_TIME)))
-+ goto out_invalid;
-+
-+ /* After we know we have a somewhat valid key, we now try to assign
-+ * nonces to all of the packets in the queue. If we can't assign nonces
-+ * for all of them, we just consider it a failure and wait for the next
-+ * handshake.
-+ */
-+ skb_queue_walk(&packets, skb) {
-+ /* 0 for no outer TOS: no leak. TODO: at some later point, we
-+ * might consider using flowi->tos as outer instead.
-+ */
-+ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
-+ PACKET_CB(skb)->nonce =
-+ atomic64_inc_return(&key->counter.counter) - 1;
-+ if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
-+ goto out_invalid;
-+ }
-+
-+ packets.prev->next = NULL;
-+ wg_peer_get(keypair->entry.peer);
-+ PACKET_CB(packets.next)->keypair = keypair;
-+ wg_packet_create_data(packets.next);
-+ return;
-+
-+out_invalid:
-+ WRITE_ONCE(key->is_valid, false);
-+out_nokey:
-+ wg_noise_keypair_put(keypair, false);
-+
-+ /* We orphan the packets if we're waiting on a handshake, so that they
-+ * don't block a socket's pool.
-+ */
-+ skb_queue_walk(&packets, skb)
-+ skb_orphan(skb);
-+ /* Then we put them back on the top of the queue. We're not too
-+ * concerned about accidentally getting things a little out of order if
-+ * packets are being added really fast, because this queue is for before
-+ * packets can even be sent and it's small anyway.
-+ */
-+ spin_lock_bh(&peer->staged_packet_queue.lock);
-+ skb_queue_splice(&packets, &peer->staged_packet_queue);
-+ spin_unlock_bh(&peer->staged_packet_queue.lock);
-+
-+ /* If we're exiting because there's something wrong with the key, it
-+ * means we should initiate a new handshake.
-+ */
-+ wg_packet_send_queued_handshake_initiation(peer, false);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/socket.c
-@@ -0,0 +1,437 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "device.h"
-+#include "peer.h"
-+#include "socket.h"
-+#include "queueing.h"
-+#include "messages.h"
-+
-+#include <linux/ctype.h>
-+#include <linux/net.h>
-+#include <linux/if_vlan.h>
-+#include <linux/if_ether.h>
-+#include <linux/inetdevice.h>
-+#include <net/udp_tunnel.h>
-+#include <net/ipv6.h>
-+
-+static int send4(struct wg_device *wg, struct sk_buff *skb,
-+ struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
-+{
-+ struct flowi4 fl = {
-+ .saddr = endpoint->src4.s_addr,
-+ .daddr = endpoint->addr4.sin_addr.s_addr,
-+ .fl4_dport = endpoint->addr4.sin_port,
-+ .flowi4_mark = wg->fwmark,
-+ .flowi4_proto = IPPROTO_UDP
-+ };
-+ struct rtable *rt = NULL;
-+ struct sock *sock;
-+ int ret = 0;
-+
-+ skb_mark_not_on_list(skb);
-+ skb->dev = wg->dev;
-+ skb->mark = wg->fwmark;
-+
-+ rcu_read_lock_bh();
-+ sock = rcu_dereference_bh(wg->sock4);
-+
-+ if (unlikely(!sock)) {
-+ ret = -ENONET;
-+ goto err;
-+ }
-+
-+ fl.fl4_sport = inet_sk(sock)->inet_sport;
-+
-+ if (cache)
-+ rt = dst_cache_get_ip4(cache, &fl.saddr);
-+
-+ if (!rt) {
-+ security_sk_classify_flow(sock, flowi4_to_flowi(&fl));
-+ if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0,
-+ fl.saddr, RT_SCOPE_HOST))) {
-+ endpoint->src4.s_addr = 0;
-+ *(__force __be32 *)&endpoint->src_if4 = 0;
-+ fl.saddr = 0;
-+ if (cache)
-+ dst_cache_reset(cache);
-+ }
-+ rt = ip_route_output_flow(sock_net(sock), &fl, sock);
-+ if (unlikely(endpoint->src_if4 && ((IS_ERR(rt) &&
-+ PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) &&
-+ rt->dst.dev->ifindex != endpoint->src_if4)))) {
-+ endpoint->src4.s_addr = 0;
-+ *(__force __be32 *)&endpoint->src_if4 = 0;
-+ fl.saddr = 0;
-+ if (cache)
-+ dst_cache_reset(cache);
-+ if (!IS_ERR(rt))
-+ ip_rt_put(rt);
-+ rt = ip_route_output_flow(sock_net(sock), &fl, sock);
-+ }
-+ if (unlikely(IS_ERR(rt))) {
-+ ret = PTR_ERR(rt);
-+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
-+ wg->dev->name, &endpoint->addr, ret);
-+ goto err;
-+ } else if (unlikely(rt->dst.dev == skb->dev)) {
-+ ip_rt_put(rt);
-+ ret = -ELOOP;
-+ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-+ wg->dev->name, &endpoint->addr);
-+ goto err;
-+ }
-+ if (cache)
-+ dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
-+ }
-+
-+ skb->ignore_df = 1;
-+ udp_tunnel_xmit_skb(rt, sock, skb, fl.saddr, fl.daddr, ds,
-+ ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport,
-+ fl.fl4_dport, false, false);
-+ goto out;
-+
-+err:
-+ kfree_skb(skb);
-+out:
-+ rcu_read_unlock_bh();
-+ return ret;
-+}
-+
-+static int send6(struct wg_device *wg, struct sk_buff *skb,
-+ struct endpoint *endpoint, u8 ds, struct dst_cache *cache)
-+{
-+#if IS_ENABLED(CONFIG_IPV6)
-+ struct flowi6 fl = {
-+ .saddr = endpoint->src6,
-+ .daddr = endpoint->addr6.sin6_addr,
-+ .fl6_dport = endpoint->addr6.sin6_port,
-+ .flowi6_mark = wg->fwmark,
-+ .flowi6_oif = endpoint->addr6.sin6_scope_id,
-+ .flowi6_proto = IPPROTO_UDP
-+ /* TODO: addr->sin6_flowinfo */
-+ };
-+ struct dst_entry *dst = NULL;
-+ struct sock *sock;
-+ int ret = 0;
-+
-+ skb_mark_not_on_list(skb);
-+ skb->dev = wg->dev;
-+ skb->mark = wg->fwmark;
-+
-+ rcu_read_lock_bh();
-+ sock = rcu_dereference_bh(wg->sock6);
-+
-+ if (unlikely(!sock)) {
-+ ret = -ENONET;
-+ goto err;
-+ }
-+
-+ fl.fl6_sport = inet_sk(sock)->inet_sport;
-+
-+ if (cache)
-+ dst = dst_cache_get_ip6(cache, &fl.saddr);
-+
-+ if (!dst) {
-+ security_sk_classify_flow(sock, flowi6_to_flowi(&fl));
-+ if (unlikely(!ipv6_addr_any(&fl.saddr) &&
-+ !ipv6_chk_addr(sock_net(sock), &fl.saddr, NULL, 0))) {
-+ endpoint->src6 = fl.saddr = in6addr_any;
-+ if (cache)
-+ dst_cache_reset(cache);
-+ }
-+ dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl,
-+ NULL);
-+ if (unlikely(IS_ERR(dst))) {
-+ ret = PTR_ERR(dst);
-+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
-+ wg->dev->name, &endpoint->addr, ret);
-+ goto err;
-+ } else if (unlikely(dst->dev == skb->dev)) {
-+ dst_release(dst);
-+ ret = -ELOOP;
-+ net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-+ wg->dev->name, &endpoint->addr);
-+ goto err;
-+ }
-+ if (cache)
-+ dst_cache_set_ip6(cache, dst, &fl.saddr);
-+ }
-+
-+ skb->ignore_df = 1;
-+ udp_tunnel6_xmit_skb(dst, sock, skb, skb->dev, &fl.saddr, &fl.daddr, ds,
-+ ip6_dst_hoplimit(dst), 0, fl.fl6_sport,
-+ fl.fl6_dport, false);
-+ goto out;
-+
-+err:
-+ kfree_skb(skb);
-+out:
-+ rcu_read_unlock_bh();
-+ return ret;
-+#else
-+ return -EAFNOSUPPORT;
-+#endif
-+}
-+
-+int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb, u8 ds)
-+{
-+ size_t skb_len = skb->len;
-+ int ret = -EAFNOSUPPORT;
-+
-+ read_lock_bh(&peer->endpoint_lock);
-+ if (peer->endpoint.addr.sa_family == AF_INET)
-+ ret = send4(peer->device, skb, &peer->endpoint, ds,
-+ &peer->endpoint_cache);
-+ else if (peer->endpoint.addr.sa_family == AF_INET6)
-+ ret = send6(peer->device, skb, &peer->endpoint, ds,
-+ &peer->endpoint_cache);
-+ else
-+ dev_kfree_skb(skb);
-+ if (likely(!ret))
-+ peer->tx_bytes += skb_len;
-+ read_unlock_bh(&peer->endpoint_lock);
-+
-+ return ret;
-+}
-+
-+int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *buffer,
-+ size_t len, u8 ds)
-+{
-+ struct sk_buff *skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);
-+
-+ if (unlikely(!skb))
-+ return -ENOMEM;
-+
-+ skb_reserve(skb, SKB_HEADER_LEN);
-+ skb_set_inner_network_header(skb, 0);
-+ skb_put_data(skb, buffer, len);
-+ return wg_socket_send_skb_to_peer(peer, skb, ds);
-+}
-+
-+int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg,
-+ struct sk_buff *in_skb, void *buffer,
-+ size_t len)
-+{
-+ int ret = 0;
-+ struct sk_buff *skb;
-+ struct endpoint endpoint;
-+
-+ if (unlikely(!in_skb))
-+ return -EINVAL;
-+ ret = wg_socket_endpoint_from_skb(&endpoint, in_skb);
-+ if (unlikely(ret < 0))
-+ return ret;
-+
-+ skb = alloc_skb(len + SKB_HEADER_LEN, GFP_ATOMIC);
-+ if (unlikely(!skb))
-+ return -ENOMEM;
-+ skb_reserve(skb, SKB_HEADER_LEN);
-+ skb_set_inner_network_header(skb, 0);
-+ skb_put_data(skb, buffer, len);
-+
-+ if (endpoint.addr.sa_family == AF_INET)
-+ ret = send4(wg, skb, &endpoint, 0, NULL);
-+ else if (endpoint.addr.sa_family == AF_INET6)
-+ ret = send6(wg, skb, &endpoint, 0, NULL);
-+ /* No other possibilities if the endpoint is valid, which it is,
-+ * as we checked above.
-+ */
-+
-+ return ret;
-+}
-+
-+int wg_socket_endpoint_from_skb(struct endpoint *endpoint,
-+ const struct sk_buff *skb)
-+{
-+ memset(endpoint, 0, sizeof(*endpoint));
-+ if (skb->protocol == htons(ETH_P_IP)) {
-+ endpoint->addr4.sin_family = AF_INET;
-+ endpoint->addr4.sin_port = udp_hdr(skb)->source;
-+ endpoint->addr4.sin_addr.s_addr = ip_hdr(skb)->saddr;
-+ endpoint->src4.s_addr = ip_hdr(skb)->daddr;
-+ endpoint->src_if4 = skb->skb_iif;
-+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
-+ endpoint->addr6.sin6_family = AF_INET6;
-+ endpoint->addr6.sin6_port = udp_hdr(skb)->source;
-+ endpoint->addr6.sin6_addr = ipv6_hdr(skb)->saddr;
-+ endpoint->addr6.sin6_scope_id = ipv6_iface_scope_id(
-+ &ipv6_hdr(skb)->saddr, skb->skb_iif);
-+ endpoint->src6 = ipv6_hdr(skb)->daddr;
-+ } else {
-+ return -EINVAL;
-+ }
-+ return 0;
-+}
-+
-+static bool endpoint_eq(const struct endpoint *a, const struct endpoint *b)
-+{
-+ return (a->addr.sa_family == AF_INET && b->addr.sa_family == AF_INET &&
-+ a->addr4.sin_port == b->addr4.sin_port &&
-+ a->addr4.sin_addr.s_addr == b->addr4.sin_addr.s_addr &&
-+ a->src4.s_addr == b->src4.s_addr && a->src_if4 == b->src_if4) ||
-+ (a->addr.sa_family == AF_INET6 &&
-+ b->addr.sa_family == AF_INET6 &&
-+ a->addr6.sin6_port == b->addr6.sin6_port &&
-+ ipv6_addr_equal(&a->addr6.sin6_addr, &b->addr6.sin6_addr) &&
-+ a->addr6.sin6_scope_id == b->addr6.sin6_scope_id &&
-+ ipv6_addr_equal(&a->src6, &b->src6)) ||
-+ unlikely(!a->addr.sa_family && !b->addr.sa_family);
-+}
-+
-+void wg_socket_set_peer_endpoint(struct wg_peer *peer,
-+ const struct endpoint *endpoint)
-+{
-+ /* First we check unlocked, in order to optimize, since it's pretty rare
-+ * that an endpoint will change. If we happen to be mid-write, and two
-+ * CPUs wind up writing the same thing or something slightly different,
-+ * it doesn't really matter much either.
-+ */
-+ if (endpoint_eq(endpoint, &peer->endpoint))
-+ return;
-+ write_lock_bh(&peer->endpoint_lock);
-+ if (endpoint->addr.sa_family == AF_INET) {
-+ peer->endpoint.addr4 = endpoint->addr4;
-+ peer->endpoint.src4 = endpoint->src4;
-+ peer->endpoint.src_if4 = endpoint->src_if4;
-+ } else if (endpoint->addr.sa_family == AF_INET6) {
-+ peer->endpoint.addr6 = endpoint->addr6;
-+ peer->endpoint.src6 = endpoint->src6;
-+ } else {
-+ goto out;
-+ }
-+ dst_cache_reset(&peer->endpoint_cache);
-+out:
-+ write_unlock_bh(&peer->endpoint_lock);
-+}
-+
-+void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer,
-+ const struct sk_buff *skb)
-+{
-+ struct endpoint endpoint;
-+
-+ if (!wg_socket_endpoint_from_skb(&endpoint, skb))
-+ wg_socket_set_peer_endpoint(peer, &endpoint);
-+}
-+
-+void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer)
-+{
-+ write_lock_bh(&peer->endpoint_lock);
-+ memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6));
-+ dst_cache_reset(&peer->endpoint_cache);
-+ write_unlock_bh(&peer->endpoint_lock);
-+}
-+
-+static int wg_receive(struct sock *sk, struct sk_buff *skb)
-+{
-+ struct wg_device *wg;
-+
-+ if (unlikely(!sk))
-+ goto err;
-+ wg = sk->sk_user_data;
-+ if (unlikely(!wg))
-+ goto err;
-+ wg_packet_receive(wg, skb);
-+ return 0;
-+
-+err:
-+ kfree_skb(skb);
-+ return 0;
-+}
-+
-+static void sock_free(struct sock *sock)
-+{
-+ if (unlikely(!sock))
-+ return;
-+ sk_clear_memalloc(sock);
-+ udp_tunnel_sock_release(sock->sk_socket);
-+}
-+
-+static void set_sock_opts(struct socket *sock)
-+{
-+ sock->sk->sk_allocation = GFP_ATOMIC;
-+ sock->sk->sk_sndbuf = INT_MAX;
-+ sk_set_memalloc(sock->sk);
-+}
-+
-+int wg_socket_init(struct wg_device *wg, u16 port)
-+{
-+ int ret;
-+ struct udp_tunnel_sock_cfg cfg = {
-+ .sk_user_data = wg,
-+ .encap_type = 1,
-+ .encap_rcv = wg_receive
-+ };
-+ struct socket *new4 = NULL, *new6 = NULL;
-+ struct udp_port_cfg port4 = {
-+ .family = AF_INET,
-+ .local_ip.s_addr = htonl(INADDR_ANY),
-+ .local_udp_port = htons(port),
-+ .use_udp_checksums = true
-+ };
-+#if IS_ENABLED(CONFIG_IPV6)
-+ int retries = 0;
-+ struct udp_port_cfg port6 = {
-+ .family = AF_INET6,
-+ .local_ip6 = IN6ADDR_ANY_INIT,
-+ .use_udp6_tx_checksums = true,
-+ .use_udp6_rx_checksums = true,
-+ .ipv6_v6only = true
-+ };
-+#endif
-+
-+#if IS_ENABLED(CONFIG_IPV6)
-+retry:
-+#endif
-+
-+ ret = udp_sock_create(wg->creating_net, &port4, &new4);
-+ if (ret < 0) {
-+ pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
-+ return ret;
-+ }
-+ set_sock_opts(new4);
-+ setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
-+
-+#if IS_ENABLED(CONFIG_IPV6)
-+ if (ipv6_mod_enabled()) {
-+ port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
-+ ret = udp_sock_create(wg->creating_net, &port6, &new6);
-+ if (ret < 0) {
-+ udp_tunnel_sock_release(new4);
-+ if (ret == -EADDRINUSE && !port && retries++ < 100)
-+ goto retry;
-+ pr_err("%s: Could not create IPv6 socket\n",
-+ wg->dev->name);
-+ return ret;
-+ }
-+ set_sock_opts(new6);
-+ setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
-+ }
-+#endif
-+
-+ wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
-+ return 0;
-+}
-+
-+void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
-+ struct sock *new6)
-+{
-+ struct sock *old4, *old6;
-+
-+ mutex_lock(&wg->socket_update_lock);
-+ old4 = rcu_dereference_protected(wg->sock4,
-+ lockdep_is_held(&wg->socket_update_lock));
-+ old6 = rcu_dereference_protected(wg->sock6,
-+ lockdep_is_held(&wg->socket_update_lock));
-+ rcu_assign_pointer(wg->sock4, new4);
-+ rcu_assign_pointer(wg->sock6, new6);
-+ if (new4)
-+ wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
-+ mutex_unlock(&wg->socket_update_lock);
-+ synchronize_rcu();
-+ synchronize_net();
-+ sock_free(old4);
-+ sock_free(old6);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/socket.h
-@@ -0,0 +1,44 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_SOCKET_H
-+#define _WG_SOCKET_H
-+
-+#include <linux/netdevice.h>
-+#include <linux/udp.h>
-+#include <linux/if_vlan.h>
-+#include <linux/if_ether.h>
-+
-+int wg_socket_init(struct wg_device *wg, u16 port);
-+void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
-+ struct sock *new6);
-+int wg_socket_send_buffer_to_peer(struct wg_peer *peer, void *data,
-+ size_t len, u8 ds);
-+int wg_socket_send_skb_to_peer(struct wg_peer *peer, struct sk_buff *skb,
-+ u8 ds);
-+int wg_socket_send_buffer_as_reply_to_skb(struct wg_device *wg,
-+ struct sk_buff *in_skb,
-+ void *out_buffer, size_t len);
-+
-+int wg_socket_endpoint_from_skb(struct endpoint *endpoint,
-+ const struct sk_buff *skb);
-+void wg_socket_set_peer_endpoint(struct wg_peer *peer,
-+ const struct endpoint *endpoint);
-+void wg_socket_set_peer_endpoint_from_skb(struct wg_peer *peer,
-+ const struct sk_buff *skb);
-+void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer);
-+
-+#if defined(CONFIG_DYNAMIC_DEBUG) || defined(DEBUG)
-+#define net_dbg_skb_ratelimited(fmt, dev, skb, ...) do { \
-+ struct endpoint __endpoint; \
-+ wg_socket_endpoint_from_skb(&__endpoint, skb); \
-+ net_dbg_ratelimited(fmt, dev, &__endpoint.addr, \
-+ ##__VA_ARGS__); \
-+ } while (0)
-+#else
-+#define net_dbg_skb_ratelimited(fmt, skb, ...)
-+#endif
-+
-+#endif /* _WG_SOCKET_H */
---- /dev/null
-+++ b/drivers/net/wireguard/timers.c
-@@ -0,0 +1,243 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#include "timers.h"
-+#include "device.h"
-+#include "peer.h"
-+#include "queueing.h"
-+#include "socket.h"
-+
-+/*
-+ * - Timer for retransmitting the handshake if we don't hear back after
-+ * `REKEY_TIMEOUT + jitter` ms.
-+ *
-+ * - Timer for sending empty packet if we have received a packet but after have
-+ * not sent one for `KEEPALIVE_TIMEOUT` ms.
-+ *
-+ * - Timer for initiating new handshake if we have sent a packet but after have
-+ * not received one (even empty) for `(KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) +
-+ * jitter` ms.
-+ *
-+ * - Timer for zeroing out all ephemeral keys after `(REJECT_AFTER_TIME * 3)` ms
-+ * if no new keys have been received.
-+ *
-+ * - Timer for, if enabled, sending an empty authenticated packet every user-
-+ * specified seconds.
-+ */
-+
-+static inline void mod_peer_timer(struct wg_peer *peer,
-+ struct timer_list *timer,
-+ unsigned long expires)
-+{
-+ rcu_read_lock_bh();
-+ if (likely(netif_running(peer->device->dev) &&
-+ !READ_ONCE(peer->is_dead)))
-+ mod_timer(timer, expires);
-+ rcu_read_unlock_bh();
-+}
-+
-+static void wg_expired_retransmit_handshake(struct timer_list *timer)
-+{
-+ struct wg_peer *peer = from_timer(peer, timer,
-+ timer_retransmit_handshake);
-+
-+ if (peer->timer_handshake_attempts > MAX_TIMER_HANDSHAKES) {
-+ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d attempts, giving up\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr, MAX_TIMER_HANDSHAKES + 2);
-+
-+ del_timer(&peer->timer_send_keepalive);
-+ /* We drop all packets without a keypair and don't try again,
-+ * if we try unsuccessfully for too long to make a handshake.
-+ */
-+ wg_packet_purge_staged_packets(peer);
-+
-+ /* We set a timer for destroying any residue that might be left
-+ * of a partial exchange.
-+ */
-+ if (!timer_pending(&peer->timer_zero_key_material))
-+ mod_peer_timer(peer, &peer->timer_zero_key_material,
-+ jiffies + REJECT_AFTER_TIME * 3 * HZ);
-+ } else {
-+ ++peer->timer_handshake_attempts;
-+ pr_debug("%s: Handshake for peer %llu (%pISpfsc) did not complete after %d seconds, retrying (try %d)\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr, REKEY_TIMEOUT,
-+ peer->timer_handshake_attempts + 1);
-+
-+ /* We clear the endpoint address src address, in case this is
-+ * the cause of trouble.
-+ */
-+ wg_socket_clear_peer_endpoint_src(peer);
-+
-+ wg_packet_send_queued_handshake_initiation(peer, true);
-+ }
-+}
-+
-+static void wg_expired_send_keepalive(struct timer_list *timer)
-+{
-+ struct wg_peer *peer = from_timer(peer, timer, timer_send_keepalive);
-+
-+ wg_packet_send_keepalive(peer);
-+ if (peer->timer_need_another_keepalive) {
-+ peer->timer_need_another_keepalive = false;
-+ mod_peer_timer(peer, &peer->timer_send_keepalive,
-+ jiffies + KEEPALIVE_TIMEOUT * HZ);
-+ }
-+}
-+
-+static void wg_expired_new_handshake(struct timer_list *timer)
-+{
-+ struct wg_peer *peer = from_timer(peer, timer, timer_new_handshake);
-+
-+ pr_debug("%s: Retrying handshake with peer %llu (%pISpfsc) because we stopped hearing back after %d seconds\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr, KEEPALIVE_TIMEOUT + REKEY_TIMEOUT);
-+ /* We clear the endpoint address src address, in case this is the cause
-+ * of trouble.
-+ */
-+ wg_socket_clear_peer_endpoint_src(peer);
-+ wg_packet_send_queued_handshake_initiation(peer, false);
-+}
-+
-+static void wg_expired_zero_key_material(struct timer_list *timer)
-+{
-+ struct wg_peer *peer = from_timer(peer, timer, timer_zero_key_material);
-+
-+ rcu_read_lock_bh();
-+ if (!READ_ONCE(peer->is_dead)) {
-+ wg_peer_get(peer);
-+ if (!queue_work(peer->device->handshake_send_wq,
-+ &peer->clear_peer_work))
-+ /* If the work was already on the queue, we want to drop
-+ * the extra reference.
-+ */
-+ wg_peer_put(peer);
-+ }
-+ rcu_read_unlock_bh();
-+}
-+
-+static void wg_queued_expired_zero_key_material(struct work_struct *work)
-+{
-+ struct wg_peer *peer = container_of(work, struct wg_peer,
-+ clear_peer_work);
-+
-+ pr_debug("%s: Zeroing out all keys for peer %llu (%pISpfsc), since we haven't received a new one in %d seconds\n",
-+ peer->device->dev->name, peer->internal_id,
-+ &peer->endpoint.addr, REJECT_AFTER_TIME * 3);
-+ wg_noise_handshake_clear(&peer->handshake);
-+ wg_noise_keypairs_clear(&peer->keypairs);
-+ wg_peer_put(peer);
-+}
-+
-+static void wg_expired_send_persistent_keepalive(struct timer_list *timer)
-+{
-+ struct wg_peer *peer = from_timer(peer, timer,
-+ timer_persistent_keepalive);
-+
-+ if (likely(peer->persistent_keepalive_interval))
-+ wg_packet_send_keepalive(peer);
-+}
-+
-+/* Should be called after an authenticated data packet is sent. */
-+void wg_timers_data_sent(struct wg_peer *peer)
-+{
-+ if (!timer_pending(&peer->timer_new_handshake))
-+ mod_peer_timer(peer, &peer->timer_new_handshake,
-+ jiffies + (KEEPALIVE_TIMEOUT + REKEY_TIMEOUT) * HZ +
-+ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES));
-+}
-+
-+/* Should be called after an authenticated data packet is received. */
-+void wg_timers_data_received(struct wg_peer *peer)
-+{
-+ if (likely(netif_running(peer->device->dev))) {
-+ if (!timer_pending(&peer->timer_send_keepalive))
-+ mod_peer_timer(peer, &peer->timer_send_keepalive,
-+ jiffies + KEEPALIVE_TIMEOUT * HZ);
-+ else
-+ peer->timer_need_another_keepalive = true;
-+ }
-+}
-+
-+/* Should be called after any type of authenticated packet is sent, whether
-+ * keepalive, data, or handshake.
-+ */
-+void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer)
-+{
-+ del_timer(&peer->timer_send_keepalive);
-+}
-+
-+/* Should be called after any type of authenticated packet is received, whether
-+ * keepalive, data, or handshake.
-+ */
-+void wg_timers_any_authenticated_packet_received(struct wg_peer *peer)
-+{
-+ del_timer(&peer->timer_new_handshake);
-+}
-+
-+/* Should be called after a handshake initiation message is sent. */
-+void wg_timers_handshake_initiated(struct wg_peer *peer)
-+{
-+ mod_peer_timer(peer, &peer->timer_retransmit_handshake,
-+ jiffies + REKEY_TIMEOUT * HZ +
-+ prandom_u32_max(REKEY_TIMEOUT_JITTER_MAX_JIFFIES));
-+}
-+
-+/* Should be called after a handshake response message is received and processed
-+ * or when getting key confirmation via the first data message.
-+ */
-+void wg_timers_handshake_complete(struct wg_peer *peer)
-+{
-+ del_timer(&peer->timer_retransmit_handshake);
-+ peer->timer_handshake_attempts = 0;
-+ peer->sent_lastminute_handshake = false;
-+ ktime_get_real_ts64(&peer->walltime_last_handshake);
-+}
-+
-+/* Should be called after an ephemeral key is created, which is before sending a
-+ * handshake response or after receiving a handshake response.
-+ */
-+void wg_timers_session_derived(struct wg_peer *peer)
-+{
-+ mod_peer_timer(peer, &peer->timer_zero_key_material,
-+ jiffies + REJECT_AFTER_TIME * 3 * HZ);
-+}
-+
-+/* Should be called before a packet with authentication, whether
-+ * keepalive, data, or handshakem is sent, or after one is received.
-+ */
-+void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer)
-+{
-+ if (peer->persistent_keepalive_interval)
-+ mod_peer_timer(peer, &peer->timer_persistent_keepalive,
-+ jiffies + peer->persistent_keepalive_interval * HZ);
-+}
-+
-+void wg_timers_init(struct wg_peer *peer)
-+{
-+ timer_setup(&peer->timer_retransmit_handshake,
-+ wg_expired_retransmit_handshake, 0);
-+ timer_setup(&peer->timer_send_keepalive, wg_expired_send_keepalive, 0);
-+ timer_setup(&peer->timer_new_handshake, wg_expired_new_handshake, 0);
-+ timer_setup(&peer->timer_zero_key_material,
-+ wg_expired_zero_key_material, 0);
-+ timer_setup(&peer->timer_persistent_keepalive,
-+ wg_expired_send_persistent_keepalive, 0);
-+ INIT_WORK(&peer->clear_peer_work, wg_queued_expired_zero_key_material);
-+ peer->timer_handshake_attempts = 0;
-+ peer->sent_lastminute_handshake = false;
-+ peer->timer_need_another_keepalive = false;
-+}
-+
-+void wg_timers_stop(struct wg_peer *peer)
-+{
-+ del_timer_sync(&peer->timer_retransmit_handshake);
-+ del_timer_sync(&peer->timer_send_keepalive);
-+ del_timer_sync(&peer->timer_new_handshake);
-+ del_timer_sync(&peer->timer_zero_key_material);
-+ del_timer_sync(&peer->timer_persistent_keepalive);
-+ flush_work(&peer->clear_peer_work);
-+}
---- /dev/null
-+++ b/drivers/net/wireguard/timers.h
-@@ -0,0 +1,31 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#ifndef _WG_TIMERS_H
-+#define _WG_TIMERS_H
-+
-+#include <linux/ktime.h>
-+
-+struct wg_peer;
-+
-+void wg_timers_init(struct wg_peer *peer);
-+void wg_timers_stop(struct wg_peer *peer);
-+void wg_timers_data_sent(struct wg_peer *peer);
-+void wg_timers_data_received(struct wg_peer *peer);
-+void wg_timers_any_authenticated_packet_sent(struct wg_peer *peer);
-+void wg_timers_any_authenticated_packet_received(struct wg_peer *peer);
-+void wg_timers_handshake_initiated(struct wg_peer *peer);
-+void wg_timers_handshake_complete(struct wg_peer *peer);
-+void wg_timers_session_derived(struct wg_peer *peer);
-+void wg_timers_any_authenticated_packet_traversal(struct wg_peer *peer);
-+
-+static inline bool wg_birthdate_has_expired(u64 birthday_nanoseconds,
-+ u64 expiration_seconds)
-+{
-+ return (s64)(birthday_nanoseconds + expiration_seconds * NSEC_PER_SEC)
-+ <= (s64)ktime_get_coarse_boottime_ns();
-+}
-+
-+#endif /* _WG_TIMERS_H */
---- /dev/null
-+++ b/drivers/net/wireguard/version.h
-@@ -0,0 +1 @@
-+#define WIREGUARD_VERSION "1.0.0"
---- /dev/null
-+++ b/include/uapi/linux/wireguard.h
-@@ -0,0 +1,196 @@
-+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ *
-+ * Documentation
-+ * =============
-+ *
-+ * The below enums and macros are for interfacing with WireGuard, using generic
-+ * netlink, with family WG_GENL_NAME and version WG_GENL_VERSION. It defines two
-+ * methods: get and set. Note that while they share many common attributes,
-+ * these two functions actually accept a slightly different set of inputs and
-+ * outputs.
-+ *
-+ * WG_CMD_GET_DEVICE
-+ * -----------------
-+ *
-+ * May only be called via NLM_F_REQUEST | NLM_F_DUMP. The command should contain
-+ * one but not both of:
-+ *
-+ * WGDEVICE_A_IFINDEX: NLA_U32
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ *
-+ * The kernel will then return several messages (NLM_F_MULTI) containing the
-+ * following tree of nested items:
-+ *
-+ * WGDEVICE_A_IFINDEX: NLA_U32
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
-+ * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
-+ * WGDEVICE_A_LISTEN_PORT: NLA_U16
-+ * WGDEVICE_A_FWMARK: NLA_U32
-+ * WGDEVICE_A_PEERS: NLA_NESTED
-+ * 0: NLA_NESTED
-+ * WGPEER_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
-+ * WGPEER_A_PRESHARED_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
-+ * WGPEER_A_ENDPOINT: NLA_MIN_LEN(struct sockaddr), struct sockaddr_in or struct sockaddr_in6
-+ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16
-+ * WGPEER_A_LAST_HANDSHAKE_TIME: NLA_EXACT_LEN, struct __kernel_timespec
-+ * WGPEER_A_RX_BYTES: NLA_U64
-+ * WGPEER_A_TX_BYTES: NLA_U64
-+ * WGPEER_A_ALLOWEDIPS: NLA_NESTED
-+ * 0: NLA_NESTED
-+ * WGALLOWEDIP_A_FAMILY: NLA_U16
-+ * WGALLOWEDIP_A_IPADDR: NLA_MIN_LEN(struct in_addr), struct in_addr or struct in6_addr
-+ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8
-+ * 0: NLA_NESTED
-+ * ...
-+ * 0: NLA_NESTED
-+ * ...
-+ * ...
-+ * WGPEER_A_PROTOCOL_VERSION: NLA_U32
-+ * 0: NLA_NESTED
-+ * ...
-+ * ...
-+ *
-+ * It is possible that all of the allowed IPs of a single peer will not
-+ * fit within a single netlink message. In that case, the same peer will
-+ * be written in the following message, except it will only contain
-+ * WGPEER_A_PUBLIC_KEY and WGPEER_A_ALLOWEDIPS. This may occur several
-+ * times in a row for the same peer. It is then up to the receiver to
-+ * coalesce adjacent peers. Likewise, it is possible that all peers will
-+ * not fit within a single message. So, subsequent peers will be sent
-+ * in following messages, except those will only contain WGDEVICE_A_IFNAME
-+ * and WGDEVICE_A_PEERS. It is then up to the receiver to coalesce these
-+ * messages to form the complete list of peers.
-+ *
-+ * Since this is an NLA_F_DUMP command, the final message will always be
-+ * NLMSG_DONE, even if an error occurs. However, this NLMSG_DONE message
-+ * contains an integer error code. It is either zero or a negative error
-+ * code corresponding to the errno.
-+ *
-+ * WG_CMD_SET_DEVICE
-+ * -----------------
-+ *
-+ * May only be called via NLM_F_REQUEST. The command should contain the
-+ * following tree of nested items, containing one but not both of
-+ * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME:
-+ *
-+ * WGDEVICE_A_IFINDEX: NLA_U32
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current
-+ * peers should be removed prior to adding the list below.
-+ * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove
-+ * WGDEVICE_A_LISTEN_PORT: NLA_U16, 0 to choose randomly
-+ * WGDEVICE_A_FWMARK: NLA_U32, 0 to disable
-+ * WGDEVICE_A_PEERS: NLA_NESTED
-+ * 0: NLA_NESTED
-+ * WGPEER_A_PUBLIC_KEY: len WG_KEY_LEN
-+ * WGPEER_A_FLAGS: NLA_U32, 0 and/or WGPEER_F_REMOVE_ME if the
-+ * specified peer should not exist at the end of the
-+ * operation, rather than added/updated and/or
-+ * WGPEER_F_REPLACE_ALLOWEDIPS if all current allowed
-+ * IPs of this peer should be removed prior to adding
-+ * the list below and/or WGPEER_F_UPDATE_ONLY if the
-+ * peer should only be set if it already exists.
-+ * WGPEER_A_PRESHARED_KEY: len WG_KEY_LEN, all zeros to remove
-+ * WGPEER_A_ENDPOINT: struct sockaddr_in or struct sockaddr_in6
-+ * WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL: NLA_U16, 0 to disable
-+ * WGPEER_A_ALLOWEDIPS: NLA_NESTED
-+ * 0: NLA_NESTED
-+ * WGALLOWEDIP_A_FAMILY: NLA_U16
-+ * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr
-+ * WGALLOWEDIP_A_CIDR_MASK: NLA_U8
-+ * 0: NLA_NESTED
-+ * ...
-+ * 0: NLA_NESTED
-+ * ...
-+ * ...
-+ * WGPEER_A_PROTOCOL_VERSION: NLA_U32, should not be set or used at
-+ * all by most users of this API, as the
-+ * most recent protocol will be used when
-+ * this is unset. Otherwise, must be set
-+ * to 1.
-+ * 0: NLA_NESTED
-+ * ...
-+ * ...
-+ *
-+ * It is possible that the amount of configuration data exceeds that of
-+ * the maximum message length accepted by the kernel. In that case, several
-+ * messages should be sent one after another, with each successive one
-+ * filling in information not contained in the prior. Note that if
-+ * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably
-+ * should not be specified in fragments that come after, so that the list
-+ * of peers is only cleared the first time but appened after. Likewise for
-+ * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message
-+ * of a peer, it likely should not be specified in subsequent fragments.
-+ *
-+ * If an error occurs, NLMSG_ERROR will reply containing an errno.
-+ */
-+
-+#ifndef _WG_UAPI_WIREGUARD_H
-+#define _WG_UAPI_WIREGUARD_H
-+
-+#define WG_GENL_NAME "wireguard"
-+#define WG_GENL_VERSION 1
-+
-+#define WG_KEY_LEN 32
-+
-+enum wg_cmd {
-+ WG_CMD_GET_DEVICE,
-+ WG_CMD_SET_DEVICE,
-+ __WG_CMD_MAX
-+};
-+#define WG_CMD_MAX (__WG_CMD_MAX - 1)
-+
-+enum wgdevice_flag {
-+ WGDEVICE_F_REPLACE_PEERS = 1U << 0,
-+ __WGDEVICE_F_ALL = WGDEVICE_F_REPLACE_PEERS
-+};
-+enum wgdevice_attribute {
-+ WGDEVICE_A_UNSPEC,
-+ WGDEVICE_A_IFINDEX,
-+ WGDEVICE_A_IFNAME,
-+ WGDEVICE_A_PRIVATE_KEY,
-+ WGDEVICE_A_PUBLIC_KEY,
-+ WGDEVICE_A_FLAGS,
-+ WGDEVICE_A_LISTEN_PORT,
-+ WGDEVICE_A_FWMARK,
-+ WGDEVICE_A_PEERS,
-+ __WGDEVICE_A_LAST
-+};
-+#define WGDEVICE_A_MAX (__WGDEVICE_A_LAST - 1)
-+
-+enum wgpeer_flag {
-+ WGPEER_F_REMOVE_ME = 1U << 0,
-+ WGPEER_F_REPLACE_ALLOWEDIPS = 1U << 1,
-+ WGPEER_F_UPDATE_ONLY = 1U << 2,
-+ __WGPEER_F_ALL = WGPEER_F_REMOVE_ME | WGPEER_F_REPLACE_ALLOWEDIPS |
-+ WGPEER_F_UPDATE_ONLY
-+};
-+enum wgpeer_attribute {
-+ WGPEER_A_UNSPEC,
-+ WGPEER_A_PUBLIC_KEY,
-+ WGPEER_A_PRESHARED_KEY,
-+ WGPEER_A_FLAGS,
-+ WGPEER_A_ENDPOINT,
-+ WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL,
-+ WGPEER_A_LAST_HANDSHAKE_TIME,
-+ WGPEER_A_RX_BYTES,
-+ WGPEER_A_TX_BYTES,
-+ WGPEER_A_ALLOWEDIPS,
-+ WGPEER_A_PROTOCOL_VERSION,
-+ __WGPEER_A_LAST
-+};
-+#define WGPEER_A_MAX (__WGPEER_A_LAST - 1)
-+
-+enum wgallowedip_attribute {
-+ WGALLOWEDIP_A_UNSPEC,
-+ WGALLOWEDIP_A_FAMILY,
-+ WGALLOWEDIP_A_IPADDR,
-+ WGALLOWEDIP_A_CIDR_MASK,
-+ __WGALLOWEDIP_A_LAST
-+};
-+#define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1)
-+
-+#endif /* _WG_UAPI_WIREGUARD_H */
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -0,0 +1,537 @@
-+#!/bin/bash
-+# SPDX-License-Identifier: GPL-2.0
-+#
-+# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+#
-+# This script tests the below topology:
-+#
-+# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐
-+# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │
-+# │ │ │ │ │ │
-+# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│
-+# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││
-+# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│
-+# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││
-+# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││
-+# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│
-+# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘
-+# └──────────────────────────────────┘
-+#
-+# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the
-+# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0
-+# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further
-+# details on how this is accomplished.
-+set -e
-+
-+exec 3>&1
-+export WG_HIDE_KEYS=never
-+netns0="wg-test-$$-0"
-+netns1="wg-test-$$-1"
-+netns2="wg-test-$$-2"
-+pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; }
-+pp() { pretty "" "$*"; "$@"; }
-+maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; }
-+n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; }
-+n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; }
-+n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; }
-+ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
-+ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
-+ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
-+sleep() { read -t "$1" -N 0 || true; }
-+waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
-+waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
-+waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
-+waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
-+
-+cleanup() {
-+ set +e
-+ exec 2>/dev/null
-+ printf "$orig_message_cost" > /proc/sys/net/core/message_cost
-+ ip0 link del dev wg0
-+ ip1 link del dev wg0
-+ ip2 link del dev wg0
-+ local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
-+ [[ -n $to_kill ]] && kill $to_kill
-+ pp ip netns del $netns1
-+ pp ip netns del $netns2
-+ pp ip netns del $netns0
-+ exit
-+}
-+
-+orig_message_cost="$(< /proc/sys/net/core/message_cost)"
-+trap cleanup EXIT
-+printf 0 > /proc/sys/net/core/message_cost
-+
-+ip netns del $netns0 2>/dev/null || true
-+ip netns del $netns1 2>/dev/null || true
-+ip netns del $netns2 2>/dev/null || true
-+pp ip netns add $netns0
-+pp ip netns add $netns1
-+pp ip netns add $netns2
-+ip0 link set up dev lo
-+
-+ip0 link add dev wg0 type wireguard
-+ip0 link set wg0 netns $netns1
-+ip0 link add dev wg0 type wireguard
-+ip0 link set wg0 netns $netns2
-+key1="$(pp wg genkey)"
-+key2="$(pp wg genkey)"
-+key3="$(pp wg genkey)"
-+pub1="$(pp wg pubkey <<<"$key1")"
-+pub2="$(pp wg pubkey <<<"$key2")"
-+pub3="$(pp wg pubkey <<<"$key3")"
-+psk="$(pp wg genpsk)"
-+[[ -n $key1 && -n $key2 && -n $psk ]]
-+
-+configure_peers() {
-+ ip1 addr add 192.168.241.1/24 dev wg0
-+ ip1 addr add fd00::1/24 dev wg0
-+
-+ ip2 addr add 192.168.241.2/24 dev wg0
-+ ip2 addr add fd00::2/24 dev wg0
-+
-+ n1 wg set wg0 \
-+ private-key <(echo "$key1") \
-+ listen-port 1 \
-+ peer "$pub2" \
-+ preshared-key <(echo "$psk") \
-+ allowed-ips 192.168.241.2/32,fd00::2/128
-+ n2 wg set wg0 \
-+ private-key <(echo "$key2") \
-+ listen-port 2 \
-+ peer "$pub1" \
-+ preshared-key <(echo "$psk") \
-+ allowed-ips 192.168.241.1/32,fd00::1/128
-+
-+ ip1 link set up dev wg0
-+ ip2 link set up dev wg0
-+}
-+configure_peers
-+
-+tests() {
-+ # Ping over IPv4
-+ n2 ping -c 10 -f -W 1 192.168.241.1
-+ n1 ping -c 10 -f -W 1 192.168.241.2
-+
-+ # Ping over IPv6
-+ n2 ping6 -c 10 -f -W 1 fd00::1
-+ n1 ping6 -c 10 -f -W 1 fd00::2
-+
-+ # TCP over IPv4
-+ n2 iperf3 -s -1 -B 192.168.241.2 &
-+ waitiperf $netns2
-+ n1 iperf3 -Z -t 3 -c 192.168.241.2
-+
-+ # TCP over IPv6
-+ n1 iperf3 -s -1 -B fd00::1 &
-+ waitiperf $netns1
-+ n2 iperf3 -Z -t 3 -c fd00::1
-+
-+ # UDP over IPv4
-+ n1 iperf3 -s -1 -B 192.168.241.1 &
-+ waitiperf $netns1
-+ n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1
-+
-+ # UDP over IPv6
-+ n2 iperf3 -s -1 -B fd00::2 &
-+ waitiperf $netns2
-+ n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
-+}
-+
-+[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
-+big_mtu=$(( 34816 - 1500 + $orig_mtu ))
-+
-+# Test using IPv4 as outer transport
-+n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
-+n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1
-+# Before calling tests, we first make sure that the stats counters and timestamper are working
-+n2 ping -c 10 -f -W 1 192.168.241.1
-+{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0)
-+(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) ))
-+{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0)
-+(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) ))
-+read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer)
-+(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) ))
-+read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer)
-+(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) ))
-+read _ timestamp < <(n1 wg show wg0 latest-handshakes)
-+(( timestamp != 0 ))
-+
-+tests
-+ip1 link set wg0 mtu $big_mtu
-+ip2 link set wg0 mtu $big_mtu
-+tests
-+
-+ip1 link set wg0 mtu $orig_mtu
-+ip2 link set wg0 mtu $orig_mtu
-+
-+# Test using IPv6 as outer transport
-+n1 wg set wg0 peer "$pub2" endpoint [::1]:2
-+n2 wg set wg0 peer "$pub1" endpoint [::1]:1
-+tests
-+ip1 link set wg0 mtu $big_mtu
-+ip2 link set wg0 mtu $big_mtu
-+tests
-+
-+# Test that route MTUs work with the padding
-+ip1 link set wg0 mtu 1300
-+ip2 link set wg0 mtu 1300
-+n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
-+n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1
-+n0 iptables -A INPUT -m length --length 1360 -j DROP
-+n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299
-+n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299
-+n2 ping -c 1 -W 1 -s 1269 192.168.241.1
-+n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299
-+n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299
-+n0 iptables -F INPUT
-+
-+ip1 link set wg0 mtu $orig_mtu
-+ip2 link set wg0 mtu $orig_mtu
-+
-+# Test using IPv4 that roaming works
-+ip0 -4 addr del 127.0.0.1/8 dev lo
-+ip0 -4 addr add 127.212.121.99/8 dev lo
-+n1 wg set wg0 listen-port 9999
-+n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2
-+n1 ping6 -W 1 -c 1 fd00::2
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]]
-+
-+# Test using IPv6 that roaming works
-+n1 wg set wg0 listen-port 9998
-+n1 wg set wg0 peer "$pub2" endpoint [::1]:2
-+n1 ping -W 1 -c 1 192.168.241.2
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]]
-+
-+# Test that crypto-RP filter works
-+n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24
-+exec 4< <(n1 ncat -l -u -p 1111)
-+ncat_pid=$!
-+waitncatudp $netns1
-+n2 ncat -u 192.168.241.1 1111 <<<"X"
-+read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]]
-+kill $ncat_pid
-+more_specific_key="$(pp wg genkey | pp wg pubkey)"
-+n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32
-+n2 wg set wg0 listen-port 9997
-+exec 4< <(n1 ncat -l -u -p 1111)
-+ncat_pid=$!
-+waitncatudp $netns1
-+n2 ncat -u 192.168.241.1 1111 <<<"X"
-+! read -r -N 1 -t 1 out <&4 || false
-+kill $ncat_pid
-+n1 wg set wg0 peer "$more_specific_key" remove
-+[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]]
-+
-+# Test that we can change private keys keys and immediately handshake
-+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2
-+n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32
-+n1 ping -W 1 -c 1 192.168.241.2
-+n1 wg set wg0 private-key <(echo "$key3")
-+n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
-+n1 ping -W 1 -c 1 192.168.241.2
-+
-+ip1 link del wg0
-+ip2 link del wg0
-+
-+# Test using NAT. We now change the topology to this:
-+# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐
-+# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │
-+# │ │ │ │ │ │
-+# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │
-+# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │
-+# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │
-+# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │
-+# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │
-+# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │
-+# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘
-+
-+ip1 link add dev wg0 type wireguard
-+ip2 link add dev wg0 type wireguard
-+configure_peers
-+
-+ip0 link add vethrc type veth peer name vethc
-+ip0 link add vethrs type veth peer name veths
-+ip0 link set vethc netns $netns1
-+ip0 link set veths netns $netns2
-+ip0 link set vethrc up
-+ip0 link set vethrs up
-+ip0 addr add 192.168.1.1/24 dev vethrc
-+ip0 addr add 10.0.0.1/24 dev vethrs
-+ip1 addr add 192.168.1.100/24 dev vethc
-+ip1 link set vethc up
-+ip1 route add default via 192.168.1.1
-+ip2 addr add 10.0.0.100/24 dev veths
-+ip2 link set veths up
-+waitiface $netns0 vethrc
-+waitiface $netns0 vethrs
-+waitiface $netns1 vethc
-+waitiface $netns2 veths
-+
-+n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
-+n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout'
-+n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream'
-+n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1
-+
-+n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1
-+n1 ping -W 1 -c 1 192.168.241.2
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
-+# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`).
-+pp sleep 3
-+n2 ping -W 1 -c 1 192.168.241.1
-+n1 wg set wg0 peer "$pub2" persistent-keepalive 0
-+
-+# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
-+ip1 -6 addr add fc00::9/96 dev vethc
-+ip1 -6 route add default via fc00::1
-+ip2 -4 addr add 192.168.99.7/32 dev wg0
-+ip2 -6 addr add abab::1111/128 dev wg0
-+n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111
-+ip1 -6 route add default dev wg0 table 51820
-+ip1 -6 rule add not fwmark 51820 table 51820
-+ip1 -6 rule add table main suppress_prefixlength 0
-+ip1 -4 route add default dev wg0 table 51820
-+ip1 -4 rule add not fwmark 51820 table 51820
-+ip1 -4 rule add table main suppress_prefixlength 0
-+# suppress_prefixlength only got added in 3.12, and we want to support 3.10+.
-+if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then
-+ # Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
-+ n1 ping -W 1 -c 100 -f 192.168.99.7
-+ n1 ping -W 1 -c 100 -f abab::1111
-+fi
-+
-+n0 iptables -t nat -F
-+ip0 link del vethrc
-+ip0 link del vethrs
-+ip1 link del wg0
-+ip2 link del wg0
-+
-+# Test that saddr routing is sticky but not too sticky, changing to this topology:
-+# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐
-+# │ $ns1 namespace │ │ $ns2 namespace │
-+# │ │ │ │
-+# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │
-+# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │
-+# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │
-+# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │
-+# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │
-+# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │
-+# └────────────────────────────────────────┘ └────────────────────────────────────────┘
-+
-+ip1 link add dev wg0 type wireguard
-+ip2 link add dev wg0 type wireguard
-+configure_peers
-+ip1 link add veth1 type veth peer name veth2
-+ip1 link set veth2 netns $netns2
-+n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad'
-+n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad'
-+n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad'
-+n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad'
-+n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries'
-+
-+# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed
-+ip1 addr add 10.0.0.1/24 dev veth1
-+ip1 addr add fd00:aa::1/96 dev veth1
-+ip2 addr add 10.0.0.2/24 dev veth2
-+ip2 addr add fd00:aa::2/96 dev veth2
-+ip1 link set veth1 up
-+ip2 link set veth2 up
-+waitiface $netns1 veth1
-+waitiface $netns2 veth2
-+n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2
-+n1 ping -W 1 -c 1 192.168.241.2
-+ip1 addr add 10.0.0.10/24 dev veth1
-+ip1 addr del 10.0.0.1/24 dev veth1
-+n1 ping -W 1 -c 1 192.168.241.2
-+n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2
-+n1 ping -W 1 -c 1 192.168.241.2
-+ip1 addr add fd00:aa::10/96 dev veth1
-+ip1 addr del fd00:aa::1/96 dev veth1
-+n1 ping -W 1 -c 1 192.168.241.2
-+
-+# Now we show that we can successfully do reply to sender routing
-+ip1 link set veth1 down
-+ip2 link set veth2 down
-+ip1 addr flush dev veth1
-+ip2 addr flush dev veth2
-+ip1 addr add 10.0.0.1/24 dev veth1
-+ip1 addr add 10.0.0.2/24 dev veth1
-+ip1 addr add fd00:aa::1/96 dev veth1
-+ip1 addr add fd00:aa::2/96 dev veth1
-+ip2 addr add 10.0.0.3/24 dev veth2
-+ip2 addr add fd00:aa::3/96 dev veth2
-+ip1 link set veth1 up
-+ip2 link set veth2 up
-+waitiface $netns1 veth1
-+waitiface $netns2 veth2
-+n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
-+n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]]
-+n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]]
-+n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]]
-+
-+# What happens if the inbound destination address belongs to a different interface as the default route?
-+ip1 link add dummy0 type dummy
-+ip1 addr add 10.50.0.1/24 dev dummy0
-+ip1 link set dummy0 up
-+ip2 route add 10.50.0.0/24 dev veth2
-+n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1
-+n2 ping -W 1 -c 1 192.168.241.1
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]]
-+
-+ip1 link del dummy0
-+ip1 addr flush dev veth1
-+ip2 addr flush dev veth2
-+ip1 route flush dev veth1
-+ip2 route flush dev veth2
-+
-+# Now we see what happens if another interface route takes precedence over an ongoing one
-+ip1 link add veth3 type veth peer name veth4
-+ip1 link set veth4 netns $netns2
-+ip1 addr add 10.0.0.1/24 dev veth1
-+ip2 addr add 10.0.0.2/24 dev veth2
-+ip1 addr add 10.0.0.3/24 dev veth3
-+ip1 link set veth1 up
-+ip2 link set veth2 up
-+ip1 link set veth3 up
-+ip2 link set veth4 up
-+waitiface $netns1 veth1
-+waitiface $netns2 veth2
-+waitiface $netns1 veth3
-+waitiface $netns2 veth4
-+ip1 route flush dev veth1
-+ip1 route flush dev veth3
-+ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2
-+n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2
-+n1 ping -W 1 -c 1 192.168.241.2
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]]
-+ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1
-+n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter'
-+n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter'
-+n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter'
-+n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter'
-+n1 ping -W 1 -c 1 192.168.241.2
-+[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]]
-+
-+ip1 link del veth1
-+ip1 link del veth3
-+ip1 link del wg0
-+ip2 link del wg0
-+
-+# We test that Netlink/IPC is working properly by doing things that usually cause split responses
-+ip0 link add dev wg0 type wireguard
-+config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" )
-+for a in {1..255}; do
-+ for b in {0..255}; do
-+ config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" )
-+ done
-+done
-+n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
-+i=0
-+for ip in $(n0 wg show wg0 allowed-ips); do
-+ ((++i))
-+done
-+((i == 255*256*2+1))
-+ip0 link del wg0
-+ip0 link add dev wg0 type wireguard
-+config=( "[Interface]" "PrivateKey=$(wg genkey)" )
-+for a in {1..40}; do
-+ config+=( "[Peer]" "PublicKey=$(wg genkey)" )
-+ for b in {1..52}; do
-+ config+=( "AllowedIPs=$a.$b.0.0/16" )
-+ done
-+done
-+n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
-+i=0
-+while read -r line; do
-+ j=0
-+ for ip in $line; do
-+ ((++j))
-+ done
-+ ((j == 53))
-+ ((++i))
-+done < <(n0 wg show wg0 allowed-ips)
-+((i == 40))
-+ip0 link del wg0
-+ip0 link add wg0 type wireguard
-+config=( )
-+for i in {1..29}; do
-+ config+=( "[Peer]" "PublicKey=$(wg genkey)" )
-+done
-+config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" )
-+n0 wg setconf wg0 <(printf '%s\n' "${config[@]}")
-+n0 wg showconf wg0 > /dev/null
-+ip0 link del wg0
-+
-+allowedips=( )
-+for i in {1..197}; do
-+ allowedips+=( abcd::$i )
-+done
-+saved_ifs="$IFS"
-+IFS=,
-+allowedips="${allowedips[*]}"
-+IFS="$saved_ifs"
-+ip0 link add wg0 type wireguard
-+n0 wg set wg0 peer "$pub1"
-+n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips"
-+{
-+ read -r pub allowedips
-+ [[ $pub == "$pub1" && $allowedips == "(none)" ]]
-+ read -r pub allowedips
-+ [[ $pub == "$pub2" ]]
-+ i=0
-+ for _ in $allowedips; do
-+ ((++i))
-+ done
-+ ((i == 197))
-+} < <(n0 wg show wg0 allowed-ips)
-+ip0 link del wg0
-+
-+! n0 wg show doesnotexist || false
-+
-+ip0 link add wg0 type wireguard
-+n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk")
-+[[ $(n0 wg show wg0 private-key) == "$key1" ]]
-+[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]]
-+n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null
-+[[ $(n0 wg show wg0 private-key) == "(none)" ]]
-+[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]]
-+n0 wg set wg0 peer "$pub2"
-+n0 wg set wg0 private-key <(echo "$key2")
-+[[ $(n0 wg show wg0 public-key) == "$pub2" ]]
-+[[ -z $(n0 wg show wg0 peers) ]]
-+n0 wg set wg0 peer "$pub2"
-+[[ -z $(n0 wg show wg0 peers) ]]
-+n0 wg set wg0 private-key <(echo "$key1")
-+n0 wg set wg0 peer "$pub2"
-+[[ $(n0 wg show wg0 peers) == "$pub2" ]]
-+n0 wg set wg0 private-key <(echo "/${key1:1}")
-+[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]]
-+n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16
-+n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0
-+n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
-+n0 wg set wg0 peer "$pub2" allowed-ips ::/0
-+ip0 link del wg0
-+
-+declare -A objects
-+while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
-+ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue
-+ objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}"
-+done < /dev/kmsg
-+alldeleted=1
-+for object in "${!objects[@]}"; do
-+ if [[ ${objects["$object"]} != *createddestroyed ]]; then
-+ echo "Error: $object: merely ${objects["$object"]}" >&3
-+ alldeleted=0
-+ fi
-+done
-+[[ $alldeleted -eq 1 ]]
-+pretty "" "Objects that were created were also destroyed."
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Sun, 15 Dec 2019 22:08:01 +0100
+Subject: [PATCH] wireguard: Kconfig: select parent dependency for crypto
+
+commit d7c68a38bb4f9b7c1a2e4a772872c752ee5c44a6 upstream.
+
+This fixes the crypto selection submenu depenencies. Otherwise, we'd
+wind up issuing warnings in which certain dependencies we also select
+couldn't be satisfied. This condition was triggered by the addition of
+the test suite autobuilder in the previous commit.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/Kconfig | 2 ++
+ 1 file changed, 2 insertions(+)
+
+--- a/drivers/net/Kconfig
++++ b/drivers/net/Kconfig
+@@ -85,6 +85,8 @@ config WIREGUARD
+ select CRYPTO_POLY1305_X86_64 if X86 && 64BIT
+ select CRYPTO_BLAKE2S_X86 if X86 && 64BIT
+ select CRYPTO_CURVE25519_X86 if X86 && 64BIT
++ select ARM_CRYPTO if ARM
++ select ARM64_CRYPTO if ARM64
+ select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
+ select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_POLY1305_ARM if ARM
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Josh Soref <jsoref@gmail.com>
+Date: Sun, 15 Dec 2019 22:08:02 +0100
+Subject: [PATCH] wireguard: global: fix spelling mistakes in comments
+
+commit a2ec8b5706944d228181c8b91d815f41d6dd8e7b upstream.
+
+This fixes two spelling errors in source code comments.
+
+Signed-off-by: Josh Soref <jsoref@gmail.com>
+[Jason: rewrote commit message]
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 2 +-
+ include/uapi/linux/wireguard.h | 8 ++++----
+ 2 files changed, 5 insertions(+), 5 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -380,7 +380,7 @@ static void wg_packet_consume_data_done(
+ /* We've already verified the Poly1305 auth tag, which means this packet
+ * was not modified in transit. We can therefore tell the networking
+ * stack that all checksums of every layer of encapsulation have already
+- * been checked "by the hardware" and therefore is unneccessary to check
++ * been checked "by the hardware" and therefore is unnecessary to check
+ * again in software.
+ */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+--- a/include/uapi/linux/wireguard.h
++++ b/include/uapi/linux/wireguard.h
+@@ -18,13 +18,13 @@
+ * one but not both of:
+ *
+ * WGDEVICE_A_IFINDEX: NLA_U32
+- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
+ *
+ * The kernel will then return several messages (NLM_F_MULTI) containing the
+ * following tree of nested items:
+ *
+ * WGDEVICE_A_IFINDEX: NLA_U32
+- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
+ * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
+ * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
+ * WGDEVICE_A_LISTEN_PORT: NLA_U16
+@@ -77,7 +77,7 @@
+ * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME:
+ *
+ * WGDEVICE_A_IFINDEX: NLA_U32
+- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
++ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
+ * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current
+ * peers should be removed prior to adding the list below.
+ * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove
+@@ -121,7 +121,7 @@
+ * filling in information not contained in the prior. Note that if
+ * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably
+ * should not be specified in fragments that come after, so that the list
+- * of peers is only cleared the first time but appened after. Likewise for
++ * of peers is only cleared the first time but appended after. Likewise for
+ * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message
+ * of a peer, it likely should not be specified in subsequent fragments.
+ *
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Sun, 15 Dec 2019 22:08:00 +0100
-Subject: [PATCH] wireguard: selftests: import harness makefile for test suite
-
-commit 65d88d04114bca7d85faebd5fed61069cb2b632c upstream.
-
-WireGuard has been using this on build.wireguard.com for the last
-several years with considerable success. It allows for very quick and
-iterative development cycles, and supports several platforms.
-
-To run the test suite on your current platform in QEMU:
-
- $ make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
-
-To run it with KASAN and such turned on:
-
- $ DEBUG_KERNEL=yes make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
-
-To run it emulated for another platform in QEMU:
-
- $ ARCH=arm make -C tools/testing/selftests/wireguard/qemu -j$(nproc)
-
-At the moment, we support aarch64_be, aarch64, arm, armeb, i686, m68k,
-mips64, mips64el, mips, mipsel, powerpc64le, powerpc, and x86_64.
-
-The system supports incremental rebuilding, so it should be very fast to
-change a single file and then test it out and have immediate feedback.
-
-This requires for the right toolchain and qemu to be installed prior.
-I've had success with those from musl.cc.
-
-This is tailored for WireGuard at the moment, though later projects
-might generalize it for other network testing.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- .../selftests/wireguard/qemu/.gitignore | 2 +
- .../testing/selftests/wireguard/qemu/Makefile | 385 ++++++++++++++++++
- .../wireguard/qemu/arch/aarch64.config | 5 +
- .../wireguard/qemu/arch/aarch64_be.config | 6 +
- .../selftests/wireguard/qemu/arch/arm.config | 9 +
- .../wireguard/qemu/arch/armeb.config | 10 +
- .../selftests/wireguard/qemu/arch/i686.config | 5 +
- .../selftests/wireguard/qemu/arch/m68k.config | 9 +
- .../selftests/wireguard/qemu/arch/mips.config | 11 +
- .../wireguard/qemu/arch/mips64.config | 14 +
- .../wireguard/qemu/arch/mips64el.config | 15 +
- .../wireguard/qemu/arch/mipsel.config | 12 +
- .../wireguard/qemu/arch/powerpc.config | 10 +
- .../wireguard/qemu/arch/powerpc64le.config | 12 +
- .../wireguard/qemu/arch/x86_64.config | 5 +
- .../selftests/wireguard/qemu/debug.config | 67 +++
- tools/testing/selftests/wireguard/qemu/init.c | 284 +++++++++++++
- .../selftests/wireguard/qemu/kernel.config | 86 ++++
- 18 files changed, 947 insertions(+)
- create mode 100644 tools/testing/selftests/wireguard/qemu/.gitignore
- create mode 100644 tools/testing/selftests/wireguard/qemu/Makefile
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/arm.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/armeb.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/i686.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/m68k.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mips64el.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/mipsel.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/arch/x86_64.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/debug.config
- create mode 100644 tools/testing/selftests/wireguard/qemu/init.c
- create mode 100644 tools/testing/selftests/wireguard/qemu/kernel.config
-
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/.gitignore
-@@ -0,0 +1,2 @@
-+build/
-+distfiles/
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/Makefile
-@@ -0,0 +1,385 @@
-+# SPDX-License-Identifier: GPL-2.0
-+#
-+# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+
-+PWD := $(shell pwd)
-+
-+CHOST := $(shell gcc -dumpmachine)
-+ifneq (,$(ARCH))
-+CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
-+ifeq (,$(CBUILD))
-+$(error The toolchain for $(ARCH) is not installed)
-+endif
-+else
-+CBUILD := $(CHOST)
-+ARCH := $(firstword $(subst -, ,$(CBUILD)))
-+endif
-+
-+# Set these from the environment to override
-+KERNEL_PATH ?= $(PWD)/../../../../..
-+BUILD_PATH ?= $(PWD)/build/$(ARCH)
-+DISTFILES_PATH ?= $(PWD)/distfiles
-+NR_CPUS ?= 4
-+
-+MIRROR := https://download.wireguard.com/qemu-test/distfiles/
-+
-+default: qemu
-+
-+# variable name, tarball project name, version, tarball extension, default URI base
-+define tar_download =
-+$(1)_VERSION := $(3)
-+$(1)_NAME := $(2)-$$($(1)_VERSION)
-+$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4)
-+$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME)
-+$(call file_download,$$($(1)_NAME)$(4),$(5),$(6))
-+endef
-+
-+define file_download =
-+$(DISTFILES_PATH)/$(1):
-+ mkdir -p $(DISTFILES_PATH)
-+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
-+ if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
-+endef
-+
-+$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61))
-+$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
-+$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f))
-+$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
-+$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2))
-+$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5))
-+$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21))
-+$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a))
-+$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071))
-+
-+KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
-+rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-+WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*)
-+
-+export CFLAGS ?= -O3 -pipe
-+export LDFLAGS ?=
-+export CPPFLAGS := -I$(BUILD_PATH)/include
-+
-+ifeq ($(CHOST),$(CBUILD))
-+CROSS_COMPILE_FLAG := --host=$(CHOST)
-+NOPIE_GCC := gcc -fno-PIE
-+CFLAGS += -march=native
-+STRIP := strip
-+else
-+$(info Cross compilation: building for $(CBUILD) using $(CHOST))
-+CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
-+export CROSS_COMPILE=$(CBUILD)-
-+NOPIE_GCC := $(CBUILD)-gcc -fno-PIE
-+STRIP := $(CBUILD)-strip
-+endif
-+ifeq ($(ARCH),aarch64)
-+QEMU_ARCH := aarch64
-+KERNEL_ARCH := arm64
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
-+else
-+QEMU_MACHINE := -cpu cortex-a53 -machine virt
-+CFLAGS += -march=armv8-a -mtune=cortex-a53
-+endif
-+else ifeq ($(ARCH),aarch64_be)
-+QEMU_ARCH := aarch64
-+KERNEL_ARCH := arm64
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
-+else
-+QEMU_MACHINE := -cpu cortex-a53 -machine virt
-+CFLAGS += -march=armv8-a -mtune=cortex-a53
-+endif
-+else ifeq ($(ARCH),arm)
-+QEMU_ARCH := arm
-+KERNEL_ARCH := arm
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
-+else
-+QEMU_MACHINE := -cpu cortex-a15 -machine virt
-+CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux
-+endif
-+else ifeq ($(ARCH),armeb)
-+QEMU_ARCH := arm
-+KERNEL_ARCH := arm
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
-+else
-+QEMU_MACHINE := -cpu cortex-a15 -machine virt
-+CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian.
-+LDFLAGS += -Wl,--be8
-+endif
-+else ifeq ($(ARCH),x86_64)
-+QEMU_ARCH := x86_64
-+KERNEL_ARCH := x86_64
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine q35,accel=kvm
-+else
-+QEMU_MACHINE := -cpu Skylake-Server -machine q35
-+CFLAGS += -march=skylake-avx512
-+endif
-+else ifeq ($(ARCH),i686)
-+QEMU_ARCH := i386
-+KERNEL_ARCH := x86
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
-+ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST))
-+QEMU_MACHINE := -cpu host -machine q35,accel=kvm
-+else
-+QEMU_MACHINE := -cpu coreduo -machine q35
-+CFLAGS += -march=prescott
-+endif
-+else ifeq ($(ARCH),mips64)
-+QEMU_ARCH := mips64
-+KERNEL_ARCH := mips
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine malta,accel=kvm
-+CFLAGS += -EB
-+else
-+QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
-+CFLAGS += -march=mips64r2 -EB
-+endif
-+else ifeq ($(ARCH),mips64el)
-+QEMU_ARCH := mips64el
-+KERNEL_ARCH := mips
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine malta,accel=kvm
-+CFLAGS += -EL
-+else
-+QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
-+CFLAGS += -march=mips64r2 -EL
-+endif
-+else ifeq ($(ARCH),mips)
-+QEMU_ARCH := mips
-+KERNEL_ARCH := mips
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine malta,accel=kvm
-+CFLAGS += -EB
-+else
-+QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
-+CFLAGS += -march=mips32r2 -EB
-+endif
-+else ifeq ($(ARCH),mipsel)
-+QEMU_ARCH := mipsel
-+KERNEL_ARCH := mips
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host -machine malta,accel=kvm
-+CFLAGS += -EL
-+else
-+QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
-+CFLAGS += -march=mips32r2 -EL
-+endif
-+else ifeq ($(ARCH),powerpc64le)
-+QEMU_ARCH := ppc64
-+KERNEL_ARCH := powerpc
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
-+else
-+QEMU_MACHINE := -machine pseries
-+endif
-+CFLAGS += -mcpu=powerpc64le -mlong-double-64
-+else ifeq ($(ARCH),powerpc)
-+QEMU_ARCH := ppc
-+KERNEL_ARCH := powerpc
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
-+else
-+QEMU_MACHINE := -machine ppce500
-+endif
-+CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt
-+else ifeq ($(ARCH),m68k)
-+QEMU_ARCH := m68k
-+KERNEL_ARCH := m68k
-+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
-+ifeq ($(CHOST),$(CBUILD))
-+QEMU_MACHINE := -cpu host,accel=kvm -machine q800
-+else
-+QEMU_MACHINE := -machine q800
-+endif
-+else
-+$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
-+endif
-+
-+REAL_CC := $(CBUILD)-gcc
-+MUSL_CC := $(BUILD_PATH)/musl-gcc
-+export CC := $(MUSL_CC)
-+USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed
-+
-+build: $(KERNEL_BZIMAGE)
-+qemu: $(KERNEL_BZIMAGE)
-+ rm -f $(BUILD_PATH)/result
-+ timeout --foreground 20m qemu-system-$(QEMU_ARCH) \
-+ -nodefaults \
-+ -nographic \
-+ -smp $(NR_CPUS) \
-+ $(QEMU_MACHINE) \
-+ -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \
-+ -serial stdio \
-+ -serial file:$(BUILD_PATH)/result \
-+ -no-reboot \
-+ -monitor none \
-+ -kernel $<
-+ grep -Fq success $(BUILD_PATH)/result
-+
-+$(BUILD_PATH)/init-cpio-spec.txt:
-+ mkdir -p $(BUILD_PATH)
-+ echo "file /init $(BUILD_PATH)/init 755 0 0" > $@
-+ echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@
-+ echo "dir /dev 755 0 0" >> $@
-+ echo "nod /dev/console 644 0 0 c 5 1" >> $@
-+ echo "dir /bin 755 0 0" >> $@
-+ echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@
-+ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@
-+ echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@
-+ echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@
-+ echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@
-+ echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@
-+ echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@
-+ echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@
-+ echo "slink /bin/iptables xtables-multi 777 0 0" >> $@
-+ echo "slink /bin/ping6 ping 777 0 0" >> $@
-+ echo "dir /lib 755 0 0" >> $@
-+ echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
-+ echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@
-+
-+$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config
-+ mkdir -p $(KERNEL_BUILD_PATH)
-+ cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config
-+ printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config
-+ cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig
-+ cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
-+ $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
-+
-+$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)"
-+
-+$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
-+ touch $@
-+
-+$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD)
-+ $(MAKE) -C $(MUSL_PATH)
-+ $(STRIP) -s $@
-+
-+$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so
-+ $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers
-+ touch $@
-+
-+$(MUSL_CC): $(MUSL_PATH)/lib/libc.so
-+ sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
-+ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc
-+ chmod +x $(BUILD_PATH)/musl-gcc
-+
-+$(IPERF_PATH)/.installed: $(IPERF_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ sed -i '1s/^/#include <stdint.h>/' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h
-+ sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile*
-+ touch $@
-+
-+$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
-+ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-+ $(MAKE) -C $(IPERF_PATH)
-+ $(STRIP) -s $@
-+
-+$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ touch $@
-+
-+$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
-+ cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-+ $(MAKE) -C $(LIBMNL_PATH)
-+ sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
-+
-+$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ touch $@
-+
-+$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
-+ $(STRIP) -s $@
-+
-+$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
-+ mkdir -p $(BUILD_PATH)
-+ $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $<
-+ $(STRIP) -s $@
-+
-+$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ touch $@
-+
-+$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS)
-+ $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping
-+ $(STRIP) -s $@
-+
-+$(BASH_PATH)/.installed: $(BASH_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ touch $@
-+
-+$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS)
-+ cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble
-+ $(MAKE) -C $(BASH_PATH)
-+ $(STRIP) -s $@
-+
-+$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
-+ printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
-+ touch $@
-+
-+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
-+ $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
-+
-+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
-+ $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
-+
-+$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
-+ touch $@
-+
-+$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+ cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
-+ $(MAKE) -C $(IPTABLES_PATH)
-+ $(STRIP) -s $@
-+
-+$(NMAP_PATH)/.installed: $(NMAP_TAR)
-+ mkdir -p $(BUILD_PATH)
-+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-+ touch $@
-+
-+$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS)
-+ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux
-+ $(MAKE) -C $(NMAP_PATH) build-ncat
-+ $(STRIP) -s $@
-+
-+clean:
-+ rm -rf $(BUILD_PATH)
-+
-+distclean: clean
-+ rm -rf $(DISTFILES_PATH)
-+
-+menuconfig: $(KERNEL_BUILD_PATH)/.config
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig
-+
-+.PHONY: qemu build clean distclean menuconfig
-+.DELETE_ON_ERROR:
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config
-@@ -0,0 +1,5 @@
-+CONFIG_SERIAL_AMBA_PL011=y
-+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
-@@ -0,0 +1,6 @@
-+CONFIG_CPU_BIG_ENDIAN=y
-+CONFIG_SERIAL_AMBA_PL011=y
-+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config
-@@ -0,0 +1,9 @@
-+CONFIG_MMU=y
-+CONFIG_ARCH_MULTI_V7=y
-+CONFIG_ARCH_VIRT=y
-+CONFIG_THUMB2_KERNEL=n
-+CONFIG_SERIAL_AMBA_PL011=y
-+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config
-@@ -0,0 +1,10 @@
-+CONFIG_MMU=y
-+CONFIG_ARCH_MULTI_V7=y
-+CONFIG_ARCH_VIRT=y
-+CONFIG_THUMB2_KERNEL=n
-+CONFIG_SERIAL_AMBA_PL011=y
-+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
-+CONFIG_CPU_BIG_ENDIAN=y
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config
-@@ -0,0 +1,5 @@
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
-@@ -0,0 +1,9 @@
-+CONFIG_MMU=y
-+CONFIG_M68040=y
-+CONFIG_MAC=y
-+CONFIG_SERIAL_PMACZILOG=y
-+CONFIG_SERIAL_PMACZILOG_TTYS=y
-+CONFIG_SERIAL_PMACZILOG_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config
-@@ -0,0 +1,11 @@
-+CONFIG_CPU_MIPS32_R2=y
-+CONFIG_MIPS_MALTA=y
-+CONFIG_MIPS_CPS=y
-+CONFIG_MIPS_FP_SUPPORT=y
-+CONFIG_POWER_RESET=y
-+CONFIG_POWER_RESET_SYSCON=y
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config
-@@ -0,0 +1,14 @@
-+CONFIG_64BIT=y
-+CONFIG_CPU_MIPS64_R2=y
-+CONFIG_MIPS32_N32=y
-+CONFIG_CPU_HAS_MSA=y
-+CONFIG_MIPS_MALTA=y
-+CONFIG_MIPS_CPS=y
-+CONFIG_MIPS_FP_SUPPORT=y
-+CONFIG_POWER_RESET=y
-+CONFIG_POWER_RESET_SYSCON=y
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config
-@@ -0,0 +1,15 @@
-+CONFIG_64BIT=y
-+CONFIG_CPU_MIPS64_R2=y
-+CONFIG_MIPS32_N32=y
-+CONFIG_CPU_HAS_MSA=y
-+CONFIG_MIPS_MALTA=y
-+CONFIG_CPU_LITTLE_ENDIAN=y
-+CONFIG_MIPS_CPS=y
-+CONFIG_MIPS_FP_SUPPORT=y
-+CONFIG_POWER_RESET=y
-+CONFIG_POWER_RESET_SYSCON=y
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config
-@@ -0,0 +1,12 @@
-+CONFIG_CPU_MIPS32_R2=y
-+CONFIG_MIPS_MALTA=y
-+CONFIG_CPU_LITTLE_ENDIAN=y
-+CONFIG_MIPS_CPS=y
-+CONFIG_MIPS_FP_SUPPORT=y
-+CONFIG_POWER_RESET=y
-+CONFIG_POWER_RESET_SYSCON=y
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config
-@@ -0,0 +1,10 @@
-+CONFIG_PPC_QEMU_E500=y
-+CONFIG_FSL_SOC_BOOKE=y
-+CONFIG_PPC_85xx=y
-+CONFIG_PHYS_64BIT=y
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_MATH_EMULATION=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1024
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
-@@ -0,0 +1,12 @@
-+CONFIG_PPC64=y
-+CONFIG_PPC_PSERIES=y
-+CONFIG_ALTIVEC=y
-+CONFIG_VSX=y
-+CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
-+CONFIG_PPC_RADIX_MMU=y
-+CONFIG_HVC_CONSOLE=y
-+CONFIG_CPU_LITTLE_ENDIAN=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
-+CONFIG_SECTION_MISMATCH_WARN_ONLY=y
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
-@@ -0,0 +1,5 @@
-+CONFIG_SERIAL_8250=y
-+CONFIG_SERIAL_8250_CONSOLE=y
-+CONFIG_CMDLINE_BOOL=y
-+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
-+CONFIG_FRAME_WARN=1280
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/debug.config
-@@ -0,0 +1,67 @@
-+CONFIG_LOCALVERSION="-debug"
-+CONFIG_ENABLE_WARN_DEPRECATED=y
-+CONFIG_ENABLE_MUST_CHECK=y
-+CONFIG_FRAME_POINTER=y
-+CONFIG_STACK_VALIDATION=y
-+CONFIG_DEBUG_KERNEL=y
-+CONFIG_DEBUG_INFO=y
-+CONFIG_DEBUG_INFO_DWARF4=y
-+CONFIG_PAGE_EXTENSION=y
-+CONFIG_PAGE_POISONING=y
-+CONFIG_DEBUG_OBJECTS=y
-+CONFIG_DEBUG_OBJECTS_FREE=y
-+CONFIG_DEBUG_OBJECTS_TIMERS=y
-+CONFIG_DEBUG_OBJECTS_WORK=y
-+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
-+CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
-+CONFIG_SLUB_DEBUG_ON=y
-+CONFIG_DEBUG_VM=y
-+CONFIG_DEBUG_MEMORY_INIT=y
-+CONFIG_HAVE_DEBUG_STACKOVERFLOW=y
-+CONFIG_DEBUG_STACKOVERFLOW=y
-+CONFIG_HAVE_ARCH_KMEMCHECK=y
-+CONFIG_HAVE_ARCH_KASAN=y
-+CONFIG_KASAN=y
-+CONFIG_KASAN_INLINE=y
-+CONFIG_UBSAN=y
-+CONFIG_UBSAN_SANITIZE_ALL=y
-+CONFIG_UBSAN_NO_ALIGNMENT=y
-+CONFIG_UBSAN_NULL=y
-+CONFIG_DEBUG_KMEMLEAK=y
-+CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192
-+CONFIG_DEBUG_STACK_USAGE=y
-+CONFIG_DEBUG_SHIRQ=y
-+CONFIG_WQ_WATCHDOG=y
-+CONFIG_SCHED_DEBUG=y
-+CONFIG_SCHED_INFO=y
-+CONFIG_SCHEDSTATS=y
-+CONFIG_SCHED_STACK_END_CHECK=y
-+CONFIG_DEBUG_TIMEKEEPING=y
-+CONFIG_TIMER_STATS=y
-+CONFIG_DEBUG_PREEMPT=y
-+CONFIG_DEBUG_RT_MUTEXES=y
-+CONFIG_DEBUG_SPINLOCK=y
-+CONFIG_DEBUG_MUTEXES=y
-+CONFIG_DEBUG_LOCK_ALLOC=y
-+CONFIG_PROVE_LOCKING=y
-+CONFIG_LOCKDEP=y
-+CONFIG_DEBUG_ATOMIC_SLEEP=y
-+CONFIG_TRACE_IRQFLAGS=y
-+CONFIG_DEBUG_BUGVERBOSE=y
-+CONFIG_DEBUG_LIST=y
-+CONFIG_DEBUG_PI_LIST=y
-+CONFIG_PROVE_RCU=y
-+CONFIG_SPARSE_RCU_POINTER=y
-+CONFIG_RCU_CPU_STALL_TIMEOUT=21
-+CONFIG_RCU_TRACE=y
-+CONFIG_RCU_EQS_DEBUG=y
-+CONFIG_USER_STACKTRACE_SUPPORT=y
-+CONFIG_DEBUG_SG=y
-+CONFIG_DEBUG_NOTIFIERS=y
-+CONFIG_DOUBLEFAULT=y
-+CONFIG_X86_DEBUG_FPU=y
-+CONFIG_DEBUG_SECTION_MISMATCH=y
-+CONFIG_DEBUG_PAGEALLOC=y
-+CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y
-+CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/init.c
-@@ -0,0 +1,284 @@
-+// SPDX-License-Identifier: GPL-2.0
-+/*
-+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-+ */
-+
-+#define _GNU_SOURCE
-+#include <unistd.h>
-+#include <errno.h>
-+#include <string.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <stdbool.h>
-+#include <fcntl.h>
-+#include <sys/wait.h>
-+#include <sys/mount.h>
-+#include <sys/types.h>
-+#include <sys/stat.h>
-+#include <sys/types.h>
-+#include <sys/io.h>
-+#include <sys/ioctl.h>
-+#include <sys/reboot.h>
-+#include <sys/utsname.h>
-+#include <sys/sendfile.h>
-+#include <linux/random.h>
-+#include <linux/version.h>
-+
-+__attribute__((noreturn)) static void poweroff(void)
-+{
-+ fflush(stdout);
-+ fflush(stderr);
-+ reboot(RB_AUTOBOOT);
-+ sleep(30);
-+ fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n");
-+ exit(1);
-+}
-+
-+static void panic(const char *what)
-+{
-+ fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno));
-+ poweroff();
-+}
-+
-+#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m")
-+
-+static void print_banner(void)
-+{
-+ struct utsname utsname;
-+ int len;
-+
-+ if (uname(&utsname) < 0)
-+ panic("uname");
-+
-+ len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine);
-+ printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, "");
-+}
-+
-+static void seed_rng(void)
-+{
-+ int fd;
-+ struct {
-+ int entropy_count;
-+ int buffer_size;
-+ unsigned char buffer[256];
-+ } entropy = {
-+ .entropy_count = sizeof(entropy.buffer) * 8,
-+ .buffer_size = sizeof(entropy.buffer),
-+ .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!"
-+ };
-+
-+ if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9)))
-+ panic("mknod(/dev/urandom)");
-+ fd = open("/dev/urandom", O_WRONLY);
-+ if (fd < 0)
-+ panic("open(urandom)");
-+ for (int i = 0; i < 256; ++i) {
-+ if (ioctl(fd, RNDADDENTROPY, &entropy) < 0)
-+ panic("ioctl(urandom)");
-+ }
-+ close(fd);
-+}
-+
-+static void mount_filesystems(void)
-+{
-+ pretty_message("[+] Mounting filesystems...");
-+ mkdir("/dev", 0755);
-+ mkdir("/proc", 0755);
-+ mkdir("/sys", 0755);
-+ mkdir("/tmp", 0755);
-+ mkdir("/run", 0755);
-+ mkdir("/var", 0755);
-+ if (mount("none", "/dev", "devtmpfs", 0, NULL))
-+ panic("devtmpfs mount");
-+ if (mount("none", "/proc", "proc", 0, NULL))
-+ panic("procfs mount");
-+ if (mount("none", "/sys", "sysfs", 0, NULL))
-+ panic("sysfs mount");
-+ if (mount("none", "/tmp", "tmpfs", 0, NULL))
-+ panic("tmpfs mount");
-+ if (mount("none", "/run", "tmpfs", 0, NULL))
-+ panic("tmpfs mount");
-+ if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL))
-+ ; /* Not a problem if it fails.*/
-+ if (symlink("/run", "/var/run"))
-+ panic("run symlink");
-+ if (symlink("/proc/self/fd", "/dev/fd"))
-+ panic("fd symlink");
-+}
-+
-+static void enable_logging(void)
-+{
-+ int fd;
-+ pretty_message("[+] Enabling logging...");
-+ fd = open("/proc/sys/kernel/printk", O_WRONLY);
-+ if (fd >= 0) {
-+ if (write(fd, "9\n", 2) != 2)
-+ panic("write(printk)");
-+ close(fd);
-+ }
-+ fd = open("/proc/sys/debug/exception-trace", O_WRONLY);
-+ if (fd >= 0) {
-+ if (write(fd, "1\n", 2) != 2)
-+ panic("write(exception-trace)");
-+ close(fd);
-+ }
-+ fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY);
-+ if (fd >= 0) {
-+ if (write(fd, "1\n", 2) != 2)
-+ panic("write(panic_on_warn)");
-+ close(fd);
-+ }
-+}
-+
-+static void kmod_selftests(void)
-+{
-+ FILE *file;
-+ char line[2048], *start, *pass;
-+ bool success = true;
-+ pretty_message("[+] Module self-tests:");
-+ file = fopen("/proc/kmsg", "r");
-+ if (!file)
-+ panic("fopen(kmsg)");
-+ if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0)
-+ panic("fcntl(kmsg, nonblock)");
-+ while (fgets(line, sizeof(line), file)) {
-+ start = strstr(line, "wireguard: ");
-+ if (!start)
-+ continue;
-+ start += 11;
-+ *strchrnul(start, '\n') = '\0';
-+ if (strstr(start, "www.wireguard.com"))
-+ break;
-+ pass = strstr(start, ": pass");
-+ if (!pass || pass[6] != '\0') {
-+ success = false;
-+ printf(" \x1b[31m* %s\x1b[0m\n", start);
-+ } else
-+ printf(" \x1b[32m* %s\x1b[0m\n", start);
-+ }
-+ fclose(file);
-+ if (!success) {
-+ puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m");
-+ poweroff();
-+ }
-+}
-+
-+static void launch_tests(void)
-+{
-+ char cmdline[4096], *success_dev;
-+ int status, fd;
-+ pid_t pid;
-+
-+ pretty_message("[+] Launching tests...");
-+ pid = fork();
-+ if (pid == -1)
-+ panic("fork");
-+ else if (pid == 0) {
-+ execl("/init.sh", "init", NULL);
-+ panic("exec");
-+ }
-+ if (waitpid(pid, &status, 0) < 0)
-+ panic("waitpid");
-+ if (WIFEXITED(status) && WEXITSTATUS(status) == 0) {
-+ pretty_message("[+] Tests successful! :-)");
-+ fd = open("/proc/cmdline", O_RDONLY);
-+ if (fd < 0)
-+ panic("open(/proc/cmdline)");
-+ if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0)
-+ panic("read(/proc/cmdline)");
-+ cmdline[sizeof(cmdline) - 1] = '\0';
-+ for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) {
-+ if (strncmp(success_dev, "wg.success=", 11))
-+ continue;
-+ memcpy(success_dev + 11 - 5, "/dev/", 5);
-+ success_dev += 11 - 5;
-+ break;
-+ }
-+ if (!success_dev || !strlen(success_dev))
-+ panic("Unable to find success device");
-+
-+ fd = open(success_dev, O_WRONLY);
-+ if (fd < 0)
-+ panic("open(success_dev)");
-+ if (write(fd, "success\n", 8) != 8)
-+ panic("write(success_dev)");
-+ close(fd);
-+ } else {
-+ const char *why = "unknown cause";
-+ int what = -1;
-+
-+ if (WIFEXITED(status)) {
-+ why = "exit code";
-+ what = WEXITSTATUS(status);
-+ } else if (WIFSIGNALED(status)) {
-+ why = "signal";
-+ what = WTERMSIG(status);
-+ }
-+ printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what);
-+ }
-+}
-+
-+static void ensure_console(void)
-+{
-+ for (unsigned int i = 0; i < 1000; ++i) {
-+ int fd = open("/dev/console", O_RDWR);
-+ if (fd < 0) {
-+ usleep(50000);
-+ continue;
-+ }
-+ dup2(fd, 0);
-+ dup2(fd, 1);
-+ dup2(fd, 2);
-+ close(fd);
-+ if (write(1, "\0\0\0\0\n", 5) == 5)
-+ return;
-+ }
-+ panic("Unable to open console device");
-+}
-+
-+static void clear_leaks(void)
-+{
-+ int fd;
-+
-+ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY);
-+ if (fd < 0)
-+ return;
-+ pretty_message("[+] Starting memory leak detection...");
-+ write(fd, "clear\n", 5);
-+ close(fd);
-+}
-+
-+static void check_leaks(void)
-+{
-+ int fd;
-+
-+ fd = open("/sys/kernel/debug/kmemleak", O_WRONLY);
-+ if (fd < 0)
-+ return;
-+ pretty_message("[+] Scanning for memory leaks...");
-+ sleep(2); /* Wait for any grace periods. */
-+ write(fd, "scan\n", 5);
-+ close(fd);
-+
-+ fd = open("/sys/kernel/debug/kmemleak", O_RDONLY);
-+ if (fd < 0)
-+ return;
-+ if (sendfile(1, fd, NULL, 0x7ffff000) > 0)
-+ panic("Memory leaks encountered");
-+ close(fd);
-+}
-+
-+int main(int argc, char *argv[])
-+{
-+ seed_rng();
-+ ensure_console();
-+ print_banner();
-+ mount_filesystems();
-+ kmod_selftests();
-+ enable_logging();
-+ clear_leaks();
-+ launch_tests();
-+ check_leaks();
-+ poweroff();
-+ return 1;
-+}
---- /dev/null
-+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
-@@ -0,0 +1,86 @@
-+CONFIG_LOCALVERSION=""
-+CONFIG_NET=y
-+CONFIG_NETDEVICES=y
-+CONFIG_NET_CORE=y
-+CONFIG_NET_IPIP=y
-+CONFIG_DUMMY=y
-+CONFIG_VETH=y
-+CONFIG_MULTIUSER=y
-+CONFIG_NAMESPACES=y
-+CONFIG_NET_NS=y
-+CONFIG_UNIX=y
-+CONFIG_INET=y
-+CONFIG_IPV6=y
-+CONFIG_NETFILTER=y
-+CONFIG_NETFILTER_ADVANCED=y
-+CONFIG_NF_CONNTRACK=y
-+CONFIG_NF_NAT=y
-+CONFIG_NETFILTER_XTABLES=y
-+CONFIG_NETFILTER_XT_NAT=y
-+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
-+CONFIG_NF_CONNTRACK_IPV4=y
-+CONFIG_NF_NAT_IPV4=y
-+CONFIG_IP_NF_IPTABLES=y
-+CONFIG_IP_NF_FILTER=y
-+CONFIG_IP_NF_NAT=y
-+CONFIG_IP_ADVANCED_ROUTER=y
-+CONFIG_IP_MULTIPLE_TABLES=y
-+CONFIG_IPV6_MULTIPLE_TABLES=y
-+CONFIG_TTY=y
-+CONFIG_BINFMT_ELF=y
-+CONFIG_BINFMT_SCRIPT=y
-+CONFIG_VDSO=y
-+CONFIG_VIRTUALIZATION=y
-+CONFIG_HYPERVISOR_GUEST=y
-+CONFIG_PARAVIRT=y
-+CONFIG_KVM_GUEST=y
-+CONFIG_PARAVIRT_SPINLOCKS=y
-+CONFIG_PRINTK=y
-+CONFIG_KALLSYMS=y
-+CONFIG_BUG=y
-+CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
-+CONFIG_EMBEDDED=n
-+CONFIG_BASE_FULL=y
-+CONFIG_FUTEX=y
-+CONFIG_SHMEM=y
-+CONFIG_SLUB=y
-+CONFIG_SPARSEMEM_VMEMMAP=y
-+CONFIG_SMP=y
-+CONFIG_SCHED_SMT=y
-+CONFIG_SCHED_MC=y
-+CONFIG_NUMA=y
-+CONFIG_PREEMPT=y
-+CONFIG_NO_HZ=y
-+CONFIG_NO_HZ_IDLE=y
-+CONFIG_NO_HZ_FULL=n
-+CONFIG_HZ_PERIODIC=n
-+CONFIG_HIGH_RES_TIMERS=y
-+CONFIG_ARCH_RANDOM=y
-+CONFIG_FILE_LOCKING=y
-+CONFIG_POSIX_TIMERS=y
-+CONFIG_DEVTMPFS=y
-+CONFIG_PROC_FS=y
-+CONFIG_PROC_SYSCTL=y
-+CONFIG_SYSFS=y
-+CONFIG_TMPFS=y
-+CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
-+CONFIG_PRINTK_TIME=y
-+CONFIG_BLK_DEV_INITRD=y
-+CONFIG_LEGACY_VSYSCALL_NONE=y
-+CONFIG_KERNEL_GZIP=y
-+CONFIG_PANIC_ON_OOPS=y
-+CONFIG_BUG_ON_DATA_CORRUPTION=y
-+CONFIG_LOCKUP_DETECTOR=y
-+CONFIG_SOFTLOCKUP_DETECTOR=y
-+CONFIG_HARDLOCKUP_DETECTOR=y
-+CONFIG_WQ_WATCHDOG=y
-+CONFIG_DETECT_HUNG_TASK=y
-+CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y
-+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
-+CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
-+CONFIG_PANIC_TIMEOUT=-1
-+CONFIG_STACKTRACE=y
-+CONFIG_EARLY_PRINTK=y
-+CONFIG_GDB_SCRIPTS=y
-+CONFIG_WIREGUARD=y
-+CONFIG_WIREGUARD_DEBUG=y
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Sun, 15 Dec 2019 22:08:01 +0100
-Subject: [PATCH] wireguard: Kconfig: select parent dependency for crypto
-
-commit d7c68a38bb4f9b7c1a2e4a772872c752ee5c44a6 upstream.
-
-This fixes the crypto selection submenu depenencies. Otherwise, we'd
-wind up issuing warnings in which certain dependencies we also select
-couldn't be satisfied. This condition was triggered by the addition of
-the test suite autobuilder in the previous commit.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/Kconfig | 2 ++
- 1 file changed, 2 insertions(+)
-
---- a/drivers/net/Kconfig
-+++ b/drivers/net/Kconfig
-@@ -85,6 +85,8 @@ config WIREGUARD
- select CRYPTO_POLY1305_X86_64 if X86 && 64BIT
- select CRYPTO_BLAKE2S_X86 if X86 && 64BIT
- select CRYPTO_CURVE25519_X86 if X86 && 64BIT
-+ select ARM_CRYPTO if ARM
-+ select ARM64_CRYPTO if ARM64
- select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
- select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
- select CRYPTO_POLY1305_ARM if ARM
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: YueHaibing <yuehaibing@huawei.com>
+Date: Sun, 15 Dec 2019 22:08:03 +0100
+Subject: [PATCH] wireguard: main: remove unused include <linux/version.h>
+
+commit 43967b6ff91e53bcce5ae08c16a0588a475b53a1 upstream.
+
+Remove <linux/version.h> from the includes for main.c, which is unused.
+
+Signed-off-by: YueHaibing <yuehaibing@huawei.com>
+[Jason: reworded commit message]
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/main.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/drivers/net/wireguard/main.c
++++ b/drivers/net/wireguard/main.c
+@@ -12,7 +12,6 @@
+
+ #include <uapi/linux/wireguard.h>
+
+-#include <linux/version.h>
+ #include <linux/init.h>
+ #include <linux/module.h>
+ #include <linux/genetlink.h>
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Wei Yongjun <weiyongjun1@huawei.com>
+Date: Sun, 15 Dec 2019 22:08:04 +0100
+Subject: [PATCH] wireguard: allowedips: use kfree_rcu() instead of call_rcu()
+
+commit d89ee7d5c73af15c1c6f12b016cdf469742b5726 upstream.
+
+The callback function of call_rcu() just calls a kfree(), so we
+can use kfree_rcu() instead of call_rcu() + callback function.
+
+Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/allowedips.c | 7 +------
+ 1 file changed, 1 insertion(+), 6 deletions(-)
+
+--- a/drivers/net/wireguard/allowedips.c
++++ b/drivers/net/wireguard/allowedips.c
+@@ -31,11 +31,6 @@ static void copy_and_assign_cidr(struct
+ #define CHOOSE_NODE(parent, key) \
+ parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
+
+-static void node_free_rcu(struct rcu_head *rcu)
+-{
+- kfree(container_of(rcu, struct allowedips_node, rcu));
+-}
+-
+ static void push_rcu(struct allowedips_node **stack,
+ struct allowedips_node __rcu *p, unsigned int *len)
+ {
+@@ -112,7 +107,7 @@ static void walk_remove_by_peer(struct a
+ if (!node->bit[0] || !node->bit[1]) {
+ rcu_assign_pointer(*nptr, DEREF(
+ &node->bit[!REF(node->bit[0])]));
+- call_rcu(&node->rcu, node_free_rcu);
++ kfree_rcu(node, rcu);
+ node = DEREF(nptr);
+ }
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Josh Soref <jsoref@gmail.com>
-Date: Sun, 15 Dec 2019 22:08:02 +0100
-Subject: [PATCH] wireguard: global: fix spelling mistakes in comments
-
-commit a2ec8b5706944d228181c8b91d815f41d6dd8e7b upstream.
-
-This fixes two spelling errors in source code comments.
-
-Signed-off-by: Josh Soref <jsoref@gmail.com>
-[Jason: rewrote commit message]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 2 +-
- include/uapi/linux/wireguard.h | 8 ++++----
- 2 files changed, 5 insertions(+), 5 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -380,7 +380,7 @@ static void wg_packet_consume_data_done(
- /* We've already verified the Poly1305 auth tag, which means this packet
- * was not modified in transit. We can therefore tell the networking
- * stack that all checksums of every layer of encapsulation have already
-- * been checked "by the hardware" and therefore is unneccessary to check
-+ * been checked "by the hardware" and therefore is unnecessary to check
- * again in software.
- */
- skb->ip_summed = CHECKSUM_UNNECESSARY;
---- a/include/uapi/linux/wireguard.h
-+++ b/include/uapi/linux/wireguard.h
-@@ -18,13 +18,13 @@
- * one but not both of:
- *
- * WGDEVICE_A_IFINDEX: NLA_U32
-- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
- *
- * The kernel will then return several messages (NLM_F_MULTI) containing the
- * following tree of nested items:
- *
- * WGDEVICE_A_IFINDEX: NLA_U32
-- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
- * WGDEVICE_A_PRIVATE_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
- * WGDEVICE_A_PUBLIC_KEY: NLA_EXACT_LEN, len WG_KEY_LEN
- * WGDEVICE_A_LISTEN_PORT: NLA_U16
-@@ -77,7 +77,7 @@
- * WGDEVICE_A_IFINDEX and WGDEVICE_A_IFNAME:
- *
- * WGDEVICE_A_IFINDEX: NLA_U32
-- * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMESIZ - 1
-+ * WGDEVICE_A_IFNAME: NLA_NUL_STRING, maxlen IFNAMSIZ - 1
- * WGDEVICE_A_FLAGS: NLA_U32, 0 or WGDEVICE_F_REPLACE_PEERS if all current
- * peers should be removed prior to adding the list below.
- * WGDEVICE_A_PRIVATE_KEY: len WG_KEY_LEN, all zeros to remove
-@@ -121,7 +121,7 @@
- * filling in information not contained in the prior. Note that if
- * WGDEVICE_F_REPLACE_PEERS is specified in the first message, it probably
- * should not be specified in fragments that come after, so that the list
-- * of peers is only cleared the first time but appened after. Likewise for
-+ * of peers is only cleared the first time but appended after. Likewise for
- * peers, if WGPEER_F_REPLACE_ALLOWEDIPS is specified in the first message
- * of a peer, it likely should not be specified in subsequent fragments.
- *
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: YueHaibing <yuehaibing@huawei.com>
-Date: Sun, 15 Dec 2019 22:08:03 +0100
-Subject: [PATCH] wireguard: main: remove unused include <linux/version.h>
-
-commit 43967b6ff91e53bcce5ae08c16a0588a475b53a1 upstream.
-
-Remove <linux/version.h> from the includes for main.c, which is unused.
-
-Signed-off-by: YueHaibing <yuehaibing@huawei.com>
-[Jason: reworded commit message]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/main.c | 1 -
- 1 file changed, 1 deletion(-)
-
---- a/drivers/net/wireguard/main.c
-+++ b/drivers/net/wireguard/main.c
-@@ -12,7 +12,6 @@
-
- #include <uapi/linux/wireguard.h>
-
--#include <linux/version.h>
- #include <linux/init.h>
- #include <linux/module.h>
- #include <linux/genetlink.h>
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Thu, 2 Jan 2020 17:47:49 +0100
+Subject: [PATCH] wireguard: selftests: remove ancient kernel compatibility
+ code
+
+commit 9a69a4c8802adf642bc4a13d471b5a86b44ed434 upstream.
+
+Quite a bit of the test suite was designed to work with ancient kernels.
+Thankfully we no longer have to deal with this. This commit updates
+things that we can finally update and removes things that we can finally
+remove, to avoid the build-up of the last several years as a result of
+having to support ancient kernels. We can finally rely on suppress_
+prefixlength being available. On the build side of things, the no-PIE
+hack is no longer required, and we can bump some of the tools, repair
+our m68k and i686-kvm support, and get better coverage of the static
+branches used in the crypto lib and in udp_tunnel.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/netns.sh | 11 +--
+ .../testing/selftests/wireguard/qemu/Makefile | 82 ++++++++++---------
+ .../selftests/wireguard/qemu/arch/m68k.config | 2 +-
+ tools/testing/selftests/wireguard/qemu/init.c | 1 +
+ .../selftests/wireguard/qemu/kernel.config | 2 +
+ 5 files changed, 50 insertions(+), 48 deletions(-)
+
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -37,7 +37,7 @@ n2() { pretty 2 "$*"; maybe_exec ip netn
+ ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
+ ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
+ ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
+-sleep() { read -t "$1" -N 0 || true; }
++sleep() { read -t "$1" -N 1 || true; }
+ waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
+ waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
+ waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
+@@ -294,12 +294,9 @@ ip1 -6 rule add table main suppress_pref
+ ip1 -4 route add default dev wg0 table 51820
+ ip1 -4 rule add not fwmark 51820 table 51820
+ ip1 -4 rule add table main suppress_prefixlength 0
+-# suppress_prefixlength only got added in 3.12, and we want to support 3.10+.
+-if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then
+- # Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
+- n1 ping -W 1 -c 100 -f 192.168.99.7
+- n1 ping -W 1 -c 100 -f abab::1111
+-fi
++# Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
++n1 ping -W 1 -c 100 -f 192.168.99.7
++n1 ping -W 1 -c 100 -f abab::1111
+
+ n0 iptables -t nat -F
+ ip0 link del vethrc
+--- a/tools/testing/selftests/wireguard/qemu/Makefile
++++ b/tools/testing/selftests/wireguard/qemu/Makefile
+@@ -5,6 +5,7 @@
+ PWD := $(shell pwd)
+
+ CHOST := $(shell gcc -dumpmachine)
++HOST_ARCH := $(firstword $(subst -, ,$(CHOST)))
+ ifneq (,$(ARCH))
+ CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
+ ifeq (,$(CBUILD))
+@@ -37,19 +38,19 @@ endef
+ define file_download =
+ $(DISTFILES_PATH)/$(1):
+ mkdir -p $(DISTFILES_PATH)
+- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
+ if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
+ endef
+
+-$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61))
++$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
+ $(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
+-$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f))
++$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
+ $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
+-$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2))
+-$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5))
+-$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21))
+-$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a))
+-$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071))
++$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
++$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
++$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
++$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
++$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
+
+ KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
+ rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
+@@ -59,23 +60,21 @@ export CFLAGS ?= -O3 -pipe
+ export LDFLAGS ?=
+ export CPPFLAGS := -I$(BUILD_PATH)/include
+
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ CROSS_COMPILE_FLAG := --host=$(CHOST)
+-NOPIE_GCC := gcc -fno-PIE
+ CFLAGS += -march=native
+ STRIP := strip
+ else
+ $(info Cross compilation: building for $(CBUILD) using $(CHOST))
+ CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
+ export CROSS_COMPILE=$(CBUILD)-
+-NOPIE_GCC := $(CBUILD)-gcc -fno-PIE
+ STRIP := $(CBUILD)-strip
+ endif
+ ifeq ($(ARCH),aarch64)
+ QEMU_ARCH := aarch64
+ KERNEL_ARCH := arm64
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
+ else
+ QEMU_MACHINE := -cpu cortex-a53 -machine virt
+@@ -85,7 +84,7 @@ else ifeq ($(ARCH),aarch64_be)
+ QEMU_ARCH := aarch64
+ KERNEL_ARCH := arm64
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
+ else
+ QEMU_MACHINE := -cpu cortex-a53 -machine virt
+@@ -95,7 +94,7 @@ else ifeq ($(ARCH),arm)
+ QEMU_ARCH := arm
+ KERNEL_ARCH := arm
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
+ else
+ QEMU_MACHINE := -cpu cortex-a15 -machine virt
+@@ -105,7 +104,7 @@ else ifeq ($(ARCH),armeb)
+ QEMU_ARCH := arm
+ KERNEL_ARCH := arm
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
+ else
+ QEMU_MACHINE := -cpu cortex-a15 -machine virt
+@@ -116,7 +115,7 @@ else ifeq ($(ARCH),x86_64)
+ QEMU_ARCH := x86_64
+ KERNEL_ARCH := x86_64
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine q35,accel=kvm
+ else
+ QEMU_MACHINE := -cpu Skylake-Server -machine q35
+@@ -126,7 +125,7 @@ else ifeq ($(ARCH),i686)
+ QEMU_ARCH := i386
+ KERNEL_ARCH := x86
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
+-ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST))
++ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine q35,accel=kvm
+ else
+ QEMU_MACHINE := -cpu coreduo -machine q35
+@@ -136,7 +135,7 @@ else ifeq ($(ARCH),mips64)
+ QEMU_ARCH := mips64
+ KERNEL_ARCH := mips
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine malta,accel=kvm
+ CFLAGS += -EB
+ else
+@@ -147,7 +146,7 @@ else ifeq ($(ARCH),mips64el)
+ QEMU_ARCH := mips64el
+ KERNEL_ARCH := mips
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine malta,accel=kvm
+ CFLAGS += -EL
+ else
+@@ -158,7 +157,7 @@ else ifeq ($(ARCH),mips)
+ QEMU_ARCH := mips
+ KERNEL_ARCH := mips
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine malta,accel=kvm
+ CFLAGS += -EB
+ else
+@@ -169,7 +168,7 @@ else ifeq ($(ARCH),mipsel)
+ QEMU_ARCH := mipsel
+ KERNEL_ARCH := mips
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host -machine malta,accel=kvm
+ CFLAGS += -EL
+ else
+@@ -180,7 +179,7 @@ else ifeq ($(ARCH),powerpc64le)
+ QEMU_ARCH := ppc64
+ KERNEL_ARCH := powerpc
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
+ else
+ QEMU_MACHINE := -machine pseries
+@@ -190,7 +189,7 @@ else ifeq ($(ARCH),powerpc)
+ QEMU_ARCH := ppc
+ KERNEL_ARCH := powerpc
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
+-ifeq ($(CHOST),$(CBUILD))
++ifeq ($(HOST_ARCH),$(ARCH))
+ QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
+ else
+ QEMU_MACHINE := -machine ppce500
+@@ -200,10 +199,11 @@ else ifeq ($(ARCH),m68k)
+ QEMU_ARCH := m68k
+ KERNEL_ARCH := m68k
+ KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+-ifeq ($(CHOST),$(CBUILD))
+-QEMU_MACHINE := -cpu host,accel=kvm -machine q800
++KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config)
++ifeq ($(HOST_ARCH),$(ARCH))
++QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
+ else
+-QEMU_MACHINE := -machine q800
++QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
+ endif
+ else
+ $(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
+@@ -238,14 +238,14 @@ $(BUILD_PATH)/init-cpio-spec.txt:
+ echo "nod /dev/console 644 0 0 c 5 1" >> $@
+ echo "dir /bin 755 0 0" >> $@
+ echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@
+- echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@
++ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@
+ echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@
+ echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@
+ echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@
+ echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@
+ echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@
+- echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@
+- echo "slink /bin/iptables xtables-multi 777 0 0" >> $@
++ echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@
++ echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@
+ echo "slink /bin/ping6 ping 777 0 0" >> $@
+ echo "dir /lib 755 0 0" >> $@
+ echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
+@@ -260,8 +260,8 @@ $(KERNEL_BUILD_PATH)/.config: kernel.con
+ cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
+ $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
+
+-$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
+- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)"
++$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE)
+
+ $(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
+@@ -280,7 +280,7 @@ $(BUILD_PATH)/include/.installed: $(MUSL
+
+ $(MUSL_CC): $(MUSL_PATH)/lib/libc.so
+ sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
+- printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc
++ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc
+ chmod +x $(BUILD_PATH)/musl-gcc
+
+ $(IPERF_PATH)/.installed: $(IPERF_TAR)
+@@ -291,7 +291,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR)
+ touch $@
+
+ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
+- cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
++ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no
+ $(MAKE) -C $(IPERF_PATH)
+ $(STRIP) -s $@
+
+@@ -308,8 +308,8 @@ $(WIREGUARD_TOOLS_PATH)/.installed: $(WI
+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
+ touch $@
+
+-$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
++$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
+ $(STRIP) -s $@
+
+ $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
+@@ -323,7 +323,8 @@ $(IPUTILS_PATH)/.installed: $(IPUTILS_TA
+ touch $@
+
+ $(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS)
+- $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping
++ sed -i /atexit/d $(IPUTILS_PATH)/ping.c
++ cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS)
+ $(STRIP) -s $@
+
+ $(BASH_PATH)/.installed: $(BASH_TAR)
+@@ -357,7 +358,7 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_
+ sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
+ touch $@
+
+-$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
++$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+ cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
+ $(MAKE) -C $(IPTABLES_PATH)
+ $(STRIP) -s $@
+@@ -368,8 +369,9 @@ $(NMAP_PATH)/.installed: $(NMAP_TAR)
+ touch $@
+
+ $(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS)
+- cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux
+- $(MAKE) -C $(NMAP_PATH) build-ncat
++ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh
++ $(MAKE) -C $(NMAP_PATH)/libpcap
++ $(MAKE) -C $(NMAP_PATH)/ncat
+ $(STRIP) -s $@
+
+ clean:
+@@ -379,7 +381,7 @@ distclean: clean
+ rm -rf $(DISTFILES_PATH)
+
+ menuconfig: $(KERNEL_BUILD_PATH)/.config
+- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig
++ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig
+
+ .PHONY: qemu build clean distclean menuconfig
+ .DELETE_ON_ERROR:
+--- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config
++++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
+@@ -1,9 +1,9 @@
+ CONFIG_MMU=y
++CONFIG_M68KCLASSIC=y
+ CONFIG_M68040=y
+ CONFIG_MAC=y
+ CONFIG_SERIAL_PMACZILOG=y
+ CONFIG_SERIAL_PMACZILOG_TTYS=y
+ CONFIG_SERIAL_PMACZILOG_CONSOLE=y
+-CONFIG_CMDLINE_BOOL=y
+ CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+ CONFIG_FRAME_WARN=1024
+--- a/tools/testing/selftests/wireguard/qemu/init.c
++++ b/tools/testing/selftests/wireguard/qemu/init.c
+@@ -21,6 +21,7 @@
+ #include <sys/reboot.h>
+ #include <sys/utsname.h>
+ #include <sys/sendfile.h>
++#include <sys/sysmacros.h>
+ #include <linux/random.h>
+ #include <linux/version.h>
+
+--- a/tools/testing/selftests/wireguard/qemu/kernel.config
++++ b/tools/testing/selftests/wireguard/qemu/kernel.config
+@@ -39,6 +39,7 @@ CONFIG_PRINTK=y
+ CONFIG_KALLSYMS=y
+ CONFIG_BUG=y
+ CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
++CONFIG_JUMP_LABEL=y
+ CONFIG_EMBEDDED=n
+ CONFIG_BASE_FULL=y
+ CONFIG_FUTEX=y
+@@ -55,6 +56,7 @@ CONFIG_NO_HZ_IDLE=y
+ CONFIG_NO_HZ_FULL=n
+ CONFIG_HZ_PERIODIC=n
+ CONFIG_HIGH_RES_TIMERS=y
++CONFIG_COMPAT_32BIT_TIME=y
+ CONFIG_ARCH_RANDOM=y
+ CONFIG_FILE_LOCKING=y
+ CONFIG_POSIX_TIMERS=y
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wei Yongjun <weiyongjun1@huawei.com>
-Date: Sun, 15 Dec 2019 22:08:04 +0100
-Subject: [PATCH] wireguard: allowedips: use kfree_rcu() instead of call_rcu()
-
-commit d89ee7d5c73af15c1c6f12b016cdf469742b5726 upstream.
-
-The callback function of call_rcu() just calls a kfree(), so we
-can use kfree_rcu() instead of call_rcu() + callback function.
-
-Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/allowedips.c | 7 +------
- 1 file changed, 1 insertion(+), 6 deletions(-)
-
---- a/drivers/net/wireguard/allowedips.c
-+++ b/drivers/net/wireguard/allowedips.c
-@@ -31,11 +31,6 @@ static void copy_and_assign_cidr(struct
- #define CHOOSE_NODE(parent, key) \
- parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
-
--static void node_free_rcu(struct rcu_head *rcu)
--{
-- kfree(container_of(rcu, struct allowedips_node, rcu));
--}
--
- static void push_rcu(struct allowedips_node **stack,
- struct allowedips_node __rcu *p, unsigned int *len)
- {
-@@ -112,7 +107,7 @@ static void walk_remove_by_peer(struct a
- if (!node->bit[0] || !node->bit[1]) {
- rcu_assign_pointer(*nptr, DEREF(
- &node->bit[!REF(node->bit[0])]));
-- call_rcu(&node->rcu, node_free_rcu);
-+ kfree_rcu(node, rcu);
- node = DEREF(nptr);
- }
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Thu, 2 Jan 2020 17:47:50 +0100
+Subject: [PATCH] wireguard: queueing: do not account for pfmemalloc when
+ clearing skb header
+
+commit 04d2ea92a18417619182cbb79063f154892b0150 upstream.
+
+Before 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_
+header()"), the pfmemalloc flag used to be between headers_start and
+headers_end, which is a region we clear when preparing the packet for
+encryption/decryption. This is a parameter we certainly want to
+preserve, which is why 8b7008620b84 moved it out of there. The code here
+was written in a world before 8b7008620b84, though, where we had to
+manually account for it. This commit brings things up to speed.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/queueing.h | 3 ---
+ 1 file changed, 3 deletions(-)
+
+--- a/drivers/net/wireguard/queueing.h
++++ b/drivers/net/wireguard/queueing.h
+@@ -83,13 +83,10 @@ static inline __be16 wg_skb_examine_untr
+
+ static inline void wg_reset_packet(struct sk_buff *skb)
+ {
+- const int pfmemalloc = skb->pfmemalloc;
+-
+ skb_scrub_packet(skb, true);
+ memset(&skb->headers_start, 0,
+ offsetof(struct sk_buff, headers_end) -
+ offsetof(struct sk_buff, headers_start));
+- skb->pfmemalloc = pfmemalloc;
+ skb->queue_mapping = 0;
+ skb->nohdr = 0;
+ skb->peeked = 0;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Thu, 2 Jan 2020 17:47:49 +0100
-Subject: [PATCH] wireguard: selftests: remove ancient kernel compatibility
- code
-
-commit 9a69a4c8802adf642bc4a13d471b5a86b44ed434 upstream.
-
-Quite a bit of the test suite was designed to work with ancient kernels.
-Thankfully we no longer have to deal with this. This commit updates
-things that we can finally update and removes things that we can finally
-remove, to avoid the build-up of the last several years as a result of
-having to support ancient kernels. We can finally rely on suppress_
-prefixlength being available. On the build side of things, the no-PIE
-hack is no longer required, and we can bump some of the tools, repair
-our m68k and i686-kvm support, and get better coverage of the static
-branches used in the crypto lib and in udp_tunnel.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/netns.sh | 11 +--
- .../testing/selftests/wireguard/qemu/Makefile | 82 ++++++++++---------
- .../selftests/wireguard/qemu/arch/m68k.config | 2 +-
- tools/testing/selftests/wireguard/qemu/init.c | 1 +
- .../selftests/wireguard/qemu/kernel.config | 2 +
- 5 files changed, 50 insertions(+), 48 deletions(-)
-
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -37,7 +37,7 @@ n2() { pretty 2 "$*"; maybe_exec ip netn
- ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
- ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
- ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
--sleep() { read -t "$1" -N 0 || true; }
-+sleep() { read -t "$1" -N 1 || true; }
- waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
- waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
- waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
-@@ -294,12 +294,9 @@ ip1 -6 rule add table main suppress_pref
- ip1 -4 route add default dev wg0 table 51820
- ip1 -4 rule add not fwmark 51820 table 51820
- ip1 -4 rule add table main suppress_prefixlength 0
--# suppress_prefixlength only got added in 3.12, and we want to support 3.10+.
--if [[ $(ip1 -4 rule show all) == *suppress_prefixlength* ]]; then
-- # Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
-- n1 ping -W 1 -c 100 -f 192.168.99.7
-- n1 ping -W 1 -c 100 -f abab::1111
--fi
-+# Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
-+n1 ping -W 1 -c 100 -f 192.168.99.7
-+n1 ping -W 1 -c 100 -f abab::1111
-
- n0 iptables -t nat -F
- ip0 link del vethrc
---- a/tools/testing/selftests/wireguard/qemu/Makefile
-+++ b/tools/testing/selftests/wireguard/qemu/Makefile
-@@ -5,6 +5,7 @@
- PWD := $(shell pwd)
-
- CHOST := $(shell gcc -dumpmachine)
-+HOST_ARCH := $(firstword $(subst -, ,$(CHOST)))
- ifneq (,$(ARCH))
- CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
- ifeq (,$(CBUILD))
-@@ -37,19 +38,19 @@ endef
- define file_download =
- $(DISTFILES_PATH)/$(1):
- mkdir -p $(DISTFILES_PATH)
-- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -t inf --retry-on-http-error=404 -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
-+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
- endef
-
--$(eval $(call tar_download,MUSL,musl,1.1.20,.tar.gz,https://www.musl-libc.org/releases/,44be8771d0e6c6b5f82dd15662eb2957c9a3173a19a8b49966ac0542bbd40d61))
-+$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
- $(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
--$(eval $(call tar_download,IPERF,iperf,3.1.7,.tar.gz,http://downloads.es.net/pub/iperf/,a4ef73406fe92250602b8da2ae89ec53211f805df97a1d1d629db5a14043734f))
-+$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
- $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
--$(eval $(call tar_download,IPROUTE2,iproute2,5.1.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,9b43707d6075ecdca14803ca8ce0c8553848c49fa1586d12fd508d66577243f2))
--$(eval $(call tar_download,IPTABLES,iptables,1.6.1,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,0fc2d7bd5d7be11311726466789d4c65fb4c8e096c9182b56ce97440864f0cf5))
--$(eval $(call tar_download,NMAP,nmap,7.60,.tar.bz2,https://nmap.org/dist/,a8796ecc4fa6c38aad6139d9515dc8113023a82e9d787e5a5fb5fa1b05516f21))
--$(eval $(call tar_download,IPUTILS,iputils,s20161105,.tar.gz,https://github.com/iputils/iputils/archive/s20161105.tar.gz/#,f813092f03d17294fd23544b129b95cdb87fe19f7970a51908a6b88509acad8a))
--$(eval $(call tar_download,WIREGUARD_TOOLS,WireGuard,0.0.20191212,.tar.xz,https://git.zx2c4.com/WireGuard/snapshot/,b0d718380f7a8822b2f12d75e462fa4eafa3a77871002981f367cd4fe2a1b071))
-+$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
-+$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
-+$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
-+$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
-
- KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
- rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-@@ -59,23 +60,21 @@ export CFLAGS ?= -O3 -pipe
- export LDFLAGS ?=
- export CPPFLAGS := -I$(BUILD_PATH)/include
-
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- CROSS_COMPILE_FLAG := --host=$(CHOST)
--NOPIE_GCC := gcc -fno-PIE
- CFLAGS += -march=native
- STRIP := strip
- else
- $(info Cross compilation: building for $(CBUILD) using $(CHOST))
- CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
- export CROSS_COMPILE=$(CBUILD)-
--NOPIE_GCC := $(CBUILD)-gcc -fno-PIE
- STRIP := $(CBUILD)-strip
- endif
- ifeq ($(ARCH),aarch64)
- QEMU_ARCH := aarch64
- KERNEL_ARCH := arm64
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
- else
- QEMU_MACHINE := -cpu cortex-a53 -machine virt
-@@ -85,7 +84,7 @@ else ifeq ($(ARCH),aarch64_be)
- QEMU_ARCH := aarch64
- KERNEL_ARCH := arm64
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
- else
- QEMU_MACHINE := -cpu cortex-a53 -machine virt
-@@ -95,7 +94,7 @@ else ifeq ($(ARCH),arm)
- QEMU_ARCH := arm
- KERNEL_ARCH := arm
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
- else
- QEMU_MACHINE := -cpu cortex-a15 -machine virt
-@@ -105,7 +104,7 @@ else ifeq ($(ARCH),armeb)
- QEMU_ARCH := arm
- KERNEL_ARCH := arm
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
- else
- QEMU_MACHINE := -cpu cortex-a15 -machine virt
-@@ -116,7 +115,7 @@ else ifeq ($(ARCH),x86_64)
- QEMU_ARCH := x86_64
- KERNEL_ARCH := x86_64
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine q35,accel=kvm
- else
- QEMU_MACHINE := -cpu Skylake-Server -machine q35
-@@ -126,7 +125,7 @@ else ifeq ($(ARCH),i686)
- QEMU_ARCH := i386
- KERNEL_ARCH := x86
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
--ifeq ($(subst i686,x86_64,$(CBUILD)),$(CHOST))
-+ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH))
- QEMU_MACHINE := -cpu host -machine q35,accel=kvm
- else
- QEMU_MACHINE := -cpu coreduo -machine q35
-@@ -136,7 +135,7 @@ else ifeq ($(ARCH),mips64)
- QEMU_ARCH := mips64
- KERNEL_ARCH := mips
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine malta,accel=kvm
- CFLAGS += -EB
- else
-@@ -147,7 +146,7 @@ else ifeq ($(ARCH),mips64el)
- QEMU_ARCH := mips64el
- KERNEL_ARCH := mips
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine malta,accel=kvm
- CFLAGS += -EL
- else
-@@ -158,7 +157,7 @@ else ifeq ($(ARCH),mips)
- QEMU_ARCH := mips
- KERNEL_ARCH := mips
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine malta,accel=kvm
- CFLAGS += -EB
- else
-@@ -169,7 +168,7 @@ else ifeq ($(ARCH),mipsel)
- QEMU_ARCH := mipsel
- KERNEL_ARCH := mips
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host -machine malta,accel=kvm
- CFLAGS += -EL
- else
-@@ -180,7 +179,7 @@ else ifeq ($(ARCH),powerpc64le)
- QEMU_ARCH := ppc64
- KERNEL_ARCH := powerpc
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
- else
- QEMU_MACHINE := -machine pseries
-@@ -190,7 +189,7 @@ else ifeq ($(ARCH),powerpc)
- QEMU_ARCH := ppc
- KERNEL_ARCH := powerpc
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
--ifeq ($(CHOST),$(CBUILD))
-+ifeq ($(HOST_ARCH),$(ARCH))
- QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
- else
- QEMU_MACHINE := -machine ppce500
-@@ -200,10 +199,11 @@ else ifeq ($(ARCH),m68k)
- QEMU_ARCH := m68k
- KERNEL_ARCH := m68k
- KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
--ifeq ($(CHOST),$(CBUILD))
--QEMU_MACHINE := -cpu host,accel=kvm -machine q800
-+KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config)
-+ifeq ($(HOST_ARCH),$(ARCH))
-+QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
- else
--QEMU_MACHINE := -machine q800
-+QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
- endif
- else
- $(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
-@@ -238,14 +238,14 @@ $(BUILD_PATH)/init-cpio-spec.txt:
- echo "nod /dev/console 644 0 0 c 5 1" >> $@
- echo "dir /bin 755 0 0" >> $@
- echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@
-- echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/tools/wg 755 0 0" >> $@
-+ echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@
- echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@
- echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@
- echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@
- echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@
- echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@
-- echo "file /bin/xtables-multi $(IPTABLES_PATH)/iptables/xtables-multi 755 0 0" >> $@
-- echo "slink /bin/iptables xtables-multi 777 0 0" >> $@
-+ echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@
-+ echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@
- echo "slink /bin/ping6 ping 777 0 0" >> $@
- echo "dir /lib 755 0 0" >> $@
- echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
-@@ -260,8 +260,8 @@ $(KERNEL_BUILD_PATH)/.config: kernel.con
- cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
- $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
-
--$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/tools/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
-- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)"
-+$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE)
-
- $(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
-@@ -280,7 +280,7 @@ $(BUILD_PATH)/include/.installed: $(MUSL
-
- $(MUSL_CC): $(MUSL_PATH)/lib/libc.so
- sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
-- printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" -fno-stack-protector -no-pie "$$@"\n' > $(BUILD_PATH)/musl-gcc
-+ printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc
- chmod +x $(BUILD_PATH)/musl-gcc
-
- $(IPERF_PATH)/.installed: $(IPERF_TAR)
-@@ -291,7 +291,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR)
- touch $@
-
- $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
-- cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-+ cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no
- $(MAKE) -C $(IPERF_PATH)
- $(STRIP) -s $@
-
-@@ -308,8 +308,8 @@ $(WIREGUARD_TOOLS_PATH)/.installed: $(WI
- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- touch $@
-
--$(WIREGUARD_TOOLS_PATH)/src/tools/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src/tools LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
-+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+ LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
- $(STRIP) -s $@
-
- $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
-@@ -323,7 +323,8 @@ $(IPUTILS_PATH)/.installed: $(IPUTILS_TA
- touch $@
-
- $(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS)
-- $(MAKE) -C $(IPUTILS_PATH) USE_CAP=no USE_IDN=no USE_NETTLE=no USE_CRYPTO=no ping
-+ sed -i /atexit/d $(IPUTILS_PATH)/ping.c
-+ cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS)
- $(STRIP) -s $@
-
- $(BASH_PATH)/.installed: $(BASH_TAR)
-@@ -357,7 +358,7 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_
- sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
- touch $@
-
--$(IPTABLES_PATH)/iptables/xtables-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
- $(MAKE) -C $(IPTABLES_PATH)
- $(STRIP) -s $@
-@@ -368,8 +369,9 @@ $(NMAP_PATH)/.installed: $(NMAP_TAR)
- touch $@
-
- $(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS)
-- cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux
-- $(MAKE) -C $(NMAP_PATH) build-ncat
-+ cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh
-+ $(MAKE) -C $(NMAP_PATH)/libpcap
-+ $(MAKE) -C $(NMAP_PATH)/ncat
- $(STRIP) -s $@
-
- clean:
-@@ -379,7 +381,7 @@ distclean: clean
- rm -rf $(DISTFILES_PATH)
-
- menuconfig: $(KERNEL_BUILD_PATH)/.config
-- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) CC="$(NOPIE_GCC)" menuconfig
-+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig
-
- .PHONY: qemu build clean distclean menuconfig
- .DELETE_ON_ERROR:
---- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config
-+++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
-@@ -1,9 +1,9 @@
- CONFIG_MMU=y
-+CONFIG_M68KCLASSIC=y
- CONFIG_M68040=y
- CONFIG_MAC=y
- CONFIG_SERIAL_PMACZILOG=y
- CONFIG_SERIAL_PMACZILOG_TTYS=y
- CONFIG_SERIAL_PMACZILOG_CONSOLE=y
--CONFIG_CMDLINE_BOOL=y
- CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
- CONFIG_FRAME_WARN=1024
---- a/tools/testing/selftests/wireguard/qemu/init.c
-+++ b/tools/testing/selftests/wireguard/qemu/init.c
-@@ -21,6 +21,7 @@
- #include <sys/reboot.h>
- #include <sys/utsname.h>
- #include <sys/sendfile.h>
-+#include <sys/sysmacros.h>
- #include <linux/random.h>
- #include <linux/version.h>
-
---- a/tools/testing/selftests/wireguard/qemu/kernel.config
-+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
-@@ -39,6 +39,7 @@ CONFIG_PRINTK=y
- CONFIG_KALLSYMS=y
- CONFIG_BUG=y
- CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y
-+CONFIG_JUMP_LABEL=y
- CONFIG_EMBEDDED=n
- CONFIG_BASE_FULL=y
- CONFIG_FUTEX=y
-@@ -55,6 +56,7 @@ CONFIG_NO_HZ_IDLE=y
- CONFIG_NO_HZ_FULL=n
- CONFIG_HZ_PERIODIC=n
- CONFIG_HIGH_RES_TIMERS=y
-+CONFIG_COMPAT_32BIT_TIME=y
- CONFIG_ARCH_RANDOM=y
- CONFIG_FILE_LOCKING=y
- CONFIG_POSIX_TIMERS=y
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Thu, 2 Jan 2020 17:47:51 +0100
+Subject: [PATCH] wireguard: socket: mark skbs as not on list when receiving
+ via gro
+
+commit 736775d06bac60d7a353e405398b48b2bd8b1e54 upstream.
+
+Certain drivers will pass gro skbs to udp, at which point the udp driver
+simply iterates through them and passes them off to encap_rcv, which is
+where we pick up. At the moment, we're not attempting to coalesce these
+into bundles, but we also don't want to wind up having cascaded lists of
+skbs treated separately. The right behavior here, then, is to just mark
+each incoming one as not on a list. This can be seen in practice, for
+example, with Qualcomm's rmnet_perf driver.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Tested-by: Yaroslav Furman <yaro330@gmail.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/socket.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -333,6 +333,7 @@ static int wg_receive(struct sock *sk, s
+ wg = sk->sk_user_data;
+ if (unlikely(!wg))
+ goto err;
++ skb_mark_not_on_list(skb);
+ wg_packet_receive(wg, skb);
+ return 0;
+
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Tue, 4 Feb 2020 22:17:25 +0100
+Subject: [PATCH] wireguard: allowedips: fix use-after-free in
+ root_remove_peer_lists
+
+commit 9981159fc3b677b357f84e069a11de5a5ec8a2a8 upstream.
+
+In the unlikely case a new node could not be allocated, we need to
+remove @newnode from @peer->allowedips_list before freeing it.
+
+syzbot reported:
+
+BUG: KASAN: use-after-free in __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54
+Read of size 8 at addr ffff88809881a538 by task syz-executor.4/30133
+
+CPU: 0 PID: 30133 Comm: syz-executor.4 Not tainted 5.5.0-syzkaller #0
+Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
+Call Trace:
+ __dump_stack lib/dump_stack.c:77 [inline]
+ dump_stack+0x197/0x210 lib/dump_stack.c:118
+ print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
+ __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506
+ kasan_report+0x12/0x20 mm/kasan/common.c:639
+ __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
+ __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54
+ __list_del_entry include/linux/list.h:132 [inline]
+ list_del include/linux/list.h:146 [inline]
+ root_remove_peer_lists+0x24f/0x4b0 drivers/net/wireguard/allowedips.c:65
+ wg_allowedips_free+0x232/0x390 drivers/net/wireguard/allowedips.c:300
+ wg_peer_remove_all+0xd5/0x620 drivers/net/wireguard/peer.c:187
+ wg_set_device+0xd01/0x1350 drivers/net/wireguard/netlink.c:542
+ genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
+ genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
+ genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
+ netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
+ genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
+ netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
+ netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
+ netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
+ sock_sendmsg_nosec net/socket.c:652 [inline]
+ sock_sendmsg+0xd7/0x130 net/socket.c:672
+ ____sys_sendmsg+0x753/0x880 net/socket.c:2343
+ ___sys_sendmsg+0x100/0x170 net/socket.c:2397
+ __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
+ __do_sys_sendmsg net/socket.c:2439 [inline]
+ __se_sys_sendmsg net/socket.c:2437 [inline]
+ __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
+ do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
+ entry_SYSCALL_64_after_hwframe+0x49/0xbe
+RIP: 0033:0x45b399
+Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
+RSP: 002b:00007f99a9bcdc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
+RAX: ffffffffffffffda RBX: 00007f99a9bce6d4 RCX: 000000000045b399
+RDX: 0000000000000000 RSI: 0000000020001340 RDI: 0000000000000003
+RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
+R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004
+R13: 00000000000009ba R14: 00000000004cb2b8 R15: 0000000000000009
+
+Allocated by task 30103:
+ save_stack+0x23/0x90 mm/kasan/common.c:72
+ set_track mm/kasan/common.c:80 [inline]
+ __kasan_kmalloc mm/kasan/common.c:513 [inline]
+ __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
+ kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527
+ kmem_cache_alloc_trace+0x158/0x790 mm/slab.c:3551
+ kmalloc include/linux/slab.h:556 [inline]
+ kzalloc include/linux/slab.h:670 [inline]
+ add+0x70a/0x1970 drivers/net/wireguard/allowedips.c:236
+ wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320
+ set_allowedip drivers/net/wireguard/netlink.c:343 [inline]
+ set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468
+ wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591
+ genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
+ genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
+ genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
+ netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
+ genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
+ netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
+ netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
+ netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
+ sock_sendmsg_nosec net/socket.c:652 [inline]
+ sock_sendmsg+0xd7/0x130 net/socket.c:672
+ ____sys_sendmsg+0x753/0x880 net/socket.c:2343
+ ___sys_sendmsg+0x100/0x170 net/socket.c:2397
+ __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
+ __do_sys_sendmsg net/socket.c:2439 [inline]
+ __se_sys_sendmsg net/socket.c:2437 [inline]
+ __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
+ do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
+ entry_SYSCALL_64_after_hwframe+0x49/0xbe
+
+Freed by task 30103:
+ save_stack+0x23/0x90 mm/kasan/common.c:72
+ set_track mm/kasan/common.c:80 [inline]
+ kasan_set_free_info mm/kasan/common.c:335 [inline]
+ __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
+ kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
+ __cache_free mm/slab.c:3426 [inline]
+ kfree+0x10a/0x2c0 mm/slab.c:3757
+ add+0x12d2/0x1970 drivers/net/wireguard/allowedips.c:266
+ wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320
+ set_allowedip drivers/net/wireguard/netlink.c:343 [inline]
+ set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468
+ wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591
+ genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
+ genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
+ genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
+ netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
+ genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
+ netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
+ netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
+ netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
+ sock_sendmsg_nosec net/socket.c:652 [inline]
+ sock_sendmsg+0xd7/0x130 net/socket.c:672
+ ____sys_sendmsg+0x753/0x880 net/socket.c:2343
+ ___sys_sendmsg+0x100/0x170 net/socket.c:2397
+ __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
+ __do_sys_sendmsg net/socket.c:2439 [inline]
+ __se_sys_sendmsg net/socket.c:2437 [inline]
+ __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
+ do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
+ entry_SYSCALL_64_after_hwframe+0x49/0xbe
+
+The buggy address belongs to the object at ffff88809881a500
+ which belongs to the cache kmalloc-64 of size 64
+The buggy address is located 56 bytes inside of
+ 64-byte region [ffff88809881a500, ffff88809881a540)
+The buggy address belongs to the page:
+page:ffffea0002620680 refcount:1 mapcount:0 mapping:ffff8880aa400380 index:0x0
+raw: 00fffe0000000200 ffffea000250b748 ffffea000254bac8 ffff8880aa400380
+raw: 0000000000000000 ffff88809881a000 0000000100000020 0000000000000000
+page dumped because: kasan: bad access detected
+
+Memory state around the buggy address:
+ ffff88809881a400: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
+ ffff88809881a480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
+>ffff88809881a500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
+ ^
+ ffff88809881a580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
+ ffff88809881a600: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: syzbot <syzkaller@googlegroups.com>
+Cc: Jason A. Donenfeld <Jason@zx2c4.com>
+Cc: wireguard@lists.zx2c4.com
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/allowedips.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/net/wireguard/allowedips.c
++++ b/drivers/net/wireguard/allowedips.c
+@@ -263,6 +263,7 @@ static int add(struct allowedips_node __
+ } else {
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
+ if (unlikely(!node)) {
++ list_del(&newnode->peer_list);
+ kfree(newnode);
+ return -ENOMEM;
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Thu, 2 Jan 2020 17:47:50 +0100
-Subject: [PATCH] wireguard: queueing: do not account for pfmemalloc when
- clearing skb header
-
-commit 04d2ea92a18417619182cbb79063f154892b0150 upstream.
-
-Before 8b7008620b84 ("net: Don't copy pfmemalloc flag in __copy_skb_
-header()"), the pfmemalloc flag used to be between headers_start and
-headers_end, which is a region we clear when preparing the packet for
-encryption/decryption. This is a parameter we certainly want to
-preserve, which is why 8b7008620b84 moved it out of there. The code here
-was written in a world before 8b7008620b84, though, where we had to
-manually account for it. This commit brings things up to speed.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/queueing.h | 3 ---
- 1 file changed, 3 deletions(-)
-
---- a/drivers/net/wireguard/queueing.h
-+++ b/drivers/net/wireguard/queueing.h
-@@ -83,13 +83,10 @@ static inline __be16 wg_skb_examine_untr
-
- static inline void wg_reset_packet(struct sk_buff *skb)
- {
-- const int pfmemalloc = skb->pfmemalloc;
--
- skb_scrub_packet(skb, true);
- memset(&skb->headers_start, 0,
- offsetof(struct sk_buff, headers_end) -
- offsetof(struct sk_buff, headers_start));
-- skb->pfmemalloc = pfmemalloc;
- skb->queue_mapping = 0;
- skb->nohdr = 0;
- skb->peeked = 0;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 4 Feb 2020 22:17:26 +0100
+Subject: [PATCH] wireguard: noise: reject peers with low order public keys
+
+commit ec31c2676a10e064878927b243fada8c2fb0c03c upstream.
+
+Our static-static calculation returns a failure if the public key is of
+low order. We check for this when peers are added, and don't allow them
+to be added if they're low order, except in the case where we haven't
+yet been given a private key. In that case, we would defer the removal
+of the peer until we're given a private key, since at that point we're
+doing new static-static calculations which incur failures we can act on.
+This meant, however, that we wound up removing peers rather late in the
+configuration flow.
+
+Syzkaller points out that peer_remove calls flush_workqueue, which in
+turn might then wait for sending a handshake initiation to complete.
+Since handshake initiation needs the static identity lock, holding the
+static identity lock while calling peer_remove can result in a rare
+deadlock. We have precisely this case in this situation of late-stage
+peer removal based on an invalid public key. We can't drop the lock when
+removing, because then incoming handshakes might interact with a bogus
+static-static calculation.
+
+While the band-aid patch for this would involve breaking up the peer
+removal into two steps like wg_peer_remove_all does, in order to solve
+the locking issue, there's actually a much more elegant way of fixing
+this:
+
+If the static-static calculation succeeds with one private key, it
+*must* succeed with all others, because all 32-byte strings map to valid
+private keys, thanks to clamping. That means we can get rid of this
+silly dance and locking headaches of removing peers late in the
+configuration flow, and instead just reject them early on, regardless of
+whether the device has yet been assigned a private key. For the case
+where the device doesn't yet have a private key, we safely use zeros
+just for the purposes of checking for low order points by way of
+checking the output of the calculation.
+
+The following PoC will trigger the deadlock:
+
+ip link add wg0 type wireguard
+ip addr add 10.0.0.1/24 dev wg0
+ip link set wg0 up
+ping -f 10.0.0.2 &
+while true; do
+ wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234
+ wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=)
+done
+
+[ 0.949105] ======================================================
+[ 0.949550] WARNING: possible circular locking dependency detected
+[ 0.950143] 5.5.0-debug+ #18 Not tainted
+[ 0.950431] ------------------------------------------------------
+[ 0.950959] wg/89 is trying to acquire lock:
+[ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0
+[ 0.951865]
+[ 0.951865] but task is already holding lock:
+[ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0
+[ 0.953011]
+[ 0.953011] which lock already depends on the new lock.
+[ 0.953011]
+[ 0.953651]
+[ 0.953651] the existing dependency chain (in reverse order) is:
+[ 0.954292]
+[ 0.954292] -> #2 (&wg->static_identity.lock){++++}:
+[ 0.954804] lock_acquire+0x127/0x350
+[ 0.955133] down_read+0x83/0x410
+[ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700
+[ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280
+[ 0.956401] wg_packet_handshake_send_worker+0x10/0x20
+[ 0.956841] process_one_work+0x806/0x1500
+[ 0.957167] worker_thread+0x8c/0xcb0
+[ 0.957549] kthread+0x2ee/0x3b0
+[ 0.957792] ret_from_fork+0x24/0x30
+[ 0.958234]
+[ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}:
+[ 0.958808] lock_acquire+0x127/0x350
+[ 0.959075] process_one_work+0x7ab/0x1500
+[ 0.959369] worker_thread+0x8c/0xcb0
+[ 0.959639] kthread+0x2ee/0x3b0
+[ 0.959896] ret_from_fork+0x24/0x30
+[ 0.960346]
+[ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}:
+[ 0.960945] check_prev_add+0x167/0x1e20
+[ 0.961351] __lock_acquire+0x2012/0x3170
+[ 0.961725] lock_acquire+0x127/0x350
+[ 0.961990] flush_workqueue+0x106/0x12f0
+[ 0.962280] peer_remove_after_dead+0x160/0x220
+[ 0.962600] wg_set_device+0xa24/0xcc0
+[ 0.962994] genl_rcv_msg+0x52f/0xe90
+[ 0.963298] netlink_rcv_skb+0x111/0x320
+[ 0.963618] genl_rcv+0x1f/0x30
+[ 0.963853] netlink_unicast+0x3f6/0x610
+[ 0.964245] netlink_sendmsg+0x700/0xb80
+[ 0.964586] __sys_sendto+0x1dd/0x2c0
+[ 0.964854] __x64_sys_sendto+0xd8/0x1b0
+[ 0.965141] do_syscall_64+0x90/0xd9a
+[ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe
+[ 0.965769]
+[ 0.965769] other info that might help us debug this:
+[ 0.965769]
+[ 0.966337] Chain exists of:
+[ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock
+[ 0.966337]
+[ 0.967417] Possible unsafe locking scenario:
+[ 0.967417]
+[ 0.967836] CPU0 CPU1
+[ 0.968155] ---- ----
+[ 0.968497] lock(&wg->static_identity.lock);
+[ 0.968779] lock((work_completion)(&peer->transmit_handshake_work));
+[ 0.969345] lock(&wg->static_identity.lock);
+[ 0.969809] lock((wq_completion)wg-kex-wg0);
+[ 0.970146]
+[ 0.970146] *** DEADLOCK ***
+[ 0.970146]
+[ 0.970531] 5 locks held by wg/89:
+[ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30
+[ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90
+[ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0
+[ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0
+[ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0
+[ 0.973653]
+[ 0.973653] stack backtrace:
+[ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18
+[ 0.974476] Call Trace:
+[ 0.974638] dump_stack+0x97/0xe0
+[ 0.974869] check_noncircular+0x312/0x3e0
+[ 0.975132] ? print_circular_bug+0x1f0/0x1f0
+[ 0.975410] ? __kernel_text_address+0x9/0x30
+[ 0.975727] ? unwind_get_return_address+0x51/0x90
+[ 0.976024] check_prev_add+0x167/0x1e20
+[ 0.976367] ? graph_lock+0x70/0x160
+[ 0.976682] __lock_acquire+0x2012/0x3170
+[ 0.976998] ? register_lock_class+0x1140/0x1140
+[ 0.977323] lock_acquire+0x127/0x350
+[ 0.977627] ? flush_workqueue+0xe3/0x12f0
+[ 0.977890] flush_workqueue+0x106/0x12f0
+[ 0.978147] ? flush_workqueue+0xe3/0x12f0
+[ 0.978410] ? find_held_lock+0x2c/0x110
+[ 0.978662] ? lock_downgrade+0x6e0/0x6e0
+[ 0.978919] ? queue_rcu_work+0x60/0x60
+[ 0.979166] ? netif_napi_del+0x151/0x3b0
+[ 0.979501] ? peer_remove_after_dead+0x160/0x220
+[ 0.979871] peer_remove_after_dead+0x160/0x220
+[ 0.980232] wg_set_device+0xa24/0xcc0
+[ 0.980516] ? deref_stack_reg+0x8e/0xc0
+[ 0.980801] ? set_peer+0xe10/0xe10
+[ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150
+[ 0.981430] ? __nla_validate_parse+0x163/0x270
+[ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310
+[ 0.982078] genl_rcv_msg+0x52f/0xe90
+[ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310
+[ 0.982690] ? register_lock_class+0x1140/0x1140
+[ 0.983049] netlink_rcv_skb+0x111/0x320
+[ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310
+[ 0.983645] ? netlink_ack+0x880/0x880
+[ 0.983888] genl_rcv+0x1f/0x30
+[ 0.984168] netlink_unicast+0x3f6/0x610
+[ 0.984443] ? netlink_detachskb+0x60/0x60
+[ 0.984729] ? find_held_lock+0x2c/0x110
+[ 0.984976] netlink_sendmsg+0x700/0xb80
+[ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60
+[ 0.985533] __sys_sendto+0x1dd/0x2c0
+[ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0
+[ 0.986039] ? sockfd_lookup_light+0x17/0x160
+[ 0.986397] ? __sys_recvmsg+0x8c/0xf0
+[ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0
+[ 0.987018] __x64_sys_sendto+0xd8/0x1b0
+[ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0
+[ 0.987666] do_syscall_64+0x90/0xd9a
+[ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe
+[ 0.988223] RIP: 0033:0x7fe77c12003e
+[ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4
+[ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
+[ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e
+[ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004
+[ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c
+[ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c
+[ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Reported-by: syzbot <syzkaller@googlegroups.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/netlink.c | 6 ++----
+ drivers/net/wireguard/noise.c | 10 +++++++---
+ 2 files changed, 9 insertions(+), 7 deletions(-)
+
+--- a/drivers/net/wireguard/netlink.c
++++ b/drivers/net/wireguard/netlink.c
+@@ -575,10 +575,8 @@ static int wg_set_device(struct sk_buff
+ private_key);
+ list_for_each_entry_safe(peer, temp, &wg->peer_list,
+ peer_list) {
+- if (wg_noise_precompute_static_static(peer))
+- wg_noise_expire_current_peer_keypairs(peer);
+- else
+- wg_peer_remove(peer);
++ BUG_ON(!wg_noise_precompute_static_static(peer));
++ wg_noise_expire_current_peer_keypairs(peer);
+ }
+ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
+ up_write(&wg->static_identity.lock);
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -46,17 +46,21 @@ void __init wg_noise_init(void)
+ /* Must hold peer->handshake.static_identity->lock */
+ bool wg_noise_precompute_static_static(struct wg_peer *peer)
+ {
+- bool ret = true;
++ bool ret;
+
+ down_write(&peer->handshake.lock);
+- if (peer->handshake.static_identity->has_identity)
++ if (peer->handshake.static_identity->has_identity) {
+ ret = curve25519(
+ peer->handshake.precomputed_static_static,
+ peer->handshake.static_identity->static_private,
+ peer->handshake.remote_static);
+- else
++ } else {
++ u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 };
++
++ ret = curve25519(empty, empty, peer->handshake.remote_static);
+ memset(peer->handshake.precomputed_static_static, 0,
+ NOISE_PUBLIC_KEY_LEN);
++ }
+ up_write(&peer->handshake.lock);
+ return ret;
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Thu, 2 Jan 2020 17:47:51 +0100
-Subject: [PATCH] wireguard: socket: mark skbs as not on list when receiving
- via gro
-
-commit 736775d06bac60d7a353e405398b48b2bd8b1e54 upstream.
-
-Certain drivers will pass gro skbs to udp, at which point the udp driver
-simply iterates through them and passes them off to encap_rcv, which is
-where we pick up. At the moment, we're not attempting to coalesce these
-into bundles, but we also don't want to wind up having cascaded lists of
-skbs treated separately. The right behavior here, then, is to just mark
-each incoming one as not on a list. This can be seen in practice, for
-example, with Qualcomm's rmnet_perf driver.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Tested-by: Yaroslav Furman <yaro330@gmail.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/socket.c | 1 +
- 1 file changed, 1 insertion(+)
-
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -333,6 +333,7 @@ static int wg_receive(struct sock *sk, s
- wg = sk->sk_user_data;
- if (unlikely(!wg))
- goto err;
-+ skb_mark_not_on_list(skb);
- wg_packet_receive(wg, skb);
- return 0;
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Eric Dumazet <edumazet@google.com>
-Date: Tue, 4 Feb 2020 22:17:25 +0100
-Subject: [PATCH] wireguard: allowedips: fix use-after-free in
- root_remove_peer_lists
-
-commit 9981159fc3b677b357f84e069a11de5a5ec8a2a8 upstream.
-
-In the unlikely case a new node could not be allocated, we need to
-remove @newnode from @peer->allowedips_list before freeing it.
-
-syzbot reported:
-
-BUG: KASAN: use-after-free in __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54
-Read of size 8 at addr ffff88809881a538 by task syz-executor.4/30133
-
-CPU: 0 PID: 30133 Comm: syz-executor.4 Not tainted 5.5.0-syzkaller #0
-Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
-Call Trace:
- __dump_stack lib/dump_stack.c:77 [inline]
- dump_stack+0x197/0x210 lib/dump_stack.c:118
- print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
- __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506
- kasan_report+0x12/0x20 mm/kasan/common.c:639
- __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135
- __list_del_entry_valid+0xdc/0xf5 lib/list_debug.c:54
- __list_del_entry include/linux/list.h:132 [inline]
- list_del include/linux/list.h:146 [inline]
- root_remove_peer_lists+0x24f/0x4b0 drivers/net/wireguard/allowedips.c:65
- wg_allowedips_free+0x232/0x390 drivers/net/wireguard/allowedips.c:300
- wg_peer_remove_all+0xd5/0x620 drivers/net/wireguard/peer.c:187
- wg_set_device+0xd01/0x1350 drivers/net/wireguard/netlink.c:542
- genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
- genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
- genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
- netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
- genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
- netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
- netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
- netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
- sock_sendmsg_nosec net/socket.c:652 [inline]
- sock_sendmsg+0xd7/0x130 net/socket.c:672
- ____sys_sendmsg+0x753/0x880 net/socket.c:2343
- ___sys_sendmsg+0x100/0x170 net/socket.c:2397
- __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
- __do_sys_sendmsg net/socket.c:2439 [inline]
- __se_sys_sendmsg net/socket.c:2437 [inline]
- __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
- do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
- entry_SYSCALL_64_after_hwframe+0x49/0xbe
-RIP: 0033:0x45b399
-Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
-RSP: 002b:00007f99a9bcdc78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
-RAX: ffffffffffffffda RBX: 00007f99a9bce6d4 RCX: 000000000045b399
-RDX: 0000000000000000 RSI: 0000000020001340 RDI: 0000000000000003
-RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
-R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000004
-R13: 00000000000009ba R14: 00000000004cb2b8 R15: 0000000000000009
-
-Allocated by task 30103:
- save_stack+0x23/0x90 mm/kasan/common.c:72
- set_track mm/kasan/common.c:80 [inline]
- __kasan_kmalloc mm/kasan/common.c:513 [inline]
- __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
- kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527
- kmem_cache_alloc_trace+0x158/0x790 mm/slab.c:3551
- kmalloc include/linux/slab.h:556 [inline]
- kzalloc include/linux/slab.h:670 [inline]
- add+0x70a/0x1970 drivers/net/wireguard/allowedips.c:236
- wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320
- set_allowedip drivers/net/wireguard/netlink.c:343 [inline]
- set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468
- wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591
- genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
- genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
- genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
- netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
- genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
- netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
- netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
- netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
- sock_sendmsg_nosec net/socket.c:652 [inline]
- sock_sendmsg+0xd7/0x130 net/socket.c:672
- ____sys_sendmsg+0x753/0x880 net/socket.c:2343
- ___sys_sendmsg+0x100/0x170 net/socket.c:2397
- __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
- __do_sys_sendmsg net/socket.c:2439 [inline]
- __se_sys_sendmsg net/socket.c:2437 [inline]
- __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
- do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
- entry_SYSCALL_64_after_hwframe+0x49/0xbe
-
-Freed by task 30103:
- save_stack+0x23/0x90 mm/kasan/common.c:72
- set_track mm/kasan/common.c:80 [inline]
- kasan_set_free_info mm/kasan/common.c:335 [inline]
- __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
- kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
- __cache_free mm/slab.c:3426 [inline]
- kfree+0x10a/0x2c0 mm/slab.c:3757
- add+0x12d2/0x1970 drivers/net/wireguard/allowedips.c:266
- wg_allowedips_insert_v4+0xf6/0x160 drivers/net/wireguard/allowedips.c:320
- set_allowedip drivers/net/wireguard/netlink.c:343 [inline]
- set_peer+0xfb9/0x1150 drivers/net/wireguard/netlink.c:468
- wg_set_device+0xbd4/0x1350 drivers/net/wireguard/netlink.c:591
- genl_family_rcv_msg_doit net/netlink/genetlink.c:672 [inline]
- genl_family_rcv_msg net/netlink/genetlink.c:717 [inline]
- genl_rcv_msg+0x67d/0xea0 net/netlink/genetlink.c:734
- netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
- genl_rcv+0x29/0x40 net/netlink/genetlink.c:745
- netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
- netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328
- netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917
- sock_sendmsg_nosec net/socket.c:652 [inline]
- sock_sendmsg+0xd7/0x130 net/socket.c:672
- ____sys_sendmsg+0x753/0x880 net/socket.c:2343
- ___sys_sendmsg+0x100/0x170 net/socket.c:2397
- __sys_sendmsg+0x105/0x1d0 net/socket.c:2430
- __do_sys_sendmsg net/socket.c:2439 [inline]
- __se_sys_sendmsg net/socket.c:2437 [inline]
- __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2437
- do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
- entry_SYSCALL_64_after_hwframe+0x49/0xbe
-
-The buggy address belongs to the object at ffff88809881a500
- which belongs to the cache kmalloc-64 of size 64
-The buggy address is located 56 bytes inside of
- 64-byte region [ffff88809881a500, ffff88809881a540)
-The buggy address belongs to the page:
-page:ffffea0002620680 refcount:1 mapcount:0 mapping:ffff8880aa400380 index:0x0
-raw: 00fffe0000000200 ffffea000250b748 ffffea000254bac8 ffff8880aa400380
-raw: 0000000000000000 ffff88809881a000 0000000100000020 0000000000000000
-page dumped because: kasan: bad access detected
-
-Memory state around the buggy address:
- ffff88809881a400: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
- ffff88809881a480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
->ffff88809881a500: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
- ^
- ffff88809881a580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
- ffff88809881a600: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Eric Dumazet <edumazet@google.com>
-Reported-by: syzbot <syzkaller@googlegroups.com>
-Cc: Jason A. Donenfeld <Jason@zx2c4.com>
-Cc: wireguard@lists.zx2c4.com
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/allowedips.c | 1 +
- 1 file changed, 1 insertion(+)
-
---- a/drivers/net/wireguard/allowedips.c
-+++ b/drivers/net/wireguard/allowedips.c
-@@ -263,6 +263,7 @@ static int add(struct allowedips_node __
- } else {
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- if (unlikely(!node)) {
-+ list_del(&newnode->peer_list);
- kfree(newnode);
- return -ENOMEM;
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 4 Feb 2020 22:17:27 +0100
+Subject: [PATCH] wireguard: selftests: ensure non-addition of peers with
+ failed precomputation
+
+commit f9398acba6a4ae9cb98bfe4d56414d376eff8d57 upstream.
+
+Ensure that peers with low order points are ignored, both in the case
+where we already have a device private key and in the case where we do
+not. This adds points that naturally give a zero output.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/netns.sh | 6 ++++++
+ 1 file changed, 6 insertions(+)
+
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -516,6 +516,12 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0
+ n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0
+ n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
+ n0 wg set wg0 peer "$pub2" allowed-ips ::/0
++n0 wg set wg0 peer "$pub2" remove
++low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= )
++n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer }
++[[ -z $(n0 wg show wg0 peers) ]]
++n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer }
++[[ -z $(n0 wg show wg0 peers) ]]
+ ip0 link del wg0
+
+ declare -A objects
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 4 Feb 2020 22:17:26 +0100
-Subject: [PATCH] wireguard: noise: reject peers with low order public keys
-
-commit ec31c2676a10e064878927b243fada8c2fb0c03c upstream.
-
-Our static-static calculation returns a failure if the public key is of
-low order. We check for this when peers are added, and don't allow them
-to be added if they're low order, except in the case where we haven't
-yet been given a private key. In that case, we would defer the removal
-of the peer until we're given a private key, since at that point we're
-doing new static-static calculations which incur failures we can act on.
-This meant, however, that we wound up removing peers rather late in the
-configuration flow.
-
-Syzkaller points out that peer_remove calls flush_workqueue, which in
-turn might then wait for sending a handshake initiation to complete.
-Since handshake initiation needs the static identity lock, holding the
-static identity lock while calling peer_remove can result in a rare
-deadlock. We have precisely this case in this situation of late-stage
-peer removal based on an invalid public key. We can't drop the lock when
-removing, because then incoming handshakes might interact with a bogus
-static-static calculation.
-
-While the band-aid patch for this would involve breaking up the peer
-removal into two steps like wg_peer_remove_all does, in order to solve
-the locking issue, there's actually a much more elegant way of fixing
-this:
-
-If the static-static calculation succeeds with one private key, it
-*must* succeed with all others, because all 32-byte strings map to valid
-private keys, thanks to clamping. That means we can get rid of this
-silly dance and locking headaches of removing peers late in the
-configuration flow, and instead just reject them early on, regardless of
-whether the device has yet been assigned a private key. For the case
-where the device doesn't yet have a private key, we safely use zeros
-just for the purposes of checking for low order points by way of
-checking the output of the calculation.
-
-The following PoC will trigger the deadlock:
-
-ip link add wg0 type wireguard
-ip addr add 10.0.0.1/24 dev wg0
-ip link set wg0 up
-ping -f 10.0.0.2 &
-while true; do
- wg set wg0 private-key /dev/null peer AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= allowed-ips 10.0.0.0/24 endpoint 10.0.0.3:1234
- wg set wg0 private-key <(echo AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=)
-done
-
-[ 0.949105] ======================================================
-[ 0.949550] WARNING: possible circular locking dependency detected
-[ 0.950143] 5.5.0-debug+ #18 Not tainted
-[ 0.950431] ------------------------------------------------------
-[ 0.950959] wg/89 is trying to acquire lock:
-[ 0.951252] ffff8880333e2128 ((wq_completion)wg-kex-wg0){+.+.}, at: flush_workqueue+0xe3/0x12f0
-[ 0.951865]
-[ 0.951865] but task is already holding lock:
-[ 0.952280] ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0
-[ 0.953011]
-[ 0.953011] which lock already depends on the new lock.
-[ 0.953011]
-[ 0.953651]
-[ 0.953651] the existing dependency chain (in reverse order) is:
-[ 0.954292]
-[ 0.954292] -> #2 (&wg->static_identity.lock){++++}:
-[ 0.954804] lock_acquire+0x127/0x350
-[ 0.955133] down_read+0x83/0x410
-[ 0.955428] wg_noise_handshake_create_initiation+0x97/0x700
-[ 0.955885] wg_packet_send_handshake_initiation+0x13a/0x280
-[ 0.956401] wg_packet_handshake_send_worker+0x10/0x20
-[ 0.956841] process_one_work+0x806/0x1500
-[ 0.957167] worker_thread+0x8c/0xcb0
-[ 0.957549] kthread+0x2ee/0x3b0
-[ 0.957792] ret_from_fork+0x24/0x30
-[ 0.958234]
-[ 0.958234] -> #1 ((work_completion)(&peer->transmit_handshake_work)){+.+.}:
-[ 0.958808] lock_acquire+0x127/0x350
-[ 0.959075] process_one_work+0x7ab/0x1500
-[ 0.959369] worker_thread+0x8c/0xcb0
-[ 0.959639] kthread+0x2ee/0x3b0
-[ 0.959896] ret_from_fork+0x24/0x30
-[ 0.960346]
-[ 0.960346] -> #0 ((wq_completion)wg-kex-wg0){+.+.}:
-[ 0.960945] check_prev_add+0x167/0x1e20
-[ 0.961351] __lock_acquire+0x2012/0x3170
-[ 0.961725] lock_acquire+0x127/0x350
-[ 0.961990] flush_workqueue+0x106/0x12f0
-[ 0.962280] peer_remove_after_dead+0x160/0x220
-[ 0.962600] wg_set_device+0xa24/0xcc0
-[ 0.962994] genl_rcv_msg+0x52f/0xe90
-[ 0.963298] netlink_rcv_skb+0x111/0x320
-[ 0.963618] genl_rcv+0x1f/0x30
-[ 0.963853] netlink_unicast+0x3f6/0x610
-[ 0.964245] netlink_sendmsg+0x700/0xb80
-[ 0.964586] __sys_sendto+0x1dd/0x2c0
-[ 0.964854] __x64_sys_sendto+0xd8/0x1b0
-[ 0.965141] do_syscall_64+0x90/0xd9a
-[ 0.965408] entry_SYSCALL_64_after_hwframe+0x49/0xbe
-[ 0.965769]
-[ 0.965769] other info that might help us debug this:
-[ 0.965769]
-[ 0.966337] Chain exists of:
-[ 0.966337] (wq_completion)wg-kex-wg0 --> (work_completion)(&peer->transmit_handshake_work) --> &wg->static_identity.lock
-[ 0.966337]
-[ 0.967417] Possible unsafe locking scenario:
-[ 0.967417]
-[ 0.967836] CPU0 CPU1
-[ 0.968155] ---- ----
-[ 0.968497] lock(&wg->static_identity.lock);
-[ 0.968779] lock((work_completion)(&peer->transmit_handshake_work));
-[ 0.969345] lock(&wg->static_identity.lock);
-[ 0.969809] lock((wq_completion)wg-kex-wg0);
-[ 0.970146]
-[ 0.970146] *** DEADLOCK ***
-[ 0.970146]
-[ 0.970531] 5 locks held by wg/89:
-[ 0.970908] #0: ffffffff827433c8 (cb_lock){++++}, at: genl_rcv+0x10/0x30
-[ 0.971400] #1: ffffffff82743480 (genl_mutex){+.+.}, at: genl_rcv_msg+0x642/0xe90
-[ 0.971924] #2: ffffffff827160c0 (rtnl_mutex){+.+.}, at: wg_set_device+0x9f/0xcc0
-[ 0.972488] #3: ffff888032819de0 (&wg->device_update_lock){+.+.}, at: wg_set_device+0xb0/0xcc0
-[ 0.973095] #4: ffff888032819bc0 (&wg->static_identity.lock){++++}, at: wg_set_device+0x95d/0xcc0
-[ 0.973653]
-[ 0.973653] stack backtrace:
-[ 0.973932] CPU: 1 PID: 89 Comm: wg Not tainted 5.5.0-debug+ #18
-[ 0.974476] Call Trace:
-[ 0.974638] dump_stack+0x97/0xe0
-[ 0.974869] check_noncircular+0x312/0x3e0
-[ 0.975132] ? print_circular_bug+0x1f0/0x1f0
-[ 0.975410] ? __kernel_text_address+0x9/0x30
-[ 0.975727] ? unwind_get_return_address+0x51/0x90
-[ 0.976024] check_prev_add+0x167/0x1e20
-[ 0.976367] ? graph_lock+0x70/0x160
-[ 0.976682] __lock_acquire+0x2012/0x3170
-[ 0.976998] ? register_lock_class+0x1140/0x1140
-[ 0.977323] lock_acquire+0x127/0x350
-[ 0.977627] ? flush_workqueue+0xe3/0x12f0
-[ 0.977890] flush_workqueue+0x106/0x12f0
-[ 0.978147] ? flush_workqueue+0xe3/0x12f0
-[ 0.978410] ? find_held_lock+0x2c/0x110
-[ 0.978662] ? lock_downgrade+0x6e0/0x6e0
-[ 0.978919] ? queue_rcu_work+0x60/0x60
-[ 0.979166] ? netif_napi_del+0x151/0x3b0
-[ 0.979501] ? peer_remove_after_dead+0x160/0x220
-[ 0.979871] peer_remove_after_dead+0x160/0x220
-[ 0.980232] wg_set_device+0xa24/0xcc0
-[ 0.980516] ? deref_stack_reg+0x8e/0xc0
-[ 0.980801] ? set_peer+0xe10/0xe10
-[ 0.981040] ? __ww_mutex_check_waiters+0x150/0x150
-[ 0.981430] ? __nla_validate_parse+0x163/0x270
-[ 0.981719] ? genl_family_rcv_msg_attrs_parse+0x13f/0x310
-[ 0.982078] genl_rcv_msg+0x52f/0xe90
-[ 0.982348] ? genl_family_rcv_msg_attrs_parse+0x310/0x310
-[ 0.982690] ? register_lock_class+0x1140/0x1140
-[ 0.983049] netlink_rcv_skb+0x111/0x320
-[ 0.983298] ? genl_family_rcv_msg_attrs_parse+0x310/0x310
-[ 0.983645] ? netlink_ack+0x880/0x880
-[ 0.983888] genl_rcv+0x1f/0x30
-[ 0.984168] netlink_unicast+0x3f6/0x610
-[ 0.984443] ? netlink_detachskb+0x60/0x60
-[ 0.984729] ? find_held_lock+0x2c/0x110
-[ 0.984976] netlink_sendmsg+0x700/0xb80
-[ 0.985220] ? netlink_broadcast_filtered+0xa60/0xa60
-[ 0.985533] __sys_sendto+0x1dd/0x2c0
-[ 0.985763] ? __x64_sys_getpeername+0xb0/0xb0
-[ 0.986039] ? sockfd_lookup_light+0x17/0x160
-[ 0.986397] ? __sys_recvmsg+0x8c/0xf0
-[ 0.986711] ? __sys_recvmsg_sock+0xd0/0xd0
-[ 0.987018] __x64_sys_sendto+0xd8/0x1b0
-[ 0.987283] ? lockdep_hardirqs_on+0x39b/0x5a0
-[ 0.987666] do_syscall_64+0x90/0xd9a
-[ 0.987903] entry_SYSCALL_64_after_hwframe+0x49/0xbe
-[ 0.988223] RIP: 0033:0x7fe77c12003e
-[ 0.988508] Code: c3 8b 07 85 c0 75 24 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 4
-[ 0.989666] RSP: 002b:00007fffada2ed58 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
-[ 0.990137] RAX: ffffffffffffffda RBX: 00007fe77c159d48 RCX: 00007fe77c12003e
-[ 0.990583] RDX: 0000000000000040 RSI: 000055fd1d38e020 RDI: 0000000000000004
-[ 0.991091] RBP: 000055fd1d38e020 R08: 000055fd1cb63358 R09: 000000000000000c
-[ 0.991568] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000002c
-[ 0.992014] R13: 0000000000000004 R14: 000055fd1d38e020 R15: 0000000000000001
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Reported-by: syzbot <syzkaller@googlegroups.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/netlink.c | 6 ++----
- drivers/net/wireguard/noise.c | 10 +++++++---
- 2 files changed, 9 insertions(+), 7 deletions(-)
-
---- a/drivers/net/wireguard/netlink.c
-+++ b/drivers/net/wireguard/netlink.c
-@@ -575,10 +575,8 @@ static int wg_set_device(struct sk_buff
- private_key);
- list_for_each_entry_safe(peer, temp, &wg->peer_list,
- peer_list) {
-- if (wg_noise_precompute_static_static(peer))
-- wg_noise_expire_current_peer_keypairs(peer);
-- else
-- wg_peer_remove(peer);
-+ BUG_ON(!wg_noise_precompute_static_static(peer));
-+ wg_noise_expire_current_peer_keypairs(peer);
- }
- wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
- up_write(&wg->static_identity.lock);
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -46,17 +46,21 @@ void __init wg_noise_init(void)
- /* Must hold peer->handshake.static_identity->lock */
- bool wg_noise_precompute_static_static(struct wg_peer *peer)
- {
-- bool ret = true;
-+ bool ret;
-
- down_write(&peer->handshake.lock);
-- if (peer->handshake.static_identity->has_identity)
-+ if (peer->handshake.static_identity->has_identity) {
- ret = curve25519(
- peer->handshake.precomputed_static_static,
- peer->handshake.static_identity->static_private,
- peer->handshake.remote_static);
-- else
-+ } else {
-+ u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 };
-+
-+ ret = curve25519(empty, empty, peer->handshake.remote_static);
- memset(peer->handshake.precomputed_static_static, 0,
- NOISE_PUBLIC_KEY_LEN);
-+ }
- up_write(&peer->handshake.lock);
- return ret;
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 4 Feb 2020 22:17:29 +0100
+Subject: [PATCH] wireguard: selftests: tie socket waiting to target pid
+
+commit 88f404a9b1d75388225b1c67b6dd327cb2182777 upstream.
+
+Without this, we wind up proceeding too early sometimes when the
+previous process has just used the same listening port. So, we tie the
+listening socket query to the specific pid we're interested in.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/netns.sh | 17 ++++++++---------
+ 1 file changed, 8 insertions(+), 9 deletions(-)
+
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -38,9 +38,8 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0
+ ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
+ ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
+ sleep() { read -t "$1" -N 1 || true; }
+-waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
+-waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
+-waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
++waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
++waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; }
+ waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
+
+ cleanup() {
+@@ -119,22 +118,22 @@ tests() {
+
+ # TCP over IPv4
+ n2 iperf3 -s -1 -B 192.168.241.2 &
+- waitiperf $netns2
++ waitiperf $netns2 $!
+ n1 iperf3 -Z -t 3 -c 192.168.241.2
+
+ # TCP over IPv6
+ n1 iperf3 -s -1 -B fd00::1 &
+- waitiperf $netns1
++ waitiperf $netns1 $!
+ n2 iperf3 -Z -t 3 -c fd00::1
+
+ # UDP over IPv4
+ n1 iperf3 -s -1 -B 192.168.241.1 &
+- waitiperf $netns1
++ waitiperf $netns1 $!
+ n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1
+
+ # UDP over IPv6
+ n2 iperf3 -s -1 -B fd00::2 &
+- waitiperf $netns2
++ waitiperf $netns2 $!
+ n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
+ }
+
+@@ -207,7 +206,7 @@ n1 ping -W 1 -c 1 192.168.241.2
+ n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24
+ exec 4< <(n1 ncat -l -u -p 1111)
+ ncat_pid=$!
+-waitncatudp $netns1
++waitncatudp $netns1 $ncat_pid
+ n2 ncat -u 192.168.241.1 1111 <<<"X"
+ read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]]
+ kill $ncat_pid
+@@ -216,7 +215,7 @@ n1 wg set wg0 peer "$more_specific_key"
+ n2 wg set wg0 listen-port 9997
+ exec 4< <(n1 ncat -l -u -p 1111)
+ ncat_pid=$!
+-waitncatudp $netns1
++waitncatudp $netns1 $ncat_pid
+ n2 ncat -u 192.168.241.1 1111 <<<"X"
+ ! read -r -N 1 -t 1 out <&4 || false
+ kill $ncat_pid
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 11 Feb 2020 20:47:08 +0100
+Subject: [PATCH] wireguard: device: use icmp_ndo_send helper
+
+commit a12d7f3cbdc72c7625881c8dc2660fc2c979fdf2 upstream.
+
+Because wireguard is calling icmp from network device context, it should
+use the ndo helper so that the rate limiting applies correctly. This
+commit adds a small test to the wireguard test suite to ensure that the
+new functions continue doing the right thing in the context of
+wireguard. It does this by setting up a condition that will definately
+evoke an icmp error message from the driver, but along a nat'd path.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 4 ++--
+ tools/testing/selftests/wireguard/netns.sh | 11 +++++++++++
+ 2 files changed, 13 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -203,9 +203,9 @@ err_peer:
+ err:
+ ++dev->stats.tx_errors;
+ if (skb->protocol == htons(ETH_P_IP))
+- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
++ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ else if (skb->protocol == htons(ETH_P_IPV6))
+- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
++ icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
+ kfree_skb(skb);
+ return ret;
+ }
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -24,6 +24,7 @@
+ set -e
+
+ exec 3>&1
++export LANG=C
+ export WG_HIDE_KEYS=never
+ netns0="wg-test-$$-0"
+ netns1="wg-test-$$-1"
+@@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_pref
+ n1 ping -W 1 -c 100 -f 192.168.99.7
+ n1 ping -W 1 -c 100 -f abab::1111
+
++# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route.
++n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2
++n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit.
++n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
++ip0 -4 route add 192.168.241.1 via 10.0.0.100
++n2 wg set wg0 peer "$pub1" remove
++[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]]
++
+ n0 iptables -t nat -F
++n0 iptables -t filter -F
++n2 iptables -t nat -F
+ ip0 link del vethrc
+ ip0 link del vethrs
+ ip1 link del wg0
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 4 Feb 2020 22:17:27 +0100
-Subject: [PATCH] wireguard: selftests: ensure non-addition of peers with
- failed precomputation
-
-commit f9398acba6a4ae9cb98bfe4d56414d376eff8d57 upstream.
-
-Ensure that peers with low order points are ignored, both in the case
-where we already have a device private key and in the case where we do
-not. This adds points that naturally give a zero output.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/netns.sh | 6 ++++++
- 1 file changed, 6 insertions(+)
-
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -516,6 +516,12 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0
- n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0
- n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
- n0 wg set wg0 peer "$pub2" allowed-ips ::/0
-+n0 wg set wg0 peer "$pub2" remove
-+low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= )
-+n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer }
-+[[ -z $(n0 wg show wg0 peers) ]]
-+n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer }
-+[[ -z $(n0 wg show wg0 peers) ]]
- ip0 link del wg0
-
- declare -A objects
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Fri, 14 Feb 2020 23:57:20 +0100
+Subject: [PATCH] wireguard: selftests: reduce complexity and fix make races
+
+commit 04ddf1208f03e1dbc39a4619c40eba640051b950 upstream.
+
+This gives us fewer dependencies and shortens build time, fixes up some
+hash checking race conditions, and also fixes missing directory creation
+that caused issues on massively parallel builds.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ .../testing/selftests/wireguard/qemu/Makefile | 38 +++++++------------
+ 1 file changed, 14 insertions(+), 24 deletions(-)
+
+--- a/tools/testing/selftests/wireguard/qemu/Makefile
++++ b/tools/testing/selftests/wireguard/qemu/Makefile
+@@ -38,19 +38,17 @@ endef
+ define file_download =
+ $(DISTFILES_PATH)/$(1):
+ mkdir -p $(DISTFILES_PATH)
+- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
+- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
++ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
+ endef
+
+ $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
+-$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
+ $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
+ $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
+ $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
+ $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
+ $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
+ $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
+-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
++$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
+
+ KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
+ rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
+@@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH
+ $(MAKE) -C $(IPERF_PATH)
+ $(STRIP) -s $@
+
+-$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
+- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
+- touch $@
+-
+-$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
+- cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
+- $(MAKE) -C $(LIBMNL_PATH)
+- sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
+-
+ $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
++ mkdir -p $(BUILD_PATH)
+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
+ touch $@
+
+-$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
++$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
++ $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
+ $(STRIP) -s $@
+
+ $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
+@@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.insta
+ $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
+ mkdir -p $(BUILD_PATH)
+ flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
+- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
++ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
+ printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
+ touch $@
+
+-$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
+- $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
+-
+-$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
+- $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
++$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
++ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
++ $(STRIP) -s $@
++
++$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
++ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
++ $(STRIP) -s $@
+
+ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
+ mkdir -p $(BUILD_PATH)
+@@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_
+ sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
+ touch $@
+
+-$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
+- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
++$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
++ cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
+ $(MAKE) -C $(IPTABLES_PATH)
+ $(STRIP) -s $@
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 4 Feb 2020 22:17:29 +0100
-Subject: [PATCH] wireguard: selftests: tie socket waiting to target pid
-
-commit 88f404a9b1d75388225b1c67b6dd327cb2182777 upstream.
-
-Without this, we wind up proceeding too early sometimes when the
-previous process has just used the same listening port. So, we tie the
-listening socket query to the specific pid we're interested in.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/netns.sh | 17 ++++++++---------
- 1 file changed, 8 insertions(+), 9 deletions(-)
-
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -38,9 +38,8 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0
- ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
- ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
- sleep() { read -t "$1" -N 1 || true; }
--waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; }
--waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
--waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; }
-+waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
-+waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; }
- waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
-
- cleanup() {
-@@ -119,22 +118,22 @@ tests() {
-
- # TCP over IPv4
- n2 iperf3 -s -1 -B 192.168.241.2 &
-- waitiperf $netns2
-+ waitiperf $netns2 $!
- n1 iperf3 -Z -t 3 -c 192.168.241.2
-
- # TCP over IPv6
- n1 iperf3 -s -1 -B fd00::1 &
-- waitiperf $netns1
-+ waitiperf $netns1 $!
- n2 iperf3 -Z -t 3 -c fd00::1
-
- # UDP over IPv4
- n1 iperf3 -s -1 -B 192.168.241.1 &
-- waitiperf $netns1
-+ waitiperf $netns1 $!
- n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1
-
- # UDP over IPv6
- n2 iperf3 -s -1 -B fd00::2 &
-- waitiperf $netns2
-+ waitiperf $netns2 $!
- n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
- }
-
-@@ -207,7 +206,7 @@ n1 ping -W 1 -c 1 192.168.241.2
- n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24
- exec 4< <(n1 ncat -l -u -p 1111)
- ncat_pid=$!
--waitncatudp $netns1
-+waitncatudp $netns1 $ncat_pid
- n2 ncat -u 192.168.241.1 1111 <<<"X"
- read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]]
- kill $ncat_pid
-@@ -216,7 +215,7 @@ n1 wg set wg0 peer "$more_specific_key"
- n2 wg set wg0 listen-port 9997
- exec 4< <(n1 ncat -l -u -p 1111)
- ncat_pid=$!
--waitncatudp $netns1
-+waitncatudp $netns1 $ncat_pid
- n2 ncat -u 192.168.241.1 1111 <<<"X"
- ! read -r -N 1 -t 1 out <&4 || false
- kill $ncat_pid
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 11 Feb 2020 20:47:08 +0100
-Subject: [PATCH] wireguard: device: use icmp_ndo_send helper
-
-commit a12d7f3cbdc72c7625881c8dc2660fc2c979fdf2 upstream.
-
-Because wireguard is calling icmp from network device context, it should
-use the ndo helper so that the rate limiting applies correctly. This
-commit adds a small test to the wireguard test suite to ensure that the
-new functions continue doing the right thing in the context of
-wireguard. It does this by setting up a condition that will definately
-evoke an icmp error message from the driver, but along a nat'd path.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 4 ++--
- tools/testing/selftests/wireguard/netns.sh | 11 +++++++++++
- 2 files changed, 13 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -203,9 +203,9 @@ err_peer:
- err:
- ++dev->stats.tx_errors;
- if (skb->protocol == htons(ETH_P_IP))
-- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
-+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
- else if (skb->protocol == htons(ETH_P_IPV6))
-- icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-+ icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
- kfree_skb(skb);
- return ret;
- }
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -24,6 +24,7 @@
- set -e
-
- exec 3>&1
-+export LANG=C
- export WG_HIDE_KEYS=never
- netns0="wg-test-$$-0"
- netns1="wg-test-$$-1"
-@@ -297,7 +298,17 @@ ip1 -4 rule add table main suppress_pref
- n1 ping -W 1 -c 100 -f 192.168.99.7
- n1 ping -W 1 -c 100 -f abab::1111
-
-+# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route.
-+n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2
-+n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit.
-+n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward'
-+ip0 -4 route add 192.168.241.1 via 10.0.0.100
-+n2 wg set wg0 peer "$pub1" remove
-+[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]]
-+
- n0 iptables -t nat -F
-+n0 iptables -t filter -F
-+n2 iptables -t nat -F
- ip0 link del vethrc
- ip0 link del vethrs
- ip1 link del wg0
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Fri, 14 Feb 2020 23:57:21 +0100
+Subject: [PATCH] wireguard: receive: reset last_under_load to zero
+
+commit 2a8a4df36462aa85b0db87b7c5ea145ba67e34a8 upstream.
+
+This is a small optimization that prevents more expensive comparisons
+from happening when they are no longer necessary, by clearing the
+last_under_load variable whenever we wind up in a state where we were
+under load but we no longer are.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Suggested-by: Matt Dunwoodie <ncon@noconroy.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 7 +++++--
+ 1 file changed, 5 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -118,10 +118,13 @@ static void wg_receive_handshake_packet(
+
+ under_load = skb_queue_len(&wg->incoming_handshakes) >=
+ MAX_QUEUED_INCOMING_HANDSHAKES / 8;
+- if (under_load)
++ if (under_load) {
+ last_under_load = ktime_get_coarse_boottime_ns();
+- else if (last_under_load)
++ } else if (last_under_load) {
+ under_load = !wg_birthdate_has_expired(last_under_load, 1);
++ if (!under_load)
++ last_under_load = 0;
++ }
+ mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
+ under_load);
+ if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Fri, 14 Feb 2020 23:57:20 +0100
-Subject: [PATCH] wireguard: selftests: reduce complexity and fix make races
-
-commit 04ddf1208f03e1dbc39a4619c40eba640051b950 upstream.
-
-This gives us fewer dependencies and shortens build time, fixes up some
-hash checking race conditions, and also fixes missing directory creation
-that caused issues on massively parallel builds.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- .../testing/selftests/wireguard/qemu/Makefile | 38 +++++++------------
- 1 file changed, 14 insertions(+), 24 deletions(-)
-
---- a/tools/testing/selftests/wireguard/qemu/Makefile
-+++ b/tools/testing/selftests/wireguard/qemu/Makefile
-@@ -38,19 +38,17 @@ endef
- define file_download =
- $(DISTFILES_PATH)/$(1):
- mkdir -p $(DISTFILES_PATH)
-- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp'
-- if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi
-+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
- endef
-
- $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
--$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81))
- $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
- $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
- $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
- $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
- $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
- $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
--$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f))
-+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
-
- KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
- rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-@@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH
- $(MAKE) -C $(IPERF_PATH)
- $(STRIP) -s $@
-
--$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR)
-- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-- touch $@
--
--$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS)
-- cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared
-- $(MAKE) -C $(LIBMNL_PATH)
-- sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc
--
- $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR)
-+ mkdir -p $(BUILD_PATH)
- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- touch $@
-
--$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg
-+$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS)
-+ $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg
- $(STRIP) -s $@
-
- $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
-@@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.insta
- $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
- mkdir -p $(BUILD_PATH)
- flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
-- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk
-+ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
- printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
- touch $@
-
--$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
-- $(STRIP) -s $(IPROUTE2_PATH)/ip/ip
--
--$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-- LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
-- $(STRIP) -s $(IPROUTE2_PATH)/misc/ss
-+$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
-+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip
-+ $(STRIP) -s $@
-+
-+$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
-+ $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss
-+ $(STRIP) -s $@
-
- $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR)
- mkdir -p $(BUILD_PATH)
-@@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_
- sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure
- touch $@
-
--$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS)
-- cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include
-+$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS)
-+ cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include
- $(MAKE) -C $(IPTABLES_PATH)
- $(STRIP) -s $@
-
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Fri, 14 Feb 2020 23:57:22 +0100
+Subject: [PATCH] wireguard: send: account for mtu=0 devices
+
+commit 175f1ca9a9ed8689d2028da1a7c624bb4fb4ff7e upstream.
+
+It turns out there's an easy way to get packets queued up while still
+having an MTU of zero, and that's via persistent keep alive. This commit
+makes sure that in whatever condition, we don't wind up dividing by
+zero. Note that an MTU of zero for a wireguard interface is something
+quasi-valid, so I don't think the correct fix is to limit it via
+min_mtu. This can be reproduced easily with:
+
+ip link add wg0 type wireguard
+ip link add wg1 type wireguard
+ip link set wg0 up mtu 0
+ip link set wg1 up
+wg set wg0 private-key <(wg genkey)
+wg set wg1 listen-port 1 private-key <(wg genkey) peer $(wg show wg0 public-key)
+wg set wg0 peer $(wg show wg1 public-key) persistent-keepalive 1 endpoint 127.0.0.1:1
+
+However, while min_mtu=0 seems fine, it makes sense to restrict the
+max_mtu. This commit also restricts the maximum MTU to the greatest
+number for which rounding up to the padding multiple won't overflow a
+signed integer. Packets this large were always rejected anyway
+eventually, due to checks deeper in, but it seems more sound not to even
+let the administrator configure something that won't work anyway.
+
+We use this opportunity to clean up this function a bit so that it's
+clear which paths we're expecting.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Cc: Eric Dumazet <eric.dumazet@gmail.com>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 7 ++++---
+ drivers/net/wireguard/send.c | 16 +++++++++++-----
+ 2 files changed, 15 insertions(+), 8 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -258,6 +258,8 @@ static void wg_setup(struct net_device *
+ enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+ NETIF_F_SG | NETIF_F_GSO |
+ NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
++ const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
++ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+
+ dev->netdev_ops = &netdev_ops;
+ dev->hard_header_len = 0;
+@@ -271,9 +273,8 @@ static void wg_setup(struct net_device *
+ dev->features |= WG_NETDEV_FEATURES;
+ dev->hw_features |= WG_NETDEV_FEATURES;
+ dev->hw_enc_features |= WG_NETDEV_FEATURES;
+- dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
+- sizeof(struct udphdr) -
+- max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
++ dev->mtu = ETH_DATA_LEN - overhead;
++ dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
+
+ SET_NETDEV_DEVTYPE(dev, &device_type);
+
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_pee
+
+ static unsigned int calculate_skb_padding(struct sk_buff *skb)
+ {
++ unsigned int padded_size, last_unit = skb->len;
++
++ if (unlikely(!PACKET_CB(skb)->mtu))
++ return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit;
++
+ /* We do this modulo business with the MTU, just in case the networking
+ * layer gives us a packet that's bigger than the MTU. In that case, we
+ * wouldn't want the final subtraction to overflow in the case of the
+- * padded_size being clamped.
++ * padded_size being clamped. Fortunately, that's very rarely the case,
++ * so we optimize for that not happening.
+ */
+- unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
+- unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
++ if (unlikely(last_unit > PACKET_CB(skb)->mtu))
++ last_unit %= PACKET_CB(skb)->mtu;
+
+- if (padded_size > PACKET_CB(skb)->mtu)
+- padded_size = PACKET_CB(skb)->mtu;
++ padded_size = min(PACKET_CB(skb)->mtu,
++ ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE));
+ return padded_size - last_unit;
+ }
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Fri, 14 Feb 2020 23:57:21 +0100
-Subject: [PATCH] wireguard: receive: reset last_under_load to zero
-
-commit 2a8a4df36462aa85b0db87b7c5ea145ba67e34a8 upstream.
-
-This is a small optimization that prevents more expensive comparisons
-from happening when they are no longer necessary, by clearing the
-last_under_load variable whenever we wind up in a state where we were
-under load but we no longer are.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Suggested-by: Matt Dunwoodie <ncon@noconroy.net>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 7 +++++--
- 1 file changed, 5 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -118,10 +118,13 @@ static void wg_receive_handshake_packet(
-
- under_load = skb_queue_len(&wg->incoming_handshakes) >=
- MAX_QUEUED_INCOMING_HANDSHAKES / 8;
-- if (under_load)
-+ if (under_load) {
- last_under_load = ktime_get_coarse_boottime_ns();
-- else if (last_under_load)
-+ } else if (last_under_load) {
- under_load = !wg_birthdate_has_expired(last_under_load, 1);
-+ if (!under_load)
-+ last_under_load = 0;
-+ }
- mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb,
- under_load);
- if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) ||
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Fri, 14 Feb 2020 23:57:23 +0100
+Subject: [PATCH] wireguard: socket: remove extra call to synchronize_net
+
+commit 1fbc33b0a7feb6ca72bf7dc8a05d81485ee8ee2e upstream.
+
+synchronize_net() is a wrapper around synchronize_rcu(), so there's no
+point in having synchronize_net and synchronize_rcu back to back,
+despite the documentation comment suggesting maybe it's somewhat useful,
+"Wait for packets currently being received to be done." This commit
+removes the extra call.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/socket.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device *
+ wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
+ mutex_unlock(&wg->socket_update_lock);
+ synchronize_rcu();
+- synchronize_net();
+ sock_free(old4);
+ sock_free(old6);
+ }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: YueHaibing <yuehaibing@huawei.com>
+Date: Wed, 18 Mar 2020 18:30:43 -0600
+Subject: [PATCH] wireguard: selftests: remove duplicated include <sys/types.h>
+
+commit 166391159c5deb84795d2ff46e95f276177fa5fb upstream.
+
+This commit removes a duplicated include.
+
+Signed-off-by: YueHaibing <yuehaibing@huawei.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/qemu/init.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/tools/testing/selftests/wireguard/qemu/init.c
++++ b/tools/testing/selftests/wireguard/qemu/init.c
+@@ -13,7 +13,6 @@
+ #include <fcntl.h>
+ #include <sys/wait.h>
+ #include <sys/mount.h>
+-#include <sys/types.h>
+ #include <sys/stat.h>
+ #include <sys/types.h>
+ #include <sys/io.h>
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Fri, 14 Feb 2020 23:57:22 +0100
-Subject: [PATCH] wireguard: send: account for mtu=0 devices
-
-commit 175f1ca9a9ed8689d2028da1a7c624bb4fb4ff7e upstream.
-
-It turns out there's an easy way to get packets queued up while still
-having an MTU of zero, and that's via persistent keep alive. This commit
-makes sure that in whatever condition, we don't wind up dividing by
-zero. Note that an MTU of zero for a wireguard interface is something
-quasi-valid, so I don't think the correct fix is to limit it via
-min_mtu. This can be reproduced easily with:
-
-ip link add wg0 type wireguard
-ip link add wg1 type wireguard
-ip link set wg0 up mtu 0
-ip link set wg1 up
-wg set wg0 private-key <(wg genkey)
-wg set wg1 listen-port 1 private-key <(wg genkey) peer $(wg show wg0 public-key)
-wg set wg0 peer $(wg show wg1 public-key) persistent-keepalive 1 endpoint 127.0.0.1:1
-
-However, while min_mtu=0 seems fine, it makes sense to restrict the
-max_mtu. This commit also restricts the maximum MTU to the greatest
-number for which rounding up to the padding multiple won't overflow a
-signed integer. Packets this large were always rejected anyway
-eventually, due to checks deeper in, but it seems more sound not to even
-let the administrator configure something that won't work anyway.
-
-We use this opportunity to clean up this function a bit so that it's
-clear which paths we're expecting.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Cc: Eric Dumazet <eric.dumazet@gmail.com>
-Reviewed-by: Eric Dumazet <edumazet@google.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 7 ++++---
- drivers/net/wireguard/send.c | 16 +++++++++++-----
- 2 files changed, 15 insertions(+), 8 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -258,6 +258,8 @@ static void wg_setup(struct net_device *
- enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
- NETIF_F_SG | NETIF_F_GSO |
- NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA };
-+ const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) +
-+ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
-
- dev->netdev_ops = &netdev_ops;
- dev->hard_header_len = 0;
-@@ -271,9 +273,8 @@ static void wg_setup(struct net_device *
- dev->features |= WG_NETDEV_FEATURES;
- dev->hw_features |= WG_NETDEV_FEATURES;
- dev->hw_enc_features |= WG_NETDEV_FEATURES;
-- dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH -
-- sizeof(struct udphdr) -
-- max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
-+ dev->mtu = ETH_DATA_LEN - overhead;
-+ dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead;
-
- SET_NETDEV_DEVTYPE(dev, &device_type);
-
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_pee
-
- static unsigned int calculate_skb_padding(struct sk_buff *skb)
- {
-+ unsigned int padded_size, last_unit = skb->len;
-+
-+ if (unlikely(!PACKET_CB(skb)->mtu))
-+ return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit;
-+
- /* We do this modulo business with the MTU, just in case the networking
- * layer gives us a packet that's bigger than the MTU. In that case, we
- * wouldn't want the final subtraction to overflow in the case of the
-- * padded_size being clamped.
-+ * padded_size being clamped. Fortunately, that's very rarely the case,
-+ * so we optimize for that not happening.
- */
-- unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu;
-- unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE);
-+ if (unlikely(last_unit > PACKET_CB(skb)->mtu))
-+ last_unit %= PACKET_CB(skb)->mtu;
-
-- if (padded_size > PACKET_CB(skb)->mtu)
-- padded_size = PACKET_CB(skb)->mtu;
-+ padded_size = min(PACKET_CB(skb)->mtu,
-+ ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE));
- return padded_size - last_unit;
- }
-
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 18 Mar 2020 18:30:45 -0600
+Subject: [PATCH] wireguard: queueing: account for skb->protocol==0
+
+commit a5588604af448664e796daf3c1d5a4523c60667b upstream.
+
+We carry out checks to the effect of:
+
+ if (skb->protocol != wg_examine_packet_protocol(skb))
+ goto err;
+
+By having wg_skb_examine_untrusted_ip_hdr return 0 on failure, this
+means that the check above still passes in the case where skb->protocol
+is zero, which is possible to hit with AF_PACKET:
+
+ struct sockaddr_pkt saddr = { .spkt_device = "wg0" };
+ unsigned char buffer[5] = { 0 };
+ sendto(socket(AF_PACKET, SOCK_PACKET, /* skb->protocol = */ 0),
+ buffer, sizeof(buffer), 0, (const struct sockaddr *)&saddr, sizeof(saddr));
+
+Additional checks mean that this isn't actually a problem in the code
+base, but I could imagine it becoming a problem later if the function is
+used more liberally.
+
+I would prefer to fix this by having wg_examine_packet_protocol return a
+32-bit ~0 value on failure, which will never match any value of
+skb->protocol, which would simply change the generated code from a mov
+to a movzx. However, sparse complains, and adding __force casts doesn't
+seem like a good idea, so instead we just add a simple helper function
+to check for the zero return value. Since wg_examine_packet_protocol
+itself gets inlined, this winds up not adding an additional branch to
+the generated code, since the 0 return value already happens in a
+mergable branch.
+
+Reported-by: Fabian Freyer <fabianfreyer@radicallyopensecurity.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 2 +-
+ drivers/net/wireguard/queueing.h | 8 +++++++-
+ drivers/net/wireguard/receive.c | 4 ++--
+ 3 files changed, 10 insertions(+), 4 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -122,7 +122,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
+ u32 mtu;
+ int ret;
+
+- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) {
++ if (unlikely(!wg_check_packet_protocol(skb))) {
+ ret = -EPROTONOSUPPORT;
+ net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
+ goto err;
+--- a/drivers/net/wireguard/queueing.h
++++ b/drivers/net/wireguard/queueing.h
+@@ -66,7 +66,7 @@ struct packet_cb {
+ #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
+
+ /* Returns either the correct skb->protocol value, or 0 if invalid. */
+-static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb)
++static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb)
+ {
+ if (skb_network_header(skb) >= skb->head &&
+ (skb_network_header(skb) + sizeof(struct iphdr)) <=
+@@ -81,6 +81,12 @@ static inline __be16 wg_skb_examine_untr
+ return 0;
+ }
+
++static inline bool wg_check_packet_protocol(struct sk_buff *skb)
++{
++ __be16 real_protocol = wg_examine_packet_protocol(skb);
++ return real_protocol && skb->protocol == real_protocol;
++}
++
+ static inline void wg_reset_packet(struct sk_buff *skb)
+ {
+ skb_scrub_packet(skb, true);
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -56,7 +56,7 @@ static int prepare_skb_header(struct sk_
+ size_t data_offset, data_len, header_len;
+ struct udphdr *udp;
+
+- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol ||
++ if (unlikely(!wg_check_packet_protocol(skb) ||
+ skb_transport_header(skb) < skb->head ||
+ (skb_transport_header(skb) + sizeof(struct udphdr)) >
+ skb_tail_pointer(skb)))
+@@ -388,7 +388,7 @@ static void wg_packet_consume_data_done(
+ */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->csum_level = ~0; /* All levels */
+- skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb);
++ skb->protocol = wg_examine_packet_protocol(skb);
+ if (skb->protocol == htons(ETH_P_IP)) {
+ len = ntohs(ip_hdr(skb)->tot_len);
+ if (unlikely(len < sizeof(struct iphdr)))
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Fri, 14 Feb 2020 23:57:23 +0100
-Subject: [PATCH] wireguard: socket: remove extra call to synchronize_net
-
-commit 1fbc33b0a7feb6ca72bf7dc8a05d81485ee8ee2e upstream.
-
-synchronize_net() is a wrapper around synchronize_rcu(), so there's no
-point in having synchronize_net and synchronize_rcu back to back,
-despite the documentation comment suggesting maybe it's somewhat useful,
-"Wait for packets currently being received to be done." This commit
-removes the extra call.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
-Reviewed-by: Eric Dumazet <edumazet@google.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/socket.c | 1 -
- 1 file changed, 1 deletion(-)
-
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device *
- wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
- mutex_unlock(&wg->socket_update_lock);
- synchronize_rcu();
-- synchronize_net();
- sock_free(old4);
- sock_free(old6);
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 18 Mar 2020 18:30:46 -0600
+Subject: [PATCH] wireguard: receive: remove dead code from default packet type
+ case
+
+commit 2b8765c52db24c0fbcc81bac9b5e8390f2c7d3c8 upstream.
+
+The situation in which we wind up hitting the default case here
+indicates a major bug in earlier parsing code. It is not a usual thing
+that should ever happen, which means a "friendly" message for it doesn't
+make sense. Rather, replace this with a WARN_ON, just like we do earlier
+in the file for a similar situation, so that somebody sends us a bug
+report and we can fix it.
+
+Reported-by: Fabian Freyer <fabianfreyer@radicallyopensecurity.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -587,8 +587,7 @@ void wg_packet_receive(struct wg_device
+ wg_packet_consume_data(wg, skb);
+ break;
+ default:
+- net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n",
+- wg->dev->name, skb);
++ WARN(1, "Non-exhaustive parsing of packet header lead to unknown packet type!\n");
+ goto err;
+ }
+ return;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: YueHaibing <yuehaibing@huawei.com>
-Date: Wed, 18 Mar 2020 18:30:43 -0600
-Subject: [PATCH] wireguard: selftests: remove duplicated include <sys/types.h>
-
-commit 166391159c5deb84795d2ff46e95f276177fa5fb upstream.
-
-This commit removes a duplicated include.
-
-Signed-off-by: YueHaibing <yuehaibing@huawei.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/qemu/init.c | 1 -
- 1 file changed, 1 deletion(-)
-
---- a/tools/testing/selftests/wireguard/qemu/init.c
-+++ b/tools/testing/selftests/wireguard/qemu/init.c
-@@ -13,7 +13,6 @@
- #include <fcntl.h>
- #include <sys/wait.h>
- #include <sys/mount.h>
--#include <sys/types.h>
- #include <sys/stat.h>
- #include <sys/types.h>
- #include <sys/io.h>
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 18 Mar 2020 18:30:47 -0600
+Subject: [PATCH] wireguard: noise: error out precomputed DH during handshake
+ rather than config
+
+commit 11a7686aa99c7fe4b3f80f6dcccd54129817984d upstream.
+
+We precompute the static-static ECDH during configuration time, in order
+to save an expensive computation later when receiving network packets.
+However, not all ECDH computations yield a contributory result. Prior,
+we were just not letting those peers be added to the interface. However,
+this creates a strange inconsistency, since it was still possible to add
+other weird points, like a valid public key plus a low-order point, and,
+like points that result in zeros, a handshake would not complete. In
+order to make the behavior more uniform and less surprising, simply
+allow all peers to be added. Then, we'll error out later when doing the
+crypto if there's an issue. This also adds more separation between the
+crypto layer and the configuration layer.
+
+Discussed-with: Mathias Hall-Andersen <mathias@hall-andersen.dk>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/netlink.c | 8 +---
+ drivers/net/wireguard/noise.c | 55 ++++++++++++----------
+ drivers/net/wireguard/noise.h | 12 ++---
+ drivers/net/wireguard/peer.c | 7 +--
+ tools/testing/selftests/wireguard/netns.sh | 15 ++++--
+ 5 files changed, 49 insertions(+), 48 deletions(-)
+
+--- a/drivers/net/wireguard/netlink.c
++++ b/drivers/net/wireguard/netlink.c
+@@ -417,11 +417,7 @@ static int set_peer(struct wg_device *wg
+
+ peer = wg_peer_create(wg, public_key, preshared_key);
+ if (IS_ERR(peer)) {
+- /* Similar to the above, if the key is invalid, we skip
+- * it without fanfare, so that services don't need to
+- * worry about doing key validation themselves.
+- */
+- ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer);
++ ret = PTR_ERR(peer);
+ peer = NULL;
+ goto out;
+ }
+@@ -575,7 +571,7 @@ static int wg_set_device(struct sk_buff
+ private_key);
+ list_for_each_entry_safe(peer, temp, &wg->peer_list,
+ peer_list) {
+- BUG_ON(!wg_noise_precompute_static_static(peer));
++ wg_noise_precompute_static_static(peer);
+ wg_noise_expire_current_peer_keypairs(peer);
+ }
+ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -44,32 +44,23 @@ void __init wg_noise_init(void)
+ }
+
+ /* Must hold peer->handshake.static_identity->lock */
+-bool wg_noise_precompute_static_static(struct wg_peer *peer)
++void wg_noise_precompute_static_static(struct wg_peer *peer)
+ {
+- bool ret;
+-
+ down_write(&peer->handshake.lock);
+- if (peer->handshake.static_identity->has_identity) {
+- ret = curve25519(
+- peer->handshake.precomputed_static_static,
++ if (!peer->handshake.static_identity->has_identity ||
++ !curve25519(peer->handshake.precomputed_static_static,
+ peer->handshake.static_identity->static_private,
+- peer->handshake.remote_static);
+- } else {
+- u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 };
+-
+- ret = curve25519(empty, empty, peer->handshake.remote_static);
++ peer->handshake.remote_static))
+ memset(peer->handshake.precomputed_static_static, 0,
+ NOISE_PUBLIC_KEY_LEN);
+- }
+ up_write(&peer->handshake.lock);
+- return ret;
+ }
+
+-bool wg_noise_handshake_init(struct noise_handshake *handshake,
+- struct noise_static_identity *static_identity,
+- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
+- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
+- struct wg_peer *peer)
++void wg_noise_handshake_init(struct noise_handshake *handshake,
++ struct noise_static_identity *static_identity,
++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
++ struct wg_peer *peer)
+ {
+ memset(handshake, 0, sizeof(*handshake));
+ init_rwsem(&handshake->lock);
+@@ -81,7 +72,7 @@ bool wg_noise_handshake_init(struct nois
+ NOISE_SYMMETRIC_KEY_LEN);
+ handshake->static_identity = static_identity;
+ handshake->state = HANDSHAKE_ZEROED;
+- return wg_noise_precompute_static_static(peer);
++ wg_noise_precompute_static_static(peer);
+ }
+
+ static void handshake_zero(struct noise_handshake *handshake)
+@@ -403,6 +394,19 @@ static bool __must_check mix_dh(u8 chain
+ return true;
+ }
+
++static bool __must_check mix_precomputed_dh(u8 chaining_key[NOISE_HASH_LEN],
++ u8 key[NOISE_SYMMETRIC_KEY_LEN],
++ const u8 precomputed[NOISE_PUBLIC_KEY_LEN])
++{
++ static u8 zero_point[NOISE_PUBLIC_KEY_LEN];
++ if (unlikely(!crypto_memneq(precomputed, zero_point, NOISE_PUBLIC_KEY_LEN)))
++ return false;
++ kdf(chaining_key, key, NULL, precomputed, NOISE_HASH_LEN,
++ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
++ chaining_key);
++ return true;
++}
++
+ static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len)
+ {
+ struct blake2s_state blake;
+@@ -531,10 +535,9 @@ wg_noise_handshake_create_initiation(str
+ NOISE_PUBLIC_KEY_LEN, key, handshake->hash);
+
+ /* ss */
+- kdf(handshake->chaining_key, key, NULL,
+- handshake->precomputed_static_static, NOISE_HASH_LEN,
+- NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
+- handshake->chaining_key);
++ if (!mix_precomputed_dh(handshake->chaining_key, key,
++ handshake->precomputed_static_static))
++ goto out;
+
+ /* {t} */
+ tai64n_now(timestamp);
+@@ -595,9 +598,9 @@ wg_noise_handshake_consume_initiation(st
+ handshake = &peer->handshake;
+
+ /* ss */
+- kdf(chaining_key, key, NULL, handshake->precomputed_static_static,
+- NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
+- chaining_key);
++ if (!mix_precomputed_dh(chaining_key, key,
++ handshake->precomputed_static_static))
++ goto out;
+
+ /* {t} */
+ if (!message_decrypt(t, src->encrypted_timestamp,
+--- a/drivers/net/wireguard/noise.h
++++ b/drivers/net/wireguard/noise.h
+@@ -94,11 +94,11 @@ struct noise_handshake {
+ struct wg_device;
+
+ void wg_noise_init(void);
+-bool wg_noise_handshake_init(struct noise_handshake *handshake,
+- struct noise_static_identity *static_identity,
+- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
+- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
+- struct wg_peer *peer);
++void wg_noise_handshake_init(struct noise_handshake *handshake,
++ struct noise_static_identity *static_identity,
++ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
++ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
++ struct wg_peer *peer);
+ void wg_noise_handshake_clear(struct noise_handshake *handshake);
+ static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns)
+ {
+@@ -116,7 +116,7 @@ void wg_noise_expire_current_peer_keypai
+ void wg_noise_set_static_identity_private_key(
+ struct noise_static_identity *static_identity,
+ const u8 private_key[NOISE_PUBLIC_KEY_LEN]);
+-bool wg_noise_precompute_static_static(struct wg_peer *peer);
++void wg_noise_precompute_static_static(struct wg_peer *peer);
+
+ bool
+ wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
+--- a/drivers/net/wireguard/peer.c
++++ b/drivers/net/wireguard/peer.c
+@@ -34,11 +34,8 @@ struct wg_peer *wg_peer_create(struct wg
+ return ERR_PTR(ret);
+ peer->device = wg;
+
+- if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
+- public_key, preshared_key, peer)) {
+- ret = -EKEYREJECTED;
+- goto err_1;
+- }
++ wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
++ public_key, preshared_key, peer);
+ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+ goto err_1;
+ if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -527,11 +527,16 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0
+ n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
+ n0 wg set wg0 peer "$pub2" allowed-ips ::/0
+ n0 wg set wg0 peer "$pub2" remove
+-low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= )
+-n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer }
+-[[ -z $(n0 wg show wg0 peers) ]]
+-n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer }
+-[[ -z $(n0 wg show wg0 peers) ]]
++for low_order_point in AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38=; do
++ n0 wg set wg0 peer "$low_order_point" persistent-keepalive 1 endpoint 127.0.0.1:1111
++done
++[[ -n $(n0 wg show wg0 peers) ]]
++exec 4< <(n0 ncat -l -u -p 1111)
++ncat_pid=$!
++waitncatudp $netns0 $ncat_pid
++ip0 link set wg0 up
++! read -r -n 1 -t 2 <&4 || false
++kill $ncat_pid
+ ip0 link del wg0
+
+ declare -A objects
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 18 Mar 2020 18:30:45 -0600
-Subject: [PATCH] wireguard: queueing: account for skb->protocol==0
-
-commit a5588604af448664e796daf3c1d5a4523c60667b upstream.
-
-We carry out checks to the effect of:
-
- if (skb->protocol != wg_examine_packet_protocol(skb))
- goto err;
-
-By having wg_skb_examine_untrusted_ip_hdr return 0 on failure, this
-means that the check above still passes in the case where skb->protocol
-is zero, which is possible to hit with AF_PACKET:
-
- struct sockaddr_pkt saddr = { .spkt_device = "wg0" };
- unsigned char buffer[5] = { 0 };
- sendto(socket(AF_PACKET, SOCK_PACKET, /* skb->protocol = */ 0),
- buffer, sizeof(buffer), 0, (const struct sockaddr *)&saddr, sizeof(saddr));
-
-Additional checks mean that this isn't actually a problem in the code
-base, but I could imagine it becoming a problem later if the function is
-used more liberally.
-
-I would prefer to fix this by having wg_examine_packet_protocol return a
-32-bit ~0 value on failure, which will never match any value of
-skb->protocol, which would simply change the generated code from a mov
-to a movzx. However, sparse complains, and adding __force casts doesn't
-seem like a good idea, so instead we just add a simple helper function
-to check for the zero return value. Since wg_examine_packet_protocol
-itself gets inlined, this winds up not adding an additional branch to
-the generated code, since the 0 return value already happens in a
-mergable branch.
-
-Reported-by: Fabian Freyer <fabianfreyer@radicallyopensecurity.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 2 +-
- drivers/net/wireguard/queueing.h | 8 +++++++-
- drivers/net/wireguard/receive.c | 4 ++--
- 3 files changed, 10 insertions(+), 4 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -122,7 +122,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
- u32 mtu;
- int ret;
-
-- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol)) {
-+ if (unlikely(!wg_check_packet_protocol(skb))) {
- ret = -EPROTONOSUPPORT;
- net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name);
- goto err;
---- a/drivers/net/wireguard/queueing.h
-+++ b/drivers/net/wireguard/queueing.h
-@@ -66,7 +66,7 @@ struct packet_cb {
- #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
-
- /* Returns either the correct skb->protocol value, or 0 if invalid. */
--static inline __be16 wg_skb_examine_untrusted_ip_hdr(struct sk_buff *skb)
-+static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb)
- {
- if (skb_network_header(skb) >= skb->head &&
- (skb_network_header(skb) + sizeof(struct iphdr)) <=
-@@ -81,6 +81,12 @@ static inline __be16 wg_skb_examine_untr
- return 0;
- }
-
-+static inline bool wg_check_packet_protocol(struct sk_buff *skb)
-+{
-+ __be16 real_protocol = wg_examine_packet_protocol(skb);
-+ return real_protocol && skb->protocol == real_protocol;
-+}
-+
- static inline void wg_reset_packet(struct sk_buff *skb)
- {
- skb_scrub_packet(skb, true);
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -56,7 +56,7 @@ static int prepare_skb_header(struct sk_
- size_t data_offset, data_len, header_len;
- struct udphdr *udp;
-
-- if (unlikely(wg_skb_examine_untrusted_ip_hdr(skb) != skb->protocol ||
-+ if (unlikely(!wg_check_packet_protocol(skb) ||
- skb_transport_header(skb) < skb->head ||
- (skb_transport_header(skb) + sizeof(struct udphdr)) >
- skb_tail_pointer(skb)))
-@@ -388,7 +388,7 @@ static void wg_packet_consume_data_done(
- */
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->csum_level = ~0; /* All levels */
-- skb->protocol = wg_skb_examine_untrusted_ip_hdr(skb);
-+ skb->protocol = wg_examine_packet_protocol(skb);
- if (skb->protocol == htons(ETH_P_IP)) {
- len = ntohs(ip_hdr(skb)->tot_len);
- if (unlikely(len < sizeof(struct iphdr)))
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 18 Mar 2020 18:30:46 -0600
-Subject: [PATCH] wireguard: receive: remove dead code from default packet type
- case
-
-commit 2b8765c52db24c0fbcc81bac9b5e8390f2c7d3c8 upstream.
-
-The situation in which we wind up hitting the default case here
-indicates a major bug in earlier parsing code. It is not a usual thing
-that should ever happen, which means a "friendly" message for it doesn't
-make sense. Rather, replace this with a WARN_ON, just like we do earlier
-in the file for a similar situation, so that somebody sends us a bug
-report and we can fix it.
-
-Reported-by: Fabian Freyer <fabianfreyer@radicallyopensecurity.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 3 +--
- 1 file changed, 1 insertion(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -587,8 +587,7 @@ void wg_packet_receive(struct wg_device
- wg_packet_consume_data(wg, skb);
- break;
- default:
-- net_dbg_skb_ratelimited("%s: Invalid packet from %pISpfsc\n",
-- wg->dev->name, skb);
-+ WARN(1, "Non-exhaustive parsing of packet header lead to unknown packet type!\n");
- goto err;
- }
- return;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Sultan Alsawaf <sultan@kerneltoast.com>
+Date: Wed, 29 Apr 2020 14:59:20 -0600
+Subject: [PATCH] wireguard: send: remove errant newline from
+ packet_encrypt_worker
+
+commit d6833e42786e050e7522d6a91a9361e54085897d upstream.
+
+This commit removes a useless newline at the end of a scope, which
+doesn't add anything in the way of organization or readability.
+
+Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/send.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -304,7 +304,6 @@ void wg_packet_encrypt_worker(struct wor
+ }
+ wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
+ state);
+-
+ }
+ }
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 18 Mar 2020 18:30:47 -0600
-Subject: [PATCH] wireguard: noise: error out precomputed DH during handshake
- rather than config
-
-commit 11a7686aa99c7fe4b3f80f6dcccd54129817984d upstream.
-
-We precompute the static-static ECDH during configuration time, in order
-to save an expensive computation later when receiving network packets.
-However, not all ECDH computations yield a contributory result. Prior,
-we were just not letting those peers be added to the interface. However,
-this creates a strange inconsistency, since it was still possible to add
-other weird points, like a valid public key plus a low-order point, and,
-like points that result in zeros, a handshake would not complete. In
-order to make the behavior more uniform and less surprising, simply
-allow all peers to be added. Then, we'll error out later when doing the
-crypto if there's an issue. This also adds more separation between the
-crypto layer and the configuration layer.
-
-Discussed-with: Mathias Hall-Andersen <mathias@hall-andersen.dk>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/netlink.c | 8 +---
- drivers/net/wireguard/noise.c | 55 ++++++++++++----------
- drivers/net/wireguard/noise.h | 12 ++---
- drivers/net/wireguard/peer.c | 7 +--
- tools/testing/selftests/wireguard/netns.sh | 15 ++++--
- 5 files changed, 49 insertions(+), 48 deletions(-)
-
---- a/drivers/net/wireguard/netlink.c
-+++ b/drivers/net/wireguard/netlink.c
-@@ -417,11 +417,7 @@ static int set_peer(struct wg_device *wg
-
- peer = wg_peer_create(wg, public_key, preshared_key);
- if (IS_ERR(peer)) {
-- /* Similar to the above, if the key is invalid, we skip
-- * it without fanfare, so that services don't need to
-- * worry about doing key validation themselves.
-- */
-- ret = PTR_ERR(peer) == -EKEYREJECTED ? 0 : PTR_ERR(peer);
-+ ret = PTR_ERR(peer);
- peer = NULL;
- goto out;
- }
-@@ -575,7 +571,7 @@ static int wg_set_device(struct sk_buff
- private_key);
- list_for_each_entry_safe(peer, temp, &wg->peer_list,
- peer_list) {
-- BUG_ON(!wg_noise_precompute_static_static(peer));
-+ wg_noise_precompute_static_static(peer);
- wg_noise_expire_current_peer_keypairs(peer);
- }
- wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -44,32 +44,23 @@ void __init wg_noise_init(void)
- }
-
- /* Must hold peer->handshake.static_identity->lock */
--bool wg_noise_precompute_static_static(struct wg_peer *peer)
-+void wg_noise_precompute_static_static(struct wg_peer *peer)
- {
-- bool ret;
--
- down_write(&peer->handshake.lock);
-- if (peer->handshake.static_identity->has_identity) {
-- ret = curve25519(
-- peer->handshake.precomputed_static_static,
-+ if (!peer->handshake.static_identity->has_identity ||
-+ !curve25519(peer->handshake.precomputed_static_static,
- peer->handshake.static_identity->static_private,
-- peer->handshake.remote_static);
-- } else {
-- u8 empty[NOISE_PUBLIC_KEY_LEN] = { 0 };
--
-- ret = curve25519(empty, empty, peer->handshake.remote_static);
-+ peer->handshake.remote_static))
- memset(peer->handshake.precomputed_static_static, 0,
- NOISE_PUBLIC_KEY_LEN);
-- }
- up_write(&peer->handshake.lock);
-- return ret;
- }
-
--bool wg_noise_handshake_init(struct noise_handshake *handshake,
-- struct noise_static_identity *static_identity,
-- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-- struct wg_peer *peer)
-+void wg_noise_handshake_init(struct noise_handshake *handshake,
-+ struct noise_static_identity *static_identity,
-+ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-+ struct wg_peer *peer)
- {
- memset(handshake, 0, sizeof(*handshake));
- init_rwsem(&handshake->lock);
-@@ -81,7 +72,7 @@ bool wg_noise_handshake_init(struct nois
- NOISE_SYMMETRIC_KEY_LEN);
- handshake->static_identity = static_identity;
- handshake->state = HANDSHAKE_ZEROED;
-- return wg_noise_precompute_static_static(peer);
-+ wg_noise_precompute_static_static(peer);
- }
-
- static void handshake_zero(struct noise_handshake *handshake)
-@@ -403,6 +394,19 @@ static bool __must_check mix_dh(u8 chain
- return true;
- }
-
-+static bool __must_check mix_precomputed_dh(u8 chaining_key[NOISE_HASH_LEN],
-+ u8 key[NOISE_SYMMETRIC_KEY_LEN],
-+ const u8 precomputed[NOISE_PUBLIC_KEY_LEN])
-+{
-+ static u8 zero_point[NOISE_PUBLIC_KEY_LEN];
-+ if (unlikely(!crypto_memneq(precomputed, zero_point, NOISE_PUBLIC_KEY_LEN)))
-+ return false;
-+ kdf(chaining_key, key, NULL, precomputed, NOISE_HASH_LEN,
-+ NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
-+ chaining_key);
-+ return true;
-+}
-+
- static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len)
- {
- struct blake2s_state blake;
-@@ -531,10 +535,9 @@ wg_noise_handshake_create_initiation(str
- NOISE_PUBLIC_KEY_LEN, key, handshake->hash);
-
- /* ss */
-- kdf(handshake->chaining_key, key, NULL,
-- handshake->precomputed_static_static, NOISE_HASH_LEN,
-- NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
-- handshake->chaining_key);
-+ if (!mix_precomputed_dh(handshake->chaining_key, key,
-+ handshake->precomputed_static_static))
-+ goto out;
-
- /* {t} */
- tai64n_now(timestamp);
-@@ -595,9 +598,9 @@ wg_noise_handshake_consume_initiation(st
- handshake = &peer->handshake;
-
- /* ss */
-- kdf(chaining_key, key, NULL, handshake->precomputed_static_static,
-- NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN,
-- chaining_key);
-+ if (!mix_precomputed_dh(chaining_key, key,
-+ handshake->precomputed_static_static))
-+ goto out;
-
- /* {t} */
- if (!message_decrypt(t, src->encrypted_timestamp,
---- a/drivers/net/wireguard/noise.h
-+++ b/drivers/net/wireguard/noise.h
-@@ -94,11 +94,11 @@ struct noise_handshake {
- struct wg_device;
-
- void wg_noise_init(void);
--bool wg_noise_handshake_init(struct noise_handshake *handshake,
-- struct noise_static_identity *static_identity,
-- const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-- const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-- struct wg_peer *peer);
-+void wg_noise_handshake_init(struct noise_handshake *handshake,
-+ struct noise_static_identity *static_identity,
-+ const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN],
-+ const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN],
-+ struct wg_peer *peer);
- void wg_noise_handshake_clear(struct noise_handshake *handshake);
- static inline void wg_noise_reset_last_sent_handshake(atomic64_t *handshake_ns)
- {
-@@ -116,7 +116,7 @@ void wg_noise_expire_current_peer_keypai
- void wg_noise_set_static_identity_private_key(
- struct noise_static_identity *static_identity,
- const u8 private_key[NOISE_PUBLIC_KEY_LEN]);
--bool wg_noise_precompute_static_static(struct wg_peer *peer);
-+void wg_noise_precompute_static_static(struct wg_peer *peer);
-
- bool
- wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst,
---- a/drivers/net/wireguard/peer.c
-+++ b/drivers/net/wireguard/peer.c
-@@ -34,11 +34,8 @@ struct wg_peer *wg_peer_create(struct wg
- return ERR_PTR(ret);
- peer->device = wg;
-
-- if (!wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
-- public_key, preshared_key, peer)) {
-- ret = -EKEYREJECTED;
-- goto err_1;
-- }
-+ wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
-+ public_key, preshared_key, peer);
- if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
- goto err_1;
- if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -527,11 +527,16 @@ n0 wg set wg0 peer "$pub2" allowed-ips 0
- n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75
- n0 wg set wg0 peer "$pub2" allowed-ips ::/0
- n0 wg set wg0 peer "$pub2" remove
--low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= )
--n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer }
--[[ -z $(n0 wg show wg0 peers) ]]
--n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer }
--[[ -z $(n0 wg show wg0 peers) ]]
-+for low_order_point in AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38=; do
-+ n0 wg set wg0 peer "$low_order_point" persistent-keepalive 1 endpoint 127.0.0.1:1111
-+done
-+[[ -n $(n0 wg show wg0 peers) ]]
-+exec 4< <(n0 ncat -l -u -p 1111)
-+ncat_pid=$!
-+waitncatudp $netns0 $ncat_pid
-+ip0 link set wg0 up
-+! read -r -n 1 -t 2 <&4 || false
-+kill $ncat_pid
- ip0 link del wg0
-
- declare -A objects
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 29 Apr 2020 14:59:21 -0600
+Subject: [PATCH] wireguard: queueing: cleanup ptr_ring in error path of
+ packet_queue_init
+
+commit 130c58606171326c81841a49cc913cd354113dd9 upstream.
+
+Prior, if the alloc_percpu of packet_percpu_multicore_worker_alloc
+failed, the previously allocated ptr_ring wouldn't be freed. This commit
+adds the missing call to ptr_ring_cleanup in the error case.
+
+Reported-by: Sultan Alsawaf <sultan@kerneltoast.com>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/queueing.c | 4 +++-
+ 1 file changed, 3 insertions(+), 1 deletion(-)
+
+--- a/drivers/net/wireguard/queueing.c
++++ b/drivers/net/wireguard/queueing.c
+@@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_qu
+ if (multicore) {
+ queue->worker = wg_packet_percpu_multicore_worker_alloc(
+ function, queue);
+- if (!queue->worker)
++ if (!queue->worker) {
++ ptr_ring_cleanup(&queue->ring, NULL);
+ return -ENOMEM;
++ }
+ } else {
+ INIT_WORK(&queue->work, function);
+ }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
+Date: Wed, 29 Apr 2020 14:59:22 -0600
+Subject: [PATCH] wireguard: receive: use tunnel helpers for decapsulating ECN
+ markings
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+commit eebabcb26ea1e3295704477c6cd4e772c96a9559 upstream.
+
+WireGuard currently only propagates ECN markings on tunnel decap according
+to the old RFC3168 specification. However, the spec has since been updated
+in RFC6040 to recommend slightly different decapsulation semantics. This
+was implemented in the kernel as a set of common helpers for ECN
+decapsulation, so let's just switch over WireGuard to using those, so it
+can benefit from this enhancement and any future tweaks. We do not drop
+packets with invalid ECN marking combinations, because WireGuard is
+frequently used to work around broken ISPs, which could be doing that.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
+Cc: Dave Taht <dave.taht@gmail.com>
+Cc: Rodney W. Grimes <ietf@gndrsh.dnsmgr.net>
+Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 6 ++----
+ 1 file changed, 2 insertions(+), 4 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -393,13 +393,11 @@ static void wg_packet_consume_data_done(
+ len = ntohs(ip_hdr(skb)->tot_len);
+ if (unlikely(len < sizeof(struct iphdr)))
+ goto dishonest_packet_size;
+- if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
+- IP_ECN_set_ce(ip_hdr(skb));
++ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ len = ntohs(ipv6_hdr(skb)->payload_len) +
+ sizeof(struct ipv6hdr);
+- if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
+- IP6_ECN_set_ce(skb, ipv6_hdr(skb));
++ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb)));
+ } else {
+ goto dishonest_packet_type;
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Sultan Alsawaf <sultan@kerneltoast.com>
-Date: Wed, 29 Apr 2020 14:59:20 -0600
-Subject: [PATCH] wireguard: send: remove errant newline from
- packet_encrypt_worker
-
-commit d6833e42786e050e7522d6a91a9361e54085897d upstream.
-
-This commit removes a useless newline at the end of a scope, which
-doesn't add anything in the way of organization or readability.
-
-Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/send.c | 1 -
- 1 file changed, 1 deletion(-)
-
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -304,7 +304,6 @@ void wg_packet_encrypt_worker(struct wor
- }
- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
- state);
--
- }
- }
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 29 Apr 2020 14:59:21 -0600
-Subject: [PATCH] wireguard: queueing: cleanup ptr_ring in error path of
- packet_queue_init
-
-commit 130c58606171326c81841a49cc913cd354113dd9 upstream.
-
-Prior, if the alloc_percpu of packet_percpu_multicore_worker_alloc
-failed, the previously allocated ptr_ring wouldn't be freed. This commit
-adds the missing call to ptr_ring_cleanup in the error case.
-
-Reported-by: Sultan Alsawaf <sultan@kerneltoast.com>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/queueing.c | 4 +++-
- 1 file changed, 3 insertions(+), 1 deletion(-)
-
---- a/drivers/net/wireguard/queueing.c
-+++ b/drivers/net/wireguard/queueing.c
-@@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_qu
- if (multicore) {
- queue->worker = wg_packet_percpu_multicore_worker_alloc(
- function, queue);
-- if (!queue->worker)
-+ if (!queue->worker) {
-+ ptr_ring_cleanup(&queue->ring, NULL);
- return -ENOMEM;
-+ }
- } else {
- INIT_WORK(&queue->work, function);
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 6 May 2020 15:33:02 -0600
+Subject: [PATCH] wireguard: selftests: use normal kernel stack size on ppc64
+
+commit a0fd7cc87a018df1a17f9d3f0bd994c1f22c6b34 upstream.
+
+While at some point it might have made sense to be running these tests
+on ppc64 with 4k stacks, the kernel hasn't actually used 4k stacks on
+64-bit powerpc in a long time, and more interesting things that we test
+don't really work when we deviate from the default (16k). So, we stop
+pushing our luck in this commit, and return to the default instead of
+the minimum.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
++++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+@@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y
+ CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
+ CONFIG_SECTION_MISMATCH_WARN_ONLY=y
+ CONFIG_FRAME_WARN=1280
++CONFIG_THREAD_SHIFT=14
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
-Date: Wed, 29 Apr 2020 14:59:22 -0600
-Subject: [PATCH] wireguard: receive: use tunnel helpers for decapsulating ECN
- markings
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-commit eebabcb26ea1e3295704477c6cd4e772c96a9559 upstream.
-
-WireGuard currently only propagates ECN markings on tunnel decap according
-to the old RFC3168 specification. However, the spec has since been updated
-in RFC6040 to recommend slightly different decapsulation semantics. This
-was implemented in the kernel as a set of common helpers for ECN
-decapsulation, so let's just switch over WireGuard to using those, so it
-can benefit from this enhancement and any future tweaks. We do not drop
-packets with invalid ECN marking combinations, because WireGuard is
-frequently used to work around broken ISPs, which could be doing that.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
-Cc: Dave Taht <dave.taht@gmail.com>
-Cc: Rodney W. Grimes <ietf@gndrsh.dnsmgr.net>
-Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 6 ++----
- 1 file changed, 2 insertions(+), 4 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -393,13 +393,11 @@ static void wg_packet_consume_data_done(
- len = ntohs(ip_hdr(skb)->tot_len);
- if (unlikely(len < sizeof(struct iphdr)))
- goto dishonest_packet_size;
-- if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-- IP_ECN_set_ce(ip_hdr(skb));
-+ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos);
- } else if (skb->protocol == htons(ETH_P_IPV6)) {
- len = ntohs(ipv6_hdr(skb)->payload_len) +
- sizeof(struct ipv6hdr);
-- if (INET_ECN_is_ce(PACKET_CB(skb)->ds))
-- IP6_ECN_set_ce(skb, ipv6_hdr(skb));
-+ INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb)));
- } else {
- goto dishonest_packet_type;
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 6 May 2020 15:33:03 -0600
+Subject: [PATCH] wireguard: socket: remove errant restriction on looping to
+ self
+
+commit b673e24aad36981f327a6570412ffa7754de8911 upstream.
+
+It's already possible to create two different interfaces and loop
+packets between them. This has always been possible with tunnels in the
+kernel, and isn't specific to wireguard. Therefore, the networking stack
+already needs to deal with that. At the very least, the packet winds up
+exceeding the MTU and is discarded at that point. So, since this is
+already something that happens, there's no need to forbid the not very
+exceptional case of routing a packet back to the same interface; this
+loop is no different than others, and we shouldn't special case it, but
+rather rely on generic handling of loops in general. This also makes it
+easier to do interesting things with wireguard such as onion routing.
+
+At the same time, we add a selftest for this, ensuring that both onion
+routing works and infinite routing loops do not crash the kernel. We
+also add a test case for wireguard interfaces nesting packets and
+sending traffic between each other, as well as the loop in this case
+too. We make sure to send some throughput-heavy traffic for this use
+case, to stress out any possible recursion issues with the locks around
+workqueues.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/socket.c | 12 -----
+ tools/testing/selftests/wireguard/netns.sh | 54 ++++++++++++++++++++--
+ 2 files changed, 51 insertions(+), 15 deletions(-)
+
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, s
+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
+ wg->dev->name, &endpoint->addr, ret);
+ goto err;
+- } else if (unlikely(rt->dst.dev == skb->dev)) {
+- ip_rt_put(rt);
+- ret = -ELOOP;
+- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
+- wg->dev->name, &endpoint->addr);
+- goto err;
+ }
+ if (cache)
+ dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
+@@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, s
+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
+ wg->dev->name, &endpoint->addr, ret);
+ goto err;
+- } else if (unlikely(dst->dev == skb->dev)) {
+- dst_release(dst);
+- ret = -ELOOP;
+- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
+- wg->dev->name, &endpoint->addr);
+- goto err;
+ }
+ if (cache)
+ dst_cache_set_ip6(cache, dst, &fl.saddr);
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -48,8 +48,11 @@ cleanup() {
+ exec 2>/dev/null
+ printf "$orig_message_cost" > /proc/sys/net/core/message_cost
+ ip0 link del dev wg0
++ ip0 link del dev wg1
+ ip1 link del dev wg0
++ ip1 link del dev wg1
+ ip2 link del dev wg0
++ ip2 link del dev wg1
+ local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
+ [[ -n $to_kill ]] && kill $to_kill
+ pp ip netns del $netns1
+@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2
+ key1="$(pp wg genkey)"
+ key2="$(pp wg genkey)"
+ key3="$(pp wg genkey)"
++key4="$(pp wg genkey)"
+ pub1="$(pp wg pubkey <<<"$key1")"
+ pub2="$(pp wg pubkey <<<"$key2")"
+ pub3="$(pp wg pubkey <<<"$key3")"
++pub4="$(pp wg pubkey <<<"$key4")"
+ psk="$(pp wg genpsk)"
+ [[ -n $key1 && -n $key2 && -n $psk ]]
+
+ configure_peers() {
+ ip1 addr add 192.168.241.1/24 dev wg0
+- ip1 addr add fd00::1/24 dev wg0
++ ip1 addr add fd00::1/112 dev wg0
+
+ ip2 addr add 192.168.241.2/24 dev wg0
+- ip2 addr add fd00::2/24 dev wg0
++ ip2 addr add fd00::2/112 dev wg0
+
+ n1 wg set wg0 \
+ private-key <(echo "$key1") \
+@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2
+ n1 wg set wg0 private-key <(echo "$key3")
+ n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
+ n1 ping -W 1 -c 1 192.168.241.2
++n2 wg set wg0 peer "$pub3" remove
+
+-ip1 link del wg0
++# Test that we can route wg through wg
++ip1 addr flush dev wg0
++ip2 addr flush dev wg0
++ip1 addr add fd00::5:1/112 dev wg0
++ip2 addr add fd00::5:2/112 dev wg0
++n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2
++n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998
++ip1 link add wg1 type wireguard
++ip2 link add wg1 type wireguard
++ip1 addr add 192.168.241.1/24 dev wg1
++ip1 addr add fd00::1/112 dev wg1
++ip2 addr add 192.168.241.2/24 dev wg1
++ip2 addr add fd00::2/112 dev wg1
++ip1 link set mtu 1340 up dev wg1
++ip2 link set mtu 1340 up dev wg1
++n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5
++n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5
++tests
++# Try to set up a routing loop between the two namespaces
++ip1 link set netns $netns0 dev wg1
++ip0 addr add 192.168.241.1/24 dev wg1
++ip0 link set up dev wg1
++n0 ping -W 1 -c 1 192.168.241.2
++n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
+ ip2 link del wg0
++ip2 link del wg1
++! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
++
++ip0 link del wg1
++ip1 link del wg0
+
+ # Test using NAT. We now change the topology to this:
+ # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐
+@@ -282,6 +316,20 @@ pp sleep 3
+ n2 ping -W 1 -c 1 192.168.241.1
+ n1 wg set wg0 peer "$pub2" persistent-keepalive 0
+
++# Test that onion routing works, even when it loops
++n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
++ip1 addr add 192.168.242.1/24 dev wg0
++ip2 link add wg1 type wireguard
++ip2 addr add 192.168.242.2/24 dev wg1
++n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32
++ip2 link set wg1 up
++n1 ping -W 1 -c 1 192.168.242.2
++ip2 link del wg1
++n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5
++! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel
++n1 wg set wg0 peer "$pub3" remove
++ip1 addr del 192.168.242.1/24 dev wg0
++
+ # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
+ ip1 -6 addr add fc00::9/96 dev vethc
+ ip1 -6 route add default via fc00::1
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 6 May 2020 15:33:02 -0600
-Subject: [PATCH] wireguard: selftests: use normal kernel stack size on ppc64
-
-commit a0fd7cc87a018df1a17f9d3f0bd994c1f22c6b34 upstream.
-
-While at some point it might have made sense to be running these tests
-on ppc64 with 4k stacks, the kernel hasn't actually used 4k stacks on
-64-bit powerpc in a long time, and more interesting things that we test
-don't really work when we deviate from the default (16k). So, we stop
-pushing our luck in this commit, and return to the default instead of
-the minimum.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config | 1 +
- 1 file changed, 1 insertion(+)
-
---- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
-+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
-@@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y
- CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
- CONFIG_SECTION_MISMATCH_WARN_ONLY=y
- CONFIG_FRAME_WARN=1280
-+CONFIG_THREAD_SHIFT=14
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 6 May 2020 15:33:04 -0600
+Subject: [PATCH] wireguard: send/receive: cond_resched() when processing
+ worker ringbuffers
+
+commit 4005f5c3c9d006157ba716594e0d70c88a235c5e upstream.
+
+Users with pathological hardware reported CPU stalls on CONFIG_
+PREEMPT_VOLUNTARY=y, because the ringbuffers would stay full, meaning
+these workers would never terminate. That turned out not to be okay on
+systems without forced preemption, which Sultan observed. This commit
+adds a cond_resched() to the bottom of each loop iteration, so that
+these workers don't hog the core. Note that we don't need this on the
+napi poll worker, since that terminates after its budget is expended.
+
+Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
+Reported-by: Wang Jian <larkwang@gmail.com>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 2 ++
+ drivers/net/wireguard/send.c | 4 ++++
+ 2 files changed, 6 insertions(+)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct wor
+ &PACKET_CB(skb)->keypair->receiving)) ?
+ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
+ wg_queue_enqueue_per_peer_napi(skb, state);
++ if (need_resched())
++ cond_resched();
+ }
+ }
+
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_str
+
+ wg_noise_keypair_put(keypair, false);
+ wg_peer_put(peer);
++ if (need_resched())
++ cond_resched();
+ }
+ }
+
+@@ -304,6 +306,8 @@ void wg_packet_encrypt_worker(struct wor
+ }
+ wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
+ state);
++ if (need_resched())
++ cond_resched();
+ }
+ }
+
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 6 May 2020 15:33:05 -0600
+Subject: [PATCH] wireguard: selftests: initalize ipv6 members to NULL to
+ squelch clang warning
+
+commit 4fed818ef54b08d4b29200e416cce65546ad5312 upstream.
+
+Without setting these to NULL, clang complains in certain
+configurations that have CONFIG_IPV6=n:
+
+In file included from drivers/net/wireguard/ratelimiter.c:223:
+drivers/net/wireguard/selftest/ratelimiter.c:173:34: error: variable 'skb6' is uninitialized when used here [-Werror,-Wuninitialized]
+ ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
+ ^~~~
+drivers/net/wireguard/selftest/ratelimiter.c:123:29: note: initialize the variable 'skb6' to silence this warning
+ struct sk_buff *skb4, *skb6;
+ ^
+ = NULL
+drivers/net/wireguard/selftest/ratelimiter.c:173:40: error: variable 'hdr6' is uninitialized when used here [-Werror,-Wuninitialized]
+ ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
+ ^~~~
+drivers/net/wireguard/selftest/ratelimiter.c:125:22: note: initialize the variable 'hdr6' to silence this warning
+ struct ipv6hdr *hdr6;
+ ^
+
+We silence this warning by setting the variables to NULL as the warning
+suggests.
+
+Reported-by: Arnd Bergmann <arnd@arndb.de>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/selftest/ratelimiter.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/selftest/ratelimiter.c
++++ b/drivers/net/wireguard/selftest/ratelimiter.c
+@@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void
+ enum { TRIALS_BEFORE_GIVING_UP = 5000 };
+ bool success = false;
+ int test = 0, trials;
+- struct sk_buff *skb4, *skb6;
++ struct sk_buff *skb4, *skb6 = NULL;
+ struct iphdr *hdr4;
+- struct ipv6hdr *hdr6;
++ struct ipv6hdr *hdr6 = NULL;
+
+ if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
+ return true;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 6 May 2020 15:33:03 -0600
-Subject: [PATCH] wireguard: socket: remove errant restriction on looping to
- self
-
-commit b673e24aad36981f327a6570412ffa7754de8911 upstream.
-
-It's already possible to create two different interfaces and loop
-packets between them. This has always been possible with tunnels in the
-kernel, and isn't specific to wireguard. Therefore, the networking stack
-already needs to deal with that. At the very least, the packet winds up
-exceeding the MTU and is discarded at that point. So, since this is
-already something that happens, there's no need to forbid the not very
-exceptional case of routing a packet back to the same interface; this
-loop is no different than others, and we shouldn't special case it, but
-rather rely on generic handling of loops in general. This also makes it
-easier to do interesting things with wireguard such as onion routing.
-
-At the same time, we add a selftest for this, ensuring that both onion
-routing works and infinite routing loops do not crash the kernel. We
-also add a test case for wireguard interfaces nesting packets and
-sending traffic between each other, as well as the loop in this case
-too. We make sure to send some throughput-heavy traffic for this use
-case, to stress out any possible recursion issues with the locks around
-workqueues.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/socket.c | 12 -----
- tools/testing/selftests/wireguard/netns.sh | 54 ++++++++++++++++++++--
- 2 files changed, 51 insertions(+), 15 deletions(-)
-
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, s
- net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
- wg->dev->name, &endpoint->addr, ret);
- goto err;
-- } else if (unlikely(rt->dst.dev == skb->dev)) {
-- ip_rt_put(rt);
-- ret = -ELOOP;
-- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-- wg->dev->name, &endpoint->addr);
-- goto err;
- }
- if (cache)
- dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
-@@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, s
- net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
- wg->dev->name, &endpoint->addr, ret);
- goto err;
-- } else if (unlikely(dst->dev == skb->dev)) {
-- dst_release(dst);
-- ret = -ELOOP;
-- net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n",
-- wg->dev->name, &endpoint->addr);
-- goto err;
- }
- if (cache)
- dst_cache_set_ip6(cache, dst, &fl.saddr);
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -48,8 +48,11 @@ cleanup() {
- exec 2>/dev/null
- printf "$orig_message_cost" > /proc/sys/net/core/message_cost
- ip0 link del dev wg0
-+ ip0 link del dev wg1
- ip1 link del dev wg0
-+ ip1 link del dev wg1
- ip2 link del dev wg0
-+ ip2 link del dev wg1
- local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)"
- [[ -n $to_kill ]] && kill $to_kill
- pp ip netns del $netns1
-@@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2
- key1="$(pp wg genkey)"
- key2="$(pp wg genkey)"
- key3="$(pp wg genkey)"
-+key4="$(pp wg genkey)"
- pub1="$(pp wg pubkey <<<"$key1")"
- pub2="$(pp wg pubkey <<<"$key2")"
- pub3="$(pp wg pubkey <<<"$key3")"
-+pub4="$(pp wg pubkey <<<"$key4")"
- psk="$(pp wg genpsk)"
- [[ -n $key1 && -n $key2 && -n $psk ]]
-
- configure_peers() {
- ip1 addr add 192.168.241.1/24 dev wg0
-- ip1 addr add fd00::1/24 dev wg0
-+ ip1 addr add fd00::1/112 dev wg0
-
- ip2 addr add 192.168.241.2/24 dev wg0
-- ip2 addr add fd00::2/24 dev wg0
-+ ip2 addr add fd00::2/112 dev wg0
-
- n1 wg set wg0 \
- private-key <(echo "$key1") \
-@@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2
- n1 wg set wg0 private-key <(echo "$key3")
- n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove
- n1 ping -W 1 -c 1 192.168.241.2
-+n2 wg set wg0 peer "$pub3" remove
-
--ip1 link del wg0
-+# Test that we can route wg through wg
-+ip1 addr flush dev wg0
-+ip2 addr flush dev wg0
-+ip1 addr add fd00::5:1/112 dev wg0
-+ip2 addr add fd00::5:2/112 dev wg0
-+n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2
-+n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998
-+ip1 link add wg1 type wireguard
-+ip2 link add wg1 type wireguard
-+ip1 addr add 192.168.241.1/24 dev wg1
-+ip1 addr add fd00::1/112 dev wg1
-+ip2 addr add 192.168.241.2/24 dev wg1
-+ip2 addr add fd00::2/112 dev wg1
-+ip1 link set mtu 1340 up dev wg1
-+ip2 link set mtu 1340 up dev wg1
-+n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5
-+n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5
-+tests
-+# Try to set up a routing loop between the two namespaces
-+ip1 link set netns $netns0 dev wg1
-+ip0 addr add 192.168.241.1/24 dev wg1
-+ip0 link set up dev wg1
-+n0 ping -W 1 -c 1 192.168.241.2
-+n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
- ip2 link del wg0
-+ip2 link del wg1
-+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
-+
-+ip0 link del wg1
-+ip1 link del wg0
-
- # Test using NAT. We now change the topology to this:
- # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐
-@@ -282,6 +316,20 @@ pp sleep 3
- n2 ping -W 1 -c 1 192.168.241.1
- n1 wg set wg0 peer "$pub2" persistent-keepalive 0
-
-+# Test that onion routing works, even when it loops
-+n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
-+ip1 addr add 192.168.242.1/24 dev wg0
-+ip2 link add wg1 type wireguard
-+ip2 addr add 192.168.242.2/24 dev wg1
-+n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32
-+ip2 link set wg1 up
-+n1 ping -W 1 -c 1 192.168.242.2
-+ip2 link del wg1
-+n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5
-+! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel
-+n1 wg set wg0 peer "$pub3" remove
-+ip1 addr del 192.168.242.1/24 dev wg0
-+
- # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs.
- ip1 -6 addr add fc00::9/96 dev vethc
- ip1 -6 route add default via fc00::1
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 6 May 2020 15:33:04 -0600
-Subject: [PATCH] wireguard: send/receive: cond_resched() when processing
- worker ringbuffers
-
-commit 4005f5c3c9d006157ba716594e0d70c88a235c5e upstream.
-
-Users with pathological hardware reported CPU stalls on CONFIG_
-PREEMPT_VOLUNTARY=y, because the ringbuffers would stay full, meaning
-these workers would never terminate. That turned out not to be okay on
-systems without forced preemption, which Sultan observed. This commit
-adds a cond_resched() to the bottom of each loop iteration, so that
-these workers don't hog the core. Note that we don't need this on the
-napi poll worker, since that terminates after its budget is expended.
-
-Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
-Reported-by: Wang Jian <larkwang@gmail.com>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 2 ++
- drivers/net/wireguard/send.c | 4 ++++
- 2 files changed, 6 insertions(+)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct wor
- &PACKET_CB(skb)->keypair->receiving)) ?
- PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
- wg_queue_enqueue_per_peer_napi(skb, state);
-+ if (need_resched())
-+ cond_resched();
- }
- }
-
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_str
-
- wg_noise_keypair_put(keypair, false);
- wg_peer_put(peer);
-+ if (need_resched())
-+ cond_resched();
- }
- }
-
-@@ -304,6 +306,8 @@ void wg_packet_encrypt_worker(struct wor
- }
- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
- state);
-+ if (need_resched())
-+ cond_resched();
- }
- }
-
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 6 May 2020 15:33:06 -0600
+Subject: [PATCH] wireguard: send/receive: use explicit unlikely branch instead
+ of implicit coalescing
+
+commit 243f2148937adc72bcaaa590d482d599c936efde upstream.
+
+It's very unlikely that send will become true. It's nearly always false
+between 0 and 120 seconds of a session, and in most cases becomes true
+only between 120 and 121 seconds before becoming false again. So,
+unlikely(send) is clearly the right option here.
+
+What happened before was that we had this complex boolean expression
+with multiple likely and unlikely clauses nested. Since this is
+evaluated left-to-right anyway, the whole thing got converted to
+unlikely. So, we can clean this up to better represent what's going on.
+
+The generated code is the same.
+
+Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 13 ++++++-------
+ drivers/net/wireguard/send.c | 15 ++++++---------
+ 2 files changed, 12 insertions(+), 16 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker(
+ static void keep_key_fresh(struct wg_peer *peer)
+ {
+ struct noise_keypair *keypair;
+- bool send = false;
++ bool send;
+
+ if (peer->sent_lastminute_handshake)
+ return;
+
+ rcu_read_lock_bh();
+ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
+- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
+- keypair->i_am_the_initiator &&
+- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
+- REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT)))
+- send = true;
++ send = keypair && READ_ONCE(keypair->sending.is_valid) &&
++ keypair->i_am_the_initiator &&
++ wg_birthdate_has_expired(keypair->sending.birthdate,
++ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT);
+ rcu_read_unlock_bh();
+
+- if (send) {
++ if (unlikely(send)) {
+ peer->sent_lastminute_handshake = true;
+ wg_packet_send_queued_handshake_initiation(peer, false);
+ }
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(str
+ static void keep_key_fresh(struct wg_peer *peer)
+ {
+ struct noise_keypair *keypair;
+- bool send = false;
++ bool send;
+
+ rcu_read_lock_bh();
+ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
+- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
+- (unlikely(atomic64_read(&keypair->sending.counter.counter) >
+- REKEY_AFTER_MESSAGES) ||
+- (keypair->i_am_the_initiator &&
+- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
+- REKEY_AFTER_TIME)))))
+- send = true;
++ send = keypair && READ_ONCE(keypair->sending.is_valid) &&
++ (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES ||
++ (keypair->i_am_the_initiator &&
++ wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME)));
+ rcu_read_unlock_bh();
+
+- if (send)
++ if (unlikely(send))
+ wg_packet_send_queued_handshake_initiation(peer, false);
+ }
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 6 May 2020 15:33:05 -0600
-Subject: [PATCH] wireguard: selftests: initalize ipv6 members to NULL to
- squelch clang warning
-
-commit 4fed818ef54b08d4b29200e416cce65546ad5312 upstream.
-
-Without setting these to NULL, clang complains in certain
-configurations that have CONFIG_IPV6=n:
-
-In file included from drivers/net/wireguard/ratelimiter.c:223:
-drivers/net/wireguard/selftest/ratelimiter.c:173:34: error: variable 'skb6' is uninitialized when used here [-Werror,-Wuninitialized]
- ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
- ^~~~
-drivers/net/wireguard/selftest/ratelimiter.c:123:29: note: initialize the variable 'skb6' to silence this warning
- struct sk_buff *skb4, *skb6;
- ^
- = NULL
-drivers/net/wireguard/selftest/ratelimiter.c:173:40: error: variable 'hdr6' is uninitialized when used here [-Werror,-Wuninitialized]
- ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count);
- ^~~~
-drivers/net/wireguard/selftest/ratelimiter.c:125:22: note: initialize the variable 'hdr6' to silence this warning
- struct ipv6hdr *hdr6;
- ^
-
-We silence this warning by setting the variables to NULL as the warning
-suggests.
-
-Reported-by: Arnd Bergmann <arnd@arndb.de>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/selftest/ratelimiter.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/selftest/ratelimiter.c
-+++ b/drivers/net/wireguard/selftest/ratelimiter.c
-@@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void
- enum { TRIALS_BEFORE_GIVING_UP = 5000 };
- bool success = false;
- int test = 0, trials;
-- struct sk_buff *skb4, *skb6;
-+ struct sk_buff *skb4, *skb6 = NULL;
- struct iphdr *hdr4;
-- struct ipv6hdr *hdr6;
-+ struct ipv6hdr *hdr6 = NULL;
-
- if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN))
- return true;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 19 May 2020 22:49:27 -0600
+Subject: [PATCH] wireguard: selftests: use newer iproute2 for gcc-10
+
+commit ee3c1aa3f34b7842c1557cfe5d8c3f7b8c692de8 upstream.
+
+gcc-10 switched to defaulting to -fno-common, which broke iproute2-5.4.
+This was fixed in iproute-5.6, so switch to that. Because we're after a
+stable testing surface, we generally don't like to bump these
+unnecessarily, but in this case, being able to actually build is a basic
+necessity.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/qemu/Makefile | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/tools/testing/selftests/wireguard/qemu/Makefile
++++ b/tools/testing/selftests/wireguard/qemu/Makefile
+@@ -44,7 +44,7 @@ endef
+ $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
+ $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
+ $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
+-$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
++$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692))
+ $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
+ $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
+ $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 19 May 2020 22:49:28 -0600
+Subject: [PATCH] wireguard: noise: read preshared key while taking lock
+
+commit bc67d371256f5c47d824e2eec51e46c8d62d022e upstream.
+
+Prior we read the preshared key after dropping the handshake lock, which
+isn't an actual crypto issue if it races, but it's still not quite
+correct. So copy that part of the state into a temporary like we do with
+the rest of the handshake state variables. Then we can release the lock,
+operate on the temporary, and zero it out at the end of the function. In
+performance tests, the impact of this was entirely unnoticable, probably
+because those bytes are coming from the same cacheline as other things
+that are being copied out in the same manner.
+
+Reported-by: Matt Dunwoodie <ncon@noconroy.net>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/noise.c | 6 +++++-
+ 1 file changed, 5 insertions(+), 1 deletion(-)
+
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -715,6 +715,7 @@ wg_noise_handshake_consume_response(stru
+ u8 e[NOISE_PUBLIC_KEY_LEN];
+ u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
+ u8 static_private[NOISE_PUBLIC_KEY_LEN];
++ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
+
+ down_read(&wg->static_identity.lock);
+
+@@ -733,6 +734,8 @@ wg_noise_handshake_consume_response(stru
+ memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
+ memcpy(ephemeral_private, handshake->ephemeral_private,
+ NOISE_PUBLIC_KEY_LEN);
++ memcpy(preshared_key, handshake->preshared_key,
++ NOISE_SYMMETRIC_KEY_LEN);
+ up_read(&handshake->lock);
+
+ if (state != HANDSHAKE_CREATED_INITIATION)
+@@ -750,7 +753,7 @@ wg_noise_handshake_consume_response(stru
+ goto fail;
+
+ /* psk */
+- mix_psk(chaining_key, hash, key, handshake->preshared_key);
++ mix_psk(chaining_key, hash, key, preshared_key);
+
+ /* {} */
+ if (!message_decrypt(NULL, src->encrypted_nothing,
+@@ -783,6 +786,7 @@ out:
+ memzero_explicit(chaining_key, NOISE_HASH_LEN);
+ memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
+ memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
++ memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN);
+ up_read(&wg->static_identity.lock);
+ return ret_peer;
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 6 May 2020 15:33:06 -0600
-Subject: [PATCH] wireguard: send/receive: use explicit unlikely branch instead
- of implicit coalescing
-
-commit 243f2148937adc72bcaaa590d482d599c936efde upstream.
-
-It's very unlikely that send will become true. It's nearly always false
-between 0 and 120 seconds of a session, and in most cases becomes true
-only between 120 and 121 seconds before becoming false again. So,
-unlikely(send) is clearly the right option here.
-
-What happened before was that we had this complex boolean expression
-with multiple likely and unlikely clauses nested. Since this is
-evaluated left-to-right anyway, the whole thing got converted to
-unlikely. So, we can clean this up to better represent what's going on.
-
-The generated code is the same.
-
-Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 13 ++++++-------
- drivers/net/wireguard/send.c | 15 ++++++---------
- 2 files changed, 12 insertions(+), 16 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker(
- static void keep_key_fresh(struct wg_peer *peer)
- {
- struct noise_keypair *keypair;
-- bool send = false;
-+ bool send;
-
- if (peer->sent_lastminute_handshake)
- return;
-
- rcu_read_lock_bh();
- keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-- keypair->i_am_the_initiator &&
-- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-- REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT)))
-- send = true;
-+ send = keypair && READ_ONCE(keypair->sending.is_valid) &&
-+ keypair->i_am_the_initiator &&
-+ wg_birthdate_has_expired(keypair->sending.birthdate,
-+ REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT);
- rcu_read_unlock_bh();
-
-- if (send) {
-+ if (unlikely(send)) {
- peer->sent_lastminute_handshake = true;
- wg_packet_send_queued_handshake_initiation(peer, false);
- }
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(str
- static void keep_key_fresh(struct wg_peer *peer)
- {
- struct noise_keypair *keypair;
-- bool send = false;
-+ bool send;
-
- rcu_read_lock_bh();
- keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
-- if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) &&
-- (unlikely(atomic64_read(&keypair->sending.counter.counter) >
-- REKEY_AFTER_MESSAGES) ||
-- (keypair->i_am_the_initiator &&
-- unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
-- REKEY_AFTER_TIME)))))
-- send = true;
-+ send = keypair && READ_ONCE(keypair->sending.is_valid) &&
-+ (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES ||
-+ (keypair->i_am_the_initiator &&
-+ wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME)));
- rcu_read_unlock_bh();
-
-- if (send)
-+ if (unlikely(send))
- wg_packet_send_queued_handshake_initiation(peer, false);
- }
-
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 19 May 2020 22:49:29 -0600
+Subject: [PATCH] wireguard: queueing: preserve flow hash across packet
+ scrubbing
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+commit c78a0b4a78839d572d8a80f6a62221c0d7843135 upstream.
+
+It's important that we clear most header fields during encapsulation and
+decapsulation, because the packet is substantially changed, and we don't
+want any info leak or logic bug due to an accidental correlation. But,
+for encapsulation, it's wrong to clear skb->hash, since it's used by
+fq_codel and flow dissection in general. Without it, classification does
+not proceed as usual. This change might make it easier to estimate the
+number of innerflows by examining clustering of out of order packets,
+but this shouldn't open up anything that can't already be inferred
+otherwise (e.g. syn packet size inference), and fq_codel can be disabled
+anyway.
+
+Furthermore, it might be the case that the hash isn't used or queried at
+all until after wireguard transmits the encrypted UDP packet, which
+means skb->hash might still be zero at this point, and thus no hash
+taken over the inner packet data. In order to address this situation, we
+force a calculation of skb->hash before encrypting packet data.
+
+Of course this means that fq_codel might transmit packets slightly more
+out of order than usual. Toke did some testing on beefy machines with
+high quantities of parallel flows and found that increasing the
+reply-attack counter to 8192 takes care of the most pathological cases
+pretty well.
+
+Reported-by: Dave Taht <dave.taht@gmail.com>
+Reviewed-and-tested-by: Toke Høiland-Jørgensen <toke@toke.dk>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/messages.h | 2 +-
+ drivers/net/wireguard/queueing.h | 10 +++++++++-
+ drivers/net/wireguard/receive.c | 2 +-
+ drivers/net/wireguard/send.c | 7 ++++++-
+ 4 files changed, 17 insertions(+), 4 deletions(-)
+
+--- a/drivers/net/wireguard/messages.h
++++ b/drivers/net/wireguard/messages.h
+@@ -32,7 +32,7 @@ enum cookie_values {
+ };
+
+ enum counter_values {
+- COUNTER_BITS_TOTAL = 2048,
++ COUNTER_BITS_TOTAL = 8192,
+ COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
+ COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
+ };
+--- a/drivers/net/wireguard/queueing.h
++++ b/drivers/net/wireguard/queueing.h
+@@ -87,12 +87,20 @@ static inline bool wg_check_packet_proto
+ return real_protocol && skb->protocol == real_protocol;
+ }
+
+-static inline void wg_reset_packet(struct sk_buff *skb)
++static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating)
+ {
++ u8 l4_hash = skb->l4_hash;
++ u8 sw_hash = skb->sw_hash;
++ u32 hash = skb->hash;
+ skb_scrub_packet(skb, true);
+ memset(&skb->headers_start, 0,
+ offsetof(struct sk_buff, headers_end) -
+ offsetof(struct sk_buff, headers_start));
++ if (encapsulating) {
++ skb->l4_hash = l4_hash;
++ skb->sw_hash = sw_hash;
++ skb->hash = hash;
++ }
+ skb->queue_mapping = 0;
+ skb->nohdr = 0;
+ skb->peeked = 0;
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -484,7 +484,7 @@ int wg_packet_rx_poll(struct napi_struct
+ if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
+ goto next;
+
+- wg_reset_packet(skb);
++ wg_reset_packet(skb, false);
+ wg_packet_consume_data_done(peer, skb, &endpoint);
+ free = false;
+
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -167,6 +167,11 @@ static bool encrypt_packet(struct sk_buf
+ struct sk_buff *trailer;
+ int num_frags;
+
++ /* Force hash calculation before encryption so that flow analysis is
++ * consistent over the inner packet.
++ */
++ skb_get_hash(skb);
++
+ /* Calculate lengths. */
+ padding_len = calculate_skb_padding(skb);
+ trailer_len = padding_len + noise_encrypted_len(0);
+@@ -295,7 +300,7 @@ void wg_packet_encrypt_worker(struct wor
+ skb_list_walk_safe(first, skb, next) {
+ if (likely(encrypt_packet(skb,
+ PACKET_CB(first)->keypair))) {
+- wg_reset_packet(skb);
++ wg_reset_packet(skb, true);
+ } else {
+ state = PACKET_STATE_DEAD;
+ break;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 19 May 2020 22:49:27 -0600
-Subject: [PATCH] wireguard: selftests: use newer iproute2 for gcc-10
-
-commit ee3c1aa3f34b7842c1557cfe5d8c3f7b8c692de8 upstream.
-
-gcc-10 switched to defaulting to -fno-common, which broke iproute2-5.4.
-This was fixed in iproute-5.6, so switch to that. Because we're after a
-stable testing surface, we generally don't like to bump these
-unnecessarily, but in this case, being able to actually build is a basic
-necessity.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/qemu/Makefile | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
---- a/tools/testing/selftests/wireguard/qemu/Makefile
-+++ b/tools/testing/selftests/wireguard/qemu/Makefile
-@@ -44,7 +44,7 @@ endef
- $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3))
- $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
- $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
--$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae))
-+$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692))
- $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
- $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
- $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 19 May 2020 22:49:28 -0600
-Subject: [PATCH] wireguard: noise: read preshared key while taking lock
-
-commit bc67d371256f5c47d824e2eec51e46c8d62d022e upstream.
-
-Prior we read the preshared key after dropping the handshake lock, which
-isn't an actual crypto issue if it races, but it's still not quite
-correct. So copy that part of the state into a temporary like we do with
-the rest of the handshake state variables. Then we can release the lock,
-operate on the temporary, and zero it out at the end of the function. In
-performance tests, the impact of this was entirely unnoticable, probably
-because those bytes are coming from the same cacheline as other things
-that are being copied out in the same manner.
-
-Reported-by: Matt Dunwoodie <ncon@noconroy.net>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/noise.c | 6 +++++-
- 1 file changed, 5 insertions(+), 1 deletion(-)
-
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -715,6 +715,7 @@ wg_noise_handshake_consume_response(stru
- u8 e[NOISE_PUBLIC_KEY_LEN];
- u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN];
- u8 static_private[NOISE_PUBLIC_KEY_LEN];
-+ u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN];
-
- down_read(&wg->static_identity.lock);
-
-@@ -733,6 +734,8 @@ wg_noise_handshake_consume_response(stru
- memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN);
- memcpy(ephemeral_private, handshake->ephemeral_private,
- NOISE_PUBLIC_KEY_LEN);
-+ memcpy(preshared_key, handshake->preshared_key,
-+ NOISE_SYMMETRIC_KEY_LEN);
- up_read(&handshake->lock);
-
- if (state != HANDSHAKE_CREATED_INITIATION)
-@@ -750,7 +753,7 @@ wg_noise_handshake_consume_response(stru
- goto fail;
-
- /* psk */
-- mix_psk(chaining_key, hash, key, handshake->preshared_key);
-+ mix_psk(chaining_key, hash, key, preshared_key);
-
- /* {} */
- if (!message_decrypt(NULL, src->encrypted_nothing,
-@@ -783,6 +786,7 @@ out:
- memzero_explicit(chaining_key, NOISE_HASH_LEN);
- memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN);
- memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN);
-+ memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN);
- up_read(&wg->static_identity.lock);
- return ret_peer;
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 19 May 2020 22:49:30 -0600
+Subject: [PATCH] wireguard: noise: separate receive counter from send counter
+
+commit a9e90d9931f3a474f04bab782ccd9d77904941e9 upstream.
+
+In "wireguard: queueing: preserve flow hash across packet scrubbing", we
+were required to slightly increase the size of the receive replay
+counter to something still fairly small, but an increase nonetheless.
+It turns out that we can recoup some of the additional memory overhead
+by splitting up the prior union type into two distinct types. Before, we
+used the same "noise_counter" union for both sending and receiving, with
+sending just using a simple atomic64_t, while receiving used the full
+replay counter checker. This meant that most of the memory being
+allocated for the sending counter was being wasted. Since the old
+"noise_counter" type increased in size in the prior commit, now is a
+good time to split up that union type into a distinct "noise_replay_
+counter" for receiving and a boring atomic64_t for sending, each using
+neither more nor less memory than required.
+
+Also, since sometimes the replay counter is accessed without
+necessitating additional accesses to the bitmap, we can reduce cache
+misses by hoisting the always-necessary lock above the bitmap in the
+struct layout. We also change a "noise_replay_counter" stack allocation
+to kmalloc in a -DDEBUG selftest so that KASAN doesn't trigger a stack
+frame warning.
+
+All and all, removing a bit of abstraction in this commit makes the code
+simpler and smaller, in addition to the motivating memory usage
+recuperation. For example, passing around raw "noise_symmetric_key"
+structs is something that really only makes sense within noise.c, in the
+one place where the sending and receiving keys can safely be thought of
+as the same type of object; subsequent to that, it's important that we
+uniformly access these through keypair->{sending,receiving}, where their
+distinct roles are always made explicit. So this patch allows us to draw
+that distinction clearly as well.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/noise.c | 16 +++------
+ drivers/net/wireguard/noise.h | 14 ++++----
+ drivers/net/wireguard/receive.c | 42 ++++++++++++------------
+ drivers/net/wireguard/selftest/counter.c | 17 +++++++---
+ drivers/net/wireguard/send.c | 12 +++----
+ 5 files changed, 48 insertions(+), 53 deletions(-)
+
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -104,6 +104,7 @@ static struct noise_keypair *keypair_cre
+
+ if (unlikely(!keypair))
+ return NULL;
++ spin_lock_init(&keypair->receiving_counter.lock);
+ keypair->internal_id = atomic64_inc_return(&keypair_counter);
+ keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
+ keypair->entry.peer = peer;
+@@ -358,25 +359,16 @@ out:
+ memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
+ }
+
+-static void symmetric_key_init(struct noise_symmetric_key *key)
+-{
+- spin_lock_init(&key->counter.receive.lock);
+- atomic64_set(&key->counter.counter, 0);
+- memset(key->counter.receive.backtrack, 0,
+- sizeof(key->counter.receive.backtrack));
+- key->birthdate = ktime_get_coarse_boottime_ns();
+- key->is_valid = true;
+-}
+-
+ static void derive_keys(struct noise_symmetric_key *first_dst,
+ struct noise_symmetric_key *second_dst,
+ const u8 chaining_key[NOISE_HASH_LEN])
+ {
++ u64 birthdate = ktime_get_coarse_boottime_ns();
+ kdf(first_dst->key, second_dst->key, NULL, NULL,
+ NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
+ chaining_key);
+- symmetric_key_init(first_dst);
+- symmetric_key_init(second_dst);
++ first_dst->birthdate = second_dst->birthdate = birthdate;
++ first_dst->is_valid = second_dst->is_valid = true;
+ }
+
+ static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
+--- a/drivers/net/wireguard/noise.h
++++ b/drivers/net/wireguard/noise.h
+@@ -15,18 +15,14 @@
+ #include <linux/mutex.h>
+ #include <linux/kref.h>
+
+-union noise_counter {
+- struct {
+- u64 counter;
+- unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
+- spinlock_t lock;
+- } receive;
+- atomic64_t counter;
++struct noise_replay_counter {
++ u64 counter;
++ spinlock_t lock;
++ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
+ };
+
+ struct noise_symmetric_key {
+ u8 key[NOISE_SYMMETRIC_KEY_LEN];
+- union noise_counter counter;
+ u64 birthdate;
+ bool is_valid;
+ };
+@@ -34,7 +30,9 @@ struct noise_symmetric_key {
+ struct noise_keypair {
+ struct index_hashtable_entry entry;
+ struct noise_symmetric_key sending;
++ atomic64_t sending_counter;
+ struct noise_symmetric_key receiving;
++ struct noise_replay_counter receiving_counter;
+ __le32 remote_index;
+ bool i_am_the_initiator;
+ struct kref refcount;
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -245,20 +245,20 @@ static void keep_key_fresh(struct wg_pee
+ }
+ }
+
+-static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
++static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
+ {
+ struct scatterlist sg[MAX_SKB_FRAGS + 8];
+ struct sk_buff *trailer;
+ unsigned int offset;
+ int num_frags;
+
+- if (unlikely(!key))
++ if (unlikely(!keypair))
+ return false;
+
+- if (unlikely(!READ_ONCE(key->is_valid) ||
+- wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
+- key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
+- WRITE_ONCE(key->is_valid, false);
++ if (unlikely(!READ_ONCE(keypair->receiving.is_valid) ||
++ wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) ||
++ keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) {
++ WRITE_ONCE(keypair->receiving.is_valid, false);
+ return false;
+ }
+
+@@ -283,7 +283,7 @@ static bool decrypt_packet(struct sk_buf
+
+ if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
+ PACKET_CB(skb)->nonce,
+- key->key))
++ keypair->receiving.key))
+ return false;
+
+ /* Another ugly situation of pushing and pulling the header so as to
+@@ -298,41 +298,41 @@ static bool decrypt_packet(struct sk_buf
+ }
+
+ /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
+-static bool counter_validate(union noise_counter *counter, u64 their_counter)
++static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter)
+ {
+ unsigned long index, index_current, top, i;
+ bool ret = false;
+
+- spin_lock_bh(&counter->receive.lock);
++ spin_lock_bh(&counter->lock);
+
+- if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
++ if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 ||
+ their_counter >= REJECT_AFTER_MESSAGES))
+ goto out;
+
+ ++their_counter;
+
+ if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
+- counter->receive.counter))
++ counter->counter))
+ goto out;
+
+ index = their_counter >> ilog2(BITS_PER_LONG);
+
+- if (likely(their_counter > counter->receive.counter)) {
+- index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
++ if (likely(their_counter > counter->counter)) {
++ index_current = counter->counter >> ilog2(BITS_PER_LONG);
+ top = min_t(unsigned long, index - index_current,
+ COUNTER_BITS_TOTAL / BITS_PER_LONG);
+ for (i = 1; i <= top; ++i)
+- counter->receive.backtrack[(i + index_current) &
++ counter->backtrack[(i + index_current) &
+ ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
+- counter->receive.counter = their_counter;
++ counter->counter = their_counter;
+ }
+
+ index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
+ ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
+- &counter->receive.backtrack[index]);
++ &counter->backtrack[index]);
+
+ out:
+- spin_unlock_bh(&counter->receive.lock);
++ spin_unlock_bh(&counter->lock);
+ return ret;
+ }
+
+@@ -472,12 +472,12 @@ int wg_packet_rx_poll(struct napi_struct
+ if (unlikely(state != PACKET_STATE_CRYPTED))
+ goto next;
+
+- if (unlikely(!counter_validate(&keypair->receiving.counter,
++ if (unlikely(!counter_validate(&keypair->receiving_counter,
+ PACKET_CB(skb)->nonce))) {
+ net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
+ peer->device->dev->name,
+ PACKET_CB(skb)->nonce,
+- keypair->receiving.counter.receive.counter);
++ keypair->receiving_counter.counter);
+ goto next;
+ }
+
+@@ -511,8 +511,8 @@ void wg_packet_decrypt_worker(struct wor
+ struct sk_buff *skb;
+
+ while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
+- enum packet_state state = likely(decrypt_packet(skb,
+- &PACKET_CB(skb)->keypair->receiving)) ?
++ enum packet_state state =
++ likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
+ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
+ wg_queue_enqueue_per_peer_napi(skb, state);
+ if (need_resched())
+--- a/drivers/net/wireguard/selftest/counter.c
++++ b/drivers/net/wireguard/selftest/counter.c
+@@ -6,18 +6,24 @@
+ #ifdef DEBUG
+ bool __init wg_packet_counter_selftest(void)
+ {
++ struct noise_replay_counter *counter;
+ unsigned int test_num = 0, i;
+- union noise_counter counter;
+ bool success = true;
+
+-#define T_INIT do { \
+- memset(&counter, 0, sizeof(union noise_counter)); \
+- spin_lock_init(&counter.receive.lock); \
++ counter = kmalloc(sizeof(*counter), GFP_KERNEL);
++ if (unlikely(!counter)) {
++ pr_err("nonce counter self-test malloc: FAIL\n");
++ return false;
++ }
++
++#define T_INIT do { \
++ memset(counter, 0, sizeof(*counter)); \
++ spin_lock_init(&counter->lock); \
+ } while (0)
+ #define T_LIM (COUNTER_WINDOW_SIZE + 1)
+ #define T(n, v) do { \
+ ++test_num; \
+- if (counter_validate(&counter, n) != (v)) { \
++ if (counter_validate(counter, n) != (v)) { \
+ pr_err("nonce counter self-test %u: FAIL\n", \
+ test_num); \
+ success = false; \
+@@ -99,6 +105,7 @@ bool __init wg_packet_counter_selftest(v
+
+ if (success)
+ pr_info("nonce counter self-tests: pass\n");
++ kfree(counter);
+ return success;
+ }
+ #endif
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -129,7 +129,7 @@ static void keep_key_fresh(struct wg_pee
+ rcu_read_lock_bh();
+ keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
+ send = keypair && READ_ONCE(keypair->sending.is_valid) &&
+- (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES ||
++ (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES ||
+ (keypair->i_am_the_initiator &&
+ wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME)));
+ rcu_read_unlock_bh();
+@@ -349,7 +349,6 @@ void wg_packet_purge_staged_packets(stru
+
+ void wg_packet_send_staged_packets(struct wg_peer *peer)
+ {
+- struct noise_symmetric_key *key;
+ struct noise_keypair *keypair;
+ struct sk_buff_head packets;
+ struct sk_buff *skb;
+@@ -369,10 +368,9 @@ void wg_packet_send_staged_packets(struc
+ rcu_read_unlock_bh();
+ if (unlikely(!keypair))
+ goto out_nokey;
+- key = &keypair->sending;
+- if (unlikely(!READ_ONCE(key->is_valid)))
++ if (unlikely(!READ_ONCE(keypair->sending.is_valid)))
+ goto out_nokey;
+- if (unlikely(wg_birthdate_has_expired(key->birthdate,
++ if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
+ REJECT_AFTER_TIME)))
+ goto out_invalid;
+
+@@ -387,7 +385,7 @@ void wg_packet_send_staged_packets(struc
+ */
+ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
+ PACKET_CB(skb)->nonce =
+- atomic64_inc_return(&key->counter.counter) - 1;
++ atomic64_inc_return(&keypair->sending_counter) - 1;
+ if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
+ goto out_invalid;
+ }
+@@ -399,7 +397,7 @@ void wg_packet_send_staged_packets(struc
+ return;
+
+ out_invalid:
+- WRITE_ONCE(key->is_valid, false);
++ WRITE_ONCE(keypair->sending.is_valid, false);
+ out_nokey:
+ wg_noise_keypair_put(keypair, false);
+
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Frank Werner-Krippendorf <mail@hb9fxq.ch>
+Date: Tue, 23 Jun 2020 03:59:44 -0600
+Subject: [PATCH] wireguard: noise: do not assign initiation time in if
+ condition
+
+commit 558b353c9c2a717509f291c066c6bd8f5f5e21be upstream.
+
+Fixes an error condition reported by checkpatch.pl which caused by
+assigning a variable in an if condition in wg_noise_handshake_consume_
+initiation().
+
+Signed-off-by: Frank Werner-Krippendorf <mail@hb9fxq.ch>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/noise.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(st
+ memcpy(handshake->hash, hash, NOISE_HASH_LEN);
+ memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
+ handshake->remote_index = src->sender_index;
+- if ((s64)(handshake->last_initiation_consumption -
+- (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
++ initiation_consumption = ktime_get_coarse_boottime_ns();
++ if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0)
+ handshake->last_initiation_consumption = initiation_consumption;
+ handshake->state = HANDSHAKE_CONSUMED_INITIATION;
+ up_write(&handshake->lock);
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 19 May 2020 22:49:29 -0600
-Subject: [PATCH] wireguard: queueing: preserve flow hash across packet
- scrubbing
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-commit c78a0b4a78839d572d8a80f6a62221c0d7843135 upstream.
-
-It's important that we clear most header fields during encapsulation and
-decapsulation, because the packet is substantially changed, and we don't
-want any info leak or logic bug due to an accidental correlation. But,
-for encapsulation, it's wrong to clear skb->hash, since it's used by
-fq_codel and flow dissection in general. Without it, classification does
-not proceed as usual. This change might make it easier to estimate the
-number of innerflows by examining clustering of out of order packets,
-but this shouldn't open up anything that can't already be inferred
-otherwise (e.g. syn packet size inference), and fq_codel can be disabled
-anyway.
-
-Furthermore, it might be the case that the hash isn't used or queried at
-all until after wireguard transmits the encrypted UDP packet, which
-means skb->hash might still be zero at this point, and thus no hash
-taken over the inner packet data. In order to address this situation, we
-force a calculation of skb->hash before encrypting packet data.
-
-Of course this means that fq_codel might transmit packets slightly more
-out of order than usual. Toke did some testing on beefy machines with
-high quantities of parallel flows and found that increasing the
-reply-attack counter to 8192 takes care of the most pathological cases
-pretty well.
-
-Reported-by: Dave Taht <dave.taht@gmail.com>
-Reviewed-and-tested-by: Toke Høiland-Jørgensen <toke@toke.dk>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/messages.h | 2 +-
- drivers/net/wireguard/queueing.h | 10 +++++++++-
- drivers/net/wireguard/receive.c | 2 +-
- drivers/net/wireguard/send.c | 7 ++++++-
- 4 files changed, 17 insertions(+), 4 deletions(-)
-
---- a/drivers/net/wireguard/messages.h
-+++ b/drivers/net/wireguard/messages.h
-@@ -32,7 +32,7 @@ enum cookie_values {
- };
-
- enum counter_values {
-- COUNTER_BITS_TOTAL = 2048,
-+ COUNTER_BITS_TOTAL = 8192,
- COUNTER_REDUNDANT_BITS = BITS_PER_LONG,
- COUNTER_WINDOW_SIZE = COUNTER_BITS_TOTAL - COUNTER_REDUNDANT_BITS
- };
---- a/drivers/net/wireguard/queueing.h
-+++ b/drivers/net/wireguard/queueing.h
-@@ -87,12 +87,20 @@ static inline bool wg_check_packet_proto
- return real_protocol && skb->protocol == real_protocol;
- }
-
--static inline void wg_reset_packet(struct sk_buff *skb)
-+static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating)
- {
-+ u8 l4_hash = skb->l4_hash;
-+ u8 sw_hash = skb->sw_hash;
-+ u32 hash = skb->hash;
- skb_scrub_packet(skb, true);
- memset(&skb->headers_start, 0,
- offsetof(struct sk_buff, headers_end) -
- offsetof(struct sk_buff, headers_start));
-+ if (encapsulating) {
-+ skb->l4_hash = l4_hash;
-+ skb->sw_hash = sw_hash;
-+ skb->hash = hash;
-+ }
- skb->queue_mapping = 0;
- skb->nohdr = 0;
- skb->peeked = 0;
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -484,7 +484,7 @@ int wg_packet_rx_poll(struct napi_struct
- if (unlikely(wg_socket_endpoint_from_skb(&endpoint, skb)))
- goto next;
-
-- wg_reset_packet(skb);
-+ wg_reset_packet(skb, false);
- wg_packet_consume_data_done(peer, skb, &endpoint);
- free = false;
-
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -167,6 +167,11 @@ static bool encrypt_packet(struct sk_buf
- struct sk_buff *trailer;
- int num_frags;
-
-+ /* Force hash calculation before encryption so that flow analysis is
-+ * consistent over the inner packet.
-+ */
-+ skb_get_hash(skb);
-+
- /* Calculate lengths. */
- padding_len = calculate_skb_padding(skb);
- trailer_len = padding_len + noise_encrypted_len(0);
-@@ -295,7 +300,7 @@ void wg_packet_encrypt_worker(struct wor
- skb_list_walk_safe(first, skb, next) {
- if (likely(encrypt_packet(skb,
- PACKET_CB(first)->keypair))) {
-- wg_reset_packet(skb);
-+ wg_reset_packet(skb, true);
- } else {
- state = PACKET_STATE_DEAD;
- break;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Tue, 23 Jun 2020 03:59:45 -0600
+Subject: [PATCH] wireguard: device: avoid circular netns references
+
+commit 900575aa33a3eaaef802b31de187a85c4a4b4bd0 upstream.
+
+Before, we took a reference to the creating netns if the new netns was
+different. This caused issues with circular references, with two
+wireguard interfaces swapping namespaces. The solution is to rather not
+take any extra references at all, but instead simply invalidate the
+creating netns pointer when that netns is deleted.
+
+In order to prevent this from happening again, this commit improves the
+rough object leak tracking by allowing it to account for created and
+destroyed interfaces, aside from just peers and keys. That then makes it
+possible to check for the object leak when having two interfaces take a
+reference to each others' namespaces.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 58 ++++++++++------------
+ drivers/net/wireguard/device.h | 3 +-
+ drivers/net/wireguard/netlink.c | 14 ++++--
+ drivers/net/wireguard/socket.c | 25 +++++++---
+ tools/testing/selftests/wireguard/netns.sh | 13 ++++-
+ 5 files changed, 67 insertions(+), 46 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -45,17 +45,18 @@ static int wg_open(struct net_device *de
+ if (dev_v6)
+ dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
+
++ mutex_lock(&wg->device_update_lock);
+ ret = wg_socket_init(wg, wg->incoming_port);
+ if (ret < 0)
+- return ret;
+- mutex_lock(&wg->device_update_lock);
++ goto out;
+ list_for_each_entry(peer, &wg->peer_list, peer_list) {
+ wg_packet_send_staged_packets(peer);
+ if (peer->persistent_keepalive_interval)
+ wg_packet_send_keepalive(peer);
+ }
++out:
+ mutex_unlock(&wg->device_update_lock);
+- return 0;
++ return ret;
+ }
+
+ #ifdef CONFIG_PM_SLEEP
+@@ -225,6 +226,7 @@ static void wg_destruct(struct net_devic
+ list_del(&wg->device_list);
+ rtnl_unlock();
+ mutex_lock(&wg->device_update_lock);
++ rcu_assign_pointer(wg->creating_net, NULL);
+ wg->incoming_port = 0;
+ wg_socket_reinit(wg, NULL, NULL);
+ /* The final references are cleared in the below calls to destroy_workqueue. */
+@@ -240,13 +242,11 @@ static void wg_destruct(struct net_devic
+ skb_queue_purge(&wg->incoming_handshakes);
+ free_percpu(dev->tstats);
+ free_percpu(wg->incoming_handshakes_worker);
+- if (wg->have_creating_net_ref)
+- put_net(wg->creating_net);
+ kvfree(wg->index_hashtable);
+ kvfree(wg->peer_hashtable);
+ mutex_unlock(&wg->device_update_lock);
+
+- pr_debug("%s: Interface deleted\n", dev->name);
++ pr_debug("%s: Interface destroyed\n", dev->name);
+ free_netdev(dev);
+ }
+
+@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_ne
+ struct wg_device *wg = netdev_priv(dev);
+ int ret = -ENOMEM;
+
+- wg->creating_net = src_net;
++ rcu_assign_pointer(wg->creating_net, src_net);
+ init_rwsem(&wg->static_identity.lock);
+ mutex_init(&wg->socket_update_lock);
+ mutex_init(&wg->device_update_lock);
+@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __r
+ .newlink = wg_newlink,
+ };
+
+-static int wg_netdevice_notification(struct notifier_block *nb,
+- unsigned long action, void *data)
++static void wg_netns_pre_exit(struct net *net)
+ {
+- struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
+- struct wg_device *wg = netdev_priv(dev);
+-
+- ASSERT_RTNL();
+-
+- if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
+- return 0;
++ struct wg_device *wg;
+
+- if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
+- put_net(wg->creating_net);
+- wg->have_creating_net_ref = false;
+- } else if (dev_net(dev) != wg->creating_net &&
+- !wg->have_creating_net_ref) {
+- wg->have_creating_net_ref = true;
+- get_net(wg->creating_net);
++ rtnl_lock();
++ list_for_each_entry(wg, &device_list, device_list) {
++ if (rcu_access_pointer(wg->creating_net) == net) {
++ pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
++ netif_carrier_off(wg->dev);
++ mutex_lock(&wg->device_update_lock);
++ rcu_assign_pointer(wg->creating_net, NULL);
++ wg_socket_reinit(wg, NULL, NULL);
++ mutex_unlock(&wg->device_update_lock);
++ }
+ }
+- return 0;
++ rtnl_unlock();
+ }
+
+-static struct notifier_block netdevice_notifier = {
+- .notifier_call = wg_netdevice_notification
++static struct pernet_operations pernet_ops = {
++ .pre_exit = wg_netns_pre_exit
+ };
+
+ int __init wg_device_init(void)
+@@ -429,18 +425,18 @@ int __init wg_device_init(void)
+ return ret;
+ #endif
+
+- ret = register_netdevice_notifier(&netdevice_notifier);
++ ret = register_pernet_device(&pernet_ops);
+ if (ret)
+ goto error_pm;
+
+ ret = rtnl_link_register(&link_ops);
+ if (ret)
+- goto error_netdevice;
++ goto error_pernet;
+
+ return 0;
+
+-error_netdevice:
+- unregister_netdevice_notifier(&netdevice_notifier);
++error_pernet:
++ unregister_pernet_device(&pernet_ops);
+ error_pm:
+ #ifdef CONFIG_PM_SLEEP
+ unregister_pm_notifier(&pm_notifier);
+@@ -451,7 +447,7 @@ error_pm:
+ void wg_device_uninit(void)
+ {
+ rtnl_link_unregister(&link_ops);
+- unregister_netdevice_notifier(&netdevice_notifier);
++ unregister_pernet_device(&pernet_ops);
+ #ifdef CONFIG_PM_SLEEP
+ unregister_pm_notifier(&pm_notifier);
+ #endif
+--- a/drivers/net/wireguard/device.h
++++ b/drivers/net/wireguard/device.h
+@@ -40,7 +40,7 @@ struct wg_device {
+ struct net_device *dev;
+ struct crypt_queue encrypt_queue, decrypt_queue;
+ struct sock __rcu *sock4, *sock6;
+- struct net *creating_net;
++ struct net __rcu *creating_net;
+ struct noise_static_identity static_identity;
+ struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
+ struct workqueue_struct *packet_crypt_wq;
+@@ -56,7 +56,6 @@ struct wg_device {
+ unsigned int num_peers, device_update_gen;
+ u32 fwmark;
+ u16 incoming_port;
+- bool have_creating_net_ref;
+ };
+
+ int wg_device_init(void);
+--- a/drivers/net/wireguard/netlink.c
++++ b/drivers/net/wireguard/netlink.c
+@@ -517,11 +517,15 @@ static int wg_set_device(struct sk_buff
+ if (flags & ~__WGDEVICE_F_ALL)
+ goto out;
+
+- ret = -EPERM;
+- if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
+- info->attrs[WGDEVICE_A_FWMARK]) &&
+- !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
+- goto out;
++ if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) {
++ struct net *net;
++ rcu_read_lock();
++ net = rcu_dereference(wg->creating_net);
++ ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0;
++ rcu_read_unlock();
++ if (ret)
++ goto out;
++ }
+
+ ++wg->device_update_gen;
+
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket
+
+ int wg_socket_init(struct wg_device *wg, u16 port)
+ {
++ struct net *net;
+ int ret;
+ struct udp_tunnel_sock_cfg cfg = {
+ .sk_user_data = wg,
+@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg,
+ };
+ #endif
+
++ rcu_read_lock();
++ net = rcu_dereference(wg->creating_net);
++ net = net ? maybe_get_net(net) : NULL;
++ rcu_read_unlock();
++ if (unlikely(!net))
++ return -ENONET;
++
+ #if IS_ENABLED(CONFIG_IPV6)
+ retry:
+ #endif
+
+- ret = udp_sock_create(wg->creating_net, &port4, &new4);
++ ret = udp_sock_create(net, &port4, &new4);
+ if (ret < 0) {
+ pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
+- return ret;
++ goto out;
+ }
+ set_sock_opts(new4);
+- setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
++ setup_udp_tunnel_sock(net, new4, &cfg);
+
+ #if IS_ENABLED(CONFIG_IPV6)
+ if (ipv6_mod_enabled()) {
+ port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
+- ret = udp_sock_create(wg->creating_net, &port6, &new6);
++ ret = udp_sock_create(net, &port6, &new6);
+ if (ret < 0) {
+ udp_tunnel_sock_release(new4);
+ if (ret == -EADDRINUSE && !port && retries++ < 100)
+ goto retry;
+ pr_err("%s: Could not create IPv6 socket\n",
+ wg->dev->name);
+- return ret;
++ goto out;
+ }
+ set_sock_opts(new6);
+- setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
++ setup_udp_tunnel_sock(net, new6, &cfg);
+ }
+ #endif
+
+ wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
+- return 0;
++ ret = 0;
++out:
++ put_net(net);
++ return ret;
+ }
+
+ void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -587,9 +587,20 @@ ip0 link set wg0 up
+ kill $ncat_pid
+ ip0 link del wg0
+
++# Ensure there aren't circular reference loops
++ip1 link add wg1 type wireguard
++ip2 link add wg2 type wireguard
++ip1 link set wg1 netns $netns2
++ip2 link set wg2 netns $netns1
++pp ip netns delete $netns1
++pp ip netns delete $netns2
++pp ip netns add $netns1
++pp ip netns add $netns2
++
++sleep 2 # Wait for cleanup and grace periods
+ declare -A objects
+ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
+- [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue
++ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ ?[0-9]*)\ .*(created|destroyed).* ]] || continue
+ objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}"
+ done < /dev/kmsg
+ alldeleted=1
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 19 May 2020 22:49:30 -0600
-Subject: [PATCH] wireguard: noise: separate receive counter from send counter
-
-commit a9e90d9931f3a474f04bab782ccd9d77904941e9 upstream.
-
-In "wireguard: queueing: preserve flow hash across packet scrubbing", we
-were required to slightly increase the size of the receive replay
-counter to something still fairly small, but an increase nonetheless.
-It turns out that we can recoup some of the additional memory overhead
-by splitting up the prior union type into two distinct types. Before, we
-used the same "noise_counter" union for both sending and receiving, with
-sending just using a simple atomic64_t, while receiving used the full
-replay counter checker. This meant that most of the memory being
-allocated for the sending counter was being wasted. Since the old
-"noise_counter" type increased in size in the prior commit, now is a
-good time to split up that union type into a distinct "noise_replay_
-counter" for receiving and a boring atomic64_t for sending, each using
-neither more nor less memory than required.
-
-Also, since sometimes the replay counter is accessed without
-necessitating additional accesses to the bitmap, we can reduce cache
-misses by hoisting the always-necessary lock above the bitmap in the
-struct layout. We also change a "noise_replay_counter" stack allocation
-to kmalloc in a -DDEBUG selftest so that KASAN doesn't trigger a stack
-frame warning.
-
-All and all, removing a bit of abstraction in this commit makes the code
-simpler and smaller, in addition to the motivating memory usage
-recuperation. For example, passing around raw "noise_symmetric_key"
-structs is something that really only makes sense within noise.c, in the
-one place where the sending and receiving keys can safely be thought of
-as the same type of object; subsequent to that, it's important that we
-uniformly access these through keypair->{sending,receiving}, where their
-distinct roles are always made explicit. So this patch allows us to draw
-that distinction clearly as well.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/noise.c | 16 +++------
- drivers/net/wireguard/noise.h | 14 ++++----
- drivers/net/wireguard/receive.c | 42 ++++++++++++------------
- drivers/net/wireguard/selftest/counter.c | 17 +++++++---
- drivers/net/wireguard/send.c | 12 +++----
- 5 files changed, 48 insertions(+), 53 deletions(-)
-
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -104,6 +104,7 @@ static struct noise_keypair *keypair_cre
-
- if (unlikely(!keypair))
- return NULL;
-+ spin_lock_init(&keypair->receiving_counter.lock);
- keypair->internal_id = atomic64_inc_return(&keypair_counter);
- keypair->entry.type = INDEX_HASHTABLE_KEYPAIR;
- keypair->entry.peer = peer;
-@@ -358,25 +359,16 @@ out:
- memzero_explicit(output, BLAKE2S_HASH_SIZE + 1);
- }
-
--static void symmetric_key_init(struct noise_symmetric_key *key)
--{
-- spin_lock_init(&key->counter.receive.lock);
-- atomic64_set(&key->counter.counter, 0);
-- memset(key->counter.receive.backtrack, 0,
-- sizeof(key->counter.receive.backtrack));
-- key->birthdate = ktime_get_coarse_boottime_ns();
-- key->is_valid = true;
--}
--
- static void derive_keys(struct noise_symmetric_key *first_dst,
- struct noise_symmetric_key *second_dst,
- const u8 chaining_key[NOISE_HASH_LEN])
- {
-+ u64 birthdate = ktime_get_coarse_boottime_ns();
- kdf(first_dst->key, second_dst->key, NULL, NULL,
- NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0,
- chaining_key);
-- symmetric_key_init(first_dst);
-- symmetric_key_init(second_dst);
-+ first_dst->birthdate = second_dst->birthdate = birthdate;
-+ first_dst->is_valid = second_dst->is_valid = true;
- }
-
- static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN],
---- a/drivers/net/wireguard/noise.h
-+++ b/drivers/net/wireguard/noise.h
-@@ -15,18 +15,14 @@
- #include <linux/mutex.h>
- #include <linux/kref.h>
-
--union noise_counter {
-- struct {
-- u64 counter;
-- unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
-- spinlock_t lock;
-- } receive;
-- atomic64_t counter;
-+struct noise_replay_counter {
-+ u64 counter;
-+ spinlock_t lock;
-+ unsigned long backtrack[COUNTER_BITS_TOTAL / BITS_PER_LONG];
- };
-
- struct noise_symmetric_key {
- u8 key[NOISE_SYMMETRIC_KEY_LEN];
-- union noise_counter counter;
- u64 birthdate;
- bool is_valid;
- };
-@@ -34,7 +30,9 @@ struct noise_symmetric_key {
- struct noise_keypair {
- struct index_hashtable_entry entry;
- struct noise_symmetric_key sending;
-+ atomic64_t sending_counter;
- struct noise_symmetric_key receiving;
-+ struct noise_replay_counter receiving_counter;
- __le32 remote_index;
- bool i_am_the_initiator;
- struct kref refcount;
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -245,20 +245,20 @@ static void keep_key_fresh(struct wg_pee
- }
- }
-
--static bool decrypt_packet(struct sk_buff *skb, struct noise_symmetric_key *key)
-+static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair)
- {
- struct scatterlist sg[MAX_SKB_FRAGS + 8];
- struct sk_buff *trailer;
- unsigned int offset;
- int num_frags;
-
-- if (unlikely(!key))
-+ if (unlikely(!keypair))
- return false;
-
-- if (unlikely(!READ_ONCE(key->is_valid) ||
-- wg_birthdate_has_expired(key->birthdate, REJECT_AFTER_TIME) ||
-- key->counter.receive.counter >= REJECT_AFTER_MESSAGES)) {
-- WRITE_ONCE(key->is_valid, false);
-+ if (unlikely(!READ_ONCE(keypair->receiving.is_valid) ||
-+ wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) ||
-+ keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) {
-+ WRITE_ONCE(keypair->receiving.is_valid, false);
- return false;
- }
-
-@@ -283,7 +283,7 @@ static bool decrypt_packet(struct sk_buf
-
- if (!chacha20poly1305_decrypt_sg_inplace(sg, skb->len, NULL, 0,
- PACKET_CB(skb)->nonce,
-- key->key))
-+ keypair->receiving.key))
- return false;
-
- /* Another ugly situation of pushing and pulling the header so as to
-@@ -298,41 +298,41 @@ static bool decrypt_packet(struct sk_buf
- }
-
- /* This is RFC6479, a replay detection bitmap algorithm that avoids bitshifts */
--static bool counter_validate(union noise_counter *counter, u64 their_counter)
-+static bool counter_validate(struct noise_replay_counter *counter, u64 their_counter)
- {
- unsigned long index, index_current, top, i;
- bool ret = false;
-
-- spin_lock_bh(&counter->receive.lock);
-+ spin_lock_bh(&counter->lock);
-
-- if (unlikely(counter->receive.counter >= REJECT_AFTER_MESSAGES + 1 ||
-+ if (unlikely(counter->counter >= REJECT_AFTER_MESSAGES + 1 ||
- their_counter >= REJECT_AFTER_MESSAGES))
- goto out;
-
- ++their_counter;
-
- if (unlikely((COUNTER_WINDOW_SIZE + their_counter) <
-- counter->receive.counter))
-+ counter->counter))
- goto out;
-
- index = their_counter >> ilog2(BITS_PER_LONG);
-
-- if (likely(their_counter > counter->receive.counter)) {
-- index_current = counter->receive.counter >> ilog2(BITS_PER_LONG);
-+ if (likely(their_counter > counter->counter)) {
-+ index_current = counter->counter >> ilog2(BITS_PER_LONG);
- top = min_t(unsigned long, index - index_current,
- COUNTER_BITS_TOTAL / BITS_PER_LONG);
- for (i = 1; i <= top; ++i)
-- counter->receive.backtrack[(i + index_current) &
-+ counter->backtrack[(i + index_current) &
- ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0;
-- counter->receive.counter = their_counter;
-+ counter->counter = their_counter;
- }
-
- index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1;
- ret = !test_and_set_bit(their_counter & (BITS_PER_LONG - 1),
-- &counter->receive.backtrack[index]);
-+ &counter->backtrack[index]);
-
- out:
-- spin_unlock_bh(&counter->receive.lock);
-+ spin_unlock_bh(&counter->lock);
- return ret;
- }
-
-@@ -472,12 +472,12 @@ int wg_packet_rx_poll(struct napi_struct
- if (unlikely(state != PACKET_STATE_CRYPTED))
- goto next;
-
-- if (unlikely(!counter_validate(&keypair->receiving.counter,
-+ if (unlikely(!counter_validate(&keypair->receiving_counter,
- PACKET_CB(skb)->nonce))) {
- net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n",
- peer->device->dev->name,
- PACKET_CB(skb)->nonce,
-- keypair->receiving.counter.receive.counter);
-+ keypair->receiving_counter.counter);
- goto next;
- }
-
-@@ -511,8 +511,8 @@ void wg_packet_decrypt_worker(struct wor
- struct sk_buff *skb;
-
- while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
-- enum packet_state state = likely(decrypt_packet(skb,
-- &PACKET_CB(skb)->keypair->receiving)) ?
-+ enum packet_state state =
-+ likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
- PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
- wg_queue_enqueue_per_peer_napi(skb, state);
- if (need_resched())
---- a/drivers/net/wireguard/selftest/counter.c
-+++ b/drivers/net/wireguard/selftest/counter.c
-@@ -6,18 +6,24 @@
- #ifdef DEBUG
- bool __init wg_packet_counter_selftest(void)
- {
-+ struct noise_replay_counter *counter;
- unsigned int test_num = 0, i;
-- union noise_counter counter;
- bool success = true;
-
--#define T_INIT do { \
-- memset(&counter, 0, sizeof(union noise_counter)); \
-- spin_lock_init(&counter.receive.lock); \
-+ counter = kmalloc(sizeof(*counter), GFP_KERNEL);
-+ if (unlikely(!counter)) {
-+ pr_err("nonce counter self-test malloc: FAIL\n");
-+ return false;
-+ }
-+
-+#define T_INIT do { \
-+ memset(counter, 0, sizeof(*counter)); \
-+ spin_lock_init(&counter->lock); \
- } while (0)
- #define T_LIM (COUNTER_WINDOW_SIZE + 1)
- #define T(n, v) do { \
- ++test_num; \
-- if (counter_validate(&counter, n) != (v)) { \
-+ if (counter_validate(counter, n) != (v)) { \
- pr_err("nonce counter self-test %u: FAIL\n", \
- test_num); \
- success = false; \
-@@ -99,6 +105,7 @@ bool __init wg_packet_counter_selftest(v
-
- if (success)
- pr_info("nonce counter self-tests: pass\n");
-+ kfree(counter);
- return success;
- }
- #endif
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -129,7 +129,7 @@ static void keep_key_fresh(struct wg_pee
- rcu_read_lock_bh();
- keypair = rcu_dereference_bh(peer->keypairs.current_keypair);
- send = keypair && READ_ONCE(keypair->sending.is_valid) &&
-- (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES ||
-+ (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES ||
- (keypair->i_am_the_initiator &&
- wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME)));
- rcu_read_unlock_bh();
-@@ -349,7 +349,6 @@ void wg_packet_purge_staged_packets(stru
-
- void wg_packet_send_staged_packets(struct wg_peer *peer)
- {
-- struct noise_symmetric_key *key;
- struct noise_keypair *keypair;
- struct sk_buff_head packets;
- struct sk_buff *skb;
-@@ -369,10 +368,9 @@ void wg_packet_send_staged_packets(struc
- rcu_read_unlock_bh();
- if (unlikely(!keypair))
- goto out_nokey;
-- key = &keypair->sending;
-- if (unlikely(!READ_ONCE(key->is_valid)))
-+ if (unlikely(!READ_ONCE(keypair->sending.is_valid)))
- goto out_nokey;
-- if (unlikely(wg_birthdate_has_expired(key->birthdate,
-+ if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate,
- REJECT_AFTER_TIME)))
- goto out_invalid;
-
-@@ -387,7 +385,7 @@ void wg_packet_send_staged_packets(struc
- */
- PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb);
- PACKET_CB(skb)->nonce =
-- atomic64_inc_return(&key->counter.counter) - 1;
-+ atomic64_inc_return(&keypair->sending_counter) - 1;
- if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES))
- goto out_invalid;
- }
-@@ -399,7 +397,7 @@ void wg_packet_send_staged_packets(struc
- return;
-
- out_invalid:
-- WRITE_ONCE(key->is_valid, false);
-+ WRITE_ONCE(keypair->sending.is_valid, false);
- out_nokey:
- wg_noise_keypair_put(keypair, false);
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Frank Werner-Krippendorf <mail@hb9fxq.ch>
-Date: Tue, 23 Jun 2020 03:59:44 -0600
-Subject: [PATCH] wireguard: noise: do not assign initiation time in if
- condition
-
-commit 558b353c9c2a717509f291c066c6bd8f5f5e21be upstream.
-
-Fixes an error condition reported by checkpatch.pl which caused by
-assigning a variable in an if condition in wg_noise_handshake_consume_
-initiation().
-
-Signed-off-by: Frank Werner-Krippendorf <mail@hb9fxq.ch>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/noise.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -617,8 +617,8 @@ wg_noise_handshake_consume_initiation(st
- memcpy(handshake->hash, hash, NOISE_HASH_LEN);
- memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN);
- handshake->remote_index = src->sender_index;
-- if ((s64)(handshake->last_initiation_consumption -
-- (initiation_consumption = ktime_get_coarse_boottime_ns())) < 0)
-+ initiation_consumption = ktime_get_coarse_boottime_ns();
-+ if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0)
- handshake->last_initiation_consumption = initiation_consumption;
- handshake->state = HANDSHAKE_CONSUMED_INITIATION;
- up_write(&handshake->lock);
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 24 Jun 2020 16:06:03 -0600
+Subject: [PATCH] wireguard: receive: account for napi_gro_receive never
+ returning GRO_DROP
+
+commit df08126e3833e9dca19e2407db5f5860a7c194fb upstream.
+
+The napi_gro_receive function no longer returns GRO_DROP ever, making
+handling GRO_DROP dead code. This commit removes that dead code.
+Further, it's not even clear that device drivers have any business in
+taking action after passing off received packets; that's arguably out of
+their hands.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Fixes: 6570bc79c0df ("net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/receive.c | 10 ++--------
+ 1 file changed, 2 insertions(+), 8 deletions(-)
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(
+ if (unlikely(routed_peer != peer))
+ goto dishonest_packet_peer;
+
+- if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
+- ++dev->stats.rx_dropped;
+- net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
+- dev->name, peer->internal_id,
+- &peer->endpoint.addr);
+- } else {
+- update_rx_stats(peer, message_data_len(len_before_trim));
+- }
++ napi_gro_receive(&peer->napi, skb);
++ update_rx_stats(peer, message_data_len(len_before_trim));
+ return;
+
+ dishonest_packet_peer:
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 29 Jun 2020 19:06:18 -0600
+Subject: [PATCH] net: ip_tunnel: add header_ops for layer 3 devices
+
+commit 2606aff916854b61234bf85001be9777bab2d5f8 upstream.
+
+Some devices that take straight up layer 3 packets benefit from having a
+shared header_ops so that AF_PACKET sockets can inject packets that are
+recognized. This shared infrastructure will be used by other drivers
+that currently can't inject packets using AF_PACKET. It also exposes the
+parser function, as it is useful in standalone form too.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Acked-by: Willem de Bruijn <willemb@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ include/net/ip_tunnels.h | 3 +++
+ net/ipv4/ip_tunnel_core.c | 18 ++++++++++++++++++
+ 2 files changed, 21 insertions(+)
+
+--- a/include/net/ip_tunnels.h
++++ b/include/net/ip_tunnels.h
+@@ -289,6 +289,9 @@ int ip_tunnel_newlink(struct net_device
+ struct ip_tunnel_parm *p, __u32 fwmark);
+ void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
+
++extern const struct header_ops ip_tunnel_header_ops;
++__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
++
+ struct ip_tunnel_encap_ops {
+ size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+ int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+--- a/net/ipv4/ip_tunnel_core.c
++++ b/net/ipv4/ip_tunnel_core.c
+@@ -446,3 +446,21 @@ void ip_tunnel_unneed_metadata(void)
+ static_branch_dec(&ip_tunnel_metadata_cnt);
+ }
+ EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
++
++/* Returns either the correct skb->protocol value, or 0 if invalid. */
++__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
++{
++ if (skb_network_header(skb) >= skb->head &&
++ (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
++ ip_hdr(skb)->version == 4)
++ return htons(ETH_P_IP);
++ if (skb_network_header(skb) >= skb->head &&
++ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
++ ipv6_hdr(skb)->version == 6)
++ return htons(ETH_P_IPV6);
++ return 0;
++}
++EXPORT_SYMBOL(ip_tunnel_parse_protocol);
++
++const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol };
++EXPORT_SYMBOL(ip_tunnel_header_ops);
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Tue, 23 Jun 2020 03:59:45 -0600
-Subject: [PATCH] wireguard: device: avoid circular netns references
-
-commit 900575aa33a3eaaef802b31de187a85c4a4b4bd0 upstream.
-
-Before, we took a reference to the creating netns if the new netns was
-different. This caused issues with circular references, with two
-wireguard interfaces swapping namespaces. The solution is to rather not
-take any extra references at all, but instead simply invalidate the
-creating netns pointer when that netns is deleted.
-
-In order to prevent this from happening again, this commit improves the
-rough object leak tracking by allowing it to account for created and
-destroyed interfaces, aside from just peers and keys. That then makes it
-possible to check for the object leak when having two interfaces take a
-reference to each others' namespaces.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 58 ++++++++++------------
- drivers/net/wireguard/device.h | 3 +-
- drivers/net/wireguard/netlink.c | 14 ++++--
- drivers/net/wireguard/socket.c | 25 +++++++---
- tools/testing/selftests/wireguard/netns.sh | 13 ++++-
- 5 files changed, 67 insertions(+), 46 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -45,17 +45,18 @@ static int wg_open(struct net_device *de
- if (dev_v6)
- dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE;
-
-+ mutex_lock(&wg->device_update_lock);
- ret = wg_socket_init(wg, wg->incoming_port);
- if (ret < 0)
-- return ret;
-- mutex_lock(&wg->device_update_lock);
-+ goto out;
- list_for_each_entry(peer, &wg->peer_list, peer_list) {
- wg_packet_send_staged_packets(peer);
- if (peer->persistent_keepalive_interval)
- wg_packet_send_keepalive(peer);
- }
-+out:
- mutex_unlock(&wg->device_update_lock);
-- return 0;
-+ return ret;
- }
-
- #ifdef CONFIG_PM_SLEEP
-@@ -225,6 +226,7 @@ static void wg_destruct(struct net_devic
- list_del(&wg->device_list);
- rtnl_unlock();
- mutex_lock(&wg->device_update_lock);
-+ rcu_assign_pointer(wg->creating_net, NULL);
- wg->incoming_port = 0;
- wg_socket_reinit(wg, NULL, NULL);
- /* The final references are cleared in the below calls to destroy_workqueue. */
-@@ -240,13 +242,11 @@ static void wg_destruct(struct net_devic
- skb_queue_purge(&wg->incoming_handshakes);
- free_percpu(dev->tstats);
- free_percpu(wg->incoming_handshakes_worker);
-- if (wg->have_creating_net_ref)
-- put_net(wg->creating_net);
- kvfree(wg->index_hashtable);
- kvfree(wg->peer_hashtable);
- mutex_unlock(&wg->device_update_lock);
-
-- pr_debug("%s: Interface deleted\n", dev->name);
-+ pr_debug("%s: Interface destroyed\n", dev->name);
- free_netdev(dev);
- }
-
-@@ -292,7 +292,7 @@ static int wg_newlink(struct net *src_ne
- struct wg_device *wg = netdev_priv(dev);
- int ret = -ENOMEM;
-
-- wg->creating_net = src_net;
-+ rcu_assign_pointer(wg->creating_net, src_net);
- init_rwsem(&wg->static_identity.lock);
- mutex_init(&wg->socket_update_lock);
- mutex_init(&wg->device_update_lock);
-@@ -393,30 +393,26 @@ static struct rtnl_link_ops link_ops __r
- .newlink = wg_newlink,
- };
-
--static int wg_netdevice_notification(struct notifier_block *nb,
-- unsigned long action, void *data)
-+static void wg_netns_pre_exit(struct net *net)
- {
-- struct net_device *dev = ((struct netdev_notifier_info *)data)->dev;
-- struct wg_device *wg = netdev_priv(dev);
--
-- ASSERT_RTNL();
--
-- if (action != NETDEV_REGISTER || dev->netdev_ops != &netdev_ops)
-- return 0;
-+ struct wg_device *wg;
-
-- if (dev_net(dev) == wg->creating_net && wg->have_creating_net_ref) {
-- put_net(wg->creating_net);
-- wg->have_creating_net_ref = false;
-- } else if (dev_net(dev) != wg->creating_net &&
-- !wg->have_creating_net_ref) {
-- wg->have_creating_net_ref = true;
-- get_net(wg->creating_net);
-+ rtnl_lock();
-+ list_for_each_entry(wg, &device_list, device_list) {
-+ if (rcu_access_pointer(wg->creating_net) == net) {
-+ pr_debug("%s: Creating namespace exiting\n", wg->dev->name);
-+ netif_carrier_off(wg->dev);
-+ mutex_lock(&wg->device_update_lock);
-+ rcu_assign_pointer(wg->creating_net, NULL);
-+ wg_socket_reinit(wg, NULL, NULL);
-+ mutex_unlock(&wg->device_update_lock);
-+ }
- }
-- return 0;
-+ rtnl_unlock();
- }
-
--static struct notifier_block netdevice_notifier = {
-- .notifier_call = wg_netdevice_notification
-+static struct pernet_operations pernet_ops = {
-+ .pre_exit = wg_netns_pre_exit
- };
-
- int __init wg_device_init(void)
-@@ -429,18 +425,18 @@ int __init wg_device_init(void)
- return ret;
- #endif
-
-- ret = register_netdevice_notifier(&netdevice_notifier);
-+ ret = register_pernet_device(&pernet_ops);
- if (ret)
- goto error_pm;
-
- ret = rtnl_link_register(&link_ops);
- if (ret)
-- goto error_netdevice;
-+ goto error_pernet;
-
- return 0;
-
--error_netdevice:
-- unregister_netdevice_notifier(&netdevice_notifier);
-+error_pernet:
-+ unregister_pernet_device(&pernet_ops);
- error_pm:
- #ifdef CONFIG_PM_SLEEP
- unregister_pm_notifier(&pm_notifier);
-@@ -451,7 +447,7 @@ error_pm:
- void wg_device_uninit(void)
- {
- rtnl_link_unregister(&link_ops);
-- unregister_netdevice_notifier(&netdevice_notifier);
-+ unregister_pernet_device(&pernet_ops);
- #ifdef CONFIG_PM_SLEEP
- unregister_pm_notifier(&pm_notifier);
- #endif
---- a/drivers/net/wireguard/device.h
-+++ b/drivers/net/wireguard/device.h
-@@ -40,7 +40,7 @@ struct wg_device {
- struct net_device *dev;
- struct crypt_queue encrypt_queue, decrypt_queue;
- struct sock __rcu *sock4, *sock6;
-- struct net *creating_net;
-+ struct net __rcu *creating_net;
- struct noise_static_identity static_identity;
- struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
- struct workqueue_struct *packet_crypt_wq;
-@@ -56,7 +56,6 @@ struct wg_device {
- unsigned int num_peers, device_update_gen;
- u32 fwmark;
- u16 incoming_port;
-- bool have_creating_net_ref;
- };
-
- int wg_device_init(void);
---- a/drivers/net/wireguard/netlink.c
-+++ b/drivers/net/wireguard/netlink.c
-@@ -517,11 +517,15 @@ static int wg_set_device(struct sk_buff
- if (flags & ~__WGDEVICE_F_ALL)
- goto out;
-
-- ret = -EPERM;
-- if ((info->attrs[WGDEVICE_A_LISTEN_PORT] ||
-- info->attrs[WGDEVICE_A_FWMARK]) &&
-- !ns_capable(wg->creating_net->user_ns, CAP_NET_ADMIN))
-- goto out;
-+ if (info->attrs[WGDEVICE_A_LISTEN_PORT] || info->attrs[WGDEVICE_A_FWMARK]) {
-+ struct net *net;
-+ rcu_read_lock();
-+ net = rcu_dereference(wg->creating_net);
-+ ret = !net || !ns_capable(net->user_ns, CAP_NET_ADMIN) ? -EPERM : 0;
-+ rcu_read_unlock();
-+ if (ret)
-+ goto out;
-+ }
-
- ++wg->device_update_gen;
-
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -347,6 +347,7 @@ static void set_sock_opts(struct socket
-
- int wg_socket_init(struct wg_device *wg, u16 port)
- {
-+ struct net *net;
- int ret;
- struct udp_tunnel_sock_cfg cfg = {
- .sk_user_data = wg,
-@@ -371,37 +372,47 @@ int wg_socket_init(struct wg_device *wg,
- };
- #endif
-
-+ rcu_read_lock();
-+ net = rcu_dereference(wg->creating_net);
-+ net = net ? maybe_get_net(net) : NULL;
-+ rcu_read_unlock();
-+ if (unlikely(!net))
-+ return -ENONET;
-+
- #if IS_ENABLED(CONFIG_IPV6)
- retry:
- #endif
-
-- ret = udp_sock_create(wg->creating_net, &port4, &new4);
-+ ret = udp_sock_create(net, &port4, &new4);
- if (ret < 0) {
- pr_err("%s: Could not create IPv4 socket\n", wg->dev->name);
-- return ret;
-+ goto out;
- }
- set_sock_opts(new4);
-- setup_udp_tunnel_sock(wg->creating_net, new4, &cfg);
-+ setup_udp_tunnel_sock(net, new4, &cfg);
-
- #if IS_ENABLED(CONFIG_IPV6)
- if (ipv6_mod_enabled()) {
- port6.local_udp_port = inet_sk(new4->sk)->inet_sport;
-- ret = udp_sock_create(wg->creating_net, &port6, &new6);
-+ ret = udp_sock_create(net, &port6, &new6);
- if (ret < 0) {
- udp_tunnel_sock_release(new4);
- if (ret == -EADDRINUSE && !port && retries++ < 100)
- goto retry;
- pr_err("%s: Could not create IPv6 socket\n",
- wg->dev->name);
-- return ret;
-+ goto out;
- }
- set_sock_opts(new6);
-- setup_udp_tunnel_sock(wg->creating_net, new6, &cfg);
-+ setup_udp_tunnel_sock(net, new6, &cfg);
- }
- #endif
-
- wg_socket_reinit(wg, new4->sk, new6 ? new6->sk : NULL);
-- return 0;
-+ ret = 0;
-+out:
-+ put_net(net);
-+ return ret;
- }
-
- void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -587,9 +587,20 @@ ip0 link set wg0 up
- kill $ncat_pid
- ip0 link del wg0
-
-+# Ensure there aren't circular reference loops
-+ip1 link add wg1 type wireguard
-+ip2 link add wg2 type wireguard
-+ip1 link set wg1 netns $netns2
-+ip2 link set wg2 netns $netns1
-+pp ip netns delete $netns1
-+pp ip netns delete $netns2
-+pp ip netns add $netns1
-+pp ip netns add $netns2
-+
-+sleep 2 # Wait for cleanup and grace periods
- declare -A objects
- while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
-- [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue
-+ [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ ?[0-9]*)\ .*(created|destroyed).* ]] || continue
- objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}"
- done < /dev/kmsg
- alldeleted=1
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 29 Jun 2020 19:06:20 -0600
+Subject: [PATCH] wireguard: implement header_ops->parse_protocol for AF_PACKET
+
+commit 01a4967c71c004f8ecad4ab57021348636502fa9 upstream.
+
+WireGuard uses skb->protocol to determine packet type, and bails out if
+it's not set or set to something it's not expecting. For AF_PACKET
+injection, we need to support its call chain of:
+
+ packet_sendmsg -> packet_snd -> packet_parse_headers ->
+ dev_parse_header_protocol -> parse_protocol
+
+Without a valid parse_protocol, this returns zero, and wireguard then
+rejects the skb. So, this wires up the ip_tunnel handler for layer 3
+packets for that case.
+
+Reported-by: Hans Wippel <ndev@hwipl.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -262,6 +262,7 @@ static void wg_setup(struct net_device *
+ max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
+
+ dev->netdev_ops = &netdev_ops;
++ dev->header_ops = &ip_tunnel_header_ops;
+ dev->hard_header_len = 0;
+ dev->addr_len = 0;
+ dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 24 Jun 2020 16:06:03 -0600
-Subject: [PATCH] wireguard: receive: account for napi_gro_receive never
- returning GRO_DROP
-
-commit df08126e3833e9dca19e2407db5f5860a7c194fb upstream.
-
-The napi_gro_receive function no longer returns GRO_DROP ever, making
-handling GRO_DROP dead code. This commit removes that dead code.
-Further, it's not even clear that device drivers have any business in
-taking action after passing off received packets; that's arguably out of
-their hands.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Fixes: 6570bc79c0df ("net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/receive.c | 10 ++--------
- 1 file changed, 2 insertions(+), 8 deletions(-)
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -414,14 +414,8 @@ static void wg_packet_consume_data_done(
- if (unlikely(routed_peer != peer))
- goto dishonest_packet_peer;
-
-- if (unlikely(napi_gro_receive(&peer->napi, skb) == GRO_DROP)) {
-- ++dev->stats.rx_dropped;
-- net_dbg_ratelimited("%s: Failed to give packet to userspace from peer %llu (%pISpfsc)\n",
-- dev->name, peer->internal_id,
-- &peer->endpoint.addr);
-- } else {
-- update_rx_stats(peer, message_data_len(len_before_trim));
-- }
-+ napi_gro_receive(&peer->napi, skb);
-+ update_rx_stats(peer, message_data_len(len_before_trim));
- return;
-
- dishonest_packet_peer:
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 29 Jun 2020 19:06:18 -0600
-Subject: [PATCH] net: ip_tunnel: add header_ops for layer 3 devices
-
-commit 2606aff916854b61234bf85001be9777bab2d5f8 upstream.
-
-Some devices that take straight up layer 3 packets benefit from having a
-shared header_ops so that AF_PACKET sockets can inject packets that are
-recognized. This shared infrastructure will be used by other drivers
-that currently can't inject packets using AF_PACKET. It also exposes the
-parser function, as it is useful in standalone form too.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Acked-by: Willem de Bruijn <willemb@google.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- include/net/ip_tunnels.h | 3 +++
- net/ipv4/ip_tunnel_core.c | 18 ++++++++++++++++++
- 2 files changed, 21 insertions(+)
-
---- a/include/net/ip_tunnels.h
-+++ b/include/net/ip_tunnels.h
-@@ -289,6 +289,9 @@ int ip_tunnel_newlink(struct net_device
- struct ip_tunnel_parm *p, __u32 fwmark);
- void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
-
-+extern const struct header_ops ip_tunnel_header_ops;
-+__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
-+
- struct ip_tunnel_encap_ops {
- size_t (*encap_hlen)(struct ip_tunnel_encap *e);
- int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
---- a/net/ipv4/ip_tunnel_core.c
-+++ b/net/ipv4/ip_tunnel_core.c
-@@ -446,3 +446,21 @@ void ip_tunnel_unneed_metadata(void)
- static_branch_dec(&ip_tunnel_metadata_cnt);
- }
- EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
-+
-+/* Returns either the correct skb->protocol value, or 0 if invalid. */
-+__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
-+{
-+ if (skb_network_header(skb) >= skb->head &&
-+ (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
-+ ip_hdr(skb)->version == 4)
-+ return htons(ETH_P_IP);
-+ if (skb_network_header(skb) >= skb->head &&
-+ (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
-+ ipv6_hdr(skb)->version == 6)
-+ return htons(ETH_P_IPV6);
-+ return 0;
-+}
-+EXPORT_SYMBOL(ip_tunnel_parse_protocol);
-+
-+const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol };
-+EXPORT_SYMBOL(ip_tunnel_header_ops);
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 29 Jun 2020 19:06:21 -0600
+Subject: [PATCH] wireguard: queueing: make use of ip_tunnel_parse_protocol
+
+commit 1a574074ae7d1d745c16f7710655f38a53174c27 upstream.
+
+Now that wg_examine_packet_protocol has been added for general
+consumption as ip_tunnel_parse_protocol, it's possible to remove
+wg_examine_packet_protocol and simply use the new
+ip_tunnel_parse_protocol function directly.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/queueing.h | 19 ++-----------------
+ drivers/net/wireguard/receive.c | 2 +-
+ 2 files changed, 3 insertions(+), 18 deletions(-)
+
+--- a/drivers/net/wireguard/queueing.h
++++ b/drivers/net/wireguard/queueing.h
+@@ -11,6 +11,7 @@
+ #include <linux/skbuff.h>
+ #include <linux/ip.h>
+ #include <linux/ipv6.h>
++#include <net/ip_tunnels.h>
+
+ struct wg_device;
+ struct wg_peer;
+@@ -65,25 +66,9 @@ struct packet_cb {
+ #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb))
+ #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
+
+-/* Returns either the correct skb->protocol value, or 0 if invalid. */
+-static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb)
+-{
+- if (skb_network_header(skb) >= skb->head &&
+- (skb_network_header(skb) + sizeof(struct iphdr)) <=
+- skb_tail_pointer(skb) &&
+- ip_hdr(skb)->version == 4)
+- return htons(ETH_P_IP);
+- if (skb_network_header(skb) >= skb->head &&
+- (skb_network_header(skb) + sizeof(struct ipv6hdr)) <=
+- skb_tail_pointer(skb) &&
+- ipv6_hdr(skb)->version == 6)
+- return htons(ETH_P_IPV6);
+- return 0;
+-}
+-
+ static inline bool wg_check_packet_protocol(struct sk_buff *skb)
+ {
+- __be16 real_protocol = wg_examine_packet_protocol(skb);
++ __be16 real_protocol = ip_tunnel_parse_protocol(skb);
+ return real_protocol && skb->protocol == real_protocol;
+ }
+
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -387,7 +387,7 @@ static void wg_packet_consume_data_done(
+ */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->csum_level = ~0; /* All levels */
+- skb->protocol = wg_examine_packet_protocol(skb);
++ skb->protocol = ip_tunnel_parse_protocol(skb);
+ if (skb->protocol == htons(ETH_P_IP)) {
+ len = ntohs(ip_hdr(skb)->tot_len);
+ if (unlikely(len < sizeof(struct iphdr)))
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Johannes Berg <johannes.berg@intel.com>
+Date: Tue, 18 Aug 2020 10:17:31 +0200
+Subject: [PATCH] netlink: consistently use NLA_POLICY_EXACT_LEN()
+
+commit 8140860c817f3e9f78bcd1e420b9777ddcbaa629 upstream.
+
+Change places that open-code NLA_POLICY_EXACT_LEN() to
+use the macro instead, giving us flexibility in how we
+handle the details of the macro.
+
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+[Jason: only picked the drivers/net/wireguard/* part]
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/netlink.c | 10 +++++-----
+ 1 file changed, 5 insertions(+), 5 deletions(-)
+
+--- a/drivers/net/wireguard/netlink.c
++++ b/drivers/net/wireguard/netlink.c
+@@ -22,8 +22,8 @@ static struct genl_family genl_family;
+ static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = {
+ [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 },
+ [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+- [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
+- [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
++ [WGDEVICE_A_PRIVATE_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
++ [WGDEVICE_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
+ [WGDEVICE_A_FLAGS] = { .type = NLA_U32 },
+ [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 },
+ [WGDEVICE_A_FWMARK] = { .type = NLA_U32 },
+@@ -31,12 +31,12 @@ static const struct nla_policy device_po
+ };
+
+ static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
+- [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
+- [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN },
++ [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
++ [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN),
+ [WGPEER_A_FLAGS] = { .type = NLA_U32 },
+ [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
+ [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
+- [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) },
++ [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)),
+ [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
+ [WGPEER_A_TX_BYTES] = { .type = NLA_U64 },
+ [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED },
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 29 Jun 2020 19:06:20 -0600
-Subject: [PATCH] wireguard: implement header_ops->parse_protocol for AF_PACKET
-
-commit 01a4967c71c004f8ecad4ab57021348636502fa9 upstream.
-
-WireGuard uses skb->protocol to determine packet type, and bails out if
-it's not set or set to something it's not expecting. For AF_PACKET
-injection, we need to support its call chain of:
-
- packet_sendmsg -> packet_snd -> packet_parse_headers ->
- dev_parse_header_protocol -> parse_protocol
-
-Without a valid parse_protocol, this returns zero, and wireguard then
-rejects the skb. So, this wires up the ip_tunnel handler for layer 3
-packets for that case.
-
-Reported-by: Hans Wippel <ndev@hwipl.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 1 +
- 1 file changed, 1 insertion(+)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -262,6 +262,7 @@ static void wg_setup(struct net_device *
- max(sizeof(struct ipv6hdr), sizeof(struct iphdr));
-
- dev->netdev_ops = &netdev_ops;
-+ dev->header_ops = &ip_tunnel_header_ops;
- dev->hard_header_len = 0;
- dev->addr_len = 0;
- dev->needed_headroom = DATA_PACKET_HEAD_ROOM;
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Johannes Berg <johannes.berg@intel.com>
+Date: Tue, 18 Aug 2020 10:17:32 +0200
+Subject: [PATCH] netlink: consistently use NLA_POLICY_MIN_LEN()
+
+commit bc0435855041d7fff0b83dd992fc4be34aa11afb upstream.
+
+Change places that open-code NLA_POLICY_MIN_LEN() to
+use the macro instead, giving us flexibility in how we
+handle the details of the macro.
+
+Signed-off-by: Johannes Berg <johannes.berg@intel.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+[Jason: only picked the drivers/net/wireguard/* part]
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/netlink.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/netlink.c
++++ b/drivers/net/wireguard/netlink.c
+@@ -34,7 +34,7 @@ static const struct nla_policy peer_poli
+ [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
+ [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN),
+ [WGPEER_A_FLAGS] = { .type = NLA_U32 },
+- [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
++ [WGPEER_A_ENDPOINT] = NLA_POLICY_MIN_LEN(sizeof(struct sockaddr)),
+ [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
+ [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)),
+ [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
+@@ -45,7 +45,7 @@ static const struct nla_policy peer_poli
+
+ static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = {
+ [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 },
+- [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) },
++ [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)),
+ [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }
+ };
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 29 Jun 2020 19:06:21 -0600
-Subject: [PATCH] wireguard: queueing: make use of ip_tunnel_parse_protocol
-
-commit 1a574074ae7d1d745c16f7710655f38a53174c27 upstream.
-
-Now that wg_examine_packet_protocol has been added for general
-consumption as ip_tunnel_parse_protocol, it's possible to remove
-wg_examine_packet_protocol and simply use the new
-ip_tunnel_parse_protocol function directly.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/queueing.h | 19 ++-----------------
- drivers/net/wireguard/receive.c | 2 +-
- 2 files changed, 3 insertions(+), 18 deletions(-)
-
---- a/drivers/net/wireguard/queueing.h
-+++ b/drivers/net/wireguard/queueing.h
-@@ -11,6 +11,7 @@
- #include <linux/skbuff.h>
- #include <linux/ip.h>
- #include <linux/ipv6.h>
-+#include <net/ip_tunnels.h>
-
- struct wg_device;
- struct wg_peer;
-@@ -65,25 +66,9 @@ struct packet_cb {
- #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb))
- #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
-
--/* Returns either the correct skb->protocol value, or 0 if invalid. */
--static inline __be16 wg_examine_packet_protocol(struct sk_buff *skb)
--{
-- if (skb_network_header(skb) >= skb->head &&
-- (skb_network_header(skb) + sizeof(struct iphdr)) <=
-- skb_tail_pointer(skb) &&
-- ip_hdr(skb)->version == 4)
-- return htons(ETH_P_IP);
-- if (skb_network_header(skb) >= skb->head &&
-- (skb_network_header(skb) + sizeof(struct ipv6hdr)) <=
-- skb_tail_pointer(skb) &&
-- ipv6_hdr(skb)->version == 6)
-- return htons(ETH_P_IPV6);
-- return 0;
--}
--
- static inline bool wg_check_packet_protocol(struct sk_buff *skb)
- {
-- __be16 real_protocol = wg_examine_packet_protocol(skb);
-+ __be16 real_protocol = ip_tunnel_parse_protocol(skb);
- return real_protocol && skb->protocol == real_protocol;
- }
-
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -387,7 +387,7 @@ static void wg_packet_consume_data_done(
- */
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->csum_level = ~0; /* All levels */
-- skb->protocol = wg_examine_packet_protocol(skb);
-+ skb->protocol = ip_tunnel_parse_protocol(skb);
- if (skb->protocol == htons(ETH_P_IP)) {
- len = ntohs(ip_hdr(skb)->tot_len);
- if (unlikely(len < sizeof(struct iphdr)))
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Johannes Berg <johannes.berg@intel.com>
-Date: Tue, 18 Aug 2020 10:17:31 +0200
-Subject: [PATCH] netlink: consistently use NLA_POLICY_EXACT_LEN()
-
-commit 8140860c817f3e9f78bcd1e420b9777ddcbaa629 upstream.
-
-Change places that open-code NLA_POLICY_EXACT_LEN() to
-use the macro instead, giving us flexibility in how we
-handle the details of the macro.
-
-Signed-off-by: Johannes Berg <johannes.berg@intel.com>
-Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-[Jason: only picked the drivers/net/wireguard/* part]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/netlink.c | 10 +++++-----
- 1 file changed, 5 insertions(+), 5 deletions(-)
-
---- a/drivers/net/wireguard/netlink.c
-+++ b/drivers/net/wireguard/netlink.c
-@@ -22,8 +22,8 @@ static struct genl_family genl_family;
- static const struct nla_policy device_policy[WGDEVICE_A_MAX + 1] = {
- [WGDEVICE_A_IFINDEX] = { .type = NLA_U32 },
- [WGDEVICE_A_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-- [WGDEVICE_A_PRIVATE_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-- [WGDEVICE_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-+ [WGDEVICE_A_PRIVATE_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
-+ [WGDEVICE_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
- [WGDEVICE_A_FLAGS] = { .type = NLA_U32 },
- [WGDEVICE_A_LISTEN_PORT] = { .type = NLA_U16 },
- [WGDEVICE_A_FWMARK] = { .type = NLA_U32 },
-@@ -31,12 +31,12 @@ static const struct nla_policy device_po
- };
-
- static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = {
-- [WGPEER_A_PUBLIC_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_PUBLIC_KEY_LEN },
-- [WGPEER_A_PRESHARED_KEY] = { .type = NLA_EXACT_LEN, .len = NOISE_SYMMETRIC_KEY_LEN },
-+ [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
-+ [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN),
- [WGPEER_A_FLAGS] = { .type = NLA_U32 },
- [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
- [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
-- [WGPEER_A_LAST_HANDSHAKE_TIME] = { .type = NLA_EXACT_LEN, .len = sizeof(struct __kernel_timespec) },
-+ [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)),
- [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
- [WGPEER_A_TX_BYTES] = { .type = NLA_U64 },
- [WGPEER_A_ALLOWEDIPS] = { .type = NLA_NESTED },
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 9 Sep 2020 13:58:14 +0200
+Subject: [PATCH] wireguard: noise: take lock when removing handshake entry
+ from table
+
+commit 9179ba31367bcf481c3c79b5f028c94faad9f30a upstream.
+
+Eric reported that syzkaller found a race of this variety:
+
+CPU 1 CPU 2
+-------------------------------------------|---------------------------------------
+wg_index_hashtable_replace(old, ...) |
+ if (hlist_unhashed(&old->index_hash)) |
+ | wg_index_hashtable_remove(old)
+ | hlist_del_init_rcu(&old->index_hash)
+ | old->index_hash.pprev = NULL
+ hlist_replace_rcu(&old->index_hash, ...) |
+ *old->index_hash.pprev |
+
+Syzbot wasn't actually able to reproduce this more than once or create a
+reproducer, because the race window between checking "hlist_unhashed" and
+calling "hlist_replace_rcu" is just so small. Adding an mdelay(5) or
+similar there helps make this demonstrable using this simple script:
+
+ #!/bin/bash
+ set -ex
+ trap 'kill $pid1; kill $pid2; ip link del wg0; ip link del wg1' EXIT
+ ip link add wg0 type wireguard
+ ip link add wg1 type wireguard
+ wg set wg0 private-key <(wg genkey) listen-port 9999
+ wg set wg1 private-key <(wg genkey) peer $(wg show wg0 public-key) endpoint 127.0.0.1:9999 persistent-keepalive 1
+ wg set wg0 peer $(wg show wg1 public-key)
+ ip link set wg0 up
+ yes link set wg1 up | ip -force -batch - &
+ pid1=$!
+ yes link set wg1 down | ip -force -batch - &
+ pid2=$!
+ wait
+
+The fundumental underlying problem is that we permit calls to wg_index_
+hashtable_remove(handshake.entry) without requiring the caller to take
+the handshake mutex that is intended to protect members of handshake
+during mutations. This is consistently the case with calls to wg_index_
+hashtable_insert(handshake.entry) and wg_index_hashtable_replace(
+handshake.entry), but it's missing from a pertinent callsite of wg_
+index_hashtable_remove(handshake.entry). So, this patch makes sure that
+mutex is taken.
+
+The original code was a little bit funky though, in the form of:
+
+ remove(handshake.entry)
+ lock(), memzero(handshake.some_members), unlock()
+ remove(handshake.entry)
+
+The original intention of that double removal pattern outside the lock
+appears to be some attempt to prevent insertions that might happen while
+locks are dropped during expensive crypto operations, but actually, all
+callers of wg_index_hashtable_insert(handshake.entry) take the write
+lock and then explicitly check handshake.state, as they should, which
+the aforementioned memzero clears, which means an insertion should
+already be impossible. And regardless, the original intention was
+necessarily racy, since it wasn't guaranteed that something else would
+run after the unlock() instead of after the remove(). So, from a
+soundness perspective, it seems positive to remove what looks like a
+hack at best.
+
+The crash from both syzbot and from the script above is as follows:
+
+ general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN
+ KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
+ CPU: 0 PID: 7395 Comm: kworker/0:3 Not tainted 5.9.0-rc4-syzkaller #0
+ Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
+ Workqueue: wg-kex-wg1 wg_packet_handshake_receive_worker
+ RIP: 0010:hlist_replace_rcu include/linux/rculist.h:505 [inline]
+ RIP: 0010:wg_index_hashtable_replace+0x176/0x330 drivers/net/wireguard/peerlookup.c:174
+ Code: 00 fc ff df 48 89 f9 48 c1 e9 03 80 3c 01 00 0f 85 44 01 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 10 48 89 c6 48 c1 ee 03 <80> 3c 0e 00 0f 85 06 01 00 00 48 85 d2 4c 89 28 74 47 e8 a3 4f b5
+ RSP: 0018:ffffc90006a97bf8 EFLAGS: 00010246
+ RAX: 0000000000000000 RBX: ffff888050ffc4f8 RCX: dffffc0000000000
+ RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88808e04e010
+ RBP: ffff88808e04e000 R08: 0000000000000001 R09: ffff8880543d0000
+ R10: ffffed100a87a000 R11: 000000000000016e R12: ffff8880543d0000
+ R13: ffff88808e04e008 R14: ffff888050ffc508 R15: ffff888050ffc500
+ FS: 0000000000000000(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
+ CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+ CR2: 00000000f5505db0 CR3: 0000000097cf7000 CR4: 00000000001526f0
+ DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
+ DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
+ Call Trace:
+ wg_noise_handshake_begin_session+0x752/0xc9a drivers/net/wireguard/noise.c:820
+ wg_receive_handshake_packet drivers/net/wireguard/receive.c:183 [inline]
+ wg_packet_handshake_receive_worker+0x33b/0x730 drivers/net/wireguard/receive.c:220
+ process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
+ worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
+ kthread+0x3b5/0x4a0 kernel/kthread.c:292
+ ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
+
+Reported-by: syzbot <syzkaller@googlegroups.com>
+Reported-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/noise.c | 5 +----
+ 1 file changed, 1 insertion(+), 4 deletions(-)
+
+--- a/drivers/net/wireguard/noise.c
++++ b/drivers/net/wireguard/noise.c
+@@ -87,15 +87,12 @@ static void handshake_zero(struct noise_
+
+ void wg_noise_handshake_clear(struct noise_handshake *handshake)
+ {
++ down_write(&handshake->lock);
+ wg_index_hashtable_remove(
+ handshake->entry.peer->device->index_hashtable,
+ &handshake->entry);
+- down_write(&handshake->lock);
+ handshake_zero(handshake);
+ up_write(&handshake->lock);
+- wg_index_hashtable_remove(
+- handshake->entry.peer->device->index_hashtable,
+- &handshake->entry);
+ }
+
+ static struct noise_keypair *keypair_create(struct wg_peer *peer)
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Johannes Berg <johannes.berg@intel.com>
-Date: Tue, 18 Aug 2020 10:17:32 +0200
-Subject: [PATCH] netlink: consistently use NLA_POLICY_MIN_LEN()
-
-commit bc0435855041d7fff0b83dd992fc4be34aa11afb upstream.
-
-Change places that open-code NLA_POLICY_MIN_LEN() to
-use the macro instead, giving us flexibility in how we
-handle the details of the macro.
-
-Signed-off-by: Johannes Berg <johannes.berg@intel.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-[Jason: only picked the drivers/net/wireguard/* part]
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/netlink.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/netlink.c
-+++ b/drivers/net/wireguard/netlink.c
-@@ -34,7 +34,7 @@ static const struct nla_policy peer_poli
- [WGPEER_A_PUBLIC_KEY] = NLA_POLICY_EXACT_LEN(NOISE_PUBLIC_KEY_LEN),
- [WGPEER_A_PRESHARED_KEY] = NLA_POLICY_EXACT_LEN(NOISE_SYMMETRIC_KEY_LEN),
- [WGPEER_A_FLAGS] = { .type = NLA_U32 },
-- [WGPEER_A_ENDPOINT] = { .type = NLA_MIN_LEN, .len = sizeof(struct sockaddr) },
-+ [WGPEER_A_ENDPOINT] = NLA_POLICY_MIN_LEN(sizeof(struct sockaddr)),
- [WGPEER_A_PERSISTENT_KEEPALIVE_INTERVAL] = { .type = NLA_U16 },
- [WGPEER_A_LAST_HANDSHAKE_TIME] = NLA_POLICY_EXACT_LEN(sizeof(struct __kernel_timespec)),
- [WGPEER_A_RX_BYTES] = { .type = NLA_U64 },
-@@ -45,7 +45,7 @@ static const struct nla_policy peer_poli
-
- static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = {
- [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 },
-- [WGALLOWEDIP_A_IPADDR] = { .type = NLA_MIN_LEN, .len = sizeof(struct in_addr) },
-+ [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)),
- [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }
- };
-
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Wed, 9 Sep 2020 13:58:15 +0200
+Subject: [PATCH] wireguard: peerlookup: take lock before checking hash in
+ replace operation
+
+commit 6147f7b1e90ff09bd52afc8b9206a7fcd133daf7 upstream.
+
+Eric's suggested fix for the previous commit's mentioned race condition
+was to simply take the table->lock in wg_index_hashtable_replace(). The
+table->lock of the hash table is supposed to protect the bucket heads,
+not the entires, but actually, since all the mutator functions are
+already taking it, it makes sense to take it too for the test to
+hlist_unhashed, as a defense in depth measure, so that it no longer
+races with deletions, regardless of what other locks are protecting
+individual entries. This is sensible from a performance perspective
+because, as Eric pointed out, the case of being unhashed is already the
+unlikely case, so this won't add common contention. And comparing
+instructions, this basically doesn't make much of a difference other
+than pushing and popping %r13, used by the new `bool ret`. More
+generally, I like the idea of locking consistency across table mutator
+functions, and this might let me rest slightly easier at night.
+
+Suggested-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/peerlookup.c | 11 ++++++++---
+ 1 file changed, 8 insertions(+), 3 deletions(-)
+
+--- a/drivers/net/wireguard/peerlookup.c
++++ b/drivers/net/wireguard/peerlookup.c
+@@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct i
+ struct index_hashtable_entry *old,
+ struct index_hashtable_entry *new)
+ {
+- if (unlikely(hlist_unhashed(&old->index_hash)))
+- return false;
++ bool ret;
++
+ spin_lock_bh(&table->lock);
++ ret = !hlist_unhashed(&old->index_hash);
++ if (unlikely(!ret))
++ goto out;
++
+ new->index = old->index;
+ hlist_replace_rcu(&old->index_hash, &new->index_hash);
+
+@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct i
+ * simply gets dropped, which isn't terrible.
+ */
+ INIT_HLIST_NODE(&old->index_hash);
++out:
+ spin_unlock_bh(&table->lock);
+- return true;
++ return ret;
+ }
+
+ void wg_index_hashtable_remove(struct index_hashtable *table,
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 9 Sep 2020 13:58:14 +0200
-Subject: [PATCH] wireguard: noise: take lock when removing handshake entry
- from table
-
-commit 9179ba31367bcf481c3c79b5f028c94faad9f30a upstream.
-
-Eric reported that syzkaller found a race of this variety:
-
-CPU 1 CPU 2
--------------------------------------------|---------------------------------------
-wg_index_hashtable_replace(old, ...) |
- if (hlist_unhashed(&old->index_hash)) |
- | wg_index_hashtable_remove(old)
- | hlist_del_init_rcu(&old->index_hash)
- | old->index_hash.pprev = NULL
- hlist_replace_rcu(&old->index_hash, ...) |
- *old->index_hash.pprev |
-
-Syzbot wasn't actually able to reproduce this more than once or create a
-reproducer, because the race window between checking "hlist_unhashed" and
-calling "hlist_replace_rcu" is just so small. Adding an mdelay(5) or
-similar there helps make this demonstrable using this simple script:
-
- #!/bin/bash
- set -ex
- trap 'kill $pid1; kill $pid2; ip link del wg0; ip link del wg1' EXIT
- ip link add wg0 type wireguard
- ip link add wg1 type wireguard
- wg set wg0 private-key <(wg genkey) listen-port 9999
- wg set wg1 private-key <(wg genkey) peer $(wg show wg0 public-key) endpoint 127.0.0.1:9999 persistent-keepalive 1
- wg set wg0 peer $(wg show wg1 public-key)
- ip link set wg0 up
- yes link set wg1 up | ip -force -batch - &
- pid1=$!
- yes link set wg1 down | ip -force -batch - &
- pid2=$!
- wait
-
-The fundumental underlying problem is that we permit calls to wg_index_
-hashtable_remove(handshake.entry) without requiring the caller to take
-the handshake mutex that is intended to protect members of handshake
-during mutations. This is consistently the case with calls to wg_index_
-hashtable_insert(handshake.entry) and wg_index_hashtable_replace(
-handshake.entry), but it's missing from a pertinent callsite of wg_
-index_hashtable_remove(handshake.entry). So, this patch makes sure that
-mutex is taken.
-
-The original code was a little bit funky though, in the form of:
-
- remove(handshake.entry)
- lock(), memzero(handshake.some_members), unlock()
- remove(handshake.entry)
-
-The original intention of that double removal pattern outside the lock
-appears to be some attempt to prevent insertions that might happen while
-locks are dropped during expensive crypto operations, but actually, all
-callers of wg_index_hashtable_insert(handshake.entry) take the write
-lock and then explicitly check handshake.state, as they should, which
-the aforementioned memzero clears, which means an insertion should
-already be impossible. And regardless, the original intention was
-necessarily racy, since it wasn't guaranteed that something else would
-run after the unlock() instead of after the remove(). So, from a
-soundness perspective, it seems positive to remove what looks like a
-hack at best.
-
-The crash from both syzbot and from the script above is as follows:
-
- general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN
- KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
- CPU: 0 PID: 7395 Comm: kworker/0:3 Not tainted 5.9.0-rc4-syzkaller #0
- Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
- Workqueue: wg-kex-wg1 wg_packet_handshake_receive_worker
- RIP: 0010:hlist_replace_rcu include/linux/rculist.h:505 [inline]
- RIP: 0010:wg_index_hashtable_replace+0x176/0x330 drivers/net/wireguard/peerlookup.c:174
- Code: 00 fc ff df 48 89 f9 48 c1 e9 03 80 3c 01 00 0f 85 44 01 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 10 48 89 c6 48 c1 ee 03 <80> 3c 0e 00 0f 85 06 01 00 00 48 85 d2 4c 89 28 74 47 e8 a3 4f b5
- RSP: 0018:ffffc90006a97bf8 EFLAGS: 00010246
- RAX: 0000000000000000 RBX: ffff888050ffc4f8 RCX: dffffc0000000000
- RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88808e04e010
- RBP: ffff88808e04e000 R08: 0000000000000001 R09: ffff8880543d0000
- R10: ffffed100a87a000 R11: 000000000000016e R12: ffff8880543d0000
- R13: ffff88808e04e008 R14: ffff888050ffc508 R15: ffff888050ffc500
- FS: 0000000000000000(0000) GS:ffff8880ae600000(0000) knlGS:0000000000000000
- CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
- CR2: 00000000f5505db0 CR3: 0000000097cf7000 CR4: 00000000001526f0
- DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
- DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
- Call Trace:
- wg_noise_handshake_begin_session+0x752/0xc9a drivers/net/wireguard/noise.c:820
- wg_receive_handshake_packet drivers/net/wireguard/receive.c:183 [inline]
- wg_packet_handshake_receive_worker+0x33b/0x730 drivers/net/wireguard/receive.c:220
- process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
- worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
- kthread+0x3b5/0x4a0 kernel/kthread.c:292
- ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
-
-Reported-by: syzbot <syzkaller@googlegroups.com>
-Reported-by: Eric Dumazet <edumazet@google.com>
-Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/noise.c | 5 +----
- 1 file changed, 1 insertion(+), 4 deletions(-)
-
---- a/drivers/net/wireguard/noise.c
-+++ b/drivers/net/wireguard/noise.c
-@@ -87,15 +87,12 @@ static void handshake_zero(struct noise_
-
- void wg_noise_handshake_clear(struct noise_handshake *handshake)
- {
-+ down_write(&handshake->lock);
- wg_index_hashtable_remove(
- handshake->entry.peer->device->index_hashtable,
- &handshake->entry);
-- down_write(&handshake->lock);
- handshake_zero(handshake);
- up_write(&handshake->lock);
-- wg_index_hashtable_remove(
-- handshake->entry.peer->device->index_hashtable,
-- &handshake->entry);
- }
-
- static struct noise_keypair *keypair_create(struct wg_peer *peer)
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Thu, 29 Oct 2020 03:56:05 +0100
+Subject: [PATCH] wireguard: selftests: check that route_me_harder packets use
+ the right sk
+
+commit af8afcf1fdd5f365f70e2386c2d8c7a1abd853d7 upstream.
+
+If netfilter changes the packet mark, the packet is rerouted. The
+ip_route_me_harder family of functions fails to use the right sk, opting
+to instead use skb->sk, resulting in a routing loop when used with
+tunnels. With the next change fixing this issue in netfilter, test for
+the relevant condition inside our test suite, since wireguard was where
+the bug was discovered.
+
+Reported-by: Chen Minqiang <ptpt52@gmail.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/netns.sh | 8 ++++++++
+ tools/testing/selftests/wireguard/qemu/kernel.config | 2 ++
+ 2 files changed, 10 insertions(+)
+
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -316,6 +316,14 @@ pp sleep 3
+ n2 ping -W 1 -c 1 192.168.241.1
+ n1 wg set wg0 peer "$pub2" persistent-keepalive 0
+
++# Test that sk_bound_dev_if works
++n1 ping -I wg0 -c 1 -W 1 192.168.241.2
++# What about when the mark changes and the packet must be rerouted?
++n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
++n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
++n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
++n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
++
+ # Test that onion routing works, even when it loops
+ n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
+ ip1 addr add 192.168.242.1/24 dev wg0
+--- a/tools/testing/selftests/wireguard/qemu/kernel.config
++++ b/tools/testing/selftests/wireguard/qemu/kernel.config
+@@ -18,10 +18,12 @@ CONFIG_NF_NAT=y
+ CONFIG_NETFILTER_XTABLES=y
+ CONFIG_NETFILTER_XT_NAT=y
+ CONFIG_NETFILTER_XT_MATCH_LENGTH=y
++CONFIG_NETFILTER_XT_MARK=y
+ CONFIG_NF_CONNTRACK_IPV4=y
+ CONFIG_NF_NAT_IPV4=y
+ CONFIG_IP_NF_IPTABLES=y
+ CONFIG_IP_NF_FILTER=y
++CONFIG_IP_NF_MANGLE=y
+ CONFIG_IP_NF_NAT=y
+ CONFIG_IP_ADVANCED_ROUTER=y
+ CONFIG_IP_MULTIPLE_TABLES=y
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Antonio Quartulli <a@unstable.cc>
+Date: Mon, 22 Feb 2021 17:25:43 +0100
+Subject: [PATCH] wireguard: avoid double unlikely() notation when using
+ IS_ERR()
+
+commit 30ac4e2f54ec067b7b9ca0db27e75681581378d6 upstream.
+
+The definition of IS_ERR() already applies the unlikely() notation
+when checking the error status of the passed pointer. For this
+reason there is no need to have the same notation outside of
+IS_ERR() itself.
+
+Clean up code by removing redundant notation.
+
+Signed-off-by: Antonio Quartulli <a@unstable.cc>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 2 +-
+ drivers/net/wireguard/socket.c | 4 ++--
+ 2 files changed, 3 insertions(+), 3 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -157,7 +157,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
+ } else {
+ struct sk_buff *segs = skb_gso_segment(skb, 0);
+
+- if (unlikely(IS_ERR(segs))) {
++ if (IS_ERR(segs)) {
+ ret = PTR_ERR(segs);
+ goto err_peer;
+ }
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -71,7 +71,7 @@ static int send4(struct wg_device *wg, s
+ ip_rt_put(rt);
+ rt = ip_route_output_flow(sock_net(sock), &fl, sock);
+ }
+- if (unlikely(IS_ERR(rt))) {
++ if (IS_ERR(rt)) {
+ ret = PTR_ERR(rt);
+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
+ wg->dev->name, &endpoint->addr, ret);
+@@ -138,7 +138,7 @@ static int send6(struct wg_device *wg, s
+ }
+ dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl,
+ NULL);
+- if (unlikely(IS_ERR(dst))) {
++ if (IS_ERR(dst)) {
+ ret = PTR_ERR(dst);
+ net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
+ wg->dev->name, &endpoint->addr, ret);
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Wed, 9 Sep 2020 13:58:15 +0200
-Subject: [PATCH] wireguard: peerlookup: take lock before checking hash in
- replace operation
-
-commit 6147f7b1e90ff09bd52afc8b9206a7fcd133daf7 upstream.
-
-Eric's suggested fix for the previous commit's mentioned race condition
-was to simply take the table->lock in wg_index_hashtable_replace(). The
-table->lock of the hash table is supposed to protect the bucket heads,
-not the entires, but actually, since all the mutator functions are
-already taking it, it makes sense to take it too for the test to
-hlist_unhashed, as a defense in depth measure, so that it no longer
-races with deletions, regardless of what other locks are protecting
-individual entries. This is sensible from a performance perspective
-because, as Eric pointed out, the case of being unhashed is already the
-unlikely case, so this won't add common contention. And comparing
-instructions, this basically doesn't make much of a difference other
-than pushing and popping %r13, used by the new `bool ret`. More
-generally, I like the idea of locking consistency across table mutator
-functions, and this might let me rest slightly easier at night.
-
-Suggested-by: Eric Dumazet <edumazet@google.com>
-Link: https://lore.kernel.org/wireguard/20200908145911.4090480-1-edumazet@google.com/
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/peerlookup.c | 11 ++++++++---
- 1 file changed, 8 insertions(+), 3 deletions(-)
-
---- a/drivers/net/wireguard/peerlookup.c
-+++ b/drivers/net/wireguard/peerlookup.c
-@@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct i
- struct index_hashtable_entry *old,
- struct index_hashtable_entry *new)
- {
-- if (unlikely(hlist_unhashed(&old->index_hash)))
-- return false;
-+ bool ret;
-+
- spin_lock_bh(&table->lock);
-+ ret = !hlist_unhashed(&old->index_hash);
-+ if (unlikely(!ret))
-+ goto out;
-+
- new->index = old->index;
- hlist_replace_rcu(&old->index_hash, &new->index_hash);
-
-@@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct i
- * simply gets dropped, which isn't terrible.
- */
- INIT_HLIST_NODE(&old->index_hash);
-+out:
- spin_unlock_bh(&table->lock);
-- return true;
-+ return ret;
- }
-
- void wg_index_hashtable_remove(struct index_hashtable *table,
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Thu, 29 Oct 2020 03:56:05 +0100
-Subject: [PATCH] wireguard: selftests: check that route_me_harder packets use
- the right sk
-
-commit af8afcf1fdd5f365f70e2386c2d8c7a1abd853d7 upstream.
-
-If netfilter changes the packet mark, the packet is rerouted. The
-ip_route_me_harder family of functions fails to use the right sk, opting
-to instead use skb->sk, resulting in a routing loop when used with
-tunnels. With the next change fixing this issue in netfilter, test for
-the relevant condition inside our test suite, since wireguard was where
-the bug was discovered.
-
-Reported-by: Chen Minqiang <ptpt52@gmail.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/netns.sh | 8 ++++++++
- tools/testing/selftests/wireguard/qemu/kernel.config | 2 ++
- 2 files changed, 10 insertions(+)
-
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -316,6 +316,14 @@ pp sleep 3
- n2 ping -W 1 -c 1 192.168.241.1
- n1 wg set wg0 peer "$pub2" persistent-keepalive 0
-
-+# Test that sk_bound_dev_if works
-+n1 ping -I wg0 -c 1 -W 1 192.168.241.2
-+# What about when the mark changes and the packet must be rerouted?
-+n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
-+n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
-+n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
-+n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
-+
- # Test that onion routing works, even when it loops
- n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
- ip1 addr add 192.168.242.1/24 dev wg0
---- a/tools/testing/selftests/wireguard/qemu/kernel.config
-+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
-@@ -18,10 +18,12 @@ CONFIG_NF_NAT=y
- CONFIG_NETFILTER_XTABLES=y
- CONFIG_NETFILTER_XT_NAT=y
- CONFIG_NETFILTER_XT_MATCH_LENGTH=y
-+CONFIG_NETFILTER_XT_MARK=y
- CONFIG_NF_CONNTRACK_IPV4=y
- CONFIG_NF_NAT_IPV4=y
- CONFIG_IP_NF_IPTABLES=y
- CONFIG_IP_NF_FILTER=y
-+CONFIG_IP_NF_MANGLE=y
- CONFIG_IP_NF_NAT=y
- CONFIG_IP_ADVANCED_ROUTER=y
- CONFIG_IP_MULTIPLE_TABLES=y
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Jann Horn <jannh@google.com>
+Date: Mon, 22 Feb 2021 17:25:44 +0100
+Subject: [PATCH] wireguard: socket: remove bogus __be32 annotation
+
+commit 7f57bd8dc22de35ddd895294aa554003e4f19a72 upstream.
+
+The endpoint->src_if4 has nothing to do with fixed-endian numbers; remove
+the bogus annotation.
+
+This was introduced in
+https://git.zx2c4.com/wireguard-monolithic-historical/commit?id=14e7d0a499a676ec55176c0de2f9fcbd34074a82
+in the historical WireGuard repo because the old code used to
+zero-initialize multiple members as follows:
+
+ endpoint->src4.s_addr = endpoint->src_if4 = fl.saddr = 0;
+
+Because fl.saddr is fixed-endian and an assignment returns a value with the
+type of its left operand, this meant that sparse detected an assignment
+between values of different endianness.
+
+Since then, this assignment was already split up into separate statements;
+just the cast survived.
+
+Signed-off-by: Jann Horn <jannh@google.com>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/socket.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/socket.c
++++ b/drivers/net/wireguard/socket.c
+@@ -53,7 +53,7 @@ static int send4(struct wg_device *wg, s
+ if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0,
+ fl.saddr, RT_SCOPE_HOST))) {
+ endpoint->src4.s_addr = 0;
+- *(__force __be32 *)&endpoint->src_if4 = 0;
++ endpoint->src_if4 = 0;
+ fl.saddr = 0;
+ if (cache)
+ dst_cache_reset(cache);
+@@ -63,7 +63,7 @@ static int send4(struct wg_device *wg, s
+ PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) &&
+ rt->dst.dev->ifindex != endpoint->src_if4)))) {
+ endpoint->src4.s_addr = 0;
+- *(__force __be32 *)&endpoint->src_if4 = 0;
++ endpoint->src_if4 = 0;
+ fl.saddr = 0;
+ if (cache)
+ dst_cache_reset(cache);
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Antonio Quartulli <a@unstable.cc>
-Date: Mon, 22 Feb 2021 17:25:43 +0100
-Subject: [PATCH] wireguard: avoid double unlikely() notation when using
- IS_ERR()
-
-commit 30ac4e2f54ec067b7b9ca0db27e75681581378d6 upstream.
-
-The definition of IS_ERR() already applies the unlikely() notation
-when checking the error status of the passed pointer. For this
-reason there is no need to have the same notation outside of
-IS_ERR() itself.
-
-Clean up code by removing redundant notation.
-
-Signed-off-by: Antonio Quartulli <a@unstable.cc>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 2 +-
- drivers/net/wireguard/socket.c | 4 ++--
- 2 files changed, 3 insertions(+), 3 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -157,7 +157,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
- } else {
- struct sk_buff *segs = skb_gso_segment(skb, 0);
-
-- if (unlikely(IS_ERR(segs))) {
-+ if (IS_ERR(segs)) {
- ret = PTR_ERR(segs);
- goto err_peer;
- }
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -71,7 +71,7 @@ static int send4(struct wg_device *wg, s
- ip_rt_put(rt);
- rt = ip_route_output_flow(sock_net(sock), &fl, sock);
- }
-- if (unlikely(IS_ERR(rt))) {
-+ if (IS_ERR(rt)) {
- ret = PTR_ERR(rt);
- net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
- wg->dev->name, &endpoint->addr, ret);
-@@ -138,7 +138,7 @@ static int send6(struct wg_device *wg, s
- }
- dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sock), sock, &fl,
- NULL);
-- if (unlikely(IS_ERR(dst))) {
-+ if (IS_ERR(dst)) {
- ret = PTR_ERR(dst);
- net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n",
- wg->dev->name, &endpoint->addr, ret);
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 22 Feb 2021 17:25:45 +0100
+Subject: [PATCH] wireguard: selftests: test multiple parallel streams
+
+commit d5a49aa6c3e264a93a7d08485d66e346be0969dd upstream.
+
+In order to test ndo_start_xmit being called in parallel, explicitly add
+separate tests, which should all run on different cores. This should
+help tease out bugs associated with queueing up packets from different
+cores in parallel. Currently, it hasn't found those types of bugs, but
+given future planned work, this is a useful regression to avoid.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ tools/testing/selftests/wireguard/netns.sh | 15 ++++++++++++++-
+ 1 file changed, 14 insertions(+), 1 deletion(-)
+
+--- a/tools/testing/selftests/wireguard/netns.sh
++++ b/tools/testing/selftests/wireguard/netns.sh
+@@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0
+ ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
+ ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
+ sleep() { read -t "$1" -N 1 || true; }
+-waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
++waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
+ waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; }
+ waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
+
+@@ -141,6 +141,19 @@ tests() {
+ n2 iperf3 -s -1 -B fd00::2 &
+ waitiperf $netns2 $!
+ n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
++
++ # TCP over IPv4, in parallel
++ for max in 4 5 50; do
++ local pids=( )
++ for ((i=0; i < max; ++i)) do
++ n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 &
++ pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i ))
++ done
++ for ((i=0; i < max; ++i)) do
++ n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 &
++ done
++ wait "${pids[@]}"
++ done
+ }
+
+ [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 22 Feb 2021 17:25:46 +0100
+Subject: [PATCH] wireguard: peer: put frequently used members above cache
+ lines
+
+commit 5a0598695634a6bb4126818902dd9140cd9df8b6 upstream.
+
+The is_dead boolean is checked for every single packet, while the
+internal_id member is used basically only for pr_debug messages. So it
+makes sense to hoist up is_dead into some space formerly unused by a
+struct hole, while demoting internal_api to below the lowest struct
+cache line.
+
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/peer.h | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/net/wireguard/peer.h
++++ b/drivers/net/wireguard/peer.h
+@@ -39,6 +39,7 @@ struct wg_peer {
+ struct crypt_queue tx_queue, rx_queue;
+ struct sk_buff_head staged_packet_queue;
+ int serial_work_cpu;
++ bool is_dead;
+ struct noise_keypairs keypairs;
+ struct endpoint endpoint;
+ struct dst_cache endpoint_cache;
+@@ -61,9 +62,8 @@ struct wg_peer {
+ struct rcu_head rcu;
+ struct list_head peer_list;
+ struct list_head allowedips_list;
+- u64 internal_id;
+ struct napi_struct napi;
+- bool is_dead;
++ u64 internal_id;
+ };
+
+ struct wg_peer *wg_peer_create(struct wg_device *wg,
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Jann Horn <jannh@google.com>
-Date: Mon, 22 Feb 2021 17:25:44 +0100
-Subject: [PATCH] wireguard: socket: remove bogus __be32 annotation
-
-commit 7f57bd8dc22de35ddd895294aa554003e4f19a72 upstream.
-
-The endpoint->src_if4 has nothing to do with fixed-endian numbers; remove
-the bogus annotation.
-
-This was introduced in
-https://git.zx2c4.com/wireguard-monolithic-historical/commit?id=14e7d0a499a676ec55176c0de2f9fcbd34074a82
-in the historical WireGuard repo because the old code used to
-zero-initialize multiple members as follows:
-
- endpoint->src4.s_addr = endpoint->src_if4 = fl.saddr = 0;
-
-Because fl.saddr is fixed-endian and an assignment returns a value with the
-type of its left operand, this meant that sparse detected an assignment
-between values of different endianness.
-
-Since then, this assignment was already split up into separate statements;
-just the cast survived.
-
-Signed-off-by: Jann Horn <jannh@google.com>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/socket.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/socket.c
-+++ b/drivers/net/wireguard/socket.c
-@@ -53,7 +53,7 @@ static int send4(struct wg_device *wg, s
- if (unlikely(!inet_confirm_addr(sock_net(sock), NULL, 0,
- fl.saddr, RT_SCOPE_HOST))) {
- endpoint->src4.s_addr = 0;
-- *(__force __be32 *)&endpoint->src_if4 = 0;
-+ endpoint->src_if4 = 0;
- fl.saddr = 0;
- if (cache)
- dst_cache_reset(cache);
-@@ -63,7 +63,7 @@ static int send4(struct wg_device *wg, s
- PTR_ERR(rt) == -EINVAL) || (!IS_ERR(rt) &&
- rt->dst.dev->ifindex != endpoint->src_if4)))) {
- endpoint->src4.s_addr = 0;
-- *(__force __be32 *)&endpoint->src_if4 = 0;
-+ endpoint->src_if4 = 0;
- fl.saddr = 0;
- if (cache)
- dst_cache_reset(cache);
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 22 Feb 2021 17:25:47 +0100
+Subject: [PATCH] wireguard: device: do not generate ICMP for non-IP packets
+
+commit 99fff5264e7ab06f45b0ad60243475be0a8d0559 upstream.
+
+If skb->protocol doesn't match the actual skb->data header, it's
+probably not a good idea to pass it off to icmp{,v6}_ndo_send, which is
+expecting to reply to a valid IP packet. So this commit has that early
+mismatch case jump to a later error label.
+
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 7 ++++---
+ 1 file changed, 4 insertions(+), 3 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -138,7 +138,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
+ dev->name, &ipv6_hdr(skb)->daddr);
+- goto err;
++ goto err_icmp;
+ }
+
+ family = READ_ONCE(peer->endpoint.addr.sa_family);
+@@ -201,12 +201,13 @@ static netdev_tx_t wg_xmit(struct sk_buf
+
+ err_peer:
+ wg_peer_put(peer);
+-err:
+- ++dev->stats.tx_errors;
++err_icmp:
+ if (skb->protocol == htons(ETH_P_IP))
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+ else if (skb->protocol == htons(ETH_P_IPV6))
+ icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
++err:
++ ++dev->stats.tx_errors;
+ kfree_skb(skb);
+ return ret;
+ }
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 22 Feb 2021 17:25:45 +0100
-Subject: [PATCH] wireguard: selftests: test multiple parallel streams
-
-commit d5a49aa6c3e264a93a7d08485d66e346be0969dd upstream.
-
-In order to test ndo_start_xmit being called in parallel, explicitly add
-separate tests, which should all run on different cores. This should
-help tease out bugs associated with queueing up packets from different
-cores in parallel. Currently, it hasn't found those types of bugs, but
-given future planned work, this is a useful regression to avoid.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- tools/testing/selftests/wireguard/netns.sh | 15 ++++++++++++++-
- 1 file changed, 14 insertions(+), 1 deletion(-)
-
---- a/tools/testing/selftests/wireguard/netns.sh
-+++ b/tools/testing/selftests/wireguard/netns.sh
-@@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0
- ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
- ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
- sleep() { read -t "$1" -N 1 || true; }
--waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
-+waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
- waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; }
- waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
-
-@@ -141,6 +141,19 @@ tests() {
- n2 iperf3 -s -1 -B fd00::2 &
- waitiperf $netns2 $!
- n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
-+
-+ # TCP over IPv4, in parallel
-+ for max in 4 5 50; do
-+ local pids=( )
-+ for ((i=0; i < max; ++i)) do
-+ n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 &
-+ pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i ))
-+ done
-+ for ((i=0; i < max; ++i)) do
-+ n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 &
-+ done
-+ wait "${pids[@]}"
-+ done
- }
-
- [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 22 Feb 2021 17:25:46 +0100
-Subject: [PATCH] wireguard: peer: put frequently used members above cache
- lines
-
-commit 5a0598695634a6bb4126818902dd9140cd9df8b6 upstream.
-
-The is_dead boolean is checked for every single packet, while the
-internal_id member is used basically only for pr_debug messages. So it
-makes sense to hoist up is_dead into some space formerly unused by a
-struct hole, while demoting internal_api to below the lowest struct
-cache line.
-
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/peer.h | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
---- a/drivers/net/wireguard/peer.h
-+++ b/drivers/net/wireguard/peer.h
-@@ -39,6 +39,7 @@ struct wg_peer {
- struct crypt_queue tx_queue, rx_queue;
- struct sk_buff_head staged_packet_queue;
- int serial_work_cpu;
-+ bool is_dead;
- struct noise_keypairs keypairs;
- struct endpoint endpoint;
- struct dst_cache endpoint_cache;
-@@ -61,9 +62,8 @@ struct wg_peer {
- struct rcu_head rcu;
- struct list_head peer_list;
- struct list_head allowedips_list;
-- u64 internal_id;
- struct napi_struct napi;
-- bool is_dead;
-+ u64 internal_id;
- };
-
- struct wg_peer *wg_peer_create(struct wg_device *wg,
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 22 Feb 2021 17:25:48 +0100
+Subject: [PATCH] wireguard: queueing: get rid of per-peer ring buffers
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+commit 8b5553ace83cced775eefd0f3f18b5c6214ccf7a upstream.
+
+Having two ring buffers per-peer means that every peer results in two
+massive ring allocations. On an 8-core x86_64 machine, this commit
+reduces the per-peer allocation from 18,688 bytes to 1,856 bytes, which
+is an 90% reduction. Ninety percent! With some single-machine
+deployments approaching 500,000 peers, we're talking about a reduction
+from 7 gigs of memory down to 700 megs of memory.
+
+In order to get rid of these per-peer allocations, this commit switches
+to using a list-based queueing approach. Currently GSO fragments are
+chained together using the skb->next pointer (the skb_list_* singly
+linked list approach), so we form the per-peer queue around the unused
+skb->prev pointer (which sort of makes sense because the links are
+pointing backwards). Use of skb_queue_* is not possible here, because
+that is based on doubly linked lists and spinlocks. Multiple cores can
+write into the queue at any given time, because its writes occur in the
+start_xmit path or in the udp_recv path. But reads happen in a single
+workqueue item per-peer, amounting to a multi-producer, single-consumer
+paradigm.
+
+The MPSC queue is implemented locklessly and never blocks. However, it
+is not linearizable (though it is serializable), with a very tight and
+unlikely race on writes, which, when hit (some tiny fraction of the
+0.15% of partial adds on a fully loaded 16-core x86_64 system), causes
+the queue reader to terminate early. However, because every packet sent
+queues up the same workqueue item after it is fully added, the worker
+resumes again, and stopping early isn't actually a problem, since at
+that point the packet wouldn't have yet been added to the encryption
+queue. These properties allow us to avoid disabling interrupts or
+spinning. The design is based on Dmitry Vyukov's algorithm [1].
+
+Performance-wise, ordinarily list-based queues aren't preferable to
+ringbuffers, because of cache misses when following pointers around.
+However, we *already* have to follow the adjacent pointers when working
+through fragments, so there shouldn't actually be any change there. A
+potential downside is that dequeueing is a bit more complicated, but the
+ptr_ring structure used prior had a spinlock when dequeueing, so all and
+all the difference appears to be a wash.
+
+Actually, from profiling, the biggest performance hit, by far, of this
+commit winds up being atomic_add_unless(count, 1, max) and atomic_
+dec(count), which account for the majority of CPU time, according to
+perf. In that sense, the previous ring buffer was superior in that it
+could check if it was full by head==tail, which the list-based approach
+cannot do.
+
+But all and all, this enables us to get massive memory savings, allowing
+WireGuard to scale for real world deployments, without taking much of a
+performance hit.
+
+[1] http://www.1024cores.net/home/lock-free-algorithms/queues/intrusive-mpsc-node-based-queue
+
+Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
+Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/wireguard/device.c | 12 ++---
+ drivers/net/wireguard/device.h | 15 +++---
+ drivers/net/wireguard/peer.c | 28 ++++-------
+ drivers/net/wireguard/peer.h | 4 +-
+ drivers/net/wireguard/queueing.c | 86 +++++++++++++++++++++++++-------
+ drivers/net/wireguard/queueing.h | 45 ++++++++++++-----
+ drivers/net/wireguard/receive.c | 16 +++---
+ drivers/net/wireguard/send.c | 31 ++++--------
+ 8 files changed, 144 insertions(+), 93 deletions(-)
+
+--- a/drivers/net/wireguard/device.c
++++ b/drivers/net/wireguard/device.c
+@@ -235,8 +235,8 @@ static void wg_destruct(struct net_devic
+ destroy_workqueue(wg->handshake_receive_wq);
+ destroy_workqueue(wg->handshake_send_wq);
+ destroy_workqueue(wg->packet_crypt_wq);
+- wg_packet_queue_free(&wg->decrypt_queue, true);
+- wg_packet_queue_free(&wg->encrypt_queue, true);
++ wg_packet_queue_free(&wg->decrypt_queue);
++ wg_packet_queue_free(&wg->encrypt_queue);
+ rcu_barrier(); /* Wait for all the peers to be actually freed. */
+ wg_ratelimiter_uninit();
+ memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
+@@ -338,12 +338,12 @@ static int wg_newlink(struct net *src_ne
+ goto err_destroy_handshake_send;
+
+ ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
+- true, MAX_QUEUED_PACKETS);
++ MAX_QUEUED_PACKETS);
+ if (ret < 0)
+ goto err_destroy_packet_crypt;
+
+ ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
+- true, MAX_QUEUED_PACKETS);
++ MAX_QUEUED_PACKETS);
+ if (ret < 0)
+ goto err_free_encrypt_queue;
+
+@@ -368,9 +368,9 @@ static int wg_newlink(struct net *src_ne
+ err_uninit_ratelimiter:
+ wg_ratelimiter_uninit();
+ err_free_decrypt_queue:
+- wg_packet_queue_free(&wg->decrypt_queue, true);
++ wg_packet_queue_free(&wg->decrypt_queue);
+ err_free_encrypt_queue:
+- wg_packet_queue_free(&wg->encrypt_queue, true);
++ wg_packet_queue_free(&wg->encrypt_queue);
+ err_destroy_packet_crypt:
+ destroy_workqueue(wg->packet_crypt_wq);
+ err_destroy_handshake_send:
+--- a/drivers/net/wireguard/device.h
++++ b/drivers/net/wireguard/device.h
+@@ -27,13 +27,14 @@ struct multicore_worker {
+
+ struct crypt_queue {
+ struct ptr_ring ring;
+- union {
+- struct {
+- struct multicore_worker __percpu *worker;
+- int last_cpu;
+- };
+- struct work_struct work;
+- };
++ struct multicore_worker __percpu *worker;
++ int last_cpu;
++};
++
++struct prev_queue {
++ struct sk_buff *head, *tail, *peeked;
++ struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff.
++ atomic_t count;
+ };
+
+ struct wg_device {
+--- a/drivers/net/wireguard/peer.c
++++ b/drivers/net/wireguard/peer.c
+@@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg
+ peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+ if (unlikely(!peer))
+ return ERR_PTR(ret);
+- peer->device = wg;
++ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
++ goto err;
+
++ peer->device = wg;
+ wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
+ public_key, preshared_key, peer);
+- if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+- goto err_1;
+- if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
+- MAX_QUEUED_PACKETS))
+- goto err_2;
+- if (wg_packet_queue_init(&peer->rx_queue, NULL, false,
+- MAX_QUEUED_PACKETS))
+- goto err_3;
+-
+ peer->internal_id = atomic64_inc_return(&peer_counter);
+ peer->serial_work_cpu = nr_cpumask_bits;
+ wg_cookie_init(&peer->latest_cookie);
+ wg_timers_init(peer);
+ wg_cookie_checker_precompute_peer_keys(peer);
+ spin_lock_init(&peer->keypairs.keypair_update_lock);
+- INIT_WORK(&peer->transmit_handshake_work,
+- wg_packet_handshake_send_worker);
++ INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker);
++ INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker);
++ wg_prev_queue_init(&peer->tx_queue);
++ wg_prev_queue_init(&peer->rx_queue);
+ rwlock_init(&peer->endpoint_lock);
+ kref_init(&peer->refcount);
+ skb_queue_head_init(&peer->staged_packet_queue);
+@@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg
+ pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id);
+ return peer;
+
+-err_3:
+- wg_packet_queue_free(&peer->tx_queue, false);
+-err_2:
+- dst_cache_destroy(&peer->endpoint_cache);
+-err_1:
++err:
+ kfree(peer);
+ return ERR_PTR(ret);
+ }
+@@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head
+ struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu);
+
+ dst_cache_destroy(&peer->endpoint_cache);
+- wg_packet_queue_free(&peer->rx_queue, false);
+- wg_packet_queue_free(&peer->tx_queue, false);
++ WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue));
+
+ /* The final zeroing takes care of clearing any remaining handshake key
+ * material and other potentially sensitive information.
+--- a/drivers/net/wireguard/peer.h
++++ b/drivers/net/wireguard/peer.h
+@@ -36,7 +36,7 @@ struct endpoint {
+
+ struct wg_peer {
+ struct wg_device *device;
+- struct crypt_queue tx_queue, rx_queue;
++ struct prev_queue tx_queue, rx_queue;
+ struct sk_buff_head staged_packet_queue;
+ int serial_work_cpu;
+ bool is_dead;
+@@ -46,7 +46,7 @@ struct wg_peer {
+ rwlock_t endpoint_lock;
+ struct noise_handshake handshake;
+ atomic64_t last_sent_handshake;
+- struct work_struct transmit_handshake_work, clear_peer_work;
++ struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work;
+ struct cookie latest_cookie;
+ struct hlist_node pubkey_hash;
+ u64 rx_bytes, tx_bytes;
+--- a/drivers/net/wireguard/queueing.c
++++ b/drivers/net/wireguard/queueing.c
+@@ -9,8 +9,7 @@ struct multicore_worker __percpu *
+ wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
+ {
+ int cpu;
+- struct multicore_worker __percpu *worker =
+- alloc_percpu(struct multicore_worker);
++ struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker);
+
+ if (!worker)
+ return NULL;
+@@ -23,7 +22,7 @@ wg_packet_percpu_multicore_worker_alloc(
+ }
+
+ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
+- bool multicore, unsigned int len)
++ unsigned int len)
+ {
+ int ret;
+
+@@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_qu
+ ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
+ if (ret)
+ return ret;
+- if (function) {
+- if (multicore) {
+- queue->worker = wg_packet_percpu_multicore_worker_alloc(
+- function, queue);
+- if (!queue->worker) {
+- ptr_ring_cleanup(&queue->ring, NULL);
+- return -ENOMEM;
+- }
+- } else {
+- INIT_WORK(&queue->work, function);
+- }
++ queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue);
++ if (!queue->worker) {
++ ptr_ring_cleanup(&queue->ring, NULL);
++ return -ENOMEM;
+ }
+ return 0;
+ }
+
+-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
++void wg_packet_queue_free(struct crypt_queue *queue)
+ {
+- if (multicore)
+- free_percpu(queue->worker);
++ free_percpu(queue->worker);
+ WARN_ON(!__ptr_ring_empty(&queue->ring));
+ ptr_ring_cleanup(&queue->ring, NULL);
+ }
++
++#define NEXT(skb) ((skb)->prev)
++#define STUB(queue) ((struct sk_buff *)&queue->empty)
++
++void wg_prev_queue_init(struct prev_queue *queue)
++{
++ NEXT(STUB(queue)) = NULL;
++ queue->head = queue->tail = STUB(queue);
++ queue->peeked = NULL;
++ atomic_set(&queue->count, 0);
++ BUILD_BUG_ON(
++ offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) -
++ offsetof(struct prev_queue, empty) ||
++ offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) -
++ offsetof(struct prev_queue, empty));
++}
++
++static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
++{
++ WRITE_ONCE(NEXT(skb), NULL);
++ WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb);
++}
++
++bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
++{
++ if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS))
++ return false;
++ __wg_prev_queue_enqueue(queue, skb);
++ return true;
++}
++
++struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue)
++{
++ struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail));
++
++ if (tail == STUB(queue)) {
++ if (!next)
++ return NULL;
++ queue->tail = next;
++ tail = next;
++ next = smp_load_acquire(&NEXT(next));
++ }
++ if (next) {
++ queue->tail = next;
++ atomic_dec(&queue->count);
++ return tail;
++ }
++ if (tail != READ_ONCE(queue->head))
++ return NULL;
++ __wg_prev_queue_enqueue(queue, STUB(queue));
++ next = smp_load_acquire(&NEXT(tail));
++ if (next) {
++ queue->tail = next;
++ atomic_dec(&queue->count);
++ return tail;
++ }
++ return NULL;
++}
++
++#undef NEXT
++#undef STUB
+--- a/drivers/net/wireguard/queueing.h
++++ b/drivers/net/wireguard/queueing.h
+@@ -17,12 +17,13 @@ struct wg_device;
+ struct wg_peer;
+ struct multicore_worker;
+ struct crypt_queue;
++struct prev_queue;
+ struct sk_buff;
+
+ /* queueing.c APIs: */
+ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
+- bool multicore, unsigned int len);
+-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore);
++ unsigned int len);
++void wg_packet_queue_free(struct crypt_queue *queue);
+ struct multicore_worker __percpu *
+ wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
+
+@@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online
+ return cpu;
+ }
+
++void wg_prev_queue_init(struct prev_queue *queue);
++
++/* Multi producer */
++bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb);
++
++/* Single consumer */
++struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue);
++
++/* Single consumer */
++static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue)
++{
++ if (queue->peeked)
++ return queue->peeked;
++ queue->peeked = wg_prev_queue_dequeue(queue);
++ return queue->peeked;
++}
++
++/* Single consumer */
++static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
++{
++ queue->peeked = NULL;
++}
++
+ static inline int wg_queue_enqueue_per_device_and_peer(
+- struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
++ struct crypt_queue *device_queue, struct prev_queue *peer_queue,
+ struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
+ {
+ int cpu;
+@@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_d
+ /* We first queue this up for the peer ingestion, but the consumer
+ * will wait for the state to change to CRYPTED or DEAD before.
+ */
+- if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
++ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb)))
+ return -ENOSPC;
++
+ /* Then we queue it up in the device queue, which consumes the
+ * packet as soon as it can.
+ */
+@@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_d
+ return 0;
+ }
+
+-static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
+- struct sk_buff *skb,
+- enum packet_state state)
++static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state)
+ {
+ /* We take a reference, because as soon as we call atomic_set, the
+ * peer can be freed from below us.
+@@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_
+ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
+
+ atomic_set_release(&PACKET_CB(skb)->state, state);
+- queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
+- peer->internal_id),
+- peer->device->packet_crypt_wq, &queue->work);
++ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id),
++ peer->device->packet_crypt_wq, &peer->transmit_packet_work);
+ wg_peer_put(peer);
+ }
+
+-static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb,
+- enum packet_state state)
++static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state)
+ {
+ /* We take a reference, because as soon as we call atomic_set, the
+ * peer can be freed from below us.
+--- a/drivers/net/wireguard/receive.c
++++ b/drivers/net/wireguard/receive.c
+@@ -444,7 +444,6 @@ packet_processed:
+ int wg_packet_rx_poll(struct napi_struct *napi, int budget)
+ {
+ struct wg_peer *peer = container_of(napi, struct wg_peer, napi);
+- struct crypt_queue *queue = &peer->rx_queue;
+ struct noise_keypair *keypair;
+ struct endpoint endpoint;
+ enum packet_state state;
+@@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct
+ if (unlikely(budget <= 0))
+ return 0;
+
+- while ((skb = __ptr_ring_peek(&queue->ring)) != NULL &&
++ while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL &&
+ (state = atomic_read_acquire(&PACKET_CB(skb)->state)) !=
+ PACKET_STATE_UNCRYPTED) {
+- __ptr_ring_discard_one(&queue->ring);
+- peer = PACKET_PEER(skb);
++ wg_prev_queue_drop_peeked(&peer->rx_queue);
+ keypair = PACKET_CB(skb)->keypair;
+ free = true;
+
+@@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct wor
+ enum packet_state state =
+ likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
+ PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
+- wg_queue_enqueue_per_peer_napi(skb, state);
++ wg_queue_enqueue_per_peer_rx(skb, state);
+ if (need_resched())
+ cond_resched();
+ }
+@@ -531,12 +529,10 @@ static void wg_packet_consume_data(struc
+ if (unlikely(READ_ONCE(peer->is_dead)))
+ goto err;
+
+- ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue,
+- &peer->rx_queue, skb,
+- wg->packet_crypt_wq,
+- &wg->decrypt_queue.last_cpu);
++ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb,
++ wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu);
+ if (unlikely(ret == -EPIPE))
+- wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD);
++ wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD);
+ if (likely(!ret || ret == -EPIPE)) {
+ rcu_read_unlock_bh();
+ return;
+--- a/drivers/net/wireguard/send.c
++++ b/drivers/net/wireguard/send.c
+@@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_
+ wg_packet_send_staged_packets(peer);
+ }
+
+-static void wg_packet_create_data_done(struct sk_buff *first,
+- struct wg_peer *peer)
++static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first)
+ {
+ struct sk_buff *skb, *next;
+ bool is_keepalive, data_sent = false;
+@@ -262,22 +261,19 @@ static void wg_packet_create_data_done(s
+
+ void wg_packet_tx_worker(struct work_struct *work)
+ {
+- struct crypt_queue *queue = container_of(work, struct crypt_queue,
+- work);
++ struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work);
+ struct noise_keypair *keypair;
+ enum packet_state state;
+ struct sk_buff *first;
+- struct wg_peer *peer;
+
+- while ((first = __ptr_ring_peek(&queue->ring)) != NULL &&
++ while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL &&
+ (state = atomic_read_acquire(&PACKET_CB(first)->state)) !=
+ PACKET_STATE_UNCRYPTED) {
+- __ptr_ring_discard_one(&queue->ring);
+- peer = PACKET_PEER(first);
++ wg_prev_queue_drop_peeked(&peer->tx_queue);
+ keypair = PACKET_CB(first)->keypair;
+
+ if (likely(state == PACKET_STATE_CRYPTED))
+- wg_packet_create_data_done(first, peer);
++ wg_packet_create_data_done(peer, first);
+ else
+ kfree_skb_list(first);
+
+@@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct wor
+ break;
+ }
+ }
+- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
+- state);
++ wg_queue_enqueue_per_peer_tx(first, state);
+ if (need_resched())
+ cond_resched();
+ }
+ }
+
+-static void wg_packet_create_data(struct sk_buff *first)
++static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first)
+ {
+- struct wg_peer *peer = PACKET_PEER(first);
+ struct wg_device *wg = peer->device;
+ int ret = -EINVAL;
+
+@@ -323,13 +317,10 @@ static void wg_packet_create_data(struct
+ if (unlikely(READ_ONCE(peer->is_dead)))
+ goto err;
+
+- ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue,
+- &peer->tx_queue, first,
+- wg->packet_crypt_wq,
+- &wg->encrypt_queue.last_cpu);
++ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first,
++ wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu);
+ if (unlikely(ret == -EPIPE))
+- wg_queue_enqueue_per_peer(&peer->tx_queue, first,
+- PACKET_STATE_DEAD);
++ wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD);
+ err:
+ rcu_read_unlock_bh();
+ if (likely(!ret || ret == -EPIPE))
+@@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struc
+ packets.prev->next = NULL;
+ wg_peer_get(keypair->entry.peer);
+ PACKET_CB(packets.next)->keypair = keypair;
+- wg_packet_create_data(packets.next);
++ wg_packet_create_data(peer, packets.next);
+ return;
+
+ out_invalid:
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 22 Feb 2021 17:25:47 +0100
-Subject: [PATCH] wireguard: device: do not generate ICMP for non-IP packets
-
-commit 99fff5264e7ab06f45b0ad60243475be0a8d0559 upstream.
-
-If skb->protocol doesn't match the actual skb->data header, it's
-probably not a good idea to pass it off to icmp{,v6}_ndo_send, which is
-expecting to reply to a valid IP packet. So this commit has that early
-mismatch case jump to a later error label.
-
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 7 ++++---
- 1 file changed, 4 insertions(+), 3 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -138,7 +138,7 @@ static netdev_tx_t wg_xmit(struct sk_buf
- else if (skb->protocol == htons(ETH_P_IPV6))
- net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n",
- dev->name, &ipv6_hdr(skb)->daddr);
-- goto err;
-+ goto err_icmp;
- }
-
- family = READ_ONCE(peer->endpoint.addr.sa_family);
-@@ -201,12 +201,13 @@ static netdev_tx_t wg_xmit(struct sk_buf
-
- err_peer:
- wg_peer_put(peer);
--err:
-- ++dev->stats.tx_errors;
-+err_icmp:
- if (skb->protocol == htons(ETH_P_IP))
- icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
- else if (skb->protocol == htons(ETH_P_IPV6))
- icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-+err:
-+ ++dev->stats.tx_errors;
- kfree_skb(skb);
- return ret;
- }
--- /dev/null
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Jason A. Donenfeld" <Jason@zx2c4.com>
+Date: Mon, 22 Feb 2021 17:25:49 +0100
+Subject: [PATCH] wireguard: kconfig: use arm chacha even with no neon
+
+commit bce2473927af8de12ad131a743f55d69d358c0b9 upstream.
+
+The condition here was incorrect: a non-neon fallback implementation is
+available on arm32 when NEON is not supported.
+
+Reported-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
+Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
+---
+ drivers/net/Kconfig | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/drivers/net/Kconfig
++++ b/drivers/net/Kconfig
+@@ -87,7 +87,7 @@ config WIREGUARD
+ select CRYPTO_CURVE25519_X86 if X86 && 64BIT
+ select ARM_CRYPTO if ARM
+ select ARM64_CRYPTO if ARM64
+- select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
++ select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON)
+ select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_POLY1305_ARM if ARM
+ select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 22 Feb 2021 17:25:48 +0100
-Subject: [PATCH] wireguard: queueing: get rid of per-peer ring buffers
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-commit 8b5553ace83cced775eefd0f3f18b5c6214ccf7a upstream.
-
-Having two ring buffers per-peer means that every peer results in two
-massive ring allocations. On an 8-core x86_64 machine, this commit
-reduces the per-peer allocation from 18,688 bytes to 1,856 bytes, which
-is an 90% reduction. Ninety percent! With some single-machine
-deployments approaching 500,000 peers, we're talking about a reduction
-from 7 gigs of memory down to 700 megs of memory.
-
-In order to get rid of these per-peer allocations, this commit switches
-to using a list-based queueing approach. Currently GSO fragments are
-chained together using the skb->next pointer (the skb_list_* singly
-linked list approach), so we form the per-peer queue around the unused
-skb->prev pointer (which sort of makes sense because the links are
-pointing backwards). Use of skb_queue_* is not possible here, because
-that is based on doubly linked lists and spinlocks. Multiple cores can
-write into the queue at any given time, because its writes occur in the
-start_xmit path or in the udp_recv path. But reads happen in a single
-workqueue item per-peer, amounting to a multi-producer, single-consumer
-paradigm.
-
-The MPSC queue is implemented locklessly and never blocks. However, it
-is not linearizable (though it is serializable), with a very tight and
-unlikely race on writes, which, when hit (some tiny fraction of the
-0.15% of partial adds on a fully loaded 16-core x86_64 system), causes
-the queue reader to terminate early. However, because every packet sent
-queues up the same workqueue item after it is fully added, the worker
-resumes again, and stopping early isn't actually a problem, since at
-that point the packet wouldn't have yet been added to the encryption
-queue. These properties allow us to avoid disabling interrupts or
-spinning. The design is based on Dmitry Vyukov's algorithm [1].
-
-Performance-wise, ordinarily list-based queues aren't preferable to
-ringbuffers, because of cache misses when following pointers around.
-However, we *already* have to follow the adjacent pointers when working
-through fragments, so there shouldn't actually be any change there. A
-potential downside is that dequeueing is a bit more complicated, but the
-ptr_ring structure used prior had a spinlock when dequeueing, so all and
-all the difference appears to be a wash.
-
-Actually, from profiling, the biggest performance hit, by far, of this
-commit winds up being atomic_add_unless(count, 1, max) and atomic_
-dec(count), which account for the majority of CPU time, according to
-perf. In that sense, the previous ring buffer was superior in that it
-could check if it was full by head==tail, which the list-based approach
-cannot do.
-
-But all and all, this enables us to get massive memory savings, allowing
-WireGuard to scale for real world deployments, without taking much of a
-performance hit.
-
-[1] http://www.1024cores.net/home/lock-free-algorithms/queues/intrusive-mpsc-node-based-queue
-
-Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
-Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/wireguard/device.c | 12 ++---
- drivers/net/wireguard/device.h | 15 +++---
- drivers/net/wireguard/peer.c | 28 ++++-------
- drivers/net/wireguard/peer.h | 4 +-
- drivers/net/wireguard/queueing.c | 86 +++++++++++++++++++++++++-------
- drivers/net/wireguard/queueing.h | 45 ++++++++++++-----
- drivers/net/wireguard/receive.c | 16 +++---
- drivers/net/wireguard/send.c | 31 ++++--------
- 8 files changed, 144 insertions(+), 93 deletions(-)
-
---- a/drivers/net/wireguard/device.c
-+++ b/drivers/net/wireguard/device.c
-@@ -235,8 +235,8 @@ static void wg_destruct(struct net_devic
- destroy_workqueue(wg->handshake_receive_wq);
- destroy_workqueue(wg->handshake_send_wq);
- destroy_workqueue(wg->packet_crypt_wq);
-- wg_packet_queue_free(&wg->decrypt_queue, true);
-- wg_packet_queue_free(&wg->encrypt_queue, true);
-+ wg_packet_queue_free(&wg->decrypt_queue);
-+ wg_packet_queue_free(&wg->encrypt_queue);
- rcu_barrier(); /* Wait for all the peers to be actually freed. */
- wg_ratelimiter_uninit();
- memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
-@@ -338,12 +338,12 @@ static int wg_newlink(struct net *src_ne
- goto err_destroy_handshake_send;
-
- ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
-- true, MAX_QUEUED_PACKETS);
-+ MAX_QUEUED_PACKETS);
- if (ret < 0)
- goto err_destroy_packet_crypt;
-
- ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
-- true, MAX_QUEUED_PACKETS);
-+ MAX_QUEUED_PACKETS);
- if (ret < 0)
- goto err_free_encrypt_queue;
-
-@@ -368,9 +368,9 @@ static int wg_newlink(struct net *src_ne
- err_uninit_ratelimiter:
- wg_ratelimiter_uninit();
- err_free_decrypt_queue:
-- wg_packet_queue_free(&wg->decrypt_queue, true);
-+ wg_packet_queue_free(&wg->decrypt_queue);
- err_free_encrypt_queue:
-- wg_packet_queue_free(&wg->encrypt_queue, true);
-+ wg_packet_queue_free(&wg->encrypt_queue);
- err_destroy_packet_crypt:
- destroy_workqueue(wg->packet_crypt_wq);
- err_destroy_handshake_send:
---- a/drivers/net/wireguard/device.h
-+++ b/drivers/net/wireguard/device.h
-@@ -27,13 +27,14 @@ struct multicore_worker {
-
- struct crypt_queue {
- struct ptr_ring ring;
-- union {
-- struct {
-- struct multicore_worker __percpu *worker;
-- int last_cpu;
-- };
-- struct work_struct work;
-- };
-+ struct multicore_worker __percpu *worker;
-+ int last_cpu;
-+};
-+
-+struct prev_queue {
-+ struct sk_buff *head, *tail, *peeked;
-+ struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff.
-+ atomic_t count;
- };
-
- struct wg_device {
---- a/drivers/net/wireguard/peer.c
-+++ b/drivers/net/wireguard/peer.c
-@@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg
- peer = kzalloc(sizeof(*peer), GFP_KERNEL);
- if (unlikely(!peer))
- return ERR_PTR(ret);
-- peer->device = wg;
-+ if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
-+ goto err;
-
-+ peer->device = wg;
- wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
- public_key, preshared_key, peer);
-- if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
-- goto err_1;
-- if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
-- MAX_QUEUED_PACKETS))
-- goto err_2;
-- if (wg_packet_queue_init(&peer->rx_queue, NULL, false,
-- MAX_QUEUED_PACKETS))
-- goto err_3;
--
- peer->internal_id = atomic64_inc_return(&peer_counter);
- peer->serial_work_cpu = nr_cpumask_bits;
- wg_cookie_init(&peer->latest_cookie);
- wg_timers_init(peer);
- wg_cookie_checker_precompute_peer_keys(peer);
- spin_lock_init(&peer->keypairs.keypair_update_lock);
-- INIT_WORK(&peer->transmit_handshake_work,
-- wg_packet_handshake_send_worker);
-+ INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker);
-+ INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker);
-+ wg_prev_queue_init(&peer->tx_queue);
-+ wg_prev_queue_init(&peer->rx_queue);
- rwlock_init(&peer->endpoint_lock);
- kref_init(&peer->refcount);
- skb_queue_head_init(&peer->staged_packet_queue);
-@@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg
- pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id);
- return peer;
-
--err_3:
-- wg_packet_queue_free(&peer->tx_queue, false);
--err_2:
-- dst_cache_destroy(&peer->endpoint_cache);
--err_1:
-+err:
- kfree(peer);
- return ERR_PTR(ret);
- }
-@@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head
- struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu);
-
- dst_cache_destroy(&peer->endpoint_cache);
-- wg_packet_queue_free(&peer->rx_queue, false);
-- wg_packet_queue_free(&peer->tx_queue, false);
-+ WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue));
-
- /* The final zeroing takes care of clearing any remaining handshake key
- * material and other potentially sensitive information.
---- a/drivers/net/wireguard/peer.h
-+++ b/drivers/net/wireguard/peer.h
-@@ -36,7 +36,7 @@ struct endpoint {
-
- struct wg_peer {
- struct wg_device *device;
-- struct crypt_queue tx_queue, rx_queue;
-+ struct prev_queue tx_queue, rx_queue;
- struct sk_buff_head staged_packet_queue;
- int serial_work_cpu;
- bool is_dead;
-@@ -46,7 +46,7 @@ struct wg_peer {
- rwlock_t endpoint_lock;
- struct noise_handshake handshake;
- atomic64_t last_sent_handshake;
-- struct work_struct transmit_handshake_work, clear_peer_work;
-+ struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work;
- struct cookie latest_cookie;
- struct hlist_node pubkey_hash;
- u64 rx_bytes, tx_bytes;
---- a/drivers/net/wireguard/queueing.c
-+++ b/drivers/net/wireguard/queueing.c
-@@ -9,8 +9,7 @@ struct multicore_worker __percpu *
- wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
- {
- int cpu;
-- struct multicore_worker __percpu *worker =
-- alloc_percpu(struct multicore_worker);
-+ struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker);
-
- if (!worker)
- return NULL;
-@@ -23,7 +22,7 @@ wg_packet_percpu_multicore_worker_alloc(
- }
-
- int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-- bool multicore, unsigned int len)
-+ unsigned int len)
- {
- int ret;
-
-@@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_qu
- ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
- if (ret)
- return ret;
-- if (function) {
-- if (multicore) {
-- queue->worker = wg_packet_percpu_multicore_worker_alloc(
-- function, queue);
-- if (!queue->worker) {
-- ptr_ring_cleanup(&queue->ring, NULL);
-- return -ENOMEM;
-- }
-- } else {
-- INIT_WORK(&queue->work, function);
-- }
-+ queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue);
-+ if (!queue->worker) {
-+ ptr_ring_cleanup(&queue->ring, NULL);
-+ return -ENOMEM;
- }
- return 0;
- }
-
--void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
-+void wg_packet_queue_free(struct crypt_queue *queue)
- {
-- if (multicore)
-- free_percpu(queue->worker);
-+ free_percpu(queue->worker);
- WARN_ON(!__ptr_ring_empty(&queue->ring));
- ptr_ring_cleanup(&queue->ring, NULL);
- }
-+
-+#define NEXT(skb) ((skb)->prev)
-+#define STUB(queue) ((struct sk_buff *)&queue->empty)
-+
-+void wg_prev_queue_init(struct prev_queue *queue)
-+{
-+ NEXT(STUB(queue)) = NULL;
-+ queue->head = queue->tail = STUB(queue);
-+ queue->peeked = NULL;
-+ atomic_set(&queue->count, 0);
-+ BUILD_BUG_ON(
-+ offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) -
-+ offsetof(struct prev_queue, empty) ||
-+ offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) -
-+ offsetof(struct prev_queue, empty));
-+}
-+
-+static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
-+{
-+ WRITE_ONCE(NEXT(skb), NULL);
-+ WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb);
-+}
-+
-+bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
-+{
-+ if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS))
-+ return false;
-+ __wg_prev_queue_enqueue(queue, skb);
-+ return true;
-+}
-+
-+struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue)
-+{
-+ struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail));
-+
-+ if (tail == STUB(queue)) {
-+ if (!next)
-+ return NULL;
-+ queue->tail = next;
-+ tail = next;
-+ next = smp_load_acquire(&NEXT(next));
-+ }
-+ if (next) {
-+ queue->tail = next;
-+ atomic_dec(&queue->count);
-+ return tail;
-+ }
-+ if (tail != READ_ONCE(queue->head))
-+ return NULL;
-+ __wg_prev_queue_enqueue(queue, STUB(queue));
-+ next = smp_load_acquire(&NEXT(tail));
-+ if (next) {
-+ queue->tail = next;
-+ atomic_dec(&queue->count);
-+ return tail;
-+ }
-+ return NULL;
-+}
-+
-+#undef NEXT
-+#undef STUB
---- a/drivers/net/wireguard/queueing.h
-+++ b/drivers/net/wireguard/queueing.h
-@@ -17,12 +17,13 @@ struct wg_device;
- struct wg_peer;
- struct multicore_worker;
- struct crypt_queue;
-+struct prev_queue;
- struct sk_buff;
-
- /* queueing.c APIs: */
- int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-- bool multicore, unsigned int len);
--void wg_packet_queue_free(struct crypt_queue *queue, bool multicore);
-+ unsigned int len);
-+void wg_packet_queue_free(struct crypt_queue *queue);
- struct multicore_worker __percpu *
- wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
-
-@@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online
- return cpu;
- }
-
-+void wg_prev_queue_init(struct prev_queue *queue);
-+
-+/* Multi producer */
-+bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb);
-+
-+/* Single consumer */
-+struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue);
-+
-+/* Single consumer */
-+static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue)
-+{
-+ if (queue->peeked)
-+ return queue->peeked;
-+ queue->peeked = wg_prev_queue_dequeue(queue);
-+ return queue->peeked;
-+}
-+
-+/* Single consumer */
-+static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
-+{
-+ queue->peeked = NULL;
-+}
-+
- static inline int wg_queue_enqueue_per_device_and_peer(
-- struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
-+ struct crypt_queue *device_queue, struct prev_queue *peer_queue,
- struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
- {
- int cpu;
-@@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_d
- /* We first queue this up for the peer ingestion, but the consumer
- * will wait for the state to change to CRYPTED or DEAD before.
- */
-- if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
-+ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb)))
- return -ENOSPC;
-+
- /* Then we queue it up in the device queue, which consumes the
- * packet as soon as it can.
- */
-@@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_d
- return 0;
- }
-
--static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
-- struct sk_buff *skb,
-- enum packet_state state)
-+static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state)
- {
- /* We take a reference, because as soon as we call atomic_set, the
- * peer can be freed from below us.
-@@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_
- struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
-
- atomic_set_release(&PACKET_CB(skb)->state, state);
-- queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
-- peer->internal_id),
-- peer->device->packet_crypt_wq, &queue->work);
-+ queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id),
-+ peer->device->packet_crypt_wq, &peer->transmit_packet_work);
- wg_peer_put(peer);
- }
-
--static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb,
-- enum packet_state state)
-+static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state)
- {
- /* We take a reference, because as soon as we call atomic_set, the
- * peer can be freed from below us.
---- a/drivers/net/wireguard/receive.c
-+++ b/drivers/net/wireguard/receive.c
-@@ -444,7 +444,6 @@ packet_processed:
- int wg_packet_rx_poll(struct napi_struct *napi, int budget)
- {
- struct wg_peer *peer = container_of(napi, struct wg_peer, napi);
-- struct crypt_queue *queue = &peer->rx_queue;
- struct noise_keypair *keypair;
- struct endpoint endpoint;
- enum packet_state state;
-@@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct
- if (unlikely(budget <= 0))
- return 0;
-
-- while ((skb = __ptr_ring_peek(&queue->ring)) != NULL &&
-+ while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL &&
- (state = atomic_read_acquire(&PACKET_CB(skb)->state)) !=
- PACKET_STATE_UNCRYPTED) {
-- __ptr_ring_discard_one(&queue->ring);
-- peer = PACKET_PEER(skb);
-+ wg_prev_queue_drop_peeked(&peer->rx_queue);
- keypair = PACKET_CB(skb)->keypair;
- free = true;
-
-@@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct wor
- enum packet_state state =
- likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
- PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
-- wg_queue_enqueue_per_peer_napi(skb, state);
-+ wg_queue_enqueue_per_peer_rx(skb, state);
- if (need_resched())
- cond_resched();
- }
-@@ -531,12 +529,10 @@ static void wg_packet_consume_data(struc
- if (unlikely(READ_ONCE(peer->is_dead)))
- goto err;
-
-- ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue,
-- &peer->rx_queue, skb,
-- wg->packet_crypt_wq,
-- &wg->decrypt_queue.last_cpu);
-+ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb,
-+ wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu);
- if (unlikely(ret == -EPIPE))
-- wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD);
-+ wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD);
- if (likely(!ret || ret == -EPIPE)) {
- rcu_read_unlock_bh();
- return;
---- a/drivers/net/wireguard/send.c
-+++ b/drivers/net/wireguard/send.c
-@@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_
- wg_packet_send_staged_packets(peer);
- }
-
--static void wg_packet_create_data_done(struct sk_buff *first,
-- struct wg_peer *peer)
-+static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first)
- {
- struct sk_buff *skb, *next;
- bool is_keepalive, data_sent = false;
-@@ -262,22 +261,19 @@ static void wg_packet_create_data_done(s
-
- void wg_packet_tx_worker(struct work_struct *work)
- {
-- struct crypt_queue *queue = container_of(work, struct crypt_queue,
-- work);
-+ struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work);
- struct noise_keypair *keypair;
- enum packet_state state;
- struct sk_buff *first;
-- struct wg_peer *peer;
-
-- while ((first = __ptr_ring_peek(&queue->ring)) != NULL &&
-+ while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL &&
- (state = atomic_read_acquire(&PACKET_CB(first)->state)) !=
- PACKET_STATE_UNCRYPTED) {
-- __ptr_ring_discard_one(&queue->ring);
-- peer = PACKET_PEER(first);
-+ wg_prev_queue_drop_peeked(&peer->tx_queue);
- keypair = PACKET_CB(first)->keypair;
-
- if (likely(state == PACKET_STATE_CRYPTED))
-- wg_packet_create_data_done(first, peer);
-+ wg_packet_create_data_done(peer, first);
- else
- kfree_skb_list(first);
-
-@@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct wor
- break;
- }
- }
-- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
-- state);
-+ wg_queue_enqueue_per_peer_tx(first, state);
- if (need_resched())
- cond_resched();
- }
- }
-
--static void wg_packet_create_data(struct sk_buff *first)
-+static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first)
- {
-- struct wg_peer *peer = PACKET_PEER(first);
- struct wg_device *wg = peer->device;
- int ret = -EINVAL;
-
-@@ -323,13 +317,10 @@ static void wg_packet_create_data(struct
- if (unlikely(READ_ONCE(peer->is_dead)))
- goto err;
-
-- ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue,
-- &peer->tx_queue, first,
-- wg->packet_crypt_wq,
-- &wg->encrypt_queue.last_cpu);
-+ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first,
-+ wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu);
- if (unlikely(ret == -EPIPE))
-- wg_queue_enqueue_per_peer(&peer->tx_queue, first,
-- PACKET_STATE_DEAD);
-+ wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD);
- err:
- rcu_read_unlock_bh();
- if (likely(!ret || ret == -EPIPE))
-@@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struc
- packets.prev->next = NULL;
- wg_peer_get(keypair->entry.peer);
- PACKET_CB(packets.next)->keypair = keypair;
-- wg_packet_create_data(packets.next);
-+ wg_packet_create_data(peer, packets.next);
- return;
-
- out_invalid:
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Jason A. Donenfeld" <Jason@zx2c4.com>
-Date: Mon, 22 Feb 2021 17:25:49 +0100
-Subject: [PATCH] wireguard: kconfig: use arm chacha even with no neon
-
-commit bce2473927af8de12ad131a743f55d69d358c0b9 upstream.
-
-The condition here was incorrect: a non-neon fallback implementation is
-available on arm32 when NEON is not supported.
-
-Reported-by: Ilya Lipnitskiy <ilya.lipnitskiy@gmail.com>
-Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
-Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
----
- drivers/net/Kconfig | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
---- a/drivers/net/Kconfig
-+++ b/drivers/net/Kconfig
-@@ -87,7 +87,7 @@ config WIREGUARD
- select CRYPTO_CURVE25519_X86 if X86 && 64BIT
- select ARM_CRYPTO if ARM
- select ARM64_CRYPTO if ARM64
-- select CRYPTO_CHACHA20_NEON if (ARM || ARM64) && KERNEL_MODE_NEON
-+ select CRYPTO_CHACHA20_NEON if ARM || (ARM64 && KERNEL_MODE_NEON)
- select CRYPTO_POLY1305_NEON if ARM64 && KERNEL_MODE_NEON
- select CRYPTO_POLY1305_ARM if ARM
- select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
+++ /dev/null
-From 6420a569504e212d618d4a4736e2c59ed80a8478 Mon Sep 17 00:00:00 2001
-From: Lech Perczak <lech.perczak@gmail.com>
-Date: Sun, 7 Feb 2021 01:54:43 +0100
-Subject: USB: serial: option: update interface mapping for ZTE P685M
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-This patch prepares for qmi_wwan driver support for the device.
-Previously "option" driver mapped itself to interfaces 0 and 3 (matching
-ff/ff/ff), while interface 3 is in fact a QMI port.
-Interfaces 1 and 2 (matching ff/00/00) expose AT commands,
-and weren't supported previously at all.
-Without this patch, a possible conflict would exist if device ID was
-added to qmi_wwan driver for interface 3.
-
-Update and simplify device ID to match interfaces 0-2 directly,
-to expose QCDM (0), PCUI (1), and modem (2) ports and avoid conflict
-with QMI (3), and ADB (4).
-
-The modem is used inside ZTE MF283+ router and carriers identify it as
-such.
-Interface mapping is:
-0: QCDM, 1: AT (PCUI), 2: AT (Modem), 3: QMI, 4: ADB
-
-T: Bus=02 Lev=02 Prnt=02 Port=05 Cnt=01 Dev#= 3 Spd=480 MxCh= 0
-D: Ver= 2.01 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
-P: Vendor=19d2 ProdID=1275 Rev=f0.00
-S: Manufacturer=ZTE,Incorporated
-S: Product=ZTE Technologies MSM
-S: SerialNumber=P685M510ZTED0000CP&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&0
-C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
-I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
-E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
-E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
-E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
-E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
-E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
-E: Ad=87(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
-E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
-E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
-
-Cc: Johan Hovold <johan@kernel.org>
-Cc: Bjørn Mork <bjorn@mork.no>
-Signed-off-by: Lech Perczak <lech.perczak@gmail.com>
-Link: https://lore.kernel.org/r/20210207005443.12936-1-lech.perczak@gmail.com
-Cc: stable@vger.kernel.org
-Signed-off-by: Johan Hovold <johan@kernel.org>
----
- drivers/usb/serial/option.c | 3 ++-
- 1 file changed, 2 insertions(+), 1 deletion(-)
-
---- a/drivers/usb/serial/option.c
-+++ b/drivers/usb/serial/option.c
-@@ -1569,7 +1569,8 @@ static const struct usb_device_id option
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1274, 0xff, 0xff, 0xff) },
-- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1275, 0xff, 0xff, 0xff) },
-+ { USB_DEVICE(ZTE_VENDOR_ID, 0x1275), /* ZTE P685M */
-+ .driver_info = RSVD(3) | RSVD(4) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1276, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1277, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1278, 0xff, 0xff, 0xff) },
config MODULES_TREE_LOOKUP
--- a/kernel/module.c
+++ b/kernel/module.c
-@@ -3125,9 +3125,11 @@ static int setup_load_info(struct load_i
+@@ -3142,9 +3142,11 @@ static int setup_load_info(struct load_i
static int check_modinfo(struct module *mod, struct load_info *info, int flags)
{
if (flags & MODULE_INIT_IGNORE_VERMAGIC)
modmagic = NULL;
-@@ -3148,6 +3150,7 @@ static int check_modinfo(struct module *
+@@ -3165,6 +3167,7 @@ static int check_modinfo(struct module *
mod->name);
add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
}
} \
\
/* __*init sections */ \
-@@ -898,6 +908,8 @@
+@@ -903,6 +913,8 @@
EXIT_TEXT \
EXIT_DATA \
EXIT_CALL \
/* Part specific fixup hooks. */
const struct spi_nor_fixups *fixups;
-@@ -1983,6 +1987,9 @@ static int spi_nor_clear_sr_bp(struct sp
+@@ -1985,6 +1989,9 @@ static int spi_nor_clear_sr_bp(struct sp
int ret;
u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
ret = read_sr(nor);
if (ret < 0) {
dev_err(nor->dev, "error while reading status register\n");
-@@ -2335,7 +2342,7 @@ static const struct flash_info spi_nor_i
+@@ -2337,7 +2344,7 @@ static const struct flash_info spi_nor_i
{ "mx25l1606e", INFO(0xc22015, 0, 64 * 1024, 32, SECT_4K) },
{ "mx25l3205d", INFO(0xc22016, 0, 64 * 1024, 64, SECT_4K) },
{ "mx25l3255e", INFO(0xc29e16, 0, 64 * 1024, 64, SECT_4K) },
{ "mx25u2033e", INFO(0xc22532, 0, 64 * 1024, 4, SECT_4K) },
{ "mx25u3235f", INFO(0xc22536, 0, 64 * 1024, 64,
SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
-@@ -5024,6 +5031,9 @@ int spi_nor_scan(struct spi_nor *nor, co
+@@ -5025,6 +5032,9 @@ int spi_nor_scan(struct spi_nor *nor, co
if (info->flags & USE_CLSR)
nor->flags |= SNOR_F_USE_CLSR;
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2704,7 +2704,7 @@ static int spi_nor_write(struct mtd_info
+@@ -2706,7 +2706,7 @@ static int spi_nor_write(struct mtd_info
write_enable(nor);
ret = spi_nor_write_data(nor, addr, page_remain, buf + i);
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -4883,6 +4883,7 @@ int spi_nor_scan(struct spi_nor *nor, co
+@@ -4884,6 +4884,7 @@ int spi_nor_scan(struct spi_nor *nor, co
*/
if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL ||
JEDEC_MFR(nor->info) == SNOR_MFR_INTEL ||
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -4397,6 +4397,7 @@ static void st_micron_set_default_init(s
+@@ -4398,6 +4398,7 @@ static void st_micron_set_default_init(s
static void winbond_set_default_init(struct spi_nor *nor)
{
nor->params.set_4byte = winbond_set_4byte;
}
-@@ -4885,6 +4886,7 @@ int spi_nor_scan(struct spi_nor *nor, co
+@@ -4886,6 +4887,7 @@ int spi_nor_scan(struct spi_nor *nor, co
JEDEC_MFR(nor->info) == SNOR_MFR_INTEL ||
JEDEC_MFR(nor->info) == SNOR_MFR_MACRONIX ||
JEDEC_MFR(nor->info) == SNOR_MFR_SST ||
depends on OF && (ARM || ARM64 || COMPILE_TEST)
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -4463,6 +4463,7 @@ static void spi_nor_info_init_params(str
+@@ -4464,6 +4464,7 @@ static void spi_nor_info_init_params(str
struct spi_nor_erase_map *map = ¶ms->erase_map;
const struct flash_info *info = nor->info;
struct device_node *np = spi_nor_get_flash_node(nor);
u8 i, erase_mask;
/* Initialize legacy flash parameters and settings. */
-@@ -4526,6 +4527,21 @@ static void spi_nor_info_init_params(str
+@@ -4527,6 +4528,21 @@ static void spi_nor_info_init_params(str
*/
erase_mask = 0;
i = 0;
if (info->flags & SECT_4K_PMC) {
erase_mask |= BIT(i);
spi_nor_set_erase_type(&map->erase_type[i], 4096u,
-@@ -4537,6 +4553,7 @@ static void spi_nor_info_init_params(str
+@@ -4538,6 +4554,7 @@ static void spi_nor_info_init_params(str
SPINOR_OP_BE_4K);
i++;
}
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2177,6 +2177,7 @@ static const struct flash_info spi_nor_i
+@@ -2179,6 +2179,7 @@ static const struct flash_info spi_nor_i
{ "en25q32b", INFO(0x1c3016, 0, 64 * 1024, 64, 0) },
{ "en25p64", INFO(0x1c2017, 0, 64 * 1024, 128, 0) },
{ "en25q64", INFO(0x1c3017, 0, 64 * 1024, 128, SECT_4K) },
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2504,6 +2504,9 @@ static const struct flash_info spi_nor_i
+@@ -2506,6 +2506,9 @@ static const struct flash_info spi_nor_i
/* XMC (Wuhan Xinxin Semiconductor Manufacturing Corp.) */
{ "XM25QH64A", INFO(0x207017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
{ "XM25QH128A", INFO(0x207018, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
static int macronix_set_4byte(struct spi_nor *nor, bool enable)
{
if (nor->spimem) {
-@@ -1259,6 +1275,10 @@ static int spi_nor_erase(struct mtd_info
+@@ -1261,6 +1277,10 @@ static int spi_nor_erase(struct mtd_info
if (ret)
return ret;
/* whole-chip erase? */
if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
unsigned long timeout;
-@@ -1315,6 +1335,7 @@ static int spi_nor_erase(struct mtd_info
+@@ -1317,6 +1337,7 @@ static int spi_nor_erase(struct mtd_info
write_disable(nor);
erase_err:
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
return ret;
-@@ -1621,7 +1642,9 @@ static int spi_nor_lock(struct mtd_info
+@@ -1623,7 +1644,9 @@ static int spi_nor_lock(struct mtd_info
if (ret)
return ret;
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_UNLOCK);
return ret;
-@@ -1636,7 +1659,9 @@ static int spi_nor_unlock(struct mtd_inf
+@@ -1638,7 +1661,9 @@ static int spi_nor_unlock(struct mtd_inf
if (ret)
return ret;
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK);
return ret;
-@@ -1651,7 +1676,9 @@ static int spi_nor_is_locked(struct mtd_
+@@ -1653,7 +1678,9 @@ static int spi_nor_is_locked(struct mtd_
if (ret)
return ret;
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK);
return ret;
-@@ -2557,6 +2584,10 @@ static int spi_nor_read(struct mtd_info
+@@ -2559,6 +2586,10 @@ static int spi_nor_read(struct mtd_info
if (ret)
return ret;
while (len) {
loff_t addr = from;
-@@ -2580,6 +2611,7 @@ static int spi_nor_read(struct mtd_info
+@@ -2582,6 +2613,7 @@ static int spi_nor_read(struct mtd_info
ret = 0;
read_err:
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_READ);
return ret;
}
-@@ -2597,6 +2629,10 @@ static int sst_write(struct mtd_info *mt
+@@ -2599,6 +2631,10 @@ static int sst_write(struct mtd_info *mt
if (ret)
return ret;
write_enable(nor);
nor->sst_write_second = false;
-@@ -2659,6 +2695,7 @@ static int sst_write(struct mtd_info *mt
+@@ -2661,6 +2697,7 @@ static int sst_write(struct mtd_info *mt
}
sst_write_err:
*retlen += actual;
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
return ret;
}
-@@ -2681,6 +2718,10 @@ static int spi_nor_write(struct mtd_info
+@@ -2683,6 +2720,10 @@ static int spi_nor_write(struct mtd_info
if (ret)
return ret;
for (i = 0; i < len; ) {
ssize_t written;
loff_t addr = to + i;
-@@ -2720,6 +2761,7 @@ static int spi_nor_write(struct mtd_info
+@@ -2722,6 +2763,7 @@ static int spi_nor_write(struct mtd_info
}
write_err:
spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
return ret;
}
-@@ -4725,9 +4767,13 @@ static int spi_nor_init(struct spi_nor *
+@@ -4726,9 +4768,13 @@ static int spi_nor_init(struct spi_nor *
* reboots (e.g., crashes). Warn the user (or hopefully, system
* designer) that this is bad.
*/
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2230,6 +2230,11 @@ static const struct flash_info spi_nor_i
+@@ -2232,6 +2232,11 @@ static const struct flash_info spi_nor_i
/* GigaDevice */
{
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2170,6 +2170,32 @@ static struct spi_nor_fixups gd25q256_fi
+@@ -2172,6 +2172,32 @@ static struct spi_nor_fixups gd25q256_fi
.default_init = gd25q256_default_init,
};
/* NOTE: double check command sets and memory organization when you add
* more nor chips. This current list focusses on newer chips, which
* have been converging on command sets which including JEDEC ID.
-@@ -2513,7 +2539,8 @@ static const struct flash_info spi_nor_i
+@@ -2515,7 +2541,8 @@ static const struct flash_info spi_nor_i
{ "w25q80", INFO(0xef5014, 0, 64 * 1024, 16, SECT_4K) },
{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16, SECT_4K) },
{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2351,6 +2351,8 @@ static const struct flash_info spi_nor_i
+@@ -2353,6 +2353,8 @@ static const struct flash_info spi_nor_i
{ "mx25u6435f", INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) },
{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
-@@ -40,6 +40,11 @@ static const u32 reg_offset_data_kpss[]
+@@ -39,6 +39,11 @@ static const u32 reg_offset_data_kpss[]
[WDT_BITE_TIME] = 0x14,
};
struct qcom_wdt {
struct watchdog_device wdd;
unsigned long rate;
-@@ -179,19 +184,29 @@ static void qcom_clk_disable_unprepare(v
+@@ -168,19 +173,29 @@ static void qcom_clk_disable_unprepare(v
clk_disable_unprepare(data);
}
dev_err(dev, "Unsupported QCOM WDT module\n");
return -ENODEV;
}
-@@ -247,7 +262,7 @@ static int qcom_wdt_probe(struct platfor
+@@ -236,7 +251,7 @@ static int qcom_wdt_probe(struct platfor
/* check if there is pretimeout support */
irq = platform_get_irq_optional(pdev, 0);
ret = devm_request_irq(dev, irq, qcom_wdt_isr,
IRQF_TRIGGER_RISING,
"wdt_bark", &wdt->wdd);
-@@ -267,7 +282,7 @@ static int qcom_wdt_probe(struct platfor
+@@ -256,7 +271,7 @@ static int qcom_wdt_probe(struct platfor
wdt->wdd.min_timeout = 1;
wdt->wdd.max_timeout = 0x10000000U / wdt->rate;
wdt->wdd.parent = dev;
if (readl(wdt_addr(wdt, WDT_STS)) & 1)
wdt->wdd.bootstatus = WDIOF_CARDRESET;
-@@ -311,9 +326,9 @@ static int __maybe_unused qcom_wdt_resum
+@@ -300,9 +315,9 @@ static int __maybe_unused qcom_wdt_resum
static SIMPLE_DEV_PM_OPS(qcom_wdt_pm_ops, qcom_wdt_suspend, qcom_wdt_resume);
static const struct of_device_id qcom_wdt_of_table[] = {
/* enable PCIe clocks and resets */
val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
-@@ -406,36 +393,6 @@ static int qcom_pcie_init_2_1_0(struct q
+@@ -408,36 +395,6 @@ static int qcom_pcie_init_2_1_0(struct q
val |= PHY_REFCLK_SSP_EN;
writel(val, pcie->parf + PCIE20_PARF_PHY_REFCLK);
/* wait for clock acquisition */
usleep_range(1000, 1500);
-@@ -448,15 +405,19 @@ static int qcom_pcie_init_2_1_0(struct q
+@@ -450,15 +407,19 @@ static int qcom_pcie_init_2_1_0(struct q
return 0;
writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) |
PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) |
PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34),
-@@ -1328,6 +1329,7 @@ err_pm_runtime_put:
+@@ -1330,6 +1331,7 @@ err_pm_runtime_put:
static const struct of_device_id qcom_pcie_match[] = {
{ .compatible = "qcom,pcie-apq8084", .data = &ops_1_0_0 },
{ .compatible = "qcom,pcie-ipq8064", .data = &ops_2_1_0 },
};
#define to_qcom_pcie(x) dev_get_drvdata((x)->dev)
-@@ -397,6 +401,11 @@ static int qcom_pcie_init_2_1_0(struct q
+@@ -399,6 +403,11 @@ static int qcom_pcie_init_2_1_0(struct q
/* wait for clock acquisition */
usleep_range(1000, 1500);
/* Set the Max TLP size to 2K, instead of using default of 4K */
writel(CFG_REMOTE_RD_REQ_BRIDGE_SIZE_2K,
-@@ -1261,6 +1270,10 @@ static int qcom_pcie_probe(struct platfo
+@@ -1263,6 +1272,10 @@ static int qcom_pcie_probe(struct platfo
goto err_pm_runtime_put;
}
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
-@@ -2377,6 +2377,12 @@ config MIPS_VPE_LOADER
+@@ -2378,6 +2378,12 @@ config MIPS_VPE_LOADER
Includes a loader for loading an elf relocatable object
onto another VPE and running it.
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
-@@ -342,6 +342,26 @@ config CRYPTO_ECHAINIV
+@@ -349,6 +349,26 @@ config CRYPTO_ECHAINIV
a sequence number xored with a salt. This is the default
algorithm for CBC.
config CRYPTO_CBC
--- a/crypto/Makefile
+++ b/crypto/Makefile
-@@ -143,6 +143,7 @@ obj-$(CONFIG_CRYPTO_CRC32) += crc32_gene
+@@ -144,6 +144,7 @@ obj-$(CONFIG_CRYPTO_CRC32) += crc32_gene
obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
obj-$(CONFIG_CRYPTO_LZO) += lzo.o lzo-rle.o
static int alg_test_aead(const struct alg_test_desc *desc, const char *driver,
u32 type, u32 mask)
{
-@@ -5012,6 +5241,15 @@ static const struct alg_test_desc alg_te
+@@ -5042,6 +5271,15 @@ static const struct alg_test_desc alg_te
.hash = __VECS(tgr192_tv_template)
}
}, {
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
-@@ -528,4 +528,8 @@ config NET_FAILOVER
+@@ -571,4 +571,8 @@ config NET_FAILOVER
a VM with direct attached VF by failing over to the paravirtual
datapath when the VF is unplugged.
endif # NETDEVICES
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
-@@ -79,3 +79,5 @@ thunderbolt-net-y += thunderbolt.o
+@@ -80,3 +80,5 @@ thunderbolt-net-y += thunderbolt.o
obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
obj-$(CONFIG_NETDEVSIM) += netdevsim/
obj-$(CONFIG_NET_FAILOVER) += net_failover.o
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2417,7 +2417,7 @@ static const struct flash_info spi_nor_i
+@@ -2419,7 +2419,7 @@ static const struct flash_info spi_nor_i
{ "s25fl512s", INFO6(0x010220, 0x4d0080, 256 * 1024, 256,
SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
SPI_NOR_HAS_LOCK | USE_CLSR) },
* All 3.1 IP version constants are greater than the 3.0 IP
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
-@@ -3543,6 +3543,10 @@ int dwc3_gadget_init(struct dwc3 *dwc)
+@@ -3558,6 +3558,10 @@ int dwc3_gadget_init(struct dwc3 *dwc)
dwc->gadget.sg_supported = true;
dwc->gadget.name = "dwc3-gadget";
dwc->gadget.lpm_capable = true;
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
-@@ -714,6 +714,17 @@
+@@ -716,6 +716,17 @@
status = "disabled";
};
when making changes to the MAC configuration. This means the
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
-@@ -3653,9 +3653,11 @@ static void mvneta_mac_link_down(struct
+@@ -3655,9 +3655,11 @@ static void mvneta_mac_link_down(struct
mvneta_set_eee(pp, false);
}
&pio {
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
-@@ -792,45 +792,41 @@
+@@ -794,45 +794,41 @@
#reset-cells = <1>;
};
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0 0 0 1 &pcie_intc0 0>,
<0 0 0 2 &pcie_intc0 1>,
-@@ -842,15 +838,39 @@
+@@ -844,15 +840,39 @@
#interrupt-cells = <1>;
};
};
interface-type = "ace";
reg = <0x5000 0x1000>;
};
-@@ -967,6 +967,8 @@
+@@ -969,6 +969,8 @@
power-domains = <&scpsys MT7622_POWER_DOMAIN_ETHSYS>;
mediatek,ethsys = <ðsys>;
mediatek,sgmiisys = <&sgmiisys>;
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
-@@ -803,6 +803,8 @@
+@@ -805,6 +805,8 @@
reg = <0 0x1a143000 0 0x1000>;
reg-names = "port0";
mediatek,pcie-cfg = <&pciecfg>;
#address-cells = <3>;
#size-cells = <2>;
interrupts = <GIC_SPI 228 IRQ_TYPE_LEVEL_LOW>;
-@@ -820,6 +822,7 @@
+@@ -822,6 +824,7 @@
bus-range = <0x00 0xff>;
ranges = <0x82000000 0 0x20000000 0x0 0x20000000 0 0x8000000>;
status = "disabled";
slot0: pcie@0,0 {
reg = <0x0000 0 0 0 0>;
-@@ -846,6 +849,8 @@
+@@ -848,6 +851,8 @@
reg = <0 0x1a145000 0 0x1000>;
reg-names = "port1";
mediatek,pcie-cfg = <&pciecfg>;
#address-cells = <3>;
#size-cells = <2>;
interrupts = <GIC_SPI 229 IRQ_TYPE_LEVEL_LOW>;
-@@ -864,6 +869,7 @@
+@@ -866,6 +871,7 @@
bus-range = <0x00 0xff>;
ranges = <0x82000000 0 0x28000000 0x0 0x28000000 0 0x8000000>;
status = "disabled";
slot1: pcie@1,0 {
reg = <0x0800 0 0 0 0>;
-@@ -923,6 +929,11 @@
+@@ -925,6 +931,11 @@
};
};
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2550,6 +2550,9 @@ static const struct flash_info spi_nor_i
+@@ -2552,6 +2552,9 @@ static const struct flash_info spi_nor_i
.fixups = &w25q256_fixups },
{ "w25q256jvm", INFO(0xef7019, 0, 64 * 1024, 512,
SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
MVNETA_RX_BUF_SIZE(pp->pkt_size));
mvneta_rxq_bm_disable(pp, rxq);
mvneta_rxq_fill(pp, rxq, rxq->size);
-@@ -4708,7 +4713,7 @@ static int mvneta_probe(struct platform_
+@@ -4715,7 +4720,7 @@ static int mvneta_probe(struct platform_
SET_NETDEV_DEV(dev, &pdev->dev);
pp->id = global_port_id++;
};
int err;
-@@ -3364,6 +3447,11 @@ static int mvneta_change_mtu(struct net_
+@@ -3366,6 +3449,11 @@ static int mvneta_change_mtu(struct net_
mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8);
}
dev->mtu = mtu;
if (!netif_running(dev)) {
-@@ -4029,6 +4117,47 @@ static int mvneta_ioctl(struct net_devic
+@@ -4036,6 +4124,47 @@ static int mvneta_ioctl(struct net_devic
return phylink_mii_ioctl(pp->phylink, ifr, cmd);
}
/* Ethtool methods */
/* Set link ksettings (phy address, speed) for ethtools */
-@@ -4425,6 +4554,7 @@ static const struct net_device_ops mvnet
+@@ -4432,6 +4561,7 @@ static const struct net_device_ops mvnet
.ndo_fix_features = mvneta_fix_features,
.ndo_get_stats64 = mvneta_get_stats64,
.ndo_do_ioctl = mvneta_ioctl,
};
static const struct ethtool_ops mvneta_eth_tool_ops = {
-@@ -4713,7 +4843,7 @@ static int mvneta_probe(struct platform_
+@@ -4720,7 +4850,7 @@ static int mvneta_probe(struct platform_
SET_NETDEV_DEV(dev, &pdev->dev);
pp->id = global_port_id++;
dma_free_coherent(pp->dev->dev.parent,
txq->size * MVNETA_DESC_ALIGNED_SIZE,
txq->descs, txq->descs_phys);
-@@ -3205,7 +3225,7 @@ static void mvneta_txq_sw_deinit(struct
+@@ -3207,7 +3227,7 @@ static void mvneta_txq_sw_deinit(struct
{
struct netdev_queue *nq = netdev_get_tx_queue(pp->dev, txq->id);
default:
bpf_warn_invalid_xdp_action(act);
/* fall through */
-@@ -4574,6 +4687,7 @@ static const struct net_device_ops mvnet
+@@ -4581,6 +4694,7 @@ static const struct net_device_ops mvnet
.ndo_get_stats64 = mvneta_get_stats64,
.ndo_do_ioctl = mvneta_ioctl,
.ndo_bpf = mvneta_xdp,
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
-@@ -4263,6 +4263,12 @@ static int mvneta_xdp_setup(struct net_d
+@@ -4270,6 +4270,12 @@ static int mvneta_xdp_setup(struct net_d
return -EOPNOTSUPP;
}
mvreg_write(pp, MVNETA_ACC_MODE, MVNETA_ACC_MODE_EXT1);
netdev_info(pp->dev, "fail to update MTU, fall back to software BM\n");
}
-@@ -4984,7 +4984,6 @@ static int mvneta_probe(struct platform_
+@@ -4991,7 +4991,6 @@ static int mvneta_probe(struct platform_
SET_NETDEV_DEV(dev, &pdev->dev);
pp->id = global_port_id++;
/* Obtain access to BM resources if enabled and already initialized */
bm_node = of_parse_phandle(dn, "buffer-manager", 0);
-@@ -5009,6 +5008,10 @@ static int mvneta_probe(struct platform_
+@@ -5016,6 +5015,10 @@ static int mvneta_probe(struct platform_
}
of_node_put(bm_node);
err = mvneta_init(&pdev->dev, pp);
if (err < 0)
goto err_netdev;
-@@ -5166,6 +5169,7 @@ static int mvneta_resume(struct device *
+@@ -5173,6 +5176,7 @@ static int mvneta_resume(struct device *
err = mvneta_bm_port_init(pdev, pp);
if (err < 0) {
dev_info(&pdev->dev, "use SW buffer management\n");
--- a/arch/arm/boot/dts/armada-388-helios4.dts
+++ b/arch/arm/boot/dts/armada-388-helios4.dts
-@@ -15,6 +15,13 @@
- model = "Helios4";
- compatible = "kobol,helios4", "marvell,armada388",
- "marvell,armada385", "marvell,armada380";
-+
-+ aliases {
+@@ -24,6 +24,10 @@
+ aliases {
+ /* So that mvebu u-boot can update the MAC addresses */
+ ethernet1 = ð0;
+ led-boot = &led_status;
+ led-failsafe = &led_status;
+ led-running = &led_status;
+ led-upgrade = &led_status;
-+ };
+ };
- memory {
- device_type = "memory";
-@@ -70,10 +77,9 @@
+ chosen {
+@@ -73,10 +77,9 @@
+ pinctrl-names = "default";
+ pinctrl-0 = <&helios_system_led_pins>;
- system-leds {
- compatible = "gpio-leds";
- status-led {
+ led_status: status-led {
label = "helios4:green:status";
---
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
-@@ -4684,6 +4684,14 @@ static int mvneta_ethtool_set_eee(struct
+@@ -4691,6 +4691,14 @@ static int mvneta_ethtool_set_eee(struct
return phylink_ethtool_set_eee(pp->phylink, eee);
}
static const struct net_device_ops mvneta_netdev_ops = {
.ndo_open = mvneta_open,
.ndo_stop = mvneta_stop,
-@@ -4694,6 +4702,7 @@ static const struct net_device_ops mvnet
+@@ -4701,6 +4709,7 @@ static const struct net_device_ops mvnet
.ndo_fix_features = mvneta_fix_features,
.ndo_get_stats64 = mvneta_get_stats64,
.ndo_do_ioctl = mvneta_ioctl,
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -4937,6 +4937,7 @@ int spi_nor_scan(struct spi_nor *nor, co
+@@ -4938,6 +4938,7 @@ int spi_nor_scan(struct spi_nor *nor, co
struct mtd_info *mtd = &nor->mtd;
struct device_node *np = spi_nor_get_flash_node(nor);
struct spi_nor_flash_parameter *params = &nor->params;
int ret;
int i;
-@@ -4999,7 +5000,12 @@ int spi_nor_scan(struct spi_nor *nor, co
+@@ -5000,7 +5001,12 @@ int spi_nor_scan(struct spi_nor *nor, co
/* Init flash parameters based on flash_info struct and SFDP */
spi_nor_init_params(nor);
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
-@@ -2303,6 +2303,11 @@ static const struct flash_info spi_nor_i
+@@ -2305,6 +2305,11 @@ static const struct flash_info spi_nor_i
SPI_NOR_4B_OPCODES | SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
.fixups = &gd25q256_fixups,
},
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
-@@ -126,6 +126,15 @@ config RDA_TIMER
+@@ -127,6 +127,15 @@ config RDA_TIMER
help
Enables the support for the RDA Micro timer driver.
config SUN4I_TIMER
bool "Sun4i timer driver" if COMPILE_TEST
depends on HAS_IOMEM
-@@ -695,5 +704,4 @@ config INGENIC_TIMER
+@@ -696,5 +705,4 @@ config INGENIC_TIMER
select IRQ_DOMAIN
help
Support for the timer/counter unit of the Ingenic JZ SoCs.
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi
-@@ -82,6 +82,28 @@
+@@ -81,6 +81,28 @@
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <40000000>;
projects / openwrt / openwrt.git / commitdiff