On Thu, Jun 13, 2024 at 8:00 PM D. Wythe <alibuda@xxxxxxxxxxxxxxxxx> wrote:
>
> From: "D. Wythe" <alibuda@xxxxxxxxxxxxxxxxx>
>
> This patch allows to create smc socket via AF_INET,
> similar to the following code,
>
> /* create v4 smc sock */
> v4 = socket(AF_INET, SOCK_STREAM, IPPROTO_SMC);
>
> /* create v6 smc sock */
> v6 = socket(AF_INET6, SOCK_STREAM, IPPROTO_SMC);
>
> There are several reasons why we believe it is appropriate here:
>
> 1. For smc sockets, it actually use IPv4 (AF-INET) or IPv6 (AF-INET6)
> address. There is no AF_SMC address at all.
>
> 2. Create smc socket in the AF_INET(6) path, which allows us to reuse
> the infrastructure of AF_INET(6) path, such as common ebpf hooks.
> Otherwise, smc have to implement it again in AF_SMC path.
>
> Signed-off-by: D. Wythe <alibuda@xxxxxxxxxxxxxxxxx>
> Reviewed-by: Wenjia Zhang <wenjia@xxxxxxxxxxxxx>
> Reviewed-by: Dust Li <dust.li@xxxxxxxxxxxxxxxxx>
> Tested-by: Niklas Schnelle <schnelle@xxxxxxxxxxxxx>
> Tested-by: Wenjia Zhang <wenjia@xxxxxxxxxxxxx>
> ---
> include/uapi/linux/in.h | 2 +
> net/smc/Makefile | 2 +-
> net/smc/af_smc.c | 16 ++++-
> net/smc/smc_inet.c | 159 ++++++++++++++++++++++++++++++++++++++++++++++++
> net/smc/smc_inet.h | 22 +++++++
> 5 files changed, 198 insertions(+), 3 deletions(-)
> create mode 100644 net/smc/smc_inet.c
> create mode 100644 net/smc/smc_inet.h
>
> diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
> index e682ab6..d358add 100644
> --- a/include/uapi/linux/in.h
> +++ b/include/uapi/linux/in.h
> @@ -81,6 +81,8 @@ enum {
> #define IPPROTO_ETHERNET IPPROTO_ETHERNET
> IPPROTO_RAW = 255, /* Raw IP packets */
> #define IPPROTO_RAW IPPROTO_RAW
> + IPPROTO_SMC = 256, /* Shared Memory Communications */
> +#define IPPROTO_SMC IPPROTO_SMC
> IPPROTO_MPTCP = 262, /* Multipath TCP connection */
> #define IPPROTO_MPTCP IPPROTO_MPTCP
> IPPROTO_MAX
> diff --git a/net/smc/Makefile b/net/smc/Makefile
> index 2c510d54..60f1c87 100644
> --- a/net/smc/Makefile
> +++ b/net/smc/Makefile
> @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o
> obj-$(CONFIG_SMC_DIAG) += smc_diag.o
> smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
> smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o
> -smc-y += smc_tracepoint.o
> +smc-y += smc_tracepoint.o smc_inet.o
> smc-$(CONFIG_SYSCTL) += smc_sysctl.o
> smc-$(CONFIG_SMC_LO) += smc_loopback.o
> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
> index 8e3ce76..435f38b 100644
> --- a/net/smc/af_smc.c
> +++ b/net/smc/af_smc.c
> @@ -54,6 +54,7 @@
> #include "smc_tracepoint.h"
> #include "smc_sysctl.h"
> #include "smc_loopback.h"
> +#include "smc_inet.h"
>
> static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group
> * creation on server
> @@ -3593,10 +3594,15 @@ static int __init smc_init(void)
> pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc);
> goto out_lo;
> }
> -
> + rc = smc_inet_init();
> + if (rc) {
> + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc);
> + goto out_ulp;
> + }
> static_branch_enable(&tcp_have_smc);
> return 0;
> -
> +out_ulp:
> + tcp_unregister_ulp(&smc_ulp_ops);
> out_lo:
> smc_loopback_exit();
> out_ib:
> @@ -3633,6 +3639,7 @@ static int __init smc_init(void)
> static void __exit smc_exit(void)
> {
> static_branch_disable(&tcp_have_smc);
> + smc_inet_exit();
> tcp_unregister_ulp(&smc_ulp_ops);
> sock_unregister(PF_SMC);
> smc_core_exit();
> @@ -3660,4 +3667,9 @@ static void __exit smc_exit(void)
> MODULE_LICENSE("GPL");
> MODULE_ALIAS_NETPROTO(PF_SMC);
> MODULE_ALIAS_TCP_ULP("smc");
> +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */
> +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1);
> +#if IS_ENABLED(CONFIG_IPV6)
> +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1);
> +#endif /* CONFIG_IPV6 */
> MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME);
> diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c
> new file mode 100644
> index 00000000..bece346
> --- /dev/null
> +++ b/net/smc/smc_inet.c
> @@ -0,0 +1,159 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Shared Memory Communications over RDMA (SMC-R) and RoCE
> + *
> + * Definitions for the IPPROTO_SMC (socket related)
> + *
> + * Copyright IBM Corp. 2016, 2018
> + * Copyright (c) 2024, Alibaba Inc.
> + *
> + * Author: D. Wythe <alibuda@xxxxxxxxxxxxxxxxx>
> + */
> +
> +#include <net/protocol.h>
> +#include <net/sock.h>
> +
> +#include "smc_inet.h"
> +#include "smc.h"
> +
> +static int smc_inet_init_sock(struct sock *sk);
> +
> +static struct proto smc_inet_prot = {
> + .name = "INET_SMC",
> + .owner = THIS_MODULE,
> + .init = smc_inet_init_sock,
> + .hash = smc_hash_sk,
> + .unhash = smc_unhash_sk,
> + .release_cb = smc_release_cb,
> + .obj_size = sizeof(struct smc_sock),
> + .h.smc_hash = &smc_v4_hashinfo,
> + .slab_flags = SLAB_TYPESAFE_BY_RCU,
> +};
> +
> +static const struct proto_ops smc_inet_stream_ops = {
> + .family = PF_INET,
> + .owner = THIS_MODULE,
> + .release = smc_release,
> + .bind = smc_bind,
> + .connect = smc_connect,
> + .socketpair = sock_no_socketpair,
> + .accept = smc_accept,
> + .getname = smc_getname,
> + .poll = smc_poll,
> + .ioctl = smc_ioctl,
> + .listen = smc_listen,
> + .shutdown = smc_shutdown,
> + .setsockopt = smc_setsockopt,
> + .getsockopt = smc_getsockopt,
> + .sendmsg = smc_sendmsg,
> + .recvmsg = smc_recvmsg,
> + .mmap = sock_no_mmap,
> + .splice_read = smc_splice_read,
> +};
> +
> +static struct inet_protosw smc_inet_protosw = {
> + .type = SOCK_STREAM,
> + .protocol = IPPROTO_SMC,
> + .prot = &smc_inet_prot,
> + .ops = &smc_inet_stream_ops,
> + .flags = INET_PROTOSW_ICSK,
When this flag is set, icsk->icsk_sync_mss must be set.
Unable to handle kernel NULL pointer dereference at virtual address
0000000000000000
Mem abort info:
ESR = 0x0000000086000005
EC = 0x21: IABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x05: level 1 translation fault
user pgtable: 4k pages, 48-bit VAs, pgdp=00000001195d1000
[0000000000000000] pgd=0800000109c46003, p4d=0800000109c46003,
pud=0000000000000000
Internal error: Oops: 0000000086000005 [#1] PREEMPT SMP
Modules linked in:
CPU: 1 UID: 0 PID: 8037 Comm: syz.3.265 Not tainted
6.11.0-rc7-syzkaller-g5f5673607153 #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 08/06/2024
pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : 0x0
lr : cipso_v4_sock_setattr+0x2a8/0x3c0 net/ipv4/cipso_ipv4.c:1910
sp : ffff80009b887a90
x29: ffff80009b887aa0 x28: ffff80008db94050 x27: 0000000000000000
x26: 1fffe0001aa6f5b3 x25: dfff800000000000 x24: ffff0000db75da00
x23: 0000000000000000 x22: ffff0000d8b78518 x21: 0000000000000000
x20: ffff0000d537ad80 x19: ffff0000d8b78000 x18: 1fffe000366d79ee
x17: ffff8000800614a8 x16: ffff800080569b84 x15: 0000000000000001
x14: 000000008b336894 x13: 00000000cd96feaa x12: 0000000000000003
x11: 0000000000040000 x10: 00000000000020a3 x9 : 1fffe0001b16f0f1
x8 : 0000000000000000 x7 : 0000000000000000 x6 : 000000000000003f
x5 : 0000000000000040 x4 : 0000000000000001 x3 : 0000000000000000
x2 : 0000000000000002 x1 : 0000000000000000 x0 : ffff0000d8b78000
Call trace:
0x0
netlbl_sock_setattr+0x2e4/0x338 net/netlabel/netlabel_kapi.c:1000
smack_netlbl_add+0xa4/0x154 security/smack/smack_lsm.c:2593
smack_socket_post_create+0xa8/0x14c security/smack/smack_lsm.c:2973
security_socket_post_create+0x94/0xd4 security/security.c:4425
__sock_create+0x4c8/0x884 net/socket.c:1587
sock_create net/socket.c:1622 [inline]
__sys_socket_create net/socket.c:1659 [inline]
__sys_socket+0x134/0x340 net/socket.c:1706
__do_sys_socket net/socket.c:1720 [inline]
__se_sys_socket net/socket.c:1718 [inline]
__arm64_sys_socket+0x7c/0x94 net/socket.c:1718
__invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712
el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730
el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598
Code: ???????? ???????? ???????? ???????? (????????)
---[ end trace 0000000000000000 ]---
