- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 V1 00/13] sched: steal tasks to improve CPU utilization
by Cheng Yu 28 Dec '23

28 Dec '23

sched: steal tasks to improve CPU utilization Cheng Jian (3): disable stealing by default sched/fair: introduce SCHED_STEAL config: enable CONFIG_SCHED_STEAL by default Steve Sistare (10): sched: Provide sparsemask, a reduced contention bitmap sched/topology: Provide hooks to allocate data shared per LLC sched/topology: Provide cfs_overload_cpus bitmap sched/fair: Dynamically update cfs_overload_cpus sched/fair: Hoist idle_stamp up from idle_balance sched/fair: Generalize the detach_task interface sched/fair: Provide can_migrate_task_llc sched/fair: Steal work from an overloaded CPU when CPU goes idle sched/fair: disable stealing if too many NUMA nodes sched/fair: Provide idle search schedstats arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched/topology.h | 3 + init/Kconfig | 15 ++ kernel/sched/core.c | 35 ++- kernel/sched/fair.c | 360 +++++++++++++++++++++++-- kernel/sched/features.h | 8 + kernel/sched/sched.h | 21 ++ kernel/sched/sparsemask.h | 210 +++++++++++++++ kernel/sched/stats.c | 15 ++ kernel/sched/stats.h | 20 ++ kernel/sched/topology.c | 141 +++++++++- 12 files changed, 804 insertions(+), 26 deletions(-) create mode 100644 kernel/sched/sparsemask.h -- 2.25.1

2 14

[PATCH v3 OLK-6.6 0/1] iommu: Enable smmu-v3 when 3408iMR/3416iMRraid card exist
by zhangnaichuan 28 Dec '23

28 Dec '23

arm64 cannot support virtualization pass-through feature when using the 3408iMR/3416iMR raid card. For solving the problem, we add two fuctions: 1.we prepare init bypass level2 entry for specific devices when smmu uses 2 level streamid entry. 2.we add smmu.bypassdev cmdline to allow SMMU bypass streams for some specific devices. usage: 3408iMRraid: smmu.bypassdev=0x1000:0x17 3416iMRraid: smmu.bypassdev=0x1000:0x15 drivers/iommu/Kconfig | 9 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 114 +++++++++++++++++++- 2 files changed, 120 insertions(+), 3 deletions(-) -- 2.33.0

2 2

[PATCH OLK-6.6 v3] tcp_comp: implement tcp compression
by Lu Wei 28 Dec '23

28 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4PNEK CVE: NA ------------------------------------------------- Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/tcp.h | 8 +- include/net/inet_sock.h | 3 + include/net/sock.h | 1 + include/net/tcp.h | 40 ++ net/ipv4/Kconfig | 10 + net/ipv4/Makefile | 1 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 42 ++ net/ipv4/tcp.c | 5 + net/ipv4/tcp_comp.c | 912 +++++++++++++++++++++++++ net/ipv4/tcp_input.c | 26 + net/ipv4/tcp_ipv4.c | 2 + net/ipv4/tcp_minisocks.c | 3 + net/ipv4/tcp_output.c | 52 ++ net/ipv6/syncookies.c | 4 + 17 files changed, 1114 insertions(+), 1 deletion(-) create mode 100644 net/ipv4/tcp_comp.c diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 33ba39711884..abc33d2c29a6 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -1222,6 +1222,7 @@ CONFIG_DEFAULT_CUBIC=y # CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y +CONFIG_TCP_COMP=y CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 44040b835333..177a6fdcce58 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -1244,6 +1244,7 @@ CONFIG_DEFAULT_CUBIC=y # CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y +CONFIG_TCP_COMP=y CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3c5efeeb024f..d94a84c291f0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,10 @@ struct tcp_options_received { snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ u8 saw_unknown:1, /* Received unknown option */ - unused:7; +#if IS_ENABLED(CONFIG_TCP_COMP) + comp_ok:1, /* COMP seen on SYN packet */ +#endif + unused:6; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -136,6 +139,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif +#if IS_ENABLED(CONFIG_TCP_COMP) + rx_opt->comp_ok = 0; +#endif } /* This is the max number of SACKS that we'll generate and process. It's safe diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 2de0e4d4a027..13c1f1e83de5 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -87,6 +87,9 @@ struct inet_request_sock { ecn_ok : 1, acked : 1, no_srccheck: 1, +#if IS_ENABLED(CONFIG_TCP_COMP) + comp_ok : 1, +#endif smc_ok : 1; u32 ir_mark; union { diff --git a/include/net/sock.h b/include/net/sock.h index 7753354d59c0..c86845136ec5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -959,6 +959,7 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_COMP, }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) diff --git a/include/net/tcp.h b/include/net/tcp.h index e9d387fffe22..cb33a2c46b2f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -195,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 +#define TCPOPT_COMP_MAGIC 0x7954 /* * TCP option lengths @@ -208,6 +209,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 +#define TCPOLEN_EXP_COMP_BASE 4 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 @@ -2531,4 +2533,42 @@ static inline u64 tcp_transmit_time(const struct sock *sk) return 0; } +#if IS_ENABLED(CONFIG_TCP_COMP) +extern struct static_key_false tcp_have_comp; + +extern unsigned long *sysctl_tcp_compression_ports; +extern int sysctl_tcp_compression_local; + +bool tcp_syn_comp_enabled(struct sock *sk); +bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq); +void tcp_init_compression(struct sock *sk); +void tcp_cleanup_compression(struct sock *sk); +int tcp_comp_init(void); +#else +static inline bool tcp_syn_comp_enabled(struct tcp_sock *tp) +{ + return false; +} + +static inline bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq) +{ + return false; +} + +static inline void tcp_init_compression(struct sock *sk) +{ +} + +static inline void tcp_cleanup_compression(struct sock *sk) +{ +} + +static inline int tcp_comp_init(void) +{ + return 0; +} +#endif + #endif /* _TCP_H */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 2dfb12230f08..a4405ea38338 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -751,3 +751,13 @@ config TCP_MD5SIG on the Internet. If unsure, say N. + +config TCP_COMP + bool "TCP: Transport Layer Compression support" + depends on CRYPTO_ZSTD=y + select STREAM_PARSER + help + Enable kernel payload compression support for TCP protocol. This allows + payload compression handling of the TCP protocol to be done in-kernel. + + If unsure, say Y. diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index b18ba8ef93ad..aa458d9f534a 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o +obj-$(CONFIG_TCP_COMP) += tcp_comp.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3b4dafefb4b0..584b29c154e8 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -391,6 +391,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; +#if IS_ENABLED(CONFIG_TCP_COMP) + ireq->comp_ok = 0; +#endif + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* We throwed the options of the initial SYN away, so we hope diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b17eb28a9690..f212133b05e9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -469,6 +469,30 @@ static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, } #endif +#if IS_ENABLED(CONFIG_TCP_COMP) +static int proc_tcp_compression_ports(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned long *bitmap = *(unsigned long **)table->data; + unsigned long bitmap_len = table->maxlen; + int ret; + + ret = proc_do_large_bitmap(table, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (bitmap_empty(bitmap, bitmap_len)) { + if (static_key_enabled(&tcp_have_comp)) + static_branch_disable(&tcp_have_comp); + } else { + if (!static_key_enabled(&tcp_have_comp)) + static_branch_enable(&tcp_have_comp); + } + } + + return ret; +} +#endif + static struct ctl_table ipv4_table[] = { { .procname = "tcp_max_orphans", @@ -587,6 +611,24 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#if IS_ENABLED(CONFIG_TCP_COMP) + { + .procname = "tcp_compression_ports", + .data = &sysctl_tcp_compression_ports, + .maxlen = 65536, + .mode = 0644, + .proc_handler = proc_tcp_compression_ports, + }, + { + .procname = "tcp_compression_local", + .data = &sysctl_tcp_compression_local, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3d3a24f79573..2703be8a7316 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -302,6 +302,10 @@ DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif +#if IS_ENABLED(CONFIG_TCP_COMP) +DEFINE_STATIC_KEY_FALSE(tcp_have_comp); +#endif + /* * Current number of TCP sockets. */ @@ -4707,5 +4711,6 @@ void __init tcp_init(void) tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); + tcp_comp_init(); mptcp_init(); } diff --git a/net/ipv4/tcp_comp.c b/net/ipv4/tcp_comp.c new file mode 100644 index 000000000000..53157a413b58 --- /dev/null +++ b/net/ipv4/tcp_comp.c @@ -0,0 +1,912 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TCP compression support + * + * Copyright(c) 2021 Huawei Technologies Co., Ltd + */ + +#include <linux/skmsg.h> +#include <linux/zstd.h> + +#define TCP_COMP_MAX_PADDING 64 +#define TCP_COMP_DATA_SIZE 65536 +#define TCP_COMP_SCRATCH_SIZE (TCP_COMP_DATA_SIZE - 1) +#define TCP_COMP_MAX_CSIZE (TCP_COMP_SCRATCH_SIZE + TCP_COMP_MAX_PADDING) +#define TCP_COMP_ALLOC_ORDER get_order(TCP_COMP_DATA_SIZE) +#define TCP_COMP_MAX_WINDOWLOG 17 +#define TCP_COMP_MAX_INPUT (1 << TCP_COMP_MAX_WINDOWLOG) + +#define TCP_COMP_SEND_PENDING 1 +#define ZSTD_COMP_DEFAULT_LEVEL 1 + +static unsigned long tcp_compression_ports[65536 / 8]; + +unsigned long *sysctl_tcp_compression_ports = tcp_compression_ports; +int sysctl_tcp_compression_local __read_mostly; + +static struct proto tcp_prot_override; + +struct tcp_comp_context_tx { + ZSTD_CStream *cstream; + void *cworkspace; + void *plaintext_data; + void *compressed_data; + struct sk_msg msg; + bool in_tcp_sendpages; +}; + +struct tcp_comp_context_rx { + ZSTD_DStream *dstream; + void *dworkspace; + void *plaintext_data; + + struct strparser strp; + void (*saved_data_ready)(struct sock *sk); + struct sk_buff *pkt; + struct sk_buff *dpkt; +}; + +struct tcp_comp_context { + struct rcu_head rcu; + + struct proto *sk_proto; + void (*sk_write_space)(struct sock *sk); + + struct tcp_comp_context_tx tx; + struct tcp_comp_context_rx rx; + + unsigned long flags; +}; + +static bool tcp_comp_is_write_pending(struct tcp_comp_context *ctx) +{ + return test_bit(TCP_COMP_SEND_PENDING, &ctx->flags); +} + +static void tcp_comp_err_abort(struct sock *sk, int err) +{ + sk->sk_err = err; + sk->sk_error_report(sk); +} + +static bool tcp_comp_enabled(__be32 saddr, __be32 daddr, int port) +{ + if (!sysctl_tcp_compression_local && + (saddr == daddr || ipv4_is_loopback(daddr))) + return false; + + return test_bit(port, sysctl_tcp_compression_ports); +} + +bool tcp_syn_comp_enabled(struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + return tcp_comp_enabled(inet->inet_saddr, inet->inet_daddr, + ntohs(inet->inet_dport)); +} + +bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq) +{ + struct inet_sock *inet = inet_sk(sk); + + if (!ireq->comp_ok) + return false; + + return tcp_comp_enabled(ireq->ir_loc_addr, ireq->ir_rmt_addr, + ntohs(inet->inet_sport)); +} + +static struct tcp_comp_context *comp_get_ctx(const struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + return (__force void *)icsk->icsk_ulp_data; +} + +static int tcp_comp_tx_context_init(struct tcp_comp_context *ctx) +{ + ZSTD_parameters params; + int csize; + + params = ZSTD_getParams(ZSTD_COMP_DEFAULT_LEVEL, PAGE_SIZE, 0); + csize = zstd_cstream_workspace_bound(&params.cParams); + if (csize <= 0) + return -EINVAL; + + ctx->tx.cworkspace = kmalloc(csize, GFP_KERNEL); + if (!ctx->tx.cworkspace) + return -ENOMEM; + + ctx->tx.cstream = zstd_init_cstream(&params, 0, ctx->tx.cworkspace, + csize); + if (!ctx->tx.cstream) + goto err_cstream; + + ctx->tx.plaintext_data = kvmalloc(TCP_COMP_SCRATCH_SIZE, GFP_KERNEL); + if (!ctx->tx.plaintext_data) + goto err_cstream; + + ctx->tx.compressed_data = kvmalloc(TCP_COMP_MAX_CSIZE, GFP_KERNEL); + if (!ctx->tx.compressed_data) + goto err_compressed; + + return 0; + +err_compressed: + kvfree(ctx->tx.plaintext_data); + ctx->tx.plaintext_data = NULL; +err_cstream: + kfree(ctx->tx.cworkspace); + ctx->tx.cworkspace = NULL; + + return -ENOMEM; +} + +static void *tcp_comp_get_tx_stream(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx->tx.plaintext_data) + tcp_comp_tx_context_init(ctx); + + return ctx->tx.plaintext_data; +} + +static int alloc_compressed_msg(struct sock *sk, int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + + sk_msg_init(msg); + + return sk_msg_alloc(sk, msg, len, 0); +} + +static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, int copy) +{ + void *dest; + int rc; + + dest = tcp_comp_get_tx_stream(sk); + if (!dest) + return -ENOSPC; + + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) + rc = copy_from_iter_nocache(dest, copy, from); + else + rc = copy_from_iter(dest, copy, from); + + if (rc != copy) + rc = -EFAULT; + + return rc; +} + +static int memcopy_to_msg(struct sock *sk, int bytes) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + int i = msg->sg.curr; + struct scatterlist *sge; + u32 copy, buf_size; + void *from, *to; + + from = ctx->tx.compressed_data; + do { + sge = sk_msg_elem(msg, i); + /* This is possible if a trim operation shrunk the buffer */ + if (msg->sg.copybreak >= sge->length) { + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + sge = sk_msg_elem(msg, i); + } + buf_size = sge->length - msg->sg.copybreak; + copy = (buf_size > bytes) ? bytes : buf_size; + to = sg_virt(sge) + msg->sg.copybreak; + msg->sg.copybreak += copy; + memcpy(to, from, copy); + bytes -= copy; + from += copy; + if (!bytes) + break; + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); + + msg->sg.curr = i; + return bytes; +} + +static int tcp_comp_compress_to_msg(struct sock *sk, int bytes) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + ZSTD_outBuffer outbuf; + ZSTD_inBuffer inbuf; + size_t ret; + + inbuf.src = ctx->tx.plaintext_data; + outbuf.dst = ctx->tx.compressed_data; + inbuf.size = bytes; + outbuf.size = TCP_COMP_MAX_CSIZE; + inbuf.pos = 0; + outbuf.pos = 0; + + ret = ZSTD_compressStream(ctx->tx.cstream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) + return -EIO; + + ret = ZSTD_flushStream(ctx->tx.cstream, &outbuf); + if (ZSTD_isError(ret)) + return -EIO; + + if (inbuf.pos != inbuf.size) + return -EIO; + + if (memcopy_to_msg(sk, outbuf.pos)) + return -EIO; + + sk_msg_trim(sk, &ctx->tx.msg, outbuf.pos); + + return 0; +} + +static int tcp_comp_push_msg(struct sock *sk, struct sk_msg *msg, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct msghdr mh; + struct bio_vec bvec; + struct scatterlist *sg; + int ret, offset; + struct page *p; + size_t size; + + ctx->tx.in_tcp_sendpages = true; + while (1) { + sg = sk_msg_elem(msg, msg->sg.start); + offset = sg->offset; + size = sg->length; + p = sg_page(sg); +retry: + memset(&mh, 0, sizeof(struct msghdr)); + memset(&bvec, 0, sizeof(struct bio_vec)); + + mh.msg_flags = flags | MSG_SPLICE_PAGES; + bvec_set_page(&bvec, p, size, offset); + iov_iter_bvec(&mh.msg_iter, ITER_SOURCE, &bvec, 1, size); + + ret = tcp_sendmsg_locked(sk, &mh, size); + if (ret != size) { + if (ret > 0) { + sk_mem_uncharge(sk, ret); + sg->offset += ret; + sg->length -= ret; + size -= ret; + offset += ret; + goto retry; + } + ctx->tx.in_tcp_sendpages = false; + return ret; + } + + sk_mem_uncharge(sk, ret); + msg->sg.size -= size; + put_page(p); + sk_msg_iter_next(msg, start); + if (msg->sg.start == msg->sg.end) + break; + } + + clear_bit(TCP_COMP_SEND_PENDING, &ctx->flags); + ctx->tx.in_tcp_sendpages = false; + + return 0; +} + +static int tcp_comp_push(struct sock *sk, int bytes, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int ret; + + ret = tcp_comp_compress_to_msg(sk, bytes); + if (ret < 0) { + pr_debug("%s: failed to compress sg\n", __func__); + return ret; + } + + set_bit(TCP_COMP_SEND_PENDING, &ctx->flags); + + ret = tcp_comp_push_msg(sk, &ctx->tx.msg, flags); + if (ret) { + pr_debug("%s: failed to tcp_comp_push_sg\n", __func__); + return ret; + } + + return 0; +} + +static int wait_on_pending_writer(struct sock *sk, long *timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + add_wait_queue(sk_sleep(sk), &wait); + while (1) { + if (!*timeo) { + ret = -EAGAIN; + break; + } + + if (signal_pending(current)) { + ret = sock_intr_errno(*timeo); + break; + } + + if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + break; + } + remove_wait_queue(sk_sleep(sk), &wait); + + return ret; +} + +static int tcp_comp_push_pending_msg(struct sock *sk, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + + if (msg->sg.start == msg->sg.end) + return 0; + + return tcp_comp_push_msg(sk, msg, flags); +} + +static int tcp_comp_complete_pending_work(struct sock *sk, int flags, + long *timeo) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int ret = 0; + + if (unlikely(sk->sk_write_pending)) + ret = wait_on_pending_writer(sk, timeo); + + if (!ret && tcp_comp_is_write_pending(ctx)) + ret = tcp_comp_push_pending_msg(sk, flags); + + return ret; +} + +static int tcp_comp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int copied = 0, err = 0; + size_t try_to_copy; + int required_size; + long timeo; + + lock_sock(sk); + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + err = tcp_comp_complete_pending_work(sk, msg->msg_flags, &timeo); + if (err) + goto out_err; + + while (msg_data_left(msg)) { + if (sk->sk_err) { + err = -sk->sk_err; + goto out_err; + } + + try_to_copy = msg_data_left(msg); + if (try_to_copy > TCP_COMP_SCRATCH_SIZE) + try_to_copy = TCP_COMP_SCRATCH_SIZE; + required_size = try_to_copy + TCP_COMP_MAX_PADDING; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; + +alloc_compressed: + err = alloc_compressed_msg(sk, required_size); + if (err) { + if (err != -ENOSPC) + goto wait_for_memory; + goto out_err; + } + + err = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy); + if (err < 0) + goto out_err; + + copied += try_to_copy; + + err = tcp_comp_push(sk, try_to_copy, msg->msg_flags); + if (err < 0) { + if (err == -ENOMEM) + goto wait_for_memory; + if (err != -EAGAIN) + tcp_comp_err_abort(sk, EBADMSG); + goto out_err; + } + + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_err; + if (ctx->tx.msg.sg.size < required_size) + goto alloc_compressed; + } + +out_err: + err = sk_stream_error(sk, msg->msg_flags, err); + + release_sock(sk); + + return copied ? copied : err; +} + +static struct sk_buff *comp_wait_data(struct sock *sk, int flags, + long timeo, int *err) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_buff *skb; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + + while (!(skb = ctx->rx.pkt)) { + if (sk->sk_err) { + *err = sock_error(sk); + return NULL; + } + + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->rx.strp); + if (ctx->rx.pkt) + return ctx->rx.pkt; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + + if (sock_flag(sk, SOCK_DONE)) + return NULL; + + if ((flags & MSG_DONTWAIT) || !timeo) { + *err = -EAGAIN; + return NULL; + } + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + sk_wait_event(sk, &timeo, ctx->rx.pkt != skb, &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + + /* Handle signals */ + if (signal_pending(current)) { + *err = sock_intr_errno(timeo); + return NULL; + } + } + + return skb; +} + +static bool comp_advance_skb(struct sock *sk, struct sk_buff *skb, + unsigned int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + + /* Finished with message */ + ctx->rx.pkt = NULL; + kfree_skb(skb); + __strp_unpause(&ctx->rx.strp); + + return true; +} + +static bool comp_advance_dskb(struct sock *sk, struct sk_buff *skb, + unsigned int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + + /* Finished with message */ + ctx->rx.dpkt = NULL; + kfree_skb(skb); + return true; +} + +static int tcp_comp_rx_context_init(struct tcp_comp_context *ctx) +{ + int dsize; + + dsize = zstd_dstream_workspace_bound(TCP_COMP_MAX_INPUT); + if (dsize <= 0) + return -EINVAL; + + ctx->rx.dworkspace = kmalloc(dsize, GFP_KERNEL); + if (!ctx->rx.dworkspace) + return -ENOMEM; + + ctx->rx.dstream = zstd_init_dstream(TCP_COMP_MAX_INPUT, + ctx->rx.dworkspace, dsize); + if (!ctx->rx.dstream) + goto err_dstream; + + ctx->rx.plaintext_data = kvmalloc(TCP_COMP_MAX_CSIZE * 32, GFP_KERNEL); + if (!ctx->rx.plaintext_data) + goto err_dstream; + + return 0; + +err_dstream: + kfree(ctx->rx.dworkspace); + ctx->rx.dworkspace = NULL; + + return -ENOMEM; +} + +static void *tcp_comp_get_rx_stream(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx->rx.plaintext_data) + tcp_comp_rx_context_init(ctx); + + return ctx->rx.plaintext_data; +} + +static int tcp_comp_decompress(struct sock *sk, struct sk_buff *skb, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + size_t ret, compressed_len = 0; + int nr_frags_over = 0; + ZSTD_outBuffer outbuf; + ZSTD_inBuffer inbuf; + struct sk_buff *nskb; + int len, plen; + void *to; + + to = tcp_comp_get_rx_stream(sk); + if (!to) + return -ENOSPC; + + if (skb_linearize_cow(skb)) + return -ENOMEM; + + nskb = skb_copy(skb, GFP_KERNEL); + if (!nskb) + return -ENOMEM; + + while (compressed_len < (skb->len - rxm->offset)) { + if (skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS) + break; + + len = 0; + plen = skb->len - rxm->offset - compressed_len; + if (plen > TCP_COMP_MAX_CSIZE) + plen = TCP_COMP_MAX_CSIZE; + + inbuf.src = (char *)skb->data + rxm->offset + compressed_len; + inbuf.pos = 0; + inbuf.size = plen; + + outbuf.dst = ctx->rx.plaintext_data; + outbuf.pos = 0; + outbuf.size = MAX_SKB_FRAGS * TCP_COMP_DATA_SIZE; + outbuf.size -= skb_shinfo(nskb)->nr_frags * TCP_COMP_DATA_SIZE; + + ret = ZSTD_decompressStream(ctx->rx.dstream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) { + kfree_skb(nskb); + return -EIO; + } + + if (!compressed_len) { + len = outbuf.pos - skb->len; + if (len > skb_tailroom(nskb)) + len = skb_tailroom(nskb); + + __skb_put(nskb, len); + + len += skb->len; + skb_copy_to_linear_data(nskb, to, len); + } + + while ((to += len, outbuf.pos -= len) > 0) { + struct page *pages; + skb_frag_t *frag; + + if (skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS) { + nr_frags_over = 1; + break; + } + + frag = skb_shinfo(nskb)->frags + + skb_shinfo(nskb)->nr_frags; + pages = alloc_pages(__GFP_NOWARN | GFP_KERNEL | __GFP_COMP, + TCP_COMP_ALLOC_ORDER); + if (!pages) { + kfree_skb(nskb); + return -ENOMEM; + } + + frag->bv_page = pages; + len = PAGE_SIZE << TCP_COMP_ALLOC_ORDER; + if (outbuf.pos < len) + len = outbuf.pos; + + frag->bv_offset = 0; + skb_frag_size_set(frag, len); + memcpy(skb_frag_address(frag), to, len); + + nskb->truesize += len; + nskb->data_len += len; + nskb->len += len; + skb_shinfo(nskb)->nr_frags++; + } + + if (nr_frags_over) + break; + + compressed_len += inbuf.pos; + } + + ctx->rx.dpkt = nskb; + rxm = strp_msg(nskb); + rxm->full_len = nskb->len; + rxm->offset = 0; + comp_advance_skb(sk, skb, compressed_len); + + return 0; +} + +static int tcp_comp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int flags, int *addr_len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm; + struct sk_buff *skb; + ssize_t copied = 0; + int target, err = 0; + long timeo; + + if (unlikely(flags & MSG_ERRQUEUE)) + return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); + + lock_sock(sk); + + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + timeo = sock_rcvtimeo(sk, flags & MSG_WAITALL); + + do { + int chunk = 0; + + if (!ctx->rx.dpkt) { + skb = comp_wait_data(sk, flags, timeo, &err); + if (!skb) + goto recv_end; + + err = tcp_comp_decompress(sk, skb, flags); + if (err < 0) { + goto recv_end; + } + } + + skb = ctx->rx.dpkt; + rxm = strp_msg(skb); + chunk = min_t(unsigned int, rxm->full_len, len); + err = skb_copy_datagram_msg(skb, rxm->offset, msg, + chunk); + if (err < 0) + goto recv_end; + + copied += chunk; + len -= chunk; + if (likely(!(flags & MSG_PEEK))) + comp_advance_dskb(sk, skb, chunk); + else + break; + + if (copied >= target && !ctx->rx.dpkt) + break; + } while (len > 0); + +recv_end: + release_sock(sk); + return copied ? : err; +} + +bool comp_stream_read(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx) + return false; + + if (ctx->rx.pkt || ctx->rx.dpkt) + return true; + + return false; +} + +static void comp_data_ready(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + strp_data_ready(&ctx->rx.strp); +} + +static void comp_queue(struct strparser *strp, struct sk_buff *skb) +{ + struct tcp_comp_context *ctx = comp_get_ctx(strp->sk); + + ctx->rx.pkt = skb; + strp_pause(strp); + ctx->rx.saved_data_ready(strp->sk); +} + +static int comp_read_size(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + + if (rxm->offset > skb->len) + return 0; + + return skb->len - rxm->offset; +} + +void comp_setup_strp(struct sock *sk, struct tcp_comp_context *ctx) +{ + struct strp_callbacks cb; + + memset(&cb, 0, sizeof(cb)); + cb.rcv_msg = comp_queue; + cb.parse_msg = comp_read_size; + strp_init(&ctx->rx.strp, sk, &cb); + + write_lock_bh(&sk->sk_callback_lock); + ctx->rx.saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = comp_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&ctx->rx.strp); +} + +static void tcp_comp_write_space(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (ctx->tx.in_tcp_sendpages) { + ctx->sk_write_space(sk); + return; + } + + if (!sk->sk_write_pending && tcp_comp_is_write_pending(ctx)) { + gfp_t sk_allocation = sk->sk_allocation; + int rc; + + sk->sk_allocation = GFP_ATOMIC; + rc = tcp_comp_push_pending_msg(sk, MSG_DONTWAIT | MSG_NOSIGNAL); + sk->sk_allocation = sk_allocation; + + if (rc < 0) + return; + } + + ctx->sk_write_space(sk); +} + +void tcp_init_compression(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_comp_context *ctx = NULL; + struct sk_msg *msg = NULL; + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->rx_opt.comp_ok) + return; + + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return; + + msg = &ctx->tx.msg; + sk_msg_init(msg); + + ctx->sk_write_space = sk->sk_write_space; + ctx->sk_proto = sk->sk_prot; + WRITE_ONCE(sk->sk_prot, &tcp_prot_override); + sk->sk_write_space = tcp_comp_write_space; + + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + + sock_set_flag(sk, SOCK_COMP); + comp_setup_strp(sk, ctx); +} + +static void tcp_comp_context_tx_free(struct tcp_comp_context *ctx) +{ + kfree(ctx->tx.cworkspace); + ctx->tx.cworkspace = NULL; + + kvfree(ctx->tx.plaintext_data); + ctx->tx.plaintext_data = NULL; + + kvfree(ctx->tx.compressed_data); + ctx->tx.compressed_data = NULL; +} + +static void tcp_comp_context_rx_free(struct tcp_comp_context *ctx) +{ + kfree(ctx->rx.dworkspace); + ctx->rx.dworkspace = NULL; + + kvfree(ctx->rx.plaintext_data); + ctx->rx.plaintext_data = NULL; +} + +static void tcp_comp_context_free(struct rcu_head *head) +{ + struct tcp_comp_context *ctx; + + ctx = container_of(head, struct tcp_comp_context, rcu); + + tcp_comp_context_tx_free(ctx); + tcp_comp_context_rx_free(ctx); + strp_done(&ctx->rx.strp); + kfree(ctx); +} + +void tcp_cleanup_compression(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx || !sock_flag(sk, SOCK_COMP)) + return; + + if (ctx->rx.pkt) { + kfree_skb(ctx->rx.pkt); + ctx->rx.pkt = NULL; + } + + if (ctx->rx.dpkt) { + kfree_skb(ctx->rx.dpkt); + ctx->rx.dpkt = NULL; + } + strp_stop(&ctx->rx.strp); + + rcu_assign_pointer(icsk->icsk_ulp_data, NULL); + call_rcu(&ctx->rcu, tcp_comp_context_free); +} + +int tcp_comp_init(void) +{ + tcp_prot_override = tcp_prot; + tcp_prot_override.sendmsg = tcp_comp_sendmsg; + tcp_prot_override.recvmsg = tcp_comp_recvmsg; + tcp_prot_override.sock_is_readable = comp_stream_read; + + return 0; +} diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fd5c13c1fbc8..a5adf4822663 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4012,6 +4012,24 @@ static bool smc_parse_options(const struct tcphdr *th, return false; } +static bool tcp_parse_comp_option(const struct tcphdr *th, + struct tcp_options_received *opt_rx, + const unsigned char *ptr, + int opsize) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (th->syn && !(opsize & 1) && + opsize >= TCPOLEN_EXP_COMP_BASE && + get_unaligned_be16(ptr) == TCPOPT_COMP_MAGIC) { + opt_rx->comp_ok = 1; + return true; + } + } +#endif + return false; +} + /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped * value on success. */ @@ -4171,6 +4189,10 @@ void tcp_parse_options(const struct net *net, if (smc_parse_options(th, opt_rx, ptr, opsize)) break; + if (tcp_parse_comp_option(th, opt_rx, ptr, + opsize)) + break; + opt_rx->saw_unknown = 1; break; @@ -6097,6 +6119,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) /* Initialize congestion control unless BPF initialized it already: */ if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); + tcp_init_compression(sk); tcp_init_buffer_space(sk); } @@ -6835,6 +6858,9 @@ static void tcp_openreq_init(struct request_sock *req, ireq->smc_ok = rx_opt->smc_ok && !(tcp_sk(sk)->smc_hs_congested && tcp_sk(sk)->smc_hs_congested(sk)); #endif +#if IS_ENABLED(CONFIG_TCP_COMP) + ireq->comp_ok = rx_opt->comp_ok; +#endif } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4167e8a48b60..9cbf23c1c039 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2304,6 +2304,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cleanup_congestion_control(sk); + tcp_cleanup_compression(sk); + tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b98d476f1594..d67a84c114ce 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -543,6 +543,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_ssthresh = req->rsk_rcv_wnd; newtp->rcv_wnd = req->rsk_rcv_wnd; newtp->rx_opt.wscale_ok = ireq->wscale_ok; +#if IS_ENABLED(CONFIG_TCP_COMP) + newtp->rx_opt.comp_ok = ireq->comp_ok; +#endif if (newtp->rx_opt.wscale_ok) { newtp->rx_opt.snd_wscale = ireq->snd_wscale; newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1917c62ad3bf..eee34f6c7643 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -422,6 +422,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) +#define OPTION_COMP BIT(11) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -438,6 +439,19 @@ static void smc_options_write(__be32 *ptr, u16 *options) #endif } +static void comp_options_write(__be32 *ptr, u16 *options) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (unlikely(OPTION_COMP & *options)) { + *ptr++ = htonl((TCPOPT_EXP << 24) | + (TCPOLEN_EXP_COMP_BASE << 16) | + (TCPOPT_COMP_MAGIC)); + } + } +#endif +} + struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ @@ -711,6 +725,8 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, smc_options_write(ptr, &options); mptcp_options_write(th, ptr, tp, opts); + + comp_options_write(ptr, &options); } static void smc_set_option(const struct tcp_sock *tp, @@ -729,6 +745,39 @@ static void smc_set_option(const struct tcp_sock *tp, #endif } +static void comp_set_option(struct sock *sk, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (tcp_syn_comp_enabled(sk)) { + if (*remaining >= TCPOLEN_EXP_COMP_BASE) { + opts->options |= OPTION_COMP; + *remaining -= TCPOLEN_EXP_COMP_BASE; + } + } + } +#endif +} + +static void comp_set_option_cond(struct sock *sk, + const struct inet_request_sock *ireq, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (tcp_synack_comp_enabled(sk, ireq)) { + if (*remaining >= TCPOLEN_EXP_COMP_BASE) { + opts->options |= OPTION_COMP; + *remaining -= TCPOLEN_EXP_COMP_BASE; + } + } + } +#endif +} + static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, @@ -830,6 +879,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } smc_set_option(tp, opts, &remaining); + comp_set_option(sk, opts, &remaining); if (sk_is_mptcp(sk)) { unsigned int size; @@ -910,6 +960,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + comp_set_option_cond((struct sock *)sk, ireq, opts, &remaining); + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8698b49dfc8d..75652826abbd 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -218,6 +218,10 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; +#if IS_ENABLED(CONFIG_TCP_COMP) + ireq->comp_ok = 0; +#endif + /* * We need to lookup the dst_entry to get the correct window size. * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten -- 2.34.1

2 1

[PATCH OLK-6.6 v3 0/2] dm btree spine: show warning if node_check failed
by Li Lingfeng 28 Dec '23

28 Dec '23

Add extra node_check function declaration back and show warning if node_check failed in node_prep_for_write(). v1->v2: Revert commit 851a8cd3f05b ("dm btree spine: remove extra node_check function declaration") to add extra node_check function declaration back. Fix commit message. v2->v3: Remove duplicate signature. Li Lingfeng (1): Revert "dm btree spine: remove extra node_check function declaration" Zhang Xiaoxu (1): dm btree spine: show warning if node_check failed in node_prep_for_write() drivers/md/persistent-data/dm-btree-spine.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.31.1

2 4

[PATCH OLK-6.6 v2] tcp_comp: implement tcp compression
by Lu Wei 28 Dec '23

28 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4PNEK CVE: NA ------------------------------------------------- Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/tcp.h | 8 +- include/net/inet_sock.h | 5 +- include/net/sock.h | 1 + include/net/tcp.h | 40 ++ net/ipv4/Kconfig | 10 + net/ipv4/Makefile | 1 + net/ipv4/syncookies.c | 2 + net/ipv4/sysctl_net_ipv4.c | 42 ++ net/ipv4/tcp.c | 5 + net/ipv4/tcp_comp.c | 912 +++++++++++++++++++++++++ net/ipv4/tcp_input.c | 26 + net/ipv4/tcp_ipv4.c | 2 + net/ipv4/tcp_minisocks.c | 3 + net/ipv4/tcp_output.c | 52 ++ net/ipv6/syncookies.c | 2 + 17 files changed, 1111 insertions(+), 2 deletions(-) create mode 100644 net/ipv4/tcp_comp.c diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 33ba39711884..abc33d2c29a6 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -1222,6 +1222,7 @@ CONFIG_DEFAULT_CUBIC=y # CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y +CONFIG_TCP_COMP=y CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index 44040b835333..177a6fdcce58 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -1244,6 +1244,7 @@ CONFIG_DEFAULT_CUBIC=y # CONFIG_DEFAULT_RENO is not set CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y +CONFIG_TCP_COMP=y CONFIG_IPV6=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3c5efeeb024f..d94a84c291f0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,10 @@ struct tcp_options_received { snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ u8 saw_unknown:1, /* Received unknown option */ - unused:7; +#if IS_ENABLED(CONFIG_TCP_COMP) + comp_ok:1, /* COMP seen on SYN packet */ +#endif + unused:6; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -136,6 +139,9 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif +#if IS_ENABLED(CONFIG_TCP_COMP) + rx_opt->comp_ok = 0; +#endif } /* This is the max number of SACKS that we'll generate and process. It's safe diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 2de0e4d4a027..2b6da8a6282d 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -87,7 +87,10 @@ struct inet_request_sock { ecn_ok : 1, acked : 1, no_srccheck: 1, - smc_ok : 1; + smc_ok : 1, +#if IS_ENABLED(CONFIG_TCP_COMP) + comp_ok : 1; +#endif u32 ir_mark; union { struct ip_options_rcu __rcu *ireq_opt; diff --git a/include/net/sock.h b/include/net/sock.h index 7753354d59c0..c86845136ec5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -959,6 +959,7 @@ enum sock_flags { SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ + SOCK_COMP, }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) diff --git a/include/net/tcp.h b/include/net/tcp.h index e9d387fffe22..cb33a2c46b2f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -195,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 +#define TCPOPT_COMP_MAGIC 0x7954 /* * TCP option lengths @@ -208,6 +209,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 +#define TCPOLEN_EXP_COMP_BASE 4 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 @@ -2531,4 +2533,42 @@ static inline u64 tcp_transmit_time(const struct sock *sk) return 0; } +#if IS_ENABLED(CONFIG_TCP_COMP) +extern struct static_key_false tcp_have_comp; + +extern unsigned long *sysctl_tcp_compression_ports; +extern int sysctl_tcp_compression_local; + +bool tcp_syn_comp_enabled(struct sock *sk); +bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq); +void tcp_init_compression(struct sock *sk); +void tcp_cleanup_compression(struct sock *sk); +int tcp_comp_init(void); +#else +static inline bool tcp_syn_comp_enabled(struct tcp_sock *tp) +{ + return false; +} + +static inline bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq) +{ + return false; +} + +static inline void tcp_init_compression(struct sock *sk) +{ +} + +static inline void tcp_cleanup_compression(struct sock *sk) +{ +} + +static inline int tcp_comp_init(void) +{ + return 0; +} +#endif + #endif /* _TCP_H */ diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 2dfb12230f08..a4405ea38338 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -751,3 +751,13 @@ config TCP_MD5SIG on the Internet. If unsure, say N. + +config TCP_COMP + bool "TCP: Transport Layer Compression support" + depends on CRYPTO_ZSTD=y + select STREAM_PARSER + help + Enable kernel payload compression support for TCP protocol. This allows + payload compression handling of the TCP protocol to be done in-kernel. + + If unsure, say Y. diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index b18ba8ef93ad..aa458d9f534a 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o +obj-$(CONFIG_TCP_COMP) += tcp_comp.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3b4dafefb4b0..42c577bfc26b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -390,6 +390,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; + if (IS_ENABLED(CONFIG_TCP_COMP)) + ireq->comp_ok = 0; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index b17eb28a9690..f212133b05e9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -469,6 +469,30 @@ static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, } #endif +#if IS_ENABLED(CONFIG_TCP_COMP) +static int proc_tcp_compression_ports(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned long *bitmap = *(unsigned long **)table->data; + unsigned long bitmap_len = table->maxlen; + int ret; + + ret = proc_do_large_bitmap(table, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (bitmap_empty(bitmap, bitmap_len)) { + if (static_key_enabled(&tcp_have_comp)) + static_branch_disable(&tcp_have_comp); + } else { + if (!static_key_enabled(&tcp_have_comp)) + static_branch_enable(&tcp_have_comp); + } + } + + return ret; +} +#endif + static struct ctl_table ipv4_table[] = { { .procname = "tcp_max_orphans", @@ -587,6 +611,24 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#if IS_ENABLED(CONFIG_TCP_COMP) + { + .procname = "tcp_compression_ports", + .data = &sysctl_tcp_compression_ports, + .maxlen = 65536, + .mode = 0644, + .proc_handler = proc_tcp_compression_ports, + }, + { + .procname = "tcp_compression_local", + .data = &sysctl_tcp_compression_local, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3d3a24f79573..2703be8a7316 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -302,6 +302,10 @@ DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif +#if IS_ENABLED(CONFIG_TCP_COMP) +DEFINE_STATIC_KEY_FALSE(tcp_have_comp); +#endif + /* * Current number of TCP sockets. */ @@ -4707,5 +4711,6 @@ void __init tcp_init(void) tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); + tcp_comp_init(); mptcp_init(); } diff --git a/net/ipv4/tcp_comp.c b/net/ipv4/tcp_comp.c new file mode 100644 index 000000000000..53157a413b58 --- /dev/null +++ b/net/ipv4/tcp_comp.c @@ -0,0 +1,912 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TCP compression support + * + * Copyright(c) 2021 Huawei Technologies Co., Ltd + */ + +#include <linux/skmsg.h> +#include <linux/zstd.h> + +#define TCP_COMP_MAX_PADDING 64 +#define TCP_COMP_DATA_SIZE 65536 +#define TCP_COMP_SCRATCH_SIZE (TCP_COMP_DATA_SIZE - 1) +#define TCP_COMP_MAX_CSIZE (TCP_COMP_SCRATCH_SIZE + TCP_COMP_MAX_PADDING) +#define TCP_COMP_ALLOC_ORDER get_order(TCP_COMP_DATA_SIZE) +#define TCP_COMP_MAX_WINDOWLOG 17 +#define TCP_COMP_MAX_INPUT (1 << TCP_COMP_MAX_WINDOWLOG) + +#define TCP_COMP_SEND_PENDING 1 +#define ZSTD_COMP_DEFAULT_LEVEL 1 + +static unsigned long tcp_compression_ports[65536 / 8]; + +unsigned long *sysctl_tcp_compression_ports = tcp_compression_ports; +int sysctl_tcp_compression_local __read_mostly; + +static struct proto tcp_prot_override; + +struct tcp_comp_context_tx { + ZSTD_CStream *cstream; + void *cworkspace; + void *plaintext_data; + void *compressed_data; + struct sk_msg msg; + bool in_tcp_sendpages; +}; + +struct tcp_comp_context_rx { + ZSTD_DStream *dstream; + void *dworkspace; + void *plaintext_data; + + struct strparser strp; + void (*saved_data_ready)(struct sock *sk); + struct sk_buff *pkt; + struct sk_buff *dpkt; +}; + +struct tcp_comp_context { + struct rcu_head rcu; + + struct proto *sk_proto; + void (*sk_write_space)(struct sock *sk); + + struct tcp_comp_context_tx tx; + struct tcp_comp_context_rx rx; + + unsigned long flags; +}; + +static bool tcp_comp_is_write_pending(struct tcp_comp_context *ctx) +{ + return test_bit(TCP_COMP_SEND_PENDING, &ctx->flags); +} + +static void tcp_comp_err_abort(struct sock *sk, int err) +{ + sk->sk_err = err; + sk->sk_error_report(sk); +} + +static bool tcp_comp_enabled(__be32 saddr, __be32 daddr, int port) +{ + if (!sysctl_tcp_compression_local && + (saddr == daddr || ipv4_is_loopback(daddr))) + return false; + + return test_bit(port, sysctl_tcp_compression_ports); +} + +bool tcp_syn_comp_enabled(struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + return tcp_comp_enabled(inet->inet_saddr, inet->inet_daddr, + ntohs(inet->inet_dport)); +} + +bool tcp_synack_comp_enabled(struct sock *sk, + const struct inet_request_sock *ireq) +{ + struct inet_sock *inet = inet_sk(sk); + + if (!ireq->comp_ok) + return false; + + return tcp_comp_enabled(ireq->ir_loc_addr, ireq->ir_rmt_addr, + ntohs(inet->inet_sport)); +} + +static struct tcp_comp_context *comp_get_ctx(const struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + return (__force void *)icsk->icsk_ulp_data; +} + +static int tcp_comp_tx_context_init(struct tcp_comp_context *ctx) +{ + ZSTD_parameters params; + int csize; + + params = ZSTD_getParams(ZSTD_COMP_DEFAULT_LEVEL, PAGE_SIZE, 0); + csize = zstd_cstream_workspace_bound(&params.cParams); + if (csize <= 0) + return -EINVAL; + + ctx->tx.cworkspace = kmalloc(csize, GFP_KERNEL); + if (!ctx->tx.cworkspace) + return -ENOMEM; + + ctx->tx.cstream = zstd_init_cstream(&params, 0, ctx->tx.cworkspace, + csize); + if (!ctx->tx.cstream) + goto err_cstream; + + ctx->tx.plaintext_data = kvmalloc(TCP_COMP_SCRATCH_SIZE, GFP_KERNEL); + if (!ctx->tx.plaintext_data) + goto err_cstream; + + ctx->tx.compressed_data = kvmalloc(TCP_COMP_MAX_CSIZE, GFP_KERNEL); + if (!ctx->tx.compressed_data) + goto err_compressed; + + return 0; + +err_compressed: + kvfree(ctx->tx.plaintext_data); + ctx->tx.plaintext_data = NULL; +err_cstream: + kfree(ctx->tx.cworkspace); + ctx->tx.cworkspace = NULL; + + return -ENOMEM; +} + +static void *tcp_comp_get_tx_stream(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx->tx.plaintext_data) + tcp_comp_tx_context_init(ctx); + + return ctx->tx.plaintext_data; +} + +static int alloc_compressed_msg(struct sock *sk, int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + + sk_msg_init(msg); + + return sk_msg_alloc(sk, msg, len, 0); +} + +static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, int copy) +{ + void *dest; + int rc; + + dest = tcp_comp_get_tx_stream(sk); + if (!dest) + return -ENOSPC; + + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) + rc = copy_from_iter_nocache(dest, copy, from); + else + rc = copy_from_iter(dest, copy, from); + + if (rc != copy) + rc = -EFAULT; + + return rc; +} + +static int memcopy_to_msg(struct sock *sk, int bytes) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + int i = msg->sg.curr; + struct scatterlist *sge; + u32 copy, buf_size; + void *from, *to; + + from = ctx->tx.compressed_data; + do { + sge = sk_msg_elem(msg, i); + /* This is possible if a trim operation shrunk the buffer */ + if (msg->sg.copybreak >= sge->length) { + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + sge = sk_msg_elem(msg, i); + } + buf_size = sge->length - msg->sg.copybreak; + copy = (buf_size > bytes) ? bytes : buf_size; + to = sg_virt(sge) + msg->sg.copybreak; + msg->sg.copybreak += copy; + memcpy(to, from, copy); + bytes -= copy; + from += copy; + if (!bytes) + break; + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); + + msg->sg.curr = i; + return bytes; +} + +static int tcp_comp_compress_to_msg(struct sock *sk, int bytes) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + ZSTD_outBuffer outbuf; + ZSTD_inBuffer inbuf; + size_t ret; + + inbuf.src = ctx->tx.plaintext_data; + outbuf.dst = ctx->tx.compressed_data; + inbuf.size = bytes; + outbuf.size = TCP_COMP_MAX_CSIZE; + inbuf.pos = 0; + outbuf.pos = 0; + + ret = ZSTD_compressStream(ctx->tx.cstream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) + return -EIO; + + ret = ZSTD_flushStream(ctx->tx.cstream, &outbuf); + if (ZSTD_isError(ret)) + return -EIO; + + if (inbuf.pos != inbuf.size) + return -EIO; + + if (memcopy_to_msg(sk, outbuf.pos)) + return -EIO; + + sk_msg_trim(sk, &ctx->tx.msg, outbuf.pos); + + return 0; +} + +static int tcp_comp_push_msg(struct sock *sk, struct sk_msg *msg, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct msghdr mh; + struct bio_vec bvec; + struct scatterlist *sg; + int ret, offset; + struct page *p; + size_t size; + + ctx->tx.in_tcp_sendpages = true; + while (1) { + sg = sk_msg_elem(msg, msg->sg.start); + offset = sg->offset; + size = sg->length; + p = sg_page(sg); +retry: + memset(&mh, 0, sizeof(struct msghdr)); + memset(&bvec, 0, sizeof(struct bio_vec)); + + mh.msg_flags = flags | MSG_SPLICE_PAGES; + bvec_set_page(&bvec, p, size, offset); + iov_iter_bvec(&mh.msg_iter, ITER_SOURCE, &bvec, 1, size); + + ret = tcp_sendmsg_locked(sk, &mh, size); + if (ret != size) { + if (ret > 0) { + sk_mem_uncharge(sk, ret); + sg->offset += ret; + sg->length -= ret; + size -= ret; + offset += ret; + goto retry; + } + ctx->tx.in_tcp_sendpages = false; + return ret; + } + + sk_mem_uncharge(sk, ret); + msg->sg.size -= size; + put_page(p); + sk_msg_iter_next(msg, start); + if (msg->sg.start == msg->sg.end) + break; + } + + clear_bit(TCP_COMP_SEND_PENDING, &ctx->flags); + ctx->tx.in_tcp_sendpages = false; + + return 0; +} + +static int tcp_comp_push(struct sock *sk, int bytes, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int ret; + + ret = tcp_comp_compress_to_msg(sk, bytes); + if (ret < 0) { + pr_debug("%s: failed to compress sg\n", __func__); + return ret; + } + + set_bit(TCP_COMP_SEND_PENDING, &ctx->flags); + + ret = tcp_comp_push_msg(sk, &ctx->tx.msg, flags); + if (ret) { + pr_debug("%s: failed to tcp_comp_push_sg\n", __func__); + return ret; + } + + return 0; +} + +static int wait_on_pending_writer(struct sock *sk, long *timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + add_wait_queue(sk_sleep(sk), &wait); + while (1) { + if (!*timeo) { + ret = -EAGAIN; + break; + } + + if (signal_pending(current)) { + ret = sock_intr_errno(*timeo); + break; + } + + if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + break; + } + remove_wait_queue(sk_sleep(sk), &wait); + + return ret; +} + +static int tcp_comp_push_pending_msg(struct sock *sk, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_msg *msg = &ctx->tx.msg; + + if (msg->sg.start == msg->sg.end) + return 0; + + return tcp_comp_push_msg(sk, msg, flags); +} + +static int tcp_comp_complete_pending_work(struct sock *sk, int flags, + long *timeo) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int ret = 0; + + if (unlikely(sk->sk_write_pending)) + ret = wait_on_pending_writer(sk, timeo); + + if (!ret && tcp_comp_is_write_pending(ctx)) + ret = tcp_comp_push_pending_msg(sk, flags); + + return ret; +} + +static int tcp_comp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + int copied = 0, err = 0; + size_t try_to_copy; + int required_size; + long timeo; + + lock_sock(sk); + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + err = tcp_comp_complete_pending_work(sk, msg->msg_flags, &timeo); + if (err) + goto out_err; + + while (msg_data_left(msg)) { + if (sk->sk_err) { + err = -sk->sk_err; + goto out_err; + } + + try_to_copy = msg_data_left(msg); + if (try_to_copy > TCP_COMP_SCRATCH_SIZE) + try_to_copy = TCP_COMP_SCRATCH_SIZE; + required_size = try_to_copy + TCP_COMP_MAX_PADDING; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; + +alloc_compressed: + err = alloc_compressed_msg(sk, required_size); + if (err) { + if (err != -ENOSPC) + goto wait_for_memory; + goto out_err; + } + + err = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy); + if (err < 0) + goto out_err; + + copied += try_to_copy; + + err = tcp_comp_push(sk, try_to_copy, msg->msg_flags); + if (err < 0) { + if (err == -ENOMEM) + goto wait_for_memory; + if (err != -EAGAIN) + tcp_comp_err_abort(sk, EBADMSG); + goto out_err; + } + + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto out_err; + if (ctx->tx.msg.sg.size < required_size) + goto alloc_compressed; + } + +out_err: + err = sk_stream_error(sk, msg->msg_flags, err); + + release_sock(sk); + + return copied ? copied : err; +} + +static struct sk_buff *comp_wait_data(struct sock *sk, int flags, + long timeo, int *err) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct sk_buff *skb; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + + while (!(skb = ctx->rx.pkt)) { + if (sk->sk_err) { + *err = sock_error(sk); + return NULL; + } + + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->rx.strp); + if (ctx->rx.pkt) + return ctx->rx.pkt; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + + if (sock_flag(sk, SOCK_DONE)) + return NULL; + + if ((flags & MSG_DONTWAIT) || !timeo) { + *err = -EAGAIN; + return NULL; + } + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + sk_wait_event(sk, &timeo, ctx->rx.pkt != skb, &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + + /* Handle signals */ + if (signal_pending(current)) { + *err = sock_intr_errno(timeo); + return NULL; + } + } + + return skb; +} + +static bool comp_advance_skb(struct sock *sk, struct sk_buff *skb, + unsigned int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + + /* Finished with message */ + ctx->rx.pkt = NULL; + kfree_skb(skb); + __strp_unpause(&ctx->rx.strp); + + return true; +} + +static bool comp_advance_dskb(struct sock *sk, struct sk_buff *skb, + unsigned int len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + + /* Finished with message */ + ctx->rx.dpkt = NULL; + kfree_skb(skb); + return true; +} + +static int tcp_comp_rx_context_init(struct tcp_comp_context *ctx) +{ + int dsize; + + dsize = zstd_dstream_workspace_bound(TCP_COMP_MAX_INPUT); + if (dsize <= 0) + return -EINVAL; + + ctx->rx.dworkspace = kmalloc(dsize, GFP_KERNEL); + if (!ctx->rx.dworkspace) + return -ENOMEM; + + ctx->rx.dstream = zstd_init_dstream(TCP_COMP_MAX_INPUT, + ctx->rx.dworkspace, dsize); + if (!ctx->rx.dstream) + goto err_dstream; + + ctx->rx.plaintext_data = kvmalloc(TCP_COMP_MAX_CSIZE * 32, GFP_KERNEL); + if (!ctx->rx.plaintext_data) + goto err_dstream; + + return 0; + +err_dstream: + kfree(ctx->rx.dworkspace); + ctx->rx.dworkspace = NULL; + + return -ENOMEM; +} + +static void *tcp_comp_get_rx_stream(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx->rx.plaintext_data) + tcp_comp_rx_context_init(ctx); + + return ctx->rx.plaintext_data; +} + +static int tcp_comp_decompress(struct sock *sk, struct sk_buff *skb, int flags) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm = strp_msg(skb); + size_t ret, compressed_len = 0; + int nr_frags_over = 0; + ZSTD_outBuffer outbuf; + ZSTD_inBuffer inbuf; + struct sk_buff *nskb; + int len, plen; + void *to; + + to = tcp_comp_get_rx_stream(sk); + if (!to) + return -ENOSPC; + + if (skb_linearize_cow(skb)) + return -ENOMEM; + + nskb = skb_copy(skb, GFP_KERNEL); + if (!nskb) + return -ENOMEM; + + while (compressed_len < (skb->len - rxm->offset)) { + if (skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS) + break; + + len = 0; + plen = skb->len - rxm->offset - compressed_len; + if (plen > TCP_COMP_MAX_CSIZE) + plen = TCP_COMP_MAX_CSIZE; + + inbuf.src = (char *)skb->data + rxm->offset + compressed_len; + inbuf.pos = 0; + inbuf.size = plen; + + outbuf.dst = ctx->rx.plaintext_data; + outbuf.pos = 0; + outbuf.size = MAX_SKB_FRAGS * TCP_COMP_DATA_SIZE; + outbuf.size -= skb_shinfo(nskb)->nr_frags * TCP_COMP_DATA_SIZE; + + ret = ZSTD_decompressStream(ctx->rx.dstream, &outbuf, &inbuf); + if (ZSTD_isError(ret)) { + kfree_skb(nskb); + return -EIO; + } + + if (!compressed_len) { + len = outbuf.pos - skb->len; + if (len > skb_tailroom(nskb)) + len = skb_tailroom(nskb); + + __skb_put(nskb, len); + + len += skb->len; + skb_copy_to_linear_data(nskb, to, len); + } + + while ((to += len, outbuf.pos -= len) > 0) { + struct page *pages; + skb_frag_t *frag; + + if (skb_shinfo(nskb)->nr_frags >= MAX_SKB_FRAGS) { + nr_frags_over = 1; + break; + } + + frag = skb_shinfo(nskb)->frags + + skb_shinfo(nskb)->nr_frags; + pages = alloc_pages(__GFP_NOWARN | GFP_KERNEL | __GFP_COMP, + TCP_COMP_ALLOC_ORDER); + if (!pages) { + kfree_skb(nskb); + return -ENOMEM; + } + + frag->bv_page = pages; + len = PAGE_SIZE << TCP_COMP_ALLOC_ORDER; + if (outbuf.pos < len) + len = outbuf.pos; + + frag->bv_offset = 0; + skb_frag_size_set(frag, len); + memcpy(skb_frag_address(frag), to, len); + + nskb->truesize += len; + nskb->data_len += len; + nskb->len += len; + skb_shinfo(nskb)->nr_frags++; + } + + if (nr_frags_over) + break; + + compressed_len += inbuf.pos; + } + + ctx->rx.dpkt = nskb; + rxm = strp_msg(nskb); + rxm->full_len = nskb->len; + rxm->offset = 0; + comp_advance_skb(sk, skb, compressed_len); + + return 0; +} + +static int tcp_comp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int flags, int *addr_len) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + struct strp_msg *rxm; + struct sk_buff *skb; + ssize_t copied = 0; + int target, err = 0; + long timeo; + + if (unlikely(flags & MSG_ERRQUEUE)) + return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); + + lock_sock(sk); + + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + timeo = sock_rcvtimeo(sk, flags & MSG_WAITALL); + + do { + int chunk = 0; + + if (!ctx->rx.dpkt) { + skb = comp_wait_data(sk, flags, timeo, &err); + if (!skb) + goto recv_end; + + err = tcp_comp_decompress(sk, skb, flags); + if (err < 0) { + goto recv_end; + } + } + + skb = ctx->rx.dpkt; + rxm = strp_msg(skb); + chunk = min_t(unsigned int, rxm->full_len, len); + err = skb_copy_datagram_msg(skb, rxm->offset, msg, + chunk); + if (err < 0) + goto recv_end; + + copied += chunk; + len -= chunk; + if (likely(!(flags & MSG_PEEK))) + comp_advance_dskb(sk, skb, chunk); + else + break; + + if (copied >= target && !ctx->rx.dpkt) + break; + } while (len > 0); + +recv_end: + release_sock(sk); + return copied ? : err; +} + +bool comp_stream_read(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx) + return false; + + if (ctx->rx.pkt || ctx->rx.dpkt) + return true; + + return false; +} + +static void comp_data_ready(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + strp_data_ready(&ctx->rx.strp); +} + +static void comp_queue(struct strparser *strp, struct sk_buff *skb) +{ + struct tcp_comp_context *ctx = comp_get_ctx(strp->sk); + + ctx->rx.pkt = skb; + strp_pause(strp); + ctx->rx.saved_data_ready(strp->sk); +} + +static int comp_read_size(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + + if (rxm->offset > skb->len) + return 0; + + return skb->len - rxm->offset; +} + +void comp_setup_strp(struct sock *sk, struct tcp_comp_context *ctx) +{ + struct strp_callbacks cb; + + memset(&cb, 0, sizeof(cb)); + cb.rcv_msg = comp_queue; + cb.parse_msg = comp_read_size; + strp_init(&ctx->rx.strp, sk, &cb); + + write_lock_bh(&sk->sk_callback_lock); + ctx->rx.saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = comp_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&ctx->rx.strp); +} + +static void tcp_comp_write_space(struct sock *sk) +{ + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (ctx->tx.in_tcp_sendpages) { + ctx->sk_write_space(sk); + return; + } + + if (!sk->sk_write_pending && tcp_comp_is_write_pending(ctx)) { + gfp_t sk_allocation = sk->sk_allocation; + int rc; + + sk->sk_allocation = GFP_ATOMIC; + rc = tcp_comp_push_pending_msg(sk, MSG_DONTWAIT | MSG_NOSIGNAL); + sk->sk_allocation = sk_allocation; + + if (rc < 0) + return; + } + + ctx->sk_write_space(sk); +} + +void tcp_init_compression(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_comp_context *ctx = NULL; + struct sk_msg *msg = NULL; + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->rx_opt.comp_ok) + return; + + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return; + + msg = &ctx->tx.msg; + sk_msg_init(msg); + + ctx->sk_write_space = sk->sk_write_space; + ctx->sk_proto = sk->sk_prot; + WRITE_ONCE(sk->sk_prot, &tcp_prot_override); + sk->sk_write_space = tcp_comp_write_space; + + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + + sock_set_flag(sk, SOCK_COMP); + comp_setup_strp(sk, ctx); +} + +static void tcp_comp_context_tx_free(struct tcp_comp_context *ctx) +{ + kfree(ctx->tx.cworkspace); + ctx->tx.cworkspace = NULL; + + kvfree(ctx->tx.plaintext_data); + ctx->tx.plaintext_data = NULL; + + kvfree(ctx->tx.compressed_data); + ctx->tx.compressed_data = NULL; +} + +static void tcp_comp_context_rx_free(struct tcp_comp_context *ctx) +{ + kfree(ctx->rx.dworkspace); + ctx->rx.dworkspace = NULL; + + kvfree(ctx->rx.plaintext_data); + ctx->rx.plaintext_data = NULL; +} + +static void tcp_comp_context_free(struct rcu_head *head) +{ + struct tcp_comp_context *ctx; + + ctx = container_of(head, struct tcp_comp_context, rcu); + + tcp_comp_context_tx_free(ctx); + tcp_comp_context_rx_free(ctx); + strp_done(&ctx->rx.strp); + kfree(ctx); +} + +void tcp_cleanup_compression(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_comp_context *ctx = comp_get_ctx(sk); + + if (!ctx || !sock_flag(sk, SOCK_COMP)) + return; + + if (ctx->rx.pkt) { + kfree_skb(ctx->rx.pkt); + ctx->rx.pkt = NULL; + } + + if (ctx->rx.dpkt) { + kfree_skb(ctx->rx.dpkt); + ctx->rx.dpkt = NULL; + } + strp_stop(&ctx->rx.strp); + + rcu_assign_pointer(icsk->icsk_ulp_data, NULL); + call_rcu(&ctx->rcu, tcp_comp_context_free); +} + +int tcp_comp_init(void) +{ + tcp_prot_override = tcp_prot; + tcp_prot_override.sendmsg = tcp_comp_sendmsg; + tcp_prot_override.recvmsg = tcp_comp_recvmsg; + tcp_prot_override.sock_is_readable = comp_stream_read; + + return 0; +} diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fd5c13c1fbc8..a5adf4822663 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4012,6 +4012,24 @@ static bool smc_parse_options(const struct tcphdr *th, return false; } +static bool tcp_parse_comp_option(const struct tcphdr *th, + struct tcp_options_received *opt_rx, + const unsigned char *ptr, + int opsize) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (th->syn && !(opsize & 1) && + opsize >= TCPOLEN_EXP_COMP_BASE && + get_unaligned_be16(ptr) == TCPOPT_COMP_MAGIC) { + opt_rx->comp_ok = 1; + return true; + } + } +#endif + return false; +} + /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped * value on success. */ @@ -4171,6 +4189,10 @@ void tcp_parse_options(const struct net *net, if (smc_parse_options(th, opt_rx, ptr, opsize)) break; + if (tcp_parse_comp_option(th, opt_rx, ptr, + opsize)) + break; + opt_rx->saw_unknown = 1; break; @@ -6097,6 +6119,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) /* Initialize congestion control unless BPF initialized it already: */ if (!icsk->icsk_ca_initialized) tcp_init_congestion_control(sk); + tcp_init_compression(sk); tcp_init_buffer_space(sk); } @@ -6835,6 +6858,9 @@ static void tcp_openreq_init(struct request_sock *req, ireq->smc_ok = rx_opt->smc_ok && !(tcp_sk(sk)->smc_hs_congested && tcp_sk(sk)->smc_hs_congested(sk)); #endif +#if IS_ENABLED(CONFIG_TCP_COMP) + ireq->comp_ok = rx_opt->comp_ok; +#endif } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4167e8a48b60..9cbf23c1c039 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2304,6 +2304,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cleanup_congestion_control(sk); + tcp_cleanup_compression(sk); + tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b98d476f1594..d67a84c114ce 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -543,6 +543,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_ssthresh = req->rsk_rcv_wnd; newtp->rcv_wnd = req->rsk_rcv_wnd; newtp->rx_opt.wscale_ok = ireq->wscale_ok; +#if IS_ENABLED(CONFIG_TCP_COMP) + newtp->rx_opt.comp_ok = ireq->comp_ok; +#endif if (newtp->rx_opt.wscale_ok) { newtp->rx_opt.snd_wscale = ireq->snd_wscale; newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1917c62ad3bf..eee34f6c7643 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -422,6 +422,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) +#define OPTION_COMP BIT(11) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -438,6 +439,19 @@ static void smc_options_write(__be32 *ptr, u16 *options) #endif } +static void comp_options_write(__be32 *ptr, u16 *options) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (unlikely(OPTION_COMP & *options)) { + *ptr++ = htonl((TCPOPT_EXP << 24) | + (TCPOLEN_EXP_COMP_BASE << 16) | + (TCPOPT_COMP_MAGIC)); + } + } +#endif +} + struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ @@ -711,6 +725,8 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, smc_options_write(ptr, &options); mptcp_options_write(th, ptr, tp, opts); + + comp_options_write(ptr, &options); } static void smc_set_option(const struct tcp_sock *tp, @@ -729,6 +745,39 @@ static void smc_set_option(const struct tcp_sock *tp, #endif } +static void comp_set_option(struct sock *sk, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (tcp_syn_comp_enabled(sk)) { + if (*remaining >= TCPOLEN_EXP_COMP_BASE) { + opts->options |= OPTION_COMP; + *remaining -= TCPOLEN_EXP_COMP_BASE; + } + } + } +#endif +} + +static void comp_set_option_cond(struct sock *sk, + const struct inet_request_sock *ireq, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_TCP_COMP) + if (static_branch_unlikely(&tcp_have_comp)) { + if (tcp_synack_comp_enabled(sk, ireq)) { + if (*remaining >= TCPOLEN_EXP_COMP_BASE) { + opts->options |= OPTION_COMP; + *remaining -= TCPOLEN_EXP_COMP_BASE; + } + } + } +#endif +} + static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, @@ -830,6 +879,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } smc_set_option(tp, opts, &remaining); + comp_set_option(sk, opts, &remaining); if (sk_is_mptcp(sk)) { unsigned int size; @@ -910,6 +960,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + comp_set_option_cond((struct sock *)sk, ireq, opts, &remaining); + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8698b49dfc8d..d17389f1afe0 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -217,6 +217,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) treq->txhash = net_tx_rndhash(); if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; + if (IS_ENABLED(CONFIG_TCP_COMP)) + ireq->comp_ok = 0; /* * We need to lookup the dst_entry to get the correct window size. -- 2.34.1

2 1

[PATCH OLK-6.6 v2] nbd: get config_lock before sock_shutdown
by Li Lingfeng 28 Dec '23

28 Dec '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8S2P0 CVE: NA ---------------------------------------- Config->socks in sock_shutdown may trigger a UAF problem. The reason is that sock_shutdown does not hold the config_lock, so that nbd_ioctl can release config->socks at this time. T0: NBD_SET_SOCK T1: NBD_DO_IT T0 T1 nbd_ioctl mutex_lock(&nbd->config_lock) // get lock __nbd_ioctl nbd_start_device_ioctl nbd_start_device mutex_unlock(&nbd->config_lock) // relase lock wait_event_interruptible (kill, enter sock_shutdown) sock_shutdown nbd_ioctl mutex_lock(&nbd->config_lock) // get lock __nbd_ioctl nbd_add_socket krealloc kfree(p) //config->socks is NULL nbd_sock *nsock = config->socks // error Fix it by moving config_lock up before sock_shutdown. Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- v1->v2: update bugzilla. drivers/block/nbd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b99c169890d5..91b1f3bff364 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1417,13 +1417,18 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd) mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); + + /* + * recv_work in flush_workqueue will not get this lock, because nbd_open + * will hold nbd->config_refs + */ + mutex_lock(&nbd->config_lock); if (ret) { sock_shutdown(nbd); nbd_clear_que(nbd); } flush_workqueue(nbd->recv_workq); - mutex_lock(&nbd->config_lock); nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) -- 2.31.1

2 1

[PATCH v2 OLK-6.6 0/1] iommu: Enable smmu-v3 when 3408iMR/3416iMRraid card exist
by zhangnaichuan 28 Dec '23

28 Dec '23

arm64 cannot support virtualization pass-through feature when using the 3408iMR/3416iMR raid card. For solving the problem, we add two fuctions: 1.we prepare init bypass level2 entry for specific devices when smmu uses 2 level streamid entry. 2.we add smmu.bypassdev cmdline to allow SMMU bypass streams for some specific devices. usage: 3408iMRraid: smmu.bypassdev=0x1000:0x17 3416iMRraid: smmu.bypassdev=0x1000:0x15 drivers/iommu/Kconfig | 9 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 120 +++++++++++++++++++- 2 files changed, 128 insertions(+), 1 deletion(-) -- 2.33.0

2 2

[PATCH v3 OLK-6.6 0/1] x86/kdump: add log before booting crash kernel
by zhangnaichuan 28 Dec '23

28 Dec '23

description: Just like arm64, print "Bye!" before booting crash kernel. arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.33.0

2 2

[PATCH v2 OLK-6.6 0/1] x86/kdump: add log before booting crash kernel
by zhangnaichuan 28 Dec '23

28 Dec '23

description: Just like arm64, print "Bye!" before booting crash kernel. arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.33.0

2 2

[PATCH OLK-6.6] arm64: topology: Support PHYTIUM CPU
by Zeng Heng 28 Dec '23

28 Dec '23

From: Hanjun Guo <guohanjun(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CGER CVE: NA --------------------------- Add the support for PHYTIUM topology detect, it's better use PPTT ACPI table to report the topology, but we can live with it at now. Signed-off-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: drivers/base/arch_topology.c Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- arch/arm64/include/asm/cputype.h | 1 + drivers/base/arch_topology.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 202588ad92e8..8629961ad39b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_PHYTIUM 0x70 #define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index b741b5ba82bd..0db635e94492 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -862,6 +862,14 @@ void store_cpu_topology(unsigned int cpuid) cpuid_topo->core_id = cpuid; cpuid_topo->package_id = cpu_to_node(cpuid); +#if defined(CONFIG_ARM64) + if (read_cpuid_implementor() == ARM_CPU_IMP_PHYTIUM) { + cpuid_topo->thread_id = 0; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = 0; + } +#endif + pr_debug("CPU%u: package %d core %d thread %d\n", cpuid, cpuid_topo->package_id, cpuid_topo->core_id, cpuid_topo->thread_id); -- 2.25.1

2 1

[PATCH OLK-6.6 V1 00/13] sched: steal tasks to improve CPU utilization
by Cheng Yu 28 Dec '23

28 Dec '23

steal tasks to improve CPU utilization Cheng Jian (3): disable stealing by default sched/fair: introduce SCHED_STEAL config: enable CONFIG_SCHED_STEAL by default Steve Sistare (10): sched: Provide sparsemask, a reduced contention bitmap sched/topology: Provide hooks to allocate data shared per LLC sched/topology: Provide cfs_overload_cpus bitmap sched/fair: Dynamically update cfs_overload_cpus sched/fair: Hoist idle_stamp up from idle_balance sched/fair: Generalize the detach_task interface sched/fair: Provide can_migrate_task_llc sched/fair: Steal work from an overloaded CPU when CPU goes idle sched/fair: disable stealing if too many NUMA nodes sched/fair: Provide idle search schedstats arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched/topology.h | 3 + init/Kconfig | 15 ++ kernel/sched/core.c | 35 ++- kernel/sched/fair.c | 360 +++++++++++++++++++++++-- kernel/sched/features.h | 8 + kernel/sched/sched.h | 21 ++ kernel/sched/sparsemask.h | 210 +++++++++++++++ kernel/sched/stats.c | 15 ++ kernel/sched/stats.h | 20 ++ kernel/sched/topology.c | 141 +++++++++- 12 files changed, 804 insertions(+), 26 deletions(-) create mode 100644 kernel/sched/sparsemask.h -- 2.25.1

2 14

[PATCH OLK-6.6] acpi: acpica: fix acpi parse and parseext cache leaks
by Zeng Heng 28 Dec '23

28 Dec '23

From: Seunghun Han <kkamagui(a)gmail.com> hulk inclusion category: bugfix bugzilla: 180974 https://gitee.com/openeuler/kernel/issues/I4DDEL CVE: CVE-2017-13694 ------------------------------------------------- I'm Seunghun Han, and I work for National Security Research Institute of South Korea. I have been doing a research on ACPI and found an ACPI cache leak in ACPI early abort cases. Boot log of ACPI cache leak is as follows: [ 0.352414] ACPI: Added _OSI(Module Device) [ 0.353182] ACPI: Added _OSI(Processor Device) [ 0.353182] ACPI: Added _OSI(3.0 _SCP Extensions) [ 0.353182] ACPI: Added _OSI(Processor Aggregator Device) [ 0.356028] ACPI: Unable to start the ACPI Interpreter [ 0.356799] ACPI Error: Could not remove SCI handler (20170303/evmisc-281) [ 0.360215] kmem_cache_destroy Acpi-State: Slab cache still has objects [ 0.360648] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.12.0-rc4-next-20170608+ #10 [ 0.361273] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 0.361873] Call Trace: [ 0.362243] ? dump_stack+0x5c/0x81 [ 0.362591] ? kmem_cache_destroy+0x1aa/0x1c0 [ 0.362944] ? acpi_sleep_proc_init+0x27/0x27 [ 0.363296] ? acpi_os_delete_cache+0xa/0x10 [ 0.363646] ? acpi_ut_delete_caches+0x6d/0x7b [ 0.364000] ? acpi_terminate+0xa/0x14 [ 0.364000] ? acpi_init+0x2af/0x34f [ 0.364000] ? __class_create+0x4c/0x80 [ 0.364000] ? video_setup+0x7f/0x7f [ 0.364000] ? acpi_sleep_proc_init+0x27/0x27 [ 0.364000] ? do_one_initcall+0x4e/0x1a0 [ 0.364000] ? kernel_init_freeable+0x189/0x20a [ 0.364000] ? rest_init+0xc0/0xc0 [ 0.364000] ? kernel_init+0xa/0x100 [ 0.364000] ? ret_from_fork+0x25/0x30 I analyzed this memory leak in detail. I found that “Acpi-State” cache and “Acpi-Parse” cache were merged because the size of cache objects was same slab cache size. I finally found “Acpi-Parse” cache and “Acpi-ParseExt” cache were leaked using SLAB_NEVER_MERGE flag in kmem_cache_create() function. Real ACPI cache leak point is as follows: [ 0.360101] ACPI: Added _OSI(Module Device) [ 0.360101] ACPI: Added _OSI(Processor Device) [ 0.360101] ACPI: Added _OSI(3.0 _SCP Extensions) [ 0.361043] ACPI: Added _OSI(Processor Aggregator Device) [ 0.364016] ACPI: Unable to start the ACPI Interpreter [ 0.365061] ACPI Error: Could not remove SCI handler (20170303/evmisc-281) [ 0.368174] kmem_cache_destroy Acpi-Parse: Slab cache still has objects [ 0.369332] CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 4.12.0-rc4-next-20170608+ #8 [ 0.371256] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 0.372000] Call Trace: [ 0.372000] ? dump_stack+0x5c/0x81 [ 0.372000] ? kmem_cache_destroy+0x1aa/0x1c0 [ 0.372000] ? acpi_sleep_proc_init+0x27/0x27 [ 0.372000] ? acpi_os_delete_cache+0xa/0x10 [ 0.372000] ? acpi_ut_delete_caches+0x56/0x7b [ 0.372000] ? acpi_terminate+0xa/0x14 [ 0.372000] ? acpi_init+0x2af/0x34f [ 0.372000] ? __class_create+0x4c/0x80 [ 0.372000] ? video_setup+0x7f/0x7f [ 0.372000] ? acpi_sleep_proc_init+0x27/0x27 [ 0.372000] ? do_one_initcall+0x4e/0x1a0 [ 0.372000] ? kernel_init_freeable+0x189/0x20a [ 0.372000] ? rest_init+0xc0/0xc0 [ 0.372000] ? kernel_init+0xa/0x100 [ 0.372000] ? ret_from_fork+0x25/0x30 [ 0.388039] kmem_cache_destroy Acpi-ParseExt: Slab cache still has objects [ 0.389063] CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 4.12.0-rc4-next-20170608+ #8 [ 0.390557] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 0.392000] Call Trace: [ 0.392000] ? dump_stack+0x5c/0x81 [ 0.392000] ? kmem_cache_destroy+0x1aa/0x1c0 [ 0.392000] ? acpi_sleep_proc_init+0x27/0x27 [ 0.392000] ? acpi_os_delete_cache+0xa/0x10 [ 0.392000] ? acpi_ut_delete_caches+0x6d/0x7b [ 0.392000] ? acpi_terminate+0xa/0x14 [ 0.392000] ? acpi_init+0x2af/0x34f [ 0.392000] ? __class_create+0x4c/0x80 [ 0.392000] ? video_setup+0x7f/0x7f [ 0.392000] ? acpi_sleep_proc_init+0x27/0x27 [ 0.392000] ? do_one_initcall+0x4e/0x1a0 [ 0.392000] ? kernel_init_freeable+0x189/0x20a [ 0.392000] ? rest_init+0xc0/0xc0 [ 0.392000] ? kernel_init+0xa/0x100 [ 0.392000] ? ret_from_fork+0x25/0x30 When early abort is occurred due to invalid ACPI information, Linux kernel terminates ACPI by calling acpi_terminate() function. The function calls acpi_ut_delete_caches() function to delete local caches (acpi_gbl_namespace_ cache, state_cache, operand_cache, ps_node_cache, ps_node_ext_cache). But the deletion codes in acpi_ut_delete_caches() function only delete slab caches using kmem_cache_destroy() function, therefore the cache objects should be flushed before acpi_ut_delete_caches() function. “Acpi-Parse” cache and “Acpi-ParseExt” cache are used in an AML parse function, acpi_ps_parse_loop(). The function should have flush codes to handle an error state due to invalid AML codes. This cache leak has a security threat because an old kernel (<= 4.9) shows memory locations of kernel functions in stack dump. Some malicious users could use this information to neutralize kernel ASLR. To fix ACPI cache leak for enhancing security, I made a patch which has flush codes in acpi_ps_parse_loop() function. I hope that this patch improves the security of Linux kernel. Thank you. Signed-off-by: Seunghun Han <kkamagui(a)gmail.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/acpi/acpica/psobject.c | 53 ++++++++++------------------------ 1 file changed, 16 insertions(+), 37 deletions(-) diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index 54471083ba54..a22d5c0008d6 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -636,7 +636,8 @@ acpi_status acpi_ps_complete_final_op(struct acpi_walk_state *walk_state, union acpi_parse_object *op, acpi_status status) { - acpi_status status2; + acpi_status return_status = AE_OK; + u8 ascending = TRUE; ACPI_FUNCTION_TRACE_PTR(ps_complete_final_op, walk_state); @@ -650,7 +651,8 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state, op)); do { if (op) { - if (walk_state->ascending_callback != NULL) { + if (ascending && + walk_state->ascending_callback != NULL) { walk_state->op = op; walk_state->op_info = acpi_ps_get_opcode_info(op->common. @@ -672,49 +674,26 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state, } if (status == AE_CTRL_TERMINATE) { - status = AE_OK; - - /* Clean up */ - do { - if (op) { - status2 = - acpi_ps_complete_this_op - (walk_state, op); - if (ACPI_FAILURE - (status2)) { - return_ACPI_STATUS - (status2); - } - } - - acpi_ps_pop_scope(& - (walk_state-> - parser_state), - &op, - &walk_state-> - arg_types, - &walk_state-> - arg_count); - - } while (op); - - return_ACPI_STATUS(status); + ascending = FALSE; + return_status = AE_CTRL_TERMINATE; } else if (ACPI_FAILURE(status)) { /* First error is most important */ - (void) - acpi_ps_complete_this_op(walk_state, - op); - return_ACPI_STATUS(status); + ascending = FALSE; + return_status = status; } } - status2 = acpi_ps_complete_this_op(walk_state, op); - if (ACPI_FAILURE(status2)) { - return_ACPI_STATUS(status2); + status = acpi_ps_complete_this_op(walk_state, op); + if (ACPI_FAILURE(status)) { + ascending = FALSE; + if (ACPI_SUCCESS(return_status) || + return_status == AE_CTRL_TERMINATE) { + return_status = status; + } } } @@ -724,5 +703,5 @@ acpi_ps_complete_final_op(struct acpi_walk_state *walk_state, } while (op); - return_ACPI_STATUS(status); + return_ACPI_STATUS(return_status); } -- 2.25.1

2 1

[PATCH OLK-6.6] pci: Enable acs for QLogic HBA cards
by Zeng Heng 28 Dec '23

28 Dec '23

From: Xishi Qiu <qiuxishi(a)huawei.com> euler inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4K05G?from=project-issue CVE: N/A ------------------------------------------------- Add support of port isolation for QLogic HBA cards. Signed-off-by: Xishi Qiu <qiuxishi(a)huawei.com> Signed-off-by: Fang Ying <fangying1(a)huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Hui Wang <john.wanghui(a)huawei.com> Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Confilicts: drivers/pci/quirks.c Signed-off-by: Xuefeng Wang <wxf.wang(a)hisilicon.com> Reviewed-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Confilicts: drivers/pci/quirks.c Reviewed-by: wangxiongfeng <wangxiongfeng2(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/pci/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index ae95d0950772..83a875b53111 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5050,6 +5050,8 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_intel_spt_pch_acs }, { 0x19a2, 0x710, pci_quirk_mf_endpoint_acs }, /* Emulex BE3-R */ { 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */ + { 0x1077, 0x2031, pci_quirk_mf_endpoint_acs}, /* QLogic QL2672 */ + { 0x1077, 0x2532, pci_quirk_mf_endpoint_acs}, /* Cavium ThunderX */ { PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs }, /* Cavium multi-function devices */ -- 2.25.1

2 1

[PATCH OLK-6.6] Revert "posix-cpu-timers: Make timespec to nsec conversion safe"
by Zeng Heng 28 Dec '23

28 Dec '23

From: Yuyao Lin <linyuyao1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I61XP8 -------------------------------- This reverts commit 098b0e01a91c42aaaf0425605cd126b03fcb0bcf. Function timespec64_to_ns() Add the upper and lower limits check in commit cb47755725da ("time: Prevent undefined behaviour in timespec64_to_ns()"), timespec64_to_ktime() only check the upper limits,so revert this patch can fix overflow. Signed-off-by: Yuyao Lin <linyuyao1(a)huawei.com> Reviewed-by: Wei Li <liwei391(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- kernel/time/posix-cpu-timers.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index e9c6f9d0e42c..5996e7323c81 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -642,11 +642,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, return -ESRCH; } - /* - * Use the to_ktime conversion because that clamps the maximum - * value to KTIME_MAX and avoid multiplication overflows. - */ - new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); + new_expires = timespec64_to_ns(&new->it_value); /* * Protect against sighand release/switch in exit/exec and p->cpu_timers -- 2.25.1

2 1

[PATCH OLK-6.6 0/2] KABI reservation for IMA and crypto
by GUO Zihua 28 Dec '23

28 Dec '23

2 3

[PATCH OLK-6.6 0/2] Make the cpuinfo_cur_freq interface read correctly
by Zeng Heng 28 Dec '23

28 Dec '23

Patch 1~2: It is required to ensure that amu can continue to work normally during the sample period while cstate is enabled. Zeng Heng (2): arm64: cpufeature: Export cpu_has_amu_feat() cpufreq: CPPC: Keep the target core awake when reading its cpufreq rate arch/arm64/kernel/cpufeature.c | 1 + drivers/cpufreq/cppc_cpufreq.c | 39 ++++++++++++++++++++++++++-------- 2 files changed, 31 insertions(+), 9 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6] x86/boot/compressed: Register dummy NMI handler in EFI boot loader, to avoid kdump crashes
by Zeng Heng 28 Dec '23

28 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69VF6 CVE: NA -------------------------------- If kdump is enabled, when using mce_inject to inject errors, EFI boot loader would decompress & load second kernel for saving the vmcore file. For normal errors that is fine. However, in the MCE case, the panic CPU that firstly enters into mce_panic() is running within NMI interrupt context, and the processor blocks delivery of subsequent NMIs until the next execution of the IRET instruction. When the panic CPU takes long time in the panic processing route, and causes the watchdog timeout, at this moment, the processor already receives NMI interrupt in the background. In the reproducer sequence below, panic CPU would run into EFI loader and raise page fault exception (like visiting `vidmem` variable when attempting to call debug_putstr()), the CPU would execute IRET instruction when it exits from the page fault handler. But the loader never registers handler for NMI vector in IDT, lack of vector handler would cause reboot, which interrupts kdump procedure and fails to save the vmcore file. Here is steps to reproduce the above issue (it's sporadic): 1. # cat uncorrected CPU 1 BANK 4 STATUS uncorrected 0xc0 MCGSTATUS EIPV MCIP ADDR 0x1234 RIP 0xdeadbabe RAISINGCPU 0 MCGCAP SER CMCI TES 0x6 2. # modprobe mce_inject 3. # mce-inject uncorrected For increasing the probability of reproduction of this issue, there are two ways to increase the probability of the bug: 1. modify the threshold value of watchdog (increase NMI frequency); 2. and/or add delays before panic() in mce_panic() and modify PANIC_TIMEOUT macro; Fixes: ca0e22d4f011 ("x86/boot/compressed/64: Always switch to own page table") Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> [ Tidy up changelog, add comments. ] Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Link: https://lore.kernel.org/r/20230110102745.2514694-1-zengheng4@huawei.com --- arch/x86/boot/compressed/ident_map_64.c | 13 +++++++++++++ arch/x86/boot/compressed/idt_64.c | 1 + arch/x86/boot/compressed/idt_handlers_64.S | 1 + arch/x86/boot/compressed/misc.h | 1 + 4 files changed, 16 insertions(+) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 08f93b0401bb..dc0ec27ff1b1 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -385,3 +385,16 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ kernel_add_identity_map(address, end); } + +void do_boot_nmi_fault(struct pt_regs *regs, unsigned long error_code) +{ + /* + * Default boot loader placeholder fault handler - there's no real + * kernel running yet, so there's not much we can do - but NMIs + * can arrive in a kdump scenario, for example by the NMI watchdog. + * + * Not having any handler would cause the CPU to silently reboot, + * so we do the second-worst thing here and ignore the NMI. + */ + debug_putstr("nmi fault raise\n"); +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 3cdf94b41456..0f3318bdf262 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -60,6 +60,7 @@ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; + set_idt_entry(X86_TRAP_NMI, boot_nmi_fault); set_idt_entry(X86_TRAP_PF, boot_page_fault); #ifdef CONFIG_AMD_MEM_ENCRYPT diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199f5b..2aef8e1b515b 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -69,6 +69,7 @@ SYM_FUNC_END(\name) .text .code64 +EXCEPTION_HANDLER boot_nmi_fault do_boot_nmi_fault error_code=0 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 #ifdef CONFIG_AMD_MEM_ENCRYPT diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index cc70d3fb9049..f06fb86b83bc 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -196,6 +196,7 @@ static inline void cleanup_exception_handling(void) { } #endif /* IDT Entry Points */ +void boot_nmi_fault(void); void boot_page_fault(void); void boot_stage1_vc(void); void boot_stage2_vc(void); -- 2.25.1

2 1

[PATCH OLK-6.6 0/3] memcg: support OOM priority for memcg
by Jinjiang Tu 28 Dec '23

28 Dec '23

Support memcg oom priority. Changelog: * rename CONFIG_MEMCG_QOS to CONFIG_MEMCG_OOM_PRIORITY * move CONFIG_MEMCG_OOM_PRIORITY to init/Kconfig * set CONFIG_MEMCG_OOM_PRIORITY default from y to n, and enable it in openeuler_defconfig * add rcu_read_lock() protection for mem_cgroup_from_task() * Instead of static key, use variable to check if the feature is enabled * use READ_ONCE/WRITE_ONCE protection when read/write oom_prio * cleanup Jing Xiangfeng (3): memcg: support priority for oom memcg: Add sysctl memcg_qos_enable memcg: enable CONFIG_MEMCG_OOM_PRIORITY by default arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/memcontrol.h | 25 +++ init/Kconfig | 14 ++ mm/memcontrol.c | 222 +++++++++++++++++++++++++ mm/oom_kill.c | 61 ++++++- 6 files changed, 319 insertions(+), 5 deletions(-) -- 2.25.1

2 4

[PATCH OLK-5.10] jbd2: fix soft lockup in journal_finish_inode_data_buffers()
by Zizhi Wo 28 Dec '23

28 Dec '23

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v6.7-rc6 commit 6c02757c936063f0631b4e43fe156f8c8f1f351f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8RRXU?from=project-issue CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- There's issue when do io test: WARN: soft lockup - CPU#45 stuck for 11s! [jbd2/dm-2-8:4170] CPU: 45 PID: 4170 Comm: jbd2/dm-2-8 Kdump: loaded Tainted: G OE Call trace: dump_backtrace+0x0/0x1a0 show_stack+0x24/0x30 dump_stack+0xb0/0x100 watchdog_timer_fn+0x254/0x3f8 __hrtimer_run_queues+0x11c/0x380 hrtimer_interrupt+0xfc/0x2f8 arch_timer_handler_phys+0x38/0x58 handle_percpu_devid_irq+0x90/0x248 generic_handle_irq+0x3c/0x58 __handle_domain_irq+0x68/0xc0 gic_handle_irq+0x90/0x320 el1_irq+0xcc/0x180 queued_spin_lock_slowpath+0x1d8/0x320 jbd2_journal_commit_transaction+0x10f4/0x1c78 [jbd2] kjournald2+0xec/0x2f0 [jbd2] kthread+0x134/0x138 ret_from_fork+0x10/0x18 Analyzed informations from vmcore as follows: (1) There are about 5k+ jbd2_inode in 'commit_transaction->t_inode_list'; (2) Now is processing the 855th jbd2_inode; (3) JBD2 task has TIF_NEED_RESCHED flag; (4) There's no pags in address_space around the 855th jbd2_inode; (5) There are some process is doing drop caches; (6) Mounted with 'nodioread_nolock' option; (7) 128 CPUs; According to informations from vmcore we know 'journal->j_list_lock' spin lock competition is fierce. So journal_finish_inode_data_buffers() maybe process slowly. Theoretically, there is scheduling point in the filemap_fdatawait_range_keep_errors(). However, if inode's address_space has no pages which taged with PAGECACHE_TAG_WRITEBACK, will not call cond_resched(). So may lead to soft lockup. journal_finish_inode_data_buffers filemap_fdatawait_range_keep_errors __filemap_fdatawait_range while (index <= end) nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; --> If 'nr_pages' is equal zero will break, then will not call cond_resched() for (i = 0; i < nr_pages; i++) wait_on_page_writeback(page); cond_resched(); To solve above issue, add scheduling point in the journal_finish_inode_data_buffers(); Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20231211112544.3879780-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/jbd2/commit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index f082836e6d40..e782f1d42dd7 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -300,6 +300,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, if (!ret) ret = err; } + cond_resched(); spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); -- 2.39.2

2 1

[PATCH OLK-6.6 0/8] Introduce qos smt expeller for co-location
by Xia Fukun 27 Dec '23

27 Dec '23

We introduce the qos smt expeller, which lets online tasks to expel offline tasks on the smt sibling cpus, and exclusively occupy CPU resources.In this way we are able to improve QOS of online tasks in co-location. Guan Jing (8): sched: Introduce qos smt expeller for co-location sched: Implement the function of qos smt expeller sched: Add statistics for qos smt expeller sched: Add tracepoint for qos smt expeller config: Enable CONFIG_QOS_SCHED_SMT_EXPELLER sched/fair: Start tracking qos_offline tasks count in cfs_rq sched/fair: Introduce QOS_SMT_EXPELL priority reversion mechanism sched/fair: Add cmdline nosmtexpell arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched.h | 13 + include/trace/events/sched.h | 55 ++++ init/Kconfig | 9 + kernel/sched/debug.c | 5 + kernel/sched/fair.c | 345 +++++++++++++++++++++++-- kernel/sched/sched.h | 27 ++ 8 files changed, 440 insertions(+), 16 deletions(-) -- 2.34.1

2 9

[PATCH OLK-6.6 0/1] iommu: Enable smmu-v3 when 3408iMR/3416iMRraid card exist
by zhangnaichuan 27 Dec '23

27 Dec '23

arm64 cannot support virtualization pass-through feature when using the 3408iMR/3416iMR raid card. For solving the problem, we add two fuctions: 1.we prepare init bypass level2 entry for specific devices when smmu uses 2 level streamid entry. 2.we add smmu.bypassdev cmdline to allow SMMU bypass streams for some specific devices. usage: 3408iMRraid: smmu.bypassdev=0x1000:0x17 3416iMRraid: smmu.bypassdev=0x1000:0x15 drivers/iommu/Kconfig | 9 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 120 +++++++++++++++++++- 2 files changed, 128 insertions(+), 1 deletion(-) -- 2.33.0

2 2

[PATCH OLK-6.6 0/1] Support priority load balance for qos scheduler
by Song Zhang 27 Dec '23

27 Dec '23

Song Zhang (1): sched: Introduce priority load balance for qos scheduler arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + init/Kconfig | 9 +++ kernel/sched/core.c | 3 + kernel/sched/fair.c | 83 +++++++++++++++++++++++++- kernel/sched/sched.h | 3 + 6 files changed, 99 insertions(+), 1 deletion(-) -- 2.33.0

2 2

[PATCH OLK-6.6 0/1] Support priority load balance for qos scheduler
by Song Zhang 27 Dec '23

27 Dec '23

Song Zhang (1): sched: Introduce priority load balance for qos scheduler arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + init/Kconfig | 9 +++ kernel/sched/core.c | 3 + kernel/sched/fair.c | 83 +++++++++++++++++++++++++- kernel/sched/sched.h | 3 + 6 files changed, 99 insertions(+), 1 deletion(-) -- 2.33.0

2 2

[PATCH OLK-6.6 0/1] drm: fix free illegal pointer when create drm_property_blob failed
by zhangnaichuan 27 Dec '23

27 Dec '23

we get (Unable to handle kernel NULL pointer dereference at virtual address 000000000000000c) when call drm_property_blob_put(). After analysis, we get the following process: alloc failed: drm_atomic_set_mode_for_crtc() drm_property_create_blob() // failed state->mode_blob = ERR_PTR(-ENOMEM) free illegal pointer: __drm_atomic_helper_crtc_destroy_state() drm_property_blob_put(state->mode_blob) drm_mode_object_put(&blob->base); // here blob is ERR_PTR(-ENOMEM) So do we have to determine if blob is an error code before calling drm_mode_object_put(). Fixes: 6bcacf51d050 (drm: Add reference counting to blob properties) drivers/gpu/drm/drm_property.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.33.0

2 2

[PATCH OLK-6.6 V1 00/12] sched: basic infrastructure for scheduler bpf
by Guan Jing 27 Dec '23

27 Dec '23

sched: basic infrastructure for scheduler bpf Guan Jing (12): sched: programmable: Introduce bpf sched sched: programmable: Add a tag for the task sched: programmable: Add a tag for the task group sched: programmable: Add user interface of task group tag sched: programmable: Add user interface of task tag sched: basic infrastructure for scheduler bpf sched: introduce bpf_sched_enable() libbpf: add support for scheduler bpf programs bpftool: recognize scheduler programs sched: Add helper functions to get cpu statistics sched: programmable: Add hook in select_task_rq_fair() sched: programmable: Add hook in can_migrate_task() fs/proc/base.c | 64 +++++++++++++++++ include/linux/bpf_sched.h | 50 ++++++++++++++ include/linux/bpf_types.h | 4 ++ include/linux/sched.h | 38 ++++++++++ include/linux/sched_hook_defs.h | 3 + include/uapi/linux/bpf.h | 9 +++ init/init_task.c | 3 + kernel/bpf/Kconfig | 10 +++ kernel/bpf/btf.c | 1 + kernel/bpf/syscall.c | 27 ++++++++ kernel/bpf/trampoline.c | 1 + kernel/bpf/verifier.c | 11 ++- kernel/sched/bpf_sched.c | 102 +++++++++++++++++++++++++++ kernel/sched/build_utility.c | 4 ++ kernel/sched/core.c | 118 ++++++++++++++++++++++++++++++++ kernel/sched/fair.c | 46 +++++++++++++ kernel/sched/sched.h | 10 +++ scripts/bpf_doc.py | 4 ++ tools/include/uapi/linux/bpf.h | 9 +++ tools/lib/bpf/bpf.c | 1 + tools/lib/bpf/libbpf.c | 23 ++++++- tools/lib/bpf/libbpf.h | 2 + tools/lib/bpf/libbpf.map | 1 + 23 files changed, 539 insertions(+), 2 deletions(-) create mode 100644 include/linux/bpf_sched.h create mode 100644 include/linux/sched_hook_defs.h create mode 100644 kernel/sched/bpf_sched.c -- 2.34.1

2 13

[PATCH v2 OLK-6.6 0/1] x86/kdump: make crash kernel boot faster
by zhangnaichuan 27 Dec '23

27 Dec '23

description: If other cpus offline before handle the crash NMI, the waiting_for_crash_ipi can not be decreased to 0, and current cpu will wait 1 second. So break if all other cpus offline. arch/x86/kernel/reboot.c | 8 ++++++++ 1 file changed, 8 insertions(+) -- 2.33.0

2 2

[PATCH OLK-6.6 0/1] arm64: Add non nmi ipi backtrace support
by Liao Chen 27 Dec '23

27 Dec '23

From: linruizhe <linruizhe(a)huawei.com> Dependencies: CONFIG_DETECT_HUNG_TASK=y CONFIG_WATCHDOG=y Li Zhengyu (1): arm64: Add non nmi ipi backtrace support arch/arm64/kernel/ipi_nmi.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) -- 2.25.1

2 2

[PATCH OLK-6.6 0/1] x86/kdump: add log before booting crash kernel
by zhangnaichuan 27 Dec '23

27 Dec '23

description: Just like arm64, print "Bye!" before booting crash kernel. arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.33.0

2 2

[PATCH OLK-6.6 0/1]
by zhangnaichuan 27 Dec '23

27 Dec '23

description: Just like arm64, print "Bye!" before booting crash kernel. arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.33.0

2 6

[PATCH openEuler-1.0-LTS] jbd2: fix soft lockup in journal_finish_inode_data_buffers()
by Zizhi Wo 27 Dec '23

27 Dec '23

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v6.7-rc6 commit 6c02757c936063f0631b4e43fe156f8c8f1f351f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8RRXU?from=project-issue CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- There's issue when do io test: WARN: soft lockup - CPU#45 stuck for 11s! [jbd2/dm-2-8:4170] CPU: 45 PID: 4170 Comm: jbd2/dm-2-8 Kdump: loaded Tainted: G OE Call trace: dump_backtrace+0x0/0x1a0 show_stack+0x24/0x30 dump_stack+0xb0/0x100 watchdog_timer_fn+0x254/0x3f8 __hrtimer_run_queues+0x11c/0x380 hrtimer_interrupt+0xfc/0x2f8 arch_timer_handler_phys+0x38/0x58 handle_percpu_devid_irq+0x90/0x248 generic_handle_irq+0x3c/0x58 __handle_domain_irq+0x68/0xc0 gic_handle_irq+0x90/0x320 el1_irq+0xcc/0x180 queued_spin_lock_slowpath+0x1d8/0x320 jbd2_journal_commit_transaction+0x10f4/0x1c78 [jbd2] kjournald2+0xec/0x2f0 [jbd2] kthread+0x134/0x138 ret_from_fork+0x10/0x18 Analyzed informations from vmcore as follows: (1) There are about 5k+ jbd2_inode in 'commit_transaction->t_inode_list'; (2) Now is processing the 855th jbd2_inode; (3) JBD2 task has TIF_NEED_RESCHED flag; (4) There's no pags in address_space around the 855th jbd2_inode; (5) There are some process is doing drop caches; (6) Mounted with 'nodioread_nolock' option; (7) 128 CPUs; According to informations from vmcore we know 'journal->j_list_lock' spin lock competition is fierce. So journal_finish_inode_data_buffers() maybe process slowly. Theoretically, there is scheduling point in the filemap_fdatawait_range_keep_errors(). However, if inode's address_space has no pages which taged with PAGECACHE_TAG_WRITEBACK, will not call cond_resched(). So may lead to soft lockup. journal_finish_inode_data_buffers filemap_fdatawait_range_keep_errors __filemap_fdatawait_range while (index <= end) nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; --> If 'nr_pages' is equal zero will break, then will not call cond_resched() for (i = 0; i < nr_pages; i++) wait_on_page_writeback(page); cond_resched(); To solve above issue, add scheduling point in the journal_finish_inode_data_buffers(); Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20231211112544.3879780-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/jbd2/commit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 8c13c0a030a4..99562835be45 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -274,6 +274,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, dirty_end); if (!ret) ret = err; + cond_resched(); spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); -- 2.39.2

2 1

[PATCH OLK-6.6 0/1]
by zhangnaichuan 27 Dec '23

27 Dec '23

Just like arm64, print "Bye!" before booting crash kernel. arch/x86/kernel/machine_kexec_64.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.33.0

2 6

[PATCH openEuler-22.03-LTS-SP2] ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet
by Guo Mengqi 27 Dec '23

27 Dec '23

From: Zhengchao Shao <shaozhengchao(a)huawei.com> mainline inclusion from mainline-v6.7-rc2 commit e2b706c691905fe78468c361aaabc719d0a496f1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PT5 CVE: CVE-2023-6932 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When I perform the following test operations: 1.ip link add br0 type bridge 2.brctl addif br0 eth0 3.ip addr add 239.0.0.1/32 dev eth0 4.ip addr add 239.0.0.1/32 dev br0 5.ip addr add 224.0.0.1/32 dev br0 6.while ((1)) do ifconfig br0 up ifconfig br0 down done 7.send IGMPv2 query packets to port eth0 continuously. For example, ./mausezahn ethX -c 0 "01 00 5e 00 00 01 00 72 19 88 aa 02 08 00 45 00 00 1c 00 01 00 00 01 02 0e 7f c0 a8 0a b7 e0 00 00 01 11 64 ee 9b 00 00 00 00" The preceding tests may trigger the refcnt uaf issue of the mc list. The stack is as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 21 PID: 144 at lib/refcount.c:25 refcount_warn_saturate (lib/refcount.c:25) CPU: 21 PID: 144 Comm: ksoftirqd/21 Kdump: loaded Not tainted 6.7.0-rc1-next-20231117-dirty #80 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:refcount_warn_saturate (lib/refcount.c:25) RSP: 0018:ffffb68f00657910 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8a00c3bf96c0 RCX: ffff8a07b6160908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8a07b6160900 RBP: ffff8a00cba36862 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffb68f006577c0 R11: ffffffffb0fdcdc8 R12: ffff8a00c3bf9680 R13: ffff8a00c3bf96f0 R14: 0000000000000000 R15: ffff8a00d8766e00 FS: 0000000000000000(0000) GS:ffff8a07b6140000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f10b520b28 CR3: 000000039741a000 CR4: 00000000000006f0 Call Trace: <TASK> igmp_heard_query (net/ipv4/igmp.c:1068) igmp_rcv (net/ipv4/igmp.c:1132) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) netif_receive_skb_internal (net/core/dev.c:5729) netif_receive_skb (net/core/dev.c:5788) br_handle_frame_finish (net/bridge/br_input.c:216) nf_hook_bridge_pre (net/bridge/br_input.c:294) __netif_receive_skb_core (net/core/dev.c:5423) __netif_receive_skb_list_core (net/core/dev.c:5606) __netif_receive_skb_list (net/core/dev.c:5674) netif_receive_skb_list_internal (net/core/dev.c:5764) napi_gro_receive (net/core/gro.c:609) e1000_clean_rx_irq (drivers/net/ethernet/intel/e1000/e1000_main.c:4467) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3805) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6735) __do_softirq (kernel/softirq.c:554) run_ksoftirqd (kernel/softirq.c:913) smpboot_thread_fn (kernel/smpboot.c:164) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) </TASK> The root causes are as follows: Thread A Thread B ... netif_receive_skb br_dev_stop ... br_multicast_leave_snoopers ... __ip_mc_dec_group ... __igmp_group_dropped igmp_rcv igmp_stop_timer igmp_heard_query //ref = 1 ip_ma_put igmp_mod_timer refcount_dec_and_test igmp_start_timer //ref = 0 ... refcount_inc //ref increases from 0 When the device receives an IGMPv2 Query message, it starts the timer immediately, regardless of whether the device is running. If the device is down and has left the multicast group, it will cause the mc list refcount uaf issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Hangbin Liu <liuhangbin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/igmp.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- net/ipv4/igmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c71b863093ac..73c24ce011f0 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = prandom_u32() % max_delay; im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet
by Guo Mengqi 27 Dec '23

27 Dec '23

From: Zhengchao Shao <shaozhengchao(a)huawei.com> mainline inclusion from mainline-v6.7-rc2 commit e2b706c691905fe78468c361aaabc719d0a496f1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PT5 CVE: CVE-2023-6932 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When I perform the following test operations: 1.ip link add br0 type bridge 2.brctl addif br0 eth0 3.ip addr add 239.0.0.1/32 dev eth0 4.ip addr add 239.0.0.1/32 dev br0 5.ip addr add 224.0.0.1/32 dev br0 6.while ((1)) do ifconfig br0 up ifconfig br0 down done 7.send IGMPv2 query packets to port eth0 continuously. For example, ./mausezahn ethX -c 0 "01 00 5e 00 00 01 00 72 19 88 aa 02 08 00 45 00 00 1c 00 01 00 00 01 02 0e 7f c0 a8 0a b7 e0 00 00 01 11 64 ee 9b 00 00 00 00" The preceding tests may trigger the refcnt uaf issue of the mc list. The stack is as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 21 PID: 144 at lib/refcount.c:25 refcount_warn_saturate (lib/refcount.c:25) CPU: 21 PID: 144 Comm: ksoftirqd/21 Kdump: loaded Not tainted 6.7.0-rc1-next-20231117-dirty #80 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:refcount_warn_saturate (lib/refcount.c:25) RSP: 0018:ffffb68f00657910 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8a00c3bf96c0 RCX: ffff8a07b6160908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8a07b6160900 RBP: ffff8a00cba36862 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffb68f006577c0 R11: ffffffffb0fdcdc8 R12: ffff8a00c3bf9680 R13: ffff8a00c3bf96f0 R14: 0000000000000000 R15: ffff8a00d8766e00 FS: 0000000000000000(0000) GS:ffff8a07b6140000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f10b520b28 CR3: 000000039741a000 CR4: 00000000000006f0 Call Trace: <TASK> igmp_heard_query (net/ipv4/igmp.c:1068) igmp_rcv (net/ipv4/igmp.c:1132) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) netif_receive_skb_internal (net/core/dev.c:5729) netif_receive_skb (net/core/dev.c:5788) br_handle_frame_finish (net/bridge/br_input.c:216) nf_hook_bridge_pre (net/bridge/br_input.c:294) __netif_receive_skb_core (net/core/dev.c:5423) __netif_receive_skb_list_core (net/core/dev.c:5606) __netif_receive_skb_list (net/core/dev.c:5674) netif_receive_skb_list_internal (net/core/dev.c:5764) napi_gro_receive (net/core/gro.c:609) e1000_clean_rx_irq (drivers/net/ethernet/intel/e1000/e1000_main.c:4467) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3805) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6735) __do_softirq (kernel/softirq.c:554) run_ksoftirqd (kernel/softirq.c:913) smpboot_thread_fn (kernel/smpboot.c:164) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) </TASK> The root causes are as follows: Thread A Thread B ... netif_receive_skb br_dev_stop ... br_multicast_leave_snoopers ... __ip_mc_dec_group ... __igmp_group_dropped igmp_rcv igmp_stop_timer igmp_heard_query //ref = 1 ip_ma_put igmp_mod_timer refcount_dec_and_test igmp_start_timer //ref = 0 ... refcount_inc //ref increases from 0 When the device receives an IGMPv2 Query message, it starts the timer immediately, regardless of whether the device is running. If the device is down and has left the multicast group, it will cause the mc list refcount uaf issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Hangbin Liu <liuhangbin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/igmp.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- net/ipv4/igmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c71b863093ac..73c24ce011f0 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = prandom_u32() % max_delay; im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS] ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet
by Guo Mengqi 27 Dec '23

27 Dec '23

From: Zhengchao Shao <shaozhengchao(a)huawei.com> mainline inclusion from mainline-v6.7-rc2 commit e2b706c691905fe78468c361aaabc719d0a496f1 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PT5 CVE: CVE-2023-6932 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When I perform the following test operations: 1.ip link add br0 type bridge 2.brctl addif br0 eth0 3.ip addr add 239.0.0.1/32 dev eth0 4.ip addr add 239.0.0.1/32 dev br0 5.ip addr add 224.0.0.1/32 dev br0 6.while ((1)) do ifconfig br0 up ifconfig br0 down done 7.send IGMPv2 query packets to port eth0 continuously. For example, ./mausezahn ethX -c 0 "01 00 5e 00 00 01 00 72 19 88 aa 02 08 00 45 00 00 1c 00 01 00 00 01 02 0e 7f c0 a8 0a b7 e0 00 00 01 11 64 ee 9b 00 00 00 00" The preceding tests may trigger the refcnt uaf issue of the mc list. The stack is as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 21 PID: 144 at lib/refcount.c:25 refcount_warn_saturate (lib/refcount.c:25) CPU: 21 PID: 144 Comm: ksoftirqd/21 Kdump: loaded Not tainted 6.7.0-rc1-next-20231117-dirty #80 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:refcount_warn_saturate (lib/refcount.c:25) RSP: 0018:ffffb68f00657910 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8a00c3bf96c0 RCX: ffff8a07b6160908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8a07b6160900 RBP: ffff8a00cba36862 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffb68f006577c0 R11: ffffffffb0fdcdc8 R12: ffff8a00c3bf9680 R13: ffff8a00c3bf96f0 R14: 0000000000000000 R15: ffff8a00d8766e00 FS: 0000000000000000(0000) GS:ffff8a07b6140000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f10b520b28 CR3: 000000039741a000 CR4: 00000000000006f0 Call Trace: <TASK> igmp_heard_query (net/ipv4/igmp.c:1068) igmp_rcv (net/ipv4/igmp.c:1132) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) netif_receive_skb_internal (net/core/dev.c:5729) netif_receive_skb (net/core/dev.c:5788) br_handle_frame_finish (net/bridge/br_input.c:216) nf_hook_bridge_pre (net/bridge/br_input.c:294) __netif_receive_skb_core (net/core/dev.c:5423) __netif_receive_skb_list_core (net/core/dev.c:5606) __netif_receive_skb_list (net/core/dev.c:5674) netif_receive_skb_list_internal (net/core/dev.c:5764) napi_gro_receive (net/core/gro.c:609) e1000_clean_rx_irq (drivers/net/ethernet/intel/e1000/e1000_main.c:4467) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3805) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6735) __do_softirq (kernel/softirq.c:554) run_ksoftirqd (kernel/softirq.c:913) smpboot_thread_fn (kernel/smpboot.c:164) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) </TASK> The root causes are as follows: Thread A Thread B ... netif_receive_skb br_dev_stop ... br_multicast_leave_snoopers ... __ip_mc_dec_group ... __igmp_group_dropped igmp_rcv igmp_stop_timer igmp_heard_query //ref = 1 ip_ma_put igmp_mod_timer refcount_dec_and_test igmp_start_timer //ref = 0 ... refcount_inc //ref increases from 0 When the device receives an IGMPv2 Query message, it starts the timer immediately, regardless of whether the device is running. If the device is down and has left the multicast group, it will cause the mc list refcount uaf issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Hangbin Liu <liuhangbin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/igmp.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- net/ipv4/igmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c71b863093ac..73c24ce011f0 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = prandom_u32() % max_delay; im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) -- 2.17.1

2 1

[PATCH OLK-6.6 0/1] x86/kdump: make crash kernel boot faster
by zhangnaichuan 27 Dec '23

27 Dec '23

description: If other cpus offline before handle the crash NMI, the waiting_for_crash_ipi can not be decreased to 0, and current cpu will wait 1 second. So break if all other cpus offline. arch/x86/kernel/reboot.c | 8 ++++++++ 1 file changed, 8 insertions(+) -- 2.33.0

2 2

openEuler Kernel SIG双周例会
by openEuler conference 27 Dec '23

27 Dec '23

您好！ Kernel SIG 邀请您参加 2023-12-29 14:00 召开的WeLink会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中（新增议题可回复本邮件申请，或直接填写至会议看板）会议链接：https://bmeeting.huaweicloud.com:36443/#/j/986451425 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the WeLink conference(auto recording) will be held at 2023-12-29 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中（新增议题可回复本邮件申请，或直接填写至会议看板） You can join the meeting at https://bmeeting.huaweicloud.com:36443/#/j/986451425. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-22.03-LTS-SP1 v3] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PGNK CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS v3] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PGNK CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP2 v3] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PGNK CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH OLK-6.6] openeuler_defconfig: enable CONFIG_EROFS_FS_ONDEMAND for x86 and arm64
by Baokun Li 27 Dec '23

27 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8RP48 -------------------------------- Enable CONFIG_EROFS_FS_ONDEMAND on x86 and arm64 by default to support lazy loading, and also enable the dependent CONFIG_CACHEFILES_ONDEMAND and CONFIG_EROFS_FS. Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 8 ++++++-- arch/x86/configs/openeuler_defconfig | 8 ++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 9297e3ca9f92..fe5e81f6eede 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -6843,7 +6843,7 @@ CONFIG_FSCACHE_STATS=y CONFIG_CACHEFILES=m # CONFIG_CACHEFILES_DEBUG is not set # CONFIG_CACHEFILES_ERROR_INJECTION is not set -# CONFIG_CACHEFILES_ONDEMAND is not set +CONFIG_CACHEFILES_ONDEMAND=y # end of Caches # @@ -6949,7 +6949,11 @@ CONFIG_PSTORE_RAM=m # CONFIG_PSTORE_BLK is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set -# CONFIG_EROFS_FS is not set +CONFIG_EROFS_FS=m +# CONFIG_EROFS_FS_DEBUG is not set +# CONFIG_EROFS_FS_XATTR is not set +# CONFIG_EROFS_FS_ZIP is not set +CONFIG_EROFS_FS_ONDEMAND=y CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=m CONFIG_NFS_V2=m diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index c7b4a4b80b66..f660a490d921 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -8048,7 +8048,7 @@ CONFIG_FSCACHE_STATS=y CONFIG_CACHEFILES=m # CONFIG_CACHEFILES_DEBUG is not set # CONFIG_CACHEFILES_ERROR_INJECTION is not set -# CONFIG_CACHEFILES_ONDEMAND is not set +CONFIG_CACHEFILES_ONDEMAND=y # end of Caches # @@ -8157,7 +8157,11 @@ CONFIG_PSTORE_RAM=m # CONFIG_PSTORE_BLK is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set -# CONFIG_EROFS_FS is not set +CONFIG_EROFS_FS=m +# CONFIG_EROFS_FS_DEBUG is not set +# CONFIG_EROFS_FS_XATTR is not set +# CONFIG_EROFS_FS_ZIP is not set +CONFIG_EROFS_FS_ONDEMAND=y CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=m # CONFIG_NFS_V2 is not set -- 2.31.1

2 1

[PATCH OLK-6.6 0/1] optimize inlining
by Yuntao Liu 27 Dec '23

27 Dec '23

From: Yuntao Liu liuyuntao12(a)huawei.com *** BLURB HERE *** Jinjie Ruan (1): optimize inlining arch/arm64/kvm/sys_regs.h | 5 +++++ arch/x86/configs/i386_defconfig | 1 + arch/x86/configs/x86_64_defconfig | 1 + drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 5 ++++- .../pci/hive_isp_css_include/print_support.h | 4 ++++ include/linux/compiler_types.h | 6 +++++- include/trace/trace_events.h | 2 +- kernel/configs/tiny.config | 1 + lib/Kconfig.debug | 13 +++++++++++++ 9 files changed, 35 insertions(+), 3 deletions(-) -- 2.34.1

2 2

[PATCH OLK-5.10 v3] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8PGNK CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH OLK-5.10 v2] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP2 v2] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1 v2] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS v2] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP2] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1

[PATCH OLK-5.10] netfilter: nft_set_pipapo: skip inactive elements during set walk
by Dong Chenchen 27 Dec '23

27 Dec '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-5.10.203 commit bf72b44fe81be08a9fcd58aabf417cd3337ffc99 category: bugfix bugzilla: 189434 CVE: CVE-2023-6817 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 317eb9685095678f2c9f5a8189de698c5354316a upstream. Otherwise set elements can be deactivated twice which will cause a crash. Reported-by: Xingyuan Mo <hdthky0(a)gmail.com> Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: net/netfilter/nft_set_pipapo.c Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 3be93175b3ff..08fc65ca31d4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1984,6 +1984,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, if (nft_set_elem_expired(&e->ext)) goto cont; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); -- 2.25.1

2 1