From a2b4a79b88b24c49d98d45a06a014ffd22ada1a4 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Sun, 10 Sep 2017 20:29:45 +0300 Subject: spi: uapi: spidev: add missing ioctl header The SPI_IOC_MESSAGE() macro references _IOC_SIZEBITS. Add linux/ioctl.h to make sure this macro is defined. This fixes the following build failure of lcdproc with the musl libc: In file included from .../sysroot/usr/include/sys/ioctl.h:7:0, from hd44780-spi.c:31: hd44780-spi.c: In function 'spi_transfer': hd44780-spi.c:89:24: error: '_IOC_SIZEBITS' undeclared (first use in this function) status = ioctl(p->fd, SPI_IOC_MESSAGE(1), &xfer); ^ Signed-off-by: Baruch Siach Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/uapi/linux/spi/spidev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index dd5f21e75805..856de39d0b89 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -23,6 +23,7 @@ #define SPIDEV_H #include +#include /* User space versions of kernel symbols for SPI clocking modes, * matching -- cgit v1.2.3 From 98589a0998b8b13c4a8fa1ccb0e62751a019faa5 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 9 Oct 2017 15:27:15 +0300 Subject: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder Signed-off-by: Shmulik Ladkani Acked-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/bpf.h | 5 +++++ include/uapi/linux/netfilter/xt_bpf.h | 1 + kernel/bpf/inode.c | 1 + net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..f1af7d63d678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0..da161b56c79e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..be1dde967208 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216c..29123934887b 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } -- cgit v1.2.3 From a961e40917fb14614d368d8bc9782ca4d6a8cd11 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 19 Oct 2017 13:30:15 -0400 Subject: membarrier: Provide register expedited private command This introduces a "register private expedited" membarrier command which allows eventual removal of important memory barrier constraints on the scheduler fast-paths. It changes how the "private expedited" membarrier command (new to 4.14) is used from user-space. This new command allows processes to register their intent to use the private expedited command. This affects how the expedited private command introduced in 4.14-rc is meant to be used, and should be merged before 4.14 final. Processes are now required to register before using MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM. This fixes a problem that arose when designing requested extensions to sys_membarrier() to allow JITs to efficiently flush old code from instruction caches. Several potential algorithms are much less painful if the user register intent to use this functionality early on, for example, before the process spawns the second thread. Registering at this time removes the need to interrupt each and every thread in that process at the first expedited sys_membarrier() system call. Signed-off-by: Mathieu Desnoyers Acked-by: Paul E. McKenney Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Alexander Viro Signed-off-by: Linus Torvalds --- fs/exec.c | 1 + include/linux/mm_types.h | 3 +++ include/linux/sched/mm.h | 16 ++++++++++++++++ include/uapi/linux/membarrier.h | 23 ++++++++++++++++------- kernel/sched/membarrier.c | 34 ++++++++++++++++++++++++++++++---- 5 files changed, 66 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/exec.c b/fs/exec.c index 5470d3c1892a..3e14ba25f678 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; + membarrier_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 46f4ecf5479a..1861ea8dba77 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,9 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ +#ifdef CONFIG_MEMBARRIER + atomic_t membarrier_state; +#endif #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index ae53e413fb13..ab9bf7b73954 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -211,4 +211,20 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_MEMBARRIER +enum { + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), + MEMBARRIER_STATE_SWITCH_MM = (1U << 1), +}; + +static inline void membarrier_execve(struct task_struct *t) +{ + atomic_set(&t->mm->membarrier_state, 0); +} +#else +static inline void membarrier_execve(struct task_struct *t) +{ +} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 6d47b3249d8a..4e01ad7ffe98 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -52,21 +52,30 @@ * (non-running threads are de facto in such a * state). This only covers threads from the * same processes as the caller thread. This - * command returns 0. The "expedited" commands - * complete faster than the non-expedited ones, - * they never block, but have the downside of - * causing extra overhead. + * command returns 0 on success. The + * "expedited" commands complete faster than + * the non-expedited ones, they never block, + * but have the downside of causing extra + * overhead. A process needs to register its + * intent to use the private expedited command + * prior to using it, otherwise this command + * returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always + * returns 0. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_SHARED = (1 << 0), /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ - MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a92fddc22747..dd7908743dab 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "sched.h" /* for cpu_rq(). */ @@ -26,21 +27,26 @@ * except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited(void) +static int membarrier_private_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; + if (!(atomic_read(¤t->mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + if (num_online_cpus() == 1) - return; + return 0; /* * Matches memory barriers around rq->curr modification in @@ -94,6 +100,24 @@ static void membarrier_private_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static void membarrier_register_private_expedited(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + /* + * We need to consider threads belonging to different thread + * groups, which use the same mm. (CLONE_VM but not + * CLONE_THREAD). + */ + if (atomic_read(&mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + &mm->membarrier_state); } /** @@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) synchronize_sched(); return 0; case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - membarrier_private_expedited(); + return membarrier_private_expedited(); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + membarrier_register_private_expedited(); return 0; default: return -EINVAL; -- cgit v1.2.3 From bfa640757e9378c2f26867e723f1287e94f5a7ad Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 27 Oct 2017 09:45:53 -0700 Subject: bpf: rename sk_actions to align with bpf infrastructure Recent additions to support multiple programs in cgroups impose a strict requirement, "all yes is yes, any no is no". To enforce this the infrastructure requires the 'no' return code, SK_DROP in this case, to be 0. To apply these rules to SK_SKB program types the sk_actions return codes need to be adjusted. This fix adds SK_PASS and makes 'SK_DROP = 0'. Finally, remove SK_ABORTED to remove any chance that the API may allow aborted program flows to be passed up the stack. This would be incorrect behavior and allow programs to break existing policies. Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 +++--- kernel/bpf/sockmap.c | 3 ++- net/core/filter.c | 5 +++-- tools/include/uapi/linux/bpf.h | 4 ++-- 4 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f90860d1f897..0d7948ce2128 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -575,7 +575,7 @@ union bpf_attr { * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -786,8 +786,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6778fb773934..66f00a2b27f4 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -122,7 +122,8 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) preempt_enable(); skb->sk = NULL; - return rc; + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) diff --git a/net/core/filter.c b/net/core/filter.c index 68eaa2f81a8e..6ae94f825f72 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1844,14 +1844,15 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + /* If user passes invalid input drop the packet. */ if (unlikely(flags)) - return SK_ABORTED; + return SK_DROP; tcb->bpf.key = key; tcb->bpf.flags = flags; tcb->bpf.map = map; - return SK_REDIRECT; + return SK_PASS; } struct sock *do_sk_redirect_map(struct sk_buff *skb) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 24b35a1fd4d6..c174971afbe6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -787,8 +787,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; -- cgit v1.2.3 From 978aa0474115f3f5848949f2efce4def0766a5cb Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 28 Oct 2017 19:43:57 +0800 Subject: sctp: fix some type cast warnings introduced since very beginning These warnings were found by running 'make C=2 M=net/sctp/'. They are there since very beginning. Note after this patch, there still one warning left in sctp_outq_flush(): sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM) Since it has been moved to sctp_stream_outq_migrate on net-next, to avoid the extra job when merging net-next to net, I will post the fix for it after the merging is done. Reported-by: Eric Dumazet Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- include/uapi/linux/sctp.h | 2 +- net/sctp/ipv6.c | 2 +- net/sctp/sm_make_chunk.c | 4 ++-- net/sctp/sm_sideeffect.c | 4 ++-- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 09d7412e9cb0..da803dfc7a39 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -231,7 +231,7 @@ struct sctp_datahdr { __be32 tsn; __be16 stream; __be16 ssn; - __be32 ppid; + __u32 ppid; __u8 payload[0]; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1..84fc2914b7fb 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -376,7 +376,7 @@ struct sctp_remote_error { __u16 sre_type; __u16 sre_flags; __u32 sre_length; - __u16 sre_error; + __be16 sre_error; sctp_assoc_t sre_assoc_id; __u8 sre_data[0]; }; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7fe9e1d1b7ec..a6dfa86c0201 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -738,7 +738,7 @@ static int sctp_v6_skb_iif(const struct sk_buff *skb) /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v6_is_ce(const struct sk_buff *skb) { - return *((__u32 *)(ipv6_hdr(skb))) & htonl(1 << 20); + return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20); } /* Dump the v6 addr to the seq file. */ diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 57c55045f5a7..514465b03829 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2854,7 +2854,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = flags; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); @@ -2867,7 +2867,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = SCTP_PARAM_DEL_IP; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 8f2762bba879..e2d9a4b49c9c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1607,12 +1607,12 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.err); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.err); + subtype, chunk, cmd->obj.u32); break; case SCTP_CMD_INIT_COUNTER_INC: -- cgit v1.2.3