From d5b5f391d434c5cc8bcb1ab2d759738797b85f52 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Nov 2013 16:23:04 +0100 Subject: ftrace, perf: Avoid infinite event generation loop Vince's perf-trinity fuzzer found yet another 'interesting' problem. When we sample the irq_work_exit tracepoint with period==1 (or PERF_SAMPLE_PERIOD) and we add an fasync SIGNAL handler we create an infinite event generation loop: ,-> | irq_work_exit() -> | trace_irq_work_exit() -> | ... | __perf_event_overflow() -> (due to fasync) | irq_work_queue() -> (irq_work_list must be empty) '--------- arch_irq_work_raise() Similar things can happen due to regular poll() wakeups if we exceed the ring-buffer wakeup watermark, or have an event_limit. To avoid this, dis-allow sampling this particular tracepoint. In order to achieve this, create a special perf_perm function pointer for each event and call this (when set) on trying to create a tracepoint perf event. [ roasted: use expr... to allow for ',' in your expression ] Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Steven Rostedt Cc: Dave Jones Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20131114152304.GC5364@laptop.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 16 ++++++++++++++++ include/linux/tracepoint.h | 4 ++++ include/trace/ftrace.h | 7 +++++++ 3 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 9abbe630c456..8c9b7a1c4138 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -248,6 +248,9 @@ struct ftrace_event_call { #ifdef CONFIG_PERF_EVENTS int perf_refcount; struct hlist_head __percpu *perf_events; + + int (*perf_perm)(struct ftrace_event_call *, + struct perf_event *); #endif }; @@ -317,6 +320,19 @@ struct ftrace_event_file { } \ early_initcall(trace_init_flags_##name); +#define __TRACE_EVENT_PERF_PERM(name, expr...) \ + static int perf_perm_##name(struct ftrace_event_call *tp_event, \ + struct perf_event *p_event) \ + { \ + return ({ expr; }); \ + } \ + static int __init trace_init_perf_perm_##name(void) \ + { \ + event_##name.perf_perm = &perf_perm_##name; \ + return 0; \ + } \ + early_initcall(trace_init_perf_perm_##name); + #define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index ebeab360d851..f16dc0a40049 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -267,6 +267,8 @@ static inline void tracepoint_synchronize_unregister(void) #define TRACE_EVENT_FLAGS(event, flag) +#define TRACE_EVENT_PERF_PERM(event, expr...) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT @@ -399,4 +401,6 @@ static inline void tracepoint_synchronize_unregister(void) #define TRACE_EVENT_FLAGS(event, flag) +#define TRACE_EVENT_PERF_PERM(event, expr...) + #endif /* ifdef TRACE_EVENT (see note above) */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 52594b20179e..6b852f60f8ae 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -90,6 +90,10 @@ #define TRACE_EVENT_FLAGS(name, value) \ __TRACE_EVENT_FLAGS(name, value) +#undef TRACE_EVENT_PERF_PERM +#define TRACE_EVENT_PERF_PERM(name, expr...) \ + __TRACE_EVENT_PERF_PERM(name, expr) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -140,6 +144,9 @@ #undef TRACE_EVENT_FLAGS #define TRACE_EVENT_FLAGS(event, flag) +#undef TRACE_EVENT_PERF_PERM +#define TRACE_EVENT_PERF_PERM(event, expr...) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* -- cgit v1.2.3 From b972fc308c2763096b61b62169f2167ee0ca5a19 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 19 Nov 2013 17:21:52 +0800 Subject: sched: Remove unused variable in 'struct sched_domain' The 'u64 last_update' variable isn't used now, remove it to save a bit of space. Signed-off-by: Alex Shi Signed-off-by: Peter Zijlstra Cc: Morten.Rasmussen@arm.com Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/r/1384852912-24791-1-git-send-email-alex.shi@linaro.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index f7efc8604652..b122395bf5f4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -823,8 +823,6 @@ struct sched_domain { unsigned int balance_interval; /* initialise to 1. units in ms. */ unsigned int nr_balance_failed; /* initialise to 0 */ - u64 last_update; - /* idle_balance() stats */ u64 max_newidle_lb_cost; unsigned long next_decay_max_lb_cost; -- cgit v1.2.3 From 6bab2c613d7fa70bb8514f89ab7455ede717142b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 15 Nov 2013 14:15:07 -0800 Subject: genirq: Correct fuzzy and fragile IRQ_RETVAL() definition commit bedd30d986a0 ("genirq: make irqreturn_t an enum") blindly replaced "0" by "IRQ_NONE" in the "IRQ_RETVAL(x)" macro definition. However, as "x" is a condition, "0" meant "boolean false", not an irqreturn_t value. All of this worked, and kept working after the addition of IRQ_WAKE_THREAD, as - both "boolean false" and "IRQ_NONE" are "0" (for the comparison), - "boolean true" and "boolean false" nicely map to the correct values of "IRQ_HANDLED" and "IRQ_NONE" (for the return value). Correct the macro definition for clarity and future-proofness. Signed-off-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/irqreturn.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index 714ba08dc092..e374e369fb2f 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -14,6 +14,6 @@ enum irqreturn { }; typedef enum irqreturn irqreturn_t; -#define IRQ_RETVAL(x) ((x) != IRQ_NONE) +#define IRQ_RETVAL(x) ((x) ? IRQ_HANDLED : IRQ_NONE) #endif -- cgit v1.2.3 From 694e096fd7c2a7d40760fc9c9dfc826bdd495ea4 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 13 Nov 2013 12:29:08 -0500 Subject: NFS: Enabling v4.2 should not recompile nfsd and lockd When CONFIG_NFS_V4_2 is toggled nfsd and lockd will be recompiled, instead of only the nfs client. This patch moves a small amount of code into the client directory to avoid unnecessary recompiles. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.h | 1 + fs/nfs/dns_resolve.c | 2 ++ fs/nfs/internal.h | 15 +++++++++++++++ fs/nfs/nfs4_fs.h | 8 ++++++++ include/linux/nfs4.h | 10 ---------- include/linux/nfs_fs.h | 18 ------------------ 6 files changed, 26 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 8485978993e8..9838fb020473 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -36,6 +36,7 @@ #include #include +#include "../nfs4_fs.h" #include "../pnfs.h" #include "../netns.h" diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index fc0f95ec7358..d25f10fb4926 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -46,7 +46,9 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, #include #include #include +#include +#include "nfs4_fs.h" #include "dns_resolve.h" #include "cache_lib.h" #include "netns.h" diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index bca6a3e3c49c..8b5cc04a8611 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -269,6 +269,21 @@ extern const u32 nfs41_maxgetdevinfo_overhead; extern struct rpc_procinfo nfs4_procedures[]; #endif +#ifdef CONFIG_NFS_V4_SECURITY_LABEL +extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); +static inline void nfs4_label_free(struct nfs4_label *label) +{ + if (label) { + kfree(label->label); + kfree(label); + } + return; +} +#else +static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } +static inline void nfs4_label_free(void *label) {} +#endif /* CONFIG_NFS_V4_SECURITY_LABEL */ + /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3ce79b04522e..5609edc742a0 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -9,6 +9,14 @@ #ifndef __LINUX_FS_NFS_NFS4_FS_H #define __LINUX_FS_NFS_NFS4_FS_H +#if defined(CONFIG_NFS_V4_2) +#define NFS4_MAX_MINOR_VERSION 2 +#elif defined(CONFIG_NFS_V4_1) +#define NFS4_MAX_MINOR_VERSION 1 +#else +#define NFS4_MAX_MINOR_VERSION 0 +#endif + #if IS_ENABLED(CONFIG_NFS_V4) #define NFS4_MAX_LOOP_ON_RECOVER (10) diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index c6f41b616965..ddd84871c0ad 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -410,16 +410,6 @@ enum lock_type4 { #define NFS4_VERSION 4 #define NFS4_MINOR_VERSION 0 -#if defined(CONFIG_NFS_V4_2) -#define NFS4_MAX_MINOR_VERSION 2 -#else -#if defined(CONFIG_NFS_V4_1) -#define NFS4_MAX_MINOR_VERSION 1 -#else -#define NFS4_MAX_MINOR_VERSION 0 -#endif /* CONFIG_NFS_V4_1 */ -#endif /* CONFIG_NFS_V4_2 */ - #define NFS4_DEBUG 1 /* Index of predefined Linux client operations */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 14a48207a304..48997374eaf0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -506,24 +506,6 @@ extern const struct inode_operations nfs_referral_inode_operations; extern int nfs_mountpoint_expiry_timeout; extern void nfs_release_automount_timer(void); -/* - * linux/fs/nfs/nfs4proc.c - */ -#ifdef CONFIG_NFS_V4_SECURITY_LABEL -extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); -static inline void nfs4_label_free(struct nfs4_label *label) -{ - if (label) { - kfree(label->label); - kfree(label); - } - return; -} -#else -static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } -static inline void nfs4_label_free(void *label) {} -#endif - /* * linux/fs/nfs/unlink.c */ -- cgit v1.2.3 From 85fbaa75037d0b6b786ff18658ddf0b4014ce2a4 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sat, 23 Nov 2013 00:46:12 +0100 Subject: inet: fix addr_len/msg->msg_namelen assignment in recv_error and rxpmtu functions Commit bceaa90240b6019ed73b49965eac7d167610be69 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") conditionally updated addr_len if the msg_name is written to. The recv_error and rxpmtu functions relied on the recvmsg functions to set up addr_len before. As this does not happen any more we have to pass addr_len to those functions as well and set it to the size of the corresponding sockaddr length. This broke traceroute and such. Fixes: bceaa90240b6 ("inet: prevent leakage of uninitialized memory to user in recv syscalls") Reported-by: Brad Spengler Reported-by: Tom Labanowski Cc: mpb Cc: David S. Miller Cc: Eric Dumazet Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/ipv6.h | 6 ++++-- include/net/ping.h | 3 ++- net/ipv4/ip_sockglue.c | 3 ++- net/ipv4/ping.c | 5 +++-- net/ipv4/raw.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 7 +++++-- net/ipv6/ping.c | 3 ++- net/ipv6/raw.c | 4 ++-- net/ipv6/udp.c | 4 ++-- net/l2tp/l2tp_ip6.c | 2 +- 12 files changed, 26 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 217bc5bfc6c6..5a25f36fe3a7 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -473,7 +473,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)); -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len); +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2a5f668cd683..eb198acaac1d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -776,8 +776,10 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); diff --git a/include/net/ping.h b/include/net/ping.h index 3f67704f3747..90f48417b03d 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -31,7 +31,8 @@ /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { - int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len); + int (*ipv6_recv_error)(struct sock *sk, struct msghdr *msg, int len, + int *addr_len); int (*ip6_datagram_recv_ctl)(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); int (*icmpv6_err_convert)(u8 type, u8 code, int *err); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3f858266fa7e..ddf32a6bc415 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -386,7 +386,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf /* * Handle MSG_ERRQUEUE */ -int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb, *skb2; @@ -423,6 +423,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len) serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 876c6ca2d8f9..840cf1b9e6ee 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -841,10 +841,11 @@ int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (flags & MSG_ERRQUEUE) { if (family == AF_INET) { - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { - return pingv6_ops.ipv6_recv_error(sk, msg, len); + return pingv6_ops.ipv6_recv_error(sk, msg, len, + addr_len); #endif } } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5cb8ddb505ee..23c3e5b5bb53 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -697,7 +697,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto out; if (flags & MSG_ERRQUEUE) { - err = ip_recv_error(sk, msg, len); + err = ip_recv_error(sk, msg, len, addr_len); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5944d7d668dd..44dfaa09b584 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1236,7 +1236,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, bool slow; if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index a454b0ff57c7..d690204a0275 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) /* * Handle MSG_ERRQUEUE */ -int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; @@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) &sin->sin6_addr); sin->sin6_scope_id = 0; } + *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); @@ -423,7 +424,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ -int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -457,6 +459,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; + *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 8815e31a87fe..a83243c3d656 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -57,7 +57,8 @@ static struct inet_protosw pingv6_protosw = { /* Compatibility glue so we can support IPv6 when it's compiled as a module */ -static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) +static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, + int *addr_len) { return -EAFNOSUPPORT; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e24ff1df0401..7fb4e14c467f 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -466,10 +466,10 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 81eb8cf8389b..bcd5699313c3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -393,10 +393,10 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, bool slow; if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) - return ipv6_recv_rxpmtu(sk, msg, len); + return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index cfd65304be60..d9b437e55007 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, *addr_len = sizeof(*lsa); if (flags & MSG_ERRQUEUE) - return ipv6_recv_error(sk, msg, len); + return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) -- cgit v1.2.3 From 5a87182aa21d6d5d306840feab9321818dd3e2a3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Nov 2013 09:09:42 +0530 Subject: cpufreq: suspend governors on system suspend/hibernate This patch adds cpufreq suspend/resume calls to dpm_{suspend|resume}_noirq() for handling suspend/resume of cpufreq governors. Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found anr issue where tunables configuration for clusters/sockets with non-boot CPUs was getting lost after suspend/resume, as we were notifying governors with CPUFREQ_GOV_POLICY_EXIT on removal of the last cpu for that policy and so deallocating memory for tunables. This is fixed by this patch as we don't allow any operation on governors after device suspend and before device resume now. Reported-and-tested-by: Lan Tianyu Reported-by: Jinhyuk Choi Signed-off-by: Viresh Kumar [rjw: Changelog, minor cleanups] Signed-off-by: Rafael J. Wysocki --- drivers/base/power/main.c | 3 +++ drivers/cpufreq/cpufreq.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/cpufreq.h | 8 ++++++++ 3 files changed, 54 insertions(+) (limited to 'include') diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 9f098a82cf04..10c3510d72a9 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "../base.h" #include "power.h" @@ -473,6 +474,7 @@ static void dpm_resume_noirq(pm_message_t state) dpm_show_time(starttime, state, "noirq"); resume_device_irqs(); cpuidle_resume(); + cpufreq_resume(); } /** @@ -885,6 +887,7 @@ static int dpm_suspend_noirq(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0; + cpufreq_suspend(); cpuidle_pause(); suspend_device_irqs(); mutex_lock(&dpm_list_mtx); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 02d534da22dd..606224a8abc2 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -47,6 +48,9 @@ static LIST_HEAD(cpufreq_policy_list); static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); #endif +/* Flag to suspend/resume CPUFreq governors */ +static bool cpufreq_suspended; + static inline bool has_target(void) { return cpufreq_driver->target_index || cpufreq_driver->target; @@ -1462,6 +1466,41 @@ static struct subsys_interface cpufreq_interface = { .remove_dev = cpufreq_remove_dev, }; +void cpufreq_suspend(void) +{ + struct cpufreq_policy *policy; + + if (!has_target()) + return; + + pr_debug("%s: Suspending Governors\n", __func__); + + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) + if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP)) + pr_err("%s: Failed to stop governor for policy: %p\n", + __func__, policy); + + cpufreq_suspended = true; +} + +void cpufreq_resume(void) +{ + struct cpufreq_policy *policy; + + if (!has_target()) + return; + + pr_debug("%s: Resuming Governors\n", __func__); + + cpufreq_suspended = false; + + list_for_each_entry(policy, &cpufreq_policy_list, policy_list) + if (__cpufreq_governor(policy, CPUFREQ_GOV_START) + || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS)) + pr_err("%s: Failed to start governor for policy: %p\n", + __func__, policy); +} + /** * cpufreq_bp_suspend - Prepare the boot CPU for system suspend. * @@ -1764,6 +1803,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, struct cpufreq_governor *gov = NULL; #endif + /* Don't start any governor operations if we are entering suspend */ + if (cpufreq_suspended) + return 0; + if (policy->governor->max_transition_latency && policy->cpuinfo.transition_latency > policy->governor->max_transition_latency) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 5bd6ab9b0c27..91716658e9a1 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -272,6 +272,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); } +#ifdef CONFIG_CPU_FREQ +void cpufreq_suspend(void); +void cpufreq_resume(void); +#else +static inline void cpufreq_suspend(void) {} +static inline void cpufreq_resume(void) {} +#endif + /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/ -- cgit v1.2.3 From 41da8b5adba77e22584f8b45f9641504fa885308 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Tue, 12 Nov 2013 11:46:10 -0600 Subject: crypto: scatterwalk - Set the chain pointer indication bit The scatterwalk_crypto_chain function invokes the scatterwalk_sg_chain function to chain two scatterlists, but the chain pointer indication bit is not set. When the resulting scatterlist is used, for example, by sg_nents to count the number of scatterlist entries, a segfault occurs because sg_nents does not follow the chain pointer to the chained scatterlist. Update scatterwalk_sg_chain to set the chain pointer indication bit as is done by the sg_chain function. Cc: stable@vger.kernel.org Signed-off-by: Tom Lendacky Signed-off-by: Herbert Xu --- include/crypto/scatterwalk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 13621cc8cf4c..64ebede184f1 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -36,6 +36,7 @@ static inline void scatterwalk_sg_chain(struct scatterlist *sg1, int num, { sg_set_page(&sg1[num - 1], (void *)sg2, 0, 0); sg1[num - 1].page_link &= ~0x02; + sg1[num - 1].page_link |= 0x01; } static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg) -- cgit v1.2.3 From e0d59733f6b1796b8d6692642c87d7dd862c3e3a Mon Sep 17 00:00:00 2001 From: Seiji Aguchi Date: Wed, 30 Oct 2013 15:27:26 -0400 Subject: efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed Currently, when mounting pstore file system, a read callback of efi_pstore driver runs mutiple times as below. - In the first read callback, scan efivar_sysfs_list from head and pass a kmsg buffer of a entry to an upper pstore layer. - In the second read callback, rescan efivar_sysfs_list from the entry and pass another kmsg buffer to it. - Repeat the scan and pass until the end of efivar_sysfs_list. In this process, an entry is read across the multiple read function calls. To avoid race between the read and erasion, the whole process above is protected by a spinlock, holding in open() and releasing in close(). At the same time, kmemdup() is called to pass the buffer to pstore filesystem during it. And then, it causes a following lockdep warning. To make the dynamic memory allocation runnable without taking spinlock, holding off a deletion of sysfs entry if it happens while scanning it via efi_pstore, and deleting it after the scan is completed. To implement it, this patch introduces two flags, scanning and deleting, to efivar_entry. On the code basis, it seems that all the scanning and deleting logic is not needed because __efivars->lock are not dropped when reading from the EFI variable store. But, the scanning and deleting logic is still needed because an efi-pstore and a pstore filesystem works as follows. In case an entry(A) is found, the pointer is saved to psi->data. And efi_pstore_read() passes the entry(A) to a pstore filesystem by releasing __efivars->lock. And then, the pstore filesystem calls efi_pstore_read() again and the same entry(A), which is saved to psi->data, is used for resuming to scan a sysfs-list. So, to protect the entry(A), the logic is needed. [ 1.143710] ------------[ cut here ]------------ [ 1.144058] WARNING: CPU: 1 PID: 1 at kernel/lockdep.c:2740 lockdep_trace_alloc+0x104/0x110() [ 1.144058] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)) [ 1.144058] Modules linked in: [ 1.144058] CPU: 1 PID: 1 Comm: systemd Not tainted 3.11.0-rc5 #2 [ 1.144058] 0000000000000009 ffff8800797e9ae0 ffffffff816614a5 ffff8800797e9b28 [ 1.144058] ffff8800797e9b18 ffffffff8105510d 0000000000000080 0000000000000046 [ 1.144058] 00000000000000d0 00000000000003af ffffffff81ccd0c0 ffff8800797e9b78 [ 1.144058] Call Trace: [ 1.144058] [] dump_stack+0x54/0x74 [ 1.144058] [] warn_slowpath_common+0x7d/0xa0 [ 1.144058] [] warn_slowpath_fmt+0x4c/0x50 [ 1.144058] [] ? vsscanf+0x57f/0x7b0 [ 1.144058] [] lockdep_trace_alloc+0x104/0x110 [ 1.144058] [] __kmalloc_track_caller+0x50/0x280 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] kmemdup+0x20/0x50 [ 1.144058] [] efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x170/0x170 [ 1.144058] [] efi_pstore_read_func+0xb4/0xe0 [ 1.144058] [] __efivar_entry_iter+0xfb/0x120 [ 1.144058] [] efi_pstore_read+0x3f/0x50 [ 1.144058] [] pstore_get_records+0x9a/0x150 [ 1.158207] [] ? selinux_d_instantiate+0x1c/0x20 [ 1.158207] [] ? parse_options+0x80/0x80 [ 1.158207] [] pstore_fill_super+0xa5/0xc0 [ 1.158207] [] mount_single+0xa2/0xd0 [ 1.158207] [] pstore_mount+0x18/0x20 [ 1.158207] [] mount_fs+0x39/0x1b0 [ 1.158207] [] ? __alloc_percpu+0x10/0x20 [ 1.158207] [] vfs_kern_mount+0x63/0xf0 [ 1.158207] [] do_mount+0x23e/0xa20 [ 1.158207] [] ? strndup_user+0x4b/0xf0 [ 1.158207] [] SyS_mount+0x83/0xc0 [ 1.158207] [] system_call_fastpath+0x16/0x1b [ 1.158207] ---[ end trace 61981bc62de9f6f4 ]--- Signed-off-by: Seiji Aguchi Tested-by: Madper Xie Cc: stable@kernel.org Signed-off-by: Matt Fleming --- drivers/firmware/efi/efi-pstore.c | 143 +++++++++++++++++++++++++++++++++++--- drivers/firmware/efi/efivars.c | 12 ++-- drivers/firmware/efi/vars.c | 12 +++- include/linux/efi.h | 4 ++ 4 files changed, 155 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 5002d50e3781..6ce31e93da55 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -18,14 +18,12 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644); static int efi_pstore_open(struct pstore_info *psi) { - efivar_entry_iter_begin(); psi->data = NULL; return 0; } static int efi_pstore_close(struct pstore_info *psi) { - efivar_entry_iter_end(); psi->data = NULL; return 0; } @@ -91,19 +89,125 @@ static int efi_pstore_read_func(struct efivar_entry *entry, void *data) __efivar_entry_get(entry, &entry->var.Attributes, &entry->var.DataSize, entry->var.Data); size = entry->var.DataSize; + memcpy(*cb_data->buf, entry->var.Data, + (size_t)min_t(unsigned long, EFIVARS_DATA_SIZE_MAX, size)); - *cb_data->buf = kmemdup(entry->var.Data, size, GFP_KERNEL); - if (*cb_data->buf == NULL) - return -ENOMEM; return size; } +/** + * efi_pstore_scan_sysfs_enter + * @entry: scanning entry + * @next: next entry + * @head: list head + */ +static void efi_pstore_scan_sysfs_enter(struct efivar_entry *pos, + struct efivar_entry *next, + struct list_head *head) +{ + pos->scanning = true; + if (&next->list != head) + next->scanning = true; +} + +/** + * __efi_pstore_scan_sysfs_exit + * @entry: deleting entry + * @turn_off_scanning: Check if a scanning flag should be turned off + */ +static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry, + bool turn_off_scanning) +{ + if (entry->deleting) { + list_del(&entry->list); + efivar_entry_iter_end(); + efivar_unregister(entry); + efivar_entry_iter_begin(); + } else if (turn_off_scanning) + entry->scanning = false; +} + +/** + * efi_pstore_scan_sysfs_exit + * @pos: scanning entry + * @next: next entry + * @head: list head + * @stop: a flag checking if scanning will stop + */ +static void efi_pstore_scan_sysfs_exit(struct efivar_entry *pos, + struct efivar_entry *next, + struct list_head *head, bool stop) +{ + __efi_pstore_scan_sysfs_exit(pos, true); + if (stop) + __efi_pstore_scan_sysfs_exit(next, &next->list != head); +} + +/** + * efi_pstore_sysfs_entry_iter + * + * @data: function-specific data to pass to callback + * @pos: entry to begin iterating from + * + * You MUST call efivar_enter_iter_begin() before this function, and + * efivar_entry_iter_end() afterwards. + * + * It is possible to begin iteration from an arbitrary entry within + * the list by passing @pos. @pos is updated on return to point to + * the next entry of the last one passed to efi_pstore_read_func(). + * To begin iterating from the beginning of the list @pos must be %NULL. + */ +static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos) +{ + struct efivar_entry *entry, *n; + struct list_head *head = &efivar_sysfs_list; + int size = 0; + + if (!*pos) { + list_for_each_entry_safe(entry, n, head, list) { + efi_pstore_scan_sysfs_enter(entry, n, head); + + size = efi_pstore_read_func(entry, data); + efi_pstore_scan_sysfs_exit(entry, n, head, size < 0); + if (size) + break; + } + *pos = n; + return size; + } + + list_for_each_entry_safe_from((*pos), n, head, list) { + efi_pstore_scan_sysfs_enter((*pos), n, head); + + size = efi_pstore_read_func((*pos), data); + efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0); + if (size) + break; + } + *pos = n; + return size; +} + +/** + * efi_pstore_read + * + * This function returns a size of NVRAM entry logged via efi_pstore_write(). + * The meaning and behavior of efi_pstore/pstore are as below. + * + * size > 0: Got data of an entry logged via efi_pstore_write() successfully, + * and pstore filesystem will continue reading subsequent entries. + * size == 0: Entry was not logged via efi_pstore_write(), + * and efi_pstore driver will continue reading subsequent entries. + * size < 0: Failed to get data of entry logging via efi_pstore_write(), + * and pstore will stop reading entry. + */ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *timespec, char **buf, bool *compressed, struct pstore_info *psi) { struct pstore_read_data data; + ssize_t size; data.id = id; data.type = type; @@ -112,8 +216,17 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, data.compressed = compressed; data.buf = buf; - return __efivar_entry_iter(efi_pstore_read_func, &efivar_sysfs_list, &data, - (struct efivar_entry **)&psi->data); + *data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL); + if (!*data.buf) + return -ENOMEM; + + efivar_entry_iter_begin(); + size = efi_pstore_sysfs_entry_iter(&data, + (struct efivar_entry **)&psi->data); + efivar_entry_iter_end(); + if (size <= 0) + kfree(*data.buf); + return size; } static int efi_pstore_write(enum pstore_type_id type, @@ -184,9 +297,17 @@ static int efi_pstore_erase_func(struct efivar_entry *entry, void *data) return 0; } + if (entry->scanning) { + /* + * Skip deletion because this entry will be deleted + * after scanning is completed. + */ + entry->deleting = true; + } else + list_del(&entry->list); + /* found */ __efivar_entry_delete(entry); - list_del(&entry->list); return 1; } @@ -214,10 +335,12 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, efivar_entry_iter_begin(); found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry); - efivar_entry_iter_end(); - if (found) + if (found && !entry->scanning) { + efivar_entry_iter_end(); efivar_unregister(entry); + } else + efivar_entry_iter_end(); return 0; } diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 933eb027d527..3dc248239197 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -383,12 +383,16 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, else if (__efivar_entry_delete(entry)) err = -EIO; - efivar_entry_iter_end(); - - if (err) + if (err) { + efivar_entry_iter_end(); return err; + } - efivar_unregister(entry); + if (!entry->scanning) { + efivar_entry_iter_end(); + efivar_unregister(entry); + } else + efivar_entry_iter_end(); /* It's dead Jim.... */ return count; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 391c67b182d9..b22659cccca4 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -683,8 +683,16 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, if (!found) return NULL; - if (remove) - list_del(&entry->list); + if (remove) { + if (entry->scanning) { + /* + * The entry will be deleted + * after scanning is completed. + */ + entry->deleting = true; + } else + list_del(&entry->list); + } return entry; } diff --git a/include/linux/efi.h b/include/linux/efi.h index bc5687d0f315..11ce6784a196 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -801,6 +801,8 @@ struct efivar_entry { struct efi_variable var; struct list_head list; struct kobject kobj; + bool scanning; + bool deleting; }; @@ -866,6 +868,8 @@ void efivar_run_worker(void); #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); +#define EFIVARS_DATA_SIZE_MAX 1024 + #endif /* CONFIG_EFI_VARS */ #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 31e20bad8d5871c6f8673c28ea26ab7a0e520086 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 28 Nov 2013 18:31:05 +0100 Subject: diag: warn about missing first netlink attribute The first netlink attribute (value 0) must always be defined as none/unspec. This is correctly done in inet_diag.h, but other diag interfaces are wrong. Because we cannot change an existing API, I add a comment to point the mistake and avoid to propagate it in a new diag API in the future. CC: Thomas Graf Signed-off-by: Nicolas Dichtel Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/netlink_diag.h | 1 + include/uapi/linux/packet_diag.h | 1 + include/uapi/linux/unix_diag.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index 4e31db4eea41..f2159d30d1f5 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -33,6 +33,7 @@ struct netlink_diag_ring { }; enum { + /* NETLINK_DIAG_NONE, standard nl API requires this attribute! */ NETLINK_DIAG_MEMINFO, NETLINK_DIAG_GROUPS, NETLINK_DIAG_RX_RING, diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index b2cc0cd9c4d9..d08c63f3dd6f 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -29,6 +29,7 @@ struct packet_diag_msg { }; enum { + /* PACKET_DIAG_NONE, standard nl API requires this attribute! */ PACKET_DIAG_INFO, PACKET_DIAG_MCLIST, PACKET_DIAG_RX_RING, diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h index b9e2a6a7446f..1eb0b8dd1830 100644 --- a/include/uapi/linux/unix_diag.h +++ b/include/uapi/linux/unix_diag.h @@ -31,6 +31,7 @@ struct unix_diag_msg { }; enum { + /* UNIX_DIAG_NONE, standard nl API requires this attribute! */ UNIX_DIAG_NAME, UNIX_DIAG_VFS, UNIX_DIAG_PEER, -- cgit v1.2.3 From 5e53e689b737526308db2b5c9f56e9d0371a1676 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 24 Nov 2013 21:09:26 +0100 Subject: genetlink/pmcraid: use proper genetlink multicast API The pmcraid driver is abusing the genetlink API and is using its family ID as the multicast group ID, which is invalid and may belong to somebody else (and likely will.) Make it use the correct API, but since this may already be used as-is by userspace, reserve a family ID for this code and also reserve that group ID to not break userspace assumptions. My previous patch broke event delivery in the driver as I missed that it wasn't using the right API and forgot to update it later in my series. While changing this, I noticed that the genetlink code could use the static group ID instead of a strcmp(), so also do that for the VFS_DQUOT family. Cc: Anil Ravindranath Cc: "James E.J. Bottomley" Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- drivers/scsi/pmcraid.c | 20 +++++++++++++++----- include/uapi/linux/genetlink.h | 1 + net/netlink/genetlink.c | 11 +++++++++-- 3 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index bd6f743d87a7..892ea6161376 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1404,11 +1404,22 @@ enum { }; #define PMCRAID_AEN_CMD_MAX (__PMCRAID_AEN_CMD_MAX - 1) +static struct genl_multicast_group pmcraid_mcgrps[] = { + { .name = "events", /* not really used - see ID discussion below */ }, +}; + static struct genl_family pmcraid_event_family = { - .id = GENL_ID_GENERATE, + /* + * Due to prior multicast group abuse (the code having assumed that + * the family ID can be used as a multicast group ID) we need to + * statically allocate a family (and thus group) ID. + */ + .id = GENL_ID_PMCRAID, .name = "pmcraid", .version = 1, - .maxattr = PMCRAID_AEN_ATTR_MAX + .maxattr = PMCRAID_AEN_ATTR_MAX, + .mcgrps = pmcraid_mcgrps, + .n_mcgrps = ARRAY_SIZE(pmcraid_mcgrps), }; /** @@ -1511,9 +1522,8 @@ static int pmcraid_notify_aen( return result; } - result = - genlmsg_multicast(&pmcraid_event_family, skb, 0, - pmcraid_event_family.id, GFP_ATOMIC); + result = genlmsg_multicast(&pmcraid_event_family, skb, + 0, 0, GFP_ATOMIC); /* If there are no listeners, genlmsg_multicast may return non-zero * value. diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index 1af72d8228e0..c3363ba1ae05 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -28,6 +28,7 @@ struct genlmsghdr { #define GENL_ID_GENERATE 0 #define GENL_ID_CTRL NLMSG_MIN_TYPE #define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1) +#define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2) /************************************************************************** * Controller diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 803206e82450..713671ae45af 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -74,9 +74,12 @@ static struct list_head family_ht[GENL_FAM_TAB_SIZE]; * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. + * Bit 18 is marked as already used since the PMCRAID driver + * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | - BIT(GENL_ID_VFS_DQUOT); + BIT(GENL_ID_VFS_DQUOT) | + BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; @@ -139,6 +142,7 @@ static u16 genl_generate_id(void) for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) { if (id_gen_idx != GENL_ID_VFS_DQUOT && + id_gen_idx != GENL_ID_PMCRAID && !genl_family_find_byid(id_gen_idx)) return id_gen_idx; if (++id_gen_idx > GENL_MAX_ID) @@ -236,9 +240,12 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) } else if (strcmp(family->name, "NET_DM") == 0) { first_id = 1; BUG_ON(n_groups != 1); - } else if (strcmp(family->name, "VFS_DQUOT") == 0) { + } else if (family->id == GENL_ID_VFS_DQUOT) { first_id = GENL_ID_VFS_DQUOT; BUG_ON(n_groups != 1); + } else if (family->id == GENL_ID_PMCRAID) { + first_id = GENL_ID_PMCRAID; + BUG_ON(n_groups != 1); } else { groups_allocated = true; err = genl_allocate_reserve_groups(n_groups, &first_id); -- cgit v1.2.3 From 6eabca54d6781f61c7318517c1463a098acb7a87 Mon Sep 17 00:00:00 2001 From: Xufeng Zhang Date: Mon, 25 Nov 2013 11:26:57 +0800 Subject: sctp: Restore 'resent' bit to avoid retransmitted chunks for RTT measurements Currently retransmitted DATA chunks could also be used for RTT measurements since there are no flag to identify whether the transmitted DATA chunk is a new one or a retransmitted one. This problem is introduced by commit ae19c5486 ("sctp: remove 'resent' bit from the chunk") which inappropriately removed the 'resent' bit completely, instead of doing this, we should set the resent bit only for the retransmitted DATA chunks. Signed-off-by: Xufeng Zhang Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + net/sctp/output.c | 3 ++- net/sctp/outqueue.c | 3 +++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2174d8da0770..ea0ca5f6e629 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -629,6 +629,7 @@ struct sctp_chunk { #define SCTP_NEED_FRTX 0x1 #define SCTP_DONT_FRTX 0x2 __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ + resent:1, /* Has this chunk ever been resent. */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ singleton:1, /* Only chunk in the packet? */ diff --git a/net/sctp/output.c b/net/sctp/output.c index e650978daf27..0e2644d0a773 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -474,10 +474,11 @@ int sctp_packet_transmit(struct sctp_packet *packet) * for a given destination transport address. */ - if (!tp->rto_pending) { + if (!chunk->resent && !tp->rto_pending) { chunk->rtt_in_progress = 1; tp->rto_pending = 1; } + has_data = 1; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index abb6db008df1..f51ba985a36e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -446,6 +446,8 @@ void sctp_retransmit_mark(struct sctp_outq *q, transport->rto_pending = 0; } + chunk->resent = 1; + /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ @@ -1375,6 +1377,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * instance). */ if (!tchunk->tsn_gap_acked && + !tchunk->resent && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; -- cgit v1.2.3 From 54b2b50c20a61b51199bedb6e5d2f8ec2568fb43 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 23 Oct 2013 06:25:40 -0400 Subject: [SCSI] Disable WRITE SAME for RAID and virtual host adapter drivers Some host adapters do not pass commands through to the target disk directly. Instead they provide an emulated target which may or may not accurately report its capabilities. In some cases the physical device characteristics are reported even when the host adapter is processing commands on the device's behalf. This can lead to adapter firmware hangs or excessive I/O errors. This patch disables WRITE SAME for devices connected to host adapters that provide an emulated target. Driver writers can disable WRITE SAME by setting the no_write_same flag in the host adapter template. [jejb: fix up rejections due to eh_deadline patch] Signed-off-by: Martin K. Petersen Cc: stable@kernel.org Signed-off-by: James Bottomley --- drivers/ata/libata-scsi.c | 1 + drivers/firewire/sbp2.c | 1 + drivers/scsi/3w-9xxx.c | 3 ++- drivers/scsi/3w-sas.c | 3 ++- drivers/scsi/3w-xxxx.c | 3 ++- drivers/scsi/aacraid/linit.c | 1 + drivers/scsi/arcmsr/arcmsr_hba.c | 1 + drivers/scsi/gdth.c | 1 + drivers/scsi/hosts.c | 1 + drivers/scsi/hpsa.c | 1 + drivers/scsi/ipr.c | 3 ++- drivers/scsi/ips.c | 1 + drivers/scsi/megaraid.c | 1 + drivers/scsi/megaraid/megaraid_mbox.c | 1 + drivers/scsi/megaraid/megaraid_sas_base.c | 1 + drivers/scsi/pmcraid.c | 1 + drivers/scsi/sd.c | 6 ++++++ drivers/scsi/storvsc_drv.c | 1 + include/scsi/scsi_host.h | 6 ++++++ 19 files changed, 33 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index db6dfcfa3e2e..ab58556d347c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3625,6 +3625,7 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht) shost->max_lun = 1; shost->max_channel = 1; shost->max_cmd_len = 16; + shost->no_write_same = 1; /* Schedule policy is determined by ->qc_defer() * callback and it needs to see every deferred qc. diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 281029daf98c..b0bb056458a3 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1623,6 +1623,7 @@ static struct scsi_host_template scsi_driver_template = { .cmd_per_lun = 1, .can_queue = 1, .sdev_attrs = sbp2_scsi_sysfs_attrs, + .no_write_same = 1, }; MODULE_AUTHOR("Kristian Hoegsberg "); diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 5e1e12c0cf42..0a7325361d29 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -2025,7 +2025,8 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = twa_host_attrs, - .emulated = 1 + .emulated = 1, + .no_write_same = 1, }; /* This function will probe and initialize a card */ diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index c845bdbeb6c0..4de346017e9f 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -1600,7 +1600,8 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = twl_host_attrs, - .emulated = 1 + .emulated = 1, + .no_write_same = 1, }; /* This function will probe and initialize a card */ diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index b9276d10b25c..752624e6bc00 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -2279,7 +2279,8 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = tw_host_attrs, - .emulated = 1 + .emulated = 1, + .no_write_same = 1, }; /* This function will probe and initialize a card */ diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index f0d432c139d0..4921ed19a027 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1081,6 +1081,7 @@ static struct scsi_host_template aac_driver_template = { #endif .use_clustering = ENABLE_CLUSTERING, .emulated = 1, + .no_write_same = 1, }; static void __aac_shutdown(struct aac_dev * aac) diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 97fd450aff09..4f6a30b8e5f9 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -137,6 +137,7 @@ static struct scsi_host_template arcmsr_scsi_host_template = { .cmd_per_lun = ARCMSR_MAX_CMD_PERLUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = arcmsr_host_attrs, + .no_write_same = 1, }; static struct pci_device_id arcmsr_device_id_table[] = { {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110)}, diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c index ee4fa40a50b1..ce5ef0190bad 100644 --- a/drivers/scsi/gdth.c +++ b/drivers/scsi/gdth.c @@ -4684,6 +4684,7 @@ static struct scsi_host_template gdth_template = { .cmd_per_lun = GDTH_MAXC_P_L, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, + .no_write_same = 1, }; #ifdef CONFIG_ISA diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index f334859024c0..f2c5005f312a 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -395,6 +395,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->use_clustering = sht->use_clustering; shost->ordered_tag = sht->ordered_tag; shost->eh_deadline = shost_eh_deadline * HZ; + shost->no_write_same = sht->no_write_same; if (sht->supported_mode == MODE_UNKNOWN) /* means we didn't set it ... default to INITIATOR */ diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 22f6432eb475..2336beff7a48 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -561,6 +561,7 @@ static struct scsi_host_template hpsa_driver_template = { .sdev_attrs = hpsa_sdev_attrs, .shost_attrs = hpsa_shost_attrs, .max_sectors = 8192, + .no_write_same = 1, }; diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 36ac1c34ce97..573f4128b6b6 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6305,7 +6305,8 @@ static struct scsi_host_template driver_template = { .use_clustering = ENABLE_CLUSTERING, .shost_attrs = ipr_ioa_attrs, .sdev_attrs = ipr_dev_attrs, - .proc_name = IPR_NAME + .proc_name = IPR_NAME, + .no_write_same = 1, }; /** diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c index 8d5ea8a1e5a6..52a216f21ae5 100644 --- a/drivers/scsi/ips.c +++ b/drivers/scsi/ips.c @@ -374,6 +374,7 @@ static struct scsi_host_template ips_driver_template = { .sg_tablesize = IPS_MAX_SG, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, + .no_write_same = 1, }; diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 90c95a3385d1..816db12ef5d5 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4244,6 +4244,7 @@ static struct scsi_host_template megaraid_template = { .eh_device_reset_handler = megaraid_reset, .eh_bus_reset_handler = megaraid_reset, .eh_host_reset_handler = megaraid_reset, + .no_write_same = 1, }; static int diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c index d1a4b82836ea..e2237a97cb9d 100644 --- a/drivers/scsi/megaraid/megaraid_mbox.c +++ b/drivers/scsi/megaraid/megaraid_mbox.c @@ -367,6 +367,7 @@ static struct scsi_host_template megaraid_template_g = { .eh_host_reset_handler = megaraid_reset_handler, .change_queue_depth = megaraid_change_queue_depth, .use_clustering = ENABLE_CLUSTERING, + .no_write_same = 1, .sdev_attrs = megaraid_sdev_attrs, .shost_attrs = megaraid_shost_attrs, }; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 0a743a5d1647..c99812bf2a73 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2148,6 +2148,7 @@ static struct scsi_host_template megasas_template = { .bios_param = megasas_bios_param, .use_clustering = ENABLE_CLUSTERING, .change_queue_depth = megasas_change_queue_depth, + .no_write_same = 1, }; /** diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index bd6f743d87a7..f413ef796b43 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -4315,6 +4315,7 @@ static struct scsi_host_template pmcraid_host_template = { .this_id = -1, .sg_tablesize = PMCRAID_MAX_IOADLS, .max_sectors = PMCRAID_IOA_MAX_SECTORS, + .no_write_same = 1, .cmd_per_lun = PMCRAID_MAX_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = pmcraid_host_attrs, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e6c4bff04339..69725f7c32c1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2659,6 +2659,12 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdev = sdkp->device; + if (sdev->host->no_write_same) { + sdev->no_write_same = 1; + + return; + } + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) { /* too large values might cause issues with arcmsr */ int vpd_buf_len = 64; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 1a28f5632797..17d740427240 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1697,6 +1697,7 @@ static struct scsi_host_template scsi_driver = { .use_clustering = DISABLE_CLUSTERING, /* Make sure we dont get a sg segment crosses a page boundary */ .dma_boundary = PAGE_SIZE-1, + .no_write_same = 1, }; enum { diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 546084964d55..fe3b58e836c8 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -475,6 +475,9 @@ struct scsi_host_template { */ unsigned ordered_tag:1; + /* True if the controller does not support WRITE SAME */ + unsigned no_write_same:1; + /* * Countdown for host blocking with no commands outstanding. */ @@ -677,6 +680,9 @@ struct Scsi_Host { /* Don't resume host in EH */ unsigned eh_noresume:1; + /* The controller does not support WRITE SAME */ + unsigned no_write_same:1; + /* * Optional work queue to be utilized by the transport */ -- cgit v1.2.3 From 98bf8362220af717862b8262b21348774890b7b4 Mon Sep 17 00:00:00 2001 From: Arvid Brodin Date: Fri, 29 Nov 2013 23:38:16 +0100 Subject: net/hsr: Support iproute print_opt ('ip -details ...') This implements the rtnl_link_ops fill_info routine for HSR. Signed-off-by: Arvid Brodin Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 4 +++- net/hsr/hsr_netlink.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b78566f59aba..6db460121f84 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -488,7 +488,9 @@ enum { IFLA_HSR_UNSPEC, IFLA_HSR_SLAVE1, IFLA_HSR_SLAVE2, - IFLA_HSR_MULTICAST_SPEC, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, __IFLA_HSR_MAX, }; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 5325af85eea6..01a5261ac7a5 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -23,6 +23,8 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_SLAVE1] = { .type = NLA_U32 }, [IFLA_HSR_SLAVE2] = { .type = NLA_U32 }, [IFLA_HSR_MULTICAST_SPEC] = { .type = NLA_U8 }, + [IFLA_HSR_SUPERVISION_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, }; @@ -59,6 +61,31 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return hsr_dev_finalize(dev, link, multicast_spec); } +static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct hsr_priv *hsr_priv; + + hsr_priv = netdev_priv(dev); + + if (hsr_priv->slave[0]) + if (nla_put_u32(skb, IFLA_HSR_SLAVE1, hsr_priv->slave[0]->ifindex)) + goto nla_put_failure; + + if (hsr_priv->slave[1]) + if (nla_put_u32(skb, IFLA_HSR_SLAVE2, hsr_priv->slave[1]->ifindex)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, + hsr_priv->sup_multicast_addr) || + nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr_priv->sequence_nr)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static struct rtnl_link_ops hsr_link_ops __read_mostly = { .kind = "hsr", .maxtype = IFLA_HSR_MAX, @@ -66,6 +93,7 @@ static struct rtnl_link_ops hsr_link_ops __read_mostly = { .priv_size = sizeof(struct hsr_priv), .setup = hsr_dev_setup, .newlink = hsr_newlink, + .fill_info = hsr_fill_info, }; -- cgit v1.2.3 From c9a9972b6f093e4e2f81f58892a7523df894144d Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Mon, 25 Nov 2013 18:34:24 +0900 Subject: gpiolib: add missing declarations Add declaration of 'struct of_phandle_args' to avoid the following warning: In file included from arch/arm/mach-tegra/board-paz00.c:21:0: include/linux/gpio/driver.h:102:17: warning: 'struct of_phandle_args' declared inside parameter list include/linux/gpio/driver.h:102:17: warning: its scope is only this definition or declaration, which is probably not what you want Also proactively add other definitions/includes that could be missing in other contexts. Signed-off-by: Alexandre Courbot Reported-by: Stephen Warren Reviewed-by: Mika Westerberg Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 82eac610ce1a..3ea2cf6b0e6c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -2,9 +2,12 @@ #define __LINUX_GPIO_DRIVER_H #include +#include struct device; struct gpio_desc; +struct of_phandle_args; +struct device_node; struct seq_file; /** -- cgit v1.2.3 From 95f19f658ce177387345b51bd48fed7b9cd7d4e8 Mon Sep 17 00:00:00 2001 From: Amit Pundir Date: Fri, 15 Nov 2013 12:56:31 +0530 Subject: epoll: drop EPOLLWAKEUP if PM_SLEEP is disabled Drop EPOLLWAKEUP from epoll events mask if CONFIG_PM_SLEEP is disabled. Signed-off-by: Amit Pundir Cc: John Stultz Cc: Alexander Viro Signed-off-by: Rafael J. Wysocki --- fs/eventpoll.c | 3 +-- include/uapi/linux/eventpoll.h | 13 ++++++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 79b65c3b9e87..8b5e2584c840 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) - epds.events &= ~EPOLLWAKEUP; + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 2c267bcbb85c..bc81fb2e1f0e 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -61,5 +61,16 @@ struct epoll_event { __u64 data; } EPOLL_PACKED; - +#ifdef CONFIG_PM_SLEEP +static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) +{ + if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) + epev->events &= ~EPOLLWAKEUP; +} +#else +static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) +{ + epev->events &= ~EPOLLWAKEUP; +} +#endif #endif /* _UAPI_LINUX_EVENTPOLL_H */ -- cgit v1.2.3