From eccdaeafaea3ed115068ba55d01f22e486e5437d Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Mon, 24 Nov 2008 15:46:31 +0100 Subject: posix-cpu-timers: fix clock_gettime with CLOCK_PROCESS_CPUTIME_ID Since CLOCK_PROCESS_CPUTIME_ID is in fact translated to -6, the switch statement in cpu_clock_sample_group() must first mask off the irrelevant bits, similar to cpu_clock_sample(). Signed-off-by: Petr Tesarik Signed-off-by: Thomas Gleixner -- posix-cpu-timers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- kernel/posix-cpu-timers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 895337b16a2..4e5288a831d 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -311,7 +311,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_cputime cputime; thread_group_cputime(p, &cputime); - switch (which_clock) { + switch (CPUCLOCK_WHICH(which_clock)) { default: return -EINVAL; case CPUCLOCK_PROF: -- cgit v1.2.3 From 70574a996fc7a70c5586eb56bd92a544eccf18b6 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 28 Nov 2008 22:08:00 +0300 Subject: sched: move double_unlock_balance() higher Move double_lock_balance()/double_unlock_balance() higher to fix the following with gcc-3.4.6: CC kernel/sched.o In file included from kernel/sched.c:1605: kernel/sched_rt.c: In function `find_lock_lowest_rq': kernel/sched_rt.c:914: sorry, unimplemented: inlining failed in call to 'double_unlock_balance': function body not available kernel/sched_rt.c:1077: sorry, unimplemented: called from here make[2]: *** [kernel/sched.o] Error 1 Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar --- kernel/sched.c | 67 +++++++++++++++++++++++++++---------------------------- kernel/sched_rt.c | 4 ---- 2 files changed, 33 insertions(+), 38 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 3d1ee429219..6a99703e0eb 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1581,6 +1581,39 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) #endif +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static int double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + int ret = 0; + + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + spin_unlock(&this_rq->lock); + BUG_ON(1); + } + if (unlikely(!spin_trylock(&busiest->lock))) { + if (busiest < this_rq) { + spin_unlock(&this_rq->lock); + spin_lock(&busiest->lock); + spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); + ret = 1; + } else + spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); + } + return ret; +} + +static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -2780,40 +2813,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) __release(rq2->lock); } -/* - * double_lock_balance - lock the busiest runqueue, this_rq is locked already. - */ -static int double_lock_balance(struct rq *this_rq, struct rq *busiest) - __releases(this_rq->lock) - __acquires(busiest->lock) - __acquires(this_rq->lock) -{ - int ret = 0; - - if (unlikely(!irqs_disabled())) { - /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); - BUG_ON(1); - } - if (unlikely(!spin_trylock(&busiest->lock))) { - if (busiest < this_rq) { - spin_unlock(&this_rq->lock); - spin_lock(&busiest->lock); - spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); - ret = 1; - } else - spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); - } - return ret; -} - -static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) - __releases(busiest->lock) -{ - spin_unlock(&busiest->lock); - lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); -} - /* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 2bdd4442359..587a16e2a8f 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -909,10 +909,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) /* Only try algorithms three times */ #define RT_MAX_TRIES 3 -static int double_lock_balance(struct rq *this_rq, struct rq *busiest); -static inline void double_unlock_balance(struct rq *this_rq, - struct rq *busiest); - static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) -- cgit v1.2.3 From 6c415b9234a8c71f290e5d4fddc467f103f32719 Mon Sep 17 00:00:00 2001 From: Arun R Bharadwaj Date: Mon, 1 Dec 2008 20:49:05 +0530 Subject: sched: add uid information to sched_debug for CONFIG_USER_SCHED Impact: extend information in /proc/sched_debug This patch adds uid information in sched_debug for CONFIG_USER_SCHED Signed-off-by: Arun R Bharadwaj Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 ++++++++++ kernel/sched_debug.c | 6 +++++- kernel/user.c | 2 ++ 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 6a99703e0eb..4c7388ef5be 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -261,6 +261,10 @@ struct task_group { struct cgroup_subsys_state css; #endif +#ifdef CONFIG_USER_SCHED + uid_t uid; +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each cpu */ struct sched_entity **se; @@ -286,6 +290,12 @@ struct task_group { #ifdef CONFIG_USER_SCHED +/* Helper function to pass uid information to create_sched_user() */ +void set_tg_uid(struct user_struct *user) +{ + user->tg->uid = user->uid; +} + /* * Root task group. * Every UID task group (including init_task_group aka UID-0) will diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index baf2f17af46..4293cfa9681 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -160,10 +160,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cgroup_path(tg->css.cgroup, path, sizeof(path)); SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); +#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) + { + uid_t uid = cfs_rq->tg->uid; + SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid); + } #else SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); #endif - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", SPLIT_NS(cfs_rq->exec_clock)); diff --git a/kernel/user.c b/kernel/user.c index 39d6159fae4..cec2224bc9f 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -101,6 +101,8 @@ static int sched_create_user(struct user_struct *up) if (IS_ERR(up->tg)) rc = -ENOMEM; + set_tg_uid(up); + return rc; } -- cgit v1.2.3 From 201955463a5c1a70d3f70d1598b27e4c2c402642 Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Tue, 2 Dec 2008 22:55:38 +0100 Subject: check_hung_task(): unsigned sysctl_hung_task_warnings cannot be less than 0 Impact: fix warnings-limit cutoff check for debug feature unsigned sysctl_hung_task_warnings cannot be less than 0 Signed-off-by: Roel Kluin Signed-off-by: Ingo Molnar --- kernel/softlockup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 3953e4aed73..dc0b3be6b7d 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -188,7 +188,7 @@ static void check_hung_task(struct task_struct *t, unsigned long now) if ((long)(now - t->last_switch_timestamp) < sysctl_hung_task_timeout_secs) return; - if (sysctl_hung_task_warnings < 0) + if (!sysctl_hung_task_warnings) return; sysctl_hung_task_warnings--; -- cgit v1.2.3 From 6c9bacb41c10ba84ff68f238e234d96f35fb64f7 Mon Sep 17 00:00:00 2001 From: john stultz Date: Mon, 1 Dec 2008 18:34:41 -0800 Subject: time: catch xtime_nsec underflows and fix them Impact: fix time warp bug Alex Shi, along with Yanmin Zhang have been noticing occasional time inconsistencies recently. Through their great diagnosis, they found that the xtime_nsec value used in update_wall_time was occasionally going negative. After looking through the code for awhile, I realized we have the possibility for an underflow when three conditions are met in update_wall_time(): 1) We have accumulated a second's worth of nanoseconds, so we incremented xtime.tv_sec and appropriately decrement xtime_nsec. (This doesn't cause xtime_nsec to go negative, but it can cause it to be small). 2) The remaining offset value is large, but just slightly less then cycle_interval. 3) clocksource_adjust() is speeding up the clock, causing a corrective amount (compensating for the increase in the multiplier being multiplied against the unaccumulated offset value) to be subtracted from xtime_nsec. This can cause xtime_nsec to underflow. Unfortunately, since we notify the NTP subsystem via second_overflow() whenever we accumulate a full second, and this effects the error accumulation that has already occured, we cannot simply revert the accumulated second from xtime nor move the second accumulation to after the clocksource_adjust call without a change in behavior. This leaves us with (at least) two options: 1) Simply return from clocksource_adjust() without making a change if we notice the adjustment would cause xtime_nsec to go negative. This would work, but I'm concerned that if a large adjustment was needed (due to the error being large), it may be possible to get stuck with an ever increasing error that becomes too large to correct (since it may always force xtime_nsec negative). This may just be paranoia on my part. 2) Catch xtime_nsec if it is negative, then add back the amount its negative to both xtime_nsec and the error. This second method is consistent with how we've handled earlier rounding issues, and also has the benefit that the error being added is always in the oposite direction also always equal or smaller then the correction being applied. So the risk of a corner case where things get out of control is lessened. This patch fixes bug 11970, as tested by Yanmin Zhang http://bugzilla.kernel.org/show_bug.cgi?id=11970 Reported-by: alex.shi@intel.com Signed-off-by: John Stultz Acked-by: "Zhang, Yanmin" Tested-by: "Zhang, Yanmin" Signed-off-by: Ingo Molnar --- kernel/time/timekeeping.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'kernel') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e7acfb482a6..fa05e88aa76 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -518,6 +518,28 @@ void update_wall_time(void) /* correct the clock when NTP error is too big */ clocksource_adjust(offset); + /* + * Since in the loop above, we accumulate any amount of time + * in xtime_nsec over a second into xtime.tv_sec, its possible for + * xtime_nsec to be fairly small after the loop. Further, if we're + * slightly speeding the clocksource up in clocksource_adjust(), + * its possible the required corrective factor to xtime_nsec could + * cause it to underflow. + * + * Now, we cannot simply roll the accumulated second back, since + * the NTP subsystem has been notified via second_overflow. So + * instead we push xtime_nsec forward by the amount we underflowed, + * and add that amount into the error. + * + * We'll correct this error next time through this function, when + * xtime_nsec is not as small. + */ + if (unlikely((s64)clock->xtime_nsec < 0)) { + s64 neg = -(s64)clock->xtime_nsec; + clock->xtime_nsec = 0; + clock->error += neg << (NTP_SCALE_SHIFT - clock->shift); + } + /* store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ -- cgit v1.2.3 From 50c396d38c1a7f0c693579ec88cb4be3c0b0645e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 30 Nov 2008 01:47:12 -0500 Subject: [PATCH] kill obsolete temporary comment in swsusp_close() it had been put there to mark the call of blkdev_put() that needed proper argument propagated to it; later patch in the same series had done just that. Signed-off-by: Al Viro --- kernel/power/swap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b7713b53d07..6da14358537 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -633,7 +633,7 @@ void swsusp_close(fmode_t mode) return; } - blkdev_put(resume_bdev, mode); /* move up */ + blkdev_put(resume_bdev, mode); } static int swsusp_header_init(void) -- cgit v1.2.3 From 5436499e6098759c2340f8b906ea52f993dc4efb Mon Sep 17 00:00:00 2001 From: Ken Chen Date: Sun, 7 Dec 2008 18:47:37 -0800 Subject: sched: fix sd_parent_degenerate on non-numa smp machine Impact: optimize the sched domains tree some more The addition of SD_SERIALIZE flag added to SD_NODE_INIT prevented top level dummy numa sched_domain to be properly degenerated on non-numa smp machine. The reason is that in sd_parent_degenerate(), it found that the child and parent does not have comon sched_domain flags due to SD_SERIALIZE. However, for non-numa smp box, the top level is a dummy with a single sched_group. Filter out SD_SERIALIZE if it is on non-numa machine to properly degenerate top level node sched_domain. this will cut back some of the sd domain walk in the load balancer code. Signed-off-by: Ken Chen Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 152828239ef..74498c840f9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6768,6 +6768,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; } if (~cflags & pflags) return 0; -- cgit v1.2.3 From efbe027e95dc13ac343b6130948418d7ead7ddf1 Mon Sep 17 00:00:00 2001 From: Vaidyanathan Srinivasan Date: Mon, 8 Dec 2008 20:52:49 +0530 Subject: sched: idle_balance() does not call load_balance_newidle() Impact: fix SD_BALANCE_NEWIDLEand broaden its use load_balance_newidle() does not get called if SD_BALANCE_NEWIDLE is set at higher level domain (3-CPU) and not in low level domain (2-MC). pulled_task is initialised to -1 and checked for non-zero which is always true if the lowest level sched_domain does not have SD_BALANCE_NEWIDLE flag set. Signed-off-by: Vaidyanathan Srinivasan Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 74498c840f9..bb9c6384d07 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3685,7 +3685,7 @@ out_balanced: static void idle_balance(int this_cpu, struct rq *this_rq) { struct sched_domain *sd; - int pulled_task = -1; + int pulled_task = 0; unsigned long next_balance = jiffies + HZ; cpumask_t tmpmask; -- cgit v1.2.3 From a3f07114e3359fb98683069ae397220e8992a24a Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Wed, 5 Nov 2008 12:47:09 -0500 Subject: [PATCH] Audit: make audit=0 actually turn off audit Currently audit=0 on the kernel command line does absolutely nothing. Audit always loads and always uses its resources such as creating the kernel netlink socket. This patch causes audit=0 to actually disable audit. Audit will use no resources and starting the userspace auditd daemon will not cause the kernel audit system to activate. Signed-off-by: Eric Paris Signed-off-by: Al Viro --- kernel/audit.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 4414e93d875..d8646c23b42 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -61,8 +61,11 @@ #include "audit.h" -/* No auditing will take place until audit_initialized != 0. +/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ +#define AUDIT_DISABLED -1 +#define AUDIT_UNINITIALIZED 0 +#define AUDIT_INITIALIZED 1 static int audit_initialized; #define AUDIT_OFF 0 @@ -965,6 +968,9 @@ static int __init audit_init(void) { int i; + if (audit_initialized == AUDIT_DISABLED) + return 0; + printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0, @@ -976,7 +982,7 @@ static int __init audit_init(void) skb_queue_head_init(&audit_skb_queue); skb_queue_head_init(&audit_skb_hold_queue); - audit_initialized = 1; + audit_initialized = AUDIT_INITIALIZED; audit_enabled = audit_default; audit_ever_enabled |= !!audit_default; @@ -999,13 +1005,21 @@ __initcall(audit_init); static int __init audit_enable(char *str) { audit_default = !!simple_strtol(str, NULL, 0); - printk(KERN_INFO "audit: %s%s\n", - audit_default ? "enabled" : "disabled", - audit_initialized ? "" : " (after initialization)"); - if (audit_initialized) { + if (!audit_default) + audit_initialized = AUDIT_DISABLED; + + printk(KERN_INFO "audit: %s", audit_default ? "enabled" : "disabled"); + + if (audit_initialized == AUDIT_INITIALIZED) { audit_enabled = audit_default; audit_ever_enabled |= !!audit_default; + } else if (audit_initialized == AUDIT_UNINITIALIZED) { + printk(" (after initialization)"); + } else { + printk(" (until reboot)"); } + printk("\n"); + return 1; } @@ -1146,7 +1160,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int reserve; unsigned long timeout_start = jiffies; - if (!audit_initialized) + if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(audit_filter_type(type))) -- cgit v1.2.3 From a64e64944f4b8ce3288519555dbaa0232414b8ac Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Nov 2008 18:37:41 -0500 Subject: [PATCH] return records for fork() both to child and parent Signed-off-by: Al Viro --- kernel/auditsc.c | 17 +++++++++++++++++ kernel/fork.c | 1 + 2 files changed, 18 insertions(+) (limited to 'kernel') diff --git a/kernel/auditsc.c b/kernel/auditsc.c index cf5bc2f5f9c..de8468050af 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1548,6 +1548,23 @@ void audit_syscall_entry(int arch, int major, context->ppid = 0; } +void audit_finish_fork(struct task_struct *child) +{ + struct audit_context *ctx = current->audit_context; + struct audit_context *p = child->audit_context; + if (!p || !ctx || !ctx->auditable) + return; + p->arch = ctx->arch; + p->major = ctx->major; + memcpy(p->argv, ctx->argv, sizeof(ctx->argv)); + p->ctime = ctx->ctime; + p->dummy = ctx->dummy; + p->auditable = ctx->auditable; + p->in_syscall = ctx->in_syscall; + p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL); + p->ppid = current->pid; +} + /** * audit_syscall_exit - deallocate audit context after a system call * @tsk: task being audited diff --git a/kernel/fork.c b/kernel/fork.c index 2a372a0e206..8d6a7dd9282 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1398,6 +1398,7 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } + audit_finish_fork(p); tracehook_report_clone(trace, regs, clone_flags, nr, p); /* -- cgit v1.2.3 From 7f0ed77d241b60f70136f15b8eef30a3de1fa249 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 1 Dec 2008 14:16:06 -0800 Subject: [patch 1/1] audit: remove excess kernel-doc Delete excess kernel-doc notation in kernel/auditsc.c: Warning(linux-2.6.27-git10//kernel/auditsc.c:1481): Excess function parameter or struct member 'tsk' description in 'audit_syscall_entry' Warning(linux-2.6.27-git10//kernel/auditsc.c:1564): Excess function parameter or struct member 'tsk' description in 'audit_syscall_exit' Signed-off-by: Randy Dunlap Cc: Al Viro Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- kernel/auditsc.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/auditsc.c b/kernel/auditsc.c index de8468050af..0a13d689549 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1459,7 +1459,6 @@ void audit_free(struct task_struct *tsk) /** * audit_syscall_entry - fill in an audit record at syscall entry - * @tsk: task being audited * @arch: architecture type * @major: major syscall type (function) * @a1: additional syscall register 1 @@ -1567,7 +1566,6 @@ void audit_finish_fork(struct task_struct *child) /** * audit_syscall_exit - deallocate audit context after a system call - * @tsk: task being audited * @valid: success/failure flag * @return_code: syscall return value * -- cgit v1.2.3 From 48887e63d6e057543067327da6b091297f7fe645 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 6 Dec 2008 01:05:50 -0500 Subject: [PATCH] fix broken timestamps in AVC generated by kernel threads Timestamp in audit_context is valid only if ->in_syscall is set. Signed-off-by: Al Viro --- kernel/audit.c | 4 +--- kernel/auditsc.c | 5 ++++- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index d8646c23b42..ce6d8ea3131 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1121,9 +1121,7 @@ unsigned int audit_serial(void) static inline void audit_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { - if (ctx) - auditsc_get_stamp(ctx, t, serial); - else { + if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { *t = CURRENT_TIME; *serial = audit_serial(); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 0a13d689549..2a3f0afc4d2 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1957,15 +1957,18 @@ EXPORT_SYMBOL_GPL(__audit_inode_child); * * Also sets the context as auditable. */ -void auditsc_get_stamp(struct audit_context *ctx, +int auditsc_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { + if (!ctx->in_syscall) + return 0; if (!ctx->serial) ctx->serial = audit_serial(); t->tv_sec = ctx->ctime.tv_sec; t->tv_nsec = ctx->ctime.tv_nsec; *serial = ctx->serial; ctx->auditable = 1; + return 1; } /* global counter which is incremented every time something logs in */ -- cgit v1.2.3 From 9a2bd244e18ffbb96c8b783210fda4eded7c7e6f Mon Sep 17 00:00:00 2001 From: Brian King Date: Tue, 9 Dec 2008 08:47:00 -0600 Subject: sched: CPU remove deadlock fix Impact: fix possible deadlock in CPU hot-remove path This patch fixes a possible deadlock scenario in the CPU remove path. migration_call grabs rq->lock, then wakes up everything on rq->migration_queue with the lock held. Then one of the tasks on the migration queue ends up calling tg_shares_up which then also tries to acquire the same rq->lock. [c000000058eab2e0] c000000000502078 ._spin_lock_irqsave+0x98/0xf0 [c000000058eab370] c00000000008011c .tg_shares_up+0x10c/0x20c [c000000058eab430] c00000000007867c .walk_tg_tree+0xc4/0xfc [c000000058eab4d0] c0000000000840c8 .try_to_wake_up+0xb0/0x3c4 [c000000058eab590] c0000000000799a0 .__wake_up_common+0x6c/0xe0 [c000000058eab640] c00000000007ada4 .complete+0x54/0x80 [c000000058eab6e0] c000000000509fa8 .migration_call+0x5fc/0x6f8 [c000000058eab7c0] c000000000504074 .notifier_call_chain+0x68/0xe0 [c000000058eab860] c000000000506568 ._cpu_down+0x2b0/0x3f4 [c000000058eaba60] c000000000506750 .cpu_down+0xa4/0x108 [c000000058eabb10] c000000000507e54 .store_online+0x44/0xa8 [c000000058eabba0] c000000000396260 .sysdev_store+0x3c/0x50 [c000000058eabc10] c0000000001a39b8 .sysfs_write_file+0x124/0x18c [c000000058eabcd0] c00000000013061c .vfs_write+0xd0/0x1bc [c000000058eabd70] c0000000001308a4 .sys_write+0x68/0x114 [c000000058eabe30] c0000000000086b4 syscall_exit+0x0/0x40 Signed-off-by: Brian King Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index b7480fb5c3d..e4bb1dd7b30 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6587,7 +6587,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) req = list_entry(rq->migration_queue.next, struct migration_req, list); list_del_init(&req->list); + spin_unlock_irq(&rq->lock); complete(&req->done); + spin_lock_irq(&rq->lock); } spin_unlock_irq(&rq->lock); break; -- cgit v1.2.3 From fbb5b7ae4b442f1923513dc6165a66c7a7f29073 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Tue, 9 Dec 2008 13:14:10 -0800 Subject: relayfs: fix infinite loop with splice() Running kmemtraced, which uses splice() on relayfs, causes a hard lock on x86-64 SMP. As described by Tom Zanussi: It looks like you hit the same problem as described here: commit 8191ecd1d14c6914c660dfa007154860a7908857 splice: fix infinite loop in generic_file_splice_read() relay uses the same loop but it never got noticed or fixed. Cc: Mathieu Desnoyers Tested-by: Pekka Enberg Signed-off-by: Tom Zanussi Signed-off-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/relay.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/relay.c b/kernel/relay.c index 32b0befdcb6..09ac2008f77 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1317,12 +1317,9 @@ static ssize_t relay_file_splice_read(struct file *in, if (ret < 0) break; else if (!ret) { - if (spliced) - break; - if (flags & SPLICE_F_NONBLOCK) { + if (flags & SPLICE_F_NONBLOCK) ret = -EAGAIN; - break; - } + break; } *ppos += ret; -- cgit v1.2.3 From 9c24624727f6d6c460e45762a408ca5f5b9b8ef2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 9 Dec 2008 13:14:27 -0800 Subject: KSYM_SYMBOL_LEN fixes Miles Lane tailing /sys files hit a BUG which Pekka Enberg has tracked to my 966c8c12dc9e77f931e2281ba25d2f0244b06949 sprint_symbol(): use less stack exposing a bug in slub's list_locations() - kallsyms_lookup() writes a 0 to namebuf[KSYM_NAME_LEN-1], but that was beyond the end of page provided. The 100 slop which list_locations() allows at end of page looks roughly enough for all the other stuff it might print after the symbol before it checks again: break out KSYM_SYMBOL_LEN earlier than before. Latencytop and ftrace and are using KSYM_NAME_LEN buffers where they need KSYM_SYMBOL_LEN buffers, and vmallocinfo a 2*KSYM_NAME_LEN buffer where it wants a KSYM_SYMBOL_LEN buffer: fix those before anyone copies them. [akpm@linux-foundation.org: ftrace.h needs module.h] Signed-off-by: Hugh Dickins Cc: Christoph Lameter Cc Miles Lane Acked-by: Pekka Enberg Acked-by: Steven Rostedt Acked-by: Frederic Weisbecker Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/latencytop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 5e7b45c5692..449db466bdb 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -191,7 +191,7 @@ static int lstats_show(struct seq_file *m, void *v) latency_record[i].time, latency_record[i].max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { - char sym[KSYM_NAME_LEN]; + char sym[KSYM_SYMBOL_LEN]; char *c; if (!latency_record[i].backtrace[q]) break; -- cgit v1.2.3 From b88ed20594db2c685555b68c52b693b75738b2f5 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 10 Dec 2008 20:48:52 +0000 Subject: fix mapping_writably_mapped() Lee Schermerhorn noticed yesterday that I broke the mapping_writably_mapped test in 2.6.7! Bad bad bug, good good find. The i_mmap_writable count must be incremented for VM_SHARED (just as i_writecount is for VM_DENYWRITE, but while holding the i_mmap_lock) when dup_mmap() copies the vma for fork: it has its own more optimal version of __vma_link_file(), and I missed this out. So the count was later going down to 0 (dangerous) when one end unmapped, then wrapping negative (inefficient) when the other end unmapped. The only impact on x86 would have been that setting a mandatory lock on a file which has at some time been opened O_RDWR and mapped MAP_SHARED (but not necessarily PROT_WRITE) across a fork, might fail with -EAGAIN when it should succeed, or succeed when it should fail. But those architectures which rely on flush_dcache_page() to flush userspace modifications back into the page before the kernel reads it, may in some cases have skipped the flush after such a fork - though any repetitive test will soon wrap the count negative, in which case it will flush_dcache_page() unnecessarily. Fix would be a two-liner, but mapping variable added, and comment moved. Reported-by: Lee Schermerhorn Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- kernel/fork.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 8d6a7dd9282..495da2e9a8b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -315,17 +315,20 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; + struct address_space *mapping = file->f_mapping; + get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); - - /* insert tmp into the share list, just after mpnt */ - spin_lock(&file->f_mapping->i_mmap_lock); + spin_lock(&mapping->i_mmap_lock); + if (tmp->vm_flags & VM_SHARED) + mapping->i_mmap_writable++; tmp->vm_truncate_count = mpnt->vm_truncate_count; - flush_dcache_mmap_lock(file->f_mapping); + flush_dcache_mmap_lock(mapping); + /* insert tmp into the share list, just after mpnt */ vma_prio_tree_add(tmp, mpnt); - flush_dcache_mmap_unlock(file->f_mapping); - spin_unlock(&file->f_mapping->i_mmap_lock); + flush_dcache_mmap_unlock(mapping); + spin_unlock(&mapping->i_mmap_lock); } /* -- cgit v1.2.3 From ee79d1bdb6a10499e53f80b1e8d14110215178ba Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 9 Dec 2008 18:49:50 +0100 Subject: sched: let arch_update_cpu_topology indicate if topology changed Change arch_update_cpu_topology so it returns 1 if the cpu topology changed and 0 if it didn't change. This will be useful for the next patch which adds a call to this function in partition_sched_domains. Signed-off-by: Heiko Carstens Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index ef212da928e..fcfbbd9dbd6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7675,8 +7675,14 @@ static struct sched_domain_attr *dattr_cur; */ static cpumask_t fallback_doms; -void __attribute__((weak)) arch_update_cpu_topology(void) +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __attribute__((weak)) arch_update_cpu_topology(void) { + return 0; } /* -- cgit v1.2.3 From d65bd5ecb2bd166cea4952a59b7e16cc3ad6ef6c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 9 Dec 2008 18:49:51 +0100 Subject: sched: add missing arch_update_cpu_topology() call arch_reinit_sched_domains() used to call arch_update_cpu_topology() via arch_init_sched_domains(). This call got lost with e761b7725234276a802322549cee5255305a0930 ("cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2)". So we might end up with outdated and missing cpus in the cpu core maps (architecture used to call arch_reinit_sched_domains if cpu topology changed). This adds a call to arch_update_cpu_topology in partition_sched_domains which gets called whenever scheduling domains get updated. Which is what is supposed to happen when cpu topology changes. Signed-off-by: Heiko Carstens Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index fcfbbd9dbd6..ad7b93be569 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7774,17 +7774,21 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new, struct sched_domain_attr *dattr_new) { int i, j, n; + int new_topology; mutex_lock(&sched_domains_mutex); /* always unregister in case we don't destroy any domains */ unregister_sched_domain_sysctl(); + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + n = doms_new ? ndoms_new : 0; /* Destroy deleted domains */ for (i = 0; i < ndoms_cur; i++) { - for (j = 0; j < n; j++) { + for (j = 0; j < n && !new_topology; j++) { if (cpus_equal(doms_cur[i], doms_new[j]) && dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; @@ -7804,7 +7808,7 @@ match1: /* Build new domains */ for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < ndoms_cur; j++) { + for (j = 0; j < ndoms_cur && !new_topology; j++) { if (cpus_equal(doms_new[i], doms_cur[j]) && dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; -- cgit v1.2.3