From 26cb63ad11e04047a64309362674bcbbd6a6f246 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 28 May 2013 10:55:48 +0200 Subject: perf: Fix perf mmap bugs Vince reported a problem found by his perf specific trinity fuzzer. Al noticed 2 problems with perf's mmap(): - it has issues against fork() since we use vma->vm_mm for accounting. - it has an rb refcount leak on double mmap(). We fix the issues against fork() by using VM_DONTCOPY; I don't think there's code out there that uses this; we didn't hear about weird accounting problems/crashes. If we do need this to work, the previously proposed VM_PINNED could make this work. Aside from the rb reference leak spotted by Al, Vince's example prog was indeed doing a double mmap() through the use of perf_event_set_output(). This exposes another problem, since we now have 2 events with one buffer, the accounting gets screwy because we account per event. Fix this by making the buffer responsible for its own accounting. Reported-by: Vince Weaver Signed-off-by: Peter Zijlstra Cc: Al Viro Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20130528085548.GA12193@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f463a46424e2..c5b6dbf9c2fc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -389,8 +389,7 @@ struct perf_event { /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; - int mmap_locked; - struct user_struct *mmap_user; + struct ring_buffer *rb; struct list_head rb_entry; -- cgit v1.2.3 From 45eacc692771bd2b1ea3d384e6345cab3da10861 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 15 May 2013 22:16:32 +0200 Subject: vtime: Use consistent clocks among nohz accounting While computing the cputime delta of dynticks CPUs, we are mixing up clocks of differents natures: * local_clock() which takes care of unstable clock sources and fix these if needed. * sched_clock() which is the weaker version of local_clock(). It doesn't compute any fixup in case of unstable source. If the clock source is stable, those two clocks are the same and we can safely compute the difference against two random points. Otherwise it results in random deltas as sched_clock() can randomly drift away, back or forward, from local_clock(). As a consequence, some strange behaviour with unstable tsc has been observed such as non progressing constant zero cputime. (The 'top' command showing no load). Fix this by only using local_clock(), or its irq safe/remote equivalent, in vtime code. Reported-by: Mike Galbraith Suggested-by: Mike Galbraith Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 4 ++-- kernel/sched/core.c | 2 +- kernel/sched/cputime.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 71a5782d8c59..b1dd2db80076 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk) } extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); -extern void vtime_init_idle(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else static inline void vtime_account_irq_exit(struct task_struct *tsk) { @@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } -static inline void vtime_init_idle(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..e1a27f918723 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4745,7 +4745,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); - vtime_init_idle(idle); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cc2dc3eea8a3..b5ccba22603b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqlock(¤t->vtime_seqlock); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock(); + current->vtime_snap = sched_clock_cpu(smp_processor_id()); write_sequnlock(¤t->vtime_seqlock); } -void vtime_init_idle(struct task_struct *t) +void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; write_seqlock_irqsave(&t->vtime_seqlock, flags); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock(); + t->vtime_snap = sched_clock_cpu(cpu); write_sequnlock_irqrestore(&t->vtime_seqlock, flags); } -- cgit v1.2.3 From 521921bad1192fb1b8f9b6a5aa673635848b8b5f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 16 May 2013 01:21:38 +0200 Subject: kvm: Move guest entry/exit APIs to context_tracking The kvm_host.h header file doesn't handle well inclusion when archs don't support KVM. This results in build crashes for such archs when they want to implement context tracking because this subsystem includes kvm_host.h in order to implement the guest_enter/exit APIs but it doesn't handle KVM off case. To fix this, move the guest_enter()/guest_exit() declarations and generic implementation to the context tracking headers. These generic APIs actually belong to this subsystem, besides other domains boundary tracking like user_enter() et al. KVM now properly becomes a user of this library, not the other buggy way around. Reported-by: Kevin Hilman Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Kevin Hilman Cc: Marcelo Tosatti Cc: Gleb Natapov Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 37 +------------------------------------ kernel/context_tracking.c | 1 - 3 files changed, 36 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 365f4a61bf04..fc09d7b0dacf 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -3,6 +3,7 @@ #include #include +#include #include struct context_tracking { @@ -19,6 +20,26 @@ struct context_tracking { } state; }; +static inline void __guest_enter(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags |= PF_VCPU; +} + +static inline void __guest_exit(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; +} + #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); @@ -35,6 +56,9 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); +extern void guest_enter(void); +extern void guest_exit(void); + static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -57,6 +81,17 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } + +static inline void guest_enter(void) +{ + __guest_enter(); +} + +static inline void guest_exit(void) +{ + __guest_exit(); +} + static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline void context_tracking_task_switch(struct task_struct *prev, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f0eea07d2c2b..8db53cfaccdb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -760,42 +761,6 @@ static inline int kvm_iommu_unmap_guest(struct kvm *kvm) } #endif -static inline void __guest_enter(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags |= PF_VCPU; -} - -static inline void __guest_exit(void) -{ - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system(current); - current->flags &= ~PF_VCPU; -} - -#ifdef CONFIG_CONTEXT_TRACKING -extern void guest_enter(void); -extern void guest_exit(void); - -#else /* !CONFIG_CONTEXT_TRACKING */ -static inline void guest_enter(void) -{ - __guest_enter(); -} - -static inline void guest_exit(void) -{ - __guest_exit(); -} -#endif /* !CONFIG_CONTEXT_TRACKING */ - static inline void kvm_guest_enter(void) { unsigned long flags; diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..85bdde1137eb 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -15,7 +15,6 @@ */ #include -#include #include #include #include -- cgit v1.2.3 From 29bb9e5a75684106a37593ad75ec75ff8312731b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 May 2013 15:23:40 -0400 Subject: tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [] dump_stack+0x19/0x1b [] lockdep_rcu_suspicious+0xfd/0x130 [] cpuacct_charge+0x185/0x1f0 [] ? cpuacct_charge+0x5/0x1f0 [] update_curr+0xec/0x240 [] put_prev_task_fair+0x228/0x480 [] __schedule+0x161/0x9b0 [] preempt_schedule+0x51/0x80 [] ? __cond_resched_softirq+0x60/0x60 [] ? retint_careful+0x12/0x2e [] ftrace_ops_control_func+0x1dc/0x210 [] ftrace_call+0x5/0x2f [] ? retint_careful+0xb/0x2e [] ? schedule_user+0x5/0x70 [] ? schedule_user+0x5/0x70 [] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar --- include/linux/preempt.h | 18 +++++++++++++++++- kernel/context_tracking.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 87a03c746f17..f5d4723cdb3d 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -33,9 +33,25 @@ do { \ preempt_schedule(); \ } while (0) +#ifdef CONFIG_CONTEXT_TRACKING + +void preempt_schedule_context(void); + +#define preempt_check_resched_context() \ +do { \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + preempt_schedule_context(); \ +} while (0) +#else + +#define preempt_check_resched_context() preempt_check_resched() + +#endif /* CONFIG_CONTEXT_TRACKING */ + #else /* !CONFIG_PREEMPT */ #define preempt_check_resched() do { } while (0) +#define preempt_check_resched_context() do { } while (0) #endif /* CONFIG_PREEMPT */ @@ -88,7 +104,7 @@ do { \ do { \ preempt_enable_no_resched_notrace(); \ barrier(); \ - preempt_check_resched(); \ + preempt_check_resched_context(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..66677003e223 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -71,6 +71,46 @@ void user_enter(void) local_irq_restore(flags); } +#ifdef CONFIG_PREEMPT +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +void __sched notrace preempt_schedule_context(void) +{ + struct thread_info *ti = current_thread_info(); + enum ctx_state prev_ctx; + + if (likely(ti->preempt_count || irqs_disabled())) + return; + + /* + * Need to disable preemption in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + preempt_disable_notrace(); + prev_ctx = exception_enter(); + preempt_enable_no_resched_notrace(); + + preempt_schedule(); + + preempt_disable_notrace(); + exception_exit(prev_ctx); + preempt_enable_notrace(); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_PREEMPT */ /** * user_exit - Inform the context tracking that the CPU is -- cgit v1.2.3 From 7995bd287134f6c8f80d94bebe7396f05a9bc42b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 20 Jun 2013 18:58:36 +0400 Subject: splice: don't pass the address of ->f_pos to methods Signed-off-by: Al Viro --- fs/internal.h | 6 ++++++ fs/read_write.c | 24 ++++++++++++++++-------- fs/splice.c | 31 ++++++++++++++++++------------- include/linux/fs.h | 2 -- include/linux/splice.h | 1 + 5 files changed, 41 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/internal.h b/fs/internal.h index eaa75f75b625..68121584ae37 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -131,6 +131,12 @@ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *); */ extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); +/* + * splice.c + */ +extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + loff_t *opos, size_t len, unsigned int flags); + /* * pipe.c */ diff --git a/fs/read_write.c b/fs/read_write.c index 03430008704e..2cefa417be34 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1064,6 +1064,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, struct fd in, out; struct inode *in_inode, *out_inode; loff_t pos; + loff_t out_pos; ssize_t retval; int fl; @@ -1077,12 +1078,14 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; - if (!ppos) - ppos = &in.file->f_pos; - else + if (!ppos) { + pos = in.file->f_pos; + } else { + pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; - retval = rw_verify_area(READ, in.file, ppos, count); + } + retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; count = retval; @@ -1099,7 +1102,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = -EINVAL; in_inode = file_inode(in.file); out_inode = file_inode(out.file); - retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count); + out_pos = out.file->f_pos; + retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; count = retval; @@ -1107,7 +1111,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); - pos = *ppos; if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) @@ -1126,18 +1129,23 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - retval = do_splice_direct(in.file, ppos, out.file, count, fl); + retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); + out.file->f_pos = out_pos; + if (ppos) + *ppos = pos; + else + in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); - if (*ppos > max) + if (pos > max) retval = -EOVERFLOW; fput_out: diff --git a/fs/splice.c b/fs/splice.c index e6b25598c8c4..9eca476227d5 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1274,7 +1274,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, { struct file *file = sd->u.file; - return do_splice_from(pipe, file, &file->f_pos, sd->total_len, + return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } @@ -1294,7 +1294,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, * */ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - size_t len, unsigned int flags) + loff_t *opos, size_t len, unsigned int flags) { struct splice_desc sd = { .len = len, @@ -1302,6 +1302,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .flags = flags, .pos = *ppos, .u.file = out, + .opos = opos, }; long ret; @@ -1325,7 +1326,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; - loff_t offset, *off; + loff_t offset; long ret; ipipe = get_pipe_info(in); @@ -1356,13 +1357,15 @@ static long do_splice(struct file *in, loff_t __user *off_in, return -EINVAL; if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; - off = &offset; - } else - off = &out->f_pos; + } else { + offset = out->f_pos; + } - ret = do_splice_from(ipipe, out, off, len, flags); + ret = do_splice_from(ipipe, out, &offset, len, flags); - if (off_out && copy_to_user(off_out, off, sizeof(loff_t))) + if (!off_out) + out->f_pos = offset; + else if (copy_to_user(off_out, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; @@ -1376,13 +1379,15 @@ static long do_splice(struct file *in, loff_t __user *off_in, return -EINVAL; if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; - off = &offset; - } else - off = &in->f_pos; + } else { + offset = in->f_pos; + } - ret = do_splice_to(in, off, opipe, len, flags); + ret = do_splice_to(in, &offset, opipe, len, flags); - if (off_in && copy_to_user(off_in, off, sizeof(loff_t))) + if (!off_in) + in->f_pos = offset; + else if (copy_to_user(off_in, &offset, sizeof(loff_t))) ret = -EFAULT; return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index 43db02e9c9fa..65c2be22b601 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2414,8 +2414,6 @@ extern ssize_t generic_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); -extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - size_t len, unsigned int flags); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); diff --git a/include/linux/splice.h b/include/linux/splice.h index 09a545a7dfa3..74575cbf2d6f 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -35,6 +35,7 @@ struct splice_desc { void *data; /* cookie */ } u; loff_t pos; /* file position */ + loff_t *opos; /* sendfile: output position */ size_t num_spliced; /* number of bytes already spliced */ bool need_wakeup; /* need to wake up writer */ }; -- cgit v1.2.3