diff options
author | Ingo Molnar <mingo@elte.hu> | 2010-02-08 08:55:43 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2010-02-08 08:55:46 +0100 |
commit | 6d3e0907b8b239d16720d144e2675ecf10d3bc3b (patch) | |
tree | e0b0743b5f6f82b057cafc4f3687396a6e01a0b4 /kernel | |
parent | 23577256953c870de9b724c3a2611ce7be6a1e4e (diff) | |
parent | 50200df462023b187d80a99a52f5f2cfe3c86c26 (diff) | |
download | linux-stable-6d3e0907b8b239d16720d144e2675ecf10d3bc3b.tar.gz linux-stable-6d3e0907b8b239d16720d144e2675ecf10d3bc3b.tar.bz2 linux-stable-6d3e0907b8b239d16720d144e2675ecf10d3bc3b.zip |
Merge branch 'sched/urgent' into sched/core
Merge reason: Merge dependent fix, update to latest -rc.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cgroup.c | 8 | ||||
-rw-r--r-- | kernel/cpu.c | 10 | ||||
-rw-r--r-- | kernel/cred.c | 2 | ||||
-rw-r--r-- | kernel/fork.c | 15 | ||||
-rw-r--r-- | kernel/futex.c | 57 | ||||
-rw-r--r-- | kernel/hw_breakpoint.c | 66 | ||||
-rw-r--r-- | kernel/kexec.c | 4 | ||||
-rw-r--r-- | kernel/kfifo.c | 108 | ||||
-rw-r--r-- | kernel/kgdb.c | 9 | ||||
-rw-r--r-- | kernel/kmod.c | 12 | ||||
-rw-r--r-- | kernel/kprobes.c | 2 | ||||
-rw-r--r-- | kernel/lockdep.c | 2 | ||||
-rw-r--r-- | kernel/module.c | 17 | ||||
-rw-r--r-- | kernel/panic.c | 3 | ||||
-rw-r--r-- | kernel/perf_event.c | 14 | ||||
-rw-r--r-- | kernel/printk.c | 1 | ||||
-rw-r--r-- | kernel/sched.c | 44 | ||||
-rw-r--r-- | kernel/sched_fair.c | 2 | ||||
-rw-r--r-- | kernel/signal.c | 3 | ||||
-rw-r--r-- | kernel/smp.c | 2 | ||||
-rw-r--r-- | kernel/softlockup.c | 15 | ||||
-rw-r--r-- | kernel/time/clockevents.c | 3 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 18 | ||||
-rw-r--r-- | kernel/timer.c | 3 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 116 | ||||
-rw-r--r-- | kernel/trace/ftrace.c | 6 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 28 | ||||
-rw-r--r-- | kernel/trace/trace.c | 7 | ||||
-rw-r--r-- | kernel/trace/trace_events_filter.c | 29 | ||||
-rw-r--r-- | kernel/trace/trace_export.c | 7 | ||||
-rw-r--r-- | kernel/trace/trace_kprobe.c | 7 | ||||
-rw-r--r-- | kernel/trace/trace_ksym.c | 140 |
32 files changed, 464 insertions, 296 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 0249f4be9b5c..aa3bee566446 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2468,7 +2468,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, /* make sure l doesn't vanish out from under us */ down_write(&l->mutex); mutex_unlock(&cgrp->pidlist_mutex); - l->use_count++; return l; } } @@ -2937,14 +2936,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, for_each_subsys(root, ss) { struct cgroup_subsys_state *css = ss->create(ss, cgrp); + if (IS_ERR(css)) { err = PTR_ERR(css); goto err_destroy; } init_cgroup_css(css, ss, cgrp); - if (ss->use_id) - if (alloc_css_id(ss, parent, cgrp)) + if (ss->use_id) { + err = alloc_css_id(ss, parent, cgrp); + if (err) goto err_destroy; + } /* At error, ->destroy() callback has to free assigned ID. */ } diff --git a/kernel/cpu.c b/kernel/cpu.c index 1c8ddd6ee940..677f25376a38 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -151,13 +151,13 @@ static inline void check_for_tasks(int cpu) write_lock_irq(&tasklist_lock); for_each_process(p) { - if (task_cpu(p) == cpu && + if (task_cpu(p) == cpu && p->state == TASK_RUNNING && (!cputime_eq(p->utime, cputime_zero) || !cputime_eq(p->stime, cputime_zero))) - printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\ - (state = %ld, flags = %x) \n", - p->comm, task_pid_nr(p), cpu, - p->state, p->flags); + printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d " + "(state = %ld, flags = %x)\n", + p->comm, task_pid_nr(p), cpu, + p->state, p->flags); } write_unlock_irq(&tasklist_lock); } diff --git a/kernel/cred.c b/kernel/cred.c index dd76cfe5f5b0..1ed8ca18790c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -224,7 +224,7 @@ struct cred *cred_alloc_blank(void) #ifdef CONFIG_KEYS new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL); if (!new->tgcred) { - kfree(new); + kmem_cache_free(cred_jar, new); return NULL; } atomic_set(&new->tgcred->usage, 1); diff --git a/kernel/fork.c b/kernel/fork.c index 5b2959b3ffc2..f88bd984df35 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1241,21 +1241,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); - /* - * The task hasn't been attached yet, so its cpus_allowed mask will - * not be changed, nor will its assigned CPU. - * - * The cpus_allowed mask of the parent may have changed after it was - * copied first time - so re-copy it here, then check the child's CPU - * to ensure it is on a valid CPU (and if not, just force it back to - * parent's CPU). This avoids alot of nasty races. - */ - p->cpus_allowed = current->cpus_allowed; - p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed; - if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) || - !cpu_online(task_cpu(p)))) - set_task_cpu(p, smp_processor_id()); - /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; diff --git a/kernel/futex.c b/kernel/futex.c index 8e3c3ffe1b9a..e7a35f1039e7 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -203,8 +203,6 @@ static void drop_futex_key_refs(union futex_key *key) * @uaddr: virtual address of the futex * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED * @key: address where result is stored. - * @rw: mapping needs to be read/write (values: VERIFY_READ, - * VERIFY_WRITE) * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -216,7 +214,7 @@ static void drop_futex_key_refs(union futex_key *key) * lock_page() might sleep, the caller should not hold a spinlock. */ static int -get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -239,7 +237,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) return -EFAULT; key->private.mm = mm; key->private.address = address; @@ -248,7 +246,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) } again: - err = get_user_pages_fast(address, 1, rw == VERIFY_WRITE, &page); + err = get_user_pages_fast(address, 1, 1, &page); if (err < 0) return err; @@ -532,8 +530,25 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); - WARN_ON(pid && pi_state->owner && - pi_state->owner->pid != pid); + + /* + * When pi_state->owner is NULL then the owner died + * and another waiter is on the fly. pi_state->owner + * is fixed up by the task which acquires + * pi_state->rt_mutex. + * + * We do not check for pid == 0 which can happen when + * the owner died and robust_list_exit() cleared the + * TID. + */ + if (pid && pi_state->owner) { + /* + * Bail out if user space manipulated the + * futex value. + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; + } atomic_inc(&pi_state->refcount); *ps = pi_state; @@ -760,6 +775,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) if (!pi_state) return -EINVAL; + /* + * If current does not own the pi_state then the futex is + * inconsistent and user space fiddled with the futex value. + */ + if (pi_state->owner != current) + return -EINVAL; + raw_spin_lock(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); @@ -867,7 +889,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ); + ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -913,10 +935,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, op_ret; retry: - ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out_put_key1; @@ -1175,11 +1197,10 @@ retry: pi_state = NULL; } - ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2, - requeue_pi ? VERIFY_WRITE : VERIFY_READ); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out_put_key1; @@ -1738,7 +1759,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared, */ retry: q->key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ); + ret = get_futex_key(uaddr, fshared, &q->key); if (unlikely(ret != 0)) return ret; @@ -1904,7 +1925,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, q.requeue_pi_key = NULL; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE); + ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) goto out; @@ -1974,7 +1995,7 @@ retry_private: /* Unqueue and drop the lock */ unqueue_me_pi(&q); - goto out; + goto out_put_key; out_unlock_put_key: queue_unlock(&q, hb); @@ -2023,7 +2044,7 @@ retry: if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE); + ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -2215,7 +2236,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, rt_waiter.task = NULL; key2 = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out; diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index dbcbf6a33a08..8a5c7d55ac9f 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -40,6 +40,7 @@ #include <linux/percpu.h> #include <linux/sched.h> #include <linux/init.h> +#include <linux/cpu.h> #include <linux/smp.h> #include <linux/hw_breakpoint.h> @@ -242,38 +243,70 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable) * ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *)) * + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM */ -int reserve_bp_slot(struct perf_event *bp) +static int __reserve_bp_slot(struct perf_event *bp) { struct bp_busy_slots slots = {0}; - int ret = 0; - - mutex_lock(&nr_bp_mutex); fetch_bp_busy_slots(&slots, bp); /* Flexible counters need to keep at least one slot */ - if (slots.pinned + (!!slots.flexible) == HBP_NUM) { - ret = -ENOSPC; - goto end; - } + if (slots.pinned + (!!slots.flexible) == HBP_NUM) + return -ENOSPC; toggle_bp_slot(bp, true); -end: + return 0; +} + +int reserve_bp_slot(struct perf_event *bp) +{ + int ret; + + mutex_lock(&nr_bp_mutex); + + ret = __reserve_bp_slot(bp); + mutex_unlock(&nr_bp_mutex); return ret; } +static void __release_bp_slot(struct perf_event *bp) +{ + toggle_bp_slot(bp, false); +} + void release_bp_slot(struct perf_event *bp) { mutex_lock(&nr_bp_mutex); - toggle_bp_slot(bp, false); + __release_bp_slot(bp); mutex_unlock(&nr_bp_mutex); } +/* + * Allow the kernel debugger to reserve breakpoint slots without + * taking a lock using the dbg_* variant of for the reserve and + * release breakpoint slots. + */ +int dbg_reserve_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + return __reserve_bp_slot(bp); +} + +int dbg_release_bp_slot(struct perf_event *bp) +{ + if (mutex_is_locked(&nr_bp_mutex)) + return -1; + + __release_bp_slot(bp); + + return 0; +} int register_perf_hw_breakpoint(struct perf_event *bp) { @@ -295,6 +328,10 @@ int register_perf_hw_breakpoint(struct perf_event *bp) if (!bp->attr.disabled || !bp->overflow_handler) ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task); + /* if arch_validate_hwbkpt_settings() fails then release bp slot */ + if (ret) + release_bp_slot(bp); + return ret; } @@ -388,7 +425,8 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, if (!cpu_events) return ERR_PTR(-ENOMEM); - for_each_possible_cpu(cpu) { + get_online_cpus(); + for_each_online_cpu(cpu) { pevent = per_cpu_ptr(cpu_events, cpu); bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered); @@ -399,18 +437,20 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, goto fail; } } + put_online_cpus(); return cpu_events; fail: - for_each_possible_cpu(cpu) { + for_each_online_cpu(cpu) { pevent = per_cpu_ptr(cpu_events, cpu); if (IS_ERR(*pevent)) break; unregister_hw_breakpoint(*pevent); } + put_online_cpus(); + free_percpu(cpu_events); - /* return the error if any */ return ERR_PTR(err); } EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint); diff --git a/kernel/kexec.c b/kernel/kexec.c index a9a93d9ee7a7..ef077fb73155 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -32,6 +32,7 @@ #include <linux/console.h> #include <linux/vmalloc.h> #include <linux/swap.h> +#include <linux/kmsg_dump.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -1074,6 +1075,9 @@ void crash_kexec(struct pt_regs *regs) if (mutex_trylock(&kexec_mutex)) { if (kexec_crash_image) { struct pt_regs fixed_regs; + + kmsg_dump(KMSG_DUMP_KEXEC); + crash_setup_regs(&fixed_regs, regs); crash_save_vmcoreinfo(); machine_crash_shutdown(&fixed_regs); diff --git a/kernel/kfifo.c b/kernel/kfifo.c index e92d519f93b1..498cabba225e 100644 --- a/kernel/kfifo.c +++ b/kernel/kfifo.c @@ -28,7 +28,7 @@ #include <linux/log2.h> #include <linux/uaccess.h> -static void _kfifo_init(struct kfifo *fifo, unsigned char *buffer, +static void _kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size) { fifo->buffer = buffer; @@ -41,10 +41,10 @@ static void _kfifo_init(struct kfifo *fifo, unsigned char *buffer, * kfifo_init - initialize a FIFO using a preallocated buffer * @fifo: the fifo to assign the buffer * @buffer: the preallocated buffer to be used. - * @size: the size of the internal buffer, this have to be a power of 2. + * @size: the size of the internal buffer, this has to be a power of 2. * */ -void kfifo_init(struct kfifo *fifo, unsigned char *buffer, unsigned int size) +void kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size) { /* size must be a power of 2 */ BUG_ON(!is_power_of_2(size)); @@ -159,8 +159,9 @@ static inline void __kfifo_out_data(struct kfifo *fifo, memcpy(to + l, fifo->buffer, len - l); } -static inline unsigned int __kfifo_from_user_data(struct kfifo *fifo, - const void __user *from, unsigned int len, unsigned int off) +static inline int __kfifo_from_user_data(struct kfifo *fifo, + const void __user *from, unsigned int len, unsigned int off, + unsigned *lenout) { unsigned int l; int ret; @@ -177,16 +178,20 @@ static inline unsigned int __kfifo_from_user_data(struct kfifo *fifo, /* first put the data starting from fifo->in to buffer end */ l = min(len, fifo->size - off); ret = copy_from_user(fifo->buffer + off, from, l); - - if (unlikely(ret)) - return ret + len - l; + if (unlikely(ret)) { + *lenout = ret; + return -EFAULT; + } + *lenout = l; /* then put the rest (if any) at the beginning of the buffer */ - return copy_from_user(fifo->buffer, from + l, len - l); + ret = copy_from_user(fifo->buffer, from + l, len - l); + *lenout += ret ? ret : len - l; + return ret ? -EFAULT : 0; } -static inline unsigned int __kfifo_to_user_data(struct kfifo *fifo, - void __user *to, unsigned int len, unsigned int off) +static inline int __kfifo_to_user_data(struct kfifo *fifo, + void __user *to, unsigned int len, unsigned int off, unsigned *lenout) { unsigned int l; int ret; @@ -203,12 +208,21 @@ static inline unsigned int __kfifo_to_user_data(struct kfifo *fifo, /* first get the data from fifo->out until the end of the buffer */ l = min(len, fifo->size - off); ret = copy_to_user(to, fifo->buffer + off, l); - - if (unlikely(ret)) - return ret + len - l; + *lenout = l; + if (unlikely(ret)) { + *lenout -= ret; + return -EFAULT; + } /* then get the rest (if any) from the beginning of the buffer */ - return copy_to_user(to + l, fifo->buffer, len - l); + len -= l; + ret = copy_to_user(to + l, fifo->buffer, len); + if (unlikely(ret)) { + *lenout += len - ret; + return -EFAULT; + } + *lenout += len; + return 0; } unsigned int __kfifo_in_n(struct kfifo *fifo, @@ -235,7 +249,7 @@ EXPORT_SYMBOL(__kfifo_in_n); * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these functions. */ -unsigned int kfifo_in(struct kfifo *fifo, const unsigned char *from, +unsigned int kfifo_in(struct kfifo *fifo, const void *from, unsigned int len) { len = min(kfifo_avail(fifo), len); @@ -277,7 +291,7 @@ EXPORT_SYMBOL(__kfifo_out_n); * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these functions. */ -unsigned int kfifo_out(struct kfifo *fifo, unsigned char *to, unsigned int len) +unsigned int kfifo_out(struct kfifo *fifo, void *to, unsigned int len) { len = min(kfifo_len(fifo), len); @@ -288,6 +302,27 @@ unsigned int kfifo_out(struct kfifo *fifo, unsigned char *to, unsigned int len) } EXPORT_SYMBOL(kfifo_out); +/** + * kfifo_out_peek - copy some data from the FIFO, but do not remove it + * @fifo: the fifo to be used. + * @to: where the data must be copied. + * @len: the size of the destination buffer. + * @offset: offset into the fifo + * + * This function copies at most @len bytes at @offset from the FIFO + * into the @to buffer and returns the number of copied bytes. + * The data is not removed from the FIFO. + */ +unsigned int kfifo_out_peek(struct kfifo *fifo, void *to, unsigned int len, + unsigned offset) +{ + len = min(kfifo_len(fifo), len + offset); + + __kfifo_out_data(fifo, to, len, offset); + return len; +} +EXPORT_SYMBOL(kfifo_out_peek); + unsigned int __kfifo_out_generic(struct kfifo *fifo, void *to, unsigned int len, unsigned int recsize, unsigned int *total) @@ -299,10 +334,13 @@ EXPORT_SYMBOL(__kfifo_out_generic); unsigned int __kfifo_from_user_n(struct kfifo *fifo, const void __user *from, unsigned int len, unsigned int recsize) { + unsigned total; + if (kfifo_avail(fifo) < len + recsize) return len + 1; - return __kfifo_from_user_data(fifo, from, len, recsize); + __kfifo_from_user_data(fifo, from, len, recsize, &total); + return total; } EXPORT_SYMBOL(__kfifo_from_user_n); @@ -311,20 +349,24 @@ EXPORT_SYMBOL(__kfifo_from_user_n); * @fifo: the fifo to be used. * @from: pointer to the data to be added. * @len: the length of the data to be added. + * @total: the actual returned data length. * * This function copies at most @len bytes from the @from into the - * FIFO depending and returns the number of copied bytes. + * FIFO depending and returns -EFAULT/0. * * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these functions. */ -unsigned int kfifo_from_user(struct kfifo *fifo, - const void __user *from, unsigned int len) +int kfifo_from_user(struct kfifo *fifo, + const void __user *from, unsigned int len, unsigned *total) { + int ret; len = min(kfifo_avail(fifo), len); - len -= __kfifo_from_user_data(fifo, from, len, 0); + ret = __kfifo_from_user_data(fifo, from, len, 0, total); + if (ret) + return ret; __kfifo_add_in(fifo, len); - return len; + return 0; } EXPORT_SYMBOL(kfifo_from_user); @@ -339,17 +381,17 @@ unsigned int __kfifo_to_user_n(struct kfifo *fifo, void __user *to, unsigned int len, unsigned int reclen, unsigned int recsize) { - unsigned int ret; + unsigned int ret, total; if (kfifo_len(fifo) < reclen + recsize) return len; - ret = __kfifo_to_user_data(fifo, to, reclen, recsize); + ret = __kfifo_to_user_data(fifo, to, reclen, recsize, &total); if (likely(ret == 0)) __kfifo_add_out(fifo, reclen + recsize); - return ret; + return total; } EXPORT_SYMBOL(__kfifo_to_user_n); @@ -358,20 +400,22 @@ EXPORT_SYMBOL(__kfifo_to_user_n); * @fifo: the fifo to be used. * @to: where the data must be copied. * @len: the size of the destination buffer. + * @lenout: pointer to output variable with copied data * * This function copies at most @len bytes from the FIFO into the - * @to buffer and returns the number of copied bytes. + * @to buffer and 0 or -EFAULT. * * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these functions. */ -unsigned int kfifo_to_user(struct kfifo *fifo, - void __user *to, unsigned int len) +int kfifo_to_user(struct kfifo *fifo, + void __user *to, unsigned int len, unsigned *lenout) { + int ret; len = min(kfifo_len(fifo), len); - len -= __kfifo_to_user_data(fifo, to, len, 0); - __kfifo_add_out(fifo, len); - return len; + ret = __kfifo_to_user_data(fifo, to, len, 0, lenout); + __kfifo_add_out(fifo, *lenout); + return ret; } EXPORT_SYMBOL(kfifo_to_user); diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 2eb517e23514..761fdd2b3034 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -583,6 +583,9 @@ static void kgdb_wait(struct pt_regs *regs) smp_wmb(); atomic_set(&cpu_in_kgdb[cpu], 1); + /* Disable any cpu specific hw breakpoints */ + kgdb_disable_hw_debug(regs); + /* Wait till primary CPU is done with debugging */ while (atomic_read(&passive_cpu_wait[cpu])) cpu_relax(); @@ -596,7 +599,7 @@ static void kgdb_wait(struct pt_regs *regs) /* Signal the primary CPU that we are done: */ atomic_set(&cpu_in_kgdb[cpu], 0); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); } @@ -1450,7 +1453,7 @@ acquirelock: (kgdb_info[cpu].task && kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) { atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); @@ -1550,7 +1553,7 @@ kgdb_restore: } /* Free kgdb_active */ atomic_set(&kgdb_active, -1); - touch_softlockup_watchdog(); + touch_softlockup_watchdog_sync(); clocksource_touch_watchdog(); local_irq_restore(flags); diff --git a/kernel/kmod.c b/kernel/kmod.c index 25b103190364..bf0e231d9702 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -520,13 +520,15 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp, return -ENOMEM; ret = call_usermodehelper_stdinpipe(sub_info, filp); - if (ret < 0) - goto out; + if (ret < 0) { + call_usermodehelper_freeinfo(sub_info); + return ret; + } - return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); + ret = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); + if (ret < 0) /* Failed to execute helper, close pipe */ + filp_close(*filp, NULL); - out: - call_usermodehelper_freeinfo(sub_info); return ret; } EXPORT_SYMBOL(call_usermodehelper_pipe); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e5342a344c43..b7df302a0204 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1035,7 +1035,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp) /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPT - rp->maxactive = max(10, 2 * num_possible_cpus()); + rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #else rp->maxactive = num_possible_cpus(); #endif diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 5feaddcdbe49..c62ec14609b9 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2147,7 +2147,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, return ret; return print_irq_inversion_bug(curr, &root, target_entry, - this, 1, irqclass); + this, 0, irqclass); } void print_irqtrace_events(struct task_struct *curr) diff --git a/kernel/module.c b/kernel/module.c index e96b8ed1cb6a..f82386bd9ee9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1010,6 +1010,12 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, * J. Corbet <corbet@lwn.net> */ #if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) + +static inline bool sect_empty(const Elf_Shdr *sect) +{ + return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; +} + struct module_sect_attr { struct module_attribute mattr; @@ -1051,8 +1057,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, /* Count loaded sections and allocate structures */ for (i = 0; i < nsect; i++) - if (sechdrs[i].sh_flags & SHF_ALLOC - && sechdrs[i].sh_size) + if (!sect_empty(&sechdrs[i])) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1070,9 +1075,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, sattr = §_attrs->attrs[0]; gattr = §_attrs->grp.attrs[0]; for (i = 0; i < nsect; i++) { - if (! (sechdrs[i].sh_flags & SHF_ALLOC)) - continue; - if (!sechdrs[i].sh_size) + if (sect_empty(&sechdrs[i])) continue; sattr->address = sechdrs[i].sh_addr; sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, @@ -1156,7 +1159,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, /* Count notes sections and allocate structures. */ notes = 0; for (i = 0; i < nsect; i++) - if ((sechdrs[i].sh_flags & SHF_ALLOC) && + if (!sect_empty(&sechdrs[i]) && (sechdrs[i].sh_type == SHT_NOTE)) ++notes; @@ -1172,7 +1175,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; for (loaded = i = 0; i < nsect; ++i) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + if (sect_empty(&sechdrs[i])) continue; if (sechdrs[i].sh_type == SHT_NOTE) { nattr->attr.name = mod->sect_attrs->attrs[loaded].name; diff --git a/kernel/panic.c b/kernel/panic.c index 5827f7b97254..c787333282b8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -75,7 +75,6 @@ NORET_TYPE void panic(const char * fmt, ...) dump_stack(); #endif - kmsg_dump(KMSG_DUMP_PANIC); /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. @@ -83,6 +82,8 @@ NORET_TYPE void panic(const char * fmt, ...) */ crash_kexec(NULL); + kmsg_dump(KMSG_DUMP_PANIC); + /* * Note smp_send_stop is the usual smp shutdown function, which * unfortunately means it may not be hardened to work in a panic diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 1f38270f08c7..d27746bd3a06 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -3268,6 +3268,9 @@ static void perf_event_task_output(struct perf_event *event, static int perf_event_task_match(struct perf_event *event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + if (event->cpu != -1 && event->cpu != smp_processor_id()) return 0; @@ -3377,6 +3380,9 @@ static void perf_event_comm_output(struct perf_event *event, static int perf_event_comm_match(struct perf_event *event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + if (event->cpu != -1 && event->cpu != smp_processor_id()) return 0; @@ -3494,6 +3500,9 @@ static void perf_event_mmap_output(struct perf_event *event, static int perf_event_mmap_match(struct perf_event *event, struct perf_mmap_event *mmap_event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + if (event->cpu != -1 && event->cpu != smp_processor_id()) return 0; @@ -5148,7 +5157,7 @@ int perf_event_init_task(struct task_struct *child) GFP_KERNEL); if (!child_ctx) { ret = -ENOMEM; - goto exit; + break; } __perf_event_init_context(child_ctx, child); @@ -5164,7 +5173,7 @@ int perf_event_init_task(struct task_struct *child) } } - if (inherited_all) { + if (child_ctx && inherited_all) { /* * Mark the child context as a clone of the parent * context, or of whatever the parent is a clone of. @@ -5184,7 +5193,6 @@ int perf_event_init_task(struct task_struct *child) get_ctx(child_ctx->parent_ctx); } -exit: mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); diff --git a/kernel/printk.c b/kernel/printk.c index 17463ca2e229..1751c456b71f 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1467,6 +1467,7 @@ EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static const char const *kmsg_reasons[] = { [KMSG_DUMP_OOPS] = "oops", [KMSG_DUMP_PANIC] = "panic", + [KMSG_DUMP_KEXEC] = "kexec", }; static const char *kmsg_to_str(enum kmsg_dump_reason reason) diff --git a/kernel/sched.c b/kernel/sched.c index 6cee227b1459..f96be9370b75 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2286,14 +2286,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } /* - * Called from: + * Gets called from 3 sites (exec, fork, wakeup), since it is called without + * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done + * by: * - * - fork, @p is stable because it isn't on the tasklist yet - * - * - exec, @p is unstable, retry loop - * - * - wake-up, we serialize ->cpus_allowed against TASK_WAKING so - * we should be good. + * exec: is unstable, retry loop + * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING */ static inline int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) @@ -2586,9 +2584,6 @@ void sched_fork(struct task_struct *p, int clone_flags) if (p->sched_class->task_fork) p->sched_class->task_fork(p); -#ifdef CONFIG_SMP - cpu = select_task_rq(p, SD_BALANCE_FORK, 0); -#endif set_task_cpu(p, cpu); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) @@ -2618,6 +2613,21 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; + int cpu __maybe_unused = get_cpu(); + +#ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: + * - cpus_allowed can change in the fork path + * - any previously selected cpu might disappear through hotplug + * + * We still have TASK_WAKING but PF_STARTING is gone now, meaning + * ->cpus_allowed is stable, we have preemption disabled, meaning + * cpu_online_mask is stable. + */ + cpu = select_task_rq(p, SD_BALANCE_FORK, 0); + set_task_cpu(p, cpu); +#endif rq = task_rq_lock(p, &flags); BUG_ON(p->state != TASK_WAKING); @@ -2631,6 +2641,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_woken(rq, p); #endif task_rq_unlock(rq, &flags); + put_cpu(); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -3687,8 +3698,11 @@ need_resched_nonpreemptible: post_schedule(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) + if (unlikely(reacquire_kernel_lock(current) < 0)) { + prev = rq->curr; + switch_count = &prev->nivcsw; goto need_resched_nonpreemptible; + } preempt_enable_no_resched(); if (need_resched()) @@ -5293,14 +5307,18 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) * the ->cpus_allowed mask from under waking tasks, which would be * possible when we change rq->lock in ttwu(), so synchronize against * TASK_WAKING to avoid that. + * + * Make an exception for freshly cloned tasks, since cpuset namespaces + * might move the task about, we have to validate the target in + * wake_up_new_task() anyway since the cpu might have gone away. */ again: - while (p->state == TASK_WAKING) + while (p->state == TASK_WAKING && !(p->flags & PF_STARTING)) cpu_relax(); rq = task_rq_lock(p, &flags); - if (p->state == TASK_WAKING) { + if (p->state == TASK_WAKING && !(p->flags & PF_STARTING)) { task_rq_unlock(rq, &flags); goto again; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0e7a7af9cf8b..b45abbe55067 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1509,7 +1509,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag * If there's an idle sibling in this domain, make that * the wake_affine target instead of the current cpu. */ - if (tmp->flags & SD_PREFER_SIBLING) + if (tmp->flags & SD_SHARE_PKG_RESOURCES) target = select_idle_sibling(p, tmp, target); if (target >= 0) { diff --git a/kernel/signal.c b/kernel/signal.c index d09692b40376..934ae5e687b9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -979,7 +979,8 @@ static void print_fatal_signal(struct pt_regs *regs, int signr) for (i = 0; i < 16; i++) { unsigned char insn; - __get_user(insn, (unsigned char *)(regs->ip + i)); + if (get_user(insn, (unsigned char *)(regs->ip + i))) + break; printk("%02x ", insn); } } diff --git a/kernel/smp.c b/kernel/smp.c index de735a6637d0..f10408422444 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -347,7 +347,7 @@ int smp_call_function_any(const struct cpumask *mask, goto call; /* Try for same node. */ - nodemask = cpumask_of_node(cpu); + nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) diff --git a/kernel/softlockup.c b/kernel/softlockup.c index d22579087e27..0d4c7898ab80 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -25,6 +25,7 @@ static DEFINE_SPINLOCK(print_lock); static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */ static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */ static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +static DEFINE_PER_CPU(bool, softlock_touch_sync); static int __read_mostly did_panic; int __read_mostly softlockup_thresh = 60; @@ -79,6 +80,12 @@ void touch_softlockup_watchdog(void) } EXPORT_SYMBOL(touch_softlockup_watchdog); +void touch_softlockup_watchdog_sync(void) +{ + __raw_get_cpu_var(softlock_touch_sync) = true; + __raw_get_cpu_var(softlockup_touch_ts) = 0; +} + void touch_all_softlockup_watchdogs(void) { int cpu; @@ -118,6 +125,14 @@ void softlockup_tick(void) } if (touch_ts == 0) { + if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) { + /* + * If the time stamp was touched atomically + * make sure the scheduler tick is up to date. + */ + per_cpu(softlock_touch_sync, this_cpu) = false; + sched_clock_tick(); + } __touch_softlockup_watchdog(); return; } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 6f740d9f0948..d7395fdfb9f3 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -259,7 +259,8 @@ void clockevents_notify(unsigned long reason, void *arg) cpu = *((int *)arg); list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { if (cpumask_test_cpu(cpu, dev->cpumask) && - cpumask_weight(dev->cpumask) == 1) { + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); list_del(&dev->list); } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e85c23404d34..13700833c181 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -343,7 +343,19 @@ static void clocksource_resume_watchdog(void) { unsigned long flags; - spin_lock_irqsave(&watchdog_lock, flags); + /* + * We use trylock here to avoid a potential dead lock when + * kgdb calls this code after the kernel has been stopped with + * watchdog_lock held. When watchdog_lock is held we just + * return and accept, that the watchdog might trigger and mark + * the monitored clock source (usually TSC) unstable. + * + * This does not affect the other caller clocksource_resume() + * because at this point the kernel is UP, interrupts are + * disabled and nothing can hold watchdog_lock. + */ + if (!spin_trylock_irqsave(&watchdog_lock, flags)) + return; clocksource_reset_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); } @@ -458,8 +470,8 @@ void clocksource_resume(void) * clocksource_touch_watchdog - Update watchdog * * Update the watchdog after exception contexts such as kgdb so as not - * to incorrectly trip the watchdog. - * + * to incorrectly trip the watchdog. This might fail when the kernel + * was stopped in code which holds watchdog_lock. */ void clocksource_touch_watchdog(void) { diff --git a/kernel/timer.c b/kernel/timer.c index 15533b792397..c61a7949387f 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1198,6 +1198,7 @@ void update_process_times(int user_tick) run_local_timers(); rcu_check_callbacks(cpu, user_tick); printk_tick(); + perf_event_do_pending(); scheduler_tick(); run_posix_cpu_timers(p); } @@ -1209,8 +1210,6 @@ static void run_timer_softirq(struct softirq_action *h) { struct tvec_base *base = __get_cpu_var(tvec_bases); - perf_event_do_pending(); - hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d006554888dc..60e2ce0181ee 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -12,39 +12,37 @@ config NOP_TRACER config HAVE_FTRACE_NMI_ENTER bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_FUNCTION_TRACER bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_FUNCTION_GRAPH_TRACER bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_FUNCTION_GRAPH_FP_TEST bool help - An arch may pass in a unique value (frame pointer) to both the - entering and exiting of a function. On exit, the value is compared - and if it does not match, then it will panic the kernel. + See Documentation/trace/ftrace-design.txt config HAVE_FUNCTION_TRACE_MCOUNT_TEST bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_DYNAMIC_FTRACE bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_FTRACE_MCOUNT_RECORD bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config HAVE_HW_BRANCH_TRACER bool @@ -52,7 +50,7 @@ config HAVE_HW_BRANCH_TRACER config HAVE_SYSCALL_TRACEPOINTS bool help - See Documentation/trace/ftrace-implementation.txt + See Documentation/trace/ftrace-design.txt config TRACER_MAX_TRACE bool @@ -83,7 +81,7 @@ config RING_BUFFER_ALLOW_SWAP # This allows those options to appear when no other tracer is selected. But the # options do not appear when something else selects it. We need the two options # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the -# hidding of the automatic options. +# hiding of the automatic options. config TRACING bool @@ -119,7 +117,7 @@ menuconfig FTRACE bool "Tracers" default y if DEBUG_KERNEL help - Enable the kernel tracing infrastructure. + Enable the kernel tracing infrastructure. if FTRACE @@ -133,7 +131,7 @@ config FUNCTION_TRACER help Enable the kernel to trace every kernel function. This is done by using a compiler feature to insert a small, 5-byte No-Operation - instruction to the beginning of every kernel function, which NOP + instruction at the beginning of every kernel function, which NOP sequence is then dynamically patched into a tracer call when tracing is enabled by the administrator. If it's runtime disabled (the bootup default), then the overhead of the instructions is very @@ -150,7 +148,7 @@ config FUNCTION_GRAPH_TRACER and its entry. Its first purpose is to trace the duration of functions and draw a call graph for each thread with some information like - the return value. This is done by setting the current return + the return value. This is done by setting the current return address on the current task structure into a stack of calls. @@ -173,7 +171,7 @@ config IRQSOFF_TRACER echo 0 > /sys/kernel/debug/tracing/tracing_max_latency - (Note that kernel size and overhead increases with this option + (Note that kernel size and overhead increase with this option enabled. This option and the preempt-off timing option can be used together or separately.) @@ -186,7 +184,7 @@ config PREEMPT_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP help - This option measures the time spent in preemption off critical + This option measures the time spent in preemption-off critical sections, with microsecond accuracy. The default measurement method is a maximum search, which is @@ -195,7 +193,7 @@ config PREEMPT_TRACER echo 0 > /sys/kernel/debug/tracing/tracing_max_latency - (Note that kernel size and overhead increases with this option + (Note that kernel size and overhead increase with this option enabled. This option and the irqs-off timing option can be used together or separately.) @@ -222,7 +220,7 @@ config ENABLE_DEFAULT_TRACERS depends on !GENERIC_TRACER select TRACING help - This tracer hooks to various trace points in the kernel + This tracer hooks to various trace points in the kernel, allowing the user to pick and choose which trace point they want to trace. It also includes the sched_switch tracer plugin. @@ -265,19 +263,19 @@ choice The likely/unlikely profiler only looks at the conditions that are annotated with a likely or unlikely macro. - The "all branch" profiler will profile every if statement in the + The "all branch" profiler will profile every if-statement in the kernel. This profiler will also enable the likely/unlikely - profiler as well. + profiler. - Either of the above profilers add a bit of overhead to the system. - If unsure choose "No branch profiling". + Either of the above profilers adds a bit of overhead to the system. + If unsure, choose "No branch profiling". config BRANCH_PROFILE_NONE bool "No branch profiling" help - No branch profiling. Branch profiling adds a bit of overhead. - Only enable it if you want to analyse the branching behavior. - Otherwise keep it disabled. + No branch profiling. Branch profiling adds a bit of overhead. + Only enable it if you want to analyse the branching behavior. + Otherwise keep it disabled. config PROFILE_ANNOTATED_BRANCHES bool "Trace likely/unlikely profiler" @@ -288,7 +286,7 @@ config PROFILE_ANNOTATED_BRANCHES /sys/kernel/debug/tracing/profile_annotated_branch - Note: this will add a significant overhead, only turn this + Note: this will add a significant overhead; only turn this on if you need to profile the system's use of these macros. config PROFILE_ALL_BRANCHES @@ -305,7 +303,7 @@ config PROFILE_ALL_BRANCHES This configuration, when enabled, will impose a great overhead on the system. This should only be enabled when the system - is to be analyzed + is to be analyzed in much detail. endchoice config TRACING_BRANCHES @@ -335,7 +333,7 @@ config POWER_TRACER depends on X86 select GENERIC_TRACER help - This tracer helps developers to analyze and optimize the kernels + This tracer helps developers to analyze and optimize the kernel's power management decisions, specifically the C-state and P-state behavior. @@ -391,14 +389,14 @@ config HW_BRANCH_TRACER select GENERIC_TRACER help This tracer records all branches on the system in a circular - buffer giving access to the last N branches for each cpu. + buffer, giving access to the last N branches for each cpu. config KMEMTRACE bool "Trace SLAB allocations" select GENERIC_TRACER help kmemtrace provides tracing for slab allocator functions, such as - kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected + kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected data is then fed to the userspace application in order to analyse allocation hotspots, internal fragmentation and so on, making it possible to see how well an allocator performs, as well as debug @@ -417,15 +415,15 @@ config WORKQUEUE_TRACER bool "Trace workqueues" select GENERIC_TRACER help - The workqueue tracer provides some statistical informations + The workqueue tracer provides some statistical information about each cpu workqueue thread such as the number of the works inserted and executed since their creation. It can help - to evaluate the amount of work each of them have to perform. + to evaluate the amount of work each of them has to perform. For example it can help a developer to decide whether he should - choose a per cpu workqueue instead of a singlethreaded one. + choose a per-cpu workqueue instead of a singlethreaded one. config BLK_DEV_IO_TRACE - bool "Support for tracing block io actions" + bool "Support for tracing block IO actions" depends on SYSFS depends on BLOCK select RELAY @@ -456,15 +454,15 @@ config KPROBE_EVENT select TRACING default y help - This allows the user to add tracing events (similar to tracepoints) on the fly - via the ftrace interface. See Documentation/trace/kprobetrace.txt - for more details. + This allows the user to add tracing events (similar to tracepoints) + on the fly via the ftrace interface. See + Documentation/trace/kprobetrace.txt for more details. Those events can be inserted wherever kprobes can probe, and record various register and memory values. - This option is also required by perf-probe subcommand of perf tools. If - you want to use perf tools, this option is strongly recommended. + This option is also required by perf-probe subcommand of perf tools. + If you want to use perf tools, this option is strongly recommended. config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" @@ -472,32 +470,32 @@ config DYNAMIC_FTRACE depends on HAVE_DYNAMIC_FTRACE default y help - This option will modify all the calls to ftrace dynamically - (will patch them out of the binary image and replaces them - with a No-Op instruction) as they are called. A table is - created to dynamically enable them again. + This option will modify all the calls to ftrace dynamically + (will patch them out of the binary image and replace them + with a No-Op instruction) as they are called. A table is + created to dynamically enable them again. - This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise - has native performance as long as no tracing is active. + This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but + otherwise has native performance as long as no tracing is active. - The changes to the code are done by a kernel thread that - wakes up once a second and checks to see if any ftrace calls - were made. If so, it runs stop_machine (stops all CPUS) - and modifies the code to jump over the call to ftrace. + The changes to the code are done by a kernel thread that + wakes up once a second and checks to see if any ftrace calls + were made. If so, it runs stop_machine (stops all CPUS) + and modifies the code to jump over the call to ftrace. config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER default n help - This option enables the kernel function profiler. A file is created - in debugfs called function_profile_enabled which defaults to zero. - When a 1 is echoed into this file profiling begins, and when a - zero is entered, profiling stops. A file in the trace_stats - directory called functions, that show the list of functions that - have been hit and their counters. + This option enables the kernel function profiler. A file is created + in debugfs called function_profile_enabled which defaults to zero. + When a 1 is echoed into this file profiling begins, and when a + zero is entered, profiling stops. A "functions" file is created in + the trace_stats directory; this file shows the list of functions that + have been hit and their counters. - If in doubt, say N + If in doubt, say N. config FTRACE_MCOUNT_RECORD def_bool y @@ -556,8 +554,8 @@ config RING_BUFFER_BENCHMARK tristate "Ring buffer benchmark stress tester" depends on RING_BUFFER help - This option creates a test to stress the ring buffer and bench mark it. - It creates its own ring buffer such that it will not interfer with + This option creates a test to stress the ring buffer and benchmark it. + It creates its own ring buffer such that it will not interfere with any other users of the ring buffer (such as ftrace). It then creates a producer and consumer that will run for 10 seconds and sleep for 10 seconds. Each interval it will print out the number of events @@ -566,7 +564,7 @@ config RING_BUFFER_BENCHMARK It does not disable interrupts or raise its priority, so it may be affected by processes that are running. - If unsure, say N + If unsure, say N. endif # FTRACE diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7968762c8167..1e6640f80454 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1690,7 +1690,7 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin) static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; - char *ptr; + int slen; switch (type) { case MATCH_FULL: @@ -1706,8 +1706,8 @@ static int ftrace_match(char *str, char *regex, int len, int type) matched = 1; break; case MATCH_END_ONLY: - ptr = strstr(str, regex); - if (ptr && (ptr[len] == 0)) + slen = strlen(str); + if (slen >= len && memcmp(str + slen - len, regex, len) == 0) matched = 1; break; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2326b04c95c4..8c1b2d290718 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -464,6 +464,8 @@ struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; struct buffer_page *head_page; + struct buffer_page *cache_reader_page; + unsigned long cache_read; u64 read_stamp; }; @@ -2716,6 +2718,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->read_stamp = cpu_buffer->read_stamp; else iter->read_stamp = iter->head_page->page->time_stamp; + iter->cache_reader_page = cpu_buffer->reader_page; + iter->cache_read = cpu_buffer->read; } /** @@ -2869,7 +2873,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) * Splice the empty reader page into the list around the head. */ reader = rb_set_head_page(cpu_buffer); - cpu_buffer->reader_page->list.next = reader->list.next; + cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next); cpu_buffer->reader_page->list.prev = reader->list.prev; /* @@ -2906,7 +2910,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) * * Now make the new head point back to the reader page. */ - reader->list.next->prev = &cpu_buffer->reader_page->list; + rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; rb_inc_page(cpu_buffer, &cpu_buffer->head_page); /* Finally update the reader page to the new head */ @@ -3060,13 +3064,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event *event; int nr_loops = 0; - if (ring_buffer_iter_empty(iter)) - return NULL; - cpu_buffer = iter->cpu_buffer; buffer = cpu_buffer->buffer; + /* + * Check if someone performed a consuming read to + * the buffer. A consuming read invalidates the iterator + * and we need to reset the iterator in this case. + */ + if (unlikely(iter->cache_read != cpu_buffer->read || + iter->cache_reader_page != cpu_buffer->reader_page)) + rb_iter_reset(iter); + again: + if (ring_buffer_iter_empty(iter)) + return NULL; + /* * We repeat when a timestamp is encountered. * We can get multiple timestamps by nested interrupts or also @@ -3081,6 +3094,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) if (rb_per_cpu_empty(cpu_buffer)) return NULL; + if (iter->head >= local_read(&iter->head_page->page->commit)) { + rb_inc_iter(iter); + goto again; + } + event = rb_iter_head_event(iter); switch (event->type_len) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8b9f20ab8eed..eac6875cb990 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -951,6 +951,11 @@ void trace_find_cmdline(int pid, char comm[]) return; } + if (WARN_ON_ONCE(pid < 0)) { + strcpy(comm, "<XXX>"); + return; + } + if (pid > PID_MAX_DEFAULT) { strcpy(comm, "<...>"); return; @@ -3949,7 +3954,7 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, if (!!(topt->flags->val & topt->opt->bit) != val) { mutex_lock(&trace_types_lock); ret = __set_tracer_option(current_trace, topt->flags, - topt->opt, val); + topt->opt, !val); mutex_unlock(&trace_types_lock); if (ret) return ret; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 50504cb228de..e42af9aad69f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -211,8 +211,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event, { char **addr = (char **)(event + pred->offset); int cmp, match; + int len = strlen(*addr) + 1; /* including tailing '\0' */ - cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len); + cmp = pred->regex.match(*addr, &pred->regex, len); match = cmp ^ pred->not; @@ -251,7 +252,18 @@ static int filter_pred_none(struct filter_pred *pred, void *event, return 0; } -/* Basic regex callbacks */ +/* + * regex_match_foo - Basic regex callbacks + * + * @str: the string to be searched + * @r: the regex structure containing the pattern string + * @len: the length of the string to be searched (including '\0') + * + * Note: + * - @str might not be NULL-terminated if it's of type DYN_STRING + * or STATIC_STRING + */ + static int regex_match_full(char *str, struct regex *r, int len) { if (strncmp(str, r->pattern, len) == 0) @@ -261,23 +273,24 @@ static int regex_match_full(char *str, struct regex *r, int len) static int regex_match_front(char *str, struct regex *r, int len) { - if (strncmp(str, r->pattern, len) == 0) + if (strncmp(str, r->pattern, r->len) == 0) return 1; return 0; } static int regex_match_middle(char *str, struct regex *r, int len) { - if (strstr(str, r->pattern)) + if (strnstr(str, r->pattern, len)) return 1; return 0; } static int regex_match_end(char *str, struct regex *r, int len) { - char *ptr = strstr(str, r->pattern); + int strlen = len - 1; - if (ptr && (ptr[r->len] == 0)) + if (strlen >= r->len && + memcmp(str + strlen - r->len, r->pattern, r->len) == 0) return 1; return 0; } @@ -781,10 +794,8 @@ static int filter_add_pred(struct filter_parse_state *ps, pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) fn = filter_pred_strloc; - else { + else fn = filter_pred_pchar; - pred->regex.field_len = strlen(pred->regex.pattern); - } } else { if (field->is_signed) ret = strict_strtoll(pred->regex.pattern, 0, &val); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 458e5bfe26d0..d4fa5dc1ee4e 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -158,7 +158,8 @@ ftrace_format_##name(struct ftrace_event_call *unused, \ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ ret = trace_define_field(event_call, #type "[" #len "]", #item, \ offsetof(typeof(field), item), \ - sizeof(field.item), 0, FILTER_OTHER); \ + sizeof(field.item), \ + is_signed_type(type), FILTER_OTHER); \ if (ret) \ return ret; @@ -168,8 +169,8 @@ ftrace_format_##name(struct ftrace_event_call *unused, \ ret = trace_define_field(event_call, #type "[" #len "]", #item, \ offsetof(typeof(field), \ container.item), \ - sizeof(field.container.item), 0, \ - FILTER_OTHER); \ + sizeof(field.container.item), \ + is_signed_type(type), FILTER_OTHER); \ if (ret) \ return ret; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 375f81a568dc..6ea90c0e2c96 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1201,10 +1201,11 @@ static int __probe_event_show_format(struct trace_seq *s, #undef SHOW_FIELD #define SHOW_FIELD(type, item, name) \ do { \ - ret = trace_seq_printf(s, "\tfield: " #type " %s;\t" \ - "offset:%u;\tsize:%u;\n", name, \ + ret = trace_seq_printf(s, "\tfield:" #type " %s;\t" \ + "offset:%u;\tsize:%u;\tsigned:%d;\n", name,\ (unsigned int)offsetof(typeof(field), item),\ - (unsigned int)sizeof(type)); \ + (unsigned int)sizeof(type), \ + is_signed_type(type)); \ if (!ret) \ return 0; \ } while (0) diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c index faf37fa4408c..94103cdcf9d8 100644 --- a/kernel/trace/trace_ksym.c +++ b/kernel/trace/trace_ksym.c @@ -26,12 +26,13 @@ #include <linux/fs.h> #include "trace_output.h" -#include "trace_stat.h" #include "trace.h" #include <linux/hw_breakpoint.h> #include <asm/hw_breakpoint.h> +#include <asm/atomic.h> + /* * For now, let us restrict the no. of symbols traced simultaneously to number * of available hardware breakpoint registers. @@ -44,7 +45,7 @@ struct trace_ksym { struct perf_event **ksym_hbp; struct perf_event_attr attr; #ifdef CONFIG_PROFILE_KSYM_TRACER - unsigned long counter; + atomic64_t counter; #endif struct hlist_node ksym_hlist; }; @@ -69,9 +70,8 @@ void ksym_collect_stats(unsigned long hbp_hit_addr) rcu_read_lock(); hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) { - if ((entry->attr.bp_addr == hbp_hit_addr) && - (entry->counter <= MAX_UL_INT)) { - entry->counter++; + if (entry->attr.bp_addr == hbp_hit_addr) { + atomic64_inc(&entry->counter); break; } } @@ -197,7 +197,6 @@ int process_new_ksym_entry(char *ksymname, int op, unsigned long addr) entry->attr.bp_addr = addr; entry->attr.bp_len = HW_BREAKPOINT_LEN_4; - ret = -EAGAIN; entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr, ksym_hbp_handler); @@ -300,8 +299,8 @@ static ssize_t ksym_trace_filter_write(struct file *file, * 2: echo 0 > ksym_trace_filter * 3: echo "*:---" > ksym_trace_filter */ - if (!buf[0] || !strcmp(buf, "0") || - !strcmp(buf, "*:---")) { + if (!input_string[0] || !strcmp(input_string, "0") || + !strcmp(input_string, "*:---")) { __ksym_trace_reset(); ret = 0; goto out; @@ -444,102 +443,77 @@ struct tracer ksym_tracer __read_mostly = .print_line = ksym_trace_output }; -__init static int init_ksym_trace(void) -{ - struct dentry *d_tracer; - struct dentry *entry; - - d_tracer = tracing_init_dentry(); - ksym_filter_entry_count = 0; - - entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer, - NULL, &ksym_tracing_fops); - if (!entry) - pr_warning("Could not create debugfs " - "'ksym_trace_filter' file\n"); - - return register_tracer(&ksym_tracer); -} -device_initcall(init_ksym_trace); - - #ifdef CONFIG_PROFILE_KSYM_TRACER -static int ksym_tracer_stat_headers(struct seq_file *m) +static int ksym_profile_show(struct seq_file *m, void *v) { + struct hlist_node *node; + struct trace_ksym *entry; + int access_type = 0; + char fn_name[KSYM_NAME_LEN]; + seq_puts(m, " Access Type "); seq_puts(m, " Symbol Counter\n"); seq_puts(m, " ----------- "); seq_puts(m, " ------ -------\n"); - return 0; -} -static int ksym_tracer_stat_show(struct seq_file *m, void *v) -{ - struct hlist_node *stat = v; - struct trace_ksym *entry; - int access_type = 0; - char fn_name[KSYM_NAME_LEN]; + rcu_read_lock(); + hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) { - entry = hlist_entry(stat, struct trace_ksym, ksym_hlist); + access_type = entry->attr.bp_type; - access_type = entry->attr.bp_type; + switch (access_type) { + case HW_BREAKPOINT_R: + seq_puts(m, " R "); + break; + case HW_BREAKPOINT_W: + seq_puts(m, " W "); + break; + case HW_BREAKPOINT_R | HW_BREAKPOINT_W: + seq_puts(m, " RW "); + break; + default: + seq_puts(m, " NA "); + } - switch (access_type) { - case HW_BREAKPOINT_R: - seq_puts(m, " R "); - break; - case HW_BREAKPOINT_W: - seq_puts(m, " W "); - break; - case HW_BREAKPOINT_R | HW_BREAKPOINT_W: - seq_puts(m, " RW "); - break; - default: - seq_puts(m, " NA "); + if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0) + seq_printf(m, " %-36s", fn_name); + else + seq_printf(m, " %-36s", "<NA>"); + seq_printf(m, " %15llu\n", + (unsigned long long)atomic64_read(&entry->counter)); } - - if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0) - seq_printf(m, " %-36s", fn_name); - else - seq_printf(m, " %-36s", "<NA>"); - seq_printf(m, " %15lu\n", entry->counter); + rcu_read_unlock(); return 0; } -static void *ksym_tracer_stat_start(struct tracer_stat *trace) +static int ksym_profile_open(struct inode *node, struct file *file) { - return ksym_filter_head.first; -} - -static void * -ksym_tracer_stat_next(void *v, int idx) -{ - struct hlist_node *stat = v; - - return stat->next; + return single_open(file, ksym_profile_show, NULL); } -static struct tracer_stat ksym_tracer_stats = { - .name = "ksym_tracer", - .stat_start = ksym_tracer_stat_start, - .stat_next = ksym_tracer_stat_next, - .stat_headers = ksym_tracer_stat_headers, - .stat_show = ksym_tracer_stat_show +static const struct file_operations ksym_profile_fops = { + .open = ksym_profile_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, }; +#endif /* CONFIG_PROFILE_KSYM_TRACER */ -__init static int ksym_tracer_stat_init(void) +__init static int init_ksym_trace(void) { - int ret; + struct dentry *d_tracer; - ret = register_stat_tracer(&ksym_tracer_stats); - if (ret) { - printk(KERN_WARNING "Warning: could not register " - "ksym tracer stats\n"); - return 1; - } + d_tracer = tracing_init_dentry(); - return 0; + trace_create_file("ksym_trace_filter", 0644, d_tracer, + NULL, &ksym_tracing_fops); + +#ifdef CONFIG_PROFILE_KSYM_TRACER + trace_create_file("ksym_profile", 0444, d_tracer, + NULL, &ksym_profile_fops); +#endif + + return register_tracer(&ksym_tracer); } -fs_initcall(ksym_tracer_stat_init); -#endif /* CONFIG_PROFILE_KSYM_TRACER */ +device_initcall(init_ksym_trace); |