summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.hz2
-rw-r--r--kernel/capability.c21
-rw-r--r--kernel/cpu.c7
-rw-r--r--kernel/dma-coherent.c10
-rw-r--r--kernel/irq/proc.c96
-rw-r--r--kernel/kexec.c66
-rw-r--r--kernel/lockdep.c303
-rw-r--r--kernel/lockdep_internals.h19
-rw-r--r--kernel/lockdep_proc.c45
-rw-r--r--kernel/module.c2
-rw-r--r--kernel/posix-timers.c19
-rw-r--r--kernel/ptrace.c5
-rw-r--r--kernel/sched.c77
-rw-r--r--kernel/sched_clock.c178
-rw-r--r--kernel/sched_fair.c21
-rw-r--r--kernel/sched_rt.c10
-rw-r--r--kernel/signal.c1
-rw-r--r--kernel/smp.c58
-rw-r--r--kernel/spinlock.c12
-rw-r--r--kernel/stop_machine.c1
-rw-r--r--kernel/sys.c2
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/workqueue.c24
23 files changed, 596 insertions, 385 deletions
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
index 382dd5a8b2d7..94fabd534b03 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
default 1000 if HZ_1000
config SCHED_HRTICK
- def_bool HIGH_RES_TIMERS && USE_GENERIC_SMP_HELPERS
+ def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
diff --git a/kernel/capability.c b/kernel/capability.c
index 0101e847603e..33e51e78c2d8 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -486,17 +486,22 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
return ret;
}
-int __capable(struct task_struct *t, int cap)
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+int capable(int cap)
{
- if (security_capable(t, cap) == 0) {
- t->flags |= PF_SUPERPRIV;
+ if (has_capability(current, cap)) {
+ current->flags |= PF_SUPERPRIV;
return 1;
}
return 0;
}
-
-int capable(int cap)
-{
- return __capable(current, cap);
-}
EXPORT_SYMBOL(capable);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e202a68d1cc1..f17e9854c246 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -349,6 +349,8 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
goto out_notify;
BUG_ON(!cpu_online(cpu));
+ cpu_set(cpu, cpu_active_map);
+
/* Now call notifier in preparation. */
raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
@@ -367,7 +369,7 @@ int __cpuinit cpu_up(unsigned int cpu)
if (!cpu_isset(cpu, cpu_possible_map)) {
printk(KERN_ERR "can't online cpu %d because it is not "
"configured as may-hotadd at boot time\n", cpu);
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) || defined(CONFIG_S390)
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
printk(KERN_ERR "please check additional_cpus= boot "
"parameter\n");
#endif
@@ -383,9 +385,6 @@ int __cpuinit cpu_up(unsigned int cpu)
err = _cpu_up(cpu, 0);
- if (cpu_online(cpu))
- cpu_set(cpu, cpu_active_map);
-
out:
cpu_maps_update_done();
return err;
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index 91e96950cd52..c1d4d5b4c61c 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -92,7 +92,7 @@ void *dma_mark_declared_memory_occupied(struct device *dev,
EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
/**
- * Try to allocate memory from the per-device coherent area.
+ * dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
*
* @dev: device from which we allocate memory
* @size: size of requested memory area
@@ -100,11 +100,11 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
* @ret: This pointer will be filled with the virtual address
* to allocated area.
*
- * This function should be only called from per-arch %dma_alloc_coherent()
+ * This function should be only called from per-arch dma_alloc_coherent()
* to support allocation from per-device coherent memory pools.
*
* Returns 0 if dma_alloc_coherent should continue with allocating from
- * generic memory areas, or !0 if dma_alloc_coherent should return %ret.
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
*/
int dma_alloc_from_coherent(struct device *dev, ssize_t size,
dma_addr_t *dma_handle, void **ret)
@@ -126,7 +126,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
}
/**
- * Try to free the memory allocated from per-device coherent memory pool.
+ * dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
* @dev: device from which the memory was allocated
* @order: the order of pages allocated
* @vaddr: virtual address of allocated pages
@@ -135,7 +135,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
* coherent memory pool and if so, releases that memory.
*
* Returns 1 if we correctly released the memory, or 0 if
- * %dma_release_coherent() should proceed with releasing memory from
+ * dma_release_coherent() should proceed with releasing memory from
* generic pools.
*/
int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c6d35d68ee9..a09dd29c2fd7 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -8,6 +8,7 @@
#include <linux/irq.h>
#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include "internals.h"
@@ -16,23 +17,18 @@ static struct proc_dir_entry *root_irq_dir;
#ifdef CONFIG_SMP
-static int irq_affinity_read_proc(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+static int irq_affinity_proc_show(struct seq_file *m, void *v)
{
- struct irq_desc *desc = irq_desc + (long)data;
+ struct irq_desc *desc = irq_desc + (long)m->private;
cpumask_t *mask = &desc->affinity;
- int len;
#ifdef CONFIG_GENERIC_PENDING_IRQ
if (desc->status & IRQ_MOVE_PENDING)
mask = &desc->pending_mask;
#endif
- len = cpumask_scnprintf(page, count, *mask);
-
- if (count - len < 2)
- return -EINVAL;
- len += sprintf(page + len, "\n");
- return len;
+ seq_cpumask(m, mask);
+ seq_putc(m, '\n');
+ return 0;
}
#ifndef is_affinity_mask_valid
@@ -40,11 +36,12 @@ static int irq_affinity_read_proc(char *page, char **start, off_t off,
#endif
int no_irq_affinity;
-static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+static ssize_t irq_affinity_proc_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *pos)
{
- unsigned int irq = (int)(long)data, full_count = count, err;
+ unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
cpumask_t new_value;
+ int err;
if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
irq_balancing_disabled(irq))
@@ -65,28 +62,38 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
if (!cpus_intersects(new_value, cpu_online_map))
/* Special case for empty set - allow the architecture
code to set default SMP affinity. */
- return irq_select_affinity(irq) ? -EINVAL : full_count;
+ return irq_select_affinity(irq) ? -EINVAL : count;
irq_set_affinity(irq, new_value);
- return full_count;
+ return count;
}
-static int default_affinity_read(char *page, char **start, off_t off,
- int count, int *eof, void *data)
+static int irq_affinity_proc_open(struct inode *inode, struct file *file)
{
- int len = cpumask_scnprintf(page, count, irq_default_affinity);
- if (count - len < 2)
- return -EINVAL;
- len += sprintf(page + len, "\n");
- return len;
+ return single_open(file, irq_affinity_proc_show, PDE(inode)->data);
}
-static int default_affinity_write(struct file *file, const char __user *buffer,
- unsigned long count, void *data)
+static const struct file_operations irq_affinity_proc_fops = {
+ .open = irq_affinity_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = irq_affinity_proc_write,
+};
+
+static int default_affinity_show(struct seq_file *m, void *v)
+{
+ seq_cpumask(m, &irq_default_affinity);
+ seq_putc(m, '\n');
+ return 0;
+}
+
+static ssize_t default_affinity_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos)
{
- unsigned int full_count = count, err;
cpumask_t new_value;
+ int err;
err = cpumask_parse_user(buffer, count, new_value);
if (err)
@@ -105,8 +112,21 @@ static int default_affinity_write(struct file *file, const char __user *buffer,
irq_default_affinity = new_value;
- return full_count;
+ return count;
}
+
+static int default_affinity_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, default_affinity_show, NULL);
+}
+
+static const struct file_operations default_affinity_proc_fops = {
+ .open = default_affinity_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = default_affinity_write,
+};
#endif
static int irq_spurious_read(char *page, char **start, off_t off,
@@ -178,16 +198,9 @@ void register_irq_proc(unsigned int irq)
irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
#ifdef CONFIG_SMP
- {
- /* create /proc/irq/<irq>/smp_affinity */
- entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir);
-
- if (entry) {
- entry->data = (void *)(long)irq;
- entry->read_proc = irq_affinity_read_proc;
- entry->write_proc = irq_affinity_write_proc;
- }
- }
+ /* create /proc/irq/<irq>/smp_affinity */
+ proc_create_data("smp_affinity", 0600, irq_desc[irq].dir,
+ &irq_affinity_proc_fops, (void *)(long)irq);
#endif
entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
@@ -208,15 +221,8 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action)
void register_default_affinity_proc(void)
{
#ifdef CONFIG_SMP
- struct proc_dir_entry *entry;
-
- /* create /proc/irq/default_smp_affinity */
- entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir);
- if (entry) {
- entry->data = NULL;
- entry->read_proc = default_affinity_read;
- entry->write_proc = default_affinity_write;
- }
+ proc_create("irq/default_smp_affinity", 0600, NULL,
+ &default_affinity_proc_fops);
#endif
}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c8a4370e2a34..59f3f0df35d4 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -12,7 +12,7 @@
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/kexec.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/syscalls.h>
@@ -77,7 +77,7 @@ int kexec_should_crash(struct task_struct *p)
*
* The code for the transition from the current kernel to the
* the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_CODE_SIZE. In the best case only a single
+ * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single
* page of memory is necessary, but some architectures require more.
* Because this memory must be identity mapped in the transition from
* virtual to physical addresses it must live in the range
@@ -242,7 +242,7 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
*/
result = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
- get_order(KEXEC_CONTROL_CODE_SIZE));
+ get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
printk(KERN_ERR "Could not allocate control_code_buffer\n");
goto out;
@@ -317,7 +317,7 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
*/
result = -ENOMEM;
image->control_code_page = kimage_alloc_control_pages(image,
- get_order(KEXEC_CONTROL_CODE_SIZE));
+ get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
printk(KERN_ERR "Could not allocate control_code_buffer\n");
goto out;
@@ -924,19 +924,14 @@ static int kimage_load_segment(struct kimage *image,
*/
struct kimage *kexec_image;
struct kimage *kexec_crash_image;
-/*
- * A home grown binary mutex.
- * Nothing can wait so this mutex is safe to use
- * in interrupt context :)
- */
-static int kexec_lock;
+
+static DEFINE_MUTEX(kexec_mutex);
asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
struct kexec_segment __user *segments,
unsigned long flags)
{
struct kimage **dest_image, *image;
- int locked;
int result;
/* We only trust the superuser with rebooting the system. */
@@ -972,8 +967,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
*
* KISS: always take the mutex.
*/
- locked = xchg(&kexec_lock, 1);
- if (locked)
+ if (!mutex_trylock(&kexec_mutex))
return -EBUSY;
dest_image = &kexec_image;
@@ -1015,8 +1009,7 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
image = xchg(dest_image, image);
out:
- locked = xchg(&kexec_lock, 0); /* Release the mutex */
- BUG_ON(!locked);
+ mutex_unlock(&kexec_mutex);
kimage_free(image);
return result;
@@ -1063,10 +1056,7 @@ asmlinkage long compat_sys_kexec_load(unsigned long entry,
void crash_kexec(struct pt_regs *regs)
{
- int locked;
-
-
- /* Take the kexec_lock here to prevent sys_kexec_load
+ /* Take the kexec_mutex here to prevent sys_kexec_load
* running on one cpu from replacing the crash kernel
* we are using after a panic on a different cpu.
*
@@ -1074,8 +1064,7 @@ void crash_kexec(struct pt_regs *regs)
* of memory the xchg(&kexec_crash_image) would be
* sufficient. But since I reuse the memory...
*/
- locked = xchg(&kexec_lock, 1);
- if (!locked) {
+ if (mutex_trylock(&kexec_mutex)) {
if (kexec_crash_image) {
struct pt_regs fixed_regs;
crash_setup_regs(&fixed_regs, regs);
@@ -1083,8 +1072,7 @@ void crash_kexec(struct pt_regs *regs)
machine_crash_shutdown(&fixed_regs);
machine_kexec(kexec_crash_image);
}
- locked = xchg(&kexec_lock, 0);
- BUG_ON(!locked);
+ mutex_unlock(&kexec_mutex);
}
}
@@ -1426,25 +1414,23 @@ static int __init crash_save_vmcoreinfo_init(void)
module_init(crash_save_vmcoreinfo_init)
-/**
- * kernel_kexec - reboot the system
- *
- * Move into place and start executing a preloaded standalone
- * executable. If nothing was preloaded return an error.
+/*
+ * Move into place and start executing a preloaded standalone
+ * executable. If nothing was preloaded return an error.
*/
int kernel_kexec(void)
{
int error = 0;
- if (xchg(&kexec_lock, 1))
+ if (!mutex_trylock(&kexec_mutex))
return -EBUSY;
if (!kexec_image) {
error = -EINVAL;
goto Unlock;
}
- if (kexec_image->preserve_context) {
#ifdef CONFIG_KEXEC_JUMP
+ if (kexec_image->preserve_context) {
mutex_lock(&pm_mutex);
pm_prepare_console();
error = freeze_processes();
@@ -1459,6 +1445,7 @@ int kernel_kexec(void)
error = disable_nonboot_cpus();
if (error)
goto Resume_devices;
+ device_pm_lock();
local_irq_disable();
/* At this point, device_suspend() has been called,
* but *not* device_power_down(). We *must*
@@ -1470,26 +1457,22 @@ int kernel_kexec(void)
error = device_power_down(PMSG_FREEZE);
if (error)
goto Enable_irqs;
- save_processor_state();
+ } else
#endif
- } else {
- blocking_notifier_call_chain(&reboot_notifier_list,
- SYS_RESTART, NULL);
- system_state = SYSTEM_RESTART;
- device_shutdown();
- sysdev_shutdown();
+ {
+ kernel_restart_prepare(NULL);
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
}
machine_kexec(kexec_image);
- if (kexec_image->preserve_context) {
#ifdef CONFIG_KEXEC_JUMP
- restore_processor_state();
+ if (kexec_image->preserve_context) {
device_power_up(PMSG_RESTORE);
Enable_irqs:
local_irq_enable();
+ device_pm_unlock();
enable_nonboot_cpus();
Resume_devices:
device_resume(PMSG_RESTORE);
@@ -1499,11 +1482,10 @@ int kernel_kexec(void)
Restore_console:
pm_restore_console();
mutex_unlock(&pm_mutex);
-#endif
}
+#endif
Unlock:
- xchg(&kexec_lock, 0);
-
+ mutex_unlock(&kexec_mutex);
return error;
}
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index d38a64362973..3bfb1877a003 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -124,6 +124,15 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
unsigned long nr_lock_classes;
static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+static inline struct lock_class *hlock_class(struct held_lock *hlock)
+{
+ if (!hlock->class_idx) {
+ DEBUG_LOCKS_WARN_ON(1);
+ return NULL;
+ }
+ return lock_classes + hlock->class_idx - 1;
+}
+
#ifdef CONFIG_LOCK_STAT
static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
@@ -222,7 +231,7 @@ static void lock_release_holdtime(struct held_lock *hlock)
holdtime = sched_clock() - hlock->holdtime_stamp;
- stats = get_lock_stats(hlock->class);
+ stats = get_lock_stats(hlock_class(hlock));
if (hlock->read)
lock_time_inc(&stats->read_holdtime, holdtime);
else
@@ -372,6 +381,19 @@ unsigned int nr_process_chains;
unsigned int max_lockdep_depth;
unsigned int max_recursion_depth;
+static unsigned int lockdep_dependency_gen_id;
+
+static bool lockdep_dependency_visit(struct lock_class *source,
+ unsigned int depth)
+{
+ if (!depth)
+ lockdep_dependency_gen_id++;
+ if (source->dep_gen_id == lockdep_dependency_gen_id)
+ return true;
+ source->dep_gen_id = lockdep_dependency_gen_id;
+ return false;
+}
+
#ifdef CONFIG_DEBUG_LOCKDEP
/*
* We cannot printk in early bootup code. Not even early_printk()
@@ -505,7 +527,7 @@ static void print_lockdep_cache(struct lockdep_map *lock)
static void print_lock(struct held_lock *hlock)
{
- print_lock_name(hlock->class);
+ print_lock_name(hlock_class(hlock));
printk(", at: ");
print_ip_sym(hlock->acquire_ip);
}
@@ -558,6 +580,9 @@ static void print_lock_dependencies(struct lock_class *class, int depth)
{
struct lock_list *entry;
+ if (lockdep_dependency_visit(class, depth))
+ return;
+
if (DEBUG_LOCKS_WARN_ON(depth >= 20))
return;
@@ -932,7 +957,7 @@ static noinline int print_circular_bug_tail(void)
if (debug_locks_silent)
return 0;
- this.class = check_source->class;
+ this.class = hlock_class(check_source);
if (!save_trace(&this.trace))
return 0;
@@ -959,6 +984,67 @@ static int noinline print_infinite_recursion_bug(void)
return 0;
}
+unsigned long __lockdep_count_forward_deps(struct lock_class *class,
+ unsigned int depth)
+{
+ struct lock_list *entry;
+ unsigned long ret = 1;
+
+ if (lockdep_dependency_visit(class, depth))
+ return 0;
+
+ /*
+ * Recurse this class's dependency list:
+ */
+ list_for_each_entry(entry, &class->locks_after, entry)
+ ret += __lockdep_count_forward_deps(entry->class, depth + 1);
+
+ return ret;
+}
+
+unsigned long lockdep_count_forward_deps(struct lock_class *class)
+{
+ unsigned long ret, flags;
+
+ local_irq_save(flags);
+ __raw_spin_lock(&lockdep_lock);
+ ret = __lockdep_count_forward_deps(class, 0);
+ __raw_spin_unlock(&lockdep_lock);
+ local_irq_restore(flags);
+
+ return ret;
+}
+
+unsigned long __lockdep_count_backward_deps(struct lock_class *class,
+ unsigned int depth)
+{
+ struct lock_list *entry;
+ unsigned long ret = 1;
+
+ if (lockdep_dependency_visit(class, depth))
+ return 0;
+ /*
+ * Recurse this class's dependency list:
+ */
+ list_for_each_entry(entry, &class->locks_before, entry)
+ ret += __lockdep_count_backward_deps(entry->class, depth + 1);
+
+ return ret;
+}
+
+unsigned long lockdep_count_backward_deps(struct lock_class *class)
+{
+ unsigned long ret, flags;
+
+ local_irq_save(flags);
+ __raw_spin_lock(&lockdep_lock);
+ ret = __lockdep_count_backward_deps(class, 0);
+ __raw_spin_unlock(&lockdep_lock);
+ local_irq_restore(flags);
+
+ return ret;
+}
+
/*
* Prove that the dependency graph starting at <entry> can not
* lead to <target>. Print an error and return 0 if it does.
@@ -968,6 +1054,9 @@ check_noncircular(struct lock_class *source, unsigned int depth)
{
struct lock_list *entry;
+ if (lockdep_dependency_visit(source, depth))
+ return 1;
+
debug_atomic_inc(&nr_cyclic_check_recursions);
if (depth > max_recursion_depth)
max_recursion_depth = depth;
@@ -977,7 +1066,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
* Check this lock's dependency list:
*/
list_for_each_entry(entry, &source->locks_after, entry) {
- if (entry->class == check_target->class)
+ if (entry->class == hlock_class(check_target))
return print_circular_bug_header(entry, depth+1);
debug_atomic_inc(&nr_cyclic_checks);
if (!check_noncircular(entry->class, depth+1))
@@ -1011,6 +1100,9 @@ find_usage_forwards(struct lock_class *source, unsigned int depth)
struct lock_list *entry;
int ret;
+ if (lockdep_dependency_visit(source, depth))
+ return 1;
+
if (depth > max_recursion_depth)
max_recursion_depth = depth;
if (depth >= RECURSION_LIMIT)
@@ -1050,6 +1142,9 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
struct lock_list *entry;
int ret;
+ if (lockdep_dependency_visit(source, depth))
+ return 1;
+
if (!__raw_spin_is_locked(&lockdep_lock))
return DEBUG_LOCKS_WARN_ON(1);
@@ -1064,6 +1159,11 @@ find_usage_backwards(struct lock_class *source, unsigned int depth)
return 2;
}
+ if (!source && debug_locks_off_graph_unlock()) {
+ WARN_ON(1);
+ return 0;
+ }
+
/*
* Check this lock's dependency list:
*/
@@ -1103,9 +1203,9 @@ print_bad_irq_dependency(struct task_struct *curr,
printk("\nand this task is already holding:\n");
print_lock(prev);
printk("which would create a new lock dependency:\n");
- print_lock_name(prev->class);
+ print_lock_name(hlock_class(prev));
printk(" ->");
- print_lock_name(next->class);
+ print_lock_name(hlock_class(next));
printk("\n");
printk("\nbut this new dependency connects a %s-irq-safe lock:\n",
@@ -1146,12 +1246,12 @@ check_usage(struct task_struct *curr, struct held_lock *prev,
find_usage_bit = bit_backwards;
/* fills in <backwards_match> */
- ret = find_usage_backwards(prev->class, 0);
+ ret = find_usage_backwards(hlock_class(prev), 0);
if (!ret || ret == 1)
return ret;
find_usage_bit = bit_forwards;
- ret = find_usage_forwards(next->class, 0);
+ ret = find_usage_forwards(hlock_class(next), 0);
if (!ret || ret == 1)
return ret;
/* ret == 2 */
@@ -1272,18 +1372,32 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
struct lockdep_map *next_instance, int read)
{
struct held_lock *prev;
+ struct held_lock *nest = NULL;
int i;
for (i = 0; i < curr->lockdep_depth; i++) {
prev = curr->held_locks + i;
- if (prev->class != next->class)
+
+ if (prev->instance == next->nest_lock)
+ nest = prev;
+
+ if (hlock_class(prev) != hlock_class(next))
continue;
+
/*
* Allow read-after-read recursion of the same
* lock class (i.e. read_lock(lock)+read_lock(lock)):
*/
if ((read == 2) && prev->read)
return 2;
+
+ /*
+ * We're holding the nest_lock, which serializes this lock's
+ * nesting behaviour.
+ */
+ if (nest)
+ return 2;
+
return print_deadlock_bug(curr, prev, next);
}
return 1;
@@ -1329,7 +1443,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
*/
check_source = next;
check_target = prev;
- if (!(check_noncircular(next->class, 0)))
+ if (!(check_noncircular(hlock_class(next), 0)))
return print_circular_bug_tail();
if (!check_prev_add_irq(curr, prev, next))
@@ -1353,8 +1467,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
* chains - the second one will be new, but L1 already has
* L2 added to its dependency list, due to the first chain.)
*/
- list_for_each_entry(entry, &prev->class->locks_after, entry) {
- if (entry->class == next->class) {
+ list_for_each_entry(entry, &hlock_class(prev)->locks_after, entry) {
+ if (entry->class == hlock_class(next)) {
if (distance == 1)
entry->distance = 1;
return 2;
@@ -1365,26 +1479,28 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
* Ok, all validations passed, add the new lock
* to the previous lock's dependency list:
*/
- ret = add_lock_to_list(prev->class, next->class,
- &prev->class->locks_after, next->acquire_ip, distance);
+ ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+ &hlock_class(prev)->locks_after,
+ next->acquire_ip, distance);
if (!ret)
return 0;
- ret = add_lock_to_list(next->class, prev->class,
- &next->class->locks_before, next->acquire_ip, distance);
+ ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+ &hlock_class(next)->locks_before,
+ next->acquire_ip, distance);
if (!ret)
return 0;
/*
* Debugging printouts:
*/
- if (verbose(prev->class) || verbose(next->class)) {
+ if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
graph_unlock();
printk("\n new dependency: ");
- print_lock_name(prev->class);
+ print_lock_name(hlock_class(prev));
printk(" => ");
- print_lock_name(next->class);
+ print_lock_name(hlock_class(next));
printk("\n");
dump_stack();
return graph_lock();
@@ -1481,7 +1597,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
struct held_lock *hlock,
u64 chain_key)
{
- struct lock_class *class = hlock->class;
+ struct lock_class *class = hlock_class(hlock);
struct list_head *hash_head = chainhashentry(chain_key);
struct lock_chain *chain;
struct held_lock *hlock_curr, *hlock_next;
@@ -1554,7 +1670,7 @@ cache_hit:
if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
chain->base = cn;
for (j = 0; j < chain->depth - 1; j++, i++) {
- int lock_id = curr->held_locks[i].class - lock_classes;
+ int lock_id = curr->held_locks[i].class_idx - 1;
chain_hlocks[chain->base + j] = lock_id;
}
chain_hlocks[chain->base + j] = class - lock_classes;
@@ -1643,14 +1759,13 @@ static void check_chain_key(struct task_struct *curr)
hlock = curr->held_locks + i;
if (chain_key != hlock->prev_chain_key) {
debug_locks_off();
- printk("hm#1, depth: %u [%u], %016Lx != %016Lx\n",
+ WARN(1, "hm#1, depth: %u [%u], %016Lx != %016Lx\n",
curr->lockdep_depth, i,
(unsigned long long)chain_key,
(unsigned long long)hlock->prev_chain_key);
- WARN_ON(1);
return;
}
- id = hlock->class - lock_classes;
+ id = hlock->class_idx - 1;
if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
return;
@@ -1662,11 +1777,10 @@ static void check_chain_key(struct task_struct *curr)
}
if (chain_key != curr->curr_chain_key) {
debug_locks_off();
- printk("hm#2, depth: %u [%u], %016Lx != %016Lx\n",
+ WARN(1, "hm#2, depth: %u [%u], %016Lx != %016Lx\n",
curr->lockdep_depth, i,
(unsigned long long)chain_key,
(unsigned long long)curr->curr_chain_key);
- WARN_ON(1);
}
#endif
}
@@ -1695,7 +1809,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
print_lock(this);
printk("{%s} state was registered at:\n", usage_str[prev_bit]);
- print_stack_trace(this->class->usage_traces + prev_bit, 1);
+ print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
print_irqtrace_events(curr);
printk("\nother info that might help us debug this:\n");
@@ -1714,7 +1828,7 @@ static inline int
valid_state(struct task_struct *curr, struct held_lock *this,
enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
{
- if (unlikely(this->class->usage_mask & (1 << bad_bit)))
+ if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
return print_usage_bug(curr, this, bad_bit, new_bit);
return 1;
}
@@ -1753,7 +1867,7 @@ print_irq_inversion_bug(struct task_struct *curr, struct lock_class *other,
lockdep_print_held_locks(curr);
printk("\nthe first lock's dependencies:\n");
- print_lock_dependencies(this->class, 0);
+ print_lock_dependencies(hlock_class(this), 0);
printk("\nthe second lock's dependencies:\n");
print_lock_dependencies(other, 0);
@@ -1776,7 +1890,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
find_usage_bit = bit;
/* fills in <forwards_match> */
- ret = find_usage_forwards(this->class, 0);
+ ret = find_usage_forwards(hlock_class(this), 0);
if (!ret || ret == 1)
return ret;
@@ -1795,7 +1909,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
find_usage_bit = bit;
/* fills in <backwards_match> */
- ret = find_usage_backwards(this->class, 0);
+ ret = find_usage_backwards(hlock_class(this), 0);
if (!ret || ret == 1)
return ret;
@@ -1861,7 +1975,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_ENABLED_HARDIRQS_READ, "hard-read"))
return 0;
#endif
- if (hardirq_verbose(this->class))
+ if (hardirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_USED_IN_SOFTIRQ:
@@ -1886,7 +2000,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_ENABLED_SOFTIRQS_READ, "soft-read"))
return 0;
#endif
- if (softirq_verbose(this->class))
+ if (softirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_USED_IN_HARDIRQ_READ:
@@ -1899,7 +2013,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
if (!check_usage_forwards(curr, this,
LOCK_ENABLED_HARDIRQS, "hard"))
return 0;
- if (hardirq_verbose(this->class))
+ if (hardirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_USED_IN_SOFTIRQ_READ:
@@ -1912,7 +2026,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
if (!check_usage_forwards(curr, this,
LOCK_ENABLED_SOFTIRQS, "soft"))
return 0;
- if (softirq_verbose(this->class))
+ if (softirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_ENABLED_HARDIRQS:
@@ -1938,7 +2052,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_USED_IN_HARDIRQ_READ, "hard-read"))
return 0;
#endif
- if (hardirq_verbose(this->class))
+ if (hardirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_ENABLED_SOFTIRQS:
@@ -1964,7 +2078,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_USED_IN_SOFTIRQ_READ, "soft-read"))
return 0;
#endif
- if (softirq_verbose(this->class))
+ if (softirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_ENABLED_HARDIRQS_READ:
@@ -1979,7 +2093,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_USED_IN_HARDIRQ, "hard"))
return 0;
#endif
- if (hardirq_verbose(this->class))
+ if (hardirq_verbose(hlock_class(this)))
ret = 2;
break;
case LOCK_ENABLED_SOFTIRQS_READ:
@@ -1994,7 +2108,7 @@ static int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
LOCK_USED_IN_SOFTIRQ, "soft"))
return 0;
#endif
- if (softirq_verbose(this->class))
+ if (softirq_verbose(hlock_class(this)))
ret = 2;
break;
default:
@@ -2310,7 +2424,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
* If already set then do not dirty the cacheline,
* nor do any checks:
*/
- if (likely(this->class->usage_mask & new_mask))
+ if (likely(hlock_class(this)->usage_mask & new_mask))
return 1;
if (!graph_lock())
@@ -2318,14 +2432,14 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
/*
* Make sure we didnt race:
*/
- if (unlikely(this->class->usage_mask & new_mask)) {
+ if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
graph_unlock();
return 1;
}
- this->class->usage_mask |= new_mask;
+ hlock_class(this)->usage_mask |= new_mask;
- if (!save_trace(this->class->usage_traces + new_bit))
+ if (!save_trace(hlock_class(this)->usage_traces + new_bit))
return 0;
switch (new_bit) {
@@ -2405,7 +2519,7 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
*/
static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int trylock, int read, int check, int hardirqs_off,
- unsigned long ip)
+ struct lockdep_map *nest_lock, unsigned long ip)
{
struct task_struct *curr = current;
struct lock_class *class = NULL;
@@ -2459,14 +2573,16 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
return 0;
hlock = curr->held_locks + depth;
-
- hlock->class = class;
+ if (DEBUG_LOCKS_WARN_ON(!class))
+ return 0;
+ hlock->class_idx = class - lock_classes + 1;
hlock->acquire_ip = ip;
hlock->instance = lock;
+ hlock->nest_lock = nest_lock;
hlock->trylock = trylock;
hlock->read = read;
hlock->check = check;
- hlock->hardirqs_off = hardirqs_off;
+ hlock->hardirqs_off = !!hardirqs_off;
#ifdef CONFIG_LOCK_STAT
hlock->waittime_stamp = 0;
hlock->holdtime_stamp = sched_clock();
@@ -2574,6 +2690,55 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
return 1;
}
+static int
+__lock_set_subclass(struct lockdep_map *lock,
+ unsigned int subclass, unsigned long ip)
+{
+ struct task_struct *curr = current;
+ struct held_lock *hlock, *prev_hlock;
+ struct lock_class *class;
+ unsigned int depth;
+ int i;
+
+ depth = curr->lockdep_depth;
+ if (DEBUG_LOCKS_WARN_ON(!depth))
+ return 0;
+
+ prev_hlock = NULL;
+ for (i = depth-1; i >= 0; i--) {
+ hlock = curr->held_locks + i;
+ /*
+ * We must not cross into another context:
+ */
+ if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
+ break;
+ if (hlock->instance == lock)
+ goto found_it;
+ prev_hlock = hlock;
+ }
+ return print_unlock_inbalance_bug(curr, lock, ip);
+
+found_it:
+ class = register_lock_class(lock, subclass, 0);
+ hlock->class_idx = class - lock_classes + 1;
+
+ curr->lockdep_depth = i;
+ curr->curr_chain_key = hlock->prev_chain_key;
+
+ for (; i < depth; i++) {
+ hlock = curr->held_locks + i;
+ if (!__lock_acquire(hlock->instance,
+ hlock_class(hlock)->subclass, hlock->trylock,
+ hlock->read, hlock->check, hlock->hardirqs_off,
+ hlock->nest_lock, hlock->acquire_ip))
+ return 0;
+ }
+
+ if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+ return 0;
+ return 1;
+}
+
/*
* Remove the lock to the list of currently held locks in a
* potentially non-nested (out of order) manner. This is a
@@ -2624,9 +2789,9 @@ found_it:
for (i++; i < depth; i++) {
hlock = curr->held_locks + i;
if (!__lock_acquire(hlock->instance,
- hlock->class->subclass, hlock->trylock,
+ hlock_class(hlock)->subclass, hlock->trylock,
hlock->read, hlock->check, hlock->hardirqs_off,
- hlock->acquire_ip))
+ hlock->nest_lock, hlock->acquire_ip))
return 0;
}
@@ -2669,7 +2834,7 @@ static int lock_release_nested(struct task_struct *curr,
#ifdef CONFIG_DEBUG_LOCKDEP
hlock->prev_chain_key = 0;
- hlock->class = NULL;
+ hlock->class_idx = 0;
hlock->acquire_ip = 0;
hlock->irq_context = 0;
#endif
@@ -2738,18 +2903,36 @@ static void check_flags(unsigned long flags)
#endif
}
+void
+lock_set_subclass(struct lockdep_map *lock,
+ unsigned int subclass, unsigned long ip)
+{
+ unsigned long flags;
+
+ if (unlikely(current->lockdep_recursion))
+ return;
+
+ raw_local_irq_save(flags);
+ current->lockdep_recursion = 1;
+ check_flags(flags);
+ if (__lock_set_subclass(lock, subclass, ip))
+ check_chain_key(current);
+ current->lockdep_recursion = 0;
+ raw_local_irq_restore(flags);
+}
+
+EXPORT_SYMBOL_GPL(lock_set_subclass);
+
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
*/
void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
- int trylock, int read, int check, unsigned long ip)
+ int trylock, int read, int check,
+ struct lockdep_map *nest_lock, unsigned long ip)
{
unsigned long flags;
- if (unlikely(!lock_stat && !prove_locking))
- return;
-
if (unlikely(current->lockdep_recursion))
return;
@@ -2758,7 +2941,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
current->lockdep_recursion = 1;
__lock_acquire(lock, subclass, trylock, read, check,
- irqs_disabled_flags(flags), ip);
+ irqs_disabled_flags(flags), nest_lock, ip);
current->lockdep_recursion = 0;
raw_local_irq_restore(flags);
}
@@ -2770,9 +2953,6 @@ void lock_release(struct lockdep_map *lock, int nested,
{
unsigned long flags;
- if (unlikely(!lock_stat && !prove_locking))
- return;
-
if (unlikely(current->lockdep_recursion))
return;
@@ -2845,9 +3025,9 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
found_it:
hlock->waittime_stamp = sched_clock();
- point = lock_contention_point(hlock->class, ip);
+ point = lock_contention_point(hlock_class(hlock), ip);
- stats = get_lock_stats(hlock->class);
+ stats = get_lock_stats(hlock_class(hlock));
if (point < ARRAY_SIZE(stats->contention_point))
stats->contention_point[i]++;
if (lock->cpu != smp_processor_id())
@@ -2893,7 +3073,7 @@ found_it:
hlock->holdtime_stamp = now;
}
- stats = get_lock_stats(hlock->class);
+ stats = get_lock_stats(hlock_class(hlock));
if (waittime) {
if (hlock->read)
lock_time_inc(&stats->read_waittime, waittime);
@@ -2988,6 +3168,7 @@ static void zap_class(struct lock_class *class)
list_del_rcu(&class->hash_entry);
list_del_rcu(&class->lock_entry);
+ class->key = NULL;
}
static inline int within(const void *addr, void *start, unsigned long size)
diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
index c3600a091a28..56b196932c08 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -17,9 +17,6 @@
*/
#define MAX_LOCKDEP_ENTRIES 8192UL
-#define MAX_LOCKDEP_KEYS_BITS 11
-#define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS)
-
#define MAX_LOCKDEP_CHAINS_BITS 14
#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS)
@@ -53,6 +50,22 @@ extern unsigned int nr_process_chains;
extern unsigned int max_lockdep_depth;
extern unsigned int max_recursion_depth;
+#ifdef CONFIG_PROVE_LOCKING
+extern unsigned long lockdep_count_forward_deps(struct lock_class *);
+extern unsigned long lockdep_count_backward_deps(struct lock_class *);
+#else
+static inline unsigned long
+lockdep_count_forward_deps(struct lock_class *class)
+{
+ return 0;
+}
+static inline unsigned long
+lockdep_count_backward_deps(struct lock_class *class)
+{
+ return 0;
+}
+#endif
+
#ifdef CONFIG_DEBUG_LOCKDEP
/*
* Various lockdep statistics:
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 9b0e940e2545..4b194d34d77f 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -63,34 +63,6 @@ static void l_stop(struct seq_file *m, void *v)
{
}
-static unsigned long count_forward_deps(struct lock_class *class)
-{
- struct lock_list *entry;
- unsigned long ret = 1;
-
- /*
- * Recurse this class's dependency list:
- */
- list_for_each_entry(entry, &class->locks_after, entry)
- ret += count_forward_deps(entry->class);
-
- return ret;
-}
-
-static unsigned long count_backward_deps(struct lock_class *class)
-{
- struct lock_list *entry;
- unsigned long ret = 1;
-
- /*
- * Recurse this class's dependency list:
- */
- list_for_each_entry(entry, &class->locks_before, entry)
- ret += count_backward_deps(entry->class);
-
- return ret;
-}
-
static void print_name(struct seq_file *m, struct lock_class *class)
{
char str[128];
@@ -110,7 +82,6 @@ static void print_name(struct seq_file *m, struct lock_class *class)
static int l_show(struct seq_file *m, void *v)
{
- unsigned long nr_forward_deps, nr_backward_deps;
struct lock_class *class = v;
struct lock_list *entry;
char c1, c2, c3, c4;
@@ -124,11 +95,10 @@ static int l_show(struct seq_file *m, void *v)
#ifdef CONFIG_DEBUG_LOCKDEP
seq_printf(m, " OPS:%8ld", class->ops);
#endif
- nr_forward_deps = count_forward_deps(class);
- seq_printf(m, " FD:%5ld", nr_forward_deps);
-
- nr_backward_deps = count_backward_deps(class);
- seq_printf(m, " BD:%5ld", nr_backward_deps);
+#ifdef CONFIG_PROVE_LOCKING
+ seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class));
+ seq_printf(m, " BD:%5ld", lockdep_count_backward_deps(class));
+#endif
get_usage_chars(class, &c1, &c2, &c3, &c4);
seq_printf(m, " %c%c%c%c", c1, c2, c3, c4);
@@ -229,6 +199,9 @@ static int lc_show(struct seq_file *m, void *v)
for (i = 0; i < chain->depth; i++) {
class = lock_chain_get_class(chain, i);
+ if (!class->key)
+ continue;
+
seq_printf(m, "[%p] ", class->key);
print_name(m, class);
seq_puts(m, "\n");
@@ -350,7 +323,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
nr_hardirq_read_unsafe++;
- sum_forward_deps += count_forward_deps(class);
+#ifdef CONFIG_PROVE_LOCKING
+ sum_forward_deps += lockdep_count_forward_deps(class);
+#endif
}
#ifdef CONFIG_DEBUG_LOCKDEP
DEBUG_LOCKS_WARN_ON(debug_atomic_read(&nr_unused_locks) != nr_unused);
diff --git a/kernel/module.c b/kernel/module.c
index 61d212120df4..08864d257eb0 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2288,7 +2288,7 @@ sys_init_module(void __user *umod,
/* Start the module */
if (mod->init != NULL)
- ret = mod->init();
+ ret = do_one_initcall(mod->init);
if (ret < 0) {
/* Init routine failed: abort. Try to protect us from
buggy refcounters. */
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 9a21681aa80f..e36d5798cbff 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -289,21 +289,29 @@ void do_schedule_next_timer(struct siginfo *info)
else
schedule_next_timer(timr);
- info->si_overrun = timr->it_overrun_last;
+ info->si_overrun += timr->it_overrun_last;
}
if (timr)
unlock_timer(timr, flags);
}
-int posix_timer_event(struct k_itimer *timr,int si_private)
+int posix_timer_event(struct k_itimer *timr, int si_private)
{
- memset(&timr->sigq->info, 0, sizeof(siginfo_t));
+ /*
+ * FIXME: if ->sigq is queued we can race with
+ * dequeue_signal()->do_schedule_next_timer().
+ *
+ * If dequeue_signal() sees the "right" value of
+ * si_sys_private it calls do_schedule_next_timer().
+ * We re-queue ->sigq and drop ->it_lock().
+ * do_schedule_next_timer() locks the timer
+ * and re-schedules it while ->sigq is pending.
+ * Not really bad, but not that we want.
+ */
timr->sigq->info.si_sys_private = si_private;
- /* Send signal to the process that owns this timer.*/
timr->sigq->info.si_signo = timr->it_sigev_signo;
- timr->sigq->info.si_errno = 0;
timr->sigq->info.si_code = SI_TIMER;
timr->sigq->info.si_tid = timr->it_id;
timr->sigq->info.si_value = timr->it_sigev_value;
@@ -435,6 +443,7 @@ static struct k_itimer * alloc_posix_timer(void)
kmem_cache_free(posix_timers_cache, tmr);
tmr = NULL;
}
+ memset(&tmr->sigq->info, 0, sizeof(siginfo_t));
return tmr;
}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 082b3fcb32a0..356699a96d56 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -140,7 +140,7 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
if (!dumpable && !capable(CAP_SYS_PTRACE))
return -EPERM;
- return security_ptrace(current, task, mode);
+ return security_ptrace_may_access(task, mode);
}
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
@@ -499,8 +499,7 @@ repeat:
goto repeat;
}
- ret = security_ptrace(current->parent, current,
- PTRACE_MODE_ATTACH);
+ ret = security_ptrace_traceme(current->parent);
/*
* Set the ptrace bit in the process ptrace flags.
diff --git a/kernel/sched.c b/kernel/sched.c
index 04160d277e7a..9a1ddb84e26d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -600,7 +600,6 @@ struct rq {
/* BKL stats */
unsigned int bkl_count;
#endif
- struct lock_class_key rq_lock_key;
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -809,9 +808,9 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
/*
* ratelimit for updating the group shares.
- * default: 0.5ms
+ * default: 0.25ms
*/
-const_debug unsigned int sysctl_sched_shares_ratelimit = 500000;
+unsigned int sysctl_sched_shares_ratelimit = 250000;
/*
* period over which we measure -rt task cpu usage in us.
@@ -834,7 +833,7 @@ static inline u64 global_rt_period(void)
static inline u64 global_rt_runtime(void)
{
- if (sysctl_sched_rt_period < 0)
+ if (sysctl_sched_rt_runtime < 0)
return RUNTIME_INF;
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
@@ -2759,10 +2758,10 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
} else {
if (rq1 < rq2) {
spin_lock(&rq1->lock);
- spin_lock(&rq2->lock);
+ spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
} else {
spin_lock(&rq2->lock);
- spin_lock(&rq1->lock);
+ spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
}
}
update_rq_clock(rq1);
@@ -2805,14 +2804,21 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
if (busiest < this_rq) {
spin_unlock(&this_rq->lock);
spin_lock(&busiest->lock);
- spin_lock(&this_rq->lock);
+ spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
ret = 1;
} else
- spin_lock(&busiest->lock);
+ spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
}
return ret;
}
+static 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
@@ -3637,7 +3643,7 @@ redo:
ld_moved = move_tasks(this_rq, this_cpu, busiest,
imbalance, sd, CPU_NEWLY_IDLE,
&all_pinned);
- spin_unlock(&busiest->lock);
+ double_unlock_balance(this_rq, busiest);
if (unlikely(all_pinned)) {
cpu_clear(cpu_of(busiest), *cpus);
@@ -3752,7 +3758,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
else
schedstat_inc(sd, alb_failed);
}
- spin_unlock(&target_rq->lock);
+ double_unlock_balance(busiest_rq, target_rq);
}
#ifdef CONFIG_NO_HZ
@@ -4663,6 +4669,52 @@ int __sched wait_for_completion_killable(struct completion *x)
}
EXPORT_SYMBOL(wait_for_completion_killable);
+/**
+ * try_wait_for_completion - try to decrement a completion without blocking
+ * @x: completion structure
+ *
+ * Returns: 0 if a decrement cannot be done without blocking
+ * 1 if a decrement succeeded.
+ *
+ * If a completion is being used as a counting completion,
+ * attempt to decrement the counter without blocking. This
+ * enables us to avoid waiting if the resource the completion
+ * is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+ int ret = 1;
+
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done)
+ ret = 0;
+ else
+ x->done--;
+ spin_unlock_irq(&x->wait.lock);
+ return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ * completion_done - Test to see if a completion has any waiters
+ * @x: completion structure
+ *
+ * Returns: 0 if there are waiters (wait_for_completion() in progress)
+ * 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+ int ret = 1;
+
+ spin_lock_irq(&x->wait.lock);
+ if (!x->done)
+ ret = 0;
+ spin_unlock_irq(&x->wait.lock);
+ return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
static long __sched
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
{
@@ -5734,6 +5786,8 @@ static inline void sched_init_granularity(void)
sysctl_sched_latency = limit;
sysctl_sched_wakeup_granularity *= factor;
+
+ sysctl_sched_shares_ratelimit *= factor;
}
#ifdef CONFIG_SMP
@@ -8000,7 +8054,6 @@ void __init sched_init(void)
rq = cpu_rq(i);
spin_lock_init(&rq->lock);
- lockdep_set_class(&rq->lock, &rq->rq_lock_key);
rq->nr_running = 0;
init_cfs_rq(&rq->cfs, rq);
init_rt_rq(&rq->rt, rq);
@@ -8457,8 +8510,8 @@ struct task_group *sched_create_group(struct task_group *parent)
WARN_ON(!parent); /* root should already exist */
tg->parent = parent;
- list_add_rcu(&tg->siblings, &parent->children);
INIT_LIST_HEAD(&tg->children);
+ list_add_rcu(&tg->siblings, &parent->children);
spin_unlock_irqrestore(&task_group_lock, flags);
return tg;
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 22ed55d1167f..204991a0bfa7 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -32,13 +32,19 @@
#include <linux/ktime.h>
#include <linux/module.h>
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+ return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static __read_mostly int sched_clock_running;
-#define MULTI_SHIFT 15
-/* Max is double, Min is 1/2 */
-#define MAX_MULTI (2LL << MULTI_SHIFT)
-#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
struct sched_clock_data {
/*
@@ -49,14 +55,9 @@ struct sched_clock_data {
raw_spinlock_t lock;
unsigned long tick_jiffies;
- u64 prev_raw;
u64 tick_raw;
u64 tick_gtod;
u64 clock;
- s64 multi;
-#ifdef CONFIG_NO_HZ
- int check_max;
-#endif
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,8 +72,6 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
return &per_cpu(sched_clock_data, cpu);
}
-static __read_mostly int sched_clock_running;
-
void sched_clock_init(void)
{
u64 ktime_now = ktime_to_ns(ktime_get());
@@ -84,90 +83,39 @@ void sched_clock_init(void)
scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
scd->tick_jiffies = now_jiffies;
- scd->prev_raw = 0;
scd->tick_raw = 0;
scd->tick_gtod = ktime_now;
scd->clock = ktime_now;
- scd->multi = 1 << MULTI_SHIFT;
-#ifdef CONFIG_NO_HZ
- scd->check_max = 1;
-#endif
}
sched_clock_running = 1;
}
-#ifdef CONFIG_NO_HZ
-/*
- * The dynamic ticks makes the delta jiffies inaccurate. This
- * prevents us from checking the maximum time update.
- * Disable the maximum check during stopped ticks.
- */
-void sched_clock_tick_stop(int cpu)
-{
- struct sched_clock_data *scd = cpu_sdc(cpu);
-
- scd->check_max = 0;
-}
-
-void sched_clock_tick_start(int cpu)
-{
- struct sched_clock_data *scd = cpu_sdc(cpu);
-
- scd->check_max = 1;
-}
-
-static int check_max(struct sched_clock_data *scd)
-{
- return scd->check_max;
-}
-#else
-static int check_max(struct sched_clock_data *scd)
-{
- return 1;
-}
-#endif /* CONFIG_NO_HZ */
-
/*
* update the percpu scd from the raw @now value
*
* - filter out backward motion
* - use jiffies to generate a min,max window to clip the raw values
*/
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
+static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
{
unsigned long now_jiffies = jiffies;
long delta_jiffies = now_jiffies - scd->tick_jiffies;
u64 clock = scd->clock;
u64 min_clock, max_clock;
- s64 delta = now - scd->prev_raw;
+ s64 delta = now - scd->tick_raw;
WARN_ON_ONCE(!irqs_disabled());
-
- /*
- * At schedule tick the clock can be just under the gtod. We don't
- * want to push it too prematurely.
- */
- min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
- if (min_clock > TICK_NSEC)
- min_clock -= TICK_NSEC / 2;
+ min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
if (unlikely(delta < 0)) {
clock++;
goto out;
}
- /*
- * The clock must stay within a jiffie of the gtod.
- * But since we may be at the start of a jiffy or the end of one
- * we add another jiffy buffer.
- */
- max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
-
- delta *= scd->multi;
- delta >>= MULTI_SHIFT;
+ max_clock = min_clock + TICK_NSEC;
- if (unlikely(clock + delta > max_clock) && check_max(scd)) {
+ if (unlikely(clock + delta > max_clock)) {
if (clock < max_clock)
clock = max_clock;
else
@@ -180,12 +128,10 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
if (unlikely(clock < min_clock))
clock = min_clock;
- if (time)
- *time = clock;
- else {
- scd->prev_raw = now;
- scd->clock = clock;
- }
+ scd->tick_jiffies = now_jiffies;
+ scd->clock = clock;
+
+ return clock;
}
static void lock_double_clock(struct sched_clock_data *data1,
@@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1,
u64 sched_clock_cpu(int cpu)
{
struct sched_clock_data *scd = cpu_sdc(cpu);
- u64 now, clock;
+ u64 now, clock, this_clock, remote_clock;
if (unlikely(!sched_clock_running))
return 0ull;
@@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu)
now = sched_clock();
if (cpu != raw_smp_processor_id()) {
- /*
- * in order to update a remote cpu's clock based on our
- * unstable raw time rebase it against:
- * tick_raw (offset between raw counters)
- * tick_gotd (tick offset between cpus)
- */
struct sched_clock_data *my_scd = this_scd();
lock_double_clock(scd, my_scd);
- now -= my_scd->tick_raw;
- now += scd->tick_raw;
+ this_clock = __update_sched_clock(my_scd, now);
+ remote_clock = scd->clock;
- now += my_scd->tick_gtod;
- now -= scd->tick_gtod;
+ /*
+ * Use the opportunity that we have both locks
+ * taken to couple the two clocks: we take the
+ * larger time as the latest time for both
+ * runqueues. (this creates monotonic movement)
+ */
+ if (likely(remote_clock < this_clock)) {
+ clock = this_clock;
+ scd->clock = clock;
+ } else {
+ /*
+ * Should be rare, but possible:
+ */
+ clock = remote_clock;
+ my_scd->clock = remote_clock;
+ }
__raw_spin_unlock(&my_scd->lock);
-
- __update_sched_clock(scd, now, &clock);
-
- __raw_spin_unlock(&scd->lock);
-
} else {
__raw_spin_lock(&scd->lock);
- __update_sched_clock(scd, now, NULL);
- clock = scd->clock;
- __raw_spin_unlock(&scd->lock);
+ clock = __update_sched_clock(scd, now);
}
+ __raw_spin_unlock(&scd->lock);
+
return clock;
}
void sched_clock_tick(void)
{
struct sched_clock_data *scd = this_scd();
- unsigned long now_jiffies = jiffies;
- s64 mult, delta_gtod, delta_raw;
u64 now, now_gtod;
if (unlikely(!sched_clock_running))
@@ -260,29 +207,14 @@ void sched_clock_tick(void)
now = sched_clock();
__raw_spin_lock(&scd->lock);
- __update_sched_clock(scd, now, NULL);
+ __update_sched_clock(scd, now);
/*
* update tick_gtod after __update_sched_clock() because that will
* already observe 1 new jiffy; adding a new tick_gtod to that would
* increase the clock 2 jiffies.
*/
- delta_gtod = now_gtod - scd->tick_gtod;
- delta_raw = now - scd->tick_raw;
-
- if ((long)delta_raw > 0) {
- mult = delta_gtod << MULTI_SHIFT;
- do_div(mult, delta_raw);
- scd->multi = mult;
- if (scd->multi > MAX_MULTI)
- scd->multi = MAX_MULTI;
- else if (scd->multi < MIN_MULTI)
- scd->multi = MIN_MULTI;
- } else
- scd->multi = 1 << MULTI_SHIFT;
-
scd->tick_raw = now;
scd->tick_gtod = now_gtod;
- scd->tick_jiffies = now_jiffies;
__raw_spin_unlock(&scd->lock);
}
@@ -301,7 +233,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
void sched_clock_idle_wakeup_event(u64 delta_ns)
{
struct sched_clock_data *scd = this_scd();
- u64 now = sched_clock();
/*
* Override the previous timestamp and ignore all
@@ -310,27 +241,30 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
* rq clock:
*/
__raw_spin_lock(&scd->lock);
- scd->prev_raw = now;
scd->clock += delta_ns;
- scd->multi = 1 << MULTI_SHIFT;
__raw_spin_unlock(&scd->lock);
touch_softlockup_watchdog();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
-#endif
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-/*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
+void sched_clock_init(void)
{
- return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+ sched_clock_running = 1;
}
+u64 sched_clock_cpu(int cpu)
+{
+ if (unlikely(!sched_clock_running))
+ return 0;
+
+ return sched_clock();
+}
+
+#endif
+
unsigned long long cpu_clock(int cpu)
{
unsigned long long clock;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index cf2cd6ce4cb2..fb8994c6d4bb 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -899,7 +899,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
* doesn't make sense. Rely on vruntime for fairness.
*/
if (rq->curr != p)
- delta = max(10000LL, delta);
+ delta = max_t(s64, 10000LL, delta);
hrtick_start(rq, delta);
}
@@ -1442,18 +1442,23 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
struct task_struct *p = NULL;
struct sched_entity *se;
- while (next != &cfs_rq->tasks) {
+ if (next == &cfs_rq->tasks)
+ return NULL;
+
+ /* Skip over entities that are not tasks */
+ do {
se = list_entry(next, struct sched_entity, group_node);
next = next->next;
+ } while (next != &cfs_rq->tasks && !entity_is_task(se));
- /* Skip over entities that are not tasks */
- if (entity_is_task(se)) {
- p = task_of(se);
- break;
- }
- }
+ if (next == &cfs_rq->tasks)
+ return NULL;
cfs_rq->balance_iterator = next;
+
+ if (entity_is_task(se))
+ p = task_of(se);
+
return p;
}
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 908c04f9dad0..998ba54b4543 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -298,7 +298,7 @@ static void __disable_runtime(struct rq *rq)
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
s64 diff;
- if (iter == rt_rq)
+ if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
continue;
spin_lock(&iter->rt_runtime_lock);
@@ -861,6 +861,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
#define RT_MAX_TRIES 3
static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
+static 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)
@@ -1022,7 +1024,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
break;
/* try again */
- spin_unlock(&lowest_rq->lock);
+ double_unlock_balance(rq, lowest_rq);
lowest_rq = NULL;
}
@@ -1091,7 +1093,7 @@ static int push_rt_task(struct rq *rq)
resched_task(lowest_rq->curr);
- spin_unlock(&lowest_rq->lock);
+ double_unlock_balance(rq, lowest_rq);
ret = 1;
out:
@@ -1197,7 +1199,7 @@ static int pull_rt_task(struct rq *this_rq)
}
skip:
- spin_unlock(&src_rq->lock);
+ double_unlock_balance(this_rq, src_rq);
}
return ret;
diff --git a/kernel/signal.c b/kernel/signal.c
index 954f77d7e3bc..c539f60c6f41 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1304,6 +1304,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
q->info.si_overrun++;
goto out;
}
+ q->info.si_overrun = 0;
signalfd_notify(t, sig);
pending = group ? &t->signal->shared_pending : &t->pending;
diff --git a/kernel/smp.c b/kernel/smp.c
index 96fc7c0edc59..782e2b93e465 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -135,7 +135,8 @@ void generic_smp_call_function_interrupt(void)
*/
smp_wmb();
data->csd.flags &= ~CSD_FLAG_WAIT;
- } else
+ }
+ if (data->csd.flags & CSD_FLAG_ALLOC)
call_rcu(&data->rcu_head, rcu_free_call_data);
}
rcu_read_unlock();
@@ -260,6 +261,42 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
generic_exec_single(cpu, data);
}
+/* Dummy function */
+static void quiesce_dummy(void *unused)
+{
+}
+
+/*
+ * Ensure stack based data used in call function mask is safe to free.
+ *
+ * This is needed by smp_call_function_mask when using on-stack data, because
+ * a single call function queue is shared by all CPUs, and any CPU may pick up
+ * the data item on the queue at any time before it is deleted. So we need to
+ * ensure that all CPUs have transitioned through a quiescent state after
+ * this call.
+ *
+ * This is a very slow function, implemented by sending synchronous IPIs to
+ * all possible CPUs. For this reason, we have to alloc data rather than use
+ * stack based data even in the case of synchronous calls. The stack based
+ * data is then just used for deadlock/oom fallback which will be very rare.
+ *
+ * If a faster scheme can be made, we could go back to preferring stack based
+ * data -- the data allocation/free is non-zero cost.
+ */
+static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
+{
+ struct call_single_data data;
+ int cpu;
+
+ data.func = quiesce_dummy;
+ data.info = NULL;
+
+ for_each_cpu_mask(cpu, mask) {
+ data.flags = CSD_FLAG_WAIT;
+ generic_exec_single(cpu, &data);
+ }
+}
+
/**
* smp_call_function_mask(): Run a function on a set of other CPUs.
* @mask: The set of cpus to run on.
@@ -285,6 +322,7 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
cpumask_t allbutself;
unsigned long flags;
int cpu, num_cpus;
+ int slowpath = 0;
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
@@ -306,15 +344,16 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
return smp_call_function_single(cpu, func, info, wait);
}
- if (!wait) {
- data = kmalloc(sizeof(*data), GFP_ATOMIC);
- if (data)
- data->csd.flags = CSD_FLAG_ALLOC;
- }
- if (!data) {
+ data = kmalloc(sizeof(*data), GFP_ATOMIC);
+ if (data) {
+ data->csd.flags = CSD_FLAG_ALLOC;
+ if (wait)
+ data->csd.flags |= CSD_FLAG_WAIT;
+ } else {
data = &d;
data->csd.flags = CSD_FLAG_WAIT;
wait = 1;
+ slowpath = 1;
}
spin_lock_init(&data->lock);
@@ -331,8 +370,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
arch_send_call_function_ipi(mask);
/* optionally wait for the CPUs to complete */
- if (wait)
+ if (wait) {
csd_flag_wait(&data->csd);
+ if (unlikely(slowpath))
+ smp_call_function_mask_quiesce_stack(mask);
+ }
return 0;
}
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index a1fb54c93cdd..29ab20749dd3 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -290,8 +290,8 @@ void __lockfunc _spin_lock_nested(spinlock_t *lock, int subclass)
spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
}
-
EXPORT_SYMBOL(_spin_lock_nested);
+
unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclass)
{
unsigned long flags;
@@ -311,9 +311,17 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
#endif
return flags;
}
-
EXPORT_SYMBOL(_spin_lock_irqsave_nested);
+void __lockfunc _spin_lock_nest_lock(spinlock_t *lock,
+ struct lockdep_map *nest_lock)
+{
+ preempt_disable();
+ spin_acquire_nest(&lock->dep_map, 0, 0, nest_lock, _RET_IP_);
+ LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
+}
+EXPORT_SYMBOL(_spin_lock_nest_lock);
+
#endif
void __lockfunc _spin_unlock(spinlock_t *lock)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e446c7c7d6a9..af3c7cea258b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -65,7 +65,6 @@ static void ack_state(void)
static int stop_cpu(struct stop_machine_data *smdata)
{
enum stopmachine_state curstate = STOPMACHINE_NONE;
- int uninitialized_var(ret);
/* Simple state machine */
do {
diff --git a/kernel/sys.c b/kernel/sys.c
index c01858090a98..3dacb00a7f76 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -274,7 +274,7 @@ void emergency_restart(void)
}
EXPORT_SYMBOL_GPL(emergency_restart);
-static void kernel_restart_prepare(char *cmd)
+void kernel_restart_prepare(char *cmd)
{
blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
system_state = SYSTEM_RESTART;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 825b4c00fe44..f5da526424a9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -289,7 +289,6 @@ void tick_nohz_stop_sched_tick(int inidle)
ts->tick_stopped = 1;
ts->idle_jiffies = last_jiffies;
rcu_enter_nohz();
- sched_clock_tick_stop(cpu);
}
/*
@@ -392,7 +391,6 @@ void tick_nohz_restart_sched_tick(void)
select_nohz_load_balancer(0);
now = ktime_get();
tick_do_update_jiffies64(now);
- sched_clock_tick_start(cpu);
cpu_clear(cpu, nohz_cpu_mask);
/*
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4a26a1382df0..4048e92aa04f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -290,11 +290,11 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
BUG_ON(get_wq_data(work) != cwq);
work_clear_pending(work);
- lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
- lock_acquire(&lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+ lock_map_acquire(&cwq->wq->lockdep_map);
+ lock_map_acquire(&lockdep_map);
f(work);
- lock_release(&lockdep_map, 1, _THIS_IP_);
- lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+ lock_map_release(&lockdep_map);
+ lock_map_release(&cwq->wq->lockdep_map);
if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
printk(KERN_ERR "BUG: workqueue leaked lock or atomic: "
@@ -413,8 +413,8 @@ void flush_workqueue(struct workqueue_struct *wq)
int cpu;
might_sleep();
- lock_acquire(&wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
- lock_release(&wq->lockdep_map, 1, _THIS_IP_);
+ lock_map_acquire(&wq->lockdep_map);
+ lock_map_release(&wq->lockdep_map);
for_each_cpu_mask_nr(cpu, *cpu_map)
flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
@@ -441,8 +441,8 @@ int flush_work(struct work_struct *work)
if (!cwq)
return 0;
- lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
- lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+ lock_map_acquire(&cwq->wq->lockdep_map);
+ lock_map_release(&cwq->wq->lockdep_map);
prev = NULL;
spin_lock_irq(&cwq->lock);
@@ -536,8 +536,8 @@ static void wait_on_work(struct work_struct *work)
might_sleep();
- lock_acquire(&work->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
- lock_release(&work->lockdep_map, 1, _THIS_IP_);
+ lock_map_acquire(&work->lockdep_map);
+ lock_map_release(&work->lockdep_map);
cwq = get_wq_data(work);
if (!cwq)
@@ -872,8 +872,8 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
if (cwq->thread == NULL)
return;
- lock_acquire(&cwq->wq->lockdep_map, 0, 0, 0, 2, _THIS_IP_);
- lock_release(&cwq->wq->lockdep_map, 1, _THIS_IP_);
+ lock_map_acquire(&cwq->wq->lockdep_map);
+ lock_map_release(&cwq->wq->lockdep_map);
flush_cpu_workqueue(cwq);
/*
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-15 12:21:17 +0000