Merge commit 'v2.6.28-rc2' into core/locking
Conflicts:
arch/um/include/asm/system.h
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 4ba4664..9cb9138 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -71,35 +71,50 @@
# less /proc/lock_stat
-01 lock_stat version 0.2
+01 lock_stat version 0.3
02 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
03 class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total
04 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
05
-06 &inode->i_data.tree_lock-W: 15 21657 0.18 1093295.30 11547131054.85 58 10415 0.16 87.51 6387.60
-07 &inode->i_data.tree_lock-R: 0 0 0.00 0.00 0.00 23302 231198 0.25 8.45 98023.38
-08 --------------------------
-09 &inode->i_data.tree_lock 0 [<ffffffff8027c08f>] add_to_page_cache+0x5f/0x190
-10
-11 ...............................................................................................................................................................................................
-12
-13 dcache_lock: 1037 1161 0.38 45.32 774.51 6611 243371 0.15 306.48 77387.24
-14 -----------
-15 dcache_lock 180 [<ffffffff802c0d7e>] sys_getcwd+0x11e/0x230
-16 dcache_lock 165 [<ffffffff802c002a>] d_alloc+0x15a/0x210
-17 dcache_lock 33 [<ffffffff8035818d>] _atomic_dec_and_lock+0x4d/0x70
-18 dcache_lock 1 [<ffffffff802beef8>] shrink_dcache_parent+0x18/0x130
+06 &mm->mmap_sem-W: 233 538 18446744073708 22924.27 607243.51 1342 45806 1.71 8595.89 1180582.34
+07 &mm->mmap_sem-R: 205 587 18446744073708 28403.36 731975.00 1940 412426 0.58 187825.45 6307502.88
+08 ---------------
+09 &mm->mmap_sem 487 [<ffffffff8053491f>] do_page_fault+0x466/0x928
+10 &mm->mmap_sem 179 [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+11 &mm->mmap_sem 279 [<ffffffff80210a57>] sys_mmap+0x75/0xce
+12 &mm->mmap_sem 76 [<ffffffff802a490b>] sys_munmap+0x32/0x59
+13 ---------------
+14 &mm->mmap_sem 270 [<ffffffff80210a57>] sys_mmap+0x75/0xce
+15 &mm->mmap_sem 431 [<ffffffff8053491f>] do_page_fault+0x466/0x928
+16 &mm->mmap_sem 138 [<ffffffff802a490b>] sys_munmap+0x32/0x59
+17 &mm->mmap_sem 145 [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+18
+19 ...............................................................................................................................................................................................
+20
+21 dcache_lock: 621 623 0.52 118.26 1053.02 6745 91930 0.29 316.29 118423.41
+22 -----------
+23 dcache_lock 179 [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+24 dcache_lock 113 [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+25 dcache_lock 99 [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+26 dcache_lock 104 [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
+27 -----------
+28 dcache_lock 192 [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+29 dcache_lock 98 [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+30 dcache_lock 72 [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+31 dcache_lock 112 [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
This excerpt shows the first two lock class statistics. Line 01 shows the
output version - each time the format changes this will be updated. Line 02-04
-show the header with column descriptions. Lines 05-10 and 13-18 show the actual
+show the header with column descriptions. Lines 05-18 and 20-31 show the actual
statistics. These statistics come in two parts; the actual stats separated by a
-short separator (line 08, 14) from the contention points.
+short separator (line 08, 13) from the contention points.
-The first lock (05-10) is a read/write lock, and shows two lines above the
+The first lock (05-18) is a read/write lock, and shows two lines above the
short separator. The contention points don't match the column descriptors,
-they have two: contentions and [<IP>] symbol.
+they have two: contentions and [<IP>] symbol. The second set of contention
+points are the points we're contending with.
+The integer part of the time values is in us.
View the top contending locks:
diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h
index 753346e..ae5f94d 100644
--- a/arch/um/include/asm/system.h
+++ b/arch/um/include/asm/system.h
@@ -11,21 +11,21 @@
extern void block_signals(void);
extern void unblock_signals(void);
-#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_save_flags(flags) do { typecheck(unsigned long, flags); \
(flags) = get_signals(); } while(0)
-#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_irq_restore(flags) do { typecheck(unsigned long, flags); \
set_signals(flags); } while(0)
-#define local_irq_save(flags) do { local_save_flags(flags); \
- local_irq_disable(); } while(0)
+#define raw_local_irq_save(flags) do { raw_local_save_flags(flags); \
+ raw_local_irq_disable(); } while(0)
-#define local_irq_enable() unblock_signals()
-#define local_irq_disable() block_signals()
+#define raw_local_irq_enable() unblock_signals()
+#define raw_local_irq_disable() block_signals()
#define irqs_disabled() \
({ \
unsigned long flags; \
- local_save_flags(flags); \
+ raw_local_save_flags(flags); \
(flags == 0); \
})
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35c5492..99192bb 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -157,6 +157,7 @@
int __ret_gu; \
unsigned long __val_gu; \
__chk_user_ptr(ptr); \
+ might_fault(); \
switch (sizeof(*(ptr))) { \
case 1: \
__get_user_x(1, __ret_gu, __val_gu, ptr); \
@@ -241,6 +242,7 @@
int __ret_pu; \
__typeof__(*(ptr)) __pu_val; \
__chk_user_ptr(ptr); \
+ might_fault(); \
__pu_val = x; \
switch (sizeof(*(ptr))) { \
case 1: \
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index d095a3a..5e06259 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -82,8 +82,8 @@
static __always_inline unsigned long __must_check
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
- might_sleep();
- return __copy_to_user_inatomic(to, from, n);
+ might_fault();
+ return __copy_to_user_inatomic(to, from, n);
}
static __always_inline unsigned long
@@ -137,7 +137,7 @@
static __always_inline unsigned long
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
- might_sleep();
+ might_fault();
if (__builtin_constant_p(n)) {
unsigned long ret;
@@ -159,7 +159,7 @@
static __always_inline unsigned long __copy_from_user_nocache(void *to,
const void __user *from, unsigned long n)
{
- might_sleep();
+ might_fault();
if (__builtin_constant_p(n)) {
unsigned long ret;
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f152..543ba88 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -29,6 +29,8 @@
int __copy_from_user(void *dst, const void __user *src, unsigned size)
{
int ret = 0;
+
+ might_fault();
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
@@ -71,6 +73,8 @@
int __copy_to_user(void __user *dst, const void *src, unsigned size)
{
int ret = 0;
+
+ might_fault();
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
@@ -113,6 +117,8 @@
int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
{
int ret = 0;
+
+ might_fault();
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst,
(__force void *)src, size);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 9e68075..4a20b2f 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -39,7 +39,7 @@
#define __do_strncpy_from_user(dst, src, count, res) \
do { \
int __d0, __d1, __d2; \
- might_sleep(); \
+ might_fault(); \
__asm__ __volatile__( \
" testl %1,%1\n" \
" jz 2f\n" \
@@ -126,7 +126,7 @@
#define __do_clear_user(addr,size) \
do { \
int __d0; \
- might_sleep(); \
+ might_fault(); \
__asm__ __volatile__( \
"0: rep; stosl\n" \
" movl %2,%0\n" \
@@ -155,7 +155,7 @@
unsigned long
clear_user(void __user *to, unsigned long n)
{
- might_sleep();
+ might_fault();
if (access_ok(VERIFY_WRITE, to, n))
__do_clear_user(to, n);
return n;
@@ -197,7 +197,7 @@
unsigned long mask = -__addr_ok(s);
unsigned long res, tmp;
- might_sleep();
+ might_fault();
__asm__ __volatile__(
" testl %0, %0\n"
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index f4df6e7..64d6c84 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -15,7 +15,7 @@
#define __do_strncpy_from_user(dst,src,count,res) \
do { \
long __d0, __d1, __d2; \
- might_sleep(); \
+ might_fault(); \
__asm__ __volatile__( \
" testq %1,%1\n" \
" jz 2f\n" \
@@ -64,7 +64,7 @@
unsigned long __clear_user(void __user *addr, unsigned long size)
{
long __d0;
- might_sleep();
+ might_fault();
/* no memory constraint because it doesn't change any memory gcc knows
about */
asm volatile(
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 4aaa4af..096476f 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -17,7 +17,7 @@
({ \
int __ret = 0; \
\
- if (unlikely(c)) { \
+ if (!oops_in_progress && unlikely(c)) { \
if (debug_locks_off() && !debug_locks_silent) \
WARN_ON(1); \
__ret = 1; \
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 396a350..fa2853b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -141,6 +141,15 @@
(__x < 0) ? -__x : __x; \
})
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void);
+#else
+static inline void might_fault(void)
+{
+ might_sleep();
+}
+#endif
+
extern struct atomic_notifier_head panic_notifier_list;
extern long (*panic_blink)(long time);
NORET_TYPE void panic(const char * fmt, ...)
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 331e5f1..fc9f8e8 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -73,6 +73,8 @@
struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES];
};
+#define LOCKSTAT_POINTS 4
+
/*
* The lock-class itself:
*/
@@ -119,7 +121,8 @@
int name_version;
#ifdef CONFIG_LOCK_STAT
- unsigned long contention_point[4];
+ unsigned long contention_point[LOCKSTAT_POINTS];
+ unsigned long contending_point[LOCKSTAT_POINTS];
#endif
};
@@ -144,6 +147,7 @@
struct lock_class_stats {
unsigned long contention_point[4];
+ unsigned long contending_point[4];
struct lock_time read_waittime;
struct lock_time write_waittime;
struct lock_time read_holdtime;
@@ -165,6 +169,7 @@
const char *name;
#ifdef CONFIG_LOCK_STAT
int cpu;
+ unsigned long ip;
#endif
};
@@ -355,7 +360,7 @@
#ifdef CONFIG_LOCK_STAT
extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
-extern void lock_acquired(struct lockdep_map *lock);
+extern void lock_acquired(struct lockdep_map *lock, unsigned long ip);
#define LOCK_CONTENDED(_lock, try, lock) \
do { \
@@ -363,13 +368,13 @@
lock_contended(&(_lock)->dep_map, _RET_IP_); \
lock(_lock); \
} \
- lock_acquired(&(_lock)->dep_map); \
+ lock_acquired(&(_lock)->dep_map, _RET_IP_); \
} while (0)
#else /* CONFIG_LOCK_STAT */
#define lock_contended(lockdep_map, ip) do {} while (0)
-#define lock_acquired(lockdep_map) do {} while (0)
+#define lock_acquired(lockdep_map, ip) do {} while (0)
#define LOCK_CONTENDED(_lock, try, lock) \
lock(_lock)
@@ -480,4 +485,22 @@
# define lock_map_release(l) do { } while (0)
#endif
+#ifdef CONFIG_PROVE_LOCKING
+# define might_lock(lock) \
+do { \
+ typecheck(struct lockdep_map *, &(lock)->dep_map); \
+ lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_); \
+ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \
+} while (0)
+# define might_lock_read(lock) \
+do { \
+ typecheck(struct lockdep_map *, &(lock)->dep_map); \
+ lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_); \
+ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \
+} while (0)
+#else
+# define might_lock(lock) do { } while (0)
+# define might_lock_read(lock) do { } while (0)
+#endif
+
#endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index fec6dec..6b58367 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -78,7 +78,7 @@
\
set_fs(KERNEL_DS); \
pagefault_disable(); \
- ret = __get_user(retval, (__force typeof(retval) __user *)(addr)); \
+ ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \
pagefault_enable(); \
set_fs(old_fs); \
ret; \
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index dbda475..234a9dc 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -136,16 +136,16 @@
#ifdef CONFIG_LOCK_STAT
static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
-static int lock_contention_point(struct lock_class *class, unsigned long ip)
+static int lock_point(unsigned long points[], unsigned long ip)
{
int i;
- for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
- if (class->contention_point[i] == 0) {
- class->contention_point[i] = ip;
+ for (i = 0; i < LOCKSTAT_POINTS; i++) {
+ if (points[i] == 0) {
+ points[i] = ip;
break;
}
- if (class->contention_point[i] == ip)
+ if (points[i] == ip)
break;
}
@@ -185,6 +185,9 @@
for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
stats.contention_point[i] += pcs->contention_point[i];
+ for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
+ stats.contending_point[i] += pcs->contending_point[i];
+
lock_time_add(&pcs->read_waittime, &stats.read_waittime);
lock_time_add(&pcs->write_waittime, &stats.write_waittime);
@@ -209,6 +212,7 @@
memset(cpu_stats, 0, sizeof(struct lock_class_stats));
}
memset(class->contention_point, 0, sizeof(class->contention_point));
+ memset(class->contending_point, 0, sizeof(class->contending_point));
}
static struct lock_class_stats *get_lock_stats(struct lock_class *class)
@@ -3001,7 +3005,7 @@
struct held_lock *hlock, *prev_hlock;
struct lock_class_stats *stats;
unsigned int depth;
- int i, point;
+ int i, contention_point, contending_point;
depth = curr->lockdep_depth;
if (DEBUG_LOCKS_WARN_ON(!depth))
@@ -3025,18 +3029,22 @@
found_it:
hlock->waittime_stamp = sched_clock();
- point = lock_contention_point(hlock_class(hlock), ip);
+ contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
+ contending_point = lock_point(hlock_class(hlock)->contending_point,
+ lock->ip);
stats = get_lock_stats(hlock_class(hlock));
- if (point < ARRAY_SIZE(stats->contention_point))
- stats->contention_point[point]++;
+ if (contention_point < LOCKSTAT_POINTS)
+ stats->contention_point[contention_point]++;
+ if (contending_point < LOCKSTAT_POINTS)
+ stats->contending_point[contending_point]++;
if (lock->cpu != smp_processor_id())
stats->bounces[bounce_contended + !!hlock->read]++;
put_lock_stats(stats);
}
static void
-__lock_acquired(struct lockdep_map *lock)
+__lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
struct task_struct *curr = current;
struct held_lock *hlock, *prev_hlock;
@@ -3085,6 +3093,7 @@
put_lock_stats(stats);
lock->cpu = cpu;
+ lock->ip = ip;
}
void lock_contended(struct lockdep_map *lock, unsigned long ip)
@@ -3106,7 +3115,7 @@
}
EXPORT_SYMBOL_GPL(lock_contended);
-void lock_acquired(struct lockdep_map *lock)
+void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
@@ -3119,7 +3128,7 @@
raw_local_irq_save(flags);
check_flags(flags);
current->lockdep_recursion = 1;
- __lock_acquired(lock);
+ __lock_acquired(lock, ip);
current->lockdep_recursion = 0;
raw_local_irq_restore(flags);
}
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 20dbcbf..13716b8 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -470,11 +470,12 @@
static void snprint_time(char *buf, size_t bufsiz, s64 nr)
{
- unsigned long rem;
+ s64 div;
+ s32 rem;
nr += 5; /* for display rounding */
- rem = do_div(nr, 1000); /* XXX: do_div_signed */
- snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
+ div = div_s64_rem(nr, 1000, &rem);
+ snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
}
static void seq_time(struct seq_file *m, s64 time)
@@ -556,7 +557,7 @@
if (stats->read_holdtime.nr)
namelen += 2;
- for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+ for (i = 0; i < LOCKSTAT_POINTS; i++) {
char sym[KSYM_SYMBOL_LEN];
char ip[32];
@@ -573,6 +574,23 @@
stats->contention_point[i],
ip, sym);
}
+ for (i = 0; i < LOCKSTAT_POINTS; i++) {
+ char sym[KSYM_SYMBOL_LEN];
+ char ip[32];
+
+ if (class->contending_point[i] == 0)
+ break;
+
+ if (!i)
+ seq_line(m, '-', 40-namelen, namelen);
+
+ sprint_symbol(sym, class->contending_point[i]);
+ snprintf(ip, sizeof(ip), "[<%p>]",
+ (void *)class->contending_point[i]);
+ seq_printf(m, "%40s %14lu %29s %s\n", name,
+ stats->contending_point[i],
+ ip, sym);
+ }
if (i) {
seq_puts(m, "\n");
seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
@@ -582,7 +600,7 @@
static void seq_header(struct seq_file *m)
{
- seq_printf(m, "lock_stat version 0.2\n");
+ seq_printf(m, "lock_stat version 0.3\n");
seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
"%14s %14s\n",
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 12c779d..39a3816 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -184,7 +184,7 @@
}
done:
- lock_acquired(&lock->dep_map);
+ lock_acquired(&lock->dep_map, ip);
/* got the lock - rejoice! */
mutex_remove_waiter(lock, &waiter, task_thread_info(task));
debug_mutex_set_owner(lock, task_thread_info(task));
diff --git a/kernel/sched.c b/kernel/sched.c
index 6625c3c..0a4dc3b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4327,7 +4327,7 @@
/*
* Underflow?
*/
- if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
return;
/*
* Is the spinlock portion underflowing?
diff --git a/mm/memory.c b/mm/memory.c
index 164951c..fc031d6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3049,3 +3049,18 @@
}
up_read(¤t->mm->mmap_sem);
}
+
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void)
+{
+ might_sleep();
+ /*
+ * it would be nicer only to annotate paths which are not under
+ * pagefault_disable, however that requires a larger audit and
+ * providing helpers like get_user_atomic.
+ */
+ if (!in_atomic() && current->mm)
+ might_lock_read(¤t->mm->mmap_sem);
+}
+EXPORT_SYMBOL(might_fault);
+#endif