*/
set_ist(_vectors_start);
- lockdep_init();
-
/*
* dtb is passed in from bootloader.
* fdt is linked in blob.
memset(__bss_start, 0, __bss_stop-__bss_start);
memset(_ssbss, 0, _esbss-_ssbss);
- lockdep_init();
-
/* initialize device tree for usage in early_printk */
early_init_devtree(_fdt_start);
notrace void __init machine_init(u64 dt_ptr)
{
- lockdep_init();
-
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
setup_paca(&boot_paca);
fixup_boot_paca();
- /* Initialize lockdep early or else spinlocks will blow */
- lockdep_init();
-
/* -------- printk is now safe to use ------- */
/* Enable early debugging if any specified (see udbg.h) */
rescue_initrd();
clear_bss_section();
init_kernel_storage_key();
- lockdep_init();
lockdep_off();
setup_lowcore_early();
setup_facility_list();
call __bzero
sub %o1, %o0, %o1
-#ifdef CONFIG_LOCKDEP
- /* We have this call this super early, as even prom_init can grab
- * spinlocks and thus call into the lockdep code.
- */
- call lockdep_init
- nop
-#endif
-
call prom_init
mov %l7, %o0 ! OpenPROM cif handler
/*
* Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
+ * And yes, this might be required on UP too when we're talking
* to devices.
*/
#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+ X86_FEATURE_XMM2) ::: "memory", "cc")
#else
#define mb() asm volatile("mfence":::"memory")
#define rmb() asm volatile("lfence":::"memory")
if (!current_set_polling_and_test()) {
trace_cpu_idle_rcuidle(1, smp_processor_id());
if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
- smp_mb(); /* quirk */
+ mb(); /* quirk */
clflush((void *)¤t_thread_info()->flags);
- smp_mb(); /* quirk */
+ mb(); /* quirk */
}
__monitor((void *)¤t_thread_info()->flags, 0, 0);
*/
reserve_top_address(lguest_data.reserve_mem);
- /*
- * If we don't initialize the lock dependency checker now, it crashes
- * atomic_notifier_chain_register, then paravirt_disable_iospace.
- */
- lockdep_init();
-
/* Hook in our special panic hypercall code. */
atomic_notifier_chain_register(&panic_notifier_list, &paniced);
* In contrast to ACCESS_ONCE these two macros will also work on aggregate
* data types like structs or unions. If the size of the accessed data
* type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE() will fall back to memcpy and print a
- * compile-time warning.
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
+ * least two memcpy()s: one for the __builtin_memcpy() and then one for
+ * the macro doing the copy of variable - '__u' allocated on the stack.
*
* Their two major use cases are: (1) Mediating communication between
* process-level code and irq/NMI handlers, all running on the same CPU,
/*
* Initialization, self-test and debugging-output methods:
*/
-extern void lockdep_init(void);
extern void lockdep_info(void);
extern void lockdep_reset(void);
extern void lockdep_reset_lock(struct lockdep_map *lock);
# define lockdep_set_current_reclaim_state(g) do { } while (0)
# define lockdep_clear_current_reclaim_state() do { } while (0)
# define lockdep_trace_alloc(g) do { } while (0)
-# define lockdep_init() do { } while (0)
# define lockdep_info() do { } while (0)
# define lockdep_init_map(lock, name, key, sub) \
do { (void)(name); (void)(key); } while (0)
char *command_line;
char *after_dashes;
- /*
- * Need to run as early as possible, to initialize the
- * lockdep hash:
- */
- lockdep_init();
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
* futex_wait(futex, val);
*
* waiters++; (a)
- * mb(); (A) <-- paired with -.
- * |
- * lock(hash_bucket(futex)); |
- * |
- * uval = *futex; |
- * | *futex = newval;
- * | sys_futex(WAKE, futex);
- * | futex_wake(futex);
- * |
- * `-------> mb(); (B)
+ * smp_mb(); (A) <-- paired with -.
+ * |
+ * lock(hash_bucket(futex)); |
+ * |
+ * uval = *futex; |
+ * | *futex = newval;
+ * | sys_futex(WAKE, futex);
+ * | futex_wake(futex);
+ * |
+ * `--------> smp_mb(); (B)
* if (uval == val)
* queue();
* unlock(hash_bucket(futex));
/*
* Ensure futex_get_mm() implies a full barrier such that
* get_futex_key() implies a full barrier. This is relied upon
- * as full barrier (B), see the ordering comment above.
+ * as smp_mb(); (B), see the ordering comment above.
*/
smp_mb__after_atomic();
}
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
- ihold(key->shared.inode); /* implies MB (B) */
+ ihold(key->shared.inode); /* implies smp_mb(); (B) */
break;
case FUT_OFF_MMSHARED:
- futex_get_mm(key); /* implies MB (B) */
+ futex_get_mm(key); /* implies smp_mb(); (B) */
break;
default:
/*
* mm, therefore the only purpose of calling get_futex_key_refs
* is because we need the barrier for the lockless waiter check.
*/
- smp_mb(); /* explicit MB (B) */
+ smp_mb(); /* explicit smp_mb(); (B) */
}
}
if (!fshared) {
key->private.mm = mm;
key->private.address = address;
- get_futex_key_refs(key); /* implies MB (B) */
+ get_futex_key_refs(key); /* implies smp_mb(); (B) */
return 0;
}
else
err = 0;
- lock_page(page);
+ /*
+ * The treatment of mapping from this point on is critical. The page
+ * lock protects many things but in this context the page lock
+ * stabilizes mapping, prevents inode freeing in the shared
+ * file-backed region case and guards against movement to swap cache.
+ *
+ * Strictly speaking the page lock is not needed in all cases being
+ * considered here and page lock forces unnecessarily serialization
+ * From this point on, mapping will be re-verified if necessary and
+ * page lock will be acquired only if it is unavoidable
+ */
+ page = compound_head(page);
+ mapping = READ_ONCE(page->mapping);
+
/*
* If page->mapping is NULL, then it cannot be a PageAnon
* page; but it might be the ZERO_PAGE or in the gate area or
* shmem_writepage move it from filecache to swapcache beneath us:
* an unlikely race, but we do need to retry for page->mapping.
*/
- mapping = compound_head(page)->mapping;
- if (!mapping) {
- int shmem_swizzled = PageSwapCache(page);
+ if (unlikely(!mapping)) {
+ int shmem_swizzled;
+
+ /*
+ * Page lock is required to identify which special case above
+ * applies. If this is really a shmem page then the page lock
+ * will prevent unexpected transitions.
+ */
+ lock_page(page);
+ shmem_swizzled = PageSwapCache(page) || page->mapping;
unlock_page(page);
put_page(page);
+
if (shmem_swizzled)
goto again;
+
return -EFAULT;
}
/*
* Private mappings are handled in a simple way.
*
+ * If the futex key is stored on an anonymous page, then the associated
+ * object is the mm which is implicitly pinned by the calling process.
+ *
* NOTE: When userspace waits on a MAP_SHARED mapping, even if
* it's a read-only handle, it's expected that futexes attach to
* the object not the particular process.
key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
key->private.mm = mm;
key->private.address = address;
+
+ get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
} else {
+ struct inode *inode;
+
+ /*
+ * The associated futex object in this case is the inode and
+ * the page->mapping must be traversed. Ordinarily this should
+ * be stabilised under page lock but it's not strictly
+ * necessary in this case as we just want to pin the inode, not
+ * update the radix tree or anything like that.
+ *
+ * The RCU read lock is taken as the inode is finally freed
+ * under RCU. If the mapping still matches expectations then the
+ * mapping->host can be safely accessed as being a valid inode.
+ */
+ rcu_read_lock();
+
+ if (READ_ONCE(page->mapping) != mapping) {
+ rcu_read_unlock();
+ put_page(page);
+
+ goto again;
+ }
+
+ inode = READ_ONCE(mapping->host);
+ if (!inode) {
+ rcu_read_unlock();
+ put_page(page);
+
+ goto again;
+ }
+
+ /*
+ * Take a reference unless it is about to be freed. Previously
+ * this reference was taken by ihold under the page lock
+ * pinning the inode in place so i_lock was unnecessary. The
+ * only way for this check to fail is if the inode was
+ * truncated in parallel so warn for now if this happens.
+ *
+ * We are not calling into get_futex_key_refs() in file-backed
+ * cases, therefore a successful atomic_inc return below will
+ * guarantee that get_futex_key() will still imply smp_mb(); (B).
+ */
+ if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+ rcu_read_unlock();
+ put_page(page);
+
+ goto again;
+ }
+
+ /* Should be impossible but lets be paranoid for now */
+ if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
+ err = -EFAULT;
+ rcu_read_unlock();
+ iput(inode);
+
+ goto out;
+ }
+
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
- key->shared.inode = mapping->host;
+ key->shared.inode = inode;
key->shared.pgoff = basepage_index(page);
+ rcu_read_unlock();
}
- get_futex_key_refs(key); /* implies MB (B) */
-
out:
- unlock_page(page);
put_page(page);
return err;
}
q->lock_ptr = &hb->lock;
- spin_lock(&hb->lock); /* implies MB (A) */
+ spin_lock(&hb->lock); /* implies smp_mb(); (A) */
return hb;
}
return ret;
}
-static int lockdep_initialized;
-
unsigned long nr_list_entries;
static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
unsigned int max_lockdep_depth;
#ifdef CONFIG_DEBUG_LOCKDEP
-/*
- * We cannot printk in early bootup code. Not even early_printk()
- * might work. So we mark any initialization errors and printk
- * about it later on, in lockdep_info().
- */
-static int lockdep_init_error;
-static const char *lock_init_error;
-static unsigned long lockdep_init_trace_data[20];
-static struct stack_trace lockdep_init_trace = {
- .max_entries = ARRAY_SIZE(lockdep_init_trace_data),
- .entries = lockdep_init_trace_data,
-};
-
/*
* Various lockdep statistics:
*/
struct hlist_head *hash_head;
struct lock_class *class;
-#ifdef CONFIG_DEBUG_LOCKDEP
- /*
- * If the architecture calls into lockdep before initializing
- * the hashes then we'll warn about it later. (we cannot printk
- * right now)
- */
- if (unlikely(!lockdep_initialized)) {
- lockdep_init();
- lockdep_init_error = 1;
- lock_init_error = lock->name;
- save_stack_trace(&lockdep_init_trace);
- }
-#endif
-
if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
debug_locks_off();
printk(KERN_ERR
raw_local_irq_restore(flags);
}
-void lockdep_init(void)
-{
- int i;
-
- /*
- * Some architectures have their own start_kernel()
- * code which calls lockdep_init(), while we also
- * call lockdep_init() from the start_kernel() itself,
- * and we want to initialize the hashes only once:
- */
- if (lockdep_initialized)
- return;
-
- for (i = 0; i < CLASSHASH_SIZE; i++)
- INIT_HLIST_HEAD(classhash_table + i);
-
- for (i = 0; i < CHAINHASH_SIZE; i++)
- INIT_HLIST_HEAD(chainhash_table + i);
-
- lockdep_initialized = 1;
-}
-
void __init lockdep_info(void)
{
printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
printk(" per task-struct memory footprint: %lu bytes\n",
sizeof(struct held_lock) * MAX_LOCK_DEPTH);
-
-#ifdef CONFIG_DEBUG_LOCKDEP
- if (lockdep_init_error) {
- printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error);
- printk("Call stack leading to lockdep invocation was:\n");
- print_stack_trace(&lockdep_init_trace, 0);
- }
-#endif
}
static void
bool (*test_key)(void);
};
-#define test_key_func(key, branch) \
- ({bool func(void) { return branch(key); } func; })
+#define test_key_func(key, branch) \
+static bool key ## _ ## branch(void) \
+{ \
+ return branch(&key); \
+}
static void invert_key(struct static_key *key)
{
return 0;
}
+test_key_func(old_true_key, static_key_true)
+test_key_func(old_false_key, static_key_false)
+test_key_func(true_key, static_branch_likely)
+test_key_func(true_key, static_branch_unlikely)
+test_key_func(false_key, static_branch_likely)
+test_key_func(false_key, static_branch_unlikely)
+test_key_func(base_old_true_key, static_key_true)
+test_key_func(base_inv_old_true_key, static_key_true)
+test_key_func(base_old_false_key, static_key_false)
+test_key_func(base_inv_old_false_key, static_key_false)
+test_key_func(base_true_key, static_branch_likely)
+test_key_func(base_true_key, static_branch_unlikely)
+test_key_func(base_inv_true_key, static_branch_likely)
+test_key_func(base_inv_true_key, static_branch_unlikely)
+test_key_func(base_false_key, static_branch_likely)
+test_key_func(base_false_key, static_branch_unlikely)
+test_key_func(base_inv_false_key, static_branch_likely)
+test_key_func(base_inv_false_key, static_branch_unlikely)
+
static int __init test_static_key_init(void)
{
int ret;
{
.init_state = true,
.key = &old_true_key,
- .test_key = test_key_func(&old_true_key, static_key_true),
+ .test_key = &old_true_key_static_key_true,
},
{
.init_state = false,
.key = &old_false_key,
- .test_key = test_key_func(&old_false_key, static_key_false),
+ .test_key = &old_false_key_static_key_false,
},
/* internal keys - new keys */
{
.init_state = true,
.key = &true_key.key,
- .test_key = test_key_func(&true_key, static_branch_likely),
+ .test_key = &true_key_static_branch_likely,
},
{
.init_state = true,
.key = &true_key.key,
- .test_key = test_key_func(&true_key, static_branch_unlikely),
+ .test_key = &true_key_static_branch_unlikely,
},
{
.init_state = false,
.key = &false_key.key,
- .test_key = test_key_func(&false_key, static_branch_likely),
+ .test_key = &false_key_static_branch_likely,
},
{
.init_state = false,
.key = &false_key.key,
- .test_key = test_key_func(&false_key, static_branch_unlikely),
+ .test_key = &false_key_static_branch_unlikely,
},
/* external keys - old keys */
{
.init_state = true,
.key = &base_old_true_key,
- .test_key = test_key_func(&base_old_true_key, static_key_true),
+ .test_key = &base_old_true_key_static_key_true,
},
{
.init_state = false,
.key = &base_inv_old_true_key,
- .test_key = test_key_func(&base_inv_old_true_key, static_key_true),
+ .test_key = &base_inv_old_true_key_static_key_true,
},
{
.init_state = false,
.key = &base_old_false_key,
- .test_key = test_key_func(&base_old_false_key, static_key_false),
+ .test_key = &base_old_false_key_static_key_false,
},
{
.init_state = true,
.key = &base_inv_old_false_key,
- .test_key = test_key_func(&base_inv_old_false_key, static_key_false),
+ .test_key = &base_inv_old_false_key_static_key_false,
},
/* external keys - new keys */
{
.init_state = true,
.key = &base_true_key.key,
- .test_key = test_key_func(&base_true_key, static_branch_likely),
+ .test_key = &base_true_key_static_branch_likely,
},
{
.init_state = true,
.key = &base_true_key.key,
- .test_key = test_key_func(&base_true_key, static_branch_unlikely),
+ .test_key = &base_true_key_static_branch_unlikely,
},
{
.init_state = false,
.key = &base_inv_true_key.key,
- .test_key = test_key_func(&base_inv_true_key, static_branch_likely),
+ .test_key = &base_inv_true_key_static_branch_likely,
},
{
.init_state = false,
.key = &base_inv_true_key.key,
- .test_key = test_key_func(&base_inv_true_key, static_branch_unlikely),
+ .test_key = &base_inv_true_key_static_branch_unlikely,
},
{
.init_state = false,
.key = &base_false_key.key,
- .test_key = test_key_func(&base_false_key, static_branch_likely),
+ .test_key = &base_false_key_static_branch_likely,
},
{
.init_state = false,
.key = &base_false_key.key,
- .test_key = test_key_func(&base_false_key, static_branch_unlikely),
+ .test_key = &base_false_key_static_branch_unlikely,
},
{
.init_state = true,
.key = &base_inv_false_key.key,
- .test_key = test_key_func(&base_inv_false_key, static_branch_likely),
+ .test_key = &base_inv_false_key_static_branch_likely,
},
{
.init_state = true,
.key = &base_inv_false_key.key,
- .test_key = test_key_func(&base_inv_false_key, static_branch_unlikely),
+ .test_key = &base_inv_false_key_static_branch_unlikely,
},
};
bool debug_locks = true;
bool debug_locks_silent;
-__attribute__((constructor)) static void liblockdep_init(void)
-{
- lockdep_init();
-}
-
__attribute__((destructor)) static void liblockdep_exit(void)
{
debug_check_no_locks_held();
void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip);
extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void lockdep_init(void);
#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
{ .name = (_name), .key = (void *)(_key), }
ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
#endif
- lockdep_init();
-
__init_state = done;
}