* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
locking: Make sparse work with inline spinlocks and rwlocks
x86/mce: Fix RCU lockdep splats
rcu: Increase RCU CPU stall timeouts if PROVE_RCU
ftrace: Replace read_barrier_depends() with rcu_dereference_raw()
rcu: Suppress RCU lockdep warnings during early boot
rcu, ftrace: Fix RCU lockdep splat in ftrace_perf_buf_prepare()
rcu: Suppress __mpol_dup() false positive from RCU lockdep
rcu: Make rcu_read_lock_sched_held() handle !PREEMPT
rcu: Add control variables to lockdep_rcu_dereference() diagnostics
rcu, cgroup: Relax the check in task_subsys_state() as early boot is now handled by lockdep-RCU
rcu: Use wrapper function instead of exporting tasklist_lock
sched, rcu: Fix rcu_dereference() for RCU-lockdep
rcu: Make task_subsys_state() RCU-lockdep checks handle boot-time use
rcu: Fix holdoff for accelerated GPs for last non-dynticked CPU
x86/gart: Unexport gart_iommu_aperture
Fix trivial conflicts in kernel/trace/ftrace.c
#include "mce-internal.h"
+ #define rcu_dereference_check_mce(p) \
+ rcu_dereference_check((p), \
+ rcu_read_lock_sched_held() || \
+ lockdep_is_held(&mce_read_mutex))
+
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
mce->finished = 0;
wmb();
for (;;) {
- entry = rcu_dereference(mcelog.next);
+ entry = rcu_dereference_check_mce(mcelog.next);
for (;;) {
/*
* When the buffer fills up discard new entries.
return -ENOMEM;
mutex_lock(&mce_read_mutex);
- next = rcu_dereference(mcelog.next);
+ next = rcu_dereference_check_mce(mcelog.next);
/* Only supports full reads right now */
if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
static unsigned int mce_poll(struct file *file, poll_table *wait)
{
poll_wait(file, &mce_wait, wait);
- if (rcu_dereference(mcelog.next))
+ if (rcu_dereference_check_mce(mcelog.next))
return POLLIN | POLLRDNORM;
return 0;
}
struct mce_bank *b = &mce_banks[i];
struct sysdev_attribute *a = &b->attr;
+ sysfs_attr_init(&a->attr);
a->attr.name = b->attrname;
snprintf(b->attrname, ATTR_LEN, "bank%d", i);
#include <linux/lockdep.h>
#include <linux/completion.h>
+#ifdef CONFIG_RCU_TORTURE_TEST
+extern int rcutorture_runnable; /* for sysctl */
+#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+
/**
* struct rcu_head - callback structure for use with RCU
* @next: next update requests in a list
# define rcu_read_release_sched() \
lock_release(&rcu_sched_lock_map, 1, _THIS_IP_)
+ static inline int debug_lockdep_rcu_enabled(void)
+ {
+ return likely(rcu_scheduler_active && debug_locks);
+ }
+
/**
* rcu_read_lock_held - might we be in RCU read-side critical section?
*
* an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING,
* this assumes we are in an RCU read-side critical section unless it can
* prove otherwise.
+ *
+ * Check rcu_scheduler_active to prevent false positives during boot.
*/
static inline int rcu_read_lock_held(void)
{
- if (debug_locks)
- return lock_is_held(&rcu_lock_map);
- return 1;
+ if (!debug_lockdep_rcu_enabled())
+ return 1;
+ return lock_is_held(&rcu_lock_map);
}
/**
* an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING,
* this assumes we are in an RCU-bh read-side critical section unless it can
* prove otherwise.
+ *
+ * Check rcu_scheduler_active to prevent false positives during boot.
*/
static inline int rcu_read_lock_bh_held(void)
{
- if (debug_locks)
- return lock_is_held(&rcu_bh_lock_map);
- return 1;
+ if (!debug_lockdep_rcu_enabled())
+ return 1;
+ return lock_is_held(&rcu_bh_lock_map);
}
/**
* this assumes we are in an RCU-sched read-side critical section unless it
* can prove otherwise. Note that disabling of preemption (including
* disabling irqs) counts as an RCU-sched read-side critical section.
+ *
+ * Check rcu_scheduler_active to prevent false positives during boot.
*/
+ #ifdef CONFIG_PREEMPT
static inline int rcu_read_lock_sched_held(void)
{
int lockdep_opinion = 0;
+ if (!debug_lockdep_rcu_enabled())
+ return 1;
if (debug_locks)
lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
- return lockdep_opinion || preempt_count() != 0 || !rcu_scheduler_active;
+ return lockdep_opinion || preempt_count() != 0;
+ }
+ #else /* #ifdef CONFIG_PREEMPT */
+ static inline int rcu_read_lock_sched_held(void)
+ {
+ return 1;
}
+ #endif /* #else #ifdef CONFIG_PREEMPT */
#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
return 1;
}
+ #ifdef CONFIG_PREEMPT
static inline int rcu_read_lock_sched_held(void)
{
- return preempt_count() != 0 || !rcu_scheduler_active;
+ return !rcu_scheduler_active || preempt_count() != 0;
+ }
+ #else /* #ifdef CONFIG_PREEMPT */
+ static inline int rcu_read_lock_sched_held(void)
+ {
+ return 1;
}
+ #endif /* #else #ifdef CONFIG_PREEMPT */
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
*/
#define rcu_dereference_check(p, c) \
({ \
- if (debug_locks && !(c)) \
+ if (debug_lockdep_rcu_enabled() && !(c)) \
lockdep_rcu_dereference(__FILE__, __LINE__); \
rcu_dereference_raw(p); \
})
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
-struct bio;
+struct bio_list;
struct fs_struct;
struct bts_context;
struct perf_event_context;
struct task_struct;
+ #ifdef CONFIG_PROVE_RCU
+ extern int lockdep_tasklist_lock_is_held(void);
+ #endif /* #ifdef CONFIG_PROVE_RCU */
+
extern void sched_init(void);
extern void sched_init_smp(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
-#if USE_SPLIT_PTLOCKS
-/*
- * The mm counters are not protected by its page_table_lock,
- * so must be incremented atomically.
- */
-#define set_mm_counter(mm, member, value) atomic_long_set(&(mm)->_##member, value)
-#define get_mm_counter(mm, member) ((unsigned long)atomic_long_read(&(mm)->_##member))
-#define add_mm_counter(mm, member, value) atomic_long_add(value, &(mm)->_##member)
-#define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
-#define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
-
-#else /* !USE_SPLIT_PTLOCKS */
-/*
- * The mm counters are protected by its page_table_lock,
- * so can be incremented directly.
- */
-#define set_mm_counter(mm, member, value) (mm)->_##member = (value)
-#define get_mm_counter(mm, member) ((mm)->_##member)
-#define add_mm_counter(mm, member, value) (mm)->_##member += (value)
-#define inc_mm_counter(mm, member) (mm)->_##member++
-#define dec_mm_counter(mm, member) (mm)->_##member--
-
-#endif /* !USE_SPLIT_PTLOCKS */
-
-#define get_mm_rss(mm) \
- (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
-#define update_hiwater_rss(mm) do { \
- unsigned long _rss = get_mm_rss(mm); \
- if ((mm)->hiwater_rss < _rss) \
- (mm)->hiwater_rss = _rss; \
-} while (0)
-#define update_hiwater_vm(mm) do { \
- if ((mm)->hiwater_vm < (mm)->total_vm) \
- (mm)->hiwater_vm = (mm)->total_vm; \
-} while (0)
-
-static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
-{
- return max(mm->hiwater_rss, get_mm_rss(mm));
-}
-
-static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
- struct mm_struct *mm)
-{
- unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
-
- if (*maxrss < hiwater_rss)
- *maxrss = hiwater_rss;
-}
-
-static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
-{
- return max(mm->hiwater_vm, mm->total_vm);
-}
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
struct plist_node pushable_tasks;
struct mm_struct *mm, *active_mm;
-
+#if defined(SPLIT_RSS_COUNTING)
+ struct task_rss_stat rss_stat;
+#endif
/* task state */
int exit_state;
int exit_code, exit_signal;
void *journal_info;
/* stacked block device info */
- struct bio *bio_list, **bio_tail;
+ struct bio_list *bio_list;
/* VM state */
struct reclaim_state *reclaim_state;
struct list_head *scm_work_list;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- /* Index of current stored adress in ret_stack */
+ /* Index of current stored address in ret_stack */
int curr_ret_stack;
/* Stack of return addresses for return function tracing */
struct ftrace_ret_stack *ret_stack;
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
- sig->cputimer.cputime = INIT_CPUTIME;
spin_lock_init(&sig->cputimer.lock);
- sig->cputimer.running = 0;
}
static inline void thread_group_cputime_free(struct signal_struct *sig)
sighand = rcu_dereference_check(tsk->sighand,
rcu_read_lock_held() ||
- lockdep_is_held(&tasklist_lock));
+ lockdep_tasklist_lock_is_held());
spin_lock(&sighand->siglock);
posix_cpu_timers_exit(tsk);
preempt_count());
acct_update_integrals(tsk);
-
+ /* sync mm's RSS info before statistics gathering */
+ sync_mm_rss(tsk, tsk->mm);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
- int why, status;
+ int why;
get_task_struct(p);
read_unlock(&tasklist_lock);
DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
- EXPORT_SYMBOL_GPL(tasklist_lock);
+
+ #ifdef CONFIG_PROVE_RCU
+ int lockdep_tasklist_lock_is_held(void)
+ {
+ return lockdep_is_held(&tasklist_lock);
+ }
+ EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
+ #endif /* #ifdef CONFIG_PROVE_RCU */
int nr_processes(void)
{
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
+ INIT_LIST_HEAD(&tmp->anon_vma_chain);
pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
vma_set_policy(tmp, pol);
+ if (anon_vma_fork(tmp, mpnt))
+ goto fail_nomem_anon_vma_fork;
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
- anon_vma_link(tmp);
file = tmp->vm_file;
if (file) {
struct inode *inode = file->f_path.dentry->d_inode;
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
return retval;
+fail_nomem_anon_vma_fork:
+ mpol_put(pol);
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
- set_mm_counter(mm, file_rss, 0);
- set_mm_counter(mm, anon_rss, 0);
+ memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
*/
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
+ unsigned long cpu_limit;
+
/* Thread group counters. */
thread_group_cputime_init(sig);
- /* Expiration times and increments. */
- sig->it[CPUCLOCK_PROF].expires = cputime_zero;
- sig->it[CPUCLOCK_PROF].incr = cputime_zero;
- sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
- sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
-
- /* Cached expiration times. */
- sig->cputime_expires.prof_exp = cputime_zero;
- sig->cputime_expires.virt_exp = cputime_zero;
- sig->cputime_expires.sched_exp = 0;
-
- if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
- sig->cputime_expires.prof_exp =
- secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+ cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ if (cpu_limit != RLIM_INFINITY) {
+ sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
sig->cputimer.running = 1;
}
if (clone_flags & CLONE_THREAD)
return 0;
- sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+ sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
tsk->signal = sig;
if (!sig)
return -ENOMEM;
atomic_set(&sig->count, 1);
atomic_set(&sig->live, 1);
init_waitqueue_head(&sig->wait_chldexit);
- sig->flags = 0;
if (clone_flags & CLONE_NEWPID)
sig->flags |= SIGNAL_UNKILLABLE;
- sig->group_exit_code = 0;
- sig->group_exit_task = NULL;
- sig->group_stop_count = 0;
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
INIT_LIST_HEAD(&sig->posix_timers);
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- sig->it_real_incr.tv64 = 0;
sig->real_timer.function = it_real_fn;
- sig->leader = 0; /* session leadership doesn't inherit */
- sig->tty_old_pgrp = NULL;
- sig->tty = NULL;
-
- sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
- sig->gtime = cputime_zero;
- sig->cgtime = cputime_zero;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
- sig->prev_utime = sig->prev_stime = cputime_zero;
-#endif
- sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
- sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
- sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
- sig->maxrss = sig->cmaxrss = 0;
- task_io_accounting_init(&sig->ioac);
- sig->sum_sched_runtime = 0;
- taskstats_tgid_init(sig);
-
task_lock(current->group_leader);
memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
task_unlock(current->group_leader);
posix_cpu_timers_init_group(sig);
- acct_init_pacct(&sig->pacct);
-
tty_audit_fork(sig);
sig->oom_adj = current->signal->oom_adj;
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
- p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
+ task_rlimit(p, RLIMIT_NPROC)) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
struct task_struct *result = NULL;
if (pid) {
struct hlist_node *first;
- first = rcu_dereference_check(pid->tasks[type].first, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock));
+ first = rcu_dereference_check(pid->tasks[type].first,
+ rcu_read_lock_held() ||
+ lockdep_tasklist_lock_is_held());
if (first)
result = hlist_entry(first, struct task_struct, pids[(type)].node);
}
EXPORT_SYMBOL(pid_task);
/*
- * Must be called under rcu_read_lock() or with tasklist_lock read-held.
+ * Must be called under rcu_read_lock().
*/
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/hash.h>
+ #include <linux/rcupdate.h>
#include <trace/events/sched.h>
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
-#endif
-
+ /*
+ * Traverse the ftrace_list, invoking all entries. The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism. The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
- struct ftrace_ops *op = ftrace_list;
-
- /* in case someone actually ports this to alpha! */
- read_barrier_depends();
+ struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
while (op != &ftrace_list_end) {
- /* silly alpha */
- read_barrier_depends();
op->func(ip, parent_ip);
- op = op->next;
+ op = rcu_dereference_raw(op->next); /*see above*/
};
}
* the ops->next pointer is valid before another CPU sees
* the ops pointer included into the ftrace_list.
*/
- smp_wmb();
- ftrace_list = ops;
+ rcu_assign_pointer(ftrace_list, ops);
if (ftrace_enabled) {
ftrace_func_t func;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
{
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
+ t->curr_ret_stack = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
GFP_KERNEL);
if (!ret_stack)
return;
- t->curr_ret_stack = -1;
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
}
/* Step 2: apply policy to a range and do splits. */
-static int mbind_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, struct mempolicy *new)
+static int mbind_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, struct mempolicy *new_pol)
{
struct vm_area_struct *next;
- int err;
+ struct vm_area_struct *prev;
+ struct vm_area_struct *vma;
+ int err = 0;
+ pgoff_t pgoff;
+ unsigned long vmstart;
+ unsigned long vmend;
- err = 0;
- for (; vma && vma->vm_start < end; vma = next) {
+ vma = find_vma_prev(mm, start, &prev);
+ if (!vma || vma->vm_start > start)
+ return -EFAULT;
+
+ for (; vma && vma->vm_start < end; prev = vma, vma = next) {
next = vma->vm_next;
- if (vma->vm_start < start)
- err = split_vma(vma->vm_mm, vma, start, 1);
- if (!err && vma->vm_end > end)
- err = split_vma(vma->vm_mm, vma, end, 0);
- if (!err)
- err = policy_vma(vma, new);
+ vmstart = max(start, vma->vm_start);
+ vmend = min(end, vma->vm_end);
+
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+ prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
+ vma->anon_vma, vma->vm_file, pgoff, new_pol);
+ if (prev) {
+ vma = prev;
+ next = vma->vm_next;
+ continue;
+ }
+ if (vma->vm_start != vmstart) {
+ err = split_vma(vma->vm_mm, vma, vmstart, 1);
+ if (err)
+ goto out;
+ }
+ if (vma->vm_end != vmend) {
+ err = split_vma(vma->vm_mm, vma, vmend, 0);
+ if (err)
+ goto out;
+ }
+ err = policy_vma(vma, new_pol);
if (err)
- break;
+ goto out;
}
+
+ out:
return err;
}
if (err)
goto out;
-/*
- * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
- * bit in 'to' is not also set in 'tmp'. Clear the found 'source'
- * bit in 'tmp', and return that <source, dest> pair for migration.
- * The pair of nodemasks 'to' and 'from' define the map.
- *
- * If no pair of bits is found that way, fallback to picking some
- * pair of 'source' and 'dest' bits that are not the same. If the
- * 'source' and 'dest' bits are the same, this represents a node
- * that will be migrating to itself, so no pages need move.
- *
- * If no bits are left in 'tmp', or if all remaining bits left
- * in 'tmp' correspond to the same bit in 'to', return false
- * (nothing left to migrate).
- *
- * This lets us pick a pair of nodes to migrate between, such that
- * if possible the dest node is not already occupied by some other
- * source node, minimizing the risk of overloading the memory on a
- * node that would happen if we migrated incoming memory to a node
- * before migrating outgoing memory source that same node.
- *
- * A single scan of tmp is sufficient. As we go, we remember the
- * most recent <s, d> pair that moved (s != d). If we find a pair
- * that not only moved, but what's better, moved to an empty slot
- * (d is not set in tmp), then we break out then, with that pair.
- * Otherwise when we finish scannng from_tmp, we at least have the
- * most recent <s, d> pair that moved. If we get all the way through
- * the scan of tmp without finding any node that moved, much less
- * moved to an empty node, then there is nothing left worth migrating.
- */
+ /*
+ * Find a 'source' bit set in 'tmp' whose corresponding 'dest'
+ * bit in 'to' is not also set in 'tmp'. Clear the found 'source'
+ * bit in 'tmp', and return that <source, dest> pair for migration.
+ * The pair of nodemasks 'to' and 'from' define the map.
+ *
+ * If no pair of bits is found that way, fallback to picking some
+ * pair of 'source' and 'dest' bits that are not the same. If the
+ * 'source' and 'dest' bits are the same, this represents a node
+ * that will be migrating to itself, so no pages need move.
+ *
+ * If no bits are left in 'tmp', or if all remaining bits left
+ * in 'tmp' correspond to the same bit in 'to', return false
+ * (nothing left to migrate).
+ *
+ * This lets us pick a pair of nodes to migrate between, such that
+ * if possible the dest node is not already occupied by some other
+ * source node, minimizing the risk of overloading the memory on a
+ * node that would happen if we migrated incoming memory to a node
+ * before migrating outgoing memory source that same node.
+ *
+ * A single scan of tmp is sufficient. As we go, we remember the
+ * most recent <s, d> pair that moved (s != d). If we find a pair
+ * that not only moved, but what's better, moved to an empty slot
+ * (d is not set in tmp), then we break out then, with that pair.
+ * Otherwise when we finish scannng from_tmp, we at least have the
+ * most recent <s, d> pair that moved. If we get all the way through
+ * the scan of tmp without finding any node that moved, much less
+ * moved to an empty node, then there is nothing left worth migrating.
+ */
tmp = *from_nodes;
while (!nodes_empty(tmp)) {
if (!IS_ERR(vma)) {
int nr_failed = 0;
- err = mbind_range(vma, start, end, new);
+ err = mbind_range(mm, start, end, new);
if (!list_empty(&pagelist))
nr_failed = migrate_pages(&pagelist, new_vma_page,
if (!new)
return ERR_PTR(-ENOMEM);
+ rcu_read_lock();
if (current_cpuset_is_being_rebound()) {
nodemask_t mems = cpuset_mems_allowed(current);
mpol_rebind_policy(old, &mems);
}
+ rcu_read_unlock();
*new = *old;
atomic_set(&new->refcnt, 1);
return new;