#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
+#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#define CPUSET_SUPER_MAGIC 0x27e0eb
+/*
+ * Tracks how many cpusets are currently defined in system.
+ * When there is only one cpuset (the root cpuset) we can
+ * short circuit some hooks.
+ */
+int number_of_cpusets __read_mostly;
+
/* See "Frequency meter" comments, below. */
struct fmeter {
* a tasks cpuset pointer we use task_lock(), which acts on a spinlock
* (task->alloc_lock) already in the task_struct routinely used for
* such matters.
+ *
+ * P.S. One more locking exception. RCU is used to guard the
+ * update of a tasks cpuset pointer by attach_task() and the
+ * access of task->cpuset->mems_generation via that pointer in
+ * the routine cpuset_update_task_memory_state().
*/
static DECLARE_MUTEX(manage_sem);
* Do not call this routine if in_interrupt().
*
* Call without callback_sem or task_lock() held. May be called
- * with or without manage_sem held. Except in early boot or
- * an exiting task, when tsk->cpuset is NULL, this routine will
- * acquire task_lock(). We don't need to use task_lock to guard
+ * with or without manage_sem held. Doesn't need task_lock to guard
* against another task changing a non-NULL cpuset pointer to NULL,
* as that is only done by a task on itself, and if the current task
* is here, it is not simultaneously in the exit code NULL'ing its
* cpuset pointer. This routine also might acquire callback_sem and
* current->mm->mmap_sem during call.
*
- * The task_lock() is required to dereference current->cpuset safely.
- * Without it, we could pick up the pointer value of current->cpuset
- * in one instruction, and then attach_task could give us a different
- * cpuset, and then the cpuset we had could be removed and freed,
- * and then on our next instruction, we could dereference a no longer
- * valid cpuset pointer to get its mems_generation field.
+ * Reading current->cpuset->mems_generation doesn't need task_lock
+ * to guard the current->cpuset derefence, because it is guarded
+ * from concurrent freeing of current->cpuset by attach_task(),
+ * using RCU.
+ *
+ * The rcu_dereference() is technically probably not needed,
+ * as I don't actually mind if I see a new cpuset pointer but
+ * an old value of mems_generation. However this really only
+ * matters on alpha systems using cpusets heavily. If I dropped
+ * that rcu_dereference(), it would save them a memory barrier.
+ * For all other arch's, rcu_dereference is a no-op anyway, and for
+ * alpha systems not using cpusets, another planned optimization,
+ * avoiding the rcu critical section for tasks in the root cpuset
+ * which is statically allocated, so can't vanish, will make this
+ * irrelevant. Better to use RCU as intended, than to engage in
+ * some cute trick to save a memory barrier that is impossible to
+ * test, for alpha systems using cpusets heavily, which might not
+ * even exist.
*
* This routine is needed to update the per-task mems_allowed data,
* within the tasks context, when it is trying to allocate memory
{
int my_cpusets_mem_gen;
struct task_struct *tsk = current;
- struct cpuset *cs = tsk->cpuset;
-
- if (unlikely(!cs))
- return;
+ struct cpuset *cs;
- task_lock(tsk);
+ rcu_read_lock();
+ cs = rcu_dereference(tsk->cpuset);
my_cpusets_mem_gen = cs->mems_generation;
- task_unlock(tsk);
+ rcu_read_unlock();
if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
- nodemask_t oldmem = tsk->mems_allowed;
- int migrate;
-
down(&callback_sem);
task_lock(tsk);
cs = tsk->cpuset; /* Maybe changed when task not locked */
- migrate = is_memory_migrate(cs);
guarantee_online_mems(cs, &tsk->mems_allowed);
tsk->cpuset_mems_generation = cs->mems_generation;
task_unlock(tsk);
up(&callback_sem);
- numa_policy_rebind(&oldmem, &tsk->mems_allowed);
- if (!nodes_equal(oldmem, tsk->mems_allowed)) {
- if (migrate) {
- do_migrate_pages(tsk->mm, &oldmem,
- &tsk->mems_allowed,
- MPOL_MF_MOVE_ALL);
- }
- }
+ mpol_rebind_task(tsk, &tsk->mems_allowed);
}
}
}
/*
+ * Handle user request to change the 'mems' memory placement
+ * of a cpuset. Needs to validate the request, update the
+ * cpusets mems_allowed and mems_generation, and for each
+ * task in the cpuset, rebind any vma mempolicies and if
+ * the cpuset is marked 'memory_migrate', migrate the tasks
+ * pages to the new memory.
+ *
* Call with manage_sem held. May take callback_sem during call.
+ * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
+ * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * their mempolicies to the cpusets new mems_allowed.
*/
static int update_nodemask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
+ nodemask_t oldmem;
+ struct task_struct *g, *p;
+ struct mm_struct **mmarray;
+ int i, n, ntasks;
+ int migrate;
+ int fudge;
int retval;
trialcs = *cs;
if (retval < 0)
goto done;
nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
+ oldmem = cs->mems_allowed;
+ if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+ retval = 0; /* Too easy - nothing to do */
+ goto done;
+ }
if (nodes_empty(trialcs.mems_allowed)) {
retval = -ENOSPC;
goto done;
cs->mems_generation = atomic_read(&cpuset_mems_generation);
up(&callback_sem);
+ set_cpuset_being_rebound(cs); /* causes mpol_copy() rebind */
+
+ fudge = 10; /* spare mmarray[] slots */
+ fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */
+ retval = -ENOMEM;
+
+ /*
+ * Allocate mmarray[] to hold mm reference for each task
+ * in cpuset cs. Can't kmalloc GFP_KERNEL while holding
+ * tasklist_lock. We could use GFP_ATOMIC, but with a
+ * few more lines of code, we can retry until we get a big
+ * enough mmarray[] w/o using GFP_ATOMIC.
+ */
+ while (1) {
+ ntasks = atomic_read(&cs->count); /* guess */
+ ntasks += fudge;
+ mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
+ if (!mmarray)
+ goto done;
+ write_lock_irq(&tasklist_lock); /* block fork */
+ if (atomic_read(&cs->count) <= ntasks)
+ break; /* got enough */
+ write_unlock_irq(&tasklist_lock); /* try again */
+ kfree(mmarray);
+ }
+
+ n = 0;
+
+ /* Load up mmarray[] with mm reference for each task in cpuset. */
+ do_each_thread(g, p) {
+ struct mm_struct *mm;
+
+ if (n >= ntasks) {
+ printk(KERN_WARNING
+ "Cpuset mempolicy rebind incomplete.\n");
+ continue;
+ }
+ if (p->cpuset != cs)
+ continue;
+ mm = get_task_mm(p);
+ if (!mm)
+ continue;
+ mmarray[n++] = mm;
+ } while_each_thread(g, p);
+ write_unlock_irq(&tasklist_lock);
+
+ /*
+ * Now that we've dropped the tasklist spinlock, we can
+ * rebind the vma mempolicies of each mm in mmarray[] to their
+ * new cpuset, and release that mm. The mpol_rebind_mm()
+ * call takes mmap_sem, which we couldn't take while holding
+ * tasklist_lock. Forks can happen again now - the mpol_copy()
+ * cpuset_being_rebound check will catch such forks, and rebind
+ * their vma mempolicies too. Because we still hold the global
+ * cpuset manage_sem, we know that no other rebind effort will
+ * be contending for the global variable cpuset_being_rebound.
+ * It's ok if we rebind the same mm twice; mpol_rebind_mm()
+ * is idempotent. Also migrate pages in each mm to new nodes.
+ */
+ migrate = is_memory_migrate(cs);
+ for (i = 0; i < n; i++) {
+ struct mm_struct *mm = mmarray[i];
+
+ mpol_rebind_mm(mm, &cs->mems_allowed);
+ if (migrate) {
+ do_migrate_pages(mm, &oldmem, &cs->mems_allowed,
+ MPOL_MF_MOVE_ALL);
+ }
+ mmput(mm);
+ }
+
+ /* We're done rebinding vma's to this cpusets new mems_allowed. */
+ kfree(mmarray);
+ set_cpuset_being_rebound(NULL);
+ retval = 0;
done:
return retval;
}
struct cpuset *oldcs;
cpumask_t cpus;
nodemask_t from, to;
+ struct mm_struct *mm;
if (sscanf(pidbuf, "%d", &pid) != 1)
return -EIO;
return -ESRCH;
}
atomic_inc(&cs->count);
- tsk->cpuset = cs;
+ rcu_assign_pointer(tsk->cpuset, cs);
task_unlock(tsk);
guarantee_online_cpus(cs, &cpus);
to = cs->mems_allowed;
up(&callback_sem);
+
+ mm = get_task_mm(tsk);
+ if (mm) {
+ mpol_rebind_mm(mm, &to);
+ mmput(mm);
+ }
+
if (is_memory_migrate(cs))
do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
put_task_struct(tsk);
+ synchronize_rcu();
if (atomic_dec_and_test(&oldcs->count))
check_for_release(oldcs, ppathbuf);
return 0;
down(&callback_sem);
list_add(&cs->sibling, &cs->parent->children);
+ number_of_cpusets++;
up(&callback_sem);
err = cpuset_create_dir(cs, name, mode);
spin_unlock(&d->d_lock);
cpuset_d_remove_dir(d);
dput(d);
+ number_of_cpusets--;
up(&callback_sem);
if (list_empty(&parent->children))
check_for_release(parent, &pathbuf);
return 0;
}
+/*
+ * cpuset_init_early - just enough so that the calls to
+ * cpuset_update_task_memory_state() in early init code
+ * are harmless.
+ */
+
+int __init cpuset_init_early(void)
+{
+ struct task_struct *tsk = current;
+
+ tsk->cpuset = &top_cpuset;
+ tsk->cpuset->mems_generation = atomic_read(&cpuset_mems_generation);
+ return 0;
+}
+
/**
* cpuset_init - initialize cpusets at system boot
*
root->d_inode->i_nlink++;
top_cpuset.dentry = root;
root->d_inode->i_op = &cpuset_dir_inode_operations;
+ number_of_cpusets = 1;
err = cpuset_populate_dir(root);
/* memory_pressure_enabled is in root cpuset only */
if (err == 0)
* tasks cpuset.
**/
-cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
+cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
{
cpumask_t mask;
down(&callback_sem);
- task_lock((struct task_struct *)tsk);
+ task_lock(tsk);
guarantee_online_cpus(tsk->cpuset, &mask);
- task_unlock((struct task_struct *)tsk);
+ task_unlock(tsk);
up(&callback_sem);
return mask;
current->mems_allowed = NODE_MASK_ALL;
}
+/**
+ * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
+ *
+ * Description: Returns the nodemask_t mems_allowed of the cpuset
+ * attached to the specified @tsk. Guaranteed to return some non-empty
+ * subset of node_online_map, even if this means going outside the
+ * tasks cpuset.
+ **/
+
+nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
+{
+ nodemask_t mask;
+
+ down(&callback_sem);
+ task_lock(tsk);
+ guarantee_online_mems(tsk->cpuset, &mask);
+ task_unlock(tsk);
+ up(&callback_sem);
+
+ return mask;
+}
+
/**
* cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
* @zl: the zonelist to be checked
* GFP_USER - only nodes in current tasks mems allowed ok.
**/
-int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
+int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
{
int node; /* node that zone z is on */
const struct cpuset *cs; /* current cpuset ancestors */
projects / deliverable / linux.git / blobdiff