+ while (!is_mem_exclusive(cs) && cs->parent)
+ cs = cs->parent;
+ return cs;
+}
+
+/**
+ * cpuset_zone_allowed - Can we allocate memory on zone z's memory node?
+ * @z: is this zone on an allowed node?
+ * @gfp_mask: memory allocation flags (we use __GFP_HARDWALL)
+ *
+ * If we're in interrupt, yes, we can always allocate. If zone
+ * z's node is in our tasks mems_allowed, yes. If it's not a
+ * __GFP_HARDWALL request and this zone's nodes is in the nearest
+ * mem_exclusive cpuset ancestor to this tasks cpuset, yes.
+ * Otherwise, no.
+ *
+ * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
+ * and do not allow allocations outside the current tasks cpuset.
+ * GFP_KERNEL allocations are not so marked, so can escape to the
+ * nearest mem_exclusive ancestor cpuset.
+ *
+ * Scanning up parent cpusets requires callback_mutex. The __alloc_pages()
+ * routine only calls here with __GFP_HARDWALL bit _not_ set if
+ * it's a GFP_KERNEL allocation, and all nodes in the current tasks
+ * mems_allowed came up empty on the first pass over the zonelist.
+ * So only GFP_KERNEL allocations, if all nodes in the cpuset are
+ * short of memory, might require taking the callback_mutex mutex.
+ *
+ * The first call here from mm/page_alloc:get_page_from_freelist()
+ * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, so
+ * no allocation on a node outside the cpuset is allowed (unless in
+ * interrupt, of course).
+ *
+ * The second pass through get_page_from_freelist() doesn't even call
+ * here for GFP_ATOMIC calls. For those calls, the __alloc_pages()
+ * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set
+ * in alloc_flags. That logic and the checks below have the combined
+ * affect that:
+ * in_interrupt - any node ok (current task context irrelevant)
+ * GFP_ATOMIC - any node ok
+ * GFP_KERNEL - any node in enclosing mem_exclusive cpuset ok
+ * GFP_USER - only nodes in current tasks mems allowed ok.
+ *
+ * Rule:
+ * Don't call cpuset_zone_allowed() if you can't sleep, unless you
+ * pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
+ * the code that might scan up ancestor cpusets and sleep.
+ **/
+
+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 */
+ int allowed; /* is allocation in zone z allowed? */
+
+ if (in_interrupt())
+ return 1;
+ node = z->zone_pgdat->node_id;
+ might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
+ if (node_isset(node, current->mems_allowed))
+ return 1;
+ if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */
+ return 0;
+
+ if (current->flags & PF_EXITING) /* Let dying task have memory */
+ return 1;
+
+ /* Not hardwall and node outside mems_allowed: scan up cpusets */
+ mutex_lock(&callback_mutex);
+
+ task_lock(current);
+ cs = nearest_exclusive_ancestor(current->cpuset);
+ task_unlock(current);
+
+ allowed = node_isset(node, cs->mems_allowed);
+ mutex_unlock(&callback_mutex);
+ return allowed;
+}
+
+/**
+ * cpuset_lock - lock out any changes to cpuset structures
+ *
+ * The out of memory (oom) code needs to mutex_lock cpusets
+ * from being changed while it scans the tasklist looking for a
+ * task in an overlapping cpuset. Expose callback_mutex via this
+ * cpuset_lock() routine, so the oom code can lock it, before
+ * locking the task list. The tasklist_lock is a spinlock, so
+ * must be taken inside callback_mutex.
+ */
+
+void cpuset_lock(void)
+{
+ mutex_lock(&callback_mutex);
+}
+
+/**
+ * cpuset_unlock - release lock on cpuset changes
+ *
+ * Undo the lock taken in a previous cpuset_lock() call.
+ */
+
+void cpuset_unlock(void)
+{
+ mutex_unlock(&callback_mutex);
+}
+
+/**
+ * cpuset_mem_spread_node() - On which node to begin search for a page
+ *
+ * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
+ * tasks in a cpuset with is_spread_page or is_spread_slab set),
+ * and if the memory allocation used cpuset_mem_spread_node()
+ * to determine on which node to start looking, as it will for
+ * certain page cache or slab cache pages such as used for file
+ * system buffers and inode caches, then instead of starting on the
+ * local node to look for a free page, rather spread the starting
+ * node around the tasks mems_allowed nodes.
+ *
+ * We don't have to worry about the returned node being offline
+ * because "it can't happen", and even if it did, it would be ok.
+ *
+ * The routines calling guarantee_online_mems() are careful to
+ * only set nodes in task->mems_allowed that are online. So it
+ * should not be possible for the following code to return an
+ * offline node. But if it did, that would be ok, as this routine
+ * is not returning the node where the allocation must be, only
+ * the node where the search should start. The zonelist passed to
+ * __alloc_pages() will include all nodes. If the slab allocator
+ * is passed an offline node, it will fall back to the local node.
+ * See kmem_cache_alloc_node().
+ */
+
+int cpuset_mem_spread_node(void)
+{
+ int node;
+
+ node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
+ if (node == MAX_NUMNODES)
+ node = first_node(current->mems_allowed);
+ current->cpuset_mem_spread_rotor = node;
+ return node;
+}
+EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
+
+/**
+ * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors?
+ * @p: pointer to task_struct of some other task.
+ *
+ * Description: Return true if the nearest mem_exclusive ancestor
+ * cpusets of tasks @p and current overlap. Used by oom killer to
+ * determine if task @p's memory usage might impact the memory
+ * available to the current task.
+ *
+ * Call while holding callback_mutex.
+ **/
+
+int cpuset_excl_nodes_overlap(const struct task_struct *p)
+{
+ const struct cpuset *cs1, *cs2; /* my and p's cpuset ancestors */
+ int overlap = 0; /* do cpusets overlap? */
+
+ task_lock(current);
+ if (current->flags & PF_EXITING) {
+ task_unlock(current);
+ goto done;
+ }
+ cs1 = nearest_exclusive_ancestor(current->cpuset);
+ task_unlock(current);
+
+ task_lock((struct task_struct *)p);
+ if (p->flags & PF_EXITING) {
+ task_unlock((struct task_struct *)p);
+ goto done;
+ }
+ cs2 = nearest_exclusive_ancestor(p->cpuset);
+ task_unlock((struct task_struct *)p);
+
+ overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
+done:
+ return overlap;
+}
+
+/*
+ * Collection of memory_pressure is suppressed unless
+ * this flag is enabled by writing "1" to the special
+ * cpuset file 'memory_pressure_enabled' in the root cpuset.
+ */
+
+int cpuset_memory_pressure_enabled __read_mostly;
+
+/**
+ * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
+ *
+ * Keep a running average of the rate of synchronous (direct)
+ * page reclaim efforts initiated by tasks in each cpuset.
+ *
+ * This represents the rate at which some task in the cpuset
+ * ran low on memory on all nodes it was allowed to use, and
+ * had to enter the kernels page reclaim code in an effort to
+ * create more free memory by tossing clean pages or swapping
+ * or writing dirty pages.
+ *
+ * Display to user space in the per-cpuset read-only file
+ * "memory_pressure". Value displayed is an integer
+ * representing the recent rate of entry into the synchronous
+ * (direct) page reclaim by any task attached to the cpuset.
+ **/
+
+void __cpuset_memory_pressure_bump(void)
+{
+ struct cpuset *cs;
+
+ task_lock(current);
+ cs = current->cpuset;
+ fmeter_markevent(&cs->fmeter);
+ task_unlock(current);