summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c19
-rw-r--r--mm/hugetlb.c27
-rw-r--r--mm/memcontrol.c49
-rw-r--r--mm/oom_kill.c2
-rw-r--r--mm/page-writeback.c2
-rw-r--r--mm/page_alloc.c3
-rw-r--r--mm/shmem.c34
-rw-r--r--mm/vmstat.c8
8 files changed, 85 insertions, 59 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8ed2ffd963c5..7340353f8aea 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait);
* jiffies for either a BDI to exit congestion of the given @sync queue
* or a write to complete.
*
- * In the absence of zone congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the absence of zone congestion, a short sleep or a cond_resched is
+ * performed to yield the processor and to allow other subsystems to make
+ * a forward progress.
*
* The return value is 0 if the sleep is for the full timeout. Otherwise,
* it is the number of jiffies that were still remaining when the function
@@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
*/
if (atomic_read(&nr_wb_congested[sync]) == 0 ||
!test_bit(ZONE_CONGESTED, &zone->flags)) {
- cond_resched();
+
+ /*
+ * Memory allocation/reclaim might be called from a WQ
+ * context and the current implementation of the WQ
+ * concurrency control doesn't recognize that a particular
+ * WQ is congested if the worker thread is looping without
+ * ever sleeping. Therefore we have to do a short sleep
+ * here rather than calling cond_resched().
+ */
+ if (current->flags & PF_WQ_WORKER)
+ schedule_timeout(1);
+ else
+ cond_resched();
/* In case we scheduled, work out time remaining */
ret = timeout - (jiffies - start);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 827bb02a43a4..ef6963b577fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -372,8 +372,10 @@ retry_locked:
spin_unlock(&resv->lock);
trg = kmalloc(sizeof(*trg), GFP_KERNEL);
- if (!trg)
+ if (!trg) {
+ kfree(nrg);
return -ENOMEM;
+ }
spin_lock(&resv->lock);
list_add(&trg->link, &resv->region_cache);
@@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t)
retry:
spin_lock(&resv->lock);
list_for_each_entry_safe(rg, trg, head, link) {
- if (rg->to <= f)
+ /*
+ * Skip regions before the range to be deleted. file_region
+ * ranges are normally of the form [from, to). However, there
+ * may be a "placeholder" entry in the map which is of the form
+ * (from, to) with from == to. Check for placeholder entries
+ * at the beginning of the range to be deleted.
+ */
+ if (rg->to <= f && (rg->to != rg->from || rg->to != f))
continue;
+
if (rg->from >= t)
break;
@@ -1886,7 +1896,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
if (!page)
goto out_uncharge_cgroup;
-
+ if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
+ SetPagePrivate(page);
+ h->resv_huge_pages--;
+ }
spin_lock(&hugetlb_lock);
list_move(&page->lru, &h->hugepage_activelist);
/* Fall through */
@@ -3693,12 +3706,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
+ } else {
+ ptep = huge_pte_alloc(mm, address, huge_page_size(h));
+ if (!ptep)
+ return VM_FAULT_OOM;
}
- ptep = huge_pte_alloc(mm, address, huge_page_size(h));
- if (!ptep)
- return VM_FAULT_OOM;
-
mapping = vma->vm_file->f_mapping;
idx = vma_hugecache_offset(h, vma, address);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9acfb165eb52..e234c21a5e6c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2128,7 +2128,7 @@ done_restock:
*/
do {
if (page_counter_read(&memcg->memory) > memcg->high) {
- current->memcg_nr_pages_over_high += nr_pages;
+ current->memcg_nr_pages_over_high += batch;
set_notify_resume(current);
break;
}
@@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void)
spin_unlock(&mc.lock);
}
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
{
- struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct cgroup_subsys_state *css;
+ struct mem_cgroup *memcg;
struct mem_cgroup *from;
struct task_struct *leader, *p;
struct mm_struct *mm;
unsigned long move_flags;
int ret = 0;
- /*
- * We are now commited to this value whatever it is. Changes in this
- * tunable will only affect upcoming migrations, not the current one.
- * So we need to save it, and keep it going.
- */
- move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
- if (!move_flags)
+ /* charge immigration isn't supported on the default hierarchy */
+ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
return 0;
/*
@@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
* multiple.
*/
p = NULL;
- cgroup_taskset_for_each_leader(leader, tset) {
+ cgroup_taskset_for_each_leader(leader, css, tset) {
WARN_ON_ONCE(p);
p = leader;
+ memcg = mem_cgroup_from_css(css);
}
if (!p)
return 0;
+ /*
+ * We are now commited to this value whatever it is. Changes in this
+ * tunable will only affect upcoming migrations, not the current one.
+ * So we need to save it, and keep it going.
+ */
+ move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
+ if (!move_flags)
+ return 0;
+
from = mem_cgroup_from_task(p);
VM_BUG_ON(from == memcg);
@@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
return ret;
}
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
if (mc.to)
mem_cgroup_clear_mc();
@@ -4985,10 +4989,10 @@ retry:
atomic_dec(&mc.from->moving_account);
}
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
{
- struct task_struct *p = cgroup_taskset_first(tset);
+ struct cgroup_subsys_state *css;
+ struct task_struct *p = cgroup_taskset_first(tset, &css);
struct mm_struct *mm = get_task_mm(p);
if (mm) {
@@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
mem_cgroup_clear_mc();
}
#else /* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
{
return 0;
}
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
{
}
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
{
}
#endif
@@ -5511,11 +5512,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
* mem_cgroup_replace_page - migrate a charge to another page
* @oldpage: currently charged page
* @newpage: page to transfer the charge to
- * @lrucare: either or both pages might be on the LRU already
*
* Migrate the charge from @oldpage to @newpage.
*
* Both pages must be locked, @newpage->mapping must be set up.
+ * Either or both pages might be on the LRU already.
*/
void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
{
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d13a33918fa2..c12680993ff3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
continue;
if (unlikely(p->flags & PF_KTHREAD))
continue;
+ if (is_global_init(p))
+ continue;
if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
continue;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e4d65445fa7..d15d88c8efa1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2,7 +2,7 @@
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
*
* Contains functions related to writing back dirty pages at the
* address_space level.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17a3c66639a9..9d666df5ef95 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type)
{
static const char types[MIGRATE_TYPES] = {
[MIGRATE_UNMOVABLE] = 'U',
- [MIGRATE_RECLAIMABLE] = 'E',
[MIGRATE_MOVABLE] = 'M',
+ [MIGRATE_RECLAIMABLE] = 'E',
+ [MIGRATE_HIGHATOMIC] = 'H',
#ifdef CONFIG_CMA
[MIGRATE_CMA] = 'C',
#endif
diff --git a/mm/shmem.c b/mm/shmem.c
index 9187eee4128b..2afcdbbdb685 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
list_add_tail(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
- swap_shmem_alloc(swap);
- shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
-
spin_lock(&info->lock);
- info->swapped++;
shmem_recalc_inode(inode);
+ info->swapped++;
spin_unlock(&info->lock);
+ swap_shmem_alloc(swap);
+ shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
+
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(page_mapped(page));
swap_writepage(page, wbc);
@@ -1078,7 +1078,7 @@ repeat:
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
- goto failed;
+ goto unlock;
}
if (page && sgp == SGP_WRITE)
@@ -1246,11 +1246,15 @@ clear:
/* Perhaps the file has been truncated since we checked */
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
+ if (alloced) {
+ ClearPageDirty(page);
+ delete_from_page_cache(page);
+ spin_lock(&info->lock);
+ shmem_recalc_inode(inode);
+ spin_unlock(&info->lock);
+ }
error = -EINVAL;
- if (alloced)
- goto trunc;
- else
- goto failed;
+ goto unlock;
}
*pagep = page;
return 0;
@@ -1258,23 +1262,13 @@ clear:
/*
* Error recovery.
*/
-trunc:
- info = SHMEM_I(inode);
- ClearPageDirty(page);
- delete_from_page_cache(page);
- spin_lock(&info->lock);
- info->alloced--;
- inode->i_blocks -= BLOCKS_PER_PAGE;
- spin_unlock(&info->lock);
decused:
- sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
unacct:
shmem_unacct_blocks(info->flags, 1);
failed:
- if (swap.val && error != -EINVAL &&
- !shmem_confirm_swap(mapping, index, swap))
+ if (swap.val && !shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
unlock:
if (page) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 879a2be23325..0d5712b0206c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
#ifdef CONFIG_PROC_FS
static char * const migratetype_names[MIGRATE_TYPES] = {
"Unmovable",
- "Reclaimable",
"Movable",
+ "Reclaimable",
"HighAtomic",
#ifdef CONFIG_CMA
"CMA",
@@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = {
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
+static struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
static cpumask_var_t cpu_stat_off;
@@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w)
* to occur in the future. Keep on running the
* update worker thread.
*/
- schedule_delayed_work_on(smp_processor_id(),
+ queue_delayed_work_on(smp_processor_id(), vmstat_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
} else {
@@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w)
if (need_update(cpu) &&
cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
- schedule_delayed_work_on(cpu,
+ queue_delayed_work_on(cpu, vmstat_wq,
&per_cpu(vmstat_work, cpu), 0);
put_online_cpus();
@@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void)
start_shepherd_timer();
cpu_notifier_register_done();
+ vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
#endif
#ifdef CONFIG_PROC_FS
proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);