summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c29
-rw-r--r--mm/memcontrol.c82
-rw-r--r--mm/mprotect.c2
-rw-r--r--mm/nommu.c1
-rw-r--r--mm/page_alloc.c14
-rw-r--r--mm/pagewalk.c5
-rw-r--r--mm/slub.c3
-rw-r--r--mm/vmscan.c2
8 files changed, 81 insertions, 57 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 61ba5e405791..ea89840fc65f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -644,7 +644,9 @@ repeat:
pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
if (pagep) {
page = radix_tree_deref_slot(pagep);
- if (unlikely(!page || page == RADIX_TREE_RETRY))
+ if (unlikely(!page))
+ goto out;
+ if (radix_tree_deref_retry(page))
goto repeat;
if (!page_cache_get_speculative(page))
@@ -660,6 +662,7 @@ repeat:
goto repeat;
}
}
+out:
rcu_read_unlock();
return page;
@@ -777,12 +780,11 @@ repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
- /*
- * this can only trigger if nr_found == 1, making livelock
- * a non issue.
- */
- if (unlikely(page == RADIX_TREE_RETRY))
+ if (radix_tree_deref_retry(page)) {
+ if (ret)
+ start = pages[ret-1]->index;
goto restart;
+ }
if (!page_cache_get_speculative(page))
goto repeat;
@@ -830,11 +832,7 @@ repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
- /*
- * this can only trigger if nr_found == 1, making livelock
- * a non issue.
- */
- if (unlikely(page == RADIX_TREE_RETRY))
+ if (radix_tree_deref_retry(page))
goto restart;
if (page->mapping == NULL || page->index != index)
@@ -887,11 +885,7 @@ repeat:
page = radix_tree_deref_slot((void **)pages[i]);
if (unlikely(!page))
continue;
- /*
- * this can only trigger if nr_found == 1, making livelock
- * a non issue.
- */
- if (unlikely(page == RADIX_TREE_RETRY))
+ if (radix_tree_deref_retry(page))
goto restart;
if (!page_cache_get_speculative(page))
@@ -1029,6 +1023,9 @@ find_page:
goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
+ /* Did it get truncated before we got the lock? */
+ if (!page->mapping)
+ goto page_not_up_to_date_locked;
if (!mapping->a_ops->is_partially_uptodate(page,
desc, offset))
goto page_not_up_to_date_locked;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9a99cfaf0a19..7a22b4129211 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -61,7 +61,14 @@ struct mem_cgroup *root_mem_cgroup __read_mostly;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
int do_swap_account __read_mostly;
-static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+
+/* for remember boot option*/
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+static int really_do_swap_account __initdata = 1;
+#else
+static int really_do_swap_account __initdata = 0;
+#endif
+
#else
#define do_swap_account (0)
#endif
@@ -278,13 +285,14 @@ enum move_type {
/* "mc" and its members are protected by cgroup_mutex */
static struct move_charge_struct {
- spinlock_t lock; /* for from, to, moving_task */
+ spinlock_t lock; /* for from, to */
struct mem_cgroup *from;
struct mem_cgroup *to;
unsigned long precharge;
unsigned long moved_charge;
unsigned long moved_swap;
struct task_struct *moving_task; /* a task moving charges */
+ struct mm_struct *mm;
wait_queue_head_t waitq; /* a waitq for other context */
} mc = {
.lock = __SPIN_LOCK_UNLOCKED(mc.lock),
@@ -2152,7 +2160,7 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc,
{
VM_BUG_ON(from == to);
VM_BUG_ON(PageLRU(pc->page));
- VM_BUG_ON(!PageCgroupLocked(pc));
+ VM_BUG_ON(!page_is_cgroup_locked(pc));
VM_BUG_ON(!PageCgroupUsed(pc));
VM_BUG_ON(pc->mem_cgroup != from);
@@ -4208,15 +4216,17 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
memset(mem, 0, size);
mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
- if (!mem->stat) {
- if (size < PAGE_SIZE)
- kfree(mem);
- else
- vfree(mem);
- mem = NULL;
- }
+ if (!mem->stat)
+ goto out_free;
spin_lock_init(&mem->pcp_counter_lock);
return mem;
+
+out_free:
+ if (size < PAGE_SIZE)
+ kfree(mem);
+ else
+ vfree(mem);
+ return NULL;
}
/*
@@ -4629,7 +4639,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
unsigned long precharge;
struct vm_area_struct *vma;
- down_read(&mm->mmap_sem);
+ /* We've already held the mmap_sem */
for (vma = mm->mmap; vma; vma = vma->vm_next) {
struct mm_walk mem_cgroup_count_precharge_walk = {
.pmd_entry = mem_cgroup_count_precharge_pte_range,
@@ -4641,7 +4651,6 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
walk_page_range(vma->vm_start, vma->vm_end,
&mem_cgroup_count_precharge_walk);
}
- up_read(&mm->mmap_sem);
precharge = mc.precharge;
mc.precharge = 0;
@@ -4692,11 +4701,16 @@ static void mem_cgroup_clear_mc(void)
mc.moved_swap = 0;
}
+ if (mc.mm) {
+ up_read(&mc.mm->mmap_sem);
+ mmput(mc.mm);
+ }
spin_lock(&mc.lock);
mc.from = NULL;
mc.to = NULL;
- mc.moving_task = NULL;
spin_unlock(&mc.lock);
+ mc.moving_task = NULL;
+ mc.mm = NULL;
mem_cgroup_end_move(from);
memcg_oom_recover(from);
memcg_oom_recover(to);
@@ -4722,12 +4736,21 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
return 0;
/* We move charges only when we move a owner of the mm */
if (mm->owner == p) {
+ /*
+ * We do all the move charge works under one mmap_sem to
+ * avoid deadlock with down_write(&mmap_sem)
+ * -> try_charge() -> if (mc.moving_task) -> sleep.
+ */
+ down_read(&mm->mmap_sem);
+
VM_BUG_ON(mc.from);
VM_BUG_ON(mc.to);
VM_BUG_ON(mc.precharge);
VM_BUG_ON(mc.moved_charge);
VM_BUG_ON(mc.moved_swap);
VM_BUG_ON(mc.moving_task);
+ VM_BUG_ON(mc.mm);
+
mem_cgroup_start_move(from);
spin_lock(&mc.lock);
mc.from = from;
@@ -4735,14 +4758,16 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
mc.precharge = 0;
mc.moved_charge = 0;
mc.moved_swap = 0;
- mc.moving_task = current;
spin_unlock(&mc.lock);
+ mc.moving_task = current;
+ mc.mm = mm;
ret = mem_cgroup_precharge_mc(mm);
if (ret)
mem_cgroup_clear_mc();
- }
- mmput(mm);
+ /* We call up_read() and mmput() in clear_mc(). */
+ } else
+ mmput(mm);
}
return ret;
}
@@ -4830,7 +4855,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
struct vm_area_struct *vma;
lru_add_drain_all();
- down_read(&mm->mmap_sem);
+ /* We've already held the mmap_sem */
for (vma = mm->mmap; vma; vma = vma->vm_next) {
int ret;
struct mm_walk mem_cgroup_move_charge_walk = {
@@ -4849,7 +4874,6 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
*/
break;
}
- up_read(&mm->mmap_sem);
}
static void mem_cgroup_move_task(struct cgroup_subsys *ss,
@@ -4858,17 +4882,11 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
struct task_struct *p,
bool threadgroup)
{
- struct mm_struct *mm;
-
- if (!mc.to)
+ if (!mc.mm)
/* no need to move charge */
return;
- mm = get_task_mm(p);
- if (mm) {
- mem_cgroup_move_charge(mm);
- mmput(mm);
- }
+ mem_cgroup_move_charge(mc.mm);
mem_cgroup_clear_mc();
}
#else /* !CONFIG_MMU */
@@ -4909,10 +4927,20 @@ struct cgroup_subsys mem_cgroup_subsys = {
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static int __init enable_swap_account(char *s)
+{
+ /* consider enabled if no parameter or 1 is given */
+ if (!s || !strcmp(s, "1"))
+ really_do_swap_account = 1;
+ else if (!strcmp(s, "0"))
+ really_do_swap_account = 0;
+ return 1;
+}
+__setup("swapaccount", enable_swap_account);
static int __init disable_swap_account(char *s)
{
- really_do_swap_account = 0;
+ enable_swap_account("0");
return 1;
}
__setup("noswapaccount", disable_swap_account);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2d1bf7cf8851..4c5133873097 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -211,6 +211,7 @@ success:
mmu_notifier_invalidate_range_end(mm, start, end);
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+ perf_event_mmap(vma);
return 0;
fail:
@@ -299,7 +300,6 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
if (error)
goto out;
- perf_event_mmap(vma);
nstart = tmp;
if (nstart < prev->vm_end)
diff --git a/mm/nommu.c b/mm/nommu.c
index 3613517c7592..27a9ac588516 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1717,6 +1717,7 @@ void exit_mmap(struct mm_struct *mm)
mm->mmap = vma->vm_next;
delete_vma_from_mm(vma);
delete_vma(mm, vma);
+ cond_resched();
}
kleave("");
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 07a654486f75..e4092704c1a9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3008,14 +3008,6 @@ static __init_refok int __build_all_zonelists(void *data)
build_zonelist_cache(pgdat);
}
-#ifdef CONFIG_MEMORY_HOTPLUG
- /* Setup real pagesets for the new zone */
- if (data) {
- struct zone *zone = data;
- setup_zone_pageset(zone);
- }
-#endif
-
/*
* Initialize the boot_pagesets that are going to be used
* for bootstrapping processors. The real pagesets for
@@ -3064,7 +3056,11 @@ void build_all_zonelists(void *data)
} else {
/* we have to stop all cpus to guarantee there is no user
of zonelist */
- stop_machine(__build_all_zonelists, data, NULL);
+#ifdef CONFIG_MEMORY_HOTPLUG
+ if (data)
+ setup_zone_pageset((struct zone *)data);
+#endif
+ stop_machine(__build_all_zonelists, NULL, NULL);
/* cpuset refresh routine should be here */
}
vm_total_pages = nr_free_pagecache_pages();
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 8b1a2ce21ee5..38cc58b8b2b0 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -139,7 +139,6 @@ int walk_page_range(unsigned long addr, unsigned long end,
pgd_t *pgd;
unsigned long next;
int err = 0;
- struct vm_area_struct *vma;
if (addr >= end)
return err;
@@ -149,15 +148,17 @@ int walk_page_range(unsigned long addr, unsigned long end,
pgd = pgd_offset(walk->mm, addr);
do {
+ struct vm_area_struct *uninitialized_var(vma);
+
next = pgd_addr_end(addr, end);
+#ifdef CONFIG_HUGETLB_PAGE
/*
* handle hugetlb vma individually because pagetable walk for
* the hugetlb page is dependent on the architecture and
* we can't handled it in the same manner as non-huge pages.
*/
vma = find_vma(walk->mm, addr);
-#ifdef CONFIG_HUGETLB_PAGE
if (vma && is_vm_hugetlb_page(vma)) {
if (vma->vm_end < next)
next = vma->vm_end;
diff --git a/mm/slub.c b/mm/slub.c
index 8fd5401bb071..981fb730aa04 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3273,9 +3273,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
kfree(n);
kfree(s);
}
+err:
up_write(&slub_lock);
-err:
if (flags & SLAB_PANIC)
panic("Cannot create slabcache %s\n", name);
else
@@ -3862,6 +3862,7 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
x += sprintf(buf + x, " N%d=%lu",
node, nodes[node]);
#endif
+ up_read(&slub_lock);
kfree(nodes);
return x + sprintf(buf + x, "\n");
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b8a6fdc21312..d31d7ce52c0e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -913,7 +913,7 @@ keep_lumpy:
* back off and wait for congestion to clear because further reclaim
* will encounter the same problem
*/
- if (nr_dirty == nr_congested)
+ if (nr_dirty == nr_congested && nr_dirty != 0)
zone_set_flag(zone, ZONE_CONGESTED);
free_page_list(&free_pages);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 03:04:25 +0000