summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c21
-rw-r--r--mm/fremap.c11
-rw-r--r--mm/huge_memory.c4
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/hugetlb_cgroup.c69
-rw-r--r--mm/memcontrol.c231
-rw-r--r--mm/memory-failure.c5
-rw-r--r--mm/memory.c50
-rw-r--r--mm/mempolicy.c6
-rw-r--r--mm/mmap.c6
-rw-r--r--mm/mremap.c21
-rw-r--r--mm/oom_kill.c6
-rw-r--r--mm/page-writeback.c4
-rw-r--r--mm/rmap.c17
-rw-r--r--mm/shmem.c11
-rw-r--r--mm/slab.c10
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slub.c7
-rw-r--r--mm/swap.c29
-rw-r--r--mm/swapfile.c19
-rw-r--r--mm/vmpressure.c53
-rw-r--r--mm/vmstat.c6
-rw-r--r--mm/zbud.c2
23 files changed, 303 insertions, 289 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d014ee5fcbbd..37d9edcd14cf 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -180,7 +180,8 @@ static ssize_t name##_show(struct device *dev, \
struct backing_dev_info *bdi = dev_get_drvdata(dev); \
\
return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \
-}
+} \
+static DEVICE_ATTR_RW(name);
BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
@@ -231,16 +232,16 @@ static ssize_t stable_pages_required_show(struct device *dev,
return snprintf(page, PAGE_SIZE-1, "%d\n",
bdi_cap_stable_pages_required(bdi) ? 1 : 0);
}
+static DEVICE_ATTR_RO(stable_pages_required);
-#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
-
-static struct device_attribute bdi_dev_attrs[] = {
- __ATTR_RW(read_ahead_kb),
- __ATTR_RW(min_ratio),
- __ATTR_RW(max_ratio),
- __ATTR_RO(stable_pages_required),
- __ATTR_NULL,
+static struct attribute *bdi_dev_attrs[] = {
+ &dev_attr_read_ahead_kb.attr,
+ &dev_attr_min_ratio.attr,
+ &dev_attr_max_ratio.attr,
+ &dev_attr_stable_pages_required.attr,
+ NULL,
};
+ATTRIBUTE_GROUPS(bdi_dev);
static __init int bdi_class_init(void)
{
@@ -248,7 +249,7 @@ static __init int bdi_class_init(void)
if (IS_ERR(bdi_class))
return PTR_ERR(bdi_class);
- bdi_class->dev_attrs = bdi_dev_attrs;
+ bdi_class->dev_groups = bdi_dev_groups;
bdi_debug_init();
return 0;
}
diff --git a/mm/fremap.c b/mm/fremap.c
index 87da3590c61e..5bff08147768 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -57,17 +57,22 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long pgoff, pgprot_t prot)
{
int err = -ENOMEM;
- pte_t *pte;
+ pte_t *pte, ptfile;
spinlock_t *ptl;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
goto out;
- if (!pte_none(*pte))
+ ptfile = pgoff_to_pte(pgoff);
+
+ if (!pte_none(*pte)) {
+ if (pte_present(*pte) && pte_soft_dirty(*pte))
+ pte_file_mksoft_dirty(ptfile);
zap_pte(mm, vma, addr, pte);
+ }
- set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
+ set_pte_at(mm, addr, pte, ptfile);
/*
* We don't need to run update_mmu_cache() here because the "file pte"
* being installed by install_file_pte() is not a real pte - it's a
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 243e710c6039..a92012a71702 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1620,7 +1620,9 @@ static void __split_huge_page_refcount(struct page *page,
((1L << PG_referenced) |
(1L << PG_swapbacked) |
(1L << PG_mlocked) |
- (1L << PG_uptodate)));
+ (1L << PG_uptodate) |
+ (1L << PG_active) |
+ (1L << PG_unevictable)));
page_tail->flags |= (1L << PG_dirty);
/* clear PageTail before overwriting first_page */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 83aff0a4d093..b60f33080a28 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2490,7 +2490,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
mm = vma->vm_mm;
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
tlb_finish_mmu(&tlb, start, end);
}
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 9cea7de22ffb..bda8e44f6fde 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -36,21 +36,13 @@ static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
{
- return container_of(s, struct hugetlb_cgroup, css);
-}
-
-static inline
-struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup)
-{
- return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup,
- hugetlb_subsys_id));
+ return s ? container_of(s, struct hugetlb_cgroup, css) : NULL;
}
static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
{
- return hugetlb_cgroup_from_css(task_subsys_state(task,
- hugetlb_subsys_id));
+ return hugetlb_cgroup_from_css(task_css(task, hugetlb_subsys_id));
}
static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
@@ -58,17 +50,15 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
return (h_cg == root_h_cgroup);
}
-static inline struct hugetlb_cgroup *parent_hugetlb_cgroup(struct cgroup *cg)
+static inline struct hugetlb_cgroup *
+parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg)
{
- if (!cg->parent)
- return NULL;
- return hugetlb_cgroup_from_cgroup(cg->parent);
+ return hugetlb_cgroup_from_css(css_parent(&h_cg->css));
}
-static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
+static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
{
int idx;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg);
for (idx = 0; idx < hugetlb_max_hstate; idx++) {
if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
@@ -77,19 +67,18 @@ static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
return false;
}
-static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgroup)
+static struct cgroup_subsys_state *
+hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
+ struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
+ struct hugetlb_cgroup *h_cgroup;
int idx;
- struct cgroup *parent_cgroup;
- struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup;
h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
if (!h_cgroup)
return ERR_PTR(-ENOMEM);
- parent_cgroup = cgroup->parent;
- if (parent_cgroup) {
- parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup);
+ if (parent_h_cgroup) {
for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
res_counter_init(&h_cgroup->hugepage[idx],
&parent_h_cgroup->hugepage[idx]);
@@ -101,11 +90,11 @@ static struct cgroup_subsys_state *hugetlb_cgroup_css_alloc(struct cgroup *cgrou
return &h_cgroup->css;
}
-static void hugetlb_cgroup_css_free(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct hugetlb_cgroup *h_cgroup;
- h_cgroup = hugetlb_cgroup_from_cgroup(cgroup);
+ h_cgroup = hugetlb_cgroup_from_css(css);
kfree(h_cgroup);
}
@@ -117,15 +106,14 @@ static void hugetlb_cgroup_css_free(struct cgroup *cgroup)
* page reference and test for page active here. This function
* cannot fail.
*/
-static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup,
+static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
struct page *page)
{
int csize;
struct res_counter *counter;
struct res_counter *fail_res;
struct hugetlb_cgroup *page_hcg;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
- struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup);
+ struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
page_hcg = hugetlb_cgroup_from_page(page);
/*
@@ -155,8 +143,9 @@ out:
* Force the hugetlb cgroup to empty the hugetlb resources by moving them to
* the parent cgroup.
*/
-static void hugetlb_cgroup_css_offline(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css)
{
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
struct hstate *h;
struct page *page;
int idx = 0;
@@ -165,13 +154,13 @@ static void hugetlb_cgroup_css_offline(struct cgroup *cgroup)
for_each_hstate(h) {
spin_lock(&hugetlb_lock);
list_for_each_entry(page, &h->hugepage_activelist, lru)
- hugetlb_cgroup_move_parent(idx, cgroup, page);
+ hugetlb_cgroup_move_parent(idx, h_cg, page);
spin_unlock(&hugetlb_lock);
idx++;
}
cond_resched();
- } while (hugetlb_cgroup_have_usage(cgroup));
+ } while (hugetlb_cgroup_have_usage(h_cg));
}
int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
@@ -253,14 +242,15 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
return;
}
-static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft,
- struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static ssize_t hugetlb_cgroup_read(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct file *file,
+ char __user *buf, size_t nbytes,
+ loff_t *ppos)
{
u64 val;
char str[64];
int idx, name, len;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
idx = MEMFILE_IDX(cft->private);
name = MEMFILE_ATTR(cft->private);
@@ -270,12 +260,12 @@ static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft,
return simple_read_from_buffer(buf, nbytes, ppos, str, len);
}
-static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
- const char *buffer)
+static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
+ struct cftype *cft, const char *buffer)
{
int idx, name, ret;
unsigned long long val;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
idx = MEMFILE_IDX(cft->private);
name = MEMFILE_ATTR(cft->private);
@@ -300,10 +290,11 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
return ret;
}
-static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
+static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,
+ unsigned int event)
{
int idx, name, ret = 0;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
idx = MEMFILE_IDX(event);
name = MEMFILE_ATTR(event);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d12ca6f3c293..3b83957b6439 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -483,10 +483,9 @@ enum res_type {
*/
static DEFINE_MUTEX(memcg_create_mutex);
-static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
{
- return container_of(s, struct mem_cgroup, css);
+ return s ? container_of(s, struct mem_cgroup, css) : NULL;
}
/* Some nice accessors for the vmpressure. */
@@ -1035,12 +1034,6 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
preempt_enable();
}
-struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
-{
- return mem_cgroup_from_css(
- cgroup_subsys_state(cont, mem_cgroup_subsys_id));
-}
-
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
/*
@@ -1051,7 +1044,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
if (unlikely(!p))
return NULL;
- return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id));
+ return mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id));
}
struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
@@ -1084,20 +1077,11 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
struct mem_cgroup *last_visited)
{
- struct cgroup *prev_cgroup, *next_cgroup;
+ struct cgroup_subsys_state *prev_css, *next_css;
- /*
- * Root is not visited by cgroup iterators so it needs an
- * explicit visit.
- */
- if (!last_visited)
- return root;
-
- prev_cgroup = (last_visited == root) ? NULL
- : last_visited->css.cgroup;
+ prev_css = last_visited ? &last_visited->css : NULL;
skip_node:
- next_cgroup = cgroup_next_descendant_pre(
- prev_cgroup, root->css.cgroup);
+ next_css = css_next_descendant_pre(prev_css, &root->css);
/*
* Even if we found a group we have to make sure it is
@@ -1106,13 +1090,13 @@ skip_node:
* last_visited css is safe to use because it is
* protected by css_get and the tree walk is rcu safe.
*/
- if (next_cgroup) {
- struct mem_cgroup *mem = mem_cgroup_from_cont(
- next_cgroup);
+ if (next_css) {
+ struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
+
if (css_tryget(&mem->css))
return mem;
else {
- prev_cgroup = next_cgroup;
+ prev_css = next_css;
goto skip_node;
}
}
@@ -1525,10 +1509,8 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
int mem_cgroup_swappiness(struct mem_cgroup *memcg)
{
- struct cgroup *cgrp = memcg->css.cgroup;
-
/* root ? */
- if (cgrp->parent == NULL)
+ if (!css_parent(&memcg->css))
return vm_swappiness;
return memcg->swappiness;
@@ -1805,12 +1787,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
for_each_mem_cgroup_tree(iter, memcg) {
- struct cgroup *cgroup = iter->css.cgroup;
- struct cgroup_iter it;
+ struct css_task_iter it;
struct task_struct *task;
- cgroup_iter_start(cgroup, &it);
- while ((task = cgroup_iter_next(cgroup, &it))) {
+ css_task_iter_start(&iter->css, &it);
+ while ((task = css_task_iter_next(&it))) {
switch (oom_scan_process_thread(task, totalpages, NULL,
false)) {
case OOM_SCAN_SELECT:
@@ -1823,7 +1804,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
case OOM_SCAN_CONTINUE:
continue;
case OOM_SCAN_ABORT:
- cgroup_iter_end(cgroup, &it);
+ css_task_iter_end(&it);
mem_cgroup_iter_break(memcg, iter);
if (chosen)
put_task_struct(chosen);
@@ -1840,7 +1821,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
get_task_struct(chosen);
}
}
- cgroup_iter_end(cgroup, &it);
+ css_task_iter_end(&it);
}
if (!chosen)
@@ -2522,7 +2503,7 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
spin_unlock(&memcg->pcp_counter_lock);
}
-static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
+static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
unsigned long action,
void *hcpu)
{
@@ -2954,10 +2935,10 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
}
#ifdef CONFIG_SLABINFO
-static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
- struct seq_file *m)
+static int mem_cgroup_slabinfo_read(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *m)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct memcg_cache_params *params;
if (!memcg_can_account_kmem(memcg))
@@ -3195,11 +3176,11 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
if (!s->memcg_params)
return -ENOMEM;
- INIT_WORK(&s->memcg_params->destroy,
- kmem_cache_destroy_work_func);
if (memcg) {
s->memcg_params->memcg = memcg;
s->memcg_params->root_cache = root_cache;
+ INIT_WORK(&s->memcg_params->destroy,
+ kmem_cache_destroy_work_func);
} else
s->memcg_params->is_root_cache = true;
@@ -4943,10 +4924,10 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
*/
static inline bool __memcg_has_children(struct mem_cgroup *memcg)
{
- struct cgroup *pos;
+ struct cgroup_subsys_state *pos;
/* bounce at first found */
- cgroup_for_each_child(pos, memcg->css.cgroup)
+ css_for_each_child(pos, &memcg->css)
return true;
return false;
}
@@ -5002,9 +4983,10 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
return 0;
}
-static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
+static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
+ unsigned int event)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
int ret;
if (mem_cgroup_is_root(memcg))
@@ -5017,21 +4999,18 @@ static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
}
-static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
+static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
{
- return mem_cgroup_from_cont(cont)->use_hierarchy;
+ return mem_cgroup_from_css(css)->use_hierarchy;
}
-static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
- u64 val)
+static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
{
int retval = 0;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
- struct cgroup *parent = cont->parent;
- struct mem_cgroup *parent_memcg = NULL;
-
- if (parent)
- parent_memcg = mem_cgroup_from_cont(parent);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css));
mutex_lock(&memcg_create_mutex);
@@ -5101,11 +5080,11 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
return val << PAGE_SHIFT;
}
-static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
- struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static ssize_t mem_cgroup_read(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct file *file,
+ char __user *buf, size_t nbytes, loff_t *ppos)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
char str[64];
u64 val;
int name, len;
@@ -5138,11 +5117,11 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
return simple_read_from_buffer(buf, nbytes, ppos, str, len);
}
-static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
+static int memcg_update_kmem_limit(struct cgroup_subsys_state *css, u64 val)
{
int ret = -EINVAL;
#ifdef CONFIG_MEMCG_KMEM
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
/*
* For simplicity, we won't allow this to be disabled. It also can't
* be changed if the cgroup has children already, or if tasks had
@@ -5158,7 +5137,7 @@ static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
mutex_lock(&memcg_create_mutex);
mutex_lock(&set_limit_mutex);
if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
- if (cgroup_task_count(cont) || memcg_has_children(memcg)) {
+ if (cgroup_task_count(css->cgroup) || memcg_has_children(memcg)) {
ret = -EBUSY;
goto out;
}
@@ -5228,10 +5207,10 @@ out:
* The user of this function is...
* RES_LIMIT.
*/
-static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
+static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
const char *buffer)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
enum res_type type;
int name;
unsigned long long val;
@@ -5255,7 +5234,7 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
else if (type == _MEMSWAP)
ret = mem_cgroup_resize_memsw_limit(memcg, val);
else if (type == _KMEM)
- ret = memcg_update_kmem_limit(cont, val);
+ ret = memcg_update_kmem_limit(css, val);
else
return -EINVAL;
break;
@@ -5283,18 +5262,15 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
unsigned long long *mem_limit, unsigned long long *memsw_limit)
{
- struct cgroup *cgroup;
unsigned long long min_limit, min_memsw_limit, tmp;
min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
- cgroup = memcg->css.cgroup;
if (!memcg->use_hierarchy)
goto out;
- while (cgroup->parent) {
- cgroup = cgroup->parent;
- memcg = mem_cgroup_from_cont(cgroup);
+ while (css_parent(&memcg->css)) {
+ memcg = mem_cgroup_from_css(css_parent(&memcg->css));
if (!memcg->use_hierarchy)
break;
tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -5307,9 +5283,9 @@ out:
*memsw_limit = min_memsw_limit;
}
-static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
+static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
int name;
enum res_type type;
@@ -5342,17 +5318,17 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
return 0;
}
-static u64 mem_cgroup_move_charge_read(struct cgroup *cgrp,
+static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
- return mem_cgroup_from_cont(cgrp)->move_charge_at_immigrate;
+ return mem_cgroup_from_css(css)->move_charge_at_immigrate;
}
#ifdef CONFIG_MMU
-static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
+static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
if (val >= (1 << NR_MOVE_TYPE))
return -EINVAL;
@@ -5367,7 +5343,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
return 0;
}
#else
-static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
+static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
return -ENOSYS;
@@ -5375,13 +5351,13 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
#endif
#ifdef CONFIG_NUMA
-static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
- struct seq_file *m)
+static int memcg_numa_stat_show(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct seq_file *m)
{
int nid;
unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
unsigned long node_nr;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
seq_printf(m, "total=%lu", total_nr);
@@ -5426,10 +5402,10 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
}
-static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_stat_show(struct cgroup_subsys_state *css, struct cftype *cft,
struct seq_file *m)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup *mi;
unsigned int i;
@@ -5513,27 +5489,23 @@ static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
return 0;
}
-static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft)
+static u64 mem_cgroup_swappiness_read(struct cgroup_subsys_state *css,
+ struct cftype *cft)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
return mem_cgroup_swappiness(memcg);
}
-static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
- u64 val)
+static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
+ struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup *parent;
-
- if (val > 100)
- return -EINVAL;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
- if (cgrp->parent == NULL)
+ if (val > 100 || !parent)
return -EINVAL;
- parent = mem_cgroup_from_cont(cgrp->parent);
-
mutex_lock(&memcg_create_mutex);
/* If under hierarchy, only empty-root can set this value */
@@ -5636,10 +5608,10 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg)
mem_cgroup_oom_notify_cb(iter);
}
-static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
+static int mem_cgroup_usage_register_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_thresholds *thresholds;
struct mem_cgroup_threshold_ary *new;
enum res_type type = MEMFILE_TYPE(cft->private);
@@ -5719,10 +5691,10 @@ unlock:
return ret;
}
-static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_usage_unregister_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_thresholds *thresholds;
struct mem_cgroup_threshold_ary *new;
enum res_type type = MEMFILE_TYPE(cft->private);
@@ -5798,10 +5770,10 @@ unlock:
mutex_unlock(&memcg->thresholds_lock);
}
-static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
+static int mem_cgroup_oom_register_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd, const char *args)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_eventfd_list *event;
enum res_type type = MEMFILE_TYPE(cft->private);
@@ -5823,10 +5795,10 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
return 0;
}
-static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
+static void mem_cgroup_oom_unregister_event(struct cgroup_subsys_state *css,
struct cftype *cft, struct eventfd_ctx *eventfd)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
struct mem_cgroup_eventfd_list *ev, *tmp;
enum res_type type = MEMFILE_TYPE(cft->private);
@@ -5844,10 +5816,10 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
spin_unlock(&memcg_oom_lock);
}
-static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
+static int mem_cgroup_oom_control_read(struct cgroup_subsys_state *css,
struct cftype *cft, struct cgroup_map_cb *cb)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
cb->fill(cb, "oom_kill_disable", memcg->oom_kill_disable);
@@ -5858,18 +5830,16 @@ static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
return 0;
}
-static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
+static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
struct cftype *cft, u64 val)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
- struct mem_cgroup *parent;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(&memcg->css));
/* cannot set to root cgroup and only 0 and 1 are allowed */
- if (!cgrp->parent || !((val == 0) || (val == 1)))
+ if (!parent || !((val == 0) || (val == 1)))
return -EINVAL;
- parent = mem_cgroup_from_cont(cgrp->parent);
-
mutex_lock(&memcg_create_mutex);
/* oom-kill-disable is a flag for subhierarchy. */
if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
@@ -6228,7 +6198,7 @@ static void __init mem_cgroup_soft_limit_tree_init(void)
}
static struct cgroup_subsys_state * __ref
-mem_cgroup_css_alloc(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct mem_cgroup *memcg;
long error = -ENOMEM;
@@ -6243,7 +6213,7 @@ mem_cgroup_css_alloc(struct cgroup *cont)
goto free_out;
/* root ? */
- if (cont->parent == NULL) {
+ if (parent_css == NULL) {
root_mem_cgroup = memcg;
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
@@ -6265,17 +6235,16 @@ free_out:
}
static int
-mem_cgroup_css_online(struct cgroup *cont)
+mem_cgroup_css_online(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg, *parent;
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+ struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
int error = 0;
- if (!cont->parent)
+ if (!parent)
return 0;
mutex_lock(&memcg_create_mutex);
- memcg = mem_cgroup_from_cont(cont);
- parent = mem_cgroup_from_cont(cont->parent);
memcg->use_hierarchy = parent->use_hierarchy;
memcg->oom_kill_disable = parent->oom_kill_disable;
@@ -6326,20 +6295,21 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
mem_cgroup_iter_invalidate(root_mem_cgroup);
}
-static void mem_cgroup_css_offline(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
kmem_cgroup_css_offline(memcg);
mem_cgroup_invalidate_reclaim_iterators(memcg);
mem_cgroup_reparent_charges(memcg);
mem_cgroup_destroy_all_caches(memcg);
+ vmpressure_cleanup(&memcg->vmpressure);
}
-static void mem_cgroup_css_free(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
{
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
memcg_destroy_kmem(memcg);
__mem_cgroup_free(memcg);
@@ -6709,12 +6679,12 @@ static void mem_cgroup_clear_mc(void)
mem_cgroup_end_move(from);
}
-static int mem_cgroup_can_attach(struct cgroup *cgroup,
+static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p = cgroup_taskset_first(tset);
int ret = 0;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
unsigned long move_charge_at_immigrate;
/*
@@ -6756,7 +6726,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup,
return ret;
}
-static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
mem_cgroup_clear_mc();
@@ -6904,7 +6874,7 @@ retry:
up_read(&mm->mmap_sem);
}
-static void mem_cgroup_move_task(struct cgroup *cont,
+static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p = cgroup_taskset_first(tset);
@@ -6919,16 +6889,16 @@ static void mem_cgroup_move_task(struct cgroup *cont,
mem_cgroup_clear_mc();
}
#else /* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup *cgroup,
+static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
return 0;
}
-static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
}
-static void mem_cgroup_move_task(struct cgroup *cont,
+static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
}
@@ -6938,15 +6908,15 @@ static void mem_cgroup_move_task(struct cgroup *cont,
* Cgroup retains root cgroups across [un]mount cycles making it necessary
* to verify sane_behavior flag on each mount attempt.
*/
-static void mem_cgroup_bind(struct cgroup *root)
+static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
{
/*
* use_hierarchy is forced with sane_behavior. cgroup core
* guarantees that @root doesn't have any children, so turning it
* on for the root memcg is enough.
*/
- if (cgroup_sane_behavior(root))
- mem_cgroup_from_cont(root)->use_hierarchy = true;
+ if (cgroup_sane_behavior(root_css->cgroup))
+ mem_cgroup_from_css(root_css)->use_hierarchy = true;
}
struct cgroup_subsys mem_cgroup_subsys = {
@@ -6968,7 +6938,6 @@ struct cgroup_subsys mem_cgroup_subsys = {
#ifdef CONFIG_MEMCG_SWAP
static int __init enable_swap_account(char *s)
{
- /* consider enabled if no parameter or 1 is given */
if (!strcmp(s, "1"))
really_do_swap_account = 1;
else if (!strcmp(s, "0"))
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2c13aa7a0164..55d7c8026ab0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1286,7 +1286,10 @@ static void memory_failure_work_func(struct work_struct *work)
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
- memory_failure(entry.pfn, entry.trapno, entry.flags);
+ if (entry.flags & MF_SOFT_OFFLINE)
+ soft_offline_page(pfn_to_page(entry.pfn), entry.flags);
+ else
+ memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}
diff --git a/mm/memory.c b/mm/memory.c
index 1ce2e2a734fc..b3c6bf9a398e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -209,14 +209,15 @@ static int tlb_next_batch(struct mmu_gather *tlb)
* tear-down from @mm. The @fullmm argument is used when @mm is without
* users and we're going to destroy the full address space (exit/execve).
*/
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
tlb->need_flush_all = 0;
- tlb->start = -1UL;
- tlb->end = 0;
+ tlb->start = start;
+ tlb->end = end;
tlb->need_flush = 0;
tlb->local.next = NULL;
tlb->local.nr = 0;
@@ -256,8 +257,6 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
{
struct mmu_gather_batch *batch, *next;
- tlb->start = start;
- tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
@@ -1099,7 +1098,6 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
spinlock_t *ptl;
pte_t *start_pte;
pte_t *pte;
- unsigned long range_start = addr;
again:
init_rss_vec(rss);
@@ -1141,9 +1139,12 @@ again:
continue;
if (unlikely(details) && details->nonlinear_vma
&& linear_page_index(details->nonlinear_vma,
- addr) != page->index)
- set_pte_at(mm, addr, pte,
- pgoff_to_pte(page->index));
+ addr) != page->index) {
+ pte_t ptfile = pgoff_to_pte(page->index);
+ if (pte_soft_dirty(ptent))
+ pte_file_mksoft_dirty(ptfile);
+ set_pte_at(mm, addr, pte, ptfile);
+ }
if (PageAnon(page))
rss[MM_ANONPAGES]--;
else {
@@ -1202,17 +1203,25 @@ again:
* and page-free while holding it.
*/
if (force_flush) {
+ unsigned long old_end;
+
force_flush = 0;
-#ifdef HAVE_GENERIC_MMU_GATHER
- tlb->start = range_start;
+ /*
+ * Flush the TLB just for the previous segment,
+ * then update the range to be the remaining
+ * TLB range.
+ */
+ old_end = tlb->end;
tlb->end = addr;
-#endif
+
tlb_flush_mmu(tlb);
- if (addr != end) {
- range_start = addr;
+
+ tlb->start = addr;
+ tlb->end = old_end;
+
+ if (addr != end)
goto again;
- }
}
return addr;
@@ -1397,7 +1406,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end = start + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, start, end);
for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
@@ -1423,7 +1432,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
unsigned long end = address + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, address, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, address, end);
unmap_single_vma(&tlb, vma, address, end, details);
@@ -3115,6 +3124,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
exclusive = 1;
}
flush_icache_page(vma, page);
+ if (pte_swp_soft_dirty(orig_pte))
+ pte = pte_mksoft_dirty(pte);
set_pte_at(mm, address, page_table, pte);
if (page == swapcache)
do_page_add_anon_rmap(page, vma, address, exclusive);
@@ -3408,6 +3419,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
entry = mk_pte(page, vma->vm_page_prot);
if (flags & FAULT_FLAG_WRITE)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+ pte_mksoft_dirty(entry);
if (anon) {
inc_mm_counter_fast(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
@@ -4066,6 +4079,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
return len;
}
+EXPORT_SYMBOL_GPL(generic_access_phys);
#endif
/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 74310017296e..4baf12e534d1 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -732,7 +732,10 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
if (prev) {
vma = prev;
next = vma->vm_next;
- continue;
+ if (mpol_equal(vma_policy(vma), new_pol))
+ continue;
+ /* vma_merge() joined vma && vma->next, case 8 */
+ goto replace;
}
if (vma->vm_start != vmstart) {
err = split_vma(vma->vm_mm, vma, vmstart, 1);
@@ -744,6 +747,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
if (err)
goto out;
}
+ replace:
err = vma_replace_policy(vma, new_pol);
if (err)
goto out;
diff --git a/mm/mmap.c b/mm/mmap.c
index fbad7b091090..f9c97d10b873 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -865,7 +865,7 @@ again: remove_next = 1 + (end > next->vm_end);
if (next->anon_vma)
anon_vma_merge(vma, next);
mm->map_count--;
- vma_set_policy(vma, vma_policy(next));
+ mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
/*
* In mprotect's case 6 (see comments on vma_merge),
@@ -2336,7 +2336,7 @@ static void unmap_region(struct mm_struct *mm,
struct mmu_gather tlb;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
unmap_vmas(&tlb, vma, start, end);
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
@@ -2709,7 +2709,7 @@ void exit_mmap(struct mm_struct *mm)
lru_add_drain();
flush_cache_mm(mm);
- tlb_gather_mmu(&tlb, mm, 1);
+ tlb_gather_mmu(&tlb, mm, 0, -1);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
diff --git a/mm/mremap.c b/mm/mremap.c
index 457d34ef3bf2..0843feb66f3d 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -15,6 +15,7 @@
#include <linux/swap.h>
#include <linux/capability.h>
#include <linux/fs.h>
+#include <linux/swapops.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/syscalls.h>
@@ -69,6 +70,23 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
return pmd;
}
+static pte_t move_soft_dirty_pte(pte_t pte)
+{
+ /*
+ * Set soft dirty bit so we can notice
+ * in userspace the ptes were moved.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ if (pte_present(pte))
+ pte = pte_mksoft_dirty(pte);
+ else if (is_swap_pte(pte))
+ pte = pte_swp_mksoft_dirty(pte);
+ else if (pte_file(pte))
+ pte = pte_file_mksoft_dirty(pte);
+#endif
+ return pte;
+}
+
static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
unsigned long old_addr, unsigned long old_end,
struct vm_area_struct *new_vma, pmd_t *new_pmd,
@@ -126,7 +144,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
continue;
pte = ptep_get_and_clear(mm, old_addr, old_pte);
pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
- set_pte_at(mm, new_addr, new_pte, pte_mksoft_dirty(pte));
+ pte = move_soft_dirty_pte(pte);
+ set_pte_at(mm, new_addr, new_pte, pte);
}
arch_leave_lazy_mmu_mode();
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 79e451a78c9e..98e75f2ac7bc 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -288,7 +288,7 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
/*
* Simple selection loop. We chose the process with the highest
- * number of 'points'.
+ * number of 'points'. Returns -1 on scan abort.
*
* (not docbooked, we don't want this one cluttering up the manual)
*/
@@ -314,7 +314,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
continue;
case OOM_SCAN_ABORT:
rcu_read_unlock();
- return ERR_PTR(-1UL);
+ return (struct task_struct *)(-1UL);
case OOM_SCAN_OK:
break;
};
@@ -657,7 +657,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
panic("Out of memory and no killable processes...\n");
}
- if (PTR_ERR(p) != -1UL) {
+ if (p != (void *)-1UL) {
oom_kill_process(p, gfp_mask, order, points, totalpages, NULL,
nodemask, "Out of memory");
killed = 1;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4514ad7415c3..3f0c895c71fe 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1619,7 +1619,7 @@ void writeback_set_ratelimit(void)
ratelimit_pages = 16;
}
-static int __cpuinit
+static int
ratelimit_handler(struct notifier_block *self, unsigned long action,
void *hcpu)
{
@@ -1634,7 +1634,7 @@ ratelimit_handler(struct notifier_block *self, unsigned long action,
}
}
-static struct notifier_block __cpuinitdata ratelimit_nb = {
+static struct notifier_block ratelimit_nb = {
.notifier_call = ratelimit_handler,
.next = NULL,
};
diff --git a/mm/rmap.c b/mm/rmap.c
index cd356df4f71a..07748e68b729 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -873,9 +873,6 @@ int page_referenced(struct page *page,
vm_flags);
if (we_locked)
unlock_page(page);
-
- if (page_test_and_clear_young(page_to_pfn(page)))
- referenced++;
}
out:
return referenced;
@@ -1236,6 +1233,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_entry_to_pte(make_hwpoison_entry(page)));
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
+ pte_t swp_pte;
if (PageSwapCache(page)) {
/*
@@ -1264,7 +1262,10 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
entry = make_migration_entry(page, pte_write(pteval));
}
- set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+ swp_pte = swp_entry_to_pte(entry);
+ if (pte_soft_dirty(pteval))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ set_pte_at(mm, address, pte, swp_pte);
BUG_ON(pte_file(*pte));
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(TTU_ACTION(flags) == TTU_MIGRATION)) {
@@ -1401,8 +1402,12 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
pteval = ptep_clear_flush(vma, address, pte);
/* If nonlinear, store the file page offset in the pte. */
- if (page->index != linear_page_index(vma, address))
- set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
+ if (page->index != linear_page_index(vma, address)) {
+ pte_t ptfile = pgoff_to_pte(page->index);
+ if (pte_soft_dirty(pteval))
+ pte_file_mksoft_dirty(ptfile);
+ set_pte_at(mm, address, pte, ptfile);
+ }
/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
diff --git a/mm/shmem.c b/mm/shmem.c
index a87990cf9f94..e43dc555069d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1798,7 +1798,8 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
}
}
- offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
+ if (offset >= 0)
+ offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
mutex_unlock(&inode->i_mutex);
return offset;
}
@@ -2908,14 +2909,8 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
/* common code */
-static char *shmem_dname(struct dentry *dentry, char *buffer, int buflen)
-{
- return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
- dentry->d_name.name);
-}
-
static struct dentry_operations anon_ops = {
- .d_dname = shmem_dname
+ .d_dname = simple_dname
};
/**
diff --git a/mm/slab.c b/mm/slab.c
index 35cb0c861508..2580db062df9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -787,7 +787,7 @@ static void next_reap_node(void)
* the CPUs getting into lockstep and contending for the global cache chain
* lock.
*/
-static void __cpuinit start_cpu_timer(int cpu)
+static void start_cpu_timer(int cpu)
{
struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
@@ -1186,7 +1186,7 @@ static inline int slabs_tofree(struct kmem_cache *cachep,
return (n->free_objects + cachep->num - 1) / cachep->num;
}
-static void __cpuinit cpuup_canceled(long cpu)
+static void cpuup_canceled(long cpu)
{
struct kmem_cache *cachep;
struct kmem_cache_node *n = NULL;
@@ -1251,7 +1251,7 @@ free_array_cache:
}
}
-static int __cpuinit cpuup_prepare(long cpu)
+static int cpuup_prepare(long cpu)
{
struct kmem_cache *cachep;
struct kmem_cache_node *n = NULL;
@@ -1334,7 +1334,7 @@ bad:
return -ENOMEM;
}
-static int __cpuinit cpuup_callback(struct notifier_block *nfb,
+static int cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
@@ -1390,7 +1390,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
return notifier_from_errno(err);
}
-static struct notifier_block __cpuinitdata cpucache_notifier = {
+static struct notifier_block cpucache_notifier = {
&cpuup_callback, NULL, 0
};
diff --git a/mm/slab.h b/mm/slab.h
index 620ceeddbe1a..a535033f7e9a 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -162,6 +162,8 @@ static inline const char *cache_name(struct kmem_cache *s)
static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
{
+ if (!s->memcg_params)
+ return NULL;
return s->memcg_params->memcg_caches[idx];
}
diff --git a/mm/slub.c b/mm/slub.c
index 3b482c863002..e3ba1f2cf60c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1968,9 +1968,6 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
int pages;
int pobjects;
- if (!s->cpu_partial)
- return;
-
do {
pages = 0;
pobjects = 0;
@@ -3773,7 +3770,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
* Use the cpu notifier to insure that the cpu slabs are flushed when
* necessary.
*/
-static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
+static int slab_cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
@@ -3799,7 +3796,7 @@ static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata slab_notifier = {
+static struct notifier_block slab_notifier = {
.notifier_call = slab_cpuup_callback
};
diff --git a/mm/swap.c b/mm/swap.c
index 4a1d0d2c52fa..62b78a6e224f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -512,12 +512,7 @@ EXPORT_SYMBOL(__lru_cache_add);
*/
void lru_cache_add(struct page *page)
{
- if (PageActive(page)) {
- VM_BUG_ON(PageUnevictable(page));
- } else if (PageUnevictable(page)) {
- VM_BUG_ON(PageActive(page));
- }
-
+ VM_BUG_ON(PageActive(page) && PageUnevictable(page));
VM_BUG_ON(PageLRU(page));
__lru_cache_add(page);
}
@@ -539,6 +534,7 @@ void add_page_to_unevictable_list(struct page *page)
spin_lock_irq(&zone->lru_lock);
lruvec = mem_cgroup_page_lruvec(page, zone);
+ ClearPageActive(page);
SetPageUnevictable(page);
SetPageLRU(page);
add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE);
@@ -774,8 +770,6 @@ EXPORT_SYMBOL(__pagevec_release);
void lru_add_page_tail(struct page *page, struct page *page_tail,
struct lruvec *lruvec, struct list_head *list)
{
- int uninitialized_var(active);
- enum lru_list lru;
const int file = 0;
VM_BUG_ON(!PageHead(page));
@@ -787,20 +781,6 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
if (!list)
SetPageLRU(page_tail);
- if (page_evictable(page_tail)) {
- if (PageActive(page)) {
- SetPageActive(page_tail);
- active = 1;
- lru = LRU_ACTIVE_ANON;
- } else {
- active = 0;
- lru = LRU_INACTIVE_ANON;
- }
- } else {
- SetPageUnevictable(page_tail);
- lru = LRU_UNEVICTABLE;
- }
-
if (likely(PageLRU(page)))
list_add_tail(&page_tail->lru, &page->lru);
else if (list) {
@@ -816,13 +796,13 @@ void lru_add_page_tail(struct page *page, struct page *page_tail,
* Use the standard add function to put page_tail on the list,
* but then correct its position so they all end up in order.
*/
- add_page_to_lru_list(page_tail, lruvec, lru);
+ add_page_to_lru_list(page_tail, lruvec, page_lru(page_tail));
list_head = page_tail->lru.prev;
list_move_tail(&page_tail->lru, list_head);
}
if (!PageUnevictable(page))
- update_page_reclaim_stat(lruvec, file, active);
+ update_page_reclaim_stat(lruvec, file, PageActive(page_tail));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -833,7 +813,6 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
int active = PageActive(page);
enum lru_list lru = page_lru(page);
- VM_BUG_ON(PageUnevictable(page));
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 36af6eeaa67e..6cf2e60983b7 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -866,6 +866,21 @@ unsigned int count_swap_pages(int type, int free)
}
#endif /* CONFIG_HIBERNATION */
+static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ /*
+ * When pte keeps soft dirty bit the pte generated
+ * from swap entry does not has it, still it's same
+ * pte from logical point of view.
+ */
+ pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
+ return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
+#else
+ return pte_same(pte, swp_pte);
+#endif
+}
+
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
@@ -892,7 +907,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+ if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
mem_cgroup_cancel_charge_swapin(memcg);
ret = 0;
goto out;
@@ -947,7 +962,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
- if (unlikely(pte_same(*pte, swp_pte))) {
+ if (unlikely(maybe_same_pte(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 736a6011c2c8..e0f62837c3f4 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -74,15 +74,10 @@ static struct vmpressure *work_to_vmpressure(struct work_struct *work)
return container_of(work, struct vmpressure, work);
}
-static struct vmpressure *cg_to_vmpressure(struct cgroup *cg)
-{
- return css_to_vmpressure(cgroup_subsys_state(cg, mem_cgroup_subsys_id));
-}
-
static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr)
{
- struct cgroup *cg = vmpressure_to_css(vmpr)->cgroup;
- struct mem_cgroup *memcg = mem_cgroup_from_cont(cg);
+ struct cgroup_subsys_state *css = vmpressure_to_css(vmpr);
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
memcg = parent_mem_cgroup(memcg);
if (!memcg)
@@ -180,12 +175,12 @@ static void vmpressure_work_fn(struct work_struct *work)
if (!vmpr->scanned)
return;
- mutex_lock(&vmpr->sr_lock);
+ spin_lock(&vmpr->sr_lock);
scanned = vmpr->scanned;
reclaimed = vmpr->reclaimed;
vmpr->scanned = 0;
vmpr->reclaimed = 0;
- mutex_unlock(&vmpr->sr_lock);
+ spin_unlock(&vmpr->sr_lock);
do {
if (vmpressure_event(vmpr, scanned, reclaimed))
@@ -240,13 +235,13 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
if (!scanned)
return;
- mutex_lock(&vmpr->sr_lock);
+ spin_lock(&vmpr->sr_lock);
vmpr->scanned += scanned;
vmpr->reclaimed += reclaimed;
scanned = vmpr->scanned;
- mutex_unlock(&vmpr->sr_lock);
+ spin_unlock(&vmpr->sr_lock);
- if (scanned < vmpressure_win || work_pending(&vmpr->work))
+ if (scanned < vmpressure_win)
return;
schedule_work(&vmpr->work);
}
@@ -283,7 +278,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
/**
* vmpressure_register_event() - Bind vmpressure notifications to an eventfd
- * @cg: cgroup that is interested in vmpressure notifications
+ * @css: css that is interested in vmpressure notifications
* @cft: cgroup control files handle
* @eventfd: eventfd context to link notifications with
* @args: event arguments (used to set up a pressure level threshold)
@@ -298,10 +293,11 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
* cftype).register_event, and then cgroup core will handle everything by
* itself.
*/
-int vmpressure_register_event(struct cgroup *cg, struct cftype *cft,
- struct eventfd_ctx *eventfd, const char *args)
+int vmpressure_register_event(struct cgroup_subsys_state *css,
+ struct cftype *cft, struct eventfd_ctx *eventfd,
+ const char *args)
{
- struct vmpressure *vmpr = cg_to_vmpressure(cg);
+ struct vmpressure *vmpr = css_to_vmpressure(css);
struct vmpressure_event *ev;
int level;
@@ -329,7 +325,7 @@ int vmpressure_register_event(struct cgroup *cg, struct cftype *cft,
/**
* vmpressure_unregister_event() - Unbind eventfd from vmpressure
- * @cg: cgroup handle
+ * @css: css handle
* @cft: cgroup control files handle
* @eventfd: eventfd context that was used to link vmpressure with the @cg
*
@@ -341,10 +337,11 @@ int vmpressure_register_event(struct cgroup *cg, struct cftype *cft,
* cftype).unregister_event, and then cgroup core will handle everything
* by itself.
*/
-void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft,
+void vmpressure_unregister_event(struct cgroup_subsys_state *css,
+ struct cftype *cft,
struct eventfd_ctx *eventfd)
{
- struct vmpressure *vmpr = cg_to_vmpressure(cg);
+ struct vmpressure *vmpr = css_to_vmpressure(css);
struct vmpressure_event *ev;
mutex_lock(&vmpr->events_lock);
@@ -367,8 +364,24 @@ void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft,
*/
void vmpressure_init(struct vmpressure *vmpr)
{
- mutex_init(&vmpr->sr_lock);
+ spin_lock_init(&vmpr->sr_lock);
mutex_init(&vmpr->events_lock);
INIT_LIST_HEAD(&vmpr->events);
INIT_WORK(&vmpr->work, vmpressure_work_fn);
}
+
+/**
+ * vmpressure_cleanup() - shuts down vmpressure control structure
+ * @vmpr: Structure to be cleaned up
+ *
+ * This function should be called before the structure in which it is
+ * embedded is cleaned up.
+ */
+void vmpressure_cleanup(struct vmpressure *vmpr)
+{
+ /*
+ * Make sure there is no pending work before eventfd infrastructure
+ * goes away.
+ */
+ flush_work(&vmpr->work);
+}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f42745e65780..20c2ef4458fa 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1182,7 +1182,7 @@ static void vmstat_update(struct work_struct *w)
round_jiffies_relative(sysctl_stat_interval));
}
-static void __cpuinit start_cpu_timer(int cpu)
+static void start_cpu_timer(int cpu)
{
struct delayed_work *work = &per_cpu(vmstat_work, cpu);
@@ -1194,7 +1194,7 @@ static void __cpuinit start_cpu_timer(int cpu)
* Use the cpu notifier to insure that the thresholds are recalculated
* when necessary.
*/
-static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
+static int vmstat_cpuup_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
@@ -1226,7 +1226,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static struct notifier_block __cpuinitdata vmstat_notifier =
+static struct notifier_block vmstat_notifier =
{ &vmstat_cpuup_callback, NULL, 0 };
#endif
diff --git a/mm/zbud.c b/mm/zbud.c
index 9bb4710e3589..ad1e781284fd 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -257,7 +257,7 @@ int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp,
if (size <= 0 || gfp & __GFP_HIGHMEM)
return -EINVAL;
- if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED)
+ if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
return -ENOSPC;
chunks = size_to_chunks(size);
spin_lock(&pool->lock);
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-23 23:26:18 +0000