aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/hugetlb.c6
-rw-r--r--mm/memcontrol.c179
-rw-r--r--mm/mmap.c24
-rw-r--r--mm/nommu.c23
-rw-r--r--mm/page_alloc.c37
-rw-r--r--mm/slub.c2
-rw-r--r--mm/swapfile.c6
-rw-r--r--mm/vmscan.c7
8 files changed, 163 insertions, 121 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2c37c67ed8c..bbf953eeb58 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -199,7 +199,8 @@ static struct page *alloc_fresh_huge_page_node(int nid)
struct page *page;
page = alloc_pages_node(nid,
- htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
+ htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ __GFP_REPEAT|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
if (page) {
if (arch_prepare_hugepage(page)) {
@@ -294,7 +295,8 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
}
spin_unlock(&hugetlb_lock);
- page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+ page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+ __GFP_REPEAT|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
spin_lock(&hugetlb_lock);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2e0bfc93484..33add96cd5f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -26,15 +26,18 @@
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
+#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
#include <asm/uaccess.h>
struct cgroup_subsys mem_cgroup_subsys;
static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
+static struct kmem_cache *page_cgroup_cache;
/*
* Statistics for memory cgroup.
@@ -236,26 +239,12 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
css);
}
-static struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
struct mem_cgroup, css);
}
-void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
-{
- struct mem_cgroup *mem;
-
- mem = mem_cgroup_from_task(p);
- css_get(&mem->css);
- mm->mem_cgroup = mem;
-}
-
-void mm_free_cgroup(struct mm_struct *mm)
-{
- css_put(&mm->mem_cgroup->css);
-}
-
static inline int page_cgroup_locked(struct page *page)
{
return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
@@ -287,10 +276,10 @@ static void unlock_page_cgroup(struct page *page)
bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
}
-static void __mem_cgroup_remove_list(struct page_cgroup *pc)
+static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
+ struct page_cgroup *pc)
{
int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
if (from)
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
@@ -301,10 +290,10 @@ static void __mem_cgroup_remove_list(struct page_cgroup *pc)
list_del_init(&pc->lru);
}
-static void __mem_cgroup_add_list(struct page_cgroup *pc)
+static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
+ struct page_cgroup *pc)
{
int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
- struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
if (!to) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
@@ -476,6 +465,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
int zid = zone_idx(z);
struct mem_cgroup_per_zone *mz;
+ BUG_ON(!mem_cont);
mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
if (active)
src = &mz->active_list;
@@ -560,7 +550,7 @@ retry:
}
unlock_page_cgroup(page);
- pc = kzalloc(sizeof(struct page_cgroup), gfp_mask);
+ pc = kmem_cache_zalloc(page_cgroup_cache, gfp_mask);
if (pc == NULL)
goto err;
@@ -574,7 +564,7 @@ retry:
mm = &init_mm;
rcu_read_lock();
- mem = rcu_dereference(mm->mem_cgroup);
+ mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
/*
* For every charge from the cgroup, increment reference count
*/
@@ -602,7 +592,6 @@ retry:
mem_cgroup_out_of_memory(mem, gfp_mask);
goto out;
}
- congestion_wait(WRITE, HZ/10);
}
pc->ref_cnt = 1;
@@ -610,7 +599,7 @@ retry:
pc->page = page;
pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
- pc->flags |= PAGE_CGROUP_FLAG_CACHE;
+ pc->flags = PAGE_CGROUP_FLAG_CACHE;
lock_page_cgroup(page);
if (page_get_page_cgroup(page)) {
@@ -622,14 +611,14 @@ retry:
*/
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
- kfree(pc);
+ kmem_cache_free(page_cgroup_cache, pc);
goto retry;
}
page_assign_page_cgroup(page, pc);
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_add_list(pc);
+ __mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
unlock_page_cgroup(page);
@@ -637,7 +626,7 @@ done:
return 0;
out:
css_put(&mem->css);
- kfree(pc);
+ kmem_cache_free(page_cgroup_cache, pc);
err:
return -ENOMEM;
}
@@ -685,7 +674,7 @@ void mem_cgroup_uncharge_page(struct page *page)
if (--(pc->ref_cnt) == 0) {
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(pc);
+ __mem_cgroup_remove_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
page_assign_page_cgroup(page, NULL);
@@ -695,7 +684,7 @@ void mem_cgroup_uncharge_page(struct page *page)
res_counter_uncharge(&mem->res, PAGE_SIZE);
css_put(&mem->css);
- kfree(pc);
+ kmem_cache_free(page_cgroup_cache, pc);
return;
}
@@ -747,7 +736,7 @@ void mem_cgroup_page_migration(struct page *page, struct page *newpage)
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_remove_list(pc);
+ __mem_cgroup_remove_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
page_assign_page_cgroup(page, NULL);
@@ -759,7 +748,7 @@ void mem_cgroup_page_migration(struct page *page, struct page *newpage)
mz = page_cgroup_zoneinfo(pc);
spin_lock_irqsave(&mz->lru_lock, flags);
- __mem_cgroup_add_list(pc);
+ __mem_cgroup_add_list(mz, pc);
spin_unlock_irqrestore(&mz->lru_lock, flags);
unlock_page_cgroup(newpage);
@@ -853,13 +842,10 @@ static int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
return 0;
}
-static ssize_t mem_cgroup_read(struct cgroup *cont,
- struct cftype *cft, struct file *file,
- char __user *userbuf, size_t nbytes, loff_t *ppos)
+static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
- return res_counter_read(&mem_cgroup_from_cont(cont)->res,
- cft->private, userbuf, nbytes, ppos,
- NULL);
+ return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
+ cft->private);
}
static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
@@ -871,27 +857,25 @@ static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
mem_cgroup_write_strategy);
}
-static ssize_t mem_force_empty_write(struct cgroup *cont,
- struct cftype *cft, struct file *file,
- const char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
{
- struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
- int ret = mem_cgroup_force_empty(mem);
- if (!ret)
- ret = nbytes;
- return ret;
+ struct mem_cgroup *mem;
+
+ mem = mem_cgroup_from_cont(cont);
+ switch (event) {
+ case RES_MAX_USAGE:
+ res_counter_reset_max(&mem->res);
+ break;
+ case RES_FAILCNT:
+ res_counter_reset_failcnt(&mem->res);
+ break;
+ }
+ return 0;
}
-/*
- * Note: This should be removed if cgroup supports write-only file.
- */
-static ssize_t mem_force_empty_read(struct cgroup *cont,
- struct cftype *cft,
- struct file *file, char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
{
- return -EINVAL;
+ return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
}
static const struct mem_cgroup_stat_desc {
@@ -902,9 +886,9 @@ static const struct mem_cgroup_stat_desc {
[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
};
-static int mem_control_stat_show(struct seq_file *m, void *arg)
+static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+ struct cgroup_map_cb *cb)
{
- struct cgroup *cont = m->private;
struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
struct mem_cgroup_stat *stat = &mem_cont->stat;
int i;
@@ -914,8 +898,7 @@ static int mem_control_stat_show(struct seq_file *m, void *arg)
val = mem_cgroup_read_stat(stat, i);
val *= mem_cgroup_stat_desc[i].unit;
- seq_printf(m, "%s %lld\n", mem_cgroup_stat_desc[i].msg,
- (long long)val);
+ cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
}
/* showing # of active pages */
{
@@ -925,52 +908,43 @@ static int mem_control_stat_show(struct seq_file *m, void *arg)
MEM_CGROUP_ZSTAT_INACTIVE);
active = mem_cgroup_get_all_zonestat(mem_cont,
MEM_CGROUP_ZSTAT_ACTIVE);
- seq_printf(m, "active %ld\n", (active) * PAGE_SIZE);
- seq_printf(m, "inactive %ld\n", (inactive) * PAGE_SIZE);
+ cb->fill(cb, "active", (active) * PAGE_SIZE);
+ cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
}
return 0;
}
-static const struct file_operations mem_control_stat_file_operations = {
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int mem_control_stat_open(struct inode *unused, struct file *file)
-{
- /* XXX __d_cont */
- struct cgroup *cont = file->f_dentry->d_parent->d_fsdata;
-
- file->f_op = &mem_control_stat_file_operations;
- return single_open(file, mem_control_stat_show, cont);
-}
-
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
.private = RES_USAGE,
- .read = mem_cgroup_read,
+ .read_u64 = mem_cgroup_read,
+ },
+ {
+ .name = "max_usage_in_bytes",
+ .private = RES_MAX_USAGE,
+ .trigger = mem_cgroup_reset,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "limit_in_bytes",
.private = RES_LIMIT,
.write = mem_cgroup_write,
- .read = mem_cgroup_read,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "failcnt",
.private = RES_FAILCNT,
- .read = mem_cgroup_read,
+ .trigger = mem_cgroup_reset,
+ .read_u64 = mem_cgroup_read,
},
{
.name = "force_empty",
- .write = mem_force_empty_write,
- .read = mem_force_empty_read,
+ .trigger = mem_force_empty_write,
},
{
.name = "stat",
- .open = mem_control_stat_open,
+ .read_map = mem_control_stat_show,
},
};
@@ -1010,6 +984,29 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
kfree(mem->info.nodeinfo[node]);
}
+static struct mem_cgroup *mem_cgroup_alloc(void)
+{
+ struct mem_cgroup *mem;
+
+ if (sizeof(*mem) < PAGE_SIZE)
+ mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+ else
+ mem = vmalloc(sizeof(*mem));
+
+ if (mem)
+ memset(mem, 0, sizeof(*mem));
+ return mem;
+}
+
+static void mem_cgroup_free(struct mem_cgroup *mem)
+{
+ if (sizeof(*mem) < PAGE_SIZE)
+ kfree(mem);
+ else
+ vfree(mem);
+}
+
+
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
@@ -1018,17 +1015,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
- init_mm.mem_cgroup = mem;
- } else
- mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
-
- if (mem == NULL)
- return ERR_PTR(-ENOMEM);
+ page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
+ } else {
+ mem = mem_cgroup_alloc();
+ if (!mem)
+ return ERR_PTR(-ENOMEM);
+ }
res_counter_init(&mem->res);
- memset(&mem->info, 0, sizeof(mem->info));
-
for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out;
@@ -1038,7 +1033,7 @@ free_out:
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
if (cont->parent != NULL)
- kfree(mem);
+ mem_cgroup_free(mem);
return ERR_PTR(-ENOMEM);
}
@@ -1058,7 +1053,7 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
- kfree(mem_cgroup_from_cont(cont));
+ mem_cgroup_free(mem_cgroup_from_cont(cont));
}
static int mem_cgroup_populate(struct cgroup_subsys *ss,
@@ -1098,10 +1093,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
if (!thread_group_leader(p))
goto out;
- css_get(&mem->css);
- rcu_assign_pointer(mm->mem_cgroup, mem);
- css_put(&old_mem->css);
-
out:
mmput(mm);
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 677d184b0d4..fac66337da2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -230,8 +230,11 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
might_sleep();
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
- if (vma->vm_file)
+ if (vma->vm_file) {
fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(vma->vm_mm);
+ }
mpol_put(vma_policy(vma));
kmem_cache_free(vm_area_cachep, vma);
return next;
@@ -623,8 +626,11 @@ again: remove_next = 1 + (end > next->vm_end);
spin_unlock(&mapping->i_mmap_lock);
if (remove_next) {
- if (file)
+ if (file) {
fput(file);
+ if (next->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
+ }
mm->map_count--;
mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
@@ -1154,6 +1160,8 @@ munmap_back:
error = file->f_op->mmap(file, vma);
if (error)
goto unmap_and_free_vma;
+ if (vm_flags & VM_EXECUTABLE)
+ added_exe_file_vma(mm);
} else if (vm_flags & VM_SHARED) {
error = shmem_zero_setup(vma);
if (error)
@@ -1185,6 +1193,8 @@ munmap_back:
mpol_put(vma_policy(vma));
kmem_cache_free(vm_area_cachep, vma);
fput(file);
+ if (vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
} else {
vma_link(mm, vma, prev, rb_link, rb_parent);
file = vma->vm_file;
@@ -1817,8 +1827,11 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
}
vma_set_policy(new, pol);
- if (new->vm_file)
+ if (new->vm_file) {
get_file(new->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ added_exe_file_vma(mm);
+ }
if (new->vm_ops && new->vm_ops->open)
new->vm_ops->open(new);
@@ -2135,8 +2148,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
new_vma->vm_start = addr;
new_vma->vm_end = addr + len;
new_vma->vm_pgoff = pgoff;
- if (new_vma->vm_file)
+ if (new_vma->vm_file) {
get_file(new_vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ added_exe_file_vma(mm);
+ }
if (new_vma->vm_ops && new_vma->vm_ops->open)
new_vma->vm_ops->open(new_vma);
vma_link(mm, new_vma, prev, rb_link, rb_parent);
diff --git a/mm/nommu.c b/mm/nommu.c
index 1d32fe89d57..ef8c62cec69 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -966,8 +966,13 @@ unsigned long do_mmap_pgoff(struct file *file,
INIT_LIST_HEAD(&vma->anon_vma_node);
atomic_set(&vma->vm_usage, 1);
- if (file)
+ if (file) {
get_file(file);
+ if (vm_flags & VM_EXECUTABLE) {
+ added_exe_file_vma(current->mm);
+ vma->vm_mm = current->mm;
+ }
+ }
vma->vm_file = file;
vma->vm_flags = vm_flags;
vma->vm_start = addr;
@@ -1022,8 +1027,11 @@ unsigned long do_mmap_pgoff(struct file *file,
up_write(&nommu_vma_sem);
kfree(vml);
if (vma) {
- if (vma->vm_file)
+ if (vma->vm_file) {
fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(vma->vm_mm);
+ }
kfree(vma);
}
return ret;
@@ -1053,7 +1061,7 @@ EXPORT_SYMBOL(do_mmap_pgoff);
/*
* handle mapping disposal for uClinux
*/
-static void put_vma(struct vm_area_struct *vma)
+static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
{
if (vma) {
down_write(&nommu_vma_sem);
@@ -1075,8 +1083,11 @@ static void put_vma(struct vm_area_struct *vma)
realalloc -= kobjsize(vma);
askedalloc -= sizeof(*vma);
- if (vma->vm_file)
+ if (vma->vm_file) {
fput(vma->vm_file);
+ if (vma->vm_flags & VM_EXECUTABLE)
+ removed_exe_file_vma(mm);
+ }
kfree(vma);
}
@@ -1113,7 +1124,7 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
found:
vml = *parent;
- put_vma(vml->vma);
+ put_vma(mm, vml->vma);
*parent = vml->next;
realalloc -= kobjsize(vml);
@@ -1158,7 +1169,7 @@ void exit_mmap(struct mm_struct * mm)
while ((tmp = mm->context.vmlist)) {
mm->context.vmlist = tmp->next;
- put_vma(tmp->vma);
+ put_vma(mm, tmp->vma);
realalloc -= kobjsize(tmp);
askedalloc -= sizeof(*tmp);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d1cf4f05dcd..0a502e99ee2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1461,7 +1461,8 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
struct task_struct *p = current;
int do_retry;
int alloc_flags;
- int did_some_progress;
+ unsigned long did_some_progress;
+ unsigned long pages_reclaimed = 0;
might_sleep_if(wait);
@@ -1611,14 +1612,26 @@ nofail_alloc:
* Don't let big-order allocations loop unless the caller explicitly
* requests that. Wait for some write requests to complete then retry.
*
- * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
- * <= 3, but that may not be true in other implementations.
+ * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
+ * means __GFP_NOFAIL, but that may not be true in other
+ * implementations.
+ *
+ * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
+ * specified, then we retry until we no longer reclaim any pages
+ * (above), or we've reclaimed an order of pages at least as
+ * large as the allocation's order. In both cases, if the
+ * allocation still fails, we stop retrying.
*/
+ pages_reclaimed += did_some_progress;
do_retry = 0;
if (!(gfp_mask & __GFP_NORETRY)) {
- if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
- (gfp_mask & __GFP_REPEAT))
+ if (order <= PAGE_ALLOC_COSTLY_ORDER) {
do_retry = 1;
+ } else {
+ if (gfp_mask & __GFP_REPEAT &&
+ pages_reclaimed < (1 << order))
+ do_retry = 1;
+ }
if (gfp_mask & __GFP_NOFAIL)
do_retry = 1;
}
@@ -2524,7 +2537,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
struct page *page;
unsigned long end_pfn = start_pfn + size;
unsigned long pfn;
+ struct zone *z;
+ z = &NODE_DATA(nid)->node_zones[zone];
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
* There can be holes in boot-time mem_map[]s
@@ -2542,7 +2557,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
init_page_count(page);
reset_page_mapcount(page);
SetPageReserved(page);
-
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
@@ -2551,8 +2565,15 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* kernel allocations are made. Later some blocks near
* the start are marked MIGRATE_RESERVE by
* setup_zone_migrate_reserve()
+ *
+ * bitmap is created for zone's valid pfn range. but memmap
+ * can be created for invalid pages (for alignment)
+ * check here not to call set_pageblock_migratetype() against
+ * pfn out of zone.
*/
- if ((pfn & (pageblock_nr_pages-1)))
+ if ((z->zone_start_pfn <= pfn)
+ && (pfn < z->zone_start_pfn + z->spanned_pages)
+ && !(pfn & (pageblock_nr_pages - 1)))
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
INIT_LIST_HEAD(&page->lru);
@@ -4464,6 +4485,8 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
+ VM_BUG_ON(pfn < zone->zone_start_pfn);
+ VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);
for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
if (flags & value)
diff --git a/mm/slub.c b/mm/slub.c
index 992ecd4f0d3..b145e798bf3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2978,7 +2978,7 @@ void __init kmem_cache_init(void)
kmalloc_caches[0].refcount = -1;
caches++;
- hotplug_memory_notifier(slab_memory_callback, 1);
+ hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
#endif
/* Able to allocate the per node structures */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 67051be7083..bd1bb592030 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1426,11 +1426,7 @@ static const struct file_operations proc_swaps_operations = {
static int __init procswaps_init(void)
{
- struct proc_dir_entry *entry;
-
- entry = create_proc_entry("swaps", 0, NULL);
- if (entry)
- entry->proc_fops = &proc_swaps_operations;
+ proc_create("swaps", 0, NULL, &proc_swaps_operations);
return 0;
}
__initcall(procswaps_init);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eceac9f9032..12e8627c974 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1299,6 +1299,9 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
* hope that some of these pages can be written. But if the allocating task
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
+ *
+ * returns: 0, if no pages reclaimed
+ * else, the number of pages reclaimed
*/
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
struct scan_control *sc)
@@ -1347,7 +1350,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
}
total_scanned += sc->nr_scanned;
if (nr_reclaimed >= sc->swap_cluster_max) {
- ret = 1;
+ ret = nr_reclaimed;
goto out;
}
@@ -1370,7 +1373,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
}
/* top priority shrink_caches still had more to do? don't OOM, then */
if (!sc->all_unreclaimable && scan_global_lru(sc))
- ret = 1;
+ ret = nr_reclaimed;
out:
/*
* Now that we've scanned all the zones at this priority level, note