/* pagein of a big page is an event. So, ignore page size */
if (nr_pages > 0)
__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]);
- else
+ else {
__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]);
+ nr_pages = -nr_pages; /* for event */
+ }
__this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages);
mem_cgroup_del_lru_list(page, page_lru(page));
}
+/*
+ * Writeback is about to end against a page which has been marked for immediate
+ * reclaim. If it still appears to be reclaimable, move it to the tail of the
+ * inactive list.
+ */
+void mem_cgroup_rotate_reclaimable_page(struct page *page)
+{
+ struct mem_cgroup_per_zone *mz;
+ struct page_cgroup *pc;
+ enum lru_list lru = page_lru(page);
+
+ if (mem_cgroup_disabled())
+ return;
+
+ pc = lookup_page_cgroup(page);
+ /* unused or root page is not rotated. */
+ if (!PageCgroupUsed(pc))
+ return;
+ /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+ smp_rmb();
+ if (mem_cgroup_is_root(pc->mem_cgroup))
+ return;
+ mz = page_cgroup_zoneinfo(pc);
+ list_move_tail(&pc->lru, &mz->lists[lru]);
+}
+
void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
{
struct mem_cgroup_per_zone *mz;
return false;
}
+/**
+ * mem_cgroup_check_margin - check if the memory cgroup allows charging
+ * @mem: memory cgroup to check
+ * @bytes: the number of bytes the caller intends to charge
+ *
+ * Returns a boolean value on whether @mem can be charged @bytes or
+ * whether this would exceed the limit.
+ */
+static bool mem_cgroup_check_margin(struct mem_cgroup *mem, unsigned long bytes)
+{
+ if (!res_counter_check_margin(&mem->res, bytes))
+ return false;
+ if (do_swap_account && !res_counter_check_margin(&mem->memsw, bytes))
+ return false;
+ return true;
+}
+
static unsigned int get_swappiness(struct mem_cgroup *memcg)
{
struct cgroup *cgrp = memcg->css.cgroup;
flags |= MEM_CGROUP_RECLAIM_NOSWAP;
} else
mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
-
- if (csize > PAGE_SIZE) /* change csize and retry */
+ /*
+ * csize can be either a huge page (HPAGE_SIZE), a batch of
+ * regular pages (CHARGE_SIZE), or a single regular page
+ * (PAGE_SIZE).
+ *
+ * Never reclaim on behalf of optional batching, retry with a
+ * single page instead.
+ */
+ if (csize == CHARGE_SIZE)
return CHARGE_RETRY;
if (!(gfp_mask & __GFP_WAIT))
return CHARGE_WOULDBLOCK;
ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
- gfp_mask, flags);
+ gfp_mask, flags);
+ if (mem_cgroup_check_margin(mem_over_limit, csize))
+ return CHARGE_RETRY;
/*
- * try_to_free_mem_cgroup_pages() might not give us a full
- * picture of reclaim. Some pages are reclaimed and might be
- * moved to swap cache or just unmapped from the cgroup.
- * Check the limit again to see if the reclaim reduced the
- * current usage of the cgroup before giving up
+ * Even though the limit is exceeded at this point, reclaim
+ * may have been able to free some pages. Retry the charge
+ * before killing the task.
+ *
+ * Only for regular pages, though: huge pages are rather
+ * unlikely to succeed so close to the limit, and we fall back
+ * to regular pages anyway in case of failure.
*/
- if (ret || mem_cgroup_check_under_limit(mem_over_limit))
+ if (csize == PAGE_SIZE && ret)
return CHARGE_RETRY;
/*
gfp_t gfp_mask, enum charge_type ctype)
{
struct mem_cgroup *mem = NULL;
+ int page_size = PAGE_SIZE;
struct page_cgroup *pc;
+ bool oom = true;
int ret;
- int page_size = PAGE_SIZE;
if (PageTransHuge(page)) {
page_size <<= compound_order(page);
VM_BUG_ON(!PageTransHuge(page));
+ /*
+ * Never OOM-kill a process for a huge page. The
+ * fault handler will fall back to regular pages.
+ */
+ oom = false;
}
pc = lookup_page_cgroup(page);
return 0;
prefetchw(pc);
- ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page_size);
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size);
if (ret || !mem)
return ret;
* page belongs to.
*/
int mem_cgroup_prepare_migration(struct page *page,
- struct page *newpage, struct mem_cgroup **ptr)
+ struct page *newpage, struct mem_cgroup **ptr, gfp_t gfp_mask)
{
struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
return 0;
*ptr = mem;
- ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false, PAGE_SIZE);
+ ret = __mem_cgroup_try_charge(NULL, gfp_mask, ptr, false, PAGE_SIZE);
css_put(&mem->css);/* drop extra refcnt */
if (ret || *ptr == NULL) {
if (PageAnon(page)) {
pte_t *pte;
spinlock_t *ptl;
- VM_BUG_ON(pmd_trans_huge(*pmd));
+ split_huge_page_pmd(walk->mm, pmd);
+
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE)
if (is_target_pte_for_mc(vma, addr, *pte, NULL))
pte_t *pte;
spinlock_t *ptl;
+ split_huge_page_pmd(walk->mm, pmd);
retry:
- VM_BUG_ON(pmd_trans_huge(*pmd));
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; addr += PAGE_SIZE) {
pte_t ptent = *(pte++);
static int __init enable_swap_account(char *s)
{
/* consider enabled if no parameter or 1 is given */
- if (!s || !strcmp(s, "1"))
+ if (!(*s) || !strcmp(s, "=1"))
really_do_swap_account = 1;
- else if (!strcmp(s, "0"))
+ else if (!strcmp(s, "=0"))
really_do_swap_account = 0;
return 1;
}
static int __init disable_swap_account(char *s)
{
- enable_swap_account("0");
+ printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n");
+ enable_swap_account("=0");
return 1;
}
__setup("noswapaccount", disable_swap_account);
git.openpandora.org / pandora-kernel.git / blobdiff