static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
static unsigned int free_huge_pages_node[MAX_NUMNODES];
+static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
+unsigned long hugepages_treat_as_movable;
+
/*
* Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
*/
static struct page *dequeue_huge_page(struct vm_area_struct *vma,
unsigned long address)
{
- int nid = numa_node_id();
+ int nid;
struct page *page = NULL;
- struct zonelist *zonelist = huge_zonelist(vma, address);
+ struct zonelist *zonelist = huge_zonelist(vma, address,
+ htlb_alloc_mask);
struct zone **z;
for (z = zonelist->zones; *z; z++) {
nid = zone_to_nid(*z);
- if (cpuset_zone_allowed_softwall(*z, GFP_HIGHUSER) &&
- !list_empty(&hugepage_freelists[nid]))
- break;
- }
-
- if (*z) {
- page = list_entry(hugepage_freelists[nid].next,
- struct page, lru);
- list_del(&page->lru);
- free_huge_pages--;
- free_huge_pages_node[nid]--;
+ if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
+ !list_empty(&hugepage_freelists[nid])) {
+ page = list_entry(hugepage_freelists[nid].next,
+ struct page, lru);
+ list_del(&page->lru);
+ free_huge_pages--;
+ free_huge_pages_node[nid]--;
+ }
}
return page;
}
static int alloc_fresh_huge_page(void)
{
- static int nid = 0;
+ static int prev_nid;
struct page *page;
- page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
- HUGETLB_PAGE_ORDER);
- nid = next_node(nid, node_online_map);
+ int nid;
+
+ /*
+ * Copy static prev_nid to local nid, work on that, then copy it
+ * back to prev_nid afterwards: otherwise there's a window in which
+ * a racer might pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * But we don't need to use a spin_lock here: it really doesn't
+ * matter if occasionally a racer chooses the same nid as we do.
+ */
+ nid = next_node(prev_nid, node_online_map);
if (nid == MAX_NUMNODES)
nid = first_node(node_online_map);
+ prev_nid = nid;
+
+ page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+ HUGETLB_PAGE_ORDER);
if (page) {
set_compound_page_dtor(page, free_huge_page);
spin_lock(&hugetlb_lock);
return page;
fail:
+ if (vma->vm_flags & VM_MAYSHARE)
+ resv_huge_pages++;
spin_unlock(&hugetlb_lock);
return NULL;
}
}
__setup("hugepages=", hugetlb_setup);
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+ int node;
+ unsigned int nr = 0;
+
+ for_each_node_mask(node, cpuset_current_mems_allowed)
+ nr += array[node];
+
+ return nr;
+}
+
#ifdef CONFIG_SYSCTL
static void update_and_free_page(struct page *page)
{
1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
1 << PG_private | 1<< PG_writeback);
}
- page[1].lru.next = NULL;
+ set_compound_page_dtor(page, NULL);
set_page_refcounted(page);
__free_pages(page, HUGETLB_PAGE_ORDER);
}
max_huge_pages = set_max_huge_pages(max_huge_pages);
return 0;
}
+
+int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_dointvec(table, write, file, buffer, length, ppos);
+ if (hugepages_treat_as_movable)
+ htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
+ else
+ htlb_alloc_mask = GFP_HIGHUSER;
+ return 0;
+}
+
#endif /* CONFIG_SYSCTL */
int hugetlb_report_meminfo(char *buf)
* hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get
* this far.
*/
-static struct page *hugetlb_nopage(struct vm_area_struct *vma,
- unsigned long address, int *unused)
+static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
BUG();
- return NULL;
+ return 0;
}
struct vm_operations_struct hugetlb_vm_ops = {
- .nopage = hugetlb_nopage,
+ .fault = hugetlb_vm_op_fault,
};
static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
pte_t entry;
entry = pte_mkwrite(pte_mkdirty(*ptep));
- ptep_set_access_flags(vma, address, ptep, entry, 1);
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
+ if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
+ }
}
avoidcopy = (page_count(old_page) == 1);
if (avoidcopy) {
set_huge_ptep_writable(vma, address, ptep);
- return VM_FAULT_MINOR;
+ return 0;
}
page_cache_get(old_page);
}
page_cache_release(new_page);
page_cache_release(old_page);
- return VM_FAULT_MINOR;
+ return 0;
}
-int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, int write_access)
{
int ret = VM_FAULT_SIGBUS;
if (idx >= size)
goto backout;
- ret = VM_FAULT_MINOR;
+ ret = 0;
if (!pte_none(*ptep))
goto backout;
return ret;
}
- ret = VM_FAULT_MINOR;
+ ret = 0;
spin_lock(&mm->page_table_lock);
/* Check for a racing update before calling hugetlb_cow */
spin_unlock(&mm->page_table_lock);
ret = hugetlb_fault(mm, vma, vaddr, 0);
spin_lock(&mm->page_table_lock);
- if (ret == VM_FAULT_MINOR)
+ if (!(ret & VM_FAULT_MAJOR))
continue;
remainder = 0;
chg = region_chg(&inode->i_mapping->private_list, from, to);
if (chg < 0)
return chg;
+ /*
+ * When cpuset is configured, it breaks the strict hugetlb page
+ * reservation as the accounting is done on a global variable. Such
+ * reservation is completely rubbish in the presence of cpuset because
+ * the reservation is not checked against page availability for the
+ * current cpuset. Application can still potentially OOM'ed by kernel
+ * with lack of free htlb page in cpuset that the task is in.
+ * Attempt to enforce strict accounting with cpuset is almost
+ * impossible (or too ugly) because cpuset is too fluid that
+ * task or memory node can be dynamically moved between cpusets.
+ *
+ * The change of semantics for shared hugetlb mapping with cpuset is
+ * undesirable. However, in order to preserve some of the semantics,
+ * we fall back to check against current free page availability as
+ * a best attempt and hopefully to minimize the impact of changing
+ * semantics that cpuset has.
+ */
+ if (chg > cpuset_mems_nr(free_huge_pages_node))
+ return -ENOMEM;
+
ret = hugetlb_acct_memory(chg);
if (ret < 0)
return ret;