#include <asm/page.h>
#include <asm/pgtable.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/node.h>
* must either hold the mmap_sem for write, or the mmap_sem for read and
* the hugetlb_instantiation mutex:
*
- * down_write(&mm->mmap_sem);
+ * down_write(&mm->mmap_sem);
* or
- * down_read(&mm->mmap_sem);
- * mutex_lock(&hugetlb_instantiation_mutex);
+ * down_read(&mm->mmap_sem);
+ * mutex_lock(&hugetlb_instantiation_mutex);
*/
struct file_region {
struct list_head link;
if (rg->from > t)
return chg;
- /* We overlap with this area, if it extends futher than
+ /* We overlap with this area, if it extends further than
* us then we must extend ourselves. Account for its
* existing reservation. */
if (rg->to > t) {
return 0;
}
-static void clear_gigantic_page(struct page *page,
- unsigned long addr, unsigned long sz)
-{
- int i;
- struct page *p = page;
-
- might_sleep();
- for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
- cond_resched();
- clear_user_highpage(p, addr + i * PAGE_SIZE);
- }
-}
-static void clear_huge_page(struct page *page,
- unsigned long addr, unsigned long sz)
-{
- int i;
-
- if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
- clear_gigantic_page(page, addr, sz);
- return;
- }
-
- might_sleep();
- for (i = 0; i < sz/PAGE_SIZE; i++) {
- cond_resched();
- clear_user_highpage(page + i, addr + i * PAGE_SIZE);
- }
-}
-
-static void copy_user_gigantic_page(struct page *dst, struct page *src,
- unsigned long addr, struct vm_area_struct *vma)
-{
- int i;
- struct hstate *h = hstate_vma(vma);
- struct page *dst_base = dst;
- struct page *src_base = src;
-
- for (i = 0; i < pages_per_huge_page(h); ) {
- cond_resched();
- copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
-
- i++;
- dst = mem_map_next(dst, dst_base, i);
- src = mem_map_next(src, src_base, i);
- }
-}
-
-static void copy_user_huge_page(struct page *dst, struct page *src,
- unsigned long addr, struct vm_area_struct *vma)
-{
- int i;
- struct hstate *h = hstate_vma(vma);
-
- if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
- copy_user_gigantic_page(dst, src, addr, vma);
- return;
- }
-
- might_sleep();
- for (i = 0; i < pages_per_huge_page(h); i++) {
- cond_resched();
- copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
- }
-}
-
static void copy_gigantic_page(struct page *dst, struct page *src)
{
int i;
/* If reserves cannot be used, ensure enough pages are in the pool */
if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
- goto err;;
+ goto err;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
MAX_NR_ZONES - 1, nodemask) {
h->nr_huge_pages--;
h->nr_huge_pages_node[page_to_nid(page)]--;
for (i = 0; i < pages_per_huge_page(h); i++) {
- page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
- 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
- 1 << PG_private | 1<< PG_writeback);
+ page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+ 1 << PG_referenced | 1 << PG_dirty |
+ 1 << PG_active | 1 << PG_reserved |
+ 1 << PG_private | 1 << PG_writeback);
}
set_compound_page_dtor(page, NULL);
set_page_refcounted(page);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
return dtor == free_huge_page;
}
-
EXPORT_SYMBOL_GPL(PageHuge);
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
}
/*
- * Increase the hugetlb pool such that it can accomodate a reservation
+ * Increase the hugetlb pool such that it can accommodate a reservation
* of size 'delta'.
*/
static int gather_surplus_pages(struct hstate *h, int delta)
/*
* The surplus_list now contains _at_least_ the number of extra pages
- * needed to accomodate the reservation. Add the appropriate number
+ * needed to accommodate the reservation. Add the appropriate number
* of pages to the hugetlb pool and free the extras back to the buddy
* allocator. Commit the entire reservation here to prevent another
* process from stealing the pages as they are added to the pool but
h->resv_huge_pages += delta;
ret = 0;
- spin_unlock(&hugetlb_lock);
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
if ((--needed) < 0)
VM_BUG_ON(page_count(page));
enqueue_huge_page(h, page);
}
+ spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
free:
*/
chg = vma_needs_reservation(h, vma, addr);
if (chg < 0)
- return ERR_PTR(chg);
+ return ERR_PTR(-VM_FAULT_OOM);
if (chg)
if (hugetlb_get_quota(inode->i_mapping, chg))
- return ERR_PTR(-ENOSPC);
+ return ERR_PTR(-VM_FAULT_SIGBUS);
spin_lock(&hugetlb_lock);
page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
struct huge_bootmem_page *m;
list_for_each_entry(m, &huge_boot_pages, list) {
- struct page *page = virt_to_page(m);
struct hstate *h = m->hstate;
+ struct page *page;
+
+#ifdef CONFIG_HIGHMEM
+ page = pfn_to_page(m->phys >> PAGE_SHIFT);
+ free_bootmem_late((unsigned long)m,
+ sizeof(struct huge_bootmem_page));
+#else
+ page = virt_to_page(m);
+#endif
__ClearPageReserved(page);
WARN_ON(page_count(page) != 1);
prep_compound_huge_page(page, h->order);
prep_new_huge_page(h, page, page_to_nid(page));
+ /*
+ * If we had gigantic hugepages allocated at boot time, we need
+ * to restore the 'stolen' pages to totalram_pages in order to
+ * fix confusing memory reports from free(1) and another
+ * side-effects, like CommitLimit going negative.
+ */
+ if (h->order > (MAX_ORDER - 1))
+ totalram_pages += 1 << h->order;
}
}
return sprintf(buf, "%lu\n", nr_huge_pages);
}
+
static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
struct kobject *kobj, struct kobj_attribute *attr,
const char *buf, size_t len)
err = strict_strtoul(buf, 10, &count);
if (err)
- return 0;
+ goto out;
h = kobj_to_hstate(kobj, &nid);
+ if (h->order >= MAX_ORDER) {
+ err = -EINVAL;
+ goto out;
+ }
+
if (nid == NUMA_NO_NODE) {
/*
* global hstate attribute
NODEMASK_FREE(nodes_allowed);
return len;
+out:
+ NODEMASK_FREE(nodes_allowed);
+ return err;
}
static ssize_t nr_hugepages_show(struct kobject *kobj,
struct hstate *h = kobj_to_hstate(kobj, NULL);
return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
}
+
static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
unsigned long input;
struct hstate *h = kobj_to_hstate(kobj, NULL);
+ if (h->order >= MAX_ORDER)
+ return -EINVAL;
+
err = strict_strtoul(buf, 10, &input);
if (err)
- return 0;
+ return err;
spin_lock(&hugetlb_lock);
h->nr_overcommit_huge_pages = input;
{
struct hstate *h = &default_hstate;
unsigned long tmp;
+ int ret;
+
+ tmp = h->max_huge_pages;
- if (!write)
- tmp = h->max_huge_pages;
+ if (write && h->order >= MAX_ORDER)
+ return -EINVAL;
table->data = &tmp;
table->maxlen = sizeof(unsigned long);
- proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ if (ret)
+ goto out;
if (write) {
NODEMASK_ALLOC(nodemask_t, nodes_allowed,
if (nodes_allowed != &node_states[N_HIGH_MEMORY])
NODEMASK_FREE(nodes_allowed);
}
-
- return 0;
+out:
+ return ret;
}
int hugetlb_sysctl_handler(struct ctl_table *table, int write,
{
struct hstate *h = &default_hstate;
unsigned long tmp;
+ int ret;
+
+ tmp = h->nr_overcommit_huge_pages;
- if (!write)
- tmp = h->nr_overcommit_huge_pages;
+ if (write && h->order >= MAX_ORDER)
+ return -EINVAL;
table->data = &tmp;
table->maxlen = sizeof(unsigned long);
- proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ if (ret)
+ goto out;
if (write) {
spin_lock(&hugetlb_lock);
h->nr_overcommit_huge_pages = tmp;
spin_unlock(&hugetlb_lock);
}
-
- return 0;
+out:
+ return ret;
}
#endif /* CONFIG_SYSCTL */
* This new VMA should share its siblings reservation map if present.
* The VMA will only ever have a valid reservation map pointer where
* it is being copied for another still existing VMA. As that VMA
- * has a reference to the reservation map it cannot dissappear until
+ * has a reference to the reservation map it cannot disappear until
* after this open call completes. It is therefore safe to take a
* new reference here without additional locking.
*/
pte_t entry;
entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
- if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+ if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
update_mmu_cache(vma, address, ptep);
- }
}
if (huge_pte_none(pte) || pte_present(pte))
return 0;
swp = pte_to_swp_entry(pte);
- if (non_swap_entry(swp) && is_migration_entry(swp)) {
+ if (non_swap_entry(swp) && is_migration_entry(swp))
return 1;
- } else
+ else
return 0;
}
if (huge_pte_none(pte) || pte_present(pte))
return 0;
swp = pte_to_swp_entry(pte);
- if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+ if (non_swap_entry(swp) && is_hwpoison_entry(swp))
return 1;
- } else
+ else
return 0;
}
unsigned long sz = huge_page_size(h);
/*
- * A page gathering list, protected by per file i_mmap_lock. The
+ * A page gathering list, protected by per file i_mmap_mutex. The
* lock is used to avoid list corruption from multiple unmapping
* of the same page since we are using page->lru.
*/
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
- spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
__unmap_hugepage_range(vma, start, end, ref_page);
- spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
}
/*
* this mapping should be shared between all the VMAs,
* __unmap_hugepage_range() is called as the lock is already held
*/
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
/* Do not unmap the current VMA */
if (iter_vma == vma)
address, address + huge_page_size(h),
page);
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return 1;
}
* When the original hugepage is shared one, it does not have
* anon_vma prepared.
*/
- if (unlikely(anon_vma_prepare(vma)))
+ if (unlikely(anon_vma_prepare(vma))) {
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ /* Caller expects lock to be held */
+ spin_lock(&mm->page_table_lock);
return VM_FAULT_OOM;
+ }
- copy_user_huge_page(new_page, old_page, address, vma);
+ copy_user_huge_page(new_page, old_page, address, vma,
+ pages_per_huge_page(h));
__SetPageUptodate(new_page);
/*
/*
* Currently, we are forced to kill the process in the event the
* original mapper has unmapped pages from the child due to a failed
- * COW. Warn that such a situation has occured as it may not be obvious
+ * COW. Warn that such a situation has occurred as it may not be obvious
*/
if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
printk(KERN_WARNING
ret = -PTR_ERR(page);
goto out;
}
- clear_huge_page(page, address, huge_page_size(h));
+ clear_huge_page(page, address, pages_per_huge_page(h));
__SetPageUptodate(page);
if (vma->vm_flags & VM_MAYSHARE) {
* So we need to block hugepage fault by PG_hwpoison bit check.
*/
if (unlikely(PageHWPoison(page))) {
- ret = VM_FAULT_HWPOISON;
+ ret = VM_FAULT_HWPOISON |
+ VM_FAULT_SET_HINDEX(h - hstates);
goto backout_unlocked;
}
page_dup_rmap(page);
migration_entry_wait(mm, (pmd_t *)ptep, address);
return 0;
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
- return VM_FAULT_HWPOISON;
+ return VM_FAULT_HWPOISON_LARGE |
+ VM_FAULT_SET_HINDEX(h - hstates);
}
ptep = huge_pte_alloc(mm, address, huge_page_size(h));
* so no worry about deadlock.
*/
page = pte_page(entry);
+ get_page(page);
if (page != pagecache_page)
lock_page(page);
unlock_page(pagecache_page);
put_page(pagecache_page);
}
- unlock_page(page);
+ if (page != pagecache_page)
+ unlock_page(page);
+ put_page(page);
out_mutex:
mutex_unlock(&hugetlb_instantiation_mutex);
BUG_ON(address >= end);
flush_cache_range(vma, address, end);
- spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
spin_lock(&mm->page_table_lock);
for (; address < end; address += huge_page_size(h)) {
ptep = huge_pte_offset(mm, address);
}
}
spin_unlock(&mm->page_table_lock);
- spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
flush_tlb_range(vma, start, end);
}
int hugetlb_reserve_pages(struct inode *inode,
long from, long to,
struct vm_area_struct *vma,
- int acctflag)
+ vm_flags_t vm_flags)
{
long ret, chg;
struct hstate *h = hstate_inode(inode);
* attempt will be made for VM_NORESERVE to allocate a page
* and filesystem quota without using reserves
*/
- if (acctflag & VM_NORESERVE)
+ if (vm_flags & VM_NORESERVE)
return 0;
/*