#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
+#include <linux/mmdebug.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
}
EXPORT_SYMBOL_GPL(PageHuge);
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageHead(page_head))
+ return 0;
+
+ dtor = get_compound_page_dtor(page_head);
+
+ return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
+pgoff_t __basepage_index(struct page *page)
+{
+ struct page *page_head = compound_head(page);
+ pgoff_t index = page_index(page_head);
+ unsigned long compound_idx;
+
+ if (!PageHuge(page_head))
+ return page_index(page);
+
+ if (compound_order(page_head) >= MAX_ORDER)
+ compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
+ else
+ compound_idx = page - page_head;
+
+ return (index << compound_order(page_head)) + compound_idx;
+}
+
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
while (nr_pages--) {
if (!free_pool_huge_page(h, &node_states[N_HIGH_MEMORY], 1))
break;
+ cond_resched_lock(&hugetlb_lock);
}
}
* and reducing the surplus.
*/
spin_unlock(&hugetlb_lock);
+
+ /* yield cpu to avoid soft lockup */
+ cond_resched();
+
ret = alloc_fresh_huge_page(h, nodes_allowed);
spin_lock(&hugetlb_lock);
if (!ret)
while (min_count < persistent_huge_pages(h)) {
if (!free_pool_huge_page(h, nodes_allowed, 0))
break;
+ cond_resched_lock(&hugetlb_lock);
}
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
static int __init hugetlb_init(void)
{
- /* Some platform decide whether they support huge pages at boot
- * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
- * there is no such support
- */
- if (HPAGE_SHIFT == 0)
+ if (!hugepages_supported())
return 0;
if (!size_to_hstate(default_hstate_size)) {
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->max_huge_pages;
if (write && h->order >= MAX_ORDER)
unsigned long tmp;
int ret;
+ if (!hugepages_supported())
+ return -ENOTSUPP;
+
tmp = h->nr_overcommit_huge_pages;
if (write && h->order >= MAX_ORDER)
void hugetlb_report_meminfo(struct seq_file *m)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return;
seq_printf(m,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
int hugetlb_report_node_meminfo(int nid, char *buf)
{
struct hstate *h = &default_hstate;
+ if (!hugepages_supported())
+ return 0;
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
"Node %d HugePages_Free: %5u\n"
update_mmu_cache(vma, address, ptep);
}
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+ swp_entry_t swp;
+
+ 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))
+ return 1;
+ else
+ return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+ swp_entry_t swp;
+
+ 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))
+ return 1;
+ else
+ return 0;
+}
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
spin_lock(&dst->page_table_lock);
spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
- if (!huge_pte_none(huge_ptep_get(src_pte))) {
+ entry = huge_ptep_get(src_pte);
+ if (huge_pte_none(entry)) { /* skip none entry */
+ ;
+ } else if (unlikely(is_hugetlb_entry_migration(entry) ||
+ is_hugetlb_entry_hwpoisoned(entry))) {
+ swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+ if (is_write_migration_entry(swp_entry) && cow) {
+ /*
+ * COW mappings require pages in both
+ * parent and child to be set to read.
+ */
+ make_migration_entry_read(&swp_entry);
+ entry = swp_entry_to_pte(swp_entry);
+ set_huge_pte_at(src, addr, src_pte, entry);
+ }
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ } else {
if (cow)
huge_ptep_set_wrprotect(src, addr, src_pte);
entry = huge_ptep_get(src_pte);
return -ENOMEM;
}
-static int is_hugetlb_entry_migration(pte_t pte)
-{
- swp_entry_t swp;
-
- 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))
- return 1;
- else
- return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
- swp_entry_t swp;
-
- 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))
- return 1;
- else
- return 0;
-}
-
void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
continue;
/*
- * HWPoisoned hugepage is already unmapped and dropped reference
+ * Migrating hugepage or HWPoisoned hugepage is already
+ * unmapped and its refcount is dropped
*/
- if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+ if (unlikely(!pte_present(pte)))
continue;
page = pte_page(pte);
if (iter_vma == vma)
continue;
+ /*
+ * Shared VMAs have their own reserves and do not affect
+ * MAP_PRIVATE accounting but it is possible that a shared
+ * VMA is using the same page so check and skip such VMAs.
+ */
+ if (iter_vma->vm_flags & VM_MAYSHARE)
+ continue;
+
/*
* Unmap the page from other VMAs without their own reserves.
* They get marked to be SIGKILLed if they fault in these
struct page *pagecache_page = NULL;
static DEFINE_MUTEX(hugetlb_instantiation_mutex);
struct hstate *h = hstate_vma(vma);
+ int need_wait_lock = 0;
ptep = huge_pte_offset(mm, address);
if (ptep) {
entry = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_migration(entry))) {
- migration_entry_wait(mm, (pmd_t *)ptep, address);
+ migration_entry_wait_huge(mm, ptep);
return 0;
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(h - hstates);
+ } else {
+ ptep = huge_pte_alloc(mm, address, huge_page_size(h));
+ if (!ptep)
+ return VM_FAULT_OOM;
}
- ptep = huge_pte_alloc(mm, address, huge_page_size(h));
- if (!ptep)
- return VM_FAULT_OOM;
-
/*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
ret = 0;
+ /*
+ * entry could be a migration/hwpoison entry at this point, so this
+ * check prevents the kernel from going below assuming that we have
+ * a active hugepage in pagecache. This goto expects the 2nd page fault,
+ * and is_hugetlb_entry_(migration|hwpoisoned) check will properly
+ * handle it.
+ */
+ if (!pte_present(entry))
+ goto out_mutex;
+
/*
* If we are going to COW the mapping later, we examine the pending
* reservations for this page now. This will ensure that any
vma, address);
}
+ spin_lock(&mm->page_table_lock);
+ /* Check for a racing update before calling hugetlb_cow */
+ if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
+ goto out_page_table_lock;
+
/*
* hugetlb_cow() requires page locks of pte_page(entry) and
* pagecache_page, so here we need take the former one
* when page != pagecache_page or !pagecache_page.
- * Note that locking order is always pagecache_page -> page,
- * so no worry about deadlock.
*/
page = pte_page(entry);
- get_page(page);
if (page != pagecache_page)
- lock_page(page);
-
- spin_lock(&mm->page_table_lock);
- /* Check for a racing update before calling hugetlb_cow */
- if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
- goto out_page_table_lock;
+ if (!trylock_page(page)) {
+ need_wait_lock = 1;
+ goto out_page_table_lock;
+ }
+ get_page(page);
if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry)) {
ret = hugetlb_cow(mm, vma, address, ptep, entry,
pagecache_page);
- goto out_page_table_lock;
+ goto out_put_page;
}
entry = pte_mkdirty(entry);
}
if (huge_ptep_set_access_flags(vma, address, ptep, entry,
flags & FAULT_FLAG_WRITE))
update_mmu_cache(vma, address, ptep);
-
+out_put_page:
+ if (page != pagecache_page)
+ unlock_page(page);
+ put_page(page);
out_page_table_lock:
spin_unlock(&mm->page_table_lock);
unlock_page(pagecache_page);
put_page(pagecache_page);
}
- if (page != pagecache_page)
- unlock_page(page);
- put_page(page);
-
out_mutex:
mutex_unlock(&hugetlb_instantiation_mutex);
+ /*
+ * Generally it's safe to hold refcount during waiting page lock. But
+ * here we just wait to defer the next page fault to avoid busy loop and
+ * the page is not used after unlocked before returning from the current
+ * page fault. So we are safe from accessing freed page, even if we wait
+ * here without taking refcount.
+ */
+ if (need_wait_lock)
+ wait_on_page_locked(page);
return ret;
}
continue;
if (huge_pmd_unshare(mm, &address, ptep))
continue;
- if (!huge_pte_none(huge_ptep_get(ptep))) {
+ pte = huge_ptep_get(ptep);
+ if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+ continue;
+ if (unlikely(is_hugetlb_entry_migration(pte))) {
+ swp_entry_t entry = pte_to_swp_entry(pte);
+
+ if (is_write_migration_entry(entry)) {
+ pte_t newpte;
+
+ make_migration_entry_read(&entry);
+ newpte = swp_entry_to_pte(entry);
+ set_huge_pte_at(mm, address, ptep, newpte);
+ }
+ continue;
+ }
+ if (!huge_pte_none(pte)) {
pte = huge_ptep_get_and_clear(mm, address, ptep);
pte = pte_mkhuge(pte_modify(pte, newprot));
set_huge_pte_at(mm, address, ptep, pte);
struct hstate *h = hstate_inode(inode);
struct hugepage_subpool *spool = subpool_inode(inode);
+ /* This should never happen */
+ if (from > to) {
+#ifdef CONFIG_DEBUG_VM
+ WARN(1, "%s called with a negative range\n", __func__);
+#endif
+ return -EINVAL;
+ }
+
/*
* Only apply hugepage reservation if asked. At fault time, an
* attempt will be made for VM_NORESERVE to allocate a page
git.openpandora.org / pandora-kernel.git / blobdiff