static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
VM_BUG_ON(!is_vm_hugetlb_page(vma));
- if (!(vma->vm_flags & VM_SHARED))
+ if (!(vma->vm_flags & VM_MAYSHARE))
return (struct resv_map *)(get_vma_private_data(vma) &
~HPAGE_RESV_MASK);
return NULL;
static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
VM_BUG_ON(!is_vm_hugetlb_page(vma));
- VM_BUG_ON(vma->vm_flags & VM_SHARED);
+ VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
set_vma_private_data(vma, (get_vma_private_data(vma) &
HPAGE_RESV_MASK) | (unsigned long)map);
static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
{
VM_BUG_ON(!is_vm_hugetlb_page(vma));
- VM_BUG_ON(vma->vm_flags & VM_SHARED);
+ VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
set_vma_private_data(vma, get_vma_private_data(vma) | flags);
}
if (vma->vm_flags & VM_NORESERVE)
return;
- if (vma->vm_flags & VM_SHARED) {
+ if (vma->vm_flags & VM_MAYSHARE) {
/* Shared mappings always use reserves */
h->resv_huge_pages--;
} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
VM_BUG_ON(!is_vm_hugetlb_page(vma));
- if (!(vma->vm_flags & VM_SHARED))
+ if (!(vma->vm_flags & VM_MAYSHARE))
vma->vm_private_data = (void *)0;
}
/* Returns true if the VMA has associated reserve pages */
static int vma_has_reserves(struct vm_area_struct *vma)
{
- if (vma->vm_flags & VM_SHARED)
+ if (vma->vm_flags & VM_MAYSHARE)
return 1;
if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
return 1;
{
int i;
- if (unlikely(sz > MAX_ORDER_NR_PAGES))
- return clear_gigantic_page(page, addr, sz);
+ if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
+ clear_gigantic_page(page, addr, sz);
+ return;
+ }
might_sleep();
for (i = 0; i < sz/PAGE_SIZE; i++) {
int i;
struct hstate *h = hstate_vma(vma);
- if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES))
- return copy_gigantic_page(dst, src, addr, vma);
+ if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
+ copy_gigantic_page(dst, src, addr, vma);
+ return;
+ }
might_sleep();
for (i = 0; i < pages_per_huge_page(h); i++) {
hugetlb_put_quota(mapping, 1);
}
-/*
- * Increment or decrement surplus_huge_pages. Keep node-specific counters
- * balanced by operating on them in a round-robin fashion.
- * Returns 1 if an adjustment was made.
- */
-static int adjust_pool_surplus(struct hstate *h, int delta)
-{
- static int prev_nid;
- int nid = prev_nid;
- int ret = 0;
-
- VM_BUG_ON(delta != -1 && delta != 1);
- do {
- nid = next_node(nid, node_online_map);
- if (nid == MAX_NUMNODES)
- nid = first_node(node_online_map);
-
- /* To shrink on this node, there must be a surplus page */
- if (delta < 0 && !h->surplus_huge_pages_node[nid])
- continue;
- /* Surplus cannot exceed the total number of pages */
- if (delta > 0 && h->surplus_huge_pages_node[nid] >=
- h->nr_huge_pages_node[nid])
- continue;
-
- h->surplus_huge_pages += delta;
- h->surplus_huge_pages_node[nid] += delta;
- ret = 1;
- break;
- } while (nid != prev_nid);
-
- prev_nid = nid;
- return ret;
-}
-
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
set_compound_page_dtor(page, free_huge_page);
put_page(page); /* free it into the hugepage allocator */
}
+static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+ int i;
+ int nr_pages = 1 << order;
+ struct page *p = page + 1;
+
+ /* we rely on prep_new_huge_page to set the destructor */
+ set_compound_order(page, order);
+ __SetPageHead(page);
+ for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+ __SetPageTail(p);
+ p->first_page = page;
+ }
+}
+
+int PageHuge(struct page *page)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageCompound(page))
+ return 0;
+
+ page = compound_head(page);
+ dtor = get_compound_page_dtor(page);
+
+ return dtor == free_huge_page;
+}
+
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
if (h->order >= MAX_ORDER)
return NULL;
- page = alloc_pages_node(nid,
+ page = alloc_pages_exact_node(nid,
htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
huge_page_order(h));
* Use a helper variable to find the next node and then
* copy it back to hugetlb_next_nid afterwards:
* otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * pass invalid nid MAX_NUMNODES to alloc_pages_exact_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. Move nid forward in the mask even
* can no longer free unreserved surplus pages. This occurs when
* the nodes with surplus pages have no free pages.
*/
- unsigned long remaining_iterations = num_online_nodes();
+ unsigned long remaining_iterations = nr_online_nodes;
/* Uncommit the reservation */
h->resv_huge_pages -= unused_resv_pages;
h->surplus_huge_pages--;
h->surplus_huge_pages_node[nid]--;
nr_pages--;
- remaining_iterations = num_online_nodes();
+ remaining_iterations = nr_online_nodes;
}
}
}
* an instantiated the change should be committed via vma_commit_reservation.
* No action is required on failure.
*/
-static int vma_needs_reservation(struct hstate *h,
+static long vma_needs_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
struct address_space *mapping = vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
- if (vma->vm_flags & VM_SHARED) {
+ if (vma->vm_flags & VM_MAYSHARE) {
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
return region_chg(&inode->i_mapping->private_list,
idx, idx + 1);
return 1;
} else {
- int err;
+ long err;
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
struct resv_map *reservations = vma_resv_map(vma);
struct address_space *mapping = vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
- if (vma->vm_flags & VM_SHARED) {
+ if (vma->vm_flags & VM_MAYSHARE) {
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
region_add(&inode->i_mapping->private_list, idx, idx + 1);
struct page *page;
struct address_space *mapping = vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
- unsigned int chg;
+ long chg;
/*
* Processes that did not create the mapping will have no reserves and
return page;
}
-__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h)
+int __weak alloc_bootmem_huge_page(struct hstate *h)
{
struct huge_bootmem_page *m;
int nr_nodes = nodes_weight(node_online_map);
* puts them into the mem_map).
*/
m = addr;
- if (m)
- goto found;
+ goto found;
}
hstate_next_node(h);
nr_nodes--;
}
#endif
+/*
+ * Increment or decrement surplus_huge_pages. Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(struct hstate *h, int delta)
+{
+ static int prev_nid;
+ int nid = prev_nid;
+ int ret = 0;
+
+ VM_BUG_ON(delta != -1 && delta != 1);
+ do {
+ nid = next_node(nid, node_online_map);
+ if (nid == MAX_NUMNODES)
+ nid = first_node(node_online_map);
+
+ /* To shrink on this node, there must be a surplus page */
+ if (delta < 0 && !h->surplus_huge_pages_node[nid])
+ continue;
+ /* Surplus cannot exceed the total number of pages */
+ if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+ h->nr_huge_pages_node[nid])
+ continue;
+
+ h->surplus_huge_pages += delta;
+ h->surplus_huge_pages_node[nid] += delta;
+ ret = 1;
+ break;
+ } while (nid != prev_nid);
+
+ prev_nid = nid;
+ return ret;
+}
+
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
{
* at the time of fork() could consume its reserves on COW instead
* of the full address range.
*/
- if (!(vma->vm_flags & VM_SHARED) &&
+ if (!(vma->vm_flags & VM_MAYSHARE) &&
is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
old_page != pagecache_page)
outside_reserve = 1;
}
static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep, int write_access)
+ unsigned long address, pte_t *ptep, unsigned int flags)
{
struct hstate *h = hstate_vma(vma);
int ret = VM_FAULT_SIGBUS;
clear_huge_page(page, address, huge_page_size(h));
__SetPageUptodate(page);
- if (vma->vm_flags & VM_SHARED) {
+ if (vma->vm_flags & VM_MAYSHARE) {
int err;
struct inode *inode = mapping->host;
* any allocations necessary to record that reservation occur outside
* the spinlock.
*/
- if (write_access && !(vma->vm_flags & VM_SHARED))
+ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
if (vma_needs_reservation(h, vma, address) < 0) {
ret = VM_FAULT_OOM;
goto backout_unlocked;
&& (vma->vm_flags & VM_SHARED)));
set_huge_pte_at(mm, address, ptep, new_pte);
- if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
/* Optimization, do the COW without a second fault */
ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
}
}
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, int write_access)
+ unsigned long address, unsigned int flags)
{
pte_t *ptep;
pte_t entry;
mutex_lock(&hugetlb_instantiation_mutex);
entry = huge_ptep_get(ptep);
if (huge_pte_none(entry)) {
- ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
+ ret = hugetlb_no_page(mm, vma, address, ptep, flags);
goto out_mutex;
}
* page now as it is used to determine if a reservation has been
* consumed.
*/
- if (write_access && !pte_write(entry)) {
+ if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) {
if (vma_needs_reservation(h, vma, address) < 0) {
ret = VM_FAULT_OOM;
goto out_mutex;
}
- if (!(vma->vm_flags & VM_SHARED))
+ if (!(vma->vm_flags & VM_MAYSHARE))
pagecache_page = hugetlbfs_pagecache_page(h,
vma, address);
}
goto out_page_table_lock;
- if (write_access) {
+ if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry)) {
ret = hugetlb_cow(mm, vma, address, ptep, entry,
pagecache_page);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- if (huge_ptep_set_access_flags(vma, address, ptep, entry, write_access))
+ if (huge_ptep_set_access_flags(vma, address, ptep, entry,
+ flags & FAULT_FLAG_WRITE))
update_mmu_cache(vma, address, entry);
out_page_table_lock:
int hugetlb_reserve_pages(struct inode *inode,
long from, long to,
- struct vm_area_struct *vma)
+ struct vm_area_struct *vma,
+ int acctflag)
{
long ret, chg;
struct hstate *h = hstate_inode(inode);
- if (vma && vma->vm_flags & VM_NORESERVE)
+ /*
+ * Only apply hugepage reservation if asked. At fault time, an
+ * attempt will be made for VM_NORESERVE to allocate a page
+ * and filesystem quota without using reserves
+ */
+ if (acctflag & VM_NORESERVE)
return 0;
/*
* to reserve the full area even if read-only as mprotect() may be
* called to make the mapping read-write. Assume !vma is a shm mapping
*/
- if (!vma || vma->vm_flags & VM_SHARED)
+ if (!vma || vma->vm_flags & VM_MAYSHARE)
chg = region_chg(&inode->i_mapping->private_list, from, to);
else {
struct resv_map *resv_map = resv_map_alloc();
if (chg < 0)
return chg;
+ /* There must be enough filesystem quota for the mapping */
if (hugetlb_get_quota(inode->i_mapping, chg))
return -ENOSPC;
+
+ /*
+ * Check enough hugepages are available for the reservation.
+ * Hand back the quota if there are not
+ */
ret = hugetlb_acct_memory(h, chg);
if (ret < 0) {
hugetlb_put_quota(inode->i_mapping, chg);
return ret;
}
- if (!vma || vma->vm_flags & VM_SHARED)
+
+ /*
+ * Account for the reservations made. Shared mappings record regions
+ * that have reservations as they are shared by multiple VMAs.
+ * When the last VMA disappears, the region map says how much
+ * the reservation was and the page cache tells how much of
+ * the reservation was consumed. Private mappings are per-VMA and
+ * only the consumed reservations are tracked. When the VMA
+ * disappears, the original reservation is the VMA size and the
+ * consumed reservations are stored in the map. Hence, nothing
+ * else has to be done for private mappings here
+ */
+ if (!vma || vma->vm_flags & VM_MAYSHARE)
region_add(&inode->i_mapping->private_list, from, to);
return 0;
}