summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c98
1 files changed, 69 insertions, 29 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3eedb187e549..1a88006ec634 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -867,7 +867,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
h->free_huge_pages_node[nid]++;
}
-static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
{
struct page *page;
@@ -887,6 +887,22 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
return page;
}
+static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+ int node;
+
+ if (nid != NUMA_NO_NODE)
+ return dequeue_huge_page_node_exact(h, nid);
+
+ for_each_online_node(node) {
+ page = dequeue_huge_page_node_exact(h, node);
+ if (page)
+ return page;
+ }
+ return NULL;
+}
+
/* Movability of hugepages depends on migration support. */
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
@@ -904,6 +920,8 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
struct page *page = NULL;
struct mempolicy *mpol;
nodemask_t *nodemask;
+ gfp_t gfp_mask;
+ int nid;
struct zonelist *zonelist;
struct zone *zone;
struct zoneref *z;
@@ -924,12 +942,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
retry_cpuset:
cpuset_mems_cookie = read_mems_allowed_begin();
- zonelist = huge_zonelist(vma, address,
- htlb_alloc_mask(h), &mpol, &nodemask);
+ gfp_mask = htlb_alloc_mask(h);
+ nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
+ zonelist = node_zonelist(nid, gfp_mask);
for_each_zone_zonelist_nodemask(zone, z, zonelist,
MAX_NR_ZONES - 1, nodemask) {
- if (cpuset_zone_allowed(zone, htlb_alloc_mask(h))) {
+ if (cpuset_zone_allowed(zone, gfp_mask)) {
page = dequeue_huge_page_node(h, zone_to_nid(zone));
if (page) {
if (avoid_reserve)
@@ -1024,9 +1043,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
((node = hstate_next_node_to_free(hs, mask)) || 1); \
nr_nodes--)
-#if defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) && \
- ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \
- defined(CONFIG_CMA))
+#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
static void destroy_compound_gigantic_page(struct page *page,
unsigned int order)
{
@@ -1158,8 +1175,7 @@ static int alloc_fresh_gigantic_page(struct hstate *h,
return 0;
}
-static inline bool gigantic_page_supported(void) { return true; }
-#else
+#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
static inline bool gigantic_page_supported(void) { return false; }
static inline void free_gigantic_page(struct page *page, unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
@@ -1545,13 +1561,13 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
do {
struct page *page;
struct mempolicy *mpol;
- struct zonelist *zl;
+ int nid;
nodemask_t *nodemask;
cpuset_mems_cookie = read_mems_allowed_begin();
- zl = huge_zonelist(vma, addr, gfp, &mpol, &nodemask);
+ nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
mpol_cond_put(mpol);
- page = __alloc_pages_nodemask(gfp, order, zl, nodemask);
+ page = __alloc_pages_nodemask(gfp, order, nid, nodemask);
if (page)
return page;
} while (read_mems_allowed_retry(cpuset_mems_cookie));
@@ -3185,17 +3201,17 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
update_mmu_cache(vma, address, ptep);
}
-static int is_hugetlb_entry_migration(pte_t pte)
+bool is_hugetlb_entry_migration(pte_t pte)
{
swp_entry_t swp;
if (huge_pte_none(pte) || pte_present(pte))
- return 0;
+ return false;
swp = pte_to_swp_entry(pte);
if (non_swap_entry(swp) && is_migration_entry(swp))
- return 1;
+ return true;
else
- return 0;
+ return false;
}
static int is_hugetlb_entry_hwpoisoned(pte_t pte)
@@ -3233,7 +3249,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
spinlock_t *src_ptl, *dst_ptl;
- src_pte = huge_pte_offset(src, addr);
+ src_pte = huge_pte_offset(src, addr, sz);
if (!src_pte)
continue;
dst_pte = huge_pte_alloc(dst, addr, sz);
@@ -3263,9 +3279,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
*/
make_migration_entry_read(&swp_entry);
entry = swp_entry_to_pte(swp_entry);
- set_huge_pte_at(src, addr, src_pte, entry);
+ set_huge_swap_pte_at(src, addr, src_pte,
+ entry, sz);
}
- set_huge_pte_at(dst, addr, dst_pte, entry);
+ set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
} else {
if (cow) {
huge_ptep_set_wrprotect(src, addr, src_pte);
@@ -3317,7 +3334,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
address = start;
for (; address < end; address += sz) {
- ptep = huge_pte_offset(mm, address);
+ ptep = huge_pte_offset(mm, address, sz);
if (!ptep)
continue;
@@ -3338,7 +3355,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
* unmapped and its refcount is dropped, so just clear pte here.
*/
if (unlikely(!pte_present(pte))) {
- huge_pte_clear(mm, address, ptep);
+ huge_pte_clear(mm, address, ptep, sz);
spin_unlock(ptl);
continue;
}
@@ -3535,7 +3552,8 @@ retry_avoidcopy:
unmap_ref_private(mm, vma, old_page, address);
BUG_ON(huge_pte_none(pte));
spin_lock(ptl);
- ptep = huge_pte_offset(mm, address & huge_page_mask(h));
+ ptep = huge_pte_offset(mm, address & huge_page_mask(h),
+ huge_page_size(h));
if (likely(ptep &&
pte_same(huge_ptep_get(ptep), pte)))
goto retry_avoidcopy;
@@ -3574,7 +3592,8 @@ retry_avoidcopy:
* before the page tables are altered
*/
spin_lock(ptl);
- ptep = huge_pte_offset(mm, address & huge_page_mask(h));
+ ptep = huge_pte_offset(mm, address & huge_page_mask(h),
+ huge_page_size(h));
if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
ClearPagePrivate(new_page);
@@ -3861,7 +3880,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
address &= huge_page_mask(h);
- ptep = huge_pte_offset(mm, address);
+ ptep = huge_pte_offset(mm, address, huge_page_size(h));
if (ptep) {
entry = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_migration(entry))) {
@@ -4118,7 +4137,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
*
* Note that page table lock is not held when pte is null.
*/
- pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h),
+ huge_page_size(h));
if (pte)
ptl = huge_pte_lock(h, mm, pte);
absent = !pte || huge_pte_none(huge_ptep_get(pte));
@@ -4257,7 +4277,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
i_mmap_lock_write(vma->vm_file->f_mapping);
for (; address < end; address += huge_page_size(h)) {
spinlock_t *ptl;
- ptep = huge_pte_offset(mm, address);
+ ptep = huge_pte_offset(mm, address, huge_page_size(h));
if (!ptep)
continue;
ptl = huge_pte_lock(h, mm, ptep);
@@ -4279,7 +4299,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
make_migration_entry_read(&entry);
newpte = swp_entry_to_pte(entry);
- set_huge_pte_at(mm, address, ptep, newpte);
+ set_huge_swap_pte_at(mm, address, ptep,
+ newpte, huge_page_size(h));
pages++;
}
spin_unlock(ptl);
@@ -4521,7 +4542,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
saddr = page_table_shareable(svma, vma, addr, idx);
if (saddr) {
- spte = huge_pte_offset(svma->vm_mm, saddr);
+ spte = huge_pte_offset(svma->vm_mm, saddr,
+ vma_mmu_pagesize(svma));
if (spte) {
get_page(virt_to_page(spte));
break;
@@ -4617,7 +4639,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
return pte;
}
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -4653,6 +4676,14 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address,
}
struct page * __weak
+follow_huge_pd(struct vm_area_struct *vma,
+ unsigned long address, hugepd_t hpd, int flags, int pdshift)
+{
+ WARN(1, "hugepd follow called with no support for hugepage directory format\n");
+ return NULL;
+}
+
+struct page * __weak
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int flags)
{
@@ -4699,6 +4730,15 @@ follow_huge_pud(struct mm_struct *mm, unsigned long address,
return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
}
+struct page * __weak
+follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags)
+{
+ if (flags & FOLL_GET)
+ return NULL;
+
+ return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
+}
+
#ifdef CONFIG_MEMORY_FAILURE
/*