summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c73
1 files changed, 44 insertions, 29 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8ee3bd8ec5b..dae27ba3be2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -24,7 +24,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/node.h>
@@ -62,10 +62,10 @@ static DEFINE_SPINLOCK(hugetlb_lock);
* 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;
@@ -475,7 +475,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
/* 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) {
@@ -503,9 +503,10 @@ static void update_and_free_page(struct hstate *h, struct page *page)
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);
@@ -591,7 +592,6 @@ int PageHuge(struct page *page)
return dtor == free_huge_page;
}
-
EXPORT_SYMBOL_GPL(PageHuge);
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
@@ -1033,10 +1033,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
*/
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);
@@ -1105,12 +1105,28 @@ static void __init gather_bootmem_prealloc(void)
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;
}
}
@@ -2116,9 +2132,8 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
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);
- }
}
@@ -2173,9 +2188,9 @@ static int is_hugetlb_entry_migration(pte_t pte)
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;
}
@@ -2186,9 +2201,9 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
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;
}
@@ -2205,7 +2220,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
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.
*/
@@ -2274,9 +2289,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
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);
}
/*
@@ -2308,7 +2323,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
* 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)
@@ -2326,7 +2341,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
address, address + huge_page_size(h),
page);
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return 1;
}
@@ -2551,7 +2566,7 @@ retry:
* 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;
}
@@ -2619,7 +2634,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
migration_entry_wait(mm, (pmd_t *)ptep, address);
return 0;
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
- return VM_FAULT_HWPOISON_LARGE |
+ return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(h - hstates);
}
@@ -2810,7 +2825,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
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);
@@ -2825,7 +2840,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
}
}
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);
}
@@ -2833,7 +2848,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
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);
@@ -2843,7 +2858,7 @@ int hugetlb_reserve_pages(struct 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;
/*
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-13 14:23:05 +0000