static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
static unsigned int free_huge_pages_node[MAX_NUMNODES];
+
+/*
+ * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
+ */
static DEFINE_SPINLOCK(hugetlb_lock);
static void enqueue_huge_page(struct page *page)
HUGETLB_PAGE_ORDER);
nid = (nid + 1) % num_online_nodes();
if (page) {
+ spin_lock(&hugetlb_lock);
nr_huge_pages++;
nr_huge_pages_node[page_to_nid(page)]++;
+ spin_unlock(&hugetlb_lock);
}
return page;
}
unsigned long i;
struct page *page;
+ if (HPAGE_SHIFT == 0)
+ return 0;
+
for (i = 0; i < MAX_NUMNODES; ++i)
INIT_LIST_HEAD(&hugepage_freelists[i]);
{
return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE);
}
-EXPORT_SYMBOL(hugetlb_total_pages);
/*
* We cannot handle pagefaults against hugetlb pages at all. They cause
.nopage = hugetlb_nopage,
};
-static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page)
+static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
+ int writable)
{
pte_t entry;
- if (vma->vm_flags & VM_WRITE) {
+ if (writable) {
entry =
pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
} else {
return entry;
}
+static void set_huge_ptep_writable(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ pte_t entry;
+
+ entry = pte_mkwrite(pte_mkdirty(*ptep));
+ ptep_set_access_flags(vma, address, ptep, entry, 1);
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
+}
+
+
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry;
struct page *ptepage;
unsigned long addr;
+ int cow;
+
+ cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+ src_pte = huge_pte_offset(src, addr);
+ if (!src_pte)
+ continue;
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto nomem;
+ spin_lock(&dst->page_table_lock);
spin_lock(&src->page_table_lock);
- src_pte = huge_pte_offset(src, addr);
- if (src_pte && !pte_none(*src_pte)) {
+ if (!pte_none(*src_pte)) {
+ if (cow)
+ ptep_set_wrprotect(src, addr, src_pte);
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
- add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
+ add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
set_huge_pte_at(dst, addr, dst_pte, entry);
}
spin_unlock(&src->page_table_lock);
+ spin_unlock(&dst->page_table_lock);
}
return 0;
BUG_ON(start & ~HPAGE_MASK);
BUG_ON(end & ~HPAGE_MASK);
+ spin_lock(&mm->page_table_lock);
+
+ /* Update high watermark before we lower rss */
+ update_hiwater_rss(mm);
+
for (address = start; address < end; address += HPAGE_SIZE) {
ptep = huge_pte_offset(mm, address);
- if (! ptep)
- /* This can happen on truncate, or if an
- * mmap() is aborted due to an error before
- * the prefault */
+ if (!ptep)
continue;
pte = huge_ptep_get_and_clear(mm, address, ptep);
page = pte_page(pte);
put_page(page);
- add_mm_counter(mm, rss, - (HPAGE_SIZE / PAGE_SIZE));
+ add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
}
+
+ spin_unlock(&mm->page_table_lock);
flush_tlb_range(vma, start, end);
}
-void zap_hugepage_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long length)
+static struct page *find_or_alloc_huge_page(struct address_space *mapping,
+ unsigned long idx, int shared)
{
- struct mm_struct *mm = vma->vm_mm;
+ struct page *page;
+ int err;
- spin_lock(&mm->page_table_lock);
- unmap_hugepage_range(vma, start, start + length);
- spin_unlock(&mm->page_table_lock);
+retry:
+ page = find_lock_page(mapping, idx);
+ if (page)
+ goto out;
+
+ if (hugetlb_get_quota(mapping))
+ goto out;
+ page = alloc_huge_page();
+ if (!page) {
+ hugetlb_put_quota(mapping);
+ goto out;
+ }
+
+ if (shared) {
+ err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+ if (err) {
+ put_page(page);
+ hugetlb_put_quota(mapping);
+ if (err == -EEXIST)
+ goto retry;
+ page = NULL;
+ }
+ } else {
+ /* Caller expects a locked page */
+ lock_page(page);
+ }
+out:
+ return page;
}
-int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
+static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep, pte_t pte)
{
- struct mm_struct *mm = current->mm;
- unsigned long addr;
- int ret = 0;
+ struct page *old_page, *new_page;
+ int i, avoidcopy;
- WARN_ON(!is_vm_hugetlb_page(vma));
- BUG_ON(vma->vm_start & ~HPAGE_MASK);
- BUG_ON(vma->vm_end & ~HPAGE_MASK);
+ old_page = pte_page(pte);
- hugetlb_prefault_arch_hook(mm);
+ /* If no-one else is actually using this page, avoid the copy
+ * and just make the page writable */
+ avoidcopy = (page_count(old_page) == 1);
+ if (avoidcopy) {
+ set_huge_ptep_writable(vma, address, ptep);
+ return VM_FAULT_MINOR;
+ }
+
+ page_cache_get(old_page);
+ new_page = alloc_huge_page();
+
+ if (!new_page) {
+ page_cache_release(old_page);
+
+ /* Logically this is OOM, not a SIGBUS, but an OOM
+ * could cause the kernel to go killing other
+ * processes which won't help the hugepage situation
+ * at all (?) */
+ return VM_FAULT_SIGBUS;
+ }
+ spin_unlock(&mm->page_table_lock);
+ for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++)
+ copy_user_highpage(new_page + i, old_page + i,
+ address + i*PAGE_SIZE);
spin_lock(&mm->page_table_lock);
- for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
- unsigned long idx;
- pte_t *pte = huge_pte_alloc(mm, addr);
- struct page *page;
- if (!pte) {
- ret = -ENOMEM;
- goto out;
- }
+ ptep = huge_pte_offset(mm, address & HPAGE_MASK);
+ if (likely(pte_same(*ptep, pte))) {
+ /* Break COW */
+ set_huge_pte_at(mm, address, ptep,
+ make_huge_pte(vma, new_page, 1));
+ /* Make the old page be freed below */
+ new_page = old_page;
+ }
+ page_cache_release(new_page);
+ page_cache_release(old_page);
+ return VM_FAULT_MINOR;
+}
- idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
- + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
- page = find_get_page(mapping, idx);
- if (!page) {
- /* charge the fs quota first */
- if (hugetlb_get_quota(mapping)) {
- ret = -ENOMEM;
- goto out;
- }
- page = alloc_huge_page();
- if (!page) {
- hugetlb_put_quota(mapping);
- ret = -ENOMEM;
- goto out;
- }
- ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
- if (! ret) {
- unlock_page(page);
- } else {
- hugetlb_put_quota(mapping);
- free_huge_page(page);
- goto out;
- }
- }
- add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
- set_huge_pte_at(mm, addr, pte, make_huge_pte(vma, page));
+int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep, int write_access)
+{
+ int ret = VM_FAULT_SIGBUS;
+ unsigned long idx;
+ unsigned long size;
+ struct page *page;
+ struct address_space *mapping;
+ pte_t new_pte;
+
+ mapping = vma->vm_file->f_mapping;
+ idx = ((address - vma->vm_start) >> HPAGE_SHIFT)
+ + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+
+ /*
+ * Use page lock to guard against racing truncation
+ * before we get page_table_lock.
+ */
+ page = find_or_alloc_huge_page(mapping, idx,
+ vma->vm_flags & VM_SHARED);
+ if (!page)
+ goto out;
+
+ BUG_ON(!PageLocked(page));
+
+ spin_lock(&mm->page_table_lock);
+ size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+ if (idx >= size)
+ goto backout;
+
+ ret = VM_FAULT_MINOR;
+ if (!pte_none(*ptep))
+ goto backout;
+
+ add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
+ new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
+ && (vma->vm_flags & VM_SHARED)));
+ set_huge_pte_at(mm, address, ptep, new_pte);
+
+ if (write_access && !(vma->vm_flags & VM_SHARED)) {
+ /* Optimization, do the COW without a second fault */
+ ret = hugetlb_cow(mm, vma, address, ptep, new_pte);
}
-out:
+
spin_unlock(&mm->page_table_lock);
+ unlock_page(page);
+out:
return ret;
+
+backout:
+ spin_unlock(&mm->page_table_lock);
+ hugetlb_put_quota(mapping);
+ unlock_page(page);
+ put_page(page);
+ goto out;
}
-/*
- * On ia64 at least, it is possible to receive a hugetlb fault from a
- * stale zero entry left in the TLB from earlier hardware prefetching.
- * Low-level arch code should already have flushed the stale entry as
- * part of its fault handling, but we do need to accept this minor fault
- * and return successfully. Whereas the "normal" case is that this is
- * an access to a hugetlb page which has been truncated off since mmap.
- */
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, int write_access)
{
- int ret = VM_FAULT_SIGBUS;
- pte_t *pte;
+ pte_t *ptep;
+ pte_t entry;
+ int ret;
+
+ ptep = huge_pte_alloc(mm, address);
+ if (!ptep)
+ return VM_FAULT_OOM;
+
+ entry = *ptep;
+ if (pte_none(entry))
+ return hugetlb_no_page(mm, vma, address, ptep, write_access);
+
+ ret = VM_FAULT_MINOR;
spin_lock(&mm->page_table_lock);
- pte = huge_pte_offset(mm, address);
- if (pte && !pte_none(*pte))
- ret = VM_FAULT_MINOR;
+ /* Check for a racing update before calling hugetlb_cow */
+ if (likely(pte_same(entry, *ptep)))
+ if (write_access && !pte_write(entry))
+ ret = hugetlb_cow(mm, vma, address, ptep, entry);
spin_unlock(&mm->page_table_lock);
+
return ret;
}
unsigned long vpfn, vaddr = *position;
int remainder = *length;
- BUG_ON(!is_vm_hugetlb_page(vma));
-
vpfn = vaddr/PAGE_SIZE;
spin_lock(&mm->page_table_lock);
while (vaddr < vma->vm_end && remainder) {
+ pte_t *pte;
+ struct page *page;
- if (pages) {
- pte_t *pte;
- struct page *page;
-
- /* Some archs (sparc64, sh*) have multiple
- * pte_ts to each hugepage. We have to make
- * sure we get the first, for the page
- * indexing below to work. */
- pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
-
- /* the hugetlb file might have been truncated */
- if (!pte || pte_none(*pte)) {
- remainder = 0;
- if (!i)
- i = -EFAULT;
- break;
- }
+ /*
+ * Some archs (sparc64, sh*) have multiple pte_ts to
+ * each hugepage. We have to make * sure we get the
+ * first, for the page indexing below to work.
+ */
+ pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
- page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
+ if (!pte || pte_none(*pte)) {
+ int ret;
+
+ spin_unlock(&mm->page_table_lock);
+ ret = hugetlb_fault(mm, vma, vaddr, 0);
+ spin_lock(&mm->page_table_lock);
+ if (ret == VM_FAULT_MINOR)
+ continue;
- WARN_ON(!PageCompound(page));
+ remainder = 0;
+ if (!i)
+ i = -EFAULT;
+ break;
+ }
+ if (pages) {
+ page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
get_page(page);
pages[i] = page;
}
projects / linux-2.6-block.git / blobdiff