*
* inode->i_mutex (while writing or truncating, not reading or faulting)
* mm->mmap_sem
- * page->flags PG_locked (lock_page)
+ * page->flags PG_locked (lock_page) * (see huegtlbfs below)
* hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
* mapping->i_mmap_rwsem
+ * hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
* anon_vma->rwsem
* mm->page_table_lock or pte_lock
* pgdat->lru_lock (in mark_page_accessed, isolate_lru_page)
* anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon)
* ->tasklist_lock
* pte map lock
+ *
+ * * hugetlbfs PageHuge() pages take locks in this order:
+ * mapping->i_mmap_rwsem
+ * hugetlb_fault_mutex (hugetlbfs specific page fault mutex)
+ * page->flags PG_locked (lock_page)
*/
#include <linux/mm.h>
* Attach the anon_vmas from src to dst.
* Returns 0 on success, -ENOMEM on failure.
*
- * If dst->anon_vma is NULL this function tries to find and reuse existing
- * anon_vma which has no vmas and only one child anon_vma. This prevents
- * degradation of anon_vma hierarchy to endless linear chain in case of
- * constantly forking task. On the other hand, an anon_vma with more than one
- * child isn't reused even if there was no alive vma, thus rmap walker has a
- * good chance of avoiding scanning the whole hierarchy when it searches where
- * page is mapped.
+ * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and
+ * anon_vma_fork(). The first three want an exact copy of src, while the last
+ * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent
+ * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call,
+ * we can identify this case by checking (!dst->anon_vma && src->anon_vma).
+ *
+ * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find
+ * and reuse existing anon_vma which has no vmas and only one child anon_vma.
+ * This prevents degradation of anon_vma hierarchy to endless linear chain in
+ * case of constantly forking task. On the other hand, an anon_vma with more
+ * than one child isn't reused even if there was no alive vma, thus rmap
+ * walker has a good chance of avoiding scanning the whole hierarchy when it
+ * searches where page is mapped.
*/
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
struct anon_vma_chain *avc, *pavc;
struct anon_vma *root = NULL;
+ struct vm_area_struct *prev = dst->vm_prev, *pprev = src->vm_prev;
+
+ /*
+ * If parent share anon_vma with its vm_prev, keep this sharing in in
+ * child.
+ *
+ * 1. Parent has vm_prev, which implies we have vm_prev.
+ * 2. Parent and its vm_prev have the same anon_vma.
+ */
+ if (!dst->anon_vma && src->anon_vma &&
+ pprev && pprev->anon_vma == src->anon_vma)
+ dst->anon_vma = prev->anon_vma;
+
list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma;
* will always reuse it. Root anon_vma is never reused:
* it has self-parent reference and at least one child.
*/
- if (!dst->anon_vma && anon_vma != src->anon_vma &&
- anon_vma->degree < 2)
+ if (!dst->anon_vma && src->anon_vma &&
+ anon_vma != src->anon_vma && anon_vma->degree < 2)
dst->anon_vma = anon_vma;
}
if (dst->anon_vma)
* chain and verify that the page in question is indeed mapped in it
* [ something equivalent to page_mapped_in_vma() ].
*
- * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap()
- * that the anon_vma pointer from page->mapping is valid if there is a
- * mapcount, we can dereference the anon_vma after observing those.
+ * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
+ * page_remove_rmap() that the anon_vma pointer from page->mapping is valid
+ * if there is a mapcount, we can dereference the anon_vma after observing
+ * those.
*/
struct anon_vma *page_get_anon_vma(struct page *page)
{
static void __page_check_anon_rmap(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
-#ifdef CONFIG_DEBUG_VM
/*
* The page's anon-rmap details (mapping and index) are guaranteed to
* be set up correctly at this point.
* are initially only visible via the pagetables, and the pte is locked
* over the call to page_add_new_anon_rmap.
*/
- BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root);
- BUG_ON(page_to_pgoff(page) != linear_page_index(vma, address));
-#endif
+ VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page);
+ VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address),
+ page);
}
/**
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
/* increment count (starts at -1) */
atomic_set(compound_mapcount_ptr(page), 0);
+ if (hpage_pincount_available(page))
+ atomic_set(compound_pincount_ptr(page), 0);
+
__inc_node_page_state(page, NR_ANON_THPS);
} else {
/* Anon THP always mapped first with PMD */
if (TestClearPageDoubleMap(page)) {
/*
* Subpages can be mapped with PTEs too. Check how many of
- * themi are still mapped.
+ * them are still mapped.
*/
for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) {
if (atomic_add_negative(-1, &page[i]._mapcount))
nr++;
}
+
+ /*
+ * Queue the page for deferred split if at least one small
+ * page of the compound page is unmapped, but at least one
+ * small page is still mapped.
+ */
+ if (nr && nr < HPAGE_PMD_NR)
+ deferred_split_huge_page(page);
} else {
nr = HPAGE_PMD_NR;
}
if (unlikely(PageMlocked(page)))
clear_page_mlock(page);
- if (nr) {
+ if (nr)
__mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr);
- deferred_split_huge_page(page);
- }
}
/**
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
+ *
+ * If called for a huge page, caller must hold i_mmap_rwsem
+ * in write mode as it is possible to call huge_pmd_unshare.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
address = pvmw.address;
if (PageHuge(page)) {
+ /*
+ * To call huge_pmd_unshare, i_mmap_rwsem must be
+ * held in write mode. Caller needs to explicitly
+ * do this outside rmap routines.
+ */
+ VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
if (huge_pmd_unshare(mm, &address, pvmw.pte)) {
/*
* huge_pmd_unshare unmapped an entire PMD
return ret;
}
-bool is_vma_temporary_stack(struct vm_area_struct *vma)
-{
- int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
-
- if (!maybe_stack)
- return false;
-
- if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
- VM_STACK_INCOMPLETE_SETUP)
- return true;
-
- return false;
-}
-
static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
{
- return is_vma_temporary_stack(vma);
+ return vma_is_temporary_stack(vma);
}
static int page_mapcount_is_zero(struct page *page)
{
BUG_ON(address < vma->vm_start || address >= vma->vm_end);
atomic_set(compound_mapcount_ptr(page), 0);
+ if (hpage_pincount_available(page))
+ atomic_set(compound_pincount_ptr(page), 0);
+
__page_set_anon_rmap(page, vma, address, 1);
}
#endif /* CONFIG_HUGETLB_PAGE */