summaryrefslogtreecommitdiff
path: root/mm/gup.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/gup.c')
-rw-r--r--mm/gup.c99
1 files changed, 76 insertions, 23 deletions
diff --git a/mm/gup.c b/mm/gup.c
index 2cd3b31e3666..c80cdc408228 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -59,13 +59,22 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
}
/*
- * FOLL_FORCE can write to even unwritable pte's, but only
- * after we've gone through a COW cycle and they are dirty.
+ * FOLL_FORCE or a forced COW break can write even to unwritable pte's,
+ * but only after we've gone through a COW cycle and they are dirty.
*/
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
- return pte_write(pte) ||
- ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
+ return pte_write(pte) || ((flags & FOLL_COW) && pte_dirty(pte));
+}
+
+/*
+ * A (separate) COW fault might break the page the other way and
+ * get_user_pages() would return the page from what is now the wrong
+ * VM. So we need to force a COW break at GUP time even for reads.
+ */
+static inline bool should_force_cow_break(struct vm_area_struct *vma, unsigned int flags)
+{
+ return is_cow_mapping(vma->vm_flags) && (flags & FOLL_GET);
}
static struct page *follow_page_pte(struct vm_area_struct *vma,
@@ -126,8 +135,12 @@ retry:
}
}
- if (flags & FOLL_GET)
- get_page_foll(page);
+ if (flags & FOLL_GET) {
+ if (unlikely(!try_get_page_foll(page))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ }
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
@@ -289,7 +302,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
goto unmap;
*page = pte_page(*pte);
}
- get_page(*page);
+ if (unlikely(!try_get_page(*page))) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
out:
ret = 0;
unmap:
@@ -502,12 +518,18 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
if (!vma || check_vma_flags(vma, gup_flags))
return i ? : -EFAULT;
if (is_vm_hugetlb_page(vma)) {
+ if (should_force_cow_break(vma, foll_flags))
+ foll_flags |= FOLL_WRITE;
i = follow_hugetlb_page(mm, vma, pages, vmas,
&start, &nr_pages, i,
- gup_flags);
+ foll_flags);
continue;
}
}
+
+ if (should_force_cow_break(vma, foll_flags))
+ foll_flags |= FOLL_WRITE;
+
retry:
/*
* If we have a pending SIGKILL, don't keep faulting pages and
@@ -1053,6 +1075,20 @@ struct page *get_dump_page(unsigned long addr)
*/
#ifdef CONFIG_HAVE_GENERIC_RCU_GUP
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+ struct page *head = compound_head(page);
+ if (WARN_ON_ONCE(atomic_read(&head->_count) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+ return head;
+}
+
#ifdef __HAVE_ARCH_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
@@ -1083,6 +1119,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
+ if (WARN_ON_ONCE(page_ref_count(page) < 0))
+ goto pte_unmap;
+
if (!page_cache_get_speculative(page))
goto pte_unmap;
@@ -1130,18 +1169,17 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
return 0;
refs = 0;
- head = pmd_page(orig);
- page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
tail = page;
do {
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
pages[*nr] = page;
(*nr)++;
page++;
refs++;
} while (addr += PAGE_SIZE, addr != end);
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pmd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1177,18 +1215,17 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
return 0;
refs = 0;
- head = pud_page(orig);
- page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+ page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
tail = page;
do {
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
pages[*nr] = page;
(*nr)++;
page++;
refs++;
} while (addr += PAGE_SIZE, addr != end);
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pud_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1220,18 +1257,17 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
return 0;
refs = 0;
- head = pgd_page(orig);
- page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+ page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
tail = page;
do {
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
pages[*nr] = page;
(*nr)++;
page++;
refs++;
} while (addr += PAGE_SIZE, addr != end);
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pgd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1325,6 +1361,10 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
/*
* Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
* the regular GUP. It will only return non-negative values.
+ *
+ * Careful, careful! COW breaking can go either way, so a non-write
+ * access can get ambiguous page results. If you call this function without
+ * 'write' set, you'd better be sure that you're ok with that ambiguity.
*/
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages)
@@ -1354,6 +1394,12 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
*
* We do not adopt an rcu_read_lock(.) here as we also want to
* block IPIs that come from THPs splitting.
+ *
+ * NOTE! We allow read-only gup_fast() here, but you'd better be
+ * careful about possible COW pages. You'll get _a_ COW page, but
+ * not necessarily the one you intended to get depending on what
+ * COW event happens after this. COW may break the page copy in a
+ * random direction.
*/
local_irq_save(flags);
@@ -1364,15 +1410,22 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
next = pgd_addr_end(addr, end);
if (pgd_none(pgd))
break;
+ /*
+ * The FAST_GUP case requires FOLL_WRITE even for pure reads,
+ * because get_user_pages() may need to cause an early COW in
+ * order to avoid confusing the normal COW routines. So only
+ * targets that are already writable are safe to do by just
+ * looking at the page tables.
+ */
if (unlikely(pgd_huge(pgd))) {
- if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+ if (!gup_huge_pgd(pgd, pgdp, addr, next, 1,
pages, &nr))
break;
} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
- PGDIR_SHIFT, next, write, pages, &nr))
+ PGDIR_SHIFT, next, 1, pages, &nr))
break;
- } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ } else if (!gup_pud_range(pgd, addr, next, 1, pages, &nr))
break;
} while (pgdp++, addr = next, addr != end);
local_irq_restore(flags);
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-22 12:13:04 +0000