summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-04-14 15:09:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-04-14 15:09:40 -0700
commit6b3a707736301c2128ca85ce85fb13f60b5e350a (patch)
tree2bf1892cf29121150adece8d1221ecd513a4e792 /mm
parent4443f8e6ac7755cd775c70d08be8042dc2f936cb (diff)
parent15fab63e1e57be9fdb5eec1bbc5916e9825e9acb (diff)
downloadlinux-6b3a707736301c2128ca85ce85fb13f60b5e350a.tar.bz2
Merge branch 'page-refs' (page ref overflow)
Merge page ref overflow branch. Jann Horn reported that he can overflow the page ref count with sufficient memory (and a filesystem that is intentionally extremely slow). Admittedly it's not exactly easy. To have more than four billion references to a page requires a minimum of 32GB of kernel memory just for the pointers to the pages, much less any metadata to keep track of those pointers. Jann needed a total of 140GB of memory and a specially crafted filesystem that leaves all reads pending (in order to not ever free the page references and just keep adding more). Still, we have a fairly straightforward way to limit the two obvious user-controllable sources of page references: direct-IO like page references gotten through get_user_pages(), and the splice pipe page duplication. So let's just do that. * branch page-refs: fs: prevent page refcount overflow in pipe_buf_get mm: prevent get_user_pages() from overflowing page refcount mm: add 'try_get_page()' helper function mm: make page ref count overflow check tighter and more explicit
Diffstat (limited to 'mm')
-rw-r--r--mm/gup.c48
-rw-r--r--mm/hugetlb.c13
2 files changed, 49 insertions, 12 deletions
diff --git a/mm/gup.c b/mm/gup.c
index f84e22685aaa..91819b8ad9cc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -160,8 +160,12 @@ retry:
goto retry;
}
- if (flags & FOLL_GET)
- get_page(page);
+ if (flags & FOLL_GET) {
+ if (unlikely(!try_get_page(page))) {
+ page = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ }
if (flags & FOLL_TOUCH) {
if ((flags & FOLL_WRITE) &&
!pte_dirty(pte) && !PageDirty(page))
@@ -298,7 +302,10 @@ retry_locked:
if (pmd_trans_unstable(pmd))
ret = -EBUSY;
} else {
- get_page(page);
+ if (unlikely(!try_get_page(page))) {
+ spin_unlock(ptl);
+ return ERR_PTR(-ENOMEM);
+ }
spin_unlock(ptl);
lock_page(page);
ret = split_huge_page(page);
@@ -500,7 +507,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
if (is_device_public_page(*page))
goto unmap;
}
- get_page(*page);
+ if (unlikely(!try_get_page(*page))) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
out:
ret = 0;
unmap:
@@ -1545,6 +1555,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
}
}
+/*
+ * 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(page_ref_count(head) < 0))
+ return NULL;
+ if (unlikely(!page_cache_add_speculative(head, refs)))
+ return NULL;
+ return head;
+}
+
#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
@@ -1579,9 +1603,9 @@ 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);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ head = try_get_compound_head(page, 1);
+ if (!head)
goto pte_unmap;
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1720,8 +1744,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pmd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pmd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1758,8 +1782,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pud_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pud_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
@@ -1795,8 +1819,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- head = compound_head(pgd_page(orig));
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(pgd_page(orig), refs);
+ if (!head) {
*nr -= refs;
return 0;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 97b1e0290c66..6cdc7b2d9100 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4299,6 +4299,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
page = pte_page(huge_ptep_get(pte));
+
+ /*
+ * Instead of doing 'try_get_page()' below in the same_page
+ * loop, just check the count once here.
+ */
+ if (unlikely(page_count(page) <= 0)) {
+ if (pages) {
+ spin_unlock(ptl);
+ remainder = 0;
+ err = -ENOMEM;
+ break;
+ }
+ }
same_page:
if (pages) {
pages[i] = mem_map_offset(page, pfn_offset);