mm: remove gup_flags FOLL_WRITE games from __get_user_pages()

commit 19be0eaffa3ac7d8eb6784ad9bdbc7d67ed8e619 upstream.

This is an ancient bug that was actually attempted to be fixed once
(badly) by me eleven years ago in commit 4ceb5db9757a ("Fix
get_user_pages() race for write access") but that was then undone due to
problems on s390 by commit f33ea7f404e5 ("fix get_user_pages bug").

In the meantime, the s390 situation has long been fixed, and we can now
fix it by checking the pte_dirty() bit properly (and do it better).  The
s390 dirty bit was implemented in abf09bed3cce ("s390/mm: implement
software dirty bits") which made it into v3.9.  Earlier kernels will
have to look at the page state itself.

Also, the VM has become more scalable, and what used a purely
theoretical race back then has become easier to trigger.

To fix it, we introduce a new internal FOLL_COW flag to mark the "yes,
we already did a COW" rather than play racy games with FOLL_WRITE that
is very fundamental, and then use the pte dirty flag to validate that
the FOLL_COW flag is still valid.

Reported-and-tested-by: Phil "not Paul" Oester <kernel@linuxace.com>
Acked-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Michal Hocko <mhocko@suse.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[wt: s/gup.c/memory.c; s/follow_page_pte/follow_page_mask;
     s/faultin_page/__get_user_page]
Signed-off-by: Willy Tarreau <w@1wt.eu>
Bug 1829674

Change-Id: I6fbb1abf656ff7e05ec4c65f07dbbdd694546fb4
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Signed-off-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-on: http://git-master/r/1241323
GVS: Gerrit_Virtual_Submit

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7c2ae69096e2eed8013147e410b642a9ffc1a611..d990cba0161d4b668228ed5f41bfbc46dc80898a 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1736,6 +1736,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_NUMA      0x200   /* force NUMA hinting page fault */
 #define FOLL_MIGRATION 0x400   /* wait for page to replace migration entry */
 #define FOLL_DURABLE   0x800   /* get the page reference for a long time */
+#define FOLL_COW       0x4000  /* internal GUP flag */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
                        void *data);

diff --git a/mm/memory.c b/mm/memory.c
index 60689778088fbc92b92d0d99e334becb2ca032b4..1b3e0937ae5ceb14f68495009500002c7982a940 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1477,6 +1477,16 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
 
 #define FOLL_CMA 0x10000000
 
+/*
+ * FOLL_FORCE can write to even 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));
+}
+
 /**
  * follow_page_mask - look up a page descriptor from a user-virtual address
  * @vma: vm_area_struct mapping @address
@@ -1585,7 +1595,7 @@ split_fallthrough:
        }
        if ((flags & FOLL_NUMA) && pte_numa(pte))
                goto no_page;
-       if ((flags & FOLL_WRITE) && !pte_write(pte))
+       if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags))
                goto unlock;
 
        page = vm_normal_page(vma, address, pte);
@@ -1948,7 +1958,7 @@ follow_page_again:
                                 */
                                if ((ret & VM_FAULT_WRITE) &&
                                    !(vma->vm_flags & VM_WRITE))
-                                       foll_flags &= ~FOLL_WRITE;
+                                       foll_flags |= FOLL_COW;
 
                                cond_resched();
                        }