fix CVE 2016-5195

diff --git a/CVE-2016-5195.patch b/CVE-2016-5195.patch
new file mode 100644 (file)
index 0000000..2805cc1
--- /dev/null
+++ b/CVE-2016-5195.patch
@@ -0,0 +1,92 @@
+From 19be0eaffa3ac7d8eb6784ad9bdbc7d67ed8e619 Mon Sep 17 00:00:00 2001
+From: Linus Torvalds <torvalds@linux-foundation.org>
+Date: Thu, 13 Oct 2016 13:07:36 -0700
+Subject: mm: remove gup_flags FOLL_WRITE games from __get_user_pages()
+
+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>
+---
+ include/linux/mm.h |  1 +
+ mm/memory.c        | 15 ++++++++++++--
+ 2 files changed, 14 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index e9caec6..ed85879 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -1971,6 +1971,7 @@ 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_TRIED    0x800   /* a retry, previous pass started an IO */
++#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 fce5131..f62b9f7 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -1467,6 +1467,17 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
+ }
+ EXPORT_SYMBOL_GPL(zap_vma_ptes);
+ 
++/*
++ * 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
+@@ -1588,7 +1599,7 @@ 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);
+@@ -1900,7 +1911,7 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+                                */
+                               if ((ret & VM_FAULT_WRITE) &&
+                                   !(vma->vm_flags & VM_WRITE))
+-                                      foll_flags &= ~FOLL_WRITE;
++                                      foll_flags |= FOLL_COW;
+ 
+                               cond_resched();
+                       }

diff --git a/Makefile b/Makefile
index 5f18162e048bfe1ca42cd751ccfe97d88b85e21f..2d5117314b5b75c4bcd2fd38d0fa90b325679dc7 100644 (file)
--- a/Makefile
+++ b/Makefile
@@ -193,6 +193,7 @@ ${KERNEL_SRC}/README: ${KERNEL_SRC}.org/README
        cp ${KERNEL_SRC}/drivers/vhost/scsi.c ${KERNEL_SRC}/drivers/vhost/scsi.c.backup 
        # vhost-scsi compile fixes
        cd ${KERNEL_SRC}; patch -p1 <../vhost-scsi-fixes.patch
+       cd ${KERNEL_SRC}; patch -p1 <../CVE-2016-5195.patch
        sed -i ${KERNEL_SRC}/Makefile -e 's/^EXTRAVERSION.*$$/EXTRAVERSION=${EXTRAVERSION}/'
        touch $@
 

diff --git a/changelog.Debian b/changelog.Debian
index d9b1520402b0ba42f597afcb2e13abb36547b91a..672a2cfacb58da2003737a155195c671fe13c5d3 100644 (file)
--- a/changelog.Debian
+++ b/changelog.Debian
@@ -4,6 +4,8 @@ pve-kernel-3.10.0 (3.10.0-50) unstable; urgency=low
 
   * bump api to 21-pve
   
+  * fix CVE 2016-5195 (CVE-2016-5195.patch)
+  
  -- Proxmox Support Team <support@proxmox.com>  Fri, 21 Oct 2016 15:43:49 +0200
 
 pve-kernel-3.10.0 (3.10.0-49) unstable; urgency=low