[Devel] [PATCH RHEL7 COMMIT] ms/mm: allow drivers to prevent new writable mappings
Konstantin Khorenko
khorenko at virtuozzo.com
Thu Oct 15 04:04:16 PDT 2015
The commit is pushed to "branch-rh7-3.10.0-229.7.2.vz7.8.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-229.7.2.vz7.8.6
------>
commit a60b63122e58834a4fd04b9be05311dd67801a07
Author: Andrew Vagin <avagin at openvz.org>
Date: Thu Oct 15 15:04:16 2015 +0400
ms/mm: allow drivers to prevent new writable mappings
The patch is required for CRIU.
https://jira.sw.ru/browse/PSBM-39834
From: David Herrmann <dh.herrmann at gmail.com>
ML: 4bb5f5d9395bc112d93a134d8f5b05611eddc9c0
This patch (of 6):
The i_mmap_writable field counts existing writable mappings of an
address_space. To allow drivers to prevent new writable mappings, make
this counter signed and prevent new writable mappings if it is negative.
This is modelled after i_writecount and DENYWRITE.
This will be required by the shmem-sealing infrastructure to prevent any
new writable mappings after the WRITE seal has been set. In case there
exists a writable mapping, this operation will fail with EBUSY.
Note that we rely on the fact that iff you already own a writable mapping,
you can increase the counter without using the helpers. This is the same
that we do for i_writecount.
Signed-off-by: David Herrmann <dh.herrmann at gmail.com>
Acked-by: Hugh Dickins <hughd at google.com>
Cc: Michael Kerrisk <mtk.manpages at gmail.com>
Cc: Ryan Lortie <desrt at desrt.ca>
Cc: Lennart Poettering <lennart at poettering.net>
Cc: Daniel Mack <zonque at gmail.com>
Cc: Andy Lutomirski <luto at amacapital.net>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Andrew Vagin <avagin at openvz.org>
---
fs/inode.c | 1 +
include/linux/fs.h | 29 +++++++++++++++++++++++++++--
kernel/fork.c | 2 +-
mm/mmap.c | 30 ++++++++++++++++++++++++------
mm/swap_state.c | 1 +
5 files changed, 54 insertions(+), 9 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 8c14103..960cd15 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -171,6 +171,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
+ atomic_set(&mapping->i_mmap_writable, 0);
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->private_data = NULL;
mapping->backing_dev_info = &default_backing_dev_info;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbbf186..f410c54 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -547,7 +547,7 @@ struct address_space {
struct inode *host; /* owner: inode, block_device */
struct radix_tree_root page_tree; /* radix tree of all pages */
spinlock_t tree_lock; /* and lock protecting it */
- unsigned int i_mmap_writable;/* count VM_SHARED mappings */
+ atomic_t i_mmap_writable;/* count VM_SHARED mappings */
struct rb_root i_mmap; /* tree of private and shared mappings */
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
struct mutex i_mmap_mutex; /* protect tree, count, list */
@@ -633,10 +633,35 @@ static inline int mapping_mapped(struct address_space *mapping)
* Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
* marks vma as VM_SHARED if it is shared, and the file was opened for
* writing i.e. vma may be mprotected writable even if now readonly.
+ *
+ * If i_mmap_writable is negative, no new writable mappings are allowed. You
+ * can only deny writable mappings, if none exists right now.
*/
static inline int mapping_writably_mapped(struct address_space *mapping)
{
- return mapping->i_mmap_writable != 0;
+ return atomic_read(&mapping->i_mmap_writable) > 0;
+}
+
+static inline int mapping_map_writable(struct address_space *mapping)
+{
+ return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
+ 0 : -EPERM;
+}
+
+static inline void mapping_unmap_writable(struct address_space *mapping)
+{
+ atomic_dec(&mapping->i_mmap_writable);
+}
+
+static inline int mapping_deny_writable(struct address_space *mapping)
+{
+ return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
+ 0 : -EBUSY;
+}
+
+static inline void mapping_allow_writable(struct address_space *mapping)
+{
+ atomic_inc(&mapping->i_mmap_writable);
}
/*
diff --git a/kernel/fork.c b/kernel/fork.c
index 505fa21..8fcc5db 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -435,7 +435,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
atomic_dec(&inode->i_writecount);
mutex_lock(&mapping->i_mmap_mutex);
if (tmp->vm_flags & VM_SHARED)
- mapping->i_mmap_writable++;
+ atomic_inc(&mapping->i_mmap_writable);
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
if (unlikely(tmp->vm_flags & VM_NONLINEAR))
diff --git a/mm/mmap.c b/mm/mmap.c
index f87a78b..7cc9812 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -222,7 +222,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma,
if (vma->vm_flags & VM_DENYWRITE)
atomic_inc(&file_inode(file)->i_writecount);
if (vma->vm_flags & VM_SHARED)
- mapping->i_mmap_writable--;
+ mapping_unmap_writable(mapping);
flush_dcache_mmap_lock(mapping);
if (unlikely(vma->vm_flags & VM_NONLINEAR))
@@ -626,7 +626,7 @@ static void __vma_link_file(struct vm_area_struct *vma)
if (vma->vm_flags & VM_DENYWRITE)
atomic_dec(&file_inode(file)->i_writecount);
if (vma->vm_flags & VM_SHARED)
- mapping->i_mmap_writable++;
+ atomic_inc(&mapping->i_mmap_writable);
flush_dcache_mmap_lock(mapping);
if (unlikely(vma->vm_flags & VM_NONLINEAR))
@@ -1575,6 +1575,17 @@ munmap_back:
if (error)
goto free_vma;
}
+ if (vm_flags & VM_SHARED) {
+ error = mapping_map_writable(file->f_mapping);
+ if (error)
+ goto allow_write_and_free_vma;
+ }
+
+ /* ->mmap() can change vma->vm_file, but must guarantee that
+ * vma_link() below can deny write-access if VM_DENYWRITE is set
+ * and map writably if VM_SHARED is set. This usually means the
+ * new file must not have been exposed to user-space, yet.
+ */
vma->vm_file = get_file(file);
error = file->f_op->mmap(file, vma);
if (error)
@@ -1629,8 +1640,12 @@ munmap_back:
vma_link(mm, vma, prev, rb_link, rb_parent);
/* Once vma denies write, undo our temporary denial count */
- if (vm_flags & VM_DENYWRITE)
- allow_write_access(file);
+ if (file) {
+ if (vm_flags & VM_SHARED)
+ mapping_unmap_writable(file->f_mapping);
+ if (vm_flags & VM_DENYWRITE)
+ allow_write_access(file);
+ }
file = vma->vm_file;
out:
perf_event_mmap(vma);
@@ -1659,14 +1674,17 @@ out:
return addr;
unmap_and_free_vma:
- if (vm_flags & VM_DENYWRITE)
- allow_write_access(file);
vma->vm_file = NULL;
fput(file);
/* Undo any partial mapping done by a device driver. */
unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
charged = 0;
+ if (vm_flags & VM_SHARED)
+ mapping_unmap_writable(file->f_mapping);
+allow_write_and_free_vma:
+ if (vm_flags & VM_DENYWRITE)
+ allow_write_access(file);
free_vma:
free_vma(mm, vma);
unacct_error:
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9252089..bc7f7eb 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -39,6 +39,7 @@ static struct backing_dev_info swap_backing_dev_info = {
struct address_space swapper_spaces[MAX_SWAPFILES] = {
[0 ... MAX_SWAPFILES - 1] = {
.page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
+ .i_mmap_writable = ATOMIC_INIT(0),
.a_ops = &swap_aops,
.backing_dev_info = &swap_backing_dev_info,
}
More information about the Devel
mailing list