The mmap syscall suffers from the ABI anti-pattern of not validating
unknown flags. However, proposals like MAP_SYNC and MAP_DIRECT need a
mechanism to define new behavior that is known to fail on older kernels
without the feature. Use the fact that specifying MAP_SHARED and
MAP_PRIVATE at the same time is invalid as a cute hack to allow a new
set of validated flags to be introduced.
This also introduces the ->fmmap() file operation that is ->mmap() plus
flags. Each ->fmmap() implementation must fail requests when a locally
unsupported flag is specified.
Cc: Jan Kara <j...@suse.cz>
Cc: Arnd Bergmann <a...@arndb.de>
Cc: Andrew Morton <a...@linux-foundation.org>
Suggested-by: Christoph Hellwig <h...@lst.de>
Signed-off-by: Dan Williams <dan.j.willi...@intel.com>
---
include/linux/fs.h | 7 +++++++
include/linux/mm.h | 2 +-
include/linux/mman.h | 3 +++
include/uapi/asm-generic/mman-common.h | 1 +
mm/mmap.c | 20 +++++++++++++++++---
5 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1104e5df39ef..bbe755d0caee 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1674,6 +1674,7 @@ struct file_operations {
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
+ int (*fmmap) (struct file *, struct vm_area_struct *, unsigned long);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
@@ -1748,6 +1749,12 @@ static inline int call_mmap(struct file *file, struct
vm_area_struct *vma)
return file->f_op->mmap(file, vma);
}
+static inline int call_fmmap(struct file *file, struct vm_area_struct *vma,
+ unsigned long flags)
+{
+ return file->f_op->fmmap(file, vma, flags);
+}
+
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_pointer,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 46b9ac5e8569..49eef48da4b7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2090,7 +2090,7 @@ extern unsigned long get_unmapped_area(struct file *,
unsigned long, unsigned lo
extern unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
- struct list_head *uf);
+ struct list_head *uf, unsigned long flags);
extern unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot, unsigned long flags,
vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
diff --git a/include/linux/mman.h b/include/linux/mman.h
index c8367041fafd..73d4ac7e7136 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -7,6 +7,9 @@
#include <linux/atomic.h>
#include <uapi/linux/mman.h>
+/* the MAP_VALIDATE set of supported flags */
+#define MAP_SUPPORTED_MASK (0)
+
extern int sysctl_overcommit_memory;
extern int sysctl_overcommit_ratio;
extern unsigned long sysctl_overcommit_kbytes;
diff --git a/include/uapi/asm-generic/mman-common.h
b/include/uapi/asm-generic/mman-common.h
index 8c27db0c5c08..8bf8c7828275 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -24,6 +24,7 @@
#else
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
#endif
+#define MAP_VALIDATE (MAP_SHARED|MAP_PRIVATE) /* mechanism to define new
shared semantics */
/*
* Flags for mlock
diff --git a/mm/mmap.c b/mm/mmap.c
index f19efcf75418..d2919a9e25bf 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1388,6 +1388,12 @@ unsigned long do_mmap(struct file *file, unsigned long
addr,
struct inode *inode = file_inode(file);
switch (flags & MAP_TYPE) {
+ case MAP_VALIDATE:
+ if (flags & ~(MAP_SUPPORTED_MASK | MAP_VALIDATE))
+ return -EINVAL;
+ if (!file->f_op->fmmap)
+ return -EOPNOTSUPP;
+ /* fall through */
case MAP_SHARED:
if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
return -EACCES;
@@ -1464,7 +1470,12 @@ unsigned long do_mmap(struct file *file, unsigned long
addr,
vm_flags |= VM_NORESERVE;
}
- addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
+ if ((flags & MAP_VALIDATE) == MAP_VALIDATE)
+ flags &= MAP_SUPPORTED_MASK;
+ else
+ flags = 0;
+
+ addr = mmap_region(file, addr, len, vm_flags, pgoff, uf, flags);
if (!IS_ERR_VALUE(addr) &&
((vm_flags & VM_LOCKED) ||
(flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
@@ -1601,7 +1612,7 @@ static inline int accountable_mapping(struct file *file,
vm_flags_t vm_flags)
unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
- struct list_head *uf)
+ struct list_head *uf, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
@@ -1686,7 +1697,10 @@ unsigned long mmap_region(struct file *file, unsigned
long addr,
* new file must not have been exposed to user-space, yet.
*/
vma->vm_file = get_file(file);
- error = call_mmap(file, vma);
+ if (flags)
+ error = call_fmmap(file, vma, flags);
+ else
+ error = call_mmap(file, vma);
if (error)
goto unmap_and_free_vma;
