Merge tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux

Pull MAP_DENYWRITE removal from David Hildenbrand:
 "Remove all in-tree usage of MAP_DENYWRITE from the kernel and remove
  VM_DENYWRITE.

  There are some (minor) user-visible changes:

   - We no longer deny write access to shared libaries loaded via legacy
     uselib(); this behavior matches modern user space e.g. dlopen().

   - We no longer deny write access to the elf interpreter after exec
     completed, treating it just like shared libraries (which it often
     is).

   - We always deny write access to the file linked via /proc/pid/exe:
     sys_prctl(PR_SET_MM_MAP/EXE_FILE) will fail if write access to the
     file cannot be denied, and write access to the file will remain
     denied until the link is effectivel gone (exec, termination,
     sys_prctl(PR_SET_MM_MAP/EXE_FILE)) -- just as if exec'ing the file.

  Cross-compiled for a bunch of architectures (alpha, microblaze, i386,
  s390x, ...) and verified via ltp that especially the relevant tests
  (i.e., creat07 and execve04) continue working as expected"

* tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux:
  fs: update documentation of get_write_access() and friends
  mm: ignore MAP_DENYWRITE in ksys_mmap_pgoff()
  mm: remove VM_DENYWRITE
  binfmt: remove in-tree usage of MAP_DENYWRITE
  kernel/fork: always deny write access to current MM exe_file
  kernel/fork: factor out replacing the current MM exe_file
  binfmt: don't use MAP_DENYWRITE when loading shared libraries via uselib()
This commit is contained in:
Linus Torvalds 2021-09-04 11:35:47 -07:00
commit 49624efa65
16 changed files with 119 additions and 103 deletions

View file

@ -3023,15 +3023,20 @@ static inline void file_end_write(struct file *file)
}
/*
* This is used for regular files where some users -- especially the
* currently executed binary in a process, previously handled via
* VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap
* read-write shared) accesses.
*
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
* This is used for regular files.
* We cannot support write (and maybe mmap read-write shared) accesses and
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
* can have the following values:
* 0: no writers, no VM_DENYWRITE mappings
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
* > 0: (i_writecount) users are writing to the file.
* deny_write_access() denies write access to a file.
* allow_write_access() re-enables write access to a file.
*
* The i_writecount field of an inode can have the following values:
* 0: no write access, no denied write access
* < 0: (-i_writecount) users that denied write access to the file.
* > 0: (i_writecount) users that have write access to the file.
*
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
* except for the cases where we don't hold i_writecount yet. Then we need to

View file

@ -281,7 +281,6 @@ extern unsigned int kobjsize(const void *objp);
#define VM_GROWSDOWN 0x00000100 /* general info on the segment */
#define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */
#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */
#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
#define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */
#define VM_LOCKED 0x00002000
@ -2573,7 +2572,8 @@ static inline int check_data_rlimit(unsigned long rlim,
extern int mm_take_all_locks(struct mm_struct *mm);
extern void mm_drop_all_locks(struct mm_struct *mm);
extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern struct file *get_mm_exe_file(struct mm_struct *mm);
extern struct file *get_task_exe_file(struct task_struct *task);

View file

@ -32,7 +32,8 @@
* The historical set of flags that all mmap implementations implicitly
* support when a ->mmap_validate() op is not provided in file_operations.
*
* MAP_EXECUTABLE is completely ignored throughout the kernel.
* MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the
* kernel.
*/
#define LEGACY_MAP_MASK (MAP_SHARED \
| MAP_PRIVATE \
@ -153,7 +154,6 @@ static inline unsigned long
calc_vm_flag_bits(unsigned long flags)
{
return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) |
_calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) |
_calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) |
_calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) |
arch_calc_vm_flag_bits(flags);