mm: make vm_mmap killable
All the callers of vm_mmap seem to check for the failure already and
bail out in one way or another on the error which means that we can
change it to use killable version of vm_mmap_pgoff and return -EINTR if
the current task gets killed while waiting for mmap_sem. This also
means that vm_mmap_pgoff can be killable by default and drop the
additional parameter.
This will help in the OOM conditions when the oom victim might be stuck
waiting for the mmap_sem for write which in turn can block oom_reaper
which relies on the mmap_sem for read to make a forward progress and
reclaim the address space of the victim.
Please note that load_elf_binary is ignoring vm_mmap error for
current->personality & MMAP_PAGE_ZERO case but that shouldn't be a
problem because the address is not used anywhere and we never return to
the userspace if we got killed.
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b530c99..d5eb8dd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2013,7 +2013,7 @@
/* These take the mm semaphore themselves */
extern unsigned long vm_brk(unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
-extern unsigned long vm_mmap(struct file *, unsigned long,
+extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
diff --git a/mm/internal.h b/mm/internal.h
index bff7fd7..a37e5b6 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -444,8 +444,7 @@
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
- unsigned long, unsigned long,
- bool);
+ unsigned long, unsigned long);
extern void set_pageblock_order(void);
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
diff --git a/mm/mmap.c b/mm/mmap.c
index 11e1f2c..4200886 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1333,7 +1333,7 @@
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff, true);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
out_fput:
if (file)
fput(file);
diff --git a/mm/nommu.c b/mm/nommu.c
index b7451274..c8bd59a 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1446,7 +1446,7 @@
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff, true);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
if (file)
fput(file);
diff --git a/mm/util.c b/mm/util.c
index 03b2377..917e0e3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -289,7 +289,7 @@
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
- unsigned long flag, unsigned long pgoff, bool killable)
+ unsigned long flag, unsigned long pgoff)
{
unsigned long ret;
struct mm_struct *mm = current->mm;
@@ -297,12 +297,8 @@
ret = security_mmap_file(file, prot, flag);
if (!ret) {
- if (killable) {
- if (down_write_killable(&mm->mmap_sem))
- return -EINTR;
- } else {
- down_write(&mm->mmap_sem);
- }
+ if (down_write_killable(&mm->mmap_sem))
+ return -EINTR;
ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
&populate);
up_write(&mm->mmap_sem);
@@ -312,7 +308,6 @@
return ret;
}
-/* XXX are all callers checking an error */
unsigned long vm_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long offset)
@@ -322,7 +317,7 @@
if (unlikely(offset_in_page(offset)))
return -EINVAL;
- return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT, false);
+ return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);