mm: make mmap_sem for write waits killable for mm syscalls

This is a follow up work for oom_reaper [1].  As the async OOM killing
depends on oom_sem for read we would really appreciate if a holder for
write didn't stood in the way.  This patchset is changing many of
down_write calls to be killable to help those cases when the writer is
blocked and waiting for readers to release the lock and so help
__oom_reap_task to process the oom victim.

Most of the patches are really trivial because the lock is help from a
shallow syscall paths where we can return EINTR trivially and allow the
current task to die (note that EINTR will never get to the userspace as
the task has fatal signal pending).  Others seem to be easy as well as
the callers are already handling fatal errors and bail and return to
userspace which should be sufficient to handle the failure gracefully.
I am not familiar with all those code paths so a deeper review is really
appreciated.

As this work is touching more areas which are not directly connected I
have tried to keep the CC list as small as possible and people who I
believed would be familiar are CCed only to the specific patches (all
should have received the cover though).

This patchset is based on linux-next and it depends on
down_write_killable for rw_semaphores which got merged into tip
locking/rwsem branch and it is merged into this next tree.  I guess it
would be easiest to route these patches via mmotm because of the
dependency on the tip tree but if respective maintainers prefer other
way I have no objections.

I haven't covered all the mmap_write(mm->mmap_sem) instances here

  $ git grep "down_write(.*\<mmap_sem\>)" next/master | wc -l
  98
  $ git grep "down_write(.*\<mmap_sem\>)" | wc -l
  62

I have tried to cover those which should be relatively easy to review in
this series because this alone should be a nice improvement.  Other
places can be changed on top.

[0] http://lkml.kernel.org/r/[email protected]
[1] http://lkml.kernel.org/r/[email protected]
[2] http://lkml.kernel.org/r/[email protected]

This patch (of 18):

This is the first step in making mmap_sem write waiters killable.  It
focuses on the trivial ones which are taking the lock early after
entering the syscall and they are not changing state before.

Therefore it is very easy to change them to use down_write_killable and
immediately return with -EINTR.  This will allow the waiter to pass away
without blocking the mmap_sem which might be required to make a forward
progress.  E.g.  the oom reaper will need the lock for reading to
dismantle the OOM victim address space.

The only tricky function in this patch is vm_mmap_pgoff which has many
call sites via vm_mmap.  To reduce the risk keep vm_mmap with the
original non-killable semantic for now.

vm_munmap callers do not bother checking the return value so open code
it into the munmap syscall path for now for simplicity.

Signed-off-by: Michal Hocko <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Konstantin Khlebnikov <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Johannes Weiner <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/internal.h

@@ -442,9 +442,10 @@ extern u64 hwpoison_filter_flags_value;
 extern u64 hwpoison_filter_memcg;
 extern u32 hwpoison_filter_enable;
 
-extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
+extern unsigned long  __must_check vm_mmap_pgoff(struct file *, unsigned long,
         unsigned long, unsigned long,
-        unsigned long, unsigned long);
+        unsigned long, unsigned long,
+        bool);
 
 extern void set_pageblock_order(void);
 unsigned long reclaim_clean_pages_from_list(struct zone *zone,

mm/madvise.c

@@ -707,10 +707,12 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 		return error;
 
 	write = madvise_need_mmap_write(behavior);
-	if (write)
-		down_write(&current->mm->mmap_sem);
-	else
+	if (write) {
+		if (down_write_killable(&current->mm->mmap_sem))
+			return -EINTR;
+	} else {
 		down_read(&current->mm->mmap_sem);
+	}
 
 	/*
 	 * If the interval [start,end) covers some unmapped address

mm/mlock.c

@@ -617,7 +617,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
 	return error;
 }
 
-static int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
+static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
 {
 	unsigned long locked;
 	unsigned long lock_limit;
@@ -635,7 +635,8 @@ static int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
 	lock_limit >>= PAGE_SHIFT;
 	locked = len >> PAGE_SHIFT;
 
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 
 	locked += current->mm->locked_vm;
 
@@ -678,7 +679,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 	ret = apply_vma_lock_flags(start, len, 0);
 	up_write(&current->mm->mmap_sem);
 
@@ -748,9 +750,10 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
 
-	ret = -ENOMEM;
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 
+	ret = -ENOMEM;
 	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
 	    capable(CAP_IPC_LOCK))
 		ret = apply_mlockall_flags(flags);
@@ -765,7 +768,8 @@ SYSCALL_DEFINE0(munlockall)
 {
 	int ret;
 
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 	ret = apply_mlockall_flags(0);
 	up_write(&current->mm->mmap_sem);
 	return ret;

mm/mmap.c

@@ -178,7 +178,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	unsigned long min_brk;
 	bool populate;
 
-	down_write(&mm->mmap_sem);
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
 
 #ifdef CONFIG_COMPAT_BRK
 	/*
@@ -1332,7 +1333,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
-	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff, true);
 out_fput:
 	if (file)
 		fput(file);
@@ -2493,6 +2494,10 @@ int vm_munmap(unsigned long start, size_t len)
 	int ret;
 	struct mm_struct *mm = current->mm;
 
+	/*
+	 * XXX convert to down_write_killable as soon as all users are able
+	 * to handle the error.
+	 */
 	down_write(&mm->mmap_sem);
 	ret = do_munmap(mm, start, len);
 	up_write(&mm->mmap_sem);
@@ -2502,8 +2507,15 @@ EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
+	int ret;
+	struct mm_struct *mm = current->mm;
+
 	profile_munmap(addr);
-	return vm_munmap(addr, len);
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+	ret = do_munmap(mm, addr, len);
+	up_write(&mm->mmap_sem);
+	return ret;
 }
 
 
@@ -2535,7 +2547,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
 		return ret;
 
-	down_write(&mm->mmap_sem);
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
 	vma = find_vma(mm, start);
 
 	if (!vma || !(vma->vm_flags & VM_SHARED))
@@ -2700,6 +2714,11 @@ unsigned long vm_brk(unsigned long addr, unsigned long len)
 	unsigned long ret;
 	bool populate;
 
+	/*
+	 * XXX not all users are chcecking the return value, convert
+	 * to down_write_killable after they are able to cope with
+	 * error
+	 */
 	down_write(&mm->mmap_sem);
 	ret = do_brk(addr, len);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);

mm/mprotect.c

@@ -379,7 +379,8 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 
 	reqprot = prot;
 
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 
 	vma = find_vma(current->mm, start);
 	error = -ENOMEM;

mm/mremap.c

@@ -503,7 +503,8 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	if (!new_len)
 		return ret;
 
-	down_write(&current->mm->mmap_sem);
+	if (down_write_killable(&current->mm->mmap_sem))
+		return -EINTR;
 
 	if (flags & MREMAP_FIXED) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,

mm/nommu.c

@@ -1446,7 +1446,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
-	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+	retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff, true);
 
 	if (file)
 		fput(file);

mm/util.c

@@ -289,15 +289,20 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast);
 
 unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot,
-	unsigned long flag, unsigned long pgoff)
+	unsigned long flag, unsigned long pgoff, bool killable)
 {
 	unsigned long ret;
 	struct mm_struct *mm = current->mm;
 	unsigned long populate;
 
 	ret = security_mmap_file(file, prot, flag);
 	if (!ret) {
-		down_write(&mm->mmap_sem);
+		if (killable) {
+			if (down_write_killable(&mm->mmap_sem))
+				return -EINTR;
+		} else {
+			down_write(&mm->mmap_sem);
+		}
 		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
 				    &populate);
 		up_write(&mm->mmap_sem);
@@ -307,6 +312,7 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	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)
@@ -316,7 +322,7 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 	if (unlikely(offset_in_page(offset)))
 		return -EINVAL;
 
-	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT, false);
 }
 EXPORT_SYMBOL(vm_mmap);