[PATCH v2 02/47] fork: take mmap_lock before copying mm_struct

["David Hildenbrand (Arm)" <david@kernel.org>]

dup_mm() copies the parent's mm_struct before dup_mmap() takes the
mmap_lock. A concurrent brk() can leave the child with a stale mm->brk
and newer heap mappings, causing later brk() requests to fail.

Other operations (e.g., PR_SET_MM) on the parent's mm_struct can similarly
cause inconsistencies.

As a simple and robust fix, grab the parent's mmap_lock earlier. This
way we don't need to update individual mm fields in dup_mmap() and
keep missing ones. Stop updating the 4 existing members (total_vm, data_vm,
exec_vm, stack_vm), as that is now no longer required.

Keep releasing the parent's mmap_lock in dup_mmap(), before
userfaultfd completion, to avoid moving the userfaultfd handling into the
caller. This should get cleaned up later.

Move uprobe_start_dup_mmap() to preserve the lock ordering.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Reported-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Harry Yoo (Meta) <harry@kernel.org>
Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
---
 kernel/fork.c | 20 ++++++++++++++------
 mm/mmap.c     |  8 +-------
 mm/nommu.c    |  2 +-
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 18b6dd851642..ee40142dab31 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1533,12 +1533,19 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	if (!mm)
 		goto fail_nomem;
 
+	uprobe_start_dup_mmap();
+	if (mmap_write_lock_killable(oldmm)) {
+		free_mm(mm);
+		goto fail_uprobe;
+	}
+
 	memcpy(mm, oldmm, sizeof(*mm));
 
-	if (!mm_init(mm, tsk))
-		goto fail_nomem;
+	if (!mm_init(mm, tsk)) {
+		mmap_write_unlock(oldmm);
+		goto fail_uprobe;
+	}
 
-	uprobe_start_dup_mmap();
 	err = dup_mmap(mm, oldmm);
 	if (err)
 		goto free_pt;
@@ -1557,9 +1564,10 @@ static struct mm_struct *dup_mm(struct task_struct *tsk,
 	mm->binfmt = NULL;
 	mm_init_owner(mm, NULL);
 	mmput(mm);
-	if (err)
-		uprobe_end_dup_mmap();
-
+	if (!err)
+		return NULL;
+fail_uprobe:
+	uprobe_end_dup_mmap();
 fail_nomem:
 	return NULL;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 148ba01c0373..7618e72766a5 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1713,8 +1713,7 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	LIST_HEAD(uf);
 	VMA_ITERATOR(vmi, mm, 0);
 
-	if (mmap_write_lock_killable(oldmm))
-		return -EINTR;
+	mmap_assert_write_locked(oldmm);
 	flush_cache_dup_mm(oldmm);
 	uprobe_dup_mmap(oldmm, mm);
 	/*
@@ -1725,11 +1724,6 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	/* No ordering required: file already has been exposed. */
 	dup_mm_exe_file(mm, oldmm);
 
-	mm->total_vm = oldmm->total_vm;
-	mm->data_vm = oldmm->data_vm;
-	mm->exec_vm = oldmm->exec_vm;
-	mm->stack_vm = oldmm->stack_vm;
-
 	/* Use __mt_dup() to efficiently build an identical maple tree. */
 	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
 	if (unlikely(retval))
diff --git a/mm/nommu.c b/mm/nommu.c
index 91ab65afda70..6c6f95329674 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1887,7 +1887,7 @@ subsys_initcall(init_admin_reserve);
 
 int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	mmap_write_lock(oldmm);
+	mmap_assert_write_locked(oldmm);
 	dup_mm_exe_file(mm, oldmm);
 	mmap_write_unlock(oldmm);
 	return 0;

-- 
2.43.0