Received-SPF: pass (google.com: domain of linux-kernel+bounces-123013-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
To: linux-mm@kvack.org,
	Andrew Morton <akpm@linux-foundation.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Baoquan He <bhe@redhat.com>,
	Lorenzo Stoakes <lstoakes@gmail.com>,
	Christoph Hellwig <hch@infradead.org>,
	Matthew Wilcox <willy@infradead.org>,
	Dave Chinner <david@fromorbit.com>,
	Uladzislau Rezki <urezki@gmail.com>,
	Oleksiy Avramchenko <oleksiy.avramchenko@sony.com>,
	Jens Axboe <axboe@kernel.dk>,
	Omar Sandoval <osandov@fb.com>
Subject: [PATCH 1/1] mm: vmalloc: Fix lockdep warning
Date: Thu, 28 Mar 2024 15:03:30 +0100
Message-Id: <20240328140330.4747-1-urezki@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

A lockdep reports a possible deadlock in the find_vmap_area_exceed_addr_lock()
function:

============================================
WARNING: possible recursive locking detected
6.9.0-rc1-00060-ged3ccc57b108-dirty #6140 Not tainted
--------------------------------------------
drgn/455 is trying to acquire lock:
ffff0000c00131d0 (&vn->busy.lock/1){+.+.}-{2:2}, at: find_vmap_area_exceed_addr_lock+0x64/0x124

but task is already holding lock:
ffff0000c0011878 (&vn->busy.lock/1){+.+.}-{2:2}, at: find_vmap_area_exceed_addr_lock+0x64/0x124

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&vn->busy.lock/1);
  lock(&vn->busy.lock/1);

 *** DEADLOCK ***

indeed it can happen if the find_vmap_area_exceed_addr_lock()
gets called concurrently because it tries to acquire two nodes
locks. It was done to prevent removing a lowest VA found on a
previous step.

To address this a lowest VA is found first without holding a
node lock where it resides. As a last step we check if a VA
still there because it can go away, if removed, proceed with
next lowest.

Fixes: 53becf32aec1 ("mm: vmalloc: support multiple nodes in vread_iter")
Tested-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Omar Sandoval <osandov@fb.com>
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 mm/vmalloc.c | 74 +++++++++++++++++++++++++++++++---------------------
 1 file changed, 44 insertions(+), 30 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e94ce4562805..a5a5dfc3843e 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -989,6 +989,27 @@ unsigned long vmalloc_nr_pages(void)
 	return atomic_long_read(&nr_vmalloc_pages);
 }
 
+static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
+{
+	struct rb_node *n = root->rb_node;
+
+	addr = (unsigned long)kasan_reset_tag((void *)addr);
+
+	while (n) {
+		struct vmap_area *va;
+
+		va = rb_entry(n, struct vmap_area, rb_node);
+		if (addr < va->va_start)
+			n = n->rb_left;
+		else if (addr >= va->va_end)
+			n = n->rb_right;
+		else
+			return va;
+	}
+
+	return NULL;
+}
+
 /* Look up the first VA which satisfies addr < va_end, NULL if none. */
 static struct vmap_area *
 __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
@@ -1025,47 +1046,40 @@ __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
 static struct vmap_node *
 find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
 {
-	struct vmap_node *vn, *va_node = NULL;
-	struct vmap_area *va_lowest;
+	unsigned long va_start_lowest;
+	struct vmap_node *vn;
 	int i;
 
-	for (i = 0; i < nr_vmap_nodes; i++) {
+repeat:
+	for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) {
 		vn = &vmap_nodes[i];
 
 		spin_lock(&vn->busy.lock);
-		va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
-		if (va_lowest) {
-			if (!va_node || va_lowest->va_start < (*va)->va_start) {
-				if (va_node)
-					spin_unlock(&va_node->busy.lock);
-
-				*va = va_lowest;
-				va_node = vn;
-				continue;
-			}
-		}
+		*va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
+
+		if (*va)
+			if (!va_start_lowest || (*va)->va_start < va_start_lowest)
+				va_start_lowest = (*va)->va_start;
 		spin_unlock(&vn->busy.lock);
 	}
 
-	return va_node;
-}
-
-static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
-{
-	struct rb_node *n = root->rb_node;
+	/*
+	 * Check if found VA exists, it might it is gone away.
+	 * In this case we repeat the search because a VA has
+	 * been removed concurrently thus we need to proceed
+	 * with next one what is a rare case.
+	 */
+	if (va_start_lowest) {
+		vn = addr_to_node(va_start_lowest);
 
-	addr = (unsigned long)kasan_reset_tag((void *)addr);
+		spin_lock(&vn->busy.lock);
+		*va = __find_vmap_area(va_start_lowest, &vn->busy.root);
 
-	while (n) {
-		struct vmap_area *va;
+		if (*va)
+			return vn;
 
-		va = rb_entry(n, struct vmap_area, rb_node);
-		if (addr < va->va_start)
-			n = n->rb_left;
-		else if (addr >= va->va_end)
-			n = n->rb_right;
-		else
-			return va;
+		spin_unlock(&vn->busy.lock);
+		goto repeat;
 	}
 
 	return NULL;
-- 
2.39.2