[PATCH v2] drm/syncobj: Limit the number of handles and use kvmalloc for user-sized arrays

[PATCH v2] drm/syncobj: Limit the number of handles and use kvmalloc for user-sized arrays

[Yu, Fei]

From: Fei Yu <fei.yu@intel.com>

The syncobj ioctls allocate several temporary arrays whose size is taken
directly from the u32 count_handles provided by userspace:

 - handles and syncobjs in drm_syncobj_array_find()
 - points and entries in drm_syncobj_array_wait_timeout()
 - points and chains in drm_syncobj_timeline_signal_ioctl()

These are kmalloc() allocations, so a count above KMALLOC_MAX_SIZE /
element size trips the WARN_ON_ONCE_GFP() in ___kmalloc_large_node():

  WARNING: mm/slub.c:5459 at ___kmalloc_large_node+0x10c/0x170 mm/slub.c:5459
  Call Trace:
   __kmalloc_large_node_noprof+0x18/0x90 mm/slub.c:5502
   __do_kmalloc_node mm/slub.c:5519 [inline]
   __kmalloc_noprof+0x3f6/0x710 mm/slub.c:5556
   _kmalloc_noprof include/linux/slab.h:995 [inline]
   _kmalloc_array_noprof include/linux/slab.h:1211 [inline]
   drm_syncobj_array_find+0x3a/0x440 drivers/gpu/drm/drm_syncobj.c:1241
   drm_syncobj_timeline_wait_ioctl+0x18a/0x640 drivers/gpu/drm/drm_syncobj.c:1356
   drm_ioctl_kernel+0x2df/0x3b0 drivers/gpu/drm/drm_ioctl.c:817
   drm_ioctl+0x70e/0xba0 drivers/gpu/drm/drm_ioctl.c:914

The wait entries are 64 bytes each on 64-bit, so with a 4 MiB
KMALLOC_MAX_SIZE a wait on more than about 64K handles already fails
today, with a warning.

Fix this in two parts:

 - Reject more than DRM_SYNCOBJ_MAX_HANDLES handles with -EINVAL in
   drm_syncobj_array_find(), which every ioctl taking a handle array goes
   through. The limit is derived from the largest per-handle allocation
   (the wait entries) and the INT_MAX size limit of kvmalloc(), so none
   of the allocations above can exceed it. That is about 33M handles on
   64-bit.

 - Switch the six allocations to kvmalloc(), so that large but valid
   handle counts no longer depend on physically contiguous memory.

Using kvmalloc() alone is not enough: the reproducer asks for more than
INT_MAX bytes, which hits the WARN_ON_ONCE() in __kvmalloc_node_noprof()
instead.

Fixes: 3e6fb72d6cef ("drm/syncobj: Add a syncobj_array_find helper")
Reported-by: syzbot+95416f957d84e858b377@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=95416f957d84e858b377
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Fei Yu <fei.yu@intel.com>
---
v2:
 - Drop __GFP_NOWARN (Christian).
 - Add DRM_SYNCOBJ_MAX_HANDLES, return -EINVAL above it, and switch all six
   arrays to kvmalloc() (Christian).
 - v1: https://lore.kernel.org/all/20261103085002.3100723-1-fei.yu@intel.com/

About the limit: INT_MAX / sizeof(struct syncobj_wait_entry) is about 33M
handles on 64-bit. It is the largest count for which every allocation stays
below the kvmalloc() INT_MAX size limit, so it does not add a new policy
number. Today the real limit is much lower: a wait on more than ~64K
handles already fails with -ENOMEM (plus the warning), because the wait
entries are a kmalloc() allocation larger than 4 MiB. If you prefer a lower,
fixed limit (e.g. SZ_1M) or GFP_KERNEL_ACCOUNT for these arrays, I can
change it.

Testing on v7.4-rc1 (x86_64, KASAN, virtio-gpu in QEMU):
 - syzbot C reproducer: base warns in ___kmalloc_large_node() (size
   0x100000920), patched is clean, ioctl returns -EINVAL.
 - wait / timeline_wait / timeline_signal / reset / signal on 200000
   signaled syncobjs: base fails wait and timeline_wait with -ENOMEM and
   the same warning; patched all succeed.
 - count == DRM_SYNCOBJ_MAX_HANDLES gets past the check (-EFAULT from the
   short user buffer), count == DRM_SYNCOBJ_MAX_HANDLES + 1 returns -EINVAL
   for wait, reset and timeline_signal.
 - kmemleak clean, checkpatch --strict clean, W=1 clean,
   DRM KUnit 667/667 passed.
 - IGT syncobj_basic, syncobj_wait, syncobj_timeline on virtio-gpu:
   202/202 subtests pass, same as base.

 drivers/gpu/drm/drm_syncobj.c | 40 ++++++++++++++++++++++-------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index f1d4da1685457..c01cf164a4f9e 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -220,6 +220,13 @@ struct syncobj_wait_entry {
 	u64    point;
 };
 
+/*
+ * Upper limit for the number of handles passed to a single ioctl. The
+ * largest per-handle allocation is the wait entry array, keep it below the
+ * INT_MAX size limit of kvmalloc().
+ */
+#define DRM_SYNCOBJ_MAX_HANDLES	(INT_MAX / sizeof(struct syncobj_wait_entry))
+
 static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj,
 				      struct syncobj_wait_entry *wait);
 
@@ -1051,7 +1058,7 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 		lockdep_assert_none_held_once();
 	}
 
-	points = kmalloc_array(count, sizeof(*points), GFP_KERNEL);
+	points = kvmalloc_array(count, sizeof(*points), GFP_KERNEL);
 	if (points == NULL)
 		return -ENOMEM;
 
@@ -1064,7 +1071,7 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 		goto err_free_points;
 	}
 
-	entries = kzalloc_objs(*entries, count);
+	entries = kvzalloc_objs(*entries, count);
 	if (!entries) {
 		timeout = -ENOMEM;
 		goto err_free_points;
@@ -1185,10 +1192,10 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs,
 						  &entries[i].fence_cb);
 		dma_fence_put(entries[i].fence);
 	}
-	kfree(entries);
+	kvfree(entries);
 
 err_free_points:
-	kfree(points);
+	kvfree(points);
 
 	return timeout;
 }
@@ -1238,7 +1245,10 @@ static int drm_syncobj_array_find(struct drm_file *file_private,
 	struct drm_syncobj **syncobjs;
 	int ret;
 
-	handles = kmalloc_array(count_handles, sizeof(*handles), GFP_KERNEL);
+	if (count_handles > DRM_SYNCOBJ_MAX_HANDLES)
+		return -EINVAL;
+
+	handles = kvmalloc_array(count_handles, sizeof(*handles), GFP_KERNEL);
 	if (handles == NULL)
 		return -ENOMEM;
 
@@ -1248,7 +1258,7 @@ static int drm_syncobj_array_find(struct drm_file *file_private,
 		goto err_free_handles;
 	}
 
-	syncobjs = kmalloc_objs(*syncobjs, count_handles);
+	syncobjs = kvmalloc_objs(*syncobjs, count_handles);
 	if (syncobjs == NULL) {
 		ret = -ENOMEM;
 		goto err_free_handles;
@@ -1262,16 +1272,16 @@ static int drm_syncobj_array_find(struct drm_file *file_private,
 		}
 	}
 
-	kfree(handles);
+	kvfree(handles);
 	*syncobjs_out = syncobjs;
 	return 0;
 
 err_put_syncobjs:
 	while (i-- > 0)
 		drm_syncobj_put(syncobjs[i]);
-	kfree(syncobjs);
+	kvfree(syncobjs);
 err_free_handles:
-	kfree(handles);
+	kvfree(handles);
 
 	return ret;
 }
@@ -1283,7 +1293,7 @@ static void drm_syncobj_array_free(struct drm_syncobj **syncobjs,
 
 	for (i = 0; i < count; i++)
 		drm_syncobj_put(syncobjs[i]);
-	kfree(syncobjs);
+	kvfree(syncobjs);
 }
 
 int
@@ -1572,8 +1582,8 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 	if (ret < 0)
 		return ret;
 
-	points = kmalloc_array(args->count_handles, sizeof(*points),
-			       GFP_KERNEL);
+	points = kvmalloc_array(args->count_handles, sizeof(*points),
+				GFP_KERNEL);
 	if (!points) {
 		ret = -ENOMEM;
 		goto out;
@@ -1586,7 +1596,7 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 		goto err_points;
 	}
 
-	chains = kmalloc_objs(*chains, args->count_handles);
+	chains = kvmalloc_objs(*chains, args->count_handles);
 	if (!chains) {
 		ret = -ENOMEM;
 		goto err_points;
@@ -1609,9 +1619,9 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data,
 		dma_fence_put(fence);
 	}
 err_chains:
-	kfree(chains);
+	kvfree(chains);
 err_points:
-	kfree(points);
+	kvfree(points);
 out:
 	drm_syncobj_array_free(syncobjs, args->count_handles);
 

base-commit: 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4
-- 
2.43.0