dmaengine: fix use-after-free in dma_chan_put() and dma_release_channel()grafted

When dma_device_put() drops the last reference on chan->device->ref,
dma_device_release() runs and may free the dma_device along with its
channels.

dma_chan_put() then still reads chan->device->owner via
dma_chan_to_owner() for the trailing module_put(). KASAN catches it:

	slab-use-after-free in dma_chan_put+0x3e6/0x4c0
	Read of size 8 by task insmod/6319
	Freed by task 6319:
	  kfree+0x225/0x470
	  dma_chan_put+0x395/0x4c0
	  dmaengine_put+0xf8/0x160

Cache the module owner in dma_chan_put() before the put so the trailing
module_put() does not need chan->device.

Fixes: 8ad342a86359 ("dmaengine: Add reference counting to dma_device struct")
Suggested-by: Sashiko <sashiko-bot@kernel.org>
Link: https://sashiko.dev/#/patchset/20260518-dmaengine-kref-fix-v1-1-4d6125048fb7@amd.com
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Shivank Garg <shivankg@amd.com>
Link: https://patch.msgid.link/20260822-dmaengine-kref-fix-v5-3-d4a4ee47d927@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

1 files changed, 39 insertions, 0 deletions

diff --git a/lib/memweight.c b/lib/memweight.c
new file mode 100644
index 000000000..94dd72cca
--- /dev/null
+++ b/lib/memweight.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+
+/**
+ * memweight - count the total number of bits set in memory area
+ * @ptr: pointer to the start of the area
+ * @bytes: the size of the area
+ */
+size_t memweight(const void *ptr, size_t bytes)
+{
+	size_t ret = 0;
+	size_t longs;
+	const unsigned char *bitmap = ptr;
+
+	for (; bytes > 0 && ((unsigned long)bitmap) % sizeof(long);
+			bytes--, bitmap++)
+		ret += hweight8(*bitmap);
+
+	longs = bytes / sizeof(long);
+	if (longs) {
+		BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
+		ret += bitmap_weight((unsigned long *)bitmap,
+				longs * BITS_PER_LONG);
+		bytes -= longs * sizeof(long);
+		bitmap += longs * sizeof(long);
+	}
+	/*
+	 * The reason that this last loop is distinct from the preceding
+	 * bitmap_weight() call is to compute 1-bits in the last region smaller
+	 * than sizeof(long) properly on big-endian systems.
+	 */
+	for (; bytes > 0; bytes--, bitmap++)
+		ret += hweight8(*bitmap);
+
+	return ret;
+}
+EXPORT_SYMBOL(memweight);