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, 150 insertions, 0 deletions

diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
new file mode 100644
index 000000000..523c79f22
--- /dev/null
+++ b/tools/testing/radix-tree/benchmark.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * benchmark.c:
+ * Author: Konstantin Khlebnikov <koct9i@gmail.com>
+ */
+#include <linux/radix-tree.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <time.h>
+#include "test.h"
+
+#define NSEC_PER_SEC	1000000000L
+
+static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
+{
+	volatile unsigned long sink = 0;
+	struct radix_tree_iter iter;
+	struct timespec start, finish;
+	long long nsec;
+	int l, loops = 1;
+	void **slot;
+
+#ifdef BENCHMARK
+again:
+#endif
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (l = 0; l < loops; l++) {
+		if (tagged) {
+			radix_tree_for_each_tagged(slot, root, &iter, 0, 0)
+				sink ^= (unsigned long)slot;
+		} else {
+			radix_tree_for_each_slot(slot, root, &iter, 0)
+				sink ^= (unsigned long)slot;
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+#ifdef BENCHMARK
+	if (loops == 1 && nsec * 5 < NSEC_PER_SEC) {
+		loops = NSEC_PER_SEC / nsec / 4 + 1;
+		goto again;
+	}
+#endif
+
+	nsec /= loops;
+	return nsec;
+}
+
+static void benchmark_insert(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_insert(root, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, insertion: %15lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		radix_tree_tag_set(root, index, 0);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, tagging: %17lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_delete(root, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, deletion: %16lld ns\n",
+		size, step, nsec);
+}
+
+static void benchmark_size(unsigned long size, unsigned long step)
+{
+	RADIX_TREE(tree, GFP_KERNEL);
+	long long normal, tagged;
+
+	benchmark_insert(&tree, size, step);
+	benchmark_tagging(&tree, size, step);
+
+	tagged = benchmark_iter(&tree, true);
+	normal = benchmark_iter(&tree, false);
+
+	printv(2, "Size: %8ld, step: %8ld, tagged iteration: %8lld ns\n",
+		size, step, tagged);
+	printv(2, "Size: %8ld, step: %8ld, normal iteration: %8lld ns\n",
+		size, step, normal);
+
+	benchmark_delete(&tree, size, step);
+
+	item_kill_tree(&tree);
+	rcu_barrier();
+}
+
+void benchmark(void)
+{
+	unsigned long size[] = {1 << 10, 1 << 20, 0};
+	unsigned long step[] = {1, 2, 7, 15, 63, 64, 65,
+				128, 256, 512, 12345, 0};
+	int c, s;
+
+	printv(1, "starting benchmarks\n");
+	printv(1, "RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT);
+
+	for (c = 0; size[c]; c++)
+		for (s = 0; step[s]; s++)
+			benchmark_size(size[c], step[s]);
+}