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, 54 insertions, 0 deletions

diff --git a/lib/bucket_locks.c b/lib/bucket_locks.c
new file mode 100644
index 000000000..d29516ca0
--- /dev/null
+++ b/lib/bucket_locks.c
@@ -0,0 +1,54 @@
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/* Allocate an array of spinlocks to be accessed by a hash. Two arguments
+ * indicate the number of elements to allocate in the array. max_size
+ * gives the maximum number of elements to allocate. cpu_mult gives
+ * the number of locks per CPU to allocate. The size is rounded up
+ * to a power of 2 to be suitable as a hash table.
+ */
+
+int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask,
+			     size_t max_size, unsigned int cpu_mult, gfp_t gfp,
+			     const char *name, struct lock_class_key *key)
+{
+	spinlock_t *tlocks = NULL;
+	unsigned int i, size;
+#if defined(CONFIG_PROVE_LOCKING)
+	unsigned int nr_pcpus = 2;
+#else
+	unsigned int nr_pcpus = num_possible_cpus();
+#endif
+
+	if (cpu_mult) {
+		nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
+		size = min_t(unsigned int, nr_pcpus * cpu_mult, max_size);
+	} else {
+		size = max_size;
+	}
+
+	if (sizeof(spinlock_t) != 0) {
+		tlocks = kvmalloc_objs(spinlock_t, size, gfp);
+		if (!tlocks)
+			return -ENOMEM;
+		for (i = 0; i < size; i++) {
+			spin_lock_init(&tlocks[i]);
+			lockdep_init_map(&tlocks[i].dep_map, name, key, 0);
+		}
+	}
+
+	*locks = tlocks;
+	*locks_mask = size - 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(__alloc_bucket_spinlocks);
+
+void free_bucket_spinlocks(spinlock_t *locks)
+{
+	kvfree(locks);
+}
+EXPORT_SYMBOL(free_bucket_spinlocks);