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, 70 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
new file mode 100644
index 000000000..e076e079f
--- /dev/null
+++ b/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/*
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
+ */
+
+static __always_inline void
+arch_set_bit(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	raw_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
+}
+
+static __always_inline void
+arch_clear_bit(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	raw_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
+}
+
+static __always_inline void
+arch_change_bit(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	raw_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
+}
+
+static __always_inline int
+arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = raw_atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
+static __always_inline int
+arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = raw_atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
+static __always_inline int
+arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = raw_atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
+#include <asm-generic/bitops/instrumented-atomic.h>
+
+#endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */