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, 75 insertions, 0 deletions

diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
new file mode 100644
index 000000000..f22ccfc0d
--- /dev/null
+++ b/include/asm-generic/atomic64.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic implementation of 64-bit atomics using spinlocks,
+ * useful on processors that don't have 64-bit atomic instructions.
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ */
+#ifndef _ASM_GENERIC_ATOMIC64_H
+#define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
+
+typedef struct {
+	s64 __aligned(sizeof(s64)) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i)	{ (i) }
+
+extern s64 generic_atomic64_read(const atomic64_t *v);
+extern void generic_atomic64_set(atomic64_t *v, s64 i);
+
+#define ATOMIC64_OP(op)							\
+extern void generic_atomic64_##op(s64 a, atomic64_t *v);
+
+#define ATOMIC64_OP_RETURN(op)						\
+extern s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v);
+
+#define ATOMIC64_FETCH_OP(op)						\
+extern s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(sub)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op)
+
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
+extern s64 generic_atomic64_dec_if_positive(atomic64_t *v);
+extern s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n);
+extern s64 generic_atomic64_xchg(atomic64_t *v, s64 new);
+extern s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u);
+
+#define arch_atomic64_read		generic_atomic64_read
+#define arch_atomic64_set		generic_atomic64_set
+#define arch_atomic64_set_release	generic_atomic64_set
+
+#define arch_atomic64_add		generic_atomic64_add
+#define arch_atomic64_add_return	generic_atomic64_add_return
+#define arch_atomic64_fetch_add		generic_atomic64_fetch_add
+#define arch_atomic64_sub		generic_atomic64_sub
+#define arch_atomic64_sub_return	generic_atomic64_sub_return
+#define arch_atomic64_fetch_sub		generic_atomic64_fetch_sub
+
+#define arch_atomic64_and		generic_atomic64_and
+#define arch_atomic64_fetch_and		generic_atomic64_fetch_and
+#define arch_atomic64_or		generic_atomic64_or
+#define arch_atomic64_fetch_or		generic_atomic64_fetch_or
+#define arch_atomic64_xor		generic_atomic64_xor
+#define arch_atomic64_fetch_xor		generic_atomic64_fetch_xor
+
+#define arch_atomic64_dec_if_positive	generic_atomic64_dec_if_positive
+#define arch_atomic64_cmpxchg		generic_atomic64_cmpxchg
+#define arch_atomic64_xchg		generic_atomic64_xchg
+#define arch_atomic64_fetch_add_unless	generic_atomic64_fetch_add_unless
+
+#endif  /*  _ASM_GENERIC_ATOMIC64_H  */