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, 137 insertions, 0 deletions

diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h
new file mode 100644
index 000000000..5b8211ca8
--- /dev/null
+++ b/include/trace/events/percpu.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM percpu
+
+#if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PERCPU_H
+
+#include <linux/tracepoint.h>
+#include <trace/events/mmflags.h>
+
+TRACE_EVENT(percpu_alloc_percpu,
+
+	TP_PROTO(unsigned long call_site,
+		 bool reserved, bool is_atomic, size_t size,
+		 size_t align, void *base_addr, int off,
+		 void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags),
+
+	TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off,
+		ptr, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,		call_site	)
+		__field(	bool,			reserved	)
+		__field(	bool,			is_atomic	)
+		__field(	size_t,			size		)
+		__field(	size_t,			align		)
+		__field(	void *,			base_addr	)
+		__field(	int,			off		)
+		__field(	void __percpu *,	ptr		)
+		__field(	size_t,			bytes_alloc	)
+		__field(	unsigned long,		gfp_flags	)
+	),
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->reserved	= reserved;
+		__entry->is_atomic	= is_atomic;
+		__entry->size		= size;
+		__entry->align		= align;
+		__entry->base_addr	= base_addr;
+		__entry->off		= off;
+		__entry->ptr		= ptr;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
+	),
+
+	TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s",
+		  (void *)__entry->call_site,
+		  __entry->reserved, __entry->is_atomic,
+		  __entry->size, __entry->align,
+		  __entry->base_addr, __entry->off, __entry->ptr,
+		  __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(percpu_free_percpu,
+
+	TP_PROTO(void *base_addr, int off, void __percpu *ptr),
+
+	TP_ARGS(base_addr, off, ptr),
+
+	TP_STRUCT__entry(
+		__field(	void *,			base_addr	)
+		__field(	int,			off		)
+		__field(	void __percpu *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+		__entry->off		= off;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("base_addr=%p off=%d ptr=%p",
+		__entry->base_addr, __entry->off, __entry->ptr)
+);
+
+TRACE_EVENT(percpu_alloc_percpu_fail,
+
+	TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align),
+
+	TP_ARGS(reserved, is_atomic, size, align),
+
+	TP_STRUCT__entry(
+		__field(	bool,	reserved	)
+		__field(	bool,	is_atomic	)
+		__field(	size_t,	size		)
+		__field(	size_t, align		)
+	),
+
+	TP_fast_assign(
+		__entry->reserved	= reserved;
+		__entry->is_atomic	= is_atomic;
+		__entry->size		= size;
+		__entry->align		= align;
+	),
+
+	TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu",
+		  __entry->reserved, __entry->is_atomic,
+		  __entry->size, __entry->align)
+);
+
+TRACE_EVENT(percpu_create_chunk,
+
+	TP_PROTO(void *base_addr),
+
+	TP_ARGS(base_addr),
+
+	TP_STRUCT__entry(
+		__field(	void *, base_addr	)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+	),
+
+	TP_printk("base_addr=%p", __entry->base_addr)
+);
+
+TRACE_EVENT(percpu_destroy_chunk,
+
+	TP_PROTO(void *base_addr),
+
+	TP_ARGS(base_addr),
+
+	TP_STRUCT__entry(
+		__field(	void *,	base_addr	)
+	),
+
+	TP_fast_assign(
+		__entry->base_addr	= base_addr;
+	),
+
+	TP_printk("base_addr=%p", __entry->base_addr)
+);
+
+#endif /* _TRACE_PERCPU_H */
+
+#include <trace/define_trace.h>