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, 87 insertions, 0 deletions

diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h
new file mode 100644
index 000000000..03b0ec7af
--- /dev/null
+++ b/include/asm-generic/delay.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_DELAY_H
+#define __ASM_GENERIC_DELAY_H
+
+#include <linux/math.h>
+#include <vdso/time64.h>
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/*
+ * The microseconds/nanosecond delay multiplicators are used to convert a
+ * constant microseconds/nanoseconds value to a value which can be used by the
+ * architectures specific implementation to transform it into loops.
+ */
+#define UDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, USEC_PER_SEC))
+#define NDELAY_CONST_MULT	((unsigned long)DIV_ROUND_UP(1ULL << 32, NSEC_PER_SEC))
+
+/*
+ * The maximum constant udelay/ndelay value picked out of thin air to prevent
+ * too long constant udelays/ndelays.
+ */
+#define DELAY_CONST_MAX   20000
+
+/**
+ * udelay - Inserting a delay based on microseconds with busy waiting
+ * @usec:	requested delay in microseconds
+ *
+ * When delaying in an atomic context ndelay(), udelay() and mdelay() are the
+ * only valid variants of delaying/sleeping to go with.
+ *
+ * When inserting delays in non atomic context which are shorter than the time
+ * which is required to queue e.g. an hrtimer and to enter then the scheduler,
+ * it is also valuable to use udelay(). But it is not simple to specify a
+ * generic threshold for this which will fit for all systems. An approximation
+ * is a threshold for all delays up to 10 microseconds.
+ *
+ * When having a delay which is larger than the architecture specific
+ * %MAX_UDELAY_MS value, please make sure mdelay() is used. Otherwise a overflow
+ * risk is given.
+ *
+ * Please note that ndelay(), udelay() and mdelay() may return early for several
+ * reasons (https://lists.openwall.net/linux-kernel/2011/01/09/56):
+ *
+ * #. computed loops_per_jiffy too low (due to the time taken to execute the
+ *    timer interrupt.)
+ * #. cache behaviour affecting the time it takes to execute the loop function.
+ * #. CPU clock rate changes.
+ */
+static __always_inline void udelay(unsigned long usec)
+{
+	if (__builtin_constant_p(usec)) {
+		if (usec >= DELAY_CONST_MAX)
+			__bad_udelay();
+		else
+			__const_udelay(usec * UDELAY_CONST_MULT);
+	} else {
+		__udelay(usec);
+	}
+}
+
+/**
+ * ndelay - Inserting a delay based on nanoseconds with busy waiting
+ * @nsec:	requested delay in nanoseconds
+ *
+ * See udelay() for basic information about ndelay() and it's variants.
+ */
+static __always_inline void ndelay(unsigned long nsec)
+{
+	if (__builtin_constant_p(nsec)) {
+		if (nsec >= DELAY_CONST_MAX)
+			__bad_ndelay();
+		else
+			__const_udelay(nsec * NDELAY_CONST_MULT);
+	} else {
+		__ndelay(nsec);
+	}
+}
+#define ndelay(x) ndelay(x)
+
+#endif /* __ASM_GENERIC_DELAY_H */