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, 84 insertions, 0 deletions

diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
new file mode 100644
index 000000000..e278e060e
--- /dev/null
+++ b/arch/arm64/lib/delay.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Delay loops based on the OpenRISC implementation.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/timex.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#define USECS_TO_CYCLES(time_usecs)			\
+	xloops_to_cycles((time_usecs) * 0x10C7UL)
+
+static inline unsigned long xloops_to_cycles(unsigned long xloops)
+{
+	return (xloops * loops_per_jiffy * HZ) >> 32;
+}
+
+/*
+ * Force the use of CNTVCT_EL0 in order to have the same base as WFxT.
+ * This avoids some annoying issues when CNTVOFF_EL2 is not reset 0 on a
+ * KVM host running at EL1 until we do a vcpu_put() on the vcpu. When
+ * running at EL2, the effective offset is always 0.
+ *
+ * Note that userspace cannot change the offset behind our back either,
+ * as the vcpu mutex is held as long as KVM_RUN is in progress.
+ */
+static cycles_t notrace __delay_cycles(void)
+{
+	guard(preempt_notrace)();
+	return __arch_counter_get_cntvct_stable();
+}
+
+void __delay(unsigned long cycles)
+{
+	cycles_t start = __delay_cycles();
+
+	if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) {
+		u64 end = start + cycles;
+
+		/*
+		 * Start with WFIT. If an interrupt makes us resume
+		 * early, use a WFET loop to complete the delay.
+		 */
+		wfit(end);
+		while ((__delay_cycles() - start) < cycles)
+			wfet(end);
+	} else 	if (arch_timer_evtstrm_available()) {
+		const cycles_t timer_evt_period =
+			USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
+
+		while ((__delay_cycles() - start + timer_evt_period) < cycles)
+			wfe();
+	}
+
+	while ((__delay_cycles() - start) < cycles)
+		cpu_relax();
+}
+EXPORT_SYMBOL(__delay);
+
+inline void __const_udelay(unsigned long xloops)
+{
+	__delay(xloops_to_cycles(xloops));
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);