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, 103 insertions, 0 deletions

diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 000000000..7e9304012
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,103 @@
+// 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/clocksource.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/*
+ * Default to the loop-based delay implementation.
+ */
+struct arm_delay_ops arm_delay_ops __ro_after_init = {
+	.delay		= __loop_delay,
+	.const_udelay	= __loop_const_udelay,
+	.udelay		= __loop_udelay,
+};
+
+static const struct delay_timer *delay_timer;
+static bool delay_calibrated;
+static u64 delay_res;
+
+bool delay_read_timer(unsigned long *timer_val)
+{
+	if (!delay_timer)
+		return false;
+	*timer_val = delay_timer->read_current_timer();
+	return true;
+}
+EXPORT_SYMBOL_GPL(delay_read_timer);
+
+static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+{
+	return (cyc * mult) >> shift;
+}
+
+static void __timer_delay(unsigned long cycles)
+{
+	cycles_t start = get_cycles();
+
+	while ((get_cycles() - start) < cycles)
+		cpu_relax();
+}
+
+static void __timer_const_udelay(unsigned long xloops)
+{
+	unsigned long long loops = xloops;
+	loops *= arm_delay_ops.ticks_per_jiffy;
+	__timer_delay(loops >> UDELAY_SHIFT);
+}
+
+static void __timer_udelay(unsigned long usecs)
+{
+	__timer_const_udelay(usecs * UDELAY_MULT);
+}
+
+void __init register_current_timer_delay(const struct delay_timer *timer)
+{
+	u32 new_mult, new_shift;
+	u64 res;
+
+	clocks_calc_mult_shift(&new_mult, &new_shift, timer->freq,
+			       NSEC_PER_SEC, 3600);
+	res = cyc_to_ns(1ULL, new_mult, new_shift);
+
+	if (res > 1000) {
+		pr_err("Ignoring delay timer %ps, which has insufficient resolution of %lluns\n",
+			timer, res);
+		return;
+	}
+
+	if (!delay_calibrated && (!delay_res || (res < delay_res))) {
+		pr_info("Switching to timer-based delay loop, resolution %lluns\n", res);
+		delay_timer			= timer;
+		lpj_fine			= timer->freq / HZ;
+		delay_res			= res;
+
+		/* cpufreq may scale loops_per_jiffy, so keep a private copy */
+		arm_delay_ops.ticks_per_jiffy	= lpj_fine;
+		arm_delay_ops.delay		= __timer_delay;
+		arm_delay_ops.const_udelay	= __timer_const_udelay;
+		arm_delay_ops.udelay		= __timer_udelay;
+	} else {
+		pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");
+	}
+}
+
+unsigned long calibrate_delay_is_known(void)
+{
+	delay_calibrated = true;
+	return lpj_fine;
+}
+
+void calibration_delay_done(void)
+{
+	delay_calibrated = true;
+}