Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 624 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-tegra186.c b/drivers/clocksource/timer-tegra186.c
new file mode 100644
index 000000000..0f626ecf6
--- /dev/null
+++ b/drivers/clocksource/timer-tegra186.c
@@ -0,0 +1,624 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019-2025 NVIDIA Corporation. All rights reserved.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clocksource.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/watchdog.h>
+
+/* shared registers */
+#define TKETSC0 0x000
+#define TKETSC1 0x004
+#define TKEUSEC 0x008
+#define TKEOSC  0x00c
+
+#define TKEIE(x) (0x100 + ((x) * 4))
+#define  TKEIE_WDT_MASK(x, y) ((y) << (16 + 4 * (x)))
+
+/* timer registers */
+#define TMRCR 0x000
+#define  TMRCR_ENABLE BIT(31)
+#define  TMRCR_PERIODIC BIT(30)
+#define  TMRCR_PTV(x) ((x) & 0x0fffffff)
+
+#define TMRSR 0x004
+#define  TMRSR_INTR_CLR BIT(30)
+#define  TMRSR_PCV GENMASK(28, 0)
+
+#define TMRCSSR 0x008
+#define  TMRCSSR_SRC_USEC (0 << 0)
+
+/* watchdog registers */
+#define WDTCR 0x000
+#define  WDTCR_SYSTEM_POR_RESET_ENABLE BIT(16)
+#define  WDTCR_SYSTEM_DEBUG_RESET_ENABLE BIT(15)
+#define  WDTCR_REMOTE_INT_ENABLE BIT(14)
+#define  WDTCR_LOCAL_FIQ_ENABLE BIT(13)
+#define  WDTCR_LOCAL_INT_ENABLE BIT(12)
+#define  WDTCR_PERIOD_MASK (0xff << 4)
+#define  WDTCR_PERIOD(x) (((x) & 0xff) << 4)
+#define  WDTCR_TIMER_SOURCE_MASK 0xf
+#define  WDTCR_TIMER_SOURCE(x) ((x) & 0xf)
+
+#define WDTSR 0x004
+#define  WDTSR_CURRENT_EXPIRATION_COUNT GENMASK(14, 12)
+
+#define WDTCMDR 0x008
+#define  WDTCMDR_DISABLE_COUNTER BIT(1)
+#define  WDTCMDR_START_COUNTER BIT(0)
+
+#define WDTUR 0x00c
+#define  WDTUR_UNLOCK_PATTERN 0x0000c45a
+
+#define TEGRA186_KERNEL_WDT_TIMEOUT 120
+
+/* WDT security configuration registers */
+#define WDTSCR(x)		(0xf02c + (x) * 4)
+#define  WDTSCR_SEC_WEN		BIT(28)
+#define  WDTSCR_SEC_REN		BIT(27)
+#define  WDTSCR_SEC_G1W		BIT(9)
+#define  WDTSCR_SEC_G1R		BIT(1)
+
+struct tegra186_timer_soc {
+	unsigned int num_timers;
+	unsigned int num_wdts;
+};
+
+struct tegra186_tmr {
+	struct tegra186_timer *parent;
+	void __iomem *regs;
+	unsigned int index;
+	unsigned int hwirq;
+};
+
+struct tegra186_wdt {
+	struct watchdog_device base;
+
+	void __iomem *regs;
+	unsigned int index;
+	bool locked;
+	bool is_kernel_wdt;
+
+	struct tegra186_tmr *tmr;
+};
+
+static inline struct tegra186_wdt *to_tegra186_wdt(struct watchdog_device *wdd)
+{
+	return container_of(wdd, struct tegra186_wdt, base);
+}
+
+struct tegra186_timer {
+	const struct tegra186_timer_soc *soc;
+	struct device *dev;
+	void __iomem *regs;
+
+	struct tegra186_wdt **wdts;
+	struct clocksource usec;
+	struct clocksource tsc;
+	struct clocksource osc;
+};
+
+static void tmr_writel(struct tegra186_tmr *tmr, u32 value, unsigned int offset)
+{
+	writel_relaxed(value, tmr->regs + offset);
+}
+
+static void wdt_writel(struct tegra186_wdt *wdt, u32 value, unsigned int offset)
+{
+	writel_relaxed(value, wdt->regs + offset);
+}
+
+static u32 wdt_readl(struct tegra186_wdt *wdt, unsigned int offset)
+{
+	return readl_relaxed(wdt->regs + offset);
+}
+
+static struct tegra186_tmr *tegra186_tmr_create(struct tegra186_timer *tegra,
+						unsigned int index)
+{
+	unsigned int offset = 0x10000 + index * 0x10000;
+	struct tegra186_tmr *tmr;
+
+	tmr = devm_kzalloc(tegra->dev, sizeof(*tmr), GFP_KERNEL);
+	if (!tmr)
+		return ERR_PTR(-ENOMEM);
+
+	tmr->parent = tegra;
+	tmr->regs = tegra->regs + offset;
+	tmr->index = index;
+	tmr->hwirq = 0;
+
+	return tmr;
+}
+
+static const struct watchdog_info tegra186_wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING,
+	.identity = "NVIDIA Tegra186 WDT",
+};
+
+static void tegra186_wdt_disable(struct tegra186_wdt *wdt)
+{
+	/* unlock and disable the watchdog */
+	wdt_writel(wdt, WDTUR_UNLOCK_PATTERN, WDTUR);
+	wdt_writel(wdt, WDTCMDR_DISABLE_COUNTER, WDTCMDR);
+
+	/* disable timer */
+	tmr_writel(wdt->tmr, 0, TMRCR);
+}
+
+static void tegra186_wdt_enable(struct tegra186_wdt *wdt)
+{
+	struct tegra186_timer *tegra = wdt->tmr->parent;
+	u32 value;
+
+	/* unmask hardware IRQ, this may have been lost across powergate */
+	value = readl(tegra->regs + TKEIE(wdt->tmr->hwirq));
+	value |= TKEIE_WDT_MASK(wdt->index, 1);
+	writel(value, tegra->regs + TKEIE(wdt->tmr->hwirq));
+
+	/* clear interrupt */
+	tmr_writel(wdt->tmr, TMRSR_INTR_CLR, TMRSR);
+
+	/* select microsecond source */
+	tmr_writel(wdt->tmr, TMRCSSR_SRC_USEC, TMRCSSR);
+
+	/* configure timer (system reset happens on the fifth expiration) */
+	value = TMRCR_PTV(wdt->base.timeout * (USEC_PER_SEC / 5)) |
+		TMRCR_PERIODIC | TMRCR_ENABLE;
+	tmr_writel(wdt->tmr, value, TMRCR);
+
+	if (!wdt->locked) {
+		value = wdt_readl(wdt, WDTCR);
+
+		/* select the proper timer source */
+		value &= ~WDTCR_TIMER_SOURCE_MASK;
+		value |= WDTCR_TIMER_SOURCE(wdt->tmr->index);
+
+		/* single timer period since that's already configured */
+		value &= ~WDTCR_PERIOD_MASK;
+		value |= WDTCR_PERIOD(1);
+
+		/* enable local interrupt for kernel watchdog */
+		if (wdt->is_kernel_wdt)
+			value |= WDTCR_LOCAL_INT_ENABLE;
+
+		/* enable system POR reset */
+		value |= WDTCR_SYSTEM_POR_RESET_ENABLE;
+
+		wdt_writel(wdt, value, WDTCR);
+	}
+
+	wdt_writel(wdt, WDTCMDR_START_COUNTER, WDTCMDR);
+}
+
+static int tegra186_wdt_start(struct watchdog_device *wdd)
+{
+	struct tegra186_wdt *wdt = to_tegra186_wdt(wdd);
+
+	tegra186_wdt_enable(wdt);
+
+	return 0;
+}
+
+static int tegra186_wdt_stop(struct watchdog_device *wdd)
+{
+	struct tegra186_wdt *wdt = to_tegra186_wdt(wdd);
+
+	tegra186_wdt_disable(wdt);
+
+	return 0;
+}
+
+static int tegra186_wdt_ping(struct watchdog_device *wdd)
+{
+	struct tegra186_wdt *wdt = to_tegra186_wdt(wdd);
+
+	tegra186_wdt_disable(wdt);
+	tegra186_wdt_enable(wdt);
+
+	return 0;
+}
+
+static irqreturn_t tegra186_wdt_irq(int irq, void *data)
+{
+	struct tegra186_wdt *wdt = data;
+
+	tegra186_wdt_disable(wdt);
+	tegra186_wdt_enable(wdt);
+
+	return IRQ_HANDLED;
+}
+
+static int tegra186_wdt_set_timeout(struct watchdog_device *wdd,
+				    unsigned int timeout)
+{
+	struct tegra186_wdt *wdt = to_tegra186_wdt(wdd);
+
+	if (watchdog_active(&wdt->base))
+		tegra186_wdt_disable(wdt);
+
+	wdt->base.timeout = timeout;
+
+	if (watchdog_active(&wdt->base))
+		tegra186_wdt_enable(wdt);
+
+	return 0;
+}
+
+static unsigned int tegra186_wdt_get_timeleft(struct watchdog_device *wdd)
+{
+	struct tegra186_wdt *wdt = to_tegra186_wdt(wdd);
+	u32 expiration, val;
+	u32 timeleft;
+
+	if (!watchdog_active(&wdt->base)) {
+		/* return zero if the watchdog timer is not activated. */
+		return 0;
+	}
+
+	/*
+	 * Reset occurs on the fifth expiration of the
+	 * watchdog timer and so when the watchdog timer is configured,
+	 * the actual value programmed into the counter is 1/5 of the
+	 * timeout value. Once the counter reaches 0, expiration count
+	 * will be increased by 1 and the down counter restarts.
+	 * Hence to get the time left before system reset we must
+	 * combine 2 parts:
+	 * 1. value of the current down counter
+	 * 2. (number of counter expirations remaining) * (timeout/5)
+	 */
+
+	/* Get the current number of counter expirations. Should be a
+	 * value between 0 and 4
+	 */
+	val = readl_relaxed(wdt->regs + WDTSR);
+	expiration = FIELD_GET(WDTSR_CURRENT_EXPIRATION_COUNT, val);
+	if (WARN_ON_ONCE(expiration > 4))
+		return 0;
+
+	/* Get the current counter value in microsecond. */
+	val = readl_relaxed(wdt->tmr->regs + TMRSR);
+	timeleft = FIELD_GET(TMRSR_PCV, val);
+
+	/*
+	 * Calculate the time remaining by adding the time for the
+	 * counter value to the time of the counter expirations that
+	 * remain.
+	 * Note: Since wdt->base.timeout is bound to 255, the maximum
+	 * value added to timeleft is
+	 *   255 * (1,000,000 / 5) * 4
+	 * = 255 * 200,000 * 4
+	 * = 204,000,000
+	 * TMRSR_PCV is a 29-bit field.
+	 * Its maximum value is 0x1fffffff = 536,870,911.
+	 * 204,000,000 + 536,870,911 = 740,870,911 = 0x2C28CAFF.
+	 * timeleft can therefore not overflow, and 64-bit calculations
+	 * are not necessary.
+	 */
+	timeleft += (wdt->base.timeout * (USEC_PER_SEC / 5)) * (4 - expiration);
+
+	/*
+	 * Convert the current counter value to seconds,
+	 * rounding to the nearest second.
+	 */
+	timeleft = DIV_ROUND_CLOSEST(timeleft, USEC_PER_SEC);
+
+	return timeleft;
+}
+
+static const struct watchdog_ops tegra186_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = tegra186_wdt_start,
+	.stop = tegra186_wdt_stop,
+	.ping = tegra186_wdt_ping,
+	.set_timeout = tegra186_wdt_set_timeout,
+	.get_timeleft = tegra186_wdt_get_timeleft,
+};
+
+static bool tegra186_wdt_is_accessible(struct tegra186_timer *tegra, unsigned int index)
+{
+	u32 value;
+
+	value = readl_relaxed(tegra->regs + WDTSCR(index));
+
+	/* Check OS write access if write blocking is enabled. */
+	if ((value & WDTSCR_SEC_WEN) && !(value & WDTSCR_SEC_G1W))
+		return false;
+
+	/* Check OS read access if read blocking is enabled. */
+	if ((value & WDTSCR_SEC_REN) && !(value & WDTSCR_SEC_G1R))
+		return false;
+
+	return true;
+}
+
+static struct tegra186_wdt *tegra186_wdt_create(struct tegra186_timer *tegra,
+						unsigned int index)
+{
+	unsigned int offset = 0x10000, source;
+	struct tegra186_wdt *wdt;
+	u32 value;
+	int err;
+
+	offset += tegra->soc->num_timers * 0x10000 + index * 0x10000;
+
+	wdt = devm_kzalloc(tegra->dev, sizeof(*wdt), GFP_KERNEL);
+	if (!wdt)
+		return ERR_PTR(-ENOMEM);
+
+	wdt->regs = tegra->regs + offset;
+	wdt->index = index;
+
+	/* read the watchdog configuration since it might be locked down */
+	value = wdt_readl(wdt, WDTCR);
+
+	if (value & WDTCR_LOCAL_INT_ENABLE)
+		wdt->locked = true;
+
+	source = value & WDTCR_TIMER_SOURCE_MASK;
+
+	wdt->tmr = tegra186_tmr_create(tegra, source);
+	if (IS_ERR(wdt->tmr))
+		return ERR_CAST(wdt->tmr);
+
+	wdt->base.info = &tegra186_wdt_info;
+	wdt->base.ops = &tegra186_wdt_ops;
+	wdt->base.min_timeout = 1;
+	wdt->base.max_timeout = 255;
+	wdt->base.parent = tegra->dev;
+
+	err = watchdog_init_timeout(&wdt->base, 5, tegra->dev);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return wdt;
+}
+
+static u64 tegra186_timer_tsc_read(struct clocksource *cs)
+{
+	struct tegra186_timer *tegra = container_of(cs, struct tegra186_timer,
+						    tsc);
+	u32 hi, lo, ss;
+
+	hi = readl_relaxed(tegra->regs + TKETSC1);
+
+	/*
+	 * The 56-bit value of the TSC is spread across two registers that are
+	 * not synchronized. In order to read them atomically, ensure that the
+	 * high 24 bits match before and after reading the low 32 bits.
+	 */
+	do {
+		/* snapshot the high 24 bits */
+		ss = hi;
+
+		lo = readl_relaxed(tegra->regs + TKETSC0);
+		hi = readl_relaxed(tegra->regs + TKETSC1);
+	} while (hi != ss);
+
+	return (u64)hi << 32 | lo;
+}
+
+static int tegra186_timer_tsc_init(struct tegra186_timer *tegra)
+{
+	tegra->tsc.name = "tsc";
+	tegra->tsc.rating = 300;
+	tegra->tsc.read = tegra186_timer_tsc_read;
+	tegra->tsc.mask = CLOCKSOURCE_MASK(56);
+	tegra->tsc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	tegra->tsc.owner = THIS_MODULE;
+
+	return clocksource_register_hz(&tegra->tsc, 31250000);
+}
+
+static u64 tegra186_timer_osc_read(struct clocksource *cs)
+{
+	struct tegra186_timer *tegra = container_of(cs, struct tegra186_timer,
+						    osc);
+
+	return readl_relaxed(tegra->regs + TKEOSC);
+}
+
+static int tegra186_timer_osc_init(struct tegra186_timer *tegra)
+{
+	tegra->osc.name = "osc";
+	tegra->osc.rating = 300;
+	tegra->osc.read = tegra186_timer_osc_read;
+	tegra->osc.mask = CLOCKSOURCE_MASK(32);
+	tegra->osc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	tegra->osc.owner = THIS_MODULE;
+
+	return clocksource_register_hz(&tegra->osc, 38400000);
+}
+
+static u64 tegra186_timer_usec_read(struct clocksource *cs)
+{
+	struct tegra186_timer *tegra = container_of(cs, struct tegra186_timer,
+						    usec);
+
+	return readl_relaxed(tegra->regs + TKEUSEC);
+}
+
+static int tegra186_timer_usec_init(struct tegra186_timer *tegra)
+{
+	tegra->usec.name = "usec";
+	tegra->usec.rating = 300;
+	tegra->usec.read = tegra186_timer_usec_read;
+	tegra->usec.mask = CLOCKSOURCE_MASK(32);
+	tegra->usec.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	tegra->usec.owner = THIS_MODULE;
+
+	return clocksource_register_hz(&tegra->usec, USEC_PER_SEC);
+}
+
+static int tegra186_timer_probe(struct platform_device *pdev)
+{
+	struct tegra186_wdt *kernel_wdt = NULL;
+	struct device *dev = &pdev->dev;
+	struct tegra186_timer *tegra;
+	unsigned int i;
+	int irq;
+	int err;
+
+	tegra = devm_kzalloc(dev, sizeof(*tegra), GFP_KERNEL);
+	if (!tegra)
+		return -ENOMEM;
+
+	tegra->soc = of_device_get_match_data(dev);
+	dev_set_drvdata(dev, tegra);
+	tegra->dev = dev;
+
+	tegra->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(tegra->regs))
+		return PTR_ERR(tegra->regs);
+
+	err = platform_get_irq(pdev, 0);
+	if (err < 0)
+		return err;
+
+	irq = err;
+
+	tegra->wdts = devm_kcalloc(dev, tegra->soc->num_wdts, sizeof(*tegra->wdts), GFP_KERNEL);
+	if (!tegra->wdts)
+		return -ENOMEM;
+
+	for (i = 0; i < tegra->soc->num_wdts; i++) {
+		if (!tegra186_wdt_is_accessible(tegra, i)) {
+			dev_warn(dev, "WDT%u is not accessible\n", i);
+			continue;
+		}
+
+		tegra->wdts[i] = tegra186_wdt_create(tegra, i);
+		if (IS_ERR(tegra->wdts[i]))
+			return dev_err_probe(dev, PTR_ERR(tegra->wdts[i]),
+					     "failed to create WDT%u\n", i);
+
+		/* Reserve the first accessible WDT for the Kernel. */
+		if (!kernel_wdt) {
+			kernel_wdt = tegra->wdts[i];
+			kernel_wdt->is_kernel_wdt = true;
+		} else {
+			err = devm_watchdog_register_device(dev, &tegra->wdts[i]->base);
+			if (err < 0)
+				return dev_err_probe(dev, err,
+						     "failed to register WDT%u\n", i);
+		}
+	}
+
+	err = tegra186_timer_tsc_init(tegra);
+	if (err < 0) {
+		dev_err(dev, "failed to register TSC counter: %d\n", err);
+		return err;
+	}
+
+	err = tegra186_timer_osc_init(tegra);
+	if (err < 0) {
+		dev_err(dev, "failed to register OSC counter: %d\n", err);
+		goto unregister_tsc;
+	}
+
+	err = tegra186_timer_usec_init(tegra);
+	if (err < 0) {
+		dev_err(dev, "failed to register USEC counter: %d\n", err);
+		goto unregister_osc;
+	}
+
+	if (kernel_wdt) {
+		err = devm_request_irq(dev, irq, tegra186_wdt_irq, 0,
+				       dev_name(dev), kernel_wdt);
+		if (err < 0)
+			goto unregister_usec;
+
+		tegra186_wdt_set_timeout(&kernel_wdt->base, TEGRA186_KERNEL_WDT_TIMEOUT);
+		tegra186_wdt_enable(kernel_wdt);
+	}
+
+	return 0;
+
+unregister_usec:
+	clocksource_unregister(&tegra->usec);
+unregister_osc:
+	clocksource_unregister(&tegra->osc);
+unregister_tsc:
+	clocksource_unregister(&tegra->tsc);
+	return err;
+}
+
+static void tegra186_timer_remove(struct platform_device *pdev)
+{
+	struct tegra186_timer *tegra = platform_get_drvdata(pdev);
+
+	clocksource_unregister(&tegra->usec);
+	clocksource_unregister(&tegra->osc);
+	clocksource_unregister(&tegra->tsc);
+}
+
+static int __maybe_unused tegra186_timer_suspend(struct device *dev)
+{
+	struct tegra186_timer *tegra = dev_get_drvdata(dev);
+	unsigned int i;
+
+	for (i = 0; i < tegra->soc->num_wdts; i++) {
+		struct tegra186_wdt *wdt = tegra->wdts[i];
+
+		if (wdt && (wdt->is_kernel_wdt || watchdog_active(&wdt->base)))
+			tegra186_wdt_disable(wdt);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra186_timer_resume(struct device *dev)
+{
+	struct tegra186_timer *tegra = dev_get_drvdata(dev);
+	unsigned int i;
+
+	for (i = 0; i < tegra->soc->num_wdts; i++) {
+		struct tegra186_wdt *wdt = tegra->wdts[i];
+
+		if (wdt && (wdt->is_kernel_wdt || watchdog_active(&wdt->base)))
+			tegra186_wdt_enable(wdt);
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(tegra186_timer_pm_ops, tegra186_timer_suspend,
+			 tegra186_timer_resume);
+
+static const struct tegra186_timer_soc tegra186_timer = {
+	.num_timers = 10,
+	.num_wdts = 2,
+};
+
+static const struct tegra186_timer_soc tegra234_timer = {
+	.num_timers = 16,
+	.num_wdts = 2,
+};
+
+static const struct of_device_id tegra186_timer_of_match[] = {
+	{ .compatible = "nvidia,tegra186-timer", .data = &tegra186_timer },
+	{ .compatible = "nvidia,tegra234-timer", .data = &tegra234_timer },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, tegra186_timer_of_match);
+
+static struct platform_driver tegra186_wdt_driver = {
+	.driver = {
+		.name = "tegra186-timer",
+		.pm = &tegra186_timer_pm_ops,
+		.of_match_table = tegra186_timer_of_match,
+	},
+	.probe = tegra186_timer_probe,
+	.remove = tegra186_timer_remove,
+};
+module_platform_driver(tegra186_wdt_driver);
+
+MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra186 timers driver");