Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 303 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-rtl-otto.c b/drivers/clocksource/timer-rtl-otto.c
new file mode 100644
index 000000000..0d1b9a01a
--- /dev/null
+++ b/drivers/clocksource/timer-rtl-otto.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/printk.h>
+#include <linux/sched_clock.h>
+#include "timer-of.h"
+
+#define RTTM_DATA		0x0
+#define RTTM_CNT		0x4
+#define RTTM_CTRL		0x8
+#define RTTM_INT		0xc
+
+#define RTTM_CTRL_ENABLE	BIT(28)
+#define RTTM_INT_PENDING	BIT(16)
+#define RTTM_INT_ENABLE		BIT(20)
+
+/*
+ * The Otto platform provides multiple 28 bit timers/counters with the following
+ * operating logic. If enabled the timer counts up. Per timer one can set a
+ * maximum counter value as an end marker. If end marker is reached the timer
+ * fires an interrupt. If the timer "overflows" by reaching the end marker or
+ * by adding 1 to 0x0fffffff the counter is reset to 0. When this happens and
+ * the timer is in operating mode COUNTER it stops. In mode TIMER it will
+ * continue to count up.
+ */
+#define RTTM_CTRL_COUNTER	0
+#define RTTM_CTRL_TIMER		BIT(24)
+
+#define RTTM_BIT_COUNT		28
+#define RTTM_MIN_DELTA		8
+#define RTTM_MAX_DELTA		CLOCKSOURCE_MASK(28)
+#define RTTM_MAX_DIVISOR	GENMASK(15, 0)
+
+/*
+ * Timers are derived from the lexra bus (LXB) clock frequency. This is 175 MHz
+ * on RTL930x and 200 MHz on the other platforms. With 3.125 MHz choose a common
+ * divisor to have enough range and detail. This provides comparability between
+ * the different platforms.
+ */
+#define RTTM_TICKS_PER_SEC	3125000
+
+struct rttm_cs {
+	struct timer_of		to;
+	struct clocksource	cs;
+};
+
+/* Simple internal register functions */
+static inline unsigned int rttm_get_counter(void __iomem *base)
+{
+	return __raw_readl(base + RTTM_CNT);
+}
+
+static inline void rttm_set_period(void __iomem *base, unsigned int period)
+{
+	__raw_writel(period, base + RTTM_DATA);
+}
+
+static inline void rttm_disable_timer(void __iomem *base)
+{
+	__raw_writel(0, base + RTTM_CTRL);
+}
+
+static inline void rttm_enable_timer(void __iomem *base, u32 mode, u32 divisor)
+{
+	__raw_writel(RTTM_CTRL_ENABLE | mode | divisor, base + RTTM_CTRL);
+}
+
+static inline void rttm_ack_irq(void __iomem *base)
+{
+	__raw_writel(__raw_readl(base + RTTM_INT) | RTTM_INT_PENDING, base + RTTM_INT);
+}
+
+static inline void rttm_enable_irq(void __iomem *base)
+{
+	__raw_writel(RTTM_INT_ENABLE, base + RTTM_INT);
+}
+
+static inline void rttm_disable_irq(void __iomem *base)
+{
+	__raw_writel(0, base + RTTM_INT);
+}
+
+/* Aggregated control functions for kernel clock framework */
+#define RTTM_DEBUG(base)			\
+	pr_debug("------------- %d %p\n",	\
+		 smp_processor_id(), base)
+
+static irqreturn_t rttm_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	rttm_ack_irq(to->of_base.base);
+	RTTM_DEBUG(to->of_base.base);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void rttm_bounce_timer(void __iomem *base, u32 mode)
+{
+	/*
+	 * When a running timer has less than ~5us left, a stop/start sequence
+	 * might fail. While the details are unknown the most evident effect is
+	 * that the subsequent interrupt will not be fired.
+	 *
+	 * As a workaround issue an intermediate restart with a very slow
+	 * frequency of ~3kHz keeping the target counter (>=8). So the follow
+	 * up restart will always be issued outside the critical window.
+	 */
+
+	rttm_disable_timer(base);
+	rttm_enable_timer(base, mode, RTTM_MAX_DIVISOR);
+}
+
+static void rttm_stop_timer(void __iomem *base)
+{
+	rttm_disable_timer(base);
+	rttm_ack_irq(base);
+}
+
+static void rttm_start_timer(struct timer_of *to, u32 mode)
+{
+	rttm_enable_timer(to->of_base.base, mode, to->of_clk.rate / RTTM_TICKS_PER_SEC);
+}
+
+static int rttm_next_event(unsigned long delta, struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	RTTM_DEBUG(to->of_base.base);
+	rttm_bounce_timer(to->of_base.base, RTTM_CTRL_COUNTER);
+	rttm_disable_timer(to->of_base.base);
+	rttm_set_period(to->of_base.base, delta);
+	rttm_start_timer(to, RTTM_CTRL_COUNTER);
+
+	return 0;
+}
+
+static int rttm_state_oneshot(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	RTTM_DEBUG(to->of_base.base);
+	rttm_bounce_timer(to->of_base.base, RTTM_CTRL_COUNTER);
+	rttm_disable_timer(to->of_base.base);
+	rttm_set_period(to->of_base.base, RTTM_TICKS_PER_SEC / HZ);
+	rttm_start_timer(to, RTTM_CTRL_COUNTER);
+
+	return 0;
+}
+
+static int rttm_state_periodic(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	RTTM_DEBUG(to->of_base.base);
+	rttm_bounce_timer(to->of_base.base, RTTM_CTRL_TIMER);
+	rttm_disable_timer(to->of_base.base);
+	rttm_set_period(to->of_base.base, RTTM_TICKS_PER_SEC / HZ);
+	rttm_start_timer(to, RTTM_CTRL_TIMER);
+
+	return 0;
+}
+
+static int rttm_state_shutdown(struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	RTTM_DEBUG(to->of_base.base);
+	rttm_stop_timer(to->of_base.base);
+
+	return 0;
+}
+
+static void rttm_setup_timer(void __iomem *base)
+{
+	RTTM_DEBUG(base);
+	rttm_stop_timer(base);
+	rttm_set_period(base, 0);
+}
+
+static u64 rttm_read_clocksource(struct clocksource *cs)
+{
+	struct rttm_cs *rcs = container_of(cs, struct rttm_cs, cs);
+
+	return rttm_get_counter(rcs->to.of_base.base);
+}
+
+/* Module initialization part. */
+static DEFINE_PER_CPU(struct timer_of, rttm_to) = {
+	.flags				= TIMER_OF_BASE | TIMER_OF_CLOCK | TIMER_OF_IRQ,
+	.of_irq = {
+		.flags			= IRQF_PERCPU | IRQF_TIMER,
+		.handler		= rttm_timer_interrupt,
+	},
+	.clkevt = {
+		.rating			= 400,
+		.features		= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+		.set_state_periodic	= rttm_state_periodic,
+		.set_state_shutdown	= rttm_state_shutdown,
+		.set_state_oneshot	= rttm_state_oneshot,
+		.set_next_event		= rttm_next_event
+	},
+};
+
+static int rttm_enable_clocksource(struct clocksource *cs)
+{
+	struct rttm_cs *rcs = container_of(cs, struct rttm_cs, cs);
+
+	rttm_disable_irq(rcs->to.of_base.base);
+	rttm_setup_timer(rcs->to.of_base.base);
+	rttm_enable_timer(rcs->to.of_base.base, RTTM_CTRL_TIMER,
+			  rcs->to.of_clk.rate / RTTM_TICKS_PER_SEC);
+
+	return 0;
+}
+
+static struct rttm_cs rttm_cs = {
+	.to = {
+		.flags	= TIMER_OF_BASE | TIMER_OF_CLOCK,
+	},
+	.cs = {
+		.name	= "realtek_otto_timer",
+		.rating	= 400,
+		.mask	= CLOCKSOURCE_MASK(RTTM_BIT_COUNT),
+		.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+		.read	= rttm_read_clocksource,
+	}
+};
+
+static u64 notrace rttm_read_clock(void)
+{
+	return rttm_get_counter(rttm_cs.to.of_base.base);
+}
+
+static int rttm_cpu_starting(unsigned int cpu)
+{
+	struct timer_of *to = per_cpu_ptr(&rttm_to, cpu);
+
+	RTTM_DEBUG(to->of_base.base);
+	to->clkevt.cpumask = cpumask_of(cpu);
+	irq_force_affinity(to->of_irq.irq, to->clkevt.cpumask);
+	clockevents_config_and_register(&to->clkevt, RTTM_TICKS_PER_SEC,
+					RTTM_MIN_DELTA, RTTM_MAX_DELTA);
+	rttm_enable_irq(to->of_base.base);
+
+	return 0;
+}
+
+static int __init rttm_probe(struct device_node *np)
+{
+	unsigned int cpu, cpu_rollback;
+	struct timer_of *to;
+	unsigned int clkidx = num_possible_cpus();
+
+	/* Use the first n timers as per CPU clock event generators */
+	for_each_possible_cpu(cpu) {
+		to = per_cpu_ptr(&rttm_to, cpu);
+		to->of_irq.index = to->of_base.index = cpu;
+		if (timer_of_init(np, to)) {
+			pr_err("setup of timer %d failed\n", cpu);
+			goto rollback;
+		}
+		rttm_setup_timer(to->of_base.base);
+	}
+
+	/* Activate the n'th + 1 timer as a stable CPU clocksource. */
+	to = &rttm_cs.to;
+	to->of_base.index = clkidx;
+	timer_of_init(np, to);
+	if (rttm_cs.to.of_base.base && rttm_cs.to.of_clk.rate) {
+		rttm_enable_clocksource(&rttm_cs.cs);
+		clocksource_register_hz(&rttm_cs.cs, RTTM_TICKS_PER_SEC);
+		sched_clock_register(rttm_read_clock, RTTM_BIT_COUNT, RTTM_TICKS_PER_SEC);
+	} else
+		pr_err(" setup of timer %d as clocksource failed", clkidx);
+
+	return cpuhp_setup_state(CPUHP_AP_REALTEK_TIMER_STARTING,
+				"timer/realtek:online",
+				rttm_cpu_starting, NULL);
+rollback:
+	pr_err("timer registration failed\n");
+	for_each_possible_cpu(cpu_rollback) {
+		if (cpu_rollback == cpu)
+			break;
+		to = per_cpu_ptr(&rttm_to, cpu_rollback);
+		timer_of_cleanup(to);
+	}
+
+	return -EINVAL;
+}
+
+TIMER_OF_DECLARE(otto_timer, "realtek,otto-timer", rttm_probe);