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, 293 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-ixp4xx.c b/drivers/clocksource/timer-ixp4xx.c
new file mode 100644
index 000000000..4238a004f
--- /dev/null
+++ b/drivers/clocksource/timer-ixp4xx.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IXP4 timer driver
+ * Copyright (C) 2019 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on arch/arm/mach-ixp4xx/common.c
+ * Copyright 2002 (C) Intel Corporation
+ * Copyright 2003-2004 (C) MontaVista, Software, Inc.
+ * Copyright (C) Deepak Saxena <dsaxena@plexity.net>
+ */
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+
+/*
+ * Constants to make it easy to access Timer Control/Status registers
+ */
+#define IXP4XX_OSTS_OFFSET	0x00  /* Continuous Timestamp */
+#define IXP4XX_OST1_OFFSET	0x04  /* Timer 1 Timestamp */
+#define IXP4XX_OSRT1_OFFSET	0x08  /* Timer 1 Reload */
+#define IXP4XX_OST2_OFFSET	0x0C  /* Timer 2 Timestamp */
+#define IXP4XX_OSRT2_OFFSET	0x10  /* Timer 2 Reload */
+#define IXP4XX_OSST_OFFSET	0x20  /* Timer Status */
+
+/*
+ * Timer register values and bit definitions
+ */
+#define IXP4XX_OST_ENABLE		0x00000001
+#define IXP4XX_OST_ONE_SHOT		0x00000002
+/* Low order bits of reload value ignored */
+#define IXP4XX_OST_RELOAD_MASK		0x00000003
+#define IXP4XX_OST_DISABLED		0x00000000
+#define IXP4XX_OSST_TIMER_1_PEND	0x00000001
+#define IXP4XX_OSST_TIMER_2_PEND	0x00000002
+#define IXP4XX_OSST_TIMER_TS_PEND	0x00000004
+/* Remaining registers are for the watchdog and defined in the watchdog driver */
+
+struct ixp4xx_timer {
+	void __iomem *base;
+	u32 latch;
+	struct clock_event_device clkevt;
+#ifdef CONFIG_ARM
+	struct delay_timer delay_timer;
+#endif
+};
+
+/*
+ * A local singleton used by sched_clock and delay timer reads, which are
+ * fast and stateless
+ */
+static struct ixp4xx_timer *local_ixp4xx_timer;
+
+static inline struct ixp4xx_timer *
+to_ixp4xx_timer(struct clock_event_device *evt)
+{
+	return container_of(evt, struct ixp4xx_timer, clkevt);
+}
+
+static unsigned long ixp4xx_read_timer(void)
+{
+	return __raw_readl(local_ixp4xx_timer->base + IXP4XX_OSTS_OFFSET);
+}
+
+static u64 notrace ixp4xx_read_sched_clock(void)
+{
+	return ixp4xx_read_timer();
+}
+
+static u64 ixp4xx_clocksource_read(struct clocksource *c)
+{
+	return ixp4xx_read_timer();
+}
+
+static irqreturn_t ixp4xx_timer_interrupt(int irq, void *dev_id)
+{
+	struct ixp4xx_timer *tmr = dev_id;
+	struct clock_event_device *evt = &tmr->clkevt;
+
+	/* Clear Pending Interrupt */
+	__raw_writel(IXP4XX_OSST_TIMER_1_PEND,
+		     tmr->base + IXP4XX_OSST_OFFSET);
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static int ixp4xx_set_next_event(unsigned long cycles,
+				 struct clock_event_device *evt)
+{
+	struct ixp4xx_timer *tmr = to_ixp4xx_timer(evt);
+	u32 val;
+
+	val = __raw_readl(tmr->base + IXP4XX_OSRT1_OFFSET);
+	/* Keep enable/oneshot bits */
+	val &= IXP4XX_OST_RELOAD_MASK;
+	__raw_writel((cycles & ~IXP4XX_OST_RELOAD_MASK) | val,
+		     tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	return 0;
+}
+
+static int ixp4xx_shutdown(struct clock_event_device *evt)
+{
+	struct ixp4xx_timer *tmr = to_ixp4xx_timer(evt);
+	u32 val;
+
+	val = __raw_readl(tmr->base + IXP4XX_OSRT1_OFFSET);
+	val &= ~IXP4XX_OST_ENABLE;
+	__raw_writel(val, tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	return 0;
+}
+
+static int ixp4xx_set_oneshot(struct clock_event_device *evt)
+{
+	struct ixp4xx_timer *tmr = to_ixp4xx_timer(evt);
+
+	__raw_writel(IXP4XX_OST_ENABLE | IXP4XX_OST_ONE_SHOT,
+		     tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	return 0;
+}
+
+static int ixp4xx_set_periodic(struct clock_event_device *evt)
+{
+	struct ixp4xx_timer *tmr = to_ixp4xx_timer(evt);
+	u32 val;
+
+	val = tmr->latch & ~IXP4XX_OST_RELOAD_MASK;
+	val |= IXP4XX_OST_ENABLE;
+	__raw_writel(val, tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	return 0;
+}
+
+static int ixp4xx_resume(struct clock_event_device *evt)
+{
+	struct ixp4xx_timer *tmr = to_ixp4xx_timer(evt);
+	u32 val;
+
+	val = __raw_readl(tmr->base + IXP4XX_OSRT1_OFFSET);
+	val |= IXP4XX_OST_ENABLE;
+	__raw_writel(val, tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	return 0;
+}
+
+/*
+ * IXP4xx timer tick
+ * We use OS timer1 on the CPU for the timer tick and the timestamp
+ * counter as a source of real clock ticks to account for missed jiffies.
+ */
+static __init int ixp4xx_timer_register(void __iomem *base,
+					int timer_irq,
+					unsigned int timer_freq)
+{
+	struct ixp4xx_timer *tmr;
+	int ret;
+
+	tmr = kzalloc_obj(*tmr);
+	if (!tmr)
+		return -ENOMEM;
+	tmr->base = base;
+
+	/*
+	 * The timer register doesn't allow to specify the two least
+	 * significant bits of the timeout value and assumes them being zero.
+	 * So make sure the latch is the best value with the two least
+	 * significant bits unset.
+	 */
+	tmr->latch = DIV_ROUND_CLOSEST(timer_freq,
+				       (IXP4XX_OST_RELOAD_MASK + 1) * HZ)
+		* (IXP4XX_OST_RELOAD_MASK + 1);
+
+	local_ixp4xx_timer = tmr;
+
+	/* Reset/disable counter */
+	__raw_writel(0, tmr->base + IXP4XX_OSRT1_OFFSET);
+
+	/* Clear any pending interrupt on timer 1 */
+	__raw_writel(IXP4XX_OSST_TIMER_1_PEND,
+		     tmr->base + IXP4XX_OSST_OFFSET);
+
+	/* Reset time-stamp counter */
+	__raw_writel(0, tmr->base + IXP4XX_OSTS_OFFSET);
+
+	clocksource_mmio_init(NULL, "OSTS", timer_freq, 200, 32,
+			      ixp4xx_clocksource_read);
+
+	tmr->clkevt.name = "ixp4xx timer1";
+	tmr->clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	tmr->clkevt.rating = 200;
+	tmr->clkevt.set_state_shutdown = ixp4xx_shutdown;
+	tmr->clkevt.set_state_periodic = ixp4xx_set_periodic;
+	tmr->clkevt.set_state_oneshot = ixp4xx_set_oneshot;
+	tmr->clkevt.tick_resume = ixp4xx_resume;
+	tmr->clkevt.set_next_event = ixp4xx_set_next_event;
+	tmr->clkevt.cpumask = cpumask_of(0);
+	tmr->clkevt.irq = timer_irq;
+	ret = request_irq(timer_irq, ixp4xx_timer_interrupt,
+			  IRQF_TIMER, "IXP4XX-TIMER1", tmr);
+	if (ret) {
+		pr_crit("no timer IRQ\n");
+		return -ENODEV;
+	}
+	clockevents_config_and_register(&tmr->clkevt, timer_freq,
+					0xf, 0xfffffffe);
+
+	sched_clock_register(ixp4xx_read_sched_clock, 32, timer_freq);
+
+#ifdef CONFIG_ARM
+	/* Also use this timer for delays */
+	tmr->delay_timer.read_current_timer = ixp4xx_read_timer;
+	tmr->delay_timer.freq = timer_freq;
+	register_current_timer_delay(&tmr->delay_timer);
+#endif
+
+	return 0;
+}
+
+static struct platform_device ixp4xx_watchdog_device = {
+	.name = "ixp4xx-watchdog",
+	.id = -1,
+};
+
+/*
+ * This probe gets called after the timer is already up and running. The main
+ * function on this platform is to spawn the watchdog device as a child.
+ */
+static int ixp4xx_timer_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	/* Pass the base address as platform data and nothing else */
+	ixp4xx_watchdog_device.dev.platform_data = local_ixp4xx_timer->base;
+	ixp4xx_watchdog_device.dev.parent = dev;
+	return platform_device_register(&ixp4xx_watchdog_device);
+}
+
+static const struct of_device_id ixp4xx_timer_dt_id[] = {
+	{ .compatible = "intel,ixp4xx-timer", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver ixp4xx_timer_driver = {
+	.probe  = ixp4xx_timer_probe,
+	.driver = {
+		.name = "ixp4xx-timer",
+		.of_match_table = ixp4xx_timer_dt_id,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver(ixp4xx_timer_driver);
+
+static __init int ixp4xx_of_timer_init(struct device_node *np)
+{
+	void __iomem *base;
+	int irq;
+	int ret;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_crit("IXP4xx: can't remap timer\n");
+		return -ENODEV;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (irq <= 0) {
+		pr_err("Can't parse IRQ\n");
+		ret = -EINVAL;
+		goto out_unmap;
+	}
+
+	/* TODO: get some fixed clocks into the device tree */
+	ret = ixp4xx_timer_register(base, irq, 66666000);
+	if (ret)
+		goto out_unmap;
+	return 0;
+
+out_unmap:
+	iounmap(base);
+	return ret;
+}
+TIMER_OF_DECLARE(ixp4xx, "intel,ixp4xx-timer", ixp4xx_of_timer_init);