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, 275 insertions, 0 deletions

diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c
new file mode 100644
index 000000000..677929372
--- /dev/null
+++ b/drivers/clocksource/acpi_pm.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/drivers/clocksource/acpi_pm.c
+ *
+ * This file contains the ACPI PM based clocksource.
+ *
+ * This code was largely moved from the i386 timer_pm.c file
+ * which was (C) Dominik Brodowski <linux@brodo.de> 2003
+ * and contained the following comments:
+ *
+ * Driver to use the Power Management Timer (PMTMR) available in some
+ * southbridges as primary timing source for the Linux kernel.
+ *
+ * Based on parts of linux/drivers/acpi/hardware/hwtimer.c, timer_pit.c,
+ * timer_hpet.c, and on Arjan van de Ven's implementation for 2.4.
+ */
+
+#include <linux/acpi_pmtmr.h>
+#include <linux/clocksource.h>
+#include <linux/timex.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <asm/io.h>
+#include <asm/time.h>
+
+static void *suspend_resume_cb_data;
+
+static void (*suspend_resume_callback)(void *data, bool suspend);
+
+/*
+ * The I/O port the PMTMR resides at.
+ * The location is detected during setup_arch(),
+ * in arch/i386/kernel/acpi/boot.c
+ */
+u32 pmtmr_ioport __read_mostly;
+
+static inline u32 read_pmtmr(void)
+{
+	/* mask the output to 24 bits */
+	return inl(pmtmr_ioport) & ACPI_PM_MASK;
+}
+
+u32 acpi_pm_read_verified(void)
+{
+	u32 v1 = 0, v2 = 0, v3 = 0;
+
+	/*
+	 * It has been reported that because of various broken
+	 * chipsets (ICH4, PIIX4 and PIIX4E) where the ACPI PM clock
+	 * source is not latched, you must read it multiple
+	 * times to ensure a safe value is read:
+	 */
+	do {
+		v1 = read_pmtmr();
+		v2 = read_pmtmr();
+		v3 = read_pmtmr();
+	} while (unlikely((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1)
+			  || (v3 > v1 && v3 < v2)));
+
+	return v2;
+}
+
+void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data)
+{
+	suspend_resume_callback = cb;
+	suspend_resume_cb_data = data;
+}
+EXPORT_SYMBOL_GPL(acpi_pmtmr_register_suspend_resume_callback);
+
+void acpi_pmtmr_unregister_suspend_resume_callback(void)
+{
+	suspend_resume_callback = NULL;
+	suspend_resume_cb_data = NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_pmtmr_unregister_suspend_resume_callback);
+
+static void acpi_pm_suspend(struct clocksource *cs)
+{
+	if (suspend_resume_callback)
+		suspend_resume_callback(suspend_resume_cb_data, true);
+}
+
+static void acpi_pm_resume(struct clocksource *cs)
+{
+	if (suspend_resume_callback)
+		suspend_resume_callback(suspend_resume_cb_data, false);
+}
+
+static u64 acpi_pm_read(struct clocksource *cs)
+{
+	return (u64)read_pmtmr();
+}
+
+static struct clocksource clocksource_acpi_pm = {
+	.name		= "acpi_pm",
+	.rating		= 200,
+	.read		= acpi_pm_read,
+	.mask		= (u64)ACPI_PM_MASK,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_CALIBRATED,
+	.suspend	= acpi_pm_suspend,
+	.resume		= acpi_pm_resume,
+};
+
+
+#ifdef CONFIG_PCI
+static int acpi_pm_good;
+static int __init acpi_pm_good_setup(char *__str)
+{
+	acpi_pm_good = 1;
+	return 1;
+}
+__setup("acpi_pm_good", acpi_pm_good_setup);
+
+static u64 acpi_pm_read_slow(struct clocksource *cs)
+{
+	return (u64)acpi_pm_read_verified();
+}
+
+static inline void acpi_pm_need_workaround(void)
+{
+	clocksource_acpi_pm.read = acpi_pm_read_slow;
+	clocksource_acpi_pm.rating = 120;
+}
+
+/*
+ * PIIX4 Errata:
+ *
+ * The power management timer may return improper results when read.
+ * Although the timer value settles properly after incrementing,
+ * while incrementing there is a 3 ns window every 69.8 ns where the
+ * timer value is indeterminate (a 4.2% chance that the data will be
+ * incorrect when read). As a result, the ACPI free running count up
+ * timer specification is violated due to erroneous reads.
+ */
+static void acpi_pm_check_blacklist(struct pci_dev *dev)
+{
+	if (acpi_pm_good)
+		return;
+
+	/* the bug has been fixed in PIIX4M */
+	if (dev->revision < 3) {
+		pr_warn("* Found PM-Timer Bug on the chipset. Due to workarounds for a bug,\n"
+			"* this clock source is slow. Consider trying other clock sources\n");
+
+		acpi_pm_need_workaround();
+	}
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_3,
+			acpi_pm_check_blacklist);
+
+static void acpi_pm_check_graylist(struct pci_dev *dev)
+{
+	if (acpi_pm_good)
+		return;
+
+	pr_warn("* The chipset may have PM-Timer Bug. Due to workarounds for a bug,\n"
+		"* this clock source is slow. If you are sure your timer does not have\n"
+		"* this bug, please use \"acpi_pm_good\" to disable the workaround\n");
+
+	acpi_pm_need_workaround();
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_0,
+			acpi_pm_check_graylist);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_LE,
+			acpi_pm_check_graylist);
+#endif
+
+#ifndef CONFIG_X86_64
+#include <asm/mach_timer.h>
+#define PMTMR_EXPECTED_RATE \
+  ((CALIBRATE_LATCH * (PMTMR_TICKS_PER_SEC >> 10)) / (PIT_TICK_RATE>>10))
+/*
+ * Some boards have the PMTMR running way too fast. We check
+ * the PMTMR rate against PIT channel 2 to catch these cases.
+ */
+static int verify_pmtmr_rate(void)
+{
+	u64 value1, value2;
+	unsigned long count, delta;
+
+	mach_prepare_counter();
+	value1 = clocksource_acpi_pm.read(&clocksource_acpi_pm);
+	mach_countup(&count);
+	value2 = clocksource_acpi_pm.read(&clocksource_acpi_pm);
+	delta = (value2 - value1) & ACPI_PM_MASK;
+
+	/* Check that the PMTMR delta is within 5% of what we expect */
+	if (delta < (PMTMR_EXPECTED_RATE * 19) / 20 ||
+	    delta > (PMTMR_EXPECTED_RATE * 21) / 20) {
+		pr_info("PM-Timer running at invalid rate: %lu%% of normal - aborting.\n",
+			100UL * delta / PMTMR_EXPECTED_RATE);
+		return -1;
+	}
+
+	return 0;
+}
+#else
+#define verify_pmtmr_rate() (0)
+#endif
+
+/* Number of monotonicity checks to perform during initialization */
+#define ACPI_PM_MONOTONICITY_CHECKS 10
+/* Number of reads we try to get two different values */
+#define ACPI_PM_READ_CHECKS 10000
+
+static int __init init_acpi_pm_clocksource(void)
+{
+	u64 value1, value2;
+	unsigned int i, j = 0;
+
+	if (!pmtmr_ioport)
+		return -ENODEV;
+
+	/* "verify" this timing source: */
+	for (j = 0; j < ACPI_PM_MONOTONICITY_CHECKS; j++) {
+		udelay(100 * j);
+		value1 = clocksource_acpi_pm.read(&clocksource_acpi_pm);
+		for (i = 0; i < ACPI_PM_READ_CHECKS; i++) {
+			value2 = clocksource_acpi_pm.read(&clocksource_acpi_pm);
+			if (value2 == value1)
+				continue;
+			if (value2 > value1)
+				break;
+			if ((value2 < value1) && ((value2) < 0xFFF))
+				break;
+			pr_info("PM-Timer had inconsistent results: %#llx, %#llx - aborting.\n",
+				value1, value2);
+			pmtmr_ioport = 0;
+			return -EINVAL;
+		}
+		if (i == ACPI_PM_READ_CHECKS) {
+			pr_info("PM-Timer failed consistency check  (%#llx) - aborting.\n",
+				value1);
+			pmtmr_ioport = 0;
+			return -ENODEV;
+		}
+	}
+
+	if (verify_pmtmr_rate() != 0){
+		pmtmr_ioport = 0;
+		return -ENODEV;
+	}
+
+	return clocksource_register_hz(&clocksource_acpi_pm, PMTMR_TICKS_PER_SEC);
+}
+
+/* We use fs_initcall because we want the PCI fixups to have run
+ * but we still need to load before device_initcall
+ */
+fs_initcall(init_acpi_pm_clocksource);
+
+/*
+ * Allow an override of the IOPort. Stupid BIOSes do not tell us about
+ * the PMTimer, but we might know where it is.
+ */
+static int __init parse_pmtmr(char *arg)
+{
+	unsigned int base;
+	int ret;
+
+	ret = kstrtouint(arg, 16, &base);
+	if (ret) {
+		pr_warn("PMTMR: invalid 'pmtmr=' value: '%s'\n", arg);
+		return 1;
+	}
+
+	pr_info("PMTMR IOPort override: 0x%04x -> 0x%04x\n", pmtmr_ioport,
+		base);
+	pmtmr_ioport = base;
+
+	return 1;
+}
+__setup("pmtmr=", parse_pmtmr);