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, 301 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c
new file mode 100644
index 000000000..ad41aaf8a
--- /dev/null
+++ b/drivers/rtc/rtc-opal.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * IBM OPAL RTC driver
+ * Copyright (C) 2014 IBM
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define DRVNAME		"rtc-opal"
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/bcd.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+	tm->tm_year = ((bcd2bin(y_m_d >> 24) * 100) +
+		       bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+	tm->tm_mon  = bcd2bin((y_m_d >> 8) & 0xff) - 1;
+	tm->tm_mday = bcd2bin(y_m_d & 0xff);
+	tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff);
+	tm->tm_min  = bcd2bin((h_m_s_ms >> 48) & 0xff);
+	tm->tm_sec  = bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+	tm->tm_wday = -1;
+}
+
+static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms)
+{
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+	*y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+	*y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+	*h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+}
+
+static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	s64 rc = OPAL_BUSY;
+	int retries = 10;
+	u32 y_m_d;
+	u64 h_m_s_ms;
+	__be32 __y_m_d;
+	__be64 __h_m_s_ms;
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
+			opal_poll_events(NULL);
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
+	}
+
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
+	opal_to_tm(y_m_d, h_m_s_ms, tm);
+
+	return 0;
+}
+
+static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm)
+{
+	s64 rc = OPAL_BUSY;
+	int retries = 10;
+	u32 y_m_d = 0;
+	u64 h_m_s_ms = 0;
+
+	tm_to_opal(tm, &y_m_d, &h_m_s_ms);
+
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_rtc_write(y_m_d, h_m_s_ms);
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
+			opal_poll_events(NULL);
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
+		} else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) {
+			if (retries--) {
+				msleep(10); /* Wait 10ms before retry */
+				rc = OPAL_BUSY; /* go around again */
+			}
+		}
+	}
+
+	return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
+
+/*
+ * TPO	Timed Power-On
+ *
+ * TPO get/set OPAL calls care about the hour and min and to make it consistent
+ * with the rtc utility time conversion functions, we use the 'u64' to store
+ * its value and perform bit shift by 32 before use..
+ */
+static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	__be32 __y_m_d, __h_m;
+	struct opal_msg msg;
+	int rc, token;
+	u64 h_m_s_ms;
+	u32 y_m_d;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	rc = opal_tpo_read(token, &__y_m_d, &__h_m);
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_get_async_rc(msg);
+	if (rc != OPAL_SUCCESS) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	y_m_d = be32_to_cpu(__y_m_d);
+	h_m_s_ms = ((u64)be32_to_cpu(__h_m) << 32);
+
+	/* check if no alarm is set */
+	if (y_m_d == 0 && h_m_s_ms == 0) {
+		pr_debug("No alarm is set\n");
+		rc = -ENOENT;
+		goto exit;
+	} else {
+		pr_debug("Alarm set to %x %llx\n", y_m_d, h_m_s_ms);
+	}
+
+	opal_to_tm(y_m_d, h_m_s_ms, &alarm->time);
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+/* Set Timed Power-On */
+static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm)
+{
+	u64 h_m_s_ms = 0;
+	struct opal_msg msg;
+	u32 y_m_d = 0;
+	int token, rc;
+
+	/* if alarm is enabled */
+	if (alarm->enabled) {
+		tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms);
+		pr_debug("Alarm set to %x %llx\n", y_m_d, h_m_s_ms);
+
+	} else {
+		pr_debug("Alarm getting disabled\n");
+	}
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			pr_err("Failed to get the async token\n");
+
+		return token;
+	}
+
+	/* TPO, we care about hour and minute */
+	rc = opal_tpo_write(token, y_m_d,
+			    (u32)((h_m_s_ms >> 32) & 0xffff0000));
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	if (rc) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = opal_get_async_rc(msg);
+	if (rc != OPAL_SUCCESS)
+		rc = -EIO;
+
+exit:
+	opal_async_release_token(token);
+	return rc;
+}
+
+static int opal_tpo_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct rtc_wkalrm alarm = { .enabled = 0 };
+
+	/*
+	 * TPO is automatically enabled when opal_set_tpo_time() is called with
+	 * non-zero rtc-time. We only handle disable case which needs to be
+	 * explicitly told to opal.
+	 */
+	return enabled ? 0 : opal_set_tpo_time(dev, &alarm);
+}
+
+static const struct rtc_class_ops opal_rtc_ops = {
+	.read_time	= opal_get_rtc_time,
+	.set_time	= opal_set_rtc_time,
+	.read_alarm	= opal_get_tpo_time,
+	.set_alarm	= opal_set_tpo_time,
+	.alarm_irq_enable = opal_tpo_alarm_irq_enable,
+};
+
+static int opal_rtc_probe(struct platform_device *pdev)
+{
+	struct rtc_device *rtc;
+
+	rtc = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	if (pdev->dev.of_node &&
+	    (of_property_read_bool(pdev->dev.of_node, "wakeup-source") ||
+	     of_property_read_bool(pdev->dev.of_node, "has-tpo")/* legacy */))
+		device_set_wakeup_capable(&pdev->dev, true);
+	else
+		clear_bit(RTC_FEATURE_ALARM, rtc->features);
+
+	rtc->ops = &opal_rtc_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_0000;
+	rtc->range_max = RTC_TIMESTAMP_END_9999;
+	clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features);
+
+	return devm_rtc_register_device(rtc);
+}
+
+static const struct of_device_id opal_rtc_match[] = {
+	{
+		.compatible	= "ibm,opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, opal_rtc_match);
+
+static const struct platform_device_id opal_rtc_driver_ids[] = {
+	{
+		.name		= "opal-rtc",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, opal_rtc_driver_ids);
+
+static struct platform_driver opal_rtc_driver = {
+	.probe		= opal_rtc_probe,
+	.id_table	= opal_rtc_driver_ids,
+	.driver		= {
+		.name		= DRVNAME,
+		.of_match_table	= opal_rtc_match,
+	},
+};
+
+static int __init opal_rtc_init(void)
+{
+	if (!firmware_has_feature(FW_FEATURE_OPAL))
+		return -ENODEV;
+
+	return platform_driver_register(&opal_rtc_driver);
+}
+
+static void __exit opal_rtc_exit(void)
+{
+	platform_driver_unregister(&opal_rtc_driver);
+}
+
+MODULE_AUTHOR("Neelesh Gupta <neelegup@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("IBM OPAL RTC driver");
+MODULE_LICENSE("GPL");
+
+module_init(opal_rtc_init);
+module_exit(opal_rtc_exit);