linux/kernel/time/timekeeping_debug.c

83 lines
2.1 KiB
C
Raw Normal View History

/*
* debugfs file to track time spent in suspend
*
* Copyright (c) 2011, Google, Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/debugfs.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/seq_file.h>
#include <linux/suspend.h>
#include <linux/time.h>
#include "timekeeping_internal.h"
timekeeping: Cap array access in timekeeping_debug It was reported that hibernation could fail on the 2nd attempt, where the system hangs at hibernate() -> syscore_resume() -> i8237A_resume() -> claim_dma_lock(), because the lock has already been taken. However there is actually no other process would like to grab this lock on that problematic platform. Further investigation showed that the problem is triggered by setting /sys/power/pm_trace to 1 before the 1st hibernation. Since once pm_trace is enabled, the rtc becomes unmeaningful after suspend, and meanwhile some BIOSes would like to adjust the 'invalid' RTC (e.g, smaller than 1970) to the release date of that motherboard during POST stage, thus after resumed, it may seem that the system had a significant long sleep time which is a completely meaningless value. Then in timekeeping_resume -> tk_debug_account_sleep_time, if the bit31 of the sleep time happened to be set to 1, fls() returns 32 and we add 1 to sleep_time_bin[32], which causes an out of bounds array access and therefor memory being overwritten. As depicted by System.map: 0xffffffff81c9d080 b sleep_time_bin 0xffffffff81c9d100 B dma_spin_lock the dma_spin_lock.val is set to 1, which caused this problem. This patch adds a sanity check in tk_debug_account_sleep_time() to ensure we don't index past the sleep_time_bin array. [jstultz: Problem diagnosed and original patch by Chen Yu, I've solved the issue slightly differently, but borrowed his excelent explanation of the issue here.] Fixes: 5c83545f24ab "power: Add option to log time spent in suspend" Reported-by: Janek Kozicki <cosurgi@gmail.com> Reported-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: linux-pm@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xunlei Pang <xpang@redhat.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: stable <stable@vger.kernel.org> Cc: Zhang Rui <rui.zhang@intel.com> Link: http://lkml.kernel.org/r/1471993702-29148-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-08-23 23:08:22 +00:00
#define NUM_BINS 32
static unsigned int sleep_time_bin[NUM_BINS] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
{
unsigned int bin;
seq_puts(s, " time (secs) count\n");
seq_puts(s, "------------------------------\n");
for (bin = 0; bin < 32; bin++) {
if (sleep_time_bin[bin] == 0)
continue;
seq_printf(s, "%10u - %-10u %4u\n",
bin ? 1 << (bin - 1) : 0, 1 << bin,
sleep_time_bin[bin]);
}
return 0;
}
static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
{
return single_open(file, tk_debug_show_sleep_time, NULL);
}
static const struct file_operations tk_debug_sleep_time_fops = {
.open = tk_debug_sleep_time_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init tk_debug_sleep_time_init(void)
{
struct dentry *d;
d = debugfs_create_file("sleep_time", 0444, NULL, NULL,
&tk_debug_sleep_time_fops);
if (!d) {
pr_err("Failed to create sleep_time debug file\n");
return -ENOMEM;
}
return 0;
}
late_initcall(tk_debug_sleep_time_init);
void tk_debug_account_sleep_time(const struct timespec64 *t)
{
timekeeping: Cap array access in timekeeping_debug It was reported that hibernation could fail on the 2nd attempt, where the system hangs at hibernate() -> syscore_resume() -> i8237A_resume() -> claim_dma_lock(), because the lock has already been taken. However there is actually no other process would like to grab this lock on that problematic platform. Further investigation showed that the problem is triggered by setting /sys/power/pm_trace to 1 before the 1st hibernation. Since once pm_trace is enabled, the rtc becomes unmeaningful after suspend, and meanwhile some BIOSes would like to adjust the 'invalid' RTC (e.g, smaller than 1970) to the release date of that motherboard during POST stage, thus after resumed, it may seem that the system had a significant long sleep time which is a completely meaningless value. Then in timekeeping_resume -> tk_debug_account_sleep_time, if the bit31 of the sleep time happened to be set to 1, fls() returns 32 and we add 1 to sleep_time_bin[32], which causes an out of bounds array access and therefor memory being overwritten. As depicted by System.map: 0xffffffff81c9d080 b sleep_time_bin 0xffffffff81c9d100 B dma_spin_lock the dma_spin_lock.val is set to 1, which caused this problem. This patch adds a sanity check in tk_debug_account_sleep_time() to ensure we don't index past the sleep_time_bin array. [jstultz: Problem diagnosed and original patch by Chen Yu, I've solved the issue slightly differently, but borrowed his excelent explanation of the issue here.] Fixes: 5c83545f24ab "power: Add option to log time spent in suspend" Reported-by: Janek Kozicki <cosurgi@gmail.com> Reported-by: Chen Yu <yu.c.chen@intel.com> Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: linux-pm@vger.kernel.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xunlei Pang <xpang@redhat.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: stable <stable@vger.kernel.org> Cc: Zhang Rui <rui.zhang@intel.com> Link: http://lkml.kernel.org/r/1471993702-29148-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-08-23 23:08:22 +00:00
/* Cap bin index so we don't overflow the array */
int bin = min(fls(t->tv_sec), NUM_BINS-1);
sleep_time_bin[bin]++;
pm_deferred_pr_dbg("Timekeeping suspended for %lld.%03lu seconds\n",
(s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC);
}