Revision efad4e475c312456edb3c789d0996d12ed744c13 authored by Michal Hocko on 01 February 2019, 22:20:34 UTC, committed by Linus Torvalds on 01 February 2019, 23:46:23 UTC
Patch series "mm, memory_hotplug: fix uninitialized pages fallouts", v2. Mikhail Zaslonko has posted fixes for the two bugs quite some time ago [1]. I have pushed back on those fixes because I believed that it is much better to plug the problem at the initialization time rather than play whack-a-mole all over the hotplug code and find all the places which expect the full memory section to be initialized. We have ended up with commit 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") merged and cause a regression [2][3]. The reason is that there might be memory layouts when two NUMA nodes share the same memory section so the merged fix is simply incorrect. In order to plug this hole we really have to be zone range aware in those handlers. I have split up the original patch into two. One is unchanged (patch 2) and I took a different approach for `removable' crash. [1] http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com [2] https://bugzilla.redhat.com/show_bug.cgi?id=1666948 [3] http://lkml.kernel.org/r/20190125163938.GA20411@dhcp22.suse.cz This patch (of 2): Mikhail has reported the following VM_BUG_ON triggered when reading sysfs removable state of a memory block: page:000003d08300c000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: is_mem_section_removable+0xb4/0x190 show_mem_removable+0x9a/0xd8 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: is_mem_section_removable+0xb4/0x190 Kernel panic - not syncing: Fatal exception: panic_on_oops The reason is that the memory block spans the zone boundary and we are stumbling over an unitialized struct page. Fix this by enforcing zone range in is_mem_section_removable so that we never run away from a zone. Link: http://lkml.kernel.org/r/20190128144506.15603-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Mikhail Zaslonko <zaslonko@linux.ibm.com> Debugged-by: Mikhail Zaslonko <zaslonko@linux.ibm.com> Tested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 9bcdeb5
tick-oneshot.c
// SPDX-License-Identifier: GPL-2.0
/*
* This file contains functions which manage high resolution tick
* related events.
*
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
*/
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include "tick-internal.h"
/**
* tick_program_event
*/
int tick_program_event(ktime_t expires, int force)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
if (unlikely(expires == KTIME_MAX)) {
/*
* We don't need the clock event device any more, stop it.
*/
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED);
dev->next_event = KTIME_MAX;
return 0;
}
if (unlikely(clockevent_state_oneshot_stopped(dev))) {
/*
* We need the clock event again, configure it in ONESHOT mode
* before using it.
*/
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
}
return clockevents_program_event(dev, expires, force);
}
/**
* tick_resume_onshot - resume oneshot mode
*/
void tick_resume_oneshot(void)
{
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
clockevents_program_event(dev, ktime_get(), true);
}
/**
* tick_setup_oneshot - setup the event device for oneshot mode (hres or nohz)
*/
void tick_setup_oneshot(struct clock_event_device *newdev,
void (*handler)(struct clock_event_device *),
ktime_t next_event)
{
newdev->event_handler = handler;
clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT);
clockevents_program_event(newdev, next_event, true);
}
/**
* tick_switch_to_oneshot - switch to oneshot mode
*/
int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
{
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
struct clock_event_device *dev = td->evtdev;
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
!tick_device_is_functional(dev)) {
pr_info("Clockevents: could not switch to one-shot mode:");
if (!dev) {
pr_cont(" no tick device\n");
} else {
if (!tick_device_is_functional(dev))
pr_cont(" %s is not functional.\n", dev->name);
else
pr_cont(" %s does not support one-shot mode.\n",
dev->name);
}
return -EINVAL;
}
td->mode = TICKDEV_MODE_ONESHOT;
dev->event_handler = handler;
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
tick_broadcast_switch_to_oneshot();
return 0;
}
/**
* tick_check_oneshot_mode - check whether the system is in oneshot mode
*
* returns 1 when either nohz or highres are enabled. otherwise 0.
*/
int tick_oneshot_mode_active(void)
{
unsigned long flags;
int ret;
local_irq_save(flags);
ret = __this_cpu_read(tick_cpu_device.mode) == TICKDEV_MODE_ONESHOT;
local_irq_restore(flags);
return ret;
}
#ifdef CONFIG_HIGH_RES_TIMERS
/**
* tick_init_highres - switch to high resolution mode
*
* Called with interrupts disabled.
*/
int tick_init_highres(void)
{
return tick_switch_to_oneshot(hrtimer_interrupt);
}
#endif
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...