Revision f9228b204f789493117e458d2fefae937edb7272 authored by Russ Anderson on 22 March 2013, 22:04:43 UTC, committed by Linus Torvalds on 22 March 2013, 23:41:20 UTC
Booting with 32 TBytes memory hits BUG at mm/page_alloc.c:552! (output
below).

The key hint is "page 4294967296 outside zone".
4294967296 = 0x100000000 (bit 32 is set).

The problem is in include/linux/mmzone.h:

  530 static inline unsigned zone_end_pfn(const struct zone *zone)
  531 {
  532         return zone->zone_start_pfn + zone->spanned_pages;
  533 }

zone_end_pfn is "unsigned" (32 bits).  Changing it to "unsigned long"
(64 bits) fixes the problem.

zone_end_pfn() was added recently in commit 108bcc96ef70 ("mm: add & use
zone_end_pfn() and zone_spans_pfn()")

Output from the failure.

  No AGP bridge found
  page 4294967296 outside zone [ 4294967296 - 4327469056 ]
  ------------[ cut here ]------------
  kernel BUG at mm/page_alloc.c:552!
  invalid opcode: 0000 [#1] SMP
  Modules linked in:
  CPU 0
  Pid: 0, comm: swapper Not tainted 3.9.0-rc2.dtp+ #10
  RIP: free_one_page+0x382/0x430
  Process swapper (pid: 0, threadinfo ffffffff81942000, task ffffffff81955420)
  Call Trace:
    __free_pages_ok+0x96/0xb0
    __free_pages+0x25/0x50
    __free_pages_bootmem+0x8a/0x8c
    __free_memory_core+0xea/0x131
    free_low_memory_core_early+0x4a/0x98
    free_all_bootmem+0x45/0x47
    mem_init+0x7b/0x14c
    start_kernel+0x216/0x433
    x86_64_start_reservations+0x2a/0x2c
    x86_64_start_kernel+0x144/0x153
  Code: 89 f1 ba 01 00 00 00 31 f6 d3 e2 4c 89 ef e8 66 a4 01 00 e9 2c fe ff ff 0f 0b eb fe 0f 0b 66 66 2e 0f 1f 84 00 00 00 00 00 eb f3 <0f> 0b eb fe 0f 0b 0f 1f 84 00 00 00 00 00 eb f6 0f 0b eb fe 49

Signed-off-by: Russ Anderson <rja@sgi.com>
Reported-by: George Beshers <gbeshers@sgi.com>
Acked-by: Hedi Berriche <hedi@sgi.com>
Cc: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 2ca067e
Raw File
task_work.c
#include <linux/spinlock.h>
#include <linux/task_work.h>
#include <linux/tracehook.h>

static struct callback_head work_exited; /* all we need is ->next == NULL */

int
task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
{
	struct callback_head *head;

	do {
		head = ACCESS_ONCE(task->task_works);
		if (unlikely(head == &work_exited))
			return -ESRCH;
		work->next = head;
	} while (cmpxchg(&task->task_works, head, work) != head);

	if (notify)
		set_notify_resume(task);
	return 0;
}

struct callback_head *
task_work_cancel(struct task_struct *task, task_work_func_t func)
{
	struct callback_head **pprev = &task->task_works;
	struct callback_head *work = NULL;
	unsigned long flags;
	/*
	 * If cmpxchg() fails we continue without updating pprev.
	 * Either we raced with task_work_add() which added the
	 * new entry before this work, we will find it again. Or
	 * we raced with task_work_run(), *pprev == NULL/exited.
	 */
	raw_spin_lock_irqsave(&task->pi_lock, flags);
	while ((work = ACCESS_ONCE(*pprev))) {
		read_barrier_depends();
		if (work->func != func)
			pprev = &work->next;
		else if (cmpxchg(pprev, work, work->next) == work)
			break;
	}
	raw_spin_unlock_irqrestore(&task->pi_lock, flags);

	return work;
}

void task_work_run(void)
{
	struct task_struct *task = current;
	struct callback_head *work, *head, *next;

	for (;;) {
		/*
		 * work->func() can do task_work_add(), do not set
		 * work_exited unless the list is empty.
		 */
		do {
			work = ACCESS_ONCE(task->task_works);
			head = !work && (task->flags & PF_EXITING) ?
				&work_exited : NULL;
		} while (cmpxchg(&task->task_works, work, head) != work);

		if (!work)
			break;
		/*
		 * Synchronize with task_work_cancel(). It can't remove
		 * the first entry == work, cmpxchg(task_works) should
		 * fail, but it can play with *work and other entries.
		 */
		raw_spin_unlock_wait(&task->pi_lock);
		smp_mb();

		/* Reverse the list to run the works in fifo order */
		head = NULL;
		do {
			next = work->next;
			work->next = head;
			head = work;
			work = next;
		} while (work);

		work = head;
		do {
			next = work->next;
			work->func(work);
			work = next;
			cond_resched();
		} while (work);
	}
}
back to top