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
trace_mmiotrace.c
/*
* Memory mapped I/O tracing
*
* Copyright (C) 2008 Pekka Paalanen <pq@iki.fi>
*/
#define DEBUG 1
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/atomic.h>
#include "trace.h"
#include "trace_output.h"
struct header_iter {
struct pci_dev *dev;
};
static struct trace_array *mmio_trace_array;
static bool overrun_detected;
static unsigned long prev_overruns;
static atomic_t dropped_count;
static void mmio_reset_data(struct trace_array *tr)
{
overrun_detected = false;
prev_overruns = 0;
tracing_reset_online_cpus(tr);
}
static int mmio_trace_init(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
mmio_trace_array = tr;
mmio_reset_data(tr);
enable_mmiotrace();
return 0;
}
static void mmio_trace_reset(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
disable_mmiotrace();
mmio_reset_data(tr);
mmio_trace_array = NULL;
}
static void mmio_trace_start(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
mmio_reset_data(tr);
}
static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
{
int ret = 0;
int i;
resource_size_t start, end;
const struct pci_driver *drv = pci_dev_driver(dev);
/* XXX: incomplete checks for trace_seq_printf() return value */
ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
dev->bus->number, dev->devfn,
dev->vendor, dev->device, dev->irq);
/*
* XXX: is pci_resource_to_user() appropriate, since we are
* supposed to interpret the __ioremap() phys_addr argument based on
* these printed values?
*/
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
ret += trace_seq_printf(s, " %llx",
(unsigned long long)(start |
(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
}
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
ret += trace_seq_printf(s, " %llx",
dev->resource[i].start < dev->resource[i].end ?
(unsigned long long)(end - start) + 1 : 0);
}
if (drv)
ret += trace_seq_printf(s, " %s\n", drv->name);
else
ret += trace_seq_printf(s, " \n");
return ret;
}
static void destroy_header_iter(struct header_iter *hiter)
{
if (!hiter)
return;
pci_dev_put(hiter->dev);
kfree(hiter);
}
static void mmio_pipe_open(struct trace_iterator *iter)
{
struct header_iter *hiter;
struct trace_seq *s = &iter->seq;
trace_seq_printf(s, "VERSION 20070824\n");
hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
if (!hiter)
return;
hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL);
iter->private = hiter;
}
/* XXX: This is not called when the pipe is closed! */
static void mmio_close(struct trace_iterator *iter)
{
struct header_iter *hiter = iter->private;
destroy_header_iter(hiter);
iter->private = NULL;
}
static unsigned long count_overruns(struct trace_iterator *iter)
{
unsigned long cnt = atomic_xchg(&dropped_count, 0);
unsigned long over = ring_buffer_overruns(iter->tr->buffer);
if (over > prev_overruns)
cnt += over - prev_overruns;
prev_overruns = over;
return cnt;
}
static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
char __user *ubuf, size_t cnt, loff_t *ppos)
{
ssize_t ret;
struct header_iter *hiter = iter->private;
struct trace_seq *s = &iter->seq;
unsigned long n;
n = count_overruns(iter);
if (n) {
/* XXX: This is later than where events were lost. */
trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
if (!overrun_detected)
pr_warning("mmiotrace has lost events.\n");
overrun_detected = true;
goto print_out;
}
if (!hiter)
return 0;
mmio_print_pcidev(s, hiter->dev);
hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev);
if (!hiter->dev) {
destroy_header_iter(hiter);
iter->private = NULL;
}
print_out:
ret = trace_seq_to_user(s, ubuf, cnt);
return (ret == -EBUSY) ? 0 : ret;
}
static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
{
struct trace_entry *entry = iter->ent;
struct trace_mmiotrace_rw *field;
struct mmiotrace_rw *rw;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret = 1;
trace_assign_type(field, entry);
rw = &field->rw;
switch (rw->opcode) {
case MMIO_READ:
ret = trace_seq_printf(s,
"R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
rw->width, secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
rw->value, rw->pc, 0);
break;
case MMIO_WRITE:
ret = trace_seq_printf(s,
"W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
rw->width, secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
rw->value, rw->pc, 0);
break;
case MMIO_UNKNOWN_OP:
ret = trace_seq_printf(s,
"UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx,"
"%02lx 0x%lx %d\n",
secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
(rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff,
(rw->value >> 0) & 0xff, rw->pc, 0);
break;
default:
ret = trace_seq_printf(s, "rw what?\n");
break;
}
if (ret)
return TRACE_TYPE_HANDLED;
return TRACE_TYPE_PARTIAL_LINE;
}
static enum print_line_t mmio_print_map(struct trace_iterator *iter)
{
struct trace_entry *entry = iter->ent;
struct trace_mmiotrace_map *field;
struct mmiotrace_map *m;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret;
trace_assign_type(field, entry);
m = &field->map;
switch (m->opcode) {
case MMIO_PROBE:
ret = trace_seq_printf(s,
"MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n",
secs, usec_rem, m->map_id,
(unsigned long long)m->phys, m->virt, m->len,
0UL, 0);
break;
case MMIO_UNPROBE:
ret = trace_seq_printf(s,
"UNMAP %u.%06lu %d 0x%lx %d\n",
secs, usec_rem, m->map_id, 0UL, 0);
break;
default:
ret = trace_seq_printf(s, "map what?\n");
break;
}
if (ret)
return TRACE_TYPE_HANDLED;
return TRACE_TYPE_PARTIAL_LINE;
}
static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
{
struct trace_entry *entry = iter->ent;
struct print_entry *print = (struct print_entry *)entry;
const char *msg = print->buf;
struct trace_seq *s = &iter->seq;
unsigned long long t = ns2usecs(iter->ts);
unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned secs = (unsigned long)t;
int ret;
/* The trailing newline must be in the message. */
ret = trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
static enum print_line_t mmio_print_line(struct trace_iterator *iter)
{
switch (iter->ent->type) {
case TRACE_MMIO_RW:
return mmio_print_rw(iter);
case TRACE_MMIO_MAP:
return mmio_print_map(iter);
case TRACE_PRINT:
return mmio_print_mark(iter);
default:
return TRACE_TYPE_HANDLED; /* ignore unknown entries */
}
}
static struct tracer mmio_tracer __read_mostly =
{
.name = "mmiotrace",
.init = mmio_trace_init,
.reset = mmio_trace_reset,
.start = mmio_trace_start,
.pipe_open = mmio_pipe_open,
.close = mmio_close,
.read = mmio_read,
.print_line = mmio_print_line,
};
__init static int init_mmio_trace(void)
{
return register_tracer(&mmio_tracer);
}
device_initcall(init_mmio_trace);
static void __trace_mmiotrace_rw(struct trace_array *tr,
struct trace_array_cpu *data,
struct mmiotrace_rw *rw)
{
struct ftrace_event_call *call = &event_mmiotrace_rw;
struct ring_buffer *buffer = tr->buffer;
struct ring_buffer_event *event;
struct trace_mmiotrace_rw *entry;
int pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
sizeof(*entry), 0, pc);
if (!event) {
atomic_inc(&dropped_count);
return;
}
entry = ring_buffer_event_data(event);
entry->rw = *rw;
if (!filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, 0, pc);
}
void mmio_trace_rw(struct mmiotrace_rw *rw)
{
struct trace_array *tr = mmio_trace_array;
struct trace_array_cpu *data = tr->data[smp_processor_id()];
__trace_mmiotrace_rw(tr, data, rw);
}
static void __trace_mmiotrace_map(struct trace_array *tr,
struct trace_array_cpu *data,
struct mmiotrace_map *map)
{
struct ftrace_event_call *call = &event_mmiotrace_map;
struct ring_buffer *buffer = tr->buffer;
struct ring_buffer_event *event;
struct trace_mmiotrace_map *entry;
int pc = preempt_count();
event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
sizeof(*entry), 0, pc);
if (!event) {
atomic_inc(&dropped_count);
return;
}
entry = ring_buffer_event_data(event);
entry->map = *map;
if (!filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, 0, pc);
}
void mmio_trace_mapping(struct mmiotrace_map *map)
{
struct trace_array *tr = mmio_trace_array;
struct trace_array_cpu *data;
preempt_disable();
data = tr->data[smp_processor_id()];
__trace_mmiotrace_map(tr, data, map);
preempt_enable();
}
int mmio_trace_printk(const char *fmt, va_list args)
{
return trace_vprintk(0, fmt, args);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...