linux/arch/powerpc/platforms/pseries/hvCall_inst.c
Li Zhong e4f387d8db powerpc: Fix unpaired probe_hcall_entry and probe_hcall_exit
Unpaired calling of probe_hcall_entry and probe_hcall_exit might happen
as following, which could cause incorrect preempt count.

__trace_hcall_entry => trace_hcall_entry -> probe_hcall_entry =>
get_cpu_var => preempt_disable

__trace_hcall_exit => trace_hcall_exit -> probe_hcall_exit =>
put_cpu_var => preempt_enable

where:
A => B and A -> B means A calls B, but
=> means A will call B through function name, and B will definitely be
called.
-> means A will call B through function pointer, so B might not be
called if the function pointer is not set.

So error happens when only one of probe_hcall_entry and probe_hcall_exit
get called during a hcall.

This patch tries to move the preempt count operations from
probe_hcall_entry and probe_hcall_exit to its callers.

Reported-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: stable@kernel.org [v2.6.32+]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-01-03 12:09:27 +11:00

166 lines
3.9 KiB
C

/*
* Copyright (C) 2006 Mike Kravetz IBM Corporation
*
* Hypervisor Call Instrumentation
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/cpumask.h>
#include <asm/hvcall.h>
#include <asm/firmware.h>
#include <asm/cputable.h>
#include <asm/trace.h>
DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
/*
* Routines for displaying the statistics in debugfs
*/
static void *hc_start(struct seq_file *m, loff_t *pos)
{
if ((int)*pos < (HCALL_STAT_ARRAY_SIZE-1))
return (void *)(unsigned long)(*pos + 1);
return NULL;
}
static void *hc_next(struct seq_file *m, void *p, loff_t * pos)
{
++*pos;
return hc_start(m, pos);
}
static void hc_stop(struct seq_file *m, void *p)
{
}
static int hc_show(struct seq_file *m, void *p)
{
unsigned long h_num = (unsigned long)p;
struct hcall_stats *hs = m->private;
if (hs[h_num].num_calls) {
if (cpu_has_feature(CPU_FTR_PURR))
seq_printf(m, "%lu %lu %lu %lu\n", h_num<<2,
hs[h_num].num_calls,
hs[h_num].tb_total,
hs[h_num].purr_total);
else
seq_printf(m, "%lu %lu %lu\n", h_num<<2,
hs[h_num].num_calls,
hs[h_num].tb_total);
}
return 0;
}
static const struct seq_operations hcall_inst_seq_ops = {
.start = hc_start,
.next = hc_next,
.stop = hc_stop,
.show = hc_show
};
static int hcall_inst_seq_open(struct inode *inode, struct file *file)
{
int rc;
struct seq_file *seq;
rc = seq_open(file, &hcall_inst_seq_ops);
seq = file->private_data;
seq->private = file->f_path.dentry->d_inode->i_private;
return rc;
}
static const struct file_operations hcall_inst_seq_fops = {
.open = hcall_inst_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#define HCALL_ROOT_DIR "hcall_inst"
#define CPU_NAME_BUF_SIZE 32
static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long *args)
{
struct hcall_stats *h;
if (opcode > MAX_HCALL_OPCODE)
return;
h = &__get_cpu_var(hcall_stats)[opcode / 4];
h->tb_start = mftb();
h->purr_start = mfspr(SPRN_PURR);
}
static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long retval,
unsigned long *retbuf)
{
struct hcall_stats *h;
if (opcode > MAX_HCALL_OPCODE)
return;
h = &__get_cpu_var(hcall_stats)[opcode / 4];
h->num_calls++;
h->tb_total += mftb() - h->tb_start;
h->purr_total += mfspr(SPRN_PURR) - h->purr_start;
}
static int __init hcall_inst_init(void)
{
struct dentry *hcall_root;
struct dentry *hcall_file;
char cpu_name_buf[CPU_NAME_BUF_SIZE];
int cpu;
if (!firmware_has_feature(FW_FEATURE_LPAR))
return 0;
if (register_trace_hcall_entry(probe_hcall_entry, NULL))
return -EINVAL;
if (register_trace_hcall_exit(probe_hcall_exit, NULL)) {
unregister_trace_hcall_entry(probe_hcall_entry, NULL);
return -EINVAL;
}
hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL);
if (!hcall_root)
return -ENOMEM;
for_each_possible_cpu(cpu) {
snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu);
hcall_file = debugfs_create_file(cpu_name_buf, S_IRUGO,
hcall_root,
per_cpu(hcall_stats, cpu),
&hcall_inst_seq_fops);
if (!hcall_file)
return -ENOMEM;
}
return 0;
}
__initcall(hcall_inst_init);