/*
* Intel MIC Platform Software Stack (MPSS)
*
* Copyright(c) 2013 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2, as
* published by the Free Software Foundation.
*
* 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.
*
* The full GNU General Public License is included in this distribution in
* the file called "COPYING".
*
* Intel MIC User Space Tools.
*/
#include "mpssd.h"
#define PAGE_SIZE 4096
char *
readsysfs(char *dir, char *entry)
{
char filename[PATH_MAX];
char value[PAGE_SIZE];
char *string = NULL;
int fd;
int len;
if (dir == NULL)
snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
else
snprintf(filename, PATH_MAX,
"%s/%s/%s", MICSYSFSDIR, dir, entry);
fd = open(filename, O_RDONLY);
if (fd < 0) {
mpsslog("Failed to open sysfs entry '%s': %s\n",
filename, strerror(errno));
return NULL;
}
len = read(fd, value, sizeof(value));
if (len < 0) {
mpsslog("Failed to read sysfs entry '%s': %s\n",
filename, strerror(errno));
goto readsys_ret;
}
if (len == 0)
goto readsys_ret;
value[len - 1] = '\0';
string = malloc(strlen(value) + 1);
if (string)
strcpy(string, value);
readsys_ret:
close(fd);
return string;
}
int
setsysfs(char *dir, char *entry, char *value)
{
char filename[PATH_MAX];
char *oldvalue;
int fd, ret = 0;
if (dir == NULL)
snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
else
snprintf(filename, PATH_MAX, "%s/%s/%s",
MICSYSFSDIR, dir, entry);
oldvalue = readsysfs(dir, entry);
fd = open(filename, O_RDWR);
if (fd < 0) {
ret = errno;
mpsslog("Failed to open sysfs entry '%s': %s\n",
filename, strerror(errno));
goto done;
}
if (!oldvalue || strcmp(value, oldvalue)) {
if (write(fd, value, strlen(value)) < 0) {
ret = errno;
mpsslog("Failed to write new sysfs entry '%s': %s\n",
filename, strerror(errno));
}
}
close(fd);
done:
if (oldvalue)
free(oldvalue);
return ret;
}
f/net/openvswitch/flow_table.h?h=nds-private-remove&id=966d2b04e070bc040319aaebfec09e0144dc3341'>diff
|
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().
This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:
__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0
Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.
The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.
Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Cc: stable@vger.kernel.org # v3.18+