7e40f2ab0a
We broke the the alignment of members of taskstats to the 8 byte boundary
with the CSA patches. In the current kernel, the taskstats structure is
not suitable for use by 32 bit applications in a 64 bit kernel.
On x86_64
Offsets of taskstats' members (64 bit kernel, 64 bit application)
@taskstats'offsetof[@taskstats'indices] = (
0, # version
4, # ac_exitcode
8, # ac_flag
9, # ac_nice
16, # cpu_count
24, # cpu_delay_total
32, # blkio_count
40, # blkio_delay_total
48, # swapin_count
56, # swapin_delay_total
64, # cpu_run_real_total
72, # cpu_run_virtual_total
80, # ac_comm
112, # ac_sched
113, # ac_pad
116, # ac_uid
120, # ac_gid
124, # ac_pid
128, # ac_ppid
132, # ac_btime
136, # ac_etime
144, # ac_utime
152, # ac_stime
160, # ac_minflt
168, # ac_majflt
176, # coremem
184, # virtmem
192, # hiwater_rss
200, # hiwater_vm
208, # read_char
216, # write_char
224, # read_syscalls
232, # write_syscalls
240, # read_bytes
248, # write_bytes
256, # cancelled_write_bytes
);
Offsets of taskstats' members (64 bit kernel, 32 bit application)
@taskstats'offsetof[@taskstats'indices] = (
0, # version
4, # ac_exitcode
8, # ac_flag
9, # ac_nice
12, # cpu_count
20, # cpu_delay_total
28, # blkio_count
36, # blkio_delay_total
44, # swapin_count
52, # swapin_delay_total
60, # cpu_run_real_total
68, # cpu_run_virtual_total
76, # ac_comm
108, # ac_sched
109, # ac_pad
112, # ac_uid
116, # ac_gid
120, # ac_pid
124, # ac_ppid
128, # ac_btime
132, # ac_etime
140, # ac_utime
148, # ac_stime
156, # ac_minflt
164, # ac_majflt
172, # coremem
180, # virtmem
188, # hiwater_rss
196, # hiwater_vm
204, # read_char
212, # write_char
220, # read_syscalls
228, # write_syscalls
236, # read_bytes
244, # write_bytes
252, # cancelled_write_bytes
);
This is one way to solve the problem without re-arranging structure members
is to pack the structure. The patch adds an __attribute__((aligned(8))) to
the taskstats structure members so that 32 bit applications using taskstats
can work with a 64 bit kernel.
Using __attribute__((packed)) would break the 64 bit alignment of members.
The fix was tested on x86_64. After the fix, we got
Offsets of taskstats' members (64 bit kernel, 64 bit application)
@taskstats'offsetof[@taskstats'indices] = (
0, # version
4, # ac_exitcode
8, # ac_flag
9, # ac_nice
16, # cpu_count
24, # cpu_delay_total
32, # blkio_count
40, # blkio_delay_total
48, # swapin_count
56, # swapin_delay_total
64, # cpu_run_real_total
72, # cpu_run_virtual_total
80, # ac_comm
112, # ac_sched
113, # ac_pad
120, # ac_uid
124, # ac_gid
128, # ac_pid
132, # ac_ppid
136, # ac_btime
144, # ac_etime
152, # ac_utime
160, # ac_stime
168, # ac_minflt
176, # ac_majflt
184, # coremem
192, # virtmem
200, # hiwater_rss
208, # hiwater_vm
216, # read_char
224, # write_char
232, # read_syscalls
240, # write_syscalls
248, # read_bytes
256, # write_bytes
264, # cancelled_write_bytes
);
Offsets of taskstats' members (64 bit kernel, 32 bit application)
@taskstats'offsetof[@taskstats'indices] = (
0, # version
4, # ac_exitcode
8, # ac_flag
9, # ac_nice
16, # cpu_count
24, # cpu_delay_total
32, # blkio_count
40, # blkio_delay_total
48, # swapin_count
56, # swapin_delay_total
64, # cpu_run_real_total
72, # cpu_run_virtual_total
80, # ac_comm
112, # ac_sched
113, # ac_pad
120, # ac_uid
124, # ac_gid
128, # ac_pid
132, # ac_ppid
136, # ac_btime
144, # ac_etime
152, # ac_utime
160, # ac_stime
168, # ac_minflt
176, # ac_majflt
184, # coremem
192, # virtmem
200, # hiwater_rss
208, # hiwater_vm
216, # read_char
224, # write_char
232, # read_syscalls
240, # write_syscalls
248, # read_bytes
256, # write_bytes
264, # cancelled_write_bytes
);
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Cc: Shailabh Nagar <nagar@watson.ibm.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
198 lines
6.3 KiB
C
198 lines
6.3 KiB
C
/* taskstats.h - exporting per-task statistics
|
|
*
|
|
* Copyright (C) Shailabh Nagar, IBM Corp. 2006
|
|
* (C) Balbir Singh, IBM Corp. 2006
|
|
* (C) Jay Lan, SGI, 2006
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of version 2.1 of the GNU Lesser General Public License
|
|
* as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
*/
|
|
|
|
#ifndef _LINUX_TASKSTATS_H
|
|
#define _LINUX_TASKSTATS_H
|
|
|
|
/* Format for per-task data returned to userland when
|
|
* - a task exits
|
|
* - listener requests stats for a task
|
|
*
|
|
* The struct is versioned. Newer versions should only add fields to
|
|
* the bottom of the struct to maintain backward compatibility.
|
|
*
|
|
*
|
|
* To add new fields
|
|
* a) bump up TASKSTATS_VERSION
|
|
* b) add comment indicating new version number at end of struct
|
|
* c) add new fields after version comment; maintain 64-bit alignment
|
|
*/
|
|
|
|
|
|
#define TASKSTATS_VERSION 4
|
|
#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
|
|
* in linux/sched.h */
|
|
|
|
struct taskstats {
|
|
|
|
/* The version number of this struct. This field is always set to
|
|
* TAKSTATS_VERSION, which is defined in <linux/taskstats.h>.
|
|
* Each time the struct is changed, the value should be incremented.
|
|
*/
|
|
__u16 version;
|
|
__u32 ac_exitcode; /* Exit status */
|
|
|
|
/* The accounting flags of a task as defined in <linux/acct.h>
|
|
* Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG.
|
|
*/
|
|
__u8 ac_flag; /* Record flags */
|
|
__u8 ac_nice; /* task_nice */
|
|
|
|
/* Delay accounting fields start
|
|
*
|
|
* All values, until comment "Delay accounting fields end" are
|
|
* available only if delay accounting is enabled, even though the last
|
|
* few fields are not delays
|
|
*
|
|
* xxx_count is the number of delay values recorded
|
|
* xxx_delay_total is the corresponding cumulative delay in nanoseconds
|
|
*
|
|
* xxx_delay_total wraps around to zero on overflow
|
|
* xxx_count incremented regardless of overflow
|
|
*/
|
|
|
|
/* Delay waiting for cpu, while runnable
|
|
* count, delay_total NOT updated atomically
|
|
*/
|
|
__u64 cpu_count __attribute__((aligned(8)));
|
|
__u64 cpu_delay_total;
|
|
|
|
/* Following four fields atomically updated using task->delays->lock */
|
|
|
|
/* Delay waiting for synchronous block I/O to complete
|
|
* does not account for delays in I/O submission
|
|
*/
|
|
__u64 blkio_count;
|
|
__u64 blkio_delay_total;
|
|
|
|
/* Delay waiting for page fault I/O (swap in only) */
|
|
__u64 swapin_count;
|
|
__u64 swapin_delay_total;
|
|
|
|
/* cpu "wall-clock" running time
|
|
* On some architectures, value will adjust for cpu time stolen
|
|
* from the kernel in involuntary waits due to virtualization.
|
|
* Value is cumulative, in nanoseconds, without a corresponding count
|
|
* and wraps around to zero silently on overflow
|
|
*/
|
|
__u64 cpu_run_real_total;
|
|
|
|
/* cpu "virtual" running time
|
|
* Uses time intervals seen by the kernel i.e. no adjustment
|
|
* for kernel's involuntary waits due to virtualization.
|
|
* Value is cumulative, in nanoseconds, without a corresponding count
|
|
* and wraps around to zero silently on overflow
|
|
*/
|
|
__u64 cpu_run_virtual_total;
|
|
/* Delay accounting fields end */
|
|
/* version 1 ends here */
|
|
|
|
/* Basic Accounting Fields start */
|
|
char ac_comm[TS_COMM_LEN]; /* Command name */
|
|
__u8 ac_sched __attribute__((aligned(8)));
|
|
/* Scheduling discipline */
|
|
__u8 ac_pad[3];
|
|
__u32 ac_uid __attribute__((aligned(8)));
|
|
/* User ID */
|
|
__u32 ac_gid; /* Group ID */
|
|
__u32 ac_pid; /* Process ID */
|
|
__u32 ac_ppid; /* Parent process ID */
|
|
__u32 ac_btime; /* Begin time [sec since 1970] */
|
|
__u64 ac_etime __attribute__((aligned(8)));
|
|
/* Elapsed time [usec] */
|
|
__u64 ac_utime; /* User CPU time [usec] */
|
|
__u64 ac_stime; /* SYstem CPU time [usec] */
|
|
__u64 ac_minflt; /* Minor Page Fault Count */
|
|
__u64 ac_majflt; /* Major Page Fault Count */
|
|
/* Basic Accounting Fields end */
|
|
|
|
/* Extended accounting fields start */
|
|
/* Accumulated RSS usage in duration of a task, in MBytes-usecs.
|
|
* The current rss usage is added to this counter every time
|
|
* a tick is charged to a task's system time. So, at the end we
|
|
* will have memory usage multiplied by system time. Thus an
|
|
* average usage per system time unit can be calculated.
|
|
*/
|
|
__u64 coremem; /* accumulated RSS usage in MB-usec */
|
|
/* Accumulated virtual memory usage in duration of a task.
|
|
* Same as acct_rss_mem1 above except that we keep track of VM usage.
|
|
*/
|
|
__u64 virtmem; /* accumulated VM usage in MB-usec */
|
|
|
|
/* High watermark of RSS and virtual memory usage in duration of
|
|
* a task, in KBytes.
|
|
*/
|
|
__u64 hiwater_rss; /* High-watermark of RSS usage, in KB */
|
|
__u64 hiwater_vm; /* High-water VM usage, in KB */
|
|
|
|
/* The following four fields are I/O statistics of a task. */
|
|
__u64 read_char; /* bytes read */
|
|
__u64 write_char; /* bytes written */
|
|
__u64 read_syscalls; /* read syscalls */
|
|
__u64 write_syscalls; /* write syscalls */
|
|
/* Extended accounting fields end */
|
|
|
|
#define TASKSTATS_HAS_IO_ACCOUNTING
|
|
/* Per-task storage I/O accounting starts */
|
|
__u64 read_bytes; /* bytes of read I/O */
|
|
__u64 write_bytes; /* bytes of write I/O */
|
|
__u64 cancelled_write_bytes; /* bytes of cancelled write I/O */
|
|
};
|
|
|
|
|
|
/*
|
|
* Commands sent from userspace
|
|
* Not versioned. New commands should only be inserted at the enum's end
|
|
* prior to __TASKSTATS_CMD_MAX
|
|
*/
|
|
|
|
enum {
|
|
TASKSTATS_CMD_UNSPEC = 0, /* Reserved */
|
|
TASKSTATS_CMD_GET, /* user->kernel request/get-response */
|
|
TASKSTATS_CMD_NEW, /* kernel->user event */
|
|
__TASKSTATS_CMD_MAX,
|
|
};
|
|
|
|
#define TASKSTATS_CMD_MAX (__TASKSTATS_CMD_MAX - 1)
|
|
|
|
enum {
|
|
TASKSTATS_TYPE_UNSPEC = 0, /* Reserved */
|
|
TASKSTATS_TYPE_PID, /* Process id */
|
|
TASKSTATS_TYPE_TGID, /* Thread group id */
|
|
TASKSTATS_TYPE_STATS, /* taskstats structure */
|
|
TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */
|
|
TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */
|
|
__TASKSTATS_TYPE_MAX,
|
|
};
|
|
|
|
#define TASKSTATS_TYPE_MAX (__TASKSTATS_TYPE_MAX - 1)
|
|
|
|
enum {
|
|
TASKSTATS_CMD_ATTR_UNSPEC = 0,
|
|
TASKSTATS_CMD_ATTR_PID,
|
|
TASKSTATS_CMD_ATTR_TGID,
|
|
TASKSTATS_CMD_ATTR_REGISTER_CPUMASK,
|
|
TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK,
|
|
__TASKSTATS_CMD_ATTR_MAX,
|
|
};
|
|
|
|
#define TASKSTATS_CMD_ATTR_MAX (__TASKSTATS_CMD_ATTR_MAX - 1)
|
|
|
|
/* NETLINK_GENERIC related info */
|
|
|
|
#define TASKSTATS_GENL_NAME "TASKSTATS"
|
|
#define TASKSTATS_GENL_VERSION 0x1
|
|
|
|
#endif /* _LINUX_TASKSTATS_H */
|