linux/block/ioprio.c
Linus Torvalds d3c8108035 for-5.17/block-2022-01-11
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmHd8DAQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpnhRD/wMAjsNO65PCA+o/bPpVi4ulx9EejAzrJnB
 5vHFvREAoOOGKvRpYGe4w3TcKyW+zPb+GtlXFjPfK+wuVzWhrQtW/+vkjKlBt8wK
 o7rzeMwTKJ9ZGvYaaQpp1yC0WURBB3qnCRQhb8dOQzhJgEXinhIOznZsut4mniLv
 fTqcDmKAb/+G6K6CQCCqnH0I/+OJZyUeSFo1kk2i4ZqCBepQpBkOL6H2rBOtGxUg
 bt1jiGHbbhCRYEE3u2kV0HP10qAChNaMQC705jV4Qpf4+3EntSxs+6nSb74dvMkX
 3+Wmp8Ctq6lpPnDL1nrAFGz3jZnB0Y+GdgOclQn3ViQd1FCXZzuYWQ3fTaBfURCZ
 /RE5nc047SqpwCFLOynM++OkaeQZ1zSxeyoFTtzDaPF4tLuaX3JHswvTzNGPw8SN
 BnexseNnNBCjJliZSEE7fOkjJDcev2dvRxPtI8/wkF4lHUgETc5IW563C53xo/Tx
 32yFjZwCVIpNWk21su/0H3iEq80wZ7PnriiN/E3JA6XbnevlRPu0NPMb0D258GCm
 yCcdPVDNZsQCB8hluqZcu0g6LSgZRo90Yg1oqKqEpAllJJMBaEAPPPuUIJh998mo
 iKGxZzgr7d9jrbGJTInp0F8b3B3/oV/hxgzy0Hu/mHP3AsnaAk9o/oEQZ7rX4Khr
 6biloqkIMA==
 =RWnJ
 -----END PGP SIGNATURE-----

Merge tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Unify where the struct request handling code is located in the blk-mq
   code (Christoph)

 - Header cleanups (Christoph)

 - Clean up the io_context handling code (Christoph, me)

 - Get rid of ->rq_disk in struct request (Christoph)

 - Error handling fix for add_disk() (Christoph)

 - request allocation cleanusp (Christoph)

 - Documentation updates (Eric, Matthew)

 - Remove trivial crypto unregister helper (Eric)

 - Reduce shared tag overhead (John)

 - Reduce poll_stats memory overhead (me)

 - Known indirect function call for dio (me)

 - Use atomic references for struct request (me)

 - Support request list issue for block and NVMe (me)

 - Improve queue dispatch pinning (Ming)

 - Improve the direct list issue code (Keith)

 - BFQ improvements (Jan)

 - Direct completion helper and use it in mmc block (Sebastian)

 - Use raw spinlock for the blktrace code (Wander)

 - fsync error handling fix (Ye)

 - Various fixes and cleanups (Lukas, Randy, Yang, Tetsuo, Ming, me)

* tag 'for-5.17/block-2022-01-11' of git://git.kernel.dk/linux-block: (132 commits)
  MAINTAINERS: add entries for block layer documentation
  docs: block: remove queue-sysfs.rst
  docs: sysfs-block: document virt_boundary_mask
  docs: sysfs-block: document stable_writes
  docs: sysfs-block: fill in missing documentation from queue-sysfs.rst
  docs: sysfs-block: add contact for nomerges
  docs: sysfs-block: sort alphabetically
  docs: sysfs-block: move to stable directory
  block: don't protect submit_bio_checks by q_usage_counter
  block: fix old-style declaration
  nvme-pci: fix queue_rqs list splitting
  block: introduce rq_list_move
  block: introduce rq_list_for_each_safe macro
  block: move rq_list macros to blk-mq.h
  block: drop needless assignment in set_task_ioprio()
  block: remove unnecessary trailing '\'
  bio.h: fix kernel-doc warnings
  block: check minor range in device_add_disk()
  block: use "unsigned long" for blk_validate_block_size().
  block: fix error unwinding in device_add_disk
  ...
2022-01-12 10:26:52 -08:00

237 lines
4.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* fs/ioprio.c
*
* Copyright (C) 2004 Jens Axboe <axboe@kernel.dk>
*
* Helper functions for setting/querying io priorities of processes. The
* system calls closely mimmick getpriority/setpriority, see the man page for
* those. The prio argument is a composite of prio class and prio data, where
* the data argument has meaning within that class. The standard scheduling
* classes have 8 distinct prio levels, with 0 being the highest prio and 7
* being the lowest.
*
* IOW, setting BE scheduling class with prio 2 is done ala:
*
* unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2;
*
* ioprio_set(PRIO_PROCESS, pid, prio);
*
* See also Documentation/block/ioprio.rst
*
*/
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/ioprio.h>
#include <linux/cred.h>
#include <linux/blkdev.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/pid_namespace.h>
int ioprio_check_cap(int ioprio)
{
int class = IOPRIO_PRIO_CLASS(ioprio);
int data = IOPRIO_PRIO_DATA(ioprio);
switch (class) {
case IOPRIO_CLASS_RT:
/*
* Originally this only checked for CAP_SYS_ADMIN,
* which was implicitly allowed for pid 0 by security
* modules such as SELinux. Make sure we check
* CAP_SYS_ADMIN first to avoid a denial/avc for
* possibly missing CAP_SYS_NICE permission.
*/
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
return -EPERM;
fallthrough;
/* rt has prio field too */
case IOPRIO_CLASS_BE:
if (data >= IOPRIO_NR_LEVELS || data < 0)
return -EINVAL;
break;
case IOPRIO_CLASS_IDLE:
break;
case IOPRIO_CLASS_NONE:
if (data)
return -EINVAL;
break;
default:
return -EINVAL;
}
return 0;
}
SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
{
struct task_struct *p, *g;
struct user_struct *user;
struct pid *pgrp;
kuid_t uid;
int ret;
ret = ioprio_check_cap(ioprio);
if (ret)
return ret;
ret = -ESRCH;
rcu_read_lock();
switch (which) {
case IOPRIO_WHO_PROCESS:
if (!who)
p = current;
else
p = find_task_by_vpid(who);
if (p)
ret = set_task_ioprio(p, ioprio);
break;
case IOPRIO_WHO_PGRP:
if (!who)
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
ret = set_task_ioprio(p, ioprio);
if (ret) {
read_unlock(&tasklist_lock);
goto out;
}
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
read_unlock(&tasklist_lock);
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
if (!uid_valid(uid))
break;
if (!who)
user = current_user();
else
user = find_user(uid);
if (!user)
break;
for_each_process_thread(g, p) {
if (!uid_eq(task_uid(p), uid) ||
!task_pid_vnr(p))
continue;
ret = set_task_ioprio(p, ioprio);
if (ret)
goto free_uid;
}
free_uid:
if (who)
free_uid(user);
break;
default:
ret = -EINVAL;
}
out:
rcu_read_unlock();
return ret;
}
static int get_task_ioprio(struct task_struct *p)
{
int ret;
ret = security_task_getioprio(p);
if (ret)
goto out;
ret = IOPRIO_DEFAULT;
task_lock(p);
if (p->io_context)
ret = p->io_context->ioprio;
task_unlock(p);
out:
return ret;
}
int ioprio_best(unsigned short aprio, unsigned short bprio)
{
if (!ioprio_valid(aprio))
aprio = IOPRIO_DEFAULT;
if (!ioprio_valid(bprio))
bprio = IOPRIO_DEFAULT;
return min(aprio, bprio);
}
SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
{
struct task_struct *g, *p;
struct user_struct *user;
struct pid *pgrp;
kuid_t uid;
int ret = -ESRCH;
int tmpio;
rcu_read_lock();
switch (which) {
case IOPRIO_WHO_PROCESS:
if (!who)
p = current;
else
p = find_task_by_vpid(who);
if (p)
ret = get_task_ioprio(p);
break;
case IOPRIO_WHO_PGRP:
if (!who)
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
tmpio = get_task_ioprio(p);
if (tmpio < 0)
continue;
if (ret == -ESRCH)
ret = tmpio;
else
ret = ioprio_best(ret, tmpio);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
read_unlock(&tasklist_lock);
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
if (!who)
user = current_user();
else
user = find_user(uid);
if (!user)
break;
for_each_process_thread(g, p) {
if (!uid_eq(task_uid(p), user->uid) ||
!task_pid_vnr(p))
continue;
tmpio = get_task_ioprio(p);
if (tmpio < 0)
continue;
if (ret == -ESRCH)
ret = tmpio;
else
ret = ioprio_best(ret, tmpio);
}
if (who)
free_uid(user);
break;
default:
ret = -EINVAL;
}
rcu_read_unlock();
return ret;
}