Orange Pi5 kernel

^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   2) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   3)  * Process number limiting controller for cgroups.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   4)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   5)  * Used to allow a cgroup hierarchy to stop any new processes from fork()ing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   6)  * after a certain limit is reached.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   7)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   8)  * Since it is trivial to hit the task limit without hitting any kmemcg limits
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300   9)  * in place, PIDs are a fundamental resource. As such, PID exhaustion must be
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  10)  * preventable in the scope of a cgroup hierarchy by allowing resource limiting
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  11)  * of the number of tasks in a cgroup.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  12)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  13)  * In order to use the `pids` controller, set the maximum number of tasks in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  14)  * pids.max (this is not available in the root cgroup for obvious reasons). The
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  15)  * number of processes currently in the cgroup is given by pids.current.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  16)  * Organisational operations are not blocked by cgroup policies, so it is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  17)  * possible to have pids.current > pids.max. However, it is not possible to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  18)  * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  19)  * would cause a cgroup policy to be violated.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  20)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  21)  * To set a cgroup to have no limit, set pids.max to "max". This is the default
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  22)  * for all new cgroups (N.B. that PID limits are hierarchical, so the most
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  23)  * stringent limit in the hierarchy is followed).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  24)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  25)  * pids.current tracks all child cgroup hierarchies, so parent/pids.current is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  26)  * a superset of parent/child/pids.current.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  27)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  28)  * Copyright (C) 2015 Aleksa Sarai <cyphar@cyphar.com>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  29)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  30) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  31) #include <linux/kernel.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  32) #include <linux/threads.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  33) #include <linux/atomic.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  34) #include <linux/cgroup.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  35) #include <linux/slab.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  36) #include <linux/sched/task.h>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  37) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  38) #define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  39) #define PIDS_MAX_STR "max"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  40) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  41) struct pids_cgroup {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  42) 	struct cgroup_subsys_state	css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  43) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  44) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  45) 	 * Use 64-bit types so that we can safely represent "max" as
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  46) 	 * %PIDS_MAX = (%PID_MAX_LIMIT + 1).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  47) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  48) 	atomic64_t			counter;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  49) 	atomic64_t			limit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  50) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  51) 	/* Handle for "pids.events" */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  52) 	struct cgroup_file		events_file;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  53) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  54) 	/* Number of times fork failed because limit was hit. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  55) 	atomic64_t			events_limit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  56) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  57) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  58) static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  59) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  60) 	return container_of(css, struct pids_cgroup, css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  61) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  62) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  63) static struct pids_cgroup *parent_pids(struct pids_cgroup *pids)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  64) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  65) 	return css_pids(pids->css.parent);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  66) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  67) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  68) static struct cgroup_subsys_state *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  69) pids_css_alloc(struct cgroup_subsys_state *parent)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  70) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  71) 	struct pids_cgroup *pids;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  72) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  73) 	pids = kzalloc(sizeof(struct pids_cgroup), GFP_KERNEL);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  74) 	if (!pids)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  75) 		return ERR_PTR(-ENOMEM);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  76) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  77) 	atomic64_set(&pids->counter, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  78) 	atomic64_set(&pids->limit, PIDS_MAX);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  79) 	atomic64_set(&pids->events_limit, 0);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  80) 	return &pids->css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  81) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  82) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  83) static void pids_css_free(struct cgroup_subsys_state *css)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  84) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  85) 	kfree(css_pids(css));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  86) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  87) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  88) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  89)  * pids_cancel - uncharge the local pid count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  90)  * @pids: the pid cgroup state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  91)  * @num: the number of pids to cancel
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  92)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  93)  * This function will WARN if the pid count goes under 0, because such a case is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  94)  * a bug in the pids controller proper.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  95)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  96) static void pids_cancel(struct pids_cgroup *pids, int num)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  97) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  98) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300  99) 	 * A negative count (or overflow for that matter) is invalid,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) 	 * and indicates a bug in the `pids` controller proper.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) 	WARN_ON_ONCE(atomic64_add_negative(-num, &pids->counter));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106)  * pids_uncharge - hierarchically uncharge the pid count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107)  * @pids: the pid cgroup state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108)  * @num: the number of pids to uncharge
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) static void pids_uncharge(struct pids_cgroup *pids, int num)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) 	struct pids_cgroup *p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) 	for (p = pids; parent_pids(p); p = parent_pids(p))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115) 		pids_cancel(p, num);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119)  * pids_charge - hierarchically charge the pid count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120)  * @pids: the pid cgroup state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121)  * @num: the number of pids to charge
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123)  * This function does *not* follow the pid limit set. It cannot fail and the new
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124)  * pid count may exceed the limit. This is only used for reverting failed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125)  * attaches, where there is no other way out than violating the limit.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) static void pids_charge(struct pids_cgroup *pids, int num)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) 	struct pids_cgroup *p;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) 	for (p = pids; parent_pids(p); p = parent_pids(p))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) 		atomic64_add(num, &p->counter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) /**
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136)  * pids_try_charge - hierarchically try to charge the pid count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137)  * @pids: the pid cgroup state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138)  * @num: the number of pids to charge
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139)  *
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140)  * This function follows the set limit. It will fail if the charge would cause
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141)  * the new value to exceed the hierarchical limit. Returns 0 if the charge
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142)  * succeeded, otherwise -EAGAIN.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) static int pids_try_charge(struct pids_cgroup *pids, int num)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) 	struct pids_cgroup *p, *q;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) 	for (p = pids; parent_pids(p); p = parent_pids(p)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149) 		int64_t new = atomic64_add_return(num, &p->counter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) 		int64_t limit = atomic64_read(&p->limit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) 		/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) 		 * Since new is capped to the maximum number of pid_t, if
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) 		 * p->limit is %PIDS_MAX then we know that this test will never
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) 		 * fail.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) 		 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) 		if (new > limit)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) 			goto revert;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) revert:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) 	for (q = pids; q != p; q = parent_pids(q))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) 		pids_cancel(q, num);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) 	pids_cancel(p, num);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) 	return -EAGAIN;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) static int pids_can_attach(struct cgroup_taskset *tset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) 	struct task_struct *task;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) 	struct cgroup_subsys_state *dst_css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) 	cgroup_taskset_for_each(task, dst_css, tset) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177) 		struct pids_cgroup *pids = css_pids(dst_css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) 		struct cgroup_subsys_state *old_css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) 		struct pids_cgroup *old_pids;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) 		/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182) 		 * No need to pin @old_css between here and cancel_attach()
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183) 		 * because cgroup core protects it from being freed before
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) 		 * the migration completes or fails.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185) 		 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) 		old_css = task_css(task, pids_cgrp_id);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) 		old_pids = css_pids(old_css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) 		pids_charge(pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) 		pids_uncharge(old_pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) static void pids_cancel_attach(struct cgroup_taskset *tset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) 	struct task_struct *task;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199) 	struct cgroup_subsys_state *dst_css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201) 	cgroup_taskset_for_each(task, dst_css, tset) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) 		struct pids_cgroup *pids = css_pids(dst_css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203) 		struct cgroup_subsys_state *old_css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) 		struct pids_cgroup *old_pids;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) 		old_css = task_css(task, pids_cgrp_id);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) 		old_pids = css_pids(old_css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209) 		pids_charge(old_pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) 		pids_uncharge(pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215)  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216)  * on cgroup_threadgroup_change_begin() held by the copy_process().
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217)  */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) static int pids_can_fork(struct task_struct *task, struct css_set *cset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) 	struct cgroup_subsys_state *css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) 	struct pids_cgroup *pids;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) 	int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) 	if (cset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) 		css = cset->subsys[pids_cgrp_id];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) 	else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) 		css = task_css_check(current, pids_cgrp_id, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) 	pids = css_pids(css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) 	err = pids_try_charge(pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) 	if (err) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) 		/* Only log the first time events_limit is incremented. */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232) 		if (atomic64_inc_return(&pids->events_limit) == 1) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) 			pr_info("cgroup: fork rejected by pids controller in ");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234) 			pr_cont_cgroup_path(css->cgroup);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) 			pr_cont("\n");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236) 		}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) 		cgroup_file_notify(&pids->events_file);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) 	return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242) static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244) 	struct cgroup_subsys_state *css;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) 	struct pids_cgroup *pids;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247) 	if (cset)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) 		css = cset->subsys[pids_cgrp_id];
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) 	else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) 		css = task_css_check(current, pids_cgrp_id, true);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251) 	pids = css_pids(css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) 	pids_uncharge(pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) static void pids_release(struct task_struct *task)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) 	struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) 	pids_uncharge(pids, 1);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263) 			      size_t nbytes, loff_t off)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) 	struct cgroup_subsys_state *css = of_css(of);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266) 	struct pids_cgroup *pids = css_pids(css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) 	int64_t limit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) 	int err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270) 	buf = strstrip(buf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271) 	if (!strcmp(buf, PIDS_MAX_STR)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) 		limit = PIDS_MAX;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273) 		goto set_limit;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) 	}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) 	err = kstrtoll(buf, 0, &limit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277) 	if (err)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) 		return err;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) 	if (limit < 0 || limit >= PIDS_MAX)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281) 		return -EINVAL;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283) set_limit:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) 	/*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285) 	 * Limit updates don't need to be mutex'd, since it isn't
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) 	 * critical that any racing fork()s follow the new limit.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) 	 */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288) 	atomic64_set(&pids->limit, limit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) 	return nbytes;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) static int pids_max_show(struct seq_file *sf, void *v)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) 	struct cgroup_subsys_state *css = seq_css(sf);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295) 	struct pids_cgroup *pids = css_pids(css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) 	int64_t limit = atomic64_read(&pids->limit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) 	if (limit >= PIDS_MAX)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299) 		seq_printf(sf, "%s\n", PIDS_MAX_STR);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) 	else
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301) 		seq_printf(sf, "%lld\n", limit);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306) static s64 pids_current_read(struct cgroup_subsys_state *css,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) 			     struct cftype *cft)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309) 	struct pids_cgroup *pids = css_pids(css);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311) 	return atomic64_read(&pids->counter);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314) static int pids_events_show(struct seq_file *sf, void *v)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316) 	struct pids_cgroup *pids = css_pids(seq_css(sf));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) 	seq_printf(sf, "max %lld\n", (s64)atomic64_read(&pids->events_limit));
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319) 	return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) static struct cftype pids_files[] = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323) 	{
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) 		.name = "max",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325) 		.write = pids_max_write,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) 		.seq_show = pids_max_show,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) 		.flags = CFTYPE_NOT_ON_ROOT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) 	},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) 	{
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) 		.name = "current",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331) 		.read_s64 = pids_current_read,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) 		.flags = CFTYPE_NOT_ON_ROOT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) 	},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334) 	{
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) 		.name = "events",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336) 		.seq_show = pids_events_show,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) 		.file_offset = offsetof(struct pids_cgroup, events_file),
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) 		.flags = CFTYPE_NOT_ON_ROOT,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339) 	},
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) 	{ }	/* terminate */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) 
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343) struct cgroup_subsys pids_cgrp_subsys = {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) 	.css_alloc	= pids_css_alloc,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) 	.css_free	= pids_css_free,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) 	.can_attach 	= pids_can_attach,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) 	.cancel_attach 	= pids_cancel_attach,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348) 	.can_fork	= pids_can_fork,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) 	.cancel_fork	= pids_cancel_fork,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350) 	.release	= pids_release,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) 	.legacy_cftypes	= pids_files,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352) 	.dfl_cftypes	= pids_files,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) 	.threaded	= true,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) };