Commit 55e6be65 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "The only notable change is Vipin's new misc cgroup controller.

  This implements generic support for resources which can be controlled
  by simply counting and limiting the number of resource instances - ie
  there's X number of these on the system and this cgroup subtree can
  have upto Y of those.

  The first user is the address space IDs used for virtual machine
  memory encryption and expected future usages are similar - niche
  hardware features with concrete resource limits and simple usage
  models"

* 'for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: use tsk->in_iowait instead of delayacct_is_task_waiting_on_io()
  cgroup/cpuset: fix typos in comments
  cgroup: misc: mark dummy misc_cg_res_total_usage() static inline
  svm/sev: Register SEV and SEV-ES ASIDs to the misc controller
  cgroup: Miscellaneous cgroup documentation.
  cgroup: Add misc cgroup controller
parents eb6bbacc ffeee417
...@@ -17,6 +17,7 @@ Control Groups version 1 ...@@ -17,6 +17,7 @@ Control Groups version 1
hugetlb hugetlb
memcg_test memcg_test
memory memory
misc
net_cls net_cls
net_prio net_prio
pids pids
......
===============
Misc controller
===============
Please refer "Misc" documentation in Documentation/admin-guide/cgroup-v2.rst
...@@ -65,8 +65,11 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgrou ...@@ -65,8 +65,11 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgrou
5-7-1. RDMA Interface Files 5-7-1. RDMA Interface Files
5-8. HugeTLB 5-8. HugeTLB
5.8-1. HugeTLB Interface Files 5.8-1. HugeTLB Interface Files
5-8. Misc 5-9. Misc
5-8-1. perf_event 5.9-1 Miscellaneous cgroup Interface Files
5.9-2 Migration and Ownership
5-10. Others
5-10-1. perf_event
5-N. Non-normative information 5-N. Non-normative information
5-N-1. CPU controller root cgroup process behaviour 5-N-1. CPU controller root cgroup process behaviour
5-N-2. IO controller root cgroup process behaviour 5-N-2. IO controller root cgroup process behaviour
...@@ -2171,6 +2174,72 @@ HugeTLB Interface Files ...@@ -2171,6 +2174,72 @@ HugeTLB Interface Files
Misc Misc
---- ----
The Miscellaneous cgroup provides the resource limiting and tracking
mechanism for the scalar resources which cannot be abstracted like the other
cgroup resources. Controller is enabled by the CONFIG_CGROUP_MISC config
option.
A resource can be added to the controller via enum misc_res_type{} in the
include/linux/misc_cgroup.h file and the corresponding name via misc_res_name[]
in the kernel/cgroup/misc.c file. Provider of the resource must set its
capacity prior to using the resource by calling misc_cg_set_capacity().
Once a capacity is set then the resource usage can be updated using charge and
uncharge APIs. All of the APIs to interact with misc controller are in
include/linux/misc_cgroup.h.
Misc Interface Files
~~~~~~~~~~~~~~~~~~~~
Miscellaneous controller provides 3 interface files. If two misc resources (res_a and res_b) are registered then:
misc.capacity
A read-only flat-keyed file shown only in the root cgroup. It shows
miscellaneous scalar resources available on the platform along with
their quantities::
$ cat misc.capacity
res_a 50
res_b 10
misc.current
A read-only flat-keyed file shown in the non-root cgroups. It shows
the current usage of the resources in the cgroup and its children.::
$ cat misc.current
res_a 3
res_b 0
misc.max
A read-write flat-keyed file shown in the non root cgroups. Allowed
maximum usage of the resources in the cgroup and its children.::
$ cat misc.max
res_a max
res_b 4
Limit can be set by::
# echo res_a 1 > misc.max
Limit can be set to max by::
# echo res_a max > misc.max
Limits can be set higher than the capacity value in the misc.capacity
file.
Migration and Ownership
~~~~~~~~~~~~~~~~~~~~~~~
A miscellaneous scalar resource is charged to the cgroup in which it is used
first, and stays charged to that cgroup until that resource is freed. Migrating
a process to a different cgroup does not move the charge to the destination
cgroup where the process has moved.
Others
------
perf_event perf_event
~~~~~~~~~~ ~~~~~~~~~~
......
...@@ -14,6 +14,7 @@ ...@@ -14,6 +14,7 @@
#include <linux/psp-sev.h> #include <linux/psp-sev.h>
#include <linux/pagemap.h> #include <linux/pagemap.h>
#include <linux/swap.h> #include <linux/swap.h>
#include <linux/misc_cgroup.h>
#include <linux/processor.h> #include <linux/processor.h>
#include <linux/trace_events.h> #include <linux/trace_events.h>
#include <asm/fpu/internal.h> #include <asm/fpu/internal.h>
...@@ -28,6 +29,21 @@ ...@@ -28,6 +29,21 @@
#define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex(x) __kvm_handle_fault_on_reboot(x)
#ifndef CONFIG_KVM_AMD_SEV
/*
* When this config is not defined, SEV feature is not supported and APIs in
* this file are not used but this file still gets compiled into the KVM AMD
* module.
*
* We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum
* misc_res_type {} defined in linux/misc_cgroup.h.
*
* Below macros allow compilation to succeed.
*/
#define MISC_CG_RES_SEV MISC_CG_RES_TYPES
#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES
#endif
static u8 sev_enc_bit; static u8 sev_enc_bit;
static int sev_flush_asids(void); static int sev_flush_asids(void);
static DECLARE_RWSEM(sev_deactivate_lock); static DECLARE_RWSEM(sev_deactivate_lock);
...@@ -89,8 +105,19 @@ static bool __sev_recycle_asids(int min_asid, int max_asid) ...@@ -89,8 +105,19 @@ static bool __sev_recycle_asids(int min_asid, int max_asid)
static int sev_asid_new(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev)
{ {
int pos, min_asid, max_asid; int pos, min_asid, max_asid, ret;
bool retry = true; bool retry = true;
enum misc_res_type type;
type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
WARN_ON(sev->misc_cg);
sev->misc_cg = get_current_misc_cg();
ret = misc_cg_try_charge(type, sev->misc_cg, 1);
if (ret) {
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return ret;
}
mutex_lock(&sev_bitmap_lock); mutex_lock(&sev_bitmap_lock);
...@@ -108,7 +135,8 @@ static int sev_asid_new(struct kvm_sev_info *sev) ...@@ -108,7 +135,8 @@ static int sev_asid_new(struct kvm_sev_info *sev)
goto again; goto again;
} }
mutex_unlock(&sev_bitmap_lock); mutex_unlock(&sev_bitmap_lock);
return -EBUSY; ret = -EBUSY;
goto e_uncharge;
} }
__set_bit(pos, sev_asid_bitmap); __set_bit(pos, sev_asid_bitmap);
...@@ -116,6 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev) ...@@ -116,6 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev)
mutex_unlock(&sev_bitmap_lock); mutex_unlock(&sev_bitmap_lock);
return pos + 1; return pos + 1;
e_uncharge:
misc_cg_uncharge(type, sev->misc_cg, 1);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
return ret;
} }
static int sev_get_asid(struct kvm *kvm) static int sev_get_asid(struct kvm *kvm)
...@@ -125,14 +158,15 @@ static int sev_get_asid(struct kvm *kvm) ...@@ -125,14 +158,15 @@ static int sev_get_asid(struct kvm *kvm)
return sev->asid; return sev->asid;
} }
static void sev_asid_free(int asid) static void sev_asid_free(struct kvm_sev_info *sev)
{ {
struct svm_cpu_data *sd; struct svm_cpu_data *sd;
int cpu, pos; int cpu, pos;
enum misc_res_type type;
mutex_lock(&sev_bitmap_lock); mutex_lock(&sev_bitmap_lock);
pos = asid - 1; pos = sev->asid - 1;
__set_bit(pos, sev_reclaim_asid_bitmap); __set_bit(pos, sev_reclaim_asid_bitmap);
for_each_possible_cpu(cpu) { for_each_possible_cpu(cpu) {
...@@ -141,6 +175,11 @@ static void sev_asid_free(int asid) ...@@ -141,6 +175,11 @@ static void sev_asid_free(int asid)
} }
mutex_unlock(&sev_bitmap_lock); mutex_unlock(&sev_bitmap_lock);
type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
misc_cg_uncharge(type, sev->misc_cg, 1);
put_misc_cg(sev->misc_cg);
sev->misc_cg = NULL;
} }
static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
...@@ -188,19 +227,20 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) ...@@ -188,19 +227,20 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
asid = sev_asid_new(sev); asid = sev_asid_new(sev);
if (asid < 0) if (asid < 0)
return ret; return ret;
sev->asid = asid;
ret = sev_platform_init(&argp->error); ret = sev_platform_init(&argp->error);
if (ret) if (ret)
goto e_free; goto e_free;
sev->active = true; sev->active = true;
sev->asid = asid;
INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->regions_list);
return 0; return 0;
e_free: e_free:
sev_asid_free(asid); sev_asid_free(sev);
sev->asid = 0;
return ret; return ret;
} }
...@@ -1315,12 +1355,12 @@ void sev_vm_destroy(struct kvm *kvm) ...@@ -1315,12 +1355,12 @@ void sev_vm_destroy(struct kvm *kvm)
mutex_unlock(&kvm->lock); mutex_unlock(&kvm->lock);
sev_unbind_asid(kvm, sev->handle); sev_unbind_asid(kvm, sev->handle);
sev_asid_free(sev->asid); sev_asid_free(sev);
} }
void __init sev_hardware_setup(void) void __init sev_hardware_setup(void)
{ {
unsigned int eax, ebx, ecx, edx; unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
bool sev_es_supported = false; bool sev_es_supported = false;
bool sev_supported = false; bool sev_supported = false;
...@@ -1352,7 +1392,11 @@ void __init sev_hardware_setup(void) ...@@ -1352,7 +1392,11 @@ void __init sev_hardware_setup(void)
if (!sev_reclaim_asid_bitmap) if (!sev_reclaim_asid_bitmap)
goto out; goto out;
pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1); sev_asid_count = max_sev_asid - min_sev_asid + 1;
if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count))
goto out;
pr_info("SEV supported: %u ASIDs\n", sev_asid_count);
sev_supported = true; sev_supported = true;
/* SEV-ES support requested? */ /* SEV-ES support requested? */
...@@ -1367,7 +1411,11 @@ void __init sev_hardware_setup(void) ...@@ -1367,7 +1411,11 @@ void __init sev_hardware_setup(void)
if (min_sev_asid == 1) if (min_sev_asid == 1)
goto out; goto out;
pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1); sev_es_asid_count = min_sev_asid - 1;
if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count))
goto out;
pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count);
sev_es_supported = true; sev_es_supported = true;
out: out:
...@@ -1382,6 +1430,8 @@ void sev_hardware_teardown(void) ...@@ -1382,6 +1430,8 @@ void sev_hardware_teardown(void)
bitmap_free(sev_asid_bitmap); bitmap_free(sev_asid_bitmap);
bitmap_free(sev_reclaim_asid_bitmap); bitmap_free(sev_reclaim_asid_bitmap);
misc_cg_set_capacity(MISC_CG_RES_SEV, 0);
misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0);
sev_flush_asids(); sev_flush_asids();
} }
......
...@@ -65,6 +65,7 @@ struct kvm_sev_info { ...@@ -65,6 +65,7 @@ struct kvm_sev_info {
unsigned long pages_locked; /* Number of pages locked */ unsigned long pages_locked; /* Number of pages locked */
struct list_head regions_list; /* List of registered regions */ struct list_head regions_list; /* List of registered regions */
u64 ap_jump_table; /* SEV-ES AP Jump Table address */ u64 ap_jump_table; /* SEV-ES AP Jump Table address */
struct misc_cg *misc_cg; /* For misc cgroup accounting */
}; };
struct kvm_svm { struct kvm_svm {
......
...@@ -61,6 +61,10 @@ SUBSYS(pids) ...@@ -61,6 +61,10 @@ SUBSYS(pids)
SUBSYS(rdma) SUBSYS(rdma)
#endif #endif
#if IS_ENABLED(CONFIG_CGROUP_MISC)
SUBSYS(misc)
#endif
/* /*
* The following subsystems are not supported on the default hierarchy. * The following subsystems are not supported on the default hierarchy.
*/ */
......
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Miscellaneous cgroup controller.
*
* Copyright 2020 Google LLC
* Author: Vipin Sharma <vipinsh@google.com>
*/
#ifndef _MISC_CGROUP_H_
#define _MISC_CGROUP_H_
/**
* Types of misc cgroup entries supported by the host.
*/
enum misc_res_type {
#ifdef CONFIG_KVM_AMD_SEV
/* AMD SEV ASIDs resource */
MISC_CG_RES_SEV,
/* AMD SEV-ES ASIDs resource */
MISC_CG_RES_SEV_ES,
#endif
MISC_CG_RES_TYPES
};
struct misc_cg;
#ifdef CONFIG_CGROUP_MISC
#include <linux/cgroup.h>
/**
* struct misc_res: Per cgroup per misc type resource
* @max: Maximum limit on the resource.
* @usage: Current usage of the resource.
* @failed: True if charged failed for the resource in a cgroup.
*/
struct misc_res {
unsigned long max;
atomic_long_t usage;
bool failed;
};
/**
* struct misc_cg - Miscellaneous controller's cgroup structure.
* @css: cgroup subsys state object.
* @res: Array of misc resources usage in the cgroup.
*/
struct misc_cg {
struct cgroup_subsys_state css;
struct misc_res res[MISC_CG_RES_TYPES];
};
unsigned long misc_cg_res_total_usage(enum misc_res_type type);
int misc_cg_set_capacity(enum misc_res_type type, unsigned long capacity);
int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
unsigned long amount);
void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg,
unsigned long amount);
/**
* css_misc() - Get misc cgroup from the css.
* @css: cgroup subsys state object.
*
* Context: Any context.
* Return:
* * %NULL - If @css is null.
* * struct misc_cg* - misc cgroup pointer of the passed css.
*/
static inline struct misc_cg *css_misc(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct misc_cg, css) : NULL;
}
/*
* get_current_misc_cg() - Find and get the misc cgroup of the current task.
*
* Returned cgroup has its ref count increased by 1. Caller must call
* put_misc_cg() to return the reference.
*
* Return: Misc cgroup to which the current task belongs to.
*/
static inline struct misc_cg *get_current_misc_cg(void)
{
return css_misc(task_get_css(current, misc_cgrp_id));
}
/*
* put_misc_cg() - Put the misc cgroup and reduce its ref count.
* @cg - cgroup to put.
*/
static inline void put_misc_cg(struct misc_cg *cg)
{
if (cg)
css_put(&cg->css);
}
#else /* !CONFIG_CGROUP_MISC */
static inline unsigned long misc_cg_res_total_usage(enum misc_res_type type)
{
return 0;
}
static inline int misc_cg_set_capacity(enum misc_res_type type,
unsigned long capacity)
{
return 0;
}
static inline int misc_cg_try_charge(enum misc_res_type type,
struct misc_cg *cg,
unsigned long amount)
{
return 0;
}
static inline void misc_cg_uncharge(enum misc_res_type type,
struct misc_cg *cg,
unsigned long amount)
{
}
static inline struct misc_cg *get_current_misc_cg(void)
{
return NULL;
}
static inline void put_misc_cg(struct misc_cg *cg)
{
}
#endif /* CONFIG_CGROUP_MISC */
#endif /* _MISC_CGROUP_H_ */
...@@ -1110,6 +1110,20 @@ config CGROUP_BPF ...@@ -1110,6 +1110,20 @@ config CGROUP_BPF
BPF_CGROUP_INET_INGRESS will be executed on the ingress path of BPF_CGROUP_INET_INGRESS will be executed on the ingress path of
inet sockets. inet sockets.
config CGROUP_MISC
bool "Misc resource controller"
default n
help
Provides a controller for miscellaneous resources on a host.
Miscellaneous scalar resources are the resources on the host system
which cannot be abstracted like the other cgroups. This controller
tracks and limits the miscellaneous resources used by a process
attached to a cgroup hierarchy.
For more information, please check misc cgroup section in
/Documentation/admin-guide/cgroup-v2.rst.
config CGROUP_DEBUG config CGROUP_DEBUG
bool "Debug controller" bool "Debug controller"
default n default n
......
...@@ -5,4 +5,5 @@ obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o ...@@ -5,4 +5,5 @@ obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
obj-$(CONFIG_CGROUP_PIDS) += pids.o obj-$(CONFIG_CGROUP_PIDS) += pids.o
obj-$(CONFIG_CGROUP_RDMA) += rdma.o obj-$(CONFIG_CGROUP_RDMA) += rdma.o
obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CPUSETS) += cpuset.o
obj-$(CONFIG_CGROUP_MISC) += misc.o
obj-$(CONFIG_CGROUP_DEBUG) += debug.o obj-$(CONFIG_CGROUP_DEBUG) += debug.o
...@@ -727,7 +727,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) ...@@ -727,7 +727,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
stats->nr_stopped++; stats->nr_stopped++;
break; break;
default: default:
if (delayacct_is_task_waiting_on_io(tsk)) if (tsk->in_iowait)
stats->nr_io_wait++; stats->nr_io_wait++;
break; break;
} }
......
...@@ -585,7 +585,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) ...@@ -585,7 +585,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
par = parent_cs(cur); par = parent_cs(cur);
/* On legacy hiearchy, we must be a subset of our parent cpuset. */ /* On legacy hierarchy, we must be a subset of our parent cpuset. */
ret = -EACCES; ret = -EACCES;
if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) if (!is_in_v2_mode() && !is_cpuset_subset(trial, par))
goto out; goto out;
...@@ -1726,7 +1726,7 @@ static void update_tasks_nodemask(struct cpuset *cs) ...@@ -1726,7 +1726,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
* When configured nodemask is changed, the effective nodemasks of this cpuset * When configured nodemask is changed, the effective nodemasks of this cpuset
* and all its descendants need to be updated. * and all its descendants need to be updated.
* *
* On legacy hiearchy, effective_mems will be the same with mems_allowed. * On legacy hierarchy, effective_mems will be the same with mems_allowed.
* *
* Called with cpuset_mutex held * Called with cpuset_mutex held
*/ */
...@@ -2500,7 +2500,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) ...@@ -2500,7 +2500,7 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
BUG(); BUG();
} }
/* Unrechable but makes gcc happy */ /* Unreachable but makes gcc happy */
return 0; return 0;
} }
......
// SPDX-License-Identifier: GPL-2.0
/*
* Miscellaneous cgroup controller
*
* Copyright 2020 Google LLC
* Author: Vipin Sharma <vipinsh@google.com>
*/
#include <linux/limits.h>
#include <linux/cgroup.h>
#include <linux/errno.h>
#include <linux/atomic.h>
#include <linux/slab.h>
#include <linux/misc_cgroup.h>
#define MAX_STR "max"
#define MAX_NUM ULONG_MAX
/* Miscellaneous res name, keep it in sync with enum misc_res_type */
static const char *const misc_res_name[] = {
#ifdef CONFIG_KVM_AMD_SEV
/* AMD SEV ASIDs resource */
"sev",
/* AMD SEV-ES ASIDs resource */
"sev_es",
#endif
};
/* Root misc cgroup */
static struct misc_cg root_cg;
/*
* Miscellaneous resources capacity for the entire machine. 0 capacity means
* resource is not initialized or not present in the host.
*
* root_cg.max and capacity are independent of each other. root_cg.max can be
* more than the actual capacity. We are using Limits resource distribution
* model of cgroup for miscellaneous controller.
*/
static unsigned long misc_res_capacity[MISC_CG_RES_TYPES];
/**
* parent_misc() - Get the parent of the passed misc cgroup.
* @cgroup: cgroup whose parent needs to be fetched.
*
* Context: Any context.
* Return:
* * struct misc_cg* - Parent of the @cgroup.
* * %NULL - If @cgroup is null or the passed cgroup does not have a parent.
*/
static struct misc_cg *parent_misc(struct misc_cg *cgroup)
{
return cgroup ? css_misc(cgroup->css.parent) : NULL;
}
/**
* valid_type() - Check if @type is valid or not.
* @type: misc res type.
*
* Context: Any context.
* Return:
* * true - If valid type.
* * false - If not valid type.
*/
static inline bool valid_type(enum misc_res_type type)
{
return type >= 0 && type < MISC_CG_RES_TYPES;
}
/**
* misc_cg_res_total_usage() - Get the current total usage of the resource.
* @type: misc res type.
*
* Context: Any context.
* Return: Current total usage of the resource.
*/
unsigned long misc_cg_res_total_usage(enum misc_res_type type)
{
if (valid_type(type))
return atomic_long_read(&root_cg.res[type].usage);
return 0;
}
EXPORT_SYMBOL_GPL(misc_cg_res_total_usage);
/**
* misc_cg_set_capacity() - Set the capacity of the misc cgroup res.
* @type: Type of the misc res.
* @capacity: Supported capacity of the misc res on the host.
*
* If capacity is 0 then the charging a misc cgroup fails for that type.
*
* Context: Any context.
* Return:
* * %0 - Successfully registered the capacity.
* * %-EINVAL - If @type is invalid.
*/
int misc_cg_set_capacity(enum misc_res_type type, unsigned long capacity)
{
if (!valid_type(type))
return -EINVAL;
WRITE_ONCE(misc_res_capacity[type], capacity);
return 0;
}
EXPORT_SYMBOL_GPL(misc_cg_set_capacity);
/**
* misc_cg_cancel_charge() - Cancel the charge from the misc cgroup.
* @type: Misc res type in misc cg to cancel the charge from.
* @cg: Misc cgroup to cancel charge from.
* @amount: Amount to cancel.
*
* Context: Any context.
*/
static void misc_cg_cancel_charge(enum misc_res_type type, struct misc_cg *cg,
unsigned long amount)
{
WARN_ONCE(atomic_long_add_negative(-amount, &cg->res[type].usage),
"misc cgroup resource %s became less than 0",
misc_res_name[type]);
}
/**
* misc_cg_try_charge() - Try charging the misc cgroup.
* @type: Misc res type to charge.
* @cg: Misc cgroup which will be charged.
* @amount: Amount to charge.
*
* Charge @amount to the misc cgroup. Caller must use the same cgroup during
* the uncharge call.
*
* Context: Any context.
* Return:
* * %0 - If successfully charged.
* * -EINVAL - If @type is invalid or misc res has 0 capacity.
* * -EBUSY - If max limit will be crossed or total usage will be more than the
* capacity.
*/
int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
unsigned long amount)
{
struct misc_cg *i, *j;
int ret;
struct misc_res *res;
int new_usage;
if (!(valid_type(type) && cg && READ_ONCE(misc_res_capacity[type])))
return -EINVAL;
if (!amount)
return 0;
for (i = cg; i; i = parent_misc(i)) {
res = &i->res[type];
new_usage = atomic_long_add_return(amount, &res->usage);
if (new_usage > READ_ONCE(res->max) ||
new_usage > READ_ONCE(misc_res_capacity[type])) {
if (!res->failed) {
pr_info("cgroup: charge rejected by the misc controller for %s resource in ",
misc_res_name[type]);
pr_cont_cgroup_path(i->css.cgroup);
pr_cont("\n");
res->failed = true;
}
ret = -EBUSY;
goto err_charge;
}
}
return 0;
err_charge:
for (j = cg; j != i; j = parent_misc(j))
misc_cg_cancel_charge(type, j, amount);
misc_cg_cancel_charge(type, i, amount);
return ret;
}
EXPORT_SYMBOL_GPL(misc_cg_try_charge);
/**
* misc_cg_uncharge() - Uncharge the misc cgroup.
* @type: Misc res type which was charged.
* @cg: Misc cgroup which will be uncharged.
* @amount: Charged amount.
*
* Context: Any context.
*/
void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg,
unsigned long amount)
{
struct misc_cg *i;
if (!(amount && valid_type(type) && cg))
return;
for (i = cg; i; i = parent_misc(i))
misc_cg_cancel_charge(type, i, amount);
}
EXPORT_SYMBOL_GPL(misc_cg_uncharge);
/**
* misc_cg_max_show() - Show the misc cgroup max limit.
* @sf: Interface file
* @v: Arguments passed
*
* Context: Any context.
* Return: 0 to denote successful print.
*/
static int misc_cg_max_show(struct seq_file *sf, void *v)
{
int i;
struct misc_cg *cg = css_misc(seq_css(sf));
unsigned long max;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
if (READ_ONCE(misc_res_capacity[i])) {
max = READ_ONCE(cg->res[i].max);
if (max == MAX_NUM)
seq_printf(sf, "%s max\n", misc_res_name[i]);
else
seq_printf(sf, "%s %lu\n", misc_res_name[i],
max);
}
}
return 0;
}
/**
* misc_cg_max_write() - Update the maximum limit of the cgroup.
* @of: Handler for the file.
* @buf: Data from the user. It should be either "max", 0, or a positive
* integer.
* @nbytes: Number of bytes of the data.
* @off: Offset in the file.
*
* User can pass data like:
* echo sev 23 > misc.max, OR
* echo sev max > misc.max
*
* Context: Any context.
* Return:
* * >= 0 - Number of bytes processed in the input.
* * -EINVAL - If buf is not valid.
* * -ERANGE - If number is bigger than the unsigned long capacity.
*/
static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct misc_cg *cg;
unsigned long max;
int ret = 0, i;
enum misc_res_type type = MISC_CG_RES_TYPES;
char *token;
buf = strstrip(buf);
token = strsep(&buf, " ");
if (!token || !buf)
return -EINVAL;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
if (!strcmp(misc_res_name[i], token)) {
type = i;
break;
}
}
if (type == MISC_CG_RES_TYPES)
return -EINVAL;
if (!strcmp(MAX_STR, buf)) {
max = MAX_NUM;
} else {
ret = kstrtoul(buf, 0, &max);
if (ret)
return ret;
}
cg = css_misc(of_css(of));
if (READ_ONCE(misc_res_capacity[type]))
WRITE_ONCE(cg->res[type].max, max);
else
ret = -EINVAL;
return ret ? ret : nbytes;
}
/**
* misc_cg_current_show() - Show the current usage of the misc cgroup.
* @sf: Interface file
* @v: Arguments passed
*
* Context: Any context.
* Return: 0 to denote successful print.
*/
static int misc_cg_current_show(struct seq_file *sf, void *v)
{
int i;
unsigned long usage;
struct misc_cg *cg = css_misc(seq_css(sf));
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
usage = atomic_long_read(&cg->res[i].usage);
if (READ_ONCE(misc_res_capacity[i]) || usage)
seq_printf(sf, "%s %lu\n", misc_res_name[i], usage);
}
return 0;
}
/**
* misc_cg_capacity_show() - Show the total capacity of misc res on the host.
* @sf: Interface file
* @v: Arguments passed
*
* Only present in the root cgroup directory.
*
* Context: Any context.
* Return: 0 to denote successful print.
*/
static int misc_cg_capacity_show(struct seq_file *sf, void *v)
{
int i;
unsigned long cap;
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
cap = READ_ONCE(misc_res_capacity[i]);
if (cap)
seq_printf(sf, "%s %lu\n", misc_res_name[i], cap);
}
return 0;
}
/* Misc cgroup interface files */
static struct cftype misc_cg_files[] = {
{
.name = "max",
.write = misc_cg_max_write,
.seq_show = misc_cg_max_show,
.flags = CFTYPE_NOT_ON_ROOT,
},
{
.name = "current",
.seq_show = misc_cg_current_show,
.flags = CFTYPE_NOT_ON_ROOT,
},
{
.name = "capacity",
.seq_show = misc_cg_capacity_show,
.flags = CFTYPE_ONLY_ON_ROOT,
},
{}
};
/**
* misc_cg_alloc() - Allocate misc cgroup.
* @parent_css: Parent cgroup.
*
* Context: Process context.
* Return:
* * struct cgroup_subsys_state* - css of the allocated cgroup.
* * ERR_PTR(-ENOMEM) - No memory available to allocate.
*/
static struct cgroup_subsys_state *
misc_cg_alloc(struct cgroup_subsys_state *parent_css)
{
enum misc_res_type i;
struct misc_cg *cg;
if (!parent_css) {
cg = &root_cg;
} else {
cg = kzalloc(sizeof(*cg), GFP_KERNEL);
if (!cg)
return ERR_PTR(-ENOMEM);
}
for (i = 0; i < MISC_CG_RES_TYPES; i++) {
WRITE_ONCE(cg->res[i].max, MAX_NUM);
atomic_long_set(&cg->res[i].usage, 0);
}
return &cg->css;
}
/**
* misc_cg_free() - Free the misc cgroup.
* @css: cgroup subsys object.
*
* Context: Any context.
*/
static void misc_cg_free(struct cgroup_subsys_state *css)
{
kfree(css_misc(css));
}
/* Cgroup controller callbacks */
struct cgroup_subsys misc_cgrp_subsys = {
.css_alloc = misc_cg_alloc,
.css_free = misc_cg_free,
.legacy_cftypes = misc_cg_files,
.dfl_cftypes = misc_cg_files,
};
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment