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

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

Documentation/admin-guide/cgroup-v1/index.rst

+1 −0
Original line number Diff line number Diff line
@@ -17,6 +17,7 @@ Control Groups version 1 
    hugetlb

    memcg_test

    memory

    misc

    net_cls

    net_prio

    pids

Documentation/admin-guide/cgroup-v1/misc.rst

0 → 100644
+4 −0
Original line number Diff line number Diff line 
===============

Misc controller

===============

Please refer "Misc" documentation in Documentation/admin-guide/cgroup-v2.rst

Documentation/admin-guide/cgroup-v2.rst

+71 −2
Original line number Diff line number Diff line
@@ -65,8 +65,11 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgrou 
       5-7-1. RDMA Interface Files

     5-8. HugeTLB

       5.8-1. HugeTLB Interface Files

     5-8. Misc

       5-8-1. perf_event

     5-9. Misc

       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-1. CPU controller root cgroup process behaviour

       5-N-2. IO controller root cgroup process behaviour
@@ -2171,6 +2174,72 @@ HugeTLB Interface Files 
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

~~~~~~~~~~

arch/x86/kvm/svm/sev.c

+60 −10
Original line number Diff line number Diff line
@@ -14,6 +14,7 @@ 
#include <linux/psp-sev.h>

#include <linux/pagemap.h>

#include <linux/swap.h>

#include <linux/misc_cgroup.h>

#include <linux/processor.h>

#include <linux/trace_events.h>

#include <asm/fpu/internal.h>
@@ -28,6 +29,21 @@ 


#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 int sev_flush_asids(void);

static DECLARE_RWSEM(sev_deactivate_lock);
@@ -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)

{

	int pos, min_asid, max_asid;

	int pos, min_asid, max_asid, ret;

	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);
@@ -108,7 +135,8 @@ static int sev_asid_new(struct kvm_sev_info *sev) 
			goto again;

		}

		mutex_unlock(&sev_bitmap_lock);

		return -EBUSY;

		ret = -EBUSY;

		goto e_uncharge;

	}



	__set_bit(pos, sev_asid_bitmap);
@@ -116,6 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev) 
	mutex_unlock(&sev_bitmap_lock);



	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)
@@ -125,14 +158,15 @@ static int sev_get_asid(struct kvm *kvm) 
	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;

	int cpu, pos;

	enum misc_res_type type;



	mutex_lock(&sev_bitmap_lock);



	pos = asid - 1;

	pos = sev->asid - 1;

	__set_bit(pos, sev_reclaim_asid_bitmap);



	for_each_possible_cpu(cpu) {
@@ -141,6 +175,11 @@ static void sev_asid_free(int asid) 
	}



	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)
@@ -188,19 +227,20 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) 
	asid = sev_asid_new(sev);

	if (asid < 0)

		return ret;

	sev->asid = asid;



	ret = sev_platform_init(&argp->error);

	if (ret)

		goto e_free;



	sev->active = true;

	sev->asid = asid;

	INIT_LIST_HEAD(&sev->regions_list);



	return 0;



e_free:

	sev_asid_free(asid);

	sev_asid_free(sev);

	sev->asid = 0;

	return ret;

}
@@ -1315,12 +1355,12 @@ void sev_vm_destroy(struct kvm *kvm) 
	mutex_unlock(&kvm->lock);



	sev_unbind_asid(kvm, sev->handle);

	sev_asid_free(sev->asid);

	sev_asid_free(sev);

}



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_supported = false;
@@ -1352,7 +1392,11 @@ void __init sev_hardware_setup(void) 
	if (!sev_reclaim_asid_bitmap)

		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-ES support requested? */
@@ -1367,7 +1411,11 @@ void __init sev_hardware_setup(void) 
	if (min_sev_asid == 1)

		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;



out:
@@ -1382,6 +1430,8 @@ void sev_hardware_teardown(void) 


	bitmap_free(sev_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();

}

arch/x86/kvm/svm/svm.h

+1 −0
Original line number Diff line number Diff line
@@ -65,6 +65,7 @@ struct kvm_sev_info { 
	unsigned long pages_locked; /* Number of pages locked */

	struct list_head regions_list;  /* List of registered regions */

	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */

	struct misc_cg *misc_cg; /* For misc cgroup accounting */

};



struct kvm_svm {