diff mbox series

[v3,1/2] cgroup: sev: Add misc cgroup controller

Message ID 20210304231946.2766648-2-vipinsh@google.com (mailing list archive)
State New, archived
Headers show
Series cgroup: New misc cgroup controller | expand

Commit Message

Vipin Sharma March 4, 2021, 11:19 p.m. UTC
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.

The first two resources added to the miscellaneous controller are Secure
Encrypted Virtualization (SEV) ASIDs and SEV - Encrypted State (SEV-ES)
ASIDs. These limited ASIDs are used for encrypting virtual machines
memory on the AMD platform

Miscellaneous controller provides 3 interface files:

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
	sev 50
	sev_es 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
	sev 3
	sev_es 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
	sev max
	sev_es 4

  Limit can be set by::

	# echo sev 1 > misc.max

  Limit can be set to max by::

	# echo sev max > misc.max

  Limits can be set more than the capacity value in the misc.capacity
  file.

Signed-off-by: Vipin Sharma <vipinsh@google.com>
Reviewed-by: David Rientjes <rientjes@google.com>
---
 arch/x86/kvm/svm/sev.c        |  65 +++++-
 arch/x86/kvm/svm/svm.h        |   1 +
 include/linux/cgroup_subsys.h |   4 +
 include/linux/misc_cgroup.h   | 130 +++++++++++
 init/Kconfig                  |  14 ++
 kernel/cgroup/Makefile        |   1 +
 kernel/cgroup/misc.c          | 402 ++++++++++++++++++++++++++++++++++
 7 files changed, 607 insertions(+), 10 deletions(-)
 create mode 100644 include/linux/misc_cgroup.h
 create mode 100644 kernel/cgroup/misc.c

Comments

Michal Koutný March 11, 2021, 6:59 p.m. UTC | #1
Hi Vipin.

On Thu, Mar 04, 2021 at 03:19:45PM -0800, Vipin Sharma <vipinsh@google.com> wrote:
>  arch/x86/kvm/svm/sev.c        |  65 +++++-
>  arch/x86/kvm/svm/svm.h        |   1 +
>  include/linux/cgroup_subsys.h |   4 +
>  include/linux/misc_cgroup.h   | 130 +++++++++++
>  init/Kconfig                  |  14 ++
>  kernel/cgroup/Makefile        |   1 +
>  kernel/cgroup/misc.c          | 402 ++++++++++++++++++++++++++++++++++
Given different two-fold nature (SEV caller vs misc controller) of some
remarks below, I think it makes sense to split this into two patches:
a) generic controller implementation,
b) hooking the controller into SEV ASIDs management.

> +#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.
BTW, was there any progress on conditioning sev.c build on
CONFIG_KVM_AMD_SEV? (So that the defines workaround isn't needeed.)

>  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;
> +	sev->misc_cg = get_current_misc_cg();
> +	ret = misc_cg_try_charge(type, sev->misc_cg, 1);
It may be safer to WARN_ON(sev->misc_cg) at this point (see below).


> [...]
> +e_uncharge:
> +	misc_cg_uncharge(type, sev->misc_cg, 1);
> +	put_misc_cg(sev->misc_cg);
> +	return ret;
vvv

> @@ -140,6 +171,10 @@ 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);
It may be safer to set sev->misc_cg to NULL here.

(IIUC, with current asid_{new,free} calls it shouldn't matter but why to
rely on it in the future.)

> +++ b/kernel/cgroup/misc.c
> [...]
> +static void misc_cg_reduce_charge(enum misc_res_type type, struct misc_cg *cg,
> +				  unsigned long amount)
misc_cg_cancel_charge seems to be a name more consistent with what we
already have in pids and memory controller.


> +static ssize_t misc_cg_max_write(struct kernfs_open_file *of, char *buf,
> +				 size_t nbytes, loff_t off)
> +{
> [...]
> +
> +	if (!strcmp(MAX_STR, buf)) {
> +		max = ULONG_MAX;
MAX_NUM for consistency with other places.

> +	} else {
> +		ret = kstrtoul(buf, 0, &max);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	cg = css_misc(of_css(of));
> +
> +	if (misc_res_capacity[type])
> +		cg->res[type].max = max;
In theory, parallel writers can clash here, so having the limit atomic
type to prevent this would resolve it. See also commit a713af394cf3
("cgroup: pids: use atomic64_t for pids->limit").

> +static int misc_cg_current_show(struct seq_file *sf, void *v)
> +{
> +	int i;
> +	struct misc_cg *cg = css_misc(seq_css(sf));
> +
> +	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
> +		if (misc_res_capacity[i])
Since there can be some residual charges after removing capacity (before
draining), maybe the condition along the line

if (misc_res_capacity[i] || atomic_long_read(&cg->res[i].usage))

would be more informative for debugging.

> +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]);
Why is READ_ONCE only here and not in other places that (actually) check
against the set capacity value? Also, there should be a paired
WRITE_ONCCE in misc_cg_set_capacity().


Thanks,
Michal
Vipin Sharma March 12, 2021, 7:07 p.m. UTC | #2
On Thu, Mar 11, 2021 at 07:59:03PM +0100, Michal Koutný wrote:
> Given different two-fold nature (SEV caller vs misc controller) of some
> remarks below, I think it makes sense to split this into two patches:
> a) generic controller implementation,
> b) hooking the controller into SEV ASIDs management.

Sounds good. I will split it.

> > +	if (misc_res_capacity[type])
> > +		cg->res[type].max = max;
> In theory, parallel writers can clash here, so having the limit atomic
> type to prevent this would resolve it. See also commit a713af394cf3
> ("cgroup: pids: use atomic64_t for pids->limit").

We should be fine without atomic64_t because we are using unsigned
long and not 64 bit explicitly. This will work on both 32 and 64 bit
machines.

But I will add READ_ONCE and WRITE_ONCE because of potential chances of
load tearing and store tearing.

Do you agree?

> > +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]);
> Why is READ_ONCE only here and not in other places that (actually) check
> against the set capacity value? Also, there should be a paired
> WRITE_ONCCE in misc_cg_set_capacity().

This was only here to avoid multiple reads of capacity and making sure
if condition and seq_print will see the same value. Also, I was not
aware of load and store tearing of properly aligned and machine word
size variables. I will add READ_ONCE and WRITE_ONCE at
other places.

Thanks
Vipin
Vipin Sharma March 12, 2021, 7:48 p.m. UTC | #3
On Thu, Mar 11, 2021 at 07:59:03PM +0100, Michal Koutný wrote:
> > +#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.
> BTW, was there any progress on conditioning sev.c build on
> CONFIG_KVM_AMD_SEV? (So that the defines workaround isn't needeed.)

Tom, Brijesh,
Is this something you guys thought about or have some plans to do in the
future? Basically to not include sev.c in compilation if
CONFIG_KVM_AMD_SEV is disabled.

Michal,
This should not be a blocker for misc controller. This thing can change
independent of misc cgroup.

Thanks
Vipin
Sean Christopherson March 12, 2021, 8:51 p.m. UTC | #4
On Fri, Mar 12, 2021, Vipin Sharma wrote:
> On Thu, Mar 11, 2021 at 07:59:03PM +0100, Michal Koutný wrote:
> > > +#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.
> > BTW, was there any progress on conditioning sev.c build on
> > CONFIG_KVM_AMD_SEV? (So that the defines workaround isn't needeed.)
> 
> Tom, Brijesh,
> Is this something you guys thought about or have some plans to do in the
> future? Basically to not include sev.c in compilation if
> CONFIG_KVM_AMD_SEV is disabled.

It's crossed my mind, but the number of stubs needed made me back off.  I'm
certainly not opposed to the idea, it's just not a trivial change.
Tom Lendacky March 12, 2021, 9:18 p.m. UTC | #5
On 3/12/21 2:51 PM, Sean Christopherson wrote:
> On Fri, Mar 12, 2021, Vipin Sharma wrote:
>> On Thu, Mar 11, 2021 at 07:59:03PM +0100, Michal Koutný wrote:
>>>> +#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.
>>> BTW, was there any progress on conditioning sev.c build on
>>> CONFIG_KVM_AMD_SEV? (So that the defines workaround isn't needeed.)
>>
>> Tom, Brijesh,
>> Is this something you guys thought about or have some plans to do in the
>> future? Basically to not include sev.c in compilation if
>> CONFIG_KVM_AMD_SEV is disabled.
> 
> It's crossed my mind, but the number of stubs needed made me back off.  I'm
> certainly not opposed to the idea, it's just not a trivial change.

Right, I looked at it when I was doing the SEV-ES work and came to the 
same conclusion.

Thanks,
Tom

>
Michal Koutný March 15, 2021, 6:34 p.m. UTC | #6
On Fri, Mar 12, 2021 at 11:07:14AM -0800, Vipin Sharma <vipinsh@google.com> wrote:
> We should be fine without atomic64_t because we are using unsigned
> long and not 64 bit explicitly. This will work on both 32 and 64 bit
> machines.
I see.

> But I will add READ_ONCE and WRITE_ONCE because of potential chances of
> load tearing and store tearing.
> 
> Do you agree?
Yes.

> This was only here to avoid multiple reads of capacity and making sure
> if condition and seq_print will see the same value.
Aha.

> Also, I was not aware of load and store tearing of properly aligned
> and machine word size variables. I will add READ_ONCE and WRITE_ONCE
> at other places.
Yeah, although it's theoretical, I think it also serves well to annotate
such unsychronized accesses.

Thanks,
Michal
Jacob Pan March 19, 2021, 9:28 p.m. UTC | #7
Hi Vipin,

On Thu,  4 Mar 2021 15:19:45 -0800, Vipin Sharma <vipinsh@google.com> wrote:

> +/* 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_
> +
nit: should you do #include <linux/cgroup.h>?
Otherwise, css may be undefined.

> +/**
> + * Types of misc cgroup entries supported by the host.
> + */

Thanks,

Jacob
Vipin Sharma March 22, 2021, 6:54 p.m. UTC | #8
On Fri, Mar 19, 2021 at 02:28:01PM -0700, Jacob Pan wrote:
> On Thu,  4 Mar 2021 15:19:45 -0800, Vipin Sharma <vipinsh@google.com> wrote:
> > +#ifndef _MISC_CGROUP_H_
> > +#define _MISC_CGROUP_H_
> > +
> nit: should you do #include <linux/cgroup.h>?
> Otherwise, css may be undefined.

User of this controller will use get_curernt_misc_cg() API which returns
a pointer. Ideally the user should use this pointer and they shouldn't have
any need to access "css" in their code. They also don't need to create a
object of 'struct misc_cg{}', because that won't be correct misc cgroup
object. They should just declare a pointer like we are doing here in
'struct kvm_sev_info {}'.

If they do need to use "css" then they can include cgroup header in their
code.

Let me know if I am overlooking something here.

Thanks
Vipin Sharma
Jacob Pan March 24, 2021, 4:17 p.m. UTC | #9
Hi Vipin,

On Mon, 22 Mar 2021 11:54:39 -0700, Vipin Sharma <vipinsh@google.com> wrote:

> On Fri, Mar 19, 2021 at 02:28:01PM -0700, Jacob Pan wrote:
> > On Thu,  4 Mar 2021 15:19:45 -0800, Vipin Sharma <vipinsh@google.com>
> > wrote:  
> > > +#ifndef _MISC_CGROUP_H_
> > > +#define _MISC_CGROUP_H_
> > > +  
> > nit: should you do #include <linux/cgroup.h>?
> > Otherwise, css may be undefined.  
> 
> User of this controller will use get_curernt_misc_cg() API which returns
> a pointer. Ideally the user should use this pointer and they shouldn't
> have any need to access "css" in their code. They also don't need to
> create a object of 'struct misc_cg{}', because that won't be correct misc
> cgroup object. They should just declare a pointer like we are doing here
> in 'struct kvm_sev_info {}'.
> 
> If they do need to use "css" then they can include cgroup header in their
> code.
> 
I didn't mean the users of misc_cgroup will use css directly. I meant if I
want to use misc cgruop in ioasid.c, I have to do the following to avoid
undefined css:
#include <linux/cgroup.h>
#include <linux/misc_cgroup.h>

So it might be simpler if you do #include <linux/cgroup.h> inside
misc_cgroup.h. Then in ioasid.c, I only need to do
#include <linux/misc_cgroup.h>.

> Let me know if I am overlooking something here.
> 
> Thanks
> Vipin Sharma


Thanks,

Jacob
Vipin Sharma March 24, 2021, 10:09 p.m. UTC | #10
On Wed, Mar 24, 2021 at 09:17:01AM -0700, Jacob Pan wrote:
> I didn't mean the users of misc_cgroup will use css directly. I meant if I
> want to use misc cgruop in ioasid.c, I have to do the following to avoid
> undefined css:
> #include <linux/cgroup.h>
> #include <linux/misc_cgroup.h>
> 
> So it might be simpler if you do #include <linux/cgroup.h> inside
> misc_cgroup.h. Then in ioasid.c, I only need to do
> #include <linux/misc_cgroup.h>.

Sorry, I misunderstood the comment first time. I agree with you, I will
add cgroup header file in the misc_cgroup.h after  #ifdef
CONFIG_CGROUP_MISC statement.

Thanks
Vipin
diff mbox series

Patch

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 48017fef1cd9..dd05a1522862 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -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>
@@ -27,6 +28,21 @@ 
 
 #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);
@@ -88,8 +104,17 @@  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;
+	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);
+		return ret;
+	}
 
 	mutex_lock(&sev_bitmap_lock);
 
@@ -107,7 +132,8 @@  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);
@@ -115,6 +141,10 @@  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);
+	return ret;
 }
 
 static int sev_get_asid(struct kvm *kvm)
@@ -124,14 +154,15 @@  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) {
@@ -140,6 +171,10 @@  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);
 }
 
 static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
@@ -187,19 +222,19 @@  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);
 	return ret;
 }
 
@@ -1243,12 +1278,12 @@  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;
 
@@ -1280,7 +1315,11 @@  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? */
@@ -1295,7 +1334,11 @@  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:
@@ -1310,6 +1353,8 @@  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();
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 6e7d070f8b86..8ed6ebf47885 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -79,6 +79,7 @@  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 {
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index acb77dcff3b4..445235487230 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -61,6 +61,10 @@  SUBSYS(pids)
 SUBSYS(rdma)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_MISC)
+SUBSYS(misc)
+#endif
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h
new file mode 100644
index 000000000000..c807840c9238
--- /dev/null
+++ b/include/linux/misc_cgroup.h
@@ -0,0 +1,130 @@ 
+/* 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
+
+/**
+ * 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 */
+
+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_ */
diff --git a/init/Kconfig b/init/Kconfig
index 29ad68325028..0b392135e555 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1105,6 +1105,20 @@  config CGROUP_BPF
 	  BPF_CGROUP_INET_INGRESS will be executed on the ingress path of
 	  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
 	bool "Debug controller"
 	default n
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile
index 5d7a76bfbbb7..12f8457ad1f9 100644
--- a/kernel/cgroup/Makefile
+++ b/kernel/cgroup/Makefile
@@ -5,4 +5,5 @@  obj-$(CONFIG_CGROUP_FREEZER) += legacy_freezer.o
 obj-$(CONFIG_CGROUP_PIDS) += pids.o
 obj-$(CONFIG_CGROUP_RDMA) += rdma.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CGROUP_MISC) += misc.o
 obj-$(CONFIG_CGROUP_DEBUG) += debug.o
diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c
new file mode 100644
index 000000000000..393d66c0b933
--- /dev/null
+++ b/kernel/cgroup/misc.c
@@ -0,0 +1,402 @@ 
+// 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
+	"sev",
+	"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(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;
+
+	misc_res_capacity[type] = capacity;
+	return 0;
+}
+EXPORT_SYMBOL(misc_cg_set_capacity);
+
+/**
+ * misc_cg_reduce_charge() - Reduce the charge from the misc cgroup.
+ * @type: Misc res type in misc cg to reduce the charge from.
+ * @cg: Misc cgroup to reduce charge from.
+ * @amount: Amount to reduce.
+ *
+ * Context: Any context.
+ */
+static void misc_cg_reduce_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 && 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 > res->max ||
+		    new_usage > 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_reduce_charge(type, j, amount);
+	misc_cg_reduce_charge(type, i, amount);
+	return ret;
+}
+EXPORT_SYMBOL(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_reduce_charge(type, i, amount);
+}
+EXPORT_SYMBOL(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));
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		if (misc_res_capacity[i]) {
+			if (cg->res[i].max == MAX_NUM)
+				seq_printf(sf, "%s max\n", misc_res_name[i]);
+			else
+				seq_printf(sf, "%s %lu\n", misc_res_name[i],
+					   cg->res[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 = ULONG_MAX;
+	} else {
+		ret = kstrtoul(buf, 0, &max);
+		if (ret)
+			return ret;
+	}
+
+	cg = css_misc(of_css(of));
+
+	if (misc_res_capacity[type])
+		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;
+	struct misc_cg *cg = css_misc(seq_css(sf));
+
+	for (i = 0; i < MISC_CG_RES_TYPES; i++) {
+		if (misc_res_capacity[i])
+			seq_printf(sf, "%s %lu\n", misc_res_name[i],
+				   atomic_long_read(&cg->res[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++) {
+		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,
+};