[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH RESEND v5 01/24] docs: create L2 Cache Allocation Technology (CAT) feature document



> From: Yi Sun
> Sent: Thursday, January 19, 2017 2:01 PM
> 
> This patch creates L2 CAT feature document in doc/features/.
> It describes details of L2 CAT.

A good write-up, but still some improvements required. :-)

> 
> Signed-off-by: Yi Sun <yi.y.sun@xxxxxxxxxxxxxxx>
> ---
>  docs/features/intel_psr_l2_cat.pandoc | 347
> ++++++++++++++++++++++++++++++++++
>  1 file changed, 347 insertions(+)
>  create mode 100644 docs/features/intel_psr_l2_cat.pandoc
> 
> diff --git a/docs/features/intel_psr_l2_cat.pandoc
> b/docs/features/intel_psr_l2_cat.pandoc
> new file mode 100644
> index 0000000..77bd61f
> --- /dev/null
> +++ b/docs/features/intel_psr_l2_cat.pandoc
> @@ -0,0 +1,347 @@
> +% Intel L2 Cache Allocation Technology (L2 CAT) Feature
> +% Revision 1.0
> +
> +\clearpage
> +
> +# Basics
> +
> +---------------- ----------------------------------------------------
> +         Status: **Tech Preview**
> +
> +Architecture(s): Intel x86
> +
> +   Component(s): Hypervisor, toolstack
> +
> +       Hardware: Atom codename Goldmont and beyond CPUs
> +---------------- ----------------------------------------------------
> +
> +# Overview
> +
> +L2 CAT allows an OS or Hypervisor/VMM to control allocation of a
> +CPU's shared L2 cache based on application priority or Class of Service
> +(COS). Each CLOS is configured using capacity bitmasks (CBM) which
> +represent cache capacity and indicate the degree of overlap and
> +isolation between classes. Once L2 CAT is configured, the processor
> +allows access to portions of L2 cache according to the established
> +class of service.

I would suggest make this doc for all CAT features, otherwise some
content looks incomplete when you say adding new options or new
ranges with assumption that reader understands the existing stuff.
Yes I do notice you provide many background about L3 CAT/CDP. Let's
just make it complete.

Also as a permanent design, 'new' is not preferred since it will become
'existing' once it's checked in.

> +
> +## Terminology
> +
> +* CAT         Cache Allocation Technology
> +* CBM         Capacity BitMasks
> +* CDP         Code and Data Prioritization
> +* COS/CLOS    Class of Service
> +* MSRs        Machine Specific Registers
> +* PSR         Intel Platform Shared Resource
> +* VMM         Virtual Machine Monitor
> +
> +# User details
> +
> +* Feature Enabling:
> +
> +  Add "psr=cat" to boot line parameter to enable all supported level CAT
> +  features.
> +
> +* xl interfaces:
> +
> +  1. `psr-cat-show [OPTIONS] domain-id`:

Need an introduction of 'domain-id'. Is it a Xen domain ID, or
new hardware-defined domain ID (e.g. one socket per domain)?

> +
> +     Show domain L2 or L3 CAT CBM.

also please introduce how CBM actually works

> +
> +     New option `-l` is added.
> +     `-l2`: Show cbm for L2 cache.
> +     `-l3`: Show cbm for L3 cache.
> +
> +     If neither `-l2` nor `-l3` is given, show both of them. If any one
> +     is not supported, will print error info.
> +
> +  2. `psr-cat-cbm-set [OPTIONS] domain-id cbm`:
> +
> +     Set domain L2 or L3 CBM.

to be consistent with 'show' - 'CBM' or 'CAT CBM'?

I understand those xl interfaces are there already. If there is chance
to change, I'd recommend removing 'cbm'. Just psr-cat-set to be
consistent with 'show'.

> +
> +     New option `-l` is added.
> +     `-l2`: Specify cbm for L2 cache.
> +     `-l3`: Specify cbm for L3 cache.
> +
> +     If neither `-l2` nor `-l3` is given, level 3 is the default option.
> +
> +  3. `psr-hwinfo [OPTIONS]`:
> +
> +     Show L2 & L3 CAT HW informations on every socket.

informations -> information

and which HW information? please elaborate.

and where is the interface of setting COS for VCPU?

> +
> +# Technical details
> +
> +L2 CAT is a member of Intel PSR features and part of CAT, it shares
> +some base PSR infrastructure in Xen.

Then add some background of PSR would be useful if nothing exists yet?

> +
> +## Hardware perspective
> +
> +L2 CAT defines a new range MSRs to assign different L2 cache access
> +patterns which are known as CBMs, each CBM is associated with a COS.
> +
> +```
> +
> +                        +----------------------------+----------------+
> +   IA32_PQR_ASSOC       | MSR (per socket)           |    Address     |
> + +----+---+-------+     +----------------------------+----------------+
> + |    |COS|       |     | IA32_L2_QOS_MASK_0         |     0xD10      |
> + +----+---+-------+     +----------------------------+----------------+
> +        └-------------> | ...                        |  ...           |
> +                        +----------------------------+----------------+
> +                        | IA32_L2_QOS_MASK_n         | 0xD10+n (n<64) |
> +                        +----------------------------+----------------+
> +```
> +
> +When context switch happens, the COS of VCPU is written to per-thread
> +MSR `IA32_PQR_ASSOC`, and then hardware enforces L2 cache allocation
> +according to the corresponding CBM.
> +
> +## The relationship between L2 CAT and L3 CAT/CDP
> +
> +L2 CAT is independent of L3 CAT/CDP, which means L2 CAT would be enabled
> +while L3 CAT/CDP is disabled, or L2 CAT and L3 CAT/CDP are all enabled.
> +
> +L2 CAT uses a new range CBMs from 0xD10 ~ 0xD10+n (n<64), following by
> +the L3 CAT/CDP CBMs, and supports setting different L2 cache accessing
> +patterns from L3 cache. 

"L2 CAT supports ..." or "L3 CAT supports..." for the last sentence? 

> Like L3 CAT/CDP requirement, the bits of CBM of
> +L2 CAT must be continuous too.
> +
> +N.B. L2 CAT and L3 CAT/CDP share the same COS field in the same
> +associate register `IA32_PQR_ASSOC`, which means one COS associates to a
> +pair of L2 CBM and L3 CBM.
> +
> +Besides, the max COS of L2 CAT may be different from L3 CAT/CDP (or
> +other PSR features in future). In some cases, a VM is permitted to have a
> +COS that is beyond one (or more) of PSR features but within the others.
> +For instance, let's assume the max COS of L2 CAT is 8 but the max COS of
> +L3 CAT is 16, when a VM is assigned 9 as COS, the L3 CBM associated to
> +COS 9 would be enforced, but for L2 CAT, the behavior is fully open (no
> +limit) since COS 9 is beyond the max COS (8) of L2 CAT.

Does user space need to know such difference since L2 CAT may not 
be effective for this vCPU?
.."

> +
> +## Design Overview
> +
> +* Core COS/CBM association
> +
> +  When enforcing L2 CAT, all cores of domains have the same default
> +  COS (COS0) which associated to the fully open CBM (all ones bitmask)

please define 'open' when introducing CBM

> +  to access all L2 cache. The default COS is used only in hypervisor
> +  and is transparent to tool stack and user.
> +
> +  System administrator can change PSR allocation policy at runtime by
> +  tool stack. Since L2 CAT share COS with L3 CAT/CDP, a COS corresponds
> +  to a 2-tuple, like [L2 CBM, L3 CBM] with only-CAT enabled, when CDP
> +  is enabled, one COS corresponds to a 3-tuple, like [L2 CBM,
> +  L3 Code_CBM, L3 Data_CBM]. If neither L3 CAT nor L3 CDP is enabled,
> +  things would be easier, one COS corresponds to one L2 CBM.
> +
> +* VCPU schedule
> +
> +  This part reuses L3 CAT COS infrastructure.

Please elaborate then.

> +
> +* Multi-sockets
> +
> +  Different sockets may have different L2 CAT capability (e.g. max COS)
> +  although it is consistent on the same socket. So the capability of
> +  per-socket L2 CAT is specified.

VCPU schedule design is important here. e.g. when migrating a VCPU 
from socket 1 to socket 2 (socket 1 has max COS as 16 while socket
2 as 8), will you prevent migration if VCPU has a COS (9)?

> +
> +## Implementation Description
> +
> +* Hypervisor interfaces:
> +
> +  1. Boot line parameter "psr=cat" now will enable L2 CAT and L3
> +     CAT if hardware supported.
> +
> +  2. SYSCTL:
> +          - XEN_SYSCTL_PSR_CAT_get_l2_info: Get L2 CAT information.
> +
> +  3. DOMCTL:
> +          - XEN_DOMCTL_PSR_CAT_OP_GET_L2_CBM: Get L2 CBM for a domain.
> +          - XEN_DOMCTL_PSR_CAT_OP_SET_L2_CBM: Set L2 CBM for a domain.
> +
> +* xl interfaces:
> +
> +  1. psr-cat-show -l2 domain-id
> +          Show L2 cbm for a domain.
> +          => XEN_SYSCTL_PSR_CAT_get_l2_info /
> +             XEN_DOMCTL_PSR_CAT_OP_GET_L2_CBM
> +
> +  2. psr-mba-set -l2 domain-id cbm
> +          Set L2 cbm for a domain.
> +          => XEN_DOMCTL_PSR_CAT_OP_SET_L2_CBM
> +
> +  3. psr-hwinfo
> +          Show PSR HW information, including L2 CAT
> +          => XEN_SYSCTL_PSR_CAT_get_l2_info

still no interface about setting COS.

> +
> +* Key data structure:
> +
> +   1. Feature HW info
> +
> +      ```
> +      struct psr_cat_hw_info {
> +          unsigned int cbm_len;
> +          unsigned int cos_max;
> +      };
> +      ```
> +
> +      - Member `cbm_len`
> +
> +        `cbm_len` is one of the hardware info of CAT.
> +
> +      - Member `cos_max`
> +
> +        `cos_max` is one of the hardware info of CAT.
> +
> +   2. Feature list node
> +
> +      ```
> +      struct feat_node {
> +          enum psr_feat_type feature;
> +          struct feat_ops ops;
> +          struct psr_cat_hw_info info;
> +          uint64_t cos_reg_val[MAX_COS_REG_NUM];
> +          struct list_head list;
> +      };
> +      ```
> +
> +      When a PSR enforcement feature is enabled, it will be added into a
> +      feature list. The head of the list is created in psr initialization.
> +
> +      - Member `feature`
> +
> +        `feature` is an integer number, to indicate which feature the list 
> entry
> +        corresponds to.
> +
> +      - Member `ops`
> +
> +        `ops` maintains a callback function list of the feature. It will be 
> introduced
> +        in details later.
> +
> +      - Member `info`
> +
> +        `info` maintains the feature HW information which can be got through
> +        psr_hwinfo command.
> +
> +      - Member `cos_reg_val`
> +
> +        `cos_reg_val` is an array to maintain the value set in all COS 
> registers of
> +        the feature.
> +
> +   3. Per-socket PSR features information structure
> +
> +      ```
> +      struct psr_cat_socket_info {
> +          unsigned int feat_mask;
> +          unsigned int nr_feat;
> +          struct list_head feat_list;
> +          unsigned int cos_ref[MAX_COS_REG_NUM];
> +          spinlock_t ref_lock;
> +      };
> +      ```
> +
> +      We collect all PSR allocation features information of a socket in
> +      this `struct psr_cat_socket_info`.
> +
> +      - Member `feat_mask`
> +
> +        `feat_mask` is a bitmap, to indicate which feature is enabled on
> +        current socket. We define `feat_mask` bitmap as:
> +
> +        bit 0~1: L3 CAT status, [01] stands for L3 CAT only and [10]
> +                 stands for L3 CDP is enalbed.
> +
> +        bit 2: L2 CAT status.
> +
> +      - Member `cos_ref`
> +
> +        `cos_ref` is an array which maintains the reference of one COS.
> +        If the COS is used by one domain, the reference will increase one.
> +        If a domain releases the COS, the reference will decrease one. The
> +        array is indexed by COS.
> +
> +   4. Feature operation functions structure
> +
> +      ```
> +      struct feat_ops {
> +          void (*init_feature)(unsigned int eax, unsigned int ebx,
> +                               unsigned int ecx, unsigned int edx,
> +                               struct feat_node *feat,
> +                               struct psr_cat_socket_info *info);
> +          int (*get_feat_info)(const struct feat_node *feat, enum cbm_type 
> type,
> +                               uint32_t dat[], uint32_t array_len);
> +          int (*get_val)(const struct feat_node *feat, unsigned int cos,
> +                         enum cbm_type type, uint64_t *val);
> +          unsigned int (*get_max_cos_max)(const struct feat_node *feat);
> +          unsigned int (*get_cos_num)(const struct feat_node *feat);
> +          int (*get_old_val)(uint64_t val[],
> +                             const struct feat_node *feat,
> +                             unsigned int old_cos);
> +          int (*set_new_val)(uint64_t val[],
> +                             const struct feat_node *feat,
> +                             unsigned int old_cos,
> +                             enum cbm_type type,
> +                             uint64_t m);
> +          int (*compare_val)(const uint64_t val[], const struct feat_node 
> *feat,
> +                             unsigned int cos, bool *found);
> +          unsigned int (*get_cos_max_from_type)(const struct feat_node *feat,
> +                                                enum cbm_type type);
> +          unsigned int (*exceeds_cos_max)(const uint64_t val[],
> +                                          const struct feat_node *feat,
> +                                          unsigned int cos);
> +          int (*write_msr)(unsigned int cos, const uint64_t val[],
> +                           struct feat_node *feat);
> +      };
> +      ```
> +
> +      We abstract above callback functions to encapsulate the feature 
> specific
> +      behaviors into them. Then, it is easy to add a new feature. We just 
> need:
> +          1) Implement such ops and callback functions for every feature.
> +          2) Register the ops into `struct feat_node`.
> +          3) Add the feature into feature list during CPU initialization.
> +
> +# Limitations
> +
> +L2 CAT can only work on HW which enables it(check by CPUID). So far, there
> +is no HW enables both L2 CAT and L3 CAT/CDP. But SW implementation has 
> considered
> +such scenario to enable both L2 CAT and L3 CAT/CDP.
> +
> +# Testing
> +
> +L2 CAT uses same xl interfaces as L3 CAT/CDP. So, we can execute these
> +commands to verify L2 CAT and L3 CAT/CDP on different HWs support them.
> +
> +For example:
> +    root@:~$ xl psr-hwinfo --cat
> +    Cache Allocation Technology (CAT): L2
> +    Socket ID       : 0
> +    Maximum COS     : 3
> +    CBM length      : 8
> +    Default CBM     : 0xff
> +
> +    root@:~$ xl psr-cat-cbm-set -l2 1 0x7f
> +
> +    root@:~$ xl psr-cat-show -l2 1
> +    Socket ID       : 0
> +    Default CBM     : 0xff
> +       ID                     NAME             CBM
> +        1                 ubuntu14            0x7f
> +
> +# Areas for improvement
> +
> +N/A
> +
> +# Known issues
> +
> +N/A
> +
> +# References
> +
> +"INTEL® RESOURCE DIRECTOR TECHNOLOGY (INTEL® RDT) ALLOCATION FEATURES"
> [Intel® 64 and IA-32 Architectures Software Developer Manuals,
> vol3](http://www.intel.com/content/www/us/en/processors/architectures-software-dev
> eloper-manuals.html)
> +
> +# History
> +
> +------------------------------------------------------------------------
> +Date       Revision Version  Notes
> +---------- -------- -------- -------------------------------------------
> +2016-08-12 1.0      Xen 4.9  Design document written
> +---------- -------- -------- -------------------------------------------
> --
> 1.9.1
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxx
> https://lists.xen.org/xen-devel
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.