1

x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files

When SNC is enabled, monitoring data is collected at the SNC node granularity,
but must be reported at L3-cache granularity for backwards compatibility in
addition to reporting at the node level.

Add a "ci" field to the rdt_mon_domain structure to save the cache information
about the enclosing L3 cache for the domain.  This provides:

1) The cache id which is needed to compose the name of the legacy monitoring
   directory, and to determine which domains should be summed to provide
   L3-scoped data.

2) The shared_cpu_map which is needed to determine which CPUs can be used to
   read the RMID counters with the MSR interface.

This is the first step to an eventual goal of monitor reporting files like this
(for a system with two SNC nodes per L3):

  $ cd /sys/fs/resctrl/mon_data
  $ tree mon_L3_00
  mon_L3_00			<- 00 here is L3 cache id
  ├── llc_occupancy		\  These files provide legacy support
  ├── mbm_local_bytes		 > for non-SNC aware monitor apps
  ├── mbm_total_bytes		/  that expect data at L3 cache level
  ├── mon_sub_L3_00		<- 00 here is SNC node id
  │   ├── llc_occupancy		\  These files are finer grained
  │   ├── mbm_local_bytes		 > data from each SNC node
  │   └── mbm_total_bytes		/
  └── mon_sub_L3_01
      ├── llc_occupancy		\
      ├── mbm_local_bytes		 > As above, but for node 1.
      └── mbm_total_bytes		/

  [ bp: Massage commit message. ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Link: https://lore.kernel.org/r/20240628215619.76401-9-tony.luck@intel.com
This commit is contained in:
Tony Luck 2024-06-28 14:56:08 -07:00 committed by Borislav Petkov (AMD)
parent ac20aa4230
commit 328ea68874
4 changed files with 9 additions and 3 deletions

View File

@ -19,7 +19,6 @@
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/cacheinfo.h>
#include <linux/cpuhotplug.h>
#include <asm/cpu_device_id.h>
@ -608,6 +607,12 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
d = &hw_dom->d_resctrl;
d->hdr.id = id;
d->hdr.type = RESCTRL_MON_DOMAIN;
d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
if (!d->ci) {
pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
mon_domain_free(hw_dom);
return;
}
cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {

View File

@ -11,7 +11,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>

View File

@ -12,7 +12,6 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
#include <linux/fs.h>

View File

@ -2,6 +2,7 @@
#ifndef _RESCTRL_H
#define _RESCTRL_H
#include <linux/cacheinfo.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/pid.h>
@ -96,6 +97,7 @@ struct rdt_ctrl_domain {
/**
* struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
* @hdr: common header for different domain types
* @ci: cache info for this domain
* @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold
* @mbm_total: saved state for MBM total bandwidth
* @mbm_local: saved state for MBM local bandwidth
@ -106,6 +108,7 @@ struct rdt_ctrl_domain {
*/
struct rdt_mon_domain {
struct rdt_domain_hdr hdr;
struct cacheinfo *ci;
unsigned long *rmid_busy_llc;
struct mbm_state *mbm_total;
struct mbm_state *mbm_local;