1. Patchew
  2. linux
  3. [PATCH v3 0/8] x86/resctrl: Add support for Sub-NUMA cluster (SNC) systems
  4. View patch

[PATCH v3 4/8] x86/resctrl: Add code to setup monitoring at L3 or NODE scope.

Tony Luck posted 8 patches 2 years, 2 months ago
[PATCH v3 4/8] x86/resctrl: Add code to setup monitoring at L3 or NODE scope.
Posted by Tony Luck 2 years, 2 months ago 
When Sub-NUMA cluster is enabled (snc_ways > 1) use the RDT_RESOURCE_NODE
instead of RDT_RESOURCE_L3 for all monitoring operations.

The mon_scale and num_rmid values from CPUID(0xf,0x1),(EBX,ECX) must be
scaled down by the number of Sub-NUMA Clusters.

A subsequent change will detect sub-NUMA cluster mode and set
"snc_ways". For now set to one (meaning each L3 cache spans one
node).

Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Peter Newman <peternewman@google.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h | 7 +++++++
 arch/x86/kernel/cpu/resctrl/core.c     | 7 ++++++-
 arch/x86/kernel/cpu/resctrl/monitor.c  | 4 ++--
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +-
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 243017096ddf..38bac0062c82 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -430,6 +430,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
 extern struct dentry *debugfs_resctrl;
 
+extern int snc_ways;
+
 enum resctrl_res_level {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L2,
@@ -447,6 +449,11 @@ enum resctrl_scope {
 	SCOPE_NODE,
 };
 
+static inline int get_mbm_res_level(void)
+{
+	return snc_ways > 1 ? RDT_RESOURCE_NODE : RDT_RESOURCE_L3;
+}
+
 static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e4bd3072927c..6fe9f87d4403 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -48,6 +48,11 @@ int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
+/*
+ * How many Sub-Numa Cluster nodes share a single L3 cache
+ */
+int snc_ways = 1;
+
 static void
 mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
 		struct rdt_resource *r);
@@ -831,7 +836,7 @@ static __init bool get_rdt_alloc_resources(void)
 
 static __init bool get_rdt_mon_resources(void)
 {
-	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+	struct rdt_resource *r = &rdt_resources_all[get_mbm_res_level()].r_resctrl;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
 		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 9be6ffdd01ae..da3f36212898 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -787,8 +787,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 	int ret;
 
 	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
-	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
-	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
+	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_ways;
+	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_ways;
 	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
 
 	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 418658f0a9ad..d037f3da9e55 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2524,7 +2524,7 @@ static int rdt_get_tree(struct fs_context *fc)
 		static_branch_enable_cpuslocked(&rdt_enable_key);
 
 	if (is_mbm_enabled()) {
-		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+		r = &rdt_resources_all[get_mbm_res_level()].r_resctrl;
 		list_for_each_entry(dom, &r->domains, list)
 			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
 	}
-- 
2.40.1
Re: [PATCH v3 4/8] x86/resctrl: Add code to setup monitoring at L3 or NODE scope.
Posted by Reinette Chatre 2 years, 1 month ago 
Hi Tony,

Regarding subject: "Add code" is not necessary.

On 7/13/2023 9:32 AM, Tony Luck wrote:
> When Sub-NUMA cluster is enabled (snc_ways > 1) use the RDT_RESOURCE_NODE
> instead of RDT_RESOURCE_L3 for all monitoring operations.

This duplication of resource does not look right to me.
RDT_RESOURCE_NODE now contains the monitoring data for RDT_RESOURCE_L3
with related structures within RDT_RESOURCE_L3 going unused.

> 
> The mon_scale and num_rmid values from CPUID(0xf,0x1),(EBX,ECX) must be
> scaled down by the number of Sub-NUMA Clusters.
> 
> A subsequent change will detect sub-NUMA cluster mode and set
> "snc_ways". For now set to one (meaning each L3 cache spans one
> node).
> 
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> Reviewed-by: Peter Newman <peternewman@google.com>
> ---
>  arch/x86/kernel/cpu/resctrl/internal.h | 7 +++++++
>  arch/x86/kernel/cpu/resctrl/core.c     | 7 ++++++-
>  arch/x86/kernel/cpu/resctrl/monitor.c  | 4 ++--
>  arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +-
>  4 files changed, 16 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index 243017096ddf..38bac0062c82 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -430,6 +430,8 @@ DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
>  
>  extern struct dentry *debugfs_resctrl;
>  
> +extern int snc_ways;
> +
>  enum resctrl_res_level {
>  	RDT_RESOURCE_L3,
>  	RDT_RESOURCE_L2,
> @@ -447,6 +449,11 @@ enum resctrl_scope {
>  	SCOPE_NODE,
>  };
>  
> +static inline int get_mbm_res_level(void)
> +{
> +	return snc_ways > 1 ? RDT_RESOURCE_NODE : RDT_RESOURCE_L3;
> +}

Need to return the enum here? It may be simpler for this helper to
just return a pointer to the resource. (Although the need for a
separate resource is still not clear to me.)

> +
>  static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
>  {
>  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
> diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
> index e4bd3072927c..6fe9f87d4403 100644
> --- a/arch/x86/kernel/cpu/resctrl/core.c
> +++ b/arch/x86/kernel/cpu/resctrl/core.c
> @@ -48,6 +48,11 @@ int max_name_width, max_data_width;
>   */
>  bool rdt_alloc_capable;
>  
> +/*
> + * How many Sub-Numa Cluster nodes share a single L3 cache
> + */
> +int snc_ways = 1;
> +

Since snc_ways is always used I think the comment should provide
more detail on the possible values it may have. For example, to
a reader it may not be obvious what the value of snc_ways should be
if SNC is disabled. Also, what does "ways" refer to? (Also mentioned
later).

>  static void
>  mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
>  		struct rdt_resource *r);
> @@ -831,7 +836,7 @@ static __init bool get_rdt_alloc_resources(void)
>  
>  static __init bool get_rdt_mon_resources(void)
>  {
> -	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
> +	struct rdt_resource *r = &rdt_resources_all[get_mbm_res_level()].r_resctrl;
>  
>  	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
>  		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 9be6ffdd01ae..da3f36212898 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -787,8 +787,8 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
>  	int ret;
>  
>  	resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
> -	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
> -	r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
> +	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale / snc_ways;
> +	r->num_rmid = (boot_cpu_data.x86_cache_max_rmid + 1) / snc_ways;
>  	hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
>  
>  	if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX)
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 418658f0a9ad..d037f3da9e55 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -2524,7 +2524,7 @@ static int rdt_get_tree(struct fs_context *fc)
>  		static_branch_enable_cpuslocked(&rdt_enable_key);
>  
>  	if (is_mbm_enabled()) {
> -		r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
> +		r = &rdt_resources_all[get_mbm_res_level()].r_resctrl;
>  		list_for_each_entry(dom, &r->domains, list)
>  			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
>  	}

This final hunk makes me wonder why the monitor.c:
mon_resource is necessary at all. A single helper used everywhere
may be simpler.

Reinette

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.