Skip to contentSkip to conversation

x86/resctrl: Fix arch_mbm_* array overrun on SNC

PATCH Applied Peter Newman 3 participants 3 messages Aug 22, 2024 – Aug 28, 2024

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 x86/resctrl: Fix arch_mbm_* array overrun on SNC

When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays.

This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently:

resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache

As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86.

Fixes e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache")

---
v1->v2:
- Squashed blank lines added to linux/resctrl.h
- Reviewed-by Reinette

v1: https://lore.kernel.org/lkml/[email protected]/

 arch/x86/include/asm/resctrl.h     | 6 ------
 arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++
 include/linux/resctrl.h            | 1 +
 3 files changed, 9 insertions(+), 6 deletions(-)
arch/x86/include/asm/resctrl.h +0 -6
index 12dbd2588ca7..8b1b6ce1e51b 100644
@@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk)
 		__resctrl_sched_in(tsk);
 }
 
-static inline u32 resctrl_arch_system_num_rmid_idx(void)
-{
-	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
-	return boot_cpu_data.x86_cache_max_rmid + 1;
-}
-
 static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
 {
 	*rmid = idx;
arch/x86/kernel/cpu/resctrl/core.c +8 -0
index 1930fce9dfe9..8591d53c144b 100644
@@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = {
 	},
 };
 
+u32 resctrl_arch_system_num_rmid_idx(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
+	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+	return r->num_rmid;
+}
+
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
  * as they do not have CPUID enumeration support for Cache allocation.
include/linux/resctrl.h +1 -0
index b0875b99e811..d94abba1c716 100644
@@ -248,6 +248,7 @@ struct resctrl_schema {
 
 /* The number of closid supported by this resource regardless of CDP */
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
+u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 /*

base-commit: 47ac09b91befbb6a235ab620c32af719f8208399

Signature · 1 line
2.46.0.295.g3b9ea8a38a-goog
maintainer
#1 lore raw

Thank you very much Peter.

Boris, could you please consider this for inclusion?

Thank you

Reinette

Quoted 78 lines · Peter Newman

When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays.

This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently:

resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache

As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86.

Fixes e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache")

---
v1->v2:
- Squashed blank lines added to linux/resctrl.h
- Reviewed-by Reinette

v1: https://lore.kernel.org/lkml/[email protected]/

  arch/x86/include/asm/resctrl.h     | 6 ------
  arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++
  include/linux/resctrl.h            | 1 +
  3 files changed, 9 insertions(+), 6 deletions(-)
arch/x86/include/asm/resctrl.h +0 -6
index 12dbd2588ca7..8b1b6ce1e51b 100644
@@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk)
  		__resctrl_sched_in(tsk);
  }
 
-static inline u32 resctrl_arch_system_num_rmid_idx(void)
-{
-	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
-	return boot_cpu_data.x86_cache_max_rmid + 1;
-}
-
  static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
  {
  	*rmid = idx;
arch/x86/kernel/cpu/resctrl/core.c +8 -0
index 1930fce9dfe9..8591d53c144b 100644
@@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = {
  	},
  };
 
+u32 resctrl_arch_system_num_rmid_idx(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
+	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+	return r->num_rmid;
+}
+
  /*
   * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
   * as they do not have CPUID enumeration support for Cache allocation.
include/linux/resctrl.h +1 -0
index b0875b99e811..d94abba1c716 100644
@@ -248,6 +248,7 @@ struct resctrl_schema {
 
  /* The number of closid supported by this resource regardless of CDP */
  u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
+u32 resctrl_arch_system_num_rmid_idx(void);
  int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
  /*

base-commit: 47ac09b91befbb6a235ab620c32af719f8208399

merge bot Applied
#2 lore raw
In reply to Peter Newman
The following commit has been merged into the x86/urgent branch of tip:

The following commit has been merged into the x86/urgent branch of tip:

Commit-ID:     a547a5880cba6f287179135381f1b484b251be31
Gitweb:        https://git.kernel.org/tip/a547a5880cba6f287179135381f1b484b251be31
Author:        Peter Newman <[email protected]>
AuthorDate:    Thu, 22 Aug 2024 12:02:11 -07:00
Committer:     Borislav Petkov (AMD) <[email protected]>
CommitterDate: Wed, 28 Aug 2024 11:13:08 +02:00

x86/resctrl: Fix arch_mbm_* array overrun on SNC

When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays.

This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently:

resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache

As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86.

Fixes e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache")
---
 arch/x86/include/asm/resctrl.h     | 6 ------
 arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++
 include/linux/resctrl.h            | 1 +
 3 files changed, 9 insertions(+), 6 deletions(-)
arch/x86/include/asm/resctrl.h +0 -6
index 12dbd25..8b1b6ce 100644
@@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk)
 		__resctrl_sched_in(tsk);
 }
 
-static inline u32 resctrl_arch_system_num_rmid_idx(void)
-{
-	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
-	return boot_cpu_data.x86_cache_max_rmid + 1;
-}
-
 static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
 {
 	*rmid = idx;
arch/x86/kernel/cpu/resctrl/core.c +8 -0
index 1930fce..8591d53 100644
@@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = {
 	},
 };
 
+u32 resctrl_arch_system_num_rmid_idx(void)
+{
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+
+	/* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+	return r->num_rmid;
+}
+
 /*
  * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
  * as they do not have CPUID enumeration support for Cache allocation.
include/linux/resctrl.h +1 -0
index b0875b9..d94abba 100644
@@ -248,6 +248,7 @@ struct resctrl_schema {
 
 /* The number of closid supported by this resource regardless of CDP */
 u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
+u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
 /*