[PATCH v19 18/20] x86/resctrl: Enable RMID shared RMID mode on Sub-NUMA Cluster (SNC) systems

[Tony Luck]

There is an MSR which configures how RMIDs are distributed across SNC
nodes. When SNC is enabled bit 0 of this MSR must be cleared.

Add an architecture specific hook into domain_add_cpu_mon() to call
a function to set the MSR.

Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/include/asm/msr-index.h       |  1 +
 arch/x86/kernel/cpu/resctrl/internal.h |  2 ++
 arch/x86/kernel/cpu/resctrl/core.c     |  2 ++
 arch/x86/kernel/cpu/resctrl/monitor.c  | 26 ++++++++++++++++++++++++++
 4 files changed, 31 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e022e6eb766c..3cb8dd6311c3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1164,6 +1164,7 @@
 #define MSR_IA32_QM_CTR			0xc8e
 #define MSR_IA32_PQR_ASSOC		0xc8f
 #define MSR_IA32_L3_CBM_BASE		0xc90
+#define MSR_RMID_SNC_CONFIG		0xca0
 #define MSR_IA32_L2_CBM_BASE		0xd10
 #define MSR_IA32_MBA_THRTL_BASE		0xd50
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 7957fc38b71c..08520321f5d0 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -532,6 +532,8 @@ static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 
 int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
+
 /*
  * Get the cacheinfo structure of the cache associated with @cpu at level @level.
  * cpuhp lock must be held.
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 95ef8fe3cb50..1930fce9dfe9 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -615,6 +615,8 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	}
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
+	arch_mon_domain_online(r, d);
+
 	if (arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
 		mon_domain_free(hw_dom);
 		return;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index e7a8e96821e5..c7559735e33a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -1069,6 +1069,32 @@ static void l3_mon_evt_init(struct rdt_resource *r)
 		list_add_tail(&mbm_local_event.list, &r->evt_list);
 }
 
+/*
+ * The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
+ * which indicates that RMIDs are configured in legacy mode.
+ * This mode is incompatible with Linux resctrl semantics
+ * as RMIDs are partitioned between SNC nodes, which requires
+ * a user to know which RMID is allocated to a task.
+ * Clearing bit 0 reconfigures the RMID counters for use
+ * in Sub-NUMA Cluster mode. This mode is better for Linux.
+ * The RMID space is divided between all SNC nodes with the
+ * RMIDs renumbered to start from zero in each node when
+ * counting operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * logical_rmid_to_physical_rmid() for code that does this.
+ */
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	u64 val;
+
+	if (snc_nodes_per_l3_cache == 1)
+		return;
+
+	rdmsrl(MSR_RMID_SNC_CONFIG, val);
+	val &= ~BIT_ULL(0);
+	wrmsrl(MSR_RMID_SNC_CONFIG, val);
+}
+
 int __init rdt_get_mon_l3_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
-- 
2.45.0