x86/resctrl: Fix AMD L3 QOS CDP enable/disable

When the AMD QoS feature CDP (code and data prioritization) is enabled
or disabled, the CDP bit in MSR 0000_0C81 is written on one of the CPUs
in an L3 domain (core complex). That is not correct - the CDP bit needs
to be updated on all the logical CPUs in the domain.

This was not spelled out clearly in the spec earlier. The specification
has been updated and the updated document, "AMD64 Technology Platform
Quality of Service Extensions Publication # 56375 Revision: 1.02 Issue
Date: October 2020" is available now. Refer the section: Code and Data
Prioritization.

Fix the issue by adding a new flag arch_has_per_cpu_cfg in rdt_cache
data structure.

The documentation can be obtained at:
https://developer.amd.com/wp-content/resources/56375.pdf
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537

 [ bp: Massage commit message. ]

Fixes: 4d05bf71f157 ("x86/resctrl: Introduce AMD QOS feature")
Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/160675180380.15628.3309402017215002347.stgit@bmoger-ubuntu

3 files changed, 14 insertions, 2 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e5f4ee8f4c3b..e8b5f1cf1ae8 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	if (d) {
 		cpumask_set_cpu(cpu, &d->cpu_mask);
+		if (r->cache.arch_has_per_cpu_cfg)
+			rdt_domain_reconfigure_cdp(r);
 		return;
 	}
 
@@ -923,6 +925,7 @@ static __init void rdt_init_res_defs_intel(void)
 		    r->rid == RDT_RESOURCE_L2CODE) {
 			r->cache.arch_has_sparse_bitmaps = false;
 			r->cache.arch_has_empty_bitmaps = false;
+			r->cache.arch_has_per_cpu_cfg = false;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
@@ -943,6 +946,7 @@ static __init void rdt_init_res_defs_amd(void)
 		    r->rid == RDT_RESOURCE_L2CODE) {
 			r->cache.arch_has_sparse_bitmaps = true;
 			r->cache.arch_has_empty_bitmaps = true;
+			r->cache.arch_has_per_cpu_cfg = true;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 80fa997fae60..f65d3c0dbc41 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -360,6 +360,8 @@ struct msr_param {
  *			executing entities
  * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
  * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
+ * @arch_has_per_cpu_cfg:	True if QOS_CFG register for this cache
+ *				level has CPU scope.
  */
 struct rdt_cache {
 	unsigned int	cbm_len;
@@ -369,6 +371,7 @@ struct rdt_cache {
 	unsigned int	shareable_bits;
 	bool		arch_has_sparse_bitmaps;
 	bool		arch_has_empty_bitmaps;
+	bool		arch_has_per_cpu_cfg;
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6f4ca4bea625..f3418428682b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1909,8 +1909,13 @@ static int set_cache_qos_cfg(int level, bool enable)
 
 	r_l = &rdt_resources_all[level];
 	list_for_each_entry(d, &r_l->domains, list) {
-		/* Pick one CPU from each domain instance to update MSR */
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		if (r_l->cache.arch_has_per_cpu_cfg)
+			/* Pick all the CPUs in the domain instance */
+			for_each_cpu(cpu, &d->cpu_mask)
+				cpumask_set_cpu(cpu, cpu_mask);
+		else
+			/* Pick one CPU from each domain instance to update MSR */
+			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 	}
 	cpu = get_cpu();
 	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */