Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:3 as permitted sender) client-ip=2620:137:e000::3:3;
From:   Tony Luck <tony.luck@intel.com>
To:     Fenghua Yu <fenghua.yu@intel.com>,
        Reinette Chatre <reinette.chatre@intel.com>,
        Peter Newman <peternewman@google.com>,
        Jonathan Corbet <corbet@lwn.net>,
        Shuah Khan <skhan@linuxfoundation.org>, x86@kernel.org
Cc:     Shaopeng Tan <tan.shaopeng@fujitsu.com>,
        James Morse <james.morse@arm.com>,
        Jamie Iles <quic_jiles@quicinc.com>,
        Babu Moger <babu.moger@amd.com>,
        Randy Dunlap <rdunlap@infradead.org>,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        patches@lists.linux.dev, Tony Luck <tony.luck@intel.com>,
        Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Subject: [PATCH v13 7/8] x86/resctrl: Sub NUMA Cluster detection and enable
Date:   Mon,  4 Dec 2023 10:53:56 -0800
Message-ID: <20231204185357.120501-8-tony.luck@intel.com>
In-Reply-To: <20231204185357.120501-1-tony.luck@intel.com>
References: <20231130003418.89964-1-tony.luck@intel.com>
 <20231204185357.120501-1-tony.luck@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

There isn't a simple hardware bit that indicates whether a CPU is
running in Sub NUMA Cluster (SNC) mode. Infer the state by comparing
the ratio of NUMA nodes to L3 cache instances.

When SNC mode is detected, reconfigure the RMID counters by updating
the MSR_RMID_SNC_CONFIG MSR on each socket as CPUs are seen.

Clearing bit zero of the MSR divides the RMIDs and renumbers the ones
on the second SNC node to start from zero.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Peter Newman <peternewman@google.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
---
 arch/x86/include/asm/msr-index.h   |   1 +
 arch/x86/kernel/cpu/resctrl/core.c | 118 +++++++++++++++++++++++++++++
 2 files changed, 119 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d51e1850ed0..94d29d81e6db 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1111,6 +1111,7 @@
 #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/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index cf5aba8a74bf..1de1c4499b7d 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -16,11 +16,14 @@
 
 #define pr_fmt(fmt)	"resctrl: " fmt
 
+#include <linux/cpu.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/cacheinfo.h>
 #include <linux/cpuhotplug.h>
+#include <linux/mod_devicetable.h>
 
+#include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
 #include <asm/resctrl.h>
 #include "internal.h"
@@ -740,11 +743,42 @@ static void clear_closid_rmid(int cpu)
 	wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
 }
 
+/*
+ * 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
+ * couning operations from tasks. Code to read the counters
+ * must adjust RMID counter numbers based on SNC node. See
+ * __rmid_read() for code that does this.
+ */
+static void snc_remap_rmids(int cpu)
+{
+	u64 val;
+
+	/* Only need to enable once per package. */
+	if (cpumask_first(topology_core_cpumask(cpu)) != cpu)
+		return;
+
+	rdmsrl(MSR_RMID_SNC_CONFIG, val);
+	val &= ~BIT_ULL(0);
+	wrmsrl(MSR_RMID_SNC_CONFIG, val);
+}
+
 static int resctrl_online_cpu(unsigned int cpu)
 {
 	struct rdt_resource *r;
 
 	mutex_lock(&rdtgroup_mutex);
+
+	if (snc_nodes_per_l3_cache > 1)
+		snc_remap_rmids(cpu);
+
 	for_each_capable_rdt_resource(r)
 		domain_add_cpu(cpu, r);
 	/* The cpu is set in default rdtgroup after online. */
@@ -999,11 +1033,95 @@ static __init bool get_rdt_resources(void)
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+/* CPU models that support MSR_RMID_SNC_CONFIG */
+static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, 0),
+	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, 0),
+	{}
+};
+
+/*
+ * There isn't a simple hardware bit that indicates whether a CPU is running
+ * in Sub NUMA Cluster (SNC) mode. Infer the state by comparing the
+ * ratio of NUMA nodes to L3 cache instances.
+ * It is not possible to accurately determine SNC state if the system is
+ * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
+ * to L3 caches. It will be OK if system is booted with hyperthreading
+ * disabled (since this doesn't affect the ratio).
+ */
+static __init int snc_get_config(void)
+{
+	unsigned long *node_caches;
+	int mem_only_nodes = 0;
+	int cpu, node, ret;
+	int num_l3_caches;
+	int cache_id;
+
+	if (!x86_match_cpu(snc_cpu_ids))
+		return 1;
+
+	node_caches = bitmap_zalloc(num_possible_cpus(), GFP_KERNEL);
+	if (!node_caches)
+		return 1;
+
+	cpus_read_lock();
+
+	if (num_online_cpus() != num_present_cpus())
+		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
+
+	for_each_node(node) {
+		cpu = cpumask_first(cpumask_of_node(node));
+		if (cpu < nr_cpu_ids) {
+			cache_id = get_cpu_cacheinfo_id(cpu, 3);
+			if (cache_id != -1)
+				set_bit(cache_id, node_caches);
+		} else {
+			mem_only_nodes++;
+		}
+	}
+	cpus_read_unlock();
+
+	num_l3_caches = bitmap_weight(node_caches, num_possible_cpus());
+	kfree(node_caches);
+
+	if (!num_l3_caches)
+		goto insane;
+
+	/* sanity check #1: Number of CPU nodes must be multiple of num_l3_caches */
+	if ((nr_node_ids - mem_only_nodes) % num_l3_caches)
+		goto insane;
+
+	ret = (nr_node_ids - mem_only_nodes) / num_l3_caches;
+
+	/* sanity check #2: Only valid results are 1, 2, 3, 4 */
+	switch (ret) {
+	case 1:
+		break;
+	case 2:
+	case 3:
+	case 4:
+		rdt_resources_all[RDT_RESOURCE_L3].r_resctrl.mon_scope = RESCTRL_NODE;
+		break;
+	default:
+		goto insane;
+	}
+
+	return ret;
+insane:
+	pr_warn("SNC insanity: CPU nodes = %d num_l3_caches = %d\n",
+		(nr_node_ids - mem_only_nodes), num_l3_caches);
+	return 1;
+}
+
 static __init void rdt_init_res_defs_intel(void)
 {
 	struct rdt_hw_resource *hw_res;
 	struct rdt_resource *r;
 
+	snc_nodes_per_l3_cache = snc_get_config();
+
 	for_each_rdt_resource(r) {
 		hw_res = resctrl_to_arch_res(r);
 
-- 
2.41.0