Received-SPF: pass (google.com: domain of linux-kernel+bounces-64312-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <20240213210252.956858282@linutronix.de>
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org,
 Tom Lendacky <thomas.lendacky@amd.com>,
 Andrew Cooper <andrew.cooper3@citrix.com>,
 Arjan van de Ven <arjan@linux.intel.com>,
 Huang Rui <ray.huang@amd.com>,
 Juergen Gross <jgross@suse.com>,
 Dimitri Sivanich <dimitri.sivanich@hpe.com>,
 Sohil Mehta <sohil.mehta@intel.com>,
 K Prateek Nayak <kprateek.nayak@amd.com>,
 Kan Liang <kan.liang@linux.intel.com>,
 Zhang Rui <rui.zhang@intel.com>,
 "Paul E. McKenney" <paulmck@kernel.org>,
 Feng Tang <feng.tang@intel.com>,
 Andy Shevchenko <andy@infradead.org>,
 Michael Kelley <mhklinux@outlook.com>,
 "Peter Zijlstra (Intel)" <peterz@infradead.org>
Subject: [patch 26/30] x86/cpu/topology: Retrieve cores per package from
 topology bitmaps
References: <20240213205415.307029033@linutronix.de>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Date: Tue, 13 Feb 2024 22:06:10 +0100 (CET)

From: Thomas Gleixner <tglx@linutronix.de>

Similar to other sizing information the number of cores per package can be
established from the topology bitmap.

Provide a function for retrieving that information and replace the buggy
hack in the CPUID evaluation with it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>


---
 arch/x86/kernel/cpu/topology.c        |   43 ++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/topology.h        |   11 ++++++++
 arch/x86/kernel/cpu/topology_common.c |   18 ++------------
 3 files changed, 57 insertions(+), 15 deletions(-)
---

--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -217,6 +217,49 @@ int topology_get_logical_id(u32 apicid,
 }
 EXPORT_SYMBOL_GPL(topology_get_logical_id);
 
+/**
+ * topology_unit_count - Retrieve the count of specified units at a given topology domain level
+ * @apicid:		The APIC ID which specifies the search range
+ * @which_units:	The domain level specifying the units to count
+ * @at_level:		The domain level at which @which_units have to be counted
+ *
+ * This returns the number of possible units according to the enumerated
+ * information.
+ *
+ * E.g. topology_count_units(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN)
+ * counts the number of possible cores in the package to which @apicid
+ * belongs.
+ *
+ * @at_level must obviously be greater than @which_level to produce useful
+ * results.  If @at_level is equal to @which_units the result is
+ * unsurprisingly 1. If @at_level is less than @which_units the results
+ * is by definition undefined and the function returns 0.
+ */
+unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+				 enum x86_topology_domains at_level)
+{
+	/* Remove the bits below @at_level to get the proper level ID of @apicid */
+	unsigned int lvlid = topo_apicid(apicid, at_level);
+	unsigned int id, end, cnt = 0;
+
+	if (lvlid >= MAX_LOCAL_APIC)
+		return 0;
+	if (!test_bit(lvlid, apic_maps[at_level].map))
+		return 0;
+	if (which_units > at_level)
+		return 0;
+	if (which_units == at_level)
+		return 1;
+
+	/* Calculate the exclusive end */
+	end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]);
+	/* Unfortunately there is no bitmap_weight_range() */
+	for (id = find_next_bit(apic_maps[which_units].map, end, lvlid);
+	     id < end; id = find_next_bit(apic_maps[which_units].map, end, ++id))
+		cnt++;
+	return cnt;
+}
+
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /**
  * topology_hotplug_apic - Handle a physical hotplugged APIC after boot
--- a/arch/x86/kernel/cpu/topology.h
+++ b/arch/x86/kernel/cpu/topology.h
@@ -53,4 +53,15 @@ static inline void topology_update_dom(s
 	tscan->dom_ncpus[dom] = ncpus;
 }
 
+#ifdef CONFIG_X86_LOCAL_APIC
+unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+				 enum x86_topology_domains at_level);
+#else
+static inline unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units,
+					       enum x86_topology_domains at_level)
+{
+	return 1;
+}
+#endif
+
 #endif /* ARCH_X86_TOPOLOGY_H */
--- a/arch/x86/kernel/cpu/topology_common.c
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -155,25 +155,15 @@ static void topo_set_ids(struct topo_sca
 	c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >>
 		x86_topo_system.dom_shifts[TOPO_SMT_DOMAIN];
 
+	/* Maximum number of cores on this package */
+	c->x86_max_cores = topology_unit_count(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN);
+
 	c->topo.amd_node_id = tscan->amd_node_id;
 
 	if (c->x86_vendor == X86_VENDOR_AMD)
 		cpu_topology_fixup_amd(tscan);
 }
 
-static void topo_set_max_cores(struct topo_scan *tscan)
-{
-	/*
-	 * Bug compatible for now. This is broken on hybrid systems:
-	 * 8 cores SMT + 8 cores w/o SMT
-	 * tscan.dom_ncpus[TOPO_DIEGRP_DOMAIN] = 24; 24 / 2 = 12 !!
-	 *
-	 * Cannot be fixed without further topology enumeration changes.
-	 */
-	tscan->c->x86_max_cores = tscan->dom_ncpus[TOPO_DIEGRP_DOMAIN] >>
-		x86_topo_system.dom_shifts[TOPO_SMT_DOMAIN];
-}
-
 void cpu_parse_topology(struct cpuinfo_x86 *c)
 {
 	unsigned int dom, cpu = smp_processor_id();
@@ -201,7 +191,6 @@ void cpu_parse_topology(struct cpuinfo_x
 	}
 
 	topo_set_ids(&tscan);
-	topo_set_max_cores(&tscan);
 }
 
 void __init cpu_init_topology(struct cpuinfo_x86 *c)
@@ -223,7 +212,6 @@ void __init cpu_init_topology(struct cpu
 	}
 
 	topo_set_ids(&tscan);
-	topo_set_max_cores(&tscan);
 
 	/*
 	 * AMD systems have Nodes per package which cannot be mapped to