[PATCH 2/3] x86/topology: Avoid wasting 128k for package id array

[Prarit Bhargava]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

I was looking at large early boot allocations and noticed that since
(1f12e32f x86/topology: Create logical package id) every 64bit system
allocates a 128k array to convert logical package ids.

This happens because the array is sized to (MAX_LOCAL_APIC * u16) = 128k.
This is a lot of waste especially for most systems which have one or two
sockets.

Use a dynamically allocated array of size logical_packages to map
the logical and physical packages.

[v2]: Decrease logical_packages when the last thread in a socket is
removed.
[v3]: Add more logic to keep logical and physical package IDs
in synch.
[v4]: Keep logical mapping static by using hybrid approach of a small logical
to physical array and keeping logical cpu information in cpu_data.

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Piotr Luc <piotr.luc@xxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Arvind Yadav <arvind.yadav.cs@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: Mathias Krause <minipli@xxxxxxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/include/asm/processor.h |  4 +-
 arch/x86/kernel/smpboot.c        | 86 +++++++++++++++++++---------------------
 2 files changed, 43 insertions(+), 47 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b390ff76e58f..f4ab1edf4e24 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -124,8 +124,10 @@ struct cpuinfo_x86 {
 	u16			booted_cores;
 	/* Physical processor id: */
 	u16			phys_proc_id;
-	/* Logical processor id: */
+	/* Logical processor (package) id: */
 	u16			logical_proc_id;
+	/* Physical package ID */
+	u16			phys_pkg_id;
 	/* Core id: */
 	u16			cpu_core_id;
 	/* Index into per_cpu list: */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ad59edd84de7..ca615bc94e82 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -99,12 +99,10 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
-/* Logical package management. We might want to allocate that dynamically */
-static int *physical_to_logical_pkg __read_mostly;
-static unsigned long *physical_package_map __read_mostly;;
-static unsigned int max_physical_pkg_id __read_mostly;
+/* Logical package management.*/
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
+static u16 *logical_to_physical_pkg_map;
 static unsigned int logical_packages __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
@@ -278,6 +276,23 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
+/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+	int log_pkg;
+
+	for (log_pkg = 0; log_pkg < logical_packages; log_pkg++)
+		if (logical_to_physical_pkg_map[log_pkg] == phys_pkg)
+			return log_pkg;
+
+	return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
 /**
  * topology_update_package_map - Update the physical to logical package map
  * @pkg:	The physical package id as retrieved via CPUID
@@ -285,17 +300,11 @@ static void notrace start_secondary(void *unused)
  */
 int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 {
-	unsigned int new;
-
-	/* Called from early boot ? */
-	if (!physical_package_map)
-		return 0;
-
-	if (pkg >= max_physical_pkg_id)
-		return -EINVAL;
+	int new;
+	u16 *ltp_pkg_map_new;
 
-	/* Set the logical package id */
-	if (test_and_set_bit(pkg, physical_package_map))
+	new = topology_phys_to_logical_pkg(pkg);
+	if (new >= 0)
 		goto found;
 
 	if (logical_packages >= __max_logical_packages) {
@@ -305,34 +314,30 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 	}
 
 	new = logical_packages++;
-	if (new != pkg) {
-		pr_info("CPU %u Converting physical %u to logical package %u\n",
-			cpu, pkg, new);
+
+	/* Allocate and copy a new array */
+	ltp_pkg_map_new = kmalloc(logical_packages * sizeof(u16), GFP_KERNEL);
+	BUG_ON(!ltp_pkg_map_new);
+	if (logical_to_physical_pkg_map) {
+		memcpy(ltp_pkg_map_new, logical_to_physical_pkg_map,
+		       logical_packages * sizeof(u16));
+		kfree(logical_to_physical_pkg_map);
 	}
-	physical_to_logical_pkg[pkg] = new;
+	logical_to_physical_pkg_map = ltp_pkg_map_new;
+	logical_to_physical_pkg_map[new] = pkg;
 
+	if (pkg != new)
+		pr_info("CPU %u Converting physical %u to logical package %u\n",
+			cpu, pkg, new);
 found:
-	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+	cpu_data(cpu).phys_pkg_id = pkg;
+	cpu_data(cpu).logical_proc_id = new;
 	return 0;
 }
 
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
-	if (phys_pkg >= max_physical_pkg_id)
-		return -1;
-	return physical_to_logical_pkg[phys_pkg];
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
 static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
 {
 	unsigned int ncpus;
-	size_t size;
 
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems. That
@@ -363,21 +368,10 @@ static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
 	}
 
 	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-	logical_packages = 0;
-
-	/*
-	 * Possibly larger than what we need as the number of apic ids per
-	 * package can be smaller than the actual used apic ids.
-	 */
-	max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
-	size = max_physical_pkg_id * sizeof(unsigned int);
-	physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
-	memset(physical_to_logical_pkg, 0xff, size);
-	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
-	physical_package_map = kzalloc(size, GFP_KERNEL);
-
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
+	logical_packages = 0;
+
 	topology_update_package_map(c->phys_proc_id, cpu);
 }
 
-- 
2.15.0.rc0.39.g2f0e14e64