x86/topology: Avoid wasting 128k for package id array

Analyzing large early boot allocations unveiled the logical package id
storage as a prominent memory waste. Since commit 1f12e32
("x86/topology: Create logical package id") every 64-bit system allocates a
128k array to convert logical package ids.

This happens because the array is sized for MAX_LOCAL_APIC which is always
32k on 64bit systems, and it needs 4 bytes for each entry.

This is fairly wasteful, especially for the common case of having only one
socket, which uses exactly 4 byte out of 128K.

There is no user of the package id map which is performance critical, so
the lookup is not required to be O(1). Store the logical processor id in
cpu_data and use a loop based lookup.

To keep the mapping stable accross cpu hotplug operations, add a flag to
cpu_data which is set when the CPU is brought up the first time. When the
flag is set, then cpu_data is not reinitialized by copying boot_cpu_data on
subsequent bringups.

[ tglx: Rename the flag to 'initialized', use proper pointers instead of
  	repeated cpu_data(x) evaluation and massage changelog. ]

Signed-off-by: Andi Kleen <[email protected]>
Signed-off-by: Prarit Bhargava <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: Tom Lendacky <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: He Chen <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Piotr Luc <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Arvind Yadav <[email protected]>
Cc: Vitaly Kuznetsov <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Tim Chen <[email protected]>
Cc: Mathias Krause <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Andi Kleen

arch/x86/include/asm/processor.h

@@ -132,6 +132,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
+	unsigned		initialized : 1;
 } __randomize_layout;
 
 struct cpuid_regs {

arch/x86/kernel/smpboot.c

@@ -101,9 +101,6 @@ 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;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
@@ -280,24 +277,37 @@ 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 cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && c->phys_proc_id == phys_pkg)
+			return c->logical_proc_id;
+	}
+	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
  * @cpu:	The cpu for which this is updated
  */
 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;
 
-	/* Set the logical package id */
-	if (test_and_set_bit(pkg, physical_package_map))
+	/* Already available somewhere? */
+	new = topology_phys_to_logical_pkg(pkg);
+	if (new >= 0)
 		goto found;
 
 	if (logical_packages >= __max_logical_packages) {
@@ -311,30 +321,14 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 		pr_info("CPU %u Converting physical %u to logical package %u\n",
 			cpu, pkg, new);
 	}
-	physical_to_logical_pkg[pkg] = new;
-
 found:
-	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[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
@@ -365,19 +359,6 @@ 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);
 
 	topology_update_package_map(c->phys_proc_id, cpu);
@@ -391,6 +372,7 @@ void __init smp_store_boot_cpu_info(void)
 	*c = boot_cpu_data;
 	c->cpu_index = id;
 	smp_init_package_map(c, id);
+	c->initialized = true;
 }
 
 /*
@@ -401,13 +383,16 @@ void smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
-	*c = boot_cpu_data;
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
+		*c = boot_cpu_data;
 	c->cpu_index = id;
 	/*
 	 * During boot time, CPU0 has this setup already. Save the info when
 	 * bringing up AP or offlined CPU0.
 	 */
 	identify_secondary_cpu(c);
+	c->initialized = true;
 }
 
 static bool