From: Andi Kleen <[email protected]> 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 for MAX_LOCAL_APIC and that 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, where we need 128K just to store a single 4 byte value. Store the logical processor id in cpudata. Add a set flag that indicates that the cpu's cpudata entry has been written. [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. [v5]: Change kmalloc to GFP_ATOMIC to fix "sleeping function" warning on virtual machines. Remove phys_pkg_id. Add spinlock to avoid concurrency issues. [v6]: Revert back to storing logical processor ID in cpudata, and add set flag to indicate that boot_cpu_data was written to a cpu's cpu_data. Signed-off-by: Andi Kleen <[email protected]> Signed-off-by: Prarit Bhargava <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: "H. Peter Anvin" <[email protected]> Cc: [email protected] Cc: Peter Zijlstra <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Dave Hansen <[email protected]> Cc: Piotr Luc <[email protected]> Cc: Kan Liang <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Stephane Eranian <[email protected]> Cc: Prarit Bhargava <[email protected]> Cc: Arvind Yadav <[email protected]> Cc: Andy Lutomirski <[email protected]> Cc: Christian Borntraeger <[email protected]> Cc: "Kirill A. Shutemov" <[email protected]> Cc: Tom Lendacky <[email protected]> Cc: He Chen <[email protected]> Cc: Mathias Krause <[email protected]> Cc: Tim Chen <[email protected]> Cc: Vitaly Kuznetsov <[email protected]> --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/smpboot.c | 75 ++++++++++++++++------------------------ 2 files changed, 30 insertions(+), 46 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index bdac19ab2488..44fd3512442f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -132,6 +132,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; + unsigned set : 1; } __randomize_layout; struct cpuid_regs { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ad59edd84de7..838d36ff7ba6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -100,9 +100,6 @@ 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; @@ -278,6 +275,25 @@ 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) { + if (cpu_data(cpu).phys_proc_id == phys_pkg && + cpu_data(cpu).set) { + return cpu_data(cpu).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 @@ -285,17 +301,11 @@ 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; - /* 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) { @@ -305,34 +315,17 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu) } new = logical_packages++; - if (new != pkg) { + if (new != pkg) 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 @@ -363,19 +356,6 @@ 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); @@ -389,6 +369,7 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; smp_init_package_map(c, id); + cpu_data(id).set = 1; } /* @@ -399,13 +380,15 @@ void smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + if (cpu_data(id).set == 0) + *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); + cpu_data(id).set = 1; } static bool -- 2.15.0.rc0.39.g2f0e14e64
