From bb8985586b7a906e116db835c64773b7a7d51663 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 17 Aug 2008 21:05:42 -0400 Subject: x86, um: ... and asm-x86 move Signed-off-by: Al Viro Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/topology.h | 258 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 258 insertions(+) create mode 100644 arch/x86/include/asm/topology.h (limited to 'arch/x86/include/asm/topology.h') diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h new file mode 100644 index 000000000000..7eca9bc022b2 --- /dev/null +++ b/arch/x86/include/asm/topology.h @@ -0,0 +1,258 @@ +/* + * Written by: Matthew Dobson, IBM Corporation + * + * Copyright (C) 2002, IBM Corp. + * + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Send feedback to + */ +#ifndef ASM_X86__TOPOLOGY_H +#define ASM_X86__TOPOLOGY_H + +#ifdef CONFIG_X86_32 +# ifdef CONFIG_X86_HT +# define ENABLE_TOPO_DEFINES +# endif +#else +# ifdef CONFIG_SMP +# define ENABLE_TOPO_DEFINES +# endif +#endif + +/* Node not present */ +#define NUMA_NO_NODE (-1) + +#ifdef CONFIG_NUMA +#include +#include + +#ifdef CONFIG_X86_32 + +/* Mappings between node number and cpus on that node. */ +extern cpumask_t node_to_cpumask_map[]; + +/* Mappings between logical cpu number and node number */ +extern int cpu_to_node_map[]; + +/* Returns the number of the node containing CPU 'cpu' */ +static inline int cpu_to_node(int cpu) +{ + return cpu_to_node_map[cpu]; +} +#define early_cpu_to_node(cpu) cpu_to_node(cpu) + +/* Returns a bitmask of CPUs on Node 'node'. + * + * Side note: this function creates the returned cpumask on the stack + * so with a high NR_CPUS count, excessive stack space is used. The + * node_to_cpumask_ptr function should be used whenever possible. + */ +static inline cpumask_t node_to_cpumask(int node) +{ + return node_to_cpumask_map[node]; +} + +#else /* CONFIG_X86_64 */ + +/* Mappings between node number and cpus on that node. */ +extern cpumask_t *node_to_cpumask_map; + +/* Mappings between logical cpu number and node number */ +DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); + +/* Returns the number of the current Node. */ +#define numa_node_id() read_pda(nodenumber) + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern int cpu_to_node(int cpu); +extern int early_cpu_to_node(int cpu); +extern const cpumask_t *_node_to_cpumask_ptr(int node); +extern cpumask_t node_to_cpumask(int node); + +#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +/* Returns the number of the node containing CPU 'cpu' */ +static inline int cpu_to_node(int cpu) +{ + return per_cpu(x86_cpu_to_node_map, cpu); +} + +/* Same function but used if called before per_cpu areas are setup */ +static inline int early_cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + + return per_cpu(x86_cpu_to_node_map, cpu); +} + +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const cpumask_t *_node_to_cpumask_ptr(int node) +{ + return &node_to_cpumask_map[node]; +} + +/* Returns a bitmask of CPUs on Node 'node'. */ +static inline cpumask_t node_to_cpumask(int node) +{ + return node_to_cpumask_map[node]; +} + +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +/* Replace default node_to_cpumask_ptr with optimized version */ +#define node_to_cpumask_ptr(v, node) \ + const cpumask_t *v = _node_to_cpumask_ptr(node) + +#define node_to_cpumask_ptr_next(v, node) \ + v = _node_to_cpumask_ptr(node) + +#endif /* CONFIG_X86_64 */ + +/* + * Returns the number of the node containing Node 'node'. This + * architecture is flat, so it is a pretty simple function! + */ +#define parent_node(node) (node) + +#define pcibus_to_node(bus) __pcibus_to_node(bus) +#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus) + +#ifdef CONFIG_X86_32 +extern unsigned long node_start_pfn[]; +extern unsigned long node_end_pfn[]; +extern unsigned long node_remap_size[]; +#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid]) + +# define SD_CACHE_NICE_TRIES 1 +# define SD_IDLE_IDX 1 +# define SD_NEWIDLE_IDX 2 +# define SD_FORKEXEC_IDX 0 + +#else + +# define SD_CACHE_NICE_TRIES 2 +# define SD_IDLE_IDX 2 +# define SD_NEWIDLE_IDX 2 +# define SD_FORKEXEC_IDX 1 + +#endif + +/* sched_domains SD_NODE_INIT for NUMAQ machines */ +#define SD_NODE_INIT (struct sched_domain) { \ + .min_interval = 8, \ + .max_interval = 32, \ + .busy_factor = 32, \ + .imbalance_pct = 125, \ + .cache_nice_tries = SD_CACHE_NICE_TRIES, \ + .busy_idx = 3, \ + .idle_idx = SD_IDLE_IDX, \ + .newidle_idx = SD_NEWIDLE_IDX, \ + .wake_idx = 1, \ + .forkexec_idx = SD_FORKEXEC_IDX, \ + .flags = SD_LOAD_BALANCE \ + | SD_BALANCE_EXEC \ + | SD_BALANCE_FORK \ + | SD_SERIALIZE \ + | SD_WAKE_BALANCE, \ + .last_balance = jiffies, \ + .balance_interval = 1, \ +} + +#ifdef CONFIG_X86_64_ACPI_NUMA +extern int __node_distance(int, int); +#define node_distance(a, b) __node_distance(a, b) +#endif + +#else /* !CONFIG_NUMA */ + +#define numa_node_id() 0 +#define cpu_to_node(cpu) 0 +#define early_cpu_to_node(cpu) 0 + +static inline const cpumask_t *_node_to_cpumask_ptr(int node) +{ + return &cpu_online_map; +} +static inline cpumask_t node_to_cpumask(int node) +{ + return cpu_online_map; +} +static inline int node_to_first_cpu(int node) +{ + return first_cpu(cpu_online_map); +} + +/* Replace default node_to_cpumask_ptr with optimized version */ +#define node_to_cpumask_ptr(v, node) \ + const cpumask_t *v = _node_to_cpumask_ptr(node) + +#define node_to_cpumask_ptr_next(v, node) \ + v = _node_to_cpumask_ptr(node) +#endif + +#include + +#ifdef CONFIG_NUMA +/* Returns the number of the first CPU on Node 'node'. */ +static inline int node_to_first_cpu(int node) +{ + node_to_cpumask_ptr(mask, node); + return first_cpu(*mask); +} +#endif + +extern cpumask_t cpu_coregroup_map(int cpu); + +#ifdef ENABLE_TOPO_DEFINES +#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) +#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +#define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu)) + +/* indicates that pointers to the topology cpumask_t maps are valid */ +#define arch_provides_topology_pointers yes +#endif + +static inline void arch_fix_phys_package_id(int num, u32 slot) +{ +} + +struct pci_bus; +void set_pci_bus_resources_arch_default(struct pci_bus *b); + +#ifdef CONFIG_SMP +#define mc_capable() (boot_cpu_data.x86_max_cores > 1) +#define smt_capable() (smp_num_siblings > 1) +#endif + +#ifdef CONFIG_NUMA +extern int get_mp_bus_to_node(int busnum); +extern void set_mp_bus_to_node(int busnum, int node); +#else +static inline int get_mp_bus_to_node(int busnum) +{ + return 0; +} +static inline void set_mp_bus_to_node(int busnum, int node) +{ +} +#endif + +#endif /* ASM_X86__TOPOLOGY_H */ -- cgit v1.2.3 From 1965aae3c98397aad957412413c07e97b1bd4e64 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 22 Oct 2008 22:26:29 -0700 Subject: x86: Fix ASM_X86__ header guards Change header guards named "ASM_X86__*" to "_ASM_X86_*" since: a. the double underscore is ugly and pointless. b. no leading underscore violates namespace constraints. Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/topology.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/include/asm/topology.h') diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 7eca9bc022b2..90ac7718469a 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -22,8 +22,8 @@ * * Send feedback to */ -#ifndef ASM_X86__TOPOLOGY_H -#define ASM_X86__TOPOLOGY_H +#ifndef _ASM_X86_TOPOLOGY_H +#define _ASM_X86_TOPOLOGY_H #ifdef CONFIG_X86_32 # ifdef CONFIG_X86_HT @@ -255,4 +255,4 @@ static inline void set_mp_bus_to_node(int busnum, int node) } #endif -#endif /* ASM_X86__TOPOLOGY_H */ +#endif /* _ASM_X86_TOPOLOGY_H */ -- cgit v1.2.3 From 9fcd18c9e63e325dbd2b4c726623f760788d5aa8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 5 Nov 2008 16:52:08 +0100 Subject: sched: re-tune balancing Impact: improve wakeup affinity on NUMA systems, tweak SMP systems Given the fixes+tweaks to the wakeup-buddy code, re-tweak the domain balancing defaults on NUMA and SMP systems. Turn on SD_WAKE_AFFINE which was off on x86 NUMA - there's no reason why we would not want to have wakeup affinity across nodes as well. (we already do this in the standard NUMA template.) lat_ctx on a NUMA box is particularly happy about this change: before: | phoenix:~/l> ./lat_ctx -s 0 2 | "size=0k ovr=2.60 | 2 5.70 after: | phoenix:~/l> ./lat_ctx -s 0 2 | "size=0k ovr=2.65 | 2 2.07 a 2.75x speedup. pipe-test is similarly happy about it too: | phoenix:~/sched-tests> ./pipe-test | 18.26 usecs/loop. | 14.70 usecs/loop. | 14.38 usecs/loop. | 10.55 usecs/loop. # +WAKE_AFFINE on domain0+domain1 | 8.63 usecs/loop. | 8.59 usecs/loop. | 9.03 usecs/loop. | 8.94 usecs/loop. | 8.96 usecs/loop. | 8.63 usecs/loop. Also: - disable SD_BALANCE_NEWIDLE on NUMA and SMP domains (keep it for siblings) - enable SD_WAKE_BALANCE on SMP domains Sysbench+postgresql improves all around the board, quite significantly: .28-rc3-11474e2c .28-rc3-11474e2c-tune ------------------------------------------------- 1: 571 688 +17.08% 2: 1236 1206 -2.55% 4: 2381 2642 +9.89% 8: 4958 5164 +3.99% 16: 9580 9574 -0.07% 32: 7128 8118 +12.20% 64: 7342 8266 +11.18% 128: 7342 8064 +8.95% 256: 7519 7884 +4.62% 512: 7350 7731 +4.93% ------------------------------------------------- SUM: 55412 59341 +6.62% So it's a win both for the runup portion, the peak area and the tail. Signed-off-by: Ingo Molnar --- arch/x86/include/asm/topology.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86/include/asm/topology.h') diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 90ac7718469a..4850e4b02b61 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -154,7 +154,7 @@ extern unsigned long node_remap_size[]; #endif -/* sched_domains SD_NODE_INIT for NUMAQ machines */ +/* sched_domains SD_NODE_INIT for NUMA machines */ #define SD_NODE_INIT (struct sched_domain) { \ .min_interval = 8, \ .max_interval = 32, \ @@ -169,8 +169,9 @@ extern unsigned long node_remap_size[]; .flags = SD_LOAD_BALANCE \ | SD_BALANCE_EXEC \ | SD_BALANCE_FORK \ - | SD_SERIALIZE \ - | SD_WAKE_BALANCE, \ + | SD_WAKE_AFFINE \ + | SD_WAKE_BALANCE \ + | SD_SERIALIZE, \ .last_balance = jiffies, \ .balance_interval = 1, \ } -- cgit v1.2.3 From 43714539eab42b2fa3653ea7bd667b36c2291b11 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Sat, 29 Nov 2008 16:50:12 +0530 Subject: sched: don't export sched_mc_power_savings in laptops Impact: do not expose a control that has no effect Fix to prevent sched_mc_power_saving from being exported through sysfs on single-socket systems. (Say multicore single socket (Laptop)) CPU core map of the boot cpu should be equal to possible number of cpus for single socket system. This fix has been developed at FOSS.in kernel workout. Signed-off-by: Mahesh Salgaonkar Acked-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/include/asm/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm/topology.h') diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 4850e4b02b61..ff386ff50ed7 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -239,7 +239,7 @@ struct pci_bus; void set_pci_bus_resources_arch_default(struct pci_bus *b); #ifdef CONFIG_SMP -#define mc_capable() (boot_cpu_data.x86_max_cores > 1) +#define mc_capable() (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids) #define smt_capable() (smp_num_siblings > 1) #endif -- cgit v1.2.3