From 19209bbb8612004bc20a1f70ff12926f99fe2643 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Mon, 30 Apr 2012 12:26:56 +0530 Subject: x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly The checks that exist in mwait_usable() for "idle=" kernel parameters are insufficient. As a result, mwait_usable() can return 1 even if "idle=nomwait" or "idle=poll" or "idle=halt" parameters are passed. Of these cases, incorrect handling of idle=nomwait is a universal problem since mwait can get used for usual CPU idling. However the rest of the cases are problematic only during CPU Hotplug (offline) because, in the CPU offline path, the function mwait_play_dead() is called, which might result in mwait being used in the offline CPUs, if mwait_usable() happens to return 1. Fix these issues by checking for the boot time "idle=" kernel parameter properly in mwait_usable(). The first issue (usual cpu idling) is demonstrated below: Before applying the patch (dmesg snippet): [ 0.000000] Command line: [...] idle=nomwait [ 0.000000] Kernel command line: [...] idle=nomwait [ 0.000000] RCU dyntick-idle grace-period acceleration is enabled. [ 0.140606] using mwait in idle threads. <======= mwait being used [ 4.303986] cpuidle: using governor ladder [ 4.308232] cpuidle: using governor menu After applying the patch: [ 0.000000] Command line: [...] idle=nomwait [ 0.000000] Kernel command line: [...] idle=nomwait [ 0.000000] RCU dyntick-idle grace-period acceleration is enabled. [ 4.264100] cpuidle: using governor ladder [ 4.268342] cpuidle: using governor menu Signed-off-by: Srivatsa S. Bhat Acked-by: Deepthi Dharwar Acked-by: Thomas Gleixner Cc: venki@google.com Cc: suresh.b.siddha@intel.com Cc: Borislav Petkov Cc: lenb@kernel.org Cc: Rafael J. Wysocki Link: http://lkml.kernel.org/r/4F9E37B8.30001@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/process.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1d92a5ab6e8..ad57d832d96 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -594,9 +594,17 @@ int mwait_usable(const struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; + /* Use mwait if idle=mwait boot option is given */ if (boot_option_idle_override == IDLE_FORCE_MWAIT) return 1; + /* + * Any idle= boot option other than idle=mwait means that we must not + * use mwait. Eg: idle=halt or idle=poll or idle=nomwait + */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return 0; + if (c->cpuid_level < MWAIT_INFO) return 0; -- cgit v1.2.3-70-g09d2 From 94c0dd3278dd3eae52eabf0fb77d472d0dd3e373 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Apr 2012 19:04:17 +0200 Subject: x86/numa: Allow specifying node_distance() for numa=fake Allows emulating more interesting NUMA configurations like a quad socket AMD Magny-Cour: "numa=fake=8:10,16,16,22,16,22,16,22, 16,10,22,16,22,16,22,16, 16,22,10,16,16,22,16,22, 22,16,16,10,22,16,22,16, 16,22,16,22,10,16,16,22, 22,16,22,16,16,10,22,16, 16,22,16,22,16,22,10,16, 22,16,22,16,22,16,16,10" Which has a non-fully-connected topology. Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-e1136ef7kdffj7yf9tjhydln@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/numa_emulation.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 53489ff6bf8..871dd886817 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -339,9 +339,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } else { unsigned long n; - n = simple_strtoul(emu_cmdline, NULL, 0); + n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); } + if (*emu_cmdline == ':') + emu_cmdline++; if (ret < 0) goto no_emu; @@ -418,7 +420,9 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) int physj = emu_nid_to_phys[j]; int dist; - if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) + if (get_option(&emu_cmdline, &dist) == 2) + ; + else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) dist = physi == physj ? LOCAL_DISTANCE : REMOTE_DISTANCE; else -- cgit v1.2.3-70-g09d2 From 0acbb440f06302058e1515861dd534594521e892 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 18 Apr 2012 19:04:09 +0200 Subject: x86/numa: Hard partition cpu topology masks on node boundaries When using numa=fake= you can get weird topologies where LLCs can span nodes and other such nonsense. Cure this by hard partitioning these masks on node boundaries. Signed-off-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-di5vwjm96q5vrb76opwuflwx@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6e1e406038c..edfd03a9e39 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -337,6 +337,11 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { struct cpuinfo_x86 *o = &cpu_data(i); +#ifdef CONFIG_NUMA_EMU + if (cpu_to_node(cpu) != cpu_to_node(i)) + continue; +#endif + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { if (c->phys_proc_id == o->phys_proc_id && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) && @@ -360,11 +365,17 @@ void __cpuinit set_cpu_sibling_map(int cpu) } for_each_cpu(i, cpu_sibling_setup_mask) { +#ifdef CONFIG_NUMA_EMU + if (cpu_to_node(cpu) != cpu_to_node(i)) + continue; +#endif + if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); } + if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); -- cgit v1.2.3-70-g09d2 From ad7687dde8780a0d618a3e3b5a62bb383696fc22 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 9 May 2012 13:31:47 +0200 Subject: x86/numa: Check for nonsensical topologies on real hw as well Instead of only checking nonsensical topologies on numa-emu, do it on real hardware as well, and print a warning. Acked-by: Peter Zijlstra Cc: Tejun Heo Cc: Yinghai Lu Cc: x86@kernel.org Link: http://lkml.kernel.org/n/tip-re15l0jqjtpz709oxozt2zoh@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index edfd03a9e39..7c53d96d44a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -337,10 +337,10 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { struct cpuinfo_x86 *o = &cpu_data(i); -#ifdef CONFIG_NUMA_EMU - if (cpu_to_node(cpu) != cpu_to_node(i)) + if (cpu_to_node(cpu) != cpu_to_node(i)) { + WARN_ONCE(1, "sched: CPU #%d's thread-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); continue; -#endif + } if (cpu_has(c, X86_FEATURE_TOPOEXT)) { if (c->phys_proc_id == o->phys_proc_id && @@ -365,10 +365,10 @@ void __cpuinit set_cpu_sibling_map(int cpu) } for_each_cpu(i, cpu_sibling_setup_mask) { -#ifdef CONFIG_NUMA_EMU - if (cpu_to_node(cpu) != cpu_to_node(i)) + if (cpu_to_node(cpu) != cpu_to_node(i)) { + WARN_ONCE(1, "sched: CPU #%d's core-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); continue; -#endif + } if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { -- cgit v1.2.3-70-g09d2 From cb83b629bae0327cf9f44f096adc38d150ceb913 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Apr 2012 15:49:36 +0200 Subject: sched/numa: Rewrite the CONFIG_NUMA sched domain support The current code groups up to 16 nodes in a level and then puts an ALLNODES domain spanning the entire tree on top of that. This doesn't reflect the numa topology and esp for the smaller not-fully-connected machines out there today this might make a difference. Therefore, build a proper numa topology based on node_distance(). Since there's no fixed numa layers anymore, the static SD_NODE_INIT and SD_ALLNODES_INIT aren't usable anymore, the new code tries to construct something similar and scales some values either on the number of cpus in the domain and/or the node_distance() ratio. Signed-off-by: Peter Zijlstra Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: David Howells Cc: "David S. Miller" Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ivan Kokshaysky Cc: linux-alpha@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-sh@vger.kernel.org Cc: Matt Turner Cc: Paul Mackerras Cc: Paul Mundt Cc: Ralf Baechle Cc: Richard Henderson Cc: sparclinux@vger.kernel.org Cc: Tony Luck Cc: x86@kernel.org Cc: Dimitri Sivanich Cc: Greg Pearson Cc: KAMEZAWA Hiroyuki Cc: bob.picco@oracle.com Cc: chris.mason@oracle.com Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/n/tip-r74n3n8hhuc2ynbrnp3vt954@git.kernel.org Signed-off-by: Ingo Molnar --- arch/ia64/include/asm/topology.h | 25 --- arch/mips/include/asm/mach-ip27/topology.h | 17 -- arch/powerpc/include/asm/topology.h | 36 ---- arch/sh/include/asm/topology.h | 25 --- arch/sparc/include/asm/topology_64.h | 19 -- arch/tile/include/asm/topology.h | 26 --- arch/x86/include/asm/topology.h | 38 ---- include/linux/topology.h | 37 ---- kernel/sched/core.c | 280 +++++++++++++++++++---------- 9 files changed, 185 insertions(+), 318 deletions(-) (limited to 'arch/x86') diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 09f646753d1..a2496e449b7 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -70,31 +70,6 @@ void build_cpu_to_node_map(void); .nr_balance_failed = 0, \ } -/* sched_domains SD_NODE_INIT for IA64 NUMA machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 8*(min(num_online_cpus(), 32U)), \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_FORK \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 64, \ - .nr_balance_failed = 0, \ -} - #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h index 1b1a7d1632b..b2cf641f206 100644 --- a/arch/mips/include/asm/mach-ip27/topology.h +++ b/arch/mips/include/asm/mach-ip27/topology.h @@ -36,23 +36,6 @@ extern unsigned char __node_distances[MAX_COMPACT_NODES][MAX_COMPACT_NODES]; #define node_distance(from, to) (__node_distances[(from)][(to)]) -/* sched_domains SD_NODE_INIT for SGI IP27 machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .flags = SD_LOAD_BALANCE | \ - SD_BALANCE_EXEC, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .nr_balance_failed = 0, \ -} - #include #endif /* _ASM_MACH_TOPOLOGY_H */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c97185885c6..852ed1b384f 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -18,12 +18,6 @@ struct device_node; */ #define RECLAIM_DISTANCE 10 -/* - * Avoid creating an extra level of balancing (SD_ALLNODES) on the largest - * POWER7 boxes which have a maximum of 32 nodes. - */ -#define SD_NODES_PER_DOMAIN 32 - #include static inline int cpu_to_node(int cpu) @@ -51,36 +45,6 @@ static inline int pcibus_to_node(struct pci_bus *bus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -/* sched_domains SD_NODE_INIT for PPC64 machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 0*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 0*SD_PREFER_LOCAL \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ -} - extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h index 88e734069fa..b0a282d65f6 100644 --- a/arch/sh/include/asm/topology.h +++ b/arch/sh/include/asm/topology.h @@ -3,31 +3,6 @@ #ifdef CONFIG_NUMA -/* sched_domains SD_NODE_INIT for sh machines */ -#define SD_NODE_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_NEWIDLE \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .nr_balance_failed = 0, \ -} - #define cpu_to_node(cpu) ((void)(cpu),0) #define parent_node(node) ((void)(node),0) diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h index 8b9c556d630..1754390a426 100644 --- a/arch/sparc/include/asm/topology_64.h +++ b/arch/sparc/include/asm/topology_64.h @@ -31,25 +31,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus) cpu_all_mask : \ cpumask_of_node(pcibus_to_node(bus))) -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 8, \ - .max_interval = 32, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 3, \ - .idle_idx = 2, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_FORK \ - | SD_BALANCE_EXEC \ - | SD_SERIALIZE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ -} - #else /* CONFIG_NUMA */ #include diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index 6fdd0c86019..7a7ce390534 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -78,32 +78,6 @@ static inline const struct cpumask *cpumask_of_node(int node) .balance_interval = 32, \ } -/* sched_domains SD_NODE_INIT for TILE architecture */ -#define SD_NODE_INIT (struct sched_domain) { \ - .min_interval = 16, \ - .max_interval = 512, \ - .busy_factor = 32, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 1, \ - .newidle_idx = 2, \ - .wake_idx = 1, \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 0*SD_WAKE_AFFINE \ - | 0*SD_PREFER_LOCAL \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - , \ - .last_balance = jiffies, \ - .balance_interval = 128, \ -} - /* By definition, we create nodes based on online memory. */ #define node_has_online_mem(nid) 1 diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index b9676ae37ad..095b21507b6 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -92,44 +92,6 @@ extern void setup_node_to_cpumask_map(void); #define pcibus_to_node(bus) __pcibus_to_node(bus) -#ifdef CONFIG_X86_32 -# define SD_CACHE_NICE_TRIES 1 -# define SD_IDLE_IDX 1 -#else -# define SD_CACHE_NICE_TRIES 2 -# define SD_IDLE_IDX 2 -#endif - -/* sched_domains SD_NODE_INIT for NUMA 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 = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 1*SD_WAKE_AFFINE \ - | 0*SD_PREFER_LOCAL \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 1, \ -} - extern int __node_distance(int, int); #define node_distance(a, b) __node_distance(a, b) diff --git a/include/linux/topology.h b/include/linux/topology.h index e26db031303..4f59bf36f0a 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -70,7 +70,6 @@ int arch_update_cpu_topology(void); * Below are the 3 major initializers used in building sched_domains: * SD_SIBLING_INIT, for SMT domains * SD_CPU_INIT, for SMP domains - * SD_NODE_INIT, for NUMA domains * * Any architecture that cares to do any tuning to these values should do so * by defining their own arch-specific initializer in include/asm/topology.h. @@ -176,48 +175,12 @@ int arch_update_cpu_topology(void); } #endif -/* sched_domains SD_ALLNODES_INIT for NUMA machines */ -#define SD_ALLNODES_INIT (struct sched_domain) { \ - .min_interval = 64, \ - .max_interval = 64*num_online_cpus(), \ - .busy_factor = 128, \ - .imbalance_pct = 133, \ - .cache_nice_tries = 1, \ - .busy_idx = 3, \ - .idle_idx = 3, \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 0*SD_BALANCE_EXEC \ - | 0*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 0*SD_WAKE_AFFINE \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 1*SD_SERIALIZE \ - | 0*SD_PREFER_SIBLING \ - , \ - .last_balance = jiffies, \ - .balance_interval = 64, \ -} - -#ifndef SD_NODES_PER_DOMAIN -#define SD_NODES_PER_DOMAIN 16 -#endif - #ifdef CONFIG_SCHED_BOOK #ifndef SD_BOOK_INIT #error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!! #endif #endif /* CONFIG_SCHED_BOOK */ -#ifdef CONFIG_NUMA -#ifndef SD_NODE_INIT -#error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! -#endif - -#endif /* CONFIG_NUMA */ - #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6001e5c3b4e..b4f2096980a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5560,7 +5560,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (cpumask_intersects(groupmask, sched_group_cpus(group))) { + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; @@ -5898,92 +5899,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -#ifdef CONFIG_NUMA - -/** - * find_next_best_node - find the next node to include in a sched_domain - * @node: node whose sched_domain we're building - * @used_nodes: nodes already in the sched_domain - * - * Find the next node to include in a given scheduling domain. Simply - * finds the closest node not already in the @used_nodes map. - * - * Should use nodemask_t. - */ -static int find_next_best_node(int node, nodemask_t *used_nodes) -{ - int i, n, val, min_val, best_node = -1; - - min_val = INT_MAX; - - for (i = 0; i < nr_node_ids; i++) { - /* Start at @node */ - n = (node + i) % nr_node_ids; - - if (!nr_cpus_node(n)) - continue; - - /* Skip already used nodes */ - if (node_isset(n, *used_nodes)) - continue; - - /* Simple min distance search */ - val = node_distance(node, n); - - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - if (best_node != -1) - node_set(best_node, *used_nodes); - return best_node; -} - -/** - * sched_domain_node_span - get a cpumask for a node's sched_domain - * @node: node whose cpumask we're constructing - * @span: resulting cpumask - * - * Given a node, construct a good cpumask for its sched_domain to span. It - * should be one that prevents unnecessary balancing, but also spreads tasks - * out optimally. - */ -static void sched_domain_node_span(int node, struct cpumask *span) -{ - nodemask_t used_nodes; - int i; - - cpumask_clear(span); - nodes_clear(used_nodes); - - cpumask_or(span, span, cpumask_of_node(node)); - node_set(node, used_nodes); - - for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, &used_nodes); - if (next_node < 0) - break; - cpumask_or(span, span, cpumask_of_node(next_node)); - } -} - -static const struct cpumask *cpu_node_mask(int cpu) -{ - lockdep_assert_held(&sched_domains_mutex); - - sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask); - - return sched_domains_tmpmask; -} - -static const struct cpumask *cpu_allnodes_mask(int cpu) -{ - return cpu_possible_mask; -} -#endif /* CONFIG_NUMA */ - static const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); @@ -6020,6 +5935,7 @@ struct sched_domain_topology_level { sched_domain_init_f init; sched_domain_mask_f mask; int flags; + int numa_level; struct sd_data data; }; @@ -6213,10 +6129,6 @@ sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ } SD_INIT_FUNC(CPU) -#ifdef CONFIG_NUMA - SD_INIT_FUNC(ALLNODES) - SD_INIT_FUNC(NODE) -#endif #ifdef CONFIG_SCHED_SMT SD_INIT_FUNC(SIBLING) #endif @@ -6338,15 +6250,191 @@ static struct sched_domain_topology_level default_topology[] = { { sd_init_BOOK, cpu_book_mask, }, #endif { sd_init_CPU, cpu_cpu_mask, }, -#ifdef CONFIG_NUMA - { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, }, - { sd_init_ALLNODES, cpu_allnodes_mask, }, -#endif { NULL, }, }; static struct sched_domain_topology_level *sched_domain_topology = default_topology; +#ifdef CONFIG_NUMA + +static int sched_domains_numa_levels; +static int sched_domains_numa_scale; +static int *sched_domains_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; + +static inline unsigned long numa_scale(unsigned long x, int level) +{ + return x * sched_domains_numa_distance[level] / sched_domains_numa_scale; +} + +static inline int sd_local_flags(int level) +{ + if (sched_domains_numa_distance[level] > REMOTE_DISTANCE) + return 0; + + return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; +} + +static struct sched_domain * +sd_numa_init(struct sched_domain_topology_level *tl, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int level = tl->numa_level; + int sd_weight = cpumask_weight( + sched_domains_numa_masks[level][cpu_to_node(cpu)]); + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 100 + numa_scale(25, level), + .cache_nice_tries = 2, + .busy_idx = 3, + .idle_idx = 2, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*SD_LOAD_BALANCE + | 1*SD_BALANCE_NEWIDLE + | 0*SD_BALANCE_EXEC + | 0*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 0*SD_WAKE_AFFINE + | 0*SD_PREFER_LOCAL + | 0*SD_SHARE_CPUPOWER + | 0*SD_POWERSAVINGS_BALANCE + | 0*SD_SHARE_PKG_RESOURCES + | 1*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | sd_local_flags(level) + , + .last_balance = jiffies, + .balance_interval = sd_weight, + }; + SD_INIT_NAME(sd, NUMA); + sd->private = &tl->data; + + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; + + return sd; +} + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_scale = curr_distance; + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + * + * XXX: could be optimized to O(n log n) by using sort() + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + int distance = node_distance(0, j); + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_nume_distance[] array includes the actual distance + * numbers. + */ + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(cpu_to_node(j), k) > + sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; default_topology[i].init; i++) + tl[i] = default_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .init = sd_numa_init, + .mask = sd_numa_mask, + .flags = SDTL_OVERLAP, + .numa_level = j, + }; + } + + sched_domain_topology = tl; +} +#else +static inline void sched_init_numa(void) +{ +} +#endif /* CONFIG_NUMA */ + static int __sdt_alloc(const struct cpumask *cpu_map) { struct sched_domain_topology_level *tl; @@ -6840,6 +6928,8 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + sched_init_numa(); + get_online_cpus(); mutex_lock(&sched_domains_mutex); init_sched_domains(cpu_active_mask); -- cgit v1.2.3-70-g09d2 From 316ad248307fba13be40f01e92a22b89457c32bc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 May 2012 13:05:59 +0200 Subject: sched/x86: Rewrite set_cpu_sibling_map() Commit ad7687dde ("x86/numa: Check for nonsensical topologies on real hw as well") is broken in that the condition can trigger for valid setups but only changes the end result for invalid setups with no real means of discerning between those. Rewrite set_cpu_sibling_map() to make the code clearer and make sure to only warn when the check changes the end result. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-klcwahu3gx467uhfiqjyhdcs@git.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 112 +++++++++++++++++++++++++++------------------- 1 file changed, 66 insertions(+), 46 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7c53d96d44a..e84c1bbea33 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -315,70 +315,90 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } -static void __cpuinit link_thread_siblings(int cpu1, int cpu2) +static bool __cpuinit +topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) { - cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1)); - cpumask_set_cpu(cpu1, cpu_core_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); - cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); - cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2), + "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! " + "[node: %d != %d]. Ignoring dependency.\n", + cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } +#define link_mask(_m, c1, c2) \ +do { \ + cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ + cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ +} while (0) -void __cpuinit set_cpu_sibling_map(int cpu) +static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - int i; - struct cpuinfo_x86 *c = &cpu_data(cpu); + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - cpumask_set_cpu(cpu, cpu_sibling_setup_mask); + if (c->phys_proc_id == o->phys_proc_id && + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && + c->compute_unit_id == o->compute_unit_id) + return topology_sane(c, o, "smt"); - if (smp_num_siblings > 1) { - for_each_cpu(i, cpu_sibling_setup_mask) { - struct cpuinfo_x86 *o = &cpu_data(i); + } else if (c->phys_proc_id == o->phys_proc_id && + c->cpu_core_id == o->cpu_core_id) { + return topology_sane(c, o, "smt"); + } - if (cpu_to_node(cpu) != cpu_to_node(i)) { - WARN_ONCE(1, "sched: CPU #%d's thread-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); - continue; - } + return false; +} - if (cpu_has(c, X86_FEATURE_TOPOEXT)) { - if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) && - c->compute_unit_id == o->compute_unit_id) - link_thread_siblings(cpu, i); - } else if (c->phys_proc_id == o->phys_proc_id && - c->cpu_core_id == o->cpu_core_id) { - link_thread_siblings(cpu, i); - } - } - } else { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); - } +static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) + return topology_sane(c, o, "llc"); + + return false; +} + +static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + if (c->phys_proc_id == o->phys_proc_id) + return topology_sane(c, o, "mc"); + + return false; +} + +void __cpuinit set_cpu_sibling_map(int cpu) +{ + bool has_mc = boot_cpu_data.x86_max_cores > 1; + bool has_smt = smp_num_siblings > 1; + struct cpuinfo_x86 *c = &cpu_data(cpu); + struct cpuinfo_x86 *o; + int i; - cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (__this_cpu_read(cpu_info.x86_max_cores) == 1) { - cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); + if (!has_smt && !has_mc) { + cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_core_mask(cpu)); c->booted_cores = 1; return; } for_each_cpu(i, cpu_sibling_setup_mask) { - if (cpu_to_node(cpu) != cpu_to_node(i)) { - WARN_ONCE(1, "sched: CPU #%d's core-sibling CPU #%d not on the same node! [node %d != %d]. Ignoring sibling dependency.\n", cpu, i, cpu_to_node(cpu), cpu_to_node(i)); - continue; - } + o = &cpu_data(i); - if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && - per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); - } + if ((i == cpu) || (has_smt && match_smt(c, o))) + link_mask(sibling, cpu, i); + + if ((i == cpu) || (has_mc && match_llc(c, o))) + link_mask(llc_shared, cpu, i); + + if ((i == cpu) || (has_mc && match_mc(c, o))) { + link_mask(core, cpu, i); - if (c->phys_proc_id == cpu_data(i).phys_proc_id) { - cpumask_set_cpu(i, cpu_core_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(i)); /* * Does this new cpu bringup a new core? */ -- cgit v1.2.3-70-g09d2 From 8e7fbcbc22c12414bcc9dfdd683637f58fb32759 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 9 Jan 2012 11:28:35 +0100 Subject: sched: Remove stale power aware scheduling remnants and dysfunctional knobs It's been broken forever (i.e. it's not scheduling in a power aware fashion), as reported by Suresh and others sending patches, and nobody cares enough to fix it properly ... so remove it to make space free for something better. There's various problems with the code as it stands today, first and foremost the user interface which is bound to topology levels and has multiple values per level. This results in a state explosion which the administrator or distro needs to master and almost nobody does. Furthermore large configuration state spaces aren't good, it means the thing doesn't just work right because it's either under so many impossibe to meet constraints, or even if there's an achievable state workloads have to be aware of it precisely and can never meet it for dynamic workloads. So pushing this kind of decision to user-space was a bad idea even with a single knob - it's exponentially worse with knobs on every node of the topology. There is a proposal to replace the user interface with a single 3 state knob: sched_balance_policy := { performance, power, auto } where 'auto' would be the preferred default which looks at things like Battery/AC mode and possible cpufreq state or whatever the hw exposes to show us power use expectations - but there's been no progress on it in the past many months. Aside from that, the actual implementation of the various knobs is known to be broken. There have been sporadic attempts at fixing things but these always stop short of reaching a mergable state. Therefore this wholesale removal with the hopes of spurring people who care to come forward once again and work on a coherent replacement. Signed-off-by: Peter Zijlstra Cc: Suresh Siddha Cc: Arjan van de Ven Cc: Vincent Guittot Cc: Vaidyanathan Srinivasan Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1326104915.2442.53.camel@twins Signed-off-by: Ingo Molnar --- Documentation/ABI/testing/sysfs-devices-system-cpu | 25 -- Documentation/scheduler/sched-domains.txt | 4 - arch/x86/kernel/smpboot.c | 3 +- drivers/base/cpu.c | 4 - include/linux/cpu.h | 2 - include/linux/sched.h | 47 ---- include/linux/topology.h | 5 - kernel/sched/core.c | 94 ------- kernel/sched/fair.c | 275 +-------------------- tools/power/cpupower/man/cpupower-set.1 | 9 - tools/power/cpupower/utils/helpers/sysfs.c | 35 +-- 11 files changed, 5 insertions(+), 498 deletions(-) (limited to 'arch/x86') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index e7be75b96e4..5dab36448b4 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -9,31 +9,6 @@ Description: /sys/devices/system/cpu/cpu#/ -What: /sys/devices/system/cpu/sched_mc_power_savings - /sys/devices/system/cpu/sched_smt_power_savings -Date: June 2006 -Contact: Linux kernel mailing list -Description: Discover and adjust the kernel's multi-core scheduler support. - - Possible values are: - - 0 - No power saving load balance (default value) - 1 - Fill one thread/core/package first for long running threads - 2 - Also bias task wakeups to semi-idle cpu package for power - savings - - sched_mc_power_savings is dependent upon SCHED_MC, which is - itself architecture dependent. - - sched_smt_power_savings is dependent upon SCHED_SMT, which - is itself architecture dependent. - - The two files are independent of each other. It is possible - that one file may be present without the other. - - Introduced by git commit 5c45bf27. - - What: /sys/devices/system/cpu/kernel_max /sys/devices/system/cpu/offline /sys/devices/system/cpu/online diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt index b7ee379b651..443f0c76bab 100644 --- a/Documentation/scheduler/sched-domains.txt +++ b/Documentation/scheduler/sched-domains.txt @@ -61,10 +61,6 @@ The implementor should read comments in include/linux/sched.h: struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of the specifics and what to tune. -For SMT, the architecture must define CONFIG_SCHED_SMT and provide a -cpumask_t cpu_sibling_map[NR_CPUS], where cpu_sibling_map[i] is the mask of -all "i"'s siblings as well as "i" itself. - Architectures may retain the regular override the default SD_*_INIT flags while using the generic domain builder in kernel/sched.c if they wish to retain the traditional SMT->SMP->NUMA topology (or some subset of that). This diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e84c1bbea33..256c20cc5e9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -429,8 +429,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ - if ((sched_mc_power_savings || sched_smt_power_savings) && - !(cpu_has(c, X86_FEATURE_AMD_DCM))) + if (!(cpu_has(c, X86_FEATURE_AMD_DCM))) return cpu_core_mask(cpu); else return cpu_llc_shared_mask(cpu); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index adf937bf409..63452943abd 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -330,8 +330,4 @@ void __init cpu_dev_init(void) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - sched_create_sysfs_power_savings_entries(cpu_subsys.dev_root); -#endif } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ee28844ae68..7230bb59a06 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -36,8 +36,6 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern int sched_create_sysfs_power_savings_entries(struct device *dev); - #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a559bf0622..3d644809c9d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -855,61 +855,14 @@ enum cpu_idle_type { #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ -#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -enum powersavings_balance_level { - POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ - POWERSAVINGS_BALANCE_BASIC, /* Fill one thread/core/package - * first for long running threads - */ - POWERSAVINGS_BALANCE_WAKEUP, /* Also bias task wakeups to semi-idle - * cpu package for power savings - */ - MAX_POWERSAVINGS_BALANCE_LEVELS -}; - -extern int sched_mc_power_savings, sched_smt_power_savings; - -static inline int sd_balance_for_mc_power(void) -{ - if (sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - if (!sched_mc_power_savings) - return SD_PREFER_SIBLING; - - return 0; -} - -static inline int sd_balance_for_package_power(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - return SD_PREFER_SIBLING; -} - extern int __weak arch_sd_sibiling_asym_packing(void); -/* - * Optimise SD flags for power savings: - * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings. - * Keep default SD flags if sched_{smt,mc}_power_saving=0 - */ - -static inline int sd_power_saving_flags(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_BALANCE_NEWIDLE; - - return 0; -} - struct sched_group_power { atomic_t ref; /* diff --git a/include/linux/topology.h b/include/linux/topology.h index 4f59bf36f0a..09558d1daac 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -98,7 +98,6 @@ int arch_update_cpu_topology(void); | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ @@ -134,8 +133,6 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_mc_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ @@ -167,8 +164,6 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_package_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bd314d7cd9f..24ca677b545 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5929,8 +5929,6 @@ static const struct cpumask *cpu_cpu_mask(int cpu) return cpumask_of_node(cpu_to_node(cpu)); } -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; - struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; @@ -6322,7 +6320,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_WAKE_AFFINE | 0*SD_PREFER_LOCAL | 0*SD_SHARE_CPUPOWER - | 0*SD_POWERSAVINGS_BALANCE | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE | 0*SD_PREFER_SIBLING @@ -6819,97 +6816,6 @@ match2: mutex_unlock(&sched_domains_mutex); } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void reinit_sched_domains(void) -{ - get_online_cpus(); - - /* Destroy domains first to force the rebuild */ - partition_sched_domains(0, NULL, NULL); - - rebuild_sched_domains(); - put_online_cpus(); -} - -static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -{ - unsigned int level = 0; - - if (sscanf(buf, "%u", &level) != 1) - return -EINVAL; - - /* - * level is always be positive so don't check for - * level < POWERSAVINGS_BALANCE_NONE which is 0 - * What happens on 0 or 1 byte write, - * need to check for count as well? - */ - - if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) - return -EINVAL; - - if (smt) - sched_smt_power_savings = level; - else - sched_mc_power_savings = level; - - reinit_sched_domains(); - - return count; -} - -#ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_mc_power_savings); -} -static ssize_t sched_mc_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 0); -} -static DEVICE_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); -#endif - -#ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_smt_power_savings); -} -static ssize_t sched_smt_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 1); -} -static DEVICE_ATTR(sched_smt_power_savings, 0644, - sched_smt_power_savings_show, - sched_smt_power_savings_store); -#endif - -int __init sched_create_sysfs_power_savings_entries(struct device *dev) -{ - int err = 0; - -#ifdef CONFIG_SCHED_SMT - if (smt_capable()) - err = device_create_file(dev, &dev_attr_sched_smt_power_savings); -#endif -#ifdef CONFIG_SCHED_MC - if (!err && mc_capable()) - err = device_create_file(dev, &dev_attr_sched_mc_power_savings); -#endif - return err; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0b42f448732..940e6d17cf9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2721,7 +2721,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) * If power savings logic is enabled for a domain, see if we * are not overloaded, if so, don't balance wider. */ - if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) { + if (tmp->flags & (SD_PREFER_LOCAL)) { unsigned long power = 0; unsigned long nr_running = 0; unsigned long capacity; @@ -2734,9 +2734,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - nr_running /= 2; - if (nr_running < capacity) want_sd = 0; } @@ -3435,14 +3432,6 @@ struct sd_lb_stats { unsigned int busiest_group_weight; int group_imb; /* Is there imbalance in this sd */ -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance; /* Is powersave balance needed for this sd */ - struct sched_group *group_min; /* Least loaded group in sd */ - struct sched_group *group_leader; /* Group which relieves group_min */ - unsigned long min_load_per_task; /* load_per_task in group_min */ - unsigned long leader_nr_running; /* Nr running of group_leader */ - unsigned long min_nr_running; /* Nr running of group_min */ -#endif }; /* @@ -3486,147 +3475,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * init_sd_power_savings_stats - Initialize power savings statistics for - * the given sched_domain, during load balancing. - * - * @sd: Sched domain whose power-savings statistics are to be initialized. - * @sds: Variable containing the statistics for sd. - * @idle: Idle status of the CPU at which we're performing load-balancing. - */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - sds->power_savings_balance = 0; - else { - sds->power_savings_balance = 1; - sds->min_nr_running = ULONG_MAX; - sds->leader_nr_running = 0; - } -} - -/** - * update_sd_power_savings_stats - Update the power saving stats for a - * sched_domain while performing load balancing. - * - * @group: sched_group belonging to the sched_domain under consideration. - * @sds: Variable containing the statistics of the sched_domain - * @local_group: Does group contain the CPU for which we're performing - * load balancing ? - * @sgs: Variable containing the statistics of the group. - */ -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - - if (!sds->power_savings_balance) - return; - - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (sds->this_nr_running >= sgs->group_capacity || - !sds->this_nr_running)) - sds->power_savings_balance = 0; - - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!sds->power_savings_balance || - sgs->sum_nr_running >= sgs->group_capacity || - !sgs->sum_nr_running) - return; - - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sgs->sum_nr_running < sds->min_nr_running) || - (sgs->sum_nr_running == sds->min_nr_running && - group_first_cpu(group) > group_first_cpu(sds->group_min))) { - sds->group_min = group; - sds->min_nr_running = sgs->sum_nr_running; - sds->min_load_per_task = sgs->sum_weighted_load / - sgs->sum_nr_running; - } - - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sgs->sum_nr_running + 1 > sgs->group_capacity) - return; - - if (sgs->sum_nr_running > sds->leader_nr_running || - (sgs->sum_nr_running == sds->leader_nr_running && - group_first_cpu(group) < group_first_cpu(sds->group_leader))) { - sds->group_leader = group; - sds->leader_nr_running = sgs->sum_nr_running; - } -} - -/** - * check_power_save_busiest_group - see if there is potential for some power-savings balance - * @env: load balance environment - * @sds: Variable containing the statistics of the sched_domain - * under consideration. - * - * Description: - * Check if we have potential to perform some power-savings balance. - * If yes, set the busiest group to be the least loaded group in the - * sched_domain, so that it's CPUs can be put to idle. - * - * Returns 1 if there is potential to perform power-savings balance. - * Else returns 0. - */ -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - if (!sds->power_savings_balance) - return 0; - - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - env->imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - return 1; - -} -#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - return; -} - -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - return; -} - -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - return 0; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - - unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; @@ -3932,7 +3780,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; - init_sd_power_savings_stats(env->sd, sds, env->idle); load_idx = get_sd_load_idx(env->sd, env->idle); do { @@ -3981,7 +3828,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, sds->group_imb = sgs.group_imb; } - update_sd_power_savings_stats(sg, sds, local_group, &sgs); sg = sg->next; } while (sg != env->sd->groups); } @@ -4276,12 +4122,6 @@ force_balance: return sds.busiest; out_balanced: - /* - * There is no obvious imbalance. But check if we can do some balancing - * to save power. - */ - if (check_power_save_busiest_group(env, &sds)) - return sds.busiest; ret: env->imbalance = 0; return NULL; @@ -4359,28 +4199,6 @@ static int need_active_balance(struct lb_env *env) */ if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) return 1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return 0; } return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); @@ -4700,104 +4518,15 @@ static struct { unsigned long next_balance; /* in jiffy units */ } nohz ____cacheline_aligned; -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * lowest_flag_domain - Return lowest sched_domain containing flag. - * @cpu: The cpu whose lowest level of sched domain is to - * be returned. - * @flag: The flag to check for the lowest sched_domain - * for the given cpu. - * - * Returns the lowest sched_domain of a cpu which contains the given flag. - */ -static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) -{ - struct sched_domain *sd; - - for_each_domain(cpu, sd) - if (sd->flags & flag) - break; - - return sd; -} - -/** - * for_each_flag_domain - Iterates over sched_domains containing the flag. - * @cpu: The cpu whose domains we're iterating over. - * @sd: variable holding the value of the power_savings_sd - * for cpu. - * @flag: The flag to filter the sched_domains to be iterated. - * - * Iterates over all the scheduler domains for a given cpu that has the 'flag' - * set, starting from the lowest sched_domain to the highest. - */ -#define for_each_flag_domain(cpu, sd, flag) \ - for (sd = lowest_flag_domain(cpu, flag); \ - (sd && (sd->flags & flag)); sd = sd->parent) - -/** - * find_new_ilb - Finds the optimum idle load balancer for nomination. - * @cpu: The cpu which is nominating a new idle_load_balancer. - * - * Returns: Returns the id of the idle load balancer if it exists, - * Else, returns >= nr_cpu_ids. - * - * This algorithm picks the idle load balancer such that it belongs to a - * semi-idle powersavings sched_domain. The idea is to try and avoid - * completely idle packages/cores just for the purpose of idle load balancing - * when there are other idle cpu's which are better suited for that job. - */ -static int find_new_ilb(int cpu) +static inline int find_new_ilb(int call_cpu) { int ilb = cpumask_first(nohz.idle_cpus_mask); - struct sched_group *ilbg; - struct sched_domain *sd; - /* - * Have idle load balancer selection from semi-idle packages only - * when power-aware load balancing is enabled - */ - if (!(sched_smt_power_savings || sched_mc_power_savings)) - goto out_done; - - /* - * Optimize for the case when we have no idle CPUs or only one - * idle CPU. Don't walk the sched_domain hierarchy in such cases - */ - if (cpumask_weight(nohz.idle_cpus_mask) < 2) - goto out_done; - - rcu_read_lock(); - for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { - ilbg = sd->groups; - - do { - if (ilbg->group_weight != - atomic_read(&ilbg->sgp->nr_busy_cpus)) { - ilb = cpumask_first_and(nohz.idle_cpus_mask, - sched_group_cpus(ilbg)); - goto unlock; - } - - ilbg = ilbg->next; - - } while (ilbg != sd->groups); - } -unlock: - rcu_read_unlock(); - -out_done: if (ilb < nr_cpu_ids && idle_cpu(ilb)) return ilb; return nr_cpu_ids; } -#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ -static inline int find_new_ilb(int call_cpu) -{ - return nr_cpu_ids; -} -#endif /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick the diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1 index c4954a9fe4e..9dbd536518a 100644 --- a/tools/power/cpupower/man/cpupower-set.1 +++ b/tools/power/cpupower/man/cpupower-set.1 @@ -85,15 +85,6 @@ Possible values are: savings .RE -sched_mc_power_savings is dependent upon SCHED_MC, which is -itself architecture dependent. - -sched_smt_power_savings is dependent upon SCHED_SMT, which -is itself architecture dependent. - -The two files are independent of each other. It is possible -that one file may be present without the other. - .SH "SEE ALSO" cpupower-info(1), cpupower-monitor(1), powertop(1) .PP diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c index c6343024a61..96e28c124b5 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -362,22 +362,7 @@ char *sysfs_get_cpuidle_driver(void) */ int sysfs_get_sched(const char *smt_mc) { - unsigned long value; - char linebuf[MAX_LINE_LEN]; - char *endp; - char path[SYSFS_PATH_MAX]; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - value = strtoul(linebuf, &endp, 0); - if (endp == linebuf || errno == ERANGE) - return -1; - return value; + return -ENODEV; } /* @@ -388,21 +373,5 @@ int sysfs_get_sched(const char *smt_mc) */ int sysfs_set_sched(const char *smt_mc, int val) { - char linebuf[MAX_LINE_LEN]; - char path[SYSFS_PATH_MAX]; - struct stat statbuf; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - sprintf(linebuf, "%d", val); - - if (stat(path, &statbuf) != 0) - return -ENODEV; - - if (sysfs_write_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - return 0; + return -ENODEV; } -- cgit v1.2.3-70-g09d2