From 6dbde3530850d4d8bfc1b6bd4006d92786a2787f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 15 Jan 2009 22:15:53 +0900 Subject: percpu: add optimized generic percpu accessors It is an optimization and a cleanup, and adds the following new generic percpu methods: percpu_read() percpu_write() percpu_add() percpu_sub() percpu_and() percpu_or() percpu_xor() and implements support for them on x86. (other architectures will fall back to a default implementation) The advantage is that for example to read a local percpu variable, instead of this sequence: return __get_cpu_var(var); ffffffff8102ca2b: 48 8b 14 fd 80 09 74 mov -0x7e8bf680(,%rdi,8),%rdx ffffffff8102ca32: 81 ffffffff8102ca33: 48 c7 c0 d8 59 00 00 mov $0x59d8,%rax ffffffff8102ca3a: 48 8b 04 10 mov (%rax,%rdx,1),%rax We can get a single instruction by using the optimized variants: return percpu_read(var); ffffffff8102ca3f: 65 48 8b 05 91 8f fd mov %gs:0x7efd8f91(%rip),%rax I also cleaned up the x86-specific APIs and made the x86 code use these new generic percpu primitives. tj: * fixed generic percpu_sub() definition as Roel Kluin pointed out * added percpu_and() for completeness's sake * made generic percpu ops atomic against preemption Signed-off-by: Ingo Molnar Signed-off-by: Tejun Heo --- arch/x86/include/asm/current.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm/current.h') diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index 0930b4f8d67..0728480f5c5 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -10,7 +10,7 @@ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { - return x86_read_percpu(current_task); + return percpu_read(current_task); } #else /* X86_32 */ -- cgit v1.2.3-70-g09d2 From c6f5e0acd5d12ee23f701f15889872e67b47caa6 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Mon, 19 Jan 2009 00:38:58 +0900 Subject: x86-64: Move current task from PDA to per-cpu and consolidate with 32-bit. Signed-off-by: Brian Gerst Signed-off-by: Tejun Heo --- arch/x86/include/asm/current.h | 24 +++--------------------- arch/x86/include/asm/pda.h | 4 ++-- arch/x86/include/asm/system.h | 4 ++-- arch/x86/kernel/asm-offsets_64.c | 1 - arch/x86/kernel/cpu/common.c | 5 +---- arch/x86/kernel/dumpstack_64.c | 2 +- arch/x86/kernel/process_64.c | 5 ++++- arch/x86/kernel/smpboot.c | 3 +-- arch/x86/xen/smp.c | 3 +-- 9 files changed, 15 insertions(+), 36 deletions(-) (limited to 'arch/x86/include/asm/current.h') diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index 0728480f5c5..c68c361697e 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -1,39 +1,21 @@ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H -#ifdef CONFIG_X86_32 #include #include +#ifndef __ASSEMBLY__ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); -static __always_inline struct task_struct *get_current(void) -{ - return percpu_read(current_task); -} - -#else /* X86_32 */ - -#ifndef __ASSEMBLY__ -#include - -struct task_struct; static __always_inline struct task_struct *get_current(void) { - return read_pda(pcurrent); + return percpu_read(current_task); } -#else /* __ASSEMBLY__ */ - -#include -#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg +#define current get_current() #endif /* __ASSEMBLY__ */ -#endif /* X86_32 */ - -#define current get_current() - #endif /* _ASM_X86_CURRENT_H */ diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h index 668d5a5b6f7..7209302d922 100644 --- a/arch/x86/include/asm/pda.h +++ b/arch/x86/include/asm/pda.h @@ -11,8 +11,8 @@ /* Per processor datastructure. %gs points to it while the kernel runs */ struct x8664_pda { - struct task_struct *pcurrent; /* 0 Current process */ - unsigned long dummy; + unsigned long unused1; + unsigned long unused2; unsigned long kernelstack; /* 16 top of kernel stack for current */ unsigned long oldrsp; /* 24 user rsp for system call */ int irqcount; /* 32 Irq nesting counter. Starts -1 */ diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index 8e626ea33a1..4399aac680e 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -94,7 +94,7 @@ do { \ "call __switch_to\n\t" \ ".globl thread_return\n" \ "thread_return:\n\t" \ - "movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \ + "movq "__percpu_seg_str"%P[current_task],%%rsi\n\t" \ "movq %P[thread_info](%%rsi),%%r8\n\t" \ LOCK_PREFIX "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \ "movq %%rax,%%rdi\n\t" \ @@ -106,7 +106,7 @@ do { \ [ti_flags] "i" (offsetof(struct thread_info, flags)), \ [tif_fork] "i" (TIF_FORK), \ [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \ + [current_task] "m" (per_cpu_var(current_task)) \ : "memory", "cc" __EXTRA_CLOBBER) #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index cae6697c099..4f7a210e1e5 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -51,7 +51,6 @@ int main(void) #define ENTRY(entry) DEFINE(pda_ ## entry, offsetof(struct x8664_pda, entry)) ENTRY(kernelstack); ENTRY(oldrsp); - ENTRY(pcurrent); ENTRY(irqcount); DEFINE(pda_size, sizeof(struct x8664_pda)); BLANK(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4221e920886..b50e38d1688 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -903,10 +903,7 @@ void __cpuinit pda_init(int cpu) pda->kernelstack = (unsigned long)stack_thread_info() - PDA_STACKOFFSET + THREAD_SIZE; - if (cpu == 0) { - /* others are initialized in smpboot.c */ - pda->pcurrent = &init_task; - } else { + if (cpu != 0) { if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE) pda->nodenumber = cpu_to_node(cpu); } diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 28e26a4315d..d35db5993fd 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -242,7 +242,7 @@ void show_registers(struct pt_regs *regs) int i; unsigned long sp; const int cpu = smp_processor_id(); - struct task_struct *cur = cpu_pda(cpu)->pcurrent; + struct task_struct *cur = current; sp = regs->sp; printk("CPU %d ", cpu); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 416fb9282f4..e00c31a4b3c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -57,6 +57,9 @@ asmlinkage extern void ret_from_fork(void); +DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; +EXPORT_PER_CPU_SYMBOL(current_task); + unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; static ATOMIC_NOTIFIER_HEAD(idle_notifier); @@ -615,7 +618,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ prev->usersp = read_pda(oldrsp); write_pda(oldrsp, next->usersp); - write_pda(pcurrent, next_p); + percpu_write(current_task, next_p); write_pda(kernelstack, (unsigned long)task_stack_page(next_p) + diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2f0e0f1090f..5854be0fb80 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -790,13 +790,12 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) set_idle_for_cpu(cpu, c_idle.idle); do_rest: -#ifdef CONFIG_X86_32 per_cpu(current_task, cpu) = c_idle.idle; +#ifdef CONFIG_X86_32 init_gdt(cpu); /* Stack for startup_32 can be just as for start_secondary onwards */ irq_ctx_init(cpu); #else - cpu_pda(cpu)->pcurrent = c_idle.idle; clear_tsk_thread_flag(c_idle.idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 9ff3b0999cf..72c2eb9b64c 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -279,12 +279,11 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) struct task_struct *idle = idle_task(cpu); int rc; + per_cpu(current_task, cpu) = idle; #ifdef CONFIG_X86_32 init_gdt(cpu); - per_cpu(current_task, cpu) = idle; irq_ctx_init(cpu); #else - cpu_pda(cpu)->pcurrent = idle; clear_tsk_thread_flag(idle, TIF_FORK); #endif xen_setup_timer(cpu); -- cgit v1.2.3-70-g09d2