From ed8d9adf357ec331603fa1049510399812cea7e5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 3 Aug 2009 14:08:48 +0900 Subject: x86, percpu: Add 'percpu_read_stable()' interface for cacheable accesses This is very useful for some common things like 'get_current()' and 'get_thread_info()', which can be used multiple times in a function, and where the result is cacheable. tj: Added the magical undocumented "P" modifier to UP __percpu_arg() to force gcc to dereference the pointer value passed in via the "p" input constraint. Without this, percpu_read_stable() returns the address of the percpu variable. Also added comment explaining the difference between percpu_read() and percpu_read_stable(). Signed-off-by: Linus Torvalds Signed-off-by: Tejun Heo Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/current.h | 2 +- arch/x86/include/asm/percpu.h | 26 +++++++++++++++++++------- arch/x86/include/asm/thread_info.h | 2 +- 3 files changed, 21 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index c68c361697e1..4d447b732d82 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -11,7 +11,7 @@ DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { - return percpu_read(current_task); + return percpu_read_stable(current_task); } #define current get_current() diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 103f1ddb0d85..04eacefcfd26 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -49,7 +49,7 @@ #define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x #define __my_cpu_offset percpu_read(this_cpu_off) #else -#define __percpu_arg(x) "%" #x +#define __percpu_arg(x) "%P" #x #endif /* @@ -104,36 +104,48 @@ do { \ } \ } while (0) -#define percpu_from_op(op, var) \ +#define percpu_from_op(op, var, constraint) \ ({ \ typeof(var) ret__; \ switch (sizeof(var)) { \ case 1: \ asm(op "b "__percpu_arg(1)",%0" \ : "=q" (ret__) \ - : "m" (var)); \ + : constraint); \ break; \ case 2: \ asm(op "w "__percpu_arg(1)",%0" \ : "=r" (ret__) \ - : "m" (var)); \ + : constraint); \ break; \ case 4: \ asm(op "l "__percpu_arg(1)",%0" \ : "=r" (ret__) \ - : "m" (var)); \ + : constraint); \ break; \ case 8: \ asm(op "q "__percpu_arg(1)",%0" \ : "=r" (ret__) \ - : "m" (var)); \ + : constraint); \ break; \ default: __bad_percpu_size(); \ } \ ret__; \ }) -#define percpu_read(var) percpu_from_op("mov", per_cpu__##var) +/* + * percpu_read() makes gcc load the percpu variable every time it is + * accessed while percpu_read_stable() allows the value to be cached. + * percpu_read_stable() is more efficient and can be used if its value + * is guaranteed to be valid across cpus. The current users include + * get_current() and get_thread_info() both of which are actually + * per-thread variables implemented as per-cpu variables and thus + * stable for the duration of the respective task. + */ +#define percpu_read(var) percpu_from_op("mov", per_cpu__##var, \ + "m" (per_cpu__##var)) +#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var, \ + "p" (&per_cpu__##var)) #define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val) #define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val) #define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index fad7d40b75f8..a1bb5a114bf2 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -213,7 +213,7 @@ DECLARE_PER_CPU(unsigned long, kernel_stack); static inline struct thread_info *current_thread_info(void) { struct thread_info *ti; - ti = (void *)(percpu_read(kernel_stack) + + ti = (void *)(percpu_read_stable(kernel_stack) + KERNEL_STACK_OFFSET - THREAD_SIZE); return ti; } -- cgit v1.2.2 From 3e352aa8ee2bd48f1a19c7742810b3a4a7ba605e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Aug 2009 14:10:11 +0900 Subject: x86, percpu: Fix DECLARE/DEFINE_PER_CPU_PAGE_ALIGNED() DECLARE/DEFINE_PER_CPU_PAGE_ALIGNED() put percpu variables in .page_aligned section without adding any alignment restrictions. Currently, this doesn't cause any problem because all users of the macros have explicit page alignment and page-sized but it's much safer to enforce page alignment from the macros. After all, it's what they claim to do. Add __aligned(PAGE_SIZE) to DECLARE/DEFINE_PER_CPU_PAGE_ALIGNED() and drop explicit alignment from it users. Signed-off-by: Tejun Heo Cc: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f1961c07af9a..12493c5485e5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1008,8 +1008,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { }; static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]) - __aligned(PAGE_SIZE); + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); /* May not be marked __init: used by software suspend */ void syscall_init(void) -- cgit v1.2.2 From bdf977b37418cdf8a2252504779a7e12a09b7575 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Aug 2009 14:12:19 +0900 Subject: x86, percpu: Collect hot percpu variables into one cacheline On x86_64, percpu variables current_task and kernel_stack are used for get_current() and current_thread_info() respectively and thus are often used close to each other. Move definition of current_task to kernel/cpu/common.c right above kernel_stack definition and align it to cacheline so that they always fall into the same cacheline. Two percpu variables defined there together - irq_stack_ptr and irq_count - are also pretty hot and will benefit from sharing the cacheline. For consistency, current_task definition for x86_32 is also moved to kernel/cpu/common.c. Putting current_task and kernel_stack into the same cacheline was suggested by Linus Torvalds. Signed-off-by: Tejun Heo Cc: Linus Torvalds Cc: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 15 +++++++++++++-- arch/x86/kernel/process_32.c | 3 --- arch/x86/kernel/process_64.c | 3 --- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 12493c5485e5..1bd88ed978bd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -987,13 +987,21 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE); -DEFINE_PER_CPU(char *, irq_stack_ptr) = - init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; +/* + * The following four percpu variables are hot. Align current_task to + * cacheline size such that all four fall in the same cacheline. + */ +DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = + &init_task; +EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(unsigned long, kernel_stack) = (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; EXPORT_PER_CPU_SYMBOL(kernel_stack); +DEFINE_PER_CPU(char *, irq_stack_ptr) = + init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; + DEFINE_PER_CPU(unsigned int, irq_count) = -1; /* @@ -1041,6 +1049,9 @@ DEFINE_PER_CPU(struct orig_ist, orig_ist); #else /* CONFIG_X86_64 */ +DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; +EXPORT_PER_CPU_SYMBOL(current_task); + #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU(unsigned long, stack_canary); #endif diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 59f4524984af..daa4107be3b4 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -61,9 +61,6 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; -EXPORT_PER_CPU_SYMBOL(current_task); - /* * Return saved PC of a blocked thread. */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ebefb5407b9d..c4c675d5ba1a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -55,9 +55,6 @@ asmlinkage extern void ret_from_fork(void); -DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; -EXPORT_PER_CPU_SYMBOL(current_task); - DEFINE_PER_CPU(unsigned long, old_rsp); static DEFINE_PER_CPU(unsigned char, is_idle); -- cgit v1.2.2