diff options
| author | Tejun Heo <tj@kernel.org> | 2009-08-03 05:12:19 (GMT) |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2009-08-03 16:29:34 (GMT) |
| commit | bdf977b37418cdf8a2252504779a7e12a09b7575 (patch) | |
| tree | 0f3896a5b39c35f3018d3cb16f797ae7d6c4a66b /arch/x86/kernel/cpu | |
| parent | 3e352aa8ee2bd48f1a19c7742810b3a4a7ba605e (diff) | |
| download | linux-fsl-qoriq-bdf977b37418cdf8a2252504779a7e12a09b7575.tar.xz | |
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 <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Diffstat (limited to 'arch/x86/kernel/cpu')
| -rw-r--r-- | arch/x86/kernel/cpu/common.c | 15 |
1 files changed, 13 insertions, 2 deletions
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 12493c5..1bd88ed 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 |