From: Steven Rostedt x86_64 uses a per_cpu variable kernel_stack to always point to the thread stack of current. This is where the thread_info is stored and is accessed from this location even when the irq or exception stack is in use. This removes the complexity of having to maintain the thread info on the stack when interrupts are running and having to copy the preempt_count and other fields to the interrupt stack. x86_32 uses the old method of copying the thread_info from the thread stack to the exception stack just before executing the exception. Having the two different requires #ifdefs and also the x86_32 way is a bit of a pain to maintain. By converting x86_32 to the same method of x86_64, we can remove #ifdefs, clean up the x86_32 code a little, and remove the overhead of the copy. Link: http://lkml.kernel.org/r/20110806012354.263834829@goodmis.org Cc: Andrew Morton Cc: Peter Zijlstra Cc: Brian Gerst Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: H. Peter Anvin Cc: Ingo Molnar Signed-off-by: Steven Rostedt --- arch/x86/include/asm/processor.h | 9 +++++ arch/x86/include/asm/thread_info.h | 48 ++++--------------------- arch/x86/kernel/cpu/common.c | 8 ++--- arch/x86/kernel/dumpstack_32.c | 41 +++++++++++++++++---- arch/x86/kernel/irq_32.c | 74 ++++++++++++++++---------------------- arch/x86/kernel/process_32.c | 4 +++ arch/x86/kernel/ptrace.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- 8 files changed, 90 insertions(+), 98 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7b034a4..d787f40 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -432,6 +432,15 @@ struct stack_canary { }; DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif +/* + * per-CPU IRQ handling stacks + */ +struct irq_stack { + u32 stack[THREAD_SIZE/sizeof(u32)]; +} __aligned(THREAD_SIZE); + +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); +DECLARE_PER_CPU(struct irq_stack *, softirq_stack); #endif /* X86_64 */ extern unsigned int xstate_size; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ed96e37..e3d1b0f 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -34,12 +34,6 @@ struct thread_info { void __user *sysenter_return; unsigned int sig_on_uaccess_error:1; unsigned int uaccess_err:1; /* uaccess failed */ -#ifdef CONFIG_X86_32 - unsigned long previous_esp; /* ESP of the previous stack in - case of nested (IRQ) stacks - (Moved to end, to be removed soon) - */ -#endif }; #define INIT_THREAD_INFO(tsk) \ @@ -153,9 +147,11 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) -#ifdef CONFIG_X86_32 +#include + +#define STACK_WARN (THREAD_SIZE/8) +#define KERNEL_STACK_OFFSET (5*(BITS_PER_LONG/8)) -#define STACK_WARN (THREAD_SIZE/8) /* * macros/functions for gaining access to the thread information structure * @@ -163,36 +159,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ - -/* how to get the current stack pointer from C */ -register unsigned long current_stack_pointer asm("esp") __used; - -/* how to get the thread information struct from C */ -static inline struct thread_info *current_thread_info(void) -{ - return (struct thread_info *) - (current_stack_pointer & ~(THREAD_SIZE - 1)); -} - -#else /* !__ASSEMBLY__ */ - -/* how to get the thread information struct from ASM */ -#define GET_THREAD_INFO(reg) \ - movl $-THREAD_SIZE, reg; \ - andl %esp, reg - -#endif - -#else /* X86_32 */ - -#include -#define KERNEL_STACK_OFFSET (5*8) - -/* - * macros/functions for gaining access to the thread information structure - * preempt_count needs to be 1 initially, until the scheduler is functional. - */ -#ifndef __ASSEMBLY__ DECLARE_PER_CPU(unsigned long, kernel_stack); static inline struct thread_info *current_thread_info(void) @@ -207,8 +173,8 @@ static inline struct thread_info *current_thread_info(void) /* how to get the thread information struct from ASM */ #define GET_THREAD_INFO(reg) \ - movq PER_CPU_VAR(kernel_stack),reg ; \ - subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg + _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \ + _ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ; /* * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in @@ -218,8 +184,6 @@ static inline struct thread_info *current_thread_info(void) #endif -#endif /* !X86_32 */ - /* * Thread-synchronous status. * diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6abc172..e45705b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1072,6 +1072,10 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); +DEFINE_PER_CPU(unsigned long, kernel_stack) = + (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; +EXPORT_PER_CPU_SYMBOL(kernel_stack); + #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, @@ -1088,10 +1092,6 @@ 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; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 187d6a7..dca820b 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,11 +16,33 @@ #include +static void *is_irq_stack(void *p, void *irq) +{ + if (p < irq || p >= (irq + THREAD_SIZE)) + return NULL; + return irq + THREAD_SIZE; +} + + +static void *is_hardirq_stack(unsigned long *stack, int cpu) +{ + void *irq = per_cpu(hardirq_stack, cpu); + + return is_irq_stack(stack, irq); +} + +static void *is_softirq_stack(unsigned long *stack, int cpu) +{ + void *irq = per_cpu(softirq_stack, cpu); + + return is_irq_stack(stack, irq); +} void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data) { + const unsigned cpu = get_cpu(); int graph = 0; u32 *prev_esp; @@ -40,18 +62,22 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, for (;;) { struct thread_info *context; + void *end_stack; + + end_stack = is_hardirq_stack(stack, cpu); + if (!end_stack) + end_stack = is_softirq_stack(stack, cpu); - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph); + context = task_thread_info(task); + bp = ops->walk_stack(context, stack, bp, ops, data, + end_stack, &graph); /* Stop if not on irq stack */ - if (task_stack_page(task) == context) + if (!end_stack) break; - /* The previous esp is just above the context */ - prev_esp = (u32 *) ((char *)context + sizeof(struct thread_info) - - sizeof(long)); + /* The previous esp is saved on the bottom of the stack */ + prev_esp = (u32 *)(end_stack - THREAD_SIZE); stack = (unsigned long *)*prev_esp; if (!stack) break; @@ -60,6 +86,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, break; touch_nmi_watchdog(); } + put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index f135cc2..988dc8b 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -55,16 +55,8 @@ static inline int check_stack_overflow(void) { return 0; } static inline void print_stack_overflow(void) { } #endif -/* - * per-CPU IRQ handling contexts (thread information and stack) - */ -union irq_ctx { - struct thread_info tinfo; - u32 stack[THREAD_SIZE/sizeof(u32)]; -} __attribute__((aligned(THREAD_SIZE))); - -static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx); -static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx); +DEFINE_PER_CPU(struct irq_stack *, hardirq_stack); +DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { @@ -77,14 +69,22 @@ static void call_on_stack(void *func, void *stack) : "memory", "cc", "edx", "ecx", "eax"); } +/* how to get the current stack pointer from C */ +register unsigned long current_stack_pointer asm("esp") __used; + +static inline void *current_stack(void) +{ + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); +} + static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { - union irq_ctx *curctx, *irqctx; + struct irq_stack *curstk, *irqstk; u32 *isp, *prev_esp, arg1, arg2; - curctx = (union irq_ctx *) current_thread_info(); - irqctx = __this_cpu_read(hardirq_ctx); + curstk = (struct irq_stack *) current_stack(); + irqstk = __this_cpu_read(hardirq_stack); /* * this is where we switch to the IRQ stack. However, if we are @@ -92,15 +92,13 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) * handler) we can't do that and just have to keep using the * current stack (which is the irq stack already after all) */ - if (unlikely(curctx == irqctx)) + if (unlikely(curstk == irqstk)) return 0; - /* build the stack frame on the IRQ stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); - irqctx->tinfo.task = curctx->tinfo.task; - /* Save the next esp after thread_info */ - prev_esp = (u32 *) ((char *)irqctx + sizeof(struct thread_info) - - sizeof(long)); + isp = (u32 *) ((char *)irqstk + sizeof(*irqstk)); + + /* Save the next esp at the bottom of the stack */ + prev_esp = (u32 *)irqstk; *prev_esp = current_stack_pointer; if (unlikely(overflow)) @@ -121,49 +119,39 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) */ void irq_ctx_init(int cpu) { - union irq_ctx *irqctx; + struct irq_stack *irqstk; - if (per_cpu(hardirq_ctx, cpu)) + if (per_cpu(hardirq_stack, cpu)) return; - irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), + irqstk = page_address(alloc_pages_node(cpu_to_node(cpu), THREADINFO_GFP, THREAD_SIZE_ORDER)); - memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); + per_cpu(hardirq_stack, cpu) = irqstk; - per_cpu(hardirq_ctx, cpu) = irqctx; - - irqctx = page_address(alloc_pages_node(cpu_to_node(cpu), + irqstk = page_address(alloc_pages_node(cpu_to_node(cpu), THREADINFO_GFP, THREAD_SIZE_ORDER)); - memset(&irqctx->tinfo, 0, sizeof(struct thread_info)); - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - - per_cpu(softirq_ctx, cpu) = irqctx; + per_cpu(softirq_stack, cpu) = irqstk; printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n", - cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); } void do_softirq_own_stack(void) { - struct thread_info *curctx; - union irq_ctx *irqctx; + struct thread_info *curstk; + struct irq_stack *irqstk; u32 *isp, *prev_esp; - curctx = current_thread_info(); - irqctx = __this_cpu_read(softirq_ctx); - irqctx->tinfo.task = curctx->task; + curstk = current_stack(); + irqstk = __this_cpu_read(softirq_stack); /* build the stack frame on the softirq stack */ - isp = (u32 *) ((char *)irqctx + sizeof(*irqctx)); + isp = (u32 *) ((char *)irqstk + sizeof(*irqstk)); /* Push the previous esp onto the stack */ - prev_esp = (u32 *) ((char *)irqctx + sizeof(struct thread_info) - - sizeof(long)); + prev_esp = (u32 *)irqstk; *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 6f1236c..09c8380 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -315,6 +315,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); + this_cpu_write(kernel_stack, + (unsigned long)task_stack_page(next_p) + + THREAD_SIZE - KERNEL_STACK_OFFSET); + /* * Restore %gs if needed (which is common) */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f352a7c..678c0ad 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -189,7 +189,7 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs) if (context == (sp & ~(THREAD_SIZE - 1))) return sp; - prev_esp = (u32 *)(context + sizeof(struct thread_info) - sizeof(long)); + prev_esp = (u32 *)(context); if (prev_esp) return (unsigned long)prev_esp; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 85dc05a..7027585 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -758,10 +758,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) #else clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); +#endif per_cpu(kernel_stack, cpu) = (unsigned long)task_stack_page(idle) - KERNEL_STACK_OFFSET + THREAD_SIZE; -#endif early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; -- 1.8.4.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/