From 55ccf3fe3f9a3441731aa79cf42a628fc4ecace9 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 16 May 2012 15:03:51 -0700 Subject: fork: move the real prepare_to_copy() users to arch_dup_task_struct() Historical prepare_to_copy() is mostly a no-op, duplicated for majority of the architectures and the rest following the x86 model of flushing the extended register state like fpu there. Remove it and use the arch_dup_task_struct() instead. Suggested-by: Oleg Nesterov Suggested-by: Linus Torvalds Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1336692811-30576-1-git-send-email-suresh.b.siddha@intel.com Acked-by: Benjamin Herrenschmidt Cc: David Howells Cc: Koichi Yasutake Cc: Paul Mackerras Cc: Paul Mundt Cc: Chris Zankel Cc: Richard Henderson Cc: Russell King Cc: Haavard Skinnemoen Cc: Mike Frysinger Cc: Mark Salter Cc: Aurelien Jacquiot Cc: Mikael Starvik Cc: Yoshinori Sato Cc: Richard Kuo Cc: Tony Luck Cc: Michal Simek Cc: Ralf Baechle Cc: Jonas Bonn Cc: James E.J. Bottomley Cc: Helge Deller Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Chen Liqin Cc: Lennox Wu Cc: David S. Miller Cc: Chris Metcalf Cc: Jeff Dike Cc: Richard Weinberger Cc: Guan Xuetao Signed-off-by: H. Peter Anvin --- arch/alpha/include/asm/processor.h | 3 --- arch/arm/include/asm/processor.h | 3 --- arch/avr32/include/asm/processor.h | 3 --- arch/blackfin/include/asm/processor.h | 2 -- arch/c6x/include/asm/processor.h | 3 --- arch/cris/include/asm/processor.h | 4 ---- arch/frv/include/asm/processor.h | 2 -- arch/frv/kernel/process.c | 11 ----------- arch/h8300/include/asm/processor.h | 2 -- arch/hexagon/include/asm/processor.h | 7 ------- arch/ia64/include/asm/processor.h | 3 --- arch/m32r/include/asm/processor.h | 2 -- arch/m68k/include/asm/processor.h | 3 --- arch/microblaze/include/asm/processor.h | 1 - arch/mips/include/asm/processor.h | 3 --- arch/mn10300/include/asm/processor.h | 3 --- arch/mn10300/kernel/process.c | 10 ++++++---- arch/openrisc/include/asm/processor.h | 4 ---- arch/parisc/include/asm/processor.h | 3 --- arch/powerpc/include/asm/processor.h | 3 --- arch/powerpc/kernel/process.c | 19 +++++++++++-------- arch/s390/include/asm/processor.h | 3 --- arch/score/include/asm/processor.h | 1 - arch/sh/include/asm/processor_32.h | 3 --- arch/sh/include/asm/processor_64.h | 1 - arch/sh/kernel/process.c | 7 +++++++ arch/sh/kernel/process_32.c | 9 --------- arch/sparc/include/asm/processor_32.h | 3 --- arch/sparc/include/asm/processor_64.h | 3 --- arch/tile/include/asm/processor.h | 3 --- arch/um/include/asm/processor-generic.h | 5 ----- arch/unicore32/include/asm/processor.h | 3 --- arch/x86/include/asm/processor.h | 3 --- arch/x86/kernel/process.c | 6 ++++++ arch/x86/kernel/process_32.c | 9 --------- arch/x86/kernel/process_64.c | 9 --------- arch/xtensa/include/asm/processor.h | 3 --- arch/xtensa/kernel/process.c | 9 ++++++--- 38 files changed, 36 insertions(+), 138 deletions(-) (limited to 'arch') diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 94afe585930..e37b887b3d9 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -49,9 +49,6 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long); /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - /* Create a kernel thread without removing it from tasklists. */ extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 5ac8d3d3e02..6354224f980 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -77,9 +77,6 @@ struct task_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - unsigned long get_wchan(struct task_struct *p); #if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327) diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h index 108502bc677..87d8baccc60 100644 --- a/arch/avr32/include/asm/processor.h +++ b/arch/avr32/include/asm/processor.h @@ -145,9 +145,6 @@ extern void release_thread(struct task_struct *); /* Create a kernel thread without removing it from tasklists */ extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while(0) - /* Return saved PC of a blocked thread */ #define thread_saved_pc(tsk) ((tsk)->thread.cpu_context.pc) diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h index 8af7772e84c..4ef7cfe43ce 100644 --- a/arch/blackfin/include/asm/processor.h +++ b/arch/blackfin/include/asm/processor.h @@ -75,8 +75,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -#define prepare_to_copy(tsk) do { } while (0) - extern int kernel_thread(int (*fn) (void *), void *arg, unsigned long flags); /* diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h index 3ff7fab956b..c50af7ef1c9 100644 --- a/arch/c6x/include/asm/processor.h +++ b/arch/c6x/include/asm/processor.h @@ -92,9 +92,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); #define copy_segments(tsk, mm) do { } while (0) diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h index 4210d72a666..37f522feabc 100644 --- a/arch/cris/include/asm/processor.h +++ b/arch/cris/include/asm/processor.h @@ -50,10 +50,6 @@ struct task_struct; #define task_pt_regs(task) user_regs(task_thread_info(task)) #define current_regs() task_pt_regs(current) -static inline void prepare_to_copy(struct task_struct *tsk) -{ -} - extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); unsigned long get_wchan(struct task_struct *p); diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index 81c2e271d62..9c768170b30 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -103,8 +103,6 @@ do { \ __frame->sp = (_usp); \ } while(0) -extern void prepare_to_copy(struct task_struct *tsk); - /* Free all resources held by a thread. */ static inline void release_thread(struct task_struct *dead_task) { diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index d4de48bd5ef..9f3dfadee09 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -180,17 +180,6 @@ asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, return do_fork(clone_flags, newsp, __frame, 0, parent_tidptr, child_tidptr); } /* end sys_clone() */ -/*****************************************************************************/ -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - //unlazy_fpu(tsk); -} /* end prepare_to_copy() */ - -/*****************************************************************************/ /* * set up the kernel stack and exception frames for a new process */ diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index 61fabf1788c..4c9f6f87b61 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -109,8 +109,6 @@ static inline void release_thread(struct task_struct *dead_task) extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); -#define prepare_to_copy(tsk) do { } while (0) - /* * Free current thread data structures etc.. */ diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index 20c5ddabbd8..e8ea459002a 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -58,13 +58,6 @@ struct thread_struct { #define cpu_relax() __vmyield() -/* - * "Unlazying all lazy status" occurs here. - */ -static inline void prepare_to_copy(struct task_struct *tsk) -{ -} - /* * Decides where the kernel will search for a free chunk of vm space during * mmaps. diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 483f6c6a423..efcca1b601c 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -343,9 +343,6 @@ struct task_struct; */ #define release_thread(dead_task) -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - /* * This is the mechanism for creating a new kernel thread. * diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h index e1f46d75746..da17253b573 100644 --- a/arch/m32r/include/asm/processor.h +++ b/arch/m32r/include/asm/processor.h @@ -118,8 +118,6 @@ struct mm_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -#define prepare_to_copy(tsk) do { } while (0) - /* * create a kernel thread without removing it from tasklists */ diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 46460fa15d5..f17c42aff7f 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -153,9 +153,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); /* diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index bffb5452729..af2bb965239 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -23,7 +23,6 @@ extern const struct seq_operations cpuinfo_op; # define cpu_relax() barrier() # define cpu_sleep() do {} while (0) -# define prepare_to_copy(tsk) do {} while (0) #define task_pt_regs(tsk) \ (((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 20e9dcf42b2..5e33fabe354 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -310,9 +310,6 @@ struct task_struct; /* Free all resources held by a thread. */ #define release_thread(thread) do { } while(0) -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); extern unsigned long thread_saved_pc(struct task_struct *tsk); diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h index f7b3c9ab2cb..247928c9f54 100644 --- a/arch/mn10300/include/asm/processor.h +++ b/arch/mn10300/include/asm/processor.h @@ -139,9 +139,6 @@ static inline void start_thread(struct pt_regs *regs, /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -extern void prepare_to_copy(struct task_struct *tsk); - /* * create a kernel thread without removing it from tasklists */ diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 14707f25153..7dab0cd3646 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -208,12 +208,14 @@ void copy_segments(struct task_struct *p, struct mm_struct *new_mm) } /* - * this gets called before we allocate a new thread and copy the current task - * into it so that we can store lazy state into memory + * this gets called so that we can store lazy state into memory and copy the + * current task into the new thread. */ -void prepare_to_copy(struct task_struct *tsk) +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - unlazy_fpu(tsk); + unlazy_fpu(src); + *dst = *src; + return 0; } /* diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index f7516fa78b5..30462f1fe95 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -72,10 +72,6 @@ struct thread_struct { #define task_pt_regs(task) user_regs(task_thread_info(task)) #define current_regs() user_regs(current_thread_info()) -extern inline void prepare_to_copy(struct task_struct *tsk) -{ -} - #define INIT_SP (sizeof(init_stack) + (unsigned long) &init_stack) #define INIT_THREAD { } diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index acdf4cad612..0e8b7b8ce8a 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -328,9 +328,6 @@ struct mm_struct; extern void release_thread(struct task_struct *); extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern void map_hpux_gateway_page(struct task_struct *tsk, struct mm_struct *mm); extern unsigned long get_wchan(struct task_struct *p); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8e2d0371fe1..854f899d0c3 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -74,9 +74,6 @@ struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -extern void prepare_to_copy(struct task_struct *tsk); - /* Create a new kernel thread. */ extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4937c969009..bc129f24e11 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -711,18 +711,21 @@ release_thread(struct task_struct *t) } /* - * This gets called before we allocate a new thread and copy - * the current task into it. + * this gets called so that we can store coprocessor state into memory and + * copy the current task into the new thread. */ -void prepare_to_copy(struct task_struct *tsk) +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_vsx_to_thread(current); - flush_spe_to_thread(current); + flush_fp_to_thread(src); + flush_altivec_to_thread(src); + flush_vsx_to_thread(src); + flush_spe_to_thread(src); #ifdef CONFIG_HAVE_HW_BREAKPOINT - flush_ptrace_hw_breakpoint(tsk); + flush_ptrace_hw_breakpoint(src); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ + + *dst = *src; + return 0; } /* diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index d499b30ea48..6cbf3131167 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -141,9 +141,6 @@ struct seq_file; extern void release_thread(struct task_struct *); extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - /* * Return saved PC of a blocked thread. */ diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h index 7e22f216d77..ab3aceb5420 100644 --- a/arch/score/include/asm/processor.h +++ b/arch/score/include/asm/processor.h @@ -26,7 +26,6 @@ extern unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() #define release_thread(thread) do {} while (0) -#define prepare_to_copy(tsk) do {} while (0) /* * User space process size: 2GB. This is hardcoded into a few places, diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 900f8d72ffe..b6311fd2d06 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -126,9 +126,6 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_pc, unsigned lo /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -void prepare_to_copy(struct task_struct *tsk); - /* * create a kernel thread without removing it from tasklists */ diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index e25c4c7d6b6..fe99afecfbc 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -172,7 +172,6 @@ extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); #define copy_segments(p, mm) do { } while (0) #define release_segments(mm) do { } while (0) #define forget_segments() do { } while (0) -#define prepare_to_copy(tsk) do { } while (0) /* * FPU lazy state save handling. */ diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c index 325f98b1736..2bde59eae10 100644 --- a/arch/sh/kernel/process.c +++ b/arch/sh/kernel/process.c @@ -6,8 +6,15 @@ struct kmem_cache *task_xstate_cachep = NULL; unsigned int xstate_size; +/* + * this gets called so that we can store lazy state into memory and copy the + * current task into the new thread. + */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { +#ifdef CONFIG_SUPERH32 + unlazy_fpu(src, task_pt_regs(src)); +#endif *dst = *src; if (src->thread.xstate) { diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 94273aaf78c..dee596113cc 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -155,15 +155,6 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) } EXPORT_SYMBOL(dump_fpu); -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - unlazy_fpu(tsk, task_pt_regs(tsk)); -} - asmlinkage void ret_from_fork(void); int copy_thread(unsigned long clone_flags, unsigned long usp, diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index 09521c6a5ed..c9c760fdc71 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -109,9 +109,6 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc, #define release_thread(tsk) do { } while(0) extern pid_t kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern unsigned long get_wchan(struct task_struct *); #define task_pt_regs(tsk) ((tsk)->thread.kregs) diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index e713db24993..67df5cc1001 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -186,9 +186,6 @@ do { \ /* Free all resources held by a thread. */ #define release_thread(tsk) do { } while (0) -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - extern pid_t kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); extern unsigned long get_wchan(struct task_struct *task); diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h index 34c1e01ffb5..15cd8a4a06c 100644 --- a/arch/tile/include/asm/processor.h +++ b/arch/tile/include/asm/processor.h @@ -210,9 +210,6 @@ static inline void release_thread(struct task_struct *dead_task) /* Nothing for now */ } -/* Prepare to copy thread state - unlazy all lazy status. */ -#define prepare_to_copy(tsk) do { } while (0) - extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern int do_work_pending(struct pt_regs *regs, u32 flags); diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 98d01bc4fa9..63b716052d2 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -76,11 +76,6 @@ static inline void release_thread(struct task_struct *task) extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); -static inline void prepare_to_copy(struct task_struct *tsk) -{ -} - - extern unsigned long thread_saved_pc(struct task_struct *t); static inline void mm_copy_segments(struct mm_struct *from_mm, diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h index f0d780a51f9..14382cb0965 100644 --- a/arch/unicore32/include/asm/processor.h +++ b/arch/unicore32/include/asm/processor.h @@ -68,9 +68,6 @@ struct task_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy status */ -#define prepare_to_copy(tsk) do { } while (0) - unsigned long get_wchan(struct task_struct *p); #define cpu_relax() barrier() diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4fa7dcceb6c..97fe04318e9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -579,9 +579,6 @@ extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy state */ -extern void prepare_to_copy(struct task_struct *tsk); - unsigned long get_wchan(struct task_struct *p); /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1d92a5ab6e8..b7e1e0e5398 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -47,10 +47,16 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); struct kmem_cache *task_xstate_cachep; EXPORT_SYMBOL_GPL(task_xstate_cachep); +/* + * this gets called so that we can store lazy state into memory and copy the + * current task into the new thread. + */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { int ret; + unlazy_fpu(src); + *dst = *src; if (fpu_allocated(&src->thread.fpu)) { memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ae6847303e2..2aa57dc909d 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -126,15 +126,6 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - unlazy_fpu(tsk); -} - int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 43d8b48b23e..c4c0645a401 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -145,15 +145,6 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) return get_desc_base(&t->thread.tls_array[tls]); } -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - unlazy_fpu(tsk); -} - int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 3acb26e8dea..5c371d8d452 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -168,9 +168,6 @@ struct mm_struct; /* Free all resources held by a thread. */ #define release_thread(thread) do { } while(0) -/* Prepare to copy thread state - unlazy all lazy status */ -extern void prepare_to_copy(struct task_struct*); - /* Create a kernel thread without removing it from tasklists */ extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 6a2d6edf8f7..9b306e550e3 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -140,13 +140,16 @@ void flush_thread(void) } /* - * This is called before the thread is copied. + * this gets called so that we can store coprocessor state into memory and + * copy the current task into the new thread. */ -void prepare_to_copy(struct task_struct *tsk) +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { #if XTENSA_HAVE_COPROCESSORS - coprocessor_flush_all(task_thread_info(tsk)); + coprocessor_flush_all(task_thread_info(src)); #endif + *dst = *src; + return 0; } /* -- cgit v1.2.3 From d75f1b391f5ef73016d14bc6f7e4725820ebaa5b Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 16 May 2012 15:03:53 -0700 Subject: x86, xsave: remove thread_has_fpu() bug check in __sanitize_i387_state() Code paths like fork(), exit() and signal handling flush the fpu state explicitly to the structures in memory. BUG_ON() in __sanitize_i387_state() is checking that the fpu state is not live any more. But for preempt kernels, task can be scheduled out and in at any place and the preload_fpu logic during context switch can make the fpu registers live again. For example, consider a 64-bit Task which uses fpu frequently and as such you will find its fpu_counter mostly non-zero. During its time slice, kernel used fpu by doing kernel_fpu_begin/kernel_fpu_end(). After this, in the same scheduling slice, task-A got a signal to handle. Then during the signal setup path we got preempted when we are just before the sanitize_i387_state() in arch/x86/kernel/xsave.c:save_i387_xstate(). And when we come back we will have the fpu registers live that can hit the bug_on. Similarly during core dump, other threads can context-switch in and out (because of spurious wakeups while waiting for the coredump to finish in kernel/exit.c:exit_mm()) and the main thread dumping core can run into this bug when it finds some other thread with its fpu registers live on some other cpu. So remove the paranoid check for now, even though it caught a bug in the multi-threaded core dump case (fixed in the previous patch). Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1336692811-30576-3-git-send-email-suresh.b.siddha@intel.com Cc: Oleg Nesterov Cc: Linus Torvalds Signed-off-by: H. Peter Anvin --- arch/x86/kernel/xsave.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index e62728e30b0..bd18149b2b0 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -48,8 +48,6 @@ void __sanitize_i387_state(struct task_struct *tsk) if (!fx) return; - BUG_ON(__thread_has_fpu(tsk)); - xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; /* -- cgit v1.2.3 From 1dcc8d7ba235a316a056f993e88f0d18b92c60d9 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Wed, 16 May 2012 15:03:54 -0700 Subject: x86, fpu: drop the fpu state during thread exit There is no need to save any active fpu state to the task structure memory if the task is dead. Just drop the state instead. For example, this saved some 1770 xsave's during the system boot of a two socket Xeon system. Suggested-by: Linus Torvalds Signed-off-by: Suresh Siddha Link: http://lkml.kernel.org/r/1336692811-30576-4-git-send-email-suresh.b.siddha@intel.com Cc: Oleg Nesterov Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b7e1e0e5398..1219fe2be8f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -87,6 +87,16 @@ void arch_task_cache_init(void) SLAB_PANIC | SLAB_NOTRACK, NULL); } +static inline void drop_fpu(struct task_struct *tsk) +{ + /* + * Forget coprocessor state.. + */ + tsk->fpu_counter = 0; + clear_fpu(tsk); + clear_used_math(); +} + /* * Free current thread data structures etc.. */ @@ -109,6 +119,8 @@ void exit_thread(void) put_cpu(); kfree(bp); } + + drop_fpu(me); } void show_regs(struct pt_regs *regs) @@ -149,12 +161,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); + drop_fpu(tsk); } static void hard_disable_TSC(void) -- cgit v1.2.3