From 8546c008924d5fd1724fa698eaa92b414bafd50d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2012 10:25:45 -0800 Subject: i387: Uninline the generic FP helpers that we expose to kernel modules Instead of exporting the very low-level internals of the FPU state save/restore code (ie things like 'fpu_owner_task'), we should export the higher-level interfaces. Inlining these things is pointless anyway: sure, sometimes the end result is small, but while 'stts()' can result in just three x86 instructions, those are not cheap instructions (writing %cr0 is a serializing instruction and a very slow one at that). So the overhead of a function call is not noticeable, and we really don't want random modules mucking about with our internal state save logic anyway. So this unexports 'fpu_owner_task', and instead uninlines and exports the actual functions that modules can use: fpu_kernel_begin/end() and unlazy_fpu(). Signed-off-by: Linus Torvalds Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202211339590.5354@i5.linux-foundation.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 2 -- arch/x86/kernel/i387.c | 80 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c0f7d68..cb71b01 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1045,7 +1045,6 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) = DEFINE_PER_CPU(unsigned int, irq_count) = -1; DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); -EXPORT_PER_CPU_SYMBOL(fpu_owner_task); /* * Special IST stacks which the CPU switches to when it calls @@ -1115,7 +1114,6 @@ void debug_stack_reset(void) DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); -EXPORT_PER_CPU_SYMBOL(fpu_owner_task); #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 739d859..17b7549 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -32,6 +32,86 @@ # define user32_fxsr_struct user_fxsr_struct #endif +/* + * Were we in an interrupt that interrupted kernel mode? + * + * We can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + */ +static inline bool interrupted_kernel_fpu_idle(void) +{ + return !__thread_has_fpu(current) && + (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static inline bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode_vm(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void kernel_fpu_begin(void) +{ + struct task_struct *me = current; + + WARN_ON_ONCE(!irq_fpu_usable()); + preempt_disable(); + if (__thread_has_fpu(me)) { + __save_init_fpu(me); + __thread_clear_has_fpu(me); + /* We do 'stts()' in kernel_fpu_end() */ + } else { + percpu_write(fpu_owner_task, NULL); + clts(); + } +} +EXPORT_SYMBOL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + stts(); + preempt_enable(); +} +EXPORT_SYMBOL(kernel_fpu_end); + +void unlazy_fpu(struct task_struct *tsk) +{ + preempt_disable(); + if (__thread_has_fpu(tsk)) { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } else + tsk->fpu_counter = 0; + preempt_enable(); +} +EXPORT_SYMBOL(unlazy_fpu); + #ifdef CONFIG_MATH_EMULATION # define HAVE_HWFP (boot_cpu_data.hard_math) #else -- cgit v1.1 From 1361b83a13d4d92e53fbb6c877528713e118b821 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2012 13:19:22 -0800 Subject: i387: Split up into exported and internal interfaces While various modules include to get access to things we actually *intend* for them to use, most of that header file was really pretty low-level internal stuff that we really don't want to expose to others. So split the header file into two: the small exported interfaces remain in , while the internal definitions that are only used by core architecture code are now in . The guiding principle for this was to expose functions that we export to modules, and leave them in , while stuff that is used by task switching or was marked GPL-only is in . The fpu-internal.h file could be further split up too, especially since arch/x86/kvm/ uses some of the remaining stuff for its module. But that kvm usage should probably be abstracted out a bit, and at least now the internal FPU accessor functions are much more contained. Even if it isn't perhaps as contained as it _could_ be. Signed-off-by: Linus Torvalds Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202211340330.5354@i5.linux-foundation.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/common.c | 1 + arch/x86/kernel/i387.c | 3 ++- arch/x86/kernel/process.c | 1 + arch/x86/kernel/process_32.c | 1 + arch/x86/kernel/process_64.c | 1 + arch/x86/kernel/ptrace.c | 1 + arch/x86/kernel/signal.c | 1 + arch/x86/kernel/traps.c | 1 + arch/x86/kernel/xsave.c | 1 + 9 files changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cb71b01..89620b1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 17b7549..7734bcb 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #ifdef CONFIG_X86_64 @@ -124,7 +125,7 @@ EXPORT_SYMBOL_GPL(xstate_size); unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32); static struct i387_fxsave_struct fx_scratch __cpuinitdata; -void __cpuinit mxcsr_feature_mask_init(void) +static void __cpuinit mxcsr_feature_mask_init(void) { unsigned long mask = 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 15763af..c38d84e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -21,6 +21,7 @@ #include #include #include +#include #include struct kmem_cache *task_xstate_cachep; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c08d1ff..ee32dee 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #ifdef CONFIG_MATH_EMULATION #include diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cfa5c90..5bad3c7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 5026738..78f05e4 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 46a01bdc..25edcfc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4bbe04d..ec61d4c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 7110911..e62728e 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -6,6 +6,7 @@ #include #include #include +#include #ifdef CONFIG_IA32_EMULATION #include #endif -- cgit v1.1