Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/fpu changes from Ingo Molnar.

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  i387: Split up <asm/i387.h> into exported and internal interfaces
  i387: Uninline the generic FP helpers that we expose to kernel modules

9 files changed, 90 insertions, 3 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b3e0081f9a2..ade9c794ed9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -28,6 +28,7 @@
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
@@ -1045,7 +1046,6 @@ 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 +1115,6 @@ 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 739d8598f78..7734bcbb5a3 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -16,6 +16,7 @@
 #include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/user.h>
 
 #ifdef CONFIG_X86_64
@@ -32,6 +33,86 @@
 # 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
@@ -44,7 +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 44eefde9210..14baf78d5a1 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -21,6 +21,7 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
 
 struct kmem_cache *task_xstate_cachep;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 49888fefe79..9d7d4842bfa 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -45,6 +45,7 @@
 #include <asm/ldt.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/desc.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 442e7bfe10a..292da13fc5a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -43,6 +43,7 @@
 #include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/mmu_context.h>
 #include <asm/prctl.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 50267386b76..78f05e438be 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -27,6 +27,7 @@
 #include <asm/system.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/debugreg.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 46a01bdc27e..25edcfc9ba5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -24,6 +24,7 @@
 #include <asm/processor.h>
 #include <asm/ucontext.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 4bbe04d9674..ec61d4c1b93 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -54,6 +54,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/mce.h>
 
 #include <asm/mach_traps.h>
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 71109111411..e62728e30b0 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -6,6 +6,7 @@
 #include <linux/bootmem.h>
 #include <linux/compat.h>
 #include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #ifdef CONFIG_IA32_EMULATION
 #include <asm/sigcontext32.h>
 #endif