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 <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202211339590.5354@i5.linux-foundation.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

2 files changed, 80 insertions, 2 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c0f7d68d318f..cb71b01ab66e 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 739d8598f789..17b7549c4134 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