i387: move TS_USEDFPU flag from thread_info to task_struct

This moves the bit that indicates whether a thread has ownership of the
FPU from the TS_USEDFPU bit in thread_info->status to a word of its own
(called 'has_fpu') in task_struct->thread.has_fpu.

This fixes two independent bugs at the same time:

 - changing 'thread_info->status' from the scheduler causes nasty
   problems for the other users of that variable, since it is defined to
   be thread-synchronous (that's what the "TS_" part of the naming was
   supposed to indicate).

   So perfectly valid code could (and did) do

	ti->status |= TS_RESTORE_SIGMASK;

   and the compiler was free to do that as separate load, or and store
   instructions.  Which can cause problems with preemption, since a task
   switch could happen in between, and change the TS_USEDFPU bit. The
   change to TS_USEDFPU would be overwritten by the final store.

   In practice, this seldom happened, though, because the 'status' field
   was seldom used more than once, so gcc would generally tend to
   generate code that used a read-modify-write instruction and thus
   happened to avoid this problem - RMW instructions are naturally low
   fat and preemption-safe.

 - On x86-32, the current_thread_info() pointer would, during interrupts
   and softirqs, point to a *copy* of the real thread_info, because
   x86-32 uses %esp to calculate the thread_info address, and thus the
   separate irq (and softirq) stacks would cause these kinds of odd
   thread_info copy aliases.

   This is normally not a problem, since interrupts aren't supposed to
   look at thread information anyway (what thread is running at
   interrupt time really isn't very well-defined), but it confused the
   heck out of irq_fpu_usable() and the code that tried to squirrel
   away the FPU state.

   (It also caused untold confusion for us poor kernel developers).

It also turns out that using 'task_struct' is actually much more natural
for most of the call sites that care about the FPU state, since they
tend to work with the task struct for other reasons anyway (ie
scheduling).  And the FPU data that we are going to save/restore is
found there too.

Thanks to Arjan Van De Ven <arjan@linux.intel.com> for pointing us to
the %esp issue.

Cc: Arjan van de Ven <arjan@linux.intel.com>
Reported-and-tested-by: Raphael Prevost <raphael@buro.asia>
Acked-and-tested-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Peter Anvin <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/i387.h

@@ -264,21 +264,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
  * be preemption protection *and* they need to be
  * properly paired with the CR0.TS changes!
  */
-static inline int __thread_has_fpu(struct thread_info *ti)
+static inline int __thread_has_fpu(struct task_struct *tsk)
 {
-	return ti->status & TS_USEDFPU;
+	return tsk->thread.has_fpu;
 }
 
 /* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct thread_info *ti)
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
-	ti->status &= ~TS_USEDFPU;
+	tsk->thread.has_fpu = 0;
 }
 
 /* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct thread_info *ti)
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
 {
-	ti->status |= TS_USEDFPU;
+	tsk->thread.has_fpu = 1;
 }
 
 /*
@@ -288,16 +288,16 @@ static inline void __thread_set_has_fpu(struct thread_info *ti)
  * These generally need preemption protection to work,
  * do try to avoid using these on their own.
  */
-static inline void __thread_fpu_end(struct thread_info *ti)
+static inline void __thread_fpu_end(struct task_struct *tsk)
 {
-	__thread_clear_has_fpu(ti);
+	__thread_clear_has_fpu(tsk);
 	stts();
 }
 
-static inline void __thread_fpu_begin(struct thread_info *ti)
+static inline void __thread_fpu_begin(struct task_struct *tsk)
 {
 	clts();
-	__thread_set_has_fpu(ti);
+	__thread_set_has_fpu(tsk);
 }
 
 /*
@@ -308,21 +308,21 @@ extern int restore_i387_xstate(void __user *buf);
 
 static inline void __unlazy_fpu(struct task_struct *tsk)
 {
-	if (__thread_has_fpu(task_thread_info(tsk))) {
+	if (__thread_has_fpu(tsk)) {
 		__save_init_fpu(tsk);
-		__thread_fpu_end(task_thread_info(tsk));
+		__thread_fpu_end(tsk);
 	} else
 		tsk->fpu_counter = 0;
 }
 
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-	if (__thread_has_fpu(task_thread_info(tsk))) {
+	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
 			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(task_thread_info(tsk));
+		__thread_fpu_end(tsk);
 	}
 }
 
@@ -337,7 +337,7 @@ static inline void __clear_fpu(struct task_struct *tsk)
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
-	return !__thread_has_fpu(current_thread_info()) &&
+	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
 }
 
@@ -371,12 +371,12 @@ static inline bool irq_fpu_usable(void)
 
 static inline void kernel_fpu_begin(void)
 {
-	struct thread_info *me = current_thread_info();
+	struct task_struct *me = current;
 
 	WARN_ON_ONCE(!irq_fpu_usable());
 	preempt_disable();
 	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me->task);
+		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
 		/* We do 'stts()' in kernel_fpu_end() */
 	} else
@@ -441,13 +441,13 @@ static inline void irq_ts_restore(int TS_state)
  */
 static inline int user_has_fpu(void)
 {
-	return __thread_has_fpu(current_thread_info());
+	return __thread_has_fpu(current);
 }
 
 static inline void user_fpu_end(void)
 {
 	preempt_disable();
-	__thread_fpu_end(current_thread_info());
+	__thread_fpu_end(current);
 	preempt_enable();
 }
 
@@ -455,7 +455,7 @@ static inline void user_fpu_begin(void)
 {
 	preempt_disable();
 	if (!user_has_fpu())
-		__thread_fpu_begin(current_thread_info());
+		__thread_fpu_begin(current);
 	preempt_enable();
 }
 
@@ -464,10 +464,10 @@ static inline void user_fpu_begin(void)
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
-	WARN_ON_ONCE(!__thread_has_fpu(task_thread_info(tsk)));
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
 	preempt_disable();
 	__save_init_fpu(tsk);
-	__thread_fpu_end(task_thread_info(tsk));
+	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 

arch/x86/include/asm/processor.h

@@ -454,6 +454,7 @@ struct thread_struct {
 	unsigned long		trap_no;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
+	unsigned long		has_fpu;
 	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */

arch/x86/include/asm/thread_info.h

@@ -247,8 +247,6 @@ static inline struct thread_info *current_thread_info(void)
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #define TS_POLLING		0x0004	/* idle task polling need_resched,
 					   skip sending interrupt */

arch/x86/kernel/traps.c

@@ -582,12 +582,11 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
  */
 void math_state_restore(void)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 
 	/* We need a safe address that is cheap to find and that is already
-	   in L1. We just brought in "thread->task", so use that */
-#define safe_address (thread->task)
+	   in L1. We're just bringing in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
 
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
@@ -604,7 +603,7 @@ void math_state_restore(void)
 		local_irq_disable();
 	}
 
-	__thread_fpu_begin(thread);
+	__thread_fpu_begin(tsk);
 
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
@@ -620,7 +619,7 @@ void math_state_restore(void)
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
-		__thread_fpu_end(thread);
+		__thread_fpu_end(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}

arch/x86/kernel/xsave.c

@@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
 	if (!fx)
 		return;
 
-	BUG_ON(__thread_has_fpu(task_thread_info(tsk)));
+	BUG_ON(__thread_has_fpu(tsk));
 
 	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 

arch/x86/kvm/vmx.c

@@ -1457,7 +1457,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (__thread_has_fpu(current_thread_info()))
+	if (__thread_has_fpu(current))
 		clts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }