static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
+ /*
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+ static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+ {
+ per_cpu(fpu_owner_task, cpu) = NULL;
+ }
+
+ /*
+ * Used to indicate that the FPU state in memory is newer than the FPU
+ * state in registers, and the FPU state should be reloaded next time the
+ * task is run. Only safe on the current task, or non-running tasks.
+ */
+ static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
+ {
+ tsk->thread.fpu.last_cpu = ~0;
+ }
+
+ static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+ {
+ return new == this_cpu_read_stable(fpu_owner_task) &&
+ cpu == new->thread.fpu.last_cpu;
+ }
+
static inline int is_ia32_compat_frame(void)
{
return config_enabled(CONFIG_IA32_EMULATION) &&
if (config_enabled(CONFIG_X86_32))
asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
- asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave));
else {
/* Using "rex64; fxsave %0" is broken because, if the memory
* operand uses any extended registers for addressing, a second
static inline int restore_fpu_checking(struct task_struct *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
- values. "m" is a random variable that should be in L1 */
+ /*
+ * 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 values.
+ * "m" is a random variable that should be in L1.
+ */
if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
asm volatile(
"fnclex\n\t"
*/
typedef struct { int preload; } fpu_switch_t;
- /*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
- static inline void __cpu_disable_lazy_restore(unsigned int cpu)
- {
- per_cpu(fpu_owner_task, cpu) = NULL;
- }
-
- static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
- {
- return new == this_cpu_read_stable(fpu_owner_task) &&
- cpu == new->thread.fpu.last_cpu;
- }
-
static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
{
fpu_switch_t fpu;
* If the task has used the math, pre-load the FPU on xsave processors
* or if the past 5 consecutive context-switches used math.
*/
- fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
- new->thread.fpu_counter > 5);
+ fpu.preload = tsk_used_math(new) &&
+ (use_eager_fpu() || new->thread.fpu_counter > 5);
+
if (__thread_has_fpu(old)) {
if (!__save_init_fpu(old))
- cpu = ~0;
- old->thread.fpu.last_cpu = cpu;
- old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */
+ task_disable_lazy_fpu_restore(old);
+ else
+ old->thread.fpu.last_cpu = cpu;
+
+ /* But leave fpu_owner_task! */
+ old->thread.fpu.has_fpu = 0;
/* Don't change CR0.TS if we just switch! */
if (fpu.preload) {
stts();
} else {
old->thread.fpu_counter = 0;
- old->thread.fpu.last_cpu = ~0;
+ task_disable_lazy_fpu_restore(old);
if (fpu.preload) {
new->thread.fpu_counter++;
- if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
+ if (fpu_lazy_restore(new, cpu))
fpu.preload = 0;
else
prefetch(new->thread.fpu.state);
fpu_fxsave(&tsk->thread.fpu);
}
- /*
- * These disable preemption on their own and are safe
- */
- static inline void save_init_fpu(struct task_struct *tsk)
- {
- WARN_ON_ONCE(!__thread_has_fpu(tsk));
-
- if (use_eager_fpu()) {
- __save_fpu(tsk);
- return;
- }
-
- preempt_disable();
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- preempt_enable();
- }
-
/*
* i387 state interaction
*/
#include <asm/fpu-internal.h>
#include <asm/user.h>
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+void kernel_fpu_disable(void)
+{
+ WARN_ON(this_cpu_read(in_kernel_fpu));
+ this_cpu_write(in_kernel_fpu, true);
+}
+
+void kernel_fpu_enable(void)
+{
+ this_cpu_write(in_kernel_fpu, false);
+}
+
/*
* Were we in an interrupt that interrupted kernel mode?
*
*/
static inline bool interrupted_kernel_fpu_idle(void)
{
+ if (this_cpu_read(in_kernel_fpu))
+ return false;
+
if (use_eager_fpu())
return __thread_has_fpu(current);
{
struct task_struct *me = current;
+ this_cpu_write(in_kernel_fpu, true);
+
if (__thread_has_fpu(me)) {
- __thread_clear_has_fpu(me);
__save_init_fpu(me);
- /* We do 'stts()' in __kernel_fpu_end() */
} else if (!use_eager_fpu()) {
this_cpu_write(fpu_owner_task, NULL);
clts();
void __kernel_fpu_end(void)
{
- if (use_eager_fpu()) {
- /*
- * For eager fpu, most the time, tsk_used_math() is true.
- * Restore the user math as we are done with the kernel usage.
- * At few instances during thread exit, signal handling etc,
- * tsk_used_math() is false. Those few places will take proper
- * actions, so we don't need to restore the math here.
- */
- if (likely(tsk_used_math(current)))
- math_state_restore();
- } else {
+ struct task_struct *me = current;
+
+ if (__thread_has_fpu(me)) {
+ if (WARN_ON(restore_fpu_checking(me)))
+ drop_init_fpu(me);
+ } else if (!use_eager_fpu()) {
stts();
}
+
+ this_cpu_write(in_kernel_fpu, false);
}
EXPORT_SYMBOL(__kernel_fpu_end);
{
preempt_disable();
if (__thread_has_fpu(tsk)) {
- __save_init_fpu(tsk);
- __thread_fpu_end(tsk);
- } else
- tsk->thread.fpu_counter = 0;
+ if (use_eager_fpu()) {
+ __save_fpu(tsk);
+ } else {
+ __save_init_fpu(tsk);
+ __thread_fpu_end(tsk);
+ }
+ }
preempt_enable();
}
EXPORT_SYMBOL(unlazy_fpu);
if (tsk_used_math(tsk)) {
if (cpu_has_fpu && tsk == current)
unlazy_fpu(tsk);
- tsk->thread.fpu.last_cpu = ~0;
+ task_disable_lazy_fpu_restore(tsk);
return 0;
}
preempt_count_dec();
}
+enum ctx_state ist_enter(struct pt_regs *regs)
+{
+ enum ctx_state prev_state;
+
+ if (user_mode_vm(regs)) {
+ /* Other than that, we're just an exception. */
+ prev_state = exception_enter();
+ } else {
+ /*
+ * We might have interrupted pretty much anything. In
+ * fact, if we're a machine check, we can even interrupt
+ * NMI processing. We don't want in_nmi() to return true,
+ * but we need to notify RCU.
+ */
+ rcu_nmi_enter();
+ prev_state = IN_KERNEL; /* the value is irrelevant. */
+ }
+
+ /*
+ * We are atomic because we're on the IST stack (or we're on x86_32,
+ * in which case we still shouldn't schedule).
+ *
+ * This must be after exception_enter(), because exception_enter()
+ * won't do anything if in_interrupt() returns true.
+ */
+ preempt_count_add(HARDIRQ_OFFSET);
+
+ /* This code is a bit fragile. Test it. */
+ rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work");
+
+ return prev_state;
+}
+
+void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
+{
+ /* Must be before exception_exit. */
+ preempt_count_sub(HARDIRQ_OFFSET);
+
+ if (user_mode_vm(regs))
+ return exception_exit(prev_state);
+ else
+ rcu_nmi_exit();
+}
+
+/**
+ * ist_begin_non_atomic() - begin a non-atomic section in an IST exception
+ * @regs: regs passed to the IST exception handler
+ *
+ * IST exception handlers normally cannot schedule. As a special
+ * exception, if the exception interrupted userspace code (i.e.
+ * user_mode_vm(regs) would return true) and the exception was not
+ * a double fault, it can be safe to schedule. ist_begin_non_atomic()
+ * begins a non-atomic section within an ist_enter()/ist_exit() region.
+ * Callers are responsible for enabling interrupts themselves inside
+ * the non-atomic section, and callers must call is_end_non_atomic()
+ * before ist_exit().
+ */
+void ist_begin_non_atomic(struct pt_regs *regs)
+{
+ BUG_ON(!user_mode_vm(regs));
+
+ /*
+ * Sanity check: we need to be on the normal thread stack. This
+ * will catch asm bugs and any attempt to use ist_preempt_enable
+ * from double_fault.
+ */
+ BUG_ON(((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack))
+ & ~(THREAD_SIZE - 1)) != 0);
+
+ preempt_count_sub(HARDIRQ_OFFSET);
+}
+
+/**
+ * ist_end_non_atomic() - begin a non-atomic section in an IST exception
+ *
+ * Ends a non-atomic section started with ist_begin_non_atomic().
+ */
+void ist_end_non_atomic(void)
+{
+ preempt_count_add(HARDIRQ_OFFSET);
+}
+
static nokprobe_inline int
do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
struct pt_regs *regs, long error_code)
* end up promoting it to a doublefault. In that case, modify
* the stack to make it look like we just entered the #GP
* handler from user space, similar to bad_iret.
+ *
+ * No need for ist_enter here because we don't use RCU.
*/
if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
regs->ip = (unsigned long)general_protection;
regs->sp = (unsigned long)&normal_regs->orig_ax;
+
return;
}
#endif
- exception_enter();
- /* Return not checked because double check cannot be ignored */
+ ist_enter(regs); /* Discard prev_state because we won't return. */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
tsk->thread.error_code = error_code;
if (poke_int3_handler(regs))
return;
- prev_state = exception_enter();
+ prev_state = ist_enter(regs);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
preempt_conditional_cli(regs);
debug_stack_usage_dec();
exit:
- exception_exit(prev_state);
+ ist_exit(regs, prev_state);
}
NOKPROBE_SYMBOL(do_int3);
#ifdef CONFIG_X86_64
/*
- * Help handler running on IST stack to switch back to user stack
- * for scheduling or signal handling. The actual stack switch is done in
- * entry.S
+ * Help handler running on IST stack to switch off the IST stack if the
+ * interrupted code was in user mode. The actual stack switch is done in
+ * entry_64.S
*/
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
- struct pt_regs *regs = eregs;
- /* Did already sync */
- if (eregs == (struct pt_regs *)eregs->sp)
- ;
- /* Exception from user space */
- else if (user_mode(eregs))
- regs = task_pt_regs(current);
- /*
- * Exception from kernel and interrupts are enabled. Move to
- * kernel process stack.
- */
- else if (eregs->flags & X86_EFLAGS_IF)
- regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs));
- if (eregs != regs)
- *regs = *eregs;
+ struct pt_regs *regs = task_pt_regs(current);
+ *regs = *eregs;
return regs;
}
NOKPROBE_SYMBOL(sync_regs);
unsigned long dr6;
int si_code;
- prev_state = exception_enter();
+ prev_state = ist_enter(regs);
get_debugreg(dr6, 6);
debug_stack_usage_dec();
exit:
- exception_exit(prev_state);
+ ist_exit(regs, prev_state);
}
NOKPROBE_SYMBOL(do_debug);
/*
* Save the info for the exception handler and clear the error.
*/
- save_init_fpu(task);
+ unlazy_fpu(task);
task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
info.si_signo = SIGFPE;
local_irq_disable();
}
+ /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
+ kernel_fpu_disable();
__thread_fpu_begin(tsk);
-
- /*
- * Paranoid restore. send a SIGSEGV if we fail to restore the state.
- */
if (unlikely(restore_fpu_checking(tsk))) {
drop_init_fpu(tsk);
force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
- return;
+ } else {
+ tsk->thread.fpu_counter++;
}
-
- tsk->thread.fpu_counter++;
+ kernel_fpu_enable();
}
EXPORT_SYMBOL_GPL(math_state_restore);