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);
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);
/* Set of traps needed for early debugging. */
void __init early_trap_init(void)
{
- set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+ /*
+ * Don't set ist to DEBUG_STACK as it doesn't work until TSS is
+ * ready in cpu_init() <-- trap_init(). Before trap_init(), CPU
+ * runs at ring 0 so it is impossible to hit an invalid stack.
+ * Using the original stack works well enough at this early
+ * stage. DEBUG_STACK will be equipped after cpu_init() in
+ * trap_init().
+ */
+ set_intr_gate_ist(X86_TRAP_DB, &debug, 0);
/* int3 can be called from all */
- set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+ set_system_intr_gate_ist(X86_TRAP_BP, &int3, 0);
#ifdef CONFIG_X86_32
set_intr_gate(X86_TRAP_PF, page_fault);
#endif
*/
cpu_init();
+ /*
+ * X86_TRAP_DB and X86_TRAP_BP have been set
+ * in early_trap_init(). However, DEBUG_STACK works only after
+ * cpu_init() loads TSS. See comments in early_trap_init().
+ */
+ set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+ /* int3 can be called from all */
+ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+
x86_init.irqs.trap_init();
#ifdef CONFIG_X86_64
git.openpandora.org / pandora-kernel.git / blobdiff