x86/entry/64: Move #BP from IST to the IRQ stack
There's nothing IST-worthy about #BP/int3. We don't allow kprobes
in the small handful of places in the kernel that run at CPL0 with
an invalid stack, and 32-bit kernels have used normal interrupt
gates for #BP forever.
Furthermore, we don't allow kprobes in places that have usergs while
in kernel mode, so "paranoid" is also unnecessary.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 5a129f5..a697e26 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1007,7 +1007,7 @@
#endif /* CONFIG_HYPERV */
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0 irqstack=1
idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8e65d8a..d823db7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -479,7 +479,7 @@
}
NOKPROBE_SYMBOL(do_general_protection);
-/* May run on IST stack. */
+/* Runs on IRQ stack. */
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -494,7 +494,15 @@
if (poke_int3_handler(regs))
return;
+ /*
+ * Use ist_enter despite the fact that we don't use an IST stack.
+ * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
+ * mode or even during context tracking state changes.
+ *
+ * This means that we can't schedule. That's okay.
+ */
ist_enter(regs);
+
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@@ -511,15 +519,10 @@
SIGTRAP) == NOTIFY_STOP)
goto exit;
- /*
- * Let others (NMI) know that the debug stack is in use
- * as we may switch to the interrupt stack.
- */
- debug_stack_usage_inc();
preempt_conditional_sti(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
- debug_stack_usage_dec();
+
exit:
ist_exit(regs);
}
@@ -885,19 +888,16 @@
cpu_init();
/*
- * X86_TRAP_DB and X86_TRAP_BP have been set
- * in early_trap_init(). However, ITS works only after
- * cpu_init() loads TSS. See comments in early_trap_init().
+ * X86_TRAP_DB was installed in early_trap_init(). However,
+ * IST 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
memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16);
set_nmi_gate(X86_TRAP_DB, &debug);
- set_nmi_gate(X86_TRAP_BP, &int3);
#endif
}