x86/entry/64: Don't use IST entry for #BP 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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d5c7f18f79aceabf2f7c43769255cd38b3142bc3..9b114675fbc05e1f589e6838f4603de871c0565d 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1138,7 +1138,7 @@ apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
 #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
 idtentry stack_segment         do_stack_segment        has_error_code=1
 
 #ifdef CONFIG_XEN

diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 56d99be3706a23b600a50d2ae366b3a8fde251ed..50bee5fe114013622ee858e4a3b7b16d1ffa8a05 100644 (file)
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -160,7 +160,6 @@ static const __initconst struct idt_data early_pf_idts[] = {
  */
 static const __initconst struct idt_data dbg_idts[] = {
        INTG(X86_TRAP_DB,       debug),
-       INTG(X86_TRAP_BP,       int3),
 };
 #endif
 
@@ -183,7 +182,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
 static const __initconst struct idt_data ist_idts[] = {
        ISTG(X86_TRAP_DB,       debug,          DEBUG_STACK),
        ISTG(X86_TRAP_NMI,      nmi,            NMI_STACK),
-       SISTG(X86_TRAP_BP,      int3,           DEBUG_STACK),
        ISTG(X86_TRAP_DF,       double_fault,   DOUBLEFAULT_STACK),
 #ifdef CONFIG_X86_MCE
        ISTG(X86_TRAP_MC,       &machine_check, MCE_STACK),

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 3d9b2308e7fad0be6f90cbf834d2e00d1f4fc417..03f3d7695daccae1af7265f2aab221da81573ce5 100644 (file)
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code)
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
-/* May run on IST stack. */
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
        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);
        RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
                        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();
        cond_local_irq_enable(regs);
        do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
        cond_local_irq_disable(regs);
-       debug_stack_usage_dec();
+
 exit:
        ist_exit(regs);
 }