Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, Andy Lutomirski <luto@kernel.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH 4.4 38/43] x86/entry/64: Dont use IST entry for #BP stack
Date:   Tue, 27 Mar 2018 18:27:42 +0200
Message-Id: <20180327162718.547354643@linuxfoundation.org>
In-Reply-To: <20180327162716.407986916@linuxfoundation.org>
References: <20180327162716.407986916@linuxfoundation.org>
User-Agent: quilt/0.65
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@kernel.org>

commit d8ba61ba58c88d5207c1ba2f7d9a2280e7d03be9 upstream.

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
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/entry/entry_64.S |    2 +-
 arch/x86/kernel/traps.c   |   24 +++++++++++-------------
 2 files changed, 12 insertions(+), 14 deletions(-)

--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1018,7 +1018,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTO
 #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
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -480,7 +480,6 @@ do_general_protection(struct pt_regs *re
 }
 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
@@ -495,7 +494,15 @@ dotraplinkage void notrace do_int3(struc
 	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
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@@ -512,15 +519,9 @@ dotraplinkage void notrace do_int3(struc
 			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);
 }
@@ -886,19 +887,16 @@ void __init trap_init(void)
 	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
 }