x86/entry/32: Fix entry_INT80_32() to expect interrupts to be on

amluto · Ingo Molnar · commit 657c1eea0019 · 2015-10-18T12:11:16.000+02:00
When I rewrote entry_INT80_32, I thought that int80 was an interrupt gate. It's a trap gate. *facepalm* Thanks to Brian Gerst for pointing out that it's better to change the entry code than to change the gate type. Suggested-by: Brian Gerst <brgerst@gmail.com> Reported-and-tested-by: Borislav Petkov <bp@suse.de> Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 150ac78 ("x86/entry/32: Switch INT80 to the new C syscall path") Link: http://lkml.kernel.org/r/dc09d9b574a5c1dcca996847875c73f8341ce0ad.1445035014.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
@@ -351,7 +351,14 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
  * in workloads that use it, and it's usually called from
  * do_fast_syscall_32, so forcibly inline it to improve performance.
  */
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+#ifdef CONFIG_X86_32
+/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */
+__visible
+#else
+/* 64-bit kernels use do_syscall_32_irqs_off() instead. */
+static
+#endif
+__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 {
 	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	unsigned int nr = (unsigned int)regs->orig_ax;
@@ -386,12 +393,14 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 	syscall_return_slowpath(regs);
 }
 
-/* Handles int $0x80 */
-__visible void do_int80_syscall_32(struct pt_regs *regs)
+#ifdef CONFIG_X86_64
+/* Handles INT80 on 64-bit kernels */
+__visible void do_syscall_32_irqs_off(struct pt_regs *regs)
 {
 	local_irq_enable();
 	do_syscall_32_irqs_on(regs);
 }
+#endif
 
 /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
 __visible long do_fast_syscall_32(struct pt_regs *regs)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
@@ -345,13 +345,13 @@ ENTRY(entry_INT80_32)
 	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
 
 	/*
-	 * User mode is traced as though IRQs are on, and the interrupt gate
-	 * turned them off.
+	 * User mode is traced as though IRQs are on.  Unlike the 64-bit
+	 * case, INT80 is a trap gate on 32-bit kernels, so interrupts
+	 * are already on (unless user code is messing around with iopl).
 	 */
-	TRACE_IRQS_OFF
 
 	movl	%esp, %eax
-	call	do_int80_syscall_32
+	call	do_syscall_32_irqs_on
 .Lsyscall_32_done:
 
 restore_all:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
@@ -303,7 +303,7 @@ ENTRY(entry_INT80_compat)
 	TRACE_IRQS_OFF
 
 	movq	%rsp, %rdi
-	call	do_int80_syscall_32
+	call	do_syscall_32_irqs_off
 .Lsyscall_32_done:
 
 	/* Go back to user mode. */
