x86/asm/entry: Fix execve() and sigreturn() syscalls to always return via IRET

Both the execve() and sigreturn() family of syscalls have the
ability to change registers in ways that may not be compatabile
with the syscall path they were called from.

In particular, SYSRET and SYSEXIT can't handle non-default %cs and %ss,
and some bits in eflags.

These syscalls have stubs that are hardcoded to jump to the IRET path,
and not return to the original syscall path.

The following commit:

   76f5df43cab5e76 ("Always allocate a complete "struct pt_regs" on the kernel stack")

recently changed this for some 32-bit compat syscalls, but introduced a bug where
execve from a 32-bit program to a 64-bit program would fail because it still returned
via SYSRETL. This caused Wine to fail when built for both 32-bit and 64-bit.

This patch sets TIF_NOTIFY_RESUME for execve() and sigreturn() so
that the IRET path is always taken on exit to userspace.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
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>
Link: http://lkml.kernel.org/r/1426978461-32089-1-git-send-email-brgerst@gmail.com
[ Improved the changelog and comments. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 17 insertions, 6 deletions

diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index d0165c9a2932..1f5e2b0e09ff 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -203,6 +203,8 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 
 	err |= restore_xstate_sig(buf, 1);
 
+	force_iret();
+
 	return err;
 }
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 74bb2e0f3030..83b874da2762 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -251,7 +251,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
  */
 #define arch_ptrace_stop_needed(code, info)				\
 ({									\
-	set_thread_flag(TIF_NOTIFY_RESUME);				\
+	force_iret();							\
 	false;								\
 })
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ba115eb6fbcf..0abf7ab20ce2 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -260,6 +260,16 @@ static inline bool is_ia32_task(void)
 #endif
 	return false;
 }
+
+/*
+ * Force syscall return via IRET by making it look as if there was
+ * some work pending. IRET is our most capable (but slowest) syscall
+ * return path, which is able to restore modified SS, CS and certain
+ * EFLAGS values that other (fast) syscall return instructions
+ * are not able to restore properly.
+ */
+#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME)
+
 #endif	/* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 1b9963faf4eb..26c596d1ee07 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -206,11 +206,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->flags		= X86_EFLAGS_IF;
-	/*
-	 * force it to the iret return path by making it look as if there was
-	 * some work pending.
-	 */
-	set_thread_flag(TIF_NOTIFY_RESUME);
+	force_iret();
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 97f5658290b7..da8b74598d90 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -239,6 +239,7 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
+	force_iret();
 }
 
 void
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index edcb862cdcae..eaa2c5e3f2cd 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -108,6 +108,8 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 
 	err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
 
+	force_iret();
+
 	return err;
 }