x86: Add support for restartable sequences

Call the rseq_handle_notify_resume() function on return to userspace if
TIF_NOTIFY_RESUME thread flag is set.

Perform fixup on the pre-signal frame when a signal is delivered on top
of a restartable sequence critical section.

Check that system calls are not invoked from within rseq critical
sections by invoking rseq_signal() from syscall_return_slowpath().
With CONFIG_DEBUG_RSEQ, such behavior results in termination of the
process with SIGSEGV.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180602124408.8430-7-mathieu.desnoyers@efficios.com

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1fe24b624d44c9cc1611c18fea8ab87ed070d147..c320ce005b0255b4646cd3c8f690c93ade7b133d 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -182,6 +182,7 @@ config X86
        select HAVE_REGS_AND_STACK_ACCESS_API
        select HAVE_RELIABLE_STACKTRACE         if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
        select HAVE_STACK_VALIDATION            if X86_64
+       select HAVE_RSEQ
        select HAVE_SYSCALL_TRACEPOINTS
        select HAVE_UNSTABLE_SCHED_CLOCK
        select HAVE_USER_RETURN_NOTIFIER

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index fbf6a6c3fd2d5e94d44b0bd32b48bf4fa2bead6a..92190879b228c82f4ec681aa9c07bccc0e32204a 100644 (file)
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -164,6 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
                if (cached_flags & _TIF_NOTIFY_RESUME) {
                        clear_thread_flag(TIF_NOTIFY_RESUME);
                        tracehook_notify_resume(regs);
+                       rseq_handle_notify_resume(regs);
                }
 
                if (cached_flags & _TIF_USER_RETURN_NOTIFY)
@@ -254,6 +255,8 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
            WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
                local_irq_enable();
 
+       rseq_syscall(regs);
+
        /*
         * First do one-time work.  If these work items are enabled, we
         * want to run them exactly once per syscall exit with IRQs on.

diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index da270b95fe4d27f15a46b5be6b8018d5cba1c334..445ca11ff8634eb27fb93f93fe362fc4bffaf588 100644 (file)
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -688,6 +688,12 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
        sigset_t *set = sigmask_to_save();
        compat_sigset_t *cset = (compat_sigset_t *) set;
 
+       /*
+        * Increment event counter and perform fixup for the pre-signal
+        * frame.
+        */
+       rseq_signal_deliver(regs);
+
        /* Set up the stack frame */
        if (is_ia32_frame(ksig)) {
                if (ksig->ka.sa.sa_flags & SA_SIGINFO)