entry: Provide generic syscall entry functionality

On syscall entry certain work needs to be done:

   - Establish state (lockdep, context tracking, tracing)
   - Conditional work (ptrace, seccomp, audit...)

This code is needlessly duplicated and  different in all
architectures.

Provide a generic version based on the x86 implementation which has all the
RCU and instrumentation bits right.

As interrupt/exception entry from user space needs parts of the same
functionality, provide a function for this as well.

syscall_enter_from_user_mode() and irqentry_enter_from_user_mode() must be
called right after the low level ASM entry. The calling code must be
non-instrumentable. After the functions returns state is correct and the
subsequent functions can be instrumented.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20200722220519.513463269@linutronix.de

1 files changed, 88 insertions, 0 deletions

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
new file mode 100644
index 000000000000..1d636dee2fec
--- /dev/null
+++ b/kernel/entry/common.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_check_user_regs(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+				unsigned long ti_work)
+{
+	long ret = 0;
+
+	/* Handle ptrace */
+	if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
+		ret = arch_syscall_enter_tracehook(regs);
+		if (ret || (ti_work & _TIF_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (ti_work & _TIF_SECCOMP) {
+		ret = __secure_computing(NULL);
+		if (ret == -1L)
+			return ret;
+	}
+
+	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, syscall);
+
+	syscall_enter_audit(regs, syscall);
+
+	return ret ? : syscall;
+}
+
+noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	unsigned long ti_work;
+
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+
+	local_irq_enable();
+	ti_work = READ_ONCE(current_thread_info()->flags);
+	if (ti_work & SYSCALL_ENTER_WORK)
+		syscall = syscall_trace_enter(regs, syscall, ti_work);
+	instrumentation_end();
+
+	return syscall;
+}
+
+noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+}