Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

The UDP reuseport conflict was a little bit tricky.

The net-next code, via bpf-next, extracted the reuseport handling
into a helper so that the BPF sk lookup code could invoke it.

At the same time, the logic for reuseport handling of unconnected
sockets changed via commit efc6b6f6c3113e8b203b9debfb72d81e0f3dcace
which changed the logic to carry on the reuseport result into the
rest of the lookup loop if we do not return immediately.

This requires moving the reuseport_has_conns() logic into the callers.

While we are here, get rid of inline directives as they do not belong
in foo.c files.

The other changes were cases of more straightforward overlapping
modifications.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 77 insertions, 30 deletions

diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 5df49366e9ab..7310a4f7f993 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init);
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -391,17 +394,26 @@ void user_rewind_single_step(struct task_struct *task)
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68b7f34a08f5..1e02e98e68dd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1811,19 +1811,42 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	unsigned long saved_reg;
 
 	/*
-	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
-	 * used to denote syscall entry/exit:
+	 * We have some ABI weirdness here in the way that we handle syscall
+	 * exit stops because we indicate whether or not the stop has been
+	 * signalled from syscall entry or syscall exit by clobbering a general
+	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+	 * and restoring its old value after the stop. This means that:
+	 *
+	 * - Any writes by the tracer to this register during the stop are
+	 *   ignored/discarded.
+	 *
+	 * - The actual value of the register is not available during the stop,
+	 *   so the tracer cannot save it and restore it later.
+	 *
+	 * - Syscall stops behave differently to seccomp and pseudo-step traps
+	 *   (the latter do not nobble any registers).
 	 */
 	regno = (is_compat_task() ? 12 : 7);
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1833,12 +1856,12 @@ int syscall_trace_enter(struct pt_regs *regs)
 	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 		if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
-			return -1;
+			return NO_SYSCALL;
 	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing() == -1)
-		return -1;
+		return NO_SYSCALL;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
@@ -1851,12 +1874,14 @@ int syscall_trace_enter(struct pt_regs *regs)
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1934,8 +1959,8 @@ static int valid_native_regs(struct user_pt_regs *regs)
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 801d56cdf701..3b4f31f35e45 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -800,7 +800,6 @@ static void setup_restart_syscall(struct pt_regs *regs)
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -824,14 +823,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f5b868292f5..5f0c04863d2c 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,21 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	user_exit();
 
 	if (has_syscall_work(flags)) {
-		/* set default errno for user-issued syscall(-1) */
+		/*
+		 * The de-facto standard way to skip a system call using ptrace
+		 * is to set the system call to -1 (NO_SYSCALL) and set x0 to a
+		 * suitable error code for consumption by userspace. However,
+		 * this cannot be distinguished from a user-issued syscall(-1)
+		 * and so we must set x0 to -ENOSYS here in case the tracer doesn't
+		 * issue the skip and we fall into trace_exit with x0 preserved.
+		 *
+		 * This is slightly odd because it also means that if a tracer
+		 * sets the system call number to -1 but does not initialise x0,
+		 * then x0 will be preserved for all system calls apart from a
+		 * user-issued syscall(-1). However, requesting a skip and not
+		 * setting the return value is unlikely to do anything sensible
+		 * anyway.
+		 */
 		if (scno == NO_SYSCALL)
 			regs->regs[0] = -ENOSYS;
 		scno = syscall_trace_enter(regs);
@@ -139,7 +156,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index d88148bef6b0..5139a5f19256 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit))
 COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
 
 CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT))
 CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
 ifneq ($(COMPAT_GCC_TOOLCHAIN),)
 CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)