Merge tag 'rcu_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU-vs-KCSAN fixes from Borislav Petkov:
 "A single commit that uses "arch_" atomic operations to avoid the
  instrumentation that comes with the non-"arch_" versions.

  In preparation for that commit, it also has another commit that makes
  these "arch_" atomic operations available to generic code.

  Without these commits, KCSAN uses can see pointless errors"

* tag 'rcu_urgent_for_5.8_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  rcu: Fixup noinstr warnings
  locking/atomics: Provide the arch_atomic_ interface to generic code

include/linux/compiler.h

@@ -123,7 +123,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #ifdef CONFIG_DEBUG_ENTRY
 /* Begin/end of an instrumentation safe region */
 #define instrumentation_begin() ({					\
-	asm volatile("%c0:\n\t"						\
+	asm volatile("%c0: nop\n\t"						\
 		     ".pushsection .discard.instr_begin\n\t"		\
 		     ".long %c0b - .\n\t"				\
 		     ".popsection\n\t" : : "i" (__COUNTER__));		\

kernel/rcu/tree.c

@@ -250,7 +250,7 @@ static noinstr void rcu_dynticks_eqs_enter(void)
 	 * next idle sojourn.
 	 */
 	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
@@ -274,13 +274,13 @@ static noinstr void rcu_dynticks_eqs_exit(void)
 	 * and we also must force ordering with the next RCU read-side
 	 * critical section.
 	 */
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is now watching.  Better not be in an extended quiescent state!
 	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
-		atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
+		arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
 		smp_mb__after_atomic(); /* _exit after clearing mask. */
 	}
 }
@@ -313,7 +313,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+	return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
 }
 
 /*
@@ -633,6 +633,10 @@ static noinstr void rcu_eqs_enter(bool user)
 	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
 	// RCU is watching here ...
@@ -692,6 +696,7 @@ noinstr void rcu_nmi_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
+	instrumentation_begin();
 	/*
 	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
 	 * (We are exiting an NMI handler, so RCU better be paying attention
@@ -705,7 +710,6 @@ noinstr void rcu_nmi_exit(void)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		instrumentation_begin();
 		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
 				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
@@ -714,13 +718,15 @@ noinstr void rcu_nmi_exit(void)
 		return;
 	}
 
-	instrumentation_begin();
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (!in_nmi())
 		rcu_prepare_for_idle();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
 
 	// RCU is watching here ...
@@ -838,6 +844,10 @@ static void noinstr rcu_eqs_exit(bool user)
 	rcu_dynticks_eqs_exit();
 	// ... but is watching here.
 	instrumentation_begin();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
@@ -983,13 +993,21 @@ noinstr void rcu_nmi_enter(void)
 		if (!in_nmi())
 			rcu_cleanup_after_idle();
 
+		instrumentation_begin();
+		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+		// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+		instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 		incby = 1;
 	} else if (!in_nmi()) {
 		instrumentation_begin();
 		rcu_irq_enter_check_tick();
 		instrumentation_end();
+	} else  {
+		instrumentation_begin();
 	}
-	instrumentation_begin();
+
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
 			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));

scripts/atomic/gen-atomic-fallback.sh

@@ -58,6 +58,21 @@ cat << EOF
 EOF
 }
 
+gen_proto_order_variant()
+{
+	local meta="$1"; shift
+	local pfx="$1"; shift
+	local name="$1"; shift
+	local sfx="$1"; shift
+	local order="$1"; shift
+	local arch="$1"
+	local atomic="$2"
+
+	local basename="${arch}${atomic}_${pfx}${name}${sfx}"
+
+	printf "#define arch_${basename}${order} ${basename}${order}\n"
+}
+
 #gen_proto_order_variants(meta, pfx, name, sfx, arch, atomic, int, args...)
 gen_proto_order_variants()
 {
@@ -72,6 +87,22 @@ gen_proto_order_variants()
 
 	local template="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")"
 
+	if [ -z "$arch" ]; then
+		gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "" "$@"
+
+		if meta_has_acquire "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_acquire" "$@"
+		fi
+		if meta_has_release "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_release" "$@"
+		fi
+		if meta_has_relaxed "${meta}"; then
+			gen_proto_order_variant "${meta}" "${pfx}" "${name}" "${sfx}" "_relaxed" "$@"
+		fi
+
+		echo ""
+	fi
+
 	# If we don't have relaxed atomics, then we don't bother with ordering fallbacks
 	# read_acquire and set_release need to be templated, though
 	if ! meta_has_relaxed "${meta}"; then