Merge branch 'strictgp.2020.08.24a' into HEAD

strictgp.2020.08.24a: Strict grace periods for KASAN testing.

Documentation/admin-guide/kernel-parameters.txt

@@ -4152,6 +4152,15 @@
 			This wake_up() will be accompanied by a
 			WARN_ONCE() splat and an ftrace_dump().
 
+	rcutree.rcu_unlock_delay= [KNL]
+			In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
+			this specifies an rcu_read_unlock()-time delay
+			in microseconds.  This defaults to zero.
+			Larger delays increase the probability of
+			catching RCU pointer leaks, that is, buggy use
+			of RCU-protected pointers after the relevant
+			rcu_read_unlock() has completed.
+
 	rcutree.sysrq_rcu= [KNL]
 			Commandeer a sysrq key to dump out Tree RCU's
 			rcu_node tree with an eye towards determining

include/linux/rcupdate.h

@@ -55,6 +55,12 @@ void __rcu_read_unlock(void);
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_TINY_RCU
+#define rcu_read_unlock_strict() do { } while (0)
+#else
+void rcu_read_unlock_strict(void);
+#endif
+
 static inline void __rcu_read_lock(void)
 {
 	preempt_disable();
@@ -63,6 +69,7 @@ static inline void __rcu_read_lock(void)
 static inline void __rcu_read_unlock(void)
 {
 	preempt_enable();
+	rcu_read_unlock_strict();
 }
 
 static inline int rcu_preempt_depth(void)

kernel/rcu/Kconfig

@@ -135,10 +135,12 @@ config RCU_FANOUT
 
 config RCU_FANOUT_LEAF
 	int "Tree-based hierarchical RCU leaf-level fanout value"
-	range 2 64 if 64BIT
+	range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
-	range 2 32 if !64BIT
+	range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
+	range 2 3 if RCU_STRICT_GRACE_PERIOD
 	depends on TREE_RCU && RCU_EXPERT
-	default 16
+	default 16 if !RCU_STRICT_GRACE_PERIOD
+	default 2 if RCU_STRICT_GRACE_PERIOD
 	help
 	  This option controls the leaf-level fanout of hierarchical
 	  implementations of RCU, and allows trading off cache misses

kernel/rcu/Kconfig.debug

@@ -114,4 +114,19 @@ config RCU_EQS_DEBUG
 	  Say N here if you need ultimate kernel/user switch latencies
 	  Say Y if you are unsure
 
+config RCU_STRICT_GRACE_PERIOD
+	bool "Provide debug RCU implementation with short grace periods"
+	depends on DEBUG_KERNEL && RCU_EXPERT
+	default n
+	select PREEMPT_COUNT if PREEMPT=n
+	help
+	  Select this option to build an RCU variant that is strict about
+	  grace periods, making them as short as it can.  This limits
+	  scalability, destroys real-time response, degrades battery
+	  lifetime and kills performance.  Don't try this on large
+	  machines, as in systems with more than about 10 or 20 CPUs.
+	  But in conjunction with tools like KASAN, it can be helpful
+	  when looking for certain types of RCU usage bugs, for example,
+	  too-short RCU read-side critical sections.
+
 endmenu # "RCU Debugging"

kernel/rcu/tree.c

@@ -165,6 +165,12 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+// Add delay to rcu_read_unlock() for strict grace periods.
+static int rcu_unlock_delay;
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
 /*
  * This rcu parameter is runtime-read-only. It reflects
  * a minimum allowed number of objects which can be cached
@@ -455,24 +461,25 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 	return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
 }
 
-#define DEFAULT_RCU_BLIMIT 10     /* Maximum callbacks per rcu_do_batch ... */
+#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
-#define DEFAULT_MAX_RCU_BLIMIT 10000 /* ... even during callback flood. */
+				// Maximum callbacks per rcu_do_batch ...
+#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood.
 static long blimit = DEFAULT_RCU_BLIMIT;
-#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */
+#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit.
 static long qhimark = DEFAULT_RCU_QHIMARK;
-#define DEFAULT_RCU_QLOMARK 100   /* Once only this many pending, use blimit. */
+#define DEFAULT_RCU_QLOMARK 100   // Once only this many pending, use blimit.
 static long qlowmark = DEFAULT_RCU_QLOMARK;
 #define DEFAULT_RCU_QOVLD_MULT 2
 #define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
-static long qovld = DEFAULT_RCU_QOVLD; /* If this many pending, hammer QS. */
+static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS.
-static long qovld_calc = -1;	  /* No pre-initialization lock acquisitions! */
+static long qovld_calc = -1;	  // No pre-initialization lock acquisitions!
 
 module_param(blimit, long, 0444);
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 module_param(qovld, long, 0444);
 
-static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
 static bool rcu_kick_kthreads;
 static int rcu_divisor = 7;
@@ -1571,6 +1578,19 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 	raw_spin_unlock_rcu_node(rnp);
 }
 
+/*
+ * In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a
+ * quiescent state.  This is intended to be invoked when the CPU notices
+ * a new grace period.
+ */
+static void rcu_strict_gp_check_qs(void)
+{
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+		rcu_read_lock();
+		rcu_read_unlock();
+	}
+}
+
 /*
  * Update CPU-local rcu_data state to record the beginnings and ends of
  * grace periods.  The caller must hold the ->lock of the leaf rcu_node
@@ -1641,6 +1661,7 @@ static void note_gp_changes(struct rcu_data *rdp)
 	}
 	needwake = __note_gp_changes(rnp, rdp);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	rcu_strict_gp_check_qs();
 	if (needwake)
 		rcu_gp_kthread_wake();
 }
@@ -1678,6 +1699,15 @@ static void rcu_gp_torture_wait(void)
 	}
 }
 
+/*
+ * Handler for on_each_cpu() to invoke the target CPU's RCU core
+ * processing.
+ */
+static void rcu_strict_gp_boundary(void *unused)
+{
+	invoke_rcu_core();
+}
+
 /*
  * Initialize a new grace period.  Return false if no grace period required.
  */
@@ -1809,6 +1839,10 @@ static bool rcu_gp_init(void)
 		WRITE_ONCE(rcu_state.gp_activity, jiffies);
 	}
 
+	// If strict, make all CPUs aware of new grace period.
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
+
 	return true;
 }
 
@@ -2025,6 +2059,10 @@ static void rcu_gp_cleanup(void)
 			   rcu_state.gp_flags & RCU_GP_FLAG_INIT);
 	}
 	raw_spin_unlock_irq_rcu_node(rnp);
+
+	// If strict, make all CPUs aware of the end of the old grace period.
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
 }
 
 /*
@@ -2203,7 +2241,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
  * structure.  This must be called from the specified CPU.
  */
 static void
-rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
+rcu_report_qs_rdp(struct rcu_data *rdp)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -2212,6 +2250,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 			       rcu_segcblist_is_offloaded(&rdp->cblist);
 	struct rcu_node *rnp;
 
+	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
@@ -2228,7 +2267,6 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
-	if (rdp->cpu == smp_processor_id())
 	rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2278,7 +2316,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
 	 * Tell RCU we are done (but rcu_report_qs_rdp() will be the
 	 * judge of that).
 	 */
-	rcu_report_qs_rdp(rdp->cpu, rdp);
+	rcu_report_qs_rdp(rdp);
 }
 
 /*
@@ -2621,6 +2659,14 @@ void rcu_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
+// Workqueue handler for an RCU reader for kernels enforcing struct RCU
+// grace periods.
+static void strict_work_handler(struct work_struct *work)
+{
+	rcu_read_lock();
+	rcu_read_unlock();
+}
+
 /* Perform RCU core processing work for the current CPU.  */
 static __latent_entropy void rcu_core(void)
 {
@@ -2665,6 +2711,10 @@ static __latent_entropy void rcu_core(void)
 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
 	trace_rcu_utilization(TPS("End RCU core"));
+
+	// If strict GPs, schedule an RCU reader in a clean environment.
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
 }
 
 static void rcu_core_si(struct softirq_action *h)
@@ -3862,6 +3912,7 @@ rcu_boot_init_percpu_data(int cpu)
 
 	/* Set up local state, ensuring consistent view of global state. */
 	rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
+	INIT_WORK(&rdp->strict_work, strict_work_handler);
 	WARN_ON_ONCE(rdp->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
 	rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;

kernel/rcu/tree.h

@@ -165,6 +165,7 @@ struct rcu_data {
 					/* period it is aware of. */
 	struct irq_work defer_qs_iw;	/* Obtain later scheduler attention. */
 	bool defer_qs_iw_pending;	/* Scheduler attention pending? */
+	struct work_struct strict_work;	/* Schedule readers for strict GPs. */
 
 	/* 2) batch handling */
 	struct rcu_segcblist cblist;	/* Segmented callback list, with */

kernel/rcu/tree_plugin.h

@@ -36,6 +36,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
 	if (IS_ENABLED(CONFIG_PROVE_RCU))
 		pr_info("\tRCU lockdep checking is enabled.\n");
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		pr_info("\tRCU strict (and thus non-scalable) grace periods enabled.\n");
 	if (RCU_NUM_LVLS >= 4)
 		pr_info("\tFour(or more)-level hierarchy is enabled.\n");
 	if (RCU_FANOUT_LEAF != 16)
@@ -374,6 +376,8 @@ void __rcu_read_lock(void)
 	rcu_preempt_read_enter();
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
 		WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX);
+	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && rcu_state.gp_kthread)
+		WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true);
 	barrier();  /* critical section after entry code. */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -455,8 +459,14 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		return;
 	}
 	t->rcu_read_unlock_special.s = 0;
-	if (special.b.need_qs)
+	if (special.b.need_qs) {
+		if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+			rcu_report_qs_rdp(rdp);
+			udelay(rcu_unlock_delay);
+		} else {
 			rcu_qs();
+		}
+	}
 
 	/*
 	 * Respond to a request by an expedited grace period for a
@@ -768,6 +778,24 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+/*
+ * If strict grace periods are enabled, and if the calling
+ * __rcu_read_unlock() marks the beginning of a quiescent state, immediately
+ * report that quiescent state and, if requested, spin for a bit.
+ */
+void rcu_read_unlock_strict(void)
+{
+	struct rcu_data *rdp;
+
+	if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+	   irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+		return;
+	rdp = this_cpu_ptr(&rcu_data);
+	rcu_report_qs_rdp(rdp);
+	udelay(rcu_unlock_delay);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_strict);
+
 /*
  * Tell them what RCU they are running.
  */