Merge tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "These are the latest RCU updates for v5.12:

   - Documentation updates.

   - Miscellaneous fixes.

   - kfree_rcu() updates: Addition of mem_dump_obj() to provide
     allocator return addresses to more easily locate bugs. This has a
     couple of RCU-related commits, but is mostly MM. Was pulled in with
     akpm's agreement.

   - Per-callback-batch tracking of numbers of callbacks, which enables
     better debugging information and smarter reactions to large numbers
     of callbacks.

   - The first round of changes to allow CPUs to be runtime switched
     from and to callback-offloaded state.

   - CONFIG_PREEMPT_RT-related changes.

   - RCU CPU stall warning updates.

   - Addition of polling grace-period APIs for SRCU.

   - Torture-test and torture-test scripting updates, including a
     "torture everything" script that runs rcutorture, locktorture,
     scftorture, rcuscale, and refscale. Plus does an allmodconfig
     build.

   - nolibc fixes for the torture tests"

* tag 'core-rcu-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (130 commits)
  percpu_ref: Dump mem_dump_obj() info upon reference-count underflow
  rcu: Make call_rcu() print mem_dump_obj() info for double-freed callback
  mm: Make mem_obj_dump() vmalloc() dumps include start and length
  mm: Make mem_dump_obj() handle vmalloc() memory
  mm: Make mem_dump_obj() handle NULL and zero-sized pointers
  mm: Add mem_dump_obj() to print source of memory block
  tools/rcutorture: Fix position of -lgcc in mkinitrd.sh
  tools/nolibc: Fix position of -lgcc in the documented example
  tools/nolibc: Emit detailed error for missing alternate syscall number definitions
  tools/nolibc: Remove incorrect definitions of __ARCH_WANT_*
  tools/nolibc: Get timeval, timespec and timezone from linux/time.h
  tools/nolibc: Implement poll() based on ppoll()
  tools/nolibc: Implement fork() based on clone()
  tools/nolibc: Make getpgrp() fall back to getpgid(0)
  tools/nolibc: Make dup2() rely on dup3() when available
  tools/nolibc: Add the definition for dup()
  rcutorture: Add rcutree.use_softirq=0 to RUDE01 and TASKS01
  torture: Maintain torture-specific set of CPUs-online books
  torture: Clean up after torture-test CPU hotplugging
  rcutorture: Make object_debug also double call_rcu() heap object
  ...

12 files changed, 213 insertions, 28 deletions

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index d6428aaf67e7..3aaa0687e8df 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -111,6 +111,8 @@ static inline void cpu_maps_update_done(void)
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
+extern int lockdep_is_cpus_held(void);
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern void cpus_write_lock(void);
 extern void cpus_write_unlock(void);
diff --git a/include/linux/list.h b/include/linux/list.h
index 89bdc92e75c3..f2af4b4aa4e9 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -901,7 +901,7 @@ static inline void hlist_add_before(struct hlist_node *n,
 }
 
 /**
- * hlist_add_behing - add a new entry after the one specified
+ * hlist_add_behind - add a new entry after the one specified
  * @n: new entry to be added
  * @prev: hlist node to add it after, which must be non-NULL
  */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 078633d43af9..bd634bc9d256 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3177,5 +3177,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 
 extern int sysctl_nr_trim_pages;
 
+void mem_dump_obj(void *object);
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index b36afe7b22c9..8afe886e85f1 100644
--- a/include/linux/rcu_segcblist.h
+++ b/include/linux/rcu_segcblist.h
@@ -63,6 +63,122 @@ struct rcu_cblist {
 #define RCU_NEXT_TAIL		3
 #define RCU_CBLIST_NSEGS	4
 
+
+/*
+ *                     ==NOCB Offloading state machine==
+ *
+ *
+ *  ----------------------------------------------------------------------------
+ *  |                         SEGCBLIST_SOFTIRQ_ONLY                           |
+ *  |                                                                          |
+ *  |  Callbacks processed by rcu_core() from softirqs or local                |
+ *  |  rcuc kthread, without holding nocb_lock.                                |
+ *  ----------------------------------------------------------------------------
+ *                                         |
+ *                                         v
+ *  ----------------------------------------------------------------------------
+ *  |                        SEGCBLIST_OFFLOADED                               |
+ *  |                                                                          |
+ *  | Callbacks processed by rcu_core() from softirqs or local                 |
+ *  | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads,     |
+ *  | allowing nocb_timer to be armed.                                         |
+ *  ----------------------------------------------------------------------------
+ *                                         |
+ *                                         v
+ *                        -----------------------------------
+ *                        |                                 |
+ *                        v                                 v
+ *  ---------------------------------------  ----------------------------------|
+ *  |        SEGCBLIST_OFFLOADED |        |  |     SEGCBLIST_OFFLOADED |       |
+ *  |        SEGCBLIST_KTHREAD_CB         |  |     SEGCBLIST_KTHREAD_GP        |
+ *  |                                     |  |                                 |
+ *  |                                     |  |                                 |
+ *  | CB kthread woke up and              |  | GP kthread woke up and          |
+ *  | acknowledged SEGCBLIST_OFFLOADED.   |  | acknowledged SEGCBLIST_OFFLOADED|
+ *  | Processes callbacks concurrently    |  |                                 |
+ *  | with rcu_core(), holding            |  |                                 |
+ *  | nocb_lock.                          |  |                                 |
+ *  ---------------------------------------  -----------------------------------
+ *                        |                                 |
+ *                        -----------------------------------
+ *                                         |
+ *                                         v
+ *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_OFFLOADED |                          |
+ *  |                           SEGCBLIST_KTHREAD_CB |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                                                                          |
+ *  |   Kthreads handle callbacks holding nocb_lock, local rcu_core() stops    |
+ *  |   handling callbacks.                                                    |
+ *  ----------------------------------------------------------------------------
+ */
+
+
+
+/*
+ *                       ==NOCB De-Offloading state machine==
+ *
+ *
+ *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_OFFLOADED |                          |
+ *  |                           SEGCBLIST_KTHREAD_CB |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                                                                          |
+ *  |   CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core()    |
+ *  |   ignores callbacks.                                                     |
+ *  ----------------------------------------------------------------------------
+ *                                      |
+ *                                      v
+ *  |--------------------------------------------------------------------------|
+ *  |                           SEGCBLIST_KTHREAD_CB |                         |
+ *  |                           SEGCBLIST_KTHREAD_GP                           |
+ *  |                                                                          |
+ *  |   CB/GP kthreads and local rcu_core() handle callbacks concurrently      |
+ *  |   holding nocb_lock. Wake up CB and GP kthreads if necessary.            |
+ *  ----------------------------------------------------------------------------
+ *                                      |
+ *                                      v
+ *                     -----------------------------------
+ *                     |                                 |
+ *                     v                                 v
+ *  ---------------------------------------------------------------------------|
+ *  |                                                                          |
+ *  |        SEGCBLIST_KTHREAD_CB         |       SEGCBLIST_KTHREAD_GP         |
+ *  |                                     |                                    |
+ *  | GP kthread woke up and              |   CB kthread woke up and           |
+ *  | acknowledged the fact that          |   acknowledged the fact that       |
+ *  | SEGCBLIST_OFFLOADED got cleared.    |   SEGCBLIST_OFFLOADED got cleared. |
+ *  |                                     |   The CB kthread goes to sleep     |
+ *  | The callbacks from the target CPU   |   until it ever gets re-offloaded. |
+ *  | will be ignored from the GP kthread |                                    |
+ *  | loop.                               |                                    |
+ *  ----------------------------------------------------------------------------
+ *                      |                                 |
+ *                      -----------------------------------
+ *                                      |
+ *                                      v
+ *  ----------------------------------------------------------------------------
+ *  |                                   0                                      |
+ *  |                                                                          |
+ *  | Callbacks processed by rcu_core() from softirqs or local                 |
+ *  | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed.    |
+ *  | Flush pending nocb_timer. Flush nocb bypass callbacks.                   |
+ *  ----------------------------------------------------------------------------
+ *                                      |
+ *                                      v
+ *  ----------------------------------------------------------------------------
+ *  |                         SEGCBLIST_SOFTIRQ_ONLY                           |
+ *  |                                                                          |
+ *  |  Callbacks processed by rcu_core() from softirqs or local                |
+ *  |  rcuc kthread, without holding nocb_lock.                                |
+ *  ----------------------------------------------------------------------------
+ */
+#define SEGCBLIST_ENABLED	BIT(0)
+#define SEGCBLIST_SOFTIRQ_ONLY	BIT(1)
+#define SEGCBLIST_KTHREAD_CB	BIT(2)
+#define SEGCBLIST_KTHREAD_GP	BIT(3)
+#define SEGCBLIST_OFFLOADED	BIT(4)
+
 struct rcu_segcblist {
 	struct rcu_head *head;
 	struct rcu_head **tails[RCU_CBLIST_NSEGS];
@@ -72,8 +188,8 @@ struct rcu_segcblist {
 #else
 	long len;
 #endif
-	u8 enabled;
-	u8 offloaded;
+	long seglen[RCU_CBLIST_NSEGS];
+	u8 flags;
 };
 
 #define RCU_SEGCBLIST_INITIALIZER(n) \
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index fd02c5fa60cb..ebd8dcca4997 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -33,6 +33,8 @@
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
 #define ulong2long(a)		(*(long *)(&(a)))
+#define USHORT_CMP_GE(a, b)	(USHRT_MAX / 2 >= (unsigned short)((a) - (b)))
+#define USHORT_CMP_LT(a, b)	(USHRT_MAX / 2 < (unsigned short)((a) - (b)))
 
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
@@ -110,8 +112,12 @@ static inline void rcu_user_exit(void) { }
 
 #ifdef CONFIG_RCU_NOCB_CPU
 void rcu_init_nohz(void);
+int rcu_nocb_cpu_offload(int cpu);
+int rcu_nocb_cpu_deoffload(int cpu);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 static inline void rcu_init_nohz(void) { }
+static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; }
+static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /**
@@ -846,19 +852,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  */
 #define __is_kvfree_rcu_offset(offset) ((offset) < 4096)
 
-/*
- * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain.
- */
-#define __kvfree_rcu(head, offset) \
-	do { \
-		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \
-		kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \
-	} while (0)
-
 /**
  * kfree_rcu() - kfree an object after a grace period.
- * @ptr:	pointer to kfree
- * @rhf:	the name of the struct rcu_head within the type of @ptr.
+ * @ptr: pointer to kfree for both single- and double-argument invocations.
+ * @rhf: the name of the struct rcu_head within the type of @ptr,
+ *       but only for double-argument invocations.
  *
  * Many rcu callbacks functions just call kfree() on the base structure.
  * These functions are trivial, but their size adds up, and furthermore
@@ -871,7 +869,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * Because the functions are not allowed in the low-order 4096 bytes of
  * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
  * If the offset is larger than 4095 bytes, a compile-time error will
- * be generated in __kvfree_rcu(). If this error is triggered, you can
+ * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can
  * either fall back to use of call_rcu() or rearrange the structure to
  * position the rcu_head structure into the first 4096 bytes.
  *
@@ -881,13 +879,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * The BUILD_BUG_ON check must not involve any function calls, hence the
  * checks are done in macros here.
  */
-#define kfree_rcu(ptr, rhf)						\
-do {									\
-	typeof (ptr) ___p = (ptr);					\
-									\
-	if (___p)							\
-		__kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \
-} while (0)
+#define kfree_rcu kvfree_rcu
 
 /**
  * kvfree_rcu() - kvfree an object after a grace period.
@@ -919,7 +911,17 @@ do {									\
 	kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__)
 
 #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME
-#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf)
+#define kvfree_rcu_arg_2(ptr, rhf)					\
+do {									\
+	typeof (ptr) ___p = (ptr);					\
+									\
+	if (___p) {									\
+		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf)));	\
+		kvfree_call_rcu(&((___p)->rhf), (rcu_callback_t)(unsigned long)		\
+			(offsetof(typeof(*(ptr)), rhf)));				\
+	}										\
+} while (0)
+
 #define kvfree_rcu_arg_1(ptr)					\
 do {								\
 	typeof(ptr) ___p = (ptr);				\
diff --git a/include/linux/slab.h b/include/linux/slab.h
index be4ba5867ac5..7ae604076767 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -186,6 +186,8 @@ void kfree(const void *);
 void kfree_sensitive(const void *);
 size_t __ksize(const void *);
 size_t ksize(const void *);
+bool kmem_valid_obj(void *object);
+void kmem_dump_obj(void *object);
 
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
 void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index e432cc92c73d..a0895bbf71ce 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -60,6 +60,9 @@ void cleanup_srcu_struct(struct srcu_struct *ssp);
 int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
 void synchronize_srcu(struct srcu_struct *ssp);
+unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp);
+unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp);
+bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 5a5a1941ca15..0e0cf4d6a72a 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -15,7 +15,8 @@
 
 struct srcu_struct {
 	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
-	short srcu_idx;			/* Current reader array element. */
+	unsigned short srcu_idx;	/* Current reader array element in bit 0x2. */
+	unsigned short srcu_idx_max;	/* Furthest future srcu_idx request. */
 	u8 srcu_gp_running;		/* GP workqueue running? */
 	u8 srcu_gp_waiting;		/* GP waiting for readers? */
 	struct swait_queue_head srcu_wq;
@@ -59,7 +60,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp)
 {
 	int idx;
 
-	idx = READ_ONCE(ssp->srcu_idx);
+	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1);
 	return idx;
 }
@@ -80,7 +81,7 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 {
 	int idx;
 
-	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
 	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
 		 tt, tf, idx,
 		 READ_ONCE(ssp->srcu_lock_nesting[!idx]),
diff --git a/include/linux/timer.h b/include/linux/timer.h
index fda13c9d1256..4118a97e62fb 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -192,6 +192,8 @@ extern int try_to_del_timer_sync(struct timer_list *timer);
 
 #define del_singleshot_timer_sync(t) del_timer_sync(t)
 
+extern bool timer_curr_running(struct timer_list *timer);
+
 extern void init_timers(void);
 struct hrtimer;
 extern enum hrtimer_restart it_real_fn(struct hrtimer *);
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 7f65bd1dd307..0910c5803f35 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -32,11 +32,27 @@
 #define TOROUT_STRING(s) \
 	pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s)
 #define VERBOSE_TOROUT_STRING(s) \
-	do { if (verbose) pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); } while (0)
+do {										\
+	if (verbose) {								\
+		verbose_torout_sleep();						\
+		pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s);		\
+	}									\
+} while (0)
 #define VERBOSE_TOROUT_ERRSTRING(s) \
-	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0)
+do {										\
+	if (verbose) {								\
+		verbose_torout_sleep();						\
+		pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s);	\
+	}									\
+} while (0)
+void verbose_torout_sleep(void);
 
 /* Definitions for online/offline exerciser. */
+#ifdef CONFIG_HOTPLUG_CPU
+int torture_num_online_cpus(void);
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+static inline int torture_num_online_cpus(void) { return 1; }
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
 typedef void torture_ofl_func(void);
 bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes,
 		     unsigned long *sum_offl, int *min_onl, int *max_onl);
@@ -61,6 +77,13 @@ static inline void torture_random_init(struct torture_random_state *trsp)
 	trsp->trs_count = 0;
 }
 
+/* Definitions for high-resolution-timer sleeps. */
+int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp);
+int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state *trsp);
+int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state *trsp);
+int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp);
+int torture_hrtimeout_s(u32 baset_s, u32 fuzzt_ms, struct torture_random_state *trsp);
+
 /* Task shuffler, which causes CPUs to occasionally go idle. */
 void torture_shuffle_task_register(struct task_struct *tp);
 int torture_shuffle_init(long shuffint);
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index cedcda6593f6..df92211cf771 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -241,4 +241,10 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 int register_vmap_purge_notifier(struct notifier_block *nb);
 int unregister_vmap_purge_notifier(struct notifier_block *nb);
 
+#ifdef CONFIG_MMU
+bool vmalloc_dump_obj(void *object);
+#else
+static inline bool vmalloc_dump_obj(void *object) { return false; }
+#endif
+
 #endif /* _LINUX_VMALLOC_H */
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 155b5cb43cfd..5fc29400e1a2 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -505,6 +505,32 @@ TRACE_EVENT_RCU(rcu_callback,
 		  __entry->qlen)
 );
 
+TRACE_EVENT_RCU(rcu_segcb_stats,
+
+		TP_PROTO(struct rcu_segcblist *rs, const char *ctx),
+
+		TP_ARGS(rs, ctx),
+
+		TP_STRUCT__entry(
+			__field(const char *, ctx)
+			__array(unsigned long, gp_seq, RCU_CBLIST_NSEGS)
+			__array(long, seglen, RCU_CBLIST_NSEGS)
+		),
+
+		TP_fast_assign(
+			__entry->ctx = ctx;
+			memcpy(__entry->seglen, rs->seglen, RCU_CBLIST_NSEGS * sizeof(long));
+			memcpy(__entry->gp_seq, rs->gp_seq, RCU_CBLIST_NSEGS * sizeof(unsigned long));
+
+		),
+
+		TP_printk("%s seglen: (DONE=%ld, WAIT=%ld, NEXT_READY=%ld, NEXT=%ld) "
+			  "gp_seq: (DONE=%lu, WAIT=%lu, NEXT_READY=%lu, NEXT=%lu)", __entry->ctx,
+			  __entry->seglen[0], __entry->seglen[1], __entry->seglen[2], __entry->seglen[3],
+			  __entry->gp_seq[0], __entry->gp_seq[1], __entry->gp_seq[2], __entry->gp_seq[3])
+
+);
+
 /*
  * Tracepoint for the registration of a single RCU callback of the special
  * kvfree() form.  The first argument is the RCU type, the second argument