Merge tag 'v3.5-rc6' into irqdomain/next

Linux 3.5-rc6

14 files changed, 617 insertions, 223 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 72fcd3069a90..2097684cf194 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -255,12 +255,17 @@ int cgroup_lock_is_held(void)
 
 EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
 
+static int css_unbias_refcnt(int refcnt)
+{
+        return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
+}
+
 /* the current nr of refs, always >= 0 whether @css is deactivated or not */
 static int css_refcnt(struct cgroup_subsys_state *css)
 {
         int v = atomic_read(&css->refcnt);
 
-        return v >= 0 ? v : v - CSS_DEACT_BIAS;
+        return css_unbias_refcnt(v);
 }
 
 /* convenient tests for these bits */
@@ -4982,10 +4987,12 @@ EXPORT_SYMBOL_GPL(__css_tryget);
 void __css_put(struct cgroup_subsys_state *css)
 {
         struct cgroup *cgrp = css->cgroup;
+        int v;
 
         rcu_read_lock();
-        atomic_dec(&css->refcnt);
-        switch (css_refcnt(css)) {
+        v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
+
+        switch (v) {
         case 1:
                 if (notify_on_release(cgrp)) {
                         set_bit(CGRP_RELEASABLE, &cgrp->flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f85c0154b333..d7d71d6ec972 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
         return !event->cgrp || event->cgrp == cpuctx->cgrp;
 }
 
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
 {
-        css_get(&event->cgrp->css);
+        return css_tryget(&event->cgrp->css);
 }
 
 static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
         event->cgrp = cgrp;
 
         /* must be done before we fput() the file */
-        perf_get_cgroup(event);
+        if (!perf_tryget_cgroup(event)) {
+                event->cgrp = NULL;
+                ret = -ENOENT;
+                goto out;
+        }
 
         /*
          * all events in a group must monitor
diff --git a/kernel/exit.c b/kernel/exit.c
index 34867cc5b42a..2f59cc334516 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,6 +72,18 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
                 list_del_rcu(&p->tasks);
                 list_del_init(&p->sibling);
                 __this_cpu_dec(process_counts);
+                /*
+                 * If we are the last child process in a pid namespace to be
+                 * reaped, notify the reaper sleeping zap_pid_ns_processes().
+                 */
+                if (IS_ENABLED(CONFIG_PID_NS)) {
+                        struct task_struct *parent = p->real_parent;
+
+                        if ((task_active_pid_ns(parent)->child_reaper == parent) &&
+                            list_empty(&parent->children) &&
+                            (parent->flags & PF_EXITING))
+                                wake_up_process(parent);
+                }
         }
         list_del_rcu(&p->thread_group);
 }
@@ -643,6 +655,7 @@ static void exit_mm(struct task_struct * tsk)
         mm_release(tsk, mm);
         if (!mm)
                 return;
+        sync_mm_rss(mm);
         /*
          * Serialize with any possible pending coredump.
          * We must hold mmap_sem around checking core_state
@@ -719,12 +732,6 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 
                 zap_pid_ns_processes(pid_ns);
                 write_lock_irq(&tasklist_lock);
-                /*
-                 * We can not clear ->child_reaper or leave it alone.
-                 * There may by stealth EXIT_DEAD tasks on ->children,
-                 * forget_original_parent() must move them somewhere.
-                 */
-                pid_ns->child_reaper = init_pid_ns.child_reaper;
         } else if (father->signal->has_child_subreaper) {
                 struct task_struct *reaper;
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 8ed89a175d79..d2a5f4ecc6dd 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,7 +27,7 @@
 #define PANIC_TIMER_STEP 100
 #define PANIC_BLINK_SPD 18
 
-int panic_on_oops;
+int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask;
 static int pause_on_oops;
 static int pause_on_oops_flag;
@@ -108,8 +108,6 @@ void panic(const char *fmt, ...)
          */
         crash_kexec(NULL);
 
-        kmsg_dump(KMSG_DUMP_PANIC);
-
         /*
          * Note smp_send_stop is the usual smp shutdown function, which
          * unfortunately means it may not be hardened to work in a panic
@@ -117,6 +115,8 @@ void panic(const char *fmt, ...)
          */
         smp_send_stop();
 
+        kmsg_dump(KMSG_DUMP_PANIC);
+
         atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
         bust_spinlocks(0);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 16b20e38c4a1..b3c7fd554250 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         }
         read_unlock(&tasklist_lock);
 
+        /* Firstly reap the EXIT_ZOMBIE children we may have. */
         do {
                 clear_thread_flag(TIF_SIGPENDING);
                 rc = sys_wait4(-1, NULL, __WALL, NULL);
         } while (rc != -ECHILD);
 
+        /*
+         * sys_wait4() above can't reap the TASK_DEAD children.
+         * Make sure they all go away, see __unhash_process().
+         */
+        for (;;) {
+                bool need_wait = false;
+
+                read_lock(&tasklist_lock);
+                if (!list_empty(&current->children)) {
+                        __set_current_state(TASK_UNINTERRUPTIBLE);
+                        need_wait = true;
+                }
+                read_unlock(&tasklist_lock);
+
+                if (!need_wait)
+                        break;
+                schedule();
+        }
+
         if (pid_ns->reboot)
                 current->signal->group_exit_code = pid_ns->reboot;
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 32462d2b364a..dba18211685e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -193,12 +193,19 @@ static int console_may_schedule;
  * separated by ',', and find the message after the ';' character.
  */
 
+enum log_flags {
+        LOG_DEFAULT = 0,
+        LOG_NOCONS = 1,         /* already flushed, do not print to console */
+};
+
 struct log {
         u64 ts_nsec;            /* timestamp in nanoseconds */
         u16 len;                /* length of entire record */
         u16 text_len;           /* length of text buffer */
         u16 dict_len;           /* length of dictionary buffer */
-        u16 level;              /* syslog level + facility */
+        u8 facility;            /* syslog facility */
+        u8 flags:5;             /* internal record flags */
+        u8 level:3;             /* syslog level */
 };
 
 /*
@@ -227,10 +234,10 @@ static u32 clear_idx;
 #define LOG_LINE_MAX 1024
 
 /* record buffer */
-#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 #define LOG_ALIGN 4
 #else
-#define LOG_ALIGN 8
+#define LOG_ALIGN __alignof__(struct log)
 #endif
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
@@ -286,6 +293,7 @@ static u32 log_next(u32 idx)
 
 /* insert record into the buffer, discard old ones, update heads */
 static void log_store(int facility, int level,
+                      enum log_flags flags, u64 ts_nsec,
                       const char *dict, u16 dict_len,
                       const char *text, u16 text_len)
 {
@@ -329,8 +337,13 @@ static void log_store(int facility, int level,
         msg->text_len = text_len;
         memcpy(log_dict(msg), dict, dict_len);
         msg->dict_len = dict_len;
-        msg->level = (facility << 3) | (level & 7);
-        msg->ts_nsec = local_clock();
+        msg->facility = facility;
+        msg->level = level & 7;
+        msg->flags = flags & 0x1f;
+        if (ts_nsec > 0)
+                msg->ts_nsec = ts_nsec;
+        else
+                msg->ts_nsec = local_clock();
         memset(log_dict(msg) + dict_len, 0, pad_len);
         msg->len = sizeof(struct log) + text_len + dict_len + pad_len;
 
@@ -414,7 +427,9 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
         if (!user)
                 return -EBADF;
 
-        mutex_lock(&user->lock);
+        ret = mutex_lock_interruptible(&user->lock);
+        if (ret)
+                return ret;
         raw_spin_lock(&logbuf_lock);
         while (user->seq == log_next_seq) {
                 if (file->f_flags & O_NONBLOCK) {
@@ -444,7 +459,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
         ts_usec = msg->ts_nsec;
         do_div(ts_usec, 1000);
         len = sprintf(user->buf, "%u,%llu,%llu;",
-                      msg->level, user->seq, ts_usec);
+                      (msg->facility << 3) | msg->level, user->seq, ts_usec);
 
         /* escape non-printable characters */
         for (i = 0; i < msg->text_len; i++) {
@@ -785,6 +800,21 @@ static bool printk_time;
 #endif
 module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
 
+static size_t print_time(u64 ts, char *buf)
+{
+        unsigned long rem_nsec;
+
+        if (!printk_time)
+                return 0;
+
+        if (!buf)
+                return 15;
+
+        rem_nsec = do_div(ts, 1000000000);
+        return sprintf(buf, "[%5lu.%06lu] ",
+                       (unsigned long)ts, rem_nsec / 1000);
+}
+
 static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
 {
         size_t len = 0;
@@ -801,18 +831,7 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
                 }
         }
 
-        if (printk_time) {
-                if (buf) {
-                        unsigned long long ts = msg->ts_nsec;
-                        unsigned long rem_nsec = do_div(ts, 1000000000);
-
-                        len += sprintf(buf + len, "[%5lu.%06lu] ",
-                                         (unsigned long) ts, rem_nsec / 1000);
-                } else {
-                        len += 15;
-                }
-        }
-
+        len += print_time(msg->ts_nsec, buf ? buf + len : NULL);
         return len;
 }
 
@@ -860,26 +879,49 @@ static int syslog_print(char __user *buf, int size)
 {
         char *text;
         struct log *msg;
-        int len;
+        int len = 0;
 
         text = kmalloc(LOG_LINE_MAX, GFP_KERNEL);
         if (!text)
                 return -ENOMEM;
 
-        raw_spin_lock_irq(&logbuf_lock);
-        if (syslog_seq < log_first_seq) {
-                /* messages are gone, move to first one */
-                syslog_seq = log_first_seq;
-                syslog_idx = log_first_idx;
-        }
-        msg = log_from_idx(syslog_idx);
-        len = msg_print_text(msg, true, text, LOG_LINE_MAX);
-        syslog_idx = log_next(syslog_idx);
-        syslog_seq++;
-        raw_spin_unlock_irq(&logbuf_lock);
+        while (size > 0) {
+                size_t n;
+
+                raw_spin_lock_irq(&logbuf_lock);
+                if (syslog_seq < log_first_seq) {
+                        /* messages are gone, move to first one */
+                        syslog_seq = log_first_seq;
+                        syslog_idx = log_first_idx;
+                }
+                if (syslog_seq == log_next_seq) {
+                        raw_spin_unlock_irq(&logbuf_lock);
+                        break;
+                }
+                msg = log_from_idx(syslog_idx);
+                n = msg_print_text(msg, true, text, LOG_LINE_MAX);
+                if (n <= size) {
+                        syslog_idx = log_next(syslog_idx);
+                        syslog_seq++;
+                } else
+                        n = 0;
+                raw_spin_unlock_irq(&logbuf_lock);
+
+                if (!n)
+                        break;
+
+                len += n;
+                size -= n;
+                buf += n;
+                n = copy_to_user(buf - n, text, n);
 
-        if (len > 0 && copy_to_user(buf, text, len))
-                len = -EFAULT;
+                if (n) {
+                        len -= n;
+                        if (!len)
+                                len = -EFAULT;
+                        break;
+                }
+        }
 
         kfree(text);
         return len;
@@ -909,7 +951,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                 /*
                  * Find first record that fits, including all following records,
                  * into the user-provided buffer for this dump.
-                */
+                 */
                 seq = clear_seq;
                 idx = clear_idx;
                 while (seq < log_next_seq) {
@@ -919,6 +961,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                         idx = log_next(idx);
                         seq++;
                 }
+
+                /* move first record forward until length fits into the buffer */
                 seq = clear_seq;
                 idx = clear_idx;
                 while (len > size && seq < log_next_seq) {
@@ -929,7 +973,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
                         seq++;
                 }
 
-                /* last message in this dump */
+                /* last message fitting into this dump */
                 next_seq = log_next_seq;
 
                 len = 0;
@@ -974,6 +1018,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
         bool clear = false;
         static int saved_console_loglevel = -1;
+        static DEFINE_MUTEX(syslog_mutex);
         int error;
 
         error = check_syslog_permissions(type, from_file);
@@ -1000,11 +1045,17 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
                         error = -EFAULT;
                         goto out;
                 }
+                error = mutex_lock_interruptible(&syslog_mutex);
+                if (error)
+                        goto out;
                 error = wait_event_interruptible(log_wait,
                                                  syslog_seq != log_next_seq);
-                if (error)
+                if (error) {
+                        mutex_unlock(&syslog_mutex);
                         goto out;
+                }
                 error = syslog_print(buf, len);
+                mutex_unlock(&syslog_mutex);
                 break;
         /* Read/clear last kernel messages */
         case SYSLOG_ACTION_READ_CLEAR:
@@ -1027,6 +1078,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
         /* Clear ring buffer */
         case SYSLOG_ACTION_CLEAR:
                 syslog_print_all(NULL, 0, true);
+                break;
         /* Disable logging to console */
         case SYSLOG_ACTION_CONSOLE_OFF:
                 if (saved_console_loglevel == -1)
@@ -1259,15 +1311,92 @@ static inline void printk_delay(void)
         }
 }
 
+/*
+ * Continuation lines are buffered, and not committed to the record buffer
+ * until the line is complete, or a race forces it. The line fragments
+ * though, are printed immediately to the consoles to ensure everything has
+ * reached the console in case of a kernel crash.
+ */
+static struct cont {
+        char buf[LOG_LINE_MAX];
+        size_t len;                     /* length == 0 means unused buffer */
+        size_t cons;                    /* bytes written to console */
+        struct task_struct *owner;      /* task of first print*/
+        u64 ts_nsec;                    /* time of first print */
+        u8 level;                       /* log level of first message */
+        u8 facility;                    /* log level of first message */
+        bool flushed:1;                 /* buffer sealed and committed */
+} cont;
+
+static void cont_flush(void)
+{
+        if (cont.flushed)
+                return;
+        if (cont.len == 0)
+                return;
+
+        log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec,
+                  NULL, 0, cont.buf, cont.len);
+
+        cont.flushed = true;
+}
+
+static bool cont_add(int facility, int level, const char *text, size_t len)
+{
+        if (cont.len && cont.flushed)
+                return false;
+
+        if (cont.len + len > sizeof(cont.buf)) {
+                cont_flush();
+                return false;
+        }
+
+        if (!cont.len) {
+                cont.facility = facility;
+                cont.level = level;
+                cont.owner = current;
+                cont.ts_nsec = local_clock();
+                cont.cons = 0;
+                cont.flushed = false;
+        }
+
+        memcpy(cont.buf + cont.len, text, len);
+        cont.len += len;
+        return true;
+}
+
+static size_t cont_print_text(char *text, size_t size)
+{
+        size_t textlen = 0;
+        size_t len;
+
+        if (cont.cons == 0) {
+                textlen += print_time(cont.ts_nsec, text);
+                size -= textlen;
+        }
+
+        len = cont.len - cont.cons;
+        if (len > 0) {
+                if (len+1 > size)
+                        len = size-1;
+                memcpy(text + textlen, cont.buf + cont.cons, len);
+                textlen += len;
+                cont.cons = cont.len;
+        }
+
+        if (cont.flushed) {
+                text[textlen++] = '\n';
+                /* got everything, release buffer */
+                cont.len = 0;
+        }
+        return textlen;
+}
+
 asmlinkage int vprintk_emit(int facility, int level,
                             const char *dict, size_t dictlen,
                             const char *fmt, va_list args)
 {
         static int recursion_bug;
-        static char cont_buf[LOG_LINE_MAX];
-        static size_t cont_len;
-        static int cont_level;
-        static struct task_struct *cont_task;
         static char textbuf[LOG_LINE_MAX];
         char *text = textbuf;
         size_t text_len;
@@ -1313,7 +1442,8 @@ asmlinkage int vprintk_emit(int facility, int level,
                 recursion_bug = 0;
                 printed_len += strlen(recursion_msg);
                 /* emit KERN_CRIT message */
-                log_store(0, 2, NULL, 0, recursion_msg, printed_len);
+                log_store(0, 2, LOG_DEFAULT, 0,
+                          NULL, 0, recursion_msg, printed_len);
         }
 
         /*
@@ -1351,55 +1481,37 @@ asmlinkage int vprintk_emit(int facility, int level,
         }
 
         if (!newline) {
-                if (cont_len && (prefix || cont_task != current)) {
-                        /*
-                         * Flush earlier buffer, which is either from a
-                         * different thread, or when we got a new prefix.
-                         */
-                        log_store(facility, cont_level, NULL, 0, cont_buf, cont_len);
-                        cont_len = 0;
-                }
-
-                if (!cont_len) {
-                        cont_level = level;
-                        cont_task = current;
-                }
+                /*
+                 * Flush the conflicting buffer. An earlier newline was missing,
+                 * or another task also prints continuation lines.
+                 */
+                if (cont.len && (prefix || cont.owner != current))
+                        cont_flush();
 
-                /* buffer or append to earlier buffer from the same thread */
-                if (cont_len + text_len > sizeof(cont_buf))
-                        text_len = sizeof(cont_buf) - cont_len;
-                memcpy(cont_buf + cont_len, text, text_len);
-                cont_len += text_len;
+                /* buffer line if possible, otherwise store it right away */
+                if (!cont_add(facility, level, text, text_len))
+                        log_store(facility, level, LOG_DEFAULT, 0,
+                                  dict, dictlen, text, text_len);
         } else {
-                if (cont_len && cont_task == current) {
-                        if (prefix) {
-                                /*
-                                 * New prefix from the same thread; flush. We
-                                 * either got no earlier newline, or we race
-                                 * with an interrupt.
-                                 */
-                                log_store(facility, cont_level,
-                                          NULL, 0, cont_buf, cont_len);
-                                cont_len = 0;
-                        }
+                bool stored = false;
 
-                        /* append to the earlier buffer and flush */
-                        if (cont_len + text_len > sizeof(cont_buf))
-                                text_len = sizeof(cont_buf) - cont_len;
-                        memcpy(cont_buf + cont_len, text, text_len);
-                        cont_len += text_len;
-                        log_store(facility, cont_level,
-                                  NULL, 0, cont_buf, cont_len);
-                        cont_len = 0;
-                        cont_task = NULL;
-                        printed_len = cont_len;
-                } else {
-                        /* ordinary single and terminated line */
-                        log_store(facility, level,
-                                  dict, dictlen, text, text_len);
-                        printed_len = text_len;
+                /*
+                 * If an earlier newline was missing and it was the same task,
+                 * either merge it with the current buffer and flush, or if
+                 * there was a race with interrupts (prefix == true) then just
+                 * flush it out and store this line separately.
+                 */
+                if (cont.len && cont.owner == current) {
+                        if (!prefix)
+                                stored = cont_add(facility, level, text, text_len);
+                        cont_flush();
                 }
+
+                if (!stored)
+                        log_store(facility, level, LOG_DEFAULT, 0,
+                                  dict, dictlen, text, text_len);
         }
+        printed_len += text_len;
 
         /*
          * Try to acquire and then immediately release the console semaphore.
@@ -1486,11 +1598,18 @@ EXPORT_SYMBOL(printk);
 #else
 
 #define LOG_LINE_MAX 0
+static struct cont {
+        size_t len;
+        size_t cons;
+        u8 level;
+        bool flushed:1;
+} cont;
 static struct log *log_from_idx(u32 idx) { return NULL; }
 static u32 log_next(u32 idx) { return 0; }
 static void call_console_drivers(int level, const char *text, size_t len) {}
 static size_t msg_print_text(const struct log *msg, bool syslog,
                              char *buf, size_t size) { return 0; }
+static size_t cont_print_text(char *text, size_t size) { return 0; }
 
 #endif /* CONFIG_PRINTK */
 
@@ -1782,6 +1901,7 @@ static u32 console_idx;
  */
 void console_unlock(void)
 {
+        static char text[LOG_LINE_MAX];
         static u64 seen_seq;
         unsigned long flags;
         bool wake_klogd = false;
@@ -1794,10 +1914,23 @@ void console_unlock(void)
 
         console_may_schedule = 0;
 
+        /* flush buffered message fragment immediately to console */
+        raw_spin_lock_irqsave(&logbuf_lock, flags);
+        if (cont.len && (cont.cons < cont.len || cont.flushed)) {
+                size_t len;
+
+                len = cont_print_text(text, sizeof(text));
+                raw_spin_unlock(&logbuf_lock);
+                stop_critical_timings();
+                call_console_drivers(cont.level, text, len);
+                start_critical_timings();
+                local_irq_restore(flags);
+        } else
+                raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
 again:
         for (;;) {
                 struct log *msg;
-                static char text[LOG_LINE_MAX];
                 size_t len;
                 int level;
 
@@ -1812,13 +1945,22 @@ again:
                         console_seq = log_first_seq;
                         console_idx = log_first_idx;
                 }
-
+skip:
                 if (console_seq == log_next_seq)
                         break;
 
                 msg = log_from_idx(console_idx);
-                level = msg->level & 7;
+                if (msg->flags & LOG_NOCONS) {
+                        /*
+                         * Skip record we have buffered and already printed
+                         * directly to the console when we received it.
+                         */
+                        console_idx = log_next(console_idx);
+                        console_seq++;
+                        goto skip;
+                }
 
+                level = msg->level;
                 len = msg_print_text(msg, false, text, sizeof(text));
 
                 console_idx = log_next(console_idx);
@@ -2300,48 +2442,210 @@ module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
  * kmsg_dump - dump kernel log to kernel message dumpers.
  * @reason: the reason (oops, panic etc) for dumping
  *
- * Iterate through each of the dump devices and call the oops/panic
- * callbacks with the log buffer.
+ * Call each of the registered dumper's dump() callback, which can
+ * retrieve the kmsg records with kmsg_dump_get_line() or
+ * kmsg_dump_get_buffer().
  */
 void kmsg_dump(enum kmsg_dump_reason reason)
 {
-        u64 idx;
         struct kmsg_dumper *dumper;
-        const char *s1, *s2;
-        unsigned long l1, l2;
         unsigned long flags;
 
         if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
                 return;
 
-        /* Theoretically, the log could move on after we do this, but
-           there's not a lot we can do about that. The new messages
-           will overwrite the start of what we dump. */
+        rcu_read_lock();
+        list_for_each_entry_rcu(dumper, &dump_list, list) {
+                if (dumper->max_reason && reason > dumper->max_reason)
+                        continue;
+
+                /* initialize iterator with data about the stored records */
+                dumper->active = true;
+
+                raw_spin_lock_irqsave(&logbuf_lock, flags);
+                dumper->cur_seq = clear_seq;
+                dumper->cur_idx = clear_idx;
+                dumper->next_seq = log_next_seq;
+                dumper->next_idx = log_next_idx;
+                raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
+                /* invoke dumper which will iterate over records */
+                dumper->dump(dumper, reason);
+
+                /* reset iterator */
+                dumper->active = false;
+        }
+        rcu_read_unlock();
+}
+
+/**
+ * kmsg_dump_get_line - retrieve one kmsg log line
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @line: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the beginning of the kmsg buffer, with the oldest kmsg
+ * record, and copy one record into the provided buffer.
+ *
+ * Consecutive calls will return the next available record moving
+ * towards the end of the buffer with the youngest messages.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog,
+                        char *line, size_t size, size_t *len)
+{
+        unsigned long flags;
+        struct log *msg;
+        size_t l = 0;
+        bool ret = false;
+
+        if (!dumper->active)
+                goto out;
 
         raw_spin_lock_irqsave(&logbuf_lock, flags);
-        if (syslog_seq < log_first_seq)
-                idx = syslog_idx;
-        else
-                idx = log_first_idx;
+        if (dumper->cur_seq < log_first_seq) {
+                /* messages are gone, move to first available one */
+                dumper->cur_seq = log_first_seq;
+                dumper->cur_idx = log_first_idx;
+        }
 
-        if (idx > log_next_idx) {
-                s1 = log_buf;
-                l1 = log_next_idx;
+        /* last entry */
+        if (dumper->cur_seq >= log_next_seq) {
+                raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+                goto out;
+        }
 
-                s2 = log_buf + idx;
-                l2 = log_buf_len - idx;
-        } else {
-                s1 = "";
-                l1 = 0;
+        msg = log_from_idx(dumper->cur_idx);
+        l = msg_print_text(msg, syslog,
+                              line, size);
 
-                s2 = log_buf + idx;
-                l2 = log_next_idx - idx;
+        dumper->cur_idx = log_next(dumper->cur_idx);
+        dumper->cur_seq++;
+        ret = true;
+        raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+        if (len)
+                *len = l;
+        return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_line);
+
+/**
+ * kmsg_dump_get_buffer - copy kmsg log lines
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @buf: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the end of the kmsg buffer and fill the provided buffer
+ * with as many of the the *youngest* kmsg records that fit into it.
+ * If the buffer is large enough, all available kmsg records will be
+ * copied with a single call.
+ *
+ * Consecutive calls will fill the buffer with the next block of
+ * available older records, not including the earlier retrieved ones.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
+                          char *buf, size_t size, size_t *len)
+{
+        unsigned long flags;
+        u64 seq;
+        u32 idx;
+        u64 next_seq;
+        u32 next_idx;
+        size_t l = 0;
+        bool ret = false;
+
+        if (!dumper->active)
+                goto out;
+
+        raw_spin_lock_irqsave(&logbuf_lock, flags);
+        if (dumper->cur_seq < log_first_seq) {
+                /* messages are gone, move to first available one */
+                dumper->cur_seq = log_first_seq;
+                dumper->cur_idx = log_first_idx;
         }
+
+        /* last entry */
+        if (dumper->cur_seq >= dumper->next_seq) {
+                raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+                goto out;
+        }
+
+        /* calculate length of entire buffer */
+        seq = dumper->cur_seq;
+        idx = dumper->cur_idx;
+        while (seq < dumper->next_seq) {
+                struct log *msg = log_from_idx(idx);
+
+                l += msg_print_text(msg, true, NULL, 0);
+                idx = log_next(idx);
+                seq++;
+        }
+
+        /* move first record forward until length fits into the buffer */
+        seq = dumper->cur_seq;
+        idx = dumper->cur_idx;
+        while (l > size && seq < dumper->next_seq) {
+                struct log *msg = log_from_idx(idx);
+
+                l -= msg_print_text(msg, true, NULL, 0);
+                idx = log_next(idx);
+                seq++;
+        }
+
+        /* last message in next interation */
+        next_seq = seq;
+        next_idx = idx;
+
+        l = 0;
+        while (seq < dumper->next_seq) {
+                struct log *msg = log_from_idx(idx);
+
+                l += msg_print_text(msg, syslog,
+                                    buf + l, size - l);
+
+                idx = log_next(idx);
+                seq++;
+        }
+
+        dumper->next_seq = next_seq;
+        dumper->next_idx = next_idx;
+        ret = true;
         raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+        if (len)
+                *len = l;
+        return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(dumper, &dump_list, list)
-                dumper->dump(dumper, reason, s1, l1, s2, l2);
-        rcu_read_unlock();
+/**
+ * kmsg_dump_rewind - reset the interator
+ * @dumper: registered kmsg dumper
+ *
+ * Reset the dumper's iterator so that kmsg_dump_get_line() and
+ * kmsg_dump_get_buffer() can be called again and used multiple
+ * times within the same dumper.dump() callback.
+ */
+void kmsg_dump_rewind(struct kmsg_dumper *dumper)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&logbuf_lock, flags);
+        dumper->cur_seq = clear_seq;
+        dumper->cur_idx = clear_idx;
+        dumper->next_seq = log_next_seq;
+        dumper->next_idx = log_next_idx;
+        raw_spin_unlock_irqrestore(&logbuf_lock, flags);
 }
+EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
 #endif
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0da7b88d92d0..38ecdda3f55f 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1397,6 +1397,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
         rdp->qlen_lazy += rsp->qlen_lazy;
         rdp->qlen += rsp->qlen;
         rdp->n_cbs_adopted += rsp->qlen;
+        if (rsp->qlen_lazy != rsp->qlen)
+                rcu_idle_count_callbacks_posted();
         rsp->qlen_lazy = 0;
         rsp->qlen = 0;
 
@@ -1528,7 +1530,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 {
         unsigned long flags;
         struct rcu_head *next, *list, **tail;
-        int bl, count, count_lazy;
+        int bl, count, count_lazy, i;
 
         /* If no callbacks are ready, just return.*/
         if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
@@ -1551,9 +1553,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
         rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
         *rdp->nxttail[RCU_DONE_TAIL] = NULL;
         tail = rdp->nxttail[RCU_DONE_TAIL];
-        for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
-                if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
-                        rdp->nxttail[count] = &rdp->nxtlist;
+        for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
+                if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
+                        rdp->nxttail[i] = &rdp->nxtlist;
         local_irq_restore(flags);
 
         /* Invoke callbacks. */
@@ -1581,9 +1583,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
         if (list != NULL) {
                 *tail = rdp->nxtlist;
                 rdp->nxtlist = list;
-                for (count = 0; count < RCU_NEXT_SIZE; count++)
-                        if (&rdp->nxtlist == rdp->nxttail[count])
-                                rdp->nxttail[count] = tail;
+                for (i = 0; i < RCU_NEXT_SIZE; i++)
+                        if (&rdp->nxtlist == rdp->nxttail[i])
+                                rdp->nxttail[i] = tail;
                         else
                                 break;
         }
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 7f5d138dedf5..ea056495783e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,6 +84,20 @@ struct rcu_dynticks {
                                     /* Process level is worth LLONG_MAX/2. */
         int dynticks_nmi_nesting;   /* Track NMI nesting level. */
         atomic_t dynticks;          /* Even value for idle, else odd. */
+#ifdef CONFIG_RCU_FAST_NO_HZ
+        int dyntick_drain;          /* Prepare-for-idle state variable. */
+        unsigned long dyntick_holdoff;
+                                    /* No retries for the jiffy of failure. */
+        struct timer_list idle_gp_timer;
+                                    /* Wake up CPU sleeping with callbacks. */
+        unsigned long idle_gp_timer_expires;
+                                    /* When to wake up CPU (for repost). */
+        bool idle_first_pass;       /* First pass of attempt to go idle? */
+        unsigned long nonlazy_posted;
+                                    /* # times non-lazy CBs posted to CPU. */
+        unsigned long nonlazy_posted_snap;
+                                    /* idle-period nonlazy_posted snapshot. */
+#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 };
 
 /* RCU's kthread states for tracing. */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 2411000d9869..5271a020887e 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1886,8 +1886,9 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
-int rcu_needs_cpu(int cpu)
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
 {
+        *delta_jiffies = ULONG_MAX;
         return rcu_cpu_has_callbacks(cpu);
 }
 
@@ -1962,41 +1963,6 @@ static void rcu_idle_count_callbacks_posted(void)
 #define RCU_IDLE_GP_DELAY 6             /* Roughly one grace period. */
 #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
 
-/* Loop counter for rcu_prepare_for_idle(). */
-static DEFINE_PER_CPU(int, rcu_dyntick_drain);
-/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
-static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
-/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
-static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
-/* Enable special processing on first attempt to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
-/* Running count of non-lazy callbacks posted, never decremented. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
-/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
-
-/*
- * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
- * callbacks on this CPU, (2) this CPU has not yet attempted to enter
- * dyntick-idle mode, or (3) this CPU is in the process of attempting to
- * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
- * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
- * it is better to incur scheduling-clock interrupts than to spin
- * continuously for the same time duration!
- */
-int rcu_needs_cpu(int cpu)
-{
-        /* Flag a new idle sojourn to the idle-entry state machine. */
-        per_cpu(rcu_idle_first_pass, cpu) = 1;
-        /* If no callbacks, RCU doesn't need the CPU. */
-        if (!rcu_cpu_has_callbacks(cpu))
-                return 0;
-        /* Otherwise, RCU needs the CPU only if it recently tried and failed. */
-        return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
-}
-
 /*
  * Does the specified flavor of RCU have non-lazy callbacks pending on
  * the specified CPU?  Both RCU flavor and CPU are specified by the
@@ -2040,6 +2006,47 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
 }
 
 /*
+ * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
+ * callbacks on this CPU, (2) this CPU has not yet attempted to enter
+ * dyntick-idle mode, or (3) this CPU is in the process of attempting to
+ * enter dyntick-idle mode.  Otherwise, if we have recently tried and failed
+ * to enter dyntick-idle mode, we refuse to try to enter it.  After all,
+ * it is better to incur scheduling-clock interrupts than to spin
+ * continuously for the same time duration!
+ *
+ * The delta_jiffies argument is used to store the time when RCU is
+ * going to need the CPU again if it still has callbacks.  The reason
+ * for this is that rcu_prepare_for_idle() might need to post a timer,
+ * but if so, it will do so after tick_nohz_stop_sched_tick() has set
+ * the wakeup time for this CPU.  This means that RCU's timer can be
+ * delayed until the wakeup time, which defeats the purpose of posting
+ * a timer.
+ */
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+{
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+        /* Flag a new idle sojourn to the idle-entry state machine. */
+        rdtp->idle_first_pass = 1;
+        /* If no callbacks, RCU doesn't need the CPU. */
+        if (!rcu_cpu_has_callbacks(cpu)) {
+                *delta_jiffies = ULONG_MAX;
+                return 0;
+        }
+        if (rdtp->dyntick_holdoff == jiffies) {
+                /* RCU recently tried and failed, so don't try again. */
+                *delta_jiffies = 1;
+                return 1;
+        }
+        /* Set up for the possibility that RCU will post a timer. */
+        if (rcu_cpu_has_nonlazy_callbacks(cpu))
+                *delta_jiffies = RCU_IDLE_GP_DELAY;
+        else
+                *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
+        return 0;
+}
+
+/*
  * Handler for smp_call_function_single().  The only point of this
  * handler is to wake the CPU up, so the handler does only tracing.
  */
@@ -2075,21 +2082,24 @@ static void rcu_idle_gp_timer_func(unsigned long cpu_in)
  */
 static void rcu_prepare_for_idle_init(int cpu)
 {
-        per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
-        setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
-                    rcu_idle_gp_timer_func, cpu);
-        per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
-        per_cpu(rcu_idle_first_pass, cpu) = 1;
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+        rdtp->dyntick_holdoff = jiffies - 1;
+        setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
+        rdtp->idle_gp_timer_expires = jiffies - 1;
+        rdtp->idle_first_pass = 1;
 }
 
 /*
  * Clean up for exit from idle.  Because we are exiting from idle, there
- * is no longer any point to rcu_idle_gp_timer, so cancel it.  This will
+ * is no longer any point to ->idle_gp_timer, so cancel it.  This will
  * do nothing if this timer is not active, so just cancel it unconditionally.
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-        del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+        del_timer(&rdtp->idle_gp_timer);
         trace_rcu_prep_idle("Cleanup after idle");
 }
 
@@ -2108,42 +2118,41 @@ static void rcu_cleanup_after_idle(int cpu)
  * Because it is not legal to invoke rcu_process_callbacks() with irqs
  * disabled, we do one pass of force_quiescent_state(), then do a
  * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
- * later.  The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ * later.  The ->dyntick_drain field controls the sequencing.
  *
  * The caller must have disabled interrupts.
  */
 static void rcu_prepare_for_idle(int cpu)
 {
         struct timer_list *tp;
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
         /*
          * If this is an idle re-entry, for example, due to use of
          * RCU_NONIDLE() or the new idle-loop tracing API within the idle
          * loop, then don't take any state-machine actions, unless the
          * momentary exit from idle queued additional non-lazy callbacks.
-         * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+         * Instead, repost the ->idle_gp_timer if this CPU has callbacks
          * pending.
          */
-        if (!per_cpu(rcu_idle_first_pass, cpu) &&
-            (per_cpu(rcu_nonlazy_posted, cpu) ==
-             per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+        if (!rdtp->idle_first_pass &&
+            (rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
                 if (rcu_cpu_has_callbacks(cpu)) {
-                        tp = &per_cpu(rcu_idle_gp_timer, cpu);
-                        mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+                        tp = &rdtp->idle_gp_timer;
+                        mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
                 }
                 return;
         }
-        per_cpu(rcu_idle_first_pass, cpu) = 0;
-        per_cpu(rcu_nonlazy_posted_snap, cpu) =
-                per_cpu(rcu_nonlazy_posted, cpu) - 1;
+        rdtp->idle_first_pass = 0;
+        rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
 
         /*
          * If there are no callbacks on this CPU, enter dyntick-idle mode.
          * Also reset state to avoid prejudicing later attempts.
          */
         if (!rcu_cpu_has_callbacks(cpu)) {
-                per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
-                per_cpu(rcu_dyntick_drain, cpu) = 0;
+                rdtp->dyntick_holdoff = jiffies - 1;
+                rdtp->dyntick_drain = 0;
                 trace_rcu_prep_idle("No callbacks");
                 return;
         }
@@ -2152,36 +2161,37 @@ static void rcu_prepare_for_idle(int cpu)
          * If in holdoff mode, just return.  We will presumably have
          * refrained from disabling the scheduling-clock tick.
          */
-        if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
+        if (rdtp->dyntick_holdoff == jiffies) {
                 trace_rcu_prep_idle("In holdoff");
                 return;
         }
 
-        /* Check and update the rcu_dyntick_drain sequencing. */
-        if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+        /* Check and update the ->dyntick_drain sequencing. */
+        if (rdtp->dyntick_drain <= 0) {
                 /* First time through, initialize the counter. */
-                per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
-        } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
+                rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
+        } else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
                    !rcu_pending(cpu) &&
                    !local_softirq_pending()) {
                 /* Can we go dyntick-idle despite still having callbacks? */
-                trace_rcu_prep_idle("Dyntick with callbacks");
-                per_cpu(rcu_dyntick_drain, cpu) = 0;
-                per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
-                if (rcu_cpu_has_nonlazy_callbacks(cpu))
-                        per_cpu(rcu_idle_gp_timer_expires, cpu) =
+                rdtp->dyntick_drain = 0;
+                rdtp->dyntick_holdoff = jiffies;
+                if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
+                        trace_rcu_prep_idle("Dyntick with callbacks");
+                        rdtp->idle_gp_timer_expires =
                                            jiffies + RCU_IDLE_GP_DELAY;
-                else
-                        per_cpu(rcu_idle_gp_timer_expires, cpu) =
+                } else {
+                        rdtp->idle_gp_timer_expires =
                                            jiffies + RCU_IDLE_LAZY_GP_DELAY;
-                tp = &per_cpu(rcu_idle_gp_timer, cpu);
-                mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
-                per_cpu(rcu_nonlazy_posted_snap, cpu) =
-                        per_cpu(rcu_nonlazy_posted, cpu);
+                        trace_rcu_prep_idle("Dyntick with lazy callbacks");
+                }
+                tp = &rdtp->idle_gp_timer;
+                mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
+                rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
                 return; /* Nothing more to do immediately. */
-        } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+        } else if (--(rdtp->dyntick_drain) <= 0) {
                 /* We have hit the limit, so time to give up. */
-                per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+                rdtp->dyntick_holdoff = jiffies;
                 trace_rcu_prep_idle("Begin holdoff");
                 invoke_rcu_core();  /* Force the CPU out of dyntick-idle. */
                 return;
@@ -2227,7 +2237,7 @@ static void rcu_prepare_for_idle(int cpu)
  */
 static void rcu_idle_count_callbacks_posted(void)
 {
-        __this_cpu_add(rcu_nonlazy_posted, 1);
+        __this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
 }
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
@@ -2238,11 +2248,12 @@ static void rcu_idle_count_callbacks_posted(void)
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
-        struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
+        struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+        struct timer_list *tltp = &rdtp->idle_gp_timer;
 
         sprintf(cp, "drain=%d %c timer=%lu",
-                per_cpu(rcu_dyntick_drain, cpu),
-                per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
+                rdtp->dyntick_drain,
+                rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
                 timer_pending(tltp) ? tltp->expires - jiffies : -1);
 }
 
diff --git a/kernel/relay.c b/kernel/relay.c
index ab56a1764d4d..e8cd2027abbd 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in,
         struct splice_pipe_desc spd = {
                 .pages = pages,
                 .nr_pages = 0,
+                .nr_pages_max = PIPE_DEF_BUFFERS,
                 .partial = partial,
                 .flags = flags,
                 .ops = &relay_pipe_buf_ops,
@@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in,
                 ret += padding;
 
 out:
-        splice_shrink_spd(pipe, &spd);
-        return ret;
+        splice_shrink_spd(&spd);
+        return ret;
 }
 
 static ssize_t relay_file_splice_read(struct file *in,
diff --git a/kernel/sys.c b/kernel/sys.c
index f0ec44dcd415..e0c8ffc50d7f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2127,9 +2127,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                                 else
                                         return -EINVAL;
                                 break;
-                case PR_GET_TID_ADDRESS:
-                        error = prctl_get_tid_address(me, (int __user **)arg2);
-                        break;
                         default:
                                 return -EINVAL;
                         }
@@ -2147,6 +2144,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
                 case PR_SET_MM:
                         error = prctl_set_mm(arg2, arg3, arg4, arg5);
                         break;
+                case PR_GET_TID_ADDRESS:
+                        error = prctl_get_tid_address(me, (int __user **)arg2);
+                        break;
                 case PR_SET_CHILD_SUBREAPER:
                         me->signal->is_child_subreaper = !!arg2;
                         error = 0;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index da70c6db496c..869997833928 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -274,6 +274,7 @@ EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 {
         unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
+        unsigned long rcu_delta_jiffies;
         ktime_t last_update, expires, now;
         struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
         u64 time_delta;
@@ -322,7 +323,7 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
                 time_delta = timekeeping_max_deferment();
         } while (read_seqretry(&xtime_lock, seq));
 
-        if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+        if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
             arch_needs_cpu(cpu)) {
                 next_jiffies = last_jiffies + 1;
                 delta_jiffies = 1;
@@ -330,6 +331,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
                 /* Get the next timer wheel timer */
                 next_jiffies = get_next_timer_interrupt(last_jiffies);
                 delta_jiffies = next_jiffies - last_jiffies;
+                if (rcu_delta_jiffies < delta_jiffies) {
+                        next_jiffies = last_jiffies + rcu_delta_jiffies;
+                        delta_jiffies = rcu_delta_jiffies;
+                }
         }
         /*
          * Do not stop the tick, if we are only one off
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68032c6177db..a7fa0702be1c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
 void tracing_off(void)
 {
         if (global_trace.buffer)
-                ring_buffer_record_on(global_trace.buffer);
+                ring_buffer_record_off(global_trace.buffer);
         /*
          * This flag is only looked at when buffers haven't been
          * allocated yet. We don't really care about the race
@@ -3609,6 +3609,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                 .pages          = pages_def,
                 .partial        = partial_def,
                 .nr_pages       = 0, /* This gets updated below. */
+                .nr_pages_max   = PIPE_DEF_BUFFERS,
                 .flags          = flags,
                 .ops            = &tracing_pipe_buf_ops,
                 .spd_release    = tracing_spd_release_pipe,
@@ -3680,7 +3681,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
         ret = splice_to_pipe(pipe, &spd);
 out:
-        splice_shrink_spd(pipe, &spd);
+        splice_shrink_spd(&spd);
         return ret;
 
 out_err:
@@ -4231,6 +4232,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
         struct splice_pipe_desc spd = {
                 .pages          = pages_def,
                 .partial        = partial_def,
+                .nr_pages_max   = PIPE_DEF_BUFFERS,
                 .flags          = flags,
                 .ops            = &buffer_pipe_buf_ops,
                 .spd_release    = buffer_spd_release,
@@ -4318,7 +4320,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
         }
 
         ret = splice_to_pipe(pipe, &spd);
-        splice_shrink_spd(pipe, &spd);
+        splice_shrink_spd(&spd);
 out:
         return ret;
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index e5e1d85b8c7c..4b1dfba70f7c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -372,6 +372,13 @@ static int watchdog(void *unused)
 
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
 static int watchdog_nmi_enable(int cpu)
 {
         struct perf_event_attr *wd_attr;
@@ -390,11 +397,21 @@ static int watchdog_nmi_enable(int cpu)
 
         /* Try to register using hardware perf events */
         event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+        /* save cpu0 error for future comparision */
+        if (cpu == 0 && IS_ERR(event))
+                cpu0_err = PTR_ERR(event);
+
         if (!IS_ERR(event)) {
-                pr_info("enabled, takes one hw-pmu counter.\n");
+                /* only print for cpu0 or different than cpu0 */
+                if (cpu == 0 || cpu0_err)
+                        pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
                 goto out_save;
         }
 
+        /* skip displaying the same error again */
+        if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+                return PTR_ERR(event);
 
         /* vary the KERN level based on the returned errno */
         if (PTR_ERR(event) == -EOPNOTSUPP)