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

Conflicts:
	drivers/net/ethernet/rocker/rocker.c

The rocker commit was two overlapping changes, one to rename
the ->vport member to ->pport, and another making the bitmask
expression use '1ULL' instead of plain '1'.

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

16 files changed, 247 insertions, 163 deletions

diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 07ce18c..0874e2e 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -604,7 +604,7 @@ return_normal:
 		   online_cpus)
 		cpu_relax();
 	if (!time_left)
-		pr_crit("KGDB: Timed out waiting for secondary CPUs.\n");
+		pr_crit("Timed out waiting for secondary CPUs.\n");
 
 	/*
 	 * At this point the primary processor is completely
@@ -696,6 +696,14 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
 
 	if (arch_kgdb_ops.enable_nmi)
 		arch_kgdb_ops.enable_nmi(0);
+	/*
+	 * Avoid entering the debugger if we were triggered due to an oops
+	 * but panic_timeout indicates the system should automatically
+	 * reboot on panic. We don't want to get stuck waiting for input
+	 * on such systems, especially if its "just" an oops.
+	 */
+	if (signo != SIGTRAP && panic_timeout)
+		return 1;
 
 	memset(ks, 0, sizeof(struct kgdb_state));
 	ks->cpu			= raw_smp_processor_id();
@@ -828,6 +836,15 @@ static int kgdb_panic_event(struct notifier_block *self,
 			    unsigned long val,
 			    void *data)
 {
+	/*
+	 * Avoid entering the debugger if we were triggered due to a panic
+	 * We don't want to get stuck waiting for input from user in such case.
+	 * panic_timeout indicates the system should automatically
+	 * reboot on panic.
+	 */
+	if (panic_timeout)
+		return NOTIFY_DONE;
+
 	if (dbg_kdb_mode)
 		kdb_printf("PANIC: %s\n", (char *)data);
 	kgdb_breakpoint();
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 7c70812..fc1ef73 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -439,7 +439,7 @@ poll_again:
  *	substituted for %d, %x or %o in the prompt.
  */
 
-char *kdb_getstr(char *buffer, size_t bufsize, char *prompt)
+char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt)
 {
 	if (prompt && kdb_prompt_str != prompt)
 		strncpy(kdb_prompt_str, prompt, CMD_BUFLEN);
@@ -548,7 +548,7 @@ static int kdb_search_string(char *searched, char *searchfor)
 	return 0;
 }
 
-int vkdb_printf(const char *fmt, va_list ap)
+int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 {
 	int diag;
 	int linecount;
@@ -680,6 +680,12 @@ int vkdb_printf(const char *fmt, va_list ap)
 			size_avail = sizeof(kdb_buffer) - len;
 			goto kdb_print_out;
 		}
+		if (kdb_grepping_flag >= KDB_GREPPING_FLAG_SEARCH)
+			/*
+			 * This was a interactive search (using '/' at more
+			 * prompt) and it has completed. Clear the flag.
+			 */
+			kdb_grepping_flag = 0;
 		/*
 		 * at this point the string is a full line and
 		 * should be printed, up to the null.
@@ -691,19 +697,20 @@ kdb_printit:
 	 * Write to all consoles.
 	 */
 	retlen = strlen(kdb_buffer);
+	cp = (char *) printk_skip_level(kdb_buffer);
 	if (!dbg_kdb_mode && kgdb_connected) {
-		gdbstub_msg_write(kdb_buffer, retlen);
+		gdbstub_msg_write(cp, retlen - (cp - kdb_buffer));
 	} else {
 		if (dbg_io_ops && !dbg_io_ops->is_console) {
-			len = retlen;
-			cp = kdb_buffer;
+			len = retlen - (cp - kdb_buffer);
+			cp2 = cp;
 			while (len--) {
-				dbg_io_ops->write_char(*cp);
-				cp++;
+				dbg_io_ops->write_char(*cp2);
+				cp2++;
 			}
 		}
 		while (c) {
-			c->write(c, kdb_buffer, retlen);
+			c->write(c, cp, retlen - (cp - kdb_buffer));
 			touch_nmi_watchdog();
 			c = c->next;
 		}
@@ -711,7 +718,10 @@ kdb_printit:
 	if (logging) {
 		saved_loglevel = console_loglevel;
 		console_loglevel = CONSOLE_LOGLEVEL_SILENT;
-		printk(KERN_INFO "%s", kdb_buffer);
+		if (printk_get_level(kdb_buffer) || src == KDB_MSGSRC_PRINTK)
+			printk("%s", kdb_buffer);
+		else
+			pr_info("%s", kdb_buffer);
 	}
 
 	if (KDB_STATE(PAGER)) {
@@ -794,11 +804,23 @@ kdb_printit:
 			kdb_nextline = linecount - 1;
 			kdb_printf("\r");
 			suspend_grep = 1; /* for this recursion */
+		} else if (buf1[0] == '/' && !kdb_grepping_flag) {
+			kdb_printf("\r");
+			kdb_getstr(kdb_grep_string, KDB_GREP_STRLEN,
+				   kdbgetenv("SEARCHPROMPT") ?: "search> ");
+			*strchrnul(kdb_grep_string, '\n') = '\0';
+			kdb_grepping_flag += KDB_GREPPING_FLAG_SEARCH;
+			suspend_grep = 1; /* for this recursion */
 		} else if (buf1[0] && buf1[0] != '\n') {
 			/* user hit something other than enter */
 			suspend_grep = 1; /* for this recursion */
-			kdb_printf("\nOnly 'q' or 'Q' are processed at more "
-				   "prompt, input ignored\n");
+			if (buf1[0] != '/')
+				kdb_printf(
+				    "\nOnly 'q', 'Q' or '/' are processed at "
+				    "more prompt, input ignored\n");
+			else
+				kdb_printf("\n'/' cannot be used during | "
+					   "grep filtering, input ignored\n");
 		} else if (kdb_grepping_flag) {
 			/* user hit enter */
 			suspend_grep = 1; /* for this recursion */
@@ -844,7 +866,7 @@ int kdb_printf(const char *fmt, ...)
 	int r;
 
 	va_start(ap, fmt);
-	r = vkdb_printf(fmt, ap);
+	r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap);
 	va_end(ap);
 
 	return r;
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 7b40c5f..4121345 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -50,8 +50,7 @@
 static int kdb_cmd_enabled = CONFIG_KDB_DEFAULT_ENABLE;
 module_param_named(cmd_enable, kdb_cmd_enabled, int, 0600);
 
-#define GREP_LEN 256
-char kdb_grep_string[GREP_LEN];
+char kdb_grep_string[KDB_GREP_STRLEN];
 int kdb_grepping_flag;
 EXPORT_SYMBOL(kdb_grepping_flag);
 int kdb_grep_leading;
@@ -870,7 +869,7 @@ static void parse_grep(const char *str)
 	len = strlen(cp);
 	if (!len)
 		return;
-	if (len >= GREP_LEN) {
+	if (len >= KDB_GREP_STRLEN) {
 		kdb_printf("search string too long\n");
 		return;
 	}
@@ -915,13 +914,12 @@ int kdb_parse(const char *cmdstr)
 	char *cp;
 	char *cpp, quoted;
 	kdbtab_t *tp;
-	int i, escaped, ignore_errors = 0, check_grep;
+	int i, escaped, ignore_errors = 0, check_grep = 0;
 
 	/*
 	 * First tokenize the command string.
 	 */
 	cp = (char *)cmdstr;
-	kdb_grepping_flag = check_grep = 0;
 
 	if (KDB_FLAG(CMD_INTERRUPT)) {
 		/* Previous command was interrupted, newline must not
@@ -1247,7 +1245,6 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		kdb_printf("due to NonMaskable Interrupt @ "
 			   kdb_machreg_fmt "\n",
 			   instruction_pointer(regs));
-		kdb_dumpregs(regs);
 		break;
 	case KDB_REASON_SSTEP:
 	case KDB_REASON_BREAK:
@@ -1281,6 +1278,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		 */
 		kdb_nextline = 1;
 		KDB_STATE_CLEAR(SUPPRESS);
+		kdb_grepping_flag = 0;
+		/* ensure the old search does not leak into '/' commands */
+		kdb_grep_string[0] = '\0';
 
 		cmdbuf = cmd_cur;
 		*cmdbuf = '\0';
@@ -2256,7 +2256,7 @@ static int kdb_cpu(int argc, const char **argv)
 	/*
 	 * Validate cpunum
 	 */
-	if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
+	if ((cpunum >= CONFIG_NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
 		return KDB_BADCPUNUM;
 
 	dbg_switch_cpu = cpunum;
@@ -2583,7 +2583,7 @@ static int kdb_summary(int argc, const char **argv)
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	kdb_printf("\nMemTotal:       %8lu kB\nMemFree:        %8lu kB\n"
 		   "Buffers:        %8lu kB\n",
-		   val.totalram, val.freeram, val.bufferram);
+		   K(val.totalram), K(val.freeram), K(val.bufferram));
 	return 0;
 }
 
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index eaacd16..75014d7 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -196,7 +196,9 @@ extern int kdb_main_loop(kdb_reason_t, kdb_reason_t,
 
 /* Miscellaneous functions and data areas */
 extern int kdb_grepping_flag;
+#define KDB_GREPPING_FLAG_SEARCH 0x8000
 extern char kdb_grep_string[];
+#define KDB_GREP_STRLEN 256
 extern int kdb_grep_leading;
 extern int kdb_grep_trailing;
 extern char *kdb_cmds[];
@@ -209,7 +211,7 @@ extern void kdb_ps1(const struct task_struct *p);
 extern void kdb_print_nameval(const char *name, unsigned long val);
 extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
 extern void kdb_meminfo_proc_show(void);
-extern char *kdb_getstr(char *, size_t, char *);
+extern char *kdb_getstr(char *, size_t, const char *);
 extern void kdb_gdb_state_pass(char *buf);
 
 /* Defines for kdb_symbol_print */
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index 52aa7e8..752d648 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -1,33 +1,7 @@
 ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
 
-# if-lt
-# Usage VAR := $(call if-lt, $(a), $(b))
-# Returns 1 if (a < b)
-if-lt = $(shell [ $(1) -lt $(2) ] && echo 1)
-
-ifeq ($(CONFIG_GCOV_FORMAT_3_4),y)
-  cc-ver := 0304
-else ifeq ($(CONFIG_GCOV_FORMAT_4_7),y)
-  cc-ver := 0407
-else
-# Use cc-version if available, otherwise set 0
-#
-# scripts/Kbuild.include, which contains cc-version function, is not included
-# during make clean "make -f scripts/Makefile.clean obj=kernel/gcov"
-# Meaning cc-ver is empty causing if-lt test to fail with
-# "/bin/sh: line 0: [: -lt: unary operator expected" error mesage.
-# This has no affect on the clean phase, but the error message could be
-# confusing/annoying. So this dummy workaround sets cc-ver to zero if cc-version
-# is not available. We can probably move if-lt to Kbuild.include, so it's also
-# not defined during clean or to include Kbuild.include in
-# scripts/Makefile.clean. But the following workaround seems least invasive.
-  cc-ver := $(if $(call cc-version),$(call cc-version),0)
-endif
-
-obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o
-
-ifeq ($(call if-lt, $(cc-ver), 0407),1)
-  obj-$(CONFIG_GCOV_KERNEL) += gcc_3_4.o
-else
-  obj-$(CONFIG_GCOV_KERNEL) += gcc_4_7.o
-endif
+obj-y := base.o fs.o
+obj-$(CONFIG_GCOV_FORMAT_3_4) += gcc_3_4.o
+obj-$(CONFIG_GCOV_FORMAT_4_7) += gcc_4_7.o
+obj-$(CONFIG_GCOV_FORMAT_AUTODETECT) += $(call cc-ifversion, -lt, 0407, \
+							gcc_3_4.o, gcc_4_7.o)
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index ff7f47d..782172f 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -314,12 +314,12 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 	rcu_read_lock();
 	func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
 				      stack_node);
-	rcu_read_unlock();
-
 	if (WARN_ON_ONCE(!func))
-		return;
+		goto unlock;
 
 	klp_arch_set_pc(regs, (unsigned long)func->new_func);
+unlock:
+	rcu_read_unlock();
 }
 
 static int klp_disable_func(struct klp_func *func)
@@ -731,7 +731,7 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 	func->state = KLP_DISABLED;
 
 	return kobject_init_and_add(&func->kobj, &klp_ktype_func,
-				    obj->kobj, func->old_name);
+				    obj->kobj, "%s", func->old_name);
 }
 
 /* parts of the initialization that is done only when the object is loaded */
@@ -807,7 +807,7 @@ static int klp_init_patch(struct klp_patch *patch)
 	patch->state = KLP_DISABLED;
 
 	ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
-				   klp_root_kobj, patch->mod->name);
+				   klp_root_kobj, "%s", patch->mod->name);
 	if (ret)
 		goto unlock;
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 3059bc2f..6357265 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1193,7 +1193,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
 	if (unlikely(ret)) {
-		remove_waiter(lock, &waiter);
+		__set_current_state(TASK_RUNNING);
+		if (rt_mutex_has_waiters(lock))
+			remove_waiter(lock, &waiter);
 		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	}
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c06df7d..01cfd69 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1811,7 +1811,7 @@ int vprintk_default(const char *fmt, va_list args)
 
 #ifdef CONFIG_KGDB_KDB
 	if (unlikely(kdb_trap_printk)) {
-		r = vkdb_printf(fmt, args);
+		r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args);
 		return r;
 	}
 #endif
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0d7bbe3..0a571e9 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -326,6 +326,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	special = t->rcu_read_unlock_special;
 	if (special.b.need_qs) {
 		rcu_preempt_qs();
+		t->rcu_read_unlock_special.b.need_qs = false;
 		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
 			return;
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 8a2e230..eae160d 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -87,8 +87,7 @@ static inline struct autogroup *autogroup_create(void)
 	 * so we don't have to move tasks around upon policy change,
 	 * or flail around trying to allocate bandwidth on the fly.
 	 * A bandwidth exception in __sched_setscheduler() allows
-	 * the policy change to proceed.  Thereafter, task_group()
-	 * returns &root_task_group, so zero bandwidth is required.
+	 * the policy change to proceed.
 	 */
 	free_rt_sched_group(tg);
 	tg->rt_se = root_task_group.rt_se;
@@ -115,9 +114,6 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	if (tg != &root_task_group)
 		return false;
 
-	if (p->sched_class != &fair_sched_class)
-		return false;
-
 	/*
 	 * We can only assume the task group can't go away on us if
 	 * autogroup_move_group() can see us on ->thread_group list.
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 7052d3f..8d0f35d 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -274,7 +274,7 @@ bool try_wait_for_completion(struct completion *x)
 	 * first without taking the lock so we can
 	 * return early in the blocking case.
 	 */
-	if (!ACCESS_ONCE(x->done))
+	if (!READ_ONCE(x->done))
 		return 0;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
@@ -297,6 +297,21 @@ EXPORT_SYMBOL(try_wait_for_completion);
  */
 bool completion_done(struct completion *x)
 {
-	return !!ACCESS_ONCE(x->done);
+	if (!READ_ONCE(x->done))
+		return false;
+
+	/*
+	 * If ->done, we need to wait for complete() to release ->wait.lock
+	 * otherwise we can end up freeing the completion before complete()
+	 * is done referencing it.
+	 *
+	 * The RMB pairs with complete()'s RELEASE of ->wait.lock and orders
+	 * the loads of ->done and ->wait.lock such that we cannot observe
+	 * the lock before complete() acquires it while observing the ->done
+	 * after it's acquired the lock.
+	 */
+	smp_rmb();
+	spin_unlock_wait(&x->wait.lock);
+	return true;
 }
 EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 13049aa..f0f831e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -307,66 +307,6 @@ __read_mostly int scheduler_running;
 int sysctl_sched_rt_runtime = 950000;
 
 /*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	lockdep_assert_held(&p->pi_lock);
-
-	for (;;) {
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
-	__acquires(p->pi_lock)
-	__acquires(rq->lock)
-{
-	struct rq *rq;
-
-	for (;;) {
-		raw_spin_lock_irqsave(&p->pi_lock, *flags);
-		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-			return rq;
-		raw_spin_unlock(&rq->lock);
-		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-
-		while (unlikely(task_on_rq_migrating(p)))
-			cpu_relax();
-	}
-}
-
-static void __task_rq_unlock(struct rq *rq)
-	__releases(rq->lock)
-{
-	raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
-	__releases(rq->lock)
-	__releases(p->pi_lock)
-{
-	raw_spin_unlock(&rq->lock);
-	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-}
-
-/*
  * this_rq_lock - lock this runqueue and disable interrupts.
  */
 static struct rq *this_rq_lock(void)
@@ -2899,7 +2839,7 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
-static void preempt_schedule_common(void)
+static void __sched notrace preempt_schedule_common(void)
 {
 	do {
 		__preempt_count_add(PREEMPT_ACTIVE);
@@ -4418,36 +4358,29 @@ EXPORT_SYMBOL_GPL(yield_to);
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
-void __sched io_schedule(void)
-{
-	struct rq *rq = raw_rq();
-
-	delayacct_blkio_start();
-	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
-	schedule();
-	current->in_iowait = 0;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
 long __sched io_schedule_timeout(long timeout)
 {
-	struct rq *rq = raw_rq();
+	int old_iowait = current->in_iowait;
+	struct rq *rq;
 	long ret;
 
+	current->in_iowait = 1;
+	if (old_iowait)
+		blk_schedule_flush_plug(current);
+	else
+		blk_flush_plug(current);
+
 	delayacct_blkio_start();
+	rq = raw_rq();
 	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
 	ret = schedule_timeout(timeout);
-	current->in_iowait = 0;
+	current->in_iowait = old_iowait;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
+
 	return ret;
 }
+EXPORT_SYMBOL(io_schedule_timeout);
 
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
@@ -7642,6 +7575,12 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {
 	struct task_struct *g, *p;
 
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
 	for_each_process_thread(g, p) {
 		if (rt_task(p) && task_group(p) == tg)
 			return 1;
@@ -7734,6 +7673,17 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
 {
 	int i, err = 0;
 
+	/*
+	 * Disallowing the root group RT runtime is BAD, it would disallow the
+	 * kernel creating (and or operating) RT threads.
+	 */
+	if (tg == &root_task_group && rt_runtime == 0)
+		return -EINVAL;
+
+	/* No period doesn't make any sense. */
+	if (rt_period == 0)
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	err = __rt_schedulable(tg, rt_period, rt_runtime);
@@ -7790,9 +7740,6 @@ static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
 	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
-	if (rt_period == 0)
-		return -EINVAL;
-
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a027799..3fa8fa6 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -511,16 +511,10 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 						     struct sched_dl_entity,
 						     dl_timer);
 	struct task_struct *p = dl_task_of(dl_se);
+	unsigned long flags;
 	struct rq *rq;
-again:
-	rq = task_rq(p);
-	raw_spin_lock(&rq->lock);
 
-	if (rq != task_rq(p)) {
-		/* Task was moved, retrying. */
-		raw_spin_unlock(&rq->lock);
-		goto again;
-	}
+	rq = task_rq_lock(current, &flags);
 
 	/*
 	 * We need to take care of several possible races here:
@@ -541,6 +535,26 @@ again:
 
 	sched_clock_tick();
 	update_rq_clock(rq);
+
+	/*
+	 * If the throttle happened during sched-out; like:
+	 *
+	 *   schedule()
+	 *     deactivate_task()
+	 *       dequeue_task_dl()
+	 *         update_curr_dl()
+	 *           start_dl_timer()
+	 *         __dequeue_task_dl()
+	 *     prev->on_rq = 0;
+	 *
+	 * We can be both throttled and !queued. Replenish the counter
+	 * but do not enqueue -- wait for our wakeup to do that.
+	 */
+	if (!task_on_rq_queued(p)) {
+		replenish_dl_entity(dl_se, dl_se);
+		goto unlock;
+	}
+
 	enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 	if (dl_task(rq->curr))
 		check_preempt_curr_dl(rq, p, 0);
@@ -555,7 +569,7 @@ again:
 		push_dl_task(rq);
 #endif
 unlock:
-	raw_spin_unlock(&rq->lock);
+	task_rq_unlock(rq, current, &flags);
 
 	return HRTIMER_NORESTART;
 }
@@ -898,6 +912,7 @@ static void yield_task_dl(struct rq *rq)
 		rq->curr->dl.dl_yielded = 1;
 		p->dl.runtime = 0;
 	}
+	update_rq_clock(rq);
 	update_curr_dl(rq);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0870db2..dc0f435 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1380,6 +1380,82 @@ static inline void sched_avg_update(struct rq *rq) { }
 
 extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);
 
+/*
+ * __task_rq_lock - lock the rq @p resides on.
+ */
+static inline struct rq *__task_rq_lock(struct task_struct *p)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	for (;;) {
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
+			return rq;
+		raw_spin_unlock(&rq->lock);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
+/*
+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
+ */
+static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(p->pi_lock)
+	__acquires(rq->lock)
+{
+	struct rq *rq;
+
+	for (;;) {
+		raw_spin_lock_irqsave(&p->pi_lock, *flags);
+		rq = task_rq(p);
+		raw_spin_lock(&rq->lock);
+		/*
+		 *	move_queued_task()		task_rq_lock()
+		 *
+		 *	ACQUIRE (rq->lock)
+		 *	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
+		 *	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
+		 *	[S] ->cpu = new_cpu		[L] task_rq()
+		 *					[L] ->on_rq
+		 *	RELEASE (rq->lock)
+		 *
+		 * If we observe the old cpu in task_rq_lock, the acquire of
+		 * the old rq->lock will fully serialize against the stores.
+		 *
+		 * If we observe the new cpu in task_rq_lock, the acquire will
+		 * pair with the WMB to ensure we must then also see migrating.
+		 */
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
+			return rq;
+		raw_spin_unlock(&rq->lock);
+		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
+	}
+}
+
+static inline void __task_rq_unlock(struct rq *rq)
+	__releases(rq->lock)
+{
+	raw_spin_unlock(&rq->lock);
+}
+
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
+	__releases(rq->lock)
+	__releases(p->pi_lock)
+{
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
+}
+
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PREEMPT
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ea9c881..a03d9cd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -97,6 +97,12 @@
 #ifndef MPX_DISABLE_MANAGEMENT
 # define MPX_DISABLE_MANAGEMENT(a)	(-EINVAL)
 #endif
+#ifndef GET_FP_MODE
+# define GET_FP_MODE(a)		(-EINVAL)
+#endif
+#ifndef SET_FP_MODE
+# define SET_FP_MODE(a,b)	(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for
@@ -1102,6 +1108,7 @@ DECLARE_RWSEM(uts_sem);
 /*
  * Work around broken programs that cannot handle "Linux 3.0".
  * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40
+ * And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60.
  */
 static int override_release(char __user *release, size_t len)
 {
@@ -1121,7 +1128,7 @@ static int override_release(char __user *release, size_t len)
 				break;
 			rest++;
 		}
-		v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40;
+		v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60;
 		copy = clamp_t(size_t, len, 1, sizeof(buf));
 		copy = scnprintf(buf, copy, "2.6.%u%s", v, rest);
 		ret = copy_to_user(release, buf, copy + 1);
@@ -2219,6 +2226,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = MPX_DISABLE_MANAGEMENT(me);
 		break;
+	case PR_SET_FP_MODE:
+		error = SET_FP_MODE(me, arg2);
+		break;
+	case PR_GET_FP_MODE:
+		error = GET_FP_MODE(me);
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 4b585e0..0f60b08 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -633,10 +633,14 @@ int ntp_validate_timex(struct timex *txc)
 	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
 		return -EPERM;
 
-	if (txc->modes & ADJ_FREQUENCY) {
-		if (LONG_MIN / PPM_SCALE > txc->freq)
+	/*
+	 * Check for potential multiplication overflows that can
+	 * only happen on 64-bit systems:
+	 */
+	if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
+		if (LLONG_MIN / PPM_SCALE > txc->freq)
 			return -EINVAL;
-		if (LONG_MAX / PPM_SCALE < txc->freq)
+		if (LLONG_MAX / PPM_SCALE < txc->freq)
 			return -EINVAL;
 	}