Merge tag 'v4.20-rc3' into for-4.21/block

Merge in -rc3 to resolve a few conflicts, but also to get a few
important fixes that have gone into mainline since the block
4.21 branch was forked off (most notably the SCSI queue issue,
which is both a conflict AND needed fix).

Signed-off-by: Jens Axboe <axboe@kernel.dk>

12 files changed, 136 insertions, 100 deletions

diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 6ad4a9fcbd6f..7921ae4fca8d 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv)
 				kdb_printf("no process for cpu %ld\n", cpu);
 				return 0;
 			}
-			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
 			kdb_parse(buf);
 			return 0;
 		}
 		kdb_printf("btc: cpu status: ");
 		kdb_parse("cpu\n");
 		for_each_online_cpu(cpu) {
-			sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu));
+			sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu));
 			kdb_parse(buf);
 			touch_nmi_watchdog();
 		}
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index ed5d34925ad0..6a4b41484afe 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
 	int count;
 	int i;
 	int diag, dtab_count;
-	int key;
+	int key, buf_size, ret;
 
 
 	diag = kdbgetintenv("DTABCOUNT", &dtab_count);
@@ -336,9 +336,8 @@ poll_again:
 		else
 			p_tmp = tmpbuffer;
 		len = strlen(p_tmp);
-		count = kallsyms_symbol_complete(p_tmp,
-						 sizeof(tmpbuffer) -
-						 (p_tmp - tmpbuffer));
+		buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer);
+		count = kallsyms_symbol_complete(p_tmp, buf_size);
 		if (tab == 2 && count > 0) {
 			kdb_printf("\n%d symbols are found.", count);
 			if (count > dtab_count) {
@@ -350,9 +349,13 @@ poll_again:
 			}
 			kdb_printf("\n");
 			for (i = 0; i < count; i++) {
-				if (WARN_ON(!kallsyms_symbol_next(p_tmp, i)))
+				ret = kallsyms_symbol_next(p_tmp, i, buf_size);
+				if (WARN_ON(!ret))
 					break;
-				kdb_printf("%s ", p_tmp);
+				if (ret != -E2BIG)
+					kdb_printf("%s ", p_tmp);
+				else
+					kdb_printf("%s... ", p_tmp);
 				*(p_tmp + len) = '\0';
 			}
 			if (i >= dtab_count)
diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
index 118527aa60ea..750497b0003a 100644
--- a/kernel/debug/kdb/kdb_keyboard.c
+++ b/kernel/debug/kdb/kdb_keyboard.c
@@ -173,11 +173,11 @@ int kdb_get_kbd_char(void)
 	case KT_LATIN:
 		if (isprint(keychar))
 			break;		/* printable characters */
-		/* drop through */
+		/* fall through */
 	case KT_SPEC:
 		if (keychar == K_ENTER)
 			break;
-		/* drop through */
+		/* fall through */
 	default:
 		return -1;	/* ignore unprintables */
 	}
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index bb4fe4e1a601..d72b32c66f7d 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1192,7 +1192,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 	if (reason == KDB_REASON_DEBUG) {
 		/* special case below */
 	} else {
-		kdb_printf("\nEntering kdb (current=0x%p, pid %d) ",
+		kdb_printf("\nEntering kdb (current=0x%px, pid %d) ",
 			   kdb_current, kdb_current ? kdb_current->pid : 0);
 #if defined(CONFIG_SMP)
 		kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1208,7 +1208,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		 */
 		switch (db_result) {
 		case KDB_DB_BPT:
-			kdb_printf("\nEntering kdb (0x%p, pid %d) ",
+			kdb_printf("\nEntering kdb (0x%px, pid %d) ",
 				   kdb_current, kdb_current->pid);
 #if defined(CONFIG_SMP)
 			kdb_printf("on processor %d ", raw_smp_processor_id());
@@ -1493,6 +1493,7 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
 	char cbuf[32];
 	char *c = cbuf;
 	int i;
+	int j;
 	unsigned long word;
 
 	memset(cbuf, '\0', sizeof(cbuf));
@@ -1538,25 +1539,9 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr,
 			wc.word = word;
 #define printable_char(c) \
 	({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; })
-			switch (bytesperword) {
-			case 8:
+			for (j = 0; j < bytesperword; j++)
 				*c++ = printable_char(*cp++);
-				*c++ = printable_char(*cp++);
-				*c++ = printable_char(*cp++);
-				*c++ = printable_char(*cp++);
-				addr += 4;
-			case 4:
-				*c++ = printable_char(*cp++);
-				*c++ = printable_char(*cp++);
-				addr += 2;
-			case 2:
-				*c++ = printable_char(*cp++);
-				addr++;
-			case 1:
-				*c++ = printable_char(*cp++);
-				addr++;
-				break;
-			}
+			addr += bytesperword;
 #undef printable_char
 		}
 	}
@@ -2048,7 +2033,7 @@ static int kdb_lsmod(int argc, const char **argv)
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
 
-		kdb_printf("%-20s%8u  0x%p ", mod->name,
+		kdb_printf("%-20s%8u  0x%px ", mod->name,
 			   mod->core_layout.size, (void *)mod);
 #ifdef CONFIG_MODULE_UNLOAD
 		kdb_printf("%4d ", module_refcount(mod));
@@ -2059,7 +2044,7 @@ static int kdb_lsmod(int argc, const char **argv)
 			kdb_printf(" (Loading)");
 		else
 			kdb_printf(" (Live)");
-		kdb_printf(" 0x%p", mod->core_layout.base);
+		kdb_printf(" 0x%px", mod->core_layout.base);
 
 #ifdef CONFIG_MODULE_UNLOAD
 		{
@@ -2341,7 +2326,7 @@ void kdb_ps1(const struct task_struct *p)
 		return;
 
 	cpu = kdb_process_cpu(p);
-	kdb_printf("0x%p %8d %8d  %d %4d   %c  0x%p %c%s\n",
+	kdb_printf("0x%px %8d %8d  %d %4d   %c  0x%px %c%s\n",
 		   (void *)p, p->pid, p->parent->pid,
 		   kdb_task_has_cpu(p), kdb_process_cpu(p),
 		   kdb_task_state_char(p),
@@ -2354,7 +2339,7 @@ void kdb_ps1(const struct task_struct *p)
 		} else {
 			if (KDB_TSK(cpu) != p)
 				kdb_printf("  Error: does not match running "
-				   "process table (0x%p)\n", KDB_TSK(cpu));
+				   "process table (0x%px)\n", KDB_TSK(cpu));
 		}
 	}
 }
@@ -2687,7 +2672,7 @@ int kdb_register_flags(char *cmd,
 	for_each_kdbcmd(kp, i) {
 		if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
 			kdb_printf("Duplicate kdb command registered: "
-				"%s, func %p help %s\n", cmd, func, help);
+				"%s, func %px help %s\n", cmd, func, help);
 			return 1;
 		}
 	}
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 1e5a502ba4a7..2118d8258b7c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -83,7 +83,7 @@ typedef struct __ksymtab {
 		unsigned long sym_start;
 		unsigned long sym_end;
 		} kdb_symtab_t;
-extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size);
 extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
 
 /* Exported Symbols for kernel loadable modules to use. */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 990b3cc526c8..50bf9b119bad 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -40,7 +40,7 @@
 int kdbgetsymval(const char *symname, kdb_symtab_t *symtab)
 {
 	if (KDB_DEBUG(AR))
-		kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname,
+		kdb_printf("kdbgetsymval: symname=%s, symtab=%px\n", symname,
 			   symtab);
 	memset(symtab, 0, sizeof(*symtab));
 	symtab->sym_start = kallsyms_lookup_name(symname);
@@ -88,7 +88,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
 	char *knt1 = NULL;
 
 	if (KDB_DEBUG(AR))
-		kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab);
+		kdb_printf("kdbnearsym: addr=0x%lx, symtab=%px\n", addr, symtab);
 	memset(symtab, 0, sizeof(*symtab));
 
 	if (addr < 4096)
@@ -149,7 +149,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
 		symtab->mod_name = "kernel";
 	if (KDB_DEBUG(AR))
 		kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, "
-		   "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret,
+		   "symtab->mod_name=%px, symtab->sym_name=%px (%s)\n", ret,
 		   symtab->sym_start, symtab->mod_name, symtab->sym_name,
 		   symtab->sym_name);
 
@@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len)
  * Parameters:
  *	prefix_name	prefix of a symbol name to lookup
  *	flag	0 means search from the head, 1 means continue search.
+ *	buf_size	maximum length that can be written to prefix_name
+ *			buffer
  * Returns:
  *	1 if a symbol matches the given prefix.
  *	0 if no string found
  */
-int kallsyms_symbol_next(char *prefix_name, int flag)
+int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size)
 {
 	int prefix_len = strlen(prefix_name);
 	static loff_t pos;
@@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag)
 		pos = 0;
 
 	while ((name = kdb_walk_kallsyms(&pos))) {
-		if (strncmp(name, prefix_name, prefix_len) == 0) {
-			strncpy(prefix_name, name, strlen(name)+1);
-			return 1;
-		}
+		if (!strncmp(name, prefix_name, prefix_len))
+			return strscpy(prefix_name, name, buf_size);
 	}
 	return 0;
 }
@@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* drop through */
+		/* fall through */
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getphysword: bad width %ld\n", (long) size);
@@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size)
 				*word = w8;
 			break;
 		}
-		/* drop through */
+		/* fall through */
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_getword: bad width %ld\n", (long) size);
@@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size)
 			diag = kdb_putarea(addr, w8);
 			break;
 		}
-		/* drop through */
+		/* fall through */
 	default:
 		diag = KDB_BADWIDTH;
 		kdb_printf("kdb_putword: bad width %ld\n", (long) size);
@@ -887,13 +887,13 @@ void debug_kusage(void)
 		   __func__, dah_first);
 	if (dah_first) {
 		h_used = (struct debug_alloc_header *)debug_alloc_pool;
-		kdb_printf("%s: h_used %p size %d\n", __func__, h_used,
+		kdb_printf("%s: h_used %px size %d\n", __func__, h_used,
 			   h_used->size);
 	}
 	do {
 		h_used = (struct debug_alloc_header *)
 			  ((char *)h_free + dah_overhead + h_free->size);
-		kdb_printf("%s: h_used %p size %d caller %p\n",
+		kdb_printf("%s: h_used %px size %d caller %px\n",
 			   __func__, h_used, h_used->size, h_used->caller);
 		h_free = (struct debug_alloc_header *)
 			  (debug_alloc_pool + h_free->next);
@@ -902,7 +902,7 @@ void debug_kusage(void)
 		  ((char *)h_free + dah_overhead + h_free->size);
 	if ((char *)h_used - debug_alloc_pool !=
 	    sizeof(debug_alloc_pool_aligned))
-		kdb_printf("%s: h_used %p size %d caller %p\n",
+		kdb_printf("%s: h_used %px size %d caller %px\n",
 			   __func__, h_used, h_used->size, h_used->caller);
 out:
 	spin_unlock(&dap_lock);
diff --git a/kernel/resource.c b/kernel/resource.c
index b3a3a1fc499e..b0fbf685c77a 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -319,16 +319,23 @@ int release_resource(struct resource *old)
 EXPORT_SYMBOL(release_resource);
 
 /**
- * Finds the lowest iomem resource that covers part of [start..end].  The
- * caller must specify start, end, flags, and desc (which may be
+ * Finds the lowest iomem resource that covers part of [@start..@end].  The
+ * caller must specify @start, @end, @flags, and @desc (which may be
  * IORES_DESC_NONE).
  *
- * If a resource is found, returns 0 and *res is overwritten with the part
- * of the resource that's within [start..end]; if none is found, returns
- * -1.
+ * If a resource is found, returns 0 and @*res is overwritten with the part
+ * of the resource that's within [@start..@end]; if none is found, returns
+ * -1 or -EINVAL for other invalid parameters.
  *
  * This function walks the whole tree and not just first level children
  * unless @first_lvl is true.
+ *
+ * @start:	start address of the resource searched for
+ * @end:	end address of same resource
+ * @flags:	flags which the resource must have
+ * @desc:	descriptor the resource must have
+ * @first_lvl:	walk only the first level children, if set
+ * @res:	return ptr, if resource found
  */
 static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 			       unsigned long flags, unsigned long desc,
@@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
  * @flags: I/O resource flags
  * @start: start addr
  * @end: end addr
+ * @arg: function argument for the callback @func
+ * @func: callback function that is called for each qualifying resource area
  *
  * NOTE: For a new descriptor search, define a new IORES_DESC in
  * <linux/ioport.h> and set it in 'desc' of a target resource entry.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f12225f26b70..091e089063be 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5851,11 +5851,14 @@ void __init sched_init_smp(void)
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
-	 * happen.
+	 * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
+	 * but there won't be any contention on it.
 	 */
+	cpus_read_lock();
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
 	mutex_unlock(&sched_domains_mutex);
+	cpus_read_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ee271bb661cc..ac855b2f4774 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 		local = 1;
 
 	/*
-	 * Retry task to preferred node migration periodically, in case it
-	 * case it previously failed, or the scheduler moved us.
+	 * Retry to migrate task to preferred node periodically, in case it
+	 * previously failed, or the scheduler moved us.
 	 */
 	if (time_after(jiffies, p->numa_migrate_retry)) {
 		task_numa_placement(p);
@@ -5674,11 +5674,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return target;
 }
 
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p);
+static unsigned long cpu_util_without(int cpu, struct task_struct *p);
 
-static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+static unsigned long capacity_spare_without(int cpu, struct task_struct *p)
 {
-	return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+	return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0);
 }
 
 /*
@@ -5738,7 +5738,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
 			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
 
-			spare_cap = capacity_spare_wake(i, p);
+			spare_cap = capacity_spare_without(i, p);
 
 			if (spare_cap > max_spare_cap)
 				max_spare_cap = spare_cap;
@@ -5889,8 +5889,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 		return prev_cpu;
 
 	/*
-	 * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
-	 * last_update_time.
+	 * We need task's util for capacity_spare_without, sync it up to
+	 * prev_cpu's last_update_time.
 	 */
 	if (!(sd_flag & SD_BALANCE_FORK))
 		sync_entity_load_avg(&p->se);
@@ -6216,10 +6216,19 @@ static inline unsigned long cpu_util(int cpu)
 }
 
 /*
- * cpu_util_wake: Compute CPU utilization with any contributions from
- * the waking task p removed.
+ * cpu_util_without: compute cpu utilization without any contributions from *p
+ * @cpu: the CPU which utilization is requested
+ * @p: the task which utilization should be discounted
+ *
+ * The utilization of a CPU is defined by the utilization of tasks currently
+ * enqueued on that CPU as well as tasks which are currently sleeping after an
+ * execution on that CPU.
+ *
+ * This method returns the utilization of the specified CPU by discounting the
+ * utilization of the specified task, whenever the task is currently
+ * contributing to the CPU utilization.
  */
-static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
+static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq;
 	unsigned int util;
@@ -6231,7 +6240,7 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
 	cfs_rq = &cpu_rq(cpu)->cfs;
 	util = READ_ONCE(cfs_rq->avg.util_avg);
 
-	/* Discount task's blocked util from CPU's util */
+	/* Discount task's util from CPU's util */
 	util -= min_t(unsigned int, util, task_util(p));
 
 	/*
@@ -6240,14 +6249,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
 	 * a) if *p is the only task sleeping on this CPU, then:
 	 *      cpu_util (== task_util) > util_est (== 0)
 	 *    and thus we return:
-	 *      cpu_util_wake = (cpu_util - task_util) = 0
+	 *      cpu_util_without = (cpu_util - task_util) = 0
 	 *
 	 * b) if other tasks are SLEEPING on this CPU, which is now exiting
 	 *    IDLE, then:
 	 *      cpu_util >= task_util
 	 *      cpu_util > util_est (== 0)
 	 *    and thus we discount *p's blocked utilization to return:
-	 *      cpu_util_wake = (cpu_util - task_util) >= 0
+	 *      cpu_util_without = (cpu_util - task_util) >= 0
 	 *
 	 * c) if other tasks are RUNNABLE on that CPU and
 	 *      util_est > cpu_util
@@ -6260,8 +6269,33 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p)
 	 * covered by the following code when estimated utilization is
 	 * enabled.
 	 */
-	if (sched_feat(UTIL_EST))
-		util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued));
+	if (sched_feat(UTIL_EST)) {
+		unsigned int estimated =
+			READ_ONCE(cfs_rq->avg.util_est.enqueued);
+
+		/*
+		 * Despite the following checks we still have a small window
+		 * for a possible race, when an execl's select_task_rq_fair()
+		 * races with LB's detach_task():
+		 *
+		 *   detach_task()
+		 *     p->on_rq = TASK_ON_RQ_MIGRATING;
+		 *     ---------------------------------- A
+		 *     deactivate_task()                   \
+		 *       dequeue_task()                     + RaceTime
+		 *         util_est_dequeue()              /
+		 *     ---------------------------------- B
+		 *
+		 * The additional check on "current == p" it's required to
+		 * properly fix the execl regression and it helps in further
+		 * reducing the chances for the above race.
+		 */
+		if (unlikely(task_on_rq_queued(p) || current == p)) {
+			estimated -= min_t(unsigned int, estimated,
+					   (_task_util_est(p) | UTIL_AVG_UNCHANGED));
+		}
+		util = max(util, estimated);
+	}
 
 	/*
 	 * Utilization (estimated) can exceed the CPU capacity, thus let's
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 7cdecfc010af..3d7355d7c3e3 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -633,38 +633,39 @@ void psi_cgroup_free(struct cgroup *cgroup)
  */
 void cgroup_move_task(struct task_struct *task, struct css_set *to)
 {
-	bool move_psi = !psi_disabled;
 	unsigned int task_flags = 0;
 	struct rq_flags rf;
 	struct rq *rq;
 
-	if (move_psi) {
-		rq = task_rq_lock(task, &rf);
+	if (psi_disabled) {
+		/*
+		 * Lame to do this here, but the scheduler cannot be locked
+		 * from the outside, so we move cgroups from inside sched/.
+		 */
+		rcu_assign_pointer(task->cgroups, to);
+		return;
+	}
 
-		if (task_on_rq_queued(task))
-			task_flags = TSK_RUNNING;
-		else if (task->in_iowait)
-			task_flags = TSK_IOWAIT;
+	rq = task_rq_lock(task, &rf);
 
-		if (task->flags & PF_MEMSTALL)
-			task_flags |= TSK_MEMSTALL;
+	if (task_on_rq_queued(task))
+		task_flags = TSK_RUNNING;
+	else if (task->in_iowait)
+		task_flags = TSK_IOWAIT;
 
-		if (task_flags)
-			psi_task_change(task, task_flags, 0);
-	}
+	if (task->flags & PF_MEMSTALL)
+		task_flags |= TSK_MEMSTALL;
 
-	/*
-	 * Lame to do this here, but the scheduler cannot be locked
-	 * from the outside, so we move cgroups from inside sched/.
-	 */
+	if (task_flags)
+		psi_task_change(task, task_flags, 0);
+
+	/* See comment above */
 	rcu_assign_pointer(task->cgroups, to);
 
-	if (move_psi) {
-		if (task_flags)
-			psi_task_change(task, 0, task_flags);
+	if (task_flags)
+		psi_task_change(task, 0, task_flags);
 
-		task_rq_unlock(rq, task, &rf);
-	}
+	task_rq_unlock(rq, task, &rf);
 }
 #endif /* CONFIG_CGROUPS */
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index ce32cf741b25..8f0644af40be 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk,
 	struct task_cputime cputime;
 	unsigned long soft;
 
-	if (dl_task(tsk))
-		check_dl_overrun(tsk);
-
 	/*
 	 * If cputimer is not running, then there are no active
 	 * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU).
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index e5222b5fb4fe..923414a246e9 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
 		goto out;
 
-	ret = sort_idmaps(&new_map);
-	if (ret < 0)
-		goto out;
-
 	ret = -EPERM;
 	/* Map the lower ids from the parent user namespace to the
 	 * kernel global id space.
@@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 		e->lower_first = lower_first;
 	}
 
+	/*
+	 * If we want to use binary search for lookup, this clones the extent
+	 * array and sorts both copies.
+	 */
+	ret = sort_idmaps(&new_map);
+	if (ret < 0)
+		goto out;
+
 	/* Install the map */
 	if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
 		memcpy(map->extent, new_map.extent,