Merge branch 'akpm' (fixes from Andrew)

Merge misc fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mqueue: sys_mq_open: do not call mnt_drop_write() if read-only
  mm/hotplug: only free wait_table if it's allocated by vmalloc
  dma-debug: update DMA debug API to better handle multiple mappings of a buffer
  dma-debug: fix locking bug in check_unmap()
  drivers/rtc/rtc-at91rm9200.c: use a variable for storing IMR
  drivers/video/ep93xx-fb.c: include <linux/io.h> for devm_ioremap()
  drivers/rtc/rtc-da9052.c: fix for rtc device registration
  mm: zone_end_pfn is too small
  poweroff: change orderly_poweroff() to use schedule_work()
  mm/hugetlb: fix total hugetlbfs pages count when using memory overcommit accouting
  printk: Provide a wake_up_klogd() off-case
  irq_work.h: fix warning when CONFIG_IRQ_WORK=n

drivers/rtc/rtc-at91rm9200.c

@@ -44,6 +44,7 @@ static DECLARE_COMPLETION(at91_rtc_updated);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;
+static u32 at91_rtc_imr;
 
 /*
  * Decode time/date into rtc_time structure
@@ -108,9 +109,11 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
 
+	at91_rtc_imr |= AT91_RTC_ACKUPD;
 	at91_rtc_write(AT91_RTC_IER, AT91_RTC_ACKUPD);
 	wait_for_completion(&at91_rtc_updated);	/* wait for ACKUPD interrupt */
 	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD);
+	at91_rtc_imr &= ~AT91_RTC_ACKUPD;
 
 	at91_rtc_write(AT91_RTC_TIMR,
 			  bin2bcd(tm->tm_sec) << 0
@@ -142,7 +145,7 @@ static int at91_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	tm->tm_yday = rtc_year_days(tm->tm_mday, tm->tm_mon, tm->tm_year);
 	tm->tm_year = at91_alarm_year - 1900;
 
-	alrm->enabled = (at91_rtc_read(AT91_RTC_IMR) & AT91_RTC_ALARM)
+	alrm->enabled = (at91_rtc_imr & AT91_RTC_ALARM)
 			? 1 : 0;
 
 	dev_dbg(dev, "%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
@@ -168,6 +171,7 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	tm.tm_sec = alrm->time.tm_sec;
 
 	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ALARM);
+	at91_rtc_imr &= ~AT91_RTC_ALARM;
 	at91_rtc_write(AT91_RTC_TIMALR,
 		  bin2bcd(tm.tm_sec) << 0
 		| bin2bcd(tm.tm_min) << 8
@@ -180,6 +184,7 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	if (alrm->enabled) {
 		at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_ALARM);
+		at91_rtc_imr |= AT91_RTC_ALARM;
 		at91_rtc_write(AT91_RTC_IER, AT91_RTC_ALARM);
 	}
 
@@ -196,9 +201,12 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 
 	if (enabled) {
 		at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_ALARM);
+		at91_rtc_imr |= AT91_RTC_ALARM;
 		at91_rtc_write(AT91_RTC_IER, AT91_RTC_ALARM);
-	} else
+	} else {
 		at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ALARM);
+		at91_rtc_imr &= ~AT91_RTC_ALARM;
+	}
 
 	return 0;
 }
@@ -207,12 +215,10 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
  */
 static int at91_rtc_proc(struct device *dev, struct seq_file *seq)
 {
-	unsigned long imr = at91_rtc_read(AT91_RTC_IMR);
-
 	seq_printf(seq, "update_IRQ\t: %s\n",
-			(imr & AT91_RTC_ACKUPD) ? "yes" : "no");
+			(at91_rtc_imr & AT91_RTC_ACKUPD) ? "yes" : "no");
 	seq_printf(seq, "periodic_IRQ\t: %s\n",
-			(imr & AT91_RTC_SECEV) ? "yes" : "no");
+			(at91_rtc_imr & AT91_RTC_SECEV) ? "yes" : "no");
 
 	return 0;
 }
@@ -227,7 +233,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	unsigned int rtsr;
 	unsigned long events = 0;
 
-	rtsr = at91_rtc_read(AT91_RTC_SR) & at91_rtc_read(AT91_RTC_IMR);
+	rtsr = at91_rtc_read(AT91_RTC_SR) & at91_rtc_imr;
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
@@ -291,6 +297,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD | AT91_RTC_ALARM |
 					AT91_RTC_SECEV | AT91_RTC_TIMEV |
 					AT91_RTC_CALEV);
+	at91_rtc_imr = 0;
 
 	ret = request_irq(irq, at91_rtc_interrupt,
 				IRQF_SHARED,
@@ -329,6 +336,7 @@ static int __exit at91_rtc_remove(struct platform_device *pdev)
 	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD | AT91_RTC_ALARM |
 					AT91_RTC_SECEV | AT91_RTC_TIMEV |
 					AT91_RTC_CALEV);
+	at91_rtc_imr = 0;
 	free_irq(irq, pdev);
 
 	rtc_device_unregister(rtc);
@@ -341,31 +349,35 @@ static int __exit at91_rtc_remove(struct platform_device *pdev)
 
 /* AT91RM9200 RTC Power management control */
 
-static u32 at91_rtc_imr;
+static u32 at91_rtc_bkpimr;
+
 
 static int at91_rtc_suspend(struct device *dev)
 {
 	/* this IRQ is shared with DBGU and other hardware which isn't
 	 * necessarily doing PM like we are...
 	 */
-	at91_rtc_imr = at91_rtc_read(AT91_RTC_IMR)
-			& (AT91_RTC_ALARM|AT91_RTC_SECEV);
-	if (at91_rtc_imr) {
-		if (device_may_wakeup(dev))
+	at91_rtc_bkpimr = at91_rtc_imr & (AT91_RTC_ALARM|AT91_RTC_SECEV);
+	if (at91_rtc_bkpimr) {
+		if (device_may_wakeup(dev)) {
 			enable_irq_wake(irq);
-		else
-			at91_rtc_write(AT91_RTC_IDR, at91_rtc_imr);
-	}
+		} else {
+			at91_rtc_write(AT91_RTC_IDR, at91_rtc_bkpimr);
+			at91_rtc_imr &= ~at91_rtc_bkpimr;
+		}
+}
 	return 0;
 }
 
 static int at91_rtc_resume(struct device *dev)
 {
-	if (at91_rtc_imr) {
-		if (device_may_wakeup(dev))
+	if (at91_rtc_bkpimr) {
+		if (device_may_wakeup(dev)) {
 			disable_irq_wake(irq);
-		else
-			at91_rtc_write(AT91_RTC_IER, at91_rtc_imr);
+		} else {
+			at91_rtc_imr |= at91_rtc_bkpimr;
+			at91_rtc_write(AT91_RTC_IER, at91_rtc_bkpimr);
+		}
 	}
 	return 0;
 }

drivers/rtc/rtc-at91rm9200.h

@@ -64,7 +64,6 @@
 #define	AT91_RTC_SCCR		0x1c			/* Status Clear Command Register */
 #define	AT91_RTC_IER		0x20			/* Interrupt Enable Register */
 #define	AT91_RTC_IDR		0x24			/* Interrupt Disable Register */
-#define	AT91_RTC_IMR		0x28			/* Interrupt Mask Register */
 
 #define	AT91_RTC_VER		0x2c			/* Valid Entry Register */
 #define		AT91_RTC_NVTIM		(1 <<  0)		/* Non valid Time */

drivers/rtc/rtc-da9052.c

@@ -239,11 +239,9 @@ static int da9052_rtc_probe(struct platform_device *pdev)
 
 	rtc->da9052 = dev_get_drvdata(pdev->dev.parent);
 	platform_set_drvdata(pdev, rtc);
-	rtc->irq = platform_get_irq_byname(pdev, "ALM");
-	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
-				da9052_rtc_irq,
-				IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				"ALM", rtc);
+	rtc->irq =  DA9052_IRQ_ALARM;
+	ret = da9052_request_irq(rtc->da9052, rtc->irq, "ALM",
+				da9052_rtc_irq, rtc);
 	if (ret != 0) {
 		rtc_err(rtc->da9052, "irq registration failed: %d\n", ret);
 		return ret;

drivers/video/ep93xx-fb.c

@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/fb.h>
+#include <linux/io.h>
 
 #include <linux/platform_data/video-ep93xx.h>
 

include/linux/irq_work.h

@@ -37,7 +37,7 @@ void irq_work_sync(struct irq_work *work);
 #ifdef CONFIG_IRQ_WORK
 bool irq_work_needs_cpu(void);
 #else
-static bool irq_work_needs_cpu(void) { return false; }
+static inline bool irq_work_needs_cpu(void) { return false; }
 #endif
 
 #endif /* _LINUX_IRQ_WORK_H */

include/linux/kernel.h

@@ -390,7 +390,6 @@ extern struct pid *session_of_pgrp(struct pid *pgrp);
 unsigned long int_sqrt(unsigned long);
 
 extern void bust_spinlocks(int yes);
-extern void wake_up_klogd(void);
 extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern int panic_on_oops;

include/linux/mmzone.h

@@ -527,7 +527,7 @@ static inline int zone_is_oom_locked(const struct zone *zone)
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
-static inline unsigned zone_end_pfn(const struct zone *zone)
+static inline unsigned long zone_end_pfn(const struct zone *zone)
 {
 	return zone->zone_start_pfn + zone->spanned_pages;
 }

include/linux/printk.h

@@ -134,6 +134,8 @@ extern int printk_delay_msec;
 extern int dmesg_restrict;
 extern int kptr_restrict;
 
+extern void wake_up_klogd(void);
+
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 #else
@@ -162,6 +164,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 	return false;
 }
 
+static inline void wake_up_klogd(void)
+{
+}
+
 static inline void log_buf_kexec_setup(void)
 {
 }

ipc/mqueue.c

@@ -840,7 +840,8 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
 		fd = error;
 	}
 	mutex_unlock(&root->d_inode->i_mutex);
-	mnt_drop_write(mnt);
+	if (!ro)
+		mnt_drop_write(mnt);
 out_putname:
 	putname(name);
 	return fd;

kernel/printk.c

@@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
 #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
 #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
 
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-
 int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* console_loglevel */
 	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
@@ -224,6 +222,7 @@ struct log {
 static DEFINE_RAW_SPINLOCK(logbuf_lock);
 
 #ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
@@ -1957,45 +1956,6 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-/*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_BUF_SIZE		512
-
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_SCHED	0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-	int pending = __this_cpu_xchg(printk_pending, 0);
-
-	if (pending & PRINTK_PENDING_SCHED) {
-		char *buf = __get_cpu_var(printk_sched_buf);
-		printk(KERN_WARNING "[sched_delayed] %s", buf);
-	}
-
-	if (pending & PRINTK_PENDING_WAKEUP)
-		wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-	preempt_disable();
-	if (waitqueue_active(&log_wait)) {
-		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
-	}
-	preempt_enable();
-}
-
 static void console_cont_flush(char *text, size_t size)
 {
 	unsigned long flags;
@@ -2458,6 +2418,44 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE		512
+
+#define PRINTK_PENDING_WAKEUP	0x01
+#define PRINTK_PENDING_SCHED	0x02
+
+static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
+	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
+}
 
 int printk_sched(const char *fmt, ...)
 {

kernel/sys.c

@@ -2185,9 +2185,8 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 
 char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
 
-static int __orderly_poweroff(void)
+static int __orderly_poweroff(bool force)
 {
-	int argc;
 	char **argv;
 	static char *envp[] = {
 		"HOME=/",
@@ -2196,20 +2195,40 @@ static int __orderly_poweroff(void)
 	};
 	int ret;
 
-	argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc);
-	if (argv == NULL) {
+	argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+	if (argv) {
+		ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+		argv_free(argv);
+	} else {
 		printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
-		       __func__, poweroff_cmd);
-		return -ENOMEM;
+					 __func__, poweroff_cmd);
+		ret = -ENOMEM;
 	}
 
-	ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC,
-				      NULL, NULL, NULL);
-	argv_free(argv);
+	if (ret && force) {
+		printk(KERN_WARNING "Failed to start orderly shutdown: "
+					"forcing the issue\n");
+		/*
+		 * I guess this should try to kick off some daemon to sync and
+		 * poweroff asap.  Or not even bother syncing if we're doing an
+		 * emergency shutdown?
+		 */
+		emergency_sync();
+		kernel_power_off();
+	}
 
 	return ret;
 }
 
+static bool poweroff_force;
+
+static void poweroff_work_func(struct work_struct *work)
+{
+	__orderly_poweroff(poweroff_force);
+}
+
+static DECLARE_WORK(poweroff_work, poweroff_work_func);
+
 /**
  * orderly_poweroff - Trigger an orderly system poweroff
  * @force: force poweroff if command execution fails
@@ -2219,21 +2238,9 @@ static int __orderly_poweroff(void)
  */
 int orderly_poweroff(bool force)
 {
-	int ret = __orderly_poweroff();
-
-	if (ret && force) {
-		printk(KERN_WARNING "Failed to start orderly shutdown: "
-		       "forcing the issue\n");
-
-		/*
-		 * I guess this should try to kick off some daemon to sync and
-		 * poweroff asap.  Or not even bother syncing if we're doing an
-		 * emergency shutdown?
-		 */
-		emergency_sync();
-		kernel_power_off();
-	}
-
-	return ret;
+	if (force) /* do not override the pending "true" */
+		poweroff_force = true;
+	schedule_work(&poweroff_work);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(orderly_poweroff);

lib/bust_spinlocks.c

@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/tty.h>
 #include <linux/wait.h>
@@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes)
 			wake_up_klogd();
 	}
 }
-
-

lib/dma-debug.c

@@ -862,17 +862,21 @@ static void check_unmap(struct dma_debug_entry *ref)
 	entry = bucket_find_exact(bucket, ref);
 
 	if (!entry) {
+		/* must drop lock before calling dma_mapping_error */
+		put_hash_bucket(bucket, &flags);
+
 		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
 			err_printk(ref->dev, NULL,
-				   "DMA-API: device driver tries "
-				   "to free an invalid DMA memory address\n");
-			return;
+				   "DMA-API: device driver tries to free an "
+				   "invalid DMA memory address\n");
+		} else {
+			err_printk(ref->dev, NULL,
+				   "DMA-API: device driver tries to free DMA "
+				   "memory it has not allocated [device "
+				   "address=0x%016llx] [size=%llu bytes]\n",
+				   ref->dev_addr, ref->size);
 		}
-		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
-			   "to free DMA memory it has not allocated "
-			   "[device address=0x%016llx] [size=%llu bytes]\n",
-			   ref->dev_addr, ref->size);
-		goto out;
+		return;
 	}
 
 	if (ref->size != entry->size) {
@@ -936,7 +940,6 @@ static void check_unmap(struct dma_debug_entry *ref)
 	hash_bucket_del(entry);
 	dma_entry_free(entry);
 
-out:
 	put_hash_bucket(bucket, &flags);
 }
 
@@ -1082,13 +1085,27 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	ref.dev = dev;
 	ref.dev_addr = dma_addr;
 	bucket = get_hash_bucket(&ref, &flags);
-	entry = bucket_find_exact(bucket, &ref);
 
-	if (!entry)
-		goto out;
+	list_for_each_entry(entry, &bucket->list, list) {
+		if (!exact_match(&ref, entry))
+			continue;
+
+		/*
+		 * The same physical address can be mapped multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therefore we implement a
+		 * best-fit algorithm here which updates the first entry
+		 * from the hash which fits the reference value and is
+		 * not currently listed as being checked.
+		 */
+		if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+			entry->map_err_type = MAP_ERR_CHECKED;
+			break;
+		}
+	}
 
-	entry->map_err_type = MAP_ERR_CHECKED;
-out:
 	put_hash_bucket(bucket, &flags);
 }
 EXPORT_SYMBOL(debug_dma_mapping_error);

mm/hugetlb.c

@@ -2124,8 +2124,12 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &default_hstate;
-	return h->nr_huge_pages * pages_per_huge_page(h);
+	struct hstate *h;
+	unsigned long nr_total_pages = 0;
+
+	for_each_hstate(h)
+		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
+	return nr_total_pages;
 }
 
 static int hugetlb_acct_memory(struct hstate *h, long delta)

mm/memory_hotplug.c

@@ -1779,7 +1779,11 @@ void try_offline_node(int nid)
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (zone->wait_table)
+		/*
+		 * wait_table may be allocated from boot memory,
+		 * here only free if it's allocated by vmalloc.
+		 */
+		if (is_vmalloc_addr(zone->wait_table))
 			vfree(zone->wait_table);
 	}