Merge branch 'akpm' (Andrew's patch-bomb)

Merge random patches from Andrew Morton.

* Merge emailed patches from Andrew Morton <akpm@linux-foundation.org>: (32 commits)
  memblock: free allocated memblock_reserved_regions later
  mm: sparse: fix usemap allocation above node descriptor section
  mm: sparse: fix section usemap placement calculation
  xtensa: fix incorrect memset
  shmem: cleanup shmem_add_to_page_cache
  shmem: fix negative rss in memcg memory.stat
  tmpfs: revert SEEK_DATA and SEEK_HOLE
  drivers/rtc/rtc-twl.c: fix threaded IRQ to use IRQF_ONESHOT
  fat: fix non-atomic NFS i_pos read
  MAINTAINERS: add OMAP CPUfreq driver to OMAP Power Management section
  sgi-xp: nested calls to spin_lock_irqsave()
  fs: ramfs: file-nommu: add SetPageUptodate()
  drivers/rtc/rtc-mxc.c: fix irq enabled interrupts warning
  mm/memory_hotplug.c: release memory resources if hotadd_new_pgdat() fails
  h8300/uaccess: add mising __clear_user()
  h8300/uaccess: remove assignment to __gu_val in unhandled case of get_user()
  h8300/time: add missing #include <asm/irq_regs.h>
  h8300/signal: fix typo "statis"
  h8300/pgtable: add missing #include <asm-generic/pgtable.h>
  drivers/rtc/rtc-ab8500.c: ensure correct probing of the AB8500 RTC when Device Tree is enabled
  ...

MAINTAINERS

@@ -4857,6 +4857,7 @@ M:	Kevin Hilman <khilman@ti.com>
 L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	arch/arm/*omap*/*pm*
+F:	drivers/cpufreq/omap-cpufreq.c
 
 OMAP POWERDOMAIN/CLOCKDOMAIN SOC ADAPTATION LAYER SUPPORT
 M:	Rajendra Nayak <rnayak@ti.com>

arch/h8300/include/asm/pgtable.h

@@ -70,4 +70,7 @@ extern int is_in_rom(unsigned long);
 #define	VMALLOC_END	0xffffffff
 
 #define arch_enter_lazy_cpu_mode()    do {} while (0)
+
+#include <asm-generic/pgtable.h>
+
 #endif /* _H8300_PGTABLE_H */

arch/h8300/include/asm/uaccess.h

@@ -100,7 +100,6 @@ extern int __put_user_bad(void);
 	break;							\
     default:							\
 	__gu_err = __get_user_bad();				\
-	__gu_val = 0;						\
 	break;							\
     }								\
     (x) = __gu_val;						\
@@ -159,4 +158,6 @@ clear_user(void *to, unsigned long n)
 	return 0;
 }
 
+#define __clear_user	clear_user
+
 #endif /* _H8300_UACCESS_H */

arch/h8300/kernel/signal.c

@@ -447,7 +447,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-statis void do_signal(struct pt_regs *regs)
+static void do_signal(struct pt_regs *regs)
 {
 	siginfo_t info;
 	int signr;

arch/h8300/kernel/time.c

@@ -27,6 +27,7 @@
 #include <linux/profile.h>
 
 #include <asm/io.h>
+#include <asm/irq_regs.h>
 #include <asm/timer.h>
 
 #define	TICK_SIZE (tick_nsec / 1000)

arch/mn10300/include/asm/ptrace.h

@@ -81,9 +81,6 @@ struct pt_regs {
 #define PTRACE_GETFPREGS          14
 #define PTRACE_SETFPREGS          15
 
-/* options set using PTRACE_SETOPTIONS */
-#define PTRACE_O_TRACESYSGOOD     0x00000001
-
 #ifdef __KERNEL__
 
 #define user_mode(regs)			(((regs)->epsw & EPSW_nSL) == EPSW_nSL)

arch/mn10300/include/asm/timex.h

@@ -11,7 +11,6 @@
 #ifndef _ASM_TIMEX_H
 #define _ASM_TIMEX_H
 
-#include <asm/hardirq.h>
 #include <unit/timex.h>
 
 #define TICK_SIZE (tick_nsec / 1000)
@@ -30,16 +29,6 @@ static inline cycles_t get_cycles(void)
 extern int init_clockevents(void);
 extern int init_clocksource(void);
 
-static inline void setup_jiffies_interrupt(int irq,
-					   struct irqaction *action)
-{
-	u16 tmp;
-	setup_irq(irq, action);
-	set_intr_level(irq, NUM2GxICR_LEVEL(CONFIG_TIMER_IRQ_LEVEL));
-	GxICR(irq) |= GxICR_ENABLE | GxICR_DETECT | GxICR_REQUEST;
-	tmp = GxICR(irq);
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_TIMEX_H */

arch/mn10300/kernel/cevt-mn10300.c

@@ -70,6 +70,16 @@ static void event_handler(struct clock_event_device *dev)
 {
 }
 
+static inline void setup_jiffies_interrupt(int irq,
+					   struct irqaction *action)
+{
+	u16 tmp;
+	setup_irq(irq, action);
+	set_intr_level(irq, NUM2GxICR_LEVEL(CONFIG_TIMER_IRQ_LEVEL));
+	GxICR(irq) |= GxICR_ENABLE | GxICR_DETECT | GxICR_REQUEST;
+	tmp = GxICR(irq);
+}
+
 int __init init_clockevents(void)
 {
 	struct clock_event_device *cd;

arch/mn10300/kernel/internal.h

@@ -9,6 +9,8 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
+#include <linux/irqreturn.h>
+
 struct clocksource;
 struct clock_event_device;
 

arch/mn10300/kernel/irq.c

@@ -170,9 +170,9 @@ mn10300_cpupic_setaffinity(struct irq_data *d, const struct cpumask *mask,
 	case SC1TXIRQ:
 #ifdef CONFIG_MN10300_TTYSM1_TIMER12
 	case TM12IRQ:
-#elif CONFIG_MN10300_TTYSM1_TIMER9
+#elif defined(CONFIG_MN10300_TTYSM1_TIMER9)
 	case TM9IRQ:
-#elif CONFIG_MN10300_TTYSM1_TIMER3
+#elif defined(CONFIG_MN10300_TTYSM1_TIMER3)
 	case TM3IRQ:
 #endif /* CONFIG_MN10300_TTYSM1_TIMER12 */
 #endif /* CONFIG_MN10300_TTYSM1 */

arch/mn10300/kernel/traps.c

@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <linux/bug.h>
 #include <linux/irq.h>
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <linux/uaccess.h>
 #include <asm/io.h>

arch/mn10300/mm/dma-alloc.c

@@ -15,6 +15,7 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
+#include <linux/export.h>
 #include <asm/io.h>
 
 static unsigned long pci_sram_allocated = 0xbc000000;

arch/mn10300/unit-asb2303/include/unit/timex.h

@@ -11,10 +11,6 @@
 #ifndef _ASM_UNIT_TIMEX_H
 #define _ASM_UNIT_TIMEX_H
 
-#ifndef __ASSEMBLY__
-#include <linux/irq.h>
-#endif /* __ASSEMBLY__ */
-
 #include <asm/timer-regs.h>
 #include <unit/clock.h>
 #include <asm/param.h>

arch/mn10300/unit-asb2303/smc91111.c

@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 
 #include <asm/io.h>
+#include <asm/irq.h>
 #include <asm/timex.h>
 #include <asm/processor.h>
 #include <asm/intctl-regs.h>

arch/mn10300/unit-asb2305/include/unit/timex.h

@@ -11,10 +11,6 @@
 #ifndef _ASM_UNIT_TIMEX_H
 #define _ASM_UNIT_TIMEX_H
 
-#ifndef __ASSEMBLY__
-#include <linux/irq.h>
-#endif /* __ASSEMBLY__ */
-
 #include <asm/timer-regs.h>
 #include <unit/clock.h>
 #include <asm/param.h>

arch/mn10300/unit-asb2305/unit-init.c

@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <asm/io.h>
+#include <asm/irq.h>
 #include <asm/setup.h>
 #include <asm/processor.h>
 #include <asm/intctl-regs.h>

arch/mn10300/unit-asb2364/include/unit/timex.h

@@ -11,10 +11,6 @@
 #ifndef _ASM_UNIT_TIMEX_H
 #define _ASM_UNIT_TIMEX_H
 
-#ifndef __ASSEMBLY__
-#include <linux/irq.h>
-#endif /* __ASSEMBLY__ */
-
 #include <asm/timer-regs.h>
 #include <unit/clock.h>
 #include <asm/param.h>

arch/xtensa/kernel/process.c

@@ -277,7 +277,7 @@ void xtensa_elf_core_copy_regs (xtensa_gregset_t *elfregs, struct pt_regs *regs)
 
 	/* Don't leak any random bits. */
 
-	memset(elfregs, 0, sizeof (elfregs));
+	memset(elfregs, 0, sizeof(*elfregs));
 
 	/* Note:  PS.EXCM is not set while user task is running; its
 	 * being set in regs->ps is for exception handling convenience.

drivers/misc/sgi-xp/xpc_uv.c

@@ -452,9 +452,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part,
 
 		if (msg->activate_gru_mq_desc_gpa !=
 		    part_uv->activate_gru_mq_desc_gpa) {
-			spin_lock_irqsave(&part_uv->flags_lock, irq_flags);
+			spin_lock(&part_uv->flags_lock);
 			part_uv->flags &= ~XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV;
-			spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags);
+			spin_unlock(&part_uv->flags_lock);
 			part_uv->activate_gru_mq_desc_gpa =
 			    msg->activate_gru_mq_desc_gpa;
 		}

drivers/rtc/rtc-ab8500.c

@@ -17,6 +17,7 @@
 #include <linux/mfd/abx500.h>
 #include <linux/mfd/abx500/ab8500.h>
 #include <linux/delay.h>
+#include <linux/of.h>
 
 #define AB8500_RTC_SOFF_STAT_REG	0x00
 #define AB8500_RTC_CC_CONF_REG		0x01
@@ -422,7 +423,7 @@ static int __devinit ab8500_rtc_probe(struct platform_device *pdev)
 	}
 
 	err = request_threaded_irq(irq, NULL, rtc_alarm_handler,
-		IRQF_NO_SUSPEND, "ab8500-rtc", rtc);
+		IRQF_NO_SUSPEND | IRQF_ONESHOT, "ab8500-rtc", rtc);
 	if (err < 0) {
 		rtc_device_unregister(rtc);
 		return err;
@@ -430,7 +431,6 @@ static int __devinit ab8500_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-
 	err = ab8500_sysfs_rtc_register(&pdev->dev);
 	if (err) {
 		dev_err(&pdev->dev, "sysfs RTC failed to register\n");
@@ -454,10 +454,16 @@ static int __devexit ab8500_rtc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id ab8500_rtc_match[] = {
+	{ .compatible = "stericsson,ab8500-rtc", },
+	{}
+};
+
 static struct platform_driver ab8500_rtc_driver = {
 	.driver = {
 		.name = "ab8500-rtc",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_rtc_match,
 	},
 	.probe	= ab8500_rtc_probe,
 	.remove = __devexit_p(ab8500_rtc_remove),

drivers/rtc/rtc-mxc.c

@@ -202,10 +202,11 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id)
 	struct platform_device *pdev = dev_id;
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
 	void __iomem *ioaddr = pdata->ioaddr;
+	unsigned long flags;
 	u32 status;
 	u32 events = 0;
 
-	spin_lock_irq(&pdata->rtc->irq_lock);
+	spin_lock_irqsave(&pdata->rtc->irq_lock, flags);
 	status = readw(ioaddr + RTC_RTCISR) & readw(ioaddr + RTC_RTCIENR);
 	/* clear interrupt sources */
 	writew(status, ioaddr + RTC_RTCISR);
@@ -224,7 +225,7 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id)
 		events |= (RTC_PF | RTC_IRQF);
 
 	rtc_update_irq(pdata->rtc, 1, events);
-	spin_unlock_irq(&pdata->rtc->irq_lock);
+	spin_unlock_irqrestore(&pdata->rtc->irq_lock, flags);
 
 	return IRQ_HANDLED;
 }

drivers/rtc/rtc-spear.c

@@ -458,12 +458,12 @@ static int __devexit spear_rtc_remove(struct platform_device *pdev)
 	clk_disable(config->clk);
 	clk_put(config->clk);
 	iounmap(config->ioaddr);
-	kfree(config);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res)
 		release_mem_region(res->start, resource_size(res));
 	platform_set_drvdata(pdev, NULL);
 	rtc_device_unregister(config->rtc);
+	kfree(config);
 
 	return 0;
 }

drivers/rtc/rtc-twl.c

@@ -510,7 +510,7 @@ static int __devinit twl_rtc_probe(struct platform_device *pdev)
 	}
 
 	ret = request_threaded_irq(irq, NULL, twl_rtc_interrupt,
-				   IRQF_TRIGGER_RISING,
+				   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
 				   dev_name(&rtc->dev), rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "IRQ is not free.\n");

fs/fat/inode.c

@@ -738,22 +738,21 @@ static int
 fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent)
 {
 	int len = *lenp;
-	u32 ipos_h, ipos_m, ipos_l;
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+	loff_t i_pos;
 
 	if (len < 5) {
 		*lenp = 5;
 		return 255; /* no room */
 	}
 
-	ipos_h = MSDOS_I(inode)->i_pos >> 8;
-	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
-	ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28;
+	i_pos = fat_i_pos_read(sbi, inode);
 	*lenp = 5;
 	fh[0] = inode->i_ino;
 	fh[1] = inode->i_generation;
-	fh[2] = ipos_h;
-	fh[3] = ipos_m | MSDOS_I(inode)->i_logstart;
-	fh[4] = ipos_l;
+	fh[2] = i_pos >> 8;
+	fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart;
+	fh[4] = (i_pos & 0x0f) << 28;
 	if (parent)
 		fh[4] |= MSDOS_I(parent)->i_logstart;
 	return 3;

fs/ocfs2/file.c

@@ -1950,7 +1950,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 	if (ret < 0)
 		mlog_errno(ret);
 
-	if (file->f_flags & O_SYNC)
+	if (file && (file->f_flags & O_SYNC))
 		handle->h_sync = 1;
 
 	ocfs2_commit_trans(osb, handle);

fs/ramfs/file-nommu.c

@@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
 		/* prevent the page from being discarded on memory pressure */
 		SetPageDirty(page);
+		SetPageUptodate(page);
 
 		unlock_page(page);
 		put_page(page);

include/linux/bootmem.h

@@ -91,6 +91,11 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal,
+				  unsigned long limit);
 extern void *__alloc_bootmem_low(unsigned long size,
 				 unsigned long align,
 				 unsigned long goal);

include/linux/memblock.h

@@ -50,9 +50,7 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end,
 				phys_addr_t size, phys_addr_t align, int nid);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
-int memblock_free_reserved_regions(void);
-int memblock_reserve_reserved_regions(void);
-
+phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
 void memblock_allow_resize(void);
 int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
 int memblock_add(phys_addr_t base, phys_addr_t size);

include/linux/mmzone.h

@@ -694,7 +694,7 @@ typedef struct pglist_data {
 					     range, including holes */
 	int node_id;
 	wait_queue_head_t kswapd_wait;
-	struct task_struct *kswapd;
+	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
 } pg_data_t;

kernel/sys.c

@@ -1788,7 +1788,6 @@ SYSCALL_DEFINE1(umask, int, mask)
 #ifdef CONFIG_CHECKPOINT_RESTORE
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
-	struct vm_area_struct *vma;
 	struct file *exe_file;
 	struct dentry *dentry;
 	int err;
@@ -1816,12 +1815,16 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	down_write(&mm->mmap_sem);
 
 	/*
-	 * Forbid mm->exe_file change if there are mapped other files.
+	 * Forbid mm->exe_file change if old file still mapped.
 	 */
 	err = -EBUSY;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
-						&exe_file->f_path))
+	if (mm->exe_file) {
+		struct vm_area_struct *vma;
+
+		for (vma = mm->mmap; vma; vma = vma->vm_next)
+			if (vma->vm_file &&
+			    path_equal(&vma->vm_file->f_path,
+				       &mm->exe_file->f_path))
 				goto exit_unlock;
 	}
 
@@ -1835,6 +1838,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
 		goto exit_unlock;
 
+	err = 0;
 	set_mm_exe_file(mm, exe_file);
 exit_unlock:
 	up_write(&mm->mmap_sem);

mm/bootmem.c

@@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {

mm/compaction.c

@@ -701,8 +701,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_lru_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			if (err == -ENOMEM) {
+				ret = COMPACT_PARTIAL;
+				goto out;
+			}
 		}
-
 	}
 
 out:

mm/memblock.c

@@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					   MAX_NUMNODES);
 }
 
-/*
- * Free memblock.reserved.regions
- */
-int __init_memblock memblock_free_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_free(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
-/*
- * Reserve memblock.reserved.regions
- */
-int __init_memblock memblock_reserve_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_reserve(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	type->total_size -= type->regions[r].size;
@@ -184,6 +160,18 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	}
 }
 
+phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
+					phys_addr_t *addr)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	*addr = __pa(memblock.reserved.regions);
+
+	return PAGE_ALIGN(sizeof(struct memblock_region) *
+			  memblock.reserved.max);
+}
+
 /**
  * memblock_double_array - double the size of the memblock regions array
  * @type: memblock type of the regions array being doubled
@@ -204,6 +192,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 						phys_addr_t new_area_size)
 {
 	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_alloc_size, new_alloc_size;
 	phys_addr_t old_size, new_size, addr;
 	int use_slab = slab_is_available();
 	int *in_slab;
@@ -217,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 	/* Calculate new doubled size */
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;
+	/*
+	 * We need to allocated new one align to PAGE_SIZE,
+	 *   so we can free them completely later.
+	 */
+	old_alloc_size = PAGE_ALIGN(old_size);
+	new_alloc_size = PAGE_ALIGN(new_size);
 
 	/* Retrieve the slab flag */
 	if (type == &memblock.memory)
@@ -245,11 +240,11 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 
 		addr = memblock_find_in_range(new_area_start + new_area_size,
 						memblock.current_limit,
-						new_size, sizeof(phys_addr_t));
+						new_alloc_size, PAGE_SIZE);
 		if (!addr && new_area_size)
 			addr = memblock_find_in_range(0,
 					min(new_area_start, memblock.current_limit),
-					new_size, sizeof(phys_addr_t));
+					new_alloc_size, PAGE_SIZE);
 
 		new_array = addr ? __va(addr) : 0;
 	}
@@ -279,13 +274,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 		kfree(old_array);
 	else if (old_array != memblock_memory_init_regions &&
 		 old_array != memblock_reserved_init_regions)
-		memblock_free(__pa(old_array), old_size);
+		memblock_free(__pa(old_array), old_alloc_size);
 
 	/* Reserve the new array if that comes from the memblock.
 	 * Otherwise, we needn't do it
 	 */
 	if (!use_slab)
-		BUG_ON(memblock_reserve(addr, new_size));
+		BUG_ON(memblock_reserve(addr, new_alloc_size));
 
 	/* Update slab flag */
 	*in_slab = use_slab;

mm/memory_hotplug.c

@@ -618,7 +618,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 		pgdat = hotadd_new_pgdat(nid, start);
 		ret = -ENOMEM;
 		if (!pgdat)
-			goto out;
+			goto error;
 		new_pgdat = 1;
 	}
 

mm/nobootmem.c

@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		__free_pages_bootmem(pfn_to_page(i), 0);
 }
 
+static unsigned long __init __free_memory_core(phys_addr_t start,
+				 phys_addr_t end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = min_t(unsigned long,
+				      PFN_DOWN(end), max_low_pfn);
+
+	if (start_pfn > end_pfn)
+		return 0;
+
+	__free_pages_memory(start_pfn, end_pfn);
+
+	return end_pfn - start_pfn;
+}
+
 unsigned long __init free_low_memory_core_early(int nodeid)
 {
 	unsigned long count = 0;
-	phys_addr_t start, end;
+	phys_addr_t start, end, size;
 	u64 i;
 
-	/* free reserved array temporarily so that it's treated as free area */
-	memblock_free_reserved_regions();
+	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+		count += __free_memory_core(start, end);
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		unsigned long start_pfn = PFN_UP(start);
-		unsigned long end_pfn = min_t(unsigned long,
-					      PFN_DOWN(end), max_low_pfn);
-		if (start_pfn < end_pfn) {
-			__free_pages_memory(start_pfn, end_pfn);
-			count += end_pfn - start_pfn;
-		}
-	}
+	/* free range that is used for reserved array if we allocate it */
+	size = get_allocated_memblock_reserved_regions_info(&start);
+	if (size)
+		count += __free_memory_core(start, start + size);
 
-	/* put region array back? */
-	memblock_reserve_reserved_regions();
 	return count;
 }
 
@@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 						   unsigned long size,
 						   unsigned long align,
 						   unsigned long goal,

mm/shmem.c

@@ -263,6 +263,24 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 	return 0;
 }
 
+/*
+ * Sometimes, before we decide whether to proceed or to fail, we must check
+ * that an entry was not already brought back from swap by a racing thread.
+ *
+ * Checking page is not enough: by the time a SwapCache page is locked, it
+ * might be reused, and again be SwapCache, using the same swap as before.
+ */
+static bool shmem_confirm_swap(struct address_space *mapping,
+			       pgoff_t index, swp_entry_t swap)
+{
+	void *item;
+
+	rcu_read_lock();
+	item = radix_tree_lookup(&mapping->page_tree, index);
+	rcu_read_unlock();
+	return item == swp_to_radix_entry(swap);
+}
+
 /*
  * Like add_to_page_cache_locked, but error if expected item has gone.
  */
@@ -270,25 +288,21 @@ static int shmem_add_to_page_cache(struct page *page,
 				   struct address_space *mapping,
 				   pgoff_t index, gfp_t gfp, void *expected)
 {
-	int error = 0;
+	int error;
 
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageSwapBacked(page));
 
-	if (!expected)
-		error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
-	if (!error) {
 	page_cache_get(page);
 	page->mapping = mapping;
 	page->index = index;
 
 	spin_lock_irq(&mapping->tree_lock);
 	if (!expected)
-			error = radix_tree_insert(&mapping->page_tree,
-							index, page);
+		error = radix_tree_insert(&mapping->page_tree, index, page);
 	else
-			error = shmem_radix_tree_replace(mapping, index,
-							expected, page);
+		error = shmem_radix_tree_replace(mapping, index, expected,
+								 page);
 	if (!error) {
 		mapping->nrpages++;
 		__inc_zone_page_state(page, NR_FILE_PAGES);
@@ -299,11 +313,6 @@ static int shmem_add_to_page_cache(struct page *page,
 		spin_unlock_irq(&mapping->tree_lock);
 		page_cache_release(page);
 	}
-		if (!expected)
-			radix_tree_preload_end();
-	}
-	if (error)
-		mem_cgroup_uncharge_cache_page(page);
 	return error;
 }
 
@@ -1124,9 +1133,9 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		/* We have to do this with page locked to prevent races */
 		lock_page(page);
 		if (!PageSwapCache(page) || page_private(page) != swap.val ||
-		    page->mapping) {
+		    !shmem_confirm_swap(mapping, index, swap)) {
 			error = -EEXIST;	/* try again */
-			goto failed;
+			goto unlock;
 		}
 		if (!PageUptodate(page)) {
 			error = -EIO;
@@ -1142,9 +1151,12 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
-		if (!error)
+		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						gfp, swp_to_radix_entry(swap));
+			/* We already confirmed swap, and make no allocation */
+			VM_BUG_ON(error);
+		}
 		if (error)
 			goto failed;
 
@@ -1181,11 +1193,18 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		__set_page_locked(page);
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
-		if (!error)
+		if (error)
+			goto decused;
+		error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 							gfp, NULL);
-		if (error)
+			radix_tree_preload_end();
+		}
+		if (error) {
+			mem_cgroup_uncharge_cache_page(page);
 			goto decused;
+		}
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
@@ -1245,14 +1264,10 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 unacct:
 	shmem_unacct_blocks(info->flags, 1);
 failed:
-	if (swap.val && error != -EINVAL) {
-		struct page *test = find_get_page(mapping, index);
-		if (test && !radix_tree_exceptional_entry(test))
-			page_cache_release(test);
-		/* Have another try if the entry has changed */
-		if (test != swp_to_radix_entry(swap))
+	if (swap.val && error != -EINVAL &&
+	    !shmem_confirm_swap(mapping, index, swap))
 		error = -EEXIST;
-	}
+unlock:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
@@ -1264,7 +1279,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		spin_unlock(&info->lock);
 		goto repeat;
 	}
-	if (error == -EEXIST)
+	if (error == -EEXIST)	/* from above or from radix_tree_insert */
 		goto repeat;
 	return error;
 }
@@ -1692,98 +1707,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	return error;
 }
 
-/*
- * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
- */
-static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
-				    pgoff_t index, pgoff_t end, int origin)
-{
-	struct page *page;
-	struct pagevec pvec;
-	pgoff_t indices[PAGEVEC_SIZE];
-	bool done = false;
-	int i;
-
-	pagevec_init(&pvec, 0);
-	pvec.nr = 1;		/* start small: we may be there already */
-	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					pvec.nr, pvec.pages, indices);
-		if (!pvec.nr) {
-			if (origin == SEEK_DATA)
-				index = end;
-			break;
-		}
-		for (i = 0; i < pvec.nr; i++, index++) {
-			if (index < indices[i]) {
-				if (origin == SEEK_HOLE) {
-					done = true;
-					break;
-				}
-				index = indices[i];
-			}
-			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
-				if (!PageUptodate(page))
-					page = NULL;
-			}
-			if (index >= end ||
-			    (page && origin == SEEK_DATA) ||
-			    (!page && origin == SEEK_HOLE)) {
-				done = true;
-				break;
-			}
-		}
-		shmem_deswap_pagevec(&pvec);
-		pagevec_release(&pvec);
-		pvec.nr = PAGEVEC_SIZE;
-		cond_resched();
-	}
-	return index;
-}
-
-static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
-{
-	struct address_space *mapping;
-	struct inode *inode;
-	pgoff_t start, end;
-	loff_t new_offset;
-
-	if (origin != SEEK_DATA && origin != SEEK_HOLE)
-		return generic_file_llseek_size(file, offset, origin,
-							MAX_LFS_FILESIZE);
-	mapping = file->f_mapping;
-	inode = mapping->host;
-	mutex_lock(&inode->i_mutex);
-	/* We're holding i_mutex so we can access i_size directly */
-
-	if (offset < 0)
-		offset = -EINVAL;
-	else if (offset >= inode->i_size)
-		offset = -ENXIO;
-	else {
-		start = offset >> PAGE_CACHE_SHIFT;
-		end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-		new_offset = shmem_seek_hole_data(mapping, start, end, origin);
-		new_offset <<= PAGE_CACHE_SHIFT;
-		if (new_offset > offset) {
-			if (new_offset < inode->i_size)
-				offset = new_offset;
-			else if (origin == SEEK_DATA)
-				offset = -ENXIO;
-			else
-				offset = inode->i_size;
-		}
-	}
-
-	if (offset >= 0 && offset != file->f_pos) {
-		file->f_pos = offset;
-		file->f_version = 0;
-	}
-	mutex_unlock(&inode->i_mutex);
-	return offset;
-}
-
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
@@ -2787,7 +2710,7 @@ static const struct address_space_operations shmem_aops = {
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
-	.llseek		= shmem_file_llseek,
+	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= shmem_file_aio_read,

mm/sparse.c

@@ -275,8 +275,9 @@ static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
-	pg_data_t *host_pgdat;
-	unsigned long goal;
+	unsigned long goal, limit;
+	unsigned long *p;
+	int nid;
 	/*
 	 * A page may contain usemaps for other sections preventing the
 	 * page being freed and making a section unremovable while
@@ -287,10 +288,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	 * from the same section as the pgdat where possible to avoid
 	 * this problem.
 	 */
-	goal = __pa(pgdat) & PAGE_SECTION_MASK;
-	host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT));
-	return __alloc_bootmem_node_nopanic(host_pgdat, size,
-					    SMP_CACHE_BYTES, goal);
+	goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+	limit = goal + (1UL << PA_SECTION_SHIFT);
+	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+	p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
+					  SMP_CACHE_BYTES, goal, limit);
+	if (!p && limit) {
+		limit = 0;
+		goto again;
+	}
+	return p;
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)

mm/vmscan.c

@@ -2955,14 +2955,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)