34 files changed, 375 insertions, 94 deletions

diff --git a/arch/i386/xen/enlighten.c b/arch/i386/xen/enlighten.c
index f0c37511d8da..f01bfcd4bdee 100644
--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -623,8 +623,8 @@ static unsigned long xen_read_cr2_direct(void)
 
 static void xen_write_cr4(unsigned long cr4)
 {
-        /* never allow TSC to be disabled */
-        native_write_cr4(cr4 & ~X86_CR4_TSD);
+        /* Just ignore cr4 changes; Xen doesn't allow us to do
+           anything anyway. */
 }
 
 static unsigned long xen_read_cr3(void)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 727a6699f2f4..c627cf86d1e3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -239,7 +239,7 @@ static void snapshot_tb_and_purr(void *data)
         struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
 
         local_irq_save(flags);
-        p->tb = mftb();
+        p->tb = get_tb_or_rtc();
         p->purr = mfspr(SPRN_PURR);
         wmb();
         p->initialized = 1;
@@ -317,7 +317,7 @@ static void snapshot_purr(void)
  */
 void snapshot_timebase(void)
 {
-        __get_cpu_var(last_jiffy) = get_tb();
+        __get_cpu_var(last_jiffy) = get_tb_or_rtc();
         snapshot_purr();
 }
 
@@ -684,6 +684,8 @@ void timer_interrupt(struct pt_regs * regs)
 
                 write_seqlock(&xtime_lock);
                 tb_next_jiffy = tb_last_jiffy + tb_ticks_per_jiffy;
+                if (__USE_RTC() && tb_next_jiffy >= 1000000000)
+                        tb_next_jiffy -= 1000000000;
                 if (per_cpu(last_jiffy, cpu) >= tb_next_jiffy) {
                         tb_last_jiffy = tb_next_jiffy;
                         do_timer(1);
@@ -977,7 +979,7 @@ void __init time_init(void)
         tb_to_ns_scale = scale;
         tb_to_ns_shift = shift;
         /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
-        boot_tb = get_tb();
+        boot_tb = get_tb_or_rtc();
 
         tm = get_boot_time();
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index cef01e4e8989..213fa31ac537 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -98,6 +98,18 @@ static struct vdso_patch_def vdso_patches[] = {
                 CPU_FTR_USE_TB, 0,
                 "__kernel_gettimeofday", NULL
         },
+        {
+                CPU_FTR_USE_TB, 0,
+                "__kernel_clock_gettime", NULL
+        },
+        {
+                CPU_FTR_USE_TB, 0,
+                "__kernel_clock_getres", NULL
+        },
+        {
+                CPU_FTR_USE_TB, 0,
+                "__kernel_get_tbfreq", NULL
+        },
 };
 
 /*
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index c784edd40ea7..5bebe7fbe056 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -579,7 +579,7 @@ static struct spu *find_victim(struct spu_context *ctx)
                 list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
                         struct spu_context *tmp = spu->ctx;
 
-                        if (tmp->prio > ctx->prio &&
+                        if (tmp && tmp->prio > ctx->prio &&
                             (!victim || tmp->prio > victim->prio))
                                 victim = spu->ctx;
                 }
@@ -611,9 +611,9 @@ static struct spu *find_victim(struct spu_context *ctx)
 
                         mutex_lock(&cbe_spu_info[node].list_mutex);
                         cbe_spu_info[node].nr_active--;
+                        spu_unbind_context(spu, victim);
                         mutex_unlock(&cbe_spu_info[node].list_mutex);
 
-                        spu_unbind_context(spu, victim);
                         victim->stats.invol_ctx_switch++;
                         spu->stats.invol_ctx_switch++;
                         mutex_unlock(&victim->state_mutex);
diff --git a/arch/um/include/kern_util.h b/arch/um/include/kern_util.h
index 8d7f7c1cb9c6..6c2be26f1d7d 100644
--- a/arch/um/include/kern_util.h
+++ b/arch/um/include/kern_util.h
@@ -117,7 +117,7 @@ extern void sigio_handler(int sig, union uml_pt_regs *regs);
 
 extern void copy_sc(union uml_pt_regs *regs, void *from);
 
-unsigned long to_irq_stack(int sig, unsigned long *mask_out);
+extern unsigned long to_irq_stack(unsigned long *mask_out);
 unsigned long from_irq_stack(int nested);
 
 #endif
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 9870febdbead..cf0dd9cf8c43 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -518,13 +518,13 @@ int init_aio_irq(int irq, char *name, irq_handler_t handler)
 
 static unsigned long pending_mask;
 
-unsigned long to_irq_stack(int sig, unsigned long *mask_out)
+unsigned long to_irq_stack(unsigned long *mask_out)
 {
         struct thread_info *ti;
         unsigned long mask, old;
         int nested;
 
-        mask = xchg(&pending_mask, 1 << sig);
+        mask = xchg(&pending_mask, *mask_out);
         if(mask != 0){
                 /* If any interrupts come in at this point, we want to
                  * make sure that their bits aren't lost by our
@@ -534,7 +534,7 @@ unsigned long to_irq_stack(int sig, unsigned long *mask_out)
                  * and pending_mask contains a bit for each interrupt
                  * that came in.
                  */
-                old = 1 << sig;
+                old = *mask_out;
                 do {
                         old |= mask;
                         mask = xchg(&pending_mask, old);
@@ -550,6 +550,7 @@ unsigned long to_irq_stack(int sig, unsigned long *mask_out)
 
                 task = cpu_tasks[ti->cpu].task;
                 tti = task_thread_info(task);
+
                 *ti = *tti;
                 ti->real_thread = tti;
                 task->stack = ti;
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index 6f92f732d253..c3ecc2a84e0c 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -320,7 +320,8 @@ int os_file_size(char *file, unsigned long long *size_out)
         }
 
         if(S_ISBLK(buf.ust_mode)){
-                int fd, blocks;
+                int fd;
+                long blocks;
 
                 fd = os_open_file(file, of_read(OPENFLAGS()), 0);
                 if(fd < 0){
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 18e5c8b67eb8..b98f7ea2d2f6 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -119,7 +119,7 @@ void (*handlers[_NSIG])(int sig, struct sigcontext *sc);
 
 void handle_signal(int sig, struct sigcontext *sc)
 {
-        unsigned long pending = 0;
+        unsigned long pending = 1UL << sig;
 
         do {
                 int nested, bail;
@@ -134,7 +134,7 @@ void handle_signal(int sig, struct sigcontext *sc)
                  * have to return, and the upper handler will deal
                  * with this interrupt.
                  */
-                bail = to_irq_stack(sig, &pending);
+                bail = to_irq_stack(&pending);
                 if(bail)
                         return;
 
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 327c9f2fa626..54816adb8e93 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -374,6 +374,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
         if (unlikely(in_atomic() || !mm))
                 goto bad_area_nosemaphore;
 
+        /*
+         * User-mode registers count as a user access even for any
+         * potential system fault or CPU buglet.
+         */
+        if (user_mode_vm(regs))
+                error_code |= PF_USER;
+
  again:
         /* When running in the kernel we expect faults to occur only to
          * addresses in user space.  All other faults represent errors in the
diff --git a/drivers/base/core.c b/drivers/base/core.c
index e6738bcbe5a9..6de33d7a29ba 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -679,14 +679,26 @@ static int device_add_class_symlinks(struct device *dev)
                         goto out_subsys;
         }
         if (dev->parent) {
-                error = sysfs_create_link(&dev->kobj, &dev->parent->kobj,
-                                          "device");
-                if (error)
-                        goto out_busid;
 #ifdef CONFIG_SYSFS_DEPRECATED
                 {
-                        char * class_name = make_class_name(dev->class->name,
-                                                                &dev->kobj);
+                        struct device *parent = dev->parent;
+                        char *class_name;
+
+                        /*
+                         * In old sysfs stacked class devices had 'device'
+                         * link pointing to real device instead of parent
+                         */
+                        while (parent->class && !parent->bus && parent->parent)
+                                parent = parent->parent;
+
+                        error = sysfs_create_link(&dev->kobj,
+                                                  &parent->kobj,
+                                                  "device");
+                        if (error)
+                                goto out_busid;
+
+                        class_name = make_class_name(dev->class->name,
+                                                        &dev->kobj);
                         if (class_name)
                                 error = sysfs_create_link(&dev->parent->kobj,
                                                         &dev->kobj, class_name);
@@ -694,6 +706,11 @@ static int device_add_class_symlinks(struct device *dev)
                         if (error)
                                 goto out_device;
                 }
+#else
+                error = sysfs_create_link(&dev->kobj, &dev->parent->kobj,
+                                          "device");
+                if (error)
+                        goto out_busid;
 #endif
         }
         return 0;
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 504a95d888b2..84d6aa500e26 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -31,6 +31,7 @@
 #include <linux/genhd.h>
 #include <linux/hdreg.h>
 #include <linux/blkpg.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/mm.h>
diff --git a/drivers/char/agp/agp.h b/drivers/char/agp/agp.h
index 35ab1a9f8e8b..8955e7ff759a 100644
--- a/drivers/char/agp/agp.h
+++ b/drivers/char/agp/agp.h
@@ -176,7 +176,7 @@ struct agp_bridge_data {
 #define I830_GMCH_MEM_MASK              0x1
 #define I830_GMCH_MEM_64M               0x1
 #define I830_GMCH_MEM_128M              0
-#define I830_GMCH_GMS_MASK              0xF0
+#define I830_GMCH_GMS_MASK              0x70
 #define I830_GMCH_GMS_DISABLED          0x00
 #define I830_GMCH_GMS_LOCAL             0x10
 #define I830_GMCH_GMS_STOLEN_512        0x20
@@ -190,6 +190,7 @@ struct agp_bridge_data {
 #define INTEL_I830_ERRSTS       0x92
 
 /* Intel 855GM/852GM registers */
+#define I855_GMCH_GMS_MASK              0xF0
 #define I855_GMCH_GMS_STOLEN_0M         0x0
 #define I855_GMCH_GMS_STOLEN_1M         (0x1 << 4)
 #define I855_GMCH_GMS_STOLEN_4M         (0x2 << 4)
diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index 7c69bf259caa..a5d0e95a227a 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -511,7 +511,7 @@ static void intel_i830_init_gtt_entries(void)
                  */
                 if (IS_G33)
                         size = 0;
-                switch (gmch_ctrl & I830_GMCH_GMS_MASK) {
+                switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
                 case I855_GMCH_GMS_STOLEN_1M:
                         gtt_entries = MB(1) - KB(size);
                         break;
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 9b07f7851061..dd441ff4af56 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2215,7 +2215,8 @@ static int ipmi_pci_resume(struct pci_dev *pdev)
 
 static struct pci_device_id ipmi_pci_devices[] = {
         { PCI_DEVICE(PCI_HP_VENDOR_ID, PCI_MMC_DEVICE_ID) },
-        { PCI_DEVICE_CLASS(PCI_ERMC_CLASSCODE, PCI_ERMC_CLASSCODE_MASK) }
+        { PCI_DEVICE_CLASS(PCI_ERMC_CLASSCODE, PCI_ERMC_CLASSCODE_MASK) },
+        { 0, }
 };
 MODULE_DEVICE_TABLE(pci, ipmi_pci_devices);
 
diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c
index c08a4152ee8f..049a46cc9f87 100644
--- a/drivers/char/mspec.c
+++ b/drivers/char/mspec.c
@@ -67,7 +67,7 @@
 /*
  * Page types allocated by the device.
  */
-enum {
+enum mspec_page_type {
         MSPEC_FETCHOP = 1,
         MSPEC_CACHED,
         MSPEC_UNCACHED
@@ -83,15 +83,25 @@ static int is_sn2;
  * One of these structures is allocated when an mspec region is mmaped. The
  * structure is pointed to by the vma->vm_private_data field in the vma struct.
  * This structure is used to record the addresses of the mspec pages.
+ * This structure is shared by all vma's that are split off from the
+ * original vma when split_vma()'s are done.
+ *
+ * The refcnt is incremented atomically because mm->mmap_sem does not
+ * protect in fork case where multiple tasks share the vma_data.
  */
 struct vma_data {
         atomic_t refcnt;        /* Number of vmas sharing the data. */
-        spinlock_t lock;        /* Serialize access to the vma. */
+        spinlock_t lock;        /* Serialize access to this structure. */
         int count;              /* Number of pages allocated. */
-        int type;               /* Type of pages allocated. */
+        enum mspec_page_type type; /* Type of pages allocated. */
+        int flags;              /* See VMD_xxx below. */
+        unsigned long vm_start; /* Original (unsplit) base. */
+        unsigned long vm_end;   /* Original (unsplit) end. */
         unsigned long maddr[0]; /* Array of MSPEC addresses. */
 };
 
+#define VMD_VMALLOCED 0x1       /* vmalloc'd rather than kmalloc'd */
+
 /* used on shub2 to clear FOP cache in the HUB */
 static unsigned long scratch_page[MAX_NUMNODES];
 #define SH2_AMO_CACHE_ENTRIES   4
@@ -129,8 +139,8 @@ mspec_zero_block(unsigned long addr, int len)
  * mspec_open
  *
  * Called when a device mapping is created by a means other than mmap
- * (via fork, etc.).  Increments the reference count on the underlying
- * mspec data so it is not freed prematurely.
+ * (via fork, munmap, etc.).  Increments the reference count on the
+ * underlying mspec data so it is not freed prematurely.
  */
 static void
 mspec_open(struct vm_area_struct *vma)
@@ -151,34 +161,44 @@ static void
 mspec_close(struct vm_area_struct *vma)
 {
         struct vma_data *vdata;
-        int i, pages, result, vdata_size;
+        int index, last_index, result;
+        unsigned long my_page;
 
         vdata = vma->vm_private_data;
-        if (!atomic_dec_and_test(&vdata->refcnt))
-                return;
 
-        pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-        vdata_size = sizeof(struct vma_data) + pages * sizeof(long);
-        for (i = 0; i < pages; i++) {
-                if (vdata->maddr[i] == 0)
+        BUG_ON(vma->vm_start < vdata->vm_start || vma->vm_end > vdata->vm_end);
+
+        spin_lock(&vdata->lock);
+        index = (vma->vm_start - vdata->vm_start) >> PAGE_SHIFT;
+        last_index = (vma->vm_end - vdata->vm_start) >> PAGE_SHIFT;
+        for (; index < last_index; index++) {
+                if (vdata->maddr[index] == 0)
                         continue;
                 /*
                  * Clear the page before sticking it back
                  * into the pool.
                  */
-                result = mspec_zero_block(vdata->maddr[i], PAGE_SIZE);
+                my_page = vdata->maddr[index];
+                vdata->maddr[index] = 0;
+                spin_unlock(&vdata->lock);
+                result = mspec_zero_block(my_page, PAGE_SIZE);
                 if (!result)
-                        uncached_free_page(vdata->maddr[i]);
+                        uncached_free_page(my_page);
                 else
                         printk(KERN_WARNING "mspec_close(): "
                                "failed to zero page %i\n",
                                result);
+                spin_lock(&vdata->lock);
         }
+        spin_unlock(&vdata->lock);
 
-        if (vdata_size <= PAGE_SIZE)
-                kfree(vdata);
-        else
+        if (!atomic_dec_and_test(&vdata->refcnt))
+                return;
+
+        if (vdata->flags & VMD_VMALLOCED)
                 vfree(vdata);
+        else
+                kfree(vdata);
 }
 
 
@@ -195,7 +215,8 @@ mspec_nopfn(struct vm_area_struct *vma, unsigned long address)
         int index;
         struct vma_data *vdata = vma->vm_private_data;
 
-        index = (address - vma->vm_start) >> PAGE_SHIFT;
+        BUG_ON(address < vdata->vm_start || address >= vdata->vm_end);
+        index = (address - vdata->vm_start) >> PAGE_SHIFT;
         maddr = (volatile unsigned long) vdata->maddr[index];
         if (maddr == 0) {
                 maddr = uncached_alloc_page(numa_node_id());
@@ -237,10 +258,11 @@ static struct vm_operations_struct mspec_vm_ops = {
  * underlying pages.
  */
 static int
-mspec_mmap(struct file *file, struct vm_area_struct *vma, int type)
+mspec_mmap(struct file *file, struct vm_area_struct *vma,
+                                        enum mspec_page_type type)
 {
         struct vma_data *vdata;
-        int pages, vdata_size;
+        int pages, vdata_size, flags = 0;
 
         if (vma->vm_pgoff != 0)
                 return -EINVAL;
@@ -255,12 +277,17 @@ mspec_mmap(struct file *file, struct vm_area_struct *vma, int type)
         vdata_size = sizeof(struct vma_data) + pages * sizeof(long);
         if (vdata_size <= PAGE_SIZE)
                 vdata = kmalloc(vdata_size, GFP_KERNEL);
-        else
+        else {
                 vdata = vmalloc(vdata_size);
+                flags = VMD_VMALLOCED;
+        }
         if (!vdata)
                 return -ENOMEM;
         memset(vdata, 0, vdata_size);
 
+        vdata->vm_start = vma->vm_start;
+        vdata->vm_end = vma->vm_end;
+        vdata->flags = flags;
         vdata->type = type;
         spin_lock_init(&vdata->lock);
         vdata->refcnt = ATOMIC_INIT(1);
diff --git a/drivers/media/video/usbvision/usbvision-cards.c b/drivers/media/video/usbvision/usbvision-cards.c
index 380564cd3317..f09eb102731b 100644
--- a/drivers/media/video/usbvision/usbvision-cards.c
+++ b/drivers/media/video/usbvision/usbvision-cards.c
@@ -1081,6 +1081,7 @@ struct usb_device_id usbvision_table [] = {
         { USB_DEVICE(0x2304, 0x0301), .driver_info=PINNA_LINX_VD_IN_CAB_PAL },
         { USB_DEVICE(0x2304, 0x0419), .driver_info=PINNA_PCTV_BUNGEE_PAL_FM },
         { USB_DEVICE(0x2400, 0x4200), .driver_info=HPG_WINTV },
+        { },    /* terminate list */
 };
 
 MODULE_DEVICE_TABLE (usb, usbvision_table);
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index cff969d05d4a..6f32a35eb106 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -816,7 +816,8 @@ static void __devexit cafe_nand_remove(struct pci_dev *pdev)
 }
 
 static struct pci_device_id cafe_nand_tbl[] = {
-        { 0x11ab, 0x4100, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_MEMORY_FLASH << 8, 0xFFFF0 }
+        { 0x11ab, 0x4100, PCI_ANY_ID, PCI_ANY_ID, PCI_CLASS_MEMORY_FLASH << 8, 0xFFFF0 },
+        { 0, }
 };
 
 MODULE_DEVICE_TABLE(pci, cafe_nand_tbl);
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index 46da5714932c..5ab3492817d1 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -61,7 +61,7 @@
 struct rtc_plat_data {
         struct rtc_device *rtc;
         void __iomem *ioaddr;
-        unsigned long baseaddr;
+        resource_size_t baseaddr;
         unsigned long last_jiffies;
         int irq;
         unsigned int irqen;
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index b2e5481ba3b6..67291b0f8283 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -55,7 +55,7 @@ struct rtc_plat_data {
         void __iomem *ioaddr_rtc;
         size_t size_nvram;
         size_t size;
-        unsigned long baseaddr;
+        resource_size_t baseaddr;
         unsigned long last_jiffies;
 };
 
diff --git a/drivers/video/intelfb/intelfbhw.c b/drivers/video/intelfb/intelfbhw.c
index b21d0dec9283..6a47682d8614 100644
--- a/drivers/video/intelfb/intelfbhw.c
+++ b/drivers/video/intelfb/intelfbhw.c
@@ -1352,7 +1352,7 @@ intelfbhw_program_mode(struct intelfb_info *dinfo,
 
         /* turn off PLL */
         tmp = INREG(dpll_reg);
-        dpll_reg &= ~DPLL_VCO_ENABLE;
+        tmp &= ~DPLL_VCO_ENABLE;
         OUTREG(dpll_reg, tmp);
 
         /* Set PLL parameters */
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 1586807b8177..c1fa1908dba0 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -140,7 +140,8 @@ struct dx_frame
 struct dx_map_entry
 {
         u32 hash;
-        u32 offs;
+        u16 offs;
+        u16 size;
 };
 
 #ifdef CONFIG_EXT3_INDEX
@@ -379,13 +380,28 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 
         entries = (struct dx_entry *) (((char *)&root->info) +
                                        root->info.info_length);
-        assert(dx_get_limit(entries) == dx_root_limit(dir,
-                                                      root->info.info_length));
+
+        if (dx_get_limit(entries) != dx_root_limit(dir,
+                                                   root->info.info_length)) {
+                ext3_warning(dir->i_sb, __FUNCTION__,
+                             "dx entry: limit != root limit");
+                brelse(bh);
+                *err = ERR_BAD_DX_DIR;
+                goto fail;
+        }
+
         dxtrace (printk("Look up %x", hash));
         while (1)
         {
                 count = dx_get_count(entries);
-                assert (count && count <= dx_get_limit(entries));
+                if (!count || count > dx_get_limit(entries)) {
+                        ext3_warning(dir->i_sb, __FUNCTION__,
+                                     "dx entry: no count or count > limit");
+                        brelse(bh);
+                        *err = ERR_BAD_DX_DIR;
+                        goto fail2;
+                }
+
                 p = entries + 1;
                 q = entries + count - 1;
                 while (p <= q)
@@ -423,8 +439,15 @@ dx_probe(struct dentry *dentry, struct inode *dir,
                 if (!(bh = ext3_bread (NULL,dir, dx_get_block(at), 0, err)))
                         goto fail2;
                 at = entries = ((struct dx_node *) bh->b_data)->entries;
-                assert (dx_get_limit(entries) == dx_node_limit (dir));
+                if (dx_get_limit(entries) != dx_node_limit (dir)) {
+                        ext3_warning(dir->i_sb, __FUNCTION__,
+                                     "dx entry: limit != node limit");
+                        brelse(bh);
+                        *err = ERR_BAD_DX_DIR;
+                        goto fail2;
+                }
                 frame++;
+                frame->bh = NULL;
         }
 fail2:
         while (frame >= frame_in) {
@@ -432,6 +455,10 @@ fail2:
                 frame--;
         }
 fail:
+        if (*err == ERR_BAD_DX_DIR)
+                ext3_warning(dir->i_sb, __FUNCTION__,
+                             "Corrupt dir inode %ld, running e2fsck is "
+                             "recommended.", dir->i_ino);
         return NULL;
 }
 
@@ -671,6 +698,10 @@ errout:
  * Directory block splitting, compacting
  */
 
+/*
+ * Create map of hash values, offsets, and sizes, stored at end of block.
+ * Returns number of entries mapped.
+ */
 static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
                         struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
 {
@@ -684,7 +715,8 @@ static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
                         ext3fs_dirhash(de->name, de->name_len, &h);
                         map_tail--;
                         map_tail->hash = h.hash;
-                        map_tail->offs = (u32) ((char *) de - base);
+                        map_tail->offs = (u16) ((char *) de - base);
+                        map_tail->size = le16_to_cpu(de->rec_len);
                         count++;
                         cond_resched();
                 }
@@ -694,6 +726,7 @@ static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
         return count;
 }
 
+/* Sort map by hash value */
 static void dx_sort_map (struct dx_map_entry *map, unsigned count)
 {
         struct dx_map_entry *p, *q, *top = map + count - 1;
@@ -1091,6 +1124,10 @@ static inline void ext3_set_de_type(struct super_block *sb,
 }
 
 #ifdef CONFIG_EXT3_INDEX
+/*
+ * Move count entries from end of map between two memory locations.
+ * Returns pointer to last entry moved.
+ */
 static struct ext3_dir_entry_2 *
 dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
 {
@@ -1109,6 +1146,10 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
         return (struct ext3_dir_entry_2 *) (to - rec_len);
 }
 
+/*
+ * Compact each dir entry in the range to the minimal rec_len.
+ * Returns pointer to last entry in range.
+ */
 static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
 {
         struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base;
@@ -1131,6 +1172,11 @@ static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
         return prev;
 }
 
+/*
+ * Split a full leaf block to make room for a new dir entry.
+ * Allocate a new block, and move entries so that they are approx. equally full.
+ * Returns pointer to de in block into which the new entry will be inserted.
+ */
 static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
                         struct buffer_head **bh,struct dx_frame *frame,
                         struct dx_hash_info *hinfo, int *error)
@@ -1142,7 +1188,7 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
         u32 hash2;
         struct dx_map_entry *map;
         char *data1 = (*bh)->b_data, *data2;
-        unsigned split;
+        unsigned split, move, size, i;
         struct ext3_dir_entry_2 *de = NULL, *de2;
         int     err = 0;
 
@@ -1170,8 +1216,19 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
         count = dx_make_map ((struct ext3_dir_entry_2 *) data1,
                              blocksize, hinfo, map);
         map -= count;
-        split = count/2; // need to adjust to actual middle
         dx_sort_map (map, count);
+        /* Split the existing block in the middle, size-wise */
+        size = 0;
+        move = 0;
+        for (i = count-1; i >= 0; i--) {
+                /* is more than half of this entry in 2nd half of the block? */
+                if (size + map[i].size/2 > blocksize/2)
+                        break;
+                size += map[i].size;
+                move++;
+        }
+        /* map index at which we will split */
+        split = count - move;
         hash2 = map[split].hash;
         continued = hash2 == map[split - 1].hash;
         dxtrace(printk("Split block %i at %x, %i/%i\n",
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index da224974af78..5fdb862e71c4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -140,7 +140,8 @@ struct dx_frame
 struct dx_map_entry
 {
         u32 hash;
-        u32 offs;
+        u16 offs;
+        u16 size;
 };
 
 #ifdef CONFIG_EXT4_INDEX
@@ -379,13 +380,28 @@ dx_probe(struct dentry *dentry, struct inode *dir,
 
         entries = (struct dx_entry *) (((char *)&root->info) +
                                        root->info.info_length);
-        assert(dx_get_limit(entries) == dx_root_limit(dir,
-                                                      root->info.info_length));
+
+        if (dx_get_limit(entries) != dx_root_limit(dir,
+                                                   root->info.info_length)) {
+                ext4_warning(dir->i_sb, __FUNCTION__,
+                             "dx entry: limit != root limit");
+                brelse(bh);
+                *err = ERR_BAD_DX_DIR;
+                goto fail;
+        }
+
         dxtrace (printk("Look up %x", hash));
         while (1)
         {
                 count = dx_get_count(entries);
-                assert (count && count <= dx_get_limit(entries));
+                if (!count || count > dx_get_limit(entries)) {
+                        ext4_warning(dir->i_sb, __FUNCTION__,
+                                     "dx entry: no count or count > limit");
+                        brelse(bh);
+                        *err = ERR_BAD_DX_DIR;
+                        goto fail2;
+                }
+
                 p = entries + 1;
                 q = entries + count - 1;
                 while (p <= q)
@@ -423,8 +439,15 @@ dx_probe(struct dentry *dentry, struct inode *dir,
                 if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err)))
                         goto fail2;
                 at = entries = ((struct dx_node *) bh->b_data)->entries;
-                assert (dx_get_limit(entries) == dx_node_limit (dir));
+                if (dx_get_limit(entries) != dx_node_limit (dir)) {
+                        ext4_warning(dir->i_sb, __FUNCTION__,
+                                     "dx entry: limit != node limit");
+                        brelse(bh);
+                        *err = ERR_BAD_DX_DIR;
+                        goto fail2;
+                }
                 frame++;
+                frame->bh = NULL;
         }
 fail2:
         while (frame >= frame_in) {
@@ -432,6 +455,10 @@ fail2:
                 frame--;
         }
 fail:
+        if (*err == ERR_BAD_DX_DIR)
+                ext4_warning(dir->i_sb, __FUNCTION__,
+                             "Corrupt dir inode %ld, running e2fsck is "
+                             "recommended.", dir->i_ino);
         return NULL;
 }
 
@@ -671,6 +698,10 @@ errout:
  * Directory block splitting, compacting
  */
 
+/*
+ * Create map of hash values, offsets, and sizes, stored at end of block.
+ * Returns number of entries mapped.
+ */
 static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
                         struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
 {
@@ -684,7 +715,8 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
                         ext4fs_dirhash(de->name, de->name_len, &h);
                         map_tail--;
                         map_tail->hash = h.hash;
-                        map_tail->offs = (u32) ((char *) de - base);
+                        map_tail->offs = (u16) ((char *) de - base);
+                        map_tail->size = le16_to_cpu(de->rec_len);
                         count++;
                         cond_resched();
                 }
@@ -694,6 +726,7 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
         return count;
 }
 
+/* Sort map by hash value */
 static void dx_sort_map (struct dx_map_entry *map, unsigned count)
 {
         struct dx_map_entry *p, *q, *top = map + count - 1;
@@ -1089,6 +1122,10 @@ static inline void ext4_set_de_type(struct super_block *sb,
 }
 
 #ifdef CONFIG_EXT4_INDEX
+/*
+ * Move count entries from end of map between two memory locations.
+ * Returns pointer to last entry moved.
+ */
 static struct ext4_dir_entry_2 *
 dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
 {
@@ -1107,6 +1144,10 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
         return (struct ext4_dir_entry_2 *) (to - rec_len);
 }
 
+/*
+ * Compact each dir entry in the range to the minimal rec_len.
+ * Returns pointer to last entry in range.
+ */
 static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size)
 {
         struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base;
@@ -1129,6 +1170,11 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size)
         return prev;
 }
 
+/*
+ * Split a full leaf block to make room for a new dir entry.
+ * Allocate a new block, and move entries so that they are approx. equally full.
+ * Returns pointer to de in block into which the new entry will be inserted.
+ */
 static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
                         struct buffer_head **bh,struct dx_frame *frame,
                         struct dx_hash_info *hinfo, int *error)
@@ -1140,7 +1186,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
         u32 hash2;
         struct dx_map_entry *map;
         char *data1 = (*bh)->b_data, *data2;
-        unsigned split;
+        unsigned split, move, size, i;
         struct ext4_dir_entry_2 *de = NULL, *de2;
         int     err = 0;
 
@@ -1168,8 +1214,19 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
         count = dx_make_map ((struct ext4_dir_entry_2 *) data1,
                              blocksize, hinfo, map);
         map -= count;
-        split = count/2; // need to adjust to actual middle
         dx_sort_map (map, count);
+        /* Split the existing block in the middle, size-wise */
+        size = 0;
+        move = 0;
+        for (i = count-1; i >= 0; i--) {
+                /* is more than half of this entry in 2nd half of the block? */
+                if (size + map[i].size/2 > blocksize/2)
+                        break;
+                size += map[i].size;
+                move++;
+        }
+        /* map index at which we will split */
+        split = count - move;
         hash2 = map[split].hash;
         continued = hash2 == map[split - 1].hash;
         dxtrace(printk("Split block %i at %x, %i/%i\n",
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 8ed593766f16..b878528b64c1 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -345,8 +345,8 @@ void __exit unregister_nfs_fs(void)
         unregister_shrinker(&acl_shrinker);
 #ifdef CONFIG_NFS_V4
         unregister_filesystem(&nfs4_fs_type);
-        nfs_unregister_sysctl();
 #endif
+        nfs_unregister_sysctl();
         unregister_filesystem(&nfs_fs_type);
 }
 
diff --git a/include/asm-powerpc/time.h b/include/asm-powerpc/time.h
index d7f5ddfbaac7..c104c15c6625 100644
--- a/include/asm-powerpc/time.h
+++ b/include/asm-powerpc/time.h
@@ -149,6 +149,11 @@ static inline u64 get_tb(void)
 }
 #endif /* !CONFIG_PPC64 */
 
+static inline u64 get_tb_or_rtc(void)
+{
+        return __USE_RTC() ? get_rtc() : get_tb();
+}
+
 static inline void set_tb(unsigned int upper, unsigned int lower)
 {
         mtspr(SPRN_TBWL, 0);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5bdd656e88cf..a020eb2d4e2a 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -159,7 +159,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-                unsigned long addr, gfp_t gfp_flags);
+                unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol);
 extern unsigned slab_node(struct mempolicy *policy);
 
 extern enum zone_type policy_zone;
@@ -256,7 +256,7 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 #define set_cpuset_being_rebound(x) do {} while (0)
 
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-                unsigned long addr, gfp_t gfp_flags)
+                unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
 {
         return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags);
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f4e324ed2e44..5445eaec6908 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -593,7 +593,7 @@ struct user_struct {
 #endif
 
         /* Hash table maintenance information */
-        struct list_head uidhash_list;
+        struct hlist_node uidhash_node;
         uid_t uid;
 };
 
@@ -1472,6 +1472,7 @@ static inline struct user_struct *get_uid(struct user_struct *u)
 }
 extern void free_uid(struct user_struct *);
 extern void switch_uid(struct user_struct *);
+extern void release_uids(struct user_namespace *ns);
 
 #include <asm/current.h>
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 1101b0ce878f..b5f41d4c2eec 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -11,7 +11,7 @@
 
 struct user_namespace {
         struct kref             kref;
-        struct list_head        uidhash_table[UIDHASH_SZ];
+        struct hlist_head       uidhash_table[UIDHASH_SZ];
         struct user_struct      *root_user;
 };
 
diff --git a/init/Kconfig b/init/Kconfig
index 96b54595f1dc..d54d0cadcc06 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -488,6 +488,7 @@ config SIGNALFD
 config TIMERFD
         bool "Enable timerfd() system call" if EMBEDDED
         select ANON_INODES
+        depends on BROKEN
         default y
         help
           Enable the timerfd() system call that allows to receive timer
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index a6b4c0c08e13..fd4fc12d2624 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -57,8 +57,10 @@ static void __init handle_initrd(void)
 
         pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
         if (pid > 0)
-                while (pid != sys_wait4(-1, NULL, 0, NULL))
+                while (pid != sys_wait4(-1, NULL, 0, NULL)) {
+                        try_to_freeze();
                         yield();
+                }
 
         /* move initrd to rootfs' /old */
         sys_fchdir(old_fd);
diff --git a/kernel/user.c b/kernel/user.c
index e7d11cef6998..9ca2848fc356 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -55,25 +55,22 @@ struct user_struct root_user = {
 /*
  * These routines must be called with the uidhash spinlock held!
  */
-static inline void uid_hash_insert(struct user_struct *up, struct list_head *hashent)
+static inline void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 {
-        list_add(&up->uidhash_list, hashent);
+        hlist_add_head(&up->uidhash_node, hashent);
 }
 
 static inline void uid_hash_remove(struct user_struct *up)
 {
-        list_del(&up->uidhash_list);
+        hlist_del_init(&up->uidhash_node);
 }
 
-static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *hashent)
+static inline struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 {
-        struct list_head *up;
-
-        list_for_each(up, hashent) {
-                struct user_struct *user;
-
-                user = list_entry(up, struct user_struct, uidhash_list);
+        struct user_struct *user;
+        struct hlist_node *h;
 
+        hlist_for_each_entry(user, h, hashent, uidhash_node) {
                 if(user->uid == uid) {
                         atomic_inc(&user->__count);
                         return user;
@@ -122,7 +119,7 @@ void free_uid(struct user_struct *up)
 
 struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
 {
-        struct list_head *hashent = uidhashentry(ns, uid);
+        struct hlist_head *hashent = uidhashentry(ns, uid);
         struct user_struct *up;
 
         spin_lock_irq(&uidhash_lock);
@@ -202,6 +199,30 @@ void switch_uid(struct user_struct *new_user)
         suid_keys(current);
 }
 
+void release_uids(struct user_namespace *ns)
+{
+        int i;
+        unsigned long flags;
+        struct hlist_head *head;
+        struct hlist_node *nd;
+
+        spin_lock_irqsave(&uidhash_lock, flags);
+        /*
+         * collapse the chains so that the user_struct-s will
+         * be still alive, but not in hashes. subsequent free_uid()
+         * will free them.
+         */
+        for (i = 0; i < UIDHASH_SZ; i++) {
+                head = ns->uidhash_table + i;
+                while (!hlist_empty(head)) {
+                        nd = head->first;
+                        hlist_del_init(nd);
+                }
+        }
+        spin_unlock_irqrestore(&uidhash_lock, flags);
+
+        free_uid(ns->root_user);
+}
 
 static int __init uid_cache_init(void)
 {
@@ -211,7 +232,7 @@ static int __init uid_cache_init(void)
                         0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
         for(n = 0; n < UIDHASH_SZ; ++n)
-                INIT_LIST_HEAD(init_user_ns.uidhash_table + n);
+                INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
 
         /* Insert the root user immediately (init already runs as root) */
         spin_lock_irq(&uidhash_lock);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 85af9422ea6e..7af90fc4f0fd 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -39,7 +39,7 @@ static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
         kref_init(&ns->kref);
 
         for (n = 0; n < UIDHASH_SZ; ++n)
-                INIT_LIST_HEAD(ns->uidhash_table + n);
+                INIT_HLIST_HEAD(ns->uidhash_table + n);
 
         /* Insert new root user.  */
         ns->root_user = alloc_uid(ns, 0);
@@ -81,7 +81,7 @@ void free_user_ns(struct kref *kref)
         struct user_namespace *ns;
 
         ns = container_of(kref, struct user_namespace, kref);
-        free_uid(ns->root_user);
+        release_uids(ns);
         kfree(ns);
 }
 
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 9d8180a0f0d8..816d7b24fa03 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -28,7 +28,9 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
         if (!ns)
                 return ERR_PTR(-ENOMEM);
 
+        down_read(&uts_sem);
         memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+        up_read(&uts_sem);
         kref_init(&ns->kref);
         return ns;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index de4cf458d6e1..84c795ee2d65 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -71,8 +71,9 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 {
         int nid;
         struct page *page = NULL;
+        struct mempolicy *mpol;
         struct zonelist *zonelist = huge_zonelist(vma, address,
-                                                htlb_alloc_mask);
+                                        htlb_alloc_mask, &mpol);
         struct zone **z;
 
         for (z = zonelist->zones; *z; z++) {
@@ -87,6 +88,7 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
                         break;
                 }
         }
+        mpol_free(mpol);        /* unref if mpol !NULL */
         return page;
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index bb54b88c3d5a..3d6ac9505d07 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1077,21 +1077,37 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
 
 #endif
 
-/* Return effective policy for a VMA */
+/*
+ * get_vma_policy(@task, @vma, @addr)
+ * @task - task for fallback if vma policy == default
+ * @vma   - virtual memory area whose policy is sought
+ * @addr  - address in @vma for shared policy lookup
+ *
+ * Returns effective policy for a VMA at specified address.
+ * Falls back to @task or system default policy, as necessary.
+ * Returned policy has extra reference count if shared, vma,
+ * or some other task's policy [show_numa_maps() can pass
+ * @task != current].  It is the caller's responsibility to
+ * free the reference in these cases.
+ */
 static struct mempolicy * get_vma_policy(struct task_struct *task,
                 struct vm_area_struct *vma, unsigned long addr)
 {
         struct mempolicy *pol = task->mempolicy;
+        int shared_pol = 0;
 
         if (vma) {
-                if (vma->vm_ops && vma->vm_ops->get_policy)
+                if (vma->vm_ops && vma->vm_ops->get_policy) {
                         pol = vma->vm_ops->get_policy(vma, addr);
-                else if (vma->vm_policy &&
+                        shared_pol = 1; /* if pol non-NULL, add ref below */
+                } else if (vma->vm_policy &&
                                 vma->vm_policy->policy != MPOL_DEFAULT)
                         pol = vma->vm_policy;
         }
         if (!pol)
                 pol = &default_policy;
+        else if (!shared_pol && pol != current->mempolicy)
+                mpol_get(pol);  /* vma or other task's policy */
         return pol;
 }
 
@@ -1207,19 +1223,45 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 }
 
 #ifdef CONFIG_HUGETLBFS
-/* Return a zonelist suitable for a huge page allocation. */
+/*
+ * huge_zonelist(@vma, @addr, @gfp_flags, @mpol)
+ * @vma = virtual memory area whose policy is sought
+ * @addr = address in @vma for shared policy lookup and interleave policy
+ * @gfp_flags = for requested zone
+ * @mpol = pointer to mempolicy pointer for reference counted 'BIND policy
+ *
+ * Returns a zonelist suitable for a huge page allocation.
+ * If the effective policy is 'BIND, returns pointer to policy's zonelist.
+ * If it is also a policy for which get_vma_policy() returns an extra
+ * reference, we must hold that reference until after allocation.
+ * In that case, return policy via @mpol so hugetlb allocation can drop
+ * the reference.  For non-'BIND referenced policies, we can/do drop the
+ * reference here, so the caller doesn't need to know about the special case
+ * for default and current task policy.
+ */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
-                                                        gfp_t gfp_flags)
+                                gfp_t gfp_flags, struct mempolicy **mpol)
 {
         struct mempolicy *pol = get_vma_policy(current, vma, addr);
+        struct zonelist *zl;
 
+        *mpol = NULL;           /* probably no unref needed */
         if (pol->policy == MPOL_INTERLEAVE) {
                 unsigned nid;
 
                 nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
+                __mpol_free(pol);               /* finished with pol */
                 return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
         }
-        return zonelist_policy(GFP_HIGHUSER, pol);
+
+        zl = zonelist_policy(GFP_HIGHUSER, pol);
+        if (unlikely(pol != &default_policy && pol != current->mempolicy)) {
+                if (pol->policy != MPOL_BIND)
+                        __mpol_free(pol);       /* finished with pol */
+                else
+                        *mpol = pol;    /* unref needed after allocation */
+        }
+        return zl;
 }
 #endif
 
@@ -1264,6 +1306,7 @@ struct page *
 alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 {
         struct mempolicy *pol = get_vma_policy(current, vma, addr);
+        struct zonelist *zl;
 
         cpuset_update_task_memory_state();
 
@@ -1273,7 +1316,19 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
                 nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
                 return alloc_page_interleave(gfp, 0, nid);
         }
-        return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
+        zl = zonelist_policy(gfp, pol);
+        if (pol != &default_policy && pol != current->mempolicy) {
+                /*
+                 * slow path: ref counted policy -- shared or vma
+                 */
+                struct page *page =  __alloc_pages(gfp, 0, zl);
+                __mpol_free(pol);
+                return page;
+        }
+        /*
+         * fast path:  default or task policy
+         */
+        return __alloc_pages(gfp, 0, zl);
 }
 
 /**
@@ -1872,6 +1927,7 @@ int show_numa_map(struct seq_file *m, void *v)
         struct numa_maps *md;
         struct file *file = vma->vm_file;
         struct mm_struct *mm = vma->vm_mm;
+        struct mempolicy *pol;
         int n;
         char buffer[50];
 
@@ -1882,8 +1938,13 @@ int show_numa_map(struct seq_file *m, void *v)
         if (!md)
                 return 0;
 
-        mpol_to_str(buffer, sizeof(buffer),
-                            get_vma_policy(priv->task, vma, vma->vm_start));
+        pol = get_vma_policy(priv->task, vma, vma->vm_start);
+        mpol_to_str(buffer, sizeof(buffer), pol);
+        /*
+         * unref shared or other task's mempolicy
+         */
+        if (pol != &default_policy && pol != current->mempolicy)
+                __mpol_free(pol);
 
         seq_printf(m, "%08lx %s", vma->vm_start, buffer);