25 files changed, 224 insertions, 78 deletions

diff --git a/include/linux/ata.h b/include/linux/ata.h
index 08a86d5cdf1b..9a061accd8b8 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -89,6 +89,8 @@ enum {
         ATA_ID_DLF              = 128,
         ATA_ID_CSFO             = 129,
         ATA_ID_CFA_POWER        = 160,
+        ATA_ID_CFA_KEY_MGMT     = 162,
+        ATA_ID_CFA_MODES        = 163,
         ATA_ID_ROT_SPEED        = 217,
         ATA_ID_PIO4             = (1 << 1),
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1b16108a5417..d8bd43bfdcf5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -531,7 +531,7 @@ extern void bio_integrity_endio(struct bio *, int);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
 extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
-extern int bio_integrity_clone(struct bio *, struct bio *, struct bio_set *);
+extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *);
 extern int bioset_integrity_create(struct bio_set *, int);
 extern void bioset_integrity_free(struct bio_set *);
 extern void bio_integrity_init_slab(void);
@@ -542,7 +542,7 @@ extern void bio_integrity_init_slab(void);
 #define bioset_integrity_create(a, b)   (0)
 #define bio_integrity_prep(a)           (0)
 #define bio_integrity_enabled(a)        (0)
-#define bio_integrity_clone(a, b, c)    (0)
+#define bio_integrity_clone(a, b, c,d ) (0)
 #define bioset_integrity_free(a)        do { } while (0)
 #define bio_integrity_free(a, b)        do { } while (0)
 #define bio_integrity_endio(a, b)       do { } while (0)
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 95837bfb5256..455d83219fae 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -65,23 +65,20 @@ extern void free_bootmem(unsigned long addr, unsigned long size);
 #define BOOTMEM_DEFAULT         0
 #define BOOTMEM_EXCLUSIVE       (1<<0)
 
+extern int reserve_bootmem(unsigned long addr,
+                           unsigned long size,
+                           int flags);
 extern int reserve_bootmem_node(pg_data_t *pgdat,
-                                 unsigned long physaddr,
-                                 unsigned long size,
-                                 int flags);
-#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
-extern int reserve_bootmem(unsigned long addr, unsigned long size, int flags);
-#endif
+                                unsigned long physaddr,
+                                unsigned long size,
+                                int flags);
 
-extern void *__alloc_bootmem_nopanic(unsigned long size,
+extern void *__alloc_bootmem(unsigned long size,
                              unsigned long align,
                              unsigned long goal);
-extern void *__alloc_bootmem(unsigned long size,
+extern void *__alloc_bootmem_nopanic(unsigned long size,
                                      unsigned long align,
                                      unsigned long goal);
-extern void *__alloc_bootmem_low(unsigned long size,
-                                 unsigned long align,
-                                 unsigned long goal);
 extern void *__alloc_bootmem_node(pg_data_t *pgdat,
                                   unsigned long size,
                                   unsigned long align,
@@ -90,30 +87,35 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
                                   unsigned long size,
                                   unsigned long align,
                                   unsigned long goal);
+extern void *__alloc_bootmem_low(unsigned long size,
+                                 unsigned long align,
+                                 unsigned long goal);
 extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
                                       unsigned long size,
                                       unsigned long align,
                                       unsigned long goal);
-#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
+
 #define alloc_bootmem(x) \
         __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_nopanic(x) \
         __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low(x) \
-        __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
 #define alloc_bootmem_pages(x) \
         __alloc_bootmem(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_nopanic(x) \
         __alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low_pages(x) \
-        __alloc_bootmem_low(x, PAGE_SIZE, 0)
 #define alloc_bootmem_node(pgdat, x) \
         __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node(pgdat, x) \
         __alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_node_nopanic(pgdat, x) \
+        __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+
+#define alloc_bootmem_low(x) \
+        __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0)
+#define alloc_bootmem_low_pages(x) \
+        __alloc_bootmem_low(x, PAGE_SIZE, 0)
 #define alloc_bootmem_low_pages_node(pgdat, x) \
         __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
-#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
 extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
                                    int flags);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 1514d534deeb..a3ed7cb8ca34 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -52,7 +52,15 @@
 #define __deprecated                    __attribute__((deprecated))
 #define __packed                        __attribute__((packed))
 #define __weak                          __attribute__((weak))
-#define __naked                         __attribute__((naked))
+
+/*
+ * it doesn't make sense on ARM (currently the only user of __naked) to trace
+ * naked functions because then mcount is called without stack and frame pointer
+ * being set up and there is no chance to restore the lr register to the value
+ * before mcount was called.
+ */
+#define __naked                         __attribute__((naked)) notrace
+
 #define __noreturn                      __attribute__((noreturn))
 
 /*
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 384b38d3e8e2..161042746afc 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -234,7 +234,6 @@ struct cpufreq_driver {
         int     (*suspend)      (struct cpufreq_policy *policy, pm_message_t pmsg);
         int     (*resume)       (struct cpufreq_policy *policy);
         struct freq_attr        **attr;
-        bool                    hide_interface;
 };
 
 /* flags */
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index f0413845f20e..1956c8d46d32 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -97,7 +97,6 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t;
 
 /**
  * struct dma_chan_percpu - the per-CPU part of struct dma_chan
- * @refcount: local_t used for open-coded "bigref" counting
  * @memcpy_count: transaction counter
  * @bytes_transferred: byte counter
  */
@@ -114,9 +113,6 @@ struct dma_chan_percpu {
  * @cookie: last cookie value returned to client
  * @chan_id: channel ID for sysfs
  * @dev: class device for sysfs
- * @refcount: kref, used in "bigref" slow-mode
- * @slow_ref: indicates that the DMA channel is free
- * @rcu: the DMA channel's RCU head
  * @device_node: used to add this to the device chan list
  * @local: per-cpu pointer to a struct dma_chan_percpu
  * @client-count: how many clients are using this channel
@@ -213,8 +209,6 @@ struct dma_async_tx_descriptor {
  * @global_node: list_head for global dma_device_list
  * @cap_mask: one or more dma_capability flags
  * @max_xor: maximum number of xor sources, 0 if no capability
- * @refcount: reference count
- * @done: IO completion struct
  * @dev_id: unique device ID
  * @dev: struct device reference for dma mapping api
  * @device_alloc_chan_resources: allocate resources and return the
@@ -227,6 +221,7 @@ struct dma_async_tx_descriptor {
  * @device_prep_dma_interrupt: prepares an end of chain interrupt operation
  * @device_prep_slave_sg: prepares a slave dma operation
  * @device_terminate_all: terminate all pending operations
+ * @device_is_tx_complete: poll for transaction completion
  * @device_issue_pending: push pending transactions to hardware
  */
 struct dma_device {
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index f28440784cf0..2f3427468956 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -24,10 +24,10 @@
 #include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/msi.h>
+#include <linux/irqreturn.h>
 
-#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
 struct intel_iommu;
-
+#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
 struct dmar_drhd_unit {
         struct list_head list;          /* list of drhd units   */
         struct  acpi_dmar_header *hdr;  /* ACPI header          */
@@ -49,7 +49,7 @@ extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
 extern void detect_intel_iommu(void);
-
+extern int enable_drhd_fault_handling(void);
 
 extern int parse_ioapics_under_ir(void);
 extern int alloc_iommu(struct dmar_drhd_unit *);
@@ -63,12 +63,12 @@ static inline int dmar_table_init(void)
 {
         return -ENODEV;
 }
+static inline int enable_drhd_fault_handling(void)
+{
+        return -1;
+}
 #endif /* !CONFIG_DMAR && !CONFIG_INTR_REMAP */
 
-#ifdef CONFIG_INTR_REMAP
-extern int intr_remapping_enabled;
-extern int enable_intr_remapping(int);
-
 struct irte {
         union {
                 struct {
@@ -97,6 +97,10 @@ struct irte {
                 __u64 high;
         };
 };
+#ifdef CONFIG_INTR_REMAP
+extern int intr_remapping_enabled;
+extern int enable_intr_remapping(int);
+
 extern int get_irte(int irq, struct irte *entry);
 extern int modify_irte(int irq, struct irte *irte_modified);
 extern int alloc_irte(struct intel_iommu *iommu, int irq, u16 count);
@@ -111,14 +115,40 @@ extern int irq_remapped(int irq);
 extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev);
 extern struct intel_iommu *map_ioapic_to_ir(int apic);
 #else
+static inline int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+{
+        return -1;
+}
+static inline int modify_irte(int irq, struct irte *irte_modified)
+{
+        return -1;
+}
+static inline int free_irte(int irq)
+{
+        return -1;
+}
+static inline int map_irq_to_irte_handle(int irq, u16 *sub_handle)
+{
+        return -1;
+}
+static inline int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index,
+                               u16 sub_handle)
+{
+        return -1;
+}
+static inline struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
+{
+        return NULL;
+}
+static inline struct intel_iommu *map_ioapic_to_ir(int apic)
+{
+        return NULL;
+}
 #define irq_remapped(irq)               (0)
 #define enable_intr_remapping(mode)     (-1)
 #define intr_remapping_enabled          (0)
 #endif
 
-#ifdef CONFIG_DMAR
-extern const char *dmar_get_fault_reason(u8 fault_reason);
-
 /* Can't use the common MSI interrupt functions
  * since DMAR is not a pci device
  */
@@ -127,8 +157,10 @@ extern void dmar_msi_mask(unsigned int irq);
 extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
+extern irqreturn_t dmar_fault(int irq, void *dev_id);
 extern int arch_setup_dmar_msi(unsigned int irq);
 
+#ifdef CONFIG_DMAR
 extern int iommu_detected, no_iommu;
 extern struct list_head dmar_rmrr_units;
 struct dmar_rmrr_unit {
diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h
index c37e9241fae7..ed21bd3dbd25 100644
--- a/include/linux/hdreg.h
+++ b/include/linux/hdreg.h
@@ -511,7 +511,6 @@ struct hd_driveid {
         unsigned short  words69_70[2];  /* reserved words 69-70
                                          * future command overlap and queuing
                                          */
-        /* HDIO_GET_IDENTITY currently returns only words 0 through 70 */
         unsigned short  words71_74[4];  /* reserved words 71-74
                                          * for IDENTIFY PACKET DEVICE command
                                          */
diff --git a/include/linux/ide.h b/include/linux/ide.h
index fe235b65207e..25087aead657 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -797,6 +797,7 @@ typedef struct hwif_s {
         struct scatterlist *sg_table;
         int sg_max_nents;               /* Maximum number of entries in it */
         int sg_nents;                   /* Current number of entries in it */
+        int orig_sg_nents;
         int sg_dma_direction;           /* dma transfer direction */
 
         /* data phase of the active command (currently only valid for PIO/DMA) */
@@ -866,6 +867,7 @@ struct ide_host {
         unsigned int    n_ports;
         struct device   *dev[2];
         unsigned int    (*init_chipset)(struct pci_dev *);
+        irq_handler_t   irq_handler;
         unsigned long   host_flags;
         void            *host_priv;
         ide_hwif_t      *cur_port;      /* for hosts requiring serialization */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d2e3cbfba14f..78c1262e8704 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -292,6 +292,8 @@ struct intel_iommu {
         spinlock_t      register_lock; /* protect register handling */
         int             seq_id; /* sequence id of the iommu */
         int             agaw; /* agaw of this iommu */
+        unsigned int    irq;
+        unsigned char   name[13];    /* Device Name */
 
 #ifdef CONFIG_DMAR
         unsigned long   *domain_ids; /* bitmap of domains */
@@ -299,8 +301,6 @@ struct intel_iommu {
         spinlock_t      lock; /* protect context, domain ids */
         struct root_entry *root_entry; /* virtual address */
 
-        unsigned int irq;
-        unsigned char name[7];    /* Device Name */
         struct iommu_flush flush;
 #endif
         struct q_inval  *qi;            /* Queued invalidation info */
@@ -321,6 +321,7 @@ extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev);
 extern int alloc_iommu(struct dmar_drhd_unit *drhd);
 extern void free_iommu(struct intel_iommu *iommu);
 extern int dmar_enable_qi(struct intel_iommu *iommu);
+extern void dmar_disable_qi(struct intel_iommu *iommu);
 extern void qi_global_iec(struct intel_iommu *iommu);
 
 extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 5d87bc09a1f5..dc18b87ed722 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -275,7 +275,7 @@ enum {
          * advised to wait only for the following duration before
          * doing SRST.
          */
-        ATA_TMOUT_PMP_SRST_WAIT = 1000,
+        ATA_TMOUT_PMP_SRST_WAIT = 5000,
 
         /* ATA bus states */
         BUS_UNKNOWN             = 0,
@@ -530,6 +530,7 @@ struct ata_queued_cmd {
         unsigned long           flags;          /* ATA_QCFLAG_xxx */
         unsigned int            tag;
         unsigned int            n_elem;
+        unsigned int            orig_n_elem;
 
         int                     dma_dir;
 
@@ -750,7 +751,8 @@ struct ata_port {
         acpi_handle             acpi_handle;
         struct ata_acpi_gtm     __acpi_init_gtm; /* use ata_acpi_init_gtm() */
 #endif
-        u8                      sector_buf[ATA_SECT_SIZE]; /* owned by EH */
+        /* owned by EH */
+        u8                      sector_buf[ATA_SECT_SIZE] ____cacheline_aligned;
 };
 
 /* The following initializer overrides a method to NULL whether one of
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index aa6fe7026de7..51855dfd8adb 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -346,6 +346,7 @@ static inline int __nlm_cmp_addr4(const struct sockaddr *sap1,
         return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr;
 }
 
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
                                   const struct sockaddr *sap2)
 {
@@ -353,6 +354,13 @@ static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
         const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2;
         return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
 }
+#else   /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
+                                  const struct sockaddr *sap2)
+{
+        return 0;
+}
+#endif  /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
 
 /*
  * Compare two host addresses
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 065cdf8c09fb..b1ea37fc7a24 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -104,6 +104,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_CAN_NONLINEAR 0x08000000     /* Has ->fault & does nonlinear pages */
 #define VM_MIXEDMAP     0x10000000      /* Can contain "struct page" and pure PFN pages */
 #define VM_SAO          0x20000000      /* Strong Access Ordering (powerpc) */
+#define VM_PFN_AT_MMAP  0x40000000      /* PFNMAP vma that is fully mapped at mmap time */
 
 #ifndef VM_STACK_DEFAULT_FLAGS          /* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -145,7 +146,7 @@ extern pgprot_t protection_map[16];
  */
 static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
 {
-        return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff);
+        return (vma->vm_flags & VM_PFN_AT_MMAP);
 }
 
 static inline int is_pfn_mapping(struct vm_area_struct *vma)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 92915e81443f..d84feb7bdbf0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -276,4 +276,7 @@ struct mm_struct {
 #endif
 };
 
+/* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
+#define mm_cpumask(mm) (&(mm)->cpu_vm_mask)
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ec54785d34f9..659366734f3f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1079,6 +1079,7 @@ extern void		synchronize_net(void);
 extern int              register_netdevice_notifier(struct notifier_block *nb);
 extern int              unregister_netdevice_notifier(struct notifier_block *nb);
 extern int              init_dummy_netdev(struct net_device *dev);
+extern void             netdev_resync_ops(struct net_device *dev);
 
 extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 extern struct net_device        *dev_get_by_index(struct net *net, int ifindex);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index a550b528319f..2e5f00066afd 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -406,6 +406,8 @@ struct nfs3_setaclargs {
         int                     mask;
         struct posix_acl *      acl_access;
         struct posix_acl *      acl_default;
+        size_t                  len;
+        unsigned int            npages;
         struct page **          pages;
 };
 
diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h
index 54487a99beb8..43011b69297c 100644
--- a/include/linux/nfsacl.h
+++ b/include/linux/nfsacl.h
@@ -37,6 +37,9 @@
 #define NFSACL_MAXPAGES         ((2*(8+12*NFS_ACL_MAX_ENTRIES) + PAGE_SIZE-1) \
                                  >> PAGE_SHIFT)
 
+#define NFS_ACL_MAX_ENTRIES_INLINE      (5)
+#define NFS_ACL_INLINE_BUFSIZE  ((2*(2+3*NFS_ACL_MAX_ENTRIES_INLINE)) << 2)
+
 static inline unsigned int
 nfsacl_size(struct posix_acl *acl_access, struct posix_acl *acl_default)
 {
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 3577ffd90d45..ee5615d65211 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -5,6 +5,7 @@
 #include <linux/slab.h> /* For kmalloc() */
 #include <linux/smp.h>
 #include <linux/cpumask.h>
+#include <linux/pfn.h>
 
 #include <asm/percpu.h>
 
@@ -52,17 +53,18 @@
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
 
-/* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
-#ifndef PERCPU_ENOUGH_ROOM
+/* enough to cover all DEFINE_PER_CPUs in modules */
 #ifdef CONFIG_MODULES
-#define PERCPU_MODULE_RESERVE   8192
+#define PERCPU_MODULE_RESERVE           (8 << 10)
 #else
-#define PERCPU_MODULE_RESERVE   0
+#define PERCPU_MODULE_RESERVE           0
 #endif
 
+#ifndef PERCPU_ENOUGH_ROOM
 #define PERCPU_ENOUGH_ROOM                                              \
-        (__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE)
-#endif  /* PERCPU_ENOUGH_ROOM */
+        (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) +      \
+         PERCPU_MODULE_RESERVE)
+#endif
 
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
@@ -76,52 +78,94 @@
 
 #ifdef CONFIG_SMP
 
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+/* minimum unit size, also is the maximum supported allocation size */
+#define PCPU_MIN_UNIT_SIZE              PFN_ALIGN(64 << 10)
+
+/*
+ * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
+ * back on the first chunk for dynamic percpu allocation if arch is
+ * manually allocating and mapping it for faster access (as a part of
+ * large page mapping for example).
+ *
+ * The following values give between one and two pages of free space
+ * after typical minimal boot (2-way SMP, single disk and NIC) with
+ * both defconfig and a distro config on x86_64 and 32.  More
+ * intelligent way to determine this would be nice.
+ */
+#if BITS_PER_LONG > 32
+#define PERCPU_DYNAMIC_RESERVE          (20 << 10)
+#else
+#define PERCPU_DYNAMIC_RESERVE          (12 << 10)
+#endif
+
+extern void *pcpu_base_addr;
+
+typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno);
+typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
+
+extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
+                                size_t static_size, size_t reserved_size,
+                                ssize_t dyn_size, ssize_t unit_size,
+                                void *base_addr,
+                                pcpu_populate_pte_fn_t populate_pte_fn);
+
+extern ssize_t __init pcpu_embed_first_chunk(
+                                size_t static_size, size_t reserved_size,
+                                ssize_t dyn_size, ssize_t unit_size);
+
+/*
+ * Use this to get to a cpu's version of the per-cpu object
+ * dynamically allocated. Non-atomic access to the current CPU's
+ * version should probably be combined with get_cpu()/put_cpu().
+ */
+#define per_cpu_ptr(ptr, cpu)   SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+
+extern void *__alloc_reserved_percpu(size_t size, size_t align);
+
+#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
 struct percpu_data {
         void *ptrs[1];
 };
 
 #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-/* 
- * Use this to get to a cpu's version of the per-cpu object dynamically
- * allocated. Non-atomic access to the current CPU's version should
- * probably be combined with get_cpu()/put_cpu().
- */ 
-#define percpu_ptr(ptr, cpu)                              \
-({                                                        \
-        struct percpu_data *__p = __percpu_disguise(ptr); \
-        (__typeof__(ptr))__p->ptrs[(cpu)];                \
+
+#define per_cpu_ptr(ptr, cpu)                                           \
+({                                                                      \
+        struct percpu_data *__p = __percpu_disguise(ptr);               \
+        (__typeof__(ptr))__p->ptrs[(cpu)];                              \
 })
 
-extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask);
-extern void percpu_free(void *__pdata);
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
+extern void *__alloc_percpu(size_t size, size_t align);
+extern void free_percpu(void *__pdata);
 
 #else /* CONFIG_SMP */
 
-#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
 
-static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+static inline void *__alloc_percpu(size_t size, size_t align)
 {
-        return kzalloc(size, gfp);
+        /*
+         * Can't easily make larger alignment work with kmalloc.  WARN
+         * on it.  Larger alignment should only be used for module
+         * percpu sections on SMP for which this path isn't used.
+         */
+        WARN_ON_ONCE(align > SMP_CACHE_BYTES);
+        return kzalloc(size, GFP_KERNEL);
 }
 
-static inline void percpu_free(void *__pdata)
+static inline void free_percpu(void *p)
 {
-        kfree(__pdata);
+        kfree(p);
 }
 
 #endif /* CONFIG_SMP */
 
-#define percpu_alloc_mask(size, gfp, mask) \
-        __percpu_alloc_mask((size), (gfp), &(mask))
-
-#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map)
-
-/* (legacy) interface for use without CPU hotplug handling */
-
-#define __alloc_percpu(size)    percpu_alloc_mask((size), GFP_KERNEL, \
-                                                  cpu_possible_map)
-#define alloc_percpu(type)      (type *)__alloc_percpu(sizeof(type))
-#define free_percpu(ptr)        percpu_free((ptr))
-#define per_cpu_ptr(ptr, cpu)   percpu_ptr((ptr), (cpu))
+#define alloc_percpu(type)      (type *)__alloc_percpu(sizeof(type), \
+                                                       __alignof__(type))
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index f3f697df1d71..80044a4f3ab9 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void);
 #define rcu_enter_nohz()        do { } while (0)
 #define rcu_exit_nohz()         do { } while (0)
 
+/* A context switch is a grace period for rcuclassic. */
+static inline int rcu_blocking_is_gp(void)
+{
+        return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 921340a7b71c..528343e6da51 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,6 +52,9 @@ struct rcu_head {
         void (*func)(struct rcu_head *head);
 };
 
+/* Internal to kernel, but needed by rcupreempt.h. */
+extern int rcu_scheduler_active;
+
 #if defined(CONFIG_CLASSIC_RCU)
 #include <linux/rcuclassic.h>
 #elif defined(CONFIG_TREE_RCU)
@@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
 extern int rcu_needs_cpu(int cpu);
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 3e05c09b54a2..74304b4538d8 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void)
 #define rcu_exit_nohz()         do { } while (0)
 #endif /* CONFIG_NO_HZ */
 
+/*
+ * A context switch is a grace period for rcupreempt synchronize_rcu()
+ * only during early boot, before the scheduler has been initialized.
+ * So, how the heck do we get a context switch?  Well, if the caller
+ * invokes synchronize_rcu(), they are willing to accept a context
+ * switch, so we simply pretend that one happened.
+ *
+ * After boot, there might be a blocked or preempted task in an RCU
+ * read-side critical section, so we cannot then take the fastpath.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+        return num_online_cpus() == 1 && !rcu_scheduler_active;
+}
+
 #endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d4368b7975c3..a722fb67bb2d 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void)
 }
 #endif /* CONFIG_NO_HZ */
 
+/* A context switch is a grace period for rcutree. */
+static inline int rcu_blocking_is_gp(void)
+{
+        return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f0a50b20e8a0..46d680643f89 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1418,6 +1418,9 @@ struct task_struct {
 #endif
 };
 
+/* Future-safe accessor for struct task_struct's cpus_allowed. */
+#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed)
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -2303,9 +2306,13 @@ extern long sched_group_rt_runtime(struct task_group *tg);
 extern int sched_group_set_rt_period(struct task_group *tg,
                                       long rt_period_us);
 extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 #endif
 #endif
 
+extern int task_can_switch_user(struct user_struct *up,
+                                        struct task_struct *tsk);
+
 #ifdef CONFIG_TASK_XACCT
 static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
 {
diff --git a/include/linux/serio.h b/include/linux/serio.h
index 1bcb357a01a1..e0417e4d3f15 100644
--- a/include/linux/serio.h
+++ b/include/linux/serio.h
@@ -212,7 +212,7 @@ static inline void serio_unpin_driver(struct serio *serio)
 #define SERIO_FUJITSU   0x35
 #define SERIO_ZHENHUA   0x36
 #define SERIO_INEXIO    0x37
-#define SERIO_TOUCHIT213        0x37
+#define SERIO_TOUCHIT213        0x38
 #define SERIO_W8001     0x39
 
 #endif
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 9c0890c7a06a..a43ebec3a7b9 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -95,6 +95,9 @@ extern struct vm_struct *remove_vm_area(const void *addr);
 
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
                         struct page ***pages);
+extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
+                                    pgprot_t prot, struct page **pages);
+extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
 extern void unmap_kernel_range(unsigned long addr, unsigned long size);
 
 /* Allocate/destroy a 'vmalloc' VM area. */
@@ -110,5 +113,6 @@ extern long vwrite(char *buf, char *addr, unsigned long count);
  */
 extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
+extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
 #endif /* _LINUX_VMALLOC_H */