Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

25 files changed, 577 insertions, 123 deletions

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a80e32b46c11..09a8743143f3 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/string.h>
+#include <linux/time.h>
 
 struct pci_dev;
 struct pci_bus;
@@ -52,6 +53,7 @@ struct device_node;
 
 #define EEH_PE_ISOLATED         (1 << 0)        /* Isolated PE          */
 #define EEH_PE_RECOVERING       (1 << 1)        /* Recovering PE        */
+#define EEH_PE_PHB_DEAD         (1 << 2)        /* Dead PHB             */
 
 struct eeh_pe {
         int type;                       /* PE type: PHB/Bus/Device      */
@@ -59,8 +61,10 @@ struct eeh_pe {
         int config_addr;                /* Traditional PCI address      */
         int addr;                       /* PE configuration address     */
         struct pci_controller *phb;     /* Associated PHB               */
+        struct pci_bus *bus;            /* Top PCI bus for bus PE       */
         int check_count;                /* Times of ignored error       */
         int freeze_count;               /* Times of froze up            */
+        struct timeval tstamp;          /* Time on first-time freeze    */
         int false_positives;            /* Times of reported #ff's      */
         struct eeh_pe *parent;          /* Parent PE                    */
         struct list_head child_list;    /* Link PE to the child list    */
@@ -95,12 +99,12 @@ struct eeh_dev {
 
 static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
 {
-        return edev->dn;
+        return edev ? edev->dn : NULL;
 }
 
 static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 {
-        return edev->pdev;
+        return edev ? edev->pdev : NULL;
 }
 
 /*
@@ -130,8 +134,9 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 struct eeh_ops {
         char *name;
         int (*init)(void);
+        int (*post_init)(void);
         void* (*of_probe)(struct device_node *dn, void *flag);
-        void* (*dev_probe)(struct pci_dev *dev, void *flag);
+        int (*dev_probe)(struct pci_dev *dev, void *flag);
         int (*set_option)(struct eeh_pe *pe, int option);
         int (*get_pe_addr)(struct eeh_pe *pe);
         int (*get_state)(struct eeh_pe *pe, int *state);
@@ -141,11 +146,12 @@ struct eeh_ops {
         int (*configure_bridge)(struct eeh_pe *pe);
         int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
         int (*write_config)(struct device_node *dn, int where, int size, u32 val);
+        int (*next_error)(struct eeh_pe **pe);
 };
 
 extern struct eeh_ops *eeh_ops;
 extern int eeh_subsystem_enabled;
-extern struct mutex eeh_mutex;
+extern raw_spinlock_t confirm_error_lock;
 extern int eeh_probe_mode;
 
 #define EEH_PROBE_MODE_DEV      (1<<0)  /* From PCI device      */
@@ -166,14 +172,14 @@ static inline int eeh_probe_mode_dev(void)
         return (eeh_probe_mode == EEH_PROBE_MODE_DEV);
 }
 
-static inline void eeh_lock(void)
+static inline void eeh_serialize_lock(unsigned long *flags)
 {
-        mutex_lock(&eeh_mutex);
+        raw_spin_lock_irqsave(&confirm_error_lock, *flags);
 }
 
-static inline void eeh_unlock(void)
+static inline void eeh_serialize_unlock(unsigned long flags)
 {
-        mutex_unlock(&eeh_mutex);
+        raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 }
 
 /*
@@ -184,8 +190,11 @@ static inline void eeh_unlock(void)
 
 typedef void *(*eeh_traverse_func)(void *data, void *flag);
 int eeh_phb_pe_create(struct pci_controller *phb);
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
 int eeh_add_to_parent_pe(struct eeh_dev *edev);
 int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
+void eeh_pe_update_time_stamp(struct eeh_pe *pe);
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
                 eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
@@ -193,12 +202,13 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
 
 void *eeh_dev_init(struct device_node *dn, void *data);
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
+int eeh_init(void);
 int __init eeh_ops_register(struct eeh_ops *ops);
 int __exit eeh_ops_unregister(const char *name);
 unsigned long eeh_check_failure(const volatile void __iomem *token,
                                 unsigned long val);
 int eeh_dev_check_failure(struct eeh_dev *edev);
-void __init eeh_addr_cache_build(void);
+void eeh_addr_cache_build(void);
 void eeh_add_device_tree_early(struct device_node *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
@@ -221,6 +231,11 @@ void eeh_remove_bus_device(struct pci_dev *, int);
 
 #else /* !CONFIG_EEH */
 
+static inline int eeh_init(void)
+{
+        return 0;
+}
+
 static inline void *eeh_dev_init(struct device_node *dn, void *data)
 {
         return NULL;
@@ -245,9 +260,6 @@ static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
 
 static inline void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) { }
 
-static inline void eeh_lock(void) { }
-static inline void eeh_unlock(void) { }
-
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index de67d830151b..89d5670b2eeb 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -31,7 +31,9 @@ struct eeh_event {
         struct eeh_pe           *pe;    /* EEH PE               */
 };
 
+int eeh_event_init(void);
 int eeh_send_failure_event(struct eeh_pe *pe);
+void eeh_remove_event(struct eeh_pe *pe);
 void eeh_handle_event(struct eeh_pe *pe);
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 46793b58a761..07ca627e52c0 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -358,12 +358,12 @@ label##_relon_pSeries:					\
         /* No guest interrupts come through here */     \
         SET_SCRATCH0(r13);              /* save r13 */  \
         EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
-                                       EXC_STD, KVMTEST_PR, vec)
+                                       EXC_STD, NOTEST, vec)
 
 #define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label)             \
         .globl label##_relon_pSeries;                           \
 label##_relon_pSeries:                                          \
-        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);        \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);            \
         EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD)
 
 #define STD_RELON_EXCEPTION_HV(loc, vec, label)         \
@@ -374,12 +374,12 @@ label##_relon_hv:					\
         /* No guest interrupts come through here */     \
         SET_SCRATCH0(r13);      /* save r13 */          \
         EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
-                                       EXC_HV, KVMTEST, vec)
+                                       EXC_HV, NOTEST, vec)
 
 #define STD_RELON_EXCEPTION_HV_OOL(vec, label)                  \
         .globl label##_relon_hv;                                \
 label##_relon_hv:                                               \
-        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec);           \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec);            \
         EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_HV)
 
 /* This associate vector numbers with bits in paca->irq_happened */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index f2498c8e595d..d750336b171d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -191,8 +191,14 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
                                       unsigned long vmaddr)
 {
 }
-#endif /* CONFIG_HUGETLB_PAGE */
 
+#define hugepd_shift(x) 0
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+                                    unsigned pdshift)
+{
+        return 0;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
 
 /*
  * FSL Book3E platforms require special gpage handling - the gpages
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index cbfe678e3dbe..c34656a8925e 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -76,6 +76,9 @@ struct iommu_table {
         struct iommu_pool large_pool;
         struct iommu_pool pools[IOMMU_NR_POOLS];
         unsigned long *it_map;       /* A simple allocation bitmap for now */
+#ifdef CONFIG_IOMMU_API
+        struct iommu_group *it_group;
+#endif
 };
 
 struct scatterlist;
@@ -98,6 +101,8 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
                                             int nid);
+extern void iommu_register_group(struct iommu_table *tbl,
+                                 int pci_domain_number, unsigned long pe_num);
 
 extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                         struct scatterlist *sglist, int nelems,
@@ -125,13 +130,6 @@ extern void iommu_init_early_pSeries(void);
 extern void iommu_init_early_dart(void);
 extern void iommu_init_early_pasemi(void);
 
-#ifdef CONFIG_PCI
-extern void pci_iommu_init(void);
-extern void pci_direct_iommu_init(void);
-#else
-static inline void pci_iommu_init(void) { }
-#endif
-
 extern void alloc_dart_table(void);
 #if defined(CONFIG_PPC64) && defined(CONFIG_PM)
 static inline void iommu_save(void)
@@ -147,5 +145,26 @@ static inline void iommu_restore(void)
 }
 #endif
 
+/* The API to support IOMMU operations for VFIO */
+extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
+                unsigned long ioba, unsigned long tce_value,
+                unsigned long npages);
+extern int iommu_tce_put_param_check(struct iommu_table *tbl,
+                unsigned long ioba, unsigned long tce);
+extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+                unsigned long hwaddr, enum dma_data_direction direction);
+extern unsigned long iommu_clear_tce(struct iommu_table *tbl,
+                unsigned long entry);
+extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+                unsigned long entry, unsigned long pages);
+extern int iommu_put_tce_user_mode(struct iommu_table *tbl,
+                unsigned long entry, unsigned long tce);
+
+extern void iommu_flush_tce(struct iommu_table *tbl);
+extern int iommu_take_ownership(struct iommu_table *tbl);
+extern void iommu_release_ownership(struct iommu_table *tbl);
+
+extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 9c1ff330c805..a1ecb14e4442 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -159,36 +159,46 @@ static inline int hpte_cache_flags_ok(unsigned long ptel, unsigned long io_type)
 }
 
 /*
- * Lock and read a linux PTE.  If it's present and writable, atomically
- * set dirty and referenced bits and return the PTE, otherwise return 0.
+ * If it's present and writable, atomically set dirty and referenced bits and
+ * return the PTE, otherwise return 0. If we find a transparent hugepage
+ * and if it is marked splitting we return 0;
  */
-static inline pte_t kvmppc_read_update_linux_pte(pte_t *p, int writing)
+static inline pte_t kvmppc_read_update_linux_pte(pte_t *ptep, int writing,
+                                                 unsigned int hugepage)
 {
-        pte_t pte, tmp;
-
-        /* wait until _PAGE_BUSY is clear then set it atomically */
-        __asm__ __volatile__ (
-                "1:     ldarx   %0,0,%3\n"
-                "       andi.   %1,%0,%4\n"
-                "       bne-    1b\n"
-                "       ori     %1,%0,%4\n"
-                "       stdcx.  %1,0,%3\n"
-                "       bne-    1b"
-                : "=&r" (pte), "=&r" (tmp), "=m" (*p)
-                : "r" (p), "i" (_PAGE_BUSY)
-                : "cc");
-
-        if (pte_present(pte)) {
-                pte = pte_mkyoung(pte);
-                if (writing && pte_write(pte))
-                        pte = pte_mkdirty(pte);
-        }
+        pte_t old_pte, new_pte = __pte(0);
+
+        while (1) {
+                old_pte = pte_val(*ptep);
+                /*
+                 * wait until _PAGE_BUSY is clear then set it atomically
+                 */
+                if (unlikely(old_pte & _PAGE_BUSY)) {
+                        cpu_relax();
+                        continue;
+                }
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                /* If hugepage and is trans splitting return None */
+                if (unlikely(hugepage &&
+                             pmd_trans_splitting(pte_pmd(old_pte))))
+                        return __pte(0);
+#endif
+                /* If pte is not present return None */
+                if (unlikely(!(old_pte & _PAGE_PRESENT)))
+                        return __pte(0);
 
-        *p = pte;       /* clears _PAGE_BUSY */
+                new_pte = pte_mkyoung(old_pte);
+                if (writing && pte_write(old_pte))
+                        new_pte = pte_mkdirty(new_pte);
 
-        return pte;
+                if (old_pte == __cmpxchg_u64((unsigned long *)ptep, old_pte,
+                                             new_pte))
+                        break;
+        }
+        return new_pte;
 }
 
+
 /* Return HPTE cache control bits corresponding to Linux pte bits */
 static inline unsigned long hpte_cache_bits(unsigned long pte_val)
 {
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index b1e7f2af1016..9b12f88d4adb 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -66,7 +66,8 @@ struct lppaca {
 
         u8      reserved6[48];
         u8      cede_latency_hint;
-        u8      reserved7[7];
+        u8      ebb_regs_in_use;
+        u8      reserved7[6];
         u8      dtl_enable_mask;        /* Dispatch Trace Log mask */
         u8      donate_dedicated_cpu;   /* Donate dedicated CPU cycles */
         u8      fpregs_in_use;
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 92386fc4e82a..8b480901165a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -36,13 +36,13 @@ struct machdep_calls {
 #ifdef CONFIG_PPC64
         void            (*hpte_invalidate)(unsigned long slot,
                                            unsigned long vpn,
-                                           int psize, int ssize,
-                                           int local);
+                                           int bpsize, int apsize,
+                                           int ssize, int local);
         long            (*hpte_updatepp)(unsigned long slot, 
                                          unsigned long newpp, 
                                          unsigned long vpn,
-                                         int psize, int ssize,
-                                         int local);
+                                         int bpsize, int apsize,
+                                         int ssize, int local);
         void            (*hpte_updateboltedpp)(unsigned long newpp, 
                                                unsigned long ea,
                                                int psize, int ssize);
@@ -57,6 +57,9 @@ struct machdep_calls {
         void            (*hpte_removebolted)(unsigned long ea,
                                              int psize, int ssize);
         void            (*flush_hash_range)(unsigned long number, int local);
+        void            (*hugepage_invalidate)(struct mm_struct *mm,
+                                               unsigned char *hpte_slot_array,
+                                               unsigned long addr, int psize);
 
         /* special for kexec, to be called in real mode, linear mapping is
          * destroyed as well */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 2accc9611248..c4cf01197273 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -340,6 +340,20 @@ extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
                      pte_t *ptep, unsigned long trap, int local, int ssize,
                      unsigned int shift, unsigned int mmu_psize);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __hash_page_thp(unsigned long ea, unsigned long access,
+                           unsigned long vsid, pmd_t *pmdp, unsigned long trap,
+                           int local, int ssize, unsigned int psize);
+#else
+static inline int __hash_page_thp(unsigned long ea, unsigned long access,
+                                  unsigned long vsid, pmd_t *pmdp,
+                                  unsigned long trap, int local,
+                                  int ssize, unsigned int psize)
+{
+        BUG();
+        return -1;
+}
+#endif
 extern void hash_failure_debug(unsigned long ea, unsigned long access,
                                unsigned long vsid, unsigned long trap,
                                int ssize, int psize, int lpsize,
diff --git a/arch/powerpc/include/asm/mpc5121.h b/arch/powerpc/include/asm/mpc5121.h
index 885c040d6194..8ae133eaf9fa 100644
--- a/arch/powerpc/include/asm/mpc5121.h
+++ b/arch/powerpc/include/asm/mpc5121.h
@@ -68,6 +68,5 @@ struct mpc512x_lpc {
 };
 
 int mpc512x_cs_config(unsigned int cs, u32 val);
-int __init mpc5121_clk_init(void);
 
 #endif /* __ASM_POWERPC_MPC5121_H__ */
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index c0f9ef90f0b8..4a1ac9fbf186 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -339,6 +339,8 @@ struct mpic
 #endif
 };
 
+extern struct bus_type mpic_subsys;
+
 /*
  * MPIC flags (passed to mpic_alloc)
  *
@@ -393,6 +395,9 @@ struct mpic
 #define MPIC_REGSET_STANDARD            MPIC_REGSET(0)  /* Original MPIC */
 #define MPIC_REGSET_TSI108              MPIC_REGSET(1)  /* Tsi108/109 PIC */
 
+/* Get the version of primary MPIC */
+extern u32 fsl_mpic_primary_get_version(void);
+
 /* Allocate the controller structure and setup the linux irq descs
  * for the range if interrupts passed in. No HW initialization is
  * actually performed.
diff --git a/arch/powerpc/include/asm/mpic_timer.h b/arch/powerpc/include/asm/mpic_timer.h
new file mode 100644
index 000000000000..0e23cd4ac8aa
--- /dev/null
+++ b/arch/powerpc/include/asm/mpic_timer.h
@@ -0,0 +1,46 @@
+/*
+ * arch/powerpc/include/asm/mpic_timer.h
+ *
+ * Header file for Mpic Global Timer
+ *
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * Author: Wang Dongsheng <Dongsheng.Wang@freescale.com>
+ *         Li Yang <leoli@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __MPIC_TIMER__
+#define __MPIC_TIMER__
+
+#include <linux/interrupt.h>
+#include <linux/time.h>
+
+struct mpic_timer {
+        void                    *dev;
+        struct cascade_priv     *cascade_handle;
+        unsigned int            num;
+        unsigned int            irq;
+};
+
+#ifdef CONFIG_MPIC_TIMER
+struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
+                const struct timeval *time);
+void mpic_start_timer(struct mpic_timer *handle);
+void mpic_stop_timer(struct mpic_timer *handle);
+void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time);
+void mpic_free_timer(struct mpic_timer *handle);
+#else
+struct mpic_timer *mpic_request_timer(irq_handler_t fn,  void *dev,
+                const struct timeval *time) { return NULL; }
+void mpic_start_timer(struct mpic_timer *handle) { }
+void mpic_stop_timer(struct mpic_timer *handle) { }
+void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time) { }
+void mpic_free_timer(struct mpic_timer *handle) { }
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index cbb9305ab15a..029fe85722aa 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -117,7 +117,13 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_SET_SLOT_LED_STATUS                55
 #define OPAL_GET_EPOW_STATUS                    56
 #define OPAL_SET_SYSTEM_ATTENTION_LED           57
+#define OPAL_RESERVED1                          58
+#define OPAL_RESERVED2                          59
+#define OPAL_PCI_NEXT_ERROR                     60
+#define OPAL_PCI_EEH_FREEZE_STATUS2             61
+#define OPAL_PCI_POLL                           62
 #define OPAL_PCI_MSI_EOI                        63
+#define OPAL_PCI_GET_PHB_DIAG_DATA2             64
 
 #ifndef __ASSEMBLY__
 
@@ -125,6 +131,7 @@ extern int opal_enter_rtas(struct rtas_args *args,
 enum OpalVendorApiTokens {
         OPAL_START_VENDOR_API_RANGE = 1000, OPAL_END_VENDOR_API_RANGE = 1999
 };
+
 enum OpalFreezeState {
         OPAL_EEH_STOPPED_NOT_FROZEN = 0,
         OPAL_EEH_STOPPED_MMIO_FREEZE = 1,
@@ -134,55 +141,69 @@ enum OpalFreezeState {
         OPAL_EEH_STOPPED_TEMP_UNAVAIL = 5,
         OPAL_EEH_STOPPED_PERM_UNAVAIL = 6
 };
+
 enum OpalEehFreezeActionToken {
         OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO = 1,
         OPAL_EEH_ACTION_CLEAR_FREEZE_DMA = 2,
         OPAL_EEH_ACTION_CLEAR_FREEZE_ALL = 3
 };
+
 enum OpalPciStatusToken {
-        OPAL_EEH_PHB_NO_ERROR = 0,
-        OPAL_EEH_PHB_FATAL = 1,
-        OPAL_EEH_PHB_RECOVERABLE = 2,
-        OPAL_EEH_PHB_BUS_ERROR = 3,
-        OPAL_EEH_PCI_NO_DEVSEL = 4,
-        OPAL_EEH_PCI_TA = 5,
-        OPAL_EEH_PCIEX_UR = 6,
-        OPAL_EEH_PCIEX_CA = 7,
-        OPAL_EEH_PCI_MMIO_ERROR = 8,
-        OPAL_EEH_PCI_DMA_ERROR = 9
+        OPAL_EEH_NO_ERROR       = 0,
+        OPAL_EEH_IOC_ERROR      = 1,
+        OPAL_EEH_PHB_ERROR      = 2,
+        OPAL_EEH_PE_ERROR       = 3,
+        OPAL_EEH_PE_MMIO_ERROR  = 4,
+        OPAL_EEH_PE_DMA_ERROR   = 5
 };
+
+enum OpalPciErrorSeverity {
+        OPAL_EEH_SEV_NO_ERROR   = 0,
+        OPAL_EEH_SEV_IOC_DEAD   = 1,
+        OPAL_EEH_SEV_PHB_DEAD   = 2,
+        OPAL_EEH_SEV_PHB_FENCED = 3,
+        OPAL_EEH_SEV_PE_ER      = 4,
+        OPAL_EEH_SEV_INF        = 5
+};
+
 enum OpalShpcAction {
         OPAL_SHPC_GET_LINK_STATE = 0,
         OPAL_SHPC_GET_SLOT_STATE = 1
 };
+
 enum OpalShpcLinkState {
         OPAL_SHPC_LINK_DOWN = 0,
         OPAL_SHPC_LINK_UP = 1
 };
+
 enum OpalMmioWindowType {
         OPAL_M32_WINDOW_TYPE = 1,
         OPAL_M64_WINDOW_TYPE = 2,
         OPAL_IO_WINDOW_TYPE = 3
 };
+
 enum OpalShpcSlotState {
         OPAL_SHPC_DEV_NOT_PRESENT = 0,
         OPAL_SHPC_DEV_PRESENT = 1
 };
+
 enum OpalExceptionHandler {
         OPAL_MACHINE_CHECK_HANDLER = 1,
         OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2,
         OPAL_SOFTPATCH_HANDLER = 3
 };
+
 enum OpalPendingState {
-        OPAL_EVENT_OPAL_INTERNAL = 0x1,
-        OPAL_EVENT_NVRAM = 0x2,
-        OPAL_EVENT_RTC = 0x4,
-        OPAL_EVENT_CONSOLE_OUTPUT = 0x8,
-        OPAL_EVENT_CONSOLE_INPUT = 0x10,
-        OPAL_EVENT_ERROR_LOG_AVAIL = 0x20,
-        OPAL_EVENT_ERROR_LOG = 0x40,
-        OPAL_EVENT_EPOW = 0x80,
-        OPAL_EVENT_LED_STATUS = 0x100
+        OPAL_EVENT_OPAL_INTERNAL        = 0x1,
+        OPAL_EVENT_NVRAM                = 0x2,
+        OPAL_EVENT_RTC                  = 0x4,
+        OPAL_EVENT_CONSOLE_OUTPUT       = 0x8,
+        OPAL_EVENT_CONSOLE_INPUT        = 0x10,
+        OPAL_EVENT_ERROR_LOG_AVAIL      = 0x20,
+        OPAL_EVENT_ERROR_LOG            = 0x40,
+        OPAL_EVENT_EPOW                 = 0x80,
+        OPAL_EVENT_LED_STATUS           = 0x100,
+        OPAL_EVENT_PCI_ERROR            = 0x200
 };
 
 /* Machine check related definitions */
@@ -364,15 +385,80 @@ struct opal_machine_check_event {
         } u;
 };
 
+enum {
+        OPAL_P7IOC_DIAG_TYPE_NONE       = 0,
+        OPAL_P7IOC_DIAG_TYPE_RGC        = 1,
+        OPAL_P7IOC_DIAG_TYPE_BI         = 2,
+        OPAL_P7IOC_DIAG_TYPE_CI         = 3,
+        OPAL_P7IOC_DIAG_TYPE_MISC       = 4,
+        OPAL_P7IOC_DIAG_TYPE_I2C        = 5,
+        OPAL_P7IOC_DIAG_TYPE_LAST       = 6
+};
+
+struct OpalIoP7IOCErrorData {
+        uint16_t type;
+
+        /* GEM */
+        uint64_t gemXfir;
+        uint64_t gemRfir;
+        uint64_t gemRirqfir;
+        uint64_t gemMask;
+        uint64_t gemRwof;
+
+        /* LEM */
+        uint64_t lemFir;
+        uint64_t lemErrMask;
+        uint64_t lemAction0;
+        uint64_t lemAction1;
+        uint64_t lemWof;
+
+        union {
+                struct OpalIoP7IOCRgcErrorData {
+                        uint64_t rgcStatus;             /* 3E1C10 */
+                        uint64_t rgcLdcp;               /* 3E1C18 */
+                }rgc;
+                struct OpalIoP7IOCBiErrorData {
+                        uint64_t biLdcp0;               /* 3C0100, 3C0118 */
+                        uint64_t biLdcp1;               /* 3C0108, 3C0120 */
+                        uint64_t biLdcp2;               /* 3C0110, 3C0128 */
+                        uint64_t biFenceStatus;         /* 3C0130, 3C0130 */
+
+                        uint8_t  biDownbound;           /* BI Downbound or Upbound */
+                }bi;
+                struct OpalIoP7IOCCiErrorData {
+                        uint64_t ciPortStatus;          /* 3Dn008 */
+                        uint64_t ciPortLdcp;            /* 3Dn010 */
+
+                        uint8_t  ciPort;                /* Index of CI port: 0/1 */
+                }ci;
+        };
+};
+
 /**
  * This structure defines the overlay which will be used to store PHB error
  * data upon request.
  */
 enum {
+        OPAL_PHB_ERROR_DATA_VERSION_1 = 1,
+};
+
+enum {
+        OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1,
+};
+
+enum {
         OPAL_P7IOC_NUM_PEST_REGS = 128,
 };
 
+struct OpalIoPhbErrorCommon {
+        uint32_t version;
+        uint32_t ioType;
+        uint32_t len;
+};
+
 struct OpalIoP7IOCPhbErrorData {
+        struct OpalIoPhbErrorCommon common;
+
         uint32_t brdgCtl;
 
         // P7IOC utl regs
@@ -530,14 +616,21 @@ int64_t opal_pci_map_pe_dma_window_real(uint64_t phb_id, uint16_t pe_number,
                                         uint64_t pci_mem_size);
 int64_t opal_pci_reset(uint64_t phb_id, uint8_t reset_scope, uint8_t assert_state);
 
-int64_t opal_pci_get_hub_diag_data(uint64_t hub_id, void *diag_buffer, uint64_t diag_buffer_len);
-int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer, uint64_t diag_buffer_len);
+int64_t opal_pci_get_hub_diag_data(uint64_t hub_id, void *diag_buffer,
+                                   uint64_t diag_buffer_len);
+int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer,
+                                   uint64_t diag_buffer_len);
+int64_t opal_pci_get_phb_diag_data2(uint64_t phb_id, void *diag_buffer,
+                                    uint64_t diag_buffer_len);
 int64_t opal_pci_fence_phb(uint64_t phb_id);
 int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope);
 int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action);
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
 int64_t opal_get_epow_status(uint64_t *status);
 int64_t opal_set_system_attention_led(uint8_t led_action);
+int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
+                            uint16_t *pci_error_type, uint16_t *severity);
+int64_t opal_pci_poll(uint64_t phb_id);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
@@ -551,6 +644,11 @@ extern void hvc_opal_init_early(void);
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
                                    int depth, void *data);
 
+extern int opal_notifier_register(struct notifier_block *nb);
+extern void opal_notifier_enable(void);
+extern void opal_notifier_disable(void);
+extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val);
+
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
 
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index f265049dd7d6..2dd7bfc459be 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -60,6 +60,7 @@ struct power_pmu {
 #define PPMU_HAS_SSLOT          0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER           0x00000040 /* Has SIER */
 #define PPMU_BHRB               0x00000080 /* has BHRB feature enabled */
+#define PPMU_EBB                0x00000100 /* supports event based branch */
 
 /*
  * Values for flags to get_alternatives()
@@ -68,6 +69,11 @@ struct power_pmu {
 #define PPMU_LIMITED_PMC_REQD   2       /* have to put this on a limited PMC */
 #define PPMU_ONLY_COUNT_RUN     4       /* only counting in run state */
 
+/*
+ * We use the event config bit 63 as a flag to request EBB.
+ */
+#define EVENT_CONFIG_EBB_SHIFT  63
+
 extern int register_power_pmu(struct power_pmu *);
 
 struct pt_regs;
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index b66ae722a8e9..f65e27b09bd3 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -221,17 +221,17 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-        return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+        return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
                                 GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-        kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+        kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
 }
 
 #define __pmd_free_tlb(tlb, pmd, addr)                \
-        pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
+        pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)                \
         pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index 45142d640720..a56b82fb0609 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -33,7 +33,8 @@
 #define PGDIR_MASK      (~(PGDIR_SIZE-1))
 
 /* Bits to mask out from a PMD to get to the PTE page */
-#define PMD_MASKED_BITS         0x1ff
+/* PMDs point to PTE table fragments which are 4K aligned.  */
+#define PMD_MASKED_BITS         0xfff
 /* Bits to mask out from a PGD/PUD to get to the PMD page */
 #define PUD_MASKED_BITS         0x1ff
 
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index e3d55f6f24fe..46db09414a10 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -10,6 +10,7 @@
 #else
 #include <asm/pgtable-ppc64-4k.h>
 #endif
+#include <asm/barrier.h>
 
 #define FIRST_USER_ADDRESS      0
 
@@ -20,7 +21,11 @@
                             PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
-
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX (PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX PMD_INDEX_SIZE
+#endif
 /*
  * Define the address range of the kernel non-linear virtual area
  */
@@ -150,7 +155,7 @@
 #define pmd_present(pmd)        (pmd_val(pmd) != 0)
 #define pmd_clear(pmdp)         (pmd_val(*(pmdp)) = 0)
 #define pmd_page_vaddr(pmd)     (pmd_val(pmd) & ~PMD_MASKED_BITS)
-#define pmd_page(pmd)           virt_to_page(pmd_page_vaddr(pmd))
+extern struct page *pmd_page(pmd_t pmd);
 
 #define pud_set(pudp, pudval)   (pud_val(*(pudp)) = (pudval))
 #define pud_none(pud)           (!pud_val(pud))
@@ -339,43 +344,217 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
+#endif /* __ASSEMBLY__ */
+
+/*
+ * THP pages can't be special. So use the _PAGE_SPECIAL
+ */
+#define _PAGE_SPLITTING _PAGE_SPECIAL
+
+/*
+ * We need to differentiate between explicit huge page and THP huge
+ * page, since THP huge page also need to track real subpage details
+ */
+#define _PAGE_THP_HUGE  _PAGE_4K_PFN
 
 /*
- * find_linux_pte returns the address of a linux pte for a given
- * effective address and directory.  If not found, it returns zero.
+ * set of bits not changed in pmd_modify.
  */
-static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
+#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS |               \
+                         _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \
+                         _PAGE_THP_HUGE)
+
+#ifndef __ASSEMBLY__
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per
+ * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
+ * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
+ *
+ * The last three bits are intentionally left to zero. This memory location
+ * are also used as normal page PTE pointers. So if we have any pointers
+ * left around while we collapse a hugepage, we need to make sure
+ * _PAGE_PRESENT and _PAGE_FILE bits of that are zero when we look at them
+ */
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
 {
-        pgd_t *pg;
-        pud_t *pu;
-        pmd_t *pm;
-        pte_t *pt = NULL;
-
-        pg = pgdir + pgd_index(ea);
-        if (!pgd_none(*pg)) {
-                pu = pud_offset(pg, ea);
-                if (!pud_none(*pu)) {
-                        pm = pmd_offset(pu, ea);
-                        if (pmd_present(*pm))
-                                pt = pte_offset_kernel(pm, ea);
-                }
-        }
-        return pt;
+        return (hpte_slot_array[index] >> 3) & 0x1;
 }
 
-#ifdef CONFIG_HUGETLB_PAGE
-pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-                                 unsigned *shift);
-#else
-static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
-                                               unsigned *shift)
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+                                           int index)
 {
-        if (shift)
-                *shift = 0;
-        return find_linux_pte(pgdir, ea);
+        return hpte_slot_array[index] >> 4;
 }
-#endif /* !CONFIG_HUGETLB_PAGE */
 
-#endif /* __ASSEMBLY__ */
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+                                        unsigned int index, unsigned int hidx)
+{
+        hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
+}
 
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+        /*
+         * The hpte hindex is stored in the pgtable whose address is in the
+         * second half of the PMD
+         *
+         * Order this load with the test for pmd_trans_huge in the caller
+         */
+        smp_rmb();
+        return *(char **)(pmdp + PTRS_PER_PMD);
+
+
+}
+
+extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+                                   pmd_t *pmdp);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
+extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
+extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot);
+extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+                       pmd_t *pmdp, pmd_t pmd);
+extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+                                 pmd_t *pmd);
+
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+        /*
+         * leaf pte for huge page, bottom two bits != 00
+         */
+        return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE);
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+        /*
+         * leaf pte for huge page, bottom two bits != 00
+         */
+        if (pmd_trans_huge(pmd))
+                return pmd_val(pmd) & _PAGE_PRESENT;
+        return 0;
+}
+
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+        if (pmd_trans_huge(pmd))
+                return pmd_val(pmd) & _PAGE_SPLITTING;
+        return 0;
+}
+
+extern int has_transparent_hugepage(void);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+        return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+        return __pmd(pte_val(pte));
+}
+
+static inline pte_t *pmdp_ptep(pmd_t *pmd)
+{
+        return (pte_t *)pmd;
+}
+
+#define pmd_pfn(pmd)            pte_pfn(pmd_pte(pmd))
+#define pmd_young(pmd)          pte_young(pmd_pte(pmd))
+#define pmd_mkold(pmd)          pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_wrprotect(pmd)      pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)        pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)        pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)        pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)          pte_write(pmd_pte(pmd))
+
+static inline pmd_t pmd_mkhuge(pmd_t pmd)
+{
+        /* Do nothing, mk_pmd() does this part.  */
+        return pmd;
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+        pmd_val(pmd) &= ~_PAGE_PRESENT;
+        return pmd;
+}
+
+static inline pmd_t pmd_mksplitting(pmd_t pmd)
+{
+        pmd_val(pmd) |= _PAGE_SPLITTING;
+        return pmd;
+}
+
+#define __HAVE_ARCH_PMD_SAME
+static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+        return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0);
+}
+
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+extern int pmdp_set_access_flags(struct vm_area_struct *vma,
+                                 unsigned long address, pmd_t *pmdp,
+                                 pmd_t entry, int dirty);
+
+extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
+                                         unsigned long addr,
+                                         pmd_t *pmdp, unsigned long clr);
+
+static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
+                                              unsigned long addr, pmd_t *pmdp)
+{
+        unsigned long old;
+
+        if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+                return 0;
+        old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+        return ((old & _PAGE_ACCESSED) != 0);
+}
+
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+                                     unsigned long address, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
+                                  unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
+extern pmd_t pmdp_get_and_clear(struct mm_struct *mm,
+                                unsigned long addr, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
+extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+                              pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+                                      pmd_t *pmdp)
+{
+
+        if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
+                return;
+
+        pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+}
+
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+                                 unsigned long address, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+                                       pgtable_t pgtable);
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+                            pmd_t *pmdp);
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index b6293d26bd39..7d6eacf249cf 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -217,6 +217,12 @@ extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
 
 extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
                        unsigned long end, int write, struct page **pages, int *nr);
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_large(pmd)          0
+#define has_transparent_hugepage() 0
+#endif
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+                                 unsigned *shift);
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/probes.h b/arch/powerpc/include/asm/probes.h
index 5f1e15b68704..3421637cfd7b 100644
--- a/arch/powerpc/include/asm/probes.h
+++ b/arch/powerpc/include/asm/probes.h
@@ -38,5 +38,30 @@ typedef u32 ppc_opcode_t;
 #define is_trap(instr)          (IS_TW(instr) || IS_TWI(instr))
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#define MSR_SINGLESTEP  (MSR_DE)
+#else
+#define MSR_SINGLESTEP  (MSR_SE)
+#endif
+
+/* Enable single stepping for the current task */
+static inline void enable_single_step(struct pt_regs *regs)
+{
+        regs->msr |= MSR_SINGLESTEP;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+        /*
+         * We turn off Critical Input Exception(CE) to ensure that the single
+         * step will be for the instruction we have the probe on; if we don't,
+         * it is possible we'd get the single step reported for CE.
+         */
+        regs->msr &= ~MSR_CE;
+        mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
+#ifdef CONFIG_PPC_47x
+        isync();
+#endif
+#endif
+}
+
+
 #endif /* __KERNEL__ */
 #endif  /* _ASM_POWERPC_PROBES_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 14a658363698..47a35b08b963 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -168,10 +168,10 @@ struct thread_struct {
          * The following help to manage the use of Debug Control Registers
          * om the BookE platforms.
          */
-        unsigned long   dbcr0;
-        unsigned long   dbcr1;
+        uint32_t        dbcr0;
+        uint32_t        dbcr1;
 #ifdef CONFIG_BOOKE
-        unsigned long   dbcr2;
+        uint32_t        dbcr2;
 #endif
         /*
          * The stored value of the DBSR register will be the value at the
@@ -179,7 +179,7 @@ struct thread_struct {
          * user (will never be written to) and has value while helping to
          * describe the reason for the last debug trap.  Torez
          */
-        unsigned long   dbsr;
+        uint32_t        dbsr;
         /*
          * The following will contain addresses used by debug applications
          * to help trace and trap on particular address locations.
@@ -200,7 +200,7 @@ struct thread_struct {
 #endif
 #endif
         /* FP and VSX 0-31 register set */
-        double          fpr[32][TS_FPRWIDTH];
+        double          fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
         struct {
 
                 unsigned int pad;
@@ -287,9 +287,9 @@ struct thread_struct {
         unsigned long   siar;
         unsigned long   sdar;
         unsigned long   sier;
-        unsigned long   mmcr0;
         unsigned long   mmcr2;
-        unsigned long   mmcra;
+        unsigned        mmcr0;
+        unsigned        used_ebb;
 #endif
 };
 
@@ -404,9 +404,7 @@ static inline void prefetchw(const void *x)
 
 #define spin_lock_prefetch(x)   prefetchw(x)
 
-#ifdef CONFIG_PPC64
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
-#endif
 
 #ifdef CONFIG_PPC64
 static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4a9e408644fe..5d7d9c2a5473 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -621,11 +621,15 @@
 #define   MMCR0_PMXE    0x04000000UL /* performance monitor exception enable */
 #define   MMCR0_FCECE   0x02000000UL /* freeze ctrs on enabled cond or event */
 #define   MMCR0_TBEE    0x00400000UL /* time base exception enable */
+#define   MMCR0_EBE     0x00100000UL /* Event based branch enable */
+#define   MMCR0_PMCC    0x000c0000UL /* PMC control */
+#define   MMCR0_PMCC_U6 0x00080000UL /* PMC1-6 are R/W by user (PR) */
 #define   MMCR0_PMC1CE  0x00008000UL /* PMC1 count enable*/
 #define   MMCR0_PMCjCE  0x00004000UL /* PMCj count enable*/
 #define   MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */
 #define   MMCR0_PMAO    0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
 #define   MMCR0_SHRFC   0x00000040UL /* SHRre freeze conditions between threads */
+#define   MMCR0_FC56    0x00000010UL /* freeze counters 5 and 6 */
 #define   MMCR0_FCTI    0x00000008UL /* freeze counters in tags inactive mode */
 #define   MMCR0_FCTA    0x00000004UL /* freeze counters in tags active mode */
 #define   MMCR0_FCWAIT  0x00000002UL /* freeze counter in WAIT state */
@@ -673,6 +677,11 @@
 #define   SIER_SIAR_VALID       0x0400000       /* SIAR contents valid */
 #define   SIER_SDAR_VALID       0x0200000       /* SDAR contents valid */
 
+/* When EBB is enabled, some of MMCR0/MMCR2/SIER are user accessible */
+#define MMCR0_USER_MASK (MMCR0_FC | MMCR0_PMXE | MMCR0_PMAO)
+#define MMCR2_USER_MASK 0x4020100804020000UL /* (FC1P|FC2P|FC3P|FC4P|FC5P|FC6P) */
+#define SIER_USER_MASK  0x7fffffUL
+
 #define SPRN_PA6T_MMCR0 795
 #define   PA6T_MMCR0_EN0        0x0000000000000001UL
 #define   PA6T_MMCR0_EN1        0x0000000000000002UL
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 34fd70488d83..c7a8bfc9f6f5 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -350,8 +350,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg)
                         (devfn << 8) | (reg & 0xff);
 }
 
-extern void __cpuinit rtas_give_timebase(void);
-extern void __cpuinit rtas_take_timebase(void);
+extern void rtas_give_timebase(void);
+extern void rtas_take_timebase(void);
 
 #ifdef CONFIG_PPC_RTAS
 static inline int page_is_rtas_user_buf(unsigned long pfn)
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 200d763a0a67..49a13e0ef234 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -67,4 +67,18 @@ static inline void flush_spe_to_thread(struct task_struct *t)
 }
 #endif
 
+static inline void clear_task_ebb(struct task_struct *t)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+    /* EBB perf events are not inherited, so clear all EBB state. */
+    t->thread.bescr = 0;
+    t->thread.mmcr2 = 0;
+    t->thread.mmcr0 = 0;
+    t->thread.siar = 0;
+    t->thread.sdar = 0;
+    t->thread.sier = 0;
+    t->thread.used_ebb = 0;
+#endif
+}
+
 #endif /* _ASM_POWERPC_SWITCH_TO_H */
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 61a59271665b..2def01ed0cb2 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -165,7 +165,8 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 /* Private function for use by PCI IO mapping code */
 extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
                                      unsigned long end);
-
+extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd,
+                                unsigned long addr);
 #else
 #error Unsupported MMU type
 #endif
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 50f261bc3e95..0d9cecddf8a4 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -22,7 +22,7 @@ extern unsigned long vdso64_rt_sigtramp;
 extern unsigned long vdso32_sigtramp;
 extern unsigned long vdso32_rt_sigtramp;
 
-int __cpuinit vdso_getcpu_init(void);
+int vdso_getcpu_init(void);
 
 #else /* __ASSEMBLY__ */