11 files changed, 244 insertions, 6 deletions

diff --git a/include/asm-ia64/acpi.h b/include/asm-ia64/acpi.h
index cd1cc39b5599..fcfad326f4c7 100644
--- a/include/asm-ia64/acpi.h
+++ b/include/asm-ia64/acpi.h
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/numa.h>
 #include <asm/system.h>
+#include <asm/numa.h>
 
 #define COMPILER_DEPENDENT_INT64        long
 #define COMPILER_DEPENDENT_UINT64       unsigned long
@@ -115,7 +116,11 @@ extern unsigned int is_cpu_cpei_target(unsigned int cpu);
 extern void set_cpei_target_cpu(unsigned int cpu);
 extern unsigned int get_cpei_target_cpu(void);
 extern void prefill_possible_map(void);
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
 extern int additional_cpus;
+#else
+#define additional_cpus 0
+#endif
 
 #ifdef CONFIG_ACPI_NUMA
 #if MAX_NUMNODES > 256
@@ -129,6 +134,34 @@ extern int __initdata nid_to_pxm_map[MAX_NUMNODES];
 
 #define acpi_unlazy_tlb(x)
 
+#ifdef CONFIG_ACPI_NUMA
+extern cpumask_t early_cpu_possible_map;
+#define for_each_possible_early_cpu(cpu)  \
+        for_each_cpu_mask((cpu), early_cpu_possible_map)
+
+static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
+{
+        int low_cpu, high_cpu;
+        int cpu;
+        int next_nid = 0;
+
+        low_cpu = cpus_weight(early_cpu_possible_map);
+
+        high_cpu = max(low_cpu, min_cpus);
+        high_cpu = min(high_cpu + reserve_cpus, NR_CPUS);
+
+        for (cpu = low_cpu; cpu < high_cpu; cpu++) {
+                cpu_set(cpu, early_cpu_possible_map);
+                if (node_cpuid[cpu].nid == NUMA_NO_NODE) {
+                        node_cpuid[cpu].nid = next_nid;
+                        next_nid++;
+                        if (next_nid >= num_online_nodes())
+                                next_nid = 0;
+                }
+        }
+}
+#endif /* CONFIG_ACPI_NUMA */
+
 #endif /*__KERNEL__*/
 
 #endif /*_ASM_ACPI_H*/
diff --git a/include/asm-ia64/cputime.h b/include/asm-ia64/cputime.h
index 72400a78002a..f9abdec6577a 100644
--- a/include/asm-ia64/cputime.h
+++ b/include/asm-ia64/cputime.h
@@ -1,6 +1,110 @@
+/*
+ * include/asm-ia64/cputime.h:
+ *              Definitions for measuring cputime on ia64 machines.
+ *
+ * Based on <asm-powerpc/cputime.h>.
+ *
+ * Copyright (C) 2007 FUJITSU LIMITED
+ * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.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.
+ *
+ * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in nsec.
+ * Otherwise we measure cpu time in jiffies using the generic definitions.
+ */
+
 #ifndef __IA64_CPUTIME_H
 #define __IA64_CPUTIME_H
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #include <asm-generic/cputime.h>
+#else
+
+#include <linux/time.h>
+#include <linux/jiffies.h>
+#include <asm/processor.h>
+
+typedef u64 cputime_t;
+typedef u64 cputime64_t;
+
+#define cputime_zero                    ((cputime_t)0)
+#define cputime_max                     ((~((cputime_t)0) >> 1) - 1)
+#define cputime_add(__a, __b)           ((__a) +  (__b))
+#define cputime_sub(__a, __b)           ((__a) -  (__b))
+#define cputime_div(__a, __n)           ((__a) /  (__n))
+#define cputime_halve(__a)              ((__a) >> 1)
+#define cputime_eq(__a, __b)            ((__a) == (__b))
+#define cputime_gt(__a, __b)            ((__a) >  (__b))
+#define cputime_ge(__a, __b)            ((__a) >= (__b))
+#define cputime_lt(__a, __b)            ((__a) <  (__b))
+#define cputime_le(__a, __b)            ((__a) <= (__b))
+
+#define cputime64_zero                  ((cputime64_t)0)
+#define cputime64_add(__a, __b)         ((__a) + (__b))
+#define cputime64_sub(__a, __b)         ((__a) - (__b))
+#define cputime_to_cputime64(__ct)      (__ct)
+
+/*
+ * Convert cputime <-> jiffies (HZ)
+ */
+#define cputime_to_jiffies(__ct)        ((__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies_to_cputime(__jif)       ((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)    ((__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies64_to_cputime64(__jif)   ((__jif) * (NSEC_PER_SEC / HZ))
+
+/*
+ * Convert cputime <-> milliseconds
+ */
+#define cputime_to_msecs(__ct)          ((__ct) / NSEC_PER_MSEC)
+#define msecs_to_cputime(__msecs)       ((__msecs) * NSEC_PER_MSEC)
+
+/*
+ * Convert cputime <-> seconds
+ */
+#define cputime_to_secs(__ct)           ((__ct) / NSEC_PER_SEC)
+#define secs_to_cputime(__secs)         ((__secs) * NSEC_PER_SEC)
+
+/*
+ * Convert cputime <-> timespec (nsec)
+ */
+static inline cputime_t timespec_to_cputime(const struct timespec *val)
+{
+        cputime_t ret = val->tv_sec * NSEC_PER_SEC;
+        return (ret + val->tv_nsec);
+}
+static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
+{
+        val->tv_sec  = ct / NSEC_PER_SEC;
+        val->tv_nsec = ct % NSEC_PER_SEC;
+}
+
+/*
+ * Convert cputime <-> timeval (msec)
+ */
+static inline cputime_t timeval_to_cputime(struct timeval *val)
+{
+        cputime_t ret = val->tv_sec * NSEC_PER_SEC;
+        return (ret + val->tv_usec * NSEC_PER_USEC);
+}
+static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
+{
+        val->tv_sec = ct / NSEC_PER_SEC;
+        val->tv_usec = (ct % NSEC_PER_SEC) / NSEC_PER_USEC;
+}
+
+/*
+ * Convert cputime <-> clock (USER_HZ)
+ */
+#define cputime_to_clock_t(__ct)        ((__ct) / (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)         ((__x) * (NSEC_PER_SEC / USER_HZ))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)      cputime_to_clock_t((cputime_t)__ct)
 
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 #endif /* __IA64_CPUTIME_H */
diff --git a/include/asm-ia64/elf.h b/include/asm-ia64/elf.h
index f8e83eca67a2..5e0c1a6bce8d 100644
--- a/include/asm-ia64/elf.h
+++ b/include/asm-ia64/elf.h
@@ -26,6 +26,7 @@
 #define ELF_ARCH        EM_IA_64
 
 #define USE_ELF_CORE_DUMP
+#define CORE_DUMP_USE_REGSET
 
 /* Least-significant four bits of ELF header's e_flags are OS-specific.  The bits are
    interpreted as follows by Linux: */
@@ -154,6 +155,30 @@ extern void ia64_init_addr_space (void);
 #define ELF_NGREG       128     /* we really need just 72 but let's leave some headroom... */
 #define ELF_NFPREG      128     /* f0 and f1 could be omitted, but so what... */
 
+/* elf_gregset_t register offsets */
+#define ELF_GR_0_OFFSET     0
+#define ELF_NAT_OFFSET     (32 * sizeof(elf_greg_t))
+#define ELF_PR_OFFSET      (33 * sizeof(elf_greg_t))
+#define ELF_BR_0_OFFSET    (34 * sizeof(elf_greg_t))
+#define ELF_CR_IIP_OFFSET  (42 * sizeof(elf_greg_t))
+#define ELF_CFM_OFFSET     (43 * sizeof(elf_greg_t))
+#define ELF_CR_IPSR_OFFSET (44 * sizeof(elf_greg_t))
+#define ELF_GR_OFFSET(i)   (ELF_GR_0_OFFSET + i * sizeof(elf_greg_t))
+#define ELF_BR_OFFSET(i)   (ELF_BR_0_OFFSET + i * sizeof(elf_greg_t))
+#define ELF_AR_RSC_OFFSET  (45 * sizeof(elf_greg_t))
+#define ELF_AR_BSP_OFFSET  (46 * sizeof(elf_greg_t))
+#define ELF_AR_BSPSTORE_OFFSET (47 * sizeof(elf_greg_t))
+#define ELF_AR_RNAT_OFFSET (48 * sizeof(elf_greg_t))
+#define ELF_AR_CCV_OFFSET  (49 * sizeof(elf_greg_t))
+#define ELF_AR_UNAT_OFFSET (50 * sizeof(elf_greg_t))
+#define ELF_AR_FPSR_OFFSET (51 * sizeof(elf_greg_t))
+#define ELF_AR_PFS_OFFSET  (52 * sizeof(elf_greg_t))
+#define ELF_AR_LC_OFFSET   (53 * sizeof(elf_greg_t))
+#define ELF_AR_EC_OFFSET   (54 * sizeof(elf_greg_t))
+#define ELF_AR_CSD_OFFSET  (55 * sizeof(elf_greg_t))
+#define ELF_AR_SSD_OFFSET  (56 * sizeof(elf_greg_t))
+#define ELF_AR_END_OFFSET  (57 * sizeof(elf_greg_t))
+
 typedef unsigned long elf_fpxregset_t;
 
 typedef unsigned long elf_greg_t;
@@ -183,12 +208,6 @@ extern void ia64_elf_core_copy_regs (struct pt_regs *src, elf_gregset_t dst);
 
 struct task_struct;
 
-extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
-extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
-
-#define ELF_CORE_COPY_TASK_REGS(tsk, elf_gregs) dump_task_regs(tsk, elf_gregs)
-#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
-
 #define GATE_EHDR       ((const struct elfhdr *) GATE_ADDR)
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
diff --git a/include/asm-ia64/kregs.h b/include/asm-ia64/kregs.h
index 7e55a584975c..aefcdfee7f23 100644
--- a/include/asm-ia64/kregs.h
+++ b/include/asm-ia64/kregs.h
@@ -31,6 +31,9 @@
 #define IA64_TR_PALCODE         1       /* itr1: maps PALcode as required by EFI */
 #define IA64_TR_CURRENT_STACK   1       /* dtr1: maps kernel's memory- & register-stacks */
 
+#define IA64_TR_ALLOC_BASE      2       /* itr&dtr: Base of dynamic TR resource*/
+#define IA64_TR_ALLOC_MAX       32      /* Max number for dynamic use*/
+
 /* Processor status register bits: */
 #define IA64_PSR_BE_BIT         1
 #define IA64_PSR_UP_BIT         2
diff --git a/include/asm-ia64/numa.h b/include/asm-ia64/numa.h
index 6a8a27cfae3e..3499ff57bf42 100644
--- a/include/asm-ia64/numa.h
+++ b/include/asm-ia64/numa.h
@@ -22,6 +22,8 @@
 
 #include <asm/mmzone.h>
 
+#define NUMA_NO_NODE    -1
+
 extern u16 cpu_to_node_map[NR_CPUS] __cacheline_aligned;
 extern cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
 extern pg_data_t *pgdat_list[MAX_NUMNODES];
diff --git a/include/asm-ia64/sal.h b/include/asm-ia64/sal.h
index f4904db3b057..89594b442f83 100644
--- a/include/asm-ia64/sal.h
+++ b/include/asm-ia64/sal.h
@@ -296,6 +296,9 @@ enum {
     EFI_GUID(0xe429faf8, 0x3cb7, 0x11d4, 0xbc, 0xa7, 0x0, 0x80, 0xc7, 0x3c, 0x88, 0x81)
 #define SAL_PLAT_BUS_ERR_SECT_GUID  \
     EFI_GUID(0xe429faf9, 0x3cb7, 0x11d4, 0xbc, 0xa7, 0x0, 0x80, 0xc7, 0x3c, 0x88, 0x81)
+#define PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID \
+    EFI_GUID(0x6cb0a200, 0x893a, 0x11da, 0x96, 0xd2, 0x0, 0x10, 0x83, 0xff, \
+                0xca, 0x4d)
 
 #define MAX_CACHE_ERRORS        6
 #define MAX_TLB_ERRORS          6
@@ -879,6 +882,24 @@ extern void ia64_jump_to_sal(struct sal_to_os_boot *);
 
 extern void ia64_sal_handler_init(void *entry_point, void *gpval);
 
+#define PALO_MAX_TLB_PURGES     0xFFFF
+#define PALO_SIG        "PALO"
+
+struct palo_table {
+        u8  signature[4];       /* Should be "PALO" */
+        u32 length;
+        u8  minor_revision;
+        u8  major_revision;
+        u8  checksum;
+        u8  reserved1[5];
+        u16 max_tlb_purges;
+        u8  reserved2[6];
+};
+
+#define NPTCG_FROM_PAL                  0
+#define NPTCG_FROM_PALO                 1
+#define NPTCG_FROM_KERNEL_PARAMETER     2
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_IA64_SAL_H */
diff --git a/include/asm-ia64/smp.h b/include/asm-ia64/smp.h
index 4fa733dd417a..ec5f355fb7e3 100644
--- a/include/asm-ia64/smp.h
+++ b/include/asm-ia64/smp.h
@@ -38,6 +38,9 @@ ia64_get_lid (void)
         return lid.f.id << 8 | lid.f.eid;
 }
 
+extern int smp_call_function_mask(cpumask_t mask, void (*func)(void *),
+                                  void *info, int wait);
+
 #define hard_smp_processor_id()         ia64_get_lid()
 
 #ifdef CONFIG_SMP
diff --git a/include/asm-ia64/system.h b/include/asm-ia64/system.h
index 595112bca3cc..dff8128fa58e 100644
--- a/include/asm-ia64/system.h
+++ b/include/asm-ia64/system.h
@@ -210,6 +210,13 @@ struct task_struct;
 extern void ia64_save_extra (struct task_struct *task);
 extern void ia64_load_extra (struct task_struct *task);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
+# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
+#else
+# define IA64_ACCOUNT_ON_SWITCH(p,n)
+#endif
+
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
 # define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
@@ -222,6 +229,7 @@ extern void ia64_load_extra (struct task_struct *task);
          || IS_IA32_PROCESS(task_pt_regs(t)) || PERFMON_IS_SYSWIDE())
 
 #define __switch_to(prev,next,last) do {                                                         \
+        IA64_ACCOUNT_ON_SWITCH(prev, next);                                                      \
         if (IA64_HAS_EXTRA_STATE(prev))                                                          \
                 ia64_save_extra(prev);                                                           \
         if (IA64_HAS_EXTRA_STATE(next))                                                          \
@@ -266,6 +274,10 @@ void cpu_idle_wait(void);
 
 void default_idle(void);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void account_system_vtime(struct task_struct *);
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/asm-ia64/thread_info.h b/include/asm-ia64/thread_info.h
index 93d83cbe0c8c..6da8069a0f77 100644
--- a/include/asm-ia64/thread_info.h
+++ b/include/asm-ia64/thread_info.h
@@ -31,6 +31,12 @@ struct thread_info {
         mm_segment_t addr_limit;        /* user-level address space limit */
         int preempt_count;              /* 0=premptable, <0=BUG; will also serve as bh-counter */
         struct restart_block restart_block;
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+        __u64 ac_stamp;
+        __u64 ac_leave;
+        __u64 ac_stime;
+        __u64 ac_utime;
+#endif
 };
 
 #define THREAD_SIZE                     KERNEL_STACK_SIZE
@@ -62,9 +68,17 @@ struct thread_info {
 #define task_stack_page(tsk)    ((void *)(tsk))
 
 #define __HAVE_THREAD_FUNCTIONS
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#define setup_thread_stack(p, org)                      \
+        *task_thread_info(p) = *task_thread_info(org);  \
+        task_thread_info(p)->ac_stime = 0;              \
+        task_thread_info(p)->ac_utime = 0;              \
+        task_thread_info(p)->task = (p);
+#else
 #define setup_thread_stack(p, org) \
         *task_thread_info(p) = *task_thread_info(org); \
         task_thread_info(p)->task = (p);
+#endif
 #define end_of_stack(p) (unsigned long *)((void *)(p) + IA64_RBS_OFFSET)
 
 #define __HAVE_ARCH_TASK_STRUCT_ALLOCATOR
diff --git a/include/asm-ia64/tlb.h b/include/asm-ia64/tlb.h
index 26edcb750f9f..20d8a39680c2 100644
--- a/include/asm-ia64/tlb.h
+++ b/include/asm-ia64/tlb.h
@@ -64,6 +64,32 @@ struct mmu_gather {
         struct page             *pages[FREE_PTE_NR];
 };
 
+struct ia64_tr_entry {
+        u64 ifa;
+        u64 itir;
+        u64 pte;
+        u64 rr;
+}; /*Record for tr entry!*/
+
+extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
+extern void ia64_ptr_entry(u64 target_mask, int slot);
+
+extern struct ia64_tr_entry __per_cpu_idtrs[NR_CPUS][2][IA64_TR_ALLOC_MAX];
+
+/*
+ region register macros
+*/
+#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
+#define RR_VE(val)      (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK      0x0000000000000001L
+#define RR_VE_SHIFT     0
+#define RR_TO_PS(val)   (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val)      (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK      0x00000000000000fcL
+#define RR_PS_SHIFT     2
+#define RR_RID_MASK     0x00000000ffffff00L
+#define RR_TO_RID(val)  ((val >> 8) & 0xffffff)
+
 /* Users of the generic TLB shootdown code must declare this storage space. */
 DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
 
diff --git a/include/asm-ia64/tlbflush.h b/include/asm-ia64/tlbflush.h
index 7774a1cac0cc..3be25dfed164 100644
--- a/include/asm-ia64/tlbflush.h
+++ b/include/asm-ia64/tlbflush.h
@@ -17,6 +17,7 @@
  * Now for some TLB flushing routines.  This is the kind of stuff that
  * can be very expensive, so try to avoid them whenever possible.
  */
+extern void setup_ptcg_sem(int max_purges, int from_palo);
 
 /*
  * Flush everything (kernel mapping may also have changed due to