diff options
Diffstat (limited to 'include/asm-ia64')
30 files changed, 1264 insertions, 1896 deletions
diff --git a/include/asm-ia64/acpi.h b/include/asm-ia64/acpi.h index cd1cc39b559..fcfad326f4c 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/bitops.h b/include/asm-ia64/bitops.h index 953d3df9dd2..e2ca8003733 100644 --- a/include/asm-ia64/bitops.h +++ b/include/asm-ia64/bitops.h @@ -407,6 +407,22 @@ fls (int t) return ia64_popcnt(x); } +/* + * Find the last (most significant) bit set. Undefined for x==0. + * Bits are numbered from 0..63 (e.g., __fls(9) == 3). + */ +static inline unsigned long +__fls (unsigned long x) +{ + x |= x >> 1; + x |= x >> 2; + x |= x >> 4; + x |= x >> 8; + x |= x >> 16; + x |= x >> 32; + return ia64_popcnt(x) - 1; +} + #include <asm-generic/bitops/fls64.h> /* diff --git a/include/asm-ia64/cputime.h b/include/asm-ia64/cputime.h index 72400a78002..f9abdec6577 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 f8e83eca67a..5e0c1a6bce8 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/gcc_intrin.h b/include/asm-ia64/gcc_intrin.h index de2ed2cbdd8..2fe292c275f 100644 --- a/include/asm-ia64/gcc_intrin.h +++ b/include/asm-ia64/gcc_intrin.h @@ -21,6 +21,10 @@ #define ia64_invala_fr(regnum) asm volatile ("invala.e f%0" :: "i"(regnum)) +#define ia64_flushrs() asm volatile ("flushrs;;":::"memory") + +#define ia64_loadrs() asm volatile ("loadrs;;":::"memory") + extern void ia64_bad_param_for_setreg (void); extern void ia64_bad_param_for_getreg (void); @@ -517,6 +521,14 @@ do { \ #define ia64_ptrd(addr, size) \ asm volatile ("ptr.d %0,%1" :: "r"(addr), "r"(size) : "memory") +#define ia64_ttag(addr) \ +({ \ + __u64 ia64_intri_res; \ + asm volatile ("ttag %0=%1" : "=r"(ia64_intri_res) : "r" (addr)); \ + ia64_intri_res; \ +}) + + /* Values for lfhint in ia64_lfetch and ia64_lfetch_fault */ #define ia64_lfhint_none 0 diff --git a/include/asm-ia64/hugetlb.h b/include/asm-ia64/hugetlb.h new file mode 100644 index 00000000000..f28a9701f1c --- /dev/null +++ b/include/asm-ia64/hugetlb.h @@ -0,0 +1,79 @@ +#ifndef _ASM_IA64_HUGETLB_H +#define _ASM_IA64_HUGETLB_H + +#include <asm/page.h> + + +void hugetlb_free_pgd_range(struct mmu_gather **tlb, unsigned long addr, + unsigned long end, unsigned long floor, + unsigned long ceiling); + +int prepare_hugepage_range(unsigned long addr, unsigned long len); + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + return (REGION_NUMBER(addr) == RGN_HPAGE || + REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE); +} + +static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) +{ +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + set_pte_at(mm, addr, ptep, pte); +} + +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + return ptep_get_and_clear(mm, addr, ptep); +} + +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} + +static inline int huge_pte_none(pte_t pte) +{ + return pte_none(pte); +} + +static inline pte_t huge_pte_wrprotect(pte_t pte) +{ + return pte_wrprotect(pte); +} + +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + ptep_set_wrprotect(mm, addr, ptep); +} + +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); +} + +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + return *ptep; +} + +static inline int arch_prepare_hugepage(struct page *page) +{ + return 0; +} + +static inline void arch_release_hugepage(struct page *page) +{ +} + +#endif /* _ASM_IA64_HUGETLB_H */ diff --git a/include/asm-ia64/ide.h b/include/asm-ia64/ide.h index 1ccf2380932..8fa3f8cd067 100644 --- a/include/asm-ia64/ide.h +++ b/include/asm-ia64/ide.h @@ -16,8 +16,6 @@ #include <linux/irq.h> -#define IDE_ARCH_OBSOLETE_DEFAULTS - static inline int ide_default_irq(unsigned long base) { switch (base) { @@ -46,14 +44,6 @@ static inline unsigned long ide_default_io_base(int index) } } -#define ide_default_io_ctl(base) ((base) + 0x206) /* obsolete */ - -#ifdef CONFIG_PCI -#define ide_init_default_irq(base) (0) -#else -#define ide_init_default_irq(base) ide_default_irq(base) -#endif - #include <asm-generic/ide_iops.h> #endif /* __KERNEL__ */ diff --git a/include/asm-ia64/kprobes.h b/include/asm-ia64/kprobes.h index d03bf9ff68e..ef71b57fc2f 100644 --- a/include/asm-ia64/kprobes.h +++ b/include/asm-ia64/kprobes.h @@ -30,8 +30,12 @@ #include <asm/break.h> #define __ARCH_WANT_KPROBES_INSN_SLOT -#define MAX_INSN_SIZE 1 +#define MAX_INSN_SIZE 2 /* last half is for kprobe-booster */ #define BREAK_INST (long)(__IA64_BREAK_KPROBE << 6) +#define NOP_M_INST (long)(1<<27) +#define BRL_INST(i1, i2) ((long)((0xcL << 37) | /* brl */ \ + (0x1L << 12) | /* many */ \ + (((i1) & 1) << 36) | ((i2) << 13))) /* imm */ typedef union cmp_inst { struct { @@ -112,6 +116,7 @@ struct arch_specific_insn { #define INST_FLAG_FIX_RELATIVE_IP_ADDR 1 #define INST_FLAG_FIX_BRANCH_REG 2 #define INST_FLAG_BREAK_INST 4 + #define INST_FLAG_BOOSTABLE 8 unsigned long inst_flag; unsigned short target_br_reg; unsigned short slot; diff --git a/include/asm-ia64/kregs.h b/include/asm-ia64/kregs.h index 7e55a584975..aefcdfee7f2 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/kvm.h b/include/asm-ia64/kvm.h new file mode 100644 index 00000000000..eb2d3559d08 --- /dev/null +++ b/include/asm-ia64/kvm.h @@ -0,0 +1,205 @@ +#ifndef __ASM_IA64_KVM_H +#define __ASM_IA64_KVM_H + +/* + * asm-ia64/kvm.h: kvm structure definitions for ia64 + * + * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#include <asm/types.h> +#include <asm/fpu.h> + +#include <linux/ioctl.h> + +/* Architectural interrupt line count. */ +#define KVM_NR_INTERRUPTS 256 + +#define KVM_IOAPIC_NUM_PINS 24 + +struct kvm_ioapic_state { + __u64 base_address; + __u32 ioregsel; + __u32 id; + __u32 irr; + __u32 pad; + union { + __u64 bits; + struct { + __u8 vector; + __u8 delivery_mode:3; + __u8 dest_mode:1; + __u8 delivery_status:1; + __u8 polarity:1; + __u8 remote_irr:1; + __u8 trig_mode:1; + __u8 mask:1; + __u8 reserve:7; + __u8 reserved[4]; + __u8 dest_id; + } fields; + } redirtbl[KVM_IOAPIC_NUM_PINS]; +}; + +#define KVM_IRQCHIP_PIC_MASTER 0 +#define KVM_IRQCHIP_PIC_SLAVE 1 +#define KVM_IRQCHIP_IOAPIC 2 + +#define KVM_CONTEXT_SIZE 8*1024 + +union context { + /* 8K size */ + char dummy[KVM_CONTEXT_SIZE]; + struct { + unsigned long psr; + unsigned long pr; + unsigned long caller_unat; + unsigned long pad; + unsigned long gr[32]; + unsigned long ar[128]; + unsigned long br[8]; + unsigned long cr[128]; + unsigned long rr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long pkr[8]; + struct ia64_fpreg fr[128]; + }; +}; + +struct thash_data { + union { + struct { + unsigned long p : 1; /* 0 */ + unsigned long rv1 : 1; /* 1 */ + unsigned long ma : 3; /* 2-4 */ + unsigned long a : 1; /* 5 */ + unsigned long d : 1; /* 6 */ + unsigned long pl : 2; /* 7-8 */ + unsigned long ar : 3; /* 9-11 */ + unsigned long ppn : 38; /* 12-49 */ + unsigned long rv2 : 2; /* 50-51 */ + unsigned long ed : 1; /* 52 */ + unsigned long ig1 : 11; /* 53-63 */ + }; + struct { + unsigned long __rv1 : 53; /* 0-52 */ + unsigned long contiguous : 1; /*53 */ + unsigned long tc : 1; /* 54 TR or TC */ + unsigned long cl : 1; + /* 55 I side or D side cache line */ + unsigned long len : 4; /* 56-59 */ + unsigned long io : 1; /* 60 entry is for io or not */ + unsigned long nomap : 1; + /* 61 entry cann't be inserted into machine TLB.*/ + unsigned long checked : 1; + /* 62 for VTLB/VHPT sanity check */ + unsigned long invalid : 1; + /* 63 invalid entry */ + }; + unsigned long page_flags; + }; /* same for VHPT and TLB */ + + union { + struct { + unsigned long rv3 : 2; + unsigned long ps : 6; + unsigned long key : 24; + unsigned long rv4 : 32; + }; + unsigned long itir; + }; + union { + struct { + unsigned long ig2 : 12; + unsigned long vpn : 49; + unsigned long vrn : 3; + }; + unsigned long ifa; + unsigned long vadr; + struct { + unsigned long tag : 63; + unsigned long ti : 1; + }; + unsigned long etag; + }; + union { + struct thash_data *next; + unsigned long rid; + unsigned long gpaddr; + }; +}; + +#define NITRS 8 +#define NDTRS 8 + +struct saved_vpd { + unsigned long vhpi; + unsigned long vgr[16]; + unsigned long vbgr[16]; + unsigned long vnat; + unsigned long vbnat; + unsigned long vcpuid[5]; + unsigned long vpsr; + unsigned long vpr; + unsigned long vcr[128]; +}; + +struct kvm_regs { + char *saved_guest; + char *saved_stack; + struct saved_vpd vpd; + /*Arch-regs*/ + int mp_state; + unsigned long vmm_rr; + /* TR and TC. */ + struct thash_data itrs[NITRS]; + struct thash_data dtrs[NDTRS]; + /* Bit is set if there is a tr/tc for the region. */ + unsigned char itr_regions; + unsigned char dtr_regions; + unsigned char tc_regions; + + char irq_check; + unsigned long saved_itc; + unsigned long itc_check; + unsigned long timer_check; + unsigned long timer_pending; + unsigned long last_itc; + + unsigned long vrr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long insvc[4]; /* Interrupt in service. */ + unsigned long xtp; + + unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_rr4; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_saved_rr0; /* from kvm_arch */ + unsigned long metaphysical_saved_rr4; /* from kvm_arch */ + unsigned long fp_psr; /*used for lazy float register */ + unsigned long saved_gp; + /*for phycial emulation */ +}; + +struct kvm_sregs { +}; + +struct kvm_fpu { +}; + +#endif diff --git a/include/asm-ia64/kvm_host.h b/include/asm-ia64/kvm_host.h new file mode 100644 index 00000000000..c082c208c1f --- /dev/null +++ b/include/asm-ia64/kvm_host.h @@ -0,0 +1,524 @@ +/* + * kvm_host.h: used for kvm module, and hold ia64-specific sections. + * + * Copyright (C) 2007, Intel Corporation. + * + * Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#ifndef __ASM_KVM_HOST_H +#define __ASM_KVM_HOST_H + + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/kvm.h> +#include <linux/kvm_para.h> +#include <linux/kvm_types.h> + +#include <asm/pal.h> +#include <asm/sal.h> + +#define KVM_MAX_VCPUS 4 +#define KVM_MEMORY_SLOTS 32 +/* memory slots that does not exposed to userspace */ +#define KVM_PRIVATE_MEM_SLOTS 4 + + +/* define exit reasons from vmm to kvm*/ +#define EXIT_REASON_VM_PANIC 0 +#define EXIT_REASON_MMIO_INSTRUCTION 1 +#define EXIT_REASON_PAL_CALL 2 +#define EXIT_REASON_SAL_CALL 3 +#define EXIT_REASON_SWITCH_RR6 4 +#define EXIT_REASON_VM_DESTROY 5 +#define EXIT_REASON_EXTERNAL_INTERRUPT 6 +#define EXIT_REASON_IPI 7 +#define EXIT_REASON_PTC_G 8 + +/*Define vmm address space and vm data space.*/ +#define KVM_VMM_SIZE (16UL<<20) +#define KVM_VMM_SHIFT 24 +#define KVM_VMM_BASE 0xD000000000000000UL +#define VMM_SIZE (8UL<<20) + +/* + * Define vm_buffer, used by PAL Services, base address. + * Note: vmbuffer is in the VMM-BLOCK, the size must be < 8M + */ +#define KVM_VM_BUFFER_BASE (KVM_VMM_BASE + VMM_SIZE) +#define KVM_VM_BUFFER_SIZE (8UL<<20) + +/*Define Virtual machine data layout.*/ +#define KVM_VM_DATA_SHIFT 24 +#define KVM_VM_DATA_SIZE (1UL << KVM_VM_DATA_SHIFT) +#define KVM_VM_DATA_BASE (KVM_VMM_BASE + KVM_VMM_SIZE) + + +#define KVM_P2M_BASE KVM_VM_DATA_BASE +#define KVM_P2M_OFS 0 +#define KVM_P2M_SIZE (8UL << 20) + +#define KVM_VHPT_BASE (KVM_P2M_BASE + KVM_P2M_SIZE) +#define KVM_VHPT_OFS KVM_P2M_SIZE +#define KVM_VHPT_BLOCK_SIZE (2UL << 20) +#define VHPT_SHIFT 18 +#define VHPT_SIZE (1UL << VHPT_SHIFT) +#define VHPT_NUM_ENTRIES (1<<(VHPT_SHIFT-5)) + +#define KVM_VTLB_BASE (KVM_VHPT_BASE+KVM_VHPT_BLOCK_SIZE) +#define KVM_VTLB_OFS (KVM_VHPT_OFS+KVM_VHPT_BLOCK_SIZE) +#define KVM_VTLB_BLOCK_SIZE (1UL<<20) +#define VTLB_SHIFT 17 +#define VTLB_SIZE (1UL<<VTLB_SHIFT) +#define VTLB_NUM_ENTRIES (1<<(VTLB_SHIFT-5)) + +#define KVM_VPD_BASE (KVM_VTLB_BASE+KVM_VTLB_BLOCK_SIZE) +#define KVM_VPD_OFS (KVM_VTLB_OFS+KVM_VTLB_BLOCK_SIZE) +#define KVM_VPD_BLOCK_SIZE (2UL<<20) +#define VPD_SHIFT 16 +#define VPD_SIZE (1UL<<VPD_SHIFT) + +#define KVM_VCPU_BASE (KVM_VPD_BASE+KVM_VPD_BLOCK_SIZE) +#define KVM_VCPU_OFS (KVM_VPD_OFS+KVM_VPD_BLOCK_SIZE) +#define KVM_VCPU_BLOCK_SIZE (2UL<<20) +#define VCPU_SHIFT 18 +#define VCPU_SIZE (1UL<<VCPU_SHIFT) +#define MAX_VCPU_NUM KVM_VCPU_BLOCK_SIZE/VCPU_SIZE + +#define KVM_VM_BASE (KVM_VCPU_BASE+KVM_VCPU_BLOCK_SIZE) +#define KVM_VM_OFS (KVM_VCPU_OFS+KVM_VCPU_BLOCK_SIZE) +#define KVM_VM_BLOCK_SIZE (1UL<<19) + +#define KVM_MEM_DIRTY_LOG_BASE (KVM_VM_BASE+KVM_VM_BLOCK_SIZE) +#define KVM_MEM_DIRTY_LOG_OFS (KVM_VM_OFS+KVM_VM_BLOCK_SIZE) +#define KVM_MEM_DIRTY_LOG_SIZE (1UL<<19) + +/* Get vpd, vhpt, tlb, vcpu, base*/ +#define VPD_ADDR(n) (KVM_VPD_BASE+n*VPD_SIZE) +#define VHPT_ADDR(n) (KVM_VHPT_BASE+n*VHPT_SIZE) +#define VTLB_ADDR(n) (KVM_VTLB_BASE+n*VTLB_SIZE) +#define VCPU_ADDR(n) (KVM_VCPU_BASE+n*VCPU_SIZE) + +/*IO section definitions*/ +#define IOREQ_READ 1 +#define IOREQ_WRITE 0 + +#define STATE_IOREQ_NONE 0 +#define STATE_IOREQ_READY 1 +#define STATE_IOREQ_INPROCESS 2 +#define STATE_IORESP_READY 3 + +/*Guest Physical address layout.*/ +#define GPFN_MEM (0UL << 60) /* Guest pfn is normal mem */ +#define GPFN_FRAME_BUFFER (1UL << 60) /* VGA framebuffer */ +#define GPFN_LOW_MMIO (2UL << 60) /* Low MMIO range */ +#define GPFN_PIB (3UL << 60) /* PIB base */ +#define GPFN_IOSAPIC (4UL << 60) /* IOSAPIC base */ +#define GPFN_LEGACY_IO (5UL << 60) /* Legacy I/O base */ +#define GPFN_GFW (6UL << 60) /* Guest Firmware */ +#define GPFN_HIGH_MMIO (7UL << 60) /* High MMIO range */ + +#define GPFN_IO_MASK (7UL << 60) /* Guest pfn is I/O type */ +#define GPFN_INV_MASK (1UL << 63) /* Guest pfn is invalid */ +#define INVALID_MFN (~0UL) +#define MEM_G (1UL << 30) +#define MEM_M (1UL << 20) +#define MMIO_START (3 * MEM_G) +#define MMIO_SIZE (512 * MEM_M) +#define VGA_IO_START 0xA0000UL +#define VGA_IO_SIZE 0x20000 +#define LEGACY_IO_START (MMIO_START + MMIO_SIZE) +#define LEGACY_IO_SIZE (64 * MEM_M) +#define IO_SAPIC_START 0xfec00000UL +#define IO_SAPIC_SIZE 0x100000 +#define PIB_START 0xfee00000UL +#define PIB_SIZE 0x200000 +#define GFW_START (4 * MEM_G - 16 * MEM_M) +#define GFW_SIZE (16 * MEM_M) + +/*Deliver mode, defined for ioapic.c*/ +#define dest_Fixed IOSAPIC_FIXED +#define dest_LowestPrio IOSAPIC_LOWEST_PRIORITY + +#define NMI_VECTOR 2 +#define ExtINT_VECTOR 0 +#define NULL_VECTOR (-1) +#define IA64_SPURIOUS_INT_VECTOR 0x0f + +#define VCPU_LID(v) (((u64)(v)->vcpu_id) << 24) + +/* + *Delivery mode + */ +#define SAPIC_DELIV_SHIFT 8 +#define SAPIC_FIXED 0x0 +#define SAPIC_LOWEST_PRIORITY 0x1 +#define SAPIC_PMI 0x2 +#define SAPIC_NMI 0x4 +#define SAPIC_INIT 0x5 +#define SAPIC_EXTINT 0x7 + +/* + * vcpu->requests bit members for arch + */ +#define KVM_REQ_PTC_G 32 +#define KVM_REQ_RESUME 33 + +#define KVM_PAGES_PER_HPAGE 1 + +struct kvm; +struct kvm_vcpu; +struct kvm_guest_debug{ +}; + +struct kvm_mmio_req { + uint64_t addr; /* physical address */ + uint64_t size; /* size in bytes */ + uint64_t data; /* data (or paddr of data) */ + uint8_t state:4; + uint8_t dir:1; /* 1=read, 0=write */ +}; + +/*Pal data struct */ +struct kvm_pal_call{ + /*In area*/ + uint64_t gr28; + uint64_t gr29; + uint64_t gr30; + uint64_t gr31; + /*Out area*/ + struct ia64_pal_retval ret; +}; + +/* Sal data structure */ +struct kvm_sal_call{ + /*In area*/ + uint64_t in0; + uint64_t in1; + uint64_t in2; + uint64_t in3; + uint64_t in4; + uint64_t in5; + uint64_t in6; + uint64_t in7; + struct sal_ret_values ret; +}; + +/*Guest change rr6*/ +struct kvm_switch_rr6 { + uint64_t old_rr; + uint64_t new_rr; +}; + +union ia64_ipi_a{ + unsigned long val; + struct { + unsigned long rv : 3; + unsigned long ir : 1; + unsigned long eid : 8; + unsigned long id : 8; + unsigned long ib_base : 44; + }; +}; + +union ia64_ipi_d { + unsigned long val; + struct { + unsigned long vector : 8; + unsigned long dm : 3; + unsigned long ig : 53; + }; +}; + +/*ipi check exit data*/ +struct kvm_ipi_data{ + union ia64_ipi_a addr; + union ia64_ipi_d data; +}; + +/*global purge data*/ +struct kvm_ptc_g { + unsigned long vaddr; + unsigned long rr; + unsigned long ps; + struct kvm_vcpu *vcpu; +}; + +/*Exit control data */ +struct exit_ctl_data{ + uint32_t exit_reason; + uint32_t vm_status; + union { + struct kvm_mmio_req ioreq; + struct kvm_pal_call pal_data; + struct kvm_sal_call sal_data; + struct kvm_switch_rr6 rr_data; + struct kvm_ipi_data ipi_data; + struct kvm_ptc_g ptc_g_data; + } u; +}; + +union pte_flags { + unsigned long val; + struct { + unsigned long p : 1; /*0 */ + unsigned long : 1; /* 1 */ + unsigned long ma : 3; /* 2-4 */ + unsigned long a : 1; /* 5 */ + unsigned long d : 1; /* 6 */ + unsigned long pl : 2; /* 7-8 */ + unsigned long ar : 3; /* 9-11 */ + unsigned long ppn : 38; /* 12-49 */ + unsigned long : 2; /* 50-51 */ + unsigned long ed : 1; /* 52 */ + }; +}; + +union ia64_pta { + unsigned long val; + struct { + unsigned long ve : 1; + unsigned long reserved0 : 1; + unsigned long size : 6; + unsigned long vf : 1; + unsigned long reserved1 : 6; + unsigned long base : 49; + }; +}; + +struct thash_cb { + /* THASH base information */ + struct thash_data *hash; /* hash table pointer */ + union ia64_pta pta; + int num; +}; + +struct kvm_vcpu_stat { +}; + +struct kvm_vcpu_arch { + int launched; + int last_exit; + int last_run_cpu; + int vmm_tr_slot; + int vm_tr_slot; + +#define KVM_MP_STATE_RUNNABLE 0 +#define KVM_MP_STATE_UNINITIALIZED 1 +#define KVM_MP_STATE_INIT_RECEIVED 2 +#define KVM_MP_STATE_HALTED 3 + int mp_state; + +#define MAX_PTC_G_NUM 3 + int ptc_g_count; + struct kvm_ptc_g ptc_g_data[MAX_PTC_G_NUM]; + + /*halt timer to wake up sleepy vcpus*/ + struct hrtimer hlt_timer; + long ht_active; + + struct kvm_lapic *apic; /* kernel irqchip context */ + struct vpd *vpd; + + /* Exit data for vmm_transition*/ + struct exit_ctl_data exit_data; + + cpumask_t cache_coherent_map; + + unsigned long vmm_rr; + unsigned long host_rr6; + unsigned long psbits[8]; + unsigned long cr_iipa; + unsigned long cr_isr; + unsigned long vsa_base; + unsigned long dirty_log_lock_pa; + unsigned long __gp; + /* TR and TC. */ + struct thash_data itrs[NITRS]; + struct thash_data dtrs[NDTRS]; + /* Bit is set if there is a tr/tc for the region. */ + unsigned char itr_regions; + unsigned char dtr_regions; + unsigned char tc_regions; + /* purge all */ + unsigned long ptce_base; + unsigned long ptce_count[2]; + unsigned long ptce_stride[2]; + /* itc/itm */ + unsigned long last_itc; + long itc_offset; + unsigned long itc_check; + unsigned long timer_check; + unsigned long timer_pending; + + unsigned long vrr[8]; + unsigned long ibr[8]; + unsigned long dbr[8]; + unsigned long insvc[4]; /* Interrupt in service. */ + unsigned long xtp; + + unsigned long metaphysical_rr0; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_rr4; /* from kvm_arch (so is pinned) */ + unsigned long metaphysical_saved_rr0; /* from kvm_arch */ + unsigned long metaphysical_saved_rr4; /* from kvm_arch */ + unsigned long fp_psr; /*used for lazy float register */ + unsigned long saved_gp; + /*for phycial emulation */ + int mode_flags; + struct thash_cb vtlb; + struct thash_cb vhpt; + char irq_check; + char irq_new_pending; + + unsigned long opcode; + unsigned long cause; + union context host; + union context guest; +}; + +struct kvm_vm_stat { + u64 remote_tlb_flush; +}; + +struct kvm_sal_data { + unsigned long boot_ip; + unsigned long boot_gp; +}; + +struct kvm_arch { + unsigned long vm_base; + unsigned long metaphysical_rr0; + unsigned long metaphysical_rr4; + unsigned long vmm_init_rr; + unsigned long vhpt_base; + unsigned long vtlb_base; + unsigned long vpd_base; + spinlock_t dirty_log_lock; + struct kvm_ioapic *vioapic; + struct kvm_vm_stat stat; + struct kvm_sal_data rdv_sal_data; +}; + +union cpuid3_t { + u64 value; + struct { + u64 number : 8; + u64 revision : 8; + u64 model : 8; + u64 family : 8; + u64 archrev : 8; + u64 rv : 24; + }; +}; + +struct kvm_pt_regs { + /* The following registers are saved by SAVE_MIN: */ + unsigned long b6; /* scratch */ + unsigned long b7; /* scratch */ + + unsigned long ar_csd; /* used by cmp8xchg16 (scratch) */ + unsigned long ar_ssd; /* reserved for future use (scratch) */ + + unsigned long r8; /* scratch (return value register 0) */ + unsigned long r9; /* scratch (return value register 1) */ + unsigned long r10; /* scratch (return value register 2) */ + unsigned long r11; /* scratch (return value register 3) */ + + unsigned long cr_ipsr; /* interrupted task's psr */ + unsigned long cr_iip; /* interrupted task's instruction pointer */ + unsigned long cr_ifs; /* interrupted task's function state */ + + unsigned long ar_unat; /* interrupted task's NaT register (preserved) */ + unsigned long ar_pfs; /* prev function state */ + unsigned long ar_rsc; /* RSE configuration */ + /* The following two are valid only if cr_ipsr.cpl > 0: */ + unsigned long ar_rnat; /* RSE NaT */ + unsigned long ar_bspstore; /* RSE bspstore */ + + unsigned long pr; /* 64 predicate registers (1 bit each) */ + unsigned long b0; /* return pointer (bp) */ + unsigned long loadrs; /* size of dirty partition << 16 */ + + unsigned long r1; /* the gp pointer */ + unsigned long r12; /* interrupted task's memory stack pointer */ + unsigned long r13; /* thread pointer */ + + unsigned long ar_fpsr; /* floating point status (preserved) */ + unsigned long r15; /* scratch */ + + /* The remaining registers are NOT saved for system calls. */ + unsigned long r14; /* scratch */ + unsigned long r2; /* scratch */ + unsigned long r3; /* scratch */ + unsigned long r16; /* scratch */ + unsigned long r17; /* scratch */ + unsigned long r18; /* scratch */ + unsigned long r19; /* scratch */ + unsigned long r20; /* scratch */ + unsigned long r21; /* scratch */ + unsigned long r22; /* scratch */ + unsigned long r23; /* scratch */ + unsigned long r24; /* scratch */ + unsigned long r25; /* scratch */ + unsigned long r26; /* scratch */ + unsigned long r27; /* scratch */ + unsigned long r28; /* scratch */ + unsigned long r29; /* scratch */ + unsigned long r30; /* scratch */ + unsigned long r31; /* scratch */ + unsigned long ar_ccv; /* compare/exchange value (scratch) */ + + /* + * Floating point registers that the kernel considers scratch: + */ + struct ia64_fpreg f6; /* scratch */ + struct ia64_fpreg f7; /* scratch */ + struct ia64_fpreg f8; /* scratch */ + struct ia64_fpreg f9; /* scratch */ + struct ia64_fpreg f10; /* scratch */ + struct ia64_fpreg f11; /* scratch */ + + unsigned long r4; /* preserved */ + unsigned long r5; /* preserved */ + unsigned long r6; /* preserved */ + unsigned long r7; /* preserved */ + unsigned long eml_unat; /* used for emulating instruction */ + unsigned long pad0; /* alignment pad */ +}; + +static inline struct kvm_pt_regs *vcpu_regs(struct kvm_vcpu *v) +{ + return (struct kvm_pt_regs *) ((unsigned long) v + IA64_STK_OFFSET) - 1; +} + +typedef int kvm_vmm_entry(void); +typedef void kvm_tramp_entry(union context *host, union context *guest); + +struct kvm_vmm_info{ + struct module *module; + kvm_vmm_entry *vmm_entry; + kvm_tramp_entry *tramp_entry; + unsigned long vmm_ivt; +}; + +int kvm_highest_pending_irq(struct kvm_vcpu *vcpu); +int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run); +void kvm_sal_emul(struct kvm_vcpu *vcpu); + +#endif diff --git a/include/asm-ia64/kvm_para.h b/include/asm-ia64/kvm_para.h new file mode 100644 index 00000000000..9f9796bb344 --- /dev/null +++ b/include/asm-ia64/kvm_para.h @@ -0,0 +1,29 @@ +#ifndef __IA64_KVM_PARA_H +#define __IA64_KVM_PARA_H + +/* + * asm-ia64/kvm_para.h + * + * Copyright (C) 2007 Xiantao Zhang <xiantao.zhang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +#endif diff --git a/include/asm-ia64/mca.h b/include/asm-ia64/mca.h index f1663aa94a5..18a4321349a 100644 --- a/include/asm-ia64/mca.h +++ b/include/asm-ia64/mca.h @@ -157,6 +157,7 @@ extern void ia64_mca_printk(const char * fmt, ...) struct ia64_mca_notify_die { struct ia64_sal_os_state *sos; int *monarch_cpu; + int *data; }; DECLARE_PER_CPU(u64, ia64_mca_pal_base); diff --git a/include/asm-ia64/meminit.h b/include/asm-ia64/meminit.h index f93308f54b6..7245a578159 100644 --- a/include/asm-ia64/meminit.h +++ b/include/asm-ia64/meminit.h @@ -35,6 +35,7 @@ extern void find_memory (void); extern void reserve_memory (void); extern void find_initrd (void); extern int filter_rsvd_memory (unsigned long start, unsigned long end, void *arg); +extern int filter_memory (unsigned long start, unsigned long end, void *arg); extern unsigned long efi_memmap_init(unsigned long *s, unsigned long *e); extern int find_max_min_low_pfn (unsigned long , unsigned long, void *); @@ -56,7 +57,7 @@ extern int reserve_elfcorehdr(unsigned long *start, unsigned long *end); #define IGNORE_PFN0 1 /* XXX fix me: ignore pfn 0 until TLB miss handler is updated... */ -extern int register_active_ranges(u64 start, u64 end, void *arg); +extern int register_active_ranges(u64 start, u64 len, int nid); #ifdef CONFIG_VIRTUAL_MEM_MAP # define LARGE_GAP 0x40000000 /* Use virtual mem map if hole is > than this */ diff --git a/include/asm-ia64/numa.h b/include/asm-ia64/numa.h index 6a8a27cfae3..3499ff57bf4 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/page.h b/include/asm-ia64/page.h index 4999a6c6377..36f39321b76 100644 --- a/include/asm-ia64/page.h +++ b/include/asm-ia64/page.h @@ -54,9 +54,6 @@ # define HPAGE_MASK (~(HPAGE_SIZE - 1)) # define HAVE_ARCH_HUGETLB_UNMAPPED_AREA -# define ARCH_HAS_HUGEPAGE_ONLY_RANGE -# define ARCH_HAS_PREPARE_HUGEPAGE_RANGE -# define ARCH_HAS_HUGETLB_FREE_PGD_RANGE #endif /* CONFIG_HUGETLB_PAGE */ #ifdef __ASSEMBLY__ @@ -153,9 +150,6 @@ typedef union ia64_va { # define htlbpage_to_page(x) (((unsigned long) REGION_NUMBER(x) << 61) \ | (REGION_OFFSET(x) >> (HPAGE_SHIFT-PAGE_SHIFT))) # define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) -# define is_hugepage_only_range(mm, addr, len) \ - (REGION_NUMBER(addr) == RGN_HPAGE || \ - REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE) extern unsigned int hpage_shift; #endif diff --git a/include/asm-ia64/pal.h b/include/asm-ia64/pal.h index 8a695d3407d..67b02901ead 100644 --- a/include/asm-ia64/pal.h +++ b/include/asm-ia64/pal.h @@ -13,6 +13,7 @@ * Copyright (C) 1999 VA Linux Systems * Copyright (C) 1999 Walt Drummond <drummond@valinux.com> * Copyright (C) 1999 Srinivasa Prasad Thirumalachar <sprasad@sprasad.engr.sgi.com> + * Copyright (C) 2008 Silicon Graphics, Inc. (SGI) * * 99/10/01 davidm Make sure we pass zero for reserved parameters. * 00/03/07 davidm Updated pal_cache_flush() to be in sync with PAL v2.6. @@ -73,6 +74,8 @@ #define PAL_CACHE_SHARED_INFO 43 /* returns information on caches shared by logical processor */ #define PAL_GET_HW_POLICY 48 /* Get current hardware resource sharing policy */ #define PAL_SET_HW_POLICY 49 /* Set current hardware resource sharing policy */ +#define PAL_VP_INFO 50 /* Information about virtual processor features */ +#define PAL_MC_HW_TRACKING 51 /* Hardware tracking status */ #define PAL_COPY_PAL 256 /* relocate PAL procedures and PAL PMI */ #define PAL_HALT_INFO 257 /* return the low power capabilities of processor */ @@ -504,7 +507,8 @@ typedef struct pal_cache_check_info_s { wiv : 1, /* Way field valid */ reserved2 : 1, dp : 1, /* Data poisoned on MBE */ - reserved3 : 8, + reserved3 : 6, + hlth : 2, /* Health indicator */ index : 20, /* Cache line index */ reserved4 : 2, @@ -542,7 +546,9 @@ typedef struct pal_tlb_check_info_s { dtc : 1, /* Fail in data TC */ itc : 1, /* Fail in inst. TC */ op : 4, /* Cache operation */ - reserved3 : 30, + reserved3 : 6, + hlth : 2, /* Health indicator */ + reserved4 : 22, is : 1, /* instruction set (1 == ia32) */ iv : 1, /* instruction set field valid */ @@ -633,7 +639,8 @@ typedef struct pal_uarch_check_info_s { way : 6, /* Way of structure */ wv : 1, /* way valid */ xv : 1, /* index valid */ - reserved1 : 8, + reserved1 : 6, + hlth : 2, /* Health indicator */ index : 8, /* Index or set of the uarch * structure that failed. */ @@ -1213,14 +1220,12 @@ ia64_pal_mc_drain (void) /* Return the machine check dynamic processor state */ static inline s64 -ia64_pal_mc_dynamic_state (u64 offset, u64 *size, u64 *pds) +ia64_pal_mc_dynamic_state (u64 info_type, u64 dy_buffer, u64 *size) { struct ia64_pal_retval iprv; - PAL_CALL(iprv, PAL_MC_DYNAMIC_STATE, offset, 0, 0); + PAL_CALL(iprv, PAL_MC_DYNAMIC_STATE, info_type, dy_buffer, 0); if (size) *size = iprv.v0; - if (pds) - *pds = iprv.v1; return iprv.status; } @@ -1281,15 +1286,41 @@ ia64_pal_mc_expected (u64 expected, u64 *previous) return iprv.status; } +typedef union pal_hw_tracking_u { + u64 pht_data; + struct { + u64 itc :4, /* Instruction cache tracking */ + dct :4, /* Date cache tracking */ + itt :4, /* Instruction TLB tracking */ + ddt :4, /* Data TLB tracking */ + reserved:48; + } pal_hw_tracking_s; +} pal_hw_tracking_u_t; + +/* + * Hardware tracking status. + */ +static inline s64 +ia64_pal_mc_hw_tracking (u64 *status) +{ + struct ia64_pal_retval iprv; + PAL_CALL(iprv, PAL_MC_HW_TRACKING, 0, 0, 0); + if (status) + *status = iprv.v0; + return iprv.status; +} + /* Register a platform dependent location with PAL to which it can save * minimal processor state in the event of a machine check or initialization * event. */ static inline s64 -ia64_pal_mc_register_mem (u64 physical_addr) +ia64_pal_mc_register_mem (u64 physical_addr, u64 size, u64 *req_size) { struct ia64_pal_retval iprv; - PAL_CALL(iprv, PAL_MC_REGISTER_MEM, physical_addr, 0, 0); + PAL_CALL(iprv, PAL_MC_REGISTER_MEM, physical_addr, size, 0); + if (req_size) + *req_size = iprv.v0; return iprv.status; } @@ -1631,6 +1662,29 @@ ia64_pal_vm_summary (pal_vm_info_1_u_t *vm_info_1, pal_vm_info_2_u_t *vm_info_2) return iprv.status; } +typedef union pal_vp_info_u { + u64 pvi_val; + struct { + u64 index: 48, /* virtual feature set info */ + vmm_id: 16; /* feature set id */ + } pal_vp_info_s; +} pal_vp_info_u_t; + +/* + * Returns infomation about virtual processor features + */ +static inline s64 +ia64_pal_vp_info (u64 feature_set, u64 vp_buffer, u64 *vp_info, u64 *vmm_id) +{ + struct ia64_pal_retval iprv; + PAL_CALL(iprv, PAL_VP_INFO, feature_set, vp_buffer, 0); + if (vp_info) + *vp_info = iprv.v0; + if (vmm_id) + *vmm_id = iprv.v1; + return iprv.status; +} + typedef union pal_itr_valid_u { u64 piv_val; struct { diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h index e6204f14f61..7a9bff47564 100644 --- a/include/asm-ia64/pgtable.h +++ b/include/asm-ia64/pgtable.h @@ -302,6 +302,8 @@ ia64_phys_addr_valid (unsigned long addr) #define pte_dirty(pte) ((pte_val(pte) & _PAGE_D) != 0) #define pte_young(pte) ((pte_val(pte) & _PAGE_A) != 0) #define pte_file(pte) ((pte_val(pte) & _PAGE_FILE) != 0) +#define pte_special(pte) 0 + /* * Note: we convert AR_RWX to AR_RX and AR_RW to AR_R by clearing the 2nd bit in the * access rights: @@ -313,6 +315,7 @@ ia64_phys_addr_valid (unsigned long addr) #define pte_mkclean(pte) (__pte(pte_val(pte) & ~_PAGE_D)) #define pte_mkdirty(pte) (__pte(pte_val(pte) | _PAGE_D)) #define pte_mkhuge(pte) (__pte(pte_val(pte))) +#define pte_mkspecial(pte) (pte) /* * Because ia64's Icache and Dcache is not coherent (on a cpu), we need to @@ -371,7 +374,7 @@ pgd_index (unsigned long address) /* The offset in the 1-level directory is given by the 3 region bits (61..63) and the level-1 bits. */ static inline pgd_t* -pgd_offset (struct mm_struct *mm, unsigned long address) +pgd_offset (const struct mm_struct *mm, unsigned long address) { return mm->pgd + pgd_index(address); } diff --git a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h index 741f7ecb986..6aff126fc07 100644 --- a/include/asm-ia64/processor.h +++ b/include/asm-ia64/processor.h @@ -119,6 +119,69 @@ struct ia64_psr { __u64 reserved4 : 19; }; +union ia64_isr { + __u64 val; + struct { + __u64 code : 16; + __u64 vector : 8; + __u64 reserved1 : 8; + __u64 x : 1; + __u64 w : 1; + __u64 r : 1; + __u64 na : 1; + __u64 sp : 1; + __u64 rs : 1; + __u64 ir : 1; + __u64 ni : 1; + __u64 so : 1; + __u64 ei : 2; + __u64 ed : 1; + __u64 reserved2 : 20; + }; +}; + +union ia64_lid { + __u64 val; + struct { + __u64 rv : 16; + __u64 eid : 8; + __u64 id : 8; + __u64 ig : 32; + }; +}; + +union ia64_tpr { + __u64 val; + struct { + __u64 ig0 : 4; + __u64 mic : 4; + __u64 rsv : 8; + __u64 mmi : 1; + __u64 ig1 : 47; + }; +}; + +union ia64_itir { + __u64 val; + struct { + __u64 rv3 : 2; /* 0-1 */ + __u64 ps : 6; /* 2-7 */ + __u64 key : 24; /* 8-31 */ + __u64 rv4 : 32; /* 32-63 */ + }; +}; + +union ia64_rr { + __u64 val; + struct { + __u64 ve : 1; /* enable hw walker */ + __u64 reserved0: 1; /* reserved */ + __u64 ps : 6; /* log page size */ + __u64 rid : 24; /* region id */ + __u64 reserved1: 32; /* reserved */ + }; +}; + /* * CPU type, hardware bug flags, and per-CPU state. Frequently used * state comes earlier: diff --git a/include/asm-ia64/sal.h b/include/asm-ia64/sal.h index f4904db3b05..89594b442f8 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/semaphore.h b/include/asm-ia64/semaphore.h index d8393d11288..d9b2034ed1d 100644 --- a/include/asm-ia64/semaphore.h +++ b/include/asm-ia64/semaphore.h @@ -1,99 +1 @@ -#ifndef _ASM_IA64_SEMAPHORE_H -#define _ASM_IA64_SEMAPHORE_H - -/* - * Copyright (C) 1998-2000 Hewlett-Packard Co - * Copyright (C) 1998-2000 David Mosberger-Tang <davidm@hpl.hp.com> - */ - -#include <linux/wait.h> -#include <linux/rwsem.h> - -#include <asm/atomic.h> - -struct semaphore { - atomic_t count; - int sleepers; - wait_queue_head_t wait; -}; - -#define __SEMAPHORE_INITIALIZER(name, n) \ -{ \ - .count = ATOMIC_INIT(n), \ - .sleepers = 0, \ - .wait = __WAIT_QUEUE_HEAD_INITIALIZER((name).wait) \ -} - -#define __DECLARE_SEMAPHORE_GENERIC(name,count) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, count) - -#define DECLARE_MUTEX(name) __DECLARE_SEMAPHORE_GENERIC(name, 1) - -static inline void -sema_init (struct semaphore *sem, int val) -{ - *sem = (struct semaphore) __SEMAPHORE_INITIALIZER(*sem, val); -} - -static inline void -init_MUTEX (struct semaphore *sem) -{ - sema_init(sem, 1); -} - -static inline void -init_MUTEX_LOCKED (struct semaphore *sem) -{ - sema_init(sem, 0); -} - -extern void __down (struct semaphore * sem); -extern int __down_interruptible (struct semaphore * sem); -extern int __down_trylock (struct semaphore * sem); -extern void __up (struct semaphore * sem); - -/* - * Atomically decrement the semaphore's count. If it goes negative, - * block the calling thread in the TASK_UNINTERRUPTIBLE state. - */ -static inline void -down (struct semaphore *sem) -{ - might_sleep(); - if (ia64_fetchadd(-1, &sem->count.counter, acq) < 1) - __down(sem); -} - -/* - * Atomically decrement the semaphore's count. If it goes negative, - * block the calling thread in the TASK_INTERRUPTIBLE state. - */ -static inline int -down_interruptible (struct semaphore * sem) -{ - int ret = 0; - - might_sleep(); - if (ia64_fetchadd(-1, &sem->count.counter, acq) < 1) - ret = __down_interruptible(sem); - return ret; -} - -static inline int -down_trylock (struct semaphore *sem) -{ - int ret = 0; - - if (ia64_fetchadd(-1, &sem->count.counter, acq) < 1) - ret = __down_trylock(sem); - return ret; -} - -static inline void -up (struct semaphore * sem) -{ - if (ia64_fetchadd(1, &sem->count.counter, rel) <= -1) - __up(sem); -} - -#endif /* _ASM_IA64_SEMAPHORE_H */ +#include <linux/semaphore.h> diff --git a/include/asm-ia64/smp.h b/include/asm-ia64/smp.h index 4fa733dd417..ec5f355fb7e 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/sn/nodepda.h b/include/asm-ia64/sn/nodepda.h index 6f6d69e39ff..ee118b901de 100644 --- a/include/asm-ia64/sn/nodepda.h +++ b/include/asm-ia64/sn/nodepda.h @@ -9,7 +9,6 @@ #define _ASM_IA64_SN_NODEPDA_H -#include <asm/semaphore.h> #include <asm/irq.h> #include <asm/sn/arch.h> #include <asm/sn/intr.h> diff --git a/include/asm-ia64/sn/xp.h b/include/asm-ia64/sn/xp.h deleted file mode 100644 index f7711b308e4..00000000000 --- a/include/asm-ia64/sn/xp.h +++ /dev/null @@ -1,485 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2004-2005 Silicon Graphics, Inc. All rights reserved. - */ - - -/* - * External Cross Partition (XP) structures and defines. - */ - - -#ifndef _ASM_IA64_SN_XP_H -#define _ASM_IA64_SN_XP_H - - -#include <linux/cache.h> -#include <linux/hardirq.h> -#include <linux/mutex.h> -#include <asm/sn/types.h> -#include <asm/sn/bte.h> - - -#ifdef USE_DBUG_ON -#define DBUG_ON(condition) BUG_ON(condition) -#else -#define DBUG_ON(condition) -#endif - - -/* - * Define the maximum number of logically defined partitions the system - * can support. It is constrained by the maximum number of hardware - * partitionable regions. The term 'region' in this context refers to the - * minimum number of nodes that can comprise an access protection grouping. - * The access protection is in regards to memory, IPI and IOI. - * - * The maximum number of hardware partitionable regions is equal to the - * maximum number of nodes in the entire system divided by the minimum number - * of nodes that comprise an access protection grouping. - */ -#define XP_MAX_PARTITIONS 64 - - -/* - * Define the number of u64s required to represent all the C-brick nasids - * as a bitmap. The cross-partition kernel modules deal only with - * C-brick nasids, thus the need for bitmaps which don't account for - * odd-numbered (non C-brick) nasids. - */ -#define XP_MAX_PHYSNODE_ID (MAX_NUMALINK_NODES / 2) -#define XP_NASID_MASK_BYTES ((XP_MAX_PHYSNODE_ID + 7) / 8) -#define XP_NASID_MASK_WORDS ((XP_MAX_PHYSNODE_ID + 63) / 64) - - -/* - * Wrapper for bte_copy() that should it return a failure status will retry - * the bte_copy() once in the hope that the failure was due to a temporary - * aberration (i.e., the link going down temporarily). - * - * src - physical address of the source of the transfer. - * vdst - virtual address of the destination of the transfer. - * len - number of bytes to transfer from source to destination. - * mode - see bte_copy() for definition. - * notification - see bte_copy() for definition. - * - * Note: xp_bte_copy() should never be called while holding a spinlock. - */ -static inline bte_result_t -xp_bte_copy(u64 src, u64 vdst, u64 len, u64 mode, void *notification) -{ - bte_result_t ret; - u64 pdst = ia64_tpa(vdst); - - - /* - * Ensure that the physically mapped memory is contiguous. - * - * We do this by ensuring that the memory is from region 7 only. - * If the need should arise to use memory from one of the other - * regions, then modify the BUG_ON() statement to ensure that the - * memory from that region is always physically contiguous. - */ - BUG_ON(REGION_NUMBER(vdst) != RGN_KERNEL); - - ret = bte_copy(src, pdst, len, mode, notification); - if ((ret != BTE_SUCCESS) && BTE_ERROR_RETRY(ret)) { - if (!in_interrupt()) { - cond_resched(); - } - ret = bte_copy(src, pdst, len, mode, notification); - } - - return ret; -} - - -/* - * XPC establishes channel connections between the local partition and any - * other partition that is currently up. Over these channels, kernel-level - * `users' can communicate with their counterparts on the other partitions. - * - * The maxinum number of channels is limited to eight. For performance reasons, - * the internal cross partition structures require sixteen bytes per channel, - * and eight allows all of this interface-shared info to fit in one cache line. - * - * XPC_NCHANNELS reflects the total number of channels currently defined. - * If the need for additional channels arises, one can simply increase - * XPC_NCHANNELS accordingly. If the day should come where that number - * exceeds the MAXIMUM number of channels allowed (eight), then one will need - * to make changes to the XPC code to allow for this. - */ -#define XPC_MEM_CHANNEL 0 /* memory channel number */ -#define XPC_NET_CHANNEL 1 /* network channel number */ - -#define XPC_NCHANNELS 2 /* #of defined channels */ -#define XPC_MAX_NCHANNELS 8 /* max #of channels allowed */ - -#if XPC_NCHANNELS > XPC_MAX_NCHANNELS -#error XPC_NCHANNELS exceeds MAXIMUM allowed. -#endif - - -/* - * The format of an XPC message is as follows: - * - * +-------+--------------------------------+ - * | flags |////////////////////////////////| - * +-------+--------------------------------+ - * | message # | - * +----------------------------------------+ - * | payload (user-defined message) | - * | | - * : - * | | - * +----------------------------------------+ - * - * The size of the payload is defined by the user via xpc_connect(). A user- - * defined message resides in the payload area. - * - * The user should have no dealings with the message header, but only the - * message's payload. When a message entry is allocated (via xpc_allocate()) - * a pointer to the payload area is returned and not the actual beginning of - * the XPC message. The user then constructs a message in the payload area - * and passes that pointer as an argument on xpc_send() or xpc_send_notify(). - * - * The size of a message entry (within a message queue) must be a cacheline - * sized multiple in order to facilitate the BTE transfer of messages from one - * message queue to another. A macro, XPC_MSG_SIZE(), is provided for the user - * that wants to fit as many msg entries as possible in a given memory size - * (e.g. a memory page). - */ -struct xpc_msg { - u8 flags; /* FOR XPC INTERNAL USE ONLY */ - u8 reserved[7]; /* FOR XPC INTERNAL USE ONLY */ - s64 number; /* FOR XPC INTERNAL USE ONLY */ - - u64 payload; /* user defined portion of message */ -}; - - -#define XPC_MSG_PAYLOAD_OFFSET (u64) (&((struct xpc_msg *)0)->payload) -#define XPC_MSG_SIZE(_payload_size) \ - L1_CACHE_ALIGN(XPC_MSG_PAYLOAD_OFFSET + (_payload_size)) - - -/* - * Define the return values and values passed to user's callout functions. - * (It is important to add new value codes at the end just preceding - * xpcUnknownReason, which must have the highest numerical value.) - */ -enum xpc_retval { - xpcSuccess = 0, - - xpcNotConnected, /* 1: channel is not connected */ - xpcConnected, /* 2: channel connected (opened) */ - xpcRETIRED1, /* 3: (formerly xpcDisconnected) */ - - xpcMsgReceived, /* 4: message received */ - xpcMsgDelivered, /* 5: message delivered and acknowledged */ - - xpcRETIRED2, /* 6: (formerly xpcTransferFailed) */ - - xpcNoWait, /* 7: operation would require wait */ - xpcRetry, /* 8: retry operation */ - xpcTimeout, /* 9: timeout in xpc_allocate_msg_wait() */ - xpcInterrupted, /* 10: interrupted wait */ - - xpcUnequalMsgSizes, /* 11: message size disparity between sides */ - xpcInvalidAddress, /* 12: invalid address */ - - xpcNoMemory, /* 13: no memory available for XPC structures */ - xpcLackOfResources, /* 14: insufficient resources for operation */ - xpcUnregistered, /* 15: channel is not registered */ - xpcAlreadyRegistered, /* 16: channel is already registered */ - - xpcPartitionDown, /* 17: remote partition is down */ - xpcNotLoaded, /* 18: XPC module is not loaded */ - xpcUnloading, /* 19: this side is unloading XPC module */ - - xpcBadMagic, /* 20: XPC MAGIC string not found */ - - xpcReactivating, /* 21: remote partition was reactivated */ - - xpcUnregistering, /* 22: this side is unregistering channel */ - xpcOtherUnregistering, /* 23: other side is unregistering channel */ - - xpcCloneKThread, /* 24: cloning kernel thread */ - xpcCloneKThreadFailed, /* 25: cloning kernel thread failed */ - - xpcNoHeartbeat, /* 26: remote partition has no heartbeat */ - - xpcPioReadError, /* 27: PIO read error */ - xpcPhysAddrRegFailed, /* 28: registration of phys addr range failed */ - - xpcBteDirectoryError, /* 29: maps to BTEFAIL_DIR */ - xpcBtePoisonError, /* 30: maps to BTEFAIL_POISON */ - xpcBteWriteError, /* 31: maps to BTEFAIL_WERR */ - xpcBteAccessError, /* 32: maps to BTEFAIL_ACCESS */ - xpcBtePWriteError, /* 33: maps to BTEFAIL_PWERR */ - xpcBtePReadError, /* 34: maps to BTEFAIL_PRERR */ - xpcBteTimeOutError, /* 35: maps to BTEFAIL_TOUT */ - xpcBteXtalkError, /* 36: maps to BTEFAIL_XTERR */ - xpcBteNotAvailable, /* 37: maps to BTEFAIL_NOTAVAIL */ - xpcBteUnmappedError, /* 38: unmapped BTEFAIL_ error */ - - xpcBadVersion, /* 39: bad version number */ - xpcVarsNotSet, /* 40: the XPC variables are not set up */ - xpcNoRsvdPageAddr, /* 41: unable to get rsvd page's phys addr */ - xpcInvalidPartid, /* 42: invalid partition ID */ - xpcLocalPartid, /* 43: local partition ID */ - - xpcOtherGoingDown, /* 44: other side going down, reason unknown */ - xpcSystemGoingDown, /* 45: system is going down, reason unknown */ - xpcSystemHalt, /* 46: system is being halted */ - xpcSystemReboot, /* 47: system is being rebooted */ - xpcSystemPoweroff, /* 48: system is being powered off */ - - xpcDisconnecting, /* 49: channel disconnecting (closing) */ - - xpcOpenCloseError, /* 50: channel open/close protocol error */ - - xpcDisconnected, /* 51: channel disconnected (closed) */ - - xpcBteSh2Start, /* 52: BTE CRB timeout */ - - /* 53: 0x1 BTE Error Response Short */ - xpcBteSh2RspShort = xpcBteSh2Start + BTEFAIL_SH2_RESP_SHORT, - - /* 54: 0x2 BTE Error Response Long */ - xpcBteSh2RspLong = xpcBteSh2Start + BTEFAIL_SH2_RESP_LONG, - - /* 56: 0x4 BTE Error Response DSB */ - xpcBteSh2RspDSB = xpcBteSh2Start + BTEFAIL_SH2_RESP_DSP, - - /* 60: 0x8 BTE Error Response Access */ - xpcBteSh2RspAccess = xpcBteSh2Start + BTEFAIL_SH2_RESP_ACCESS, - - /* 68: 0x10 BTE Error CRB timeout */ - xpcBteSh2CRBTO = xpcBteSh2Start + BTEFAIL_SH2_CRB_TO, - - /* 84: 0x20 BTE Error NACK limit */ - xpcBteSh2NACKLimit = xpcBteSh2Start + BTEFAIL_SH2_NACK_LIMIT, - - /* 115: BTE end */ - xpcBteSh2End = xpcBteSh2Start + BTEFAIL_SH2_ALL, - - xpcUnknownReason /* 116: unknown reason -- must be last in list */ -}; - - -/* - * Define the callout function types used by XPC to update the user on - * connection activity and state changes (via the user function registered by - * xpc_connect()) and to notify them of messages received and delivered (via - * the user function registered by xpc_send_notify()). - * - * The two function types are xpc_channel_func and xpc_notify_func and - * both share the following arguments, with the exception of "data", which - * only xpc_channel_func has. - * - * Arguments: - * - * reason - reason code. (See following table.) - * partid - partition ID associated with condition. - * ch_number - channel # associated with condition. - * data - pointer to optional data. (See following table.) - * key - pointer to optional user-defined value provided as the "key" - * argument to xpc_connect() or xpc_send_notify(). - * - * In the following table the "Optional Data" column applies to callouts made - * to functions registered by xpc_connect(). A "NA" in that column indicates - * that this reason code can be passed to functions registered by - * xpc_send_notify() (i.e. they don't have data arguments). - * - * Also, the first three reason codes in the following table indicate - * success, whereas the others indicate failure. When a failure reason code - * is received, one can assume that the channel is not connected. - * - * - * Reason Code | Cause | Optional Data - * =====================+================================+===================== - * xpcConnected | connection has been established| max #of entries - * | to the specified partition on | allowed in message - * | the specified channel | queue - * ---------------------+--------------------------------+--------------------- - * xpcMsgReceived | an XPC message arrived from | address of payload - * | the specified partition on the | - * | specified channel | [the user must call - * | | xpc_received() when - * | | finished with the - * | | payload] - * ---------------------+--------------------------------+--------------------- - * xpcMsgDelivered | notification that the message | NA - * | was delivered to the intended | - * | recipient and that they have | - * | acknowledged its receipt by | - * | calling xpc_received() | - * =====================+================================+===================== - * xpcUnequalMsgSizes | can't connect to the specified | NULL - * | partition on the specified | - * | channel because of mismatched | - * | message sizes | - * ---------------------+--------------------------------+--------------------- - * xpcNoMemory | insufficient memory avaiable | NULL - * | to allocate message queue | - * ---------------------+--------------------------------+--------------------- - * xpcLackOfResources | lack of resources to create | NULL - * | the necessary kthreads to | - * | support the channel | - * ---------------------+--------------------------------+--------------------- - * xpcUnregistering | this side's user has | NULL or NA - * | unregistered by calling | - * | xpc_disconnect() | - * ---------------------+--------------------------------+--------------------- - * xpcOtherUnregistering| the other side's user has | NULL or NA - * | unregistered by calling | - * | xpc_disconnect() | - * ---------------------+--------------------------------+--------------------- - * xpcNoHeartbeat | the other side's XPC is no | NULL or NA - * | longer heartbeating | - * | | - * ---------------------+--------------------------------+--------------------- - * xpcUnloading | this side's XPC module is | NULL or NA - * | being unloaded | - * | | - * ---------------------+--------------------------------+--------------------- - * xpcOtherUnloading | the other side's XPC module is | NULL or NA - * | is being unloaded | - * | | - * ---------------------+--------------------------------+--------------------- - * xpcPioReadError | xp_nofault_PIOR() returned an | NULL or NA - * | error while sending an IPI | - * | | - * ---------------------+--------------------------------+--------------------- - * xpcInvalidAddress | the address either received or | NULL or NA - * | sent by the specified partition| - * | is invalid | - * ---------------------+--------------------------------+--------------------- - * xpcBteNotAvailable | attempt to pull data from the | NULL or NA - * xpcBtePoisonError | specified partition over the | - * xpcBteWriteError | specified channel via a | - * xpcBteAccessError | bte_copy() failed | - * xpcBteTimeOutError | | - * xpcBteXtalkError | | - * xpcBteDirectoryError | | - * xpcBteGenericError | | - * xpcBteUnmappedError | | - * ---------------------+--------------------------------+--------------------- - * xpcUnknownReason | the specified channel to the | NULL or NA - * | specified partition was | - * | unavailable for unknown reasons| - * =====================+================================+===================== - */ - -typedef void (*xpc_channel_func)(enum xpc_retval reason, partid_t partid, - int ch_number, void *data, void *key); - -typedef void (*xpc_notify_func)(enum xpc_retval reason, partid_t partid, - int ch_number, void *key); - - -/* - * The following is a registration entry. There is a global array of these, - * one per channel. It is used to record the connection registration made - * by the users of XPC. As long as a registration entry exists, for any - * partition that comes up, XPC will attempt to establish a connection on - * that channel. Notification that a connection has been made will occur via - * the xpc_channel_func function. - * - * The 'func' field points to the function to call when aynchronous - * notification is required for such events as: a connection established/lost, - * or an incoming message received, or an error condition encountered. A - * non-NULL 'func' field indicates that there is an active registration for - * the channel. - */ -struct xpc_registration { - struct mutex mutex; - xpc_channel_func func; /* function to call */ - void *key; /* pointer to user's key */ - u16 nentries; /* #of msg entries in local msg queue */ - u16 msg_size; /* message queue's message size */ - u32 assigned_limit; /* limit on #of assigned kthreads */ - u32 idle_limit; /* limit on #of idle kthreads */ -} ____cacheline_aligned; - - -#define XPC_CHANNEL_REGISTERED(_c) (xpc_registrations[_c].func != NULL) - - -/* the following are valid xpc_allocate() flags */ -#define XPC_WAIT 0 /* wait flag */ -#define XPC_NOWAIT 1 /* no wait flag */ - - -struct xpc_interface { - void (*connect)(int); - void (*disconnect)(int); - enum xpc_retval (*allocate)(partid_t, int, u32, void **); - enum xpc_retval (*send)(partid_t, int, void *); - enum xpc_retval (*send_notify)(partid_t, int, void *, - xpc_notify_func, void *); - void (*received)(partid_t, int, void *); - enum xpc_retval (*partid_to_nasids)(partid_t, void *); -}; - - -extern struct xpc_interface xpc_interface; - -extern void xpc_set_interface(void (*)(int), - void (*)(int), - enum xpc_retval (*)(partid_t, int, u32, void **), - enum xpc_retval (*)(partid_t, int, void *), - enum xpc_retval (*)(partid_t, int, void *, xpc_notify_func, - void *), - void (*)(partid_t, int, void *), - enum xpc_retval (*)(partid_t, void *)); -extern void xpc_clear_interface(void); - - -extern enum xpc_retval xpc_connect(int, xpc_channel_func, void *, u16, - u16, u32, u32); -extern void xpc_disconnect(int); - -static inline enum xpc_retval -xpc_allocate(partid_t partid, int ch_number, u32 flags, void **payload) -{ - return xpc_interface.allocate(partid, ch_number, flags, payload); -} - -static inline enum xpc_retval -xpc_send(partid_t partid, int ch_number, void *payload) -{ - return xpc_interface.send(partid, ch_number, payload); -} - -static inline enum xpc_retval -xpc_send_notify(partid_t partid, int ch_number, void *payload, - xpc_notify_func func, void *key) -{ - return xpc_interface.send_notify(partid, ch_number, payload, func, key); -} - -static inline void -xpc_received(partid_t partid, int ch_number, void *payload) -{ - return xpc_interface.received(partid, ch_number, payload); -} - -static inline enum xpc_retval -xpc_partid_to_nasids(partid_t partid, void *nasids) -{ - return xpc_interface.partid_to_nasids(partid, nasids); -} - - -extern u64 xp_nofault_PIOR_target; -extern int xp_nofault_PIOR(void *); -extern int xp_error_PIOR(void); - - -#endif /* _ASM_IA64_SN_XP_H */ - diff --git a/include/asm-ia64/sn/xpc.h b/include/asm-ia64/sn/xpc.h deleted file mode 100644 index 3c0900ab800..00000000000 --- a/include/asm-ia64/sn/xpc.h +++ /dev/null @@ -1,1267 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (c) 2004-2007 Silicon Graphics, Inc. All Rights Reserved. - */ - - -/* - * Cross Partition Communication (XPC) structures and macros. - */ - -#ifndef _ASM_IA64_SN_XPC_H -#define _ASM_IA64_SN_XPC_H - - -#include <linux/interrupt.h> -#include <linux/sysctl.h> -#include <linux/device.h> -#include <linux/mutex.h> -#include <linux/completion.h> -#include <asm/pgtable.h> -#include <asm/processor.h> -#include <asm/sn/bte.h> -#include <asm/sn/clksupport.h> -#include <asm/sn/addrs.h> -#include <asm/sn/mspec.h> -#include <asm/sn/shub_mmr.h> -#include <asm/sn/xp.h> - - -/* - * XPC Version numbers consist of a major and minor number. XPC can always - * talk to versions with same major #, and never talk to versions with a - * different major #. - */ -#define _XPC_VERSION(_maj, _min) (((_maj) << 4) | ((_min) & 0xf)) -#define XPC_VERSION_MAJOR(_v) ((_v) >> 4) -#define XPC_VERSION_MINOR(_v) ((_v) & 0xf) - - -/* - * The next macros define word or bit representations for given - * C-brick nasid in either the SAL provided bit array representing - * nasids in the partition/machine or the AMO_t array used for - * inter-partition initiation communications. - * - * For SN2 machines, C-Bricks are alway even numbered NASIDs. As - * such, some space will be saved by insisting that nasid information - * passed from SAL always be packed for C-Bricks and the - * cross-partition interrupts use the same packing scheme. - */ -#define XPC_NASID_W_INDEX(_n) (((_n) / 64) / 2) -#define XPC_NASID_B_INDEX(_n) (((_n) / 2) & (64 - 1)) -#define XPC_NASID_IN_ARRAY(_n, _p) ((_p)[XPC_NASID_W_INDEX(_n)] & \ - (1UL << XPC_NASID_B_INDEX(_n))) -#define XPC_NASID_FROM_W_B(_w, _b) (((_w) * 64 + (_b)) * 2) - -#define XPC_HB_DEFAULT_INTERVAL 5 /* incr HB every x secs */ -#define XPC_HB_CHECK_DEFAULT_INTERVAL 20 /* check HB every x secs */ - -/* define the process name of HB checker and the CPU it is pinned to */ -#define XPC_HB_CHECK_THREAD_NAME "xpc_hb" -#define XPC_HB_CHECK_CPU 0 - -/* define the process name of the discovery thread */ -#define XPC_DISCOVERY_THREAD_NAME "xpc_discovery" - - -/* - * the reserved page - * - * SAL reserves one page of memory per partition for XPC. Though a full page - * in length (16384 bytes), its starting address is not page aligned, but it - * is cacheline aligned. The reserved page consists of the following: - * - * reserved page header - * - * The first cacheline of the reserved page contains the header - * (struct xpc_rsvd_page). Before SAL initialization has completed, - * SAL has set up the following fields of the reserved page header: - * SAL_signature, SAL_version, partid, and nasids_size. The other - * fields are set up by XPC. (xpc_rsvd_page points to the local - * partition's reserved page.) - * - * part_nasids mask - * mach_nasids mask - * - * SAL also sets up two bitmaps (or masks), one that reflects the actual - * nasids in this partition (part_nasids), and the other that reflects - * the actual nasids in the entire machine (mach_nasids). We're only - * interested in the even numbered nasids (which contain the processors - * and/or memory), so we only need half as many bits to represent the - * nasids. The part_nasids mask is located starting at the first cacheline - * following the reserved page header. The mach_nasids mask follows right - * after the part_nasids mask. The size in bytes of each mask is reflected - * by the reserved page header field 'nasids_size'. (Local partition's - * mask pointers are xpc_part_nasids and xpc_mach_nasids.) - * - * vars - * vars part - * - * Immediately following the mach_nasids mask are the XPC variables - * required by other partitions. First are those that are generic to all - * partitions (vars), followed on the next available cacheline by those - * which are partition specific (vars part). These are setup by XPC. - * (Local partition's vars pointers are xpc_vars and xpc_vars_part.) - * - * Note: Until vars_pa is set, the partition XPC code has not been initialized. - */ -struct xpc_rsvd_page { - u64 SAL_signature; /* SAL: unique signature */ - u64 SAL_version; /* SAL: version */ - u8 partid; /* SAL: partition ID */ - u8 version; - u8 pad1[6]; /* align to next u64 in cacheline */ - volatile u64 vars_pa; - struct timespec stamp; /* time when reserved page was setup by XPC */ - u64 pad2[9]; /* align to last u64 in cacheline */ - u64 nasids_size; /* SAL: size of each nasid mask in bytes */ -}; - -#define XPC_RP_VERSION _XPC_VERSION(1,1) /* version 1.1 of the reserved page */ - -#define XPC_SUPPORTS_RP_STAMP(_version) \ - (_version >= _XPC_VERSION(1,1)) - -/* - * compare stamps - the return value is: - * - * < 0, if stamp1 < stamp2 - * = 0, if stamp1 == stamp2 - * > 0, if stamp1 > stamp2 - */ -static inline int -xpc_compare_stamps(struct timespec *stamp1, struct timespec *stamp2) -{ - int ret; - - - if ((ret = stamp1->tv_sec - stamp2->tv_sec) == 0) { - ret = stamp1->tv_nsec - stamp2->tv_nsec; - } - return ret; -} - - -/* - * Define the structures by which XPC variables can be exported to other - * partitions. (There are two: struct xpc_vars and struct xpc_vars_part) - */ - -/* - * The following structure describes the partition generic variables - * needed by other partitions in order to properly initialize. - * - * struct xpc_vars version number also applies to struct xpc_vars_part. - * Changes to either structure and/or related functionality should be - * reflected by incrementing either the major or minor version numbers - * of struct xpc_vars. - */ -struct xpc_vars { - u8 version; - u64 heartbeat; - u64 heartbeating_to_mask; - u64 heartbeat_offline; /* if 0, heartbeat should be changing */ - int act_nasid; - int act_phys_cpuid; - u64 vars_part_pa; - u64 amos_page_pa; /* paddr of page of AMOs from MSPEC driver */ - AMO_t *amos_page; /* vaddr of page of AMOs from MSPEC driver */ -}; - -#define XPC_V_VERSION _XPC_VERSION(3,1) /* version 3.1 of the cross vars */ - -#define XPC_SUPPORTS_DISENGAGE_REQUEST(_version) \ - (_version >= _XPC_VERSION(3,1)) - - -static inline int -xpc_hb_allowed(partid_t partid, struct xpc_vars *vars) -{ - return ((vars->heartbeating_to_mask & (1UL << partid)) != 0); -} - -static inline void -xpc_allow_hb(partid_t partid, struct xpc_vars *vars) -{ - u64 old_mask, new_mask; - - do { - old_mask = vars->heartbeating_to_mask; - new_mask = (old_mask | (1UL << partid)); - } while (cmpxchg(&vars->heartbeating_to_mask, old_mask, new_mask) != - old_mask); -} - -static inline void -xpc_disallow_hb(partid_t partid, struct xpc_vars *vars) -{ - u64 old_mask, new_mask; - - do { - old_mask = vars->heartbeating_to_mask; - new_mask = (old_mask & ~(1UL << partid)); - } while (cmpxchg(&vars->heartbeating_to_mask, old_mask, new_mask) != - old_mask); -} - - -/* - * The AMOs page consists of a number of AMO variables which are divided into - * four groups, The first two groups are used to identify an IRQ's sender. - * These two groups consist of 64 and 128 AMO variables respectively. The last - * two groups, consisting of just one AMO variable each, are used to identify - * the remote partitions that are currently engaged (from the viewpoint of - * the XPC running on the remote partition). - */ -#define XPC_NOTIFY_IRQ_AMOS 0 -#define XPC_ACTIVATE_IRQ_AMOS (XPC_NOTIFY_IRQ_AMOS + XP_MAX_PARTITIONS) -#define XPC_ENGAGED_PARTITIONS_AMO (XPC_ACTIVATE_IRQ_AMOS + XP_NASID_MASK_WORDS) -#define XPC_DISENGAGE_REQUEST_AMO (XPC_ENGAGED_PARTITIONS_AMO + 1) - - -/* - * The following structure describes the per partition specific variables. - * - * An array of these structures, one per partition, will be defined. As a - * partition becomes active XPC will copy the array entry corresponding to - * itself from that partition. It is desirable that the size of this - * structure evenly divide into a cacheline, such that none of the entries - * in this array crosses a cacheline boundary. As it is now, each entry - * occupies half a cacheline. - */ -struct xpc_vars_part { - volatile u64 magic; - - u64 openclose_args_pa; /* physical address of open and close args */ - u64 GPs_pa; /* physical address of Get/Put values */ - - u64 IPI_amo_pa; /* physical address of IPI AMO_t structure */ - int IPI_nasid; /* nasid of where to send IPIs */ - int IPI_phys_cpuid; /* physical CPU ID of where to send IPIs */ - - u8 nchannels; /* #of defined channels supported */ - - u8 reserved[23]; /* pad to a full 64 bytes */ -}; - -/* - * The vars_part MAGIC numbers play a part in the first contact protocol. - * - * MAGIC1 indicates that the per partition specific variables for a remote - * partition have been initialized by this partition. - * - * MAGIC2 indicates that this partition has pulled the remote partititions - * per partition variables that pertain to this partition. - */ -#define XPC_VP_MAGIC1 0x0053524156435058L /* 'XPCVARS\0'L (little endian) */ -#define XPC_VP_MAGIC2 0x0073726176435058L /* 'XPCvars\0'L (little endian) */ - - -/* the reserved page sizes and offsets */ - -#define XPC_RP_HEADER_SIZE L1_CACHE_ALIGN(sizeof(struct xpc_rsvd_page)) -#define XPC_RP_VARS_SIZE L1_CACHE_ALIGN(sizeof(struct xpc_vars)) - -#define XPC_RP_PART_NASIDS(_rp) (u64 *) ((u8 *) _rp + XPC_RP_HEADER_SIZE) -#define XPC_RP_MACH_NASIDS(_rp) (XPC_RP_PART_NASIDS(_rp) + xp_nasid_mask_words) -#define XPC_RP_VARS(_rp) ((struct xpc_vars *) XPC_RP_MACH_NASIDS(_rp) + xp_nasid_mask_words) -#define XPC_RP_VARS_PART(_rp) (struct xpc_vars_part *) ((u8 *) XPC_RP_VARS(rp) + XPC_RP_VARS_SIZE) - - -/* - * Functions registered by add_timer() or called by kernel_thread() only - * allow for a single 64-bit argument. The following macros can be used to - * pack and unpack two (32-bit, 16-bit or 8-bit) arguments into or out from - * the passed argument. - */ -#define XPC_PACK_ARGS(_arg1, _arg2) \ - ((((u64) _arg1) & 0xffffffff) | \ - ((((u64) _arg2) & 0xffffffff) << 32)) - -#define XPC_UNPACK_ARG1(_args) (((u64) _args) & 0xffffffff) -#define XPC_UNPACK_ARG2(_args) ((((u64) _args) >> 32) & 0xffffffff) - - - -/* - * Define a Get/Put value pair (pointers) used with a message queue. - */ -struct xpc_gp { - volatile s64 get; /* Get value */ - volatile s64 put; /* Put value */ -}; - -#define XPC_GP_SIZE \ - L1_CACHE_ALIGN(sizeof(struct xpc_gp) * XPC_NCHANNELS) - - - -/* - * Define a structure that contains arguments associated with opening and - * closing a channel. - */ -struct xpc_openclose_args { - u16 reason; /* reason why channel is closing */ - u16 msg_size; /* sizeof each message entry */ - u16 remote_nentries; /* #of message entries in remote msg queue */ - u16 local_nentries; /* #of message entries in local msg queue */ - u64 local_msgqueue_pa; /* physical address of local message queue */ -}; - -#define XPC_OPENCLOSE_ARGS_SIZE \ - L1_CACHE_ALIGN(sizeof(struct xpc_openclose_args) * XPC_NCHANNELS) - - - -/* struct xpc_msg flags */ - -#define XPC_M_DONE 0x01 /* msg has been received/consumed */ -#define XPC_M_READY 0x02 /* msg is ready to be sent */ -#define XPC_M_INTERRUPT 0x04 /* send interrupt when msg consumed */ - - -#define XPC_MSG_ADDRESS(_payload) \ - ((struct xpc_msg *)((u8 *)(_payload) - XPC_MSG_PAYLOAD_OFFSET)) - - - -/* - * Defines notify entry. - * - * This is used to notify a message's sender that their message was received - * and consumed by the intended recipient. - */ -struct xpc_notify { - volatile u8 type; /* type of notification */ - - /* the following two fields are only used if type == XPC_N_CALL */ - xpc_notify_func func; /* user's notify function */ - void *key; /* pointer to user's key */ -}; - -/* struct xpc_notify type of notification */ - -#define XPC_N_CALL 0x01 /* notify function provided by user */ - - - -/* - * Define the structure that manages all the stuff required by a channel. In - * particular, they are used to manage the messages sent across the channel. - * - * This structure is private to a partition, and is NOT shared across the - * partition boundary. - * - * There is an array of these structures for each remote partition. It is - * allocated at the time a partition becomes active. The array contains one - * of these structures for each potential channel connection to that partition. - * - * Each of these structures manages two message queues (circular buffers). - * They are allocated at the time a channel connection is made. One of - * these message queues (local_msgqueue) holds the locally created messages - * that are destined for the remote partition. The other of these message - * queues (remote_msgqueue) is a locally cached copy of the remote partition's - * own local_msgqueue. - * - * The following is a description of the Get/Put pointers used to manage these - * two message queues. Consider the local_msgqueue to be on one partition - * and the remote_msgqueue to be its cached copy on another partition. A - * description of what each of the lettered areas contains is included. - * - * - * local_msgqueue remote_msgqueue - * - * |/////////| |/////////| - * w_remote_GP.get --> +---------+ |/////////| - * | F | |/////////| - * remote_GP.get --> +---------+ +---------+ <-- local_GP->get - * | | | | - * | | | E | - * | | | | - * | | +---------+ <-- w_local_GP.get - * | B | |/////////| - * | | |////D////| - * | | |/////////| - * | | +---------+ <-- w_remote_GP.put - * | | |////C////| - * local_GP->put --> +---------+ +---------+ <-- remote_GP.put - * | | |/////////| - * | A | |/////////| - * | | |/////////| - * w_local_GP.put --> +---------+ |/////////| - * |/////////| |/////////| - * - * - * ( remote_GP.[get|put] are cached copies of the remote - * partition's local_GP->[get|put], and thus their values can - * lag behind their counterparts on the remote partition. ) - * - * - * A - Messages that have been allocated, but have not yet been sent to the - * remote partition. - * - * B - Messages that have been sent, but have not yet been acknowledged by the - * remote partition as having been received. - * - * C - Area that needs to be prepared for the copying of sent messages, by - * the clearing of the message flags of any previously received messages. - * - * D - Area into which sent messages are to be copied from the remote - * partition's local_msgqueue and then delivered to their intended - * recipients. [ To allow for a multi-message copy, another pointer - * (next_msg_to_pull) has been added to keep track of the next message - * number needing to be copied (pulled). It chases after w_remote_GP.put. - * Any messages lying between w_local_GP.get and next_msg_to_pull have - * been copied and are ready to be delivered. ] - * - * E - Messages that have been copied and delivered, but have not yet been - * acknowledged by the recipient as having been received. - * - * F - Messages that have been acknowledged, but XPC has not yet notified the - * sender that the message was received by its intended recipient. - * This is also an area that needs to be prepared for the allocating of - * new messages, by the clearing of the message flags of the acknowledged - * messages. - */ -struct xpc_channel { - partid_t partid; /* ID of remote partition connected */ - spinlock_t lock; /* lock for updating this structure */ - u32 flags; /* general flags */ - - enum xpc_retval reason; /* reason why channel is disconnect'g */ - int reason_line; /* line# disconnect initiated from */ - - u16 number; /* channel # */ - - u16 msg_size; /* sizeof each msg entry */ - u16 local_nentries; /* #of msg entries in local msg queue */ - u16 remote_nentries; /* #of msg entries in remote msg queue*/ - - void *local_msgqueue_base; /* base address of kmalloc'd space */ - struct xpc_msg *local_msgqueue; /* local message queue */ - void *remote_msgqueue_base; /* base address of kmalloc'd space */ - struct xpc_msg *remote_msgqueue;/* cached copy of remote partition's */ - /* local message queue */ - u64 remote_msgqueue_pa; /* phys addr of remote partition's */ - /* local message queue */ - - atomic_t references; /* #of external references to queues */ - - atomic_t n_on_msg_allocate_wq; /* #on msg allocation wait queue */ - wait_queue_head_t msg_allocate_wq; /* msg allocation wait queue */ - - u8 delayed_IPI_flags; /* IPI flags received, but delayed */ - /* action until channel disconnected */ - - /* queue of msg senders who want to be notified when msg received */ - - atomic_t n_to_notify; /* #of msg senders to notify */ - struct xpc_notify *notify_queue;/* notify queue for messages sent */ - - xpc_channel_func func; /* user's channel function */ - void *key; /* pointer to user's key */ - - struct mutex msg_to_pull_mutex; /* next msg to pull serialization */ - struct completion wdisconnect_wait; /* wait for channel disconnect */ - - struct xpc_openclose_args *local_openclose_args; /* args passed on */ - /* opening or closing of channel */ - - /* various flavors of local and remote Get/Put values */ - - struct xpc_gp *local_GP; /* local Get/Put values */ - struct xpc_gp remote_GP; /* remote Get/Put values */ - struct xpc_gp w_local_GP; /* working local Get/Put values */ - struct xpc_gp w_remote_GP; /* working remote Get/Put values */ - s64 next_msg_to_pull; /* Put value of next msg to pull */ - - /* kthread management related fields */ - -// >>> rethink having kthreads_assigned_limit and kthreads_idle_limit; perhaps -// >>> allow the assigned limit be unbounded and let the idle limit be dynamic -// >>> dependent on activity over the last interval of time - atomic_t kthreads_assigned; /* #of kthreads assigned to channel */ - u32 kthreads_assigned_limit; /* limit on #of kthreads assigned */ - atomic_t kthreads_idle; /* #of kthreads idle waiting for work */ - u32 kthreads_idle_limit; /* limit on #of kthreads idle */ - atomic_t kthreads_active; /* #of kthreads actively working */ - // >>> following field is temporary - u32 kthreads_created; /* total #of kthreads created */ - - wait_queue_head_t idle_wq; /* idle kthread wait queue */ - -} ____cacheline_aligned; - - -/* struct xpc_channel flags */ - -#define XPC_C_WASCONNECTED 0x00000001 /* channel was connected */ - -#define XPC_C_ROPENREPLY 0x00000002 /* remote open channel reply */ -#define XPC_C_OPENREPLY 0x00000004 /* local open channel reply */ -#define XPC_C_ROPENREQUEST 0x00000008 /* remote open channel request */ -#define XPC_C_OPENREQUEST 0x00000010 /* local open channel request */ - -#define XPC_C_SETUP 0x00000020 /* channel's msgqueues are alloc'd */ -#define XPC_C_CONNECTEDCALLOUT 0x00000040 /* connected callout initiated */ -#define XPC_C_CONNECTEDCALLOUT_MADE \ - 0x00000080 /* connected callout completed */ -#define XPC_C_CONNECTED 0x00000100 /* local channel is connected */ -#define XPC_C_CONNECTING 0x00000200 /* channel is being connected */ - -#define XPC_C_RCLOSEREPLY 0x00000400 /* remote close channel reply */ -#define XPC_C_CLOSEREPLY 0x00000800 /* local close channel reply */ -#define XPC_C_RCLOSEREQUEST 0x00001000 /* remote close channel request */ -#define XPC_C_CLOSEREQUEST 0x00002000 /* local close channel request */ - -#define XPC_C_DISCONNECTED 0x00004000 /* channel is disconnected */ -#define XPC_C_DISCONNECTING 0x00008000 /* channel is being disconnected */ -#define XPC_C_DISCONNECTINGCALLOUT \ - 0x00010000 /* disconnecting callout initiated */ -#define XPC_C_DISCONNECTINGCALLOUT_MADE \ - 0x00020000 /* disconnecting callout completed */ -#define XPC_C_WDISCONNECT 0x00040000 /* waiting for channel disconnect */ - - - -/* - * Manages channels on a partition basis. There is one of these structures - * for each partition (a partition will never utilize the structure that - * represents itself). - */ -struct xpc_partition { - - /* XPC HB infrastructure */ - - u8 remote_rp_version; /* version# of partition's rsvd pg */ - struct timespec remote_rp_stamp;/* time when rsvd pg was initialized */ - u64 remote_rp_pa; /* phys addr of partition's rsvd pg */ - u64 remote_vars_pa; /* phys addr of partition's vars */ - u64 remote_vars_part_pa; /* phys addr of partition's vars part */ - u64 last_heartbeat; /* HB at last read */ - u64 remote_amos_page_pa; /* phys addr of partition's amos page */ - int remote_act_nasid; /* active part's act/deact nasid */ - int remote_act_phys_cpuid; /* active part's act/deact phys cpuid */ - u32 act_IRQ_rcvd; /* IRQs since activation */ - spinlock_t act_lock; /* protect updating of act_state */ - u8 act_state; /* from XPC HB viewpoint */ - u8 remote_vars_version; /* version# of partition's vars */ - enum xpc_retval reason; /* reason partition is deactivating */ - int reason_line; /* line# deactivation initiated from */ - int reactivate_nasid; /* nasid in partition to reactivate */ - - unsigned long disengage_request_timeout; /* timeout in jiffies */ - struct timer_list disengage_request_timer; - - - /* XPC infrastructure referencing and teardown control */ - - volatile u8 setup_state; /* infrastructure setup state */ - wait_queue_head_t teardown_wq; /* kthread waiting to teardown infra */ - atomic_t references; /* #of references to infrastructure */ - - - /* - * NONE OF THE PRECEDING FIELDS OF THIS STRUCTURE WILL BE CLEARED WHEN - * XPC SETS UP THE NECESSARY INFRASTRUCTURE TO SUPPORT CROSS PARTITION - * COMMUNICATION. ALL OF THE FOLLOWING FIELDS WILL BE CLEARED. (THE - * 'nchannels' FIELD MUST BE THE FIRST OF THE FIELDS TO BE CLEARED.) - */ - - - u8 nchannels; /* #of defined channels supported */ - atomic_t nchannels_active; /* #of channels that are not DISCONNECTED */ - atomic_t nchannels_engaged;/* #of channels engaged with remote part */ - struct xpc_channel *channels;/* array of channel structures */ - - void *local_GPs_base; /* base address of kmalloc'd space */ - struct xpc_gp *local_GPs; /* local Get/Put values */ - void *remote_GPs_base; /* base address of kmalloc'd space */ - struct xpc_gp *remote_GPs;/* copy of remote partition's local Get/Put */ - /* values */ - u64 remote_GPs_pa; /* phys address of remote partition's local */ - /* Get/Put values */ - - - /* fields used to pass args when opening or closing a channel */ - - void *local_openclose_args_base; /* base address of kmalloc'd space */ - struct xpc_openclose_args *local_openclose_args; /* local's args */ - void *remote_openclose_args_base; /* base address of kmalloc'd space */ - struct xpc_openclose_args *remote_openclose_args; /* copy of remote's */ - /* args */ - u64 remote_openclose_args_pa; /* phys addr of remote's args */ - - - /* IPI sending, receiving and handling related fields */ - - int remote_IPI_nasid; /* nasid of where to send IPIs */ - int remote_IPI_phys_cpuid; /* phys CPU ID of where to send IPIs */ - AMO_t *remote_IPI_amo_va; /* address of remote IPI AMO_t structure */ - - AMO_t *local_IPI_amo_va; /* address of IPI AMO_t structure */ - u64 local_IPI_amo; /* IPI amo flags yet to be handled */ - char IPI_owner[8]; /* IPI owner's name */ - struct timer_list dropped_IPI_timer; /* dropped IPI timer */ - - spinlock_t IPI_lock; /* IPI handler lock */ - - - /* channel manager related fields */ - - atomic_t channel_mgr_requests; /* #of requests to activate chan mgr */ - wait_queue_head_t channel_mgr_wq; /* channel mgr's wait queue */ - -} ____cacheline_aligned; - - -/* struct xpc_partition act_state values (for XPC HB) */ - -#define XPC_P_INACTIVE 0x00 /* partition is not active */ -#define XPC_P_ACTIVATION_REQ 0x01 /* created thread to activate */ -#define XPC_P_ACTIVATING 0x02 /* activation thread started */ -#define XPC_P_ACTIVE 0x03 /* xpc_partition_up() was called */ -#define XPC_P_DEACTIVATING 0x04 /* partition deactivation initiated */ - - -#define XPC_DEACTIVATE_PARTITION(_p, _reason) \ - xpc_deactivate_partition(__LINE__, (_p), (_reason)) - - -/* struct xpc_partition setup_state values */ - -#define XPC_P_UNSET 0x00 /* infrastructure was never setup */ -#define XPC_P_SETUP 0x01 /* infrastructure is setup */ -#define XPC_P_WTEARDOWN 0x02 /* waiting to teardown infrastructure */ -#define XPC_P_TORNDOWN 0x03 /* infrastructure is torndown */ - - - -/* - * struct xpc_partition IPI_timer #of seconds to wait before checking for - * dropped IPIs. These occur whenever an IPI amo write doesn't complete until - * after the IPI was received. - */ -#define XPC_P_DROPPED_IPI_WAIT (0.25 * HZ) - - -/* number of seconds to wait for other partitions to disengage */ -#define XPC_DISENGAGE_REQUEST_DEFAULT_TIMELIMIT 90 - -/* interval in seconds to print 'waiting disengagement' messages */ -#define XPC_DISENGAGE_PRINTMSG_INTERVAL 10 - - -#define XPC_PARTID(_p) ((partid_t) ((_p) - &xpc_partitions[0])) - - - -/* found in xp_main.c */ -extern struct xpc_registration xpc_registrations[]; - - -/* found in xpc_main.c */ -extern struct device *xpc_part; -extern struct device *xpc_chan; -extern int xpc_disengage_request_timelimit; -extern int xpc_disengage_request_timedout; -extern irqreturn_t xpc_notify_IRQ_handler(int, void *); -extern void xpc_dropped_IPI_check(struct xpc_partition *); -extern void xpc_activate_partition(struct xpc_partition *); -extern void xpc_activate_kthreads(struct xpc_channel *, int); -extern void xpc_create_kthreads(struct xpc_channel *, int, int); -extern void xpc_disconnect_wait(int); - - -/* found in xpc_partition.c */ -extern int xpc_exiting; -extern struct xpc_vars *xpc_vars; -extern struct xpc_rsvd_page *xpc_rsvd_page; -extern struct xpc_vars_part *xpc_vars_part; -extern struct xpc_partition xpc_partitions[XP_MAX_PARTITIONS + 1]; -extern char *xpc_remote_copy_buffer; -extern void *xpc_remote_copy_buffer_base; -extern void *xpc_kmalloc_cacheline_aligned(size_t, gfp_t, void **); -extern struct xpc_rsvd_page *xpc_rsvd_page_init(void); -extern void xpc_allow_IPI_ops(void); -extern void xpc_restrict_IPI_ops(void); -extern int xpc_identify_act_IRQ_sender(void); -extern int xpc_partition_disengaged(struct xpc_partition *); -extern enum xpc_retval xpc_mark_partition_active(struct xpc_partition *); -extern void xpc_mark_partition_inactive(struct xpc_partition *); -extern void xpc_discovery(void); -extern void xpc_check_remote_hb(void); -extern void xpc_deactivate_partition(const int, struct xpc_partition *, - enum xpc_retval); -extern enum xpc_retval xpc_initiate_partid_to_nasids(partid_t, void *); - - -/* found in xpc_channel.c */ -extern void xpc_initiate_connect(int); -extern void xpc_initiate_disconnect(int); -extern enum xpc_retval xpc_initiate_allocate(partid_t, int, u32, void **); -extern enum xpc_retval xpc_initiate_send(partid_t, int, void *); -extern enum xpc_retval xpc_initiate_send_notify(partid_t, int, void *, - xpc_notify_func, void *); -extern void xpc_initiate_received(partid_t, int, void *); -extern enum xpc_retval xpc_setup_infrastructure(struct xpc_partition *); -extern enum xpc_retval xpc_pull_remote_vars_part(struct xpc_partition *); -extern void xpc_process_channel_activity(struct xpc_partition *); -extern void xpc_connected_callout(struct xpc_channel *); -extern void xpc_deliver_msg(struct xpc_channel *); -extern void xpc_disconnect_channel(const int, struct xpc_channel *, - enum xpc_retval, unsigned long *); -extern void xpc_disconnect_callout(struct xpc_channel *, enum xpc_retval); -extern void xpc_partition_going_down(struct xpc_partition *, enum xpc_retval); -extern void xpc_teardown_infrastructure(struct xpc_partition *); - - - -static inline void -xpc_wakeup_channel_mgr(struct xpc_partition *part) -{ - if (atomic_inc_return(&part->channel_mgr_requests) == 1) { - wake_up(&part->channel_mgr_wq); - } -} - - - -/* - * These next two inlines are used to keep us from tearing down a channel's - * msg queues while a thread may be referencing them. - */ -static inline void -xpc_msgqueue_ref(struct xpc_channel *ch) -{ - atomic_inc(&ch->references); -} - -static inline void -xpc_msgqueue_deref(struct xpc_channel *ch) -{ - s32 refs = atomic_dec_return(&ch->references); - - DBUG_ON(refs < 0); - if (refs == 0) { - xpc_wakeup_channel_mgr(&xpc_partitions[ch->partid]); - } -} - - - -#define XPC_DISCONNECT_CHANNEL(_ch, _reason, _irqflgs) \ - xpc_disconnect_channel(__LINE__, _ch, _reason, _irqflgs) - - -/* - * These two inlines are used to keep us from tearing down a partition's - * setup infrastructure while a thread may be referencing it. - */ -static inline void -xpc_part_deref(struct xpc_partition *part) -{ - s32 refs = atomic_dec_return(&part->references); - - - DBUG_ON(refs < 0); - if (refs == 0 && part->setup_state == XPC_P_WTEARDOWN) { - wake_up(&part->teardown_wq); - } -} - -static inline int -xpc_part_ref(struct xpc_partition *part) -{ - int setup; - - - atomic_inc(&part->references); - setup = (part->setup_state == XPC_P_SETUP); - if (!setup) { - xpc_part_deref(part); - } - return setup; -} - - - -/* - * The following macro is to be used for the setting of the reason and - * reason_line fields in both the struct xpc_channel and struct xpc_partition - * structures. - */ -#define XPC_SET_REASON(_p, _reason, _line) \ - { \ - (_p)->reason = _reason; \ - (_p)->reason_line = _line; \ - } - - - -/* - * This next set of inlines are used to keep track of when a partition is - * potentially engaged in accessing memory belonging to another partition. - */ - -static inline void -xpc_mark_partition_engaged(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa + - (XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t))); - - - local_irq_save(irq_flags); - - /* set bit corresponding to our partid in remote partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_OR, - (1UL << sn_partition_id)); - /* - * We must always use the nofault function regardless of whether we - * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we - * didn't, we'd never know that the other partition is down and would - * keep sending IPIs and AMOs to it until the heartbeat times out. - */ - (void) xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo-> - variable), xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); -} - -static inline void -xpc_mark_partition_disengaged(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa + - (XPC_ENGAGED_PARTITIONS_AMO * sizeof(AMO_t))); - - - local_irq_save(irq_flags); - - /* clear bit corresponding to our partid in remote partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_AND, - ~(1UL << sn_partition_id)); - /* - * We must always use the nofault function regardless of whether we - * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we - * didn't, we'd never know that the other partition is down and would - * keep sending IPIs and AMOs to it until the heartbeat times out. - */ - (void) xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo-> - variable), xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); -} - -static inline void -xpc_request_partition_disengage(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa + - (XPC_DISENGAGE_REQUEST_AMO * sizeof(AMO_t))); - - - local_irq_save(irq_flags); - - /* set bit corresponding to our partid in remote partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_OR, - (1UL << sn_partition_id)); - /* - * We must always use the nofault function regardless of whether we - * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we - * didn't, we'd never know that the other partition is down and would - * keep sending IPIs and AMOs to it until the heartbeat times out. - */ - (void) xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo-> - variable), xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); -} - -static inline void -xpc_cancel_partition_disengage_request(struct xpc_partition *part) -{ - unsigned long irq_flags; - AMO_t *amo = (AMO_t *) __va(part->remote_amos_page_pa + - (XPC_DISENGAGE_REQUEST_AMO * sizeof(AMO_t))); - - - local_irq_save(irq_flags); - - /* clear bit corresponding to our partid in remote partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_AND, - ~(1UL << sn_partition_id)); - /* - * We must always use the nofault function regardless of whether we - * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we - * didn't, we'd never know that the other partition is down and would - * keep sending IPIs and AMOs to it until the heartbeat times out. - */ - (void) xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo-> - variable), xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); -} - -static inline u64 -xpc_partition_engaged(u64 partid_mask) -{ - AMO_t *amo = xpc_vars->amos_page + XPC_ENGAGED_PARTITIONS_AMO; - - - /* return our partition's AMO variable ANDed with partid_mask */ - return (FETCHOP_LOAD_OP(TO_AMO((u64) &amo->variable), FETCHOP_LOAD) & - partid_mask); -} - -static inline u64 -xpc_partition_disengage_requested(u64 partid_mask) -{ - AMO_t *amo = xpc_vars->amos_page + XPC_DISENGAGE_REQUEST_AMO; - - - /* return our partition's AMO variable ANDed with partid_mask */ - return (FETCHOP_LOAD_OP(TO_AMO((u64) &amo->variable), FETCHOP_LOAD) & - partid_mask); -} - -static inline void -xpc_clear_partition_engaged(u64 partid_mask) -{ - AMO_t *amo = xpc_vars->amos_page + XPC_ENGAGED_PARTITIONS_AMO; - - - /* clear bit(s) based on partid_mask in our partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_AND, - ~partid_mask); -} - -static inline void -xpc_clear_partition_disengage_request(u64 partid_mask) -{ - AMO_t *amo = xpc_vars->amos_page + XPC_DISENGAGE_REQUEST_AMO; - - - /* clear bit(s) based on partid_mask in our partition's AMO */ - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_AND, - ~partid_mask); -} - - - -/* - * The following set of macros and inlines are used for the sending and - * receiving of IPIs (also known as IRQs). There are two flavors of IPIs, - * one that is associated with partition activity (SGI_XPC_ACTIVATE) and - * the other that is associated with channel activity (SGI_XPC_NOTIFY). - */ - -static inline u64 -xpc_IPI_receive(AMO_t *amo) -{ - return FETCHOP_LOAD_OP(TO_AMO((u64) &amo->variable), FETCHOP_CLEAR); -} - - -static inline enum xpc_retval -xpc_IPI_send(AMO_t *amo, u64 flag, int nasid, int phys_cpuid, int vector) -{ - int ret = 0; - unsigned long irq_flags; - - - local_irq_save(irq_flags); - - FETCHOP_STORE_OP(TO_AMO((u64) &amo->variable), FETCHOP_OR, flag); - sn_send_IPI_phys(nasid, phys_cpuid, vector, 0); - - /* - * We must always use the nofault function regardless of whether we - * are on a Shub 1.1 system or a Shub 1.2 slice 0xc processor. If we - * didn't, we'd never know that the other partition is down and would - * keep sending IPIs and AMOs to it until the heartbeat times out. - */ - ret = xp_nofault_PIOR((u64 *) GLOBAL_MMR_ADDR(NASID_GET(&amo->variable), - xp_nofault_PIOR_target)); - - local_irq_restore(irq_flags); - - return ((ret == 0) ? xpcSuccess : xpcPioReadError); -} - - -/* - * IPIs associated with SGI_XPC_ACTIVATE IRQ. - */ - -/* - * Flag the appropriate AMO variable and send an IPI to the specified node. - */ -static inline void -xpc_activate_IRQ_send(u64 amos_page_pa, int from_nasid, int to_nasid, - int to_phys_cpuid) -{ - int w_index = XPC_NASID_W_INDEX(from_nasid); - int b_index = XPC_NASID_B_INDEX(from_nasid); - AMO_t *amos = (AMO_t *) __va(amos_page_pa + - (XPC_ACTIVATE_IRQ_AMOS * sizeof(AMO_t))); - - - (void) xpc_IPI_send(&amos[w_index], (1UL << b_index), to_nasid, - to_phys_cpuid, SGI_XPC_ACTIVATE); -} - -static inline void -xpc_IPI_send_activate(struct xpc_vars *vars) -{ - xpc_activate_IRQ_send(vars->amos_page_pa, cnodeid_to_nasid(0), - vars->act_nasid, vars->act_phys_cpuid); -} - -static inline void -xpc_IPI_send_activated(struct xpc_partition *part) -{ - xpc_activate_IRQ_send(part->remote_amos_page_pa, cnodeid_to_nasid(0), - part->remote_act_nasid, part->remote_act_phys_cpuid); -} - -static inline void -xpc_IPI_send_reactivate(struct xpc_partition *part) -{ - xpc_activate_IRQ_send(xpc_vars->amos_page_pa, part->reactivate_nasid, - xpc_vars->act_nasid, xpc_vars->act_phys_cpuid); -} - -static inline void -xpc_IPI_send_disengage(struct xpc_partition *part) -{ - xpc_activate_IRQ_send(part->remote_amos_page_pa, cnodeid_to_nasid(0), - part->remote_act_nasid, part->remote_act_phys_cpuid); -} - - -/* - * IPIs associated with SGI_XPC_NOTIFY IRQ. - */ - -/* - * Send an IPI to the remote partition that is associated with the - * specified channel. - */ -#define XPC_NOTIFY_IRQ_SEND(_ch, _ipi_f, _irq_f) \ - xpc_notify_IRQ_send(_ch, _ipi_f, #_ipi_f, _irq_f) - -static inline void -xpc_notify_IRQ_send(struct xpc_channel *ch, u8 ipi_flag, char *ipi_flag_string, - unsigned long *irq_flags) -{ - struct xpc_partition *part = &xpc_partitions[ch->partid]; - enum xpc_retval ret; - - - if (likely(part->act_state != XPC_P_DEACTIVATING)) { - ret = xpc_IPI_send(part->remote_IPI_amo_va, - (u64) ipi_flag << (ch->number * 8), - part->remote_IPI_nasid, - part->remote_IPI_phys_cpuid, - SGI_XPC_NOTIFY); - dev_dbg(xpc_chan, "%s sent to partid=%d, channel=%d, ret=%d\n", - ipi_flag_string, ch->partid, ch->number, ret); - if (unlikely(ret != xpcSuccess)) { - if (irq_flags != NULL) { - spin_unlock_irqrestore(&ch->lock, *irq_flags); - } - XPC_DEACTIVATE_PARTITION(part, ret); - if (irq_flags != NULL) { - spin_lock_irqsave(&ch->lock, *irq_flags); - } - } - } -} - - -/* - * Make it look like the remote partition, which is associated with the - * specified channel, sent us an IPI. This faked IPI will be handled - * by xpc_dropped_IPI_check(). - */ -#define XPC_NOTIFY_IRQ_SEND_LOCAL(_ch, _ipi_f) \ - xpc_notify_IRQ_send_local(_ch, _ipi_f, #_ipi_f) - -static inline void -xpc_notify_IRQ_send_local(struct xpc_channel *ch, u8 ipi_flag, - char *ipi_flag_string) -{ - struct xpc_partition *part = &xpc_partitions[ch->partid]; - - - FETCHOP_STORE_OP(TO_AMO((u64) &part->local_IPI_amo_va->variable), - FETCHOP_OR, ((u64) ipi_flag << (ch->number * 8))); - dev_dbg(xpc_chan, "%s sent local from partid=%d, channel=%d\n", - ipi_flag_string, ch->partid, ch->number); -} - - -/* - * The sending and receiving of IPIs includes the setting of an AMO variable - * to indicate the reason the IPI was sent. The 64-bit variable is divided - * up into eight bytes, ordered from right to left. Byte zero pertains to - * channel 0, byte one to channel 1, and so on. Each byte is described by - * the following IPI flags. - */ - -#define XPC_IPI_CLOSEREQUEST 0x01 -#define XPC_IPI_CLOSEREPLY 0x02 -#define XPC_IPI_OPENREQUEST 0x04 -#define XPC_IPI_OPENREPLY 0x08 -#define XPC_IPI_MSGREQUEST 0x10 - - -/* given an AMO variable and a channel#, get its associated IPI flags */ -#define XPC_GET_IPI_FLAGS(_amo, _c) ((u8) (((_amo) >> ((_c) * 8)) & 0xff)) -#define XPC_SET_IPI_FLAGS(_amo, _c, _f) (_amo) |= ((u64) (_f) << ((_c) * 8)) - -#define XPC_ANY_OPENCLOSE_IPI_FLAGS_SET(_amo) ((_amo) & __IA64_UL_CONST(0x0f0f0f0f0f0f0f0f)) -#define XPC_ANY_MSG_IPI_FLAGS_SET(_amo) ((_amo) & __IA64_UL_CONST(0x1010101010101010)) - - -static inline void -xpc_IPI_send_closerequest(struct xpc_channel *ch, unsigned long *irq_flags) -{ - struct xpc_openclose_args *args = ch->local_openclose_args; - - - args->reason = ch->reason; - - XPC_NOTIFY_IRQ_SEND(ch, XPC_IPI_CLOSEREQUEST, irq_flags); -} - -static inline void -xpc_IPI_send_closereply(struct xpc_channel *ch, unsigned long *irq_flags) -{ - XPC_NOTIFY_IRQ_SEND(ch, XPC_IPI_CLOSEREPLY, irq_flags); -} - -static inline void -xpc_IPI_send_openrequest(struct xpc_channel *ch, unsigned long *irq_flags) -{ - struct xpc_openclose_args *args = ch->local_openclose_args; - - - args->msg_size = ch->msg_size; - args->local_nentries = ch->local_nentries; - - XPC_NOTIFY_IRQ_SEND(ch, XPC_IPI_OPENREQUEST, irq_flags); -} - -static inline void -xpc_IPI_send_openreply(struct xpc_channel *ch, unsigned long *irq_flags) -{ - struct xpc_openclose_args *args = ch->local_openclose_args; - - - args->remote_nentries = ch->remote_nentries; - args->local_nentries = ch->local_nentries; - args->local_msgqueue_pa = __pa(ch->local_msgqueue); - - XPC_NOTIFY_IRQ_SEND(ch, XPC_IPI_OPENREPLY, irq_flags); -} - -static inline void -xpc_IPI_send_msgrequest(struct xpc_channel *ch) -{ - XPC_NOTIFY_IRQ_SEND(ch, XPC_IPI_MSGREQUEST, NULL); -} - -static inline void -xpc_IPI_send_local_msgrequest(struct xpc_channel *ch) -{ - XPC_NOTIFY_IRQ_SEND_LOCAL(ch, XPC_IPI_MSGREQUEST); -} - - -/* - * Memory for XPC's AMO variables is allocated by the MSPEC driver. These - * pages are located in the lowest granule. The lowest granule uses 4k pages - * for cached references and an alternate TLB handler to never provide a - * cacheable mapping for the entire region. This will prevent speculative - * reading of cached copies of our lines from being issued which will cause - * a PI FSB Protocol error to be generated by the SHUB. For XPC, we need 64 - * AMO variables (based on XP_MAX_PARTITIONS) for message notification and an - * additional 128 AMO variables (based on XP_NASID_MASK_WORDS) for partition - * activation and 2 AMO variables for partition deactivation. - */ -static inline AMO_t * -xpc_IPI_init(int index) -{ - AMO_t *amo = xpc_vars->amos_page + index; - - - (void) xpc_IPI_receive(amo); /* clear AMO variable */ - return amo; -} - - - -static inline enum xpc_retval -xpc_map_bte_errors(bte_result_t error) -{ - if (error == BTE_SUCCESS) - return xpcSuccess; - - if (is_shub2()) { - if (BTE_VALID_SH2_ERROR(error)) - return xpcBteSh2Start + error; - return xpcBteUnmappedError; - } - switch (error) { - case BTE_SUCCESS: return xpcSuccess; - case BTEFAIL_DIR: return xpcBteDirectoryError; - case BTEFAIL_POISON: return xpcBtePoisonError; - case BTEFAIL_WERR: return xpcBteWriteError; - case BTEFAIL_ACCESS: return xpcBteAccessError; - case BTEFAIL_PWERR: return xpcBtePWriteError; - case BTEFAIL_PRERR: return xpcBtePReadError; - case BTEFAIL_TOUT: return xpcBteTimeOutError; - case BTEFAIL_XTERR: return xpcBteXtalkError; - case BTEFAIL_NOTAVAIL: return xpcBteNotAvailable; - default: return xpcBteUnmappedError; - } -} - - - -/* - * Check to see if there is any channel activity to/from the specified - * partition. - */ -static inline void -xpc_check_for_channel_activity(struct xpc_partition *part) -{ - u64 IPI_amo; - unsigned long irq_flags; - - - IPI_amo = xpc_IPI_receive(part->local_IPI_amo_va); - if (IPI_amo == 0) { - return; - } - - spin_lock_irqsave(&part->IPI_lock, irq_flags); - part->local_IPI_amo |= IPI_amo; - spin_unlock_irqrestore(&part->IPI_lock, irq_flags); - - dev_dbg(xpc_chan, "received IPI from partid=%d, IPI_amo=0x%lx\n", - XPC_PARTID(part), IPI_amo); - - xpc_wakeup_channel_mgr(part); -} - - -#endif /* _ASM_IA64_SN_XPC_H */ - diff --git a/include/asm-ia64/system.h b/include/asm-ia64/system.h index 595112bca3c..26e250bfb91 100644 --- a/include/asm-ia64/system.h +++ b/include/asm-ia64/system.h @@ -146,23 +146,23 @@ do { \ # define local_irq_save(x) \ do { \ - unsigned long psr; \ + unsigned long __psr; \ \ - __local_irq_save(psr); \ - if (psr & IA64_PSR_I) \ + __local_irq_save(__psr); \ + if (__psr & IA64_PSR_I) \ __save_ip(); \ - (x) = psr; \ + (x) = __psr; \ } while (0) -# define local_irq_disable() do { unsigned long x; local_irq_save(x); } while (0) +# define local_irq_disable() do { unsigned long __x; local_irq_save(__x); } while (0) # define local_irq_restore(x) \ do { \ - unsigned long old_psr, psr = (x); \ + unsigned long __old_psr, __psr = (x); \ \ - local_save_flags(old_psr); \ - __local_irq_restore(psr); \ - if ((old_psr & IA64_PSR_I) && !(psr & IA64_PSR_I)) \ + local_save_flags(__old_psr); \ + __local_irq_restore(__psr); \ + if ((__old_psr & IA64_PSR_I) && !(__psr & IA64_PSR_I)) \ __save_ip(); \ } while (0) @@ -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 93d83cbe0c8..6da8069a0f7 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 26edcb750f9..20d8a39680c 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 7774a1cac0c..3be25dfed16 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 diff --git a/include/asm-ia64/topology.h b/include/asm-ia64/topology.h index 2d67b72b18d..f2f72ef2a89 100644 --- a/include/asm-ia64/topology.h +++ b/include/asm-ia64/topology.h @@ -93,7 +93,7 @@ void build_cpu_to_node_map(void); .cache_nice_tries = 2, \ .busy_idx = 3, \ .idle_idx = 2, \ - .newidle_idx = 0, /* unused */ \ + .newidle_idx = 2, \ .wake_idx = 1, \ .forkexec_idx = 1, \ .flags = SD_LOAD_BALANCE \ @@ -116,6 +116,11 @@ void build_cpu_to_node_map(void); #define smt_capable() (smp_num_siblings > 1) #endif +#define pcibus_to_cpumask(bus) (pcibus_to_node(bus) == -1 ? \ + CPU_MASK_ALL : \ + node_to_cpumask(pcibus_to_node(bus)) \ + ) + #include <asm-generic/topology.h> #endif /* _ASM_IA64_TOPOLOGY_H */ |